ilyakooo0/urbit
1
0
Fork 0
mirror of https://github.com/ilyakooo0/urbit.git synced 2024-09-19 14:37:18 +03:00
Code Issues Packages Projects Releases Wiki Activity

Revert "Merge pull request #949 from eglaysher/meson-build-clean"

Browse Source 
This reverts commit 9f795b535f, reversing
changes made to d5c7b3b932.
This commit is contained in:
Elliot Glaysher 2018-03-19 15:13:19 -07:00
parent e8aec93d69
commit e6f6315691
892 changed files with 190578 additions and 478 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
.gitignore vendored
View File

@ -30,4 +30,3 @@ node_modules/
# ??
/inst
cscope.*
build/

18
.gitmodules vendored
View File

@ -1,18 +0,0 @@
[submodule "subprojects/softfloat3"]
path = subprojects/softfloat3
url = https://github.com/urbit/berkeley-softfloat-3.git
[submodule "subprojects/commonmark-legacy"]
path = subprojects/commonmark-legacy
url = https://github.com/urbit/commonmark-legacy.git
[submodule "subprojects/http-parser-legacy"]
path = subprojects/http-parser-legacy
url = https://github.com/urbit/http-parser-legacy.git
[submodule "subprojects/ed25519"]
path = subprojects/ed25519
url = https://github.com/urbit/ed25519.git
[submodule "subprojects/libscrypt"]
path = subprojects/libscrypt
url = https://github.com/urbit/libscrypt.git
[submodule "subprojects/murmur3"]
path = subprojects/murmur3
url = https://github.com/urbit/murmur3.git

32
.travis.yml
View File

@ -1,44 +1,30 @@
language: c
script: meson build && cd ./build && ninja
script: make && make test # no ./configure
# Uncomment me if this gets annoying
#
# notifications:
# email: false
before_install:
- wget https://github.com/ninja-build/ninja/releases/download/v1.8.2/ninja-linux.zip
- unzip ninja-linux.zip
- sudo mv ninja /usr/bin/
- wget https://github.com/libuv/libuv/archive/v1.19.2.tar.gz
- tar -xvf v1.19.2.tar.gz
- cd libuv-1.19.2
- sh autogen.sh
- ./configure --prefix=/usr
- make
- sudo make install
- cd ..
install:
- pip3 install --user -I meson==0.44.1
# notifications:
# email: false
addons:
apt:
packages:
- python3
- python3-pip
- libgmp3-dev
- libsigsegv-dev
- openssl
- libssl-dev
- libncurses5-dev
- make
- exuberant-ctags
- automake
- autoconf
- make
- libtool
- g++
- ragel
- cmake
- re2c
- libcurl4-gnutls-dev
- unzip
- python
# before_deploy: "make deb" # TODO
deploy:
skip_cleanup: true
@ -46,7 +32,7 @@ deploy:
prerelease: true # turn this off for official releases
api_key:
secure: V4E7784ECSS3MO6ZIRtang9XwibDyvDYGb0MoSaP2CTlmzIAhdokr4KJFM0qM4KRaaajCdQuqi0lojgOjwdxs7e0GkAwScb33LFxQ7Chj/QkFOY7V1AnSRLR5OsXnazB0nur5aSwvcvnggQ2XW3OeF7zIvGfs9aR97SEz/xCrVE=
file: ./build/urbit # TODO upload package from before_deploy
file: bin/urbit # TODO upload package from before_deploy
on:
repo: urbit/urbit
tags: true

552
Makefile Normal file
View File

@ -0,0 +1,552 @@
# A simple makefile.
#
default: all
-include .make.conf
CORE=.MAKEFILE-VERSION
# Pick one of:
# linux
# osx
UNAME=$(shell uname)
ifeq ($(UNAME),Darwin)
OS=osx
else ifeq ($(UNAME),Linux)
OS=linux
else ifeq ($(UNAME),FreeBSD)
OS=bsd
else ifeq ($(UNAME),OpenBSD)
OS=bsd
else
$(error unknown unix)
endif
# Pick one of:
# little
# big
#
ENDIAN=little
# Binary directory - not in quotes.
#
BIN=bin
# Only include/link with this if it exists.
# (Mac OS X El Capitan clean install does not have /opt)
ifneq (,$(wildcard /opt/local/.))
OPTLOCALINC?=/opt/local/include
OPTLOCALLIB?=/opt/local/lib
endif
# Only include/link with this if it exists.
# (`brew install openssl` on Mac OS X El Capitan puts openssl here)
ifneq (,$(wildcard /usr/local/opt/openssl/.))
OPENSSLINC?=/usr/local/opt/openssl/include
OPENSSLLIB?=/usr/local/opt/openssl/lib
endif
# can't have empty -I or -L options due to whitespace sensitivity
ifdef OPTLOCALINC
OPTLOCALIFLAGS=-I$(OPTLOCALINC)
endif
ifdef OPTLOCALLIB
OPTLOCALLFLAGS=-L$(OPTLOCALLIB)
endif
ifdef OPENSSLINC
OPENSSLIFLAGS=-I$(OPENSSLINC)
endif
ifdef OPENSSLLIB
OPENSSLLFLAGS=-L$(OPENSSLLIB)
endif
CURLINC=$(shell curl-config --cflags)
CURLLIB=$(shell curl-config --libs)
RM=rm -f
CC=cc
CXX=c++
CXXFLAGS=$(CFLAGS)
CLD=c++ $(CFLAGS) -L/usr/local/lib $(OPTLOCALLFLAGS) $(OPENSSLLFLAGS)
ifeq ($(OS),osx)
CLDOSFLAGS=-bind_at_load
OSLIBS=-framework CoreServices -framework CoreFoundation
endif
ifeq ($(OS),linux)
OSLIBS=-lpthread -lrt -lcurses
DEFINES=-D_FILE_OFFSET_BITS=64 -D_LARGEFILE64_SOURCE
endif
ifeq ($(OS),bsd)
OSLIBS=-lpthread -lncurses -lkvm
endif
ifeq ($(STATIC),yes)
LIBS=-lssl -lcrypto -lncurses /usr/local/lib/libsigsegv.a /usr/local/lib/libgmp.a $(CURLLIB) $(OSLIBS)
else
LIBS=-lssl -lcrypto -lgmp -lncurses -lsigsegv $(CURLLIB) $(OSLIBS)
endif
INCLUDE=include
MDEFINES=-DU3_OS_$(OS) -DU3_OS_ENDIAN_$(ENDIAN)
DEBUG=no
ifeq ($(DEBUG),yes)
CFLAGS=-g
else
CFLAGS?=-O3
endif
LIBUV_VER=libuv-v1.7.5
LIBUV_CONFIGURE_OPTIONS=CC=$(CC)
# NOTFORCHECKIN - restore -O3
# -DGHETTO \
# -DHUSH
CFLAGS+= $(COSFLAGS) -ffast-math \
-funsigned-char \
-I/usr/local/include \
$(OPTLOCALIFLAGS) \
$(OPENSSLIFLAGS) \
$(CURLINC) \
-I$(INCLUDE) \
-Ioutside/$(LIBUV_VER)/include \
-Ioutside/anachronism/include \
-Ioutside/ed25519/src \
-Ioutside/commonmark/src \
-Ioutside/commonmark/build/src \
-Ioutside/scrypt \
-Ioutside/softfloat-3/source/include \
-Ioutside/murmur3 \
$(DEFINES) \
$(MDEFINES)
# TODO remove -Wno-*
CWFLAGS=-Wall \
-Wextra \
-Wno-sign-compare \
-Wno-unused-parameter \
-Wno-missing-field-initializers \
-Wno-strict-aliasing \
-Wno-error
ifneq ($(OS),bsd)
CWFLAGS+=-Wno-error=unused-result
endif
# glibc 2.24 deprecates readdir_r; iff glibc >=2.24,
# don't upgrade 'deprecated declarations' warnings to errors
# dependency: `getconf`, which comes w/glibc
GLIBC := $(lastword $(shell getconf GNU_LIBC_VERSION 2>/dev/null))
# dependency: none, uses make's native functions
GLIBC_MAJ := $(word 1, $(subst ., ,$(GLIBC)))
GLIBC_MIN := $(word 2, $(subst ., ,$(GLIBC)))
# dependency: `expr` shell built-in
GLIBC_GE_2_24 := $(shell expr $(GLIBC_MAJ) ">" 2 "|" \
$(GLIBC_MAJ) "=" 2 "&" $(GLIBC_MIN) ">=" 24 2>/dev/null)
ifeq (1,$(GLIBC_GE_2_24))
CWFLAGS+=-Wno-error=deprecated-declarations
endif
ifdef NO_SILENT_RULES
%.o: %.c $(CORE)
$(CC) -c $(CWFLAGS) $(CFLAGS) -o $@ $<
@$(CC) -MM -MP $(CWFLAGS) $(CFLAGS) -MT $@ $< -MF .d/$*.d
else
%.o: %.c $(CORE)
@echo " CC $@"
@$(CC) -c $(CWFLAGS) $(CFLAGS) -o $@ $<
@$(CC) -MM -MP $(CWFLAGS) $(CFLAGS) -MT $@ $< -MF .d/$*.d
endif
N_OFILES=\
noun/allocate.o \
noun/events.o \
noun/hashtable.o \
noun/imprison.o \
noun/jets.o \
noun/manage.o \
noun/nock.o \
noun/retrieve.o \
noun/trace.o \
noun/xtract.o \
noun/vortex.o \
noun/zave.o
J_A_OFILES=\
jets/a/add.o \
jets/a/dec.o \
jets/a/div.o \
jets/a/gte.o \
jets/a/gth.o \
jets/a/lte.o \
jets/a/lth.o \
jets/a/mod.o \
jets/a/mul.o \
jets/a/sub.o
J_B_OFILES=\
jets/b/bind.o \
jets/b/clap.o \
jets/b/drop.o \
jets/b/flop.o \
jets/b/lent.o \
jets/b/levy.o \
jets/b/lien.o \
jets/b/murn.o \
jets/b/need.o \
jets/b/reap.o \
jets/b/reel.o \
jets/b/roll.o \
jets/b/skid.o \
jets/b/skim.o \
jets/b/skip.o \
jets/b/scag.o \
jets/b/slag.o \
jets/b/snag.o \
jets/b/sort.o \
jets/b/turn.o \
jets/b/weld.o
J_C_OFILES=\
jets/c/bex.o \
jets/c/xeb.o \
jets/c/can.o \
jets/c/cap.o \
jets/c/cat.o \
jets/c/con.o \
jets/c/cut.o \
jets/c/dor.o \
jets/c/dvr.o \
jets/c/dis.o \
jets/c/end.o \
jets/c/gor.o \
jets/c/hor.o \
jets/c/lsh.o \
jets/c/mas.o \
jets/c/met.o \
jets/c/mix.o \
jets/c/mug.o \
jets/c/muk.o \
jets/c/peg.o \
jets/c/po.o \
jets/c/pow.o \
jets/c/rap.o \
jets/c/rep.o \
jets/c/rip.o \
jets/c/rsh.o \
jets/c/sqt.o \
jets/c/vor.o
J_D_OFILES=\
jets/d/in_has.o \
jets/d/in_int.o \
jets/d/in_gas.o \
jets/d/in_mer.o \
jets/d/in_put.o \
jets/d/in_tap.o \
jets/d/in_uni.o \
jets/d/in_wyt.o \
jets/d/in_bif.o \
jets/d/in_dif.o \
jets/d/by_gas.o \
jets/d/by_get.o \
jets/d/by_has.o \
jets/d/by_int.o \
jets/d/by_put.o \
jets/d/by_uni.o \
jets/d/by_bif.o \
jets/d/by_dif.o
J_E_OFILES=\
jets/e/aes_ecb.o \
jets/e/aes_cbc.o \
jets/e/aesc.o \
jets/e/cue.o \
jets/e/fl.o \
jets/e/jam.o \
jets/e/mat.o \
jets/e/mink.o \
jets/e/mule.o \
jets/e/parse.o \
jets/e/rd.o \
jets/e/rq.o \
jets/e/rs.o \
jets/e/rh.o \
jets/e/rub.o \
jets/e/scr.o \
jets/e/shax.o \
jets/e/lore.o \
jets/e/loss.o \
jets/e/lune.o \
jets/e/trip.o
J_E_OFILES_ED=\
jets/e/ed_puck.o \
jets/e/ed_sign.o \
jets/e/ed_veri.o \
jets/e/ed_shar.o
J_F_OFILES=\
jets/f/ap.o \
jets/f/cell.o \
jets/f/comb.o \
jets/f/cons.o \
jets/f/core.o \
jets/f/face.o \
jets/f/fitz.o \
jets/f/flan.o \
jets/f/flip.o \
jets/f/flor.o \
jets/f/fork.o \
jets/f/help.o \
jets/f/hike.o \
jets/f/look.o \
jets/f/loot.o
J_F_OFILES_UT=\
jets/f/ut.o \
jets/f/ut_burn.o \
jets/f/ut_buss.o \
jets/f/ut_conk.o \
jets/f/ut_crop.o \
jets/f/ut_find.o \
jets/f/ut_fire.o \
jets/f/ut_fish.o \
jets/f/ut_fuse.o \
jets/f/ut_gain.o \
jets/f/ut_lose.o \
jets/f/ut_mint.o \
jets/f/ut_mull.o \
jets/f/ut_nest.o \
jets/f/ut_peek.o \
jets/f/ut_peel.o \
jets/f/ut_play.o \
jets/f/ut_repo.o \
jets/f/ut_rest.o \
jets/f/ut_tack.o \
jets/f/ut_toss.o \
jets/f/ut_wrap.o
J_G_OFILES=\
jets/g/down.o
J_OFILES=\
$(J_A_OFILES) \
$(J_B_OFILES) \
$(J_C_OFILES) \
$(J_D_OFILES) \
$(J_E_OFILES) \
$(J_E_OFILES_ED) \
$(J_F_OFILES) \
$(J_F_OFILES_UT) \
$(J_G_OFILES) \
jets/tree.o
BASE_OFILES=$(N_OFILES) $(J_OFILES)
OUT_OFILES=\
outside/jhttp/http_parser.o \
outside/murmur3/MurmurHash3.o
V_OFILES=\
vere/ames.o \
vere/behn.o \
vere/cttp.o \
vere/http.o \
vere/loop.o \
vere/raft.o \
vere/reck.o \
vere/sist.o \
vere/term.o \
vere/time.o \
vere/unix.o \
vere/save.o \
vere/walk.o
MAIN_FILE =\
vere/main.o
VERE_OFILES=\
$(OUT_OFILES) \
$(BASE_OFILES) \
$(MAIN_FILE) \
$(V_OFILES)
VERE_DFILES=$(VERE_OFILES:%.o=.d/%.d)
-include $(VERE_DFILES)
TEST_HASH_MAIN_FILE =\
tests/hashtable_tests.o
TEST_HASH_OFILES=\
$(OUT_OFILES) \
$(BASE_OFILES) \
$(TEST_HASH_MAIN_FILE) \
$(V_OFILES)
TEST_HASH_DFILES=$(TEST_HASH_OFILES:%.o=.d/%.d)
-include $(TEST_HASH_DFILES)
# This is a silly hack necessitated by the fact that libuv uses configure
#
# * Making 'all' obviously requires outside/libuv,
# which requires the libuv Makefile to be created.
# * Making distclean on outside/libuv destroys the makefile.
# * ...so configuring outside/libuv is parodoxically required
# in order to distclean it!
# * But what if developer types 'make distclean all' ?
# * first target makes libuv Makefile, then destroys it...and
# second target knows that it was made.
# * ...so second target borks.
# * Solution: make libuv not only depend on its own Makefile,
# but on a side effect of creating its own makefile.
#
LIBUV_MAKEFILE=outside/$(LIBUV_VER)/Makefile
LIBUV_MAKEFILE2=outside/$(LIBUV_VER)/config.log
LIBUV=outside/$(LIBUV_VER)/.libs/libuv.a
LIBED25519=outside/ed25519/ed25519.a
LIBANACHRONISM=outside/anachronism/build/libanachronism.a
LIBCOMMONMARK=outside/commonmark/build/src/libcmark.a
LIBSCRYPT=outside/scrypt/scrypt.a
LIBSOFTFLOAT=outside/softfloat-3/build/Linux-x86_64-GCC/softfloat.a
TAGS=\
.tags \
.etags \
GPATH GTAGS GRTAGS \
cscope.in.out cscope.po.out cscope.out
all: urbit
.MAKEFILE-VERSION: Makefile .make.conf
@echo "Makefile update."
@touch .MAKEFILE-VERSION
.make.conf:
@echo "# Set custom configuration here, please!" > ".make.conf"
urbit: $(BIN)/urbit
$(LIBUV_MAKEFILE) $(LIBUV_MAKEFILE2):
cd outside/$(LIBUV_VER) ; sh autogen.sh ; ./configure $(LIBUV_CONFIGURE_OPTIONS)
# [h]act II: the plot thickens
#
# * Specifying two targets that each configure libuv works
# when the rules are executed sequentially,
# * but when attempting a parallel build, it is likely Make
# will try to configure libuv simultaneously.
# * We can specify a dependency between the two targets so
# that execution of their rule(s) is serialized.
# * Further, libuv does not seem to be friendly towards
# parallel builds either. A true fix is out of scope here
# * ...so we must instruct Make to only use one job when it
# attempts to build libuv.
#
$(LIBUV_MAKEFILE2): $(LIBUV_MAKEFILE)
$(LIBUV): $(LIBUV_MAKEFILE) $(LIBUV_MAKEFILE2)
$(MAKE) -C outside/$(LIBUV_VER) all-am -j1
$(LIBED25519):
$(MAKE) -C outside/ed25519
$(LIBANACHRONISM):
$(MAKE) -C outside/anachronism static
$(LIBCOMMONMARK):
$(MAKE) -C outside/commonmark
$(LIBSCRYPT):
$(MAKE) -C outside/scrypt MDEFINES="$(MDEFINES)"
$(LIBSOFTFLOAT):
$(MAKE) -C outside/softfloat-3/build/Linux-x86_64-GCC
$(V_OFILES): include/vere/vere.h
ifdef NO_SILENT_RULES
$(BIN)/urbit: $(LIBCOMMONMARK) $(VERE_OFILES) $(LIBUV) $(LIBED25519) $(LIBANACHRONISM) $(LIBSCRYPT) $(LIBSOFTFLOAT)
mkdir -p $(BIN)
$(CLD) $(CLDOSFLAGS) -o $(BIN)/urbit $(VERE_OFILES) $(LIBUV) $(LIBED25519) $(LIBANACHRONISM) $(LIBS) $(LIBCOMMONMARK) $(LIBSCRYPT) $(LIBSOFTFLOAT)
else
$(BIN)/urbit: $(LIBCOMMONMARK) $(VERE_OFILES) $(LIBUV) $(LIBED25519) $(LIBANACHRONISM) $(LIBSCRYPT) $(LIBSOFTFLOAT)
@echo " CCLD $(BIN)/urbit"
@mkdir -p $(BIN)
@$(CLD) $(CLDOSFLAGS) -o $(BIN)/urbit $(VERE_OFILES) $(LIBUV) $(LIBED25519) $(LIBANACHRONISM) $(LIBS) $(LIBCOMMONMARK) $(LIBSCRYPT) $(LIBSOFTFLOAT)
endif
# This should start a comet or something
test:
@echo "FIXME no tests defined"
test_hash: $(BIN)/test_hash
ifdef NO_SILENT_RULES
$(BIN)/test_hash: $(LIBCOMMONMARK) $(TEST_HASH_OFILES) $(LIBUV) $(LIBED25519) $(LIBANACHRONISM) $(LIBSCRYPT) $(LIBSOFTFLOAT)
mkdir -p $(BIN)
$(CLD) $(CLDOSFLAGS) -o $(BIN)/test_hash $(TEST_HASH_OFILES) $(LIBUV) $(LIBED25519) $(LIBANACHRONISM) $(LIBS) $(LIBCOMMONMARK) $(LIBSCRYPT) $(LIBSOFTFLOAT)
else
$(BIN)/test_hash: $(LIBCOMMONMARK) $(TEST_HASH_OFILES) $(LIBUV) $(LIBED25519) $(LIBANACHRONISM) $(LIBSCRYPT) $(LIBSOFTFLOAT)
@echo "VERE_DFILES=$(VERE_DFILES)"
@echo " CCLD $(BIN)/test_hash"
@mkdir -p $(BIN)
@$(CLD) $(CLDOSFLAGS) -o $(BIN)/test_hash $(TEST_HASH_OFILES) $(LIBUV) $(LIBED25519) $(LIBANACHRONISM) $(LIBS) $(LIBCOMMONMARK) $(LIBSCRYPT) $(LIBSOFTFLOAT)
endif
tags: ctags etags gtags cscope
ctags:
@ctags -R -f .tags --exclude=root || true
etags:
@etags -f .etags $$(find . -name '*.c' -or -name '*.h') || true
gtags:
@gtags || true
cscope:
@cscope -b -q -R || true
osxpackage:
$(RM) -r inst
$(MAKE) distclean
$(MAKE) $(BIN)/urbit LIB=/usr/local/lib/urb STATIC=yes
mkdir -p inst/usr/local/lib/urb inst/usr/local/bin
cp $(BIN)/urbit inst/usr/local/bin
cp urb/urbit.pill inst/usr/local/lib/urb
pkgbuild --root inst --identifier org.urbit.urbit --version 0.2 urbit.pkg
debbuild:
$(MAKE) $(BIN)/urbit LIB=/usr/share/urb
debinstall:
mkdir -p $(DESTDIR)/usr/bin $(DESTDIR)/usr/share/urb
install -m755 $(BIN)/urbit $(DESTDIR)/usr/bin
cp urb/urbit.pill $(DESTDIR)/usr/share/urb
clean:
$(RM) $(VERE_OFILES) $(BIN)/urbit urbit.pkg $(VERE_DFILES) $(TAGS)
$(RM) -r debian/files debian/urbit*
# 'make distclean all -jn' ∀ n>1 still does not work because it is possible
# Make will attempt to build urbit while it is also cleaning urbit..
distclean: clean $(LIBUV_MAKEFILE)
$(MAKE) -C outside/$(LIBUV_VER) distclean
$(MAKE) -C outside/ed25519 clean
$(MAKE) -C outside/anachronism clean
$(MAKE) -C outside/scrypt clean
$(MAKE) -C outside/softfloat-3/build/Linux-x86_64-GCC clean
.PHONY: clean debbuild debinstalldistclean etags osxpackage tags test

58
README.md
View File

@ -16,13 +16,15 @@ If you're doing development on Urbit, keep reading.
`vere`, the Urbit virtual machine, depends on the following:
- C compiler ([gcc](https://gcc.gnu.org) or [clang](http://clang.llvm.org))
- [Meson](http://mesonbuild.com/)
- [GNU Make](https://www.gnu.org/software/make/)
- [GMP](https://gmplib.org)
- [CMake](https://cmake.org)
- automake, autoconf, and libtool
- [OpenSSL](https://www.openssl.org)
- [libsigsegv](https://www.gnu.org/software/libsigsegv/)
- [libcurl](https://curl.haxx.se/libcurl/)
- [libuv](http://libuv.org)
- curses implementation (ncurses on Linux distributions, OS curses otherwise)
- [Ragel](https://www.colm.net/open-source/ragel/)
- [re2c](http://re2c.org)
Most of these dependencies are unfortunate; we aim to drastically shrink the
@ -32,52 +34,16 @@ for future unbundling or removal wherever possible.
## Building
Urbit uses Meson build system.
Our Makefile should handle the build smoothly on all supported platforms. It's
just a simple Makefile, written by hand for GNU Make, and the most complicated
parts of its internal machinery have to do with the varied build systems of the
bundled libraries.
Some libraries which are not found in major distributions:
- ed25519
- http-parser legacy version 0.1.0
- murmur3
- softfloat3
- urbit-scrypt
- commonmark legacy version 0.12.0
Useful targets are the default `all`, `clean`, and `distclean`. The last may not
produce an entirely clean distribution directory, and runs a bundled library's
configure script; `git clean` may be a better option.
are included as git submodules. To build urbit from source, perform the following steps:
## MacOS specifics
On macos, you need to make sure `pkg-config` uses the correct homebrew path.
The `export PKG_CONFIG_PATH=/usr/local/opt/openssl/lib/pkgconfig/:$PKG_CONFIG_PATH`
should setup the `pkg-config` path correctly, solving errors with homebrew package discovery (notably with `openssl` paths).
## Configuration & compilation
(For instructions for legacy meson, also see below)
1. Install all required dependencies.
2. `git submodule init` in the urbit repository
3. `git submodule update`
4. `meson ./build`
5. If the last step was successful, type `cd ./build` followed by `ninja`
to compile urbit.
6. The executable should appear in `./build` directory.
### Using meson & ninja
To configure project, enter the build directory and enter
`meson configure`. Without any arguments this command will display available
options. For example, to compile debug build of urbit, use
`meson configure -Ddebug=true`.
To set the prefix for installation use
`meson configure -Dprefix=/usr`, and so on.
## Configuration & compilation for legacy meson
The syntax for legacy meson (Version `0.29`) is a bit different.
1. Manually create `build` directory and invoke meson as `meson . ./build`
2. If you want to set options, this is done in one step.
Use `meson -D [options] . ./build` to prepare customized build.
Once the project is configured, use `ninja` to build it.
To install it into the default prefix, use `ninja install`.
If you want to specify custom `DESTDIR`, use `DESTDIR=... ninja install`.
The `vere` binary is produced in `bin/urbit`.
## Building the Debian Package

2
debian/control vendored
View File

@ -2,7 +2,7 @@ Source: urbit
Section: net
Priority: extra
Maintainer: Ted Blackman <ted@tlon.io>
Build-Depends: debhelper (>= 9), libgmp3-dev, libsigsegv-dev, openssl, libssl-dev,libtool, meson, re2c, libcurl4-gnutls-dev
Build-Depends: debhelper (>= 9), libgmp3-dev, libsigsegv-dev, openssl, libssl-dev, automake, autoconf, libtool, g++, ragel, cmake, re2c, libcurl4-gnutls-dev
Standards-Version: 3.9.5
Homepage: http://urbit.org

7
include/all.h
View File

@ -2,7 +2,7 @@
**
** This file is in the public domain.
*/
# include "config.h"
# include "version.h"
/** c3: C environment.
**/
# include "c/portable.h" // C and OS portability
@ -12,7 +12,7 @@
/** u3: noun environment.
**/
# include "noun/aliases.h" // general u3
# include "noun/aliases.h" // general u3
# include "noun/allocate.h" // u3a: allocation
# include "noun/events.h" // u3e: persistence
@ -24,7 +24,7 @@
# include "noun/options.h" // u3o: config options
# include "noun/retrieve.h" // u3r: noun access (error returns)
# include "noun/trace.h" // u3t: profiling / tracing
# include "noun/xtract.h" // u3x: noun access (error crashes)
# include "noun/xtract.h" // u3x: noun access (error crashes)
# include "noun/vortex.h" // u3v: arvo kernel
# include "noun/zave.h" // u3z: memoization
@ -52,3 +52,4 @@
*/
# define uH u3_term_io_hija()
# define uL(x) u3_term_io_loja(x)

5
include/c/portable.h
View File

@ -4,15 +4,10 @@
*/
/** Must be compiled on gcc with C99 support.
**/
#include "config.h"
# ifndef __GNUC__
# error "port me"
# endif
# ifndef _GNU_SOURCE
# define _GNU_SOURCE
# endif
/** System include files.

13
include/config.h.in
View File

@ -1,13 +0,0 @@
#ifndef CONFIG_H
#define CONFIG_H
#mesondefine URBIT_VERSION
#mesondefine U3_OS_linux
#mesondefine U3_OS_bsd
#mesondefine U3_OS_osx
#mesondefine U3_OS_ENDIAN_little
#mesondefine U3_OS_ENDIAN_big
#endif /*CONFIG_H*/

1
include/version.h Normal file
View File

@ -0,0 +1 @@
#define URBIT_VERSION "0.5.1"

2
jets/c/muk.c
View File

@ -2,7 +2,7 @@
**
*/
#include "all.h"
#include <murmur3.h>
#include <MurmurHash3.h>
/* functions
*/

2
jets/e/rd.c
View File

@ -2,7 +2,7 @@
**
*/
#include "all.h"
#include <softfloat.h>
#include "softfloat.h"
#define DOUBNAN 0x7ff8000000000000

8
jets/e/rh.c
View File

@ -2,7 +2,7 @@
**
*/
#include "all.h"
#include <softfloat.h>
#include "softfloat.h"
#define HALFNAN 0x7e00
@ -151,8 +151,8 @@
/* div
*/
u3_noun
u3qes_div(u3_atom a,
u3_atom b,
u3qes_div(u3_atom a,
u3_atom b,
u3_atom r)
{
union half c, d, e;
@ -183,7 +183,7 @@
/* sqt
*/
u3_noun
u3qes_sqt(u3_atom a,
u3qes_sqt(u3_atom a,
u3_atom r)
{
union half c, d;

2
jets/e/rq.c
View File

@ -2,7 +2,7 @@
**
*/
#include "all.h"
#include <softfloat.h>
#include "softfloat.h"
#define QUADNAN 0x7fff800000000000

8
jets/e/rs.c
View File

@ -2,7 +2,7 @@
**
*/
#include "all.h"
#include <softfloat.h>
#include "softfloat.h"
#define SINGNAN 0x7fc00000
@ -151,8 +151,8 @@
/* div
*/
u3_noun
u3qet_div(u3_atom a,
u3_atom b,
u3qet_div(u3_atom a,
u3_atom b,
u3_atom r)
{
union sing c, d, e;
@ -183,7 +183,7 @@
/* sqt
*/
u3_noun
u3qet_sqt(u3_atom a,
u3qet_sqt(u3_atom a,
u3_atom r)
{
union sing c, d;

123
jets/e/scr.c
View File

@ -5,9 +5,7 @@
#include <stdint.h>
#include <errno.h>
#include <libscrypt.h>
#include <sha256.h>
#include <crypto_scrypt.h>
static int _crypto_scrypt(const uint8_t *, size_t, const uint8_t *, size_t,
uint64_t, uint32_t, uint32_t, uint8_t *, size_t);
@ -19,8 +17,8 @@ static int _crypto_scrypt(const uint8_t *, size_t, const uint8_t *, size_t,
u3qes_hsl(u3_atom p, u3_atom pl,
u3_atom s, u3_atom sl,
u3_atom n,
u3_atom r,
u3_atom z,
u3_atom r,
u3_atom z,
u3_atom d)
{
// asserting that n is power of 2 in _crypto_scrypt
@ -32,7 +30,7 @@ static int _crypto_scrypt(const uint8_t *, size_t, const uint8_t *, size_t,
(((c3_d)r * 128 * ((c3_d)n + z - 1)) <= (1 << 30))))
return u3m_bail(c3__exit);
c3_y* b_p = u3a_malloc(pl + 1); c3_y* b_s= u3a_malloc(sl + 1);
c3_y* b_p = u3a_malloc(pl + 1); c3_y* b_s= u3a_malloc(sl + 1);
u3r_bytes(0, pl, b_p, p); u3r_bytes(0, sl, b_s, s);
b_p[pl] = 0; b_s[sl]=0;
c3_y* buf = u3a_malloc(d);
@ -75,7 +73,7 @@ static int _crypto_scrypt(const uint8_t *, size_t, const uint8_t *, size_t,
return u3m_bail(c3__exit);
c3_w pl = u3r_met(3, p); c3_w sl = u3r_met(3, s);
c3_y* b_p = u3a_malloc(pl + 1); c3_y* b_s= u3a_malloc(sl + 1);
c3_y* b_p = u3a_malloc(pl + 1); c3_y* b_s= u3a_malloc(sl + 1);
u3r_bytes(0, pl, b_p, p); u3r_bytes(0, sl, b_s, s);
b_p[pl] = 0; b_s[sl]=0;
c3_y* buf = u3a_malloc(d);
@ -114,12 +112,12 @@ static int _crypto_scrypt(const uint8_t *, size_t, const uint8_t *, size_t,
(c != 0)))
return u3m_bail(c3__exit);
c3_y* b_p = u3a_malloc(pl + 1); c3_y* b_s= u3a_malloc(pl + 1);
c3_y* b_p = u3a_malloc(pl + 1); c3_y* b_s= u3a_malloc(pl + 1);
u3r_bytes(0, pl, b_p, p); u3r_bytes(0, sl, b_s, s);
b_p[pl] = 0; b_s[sl]=0;
c3_y* buf = u3a_malloc(d);
libscrypt_PBKDF2_SHA256(b_p, pl, b_s, sl, c, buf, d);
PBKDF2_SHA256(b_p, pl, b_s, sl, c, buf, d);
u3_noun res = u3i_bytes(d, buf);
u3a_free(b_p); u3a_free(b_s); u3a_free(buf);
@ -149,12 +147,12 @@ static int _crypto_scrypt(const uint8_t *, size_t, const uint8_t *, size_t,
return u3m_bail(c3__exit);
c3_w pl = u3r_met(3, p); c3_w sl = u3r_met(3, s);
c3_y* b_p = u3a_malloc(pl + 1); c3_y* b_s= u3a_malloc(pl + 1);
c3_y* b_p = u3a_malloc(pl + 1); c3_y* b_s= u3a_malloc(pl + 1);
u3r_bytes(0, pl, b_p, p); u3r_bytes(0, sl, b_s, s);
b_p[pl] = 0; b_s[sl]=0;
c3_y* buf = u3a_malloc(d);
libscrypt_PBKDF2_SHA256(b_p, pl, b_s, sl, c, buf, d);
PBKDF2_SHA256(b_p, pl, b_s, sl, c, buf, d);
u3_noun res = u3i_bytes(d, buf);
u3a_free(b_p); u3a_free(b_s); u3a_free(buf);
@ -172,6 +170,35 @@ static int _crypto_scrypt(const uint8_t *, size_t, const uint8_t *, size_t,
return u3qes_pbk(p, s, c, d);
}
/*-
* Copyright 2009 Colin Percival
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
*
* THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
*
* This file was originally written by Colin Percival as part of the Tarsnap
* online backup system.
*/
/**
* crypto_scrypt(passwd, passwdlen, salt, saltlen, N, r, p, buf, buflen):
* Compute scrypt(passwd[0 .. passwdlen - 1], salt[0 .. saltlen - 1], N, r,
@ -186,5 +213,77 @@ _crypto_scrypt(const uint8_t * passwd, size_t passwdlen,
const uint8_t * salt, size_t saltlen, uint64_t N, uint32_t r, uint32_t p,
uint8_t * buf, size_t buflen)
{
return libscrypt_scrypt(passwd, passwdlen, salt, saltlen, N, r, p, buf, buflen);
void * B0, * V0, * XY0;
uint8_t * B;
uint32_t * V;
uint32_t * XY;
uint32_t i;
if (((N & (N-1)) != 0) || N == 0)
goto err0;
/* Sanity-check parameters. */
#if SIZE_MAX > UINT32_MAX
if (buflen > (((uint64_t)(1) << 32) - 1) * 32) {
errno = EFBIG;
goto err0;
}
#endif
if ((uint64_t)(r) * (uint64_t)(p) >= (1 << 30)) {
errno = EFBIG;
goto err0;
}
if (((N & (N - 1)) != 0) || (N == 0)) {
errno = EINVAL;
goto err0;
}
int test_size_max = (r > SIZE_MAX / 128 / p) || (N > SIZE_MAX / 128 / r);
#if SIZE_MAX / 256 <= UINT32_MAX
test_size_max = (r > (SIZE_MAX - 64) / 256) || test_size_max;
#endif
if(test_size_max) {
errno = ENOMEM;
goto err0;
}
/* Allocate memory. */
if ((B0 = u3a_malloc(128 * r * p + 63)) == NULL)
goto err0;
B = (uint8_t *)(((uintptr_t)(B0) + 63) & ~ (uintptr_t)(63));
if ((XY0 = u3a_malloc(256 * r + 64 + 63)) == NULL)
goto err1;
XY = (uint32_t *)(((uintptr_t)(XY0) + 63) & ~ (uintptr_t)(63));
if ((V0 = u3a_malloc(128 * r * N + 63)) == NULL)
goto err2;
V = (uint32_t *)(((uintptr_t)(V0) + 63) & ~ (uintptr_t)(63));
/* 1: (B_0 ... B_{p-1}) <-- PBKDF2(P, S, 1, p * MFLen) */
PBKDF2_SHA256(passwd, passwdlen, salt, saltlen, 1, B, p * 128 * r);
/* 2: for i = 0 to p - 1 do */
for (i = 0; i < p; i++) {
/* 3: B_i <-- MF(B_i, N) */
smix(&B[i * 128 * r], r, N, V, XY);
}
/* 5: DK <-- PBKDF2(P, B, 1, dkLen) */
PBKDF2_SHA256(passwd, passwdlen, B, p * 128 * r, 1, buf, buflen);
/* Free memory. */
u3a_free(V0);
u3a_free(XY0);
u3a_free(B0);
/* Success! */
return (0);
err2:
u3a_free(XY0);
err1:
u3a_free(B0);
err0:
/* Failure! */
return (-1);
}

326
meson.build
View File

@ -1,326 +0,0 @@
project('urbit', 'c', meson_version: '>=0.29.0')
legacy_meson = false
detect_meson_version = run_command('meson', '--version')
meson_ver = detect_meson_version.stdout()
if(meson_ver == '0.29.0\n')
legacy_meson = true
elif(not meson.version().version_compare('>=0.40.0'))
error('Meson 0.29.0 is last legacy version supported. Otherwise please upgrade to 0.40.0 or higher.')
endif
jets_a_src = [
'jets/a/add.c',
'jets/a/dec.c',
'jets/a/div.c',
'jets/a/gte.c',
'jets/a/gth.c',
'jets/a/lte.c',
'jets/a/lth.c',
'jets/a/mod.c',
'jets/a/mul.c',
'jets/a/sub.c',]
jets_b_src = [
'jets/b/bind.c',
'jets/b/clap.c',
'jets/b/drop.c',
'jets/b/flop.c',
'jets/b/lent.c',
'jets/b/levy.c',
'jets/b/lien.c',
'jets/b/murn.c',
'jets/b/need.c',
'jets/b/reap.c',
'jets/b/reel.c',
'jets/b/roll.c',
'jets/b/skid.c',
'jets/b/skim.c',
'jets/b/skip.c',
'jets/b/scag.c',
'jets/b/slag.c',
'jets/b/snag.c',
'jets/b/sort.c',
'jets/b/turn.c',
'jets/b/weld.c' ]
jets_c_src = [
'jets/c/bex.c',
'jets/c/xeb.c',
'jets/c/can.c',
'jets/c/cap.c',
'jets/c/cat.c',
'jets/c/con.c',
'jets/c/cut.c',
'jets/c/dor.c',
'jets/c/dvr.c',
'jets/c/dis.c',
'jets/c/end.c',
'jets/c/gor.c',
'jets/c/hor.c',
'jets/c/lsh.c',
'jets/c/mas.c',
'jets/c/met.c',
'jets/c/mix.c',
'jets/c/mug.c',
'jets/c/muk.c',
'jets/c/peg.c',
'jets/c/po.c',
'jets/c/pow.c',
'jets/c/rap.c',
'jets/c/rep.c',
'jets/c/rip.c',
'jets/c/rsh.c',
'jets/c/sqt.c',
'jets/c/vor.c',
]
jets_d_src = [
'jets/d/in_has.c',
'jets/d/in_int.c',
'jets/d/in_gas.c',
'jets/d/in_mer.c',
'jets/d/in_put.c',
'jets/d/in_tap.c',
'jets/d/in_uni.c',
'jets/d/in_wyt.c',
'jets/d/in_bif.c',
'jets/d/in_dif.c',
'jets/d/by_gas.c',
'jets/d/by_get.c',
'jets/d/by_has.c',
'jets/d/by_int.c',
'jets/d/by_put.c',
'jets/d/by_uni.c',
'jets/d/by_bif.c',
'jets/d/by_dif.c'
]
jets_e_src = [
'jets/e/aes_ecb.c',
'jets/e/aes_cbc.c',
'jets/e/aesc.c',
'jets/e/cue.c',
'jets/e/fl.c',
'jets/e/jam.c',
'jets/e/mat.c',
'jets/e/mink.c',
'jets/e/mule.c',
'jets/e/parse.c',
'jets/e/rd.c',
'jets/e/rq.c',
'jets/e/rs.c',
'jets/e/rh.c',
'jets/e/rub.c',
'jets/e/scr.c',
'jets/e/shax.c',
'jets/e/lore.c',
'jets/e/loss.c',
'jets/e/lune.c',
'jets/e/trip.c'
]
jets_e_ed_src = [
'jets/e/ed_puck.c',
'jets/e/ed_sign.c',
'jets/e/ed_veri.c',
'jets/e/ed_shar.c'
]
jets_f_src = [
'jets/f/ap.c',
'jets/f/cell.c',
'jets/f/comb.c',
'jets/f/cons.c',
'jets/f/core.c',
'jets/f/face.c',
'jets/f/fitz.c',
'jets/f/flan.c',
'jets/f/flip.c',
'jets/f/flor.c',
'jets/f/fork.c',
'jets/f/help.c',
'jets/f/hike.c',
'jets/f/look.c',
'jets/f/loot.c'
]
jets_f_ut_src = [
'jets/f/ut.c',
'jets/f/ut_burn.c',
'jets/f/ut_buss.c',
'jets/f/ut_conk.c',
'jets/f/ut_crop.c',
'jets/f/ut_find.c',
'jets/f/ut_fire.c',
'jets/f/ut_fish.c',
'jets/f/ut_fuse.c',
'jets/f/ut_gain.c',
'jets/f/ut_lose.c',
'jets/f/ut_mint.c',
'jets/f/ut_mull.c',
'jets/f/ut_nest.c',
'jets/f/ut_peek.c',
'jets/f/ut_peel.c',
'jets/f/ut_play.c',
'jets/f/ut_repo.c',
'jets/f/ut_rest.c',
'jets/f/ut_tack.c',
'jets/f/ut_toss.c',
'jets/f/ut_wrap.c'
]
jets_g_src = [
'jets/g/down.c'
]
jets_src = [
'jets/tree.c'
]
noun_src = ['noun/allocate.c',
'noun/events.c',
'noun/hashtable.c',
'noun/imprison.c',
'noun/jets.c',
'noun/manage.c',
'noun/nock.c',
'noun/retrieve.c',
'noun/trace.c',
'noun/vortex.c',
'noun/xtract.c',
'noun/zave.c']
vere_src = ['vere/ames.c',
'vere/behn.c',
'vere/cttp.c',
'vere/http.c',
'vere/loop.c',
'vere/main.c',
'vere/raft.c',
'vere/reck.c',
'vere/save.c',
'vere/sist.c',
'vere/term.c',
'vere/time.c',
'vere/unix.c',
'vere/walk.c']
src_list = [
vere_src, noun_src,
jets_a_src, jets_b_src,
jets_c_src, jets_d_src,
jets_e_src, jets_e_ed_src, jets_f_src, jets_f_ut_src,
jets_g_src, jets_src]
sources = []
foreach s : src_list
sources += s
endforeach
incdir = include_directories('include/')
conf_data = configuration_data()
conf_data.set('URBIT_VERSION', '"0.5.1"')
osdet = build_machine.system()
os_c_flags = []
os_deps = []
os_link_flags = []
if osdet == 'linux'
conf_data.set('U3_OS_linux', true)
if(legacy_meson)
pthread_dep = find_library('pthread')
else
pthread_dep = meson.get_compiler('c').find_library('pthread')
endif
ncurses_dep = dependency('ncurses')
os_deps = os_deps + [pthread_dep, ncurses_dep]
elif osdet == 'darwin'
conf_data.set('U3_OS_osx', true)
os_c_flags = os_c_flags + ['-bind_at_load']
# os_link_flags = ['-framework CoreServices', '-framework CoreFoundation']
if(legacy_meson)
ncurses_dep = find_library('ncurses')
else
ncurses_dep = meson.get_compiler('c').find_library('ncurses')
endif
os_deps = os_deps + [ncurses_dep]
elif osdet == 'bsd'
conf_data.set('U3_OS_bsd', true)
pthread_dep = meson.get_compiler('c').find_library('pthread')
kvm_dep = meson.get_compiler('c').find_library('kvm')
ncurses_dep = dependency('ncurses')
os_deps = os_deps + [kvm_dep, pthread_dep, ncurses_dep]
else
error('Unsupported OS detected:' + osdet)
endif
endian = build_machine.endian()
if endian == 'little'
conf_data.set('U3_OS_ENDIAN_little', true)
else
error('Little endian encoding required')
endif
configure_file(input : 'include/config.h.in',
output : 'config.h',
configuration : conf_data)
# We expect these libs to supplied with the distribution
openssl_dep = dependency('openssl', version: '>=1.0.0')
curl_dep = dependency('libcurl', version: '>=7.35.0')
libuv_dep = dependency('libuv', version: '>=1.8.0')
if(legacy_meson)
gmp_dep = find_library('gmp')
sigsegv_dep = find_library('sigsegv')
else
gmp_dep = meson.get_compiler('c').find_library('gmp')
sigsegv_dep = meson.get_compiler('c').find_library('sigsegv')
endif
# For these libs we provide fallback bundle
cmark_dep = dependency('libcmark', version: '0.12.0', fallback: ['commonmark-legacy', 'cmark_dep'])
urbitscrypt_dep = dependency('libscrypt', version: '>=0.1.21', fallback: ['libscrypt', 'libscrypt_dep'])
ed25519_dep = dependency('ed25519', version: '>=0.1.0', fallback: ['ed25519', 'ed25519_dep'])
murmur3_dep = dependency('murmur3', version: '>=0.1.0', fallback: ['murmur3', 'murmur3_dep'])
http_parser_dep = dependency('http-parser', version: '0.1.0', fallback: ['http-parser-legacy', 'http_parser_dep'])
softfloat3_dep = dependency('softfloat3', version: '>=3.0.0', fallback: ['softfloat3', 'softfloat3_dep'])
opt_flags = []
if get_option('debug')
opt_flags = ['-g']
else
opt_flags = ['-O3']
endif
executable('urbit',
sources : sources,
include_directories : incdir,
c_args : opt_flags + os_c_flags,
link_args: os_link_flags,
dependencies: [openssl_dep,
curl_dep,
libuv_dep,
cmark_dep,
gmp_dep,
sigsegv_dep,
urbitscrypt_dep,
ed25519_dep,
murmur3_dep,
http_parser_dep,
softfloat3_dep] + os_deps,
install: true)

1
meson_options.txt
View File

@ -1 +0,0 @@
option('debug', type:'boolean', value: false)

1
outside/anachronism/.gitignore vendored Normal file
View File

@ -0,0 +1 @@
build/

19
outside/anachronism/LICENSE Normal file
View File

@ -0,0 +1,19 @@
Copyright (c) 2010 Jonathan Castello
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in
all copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
THE SOFTWARE.

70
outside/anachronism/Makefile Normal file
View File

@ -0,0 +1,70 @@
SHELL = sh
UNAME = $(shell uname)
ifneq ($(UNAME),FreeBSD)
CC = gcc
else
CC = cc
endif
FLAGS = -c -fPIC -Iinclude/
CFLAGS = --pedantic -Wall -Wextra -march=native -std=gnu99
INCLUDE = include/anachronism
VERSION_MAJOR = 0
VERSION = $(VERSION_MAJOR).3.1
SO = libanachronism.so
SOFILE = $(SO).$(VERSION)
SONAME = $(SO).$(VERSION_MAJOR)
all: static shared
shared: build/ build/$(SOFILE)
static: build/ build/libanachronism.a
build/:
mkdir build
build/$(SOFILE): build/nvt.o build/parser.o
$(CC) -shared -Wl,-soname,$(SONAME) -o build/$(SOFILE) build/nvt.o build/parser.o
build/libanachronism.a: build/nvt.o build/parser.o
ar rcs build/libanachronism.a build/nvt.o build/parser.o
build/nvt.o: src/nvt.c $(INCLUDE)/nvt.h $(INCLUDE)/common.h
$(CC) $(FLAGS) $(CFLAGS) src/nvt.c -o build/nvt.o
build/parser.o: src/parser.c $(INCLUDE)/parser.h $(INCLUDE)/common.h
$(CC) $(FLAGS) $(CFLAGS) src/parser.c -o build/parser.o
src/parser.c: src/parser.rl src/parser_common.rl
ragel -C -G2 src/parser.rl -o src/parser.c
graph: doc/parser.png
doc/parser.png: src/parser.rl src/parser_common.rl
ragel -V -p src/parser.rl | dot -Tpng > doc/parser.png
install: all
install -D -d /usr/local/include/anachronism/ /usr/local/lib
install -D include/anachronism/* /usr/local/include/anachronism/
install -D build/$(SOFILE) /usr/local/lib/$(SOFILE)
install -D build/libanachronism.a /usr/local/lib/libanachronism.a
ln -s -f /usr/local/lib/$(SOFILE) /usr/local/lib/$(SONAME)
ln -s -f /usr/local/lib/$(SOFILE) /usr/local/lib/$(SO)
uninstall:
-rm -rf /usr/local/include/anachronism
-rm /usr/local/lib/libanachronism.a
-rm /usr/local/lib/$(SOFILE)
-rm /usr/local/lib/$(SONAME)
-rm /usr/local/lib/$(SO)
clean:
-rm -f build/nvt.o build/router.o build/parser.o
distclean: clean
-rm -f build/libanachronism.a build/$(SOFILE)
.PHONY: all static shared clean distclean install uninstall

158
outside/anachronism/README.md Normal file
View File

@ -0,0 +1,158 @@
# Anachronism
Anachronism is a fully-compliant implementation of [the Telnet protocol][wiki-telnet]. Fallen
out of favor in this day and age, most people only know it as a command-line
tool for debugging HTTP. Today, Telnet is most commonly used in the realm of
[MUDs][wiki-muds], though there are still a few other niches filled by Telnet.
Anachronism offers a simple API for translating between streams of data and
events, and is completely network-agnostic. Anachronism also offers **channels**, an
abstraction layer which treats Telnet as a data multiplexer. Channels make it
extremely easy to build reusable modules for Telnet sub-protocols such
as MCCP (MUD Client Compression Protocol), which can be written once and plugged
into any application that wants to include support.
[wiki-telnet]: http://en.wikipedia.org/wiki/Telnet (Telnet at Wikipedia)
[wiki-muds]: http://en.wikipedia.org/wiki/MUD (MUDs at Wikipedia)
## Installation
While Anachronism has no dependencies and is theoretically cross-platform, I've
only written a Makefile for Linux. Help would be appreciated for making this
work across more platforms.
make
sudo make install
This will install Anachronism's shared and static libraries to /usr/local/lib,
and its header files to /usr/local/include/anachronism/. You may also need to
run `ldconfig` to make Anachronism available to your project's compiler/linker.
## Usage
The anachronism/nvt.h header can be consulted for more complete documentation.
### Basic usage
The core type exposed by Anachronism is the telnet\_nvt, which represents the
Telnet RFC's "Network Virtual Terminal". An NVT is created using
telnet\_nvt\_new(). When creating an NVT, you must provide it with a set of
callbacks to send events to, and an optional void\* to store as the event
handler's context. You can use telnet\_recv() to process incoming data, and
the telnet\_send\_\*() set of functions to emit outgoing data.
#include <stdio.h>
#include <anachronism/nvt.h>
void on_event(telnet_nvt* nvt, telnet_event* event)
{
switch (event->type)
{
// A data event (normal text received)
case TELNET_EV_DATA:
{
telnet_data_event* ev = (telnet_data_event*)event;
printf("[IN]: %.*s\n", ev->length, ev->data);
break;
}
// Outgoing data emitted by the NVT
case TELNET_EV_SEND:
{
telnet_send_event* ev = (telnet_send_event*)event;
printf("[OUT]: %.*s\n", ev->length, ev->data);
break;
}
}
}
int main()
{
// Create an NVT
telnet_nvt* nvt = telnet_nvt_new(NULL, &on_event, NULL, NULL);
// Process some incoming data
const char* data = "foo bar baz";
telnet_receive(nvt, (const telnet_byte*)data, strlen(data), NULL);
// Free the NVT
telnet_nvt_free(nvt);
return 0;
}
### Telopts
Anachronism provides an easy-to-use interface to Telnet's "telopt" functionality
via the telnet\_telopt\_*() set of functions. As telopts are negotiated and
utilized, events are sent to the telopt callback provided to telnet_nvt_new().
#include <stdio.h>
#include <anachronism/nvt.h>
void on_event(telnet_nvt* nvt, telnet_event* event)
{
switch (event->type)
{
// Outgoing data emitted by the NVT
case TELNET_EV_SEND:
{
telnet_send_event* ev = (telnet_send_event*)event;
printf("[OUT]: %.*s\n", ev->length, ev->data);
break;
}
}
}
void on_telopt_event(telnet_nvt* nvt, telnet_byte telopt, telnet_telopt_event* event)
{
// telopt is the telopt this event was triggered for
switch (event->type)
{
case TELNET_EV_TELOPT_TOGGLE:
telnet_telopt_toggle_event* ev = (telnet_telopt_toggle_event*)event;
// ev->where is TELNET_TELOPT_LOCAL or TELNET_TELOPT_REMOTE,
// corresponding to Telnet's WILL/WONT and DO/DONT commands.
// ev->status is TELNET_TELOPT_ON or TELNET_TELOPT_OFF.
break;
case TELNET_EV_TELOPT_FOCUS:
telnet_telopt_focus_event* ev = (telnet_telopt_focus_event*)event;
// ev->focus is 1 or 0 depending on if a subnegotiation packet has
// begun or ended.
break;
case TELNET_EV_TELOPT_DATA:
telnet_telopt_data_event* ev = (telnet_telopt_data_event*)event;
// ev->data is a pointer to the received data.
// ev->length is the length of the data buffer.
break;
}
}
int main()
{
// Create an NVT
telnet_nvt* nvt = telnet_nvt_new(NULL, &on_event, &on_telopt_event, NULL);
// Ask to enable a telopt locally (a WILL command)
telnet_request_enable(nvt, 230, TELNET_LOCAL);
// Process some incoming data
const char* data = "\xFF\xFD\xE6" // IAC DO 230 (turn channel on)
"\xFF\xFA\xE6" // IAC SB 230 (switch to channel)
"foo bar baz" (send data)
"\xFF\xF0"; // IAC SE (switch to main)
telnet_receive(nvt, (const telnet_byte*)data, strlen(data), NULL);
// Free the NVT
telnet_nvt_free(nvt);
return 0;
}
### Interrupting
TODO: Explain how to interrupt the parser.
## Alternatives
* [libtelnet][github-libtelnet], by Elanthis<br>
It incorporates a number of (rather MUD-specific) protocols by default,
though its API is quite different.
[github-libtelnet]: https://github.com/elanthis/libtelnet (libtelnet on GitHub)
## Credits
Someone from #startups on Freenode IRC suggested the name (I'm sure as a joke).
If you read this, remind me who you are so I can credit you properly!

50
outside/anachronism/doc/channels.md Normal file
View File

@ -0,0 +1,50 @@
# Telnet
## Channels
Telnet supports data multiplexing by way of 256 built-in sub-channels, each
identified by a byte in the interval [\x00-\xFF]. By switching between
channels, you can send completely separate streams of data through the same
connection.
All channels start out closed by default. To open a channel, one host must
request or offer a channel using IAC WILL &lt;id> or IAC DO &lt;id>. The remote host
then responds with IAC DO &lt;id> or IAC WILL &lt;id>, respectively. Alternatively,
the request may be denied using IAC DONT &lt;id> or IAC WONT &lt;id>, respectively.
In order to switch to a specific channel, the IAC SB &lt;id> sequence must
be used. All data sent afterwards will be routed through that specific channel.
To switch back to the main channel, IAC SE must be used. Note that subchannels
do not support any IAC sequences except IAC IAC (an escaped \xFF byte) and
IAC SE (return to the main channel). In particular, you cannot switch directly
from one subchannel to another: you must revert to the main channel first.
Due to the unbiased nature of Telnet, neither side of the connection is
automatically recognized as the server or the client. However, a host may either
request a channel (as a client) or offer a channel (as a server). The WILL/WONT
commands are used in the role of server ("I will", "I wont"), while DO/DONT
are used in the role of client ("You do", "You do not"). As such, a channel
may be opened twice (even simultaneously).
As an example, lets assume a terminal is connected to a server using Telnet. The
server offers MCCP (data compression), but wants to know what the terminal's
window size is. The following communication might occur:
<server> IAC DO NAWS
<server> IAC WILL MCCP
<client> IAC WILL NAWS
<client> IAC SB NAWS \x50 \x00 \x50 \x00 IAC SE
<client> IAC DO MCCP
<server> IAC SB MCCP IAC SE
<server> (compressed data)
Notice that MCCP was negotiated such that the server offers the compression.
Only the server-to-client flow of data is compressed; the client would not
compress its data unless the channel was negotiated in the other direction as
well.
In general, a specific subchannel is tied to a specific Telnet subprotocol. For
example, the EXOPL subprotocol is assigned to channel 255, so that channel
should be avoided for any other purpose. A full list of registered subprotocols
can be found on the [IANA website][1].
[1]: http://www.iana.org/assignments/telnet-options

BIN
outside/anachronism/doc/parser.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 148 KiB

24
outside/anachronism/include/anachronism/common.h Normal file
View File

@ -0,0 +1,24 @@
#ifndef ANACHRONISM_COMMON_H
#define ANACHRONISM_COMMON_H
#include <stdlib.h> /* for size_t */
// Telnet bytes must be unsigned
typedef unsigned char telnet_byte;
// Error codes returned from API functions
// Positive codes are success/notice codes.
// Nonpositive codes are errors.
// ALLOC is 0 for parity with the NULL result from malloc().
typedef enum telnet_error
{
TELNET_E_NOT_SUBNEGOTIABLE = -4, // The telopt is not open for subnegotiation.
TELNET_E_BAD_PARSER = -3, // The telnet_parser* passed is NULL
TELNET_E_BAD_NVT = -2, // The telnet_nvt* passed is NULL
TELNET_E_INVALID_COMMAND = -1, // The telnet_byte passed is not an allowed command in this API method
TELNET_E_ALLOC = 0, // Not enough memory to allocate essential library structures
TELNET_E_OK = 1, // Huge Success!
TELNET_E_INTERRUPT = 2, // Parser interrupted by user code.
} telnet_error;
#endif // ANACHRONISM_COMMON_H

214
outside/anachronism/include/anachronism/nvt.h Normal file
View File

@ -0,0 +1,214 @@
#ifndef ANACHRONISM_ANACHRONISM_H
#define ANACHRONISM_ANACHRONISM_H
#ifdef __cplusplus
extern "C" {
#endif
#include <anachronism/common.h>
// predefined Telnet commands from 240-255
enum
{
IAC_SE = 240,
IAC_NOP,
IAC_DM,
IAC_BRK,
IAC_IP,
IAC_AO,
IAC_AYT,
IAC_EC,
IAC_EL,
IAC_GA,
IAC_SB,
IAC_WILL,
IAC_WONT,
IAC_DO,
IAC_DONT,
IAC_IAC,
};
typedef enum telnet_telopt_location
{
TELNET_LOCAL,
TELNET_REMOTE,
} telnet_telopt_location;
/**
* NVT Events
*/
typedef enum telnet_event_type
{
TELNET_EV_DATA, /* A stretch of plain data was received. (data, length) */
TELNET_EV_COMMAND, /* A simple IAC comamnd was recevied. (command) */
TELNET_EV_WARNING, /* A non-fatal invalid sequence was received. (message, position) */
TELNET_EV_SEND, /* Outgoing data to be sent. (data, length) */
} telnet_event_type;
typedef struct telnet_event
{
telnet_event_type type;
} telnet_event;
typedef struct telnet_data_event
{
telnet_event SUPER_;
const telnet_byte* data;
size_t length;
} telnet_data_event;
typedef struct telnet_command_event
{
telnet_event SUPER_;
telnet_byte command;
} telnet_command_event;
typedef struct telnet_warning_event
{
telnet_event SUPER_;
const char* message;
size_t position;
} telnet_warning_event;
typedef struct telnet_send_event
{
telnet_event SUPER_;
const telnet_byte* data;
size_t length;
} telnet_send_event;
/**
* Telopt Events
*/
typedef enum telnet_telopt_event_type
{
TELNET_EV_TELOPT_TOGGLE,
TELNET_EV_TELOPT_FOCUS,
TELNET_EV_TELOPT_DATA,
} telnet_telopt_event_type;
typedef struct telnet_telopt_event
{
telnet_telopt_event_type type;
} telnet_telopt_event;
typedef struct telnet_telopt_toggle_event
{
telnet_telopt_event SUPER_;
telnet_telopt_location where;
unsigned char status;
} telnet_telopt_toggle_event;
typedef struct telnet_telopt_focus_event
{
telnet_telopt_event SUPER_;
unsigned char focus;
} telnet_telopt_focus_event;
typedef struct telnet_telopt_data_event
{
telnet_telopt_event SUPER_;
const telnet_byte* data;
size_t length;
} telnet_telopt_data_event;
typedef struct telnet_nvt telnet_nvt;
typedef void (*telnet_nvt_event_callback)(telnet_nvt* nvt, telnet_event* event);
typedef void (*telnet_telopt_event_callback)(telnet_nvt* nvt, telnet_byte telopt, telnet_telopt_event* event);
typedef unsigned char (*telnet_negotiate_event_callback)(telnet_nvt* nvt, telnet_byte telopt, telnet_telopt_location where);
/**
Creates a new Telnet NVT.
Errors:
TELNET_E_ALLOC - Unable to allocate enough memory for the NVT.
*/
telnet_nvt* telnet_nvt_new(void* userdata,
telnet_nvt_event_callback nvt_callback,
telnet_telopt_event_callback telopt_callback,
telnet_negotiate_event_callback negotiate_callback);
void telnet_nvt_free(telnet_nvt* nvt);
/**
Every NVT can have some user-specific data attached, such as a user-defined struct.
This can be accessed (primarily by event callbacks) to differentiate between NVTs.
Errors:
TELNET_E_BAD_NVT - Invalid telnet_nvt* parameter.
Example:
// assuming a FILE was passed to telnet_nvt_new():
FILE out = NULL;
telnet_get_userdata(nvt, (void**)&out);
*/
telnet_error telnet_get_userdata(telnet_nvt* nvt, void** udata);
/**
Processes incoming data.
If `bytes_used` is non-NULL, it will be set to the length of the string that
was read. This is generally only useful if you use telnet_halt() in a callback.
Errors:
TELNET_E_BAD_NVT - Invalid telnet_nvt* parameter.
TELNET_E_ALLOC - Unable to allocate destination buffer for incoming text.
TELNET_E_INTERRUPT - User code interrupted the parser.
*/
telnet_error telnet_receive(telnet_nvt* nvt, const telnet_byte* data, size_t length, size_t* bytes_used);
/**
If currently parsing (i.e. telnet_recv() is running), interrupts the parser.
This is useful for things such as MCCP, where a Telnet sequence hails the start of
data that must be decompressed before being parsed.
Errors:
TELNET_E_BAD_NVT - Invalid telnet_nvt* parameter.
*/
telnet_error telnet_interrupt(telnet_nvt* nvt);
/**
Sends a string as a stream of escaped Telnet data.
Errors:
TELNET_E_BAD_NVT - Invalid telnet_nvt* parameter.
TELNET_E_ALLOC - Unable to allocate destination buffer for outgoing text.
*/
telnet_error telnet_send_data(telnet_nvt* nvt, const telnet_byte* data, const size_t length);
/**
Sends a Telnet command.
Errors:
TELNET_E_BAD_NVT - Invalid telnet_nvt* parameter.
TELNET_E_INVALID_COMMAND - The command cannot be WILL, WONT, DO, DONT, SB, or SE.
*/
telnet_error telnet_send_command(telnet_nvt* nvt, const telnet_byte command);
/**
Sends a subnegotiation packet.
Errors:
TELNET_E_BAD_NVT - Invalid telnet_nvt* parameter.
TELNET_E_ALLOC - Unable to allocate destination buffer for outgoing text.
*/
telnet_error telnet_send_subnegotiation(telnet_nvt* nvt, const telnet_byte option, const telnet_byte* data, const size_t length);
telnet_error telnet_telopt_enable(telnet_nvt* nvt, const telnet_byte telopt, telnet_telopt_location where);
telnet_error telnet_telopt_disable(telnet_nvt* nvt, const telnet_byte telopt, telnet_telopt_location where);
telnet_error telnet_telopt_status(telnet_nvt* nvt, const telnet_byte telopt, telnet_telopt_location where, unsigned char* status);
#ifdef __cplusplus
}
#endif
#endif // ANACHRONISM_ANACHRONISM_H

73
outside/anachronism/include/anachronism/parser.h Normal file
View File

@ -0,0 +1,73 @@
#ifndef ANACHRONISM_PARSER_H
#define ANACHRONISM_PARSER_H
#include <anachronism/common.h>
typedef enum telnet_parser_event_type
{
TELNET_EV_PARSER_DATA,
TELNET_EV_PARSER_COMMAND,
TELNET_EV_PARSER_OPTION,
TELNET_EV_PARSER_SUBNEGOTIATION,
TELNET_EV_PARSER_WARNING,
} telnet_parser_event_type;
typedef struct telnet_parser_event
{
telnet_parser_event_type type;
} telnet_parser_event;
typedef struct telnet_parser_data_event
{
telnet_parser_event SUPER_;
const telnet_byte* data;
size_t length;
} telnet_parser_data_event;
typedef struct telnet_parser_command_event
{
telnet_parser_event SUPER_;
telnet_byte command;
} telnet_parser_command_event;
typedef struct telnet_parser_option_event
{
telnet_parser_event SUPER_;
telnet_byte command;
telnet_byte option;
} telnet_parser_option_event;
typedef struct telnet_parser_subnegotiation_event
{
telnet_parser_event SUPER_;
int active;
telnet_byte option;
} telnet_parser_subnegotiation_event;
typedef struct telnet_parser_warning_event
{
telnet_parser_event SUPER_;
const char* message;
size_t position;
} telnet_parser_warning_event;
typedef struct telnet_parser telnet_parser;
typedef void (*telnet_parser_callback)(telnet_parser* parser, telnet_parser_event* event);
telnet_parser* telnet_parser_new(void* userdata, telnet_parser_callback callback);
void telnet_parser_free(telnet_parser* parser);
telnet_error telnet_parser_get_userdata(telnet_parser* parser, void** userdata);
telnet_error telnet_parser_parse(telnet_parser* parser,
const telnet_byte* data,
size_t length,
size_t* bytes_used);
telnet_error telnet_parser_interrupt(telnet_parser* parser);
#endif // ANACHRONISM_PARSER_H

6
outside/anachronism/src/README.md Normal file
View File

@ -0,0 +1,6 @@
* parser_common.rl
<br>The language-agnostic Ragel grammar for the Telnet protocol.
* parser.rl
<br>The C implementation of the Ragel grammar. Compiled to parser.c by Ragel.
* nvt.c
<br>The core implementation of Anachronism's NVT and Channel constructs.

631
outside/anachronism/src/nvt.c Normal file
View File

@ -0,0 +1,631 @@
#include <stdlib.h>
#include <string.h>
#include <anachronism/nvt.h>
#include <anachronism/parser.h>
#define TELOPT_TOGGLE_CALLBACK(nvt, telopt, where_, status_) do { \
if ((nvt)->telopt_callback) { \
telnet_telopt_toggle_event ev; \
ev.SUPER_.type = TELNET_EV_TELOPT_TOGGLE; \
ev.where = (where_); \
ev.status = (status_); \
\
(nvt)->telopt_callback((nvt), (telopt), (telnet_telopt_event*)&ev); \
} \
} while (0)
#define TELOPT_FOCUS_CALLBACK(nvt, telopt, status_) do { \
if ((nvt)->telopt_callback) { \
telnet_telopt_focus_event ev; \
ev.SUPER_.type = TELNET_EV_TELOPT_FOCUS; \
ev.status = (status_); \
\
(nvt)->telopt_callback((nvt), (telopt), (telnet_telopt_event*)&ev); \
} \
} while (0)
#define TELOPT_DATA_CALLBACK(nvt, telopt, data_, length_) do { \
if ((nvt)->telopt_callback) { \
telnet_telopt_data_event ev; \
ev.SUPER_.type = TELNET_EV_TELOPT_DATA; \
ev.data = (data_); \
ev.length = (length_); \
\
(nvt)->telopt_callback((nvt), (telopt), (telnet_telopt_event*)&ev); \
} \
} while (0)
#define SEND_CALLBACK(nvt, data_, length_) do { \
if ((nvt)->callback) { \
telnet_send_event ev; \
ev.SUPER_.type = TELNET_EV_SEND; \
ev.data = (data_); \
ev.length = (length_); \
\
(nvt)->callback((nvt), (telnet_event*)&ev); \
} \
} while (0)
// Q Method of Implementing TELNET Option Negotiation
// ftp://ftp.rfc-editor.org/in-notes/rfc1143.txt
typedef enum qstate {
Q_NO = 0, Q_WANTYES, Q_WANTYESNO,
Q_YES, Q_WANTNO, Q_WANTNOYES,
} qstate;
typedef struct telnet_qstate
{
unsigned remote : 3;
unsigned local : 3;
} telnet_qstate;
struct telnet_nvt
{
telnet_parser* parser;
telnet_qstate options[256]; // track the state of each subnegotiation option
short current_remote;
telnet_nvt_event_callback callback;
telnet_telopt_event_callback telopt_callback;
telnet_negotiate_event_callback negotiate_callback;
void* userdata;
};
static unsigned char telopt_status(telnet_nvt* nvt,
telnet_byte telopt,
telnet_telopt_location where)
{
unsigned int qval = (where == TELNET_LOCAL) ?
nvt->options[telopt].local :
nvt->options[telopt].remote;
switch (qval) {
case Q_YES: case Q_WANTNO: case Q_WANTNOYES:
return 1;
default:
return 0;
}
}
#define telopt_subnegotiable(nvt, telopt) (telopt_status((nvt), (telopt), TELNET_REMOTE) || telopt_status((nvt), (telopt), TELNET_LOCAL))
static void send_option(telnet_nvt* nvt, telnet_byte command, telnet_byte telopt)
{
const telnet_byte buf[] = {IAC_IAC, command, telopt};
SEND_CALLBACK(nvt, buf, 3);
}
static void process_option_event(telnet_nvt* nvt,
telnet_byte command,
telnet_byte telopt)
{
telnet_qstate* q = &nvt->options[telopt];
// Every qstate begins zeroed-out, and Q_NO is 0.
switch (command)
{
case IAC_WILL:
switch (q->remote)
{
case Q_NO:
if (nvt->negotiate_callback && nvt->negotiate_callback(nvt, telopt, TELNET_REMOTE)) {
send_option(nvt, IAC_DO, telopt);
q->remote = Q_YES;
TELOPT_TOGGLE_CALLBACK(nvt, telopt, TELNET_REMOTE, 1);
} else {
send_option(nvt, IAC_DONT, telopt);
}
break;
case Q_WANTNO:
// error
q->remote = Q_NO;
break;
case Q_WANTNOYES:
// error
q->remote = Q_YES;
TELOPT_TOGGLE_CALLBACK(nvt, telopt, TELNET_REMOTE, 1);
break;
case Q_WANTYES:
q->remote = Q_YES;
TELOPT_TOGGLE_CALLBACK(nvt, telopt, TELNET_REMOTE, 1);
break;
case Q_WANTYESNO:
send_option(nvt, IAC_DONT, telopt);
q->remote = Q_WANTNO;
TELOPT_TOGGLE_CALLBACK(nvt, telopt, TELNET_REMOTE, 1);
break;
}
break;
case IAC_WONT:
switch (q->remote)
{
case Q_YES:
send_option(nvt, IAC_DONT, telopt);
q->remote = Q_NO;
TELOPT_TOGGLE_CALLBACK(nvt, telopt, TELNET_REMOTE, 0);
break;
case Q_WANTNO:
q->remote = Q_NO;
break;
case Q_WANTNOYES:
send_option(nvt, IAC_DO, telopt);
q->remote = Q_WANTYES;
break;
case Q_WANTYES:
q->remote = Q_NO;
break;
case Q_WANTYESNO:
q->remote = Q_NO;
break;
}
break;
case IAC_DO:
switch (q->local)
{
case Q_NO:
if (nvt->negotiate_callback && nvt->negotiate_callback(nvt, telopt, TELNET_LOCAL)) {
send_option(nvt, IAC_WILL, telopt);
q->local = Q_YES;
TELOPT_TOGGLE_CALLBACK(nvt, telopt, TELNET_LOCAL, 1);
} else {
send_option(nvt, IAC_WONT, telopt);
}
break;
case Q_WANTNO:
// error
q->local = Q_NO;
break;
case Q_WANTNOYES:
// error
q->local = Q_YES;
TELOPT_TOGGLE_CALLBACK(nvt, telopt, TELNET_LOCAL, 1);
break;
case Q_WANTYES:
q->local = Q_YES;
TELOPT_TOGGLE_CALLBACK(nvt, telopt, TELNET_LOCAL, 1);
break;
case Q_WANTYESNO:
send_option(nvt, IAC_WONT, telopt);
q->local = Q_WANTNO;
TELOPT_TOGGLE_CALLBACK(nvt, telopt, TELNET_LOCAL, 1);
break;
}
break;
case IAC_DONT:
switch (q->local)
{
case Q_YES:
send_option(nvt, IAC_DONT, telopt);
q->local = Q_NO;
TELOPT_TOGGLE_CALLBACK(nvt, telopt, TELNET_LOCAL, 0);
break;
case Q_WANTNO:
q->local = Q_NO;
break;
case Q_WANTNOYES:
send_option(nvt, IAC_WILL, telopt);
q->local = Q_WANTYES;
break;
case Q_WANTYES:
q->local = Q_NO;
break;
case Q_WANTYESNO:
q->local = Q_NO;
break;
}
break;
}
}
static void process_data_event(telnet_nvt* nvt,
const telnet_byte* data,
size_t length)
{
if (nvt->current_remote == -1) {
// Main-line data
if (nvt->callback) {
telnet_data_event ev;
ev.SUPER_.type = TELNET_EV_DATA;
ev.data = data;
ev.length = length;
nvt->callback(nvt, (telnet_event*)&ev);
}
} else {
// Telopt data
telnet_byte telopt = (telnet_byte)nvt->current_remote;
if (nvt->telopt_callback) {
// Make sure the telopt is enabled
if (telopt_subnegotiable(nvt, telopt)) {
telnet_telopt_data_event ev;
ev.SUPER_.type = TELNET_EV_TELOPT_DATA;
ev.data = data;
ev.length = length;
nvt->telopt_callback(nvt, telopt, (telnet_telopt_event*)&ev);
}
}
}
}
static void process_subnegotiation_event(telnet_nvt* nvt,
int open,
telnet_byte telopt)
{
if (open) {
nvt->current_remote = telopt;
} else {
nvt->current_remote = -1;
}
if (nvt->telopt_callback) {
// Make sure the telopt is enabled
if (telopt_subnegotiable(nvt, telopt)) {
telnet_telopt_focus_event ev;
ev.SUPER_.type = TELNET_EV_TELOPT_FOCUS;
ev.focus = open;
nvt->telopt_callback(nvt, telopt, (telnet_telopt_event*)&ev);
}
}
}
static void process_event(telnet_parser* parser, telnet_parser_event* event)
{
telnet_nvt* nvt = NULL;
telnet_parser_get_userdata(parser, (void*)&nvt);
switch (event->type)
{
case TELNET_EV_PARSER_DATA:
{
telnet_parser_data_event* ev = (telnet_parser_data_event*)event;
process_data_event(nvt, ev->data, ev->length);
break;
}
case TELNET_EV_PARSER_OPTION:
{
telnet_parser_option_event* ev = (telnet_parser_option_event*)event;
process_option_event(nvt, ev->command, ev->option);
break;
}
case TELNET_EV_PARSER_SUBNEGOTIATION:
{
telnet_parser_subnegotiation_event* ev = (telnet_parser_subnegotiation_event*)event;
process_subnegotiation_event(nvt, ev->active, ev->option);
break;
}
case TELNET_EV_PARSER_COMMAND:
{
if (nvt->callback) {
telnet_parser_command_event* parser_ev = (telnet_parser_command_event*) event;
telnet_command_event ev;
ev.SUPER_.type = TELNET_EV_COMMAND;
ev.command = parser_ev->command;
nvt->callback(nvt, (telnet_event*)&ev);
}
break;
}
case TELNET_EV_PARSER_WARNING:
{
if (nvt->callback) {
telnet_parser_warning_event* parser_ev = (telnet_parser_warning_event*) event;
telnet_warning_event ev;
ev.SUPER_.type = TELNET_EV_WARNING;
ev.message = parser_ev->message;
ev.position = parser_ev->position;
nvt->callback(nvt, (telnet_event*)&ev);
}
break;
}
default:
break;
}
}
telnet_nvt* telnet_nvt_new(void* userdata,
telnet_nvt_event_callback nvt_callback,
telnet_telopt_event_callback telopt_callback,
telnet_negotiate_event_callback negotiate_callback)
{
telnet_nvt* nvt = malloc(sizeof(telnet_nvt));
if (nvt)
{
telnet_parser* parser = telnet_parser_new((void*)nvt, &process_event);
if (parser)
{
memset(nvt, 0, sizeof(*nvt));
nvt->parser = parser;
nvt->callback = nvt_callback;
nvt->telopt_callback = telopt_callback;
nvt->negotiate_callback = negotiate_callback;
nvt->userdata = userdata;
nvt->current_remote = -1;
}
else
{
free(nvt);
nvt = NULL;
}
}
return nvt;
}
void telnet_nvt_free(telnet_nvt* nvt)
{
if (nvt)
{
telnet_parser_free(nvt->parser);
free(nvt);
}
}
telnet_error telnet_get_userdata(telnet_nvt* nvt, void** userdata)
{
if (!nvt)
return TELNET_E_BAD_NVT;
*userdata = nvt->userdata;
return TELNET_E_OK;
}
telnet_error telnet_receive(telnet_nvt* nvt, const telnet_byte* data, size_t length, size_t* bytes_used)
{
if (!nvt)
return TELNET_E_BAD_NVT;
return telnet_parser_parse(nvt->parser, data, length, bytes_used);
}
telnet_error telnet_interrupt(telnet_nvt* nvt)
{
if (!nvt)
return TELNET_E_BAD_NVT;
return telnet_parser_interrupt(nvt->parser);
}
static int safe_concat(const telnet_byte* in, size_t inlen, telnet_byte* out, size_t outlen)
{
// Copy as much as possible into the buffer.
memcpy(out, in, (outlen < inlen) ? outlen : inlen);
// true if everything could be copied, false otherwise
return outlen >= inlen;
}
// Escapes any special characters in data, writing the result data to out.
// Returns -1 if not everything could be copied (and out is full).
// Otherwise returns the length of the data in out.
//
// To avoid potential -1 return values, pass in an out buffer double the length of the data buffer.
static size_t telnet_escape(const telnet_byte* data, size_t length, telnet_byte* out, size_t outsize)
{
if (data == NULL || out == NULL)
return 0;
size_t outlen = 0;
size_t left = 0;
size_t right = 0;
const char* seq = NULL;
for (; right < length; ++right)
{
switch (data[right])
{
case IAC_IAC:
seq = "\xFF\xFF";
break;
case '\r':
// Only escape \r if it doesn't immediately precede \n.
if (right + 1 >= length || data[right+1] != '\n')
{
seq = "\r\0";
break;
}
// !!FALLTHROUGH!!
default:
continue; // Move to the next character
}
// Add any normal data that hasn't been added yet.
if (safe_concat(data+left, right-left, out+outlen, outsize-outlen) == 0)
return -1;
outlen += right - left;
left = right + 1;
// Add the escape sequence.
if (safe_concat((const telnet_byte*)seq, 2, out+outlen, outsize-outlen) == 0)
return -1;
outlen += 2;
}
// Add any leftover normal data.
if (left < right)
{
if (safe_concat(data+left, right-left, out+outlen, outsize-outlen) == 0)
return -1;
outlen += right - left;
}
return outlen;
}
telnet_error telnet_send_data(telnet_nvt* nvt, const telnet_byte* data, const size_t length)
{
if (!nvt)
return TELNET_E_BAD_NVT;
else if (!nvt->callback)
return TELNET_E_OK; // immediate success since they apparently don't want the data to go anywhere
// Due to the nature of the protocol, the most any one byte can be encoded as is two bytes.
// Hence, the smallest buffer guaranteed to contain any input is double the length of the source.
size_t bufsize = sizeof(telnet_byte) * length * 2;
telnet_byte* buf = malloc(bufsize);
if (!buf)
return TELNET_E_ALLOC;
bufsize = telnet_escape(data, length, buf, bufsize);
SEND_CALLBACK(nvt, buf, bufsize);
free(buf);
buf = NULL;
return TELNET_E_OK;
}
telnet_error telnet_send_command(telnet_nvt* nvt, const telnet_byte command)
{
if (!nvt)
return TELNET_E_BAD_NVT;
else if (command >= IAC_SB || command == IAC_SE)
return TELNET_E_INVALID_COMMAND; // Invalid command
const telnet_byte buf[] = {IAC_IAC, command};
SEND_CALLBACK(nvt, buf, 2);
return TELNET_E_OK;
}
telnet_error telnet_send_subnegotiation(telnet_nvt* nvt, const telnet_byte option, const telnet_byte* data, const size_t length)
{
if (!nvt)
return TELNET_E_BAD_NVT;
else if (!telopt_subnegotiable(nvt, option))
return TELNET_E_NOT_SUBNEGOTIABLE;
else if (!nvt->callback)
return TELNET_E_OK;
// length*2 is the maximum buffer size needed for an escaped string.
// The extra five bytes are for the IAC, SB, <option>, IAC, and SE frame around the data.
size_t bufsize = (sizeof(telnet_byte) * length * 2) + 5;
telnet_byte* buf = malloc(bufsize);
if (!buf)
return TELNET_E_ALLOC;
// Begin with IAC SB <option>
telnet_byte iac[] = {IAC_IAC, IAC_SB, option};
memcpy(buf, iac, 3);
// Add the subnegotiation body
size_t escaped_length = telnet_escape(data, length, buf+3, bufsize-3) + 3;
// End with IAC SE
iac[1] = IAC_SE;
memcpy(buf+escaped_length, iac, 2);
escaped_length += 2;
SEND_CALLBACK(nvt, buf, escaped_length);
free(buf);
buf = NULL;
return TELNET_E_OK;
}
telnet_error telnet_telopt_enable(telnet_nvt* nvt,
telnet_byte telopt,
telnet_telopt_location where)
{
if (!nvt)
return TELNET_E_BAD_NVT;
telnet_qstate* q = &nvt->options[telopt];
if (where == TELNET_LOCAL) {
switch (q->local)
{
case Q_NO:
q->local = Q_WANTYES;
send_option(nvt, IAC_WILL, telopt);
break;
case Q_WANTNO:
q->local = Q_WANTNOYES;
break;
case Q_WANTYESNO:
q->local = Q_WANTYES;
break;
}
} else {
switch (q->remote)
{
case Q_NO:
q->remote = Q_WANTYES;
send_option(nvt, IAC_DO, telopt);
break;
case Q_WANTNO:
q->remote = Q_WANTNOYES;
break;
case Q_WANTYESNO:
q->remote = Q_WANTYES;
break;
}
}
return TELNET_E_OK;
}
telnet_error telnet_telopt_disable(telnet_nvt* nvt,
telnet_byte telopt,
telnet_telopt_location where)
{
if (!nvt)
return TELNET_E_BAD_NVT;
telnet_qstate* q = &nvt->options[telopt];
if (where == TELNET_LOCAL) {
switch (q->local)
{
case Q_YES:
send_option(nvt, IAC_WONT, telopt);
q->local = Q_WANTNO;
TELOPT_TOGGLE_CALLBACK(nvt, telopt, TELNET_LOCAL, 0);
break;
case Q_WANTNOYES:
q->local = Q_WANTNO;
break;
case Q_WANTYES:
q->local = Q_WANTYESNO;
break;
}
} else {
switch (q->remote)
{
case Q_YES:
send_option(nvt, IAC_DONT, telopt);
q->remote = Q_WANTNO;
TELOPT_TOGGLE_CALLBACK(nvt, telopt, TELNET_REMOTE, 0);
break;
case Q_WANTNOYES:
q->remote = Q_WANTNO;
break;
case Q_WANTYES:
q->remote = Q_WANTYESNO;
break;
}
}
return TELNET_E_OK;
}
telnet_error telnet_telopt_status(telnet_nvt* nvt,
telnet_byte telopt,
telnet_telopt_location where,
unsigned char* status)
{
if (!nvt)
return TELNET_E_BAD_NVT;
*status = telopt_status(nvt, telopt, where);
return TELNET_E_OK;
}

455
outside/anachronism/src/parser.c Normal file
View File

@ -0,0 +1,455 @@
#line 1 "src/parser.rl"
#include <string.h>
#include <anachronism/parser.h>
#define BASE_EV(ev, t) \
(ev).SUPER_.type = TELNET_EV_PARSER_##t
#define EV_DATA(ev, text, len) do {\
BASE_EV(ev, DATA);\
(ev).data = (text);\
(ev).length = (len);\
} while (0)
#define EV_COMMAND(ev, cmd) do {\
BASE_EV(ev, COMMAND);\
(ev).command = (cmd);\
} while (0)
#define EV_OPTION(ev, cmd, opt) do {\
BASE_EV(ev, OPTION);\
(ev).command = (cmd);\
(ev).option = (opt);\
} while (0)
#define EV_SUBNEGOTIATION(ev, act, opt) do {\
BASE_EV(ev, SUBNEGOTIATION);\
(ev).active = (act);\
(ev).option = (opt);\
} while (0)
#define EV_WARNING(ev, msg, pos) do {\
BASE_EV(ev, WARNING);\
(ev).message = (msg);\
(ev).position = (pos);\
} while (0)
struct telnet_parser {
int cs; /* current Ragel state */
const telnet_byte* p; /* current position */
const telnet_byte* pe; /* end of current packet */
const telnet_byte* eof; /* end-of-file marker */
telnet_byte option_mark; /* temporary storage for a command byte */
unsigned char interrupted; /* Flag for interrupts */
telnet_parser_callback callback; /* Receiver of Telnet events*/
void* userdata; /* Context for parser callback */
};
#line 53 "src/parser.c"
static const int telnet_parser_start = 7;
#line 130 "src/parser.rl"
telnet_parser* telnet_parser_new(void* userdata,
telnet_parser_callback callback)
{
telnet_parser* parser = malloc(sizeof(telnet_parser));
if (parser)
{
memset(parser, 0, sizeof(*parser));
#line 72 "src/parser.c"
{
parser->cs = telnet_parser_start;
}
#line 140 "src/parser.rl"
parser->callback = callback;
parser->userdata = userdata;
}
return parser;
}
void telnet_parser_free(telnet_parser* parser)
{
free(parser);
}
telnet_error telnet_parser_get_userdata(telnet_parser* parser, void** userdata)
{
if (!parser)
return TELNET_E_BAD_PARSER;
*userdata = parser->userdata;
return TELNET_E_OK;
}
telnet_error telnet_parser_parse(telnet_parser* parser,
const telnet_byte* data,
size_t length,
size_t* bytes_used)
{
if (!parser)
return TELNET_E_BAD_PARSER;
// Reset the interrupt flag
parser->interrupted = 0;
// Only bother saving text if it'll be used
telnet_byte* buf = NULL;
size_t buflen = 0;
if (parser->callback)
{
// Because of how the parser translates data, a run of text is guaranteed to
// be at most 'length' characters long. In practice it's usually less, due to
// escaped characters (IAC IAC -> IAC) and text separated by commands.
buf = malloc(length * sizeof(*buf));
if (!buf)
return TELNET_E_ALLOC;
}
parser->p = data;
parser->pe = data + length;
parser->eof = parser->pe;
#line 127 "src/parser.c"
{
if ( ( parser->p) == ( parser->pe) )
goto _test_eof;
switch ( parser->cs )
{
tr1:
#line 6 "src/parser_common.rl"
{( parser->p)--;}
#line 111 "src/parser.rl"
{
if (parser->callback && buf != NULL)
{
telnet_parser_warning_event ev;
EV_WARNING(ev, "Invalid \\r: not followed by \\n or \\0.", ( parser->p)-data);
parser->callback(parser, (telnet_parser_event*)&ev);
}
}
#line 57 "src/parser.rl"
{
if (parser->callback && buflen > 0)
{
telnet_parser_data_event ev;
EV_DATA(ev, buf, buflen);
parser->callback(parser, (telnet_parser_event*)&ev);
buflen = 0;
}
}
goto st7;
tr2:
#line 67 "src/parser.rl"
{
if (parser->callback && buf)
buf[buflen++] = (*( parser->p));
}
goto st7;
tr3:
#line 57 "src/parser.rl"
{
if (parser->callback && buflen > 0)
{
telnet_parser_data_event ev;
EV_DATA(ev, buf, buflen);
parser->callback(parser, (telnet_parser_event*)&ev);
buflen = 0;
}
}
#line 72 "src/parser.rl"
{
if (parser->callback && buf)
{
telnet_parser_command_event ev;
EV_COMMAND(ev, (*( parser->p)));
parser->callback(parser, (telnet_parser_event*)&ev);
}
}
goto st7;
tr12:
#line 57 "src/parser.rl"
{
if (parser->callback && buflen > 0)
{
telnet_parser_data_event ev;
EV_DATA(ev, buf, buflen);
parser->callback(parser, (telnet_parser_event*)&ev);
buflen = 0;
}
}
#line 6 "src/parser_common.rl"
{( parser->p)--;}
#line 119 "src/parser.rl"
{
if (parser->callback && buf != NULL)
{
telnet_parser_warning_event ev;
EV_WARNING(ev, "IAC followed by invalid command.", ( parser->p)-data);
parser->callback(parser, (telnet_parser_event*)&ev);
}
}
#line 102 "src/parser.rl"
{
if (parser->callback && buf != NULL)
{
telnet_parser_subnegotiation_event ev;
EV_SUBNEGOTIATION(ev, 0, parser->option_mark);
parser->callback(parser, (telnet_parser_event*)&ev);
}
}
goto st7;
tr13:
#line 57 "src/parser.rl"
{
if (parser->callback && buflen > 0)
{
telnet_parser_data_event ev;
EV_DATA(ev, buf, buflen);
parser->callback(parser, (telnet_parser_event*)&ev);
buflen = 0;
}
}
#line 102 "src/parser.rl"
{
if (parser->callback && buf != NULL)
{
telnet_parser_subnegotiation_event ev;
EV_SUBNEGOTIATION(ev, 0, parser->option_mark);
parser->callback(parser, (telnet_parser_event*)&ev);
}
}
goto st7;
tr14:
#line 84 "src/parser.rl"
{
if (parser->callback && buf)
{
telnet_parser_option_event ev;
EV_OPTION(ev, parser->option_mark, (*( parser->p)));
parser->callback(parser, (telnet_parser_event*)&ev);
}
}
goto st7;
st7:
if ( ++( parser->p) == ( parser->pe) )
goto _test_eof7;
case 7:
#line 252 "src/parser.c"
switch( (*( parser->p)) ) {
case 13u: goto tr15;
case 255u: goto st1;
}
goto tr2;
tr15:
#line 67 "src/parser.rl"
{
if (parser->callback && buf)
buf[buflen++] = (*( parser->p));
}
goto st0;
st0:
if ( ++( parser->p) == ( parser->pe) )
goto _test_eof0;
case 0:
#line 269 "src/parser.c"
switch( (*( parser->p)) ) {
case 0u: goto st7;
case 10u: goto tr2;
}
goto tr1;
st1:
if ( ++( parser->p) == ( parser->pe) )
goto _test_eof1;
case 1:
switch( (*( parser->p)) ) {
case 250u: goto tr4;
case 255u: goto tr2;
}
if ( 251u <= (*( parser->p)) && (*( parser->p)) <= 254u )
goto tr5;
goto tr3;
tr4:
#line 57 "src/parser.rl"
{
if (parser->callback && buflen > 0)
{
telnet_parser_data_event ev;
EV_DATA(ev, buf, buflen);
parser->callback(parser, (telnet_parser_event*)&ev);
buflen = 0;
}
}
goto st2;
st2:
if ( ++( parser->p) == ( parser->pe) )
goto _test_eof2;
case 2:
#line 302 "src/parser.c"
goto tr6;
tr11:
#line 6 "src/parser_common.rl"
{( parser->p)--;}
#line 111 "src/parser.rl"
{
if (parser->callback && buf != NULL)
{
telnet_parser_warning_event ev;
EV_WARNING(ev, "Invalid \\r: not followed by \\n or \\0.", ( parser->p)-data);
parser->callback(parser, (telnet_parser_event*)&ev);
}
}
#line 57 "src/parser.rl"
{
if (parser->callback && buflen > 0)
{
telnet_parser_data_event ev;
EV_DATA(ev, buf, buflen);
parser->callback(parser, (telnet_parser_event*)&ev);
buflen = 0;
}
}
goto st3;
tr7:
#line 67 "src/parser.rl"
{
if (parser->callback && buf)
buf[buflen++] = (*( parser->p));
}
goto st3;
tr6:
#line 93 "src/parser.rl"
{
parser->option_mark = (*( parser->p));
if (parser->callback && buf != NULL)
{
telnet_parser_subnegotiation_event ev;
EV_SUBNEGOTIATION(ev, 1, parser->option_mark);
parser->callback(parser, (telnet_parser_event*)&ev);
}
}
goto st3;
st3:
if ( ++( parser->p) == ( parser->pe) )
goto _test_eof3;
case 3:
#line 350 "src/parser.c"
switch( (*( parser->p)) ) {
case 13u: goto tr8;
case 255u: goto st5;
}
goto tr7;
tr8:
#line 67 "src/parser.rl"
{
if (parser->callback && buf)
buf[buflen++] = (*( parser->p));
}
goto st4;
st4:
if ( ++( parser->p) == ( parser->pe) )
goto _test_eof4;
case 4:
#line 367 "src/parser.c"
switch( (*( parser->p)) ) {
case 0u: goto st3;
case 10u: goto tr7;
}
goto tr11;
st5:
if ( ++( parser->p) == ( parser->pe) )
goto _test_eof5;
case 5:
switch( (*( parser->p)) ) {
case 240u: goto tr13;
case 255u: goto tr7;
}
goto tr12;
tr5:
#line 57 "src/parser.rl"
{
if (parser->callback && buflen > 0)
{
telnet_parser_data_event ev;
EV_DATA(ev, buf, buflen);
parser->callback(parser, (telnet_parser_event*)&ev);
buflen = 0;
}
}
#line 81 "src/parser.rl"
{
parser->option_mark = (*( parser->p));
}
goto st6;
st6:
if ( ++( parser->p) == ( parser->pe) )
goto _test_eof6;
case 6:
#line 402 "src/parser.c"
goto tr14;
}
_test_eof7: parser->cs = 7; goto _test_eof;
_test_eof0: parser->cs = 0; goto _test_eof;
_test_eof1: parser->cs = 1; goto _test_eof;
_test_eof2: parser->cs = 2; goto _test_eof;
_test_eof3: parser->cs = 3; goto _test_eof;
_test_eof4: parser->cs = 4; goto _test_eof;
_test_eof5: parser->cs = 5; goto _test_eof;
_test_eof6: parser->cs = 6; goto _test_eof;
_test_eof: {}
if ( ( parser->p) == ( parser->eof) )
{
switch ( parser->cs ) {
case 3:
case 7:
#line 57 "src/parser.rl"
{
if (parser->callback && buflen > 0)
{
telnet_parser_data_event ev;
EV_DATA(ev, buf, buflen);
parser->callback(parser, (telnet_parser_event*)&ev);
buflen = 0;
}
}
break;
#line 431 "src/parser.c"
}
}
}
#line 189 "src/parser.rl"
if (bytes_used != NULL)
*bytes_used = parser->p - data;
free(buf);
buf = NULL;
parser->p = parser->pe = parser->eof = NULL;
return (parser->interrupted) ? TELNET_E_INTERRUPT : TELNET_E_OK;
}
telnet_error telnet_parser_interrupt(telnet_parser* parser)
{
if (!parser)
return TELNET_E_BAD_PARSER;
// Force the parser to stop where it's at.
if (parser->p)
parser->eof = parser->pe = parser->p + 1;
parser->interrupted = 1;
return TELNET_E_OK;
}

211
outside/anachronism/src/parser.rl Normal file
View File

@ -0,0 +1,211 @@
#include <string.h>
#include <anachronism/parser.h>
#define BASE_EV(ev, t) \
(ev).SUPER_.type = TELNET_EV_PARSER_##t
#define EV_DATA(ev, text, len) do {\
BASE_EV(ev, DATA);\
(ev).data = (text);\
(ev).length = (len);\
} while (0)
#define EV_COMMAND(ev, cmd) do {\
BASE_EV(ev, COMMAND);\
(ev).command = (cmd);\
} while (0)
#define EV_OPTION(ev, cmd, opt) do {\
BASE_EV(ev, OPTION);\
(ev).command = (cmd);\
(ev).option = (opt);\
} while (0)
#define EV_SUBNEGOTIATION(ev, act, opt) do {\
BASE_EV(ev, SUBNEGOTIATION);\
(ev).active = (act);\
(ev).option = (opt);\
} while (0)
#define EV_WARNING(ev, msg, pos) do {\
BASE_EV(ev, WARNING);\
(ev).message = (msg);\
(ev).position = (pos);\
} while (0)
struct telnet_parser {
int cs; /* current Ragel state */
const telnet_byte* p; /* current position */
const telnet_byte* pe; /* end of current packet */
const telnet_byte* eof; /* end-of-file marker */
telnet_byte option_mark; /* temporary storage for a command byte */
unsigned char interrupted; /* Flag for interrupts */
telnet_parser_callback callback; /* Receiver of Telnet events*/
void* userdata; /* Context for parser callback */
};
%%{
machine telnet_parser;
access parser->;
variable p parser->p;
variable pe parser->pe;
variable eof parser->eof;
action flush_text {
if (parser->callback && buflen > 0)
{
telnet_parser_data_event ev;
EV_DATA(ev, buf, buflen);
parser->callback(parser, (telnet_parser_event*)&ev);
buflen = 0;
}
}
action char {
if (parser->callback && buf)
buf[buflen++] = fc;
}
action basic_command {
if (parser->callback && buf)
{
telnet_parser_command_event ev;
EV_COMMAND(ev, fc);
parser->callback(parser, (telnet_parser_event*)&ev);
}
}
action option_mark {
parser->option_mark = fc;
}
action option_command {
if (parser->callback && buf)
{
telnet_parser_option_event ev;
EV_OPTION(ev, parser->option_mark, fc);
parser->callback(parser, (telnet_parser_event*)&ev);
}
}
action subneg_command {
parser->option_mark = fc;
if (parser->callback && buf != NULL)
{
telnet_parser_subnegotiation_event ev;
EV_SUBNEGOTIATION(ev, 1, parser->option_mark);
parser->callback(parser, (telnet_parser_event*)&ev);
}
}
action subneg_command_end {
if (parser->callback && buf != NULL)
{
telnet_parser_subnegotiation_event ev;
EV_SUBNEGOTIATION(ev, 0, parser->option_mark);
parser->callback(parser, (telnet_parser_event*)&ev);
}
}
action warning_cr {
if (parser->callback && buf != NULL)
{
telnet_parser_warning_event ev;
EV_WARNING(ev, "Invalid \\r: not followed by \\n or \\0.", fpc-data);
parser->callback(parser, (telnet_parser_event*)&ev);
}
}
action warning_iac {
if (parser->callback && buf != NULL)
{
telnet_parser_warning_event ev;
EV_WARNING(ev, "IAC followed by invalid command.", fpc-data);
parser->callback(parser, (telnet_parser_event*)&ev);
}
}
include telnet_parser_common "parser_common.rl";
write data;
}%%
telnet_parser* telnet_parser_new(void* userdata,
telnet_parser_callback callback)
{
telnet_parser* parser = malloc(sizeof(telnet_parser));
if (parser)
{
memset(parser, 0, sizeof(*parser));
%% write init;
parser->callback = callback;
parser->userdata = userdata;
}
return parser;
}
void telnet_parser_free(telnet_parser* parser)
{
free(parser);
}
telnet_error telnet_parser_get_userdata(telnet_parser* parser, void** userdata)
{
if (!parser)
return TELNET_E_BAD_PARSER;
*userdata = parser->userdata;
return TELNET_E_OK;
}
telnet_error telnet_parser_parse(telnet_parser* parser,
const telnet_byte* data,
size_t length,
size_t* bytes_used)
{
if (!parser)
return TELNET_E_BAD_PARSER;
// Reset the interrupt flag
parser->interrupted = 0;
// Only bother saving text if it'll be used
telnet_byte* buf = NULL;
size_t buflen = 0;
if (parser->callback)
{
// Because of how the parser translates data, a run of text is guaranteed to
// be at most 'length' characters long. In practice it's usually less, due to
// escaped characters (IAC IAC -> IAC) and text separated by commands.
buf = malloc(length * sizeof(*buf));
if (!buf)
return TELNET_E_ALLOC;
}
parser->p = data;
parser->pe = data + length;
parser->eof = parser->pe;
%% write exec;
if (bytes_used != NULL)
*bytes_used = parser->p - data;
free(buf);
buf = NULL;
parser->p = parser->pe = parser->eof = NULL;
return (parser->interrupted) ? TELNET_E_INTERRUPT : TELNET_E_OK;
}
telnet_error telnet_parser_interrupt(telnet_parser* parser)
{
if (!parser)
return TELNET_E_BAD_PARSER;
// Force the parser to stop where it's at.
if (parser->p)
parser->eof = parser->pe = parser->p + 1;
parser->interrupted = 1;
return TELNET_E_OK;
}

85
outside/anachronism/src/parser_common.rl Normal file
View File

@ -0,0 +1,85 @@
%%{
machine telnet_parser_common;
alphtype unsigned char;
# Shorthand for tidiness.
action fhold {fhold;}
# Special bytes that must be handled differently from normal text:
CR = "\r"; # Only \0 or \n may follow
IAC = 255; # Telnet command marker
special_byte = CR | IAC;
# The only bytes that may follow a CR:
NL = "\n";
NUL = "\0";
# The only bytes that may follow an IAC:
SE = 240;
NOP = 241;
DM = 242;
BRK = 243;
IP = 244;
AO = 245;
AYT = 246;
EC = 247;
EL = 248;
GA = 249;
SB = 250;
WILL = 251;
WONT = 252;
DO = 253;
DONT = 254;
# IAC IAC is interpreted as a plain-text IAC byte.
# Sorting the above IAC commands by type:
iac_option_type = WILL | WONT | DO | DONT;
iac_subneg_type = SB;
iac_command_type = ^(iac_option_type | iac_subneg_type | IAC);
###
# Plain text
###
plain_text = (^special_byte) @char;
cr_seq = CR @char
( NUL
| NL @char
| ^(NUL|NL) @fhold @warning_cr @flush_text
);
###
# IAC sequence
###
iac_command = iac_command_type @basic_command;
iac_option = iac_option_type @option_mark
any @option_command;
iac_subneg = iac_subneg_type any @subneg_command
( plain_text
| cr_seq
| IAC IAC @char
)** %/flush_text
IAC
( SE
| ^(IAC|SE) @fhold @warning_iac
) >flush_text @subneg_command_end;
iac_seq = ( iac_command
| iac_option
| iac_subneg
);
###
# Telnet stream
###
telnet_stream = ( plain_text
| cr_seq
| IAC
( IAC @char
| iac_seq >flush_text
)
)** %/flush_text;
main := telnet_stream;
}%%

23
outside/commonmark/.editorconfig Normal file
View File

@ -0,0 +1,23 @@
# editorconfig.org
root = true
[*]
end_of_line = lf
charset = utf-8
insert_final_newline = true
[*.js]
trim_trailing_whitespace = true
indent_style = space
indent_size = 2
[*.{c,h}]
trim_trailing_whitespace = true
indent_style = tab
indent_size = 8
[Makefile]
trim_trailing_whitespace = true
indent_style = tab
indent_size = 8

33
outside/commonmark/.gitignore vendored Normal file
View File

@ -0,0 +1,33 @@
# Object files
*.o
*.ko
*.obj
*.elf
# Libraries
*.lib
*.a
# Shared objects (inc. Windows DLLs)
*.dll
*.so
*.so.*
*.dylib
# Executables
*.exe
*.out
*.app
*.i*86
*.x86_64
*.hex
*~
*.bak
*.diff
*#
*.zip
bstrlib.txt
build
cmark.dSYM/*
cmark

10
outside/commonmark/.travis.yml Normal file
View File

@ -0,0 +1,10 @@
language: c
compiler:
- clang
- gcc
before_install:
- sudo apt-get update -qq
- sudo apt-get install -qq pandoc re2c valgrind
script:
- make testtarball
- PROG=`ls cmark-*.*/build/src/cmark` make leakcheck

24
outside/commonmark/CMakeLists.txt Normal file
View File

@ -0,0 +1,24 @@
project(cmark)
cmake_minimum_required(VERSION 2.8)
if("${CMAKE_SOURCE_DIR}" STREQUAL "${CMAKE_BINARY_DIR}")
message(FATAL_ERROR "Do not build in-source.\nPlease remove CMakeCache.txt and the CMakeFiles/ directory.\nThen: mkdir build ; cd build ; cmake .. ; make")
endif()
set(PROJECT_NAME "cmark")
set(PROJECT_VERSION_MAJOR 0)
set(PROJECT_VERSION_MINOR 0)
set(PROJECT_VERSION_PATCH 1)
set(PROJECT_VERSION ${PROJECT_VERSION_MAJOR}.${PROJECT_VERSION_MINOR}.${PROJECT_VERSION_PATCH} )
add_subdirectory(src)
#add_subdirectory(api_test)
#add_subdirectory(man)
#enable_testing()
#add_subdirectory(test)
if(NOT CMAKE_BUILD_TYPE)
set(CMAKE_BUILD_TYPE "Release" CACHE STRING
"Choose the type of build, options are: Debug Release." FORCE)
endif(NOT CMAKE_BUILD_TYPE)

70
outside/commonmark/LICENSE Normal file
View File

@ -0,0 +1,70 @@
Copyright (c) 2014, John MacFarlane
All rights reserved.
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright
notice, this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above
copyright notice, this list of conditions and the following
disclaimer in the documentation and/or other materials provided
with the distribution.
* Neither the name of John MacFarlane nor the names of other
contributors may be used to endorse or promote products derived
from this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
-----
The polyfill for String.fromCodePoint included in commonmark.js is
Copyright Mathias Bynens <http://mathiasbynens.be/>
Permission is hereby granted, free of charge, to any person obtaining
a copy of this software and associated documentation files (the
"Software"), to deal in the Software without restriction, including
without limitation the rights to use, copy, modify, merge, publish,
distribute, sublicense, and/or sell copies of the Software, and to
permit persons to whom the Software is furnished to do so, subject to
the following conditions:
The above copyright notice and this permission notice shall be
included in all copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
-----
The normalization code in runtests.py was derived from the
markdowntest project, Copyright 2013 Karl Dubost:
The MIT License (MIT)
Copyright (c) 2013 Karl Dubost
Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

194
outside/commonmark/Makefile Normal file
View File

@ -0,0 +1,194 @@
SRCDIR?=src
DATADIR?=data
BUILDDIR?=build
GENERATOR?=Unix Makefiles
MINGW_BUILDDIR?=build-mingw
MINGW_INSTALLDIR?=windows
SPEC=spec.txt
SITE=_site
SPECVERSION=$(shell perl -ne 'print $$1 if /^version: *([0-9.]+)/' $(SPEC))
PKGDIR?=cmark-$(SPECVERSION)
TARBALL?=cmark-$(SPECVERSION).tar.gz
ZIPARCHIVE?=cmark-$(SPECVERSION).zip
FUZZCHARS?=2000000 # for fuzztest
BENCHDIR=bench
BENCHFILE=$(BENCHDIR)/benchinput.md
ALLTESTS=alltests.md
NUMRUNS?=10
PROG?=$(BUILDDIR)/src/cmark
BENCHINP?=README.md
JSMODULES=$(wildcard js/lib/*.js)
.PHONY: all spec leakcheck clean fuzztest dingus upload jshint test testjs benchjs update-site upload-site check npm debug mingw archive tarball ziparchive testarchive testtarball testziparchive testlib bench apidoc
all: $(BUILDDIR)
@$(MAKE) -C $(BUILDDIR)
@echo "Binaries can be found in $(BUILDDIR)/src"
check:
@cmake --version > /dev/null || (echo "You need cmake to build this program: http://www.cmake.org/download/" && exit 1)
$(BUILDDIR): check $(SRCDIR)/html/html_unescape.h $(SRCDIR)/case_fold_switch.inc man/man1/cmark.1 man/man3/cmark.3
mkdir -p $(BUILDDIR); \
cd $(BUILDDIR); \
cmake .. -G "$(GENERATOR)" -DCMAKE_BUILD_TYPE=$(BUILD_TYPE)
install: $(BUILDDIR)
$(MAKE) -C $(BUILDDIR) install
debug:
mkdir -p $(BUILDDIR); \
cd $(BUILDDIR); \
cmake .. -DCMAKE_BUILD_TYPE=Debug; \
$(MAKE)
mingw:
mkdir -p $(MINGW_BUILDDIR); \
cd $(MINGW_BUILDDIR); \
cmake .. -DCMAKE_TOOLCHAIN_FILE=../toolchain-mingw32.cmake -DCMAKE_INSTALL_PREFIX=$(MINGW_INSTALLDIR) ;\
$(MAKE) && $(MAKE) install
archive: spec.html $(BUILDDIR)
@rm -rf $(PKGDIR); \
mkdir -p $(PKGDIR)/$(SRCDIR)/html; \
mkdir -p $(PKGDIR)/api_test; \
srcfiles=`git ls-tree --full-tree -r HEAD --name-only $(SRCDIR) api_test`; \
for f in $$srcfiles; do cp -a $$f $(PKGDIR)/$$f; done; \
cp -a $(SRCDIR)/scanners.c $(PKGDIR)/$(SRCDIR)/; \
cp -a spec.html $(PKGDIR); \
cp CMakeLists.txt $(PKGDIR); \
perl -ne '$$p++ if /^### JavaScript/; print if (!$$p)' Makefile > $(PKGDIR)/Makefile; \
cp -a Makefile.nmake nmake.bat $(PKGDIR); \
cp -r man $(PKGDIR)/; \
cp -r test $(PKGDIR)/; \
cp -a README.md LICENSE spec.txt $(PKGDIR)/; \
tar czf $(TARBALL) $(PKGDIR); \
zip -q -r $(ZIPARCHIVE) $(PKGDIR); \
rm -rf $(PKGDIR) ; \
echo "Created $(TARBALL) and $(ZIPARCHIVE)."
clean:
rm -rf $(BUILDDIR) $(MINGW_BUILDDIR) $(MINGW_INSTALLDIR) $(TARBALL) $(ZIPARCHIVE) $(PKGDIR)
$(PROG): all
man/man3/cmark.3: src/cmark.h
python man/make_man_page.py $< > $@
# We include html_unescape.h in the repository, so this shouldn't
# normally need to be generated.
$(SRCDIR)/html/html_unescape.h: $(SRCDIR)/html/html_unescape.gperf
gperf -L ANSI-C -I -t -N find_entity -H hash_entity -K entity -C -l \
--null-strings -m5 $< > $@
# We include case_fold_switch.inc in the repository, so this shouldn't
# normally need to be generated.
$(SRCDIR)/case_fold_switch.inc: $(DATADIR)/CaseFolding-3.2.0.txt
perl mkcasefold.pl < $< > $@
test: $(SPEC) $(BUILDDIR)
$(MAKE) -C $(BUILDDIR) test ARGS="-V"
$(TARBALL): archive
$(ZIPARCHIVE): archive
testarchive: testtarball testziparchive
rm -rf $(PKGDIR)
testtarball: $(TARBALL)
rm -rf $(PKGDIR); \
tar xvzf $(TARBALL); \
cd $(PKGDIR); \
mkdir build && cd build && cmake .. && $(MAKE) && ctest -V
testziparchive: $(ZIPARCHIVE)
rm -rf $(PKGDIR); \
unzip $(ZIPARCHIVE); \
cd $(PKGDIR); \
mkdir build && cd build && cmake .. && $(MAKE) && ctest -V
$(ALLTESTS): spec.txt
python test/spec_tests.py --spec $< --dump-tests | python -c 'import json; import sys; tests = json.loads(sys.stdin.read()); print "\n".join([test["markdown"] for test in tests]).encode("utf-8")' > $@
leakcheck: $(ALLTESTS) $(PROG)
cat $< | valgrind --leak-check=full --dsymutil=yes --error-exitcode=1 $(PROG) >/dev/null
fuzztest:
{ for i in `seq 1 10`; do \
cat /dev/urandom | head -c $(FUZZCHARS) | iconv -f latin1 -t utf-8 | tee fuzz-$$i.txt | \
/usr/bin/env time -p $(PROG) >/dev/null && rm fuzz-$$i.txt ; \
done } 2>&1 | grep 'user\|abnormally'
# for benchmarking
$(BENCHFILE): progit/progit.md
-rm $@; for x in `seq 1 20` ; do cat $< >> $@; done
progit:
git clone https://github.com/progit/progit.git
progit/progit.md: progit
cat progit/en/*/*.markdown > $@
bench: $(BENCHFILE)
{ sudo renice 99 $$$$; \
for x in `seq 1 $(NUMRUNS)` ; do \
/usr/bin/env time -p $(PROG) </dev/null >/dev/null ; \
/usr/bin/env time -p $(PROG) <$< >/dev/null ; \
done \
} 2>&1 | grep 'real' | awk '{print $$2}' | python3 'bench/stats.py'
operf: $(PROG)
operf $(PROG) <$(BENCHINP) >/dev/null
distclean: clean
-rm -f js/commonmark.js
-rm -rf *.dSYM
-rm -f README.html
-rm -f spec.md fuzz.txt spec.html
-rm -rf $(BENCHFILE) $(ALLTESTS) progit
### JavaScript ###
js/commonmark.js: js/lib/index.js ${JSMODULES}
browserify --standalone commonmark $< -o $@
testjs: $(SPEC)
node js/test.js
jshint:
jshint ${JSMODULES}
benchjs:
node js/bench.js ${BENCHINP}
npm:
cd js; npm publish
dingus: js/commonmark.js
echo "Starting dingus server at http://localhost:9000" && python -m SimpleHTTPServer 9000
### Spec ###
spec.md: $(SPEC)
perl spec2md.pl < $< > $@
spec.html: spec.md template.html
pandoc --no-highlight --number-sections --template template.html -s --toc -S $< | \
perl -pe 's/a href="@([^"]*)"/a id="\1" href="#\1" class="definition"/g' | \
perl -pe 's/␣/<span class="space"> <\/span>/g' \
> $@
spec.pdf: spec.md template.tex specfilter.hs
pandoc -s $< --template template.tex \
--filter ./specfilter.hs -o $@ --latex-engine=xelatex --toc \
--number-sections -V documentclass=report -V tocdepth=2 \
-V classoption=twosides
### Website ###
update-site: spec.html js/commonmark.js
$(MAKE) -C $(SITE) update
upload-site: spec.html
$(MAKE) -C $(SITE) upload

57
outside/commonmark/Makefile.nmake Normal file
View File

@ -0,0 +1,57 @@
SRCDIR=src
DATADIR=data
BUILDDIR=build
INSTALLDIR=windows
SPEC=spec.txt
PROG=$(BUILDDIR)\src\cmark.exe
GENERATOR=NMake Makefiles
all: $(BUILDDIR)
@pushd $(BUILDDIR) && $(MAKE) /nologo && popd
$(BUILDDIR):
@cmake --version > nul || (echo "You need cmake to build this program: http://www.cmake.org/download/" && exit 1)
-mkdir $(BUILDDIR) 2> nul
pushd $(BUILDDIR) && \
cmake \
-G "$(GENERATOR)" \
-D CMAKE_BUILD_TYPE=$(BUILD_TYPE) \
-D CMAKE_INSTALL_PREFIX=$(INSTALLDIR) \
.. && \
popd
install: all
@pushd $(BUILDDIR) && $(MAKE) /nologo install && popd
clean:
-rmdir /s /q $(BUILDDIR) $(MINGW_INSTALLDIR) 2> nul
$(SRCDIR)\case_fold_switch.inc: $(DATADIR)\CaseFolding-3.2.0.txt
perl mkcasefold.pl < $? > $@
man\man1\cmark.1: man\cmark.1.md
pandoc $? -o $@ -s -t man
test: $(SPEC) all
@pushd $(BUILDDIR) && $(MAKE) /nologo test ARGS="-V" && popd
distclean: clean
del /q src\scanners.c 2> nul
del /q spec.md spec.html 2> nul
### Spec ###
spec.md: $(SPEC)
perl spec2md.pl < $? > $@
spec.html: spec.md template.html
pandoc --no-highlight --number-sections --template template.html -s --toc -S $? | \
perl -pe "s/a href=\"@([^"]*)\"/a id=\"\\1\" href=\"#\\1\" class=\"definition\"/g" | \
perl -pe "s/\\x{2423}/<span class=\"space\"> <\\/span>/g" \
> $@
spec.pdf: spec.md template.tex specfilter.hs
pandoc -s $? --template template.tex \
--filter specfilter.hs -o $@ --latex-engine=xelatex --toc \
--number-sections -V documentclass=report -V tocdepth=2 \
-V classoption=twosides

47
outside/commonmark/Makefile.old Normal file
View File

@ -0,0 +1,47 @@
PREFIX?=/usr/local
SRCDIR?=src
CFLAGS?=-g -O3 -Wall -Wextra -std=c99 -Isrc -Wno-missing-field-initializers -fPIC $(OPTCFLAGS)
LDFLAGS?=-g -O3 -Wall -Werror -fPIC $(OPTLDFLAGS)
HTML_OBJ=$(SRCDIR)/html/html.o $(SRCDIR)/html/houdini_href_e.o $(SRCDIR)/html/houdini_html_e.o $(SRCDIR)/html/houdini_html_u.o
CMARK_OBJ=$(SRCDIR)/inlines.o $(SRCDIR)/buffer.o $(SRCDIR)/blocks.o $(SRCDIR)/scanners.c $(SRCDIR)/print.o $(SRCDIR)/utf8.o $(SRCDIR)/references.o
CMARK_HDR = $(SRCDIR)/cmark.h $(SRCDIR)/buffer.h $(SRCDIR)/references.h \
$(SRCDIR)/chunk.h $(SRCDIR)/debug.h $(SRCDIR)/utf8.h \
$(SRCDIR)/scanners.h $(SRCDIR)/inlines.h
HTML_HDR = $(SRCDIR)/html/html_unescape.h $(SRCDIR)/html/houdini.h
$(PROG): $(SRCDIR)/html/html_unescape.h $(SRCDIR)/case_fold_switch.inc $(HTML_OBJ) $(CMARK_OBJ) $(SRCDIR)/main.c
$(CC) $(LDFLAGS) -o $@ $(HTML_OBJ) $(CMARK_OBJ) $(SRCDIR)/main.c
$(SRCDIR)/scanners.c: $(SRCDIR)/scanners.re
re2c --case-insensitive -bis $< > $@ || (rm $@ && false)
$(SRCDIR)/html/html_unescape.h: $(SRCDIR)/html/html_unescape.gperf
gperf -I -t -N find_entity -H hash_entity -K entity -C -l
--null-strings -m5 $< > $@
libcommonmark.so: $(HTML_OBJ) $(CMARK_OBJ)
$(CC) $(LDFLAGS) -shared -o $@ $^
install: libcommonmark.so $(cmark_HDR) $(HTML_HDR)
install -d $(PREFIX)/lib $(PREFIX)/include/cmark/html
install libcommonmark.so $(PREFIX)/lib/
install $(cmark_HDR) $(PREFIX)/include/cmark/
install $(HTML_HDR) $(PREFIX)/include/cmark/html/
CMARK_HDR = $(SRCDIR)/cmark.h $(SRCDIR)/buffer.h $(SRCDIR)/references.h \
$(SRCDIR)/chunk.h $(SRCDIR)/debug.h $(SRCDIR)/utf8.h \
$(SRCDIR)/scanners.h $(SRCDIR)/inlines.h
HTML_HDR = $(SRCDIR)/html/html_unescape.h $(SRCDIR)/html/houdini.h
clean:
-rm -f test $(SRCDIR)/*.o $(SRCDIR)/scanners.c $(SRCDIR)/html/*.o libcommonmark.so
-rm -f js/commonmark.js
-rm -rf *.dSYM
-rm -f README.html
-rm -f spec.md fuzz.txt spec.html

298
outside/commonmark/README.md Normal file
View File

@ -0,0 +1,298 @@
CommonMark
==========
CommonMark is a rationalized version of Markdown syntax,
with a [spec][the spec] and BSD3-licensed reference
implementations in C and JavaScript.
[Try it now!](http://spec.commonmark.org/dingus.html)
The implementations
-------------------
The C implementation provides both a shared library (`libcmark`) and a
standalone program `cmark` that converts CommonMark to HTML. It is
written in standard C99 and has no library dependencies. The parser is
very fast (see [benchmarks](benchmarks.md)).
It is easy to use `libcmark` in python, lua, ruby, and other dynamic
languages: see `wrapper.py`, `wrapper.lua`, and `wrapper.rb` in the
repository for simple examples.
The JavaScript implementation is a single JavaScript file, with
no dependencies, that can be linked to in an HTML page. Here
is a simple usage example:
``` javascript
var reader = new commonmark.DocParser();
var writer = new commonmark.HtmlRenderer();
var parsed = reader.parse("Hello *world*");
var result = writer.render(parsed);
```
A node package is also available; it includes a command-line tool called
`commonmark`.
**A note on security:**
Neither implementation attempts to sanitize link attributes or
raw HTML. If you use these libraries in applications that accept
untrusted user input, you must run the output through an HTML
sanitizer to protect against
[XSS attacks](http://en.wikipedia.org/wiki/Cross-site_scripting).
Installing (C)
--------------
Building the C program (`cmark`) and shared library (`libcmark`)
requires [cmake]. If you modify `scanners.re`, then you will also
need [re2c], which is used to generate `scanners.c` from
`scanners.re`. We have included a pre-generated `scanners.c` in
the repository to reduce build dependencies.
If you have GNU make, you can simply `make`, `make test`, and `make
install`. This calls [cmake] to create a `Makefile` in the `build`
directory, then uses that `Makefile` to create the executable and
library. The binaries can be found in `build/src`.
For a more portable method, you can use [cmake] manually. [cmake] knows
how to create build environments for many build systems. For example,
on FreeBSD:
mkdir build
cd build
cmake .. # optionally: -DCMAKE_INSTALL_PREFIX=path
make # executable will be create as build/src/cmake
make test
make install
Or, to create Xcode project files on OSX:
mkdir build
cd build
cmake -G Xcode ..
make
make test
make install
The GNU Makefile also provides a few other targets for developers.
To run a "fuzz test" against ten long randomly generated inputs:
make fuzztest
To run a test for memory leaks using valgrind:
make leakcheck
To make a release tarball and zip archive:
make archive
To test the archives:
make testarchive
Compiling for Windows
---------------------
To compile with MSVC and NMAKE:
nmake
You can cross-compile a Windows binary and dll on linux if you have the
`mingw32` compiler:
make mingw
The binaries will be in `build-mingw/windows/bin`.
Installing (JavaScript)
-----------------------
The JavaScript library can be installed through `npm`:
npm install commonmark
To build the JavaScript library as a single standalone file:
browserify --standalone commonmark js/lib/index.js -o js/commonmark.js
Or fetch a pre-built copy from
<http://spec.commonmark.org/js/commonmark.js>`.
To run tests for the JavaScript library:
make testjs
or
node js/test.js
The spec
--------
[The spec] contains over 500 embedded examples which serve as conformance
tests. To run the tests using an executable `$PROG`:
python test/spec_tests.py --program $PROG
If you want to extract the raw test data from the spec without
actually running the tests, you can do:
python test/spec_tests.py --dump-tests
and you'll get all the tests in JSON format.
[The spec]: http://jgm.github.io/CommonMark/spec.html
The source of [the spec] is `spec.txt`. This is basically a Markdown
file, with code examples written in a shorthand form:
.
Markdown source
.
expected HTML output
.
To build an HTML version of the spec, do `make spec.html`. To build a
PDF version, do `make spec.pdf`. Both these commands require that
[pandoc] is installed, and creating a PDF requires a latex installation.
The spec is written from the point of view of the human writer, not
the computer reader. It is not an algorithm---an English translation of
a computer program---but a declarative description of what counts as a block
quote, a code block, and each of the other structural elements that can
make up a Markdown document.
Because John Gruber's [canonical syntax
description](http://daringfireball.net/projects/markdown/syntax) leaves
many aspects of the syntax undetermined, writing a precise spec requires
making a large number of decisions, many of them somewhat arbitrary.
In making them, we have appealed to existing conventions and
considerations of simplicity, readability, expressive power, and
consistency. We have tried to ensure that "normal" documents in the many
incompatible existing implementations of Markdown will render, as far as
possible, as their authors intended. And we have tried to make the rules
for different elements work together harmoniously. In places where
different decisions could have been made (for example, the rules
governing list indentation), we have explained the rationale for
my choices. In a few cases, we have departed slightly from the canonical
syntax description, in ways that we think further the goals of Markdown
as stated in that description.
For the most part, we have limited ourselves to the basic elements
described in Gruber's canonical syntax description, eschewing extensions
like footnotes and definition lists. It is important to get the core
right before considering such things. However, we have included a visible
syntax for line breaks and fenced code blocks.
Differences from original Markdown
----------------------------------
There are only a few places where this spec says things that contradict
the canonical syntax description:
- It [allows all punctuation symbols to be
backslash-escaped](http://jgm.github.io/CommonMark/spec.html#backslash-escapes),
not just the symbols with special meanings in Markdown. We found
that it was just too hard to remember which symbols could be
escaped.
- It introduces an [alternative syntax for hard line
breaks](http://jgm.github.io/CommonMark/spec.html#hard-line-breaks), a
backslash at the end of the line, supplementing the
two-spaces-at-the-end-of-line rule. This is motivated by persistent
complaints about the “invisible” nature of the two-space rule.
- Link syntax has been made a bit more predictable (in a
backwards-compatible way). For example, `Markdown.pl` allows single
quotes around a title in inline links, but not in reference links.
This kind of difference is really hard for users to remember, so the
spec [allows single quotes in both
contexts](http://jgm.github.io/CommonMark/spec.html#links).
- The rule for HTML blocks differs, though in most real cases it
shouldn't make a difference. (See
[here](http://jgm.github.io/CommonMark/spec.html#html-blocks) for
details.) The spec's proposal makes it easy to include Markdown
inside HTML block-level tags, if you want to, but also allows you to
exclude this. It is also makes parsing much easier, avoiding
expensive backtracking.
- It does not collapse adjacent bird-track blocks into a single
blockquote:
> this is two
> blockquotes
> this is a single
>
> blockquote with two paragraphs
- Rules for content in lists differ in a few respects, though (as with
HTML blocks), most lists in existing documents should render as
intended. There is some discussion of the choice points and
differences [here](http://jgm.github.io/CommonMark/spec.html#motivation).
We think that the spec's proposal does better than any existing
implementation in rendering lists the way a human writer or reader
would intuitively understand them. (We could give numerous examples
of perfectly natural looking lists that nearly every existing
implementation flubs up.)
- The spec stipulates that two blank lines break out of all list
contexts. This is an attempt to deal with issues that often come up
when someone wants to have two adjacent lists, or a list followed by
an indented code block.
- Changing bullet characters, or changing from bullets to numbers or
vice versa, starts a new list. We think that is almost always going
to be the writer's intent.
- The number that begins an ordered list item may be followed by
either `.` or `)`. Changing the delimiter style starts a new
list.
- The start number of an ordered list is significant.
- [Fenced code blocks](http://jgm.github.io/CommonMark/spec.html#fenced-code-blocks) are supported, delimited by either
backticks (```` ``` ```` or tildes (` ~~~ `).
Contributing
------------
There is a [forum for discussing
CommonMark](http://talk.commonmark.org); you should use it instead of
github issues for questions and possibly open-ended discussions.
Use the [github issue tracker](http://github.com/jgm/CommonMark/issues)
only for simple, clear, actionable issues.
Authors
-------
The spec was written by John MacFarlane, drawing on
- his experience writing and maintaining Markdown implementations in several
languages, including the first Markdown parser not based on regular
expression substitutions ([pandoc](http://github.com/jgm/pandoc)) and
the first markdown parsers based on PEG grammars
([peg-markdown](http://github.com/jgm/peg-markdown),
[lunamark](http://github.com/jgm/lunamark))
- a detailed examination of the differences between existing Markdown
implementations using [BabelMark 2](http://johnmacfarlane.net/babelmark2/),
and
- extensive discussions with David Greenspan, Jeff Atwood, Vicent
Marti, Neil Williams, and Benjamin Dumke-von der Ehe.
John MacFarlane was also responsible for the original versions of the
C and JavaScript implementations. The block parsing algorithm was
worked out together with David Greenspan. Vicent Marti
optimized the C implementation for performance, increasing its speed
tenfold. Kārlis Gaņģis helped work out a better parsing algorithm
for links and emphasis, eliminating several worst-case performance
issues. Nick Wellnhofer contributed many improvements, including
most of the C library's API and its test harness.
[cmake]: http://www.cmake.org/download/
[pandoc]: http://johnmacfarlane.net/pandoc/
[re2c]: http://re2c.org

247
outside/commonmark/alternative-html-blocks.txt Normal file
View File

@ -0,0 +1,247 @@
# Appendix B: An alternate spec for HTML blocks {-}
(The following spec departs less from original markdown than the
one described above, but is also less flexible.)
An [HTML block](#html-block) <a id="html-block-tag"/> begins
with an [open tag](#open-tag), [HTML comment](#html-comment),
[processing instruction](#processing-instruction),
[declaration](#declaration), or [CDATA section](#cdata-section).
This opening element may optionally be preceded by 1-3 spaces,
and must not be followed on a line by anything other than white space.
If the opening tag is self-closing, or if it is an [HTML
comment](#html-comment), [processing
instruction](#processing-instruction), [declaration](#declaration), or
[CDATA section](#cdata-section), then the [HTML block](#html-block)
contains just that tag.
If it is an [open tag](#open-tag), then the [HTML block](#html-block)
continues until a matching closing tag is found, or until the end
of the document. Note that the matching closing tag is not necessarily
the first closing tag of the same type that is encountered, since
that tag may close a later open tag of the same type. Open and closing
tags must be balanced.
The contents of the HTML block are interpreted as raw HTML, and will not
be escaped in HTML output.
Some simple examples:
.
<table>
<tr>
<td>
hi
</td>
</tr>
</table>
okay.
.
<table>
<tr>
<td>
hi
</td>
</tr>
</table>
<p>okay.</p>
.
.
<div class="outer">
<div class="inner">
<p>foo&ouml;</p>
</div>
</div>
.
<div class="outer">
<div class="inner">
<p>foo&ouml;</p>
</div>
</div>
.
A self-closing tag:
.
<div />
.
<div />
.
Here we have an unclosed tag, and the block continues to the end of
the document:
.
<div>
<div>
foo
</div>
*bar*
.
<div>
<div>
foo
</div>
*bar*
.
A comment:
.
<!-- Foo
bar
baz -->
.
<!-- Foo
bar
baz -->
.
A processing instruction:
.
<?php
echo 'foo'
?>
.
<?php
echo 'foo'
?>
.
CDATA:
.
<![CDATA[
function matchwo(a,b)
{
if (a < b && a < 0) then
{
return 1;
}
else
{
return 0;
}
}
]]>
.
<![CDATA[
function matchwo(a,b)
{
if (a < b && a < 0) then
{
return 1;
}
else
{
return 0;
}
}
]]>
.
The opening tag can be indented 1-3 spaces, but not 4:
.
<!-- foo -->
<!-- foo -->
.
<!-- foo -->
<pre><code>&lt;!-- foo --&gt;
</code></pre>
.
The opening tag must be on a line (or lines) by itself:
.
<table><tr><td>
foo
</td></tr></table>
.
<p><table><tr<td> foo </td></tr></table></p>
.
.
<!-- foo -->bar
.
<p><!-- foo -->bar</p>
.
The opening tag need not be an HTML block tag or even an HTML tag:
.
<a>
foo
</a>
.
<a>
foo
</a>
.
.
<foo>
bar
</foo>
.
<foo>
bar
</foo>
.
So, note the difference:
.
<del>
bar
</del>
<del>bar</del>
.
<del>
bar
</del>
<p><del>bar</del></p>
.
This rule differs from John Gruber's original markdown syntax
specification, which says:
> The only restrictions are that block-level HTML elements —
> e.g. `<div>`, `<table>`, `<pre>`, `<p>`, etc. — must be separated from
> surrounding content by blank lines, and the start and end tags of the
> block should not be indented with tabs or spaces.
In some ways Gruber's rule is more restrictive than the one given
here:
- It requires that an HTML block be preceded and followed by a blank line.
- It does not allow the start tag to be indented.
- It does not allow the end tag to be indented.
- It does not require that the open tag be an HTML block-level tag.
Indeed, most markdown implementations, including some of Gruber's
own perl implementations, do not impose these restrictions.
However, unlike Gruber's rule, this one requires that the open
tag be on a line by itself. It also differs from most markdown
implementations in how it handles the case where there is no matching
closing tag (a case not mentioned in Gruber's rule). In such a case,
the rule stated above includes the whole rest of the document in the
HTML block.

25
outside/commonmark/api_test/CMakeLists.txt Normal file
View File

@ -0,0 +1,25 @@
add_executable(api_test
cplusplus.cpp
harness.c
harness.h
main.c
)
include_directories(
${PROJECT_SOURCE_DIR}/src
${PROJECT_BINARY_DIR}/src
)
target_link_libraries(api_test libcmark)
# Compiler flags
if(MSVC)
# Force to always compile with W4
if(CMAKE_CXX_FLAGS MATCHES "/W[0-4]")
string(REGEX REPLACE "/W[0-4]" "/W4" CMAKE_C_FLAGS "${CMAKE_C_FLAGS}")
else()
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} /W4")
endif()
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} /wd4127 /wd4244 /wd4267 /wd4706 /wd4800 /D_CRT_SECURE_NO_WARNINGS")
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} /TP")
elseif(CMAKE_COMPILER_IS_GNUCC OR "${CMAKE_CXX_COMPILER_ID}" STREQUAL "Clang")
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -Wall -std=c99 -pedantic")
endif()

15
outside/commonmark/api_test/cplusplus.cpp Normal file
View File

@ -0,0 +1,15 @@
#include <cstdlib>
#include "cmark.h"
#include "harness.h"
extern "C" void
test_cplusplus(test_batch_runner *runner)
{
static const char md[] = "paragraph\n";
char *html = cmark_markdown_to_html(md, sizeof(md) - 1);
STR_EQ(runner, html, "<p>paragraph</p>\n", "libcmark works with C++");
free(html);
}

102
outside/commonmark/api_test/harness.c Normal file
View File

@ -0,0 +1,102 @@
#include <stdarg.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include "harness.h"
test_batch_runner*
test_batch_runner_new()
{
return (test_batch_runner *)calloc(1, sizeof(test_batch_runner));
}
static void
test_result(test_batch_runner *runner, int cond, const char *msg, va_list ap)
{
++runner->test_num;
if (cond) {
++runner->num_passed;
}
else {
fprintf(stderr, "FAILED test %d: ", runner->test_num);
vfprintf(stderr, msg, ap);
fprintf(stderr, "\n");
++runner->num_failed;
}
}
void
SKIP(test_batch_runner *runner, int num_tests)
{
runner->test_num += num_tests;
runner->num_skipped += num_tests;
}
void
OK(test_batch_runner *runner, int cond, const char *msg, ...)
{
va_list ap;
va_start(ap, msg);
test_result(runner, cond, msg, ap);
va_end(ap);
}
void
INT_EQ(test_batch_runner *runner, int got, int expected, const char *msg, ...)
{
int cond = got == expected;
va_list ap;
va_start(ap, msg);
test_result(runner, cond, msg, ap);
va_end(ap);
if (!cond) {
fprintf(stderr, " Got: %d\n", got);
fprintf(stderr, " Expected: %d\n", expected);
}
}
void
STR_EQ(test_batch_runner *runner, const char *got, const char *expected,
const char *msg, ...)
{
int cond = strcmp(got, expected) == 0;
va_list ap;
va_start(ap, msg);
test_result(runner, cond, msg, ap);
va_end(ap);
if (!cond) {
fprintf(stderr, " Got: \"%s\"\n", got);
fprintf(stderr, " Expected: \"%s\"\n", expected);
}
}
int
test_ok(test_batch_runner *runner)
{
return runner->num_failed == 0;
}
void
test_print_summary(test_batch_runner *runner)
{
int num_passed = runner->num_passed;
int num_skipped = runner->num_skipped;
int num_failed = runner->num_failed;
fprintf(stderr, "%d tests passed, %d failed, %d skipped\n",
num_passed, num_failed, num_skipped);
if (test_ok(runner)) {
fprintf(stderr, "PASS\n");
}
else {
fprintf(stderr, "FAIL\n");
}
}

42
outside/commonmark/api_test/harness.h Normal file
View File

@ -0,0 +1,42 @@
#ifndef CMARK_API_TEST_HARNESS_H
#define CMARK_API_TEST_HARNESS_H
#ifdef __cplusplus
extern "C" {
#endif
typedef struct {
int test_num;
int num_passed;
int num_failed;
int num_skipped;
} test_batch_runner;
test_batch_runner*
test_batch_runner_new();
void
SKIP(test_batch_runner *runner, int num_tests);
void
OK(test_batch_runner *runner, int cond, const char *msg, ...);
void
INT_EQ(test_batch_runner *runner, int got, int expected, const char *msg, ...);
void
STR_EQ(test_batch_runner *runner, const char *got, const char *expected,
const char *msg, ...);
int
test_ok(test_batch_runner *runner);
void
test_print_summary(test_batch_runner *runner);
#ifdef __cplusplus
}
#endif
#endif

622
outside/commonmark/api_test/main.c Normal file
View File

@ -0,0 +1,622 @@
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#define CMARK_NO_SHORT_NAMES
#include "cmark.h"
#include "node.h"
#include "harness.h"
#define UTF8_REPL "\xEF\xBF\xBD"
void
test_cplusplus(test_batch_runner *runner);
static const cmark_node_type node_types[] = {
CMARK_NODE_DOCUMENT,
CMARK_NODE_BLOCK_QUOTE,
CMARK_NODE_LIST,
CMARK_NODE_LIST_ITEM,
CMARK_NODE_CODE_BLOCK,
CMARK_NODE_HTML,
CMARK_NODE_PARAGRAPH,
CMARK_NODE_HEADER,
CMARK_NODE_HRULE,
CMARK_NODE_REFERENCE_DEF,
CMARK_NODE_TEXT,
CMARK_NODE_SOFTBREAK,
CMARK_NODE_LINEBREAK,
CMARK_NODE_INLINE_CODE,
CMARK_NODE_INLINE_HTML,
CMARK_NODE_EMPH,
CMARK_NODE_STRONG,
CMARK_NODE_LINK,
CMARK_NODE_IMAGE
};
static const int num_node_types = sizeof(node_types) / sizeof(*node_types);
static void
test_md_to_html(test_batch_runner *runner, const char *markdown,
const char *expected_html, const char *msg);
static void
test_content(test_batch_runner *runner, cmark_node_type type,
int allowed_content);
static void
test_char(test_batch_runner *runner, int valid, const char *utf8,
const char *msg);
static void
test_incomplete_char(test_batch_runner *runner, const char *utf8,
const char *msg);
static void
test_continuation_byte(test_batch_runner *runner, const char *utf8);
static void
constructor(test_batch_runner *runner)
{
for (int i = 0; i < num_node_types; ++i) {
cmark_node_type type = node_types[i];
cmark_node *node = cmark_node_new(type);
OK(runner, node != NULL, "new type %d", type);
INT_EQ(runner, cmark_node_get_type(node), type,
"get_type %d", type);
switch (node->type) {
case CMARK_NODE_HEADER:
INT_EQ(runner, cmark_node_get_header_level(node), 1,
"default header level is 1");
node->as.header.level = 1;
break;
case CMARK_NODE_LIST:
INT_EQ(runner, cmark_node_get_list_type(node),
CMARK_BULLET_LIST,
"default is list type is bullet");
INT_EQ(runner, cmark_node_get_list_start(node), 1,
"default is list start is 1");
INT_EQ(runner, cmark_node_get_list_tight(node), 0,
"default is list is loose");
break;
default:
break;
}
cmark_node_free(node);
}
}
static void
accessors(test_batch_runner *runner)
{
static const char markdown[] =
"## Header\n"
"\n"
"* Item 1\n"
"* Item 2\n"
"\n"
"2. Item 1\n"
"\n"
"3. Item 2\n"
"\n"
"\n"
" code\n"
"\n"
"``` lang\n"
"fenced\n"
"```\n"
"\n"
"<div>html</div>\n"
"\n"
"[link](url 'title')\n";
cmark_node *doc = cmark_parse_document(markdown, sizeof(markdown) - 1);
// Getters
cmark_node *header = cmark_node_first_child(doc);
INT_EQ(runner, cmark_node_get_header_level(header), 2,
"get_header_level");
cmark_node *bullet_list = cmark_node_next(header);
INT_EQ(runner, cmark_node_get_list_type(bullet_list),
CMARK_BULLET_LIST, "get_list_type bullet");
INT_EQ(runner, cmark_node_get_list_tight(bullet_list), 1,
"get_list_tight tight");
cmark_node *ordered_list = cmark_node_next(bullet_list);
INT_EQ(runner, cmark_node_get_list_type(ordered_list),
CMARK_ORDERED_LIST, "get_list_type ordered");
INT_EQ(runner, cmark_node_get_list_start(ordered_list), 2,
"get_list_start");
INT_EQ(runner, cmark_node_get_list_tight(ordered_list), 0,
"get_list_tight loose");
cmark_node *code = cmark_node_next(ordered_list);
STR_EQ(runner, cmark_node_get_string_content(code), "code\n",
"get_string_content indented code");
cmark_node *fenced = cmark_node_next(code);
STR_EQ(runner, cmark_node_get_string_content(fenced), "fenced\n",
"get_string_content fenced code");
STR_EQ(runner, cmark_node_get_fence_info(fenced), "lang",
"get_fence_info");
cmark_node *html = cmark_node_next(fenced);
STR_EQ(runner, cmark_node_get_string_content(html),
"<div>html</div>\n", "get_string_content html");
cmark_node *paragraph = cmark_node_next(html);
INT_EQ(runner, cmark_node_get_start_line(paragraph), 19,
"get_start_line");
INT_EQ(runner, cmark_node_get_start_column(paragraph), 1,
"get_start_column");
INT_EQ(runner, cmark_node_get_end_line(paragraph), 19,
"get_end_line");
cmark_node *link = cmark_node_first_child(paragraph);
STR_EQ(runner, cmark_node_get_url(link), "url",
"get_url");
STR_EQ(runner, cmark_node_get_title(link), "title",
"get_title");
cmark_node *string = cmark_node_first_child(link);
STR_EQ(runner, cmark_node_get_string_content(string), "link",
"get_string_content string");
// Setters
OK(runner, cmark_node_set_header_level(header, 3),
"set_header_level");
OK(runner, cmark_node_set_list_type(bullet_list, CMARK_ORDERED_LIST),
"set_list_type ordered");
OK(runner, cmark_node_set_list_start(bullet_list, 3),
"set_list_start");
OK(runner, cmark_node_set_list_tight(bullet_list, 0),
"set_list_tight loose");
OK(runner, cmark_node_set_list_type(ordered_list, CMARK_BULLET_LIST),
"set_list_type bullet");
OK(runner, cmark_node_set_list_tight(ordered_list, 1),
"set_list_tight tight");
OK(runner, cmark_node_set_string_content(code, "CODE\n"),
"set_string_content indented code");
OK(runner, cmark_node_set_string_content(fenced, "FENCED\n"),
"set_string_content fenced code");
OK(runner, cmark_node_set_fence_info(fenced, "LANG"),
"set_fence_info");
OK(runner, cmark_node_set_string_content(html, "<div>HTML</div>\n"),
"set_string_content html");
OK(runner, cmark_node_set_url(link, "URL"),
"set_url");
OK(runner, cmark_node_set_title(link, "TITLE"),
"set_title");
OK(runner, cmark_node_set_string_content(string, "LINK"),
"set_string_content string");
char *rendered_html = cmark_render_html(doc);
static const char expected_html[] =
"<h3>Header</h3>\n"
"<ol start=\"3\">\n"
"<li>\n"
"<p>Item 1</p>\n"
"</li>\n"
"<li>\n"
"<p>Item 2</p>\n"
"</li>\n"
"</ol>\n"
"<ul>\n"
"<li>Item 1</li>\n"
"<li>Item 2</li>\n"
"</ul>\n"
"<pre><code>CODE\n"
"</code></pre>\n"
"<pre><code class=\"language-LANG\">FENCED\n"
"</code></pre>\n"
"<div>HTML</div>\n"
"<p><a href=\"URL\" title=\"TITLE\">LINK</a></p>\n";
STR_EQ(runner, rendered_html, expected_html, "setters work");
free(rendered_html);
// Getter errors
INT_EQ(runner, cmark_node_get_header_level(bullet_list), 0,
"get_header_level error");
INT_EQ(runner, cmark_node_get_list_type(header), CMARK_NO_LIST,
"get_list_type error");
INT_EQ(runner, cmark_node_get_list_start(code), 0,
"get_list_start error");
INT_EQ(runner, cmark_node_get_list_tight(fenced), 0,
"get_list_tight error");
OK(runner, cmark_node_get_string_content(ordered_list) == NULL,
"get_string_content error");
OK(runner, cmark_node_get_fence_info(paragraph) == NULL,
"get_fence_info error");
OK(runner, cmark_node_get_url(html) == NULL,
"get_url error");
OK(runner, cmark_node_get_title(header) == NULL,
"get_title error");
// Setter errors
OK(runner, !cmark_node_set_header_level(bullet_list, 3),
"set_header_level error");
OK(runner, !cmark_node_set_list_type(header, CMARK_ORDERED_LIST),
"set_list_type error");
OK(runner, !cmark_node_set_list_start(code, 3),
"set_list_start error");
OK(runner, !cmark_node_set_list_tight(fenced, 0),
"set_list_tight error");
OK(runner, !cmark_node_set_string_content(ordered_list, "content\n"),
"set_string_content error");
OK(runner, !cmark_node_set_fence_info(paragraph, "lang"),
"set_fence_info error");
OK(runner, !cmark_node_set_url(html, "url"),
"set_url error");
OK(runner, !cmark_node_set_title(header, "title"),
"set_title error");
OK(runner, !cmark_node_set_header_level(header, 0),
"set_header_level too small");
OK(runner, !cmark_node_set_header_level(header, 7),
"set_header_level too large");
OK(runner, !cmark_node_set_list_type(bullet_list, CMARK_NO_LIST),
"set_list_type invalid");
OK(runner, !cmark_node_set_list_start(bullet_list, -1),
"set_list_start negative");
cmark_node_free(doc);
}
static void
node_check(test_batch_runner *runner) {
// Construct an incomplete tree.
cmark_node *doc = cmark_node_new(CMARK_NODE_DOCUMENT);
cmark_node *p1 = cmark_node_new(CMARK_NODE_PARAGRAPH);
cmark_node *p2 = cmark_node_new(CMARK_NODE_PARAGRAPH);
doc->first_child = p1;
p1->next = p2;
INT_EQ(runner, cmark_node_check(doc, NULL), 4, "node_check works");
INT_EQ(runner, cmark_node_check(doc, NULL), 0,
"node_check fixes tree");
cmark_node_free(doc);
}
static void
create_tree(test_batch_runner *runner)
{
char *html;
cmark_node *doc = cmark_node_new(CMARK_NODE_DOCUMENT);
cmark_node *p = cmark_node_new(CMARK_NODE_PARAGRAPH);
OK(runner, !cmark_node_insert_before(doc, p),
"insert before root fails");
OK(runner, !cmark_node_insert_after(doc, p),
"insert after root fails");
OK(runner, cmark_node_append_child(doc, p), "append1");
INT_EQ(runner, cmark_node_check(doc, NULL), 0, "append1 consistent");
OK(runner, cmark_node_parent(p) == doc, "node_parent");
cmark_node *emph = cmark_node_new(CMARK_NODE_EMPH);
OK(runner, cmark_node_prepend_child(p, emph), "prepend1");
INT_EQ(runner, cmark_node_check(doc, NULL), 0, "prepend1 consistent");
cmark_node *str1 = cmark_node_new(CMARK_NODE_TEXT);
cmark_node_set_string_content(str1, "Hello, ");
OK(runner, cmark_node_prepend_child(p, str1), "prepend2");
INT_EQ(runner, cmark_node_check(doc, NULL), 0, "prepend2 consistent");
cmark_node *str3 = cmark_node_new(CMARK_NODE_TEXT);
cmark_node_set_string_content(str3, "!");
OK(runner, cmark_node_append_child(p, str3), "append2");
INT_EQ(runner, cmark_node_check(doc, NULL), 0, "append2 consistent");
cmark_node *str2 = cmark_node_new(CMARK_NODE_TEXT);
cmark_node_set_string_content(str2, "world");
OK(runner, cmark_node_append_child(emph, str2), "append3");
INT_EQ(runner, cmark_node_check(doc, NULL), 0, "append3 consistent");
html = cmark_render_html(doc);
STR_EQ(runner, html, "<p>Hello, <em>world</em>!</p>\n",
"render_html");
free(html);
OK(runner, cmark_node_insert_before(str1, str3), "ins before1");
INT_EQ(runner, cmark_node_check(doc, NULL), 0,
"ins before1 consistent");
// 31e
OK(runner, cmark_node_first_child(p) == str3, "ins before1 works");
OK(runner, cmark_node_insert_before(str1, emph), "ins before2");
INT_EQ(runner, cmark_node_check(doc, NULL), 0,
"ins before2 consistent");
// 3e1
OK(runner, cmark_node_last_child(p) == str1, "ins before2 works");
OK(runner, cmark_node_insert_after(str1, str3), "ins after1");
INT_EQ(runner, cmark_node_check(doc, NULL), 0,
"ins after1 consistent");
// e13
OK(runner, cmark_node_next(str1) == str3, "ins after1 works");
OK(runner, cmark_node_insert_after(str1, emph), "ins after2");
INT_EQ(runner, cmark_node_check(doc, NULL), 0,
"ins after2 consistent");
// 1e3
OK(runner, cmark_node_previous(emph) == str1, "ins after2 works");
cmark_node_unlink(emph);
html = cmark_render_html(doc);
STR_EQ(runner, html, "<p>Hello, !</p>\n",
"render_html after shuffling");
free(html);
cmark_node_free(doc);
// TODO: Test that the contents of an unlinked inline are valid
// after the parent block was destroyed. This doesn't work so far.
cmark_node_free(emph);
}
void
hierarchy(test_batch_runner *runner)
{
cmark_node *bquote1 = cmark_node_new(CMARK_NODE_BLOCK_QUOTE);
cmark_node *bquote2 = cmark_node_new(CMARK_NODE_BLOCK_QUOTE);
cmark_node *bquote3 = cmark_node_new(CMARK_NODE_BLOCK_QUOTE);
OK(runner, cmark_node_append_child(bquote1, bquote2),
"append bquote2");
OK(runner, cmark_node_append_child(bquote2, bquote3),
"append bquote3");
OK(runner, !cmark_node_append_child(bquote3, bquote3),
"adding a node as child of itself fails");
OK(runner, !cmark_node_append_child(bquote3, bquote1),
"adding a parent as child fails");
cmark_node_free(bquote1);
int max_node_type = CMARK_NODE_LAST_BLOCK > CMARK_NODE_LAST_INLINE
? CMARK_NODE_LAST_BLOCK : CMARK_NODE_LAST_INLINE;
OK(runner, max_node_type < 32, "all node types < 32");
int list_item_flag = 1 << CMARK_NODE_LIST_ITEM;
int top_level_blocks =
(1 << CMARK_NODE_BLOCK_QUOTE) |
(1 << CMARK_NODE_LIST) |
(1 << CMARK_NODE_CODE_BLOCK) |
(1 << CMARK_NODE_HTML) |
(1 << CMARK_NODE_PARAGRAPH) |
(1 << CMARK_NODE_HEADER) |
(1 << CMARK_NODE_HRULE) |
(1 << CMARK_NODE_REFERENCE_DEF);
int all_inlines =
(1 << CMARK_NODE_TEXT) |
(1 << CMARK_NODE_SOFTBREAK) |
(1 << CMARK_NODE_LINEBREAK) |
(1 << CMARK_NODE_INLINE_CODE) |
(1 << CMARK_NODE_INLINE_HTML) |
(1 << CMARK_NODE_EMPH) |
(1 << CMARK_NODE_STRONG) |
(1 << CMARK_NODE_LINK) |
(1 << CMARK_NODE_IMAGE);
test_content(runner, CMARK_NODE_DOCUMENT, top_level_blocks);
test_content(runner, CMARK_NODE_BLOCK_QUOTE, top_level_blocks);
test_content(runner, CMARK_NODE_LIST, list_item_flag);
test_content(runner, CMARK_NODE_LIST_ITEM, top_level_blocks);
test_content(runner, CMARK_NODE_CODE_BLOCK , 0);
test_content(runner, CMARK_NODE_HTML, 0);
test_content(runner, CMARK_NODE_PARAGRAPH, all_inlines);
test_content(runner, CMARK_NODE_HEADER, all_inlines);
test_content(runner, CMARK_NODE_HRULE, 0);
test_content(runner, CMARK_NODE_REFERENCE_DEF, 0);
test_content(runner, CMARK_NODE_TEXT, 0);
test_content(runner, CMARK_NODE_SOFTBREAK, 0);
test_content(runner, CMARK_NODE_LINEBREAK, 0);
test_content(runner, CMARK_NODE_INLINE_CODE, 0);
test_content(runner, CMARK_NODE_INLINE_HTML, 0);
test_content(runner, CMARK_NODE_EMPH, all_inlines);
test_content(runner, CMARK_NODE_STRONG, all_inlines);
test_content(runner, CMARK_NODE_LINK, all_inlines);
test_content(runner, CMARK_NODE_IMAGE, all_inlines);
}
static void
test_content(test_batch_runner *runner, cmark_node_type type,
int allowed_content)
{
cmark_node *node = cmark_node_new(type);
for (int i = 0; i < num_node_types; ++i) {
cmark_node_type child_type = node_types[i];
cmark_node *child = cmark_node_new(child_type);
int got = cmark_node_append_child(node, child);
int expected = (allowed_content >> child_type) & 1;
INT_EQ(runner, got, expected,
"add %d as child of %d", child_type, type);
cmark_node_free(child);
}
cmark_node_free(node);
}
static void
parser(test_batch_runner *runner)
{
test_md_to_html(runner, "No newline", "<p>No newline</p>\n",
"document without trailing newline");
}
static void
render_html(test_batch_runner *runner)
{
char *html;
static const char markdown[] =
"foo *bar*\n"
"\n"
"paragraph 2\n";
cmark_node *doc = cmark_parse_document(markdown, sizeof(markdown) - 1);
cmark_node *paragraph = cmark_node_first_child(doc);
html = cmark_render_html(paragraph);
STR_EQ(runner, html, "<p>foo <em>bar</em></p>\n",
"render single paragraph");
free(html);
cmark_node *string = cmark_node_first_child(paragraph);
html = cmark_render_html(string);
STR_EQ(runner, html, "foo ", "render single inline");
free(html);
cmark_node *emph = cmark_node_next(string);
html = cmark_render_html(emph);
STR_EQ(runner, html, "<em>bar</em>", "render inline with children");
free(html);
cmark_node_free(doc);
}
static void
utf8(test_batch_runner *runner)
{
// Ranges
test_char(runner, 1, "\x01", "valid utf8 01");
test_char(runner, 1, "\x7F", "valid utf8 7F");
test_char(runner, 0, "\x80", "invalid utf8 80");
test_char(runner, 0, "\xBF", "invalid utf8 BF");
test_char(runner, 0, "\xC0\x80", "invalid utf8 C080");
test_char(runner, 0, "\xC1\xBF", "invalid utf8 C1BF");
test_char(runner, 1, "\xC2\x80", "valid utf8 C280");
test_char(runner, 1, "\xDF\xBF", "valid utf8 DFBF");
test_char(runner, 0, "\xE0\x80\x80", "invalid utf8 E08080");
test_char(runner, 0, "\xE0\x9F\xBF", "invalid utf8 E09FBF");
test_char(runner, 1, "\xE0\xA0\x80", "valid utf8 E0A080");
test_char(runner, 1, "\xED\x9F\xBF", "valid utf8 ED9FBF");
test_char(runner, 0, "\xED\xA0\x80", "invalid utf8 EDA080");
test_char(runner, 0, "\xED\xBF\xBF", "invalid utf8 EDBFBF");
test_char(runner, 0, "\xF0\x80\x80\x80", "invalid utf8 F0808080");
test_char(runner, 0, "\xF0\x8F\xBF\xBF", "invalid utf8 F08FBFBF");
test_char(runner, 1, "\xF0\x90\x80\x80", "valid utf8 F0908080");
test_char(runner, 1, "\xF4\x8F\xBF\xBF", "valid utf8 F48FBFBF");
test_char(runner, 0, "\xF4\x90\x80\x80", "invalid utf8 F4908080");
test_char(runner, 0, "\xF7\xBF\xBF\xBF", "invalid utf8 F7BFBFBF");
test_char(runner, 0, "\xF8", "invalid utf8 F8");
test_char(runner, 0, "\xFF", "invalid utf8 FF");
// Incomplete byte sequences at end of input
test_incomplete_char(runner, "\xE0\xA0", "invalid utf8 E0A0");
test_incomplete_char(runner, "\xF0\x90\x80", "invalid utf8 F09080");
// Invalid continuation bytes
test_continuation_byte(runner, "\xC2\x80");
test_continuation_byte(runner, "\xE0\xA0\x80");
test_continuation_byte(runner, "\xF0\x90\x80\x80");
// Test string containing null character
static const char string_with_null[] = "((((\0))))";
char *html = cmark_markdown_to_html(string_with_null,
sizeof(string_with_null) - 1);
STR_EQ(runner, html, "<p>((((" UTF8_REPL "))))</p>\n",
"utf8 with U+0000");
free(html);
}
static void
test_char(test_batch_runner *runner, int valid, const char *utf8,
const char *msg)
{
char buf[20];
sprintf(buf, "((((%s))))", utf8);
if (valid) {
char expected[30];
sprintf(expected, "<p>((((%s))))</p>\n", utf8);
test_md_to_html(runner, buf, expected, msg);
}
else {
test_md_to_html(runner, buf, "<p>((((" UTF8_REPL "))))</p>\n",
msg);
}
}
static void
test_incomplete_char(test_batch_runner *runner, const char *utf8,
const char *msg)
{
char buf[20];
sprintf(buf, "----%s", utf8);
test_md_to_html(runner, buf, "<p>----" UTF8_REPL "</p>\n", msg);
}
static void
test_continuation_byte(test_batch_runner *runner, const char *utf8)
{
int len = strlen(utf8);
for (int pos = 1; pos < len; ++pos) {
char buf[20];
sprintf(buf, "((((%s))))", utf8);
buf[4+pos] = '\x20';
char expected[50];
strcpy(expected, "<p>((((" UTF8_REPL "\x20");
for (int i = pos + 1; i < len; ++i) {
strcat(expected, UTF8_REPL);
}
strcat(expected, "))))</p>\n");
char *html = cmark_markdown_to_html(buf, strlen(buf));
STR_EQ(runner, html, expected,
"invalid utf8 continuation byte %d/%d", pos, len);
free(html);
}
}
static void
test_md_to_html(test_batch_runner *runner, const char *markdown,
const char *expected_html, const char *msg)
{
char *html = cmark_markdown_to_html(markdown, strlen(markdown));
STR_EQ(runner, html, expected_html, msg);
free(html);
}
int main() {
int retval;
test_batch_runner *runner = test_batch_runner_new();
constructor(runner);
accessors(runner);
node_check(runner);
create_tree(runner);
hierarchy(runner);
parser(runner);
render_html(runner);
utf8(runner);
test_cplusplus(runner);
test_print_summary(runner);
retval = test_ok(runner) ? 0 : 1;
free(runner);
return retval;
}

595
outside/commonmark/bench/statistics.py Normal file
View File

@ -0,0 +1,595 @@
## Module statistics.py
##
## Copyright (c) 2013 Steven D'Aprano <steve+python@pearwood.info>.
##
## Licensed under the Apache License, Version 2.0 (the "License");
## you may not use this file except in compliance with the License.
## You may obtain a copy of the License at
##
## http://www.apache.org/licenses/LICENSE-2.0
##
## Unless required by applicable law or agreed to in writing, software
## distributed under the License is distributed on an "AS IS" BASIS,
## WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
## See the License for the specific language governing permissions and
## limitations under the License.
"""
Basic statistics module.
This module provides functions for calculating statistics of data, including
averages, variance, and standard deviation.
Calculating averages
--------------------
================== =============================================
Function Description
================== =============================================
mean Arithmetic mean (average) of data.
median Median (middle value) of data.
median_low Low median of data.
median_high High median of data.
median_grouped Median, or 50th percentile, of grouped data.
mode Mode (most common value) of data.
================== =============================================
Calculate the arithmetic mean ("the average") of data:
>>> mean([-1.0, 2.5, 3.25, 5.75])
2.625
Calculate the standard median of discrete data:
>>> median([2, 3, 4, 5])
3.5
Calculate the median, or 50th percentile, of data grouped into class intervals
centred on the data values provided. E.g. if your data points are rounded to
the nearest whole number:
>>> median_grouped([2, 2, 3, 3, 3, 4]) #doctest: +ELLIPSIS
2.8333333333...
This should be interpreted in this way: you have two data points in the class
interval 1.5-2.5, three data points in the class interval 2.5-3.5, and one in
the class interval 3.5-4.5. The median of these data points is 2.8333...
Calculating variability or spread
---------------------------------
================== =============================================
Function Description
================== =============================================
pvariance Population variance of data.
variance Sample variance of data.
pstdev Population standard deviation of data.
stdev Sample standard deviation of data.
================== =============================================
Calculate the standard deviation of sample data:
>>> stdev([2.5, 3.25, 5.5, 11.25, 11.75]) #doctest: +ELLIPSIS
4.38961843444...
If you have previously calculated the mean, you can pass it as the optional
second argument to the four "spread" functions to avoid recalculating it:
>>> data = [1, 2, 2, 4, 4, 4, 5, 6]
>>> mu = mean(data)
>>> pvariance(data, mu)
2.5
Exceptions
----------
A single exception is defined: StatisticsError is a subclass of ValueError.
"""
__all__ = [ 'StatisticsError',
'pstdev', 'pvariance', 'stdev', 'variance',
'median', 'median_low', 'median_high', 'median_grouped',
'mean', 'mode',
]
import collections
import math
from fractions import Fraction
from decimal import Decimal
# === Exceptions ===
class StatisticsError(ValueError):
pass
# === Private utilities ===
def _sum(data, start=0):
"""_sum(data [, start]) -> value
Return a high-precision sum of the given numeric data. If optional
argument ``start`` is given, it is added to the total. If ``data`` is
empty, ``start`` (defaulting to 0) is returned.
Examples
--------
>>> _sum([3, 2.25, 4.5, -0.5, 1.0], 0.75)
11.0
Some sources of round-off error will be avoided:
>>> _sum([1e50, 1, -1e50] * 1000) # Built-in sum returns zero.
1000.0
Fractions and Decimals are also supported:
>>> from fractions import Fraction as F
>>> _sum([F(2, 3), F(7, 5), F(1, 4), F(5, 6)])
Fraction(63, 20)
>>> from decimal import Decimal as D
>>> data = [D("0.1375"), D("0.2108"), D("0.3061"), D("0.0419")]
>>> _sum(data)
Decimal('0.6963')
Mixed types are currently treated as an error, except that int is
allowed.
"""
# We fail as soon as we reach a value that is not an int or the type of
# the first value which is not an int. E.g. _sum([int, int, float, int])
# is okay, but sum([int, int, float, Fraction]) is not.
allowed_types = set([int, type(start)])
n, d = _exact_ratio(start)
partials = {d: n} # map {denominator: sum of numerators}
# Micro-optimizations.
exact_ratio = _exact_ratio
partials_get = partials.get
# Add numerators for each denominator.
for x in data:
_check_type(type(x), allowed_types)
n, d = exact_ratio(x)
partials[d] = partials_get(d, 0) + n
# Find the expected result type. If allowed_types has only one item, it
# will be int; if it has two, use the one which isn't int.
assert len(allowed_types) in (1, 2)
if len(allowed_types) == 1:
assert allowed_types.pop() is int
T = int
else:
T = (allowed_types - set([int])).pop()
if None in partials:
assert issubclass(T, (float, Decimal))
assert not math.isfinite(partials[None])
return T(partials[None])
total = Fraction()
for d, n in sorted(partials.items()):
total += Fraction(n, d)
if issubclass(T, int):
assert total.denominator == 1
return T(total.numerator)
if issubclass(T, Decimal):
return T(total.numerator)/total.denominator
return T(total)
def _check_type(T, allowed):
if T not in allowed:
if len(allowed) == 1:
allowed.add(T)
else:
types = ', '.join([t.__name__ for t in allowed] + [T.__name__])
raise TypeError("unsupported mixed types: %s" % types)
def _exact_ratio(x):
"""Convert Real number x exactly to (numerator, denominator) pair.
>>> _exact_ratio(0.25)
(1, 4)
x is expected to be an int, Fraction, Decimal or float.
"""
try:
try:
# int, Fraction
return (x.numerator, x.denominator)
except AttributeError:
# float
try:
return x.as_integer_ratio()
except AttributeError:
# Decimal
try:
return _decimal_to_ratio(x)
except AttributeError:
msg = "can't convert type '{}' to numerator/denominator"
raise TypeError(msg.format(type(x).__name__)) from None
except (OverflowError, ValueError):
# INF or NAN
if __debug__:
# Decimal signalling NANs cannot be converted to float :-(
if isinstance(x, Decimal):
assert not x.is_finite()
else:
assert not math.isfinite(x)
return (x, None)
# FIXME This is faster than Fraction.from_decimal, but still too slow.
def _decimal_to_ratio(d):
"""Convert Decimal d to exact integer ratio (numerator, denominator).
>>> from decimal import Decimal
>>> _decimal_to_ratio(Decimal("2.6"))
(26, 10)
"""
sign, digits, exp = d.as_tuple()
if exp in ('F', 'n', 'N'): # INF, NAN, sNAN
assert not d.is_finite()
raise ValueError
num = 0
for digit in digits:
num = num*10 + digit
if exp < 0:
den = 10**-exp
else:
num *= 10**exp
den = 1
if sign:
num = -num
return (num, den)
def _counts(data):
# Generate a table of sorted (value, frequency) pairs.
table = collections.Counter(iter(data)).most_common()
if not table:
return table
# Extract the values with the highest frequency.
maxfreq = table[0][1]
for i in range(1, len(table)):
if table[i][1] != maxfreq:
table = table[:i]
break
return table
# === Measures of central tendency (averages) ===
def mean(data):
"""Return the sample arithmetic mean of data.
>>> mean([1, 2, 3, 4, 4])
2.8
>>> from fractions import Fraction as F
>>> mean([F(3, 7), F(1, 21), F(5, 3), F(1, 3)])
Fraction(13, 21)
>>> from decimal import Decimal as D
>>> mean([D("0.5"), D("0.75"), D("0.625"), D("0.375")])
Decimal('0.5625')
If ``data`` is empty, StatisticsError will be raised.
"""
if iter(data) is data:
data = list(data)
n = len(data)
if n < 1:
raise StatisticsError('mean requires at least one data point')
return _sum(data)/n
# FIXME: investigate ways to calculate medians without sorting? Quickselect?
def median(data):
"""Return the median (middle value) of numeric data.
When the number of data points is odd, return the middle data point.
When the number of data points is even, the median is interpolated by
taking the average of the two middle values:
>>> median([1, 3, 5])
3
>>> median([1, 3, 5, 7])
4.0
"""
data = sorted(data)
n = len(data)
if n == 0:
raise StatisticsError("no median for empty data")
if n%2 == 1:
return data[n//2]
else:
i = n//2
return (data[i - 1] + data[i])/2
def median_low(data):
"""Return the low median of numeric data.
When the number of data points is odd, the middle value is returned.
When it is even, the smaller of the two middle values is returned.
>>> median_low([1, 3, 5])
3
>>> median_low([1, 3, 5, 7])
3
"""
data = sorted(data)
n = len(data)
if n == 0:
raise StatisticsError("no median for empty data")
if n%2 == 1:
return data[n//2]
else:
return data[n//2 - 1]
def median_high(data):
"""Return the high median of data.
When the number of data points is odd, the middle value is returned.
When it is even, the larger of the two middle values is returned.
>>> median_high([1, 3, 5])
3
>>> median_high([1, 3, 5, 7])
5
"""
data = sorted(data)
n = len(data)
if n == 0:
raise StatisticsError("no median for empty data")
return data[n//2]
def median_grouped(data, interval=1):
""""Return the 50th percentile (median) of grouped continuous data.
>>> median_grouped([1, 2, 2, 3, 4, 4, 4, 4, 4, 5])
3.7
>>> median_grouped([52, 52, 53, 54])
52.5
This calculates the median as the 50th percentile, and should be
used when your data is continuous and grouped. In the above example,
the values 1, 2, 3, etc. actually represent the midpoint of classes
0.5-1.5, 1.5-2.5, 2.5-3.5, etc. The middle value falls somewhere in
class 3.5-4.5, and interpolation is used to estimate it.
Optional argument ``interval`` represents the class interval, and
defaults to 1. Changing the class interval naturally will change the
interpolated 50th percentile value:
>>> median_grouped([1, 3, 3, 5, 7], interval=1)
3.25
>>> median_grouped([1, 3, 3, 5, 7], interval=2)
3.5
This function does not check whether the data points are at least
``interval`` apart.
"""
data = sorted(data)
n = len(data)
if n == 0:
raise StatisticsError("no median for empty data")
elif n == 1:
return data[0]
# Find the value at the midpoint. Remember this corresponds to the
# centre of the class interval.
x = data[n//2]
for obj in (x, interval):
if isinstance(obj, (str, bytes)):
raise TypeError('expected number but got %r' % obj)
try:
L = x - interval/2 # The lower limit of the median interval.
except TypeError:
# Mixed type. For now we just coerce to float.
L = float(x) - float(interval)/2
cf = data.index(x) # Number of values below the median interval.
# FIXME The following line could be more efficient for big lists.
f = data.count(x) # Number of data points in the median interval.
return L + interval*(n/2 - cf)/f
def mode(data):
"""Return the most common data point from discrete or nominal data.
``mode`` assumes discrete data, and returns a single value. This is the
standard treatment of the mode as commonly taught in schools:
>>> mode([1, 1, 2, 3, 3, 3, 3, 4])
3
This also works with nominal (non-numeric) data:
>>> mode(["red", "blue", "blue", "red", "green", "red", "red"])
'red'
If there is not exactly one most common value, ``mode`` will raise
StatisticsError.
"""
# Generate a table of sorted (value, frequency) pairs.
table = _counts(data)
if len(table) == 1:
return table[0][0]
elif table:
raise StatisticsError(
'no unique mode; found %d equally common values' % len(table)
)
else:
raise StatisticsError('no mode for empty data')
# === Measures of spread ===
# See http://mathworld.wolfram.com/Variance.html
# http://mathworld.wolfram.com/SampleVariance.html
# http://en.wikipedia.org/wiki/Algorithms_for_calculating_variance
#
# Under no circumstances use the so-called "computational formula for
# variance", as that is only suitable for hand calculations with a small
# amount of low-precision data. It has terrible numeric properties.
#
# See a comparison of three computational methods here:
# http://www.johndcook.com/blog/2008/09/26/comparing-three-methods-of-computing-standard-deviation/
def _ss(data, c=None):
"""Return sum of square deviations of sequence data.
If ``c`` is None, the mean is calculated in one pass, and the deviations
from the mean are calculated in a second pass. Otherwise, deviations are
calculated from ``c`` as given. Use the second case with care, as it can
lead to garbage results.
"""
if c is None:
c = mean(data)
ss = _sum((x-c)**2 for x in data)
# The following sum should mathematically equal zero, but due to rounding
# error may not.
ss -= _sum((x-c) for x in data)**2/len(data)
assert not ss < 0, 'negative sum of square deviations: %f' % ss
return ss
def variance(data, xbar=None):
"""Return the sample variance of data.
data should be an iterable of Real-valued numbers, with at least two
values. The optional argument xbar, if given, should be the mean of
the data. If it is missing or None, the mean is automatically calculated.
Use this function when your data is a sample from a population. To
calculate the variance from the entire population, see ``pvariance``.
Examples:
>>> data = [2.75, 1.75, 1.25, 0.25, 0.5, 1.25, 3.5]
>>> variance(data)
1.3720238095238095
If you have already calculated the mean of your data, you can pass it as
the optional second argument ``xbar`` to avoid recalculating it:
>>> m = mean(data)
>>> variance(data, m)
1.3720238095238095
This function does not check that ``xbar`` is actually the mean of
``data``. Giving arbitrary values for ``xbar`` may lead to invalid or
impossible results.
Decimals and Fractions are supported:
>>> from decimal import Decimal as D
>>> variance([D("27.5"), D("30.25"), D("30.25"), D("34.5"), D("41.75")])
Decimal('31.01875')
>>> from fractions import Fraction as F
>>> variance([F(1, 6), F(1, 2), F(5, 3)])
Fraction(67, 108)
"""
if iter(data) is data:
data = list(data)
n = len(data)
if n < 2:
raise StatisticsError('variance requires at least two data points')
ss = _ss(data, xbar)
return ss/(n-1)
def pvariance(data, mu=None):
"""Return the population variance of ``data``.
data should be an iterable of Real-valued numbers, with at least one
value. The optional argument mu, if given, should be the mean of
the data. If it is missing or None, the mean is automatically calculated.
Use this function to calculate the variance from the entire population.
To estimate the variance from a sample, the ``variance`` function is
usually a better choice.
Examples:
>>> data = [0.0, 0.25, 0.25, 1.25, 1.5, 1.75, 2.75, 3.25]
>>> pvariance(data)
1.25
If you have already calculated the mean of the data, you can pass it as
the optional second argument to avoid recalculating it:
>>> mu = mean(data)
>>> pvariance(data, mu)
1.25
This function does not check that ``mu`` is actually the mean of ``data``.
Giving arbitrary values for ``mu`` may lead to invalid or impossible
results.
Decimals and Fractions are supported:
>>> from decimal import Decimal as D
>>> pvariance([D("27.5"), D("30.25"), D("30.25"), D("34.5"), D("41.75")])
Decimal('24.815')
>>> from fractions import Fraction as F
>>> pvariance([F(1, 4), F(5, 4), F(1, 2)])
Fraction(13, 72)
"""
if iter(data) is data:
data = list(data)
n = len(data)
if n < 1:
raise StatisticsError('pvariance requires at least one data point')
ss = _ss(data, mu)
return ss/n
def stdev(data, xbar=None):
"""Return the square root of the sample variance.
See ``variance`` for arguments and other details.
>>> stdev([1.5, 2.5, 2.5, 2.75, 3.25, 4.75])
1.0810874155219827
"""
var = variance(data, xbar)
try:
return var.sqrt()
except AttributeError:
return math.sqrt(var)
def pstdev(data, mu=None):
"""Return the square root of the population variance.
See ``pvariance`` for arguments and other details.
>>> pstdev([1.5, 2.5, 2.5, 2.75, 3.25, 4.75])
0.986893273527251
"""
var = pvariance(data, mu)
try:
return var.sqrt()
except AttributeError:
return math.sqrt(var)

19
outside/commonmark/bench/stats.py Normal file
View File

@ -0,0 +1,19 @@
#!/usr/bin/env python3
import sys
import statistics
def pairs(l, n):
return zip(*[l[i::n] for i in range(n)])
# data comes in pairs:
# n - time for running the program with no input
# m - time for running it with the benchmark input
# we measure (m - n)
values = [ float(y) - float(x) for (x,y) in pairs(sys.stdin.readlines(),2)]
print("mean = %.4f, median = %.4f, stdev = %.4f" %
(statistics.mean(values), statistics.median(values),
statistics.stdev(values)))

33
outside/commonmark/benchmarks.md Normal file
View File

@ -0,0 +1,33 @@
# Benchmarks
Some benchmarks, run on an ancient Thinkpad running Intel Core 2 Duo at 2GHz.
|Implementation | Time (sec)| Factor |
|-------------------|-----------:|--------:|
| Markdown.pl | 2921.24 | 14606.2 |
| PHP markdown | 20.85 | 104.3 |
| kramdown | 20.83 | 104.1 |
| lunamark | 6.295 | 31.5 |
| cheapskate | 5.760 | 28.8 |
| peg-markdown | 5.450 | 27.3 |
| **commonmark.js** | 2.675 | 13.4 |
| marked | 1.855 | 9.3 |
| discount | 1.705 | 8.5 |
| **cmark** | 0.295 | 1.5 |
| sundown | 0.200 | 1.0 |
To run these benchmarks, use `make bench PROG=/path/to/program`.
The input text is a 10MB Markdown file built by concatenating 20 copies
of the Markdown source of the first edition of [*Pro
Git*](https://github.com/progit/progit/tree/master/en) by Scott Chacon.
`time` is used to measure execution speed. The reported
time is the *difference* between the time to run the program
with the benchmark input and the time to run it with no input.
(This procedure ensures that implementations in dynamic languages are
not prenalized by startup time.) A median of ten runs is taken. The
process is reniced to a high priority so that the system doesn't
interrupt runs.

10
outside/commonmark/changelog.spec Normal file
View File

@ -0,0 +1,10 @@
[since 0.12]
* Updated path of test program.
* Use terminology "plain textual content" instead of "string."
* Added condition that conforming parsers strip or replace NULL characters.
* Changed Example 196 to reflect the spec's rules. It should not be a loose
list as it has no blank lines.
* Adjusted semantically insignificant formatting of HTML output.
* Added example to spec of shortcut link with following space (#214).

912
outside/commonmark/data/CaseFolding-3.2.0.txt Normal file
View File

@ -0,0 +1,912 @@
# CaseFolding-3.2.0.txt
# Date: 2002-03-22,20:54:33 GMT [MD]
#
# Case Folding Properties
#
# This file is a supplement to the UnicodeData file.
# It provides a case folding mapping generated from the Unicode Character Database.
# If all characters are mapped according to the full mapping below, then
# case differences (according to UnicodeData.txt and SpecialCasing.txt)
# are eliminated.
#
# The data supports both implementations that require simple case foldings
# (where string lengths don't change), and implementations that allow full case folding
# (where string lengths may grow). Note that where they can be supported, the
# full case foldings are superior: for example, they allow "MASSE" and "Maße" to match.
#
# NOTE: case folding does not preserve normalization formats!
#
# For information on case folding, see
# UTR #21 Case Mappings, at http://www.unicode.org/unicode/reports/tr21/
#
# ================================================================================
# Format
# ================================================================================
# The entries in this file are in the following machine-readable format:
#
# <code>; <status>; <mapping>; # <name>
#
# The status field is:
# C: common case folding, common mappings shared by both simple and full mappings.
# F: full case folding, mappings that cause strings to grow in length. Multiple characters are separated by spaces.
# S: simple case folding, mappings to single characters where different from F.
# T: special case for uppercase I and dotted uppercase I
# - For non-Turkic languages, this mapping is normally not used.
# - For Turkic languages (tr, az), this mapping can be used instead of the normal mapping for these characters.
#
# Usage:
# A. To do a simple case folding, use the mappings with status C + S.
# B. To do a full case folding, use the mappings with status C + F.
#
# The mappings with status T can be used or omitted depending on the desired case-folding
# behavior. (The default option is to exclude them.)
#
# =================================================================
0041; C; 0061; # LATIN CAPITAL LETTER A
0042; C; 0062; # LATIN CAPITAL LETTER B
0043; C; 0063; # LATIN CAPITAL LETTER C
0044; C; 0064; # LATIN CAPITAL LETTER D
0045; C; 0065; # LATIN CAPITAL LETTER E
0046; C; 0066; # LATIN CAPITAL LETTER F
0047; C; 0067; # LATIN CAPITAL LETTER G
0048; C; 0068; # LATIN CAPITAL LETTER H
0049; C; 0069; # LATIN CAPITAL LETTER I
0049; T; 0131; # LATIN CAPITAL LETTER I
004A; C; 006A; # LATIN CAPITAL LETTER J
004B; C; 006B; # LATIN CAPITAL LETTER K
004C; C; 006C; # LATIN CAPITAL LETTER L
004D; C; 006D; # LATIN CAPITAL LETTER M
004E; C; 006E; # LATIN CAPITAL LETTER N
004F; C; 006F; # LATIN CAPITAL LETTER O
0050; C; 0070; # LATIN CAPITAL LETTER P
0051; C; 0071; # LATIN CAPITAL LETTER Q
0052; C; 0072; # LATIN CAPITAL LETTER R
0053; C; 0073; # LATIN CAPITAL LETTER S
0054; C; 0074; # LATIN CAPITAL LETTER T
0055; C; 0075; # LATIN CAPITAL LETTER U
0056; C; 0076; # LATIN CAPITAL LETTER V
0057; C; 0077; # LATIN CAPITAL LETTER W
0058; C; 0078; # LATIN CAPITAL LETTER X
0059; C; 0079; # LATIN CAPITAL LETTER Y
005A; C; 007A; # LATIN CAPITAL LETTER Z
00B5; C; 03BC; # MICRO SIGN
00C0; C; 00E0; # LATIN CAPITAL LETTER A WITH GRAVE
00C1; C; 00E1; # LATIN CAPITAL LETTER A WITH ACUTE
00C2; C; 00E2; # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
00C3; C; 00E3; # LATIN CAPITAL LETTER A WITH TILDE
00C4; C; 00E4; # LATIN CAPITAL LETTER A WITH DIAERESIS
00C5; C; 00E5; # LATIN CAPITAL LETTER A WITH RING ABOVE
00C6; C; 00E6; # LATIN CAPITAL LETTER AE
00C7; C; 00E7; # LATIN CAPITAL LETTER C WITH CEDILLA
00C8; C; 00E8; # LATIN CAPITAL LETTER E WITH GRAVE
00C9; C; 00E9; # LATIN CAPITAL LETTER E WITH ACUTE
00CA; C; 00EA; # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
00CB; C; 00EB; # LATIN CAPITAL LETTER E WITH DIAERESIS
00CC; C; 00EC; # LATIN CAPITAL LETTER I WITH GRAVE
00CD; C; 00ED; # LATIN CAPITAL LETTER I WITH ACUTE
00CE; C; 00EE; # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
00CF; C; 00EF; # LATIN CAPITAL LETTER I WITH DIAERESIS
00D0; C; 00F0; # LATIN CAPITAL LETTER ETH
00D1; C; 00F1; # LATIN CAPITAL LETTER N WITH TILDE
00D2; C; 00F2; # LATIN CAPITAL LETTER O WITH GRAVE
00D3; C; 00F3; # LATIN CAPITAL LETTER O WITH ACUTE
00D4; C; 00F4; # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
00D5; C; 00F5; # LATIN CAPITAL LETTER O WITH TILDE
00D6; C; 00F6; # LATIN CAPITAL LETTER O WITH DIAERESIS
00D8; C; 00F8; # LATIN CAPITAL LETTER O WITH STROKE
00D9; C; 00F9; # LATIN CAPITAL LETTER U WITH GRAVE
00DA; C; 00FA; # LATIN CAPITAL LETTER U WITH ACUTE
00DB; C; 00FB; # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
00DC; C; 00FC; # LATIN CAPITAL LETTER U WITH DIAERESIS
00DD; C; 00FD; # LATIN CAPITAL LETTER Y WITH ACUTE
00DE; C; 00FE; # LATIN CAPITAL LETTER THORN
00DF; F; 0073 0073; # LATIN SMALL LETTER SHARP S
0100; C; 0101; # LATIN CAPITAL LETTER A WITH MACRON
0102; C; 0103; # LATIN CAPITAL LETTER A WITH BREVE
0104; C; 0105; # LATIN CAPITAL LETTER A WITH OGONEK
0106; C; 0107; # LATIN CAPITAL LETTER C WITH ACUTE
0108; C; 0109; # LATIN CAPITAL LETTER C WITH CIRCUMFLEX
010A; C; 010B; # LATIN CAPITAL LETTER C WITH DOT ABOVE
010C; C; 010D; # LATIN CAPITAL LETTER C WITH CARON
010E; C; 010F; # LATIN CAPITAL LETTER D WITH CARON
0110; C; 0111; # LATIN CAPITAL LETTER D WITH STROKE
0112; C; 0113; # LATIN CAPITAL LETTER E WITH MACRON
0114; C; 0115; # LATIN CAPITAL LETTER E WITH BREVE
0116; C; 0117; # LATIN CAPITAL LETTER E WITH DOT ABOVE
0118; C; 0119; # LATIN CAPITAL LETTER E WITH OGONEK
011A; C; 011B; # LATIN CAPITAL LETTER E WITH CARON
011C; C; 011D; # LATIN CAPITAL LETTER G WITH CIRCUMFLEX
011E; C; 011F; # LATIN CAPITAL LETTER G WITH BREVE
0120; C; 0121; # LATIN CAPITAL LETTER G WITH DOT ABOVE
0122; C; 0123; # LATIN CAPITAL LETTER G WITH CEDILLA
0124; C; 0125; # LATIN CAPITAL LETTER H WITH CIRCUMFLEX
0126; C; 0127; # LATIN CAPITAL LETTER H WITH STROKE
0128; C; 0129; # LATIN CAPITAL LETTER I WITH TILDE
012A; C; 012B; # LATIN CAPITAL LETTER I WITH MACRON
012C; C; 012D; # LATIN CAPITAL LETTER I WITH BREVE
012E; C; 012F; # LATIN CAPITAL LETTER I WITH OGONEK
0130; F; 0069 0307; # LATIN CAPITAL LETTER I WITH DOT ABOVE
0130; T; 0069; # LATIN CAPITAL LETTER I WITH DOT ABOVE
0132; C; 0133; # LATIN CAPITAL LIGATURE IJ
0134; C; 0135; # LATIN CAPITAL LETTER J WITH CIRCUMFLEX
0136; C; 0137; # LATIN CAPITAL LETTER K WITH CEDILLA
0139; C; 013A; # LATIN CAPITAL LETTER L WITH ACUTE
013B; C; 013C; # LATIN CAPITAL LETTER L WITH CEDILLA
013D; C; 013E; # LATIN CAPITAL LETTER L WITH CARON
013F; C; 0140; # LATIN CAPITAL LETTER L WITH MIDDLE DOT
0141; C; 0142; # LATIN CAPITAL LETTER L WITH STROKE
0143; C; 0144; # LATIN CAPITAL LETTER N WITH ACUTE
0145; C; 0146; # LATIN CAPITAL LETTER N WITH CEDILLA
0147; C; 0148; # LATIN CAPITAL LETTER N WITH CARON
0149; F; 02BC 006E; # LATIN SMALL LETTER N PRECEDED BY APOSTROPHE
014A; C; 014B; # LATIN CAPITAL LETTER ENG
014C; C; 014D; # LATIN CAPITAL LETTER O WITH MACRON
014E; C; 014F; # LATIN CAPITAL LETTER O WITH BREVE
0150; C; 0151; # LATIN CAPITAL LETTER O WITH DOUBLE ACUTE
0152; C; 0153; # LATIN CAPITAL LIGATURE OE
0154; C; 0155; # LATIN CAPITAL LETTER R WITH ACUTE
0156; C; 0157; # LATIN CAPITAL LETTER R WITH CEDILLA
0158; C; 0159; # LATIN CAPITAL LETTER R WITH CARON
015A; C; 015B; # LATIN CAPITAL LETTER S WITH ACUTE
015C; C; 015D; # LATIN CAPITAL LETTER S WITH CIRCUMFLEX
015E; C; 015F; # LATIN CAPITAL LETTER S WITH CEDILLA
0160; C; 0161; # LATIN CAPITAL LETTER S WITH CARON
0162; C; 0163; # LATIN CAPITAL LETTER T WITH CEDILLA
0164; C; 0165; # LATIN CAPITAL LETTER T WITH CARON
0166; C; 0167; # LATIN CAPITAL LETTER T WITH STROKE
0168; C; 0169; # LATIN CAPITAL LETTER U WITH TILDE
016A; C; 016B; # LATIN CAPITAL LETTER U WITH MACRON
016C; C; 016D; # LATIN CAPITAL LETTER U WITH BREVE
016E; C; 016F; # LATIN CAPITAL LETTER U WITH RING ABOVE
0170; C; 0171; # LATIN CAPITAL LETTER U WITH DOUBLE ACUTE
0172; C; 0173; # LATIN CAPITAL LETTER U WITH OGONEK
0174; C; 0175; # LATIN CAPITAL LETTER W WITH CIRCUMFLEX
0176; C; 0177; # LATIN CAPITAL LETTER Y WITH CIRCUMFLEX
0178; C; 00FF; # LATIN CAPITAL LETTER Y WITH DIAERESIS
0179; C; 017A; # LATIN CAPITAL LETTER Z WITH ACUTE
017B; C; 017C; # LATIN CAPITAL LETTER Z WITH DOT ABOVE
017D; C; 017E; # LATIN CAPITAL LETTER Z WITH CARON
017F; C; 0073; # LATIN SMALL LETTER LONG S
0181; C; 0253; # LATIN CAPITAL LETTER B WITH HOOK
0182; C; 0183; # LATIN CAPITAL LETTER B WITH TOPBAR
0184; C; 0185; # LATIN CAPITAL LETTER TONE SIX
0186; C; 0254; # LATIN CAPITAL LETTER OPEN O
0187; C; 0188; # LATIN CAPITAL LETTER C WITH HOOK
0189; C; 0256; # LATIN CAPITAL LETTER AFRICAN D
018A; C; 0257; # LATIN CAPITAL LETTER D WITH HOOK
018B; C; 018C; # LATIN CAPITAL LETTER D WITH TOPBAR
018E; C; 01DD; # LATIN CAPITAL LETTER REVERSED E
018F; C; 0259; # LATIN CAPITAL LETTER SCHWA
0190; C; 025B; # LATIN CAPITAL LETTER OPEN E
0191; C; 0192; # LATIN CAPITAL LETTER F WITH HOOK
0193; C; 0260; # LATIN CAPITAL LETTER G WITH HOOK
0194; C; 0263; # LATIN CAPITAL LETTER GAMMA
0196; C; 0269; # LATIN CAPITAL LETTER IOTA
0197; C; 0268; # LATIN CAPITAL LETTER I WITH STROKE
0198; C; 0199; # LATIN CAPITAL LETTER K WITH HOOK
019C; C; 026F; # LATIN CAPITAL LETTER TURNED M
019D; C; 0272; # LATIN CAPITAL LETTER N WITH LEFT HOOK
019F; C; 0275; # LATIN CAPITAL LETTER O WITH MIDDLE TILDE
01A0; C; 01A1; # LATIN CAPITAL LETTER O WITH HORN
01A2; C; 01A3; # LATIN CAPITAL LETTER OI
01A4; C; 01A5; # LATIN CAPITAL LETTER P WITH HOOK
01A6; C; 0280; # LATIN LETTER YR
01A7; C; 01A8; # LATIN CAPITAL LETTER TONE TWO
01A9; C; 0283; # LATIN CAPITAL LETTER ESH
01AC; C; 01AD; # LATIN CAPITAL LETTER T WITH HOOK
01AE; C; 0288; # LATIN CAPITAL LETTER T WITH RETROFLEX HOOK
01AF; C; 01B0; # LATIN CAPITAL LETTER U WITH HORN
01B1; C; 028A; # LATIN CAPITAL LETTER UPSILON
01B2; C; 028B; # LATIN CAPITAL LETTER V WITH HOOK
01B3; C; 01B4; # LATIN CAPITAL LETTER Y WITH HOOK
01B5; C; 01B6; # LATIN CAPITAL LETTER Z WITH STROKE
01B7; C; 0292; # LATIN CAPITAL LETTER EZH
01B8; C; 01B9; # LATIN CAPITAL LETTER EZH REVERSED
01BC; C; 01BD; # LATIN CAPITAL LETTER TONE FIVE
01C4; C; 01C6; # LATIN CAPITAL LETTER DZ WITH CARON
01C5; C; 01C6; # LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON
01C7; C; 01C9; # LATIN CAPITAL LETTER LJ
01C8; C; 01C9; # LATIN CAPITAL LETTER L WITH SMALL LETTER J
01CA; C; 01CC; # LATIN CAPITAL LETTER NJ
01CB; C; 01CC; # LATIN CAPITAL LETTER N WITH SMALL LETTER J
01CD; C; 01CE; # LATIN CAPITAL LETTER A WITH CARON
01CF; C; 01D0; # LATIN CAPITAL LETTER I WITH CARON
01D1; C; 01D2; # LATIN CAPITAL LETTER O WITH CARON
01D3; C; 01D4; # LATIN CAPITAL LETTER U WITH CARON
01D5; C; 01D6; # LATIN CAPITAL LETTER U WITH DIAERESIS AND MACRON
01D7; C; 01D8; # LATIN CAPITAL LETTER U WITH DIAERESIS AND ACUTE
01D9; C; 01DA; # LATIN CAPITAL LETTER U WITH DIAERESIS AND CARON
01DB; C; 01DC; # LATIN CAPITAL LETTER U WITH DIAERESIS AND GRAVE
01DE; C; 01DF; # LATIN CAPITAL LETTER A WITH DIAERESIS AND MACRON
01E0; C; 01E1; # LATIN CAPITAL LETTER A WITH DOT ABOVE AND MACRON
01E2; C; 01E3; # LATIN CAPITAL LETTER AE WITH MACRON
01E4; C; 01E5; # LATIN CAPITAL LETTER G WITH STROKE
01E6; C; 01E7; # LATIN CAPITAL LETTER G WITH CARON
01E8; C; 01E9; # LATIN CAPITAL LETTER K WITH CARON
01EA; C; 01EB; # LATIN CAPITAL LETTER O WITH OGONEK
01EC; C; 01ED; # LATIN CAPITAL LETTER O WITH OGONEK AND MACRON
01EE; C; 01EF; # LATIN CAPITAL LETTER EZH WITH CARON
01F0; F; 006A 030C; # LATIN SMALL LETTER J WITH CARON
01F1; C; 01F3; # LATIN CAPITAL LETTER DZ
01F2; C; 01F3; # LATIN CAPITAL LETTER D WITH SMALL LETTER Z
01F4; C; 01F5; # LATIN CAPITAL LETTER G WITH ACUTE
01F6; C; 0195; # LATIN CAPITAL LETTER HWAIR
01F7; C; 01BF; # LATIN CAPITAL LETTER WYNN
01F8; C; 01F9; # LATIN CAPITAL LETTER N WITH GRAVE
01FA; C; 01FB; # LATIN CAPITAL LETTER A WITH RING ABOVE AND ACUTE
01FC; C; 01FD; # LATIN CAPITAL LETTER AE WITH ACUTE
01FE; C; 01FF; # LATIN CAPITAL LETTER O WITH STROKE AND ACUTE
0200; C; 0201; # LATIN CAPITAL LETTER A WITH DOUBLE GRAVE
0202; C; 0203; # LATIN CAPITAL LETTER A WITH INVERTED BREVE
0204; C; 0205; # LATIN CAPITAL LETTER E WITH DOUBLE GRAVE
0206; C; 0207; # LATIN CAPITAL LETTER E WITH INVERTED BREVE
0208; C; 0209; # LATIN CAPITAL LETTER I WITH DOUBLE GRAVE
020A; C; 020B; # LATIN CAPITAL LETTER I WITH INVERTED BREVE
020C; C; 020D; # LATIN CAPITAL LETTER O WITH DOUBLE GRAVE
020E; C; 020F; # LATIN CAPITAL LETTER O WITH INVERTED BREVE
0210; C; 0211; # LATIN CAPITAL LETTER R WITH DOUBLE GRAVE
0212; C; 0213; # LATIN CAPITAL LETTER R WITH INVERTED BREVE
0214; C; 0215; # LATIN CAPITAL LETTER U WITH DOUBLE GRAVE
0216; C; 0217; # LATIN CAPITAL LETTER U WITH INVERTED BREVE
0218; C; 0219; # LATIN CAPITAL LETTER S WITH COMMA BELOW
021A; C; 021B; # LATIN CAPITAL LETTER T WITH COMMA BELOW
021C; C; 021D; # LATIN CAPITAL LETTER YOGH
021E; C; 021F; # LATIN CAPITAL LETTER H WITH CARON
0220; C; 019E; # LATIN CAPITAL LETTER N WITH LONG RIGHT LEG
0222; C; 0223; # LATIN CAPITAL LETTER OU
0224; C; 0225; # LATIN CAPITAL LETTER Z WITH HOOK
0226; C; 0227; # LATIN CAPITAL LETTER A WITH DOT ABOVE
0228; C; 0229; # LATIN CAPITAL LETTER E WITH CEDILLA
022A; C; 022B; # LATIN CAPITAL LETTER O WITH DIAERESIS AND MACRON
022C; C; 022D; # LATIN CAPITAL LETTER O WITH TILDE AND MACRON
022E; C; 022F; # LATIN CAPITAL LETTER O WITH DOT ABOVE
0230; C; 0231; # LATIN CAPITAL LETTER O WITH DOT ABOVE AND MACRON
0232; C; 0233; # LATIN CAPITAL LETTER Y WITH MACRON
0345; C; 03B9; # COMBINING GREEK YPOGEGRAMMENI
0386; C; 03AC; # GREEK CAPITAL LETTER ALPHA WITH TONOS
0388; C; 03AD; # GREEK CAPITAL LETTER EPSILON WITH TONOS
0389; C; 03AE; # GREEK CAPITAL LETTER ETA WITH TONOS
038A; C; 03AF; # GREEK CAPITAL LETTER IOTA WITH TONOS
038C; C; 03CC; # GREEK CAPITAL LETTER OMICRON WITH TONOS
038E; C; 03CD; # GREEK CAPITAL LETTER UPSILON WITH TONOS
038F; C; 03CE; # GREEK CAPITAL LETTER OMEGA WITH TONOS
0390; F; 03B9 0308 0301; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS
0391; C; 03B1; # GREEK CAPITAL LETTER ALPHA
0392; C; 03B2; # GREEK CAPITAL LETTER BETA
0393; C; 03B3; # GREEK CAPITAL LETTER GAMMA
0394; C; 03B4; # GREEK CAPITAL LETTER DELTA
0395; C; 03B5; # GREEK CAPITAL LETTER EPSILON
0396; C; 03B6; # GREEK CAPITAL LETTER ZETA
0397; C; 03B7; # GREEK CAPITAL LETTER ETA
0398; C; 03B8; # GREEK CAPITAL LETTER THETA
0399; C; 03B9; # GREEK CAPITAL LETTER IOTA
039A; C; 03BA; # GREEK CAPITAL LETTER KAPPA
039B; C; 03BB; # GREEK CAPITAL LETTER LAMDA
039C; C; 03BC; # GREEK CAPITAL LETTER MU
039D; C; 03BD; # GREEK CAPITAL LETTER NU
039E; C; 03BE; # GREEK CAPITAL LETTER XI
039F; C; 03BF; # GREEK CAPITAL LETTER OMICRON
03A0; C; 03C0; # GREEK CAPITAL LETTER PI
03A1; C; 03C1; # GREEK CAPITAL LETTER RHO
03A3; C; 03C3; # GREEK CAPITAL LETTER SIGMA
03A4; C; 03C4; # GREEK CAPITAL LETTER TAU
03A5; C; 03C5; # GREEK CAPITAL LETTER UPSILON
03A6; C; 03C6; # GREEK CAPITAL LETTER PHI
03A7; C; 03C7; # GREEK CAPITAL LETTER CHI
03A8; C; 03C8; # GREEK CAPITAL LETTER PSI
03A9; C; 03C9; # GREEK CAPITAL LETTER OMEGA
03AA; C; 03CA; # GREEK CAPITAL LETTER IOTA WITH DIALYTIKA
03AB; C; 03CB; # GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA
03B0; F; 03C5 0308 0301; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS
03C2; C; 03C3; # GREEK SMALL LETTER FINAL SIGMA
03D0; C; 03B2; # GREEK BETA SYMBOL
03D1; C; 03B8; # GREEK THETA SYMBOL
03D5; C; 03C6; # GREEK PHI SYMBOL
03D6; C; 03C0; # GREEK PI SYMBOL
03D8; C; 03D9; # GREEK LETTER ARCHAIC KOPPA
03DA; C; 03DB; # GREEK LETTER STIGMA
03DC; C; 03DD; # GREEK LETTER DIGAMMA
03DE; C; 03DF; # GREEK LETTER KOPPA
03E0; C; 03E1; # GREEK LETTER SAMPI
03E2; C; 03E3; # COPTIC CAPITAL LETTER SHEI
03E4; C; 03E5; # COPTIC CAPITAL LETTER FEI
03E6; C; 03E7; # COPTIC CAPITAL LETTER KHEI
03E8; C; 03E9; # COPTIC CAPITAL LETTER HORI
03EA; C; 03EB; # COPTIC CAPITAL LETTER GANGIA
03EC; C; 03ED; # COPTIC CAPITAL LETTER SHIMA
03EE; C; 03EF; # COPTIC CAPITAL LETTER DEI
03F0; C; 03BA; # GREEK KAPPA SYMBOL
03F1; C; 03C1; # GREEK RHO SYMBOL
03F2; C; 03C3; # GREEK LUNATE SIGMA SYMBOL
03F4; C; 03B8; # GREEK CAPITAL THETA SYMBOL
03F5; C; 03B5; # GREEK LUNATE EPSILON SYMBOL
0400; C; 0450; # CYRILLIC CAPITAL LETTER IE WITH GRAVE
0401; C; 0451; # CYRILLIC CAPITAL LETTER IO
0402; C; 0452; # CYRILLIC CAPITAL LETTER DJE
0403; C; 0453; # CYRILLIC CAPITAL LETTER GJE
0404; C; 0454; # CYRILLIC CAPITAL LETTER UKRAINIAN IE
0405; C; 0455; # CYRILLIC CAPITAL LETTER DZE
0406; C; 0456; # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I
0407; C; 0457; # CYRILLIC CAPITAL LETTER YI
0408; C; 0458; # CYRILLIC CAPITAL LETTER JE
0409; C; 0459; # CYRILLIC CAPITAL LETTER LJE
040A; C; 045A; # CYRILLIC CAPITAL LETTER NJE
040B; C; 045B; # CYRILLIC CAPITAL LETTER TSHE
040C; C; 045C; # CYRILLIC CAPITAL LETTER KJE
040D; C; 045D; # CYRILLIC CAPITAL LETTER I WITH GRAVE
040E; C; 045E; # CYRILLIC CAPITAL LETTER SHORT U
040F; C; 045F; # CYRILLIC CAPITAL LETTER DZHE
0410; C; 0430; # CYRILLIC CAPITAL LETTER A
0411; C; 0431; # CYRILLIC CAPITAL LETTER BE
0412; C; 0432; # CYRILLIC CAPITAL LETTER VE
0413; C; 0433; # CYRILLIC CAPITAL LETTER GHE
0414; C; 0434; # CYRILLIC CAPITAL LETTER DE
0415; C; 0435; # CYRILLIC CAPITAL LETTER IE
0416; C; 0436; # CYRILLIC CAPITAL LETTER ZHE
0417; C; 0437; # CYRILLIC CAPITAL LETTER ZE
0418; C; 0438; # CYRILLIC CAPITAL LETTER I
0419; C; 0439; # CYRILLIC CAPITAL LETTER SHORT I
041A; C; 043A; # CYRILLIC CAPITAL LETTER KA
041B; C; 043B; # CYRILLIC CAPITAL LETTER EL
041C; C; 043C; # CYRILLIC CAPITAL LETTER EM
041D; C; 043D; # CYRILLIC CAPITAL LETTER EN
041E; C; 043E; # CYRILLIC CAPITAL LETTER O
041F; C; 043F; # CYRILLIC CAPITAL LETTER PE
0420; C; 0440; # CYRILLIC CAPITAL LETTER ER
0421; C; 0441; # CYRILLIC CAPITAL LETTER ES
0422; C; 0442; # CYRILLIC CAPITAL LETTER TE
0423; C; 0443; # CYRILLIC CAPITAL LETTER U
0424; C; 0444; # CYRILLIC CAPITAL LETTER EF
0425; C; 0445; # CYRILLIC CAPITAL LETTER HA
0426; C; 0446; # CYRILLIC CAPITAL LETTER TSE
0427; C; 0447; # CYRILLIC CAPITAL LETTER CHE
0428; C; 0448; # CYRILLIC CAPITAL LETTER SHA
0429; C; 0449; # CYRILLIC CAPITAL LETTER SHCHA
042A; C; 044A; # CYRILLIC CAPITAL LETTER HARD SIGN
042B; C; 044B; # CYRILLIC CAPITAL LETTER YERU
042C; C; 044C; # CYRILLIC CAPITAL LETTER SOFT SIGN
042D; C; 044D; # CYRILLIC CAPITAL LETTER E
042E; C; 044E; # CYRILLIC CAPITAL LETTER YU
042F; C; 044F; # CYRILLIC CAPITAL LETTER YA
0460; C; 0461; # CYRILLIC CAPITAL LETTER OMEGA
0462; C; 0463; # CYRILLIC CAPITAL LETTER YAT
0464; C; 0465; # CYRILLIC CAPITAL LETTER IOTIFIED E
0466; C; 0467; # CYRILLIC CAPITAL LETTER LITTLE YUS
0468; C; 0469; # CYRILLIC CAPITAL LETTER IOTIFIED LITTLE YUS
046A; C; 046B; # CYRILLIC CAPITAL LETTER BIG YUS
046C; C; 046D; # CYRILLIC CAPITAL LETTER IOTIFIED BIG YUS
046E; C; 046F; # CYRILLIC CAPITAL LETTER KSI
0470; C; 0471; # CYRILLIC CAPITAL LETTER PSI
0472; C; 0473; # CYRILLIC CAPITAL LETTER FITA
0474; C; 0475; # CYRILLIC CAPITAL LETTER IZHITSA
0476; C; 0477; # CYRILLIC CAPITAL LETTER IZHITSA WITH DOUBLE GRAVE ACCENT
0478; C; 0479; # CYRILLIC CAPITAL LETTER UK
047A; C; 047B; # CYRILLIC CAPITAL LETTER ROUND OMEGA
047C; C; 047D; # CYRILLIC CAPITAL LETTER OMEGA WITH TITLO
047E; C; 047F; # CYRILLIC CAPITAL LETTER OT
0480; C; 0481; # CYRILLIC CAPITAL LETTER KOPPA
048A; C; 048B; # CYRILLIC CAPITAL LETTER SHORT I WITH TAIL
048C; C; 048D; # CYRILLIC CAPITAL LETTER SEMISOFT SIGN
048E; C; 048F; # CYRILLIC CAPITAL LETTER ER WITH TICK
0490; C; 0491; # CYRILLIC CAPITAL LETTER GHE WITH UPTURN
0492; C; 0493; # CYRILLIC CAPITAL LETTER GHE WITH STROKE
0494; C; 0495; # CYRILLIC CAPITAL LETTER GHE WITH MIDDLE HOOK
0496; C; 0497; # CYRILLIC CAPITAL LETTER ZHE WITH DESCENDER
0498; C; 0499; # CYRILLIC CAPITAL LETTER ZE WITH DESCENDER
049A; C; 049B; # CYRILLIC CAPITAL LETTER KA WITH DESCENDER
049C; C; 049D; # CYRILLIC CAPITAL LETTER KA WITH VERTICAL STROKE
049E; C; 049F; # CYRILLIC CAPITAL LETTER KA WITH STROKE
04A0; C; 04A1; # CYRILLIC CAPITAL LETTER BASHKIR KA
04A2; C; 04A3; # CYRILLIC CAPITAL LETTER EN WITH DESCENDER
04A4; C; 04A5; # CYRILLIC CAPITAL LIGATURE EN GHE
04A6; C; 04A7; # CYRILLIC CAPITAL LETTER PE WITH MIDDLE HOOK
04A8; C; 04A9; # CYRILLIC CAPITAL LETTER ABKHASIAN HA
04AA; C; 04AB; # CYRILLIC CAPITAL LETTER ES WITH DESCENDER
04AC; C; 04AD; # CYRILLIC CAPITAL LETTER TE WITH DESCENDER
04AE; C; 04AF; # CYRILLIC CAPITAL LETTER STRAIGHT U
04B0; C; 04B1; # CYRILLIC CAPITAL LETTER STRAIGHT U WITH STROKE
04B2; C; 04B3; # CYRILLIC CAPITAL LETTER HA WITH DESCENDER
04B4; C; 04B5; # CYRILLIC CAPITAL LIGATURE TE TSE
04B6; C; 04B7; # CYRILLIC CAPITAL LETTER CHE WITH DESCENDER
04B8; C; 04B9; # CYRILLIC CAPITAL LETTER CHE WITH VERTICAL STROKE
04BA; C; 04BB; # CYRILLIC CAPITAL LETTER SHHA
04BC; C; 04BD; # CYRILLIC CAPITAL LETTER ABKHASIAN CHE
04BE; C; 04BF; # CYRILLIC CAPITAL LETTER ABKHASIAN CHE WITH DESCENDER
04C1; C; 04C2; # CYRILLIC CAPITAL LETTER ZHE WITH BREVE
04C3; C; 04C4; # CYRILLIC CAPITAL LETTER KA WITH HOOK
04C5; C; 04C6; # CYRILLIC CAPITAL LETTER EL WITH TAIL
04C7; C; 04C8; # CYRILLIC CAPITAL LETTER EN WITH HOOK
04C9; C; 04CA; # CYRILLIC CAPITAL LETTER EN WITH TAIL
04CB; C; 04CC; # CYRILLIC CAPITAL LETTER KHAKASSIAN CHE
04CD; C; 04CE; # CYRILLIC CAPITAL LETTER EM WITH TAIL
04D0; C; 04D1; # CYRILLIC CAPITAL LETTER A WITH BREVE
04D2; C; 04D3; # CYRILLIC CAPITAL LETTER A WITH DIAERESIS
04D4; C; 04D5; # CYRILLIC CAPITAL LIGATURE A IE
04D6; C; 04D7; # CYRILLIC CAPITAL LETTER IE WITH BREVE
04D8; C; 04D9; # CYRILLIC CAPITAL LETTER SCHWA
04DA; C; 04DB; # CYRILLIC CAPITAL LETTER SCHWA WITH DIAERESIS
04DC; C; 04DD; # CYRILLIC CAPITAL LETTER ZHE WITH DIAERESIS
04DE; C; 04DF; # CYRILLIC CAPITAL LETTER ZE WITH DIAERESIS
04E0; C; 04E1; # CYRILLIC CAPITAL LETTER ABKHASIAN DZE
04E2; C; 04E3; # CYRILLIC CAPITAL LETTER I WITH MACRON
04E4; C; 04E5; # CYRILLIC CAPITAL LETTER I WITH DIAERESIS
04E6; C; 04E7; # CYRILLIC CAPITAL LETTER O WITH DIAERESIS
04E8; C; 04E9; # CYRILLIC CAPITAL LETTER BARRED O
04EA; C; 04EB; # CYRILLIC CAPITAL LETTER BARRED O WITH DIAERESIS
04EC; C; 04ED; # CYRILLIC CAPITAL LETTER E WITH DIAERESIS
04EE; C; 04EF; # CYRILLIC CAPITAL LETTER U WITH MACRON
04F0; C; 04F1; # CYRILLIC CAPITAL LETTER U WITH DIAERESIS
04F2; C; 04F3; # CYRILLIC CAPITAL LETTER U WITH DOUBLE ACUTE
04F4; C; 04F5; # CYRILLIC CAPITAL LETTER CHE WITH DIAERESIS
04F8; C; 04F9; # CYRILLIC CAPITAL LETTER YERU WITH DIAERESIS
0500; C; 0501; # CYRILLIC CAPITAL LETTER KOMI DE
0502; C; 0503; # CYRILLIC CAPITAL LETTER KOMI DJE
0504; C; 0505; # CYRILLIC CAPITAL LETTER KOMI ZJE
0506; C; 0507; # CYRILLIC CAPITAL LETTER KOMI DZJE
0508; C; 0509; # CYRILLIC CAPITAL LETTER KOMI LJE
050A; C; 050B; # CYRILLIC CAPITAL LETTER KOMI NJE
050C; C; 050D; # CYRILLIC CAPITAL LETTER KOMI SJE
050E; C; 050F; # CYRILLIC CAPITAL LETTER KOMI TJE
0531; C; 0561; # ARMENIAN CAPITAL LETTER AYB
0532; C; 0562; # ARMENIAN CAPITAL LETTER BEN
0533; C; 0563; # ARMENIAN CAPITAL LETTER GIM
0534; C; 0564; # ARMENIAN CAPITAL LETTER DA
0535; C; 0565; # ARMENIAN CAPITAL LETTER ECH
0536; C; 0566; # ARMENIAN CAPITAL LETTER ZA
0537; C; 0567; # ARMENIAN CAPITAL LETTER EH
0538; C; 0568; # ARMENIAN CAPITAL LETTER ET
0539; C; 0569; # ARMENIAN CAPITAL LETTER TO
053A; C; 056A; # ARMENIAN CAPITAL LETTER ZHE
053B; C; 056B; # ARMENIAN CAPITAL LETTER INI
053C; C; 056C; # ARMENIAN CAPITAL LETTER LIWN
053D; C; 056D; # ARMENIAN CAPITAL LETTER XEH
053E; C; 056E; # ARMENIAN CAPITAL LETTER CA
053F; C; 056F; # ARMENIAN CAPITAL LETTER KEN
0540; C; 0570; # ARMENIAN CAPITAL LETTER HO
0541; C; 0571; # ARMENIAN CAPITAL LETTER JA
0542; C; 0572; # ARMENIAN CAPITAL LETTER GHAD
0543; C; 0573; # ARMENIAN CAPITAL LETTER CHEH
0544; C; 0574; # ARMENIAN CAPITAL LETTER MEN
0545; C; 0575; # ARMENIAN CAPITAL LETTER YI
0546; C; 0576; # ARMENIAN CAPITAL LETTER NOW
0547; C; 0577; # ARMENIAN CAPITAL LETTER SHA
0548; C; 0578; # ARMENIAN CAPITAL LETTER VO
0549; C; 0579; # ARMENIAN CAPITAL LETTER CHA
054A; C; 057A; # ARMENIAN CAPITAL LETTER PEH
054B; C; 057B; # ARMENIAN CAPITAL LETTER JHEH
054C; C; 057C; # ARMENIAN CAPITAL LETTER RA
054D; C; 057D; # ARMENIAN CAPITAL LETTER SEH
054E; C; 057E; # ARMENIAN CAPITAL LETTER VEW
054F; C; 057F; # ARMENIAN CAPITAL LETTER TIWN
0550; C; 0580; # ARMENIAN CAPITAL LETTER REH
0551; C; 0581; # ARMENIAN CAPITAL LETTER CO
0552; C; 0582; # ARMENIAN CAPITAL LETTER YIWN
0553; C; 0583; # ARMENIAN CAPITAL LETTER PIWR
0554; C; 0584; # ARMENIAN CAPITAL LETTER KEH
0555; C; 0585; # ARMENIAN CAPITAL LETTER OH
0556; C; 0586; # ARMENIAN CAPITAL LETTER FEH
0587; F; 0565 0582; # ARMENIAN SMALL LIGATURE ECH YIWN
1E00; C; 1E01; # LATIN CAPITAL LETTER A WITH RING BELOW
1E02; C; 1E03; # LATIN CAPITAL LETTER B WITH DOT ABOVE
1E04; C; 1E05; # LATIN CAPITAL LETTER B WITH DOT BELOW
1E06; C; 1E07; # LATIN CAPITAL LETTER B WITH LINE BELOW
1E08; C; 1E09; # LATIN CAPITAL LETTER C WITH CEDILLA AND ACUTE
1E0A; C; 1E0B; # LATIN CAPITAL LETTER D WITH DOT ABOVE
1E0C; C; 1E0D; # LATIN CAPITAL LETTER D WITH DOT BELOW
1E0E; C; 1E0F; # LATIN CAPITAL LETTER D WITH LINE BELOW
1E10; C; 1E11; # LATIN CAPITAL LETTER D WITH CEDILLA
1E12; C; 1E13; # LATIN CAPITAL LETTER D WITH CIRCUMFLEX BELOW
1E14; C; 1E15; # LATIN CAPITAL LETTER E WITH MACRON AND GRAVE
1E16; C; 1E17; # LATIN CAPITAL LETTER E WITH MACRON AND ACUTE
1E18; C; 1E19; # LATIN CAPITAL LETTER E WITH CIRCUMFLEX BELOW
1E1A; C; 1E1B; # LATIN CAPITAL LETTER E WITH TILDE BELOW
1E1C; C; 1E1D; # LATIN CAPITAL LETTER E WITH CEDILLA AND BREVE
1E1E; C; 1E1F; # LATIN CAPITAL LETTER F WITH DOT ABOVE
1E20; C; 1E21; # LATIN CAPITAL LETTER G WITH MACRON
1E22; C; 1E23; # LATIN CAPITAL LETTER H WITH DOT ABOVE
1E24; C; 1E25; # LATIN CAPITAL LETTER H WITH DOT BELOW
1E26; C; 1E27; # LATIN CAPITAL LETTER H WITH DIAERESIS
1E28; C; 1E29; # LATIN CAPITAL LETTER H WITH CEDILLA
1E2A; C; 1E2B; # LATIN CAPITAL LETTER H WITH BREVE BELOW
1E2C; C; 1E2D; # LATIN CAPITAL LETTER I WITH TILDE BELOW
1E2E; C; 1E2F; # LATIN CAPITAL LETTER I WITH DIAERESIS AND ACUTE
1E30; C; 1E31; # LATIN CAPITAL LETTER K WITH ACUTE
1E32; C; 1E33; # LATIN CAPITAL LETTER K WITH DOT BELOW
1E34; C; 1E35; # LATIN CAPITAL LETTER K WITH LINE BELOW
1E36; C; 1E37; # LATIN CAPITAL LETTER L WITH DOT BELOW
1E38; C; 1E39; # LATIN CAPITAL LETTER L WITH DOT BELOW AND MACRON
1E3A; C; 1E3B; # LATIN CAPITAL LETTER L WITH LINE BELOW
1E3C; C; 1E3D; # LATIN CAPITAL LETTER L WITH CIRCUMFLEX BELOW
1E3E; C; 1E3F; # LATIN CAPITAL LETTER M WITH ACUTE
1E40; C; 1E41; # LATIN CAPITAL LETTER M WITH DOT ABOVE
1E42; C; 1E43; # LATIN CAPITAL LETTER M WITH DOT BELOW
1E44; C; 1E45; # LATIN CAPITAL LETTER N WITH DOT ABOVE
1E46; C; 1E47; # LATIN CAPITAL LETTER N WITH DOT BELOW
1E48; C; 1E49; # LATIN CAPITAL LETTER N WITH LINE BELOW
1E4A; C; 1E4B; # LATIN CAPITAL LETTER N WITH CIRCUMFLEX BELOW
1E4C; C; 1E4D; # LATIN CAPITAL LETTER O WITH TILDE AND ACUTE
1E4E; C; 1E4F; # LATIN CAPITAL LETTER O WITH TILDE AND DIAERESIS
1E50; C; 1E51; # LATIN CAPITAL LETTER O WITH MACRON AND GRAVE
1E52; C; 1E53; # LATIN CAPITAL LETTER O WITH MACRON AND ACUTE
1E54; C; 1E55; # LATIN CAPITAL LETTER P WITH ACUTE
1E56; C; 1E57; # LATIN CAPITAL LETTER P WITH DOT ABOVE
1E58; C; 1E59; # LATIN CAPITAL LETTER R WITH DOT ABOVE
1E5A; C; 1E5B; # LATIN CAPITAL LETTER R WITH DOT BELOW
1E5C; C; 1E5D; # LATIN CAPITAL LETTER R WITH DOT BELOW AND MACRON
1E5E; C; 1E5F; # LATIN CAPITAL LETTER R WITH LINE BELOW
1E60; C; 1E61; # LATIN CAPITAL LETTER S WITH DOT ABOVE
1E62; C; 1E63; # LATIN CAPITAL LETTER S WITH DOT BELOW
1E64; C; 1E65; # LATIN CAPITAL LETTER S WITH ACUTE AND DOT ABOVE
1E66; C; 1E67; # LATIN CAPITAL LETTER S WITH CARON AND DOT ABOVE
1E68; C; 1E69; # LATIN CAPITAL LETTER S WITH DOT BELOW AND DOT ABOVE
1E6A; C; 1E6B; # LATIN CAPITAL LETTER T WITH DOT ABOVE
1E6C; C; 1E6D; # LATIN CAPITAL LETTER T WITH DOT BELOW
1E6E; C; 1E6F; # LATIN CAPITAL LETTER T WITH LINE BELOW
1E70; C; 1E71; # LATIN CAPITAL LETTER T WITH CIRCUMFLEX BELOW
1E72; C; 1E73; # LATIN CAPITAL LETTER U WITH DIAERESIS BELOW
1E74; C; 1E75; # LATIN CAPITAL LETTER U WITH TILDE BELOW
1E76; C; 1E77; # LATIN CAPITAL LETTER U WITH CIRCUMFLEX BELOW
1E78; C; 1E79; # LATIN CAPITAL LETTER U WITH TILDE AND ACUTE
1E7A; C; 1E7B; # LATIN CAPITAL LETTER U WITH MACRON AND DIAERESIS
1E7C; C; 1E7D; # LATIN CAPITAL LETTER V WITH TILDE
1E7E; C; 1E7F; # LATIN CAPITAL LETTER V WITH DOT BELOW
1E80; C; 1E81; # LATIN CAPITAL LETTER W WITH GRAVE
1E82; C; 1E83; # LATIN CAPITAL LETTER W WITH ACUTE
1E84; C; 1E85; # LATIN CAPITAL LETTER W WITH DIAERESIS
1E86; C; 1E87; # LATIN CAPITAL LETTER W WITH DOT ABOVE
1E88; C; 1E89; # LATIN CAPITAL LETTER W WITH DOT BELOW
1E8A; C; 1E8B; # LATIN CAPITAL LETTER X WITH DOT ABOVE
1E8C; C; 1E8D; # LATIN CAPITAL LETTER X WITH DIAERESIS
1E8E; C; 1E8F; # LATIN CAPITAL LETTER Y WITH DOT ABOVE
1E90; C; 1E91; # LATIN CAPITAL LETTER Z WITH CIRCUMFLEX
1E92; C; 1E93; # LATIN CAPITAL LETTER Z WITH DOT BELOW
1E94; C; 1E95; # LATIN CAPITAL LETTER Z WITH LINE BELOW
1E96; F; 0068 0331; # LATIN SMALL LETTER H WITH LINE BELOW
1E97; F; 0074 0308; # LATIN SMALL LETTER T WITH DIAERESIS
1E98; F; 0077 030A; # LATIN SMALL LETTER W WITH RING ABOVE
1E99; F; 0079 030A; # LATIN SMALL LETTER Y WITH RING ABOVE
1E9A; F; 0061 02BE; # LATIN SMALL LETTER A WITH RIGHT HALF RING
1E9B; C; 1E61; # LATIN SMALL LETTER LONG S WITH DOT ABOVE
1EA0; C; 1EA1; # LATIN CAPITAL LETTER A WITH DOT BELOW
1EA2; C; 1EA3; # LATIN CAPITAL LETTER A WITH HOOK ABOVE
1EA4; C; 1EA5; # LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND ACUTE
1EA6; C; 1EA7; # LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND GRAVE
1EA8; C; 1EA9; # LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND HOOK ABOVE
1EAA; C; 1EAB; # LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND TILDE
1EAC; C; 1EAD; # LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND DOT BELOW
1EAE; C; 1EAF; # LATIN CAPITAL LETTER A WITH BREVE AND ACUTE
1EB0; C; 1EB1; # LATIN CAPITAL LETTER A WITH BREVE AND GRAVE
1EB2; C; 1EB3; # LATIN CAPITAL LETTER A WITH BREVE AND HOOK ABOVE
1EB4; C; 1EB5; # LATIN CAPITAL LETTER A WITH BREVE AND TILDE
1EB6; C; 1EB7; # LATIN CAPITAL LETTER A WITH BREVE AND DOT BELOW
1EB8; C; 1EB9; # LATIN CAPITAL LETTER E WITH DOT BELOW
1EBA; C; 1EBB; # LATIN CAPITAL LETTER E WITH HOOK ABOVE
1EBC; C; 1EBD; # LATIN CAPITAL LETTER E WITH TILDE
1EBE; C; 1EBF; # LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND ACUTE
1EC0; C; 1EC1; # LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND GRAVE
1EC2; C; 1EC3; # LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND HOOK ABOVE
1EC4; C; 1EC5; # LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND TILDE
1EC6; C; 1EC7; # LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND DOT BELOW
1EC8; C; 1EC9; # LATIN CAPITAL LETTER I WITH HOOK ABOVE
1ECA; C; 1ECB; # LATIN CAPITAL LETTER I WITH DOT BELOW
1ECC; C; 1ECD; # LATIN CAPITAL LETTER O WITH DOT BELOW
1ECE; C; 1ECF; # LATIN CAPITAL LETTER O WITH HOOK ABOVE
1ED0; C; 1ED1; # LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND ACUTE
1ED2; C; 1ED3; # LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND GRAVE
1ED4; C; 1ED5; # LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND HOOK ABOVE
1ED6; C; 1ED7; # LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND TILDE
1ED8; C; 1ED9; # LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND DOT BELOW
1EDA; C; 1EDB; # LATIN CAPITAL LETTER O WITH HORN AND ACUTE
1EDC; C; 1EDD; # LATIN CAPITAL LETTER O WITH HORN AND GRAVE
1EDE; C; 1EDF; # LATIN CAPITAL LETTER O WITH HORN AND HOOK ABOVE
1EE0; C; 1EE1; # LATIN CAPITAL LETTER O WITH HORN AND TILDE
1EE2; C; 1EE3; # LATIN CAPITAL LETTER O WITH HORN AND DOT BELOW
1EE4; C; 1EE5; # LATIN CAPITAL LETTER U WITH DOT BELOW
1EE6; C; 1EE7; # LATIN CAPITAL LETTER U WITH HOOK ABOVE
1EE8; C; 1EE9; # LATIN CAPITAL LETTER U WITH HORN AND ACUTE
1EEA; C; 1EEB; # LATIN CAPITAL LETTER U WITH HORN AND GRAVE
1EEC; C; 1EED; # LATIN CAPITAL LETTER U WITH HORN AND HOOK ABOVE
1EEE; C; 1EEF; # LATIN CAPITAL LETTER U WITH HORN AND TILDE
1EF0; C; 1EF1; # LATIN CAPITAL LETTER U WITH HORN AND DOT BELOW
1EF2; C; 1EF3; # LATIN CAPITAL LETTER Y WITH GRAVE
1EF4; C; 1EF5; # LATIN CAPITAL LETTER Y WITH DOT BELOW
1EF6; C; 1EF7; # LATIN CAPITAL LETTER Y WITH HOOK ABOVE
1EF8; C; 1EF9; # LATIN CAPITAL LETTER Y WITH TILDE
1F08; C; 1F00; # GREEK CAPITAL LETTER ALPHA WITH PSILI
1F09; C; 1F01; # GREEK CAPITAL LETTER ALPHA WITH DASIA
1F0A; C; 1F02; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND VARIA
1F0B; C; 1F03; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND VARIA
1F0C; C; 1F04; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND OXIA
1F0D; C; 1F05; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND OXIA
1F0E; C; 1F06; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND PERISPOMENI
1F0F; C; 1F07; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND PERISPOMENI
1F18; C; 1F10; # GREEK CAPITAL LETTER EPSILON WITH PSILI
1F19; C; 1F11; # GREEK CAPITAL LETTER EPSILON WITH DASIA
1F1A; C; 1F12; # GREEK CAPITAL LETTER EPSILON WITH PSILI AND VARIA
1F1B; C; 1F13; # GREEK CAPITAL LETTER EPSILON WITH DASIA AND VARIA
1F1C; C; 1F14; # GREEK CAPITAL LETTER EPSILON WITH PSILI AND OXIA
1F1D; C; 1F15; # GREEK CAPITAL LETTER EPSILON WITH DASIA AND OXIA
1F28; C; 1F20; # GREEK CAPITAL LETTER ETA WITH PSILI
1F29; C; 1F21; # GREEK CAPITAL LETTER ETA WITH DASIA
1F2A; C; 1F22; # GREEK CAPITAL LETTER ETA WITH PSILI AND VARIA
1F2B; C; 1F23; # GREEK CAPITAL LETTER ETA WITH DASIA AND VARIA
1F2C; C; 1F24; # GREEK CAPITAL LETTER ETA WITH PSILI AND OXIA
1F2D; C; 1F25; # GREEK CAPITAL LETTER ETA WITH DASIA AND OXIA
1F2E; C; 1F26; # GREEK CAPITAL LETTER ETA WITH PSILI AND PERISPOMENI
1F2F; C; 1F27; # GREEK CAPITAL LETTER ETA WITH DASIA AND PERISPOMENI
1F38; C; 1F30; # GREEK CAPITAL LETTER IOTA WITH PSILI
1F39; C; 1F31; # GREEK CAPITAL LETTER IOTA WITH DASIA
1F3A; C; 1F32; # GREEK CAPITAL LETTER IOTA WITH PSILI AND VARIA
1F3B; C; 1F33; # GREEK CAPITAL LETTER IOTA WITH DASIA AND VARIA
1F3C; C; 1F34; # GREEK CAPITAL LETTER IOTA WITH PSILI AND OXIA
1F3D; C; 1F35; # GREEK CAPITAL LETTER IOTA WITH DASIA AND OXIA
1F3E; C; 1F36; # GREEK CAPITAL LETTER IOTA WITH PSILI AND PERISPOMENI
1F3F; C; 1F37; # GREEK CAPITAL LETTER IOTA WITH DASIA AND PERISPOMENI
1F48; C; 1F40; # GREEK CAPITAL LETTER OMICRON WITH PSILI
1F49; C; 1F41; # GREEK CAPITAL LETTER OMICRON WITH DASIA
1F4A; C; 1F42; # GREEK CAPITAL LETTER OMICRON WITH PSILI AND VARIA
1F4B; C; 1F43; # GREEK CAPITAL LETTER OMICRON WITH DASIA AND VARIA
1F4C; C; 1F44; # GREEK CAPITAL LETTER OMICRON WITH PSILI AND OXIA
1F4D; C; 1F45; # GREEK CAPITAL LETTER OMICRON WITH DASIA AND OXIA
1F50; F; 03C5 0313; # GREEK SMALL LETTER UPSILON WITH PSILI
1F52; F; 03C5 0313 0300; # GREEK SMALL LETTER UPSILON WITH PSILI AND VARIA
1F54; F; 03C5 0313 0301; # GREEK SMALL LETTER UPSILON WITH PSILI AND OXIA
1F56; F; 03C5 0313 0342; # GREEK SMALL LETTER UPSILON WITH PSILI AND PERISPOMENI
1F59; C; 1F51; # GREEK CAPITAL LETTER UPSILON WITH DASIA
1F5B; C; 1F53; # GREEK CAPITAL LETTER UPSILON WITH DASIA AND VARIA
1F5D; C; 1F55; # GREEK CAPITAL LETTER UPSILON WITH DASIA AND OXIA
1F5F; C; 1F57; # GREEK CAPITAL LETTER UPSILON WITH DASIA AND PERISPOMENI
1F68; C; 1F60; # GREEK CAPITAL LETTER OMEGA WITH PSILI
1F69; C; 1F61; # GREEK CAPITAL LETTER OMEGA WITH DASIA
1F6A; C; 1F62; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND VARIA
1F6B; C; 1F63; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND VARIA
1F6C; C; 1F64; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND OXIA
1F6D; C; 1F65; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND OXIA
1F6E; C; 1F66; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND PERISPOMENI
1F6F; C; 1F67; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND PERISPOMENI
1F80; F; 1F00 03B9; # GREEK SMALL LETTER ALPHA WITH PSILI AND YPOGEGRAMMENI
1F81; F; 1F01 03B9; # GREEK SMALL LETTER ALPHA WITH DASIA AND YPOGEGRAMMENI
1F82; F; 1F02 03B9; # GREEK SMALL LETTER ALPHA WITH PSILI AND VARIA AND YPOGEGRAMMENI
1F83; F; 1F03 03B9; # GREEK SMALL LETTER ALPHA WITH DASIA AND VARIA AND YPOGEGRAMMENI
1F84; F; 1F04 03B9; # GREEK SMALL LETTER ALPHA WITH PSILI AND OXIA AND YPOGEGRAMMENI
1F85; F; 1F05 03B9; # GREEK SMALL LETTER ALPHA WITH DASIA AND OXIA AND YPOGEGRAMMENI
1F86; F; 1F06 03B9; # GREEK SMALL LETTER ALPHA WITH PSILI AND PERISPOMENI AND YPOGEGRAMMENI
1F87; F; 1F07 03B9; # GREEK SMALL LETTER ALPHA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI
1F88; F; 1F00 03B9; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND PROSGEGRAMMENI
1F88; S; 1F80; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND PROSGEGRAMMENI
1F89; F; 1F01 03B9; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND PROSGEGRAMMENI
1F89; S; 1F81; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND PROSGEGRAMMENI
1F8A; F; 1F02 03B9; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND VARIA AND PROSGEGRAMMENI
1F8A; S; 1F82; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND VARIA AND PROSGEGRAMMENI
1F8B; F; 1F03 03B9; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND VARIA AND PROSGEGRAMMENI
1F8B; S; 1F83; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND VARIA AND PROSGEGRAMMENI
1F8C; F; 1F04 03B9; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND OXIA AND PROSGEGRAMMENI
1F8C; S; 1F84; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND OXIA AND PROSGEGRAMMENI
1F8D; F; 1F05 03B9; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND OXIA AND PROSGEGRAMMENI
1F8D; S; 1F85; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND OXIA AND PROSGEGRAMMENI
1F8E; F; 1F06 03B9; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI
1F8E; S; 1F86; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI
1F8F; F; 1F07 03B9; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI
1F8F; S; 1F87; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI
1F90; F; 1F20 03B9; # GREEK SMALL LETTER ETA WITH PSILI AND YPOGEGRAMMENI
1F91; F; 1F21 03B9; # GREEK SMALL LETTER ETA WITH DASIA AND YPOGEGRAMMENI
1F92; F; 1F22 03B9; # GREEK SMALL LETTER ETA WITH PSILI AND VARIA AND YPOGEGRAMMENI
1F93; F; 1F23 03B9; # GREEK SMALL LETTER ETA WITH DASIA AND VARIA AND YPOGEGRAMMENI
1F94; F; 1F24 03B9; # GREEK SMALL LETTER ETA WITH PSILI AND OXIA AND YPOGEGRAMMENI
1F95; F; 1F25 03B9; # GREEK SMALL LETTER ETA WITH DASIA AND OXIA AND YPOGEGRAMMENI
1F96; F; 1F26 03B9; # GREEK SMALL LETTER ETA WITH PSILI AND PERISPOMENI AND YPOGEGRAMMENI
1F97; F; 1F27 03B9; # GREEK SMALL LETTER ETA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI
1F98; F; 1F20 03B9; # GREEK CAPITAL LETTER ETA WITH PSILI AND PROSGEGRAMMENI
1F98; S; 1F90; # GREEK CAPITAL LETTER ETA WITH PSILI AND PROSGEGRAMMENI
1F99; F; 1F21 03B9; # GREEK CAPITAL LETTER ETA WITH DASIA AND PROSGEGRAMMENI
1F99; S; 1F91; # GREEK CAPITAL LETTER ETA WITH DASIA AND PROSGEGRAMMENI
1F9A; F; 1F22 03B9; # GREEK CAPITAL LETTER ETA WITH PSILI AND VARIA AND PROSGEGRAMMENI
1F9A; S; 1F92; # GREEK CAPITAL LETTER ETA WITH PSILI AND VARIA AND PROSGEGRAMMENI
1F9B; F; 1F23 03B9; # GREEK CAPITAL LETTER ETA WITH DASIA AND VARIA AND PROSGEGRAMMENI
1F9B; S; 1F93; # GREEK CAPITAL LETTER ETA WITH DASIA AND VARIA AND PROSGEGRAMMENI
1F9C; F; 1F24 03B9; # GREEK CAPITAL LETTER ETA WITH PSILI AND OXIA AND PROSGEGRAMMENI
1F9C; S; 1F94; # GREEK CAPITAL LETTER ETA WITH PSILI AND OXIA AND PROSGEGRAMMENI
1F9D; F; 1F25 03B9; # GREEK CAPITAL LETTER ETA WITH DASIA AND OXIA AND PROSGEGRAMMENI
1F9D; S; 1F95; # GREEK CAPITAL LETTER ETA WITH DASIA AND OXIA AND PROSGEGRAMMENI
1F9E; F; 1F26 03B9; # GREEK CAPITAL LETTER ETA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI
1F9E; S; 1F96; # GREEK CAPITAL LETTER ETA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI
1F9F; F; 1F27 03B9; # GREEK CAPITAL LETTER ETA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI
1F9F; S; 1F97; # GREEK CAPITAL LETTER ETA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI
1FA0; F; 1F60 03B9; # GREEK SMALL LETTER OMEGA WITH PSILI AND YPOGEGRAMMENI
1FA1; F; 1F61 03B9; # GREEK SMALL LETTER OMEGA WITH DASIA AND YPOGEGRAMMENI
1FA2; F; 1F62 03B9; # GREEK SMALL LETTER OMEGA WITH PSILI AND VARIA AND YPOGEGRAMMENI
1FA3; F; 1F63 03B9; # GREEK SMALL LETTER OMEGA WITH DASIA AND VARIA AND YPOGEGRAMMENI
1FA4; F; 1F64 03B9; # GREEK SMALL LETTER OMEGA WITH PSILI AND OXIA AND YPOGEGRAMMENI
1FA5; F; 1F65 03B9; # GREEK SMALL LETTER OMEGA WITH DASIA AND OXIA AND YPOGEGRAMMENI
1FA6; F; 1F66 03B9; # GREEK SMALL LETTER OMEGA WITH PSILI AND PERISPOMENI AND YPOGEGRAMMENI
1FA7; F; 1F67 03B9; # GREEK SMALL LETTER OMEGA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI
1FA8; F; 1F60 03B9; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND PROSGEGRAMMENI
1FA8; S; 1FA0; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND PROSGEGRAMMENI
1FA9; F; 1F61 03B9; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND PROSGEGRAMMENI
1FA9; S; 1FA1; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND PROSGEGRAMMENI
1FAA; F; 1F62 03B9; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND VARIA AND PROSGEGRAMMENI
1FAA; S; 1FA2; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND VARIA AND PROSGEGRAMMENI
1FAB; F; 1F63 03B9; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND VARIA AND PROSGEGRAMMENI
1FAB; S; 1FA3; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND VARIA AND PROSGEGRAMMENI
1FAC; F; 1F64 03B9; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND OXIA AND PROSGEGRAMMENI
1FAC; S; 1FA4; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND OXIA AND PROSGEGRAMMENI
1FAD; F; 1F65 03B9; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND OXIA AND PROSGEGRAMMENI
1FAD; S; 1FA5; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND OXIA AND PROSGEGRAMMENI
1FAE; F; 1F66 03B9; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI
1FAE; S; 1FA6; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI
1FAF; F; 1F67 03B9; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI
1FAF; S; 1FA7; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI
1FB2; F; 1F70 03B9; # GREEK SMALL LETTER ALPHA WITH VARIA AND YPOGEGRAMMENI
1FB3; F; 03B1 03B9; # GREEK SMALL LETTER ALPHA WITH YPOGEGRAMMENI
1FB4; F; 03AC 03B9; # GREEK SMALL LETTER ALPHA WITH OXIA AND YPOGEGRAMMENI
1FB6; F; 03B1 0342; # GREEK SMALL LETTER ALPHA WITH PERISPOMENI
1FB7; F; 03B1 0342 03B9; # GREEK SMALL LETTER ALPHA WITH PERISPOMENI AND YPOGEGRAMMENI
1FB8; C; 1FB0; # GREEK CAPITAL LETTER ALPHA WITH VRACHY
1FB9; C; 1FB1; # GREEK CAPITAL LETTER ALPHA WITH MACRON
1FBA; C; 1F70; # GREEK CAPITAL LETTER ALPHA WITH VARIA
1FBB; C; 1F71; # GREEK CAPITAL LETTER ALPHA WITH OXIA
1FBC; F; 03B1 03B9; # GREEK CAPITAL LETTER ALPHA WITH PROSGEGRAMMENI
1FBC; S; 1FB3; # GREEK CAPITAL LETTER ALPHA WITH PROSGEGRAMMENI
1FBE; C; 03B9; # GREEK PROSGEGRAMMENI
1FC2; F; 1F74 03B9; # GREEK SMALL LETTER ETA WITH VARIA AND YPOGEGRAMMENI
1FC3; F; 03B7 03B9; # GREEK SMALL LETTER ETA WITH YPOGEGRAMMENI
1FC4; F; 03AE 03B9; # GREEK SMALL LETTER ETA WITH OXIA AND YPOGEGRAMMENI
1FC6; F; 03B7 0342; # GREEK SMALL LETTER ETA WITH PERISPOMENI
1FC7; F; 03B7 0342 03B9; # GREEK SMALL LETTER ETA WITH PERISPOMENI AND YPOGEGRAMMENI
1FC8; C; 1F72; # GREEK CAPITAL LETTER EPSILON WITH VARIA
1FC9; C; 1F73; # GREEK CAPITAL LETTER EPSILON WITH OXIA
1FCA; C; 1F74; # GREEK CAPITAL LETTER ETA WITH VARIA
1FCB; C; 1F75; # GREEK CAPITAL LETTER ETA WITH OXIA
1FCC; F; 03B7 03B9; # GREEK CAPITAL LETTER ETA WITH PROSGEGRAMMENI
1FCC; S; 1FC3; # GREEK CAPITAL LETTER ETA WITH PROSGEGRAMMENI
1FD2; F; 03B9 0308 0300; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND VARIA
1FD3; F; 03B9 0308 0301; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA
1FD6; F; 03B9 0342; # GREEK SMALL LETTER IOTA WITH PERISPOMENI
1FD7; F; 03B9 0308 0342; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND PERISPOMENI
1FD8; C; 1FD0; # GREEK CAPITAL LETTER IOTA WITH VRACHY
1FD9; C; 1FD1; # GREEK CAPITAL LETTER IOTA WITH MACRON
1FDA; C; 1F76; # GREEK CAPITAL LETTER IOTA WITH VARIA
1FDB; C; 1F77; # GREEK CAPITAL LETTER IOTA WITH OXIA
1FE2; F; 03C5 0308 0300; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND VARIA
1FE3; F; 03C5 0308 0301; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND OXIA
1FE4; F; 03C1 0313; # GREEK SMALL LETTER RHO WITH PSILI
1FE6; F; 03C5 0342; # GREEK SMALL LETTER UPSILON WITH PERISPOMENI
1FE7; F; 03C5 0308 0342; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND PERISPOMENI
1FE8; C; 1FE0; # GREEK CAPITAL LETTER UPSILON WITH VRACHY
1FE9; C; 1FE1; # GREEK CAPITAL LETTER UPSILON WITH MACRON
1FEA; C; 1F7A; # GREEK CAPITAL LETTER UPSILON WITH VARIA
1FEB; C; 1F7B; # GREEK CAPITAL LETTER UPSILON WITH OXIA
1FEC; C; 1FE5; # GREEK CAPITAL LETTER RHO WITH DASIA
1FF2; F; 1F7C 03B9; # GREEK SMALL LETTER OMEGA WITH VARIA AND YPOGEGRAMMENI
1FF3; F; 03C9 03B9; # GREEK SMALL LETTER OMEGA WITH YPOGEGRAMMENI
1FF4; F; 03CE 03B9; # GREEK SMALL LETTER OMEGA WITH OXIA AND YPOGEGRAMMENI
1FF6; F; 03C9 0342; # GREEK SMALL LETTER OMEGA WITH PERISPOMENI
1FF7; F; 03C9 0342 03B9; # GREEK SMALL LETTER OMEGA WITH PERISPOMENI AND YPOGEGRAMMENI
1FF8; C; 1F78; # GREEK CAPITAL LETTER OMICRON WITH VARIA
1FF9; C; 1F79; # GREEK CAPITAL LETTER OMICRON WITH OXIA
1FFA; C; 1F7C; # GREEK CAPITAL LETTER OMEGA WITH VARIA
1FFB; C; 1F7D; # GREEK CAPITAL LETTER OMEGA WITH OXIA
1FFC; F; 03C9 03B9; # GREEK CAPITAL LETTER OMEGA WITH PROSGEGRAMMENI
1FFC; S; 1FF3; # GREEK CAPITAL LETTER OMEGA WITH PROSGEGRAMMENI
2126; C; 03C9; # OHM SIGN
212A; C; 006B; # KELVIN SIGN
212B; C; 00E5; # ANGSTROM SIGN
2160; C; 2170; # ROMAN NUMERAL ONE
2161; C; 2171; # ROMAN NUMERAL TWO
2162; C; 2172; # ROMAN NUMERAL THREE
2163; C; 2173; # ROMAN NUMERAL FOUR
2164; C; 2174; # ROMAN NUMERAL FIVE
2165; C; 2175; # ROMAN NUMERAL SIX
2166; C; 2176; # ROMAN NUMERAL SEVEN
2167; C; 2177; # ROMAN NUMERAL EIGHT
2168; C; 2178; # ROMAN NUMERAL NINE
2169; C; 2179; # ROMAN NUMERAL TEN
216A; C; 217A; # ROMAN NUMERAL ELEVEN
216B; C; 217B; # ROMAN NUMERAL TWELVE
216C; C; 217C; # ROMAN NUMERAL FIFTY
216D; C; 217D; # ROMAN NUMERAL ONE HUNDRED
216E; C; 217E; # ROMAN NUMERAL FIVE HUNDRED
216F; C; 217F; # ROMAN NUMERAL ONE THOUSAND
24B6; C; 24D0; # CIRCLED LATIN CAPITAL LETTER A
24B7; C; 24D1; # CIRCLED LATIN CAPITAL LETTER B
24B8; C; 24D2; # CIRCLED LATIN CAPITAL LETTER C
24B9; C; 24D3; # CIRCLED LATIN CAPITAL LETTER D
24BA; C; 24D4; # CIRCLED LATIN CAPITAL LETTER E
24BB; C; 24D5; # CIRCLED LATIN CAPITAL LETTER F
24BC; C; 24D6; # CIRCLED LATIN CAPITAL LETTER G
24BD; C; 24D7; # CIRCLED LATIN CAPITAL LETTER H
24BE; C; 24D8; # CIRCLED LATIN CAPITAL LETTER I
24BF; C; 24D9; # CIRCLED LATIN CAPITAL LETTER J
24C0; C; 24DA; # CIRCLED LATIN CAPITAL LETTER K
24C1; C; 24DB; # CIRCLED LATIN CAPITAL LETTER L
24C2; C; 24DC; # CIRCLED LATIN CAPITAL LETTER M
24C3; C; 24DD; # CIRCLED LATIN CAPITAL LETTER N
24C4; C; 24DE; # CIRCLED LATIN CAPITAL LETTER O
24C5; C; 24DF; # CIRCLED LATIN CAPITAL LETTER P
24C6; C; 24E0; # CIRCLED LATIN CAPITAL LETTER Q
24C7; C; 24E1; # CIRCLED LATIN CAPITAL LETTER R
24C8; C; 24E2; # CIRCLED LATIN CAPITAL LETTER S
24C9; C; 24E3; # CIRCLED LATIN CAPITAL LETTER T
24CA; C; 24E4; # CIRCLED LATIN CAPITAL LETTER U
24CB; C; 24E5; # CIRCLED LATIN CAPITAL LETTER V
24CC; C; 24E6; # CIRCLED LATIN CAPITAL LETTER W
24CD; C; 24E7; # CIRCLED LATIN CAPITAL LETTER X
24CE; C; 24E8; # CIRCLED LATIN CAPITAL LETTER Y
24CF; C; 24E9; # CIRCLED LATIN CAPITAL LETTER Z
FB00; F; 0066 0066; # LATIN SMALL LIGATURE FF
FB01; F; 0066 0069; # LATIN SMALL LIGATURE FI
FB02; F; 0066 006C; # LATIN SMALL LIGATURE FL
FB03; F; 0066 0066 0069; # LATIN SMALL LIGATURE FFI
FB04; F; 0066 0066 006C; # LATIN SMALL LIGATURE FFL
FB05; F; 0073 0074; # LATIN SMALL LIGATURE LONG S T
FB06; F; 0073 0074; # LATIN SMALL LIGATURE ST
FB13; F; 0574 0576; # ARMENIAN SMALL LIGATURE MEN NOW
FB14; F; 0574 0565; # ARMENIAN SMALL LIGATURE MEN ECH
FB15; F; 0574 056B; # ARMENIAN SMALL LIGATURE MEN INI
FB16; F; 057E 0576; # ARMENIAN SMALL LIGATURE VEW NOW
FB17; F; 0574 056D; # ARMENIAN SMALL LIGATURE MEN XEH
FF21; C; FF41; # FULLWIDTH LATIN CAPITAL LETTER A
FF22; C; FF42; # FULLWIDTH LATIN CAPITAL LETTER B
FF23; C; FF43; # FULLWIDTH LATIN CAPITAL LETTER C
FF24; C; FF44; # FULLWIDTH LATIN CAPITAL LETTER D
FF25; C; FF45; # FULLWIDTH LATIN CAPITAL LETTER E
FF26; C; FF46; # FULLWIDTH LATIN CAPITAL LETTER F
FF27; C; FF47; # FULLWIDTH LATIN CAPITAL LETTER G
FF28; C; FF48; # FULLWIDTH LATIN CAPITAL LETTER H
FF29; C; FF49; # FULLWIDTH LATIN CAPITAL LETTER I
FF2A; C; FF4A; # FULLWIDTH LATIN CAPITAL LETTER J
FF2B; C; FF4B; # FULLWIDTH LATIN CAPITAL LETTER K
FF2C; C; FF4C; # FULLWIDTH LATIN CAPITAL LETTER L
FF2D; C; FF4D; # FULLWIDTH LATIN CAPITAL LETTER M
FF2E; C; FF4E; # FULLWIDTH LATIN CAPITAL LETTER N
FF2F; C; FF4F; # FULLWIDTH LATIN CAPITAL LETTER O
FF30; C; FF50; # FULLWIDTH LATIN CAPITAL LETTER P
FF31; C; FF51; # FULLWIDTH LATIN CAPITAL LETTER Q
FF32; C; FF52; # FULLWIDTH LATIN CAPITAL LETTER R
FF33; C; FF53; # FULLWIDTH LATIN CAPITAL LETTER S
FF34; C; FF54; # FULLWIDTH LATIN CAPITAL LETTER T
FF35; C; FF55; # FULLWIDTH LATIN CAPITAL LETTER U
FF36; C; FF56; # FULLWIDTH LATIN CAPITAL LETTER V
FF37; C; FF57; # FULLWIDTH LATIN CAPITAL LETTER W
FF38; C; FF58; # FULLWIDTH LATIN CAPITAL LETTER X
FF39; C; FF59; # FULLWIDTH LATIN CAPITAL LETTER Y
FF3A; C; FF5A; # FULLWIDTH LATIN CAPITAL LETTER Z
10400; C; 10428; # DESERET CAPITAL LETTER LONG I
10401; C; 10429; # DESERET CAPITAL LETTER LONG E
10402; C; 1042A; # DESERET CAPITAL LETTER LONG A
10403; C; 1042B; # DESERET CAPITAL LETTER LONG AH
10404; C; 1042C; # DESERET CAPITAL LETTER LONG O
10405; C; 1042D; # DESERET CAPITAL LETTER LONG OO
10406; C; 1042E; # DESERET CAPITAL LETTER SHORT I
10407; C; 1042F; # DESERET CAPITAL LETTER SHORT E
10408; C; 10430; # DESERET CAPITAL LETTER SHORT A
10409; C; 10431; # DESERET CAPITAL LETTER SHORT AH
1040A; C; 10432; # DESERET CAPITAL LETTER SHORT O
1040B; C; 10433; # DESERET CAPITAL LETTER SHORT OO
1040C; C; 10434; # DESERET CAPITAL LETTER AY
1040D; C; 10435; # DESERET CAPITAL LETTER OW
1040E; C; 10436; # DESERET CAPITAL LETTER WU
1040F; C; 10437; # DESERET CAPITAL LETTER YEE
10410; C; 10438; # DESERET CAPITAL LETTER H
10411; C; 10439; # DESERET CAPITAL LETTER PEE
10412; C; 1043A; # DESERET CAPITAL LETTER BEE
10413; C; 1043B; # DESERET CAPITAL LETTER TEE
10414; C; 1043C; # DESERET CAPITAL LETTER DEE
10415; C; 1043D; # DESERET CAPITAL LETTER CHEE
10416; C; 1043E; # DESERET CAPITAL LETTER JEE
10417; C; 1043F; # DESERET CAPITAL LETTER KAY
10418; C; 10440; # DESERET CAPITAL LETTER GAY
10419; C; 10441; # DESERET CAPITAL LETTER EF
1041A; C; 10442; # DESERET CAPITAL LETTER VEE
1041B; C; 10443; # DESERET CAPITAL LETTER ETH
1041C; C; 10444; # DESERET CAPITAL LETTER THEE
1041D; C; 10445; # DESERET CAPITAL LETTER ES
1041E; C; 10446; # DESERET CAPITAL LETTER ZEE
1041F; C; 10447; # DESERET CAPITAL LETTER ESH
10420; C; 10448; # DESERET CAPITAL LETTER ZHEE
10421; C; 10449; # DESERET CAPITAL LETTER ER
10422; C; 1044A; # DESERET CAPITAL LETTER EL
10423; C; 1044B; # DESERET CAPITAL LETTER EM
10424; C; 1044C; # DESERET CAPITAL LETTER EN
10425; C; 1044D; # DESERET CAPITAL LETTER ENG

151
outside/commonmark/dingus.html Normal file
View File

@ -0,0 +1,151 @@
<!doctype html>
<html lang="en">
<head>
<meta charset="utf-8">
<title>commonmark.js demo</title>
<script src="//code.jquery.com/jquery-1.11.0.min.js"></script>
<script src="//maxcdn.bootstrapcdn.com/bootstrap/3.1.1/js/bootstrap.min.js"></script>
<link href="//maxcdn.bootstrapcdn.com/bootstrap/3.1.1/css/bootstrap.min.css" rel="stylesheet">
<script src="js/commonmark.js"></script>
<script type="text/javascript">
var writer = new commonmark.HtmlRenderer();
var reader = new commonmark.DocParser();
function getQueryVariable(variable)
{
var query = window.location.search.substring(1);
var vars = query.split("&");
for (var i=0;i<vars.length;i++) {
var pair = vars[i].split("=");
if(pair[0] == variable){return decodeURIComponent(pair[1]);}
}
return null;
}
$(document).ready(function() {
var timer;
var x;
var parsed;
var render = function() {
if (parsed === undefined) {
return;
}
var startTime = new Date().getTime();
var result = writer.renderBlock(parsed);
var endTime = new Date().getTime();
var renderTime = endTime - startTime;
// $("#html").text(result);
$("#preview").html(result);
$("#html").text(result);
$("#ast").text(commonmark.ASTRenderer(parsed));
$("#rendertime").text(renderTime);
};
var parseAndRender = function () {
if (x) { x.abort() } // If there is an existing XHR, abort it.
clearTimeout(timer); // Clear the timer so we don't end up with dupes.
timer = setTimeout(function() { // assign timer a new timeout
var startTime = new Date().getTime();
parsed = reader.parse($("#text").val());
var endTime = new Date().getTime();
var parseTime = endTime - startTime;
$("#parsetime").text(parseTime);
$(".timing").css('visibility','visible');
/*
var warnings = parsed.warnings;
$("#warnings").html('');
for (i=0; i < warnings.length; i++) {
var w = warnings[i];
var warning = $("#warnings").append('<li></li>');
$("#warnings li").last().text('Line ' + w.line + ' column ' + w.column + ': ' + w.message);
}
*/
render();
}, 0); // ms delay
};
var initial_text = getQueryVariable("text");
if (initial_text) {
$("#text").val(initial_text);
// show HTML tab if text is from query
$('#result-tabs a[href="#result"]').tab('show');
}
// make tab insert a tab in the text box:
$("#text").keydown(function (e) {
if (e.which == 9) {
e.preventDefault();
this.value += "\t";
}
});
parseAndRender();
$("#clear-text-box").click(function(e) {
$("#text").val('');
window.location.search = "";
parseAndRender();
});
$("#permalink").click(function(e) {
window.location.pathname = "/index.html";
window.location.search = "text=" + encodeURIComponent($("#text").val());
});
$("#text").bind('keyup paste cut mouseup', parseAndRender);
$(".option").change(render);
});
</script>
<style type="text/css">
h1.title { font-family: monospace; font-size: 120%; font-weight: bold;
margin-top: 0.5em; margin-bottom: 0; }
textarea#text { height: 400px; width: 95%; font-family: monospace; font-size: 92%; }
pre code#html { font-size: 92%; font-family: monospace; }
pre#htmlpre { height: 400px; overflow: scroll; resize: vertical; width: 95%; }
div#astpre { height: 400px; overflow: scroll; resize: vertical; width: 95%; }
div#preview { height: 400px; overflow: scroll; resize: vertical; width: 95%; }
div.row { margin-top: 1em; }
blockquote { font-size: 100%; }
footer { color: #555; text-align: center; margin: 1em; }
pre { display: block; padding: 0.5em; color: #333; background: #f8f8ff }
#warnings li { color: red; font-weight: bold; }
label { padding-left: 1em; padding-top: 0; padding-bottom: 0; }
div.timing { color: gray; visibility: hidden; height: 2em; }
p#text-controls { height: 1em; margin-top: 1em; }
a#permalink { margin-left: 1em; }
span.timing { font-weight: bold; }
span.timing { font-weight: bold; }
</style>
</head>
<body>
<div class="container">
<div class="row">
<div class="col-md-6">
<h1 class="title">commonmark.js dingus</h1>
</div>
</div>
<div class="row">
<div class="col-md-6">
<p id="text-controls"><a id="clear-text-box">clear</a>&nbsp;<a
id="permalink">permalink</a></p>
<textarea id="text"></textarea>
<ul id="warnings"></ul>
<div class="timing">Parsed in <span class="timing" id="parsetime"></span>
ms. Rendered in <span class="timing" id="rendertime"></span> ms.</div>
</div>
<div class="col-md-6">
<ul id="result-tabs" class="nav nav-tabs" role="tablist">
<li class="active"><a href="#preview" role="tab" data-toggle="tab">Preview</a></li>
<li><a href="#result" role="tab" data-toggle="tab">HTML</a></li>
<li><a href="#result-ast" role="tab" data-toggle="tab">AST</a></li>
</ul>
<div class="tab-content">
<div id="preview" class="tab-pane active">
</div>
<div id="result" class="tab-pane">
<pre id="htmlpre"><code id="html"></code></pre>
</div>
<div id="result-ast" class="tab-pane">
<pre id="astpre"><code id="ast"></code></pre>
</div>
</div>
</div>
</div>
</div>
</body>
</html>

3
outside/commonmark/js/.npmignore Normal file
View File

@ -0,0 +1,3 @@
commonmark.js
*.tgz
index.html

30
outside/commonmark/js/LICENSE Normal file
View File

@ -0,0 +1,30 @@
Copyright (c) 2014, John MacFarlane
All rights reserved.
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright
notice, this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above
copyright notice, this list of conditions and the following
disclaimer in the documentation and/or other materials provided
with the distribution.
* Neither the name of John MacFarlane nor the names of other
contributors may be used to endorse or promote products derived
from this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

24
outside/commonmark/js/README.md Normal file
View File

@ -0,0 +1,24 @@
CommonMark
==========
CommonMark is a rationalized version of Markdown syntax,
with a [spec][the spec] and BSD3-licensed reference
implementations in C and JavaScript.
For more information, see <http://commonmark.org>.
To play with this library without installing it, see
the live dingus at <http://spec.commonmark.org/dingus.html>.
This package includes the commonmark library and a
command-line executable, `commonmark`.
Basic usage example:
var reader = new commonmark.DocParser();
var writer = new commonmark.HtmlRenderer();
var parsed = reader.parse("Hello *world*");
var result = writer.render(parsed);
[the spec]: http://spec.commonmark.org

405
outside/commonmark/js/ansi/ansi.js Normal file
View File

@ -0,0 +1,405 @@
/**
* References:
*
* - http://en.wikipedia.org/wiki/ANSI_escape_code
* - http://www.termsys.demon.co.uk/vtansi.htm
*
*/
/**
* Module dependencies.
*/
var emitNewlineEvents = require('./newlines')
, prefix = '\x1b[' // For all escape codes
, suffix = 'm' // Only for color codes
/**
* The ANSI escape sequences.
*/
var codes = {
up: 'A'
, down: 'B'
, forward: 'C'
, back: 'D'
, nextLine: 'E'
, previousLine: 'F'
, horizontalAbsolute: 'G'
, eraseData: 'J'
, eraseLine: 'K'
, scrollUp: 'S'
, scrollDown: 'T'
, savePosition: 's'
, restorePosition: 'u'
, queryPosition: '6n'
, hide: '?25l'
, show: '?25h'
}
/**
* Rendering ANSI codes.
*/
var styles = {
bold: 1
, italic: 3
, underline: 4
, inverse: 7
}
/**
* The negating ANSI code for the rendering modes.
*/
var reset = {
bold: 22
, italic: 23
, underline: 24
, inverse: 27
}
/**
* The standard, styleable ANSI colors.
*/
var colors = {
white: 37
, black: 30
, blue: 34
, cyan: 36
, green: 32
, magenta: 35
, red: 31
, yellow: 33
, grey: 90
, brightBlack: 90
, brightRed: 91
, brightGreen: 92
, brightYellow: 93
, brightBlue: 94
, brightMagenta: 95
, brightCyan: 96
, brightWhite: 97
}
/**
* Creates a Cursor instance based off the given `writable stream` instance.
*/
function ansi (stream, options) {
if (stream._ansicursor) {
return stream._ansicursor
} else {
return stream._ansicursor = new Cursor(stream, options)
}
}
module.exports = exports = ansi
/**
* The `Cursor` class.
*/
function Cursor (stream, options) {
if (!(this instanceof Cursor)) {
return new Cursor(stream, options)
}
if (typeof stream != 'object' || typeof stream.write != 'function') {
throw new Error('a valid Stream instance must be passed in')
}
// the stream to use
this.stream = stream
// when 'enabled' is false then all the functions are no-ops except for write()
this.enabled = options && options.enabled
if (typeof this.enabled === 'undefined') {
this.enabled = stream.isTTY
}
this.enabled = !!this.enabled
// then `buffering` is true, then `write()` calls are buffered in
// memory until `flush()` is invoked
this.buffering = !!(options && options.buffering)
this._buffer = []
// controls the foreground and background colors
this.fg = this.foreground = new Colorer(this, 0)
this.bg = this.background = new Colorer(this, 10)
// defaults
this.Bold = false
this.Italic = false
this.Underline = false
this.Inverse = false
// keep track of the number of "newlines" that get encountered
this.newlines = 0
emitNewlineEvents(stream)
stream.on('newline', function () {
this.newlines++
}.bind(this))
}
exports.Cursor = Cursor
/**
* Helper function that calls `write()` on the underlying Stream.
* Returns `this` instead of the write() return value to keep
* the chaining going.
*/
Cursor.prototype.write = function (data) {
if (this.buffering) {
this._buffer.push(arguments)
} else {
this.stream.write.apply(this.stream, arguments)
}
return this
}
/**
* Buffer `write()` calls into memory.
*
* @api public
*/
Cursor.prototype.buffer = function () {
this.buffering = true
return this
}
/**
* Write out the in-memory buffer.
*
* @api public
*/
Cursor.prototype.flush = function () {
this.buffering = false
var str = this._buffer.map(function (args) {
if (args.length != 1) throw new Error('unexpected args length! ' + args.length);
return args[0];
}).join('');
this._buffer.splice(0); // empty
this.write(str);
return this
}
/**
* The `Colorer` class manages both the background and foreground colors.
*/
function Colorer (cursor, base) {
this.current = null
this.cursor = cursor
this.base = base
}
exports.Colorer = Colorer
/**
* Write an ANSI color code, ensuring that the same code doesn't get rewritten.
*/
Colorer.prototype._setColorCode = function setColorCode (code) {
var c = String(code)
if (this.current === c) return
this.cursor.enabled && this.cursor.write(prefix + c + suffix)
this.current = c
return this
}
/**
* Set up the positional ANSI codes.
*/
Object.keys(codes).forEach(function (name) {
var code = String(codes[name])
Cursor.prototype[name] = function () {
var c = code
if (arguments.length > 0) {
c = toArray(arguments).map(Math.round).join(';') + code
}
this.enabled && this.write(prefix + c)
return this
}
})
/**
* Set up the functions for the rendering ANSI codes.
*/
Object.keys(styles).forEach(function (style) {
var name = style[0].toUpperCase() + style.substring(1)
, c = styles[style]
, r = reset[style]
Cursor.prototype[style] = function () {
if (this[name]) return
this.enabled && this.write(prefix + c + suffix)
this[name] = true
return this
}
Cursor.prototype['reset' + name] = function () {
if (!this[name]) return
this.enabled && this.write(prefix + r + suffix)
this[name] = false
return this
}
})
/**
* Setup the functions for the standard colors.
*/
Object.keys(colors).forEach(function (color) {
var code = colors[color]
Colorer.prototype[color] = function () {
this._setColorCode(this.base + code)
return this.cursor
}
Cursor.prototype[color] = function () {
return this.foreground[color]()
}
})
/**
* Makes a beep sound!
*/
Cursor.prototype.beep = function () {
this.enabled && this.write('\x07')
return this
}
/**
* Moves cursor to specific position
*/
Cursor.prototype.goto = function (x, y) {
x = x | 0
y = y | 0
this.enabled && this.write(prefix + y + ';' + x + 'H')
return this
}
/**
* Resets the color.
*/
Colorer.prototype.reset = function () {
this._setColorCode(this.base + 39)
return this.cursor
}
/**
* Resets all ANSI formatting on the stream.
*/
Cursor.prototype.reset = function () {
this.enabled && this.write(prefix + '0' + suffix)
this.Bold = false
this.Italic = false
this.Underline = false
this.Inverse = false
this.foreground.current = null
this.background.current = null
return this
}
/**
* Sets the foreground color with the given RGB values.
* The closest match out of the 216 colors is picked.
*/
Colorer.prototype.rgb = function (r, g, b) {
var base = this.base + 38
, code = rgb(r, g, b)
this._setColorCode(base + ';5;' + code)
return this.cursor
}
/**
* Same as `cursor.fg.rgb(r, g, b)`.
*/
Cursor.prototype.rgb = function (r, g, b) {
return this.foreground.rgb(r, g, b)
}
/**
* Accepts CSS color codes for use with ANSI escape codes.
* For example: `#FF000` would be bright red.
*/
Colorer.prototype.hex = function (color) {
return this.rgb.apply(this, hex(color))
}
/**
* Same as `cursor.fg.hex(color)`.
*/
Cursor.prototype.hex = function (color) {
return this.foreground.hex(color)
}
// UTIL FUNCTIONS //
/**
* Translates a 255 RGB value to a 0-5 ANSI RGV value,
* then returns the single ANSI color code to use.
*/
function rgb (r, g, b) {
var red = r / 255 * 5
, green = g / 255 * 5
, blue = b / 255 * 5
return rgb5(red, green, blue)
}
/**
* Turns rgb 0-5 values into a single ANSI color code to use.
*/
function rgb5 (r, g, b) {
var red = Math.round(r)
, green = Math.round(g)
, blue = Math.round(b)
return 16 + (red*36) + (green*6) + blue
}
/**
* Accepts a hex CSS color code string (# is optional) and
* translates it into an Array of 3 RGB 0-255 values, which
* can then be used with rgb().
*/
function hex (color) {
var c = color[0] === '#' ? color.substring(1) : color
, r = c.substring(0, 2)
, g = c.substring(2, 4)
, b = c.substring(4, 6)
return [parseInt(r, 16), parseInt(g, 16), parseInt(b, 16)]
}
/**
* Turns an array-like object into a real array.
*/
function toArray (a) {
var i = 0
, l = a.length
, rtn = []
for (; i<l; i++) {
rtn.push(a[i])
}
return rtn
}

71
outside/commonmark/js/ansi/newlines.js Normal file
View File

@ -0,0 +1,71 @@
/**
* Accepts any node Stream instance and hijacks its "write()" function,
* so that it can count any newlines that get written to the output.
*
* When a '\n' byte is encountered, then a "newline" event will be emitted
* on the stream, with no arguments. It is up to the listeners to determine
* any necessary deltas required for their use-case.
*
* Ex:
*
* var cursor = ansi(process.stdout)
* , ln = 0
* process.stdout.on('newline', function () {
* ln++
* })
*/
/**
* Module dependencies.
*/
var assert = require('assert')
var NEWLINE = '\n'.charCodeAt(0)
function emitNewlineEvents (stream) {
if (stream._emittingNewlines) {
// already emitting newline events
return
}
var write = stream.write
stream.write = function (data) {
// first write the data
var rtn = write.apply(stream, arguments)
if (stream.listeners('newline').length > 0) {
var len = data.length
, i = 0
// now try to calculate any deltas
if (typeof data == 'string') {
for (; i<len; i++) {
processByte(stream, data.charCodeAt(i))
}
} else {
// buffer
for (; i<len; i++) {
processByte(stream, data[i])
}
}
}
return rtn
}
stream._emittingNewlines = true
}
module.exports = emitNewlineEvents
/**
* Processes an individual byte being written to a stream
*/
function processByte (stream, b) {
assert.equal(typeof b, 'number')
if (b === NEWLINE) {
stream.emit('newline')
}
}

35
outside/commonmark/js/bench.js Normal file
View File

@ -0,0 +1,35 @@
var Benchmark = require('benchmark').Benchmark;
var suite = new Benchmark.Suite;
var fs = require('fs');
var sm = require('./lib/index.js');
// https://github.com/coreyti/showdown
var showdown = require('../../showdown/src/showdown');
// https://github.com/chjj/marked
var marked = require('../../marked/marked.min.js');
var benchfile = process.argv[2];
var contents = fs.readFileSync(benchfile, 'utf8');
// var converter = new showdown.converter();
suite.add('commonmark.js markdown->html', function() {
var doc = new sm.DocParser().parse(contents);
var renderer = new sm.HtmlRenderer();
renderer.renderBlock(doc);
})
.add('showdown.js markdown->html', function() {
var converter = new showdown.converter();
converter.makeHtml(contents);
})
.add('marked.js markdown->html', function() {
marked(contents);
})
.on('cycle', function(event) {
console.log(String(event.target));
})
.run();

33
outside/commonmark/js/bin/commonmark Executable file
View File

@ -0,0 +1,33 @@
#!/usr/bin/env node
var fs = require('fs');
var util = require('util');
var commonmark = require('../lib/index.js');
var parser = new commonmark.DocParser();
var renderer;
var inps = [];
var output_ast = false;
var files = [];
if (process.argv[2] === '--ast') {
output_ast = true;
files = process.argv.slice(3);
renderer = { render: function(x) {
return util.inspect(x, null, Infinity) + '\n';
} };
} else {
files = process.argv.slice(2);
renderer = new commonmark.HtmlRenderer();
}
if (files.length === 0) {
files = ['/dev/stdin'];
}
for (var i = 0; i < files.length; i++) {
file = files[i];
inps.push(fs.readFileSync(file, 'utf8'));
}
process.stdout.write(renderer.render(parser.parse(inps.join('\n'))));

12
outside/commonmark/js/index.html Normal file
View File

@ -0,0 +1,12 @@
<!DOCTYPE html>
<html>
<head>
<title>CommonMark dingus</title>
<meta http-equiv="refresh" content="0;URL='/dingus.html" >
</head>
<body>
<p>The most recent version of the CommonMark dingus can be found
at <a
href="http://try.commonmark.org/dingus.html/">/dingus.html/</a>.</p>
</body>
</html>

698
outside/commonmark/js/lib/blocks.js Normal file
View File

@ -0,0 +1,698 @@
var C_GREATERTHAN = 62;
var C_SPACE = 32;
var C_OPEN_BRACKET = 91;
var InlineParser = require('./inlines');
var unescapeString = new InlineParser().unescapeString;
// Returns true if string contains only space characters.
var isBlank = function(s) {
return /^\s*$/.test(s);
};
// Convert tabs to spaces on each line using a 4-space tab stop.
var detabLine = function(text) {
if (text.indexOf('\t') == -1) {
return text;
} else {
var lastStop = 0;
return text.replace(/\t/g, function(match, offset) {
var result = ' '.slice((offset - lastStop) % 4);
lastStop = offset + 1;
return result;
});
}
};
// Attempt to match a regex in string s at offset offset.
// Return index of match or -1.
var matchAt = function(re, s, offset) {
var res = s.slice(offset).match(re);
if (res) {
return offset + res.index;
} else {
return -1;
}
};
var BLOCKTAGNAME = '(?:article|header|aside|hgroup|iframe|blockquote|hr|body|li|map|button|object|canvas|ol|caption|output|col|p|colgroup|pre|dd|progress|div|section|dl|table|td|dt|tbody|embed|textarea|fieldset|tfoot|figcaption|th|figure|thead|footer|footer|tr|form|ul|h1|h2|h3|h4|h5|h6|video|script|style)';
var HTMLBLOCKOPEN = "<(?:" + BLOCKTAGNAME + "[\\s/>]" + "|" +
"/" + BLOCKTAGNAME + "[\\s>]" + "|" + "[?!])";
var reHtmlBlockOpen = new RegExp('^' + HTMLBLOCKOPEN, 'i');
var reHrule = /^(?:(?:\* *){3,}|(?:_ *){3,}|(?:- *){3,}) *$/;
// DOC PARSER
// These are methods of a DocParser object, defined below.
var makeBlock = function(tag, start_line, start_column) {
return { t: tag,
open: true,
last_line_blank: false,
start_line: start_line,
start_column: start_column,
end_line: start_line,
children: [],
parent: null,
// string_content is formed by concatenating strings, in finalize:
string_content: "",
strings: [],
inline_content: []
};
};
// Returns true if parent block can contain child block.
var canContain = function(parent_type, child_type) {
return ( parent_type == 'Document' ||
parent_type == 'BlockQuote' ||
parent_type == 'ListItem' ||
(parent_type == 'List' && child_type == 'ListItem') );
};
// Returns true if block type can accept lines of text.
var acceptsLines = function(block_type) {
return ( block_type == 'Paragraph' ||
block_type == 'IndentedCode' ||
block_type == 'FencedCode' );
};
// Returns true if block ends with a blank line, descending if needed
// into lists and sublists.
var endsWithBlankLine = function(block) {
if (block.last_line_blank) {
return true;
}
if ((block.t == 'List' || block.t == 'ListItem') && block.children.length > 0) {
return endsWithBlankLine(block.children[block.children.length - 1]);
} else {
return false;
}
};
// Break out of all containing lists, resetting the tip of the
// document to the parent of the highest list, and finalizing
// all the lists. (This is used to implement the "two blank lines
// break of of all lists" feature.)
var breakOutOfLists = function(block, line_number) {
var b = block;
var last_list = null;
do {
if (b.t === 'List') {
last_list = b;
}
b = b.parent;
} while (b);
if (last_list) {
while (block != last_list) {
this.finalize(block, line_number);
block = block.parent;
}
this.finalize(last_list, line_number);
this.tip = last_list.parent;
}
};
// Add a line to the block at the tip. We assume the tip
// can accept lines -- that check should be done before calling this.
var addLine = function(ln, offset) {
var s = ln.slice(offset);
if (!(this.tip.open)) {
throw({ msg: "Attempted to add line (" + ln + ") to closed container." });
}
this.tip.strings.push(s);
};
// Add block of type tag as a child of the tip. If the tip can't
// accept children, close and finalize it and try its parent,
// and so on til we find a block that can accept children.
var addChild = function(tag, line_number, offset) {
while (!canContain(this.tip.t, tag)) {
this.finalize(this.tip, line_number);
}
var column_number = offset + 1; // offset 0 = column 1
var newBlock = makeBlock(tag, line_number, column_number);
this.tip.children.push(newBlock);
newBlock.parent = this.tip;
this.tip = newBlock;
return newBlock;
};
// Parse a list marker and return data on the marker (type,
// start, delimiter, bullet character, padding) or null.
var parseListMarker = function(ln, offset) {
var rest = ln.slice(offset);
var match;
var spaces_after_marker;
var data = {};
if (rest.match(reHrule)) {
return null;
}
if ((match = rest.match(/^[*+-]( +|$)/))) {
spaces_after_marker = match[1].length;
data.type = 'Bullet';
data.bullet_char = match[0][0];
} else if ((match = rest.match(/^(\d+)([.)])( +|$)/))) {
spaces_after_marker = match[3].length;
data.type = 'Ordered';
data.start = parseInt(match[1]);
data.delimiter = match[2];
} else {
return null;
}
var blank_item = match[0].length === rest.length;
if (spaces_after_marker >= 5 ||
spaces_after_marker < 1 ||
blank_item) {
data.padding = match[0].length - spaces_after_marker + 1;
} else {
data.padding = match[0].length;
}
return data;
};
// Returns true if the two list items are of the same type,
// with the same delimiter and bullet character. This is used
// in agglomerating list items into lists.
var listsMatch = function(list_data, item_data) {
return (list_data.type === item_data.type &&
list_data.delimiter === item_data.delimiter &&
list_data.bullet_char === item_data.bullet_char);
};
// Analyze a line of text and update the document appropriately.
// We parse markdown text by calling this on each line of input,
// then finalizing the document.
var incorporateLine = function(ln, line_number) {
var all_matched = true;
var last_child;
var first_nonspace;
var offset = 0;
var match;
var data;
var blank;
var indent;
var last_matched_container;
var i;
var CODE_INDENT = 4;
var container = this.doc;
var oldtip = this.tip;
// Convert tabs to spaces:
ln = detabLine(ln);
// For each containing block, try to parse the associated line start.
// Bail out on failure: container will point to the last matching block.
// Set all_matched to false if not all containers match.
while (container.children.length > 0) {
last_child = container.children[container.children.length - 1];
if (!last_child.open) {
break;
}
container = last_child;
match = matchAt(/[^ ]/, ln, offset);
if (match === -1) {
first_nonspace = ln.length;
blank = true;
} else {
first_nonspace = match;
blank = false;
}
indent = first_nonspace - offset;
switch (container.t) {
case 'BlockQuote':
if (indent <= 3 && ln.charCodeAt(first_nonspace) === C_GREATERTHAN) {
offset = first_nonspace + 1;
if (ln.charCodeAt(offset) === C_SPACE) {
offset++;
}
} else {
all_matched = false;
}
break;
case 'ListItem':
if (indent >= container.list_data.marker_offset +
container.list_data.padding) {
offset += container.list_data.marker_offset +
container.list_data.padding;
} else if (blank) {
offset = first_nonspace;
} else {
all_matched = false;
}
break;
case 'IndentedCode':
if (indent >= CODE_INDENT) {
offset += CODE_INDENT;
} else if (blank) {
offset = first_nonspace;
} else {
all_matched = false;
}
break;
case 'Header':
case 'HorizontalRule':
// a header can never container > 1 line, so fail to match:
all_matched = false;
if (blank) {
container.last_line_blank = true;
}
break;
case 'FencedCode':
// skip optional spaces of fence offset
i = container.fence_offset;
while (i > 0 && ln.charCodeAt(offset) === C_SPACE) {
offset++;
i--;
}
break;
case 'HtmlBlock':
if (blank) {
container.last_line_blank = true;
all_matched = false;
}
break;
case 'Paragraph':
if (blank) {
container.last_line_blank = true;
all_matched = false;
}
break;
default:
}
if (!all_matched) {
container = container.parent; // back up to last matching block
break;
}
}
last_matched_container = container;
// This function is used to finalize and close any unmatched
// blocks. We aren't ready to do this now, because we might
// have a lazy paragraph continuation, in which case we don't
// want to close unmatched blocks. So we store this closure for
// use later, when we have more information.
var closeUnmatchedBlocks = function(mythis) {
// finalize any blocks not matched
while (!already_done && oldtip != last_matched_container) {
mythis.finalize(oldtip, line_number);
oldtip = oldtip.parent;
}
var already_done = true;
};
// Check to see if we've hit 2nd blank line; if so break out of list:
if (blank && container.last_line_blank) {
this.breakOutOfLists(container, line_number);
}
// Unless last matched container is a code block, try new container starts,
// adding children to the last matched container:
while (container.t != 'FencedCode' &&
container.t != 'IndentedCode' &&
container.t != 'HtmlBlock' &&
// this is a little performance optimization:
matchAt(/^[ #`~*+_=<>0-9-]/,ln,offset) !== -1) {
match = matchAt(/[^ ]/, ln, offset);
if (match === -1) {
first_nonspace = ln.length;
blank = true;
} else {
first_nonspace = match;
blank = false;
}
indent = first_nonspace - offset;
if (indent >= CODE_INDENT) {
// indented code
if (this.tip.t != 'Paragraph' && !blank) {
offset += CODE_INDENT;
closeUnmatchedBlocks(this);
container = this.addChild('IndentedCode', line_number, offset);
} else { // indent > 4 in a lazy paragraph continuation
break;
}
} else if (ln.charCodeAt(first_nonspace) === C_GREATERTHAN) {
// blockquote
offset = first_nonspace + 1;
// optional following space
if (ln.charCodeAt(offset) === C_SPACE) {
offset++;
}
closeUnmatchedBlocks(this);
container = this.addChild('BlockQuote', line_number, offset);
} else if ((match = ln.slice(first_nonspace).match(/^#{1,6}(?: +|$)/))) {
// ATX header
offset = first_nonspace + match[0].length;
closeUnmatchedBlocks(this);
container = this.addChild('Header', line_number, first_nonspace);
container.level = match[0].trim().length; // number of #s
// remove trailing ###s:
container.strings =
[ln.slice(offset).replace(/^ *#+ *$/, '').replace(/ +#+ *$/,'')];
break;
} else if ((match = ln.slice(first_nonspace).match(/^`{3,}(?!.*`)|^~{3,}(?!.*~)/))) {
// fenced code block
var fence_length = match[0].length;
closeUnmatchedBlocks(this);
container = this.addChild('FencedCode', line_number, first_nonspace);
container.fence_length = fence_length;
container.fence_char = match[0][0];
container.fence_offset = first_nonspace - offset;
offset = first_nonspace + fence_length;
break;
} else if (matchAt(reHtmlBlockOpen, ln, first_nonspace) !== -1) {
// html block
closeUnmatchedBlocks(this);
container = this.addChild('HtmlBlock', line_number, first_nonspace);
// note, we don't adjust offset because the tag is part of the text
break;
} else if (container.t == 'Paragraph' &&
container.strings.length === 1 &&
((match = ln.slice(first_nonspace).match(/^(?:=+|-+) *$/)))) {
// setext header line
closeUnmatchedBlocks(this);
container.t = 'Header'; // convert Paragraph to SetextHeader
container.level = match[0][0] === '=' ? 1 : 2;
offset = ln.length;
} else if (matchAt(reHrule, ln, first_nonspace) !== -1) {
// hrule
closeUnmatchedBlocks(this);
container = this.addChild('HorizontalRule', line_number, first_nonspace);
offset = ln.length - 1;
break;
} else if ((data = parseListMarker(ln, first_nonspace))) {
// list item
closeUnmatchedBlocks(this);
data.marker_offset = indent;
offset = first_nonspace + data.padding;
// add the list if needed
if (container.t !== 'List' ||
!(listsMatch(container.list_data, data))) {
container = this.addChild('List', line_number, first_nonspace);
container.list_data = data;
}
// add the list item
container = this.addChild('ListItem', line_number, first_nonspace);
container.list_data = data;
} else {
break;
}
if (acceptsLines(container.t)) {
// if it's a line container, it can't contain other containers
break;
}
}
// What remains at the offset is a text line. Add the text to the
// appropriate container.
match = matchAt(/[^ ]/, ln, offset);
if (match === -1) {
first_nonspace = ln.length;
blank = true;
} else {
first_nonspace = match;
blank = false;
}
indent = first_nonspace - offset;
// First check for a lazy paragraph continuation:
if (this.tip !== last_matched_container &&
!blank &&
this.tip.t == 'Paragraph' &&
this.tip.strings.length > 0) {
// lazy paragraph continuation
this.last_line_blank = false;
this.addLine(ln, offset);
} else { // not a lazy continuation
// finalize any blocks not matched
closeUnmatchedBlocks(this);
// Block quote lines are never blank as they start with >
// and we don't count blanks in fenced code for purposes of tight/loose
// lists or breaking out of lists. We also don't set last_line_blank
// on an empty list item.
container.last_line_blank = blank &&
!(container.t == 'BlockQuote' ||
container.t == 'Header' ||
container.t == 'FencedCode' ||
(container.t == 'ListItem' &&
container.children.length === 0 &&
container.start_line == line_number));
var cont = container;
while (cont.parent) {
cont.parent.last_line_blank = false;
cont = cont.parent;
}
switch (container.t) {
case 'IndentedCode':
case 'HtmlBlock':
this.addLine(ln, offset);
break;
case 'FencedCode':
// check for closing code fence:
match = (indent <= 3 &&
ln.charAt(first_nonspace) == container.fence_char &&
ln.slice(first_nonspace).match(/^(?:`{3,}|~{3,})(?= *$)/));
if (match && match[0].length >= container.fence_length) {
// don't add closing fence to container; instead, close it:
this.finalize(container, line_number);
} else {
this.addLine(ln, offset);
}
break;
case 'Header':
case 'HorizontalRule':
// nothing to do; we already added the contents.
break;
default:
if (acceptsLines(container.t)) {
this.addLine(ln, first_nonspace);
} else if (blank) {
// do nothing
} else if (container.t != 'HorizontalRule' &&
container.t != 'Header') {
// create paragraph container for line
container = this.addChild('Paragraph', line_number, first_nonspace);
this.addLine(ln, first_nonspace);
} else {
console.log("Line " + line_number.toString() +
" with container type " + container.t +
" did not match any condition.");
}
}
}
};
// Finalize a block. Close it and do any necessary postprocessing,
// e.g. creating string_content from strings, setting the 'tight'
// or 'loose' status of a list, and parsing the beginnings
// of paragraphs for reference definitions. Reset the tip to the
// parent of the closed block.
var finalize = function(block, line_number) {
var pos;
// don't do anything if the block is already closed
if (!block.open) {
return 0;
}
block.open = false;
if (line_number > block.start_line) {
block.end_line = line_number - 1;
} else {
block.end_line = line_number;
}
switch (block.t) {
case 'Paragraph':
block.string_content = block.strings.join('\n').replace(/^ */m,'');
// delete block.strings;
// try parsing the beginning as link reference definitions:
while (block.string_content.charCodeAt(0) === C_OPEN_BRACKET &&
(pos = this.inlineParser.parseReference(block.string_content,
this.refmap))) {
block.string_content = block.string_content.slice(pos);
if (isBlank(block.string_content)) {
block.t = 'ReferenceDef';
break;
}
}
break;
case 'Header':
case 'HtmlBlock':
block.string_content = block.strings.join('\n');
break;
case 'IndentedCode':
block.string_content = block.strings.join('\n').replace(/(\n *)*$/,'\n');
block.t = 'CodeBlock';
break;
case 'FencedCode':
// first line becomes info string
block.info = unescapeString(block.strings[0].trim());
if (block.strings.length == 1) {
block.string_content = '';
} else {
block.string_content = block.strings.slice(1).join('\n') + '\n';
}
block.t = 'CodeBlock';
break;
case 'List':
block.tight = true; // tight by default
var numitems = block.children.length;
var i = 0;
while (i < numitems) {
var item = block.children[i];
// check for non-final list item ending with blank line:
var last_item = i == numitems - 1;
if (endsWithBlankLine(item) && !last_item) {
block.tight = false;
break;
}
// recurse into children of list item, to see if there are
// spaces between any of them:
var numsubitems = item.children.length;
var j = 0;
while (j < numsubitems) {
var subitem = item.children[j];
var last_subitem = j == numsubitems - 1;
if (endsWithBlankLine(subitem) && !(last_item && last_subitem)) {
block.tight = false;
break;
}
j++;
}
i++;
}
break;
default:
break;
}
this.tip = block.parent || this.top;
};
// Walk through a block & children recursively, parsing string content
// into inline content where appropriate. Returns new object.
var processInlines = function(block) {
var newblock = {};
newblock.t = block.t;
newblock.start_line = block.start_line;
newblock.start_column = block.start_column;
newblock.end_line = block.end_line;
switch(block.t) {
case 'Paragraph':
newblock.inline_content =
this.inlineParser.parse(block.string_content.trim(), this.refmap);
break;
case 'Header':
newblock.inline_content =
this.inlineParser.parse(block.string_content.trim(), this.refmap);
newblock.level = block.level;
break;
case 'List':
newblock.list_data = block.list_data;
newblock.tight = block.tight;
break;
case 'CodeBlock':
newblock.string_content = block.string_content;
newblock.info = block.info;
break;
case 'HtmlBlock':
newblock.string_content = block.string_content;
break;
default:
break;
}
if (block.children) {
var newchildren = [];
for (var i = 0; i < block.children.length; i++) {
newchildren.push(this.processInlines(block.children[i]));
}
newblock.children = newchildren;
}
return newblock;
};
// The main parsing function. Returns a parsed document AST.
var parse = function(input) {
this.doc = makeBlock('Document', 1, 1);
this.tip = this.doc;
this.refmap = {};
var lines = input.replace(/\n$/,'').split(/\r\n|\n|\r/);
var len = lines.length;
for (var i = 0; i < len; i++) {
this.incorporateLine(lines[i], i+1);
}
while (this.tip) {
this.finalize(this.tip, len - 1);
}
return this.processInlines(this.doc);
};
// The DocParser object.
function DocParser(){
return {
doc: makeBlock('Document', 1, 1),
tip: this.doc,
refmap: {},
inlineParser: new InlineParser(),
breakOutOfLists: breakOutOfLists,
addLine: addLine,
addChild: addChild,
incorporateLine: incorporateLine,
finalize: finalize,
processInlines: processInlines,
parse: parse
};
}
module.exports = DocParser;

58
outside/commonmark/js/lib/from-code-point.js Normal file
View File

@ -0,0 +1,58 @@
// derived from https://github.com/mathiasbynens/String.fromCodePoint
/*! http://mths.be/fromcodepoint v0.2.1 by @mathias */
if (String.fromCodePoint) {
module.exports = function (_) {
try {
return String.fromCodePoint(_);
} catch (e) {
if (e instanceof RangeError) {
return String.fromCharCode(0xFFFD);
}
throw e;
}
}
} else {
var stringFromCharCode = String.fromCharCode;
var floor = Math.floor;
var fromCodePoint = function(_) {
var MAX_SIZE = 0x4000;
var codeUnits = [];
var highSurrogate;
var lowSurrogate;
var index = -1;
var length = arguments.length;
if (!length) {
return '';
}
var result = '';
while (++index < length) {
var codePoint = Number(arguments[index]);
if (
!isFinite(codePoint) || // `NaN`, `+Infinity`, or `-Infinity`
codePoint < 0 || // not a valid Unicode code point
codePoint > 0x10FFFF || // not a valid Unicode code point
floor(codePoint) != codePoint // not an integer
) {
return String.fromCharCode(0xFFFD);
}
if (codePoint <= 0xFFFF) { // BMP code point
codeUnits.push(codePoint);
} else { // Astral code point; split in surrogate halves
// http://mathiasbynens.be/notes/javascript-encoding#surrogate-formulae
codePoint -= 0x10000;
highSurrogate = (codePoint >> 10) + 0xD800;
lowSurrogate = (codePoint % 0x400) + 0xDC00;
codeUnits.push(highSurrogate, lowSurrogate);
}
if (index + 1 == length || codeUnits.length > MAX_SIZE) {
result += stringFromCharCode.apply(null, codeUnits);
codeUnits.length = 0;
}
}
return result;
};
module.exports = fromCodePoint;
}

168
outside/commonmark/js/lib/html-renderer.js Normal file
View File

@ -0,0 +1,168 @@
// Helper function to produce content in a pair of HTML tags.
var inTags = function(tag, attribs, contents, selfclosing) {
var result = '<' + tag;
if (attribs) {
var i = 0;
var attrib;
while ((attrib = attribs[i]) !== undefined) {
result = result.concat(' ', attrib[0], '="', attrib[1], '"');
i++;
}
}
if (contents) {
result = result.concat('>', contents, '</', tag, '>');
} else if (selfclosing) {
result = result + ' />';
} else {
result = result.concat('></', tag, '>');
}
return result;
};
// Render an inline element as HTML.
var renderInline = function(inline) {
var attrs;
switch (inline.t) {
case 'Text':
return this.escape(inline.c);
case 'Softbreak':
return this.softbreak;
case 'Hardbreak':
return inTags('br',[],"",true) + '\n';
case 'Emph':
return inTags('em', [], this.renderInlines(inline.c));
case 'Strong':
return inTags('strong', [], this.renderInlines(inline.c));
case 'Html':
return inline.c;
case 'Link':
attrs = [['href', this.escape(inline.destination, true)]];
if (inline.title) {
attrs.push(['title', this.escape(inline.title, true)]);
}
return inTags('a', attrs, this.renderInlines(inline.label));
case 'Image':
attrs = [['src', this.escape(inline.destination, true)],
['alt', this.renderInlines(inline.label).
replace(/\<[^>]*alt="([^"]*)"[^>]*\>/g, '$1').
replace(/\<[^>]*\>/g,'')]];
if (inline.title) {
attrs.push(['title', this.escape(inline.title, true)]);
}
return inTags('img', attrs, "", true);
case 'Code':
return inTags('code', [], this.escape(inline.c));
default:
console.log("Unknown inline type " + inline.t);
return "";
}
};
// Render a list of inlines.
var renderInlines = function(inlines) {
var result = '';
for (var i=0; i < inlines.length; i++) {
result = result + this.renderInline(inlines[i]);
}
return result;
};
// Render a single block element.
var renderBlock = function(block, in_tight_list) {
var tag;
var attr;
var info_words;
switch (block.t) {
case 'Document':
var whole_doc = this.renderBlocks(block.children);
return (whole_doc === '' ? '' : whole_doc + '\n');
case 'Paragraph':
if (in_tight_list) {
return this.renderInlines(block.inline_content);
} else {
return inTags('p', [], this.renderInlines(block.inline_content));
}
break;
case 'BlockQuote':
var filling = this.renderBlocks(block.children);
return inTags('blockquote', [], filling === '' ? this.innersep :
this.innersep + filling + this.innersep);
case 'ListItem':
var contents = this.renderBlocks(block.children, in_tight_list);
if (/^[<]/.test(contents)) {
contents = '\n' + contents;
}
if (/[>]$/.test(contents)) {
contents = contents + '\n';
}
return inTags('li', [], contents, false).trim();
case 'List':
tag = block.list_data.type == 'Bullet' ? 'ul' : 'ol';
attr = (!block.list_data.start || block.list_data.start == 1) ?
[] : [['start', block.list_data.start.toString()]];
return inTags(tag, attr, this.innersep +
this.renderBlocks(block.children, block.tight) +
this.innersep);
case 'Header':
tag = 'h' + block.level;
return inTags(tag, [], this.renderInlines(block.inline_content));
case 'CodeBlock':
info_words = block.info ? block.info.split(/ +/) : [];
attr = (info_words.length === 0 || info_words[0].length === 0) ?
[] : [['class','language-' + this.escape(info_words[0],true)]];
return inTags('pre', [],
inTags('code', attr, this.escape(block.string_content)));
case 'HtmlBlock':
return block.string_content;
case 'ReferenceDef':
return "";
case 'HorizontalRule':
return inTags('hr',[],"",true);
default:
console.log("Unknown block type " + block.t);
return "";
}
};
// Render a list of block elements, separated by this.blocksep.
var renderBlocks = function(blocks, in_tight_list) {
var result = [];
for (var i=0; i < blocks.length; i++) {
if (blocks[i].t !== 'ReferenceDef') {
result.push(this.renderBlock(blocks[i], in_tight_list));
}
}
return result.join(this.blocksep);
};
// The HtmlRenderer object.
function HtmlRenderer(){
return {
// default options:
blocksep: '\n', // space between blocks
innersep: '\n', // space between block container tag and contents
softbreak: '\n', // by default, soft breaks are rendered as newlines in HTML
// set to "<br />" to make them hard breaks
// set to " " if you want to ignore line wrapping in source
escape: function(s, preserve_entities) {
if (preserve_entities) {
return s.replace(/[&](?![#](x[a-f0-9]{1,8}|[0-9]{1,8});|[a-z][a-z0-9]{1,31};)/gi,'&amp;')
.replace(/[<]/g,'&lt;')
.replace(/[>]/g,'&gt;')
.replace(/["]/g,'&quot;');
} else {
return s.replace(/[&]/g,'&amp;')
.replace(/[<]/g,'&lt;')
.replace(/[>]/g,'&gt;')
.replace(/["]/g,'&quot;');
}
},
renderInline: renderInline,
renderInlines: renderInlines,
renderBlock: renderBlock,
renderBlocks: renderBlocks,
render: renderBlock
};
}
module.exports = HtmlRenderer;

2147
outside/commonmark/js/lib/html5-entities.js Normal file
View File

File diff suppressed because it is too large Load Diff

20
outside/commonmark/js/lib/index.js Executable file
View File

@ -0,0 +1,20 @@
// commonmark.js - CommomMark in JavaScript
// Copyright (C) 2014 John MacFarlane
// License: BSD3.
// Basic usage:
//
// var commonmark = require('commonmark');
// var parser = new commonmark.DocParser();
// var renderer = new commonmark.HtmlRenderer();
// console.log(renderer.render(parser.parse('Hello *world*')));
var util = require('util');
var renderAST = function(tree) {
return util.inspect(tree, {depth: null});
};
module.exports.DocParser = require('./blocks');
module.exports.HtmlRenderer = require('./html-renderer');
module.exports.ASTRenderer = renderAST;

854
outside/commonmark/js/lib/inlines.js Normal file
View File

@ -0,0 +1,854 @@
var fromCodePoint = require('./from-code-point.js');
var entityToChar = require('./html5-entities.js').entityToChar;
// Constants for character codes:
var C_NEWLINE = 10;
var C_SPACE = 32;
var C_ASTERISK = 42;
var C_UNDERSCORE = 95;
var C_BACKTICK = 96;
var C_OPEN_BRACKET = 91;
var C_CLOSE_BRACKET = 93;
var C_LESSTHAN = 60;
var C_GREATERTHAN = 62;
var C_BANG = 33;
var C_BACKSLASH = 92;
var C_AMPERSAND = 38;
var C_OPEN_PAREN = 40;
var C_COLON = 58;
// Some regexps used in inline parser:
var ESCAPABLE = '[!"#$%&\'()*+,./:;<=>?@[\\\\\\]^_`{|}~-]';
var ESCAPED_CHAR = '\\\\' + ESCAPABLE;
var IN_DOUBLE_QUOTES = '"(' + ESCAPED_CHAR + '|[^"\\x00])*"';
var IN_SINGLE_QUOTES = '\'(' + ESCAPED_CHAR + '|[^\'\\x00])*\'';
var IN_PARENS = '\\((' + ESCAPED_CHAR + '|[^)\\x00])*\\)';
var REG_CHAR = '[^\\\\()\\x00-\\x20]';
var IN_PARENS_NOSP = '\\((' + REG_CHAR + '|' + ESCAPED_CHAR + ')*\\)';
var TAGNAME = '[A-Za-z][A-Za-z0-9]*';
var ATTRIBUTENAME = '[a-zA-Z_:][a-zA-Z0-9:._-]*';
var UNQUOTEDVALUE = "[^\"'=<>`\\x00-\\x20]+";
var SINGLEQUOTEDVALUE = "'[^']*'";
var DOUBLEQUOTEDVALUE = '"[^"]*"';
var ATTRIBUTEVALUE = "(?:" + UNQUOTEDVALUE + "|" + SINGLEQUOTEDVALUE + "|" + DOUBLEQUOTEDVALUE + ")";
var ATTRIBUTEVALUESPEC = "(?:" + "\\s*=" + "\\s*" + ATTRIBUTEVALUE + ")";
var ATTRIBUTE = "(?:" + "\\s+" + ATTRIBUTENAME + ATTRIBUTEVALUESPEC + "?)";
var OPENTAG = "<" + TAGNAME + ATTRIBUTE + "*" + "\\s*/?>";
var CLOSETAG = "</" + TAGNAME + "\\s*[>]";
var HTMLCOMMENT = "<!--([^-]+|[-][^-]+)*-->";
var PROCESSINGINSTRUCTION = "[<][?].*?[?][>]";
var DECLARATION = "<![A-Z]+" + "\\s+[^>]*>";
var CDATA = "<!\\[CDATA\\[([^\\]]+|\\][^\\]]|\\]\\][^>])*\\]\\]>";
var HTMLTAG = "(?:" + OPENTAG + "|" + CLOSETAG + "|" + HTMLCOMMENT + "|" +
PROCESSINGINSTRUCTION + "|" + DECLARATION + "|" + CDATA + ")";
var ENTITY = "&(?:#x[a-f0-9]{1,8}|#[0-9]{1,8}|[a-z][a-z0-9]{1,31});";
var reHtmlTag = new RegExp('^' + HTMLTAG, 'i');
var reLinkTitle = new RegExp(
'^(?:"(' + ESCAPED_CHAR + '|[^"\\x00])*"' +
'|' +
'\'(' + ESCAPED_CHAR + '|[^\'\\x00])*\'' +
'|' +
'\\((' + ESCAPED_CHAR + '|[^)\\x00])*\\))');
var reLinkDestinationBraces = new RegExp(
'^(?:[<](?:[^<>\\n\\\\\\x00]' + '|' + ESCAPED_CHAR + '|' + '\\\\)*[>])');
var reLinkDestination = new RegExp(
'^(?:' + REG_CHAR + '+|' + ESCAPED_CHAR + '|' + IN_PARENS_NOSP + ')*');
var reEscapable = new RegExp(ESCAPABLE);
var reAllEscapedChar = new RegExp('\\\\(' + ESCAPABLE + ')', 'g');
var reEscapedChar = new RegExp('^\\\\(' + ESCAPABLE + ')');
var reEntityHere = new RegExp('^' + ENTITY, 'i');
var reEntity = new RegExp(ENTITY, 'gi');
// Matches a character with a special meaning in markdown,
// or a string of non-special characters. Note: we match
// clumps of _ or * or `, because they need to be handled in groups.
var reMain = /^(?:[_*`\n]+|[\[\]\\!<&*_]|(?: *[^\n `\[\]\\!<&*_]+)+|[ \n]+)/m;
// Replace entities and backslash escapes with literal characters.
var unescapeString = function(s) {
return s.replace(reAllEscapedChar, '$1')
.replace(reEntity, entityToChar);
};
// Normalize reference label: collapse internal whitespace
// to single space, remove leading/trailing whitespace, case fold.
var normalizeReference = function(s) {
return s.trim()
.replace(/\s+/,' ')
.toUpperCase();
};
// INLINE PARSER
// These are methods of an InlineParser object, defined below.
// An InlineParser keeps track of a subject (a string to be
// parsed) and a position in that subject.
// If re matches at current position in the subject, advance
// position in subject and return the match; otherwise return null.
var match = function(re) {
var match = re.exec(this.subject.slice(this.pos));
if (match) {
this.pos += match.index + match[0].length;
return match[0];
} else {
return null;
}
};
// Returns the code for the character at the current subject position, or -1
// there are no more characters.
var peek = function() {
if (this.pos < this.subject.length) {
return this.subject.charCodeAt(this.pos);
} else {
return -1;
}
};
// Parse zero or more space characters, including at most one newline
var spnl = function() {
this.match(/^ *(?:\n *)?/);
return 1;
};
// All of the parsers below try to match something at the current position
// in the subject. If they succeed in matching anything, they
// return the inline matched, advancing the subject.
// Attempt to parse backticks, returning either a backtick code span or a
// literal sequence of backticks.
var parseBackticks = function(inlines) {
var startpos = this.pos;
var ticks = this.match(/^`+/);
if (!ticks) {
return 0;
}
var afterOpenTicks = this.pos;
var foundCode = false;
var match;
while (!foundCode && (match = this.match(/`+/m))) {
if (match === ticks) {
inlines.push({ t: 'Code', c: this.subject.slice(afterOpenTicks,
this.pos - ticks.length)
.replace(/[ \n]+/g,' ')
.trim() });
return true;
}
}
// If we got here, we didn't match a closing backtick sequence.
this.pos = afterOpenTicks;
inlines.push({ t: 'Text', c: ticks });
return true;
};
// Parse a backslash-escaped special character, adding either the escaped
// character, a hard line break (if the backslash is followed by a newline),
// or a literal backslash to the 'inlines' list.
var parseBackslash = function(inlines) {
var subj = this.subject,
pos = this.pos;
if (subj.charCodeAt(pos) === C_BACKSLASH) {
if (subj.charAt(pos + 1) === '\n') {
this.pos = this.pos + 2;
inlines.push({ t: 'Hardbreak' });
} else if (reEscapable.test(subj.charAt(pos + 1))) {
this.pos = this.pos + 2;
inlines.push({ t: 'Text', c: subj.charAt(pos + 1) });
} else {
this.pos++;
inlines.push({t: 'Text', c: '\\'});
}
return true;
} else {
return false;
}
};
// Attempt to parse an autolink (URL or email in pointy brackets).
var parseAutolink = function(inlines) {
var m;
var dest;
if ((m = this.match(/^<([a-zA-Z0-9.!#$%&'*+\/=?^_`{|}~-]+@[a-zA-Z0-9](?:[a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?(?:\.[a-zA-Z0-9](?:[a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?)*)>/))) { // email autolink
dest = m.slice(1,-1);
inlines.push(
{t: 'Link',
label: [{ t: 'Text', c: dest }],
destination: 'mailto:' + encodeURI(unescape(dest)) });
return true;
} else if ((m = this.match(/^<(?:coap|doi|javascript|aaa|aaas|about|acap|cap|cid|crid|data|dav|dict|dns|file|ftp|geo|go|gopher|h323|http|https|iax|icap|im|imap|info|ipp|iris|iris.beep|iris.xpc|iris.xpcs|iris.lwz|ldap|mailto|mid|msrp|msrps|mtqp|mupdate|news|nfs|ni|nih|nntp|opaquelocktoken|pop|pres|rtsp|service|session|shttp|sieve|sip|sips|sms|snmp|soap.beep|soap.beeps|tag|tel|telnet|tftp|thismessage|tn3270|tip|tv|urn|vemmi|ws|wss|xcon|xcon-userid|xmlrpc.beep|xmlrpc.beeps|xmpp|z39.50r|z39.50s|adiumxtra|afp|afs|aim|apt|attachment|aw|beshare|bitcoin|bolo|callto|chrome|chrome-extension|com-eventbrite-attendee|content|cvs|dlna-playsingle|dlna-playcontainer|dtn|dvb|ed2k|facetime|feed|finger|fish|gg|git|gizmoproject|gtalk|hcp|icon|ipn|irc|irc6|ircs|itms|jar|jms|keyparc|lastfm|ldaps|magnet|maps|market|message|mms|ms-help|msnim|mumble|mvn|notes|oid|palm|paparazzi|platform|proxy|psyc|query|res|resource|rmi|rsync|rtmp|secondlife|sftp|sgn|skype|smb|soldat|spotify|ssh|steam|svn|teamspeak|things|udp|unreal|ut2004|ventrilo|view-source|webcal|wtai|wyciwyg|xfire|xri|ymsgr):[^<>\x00-\x20]*>/i))) {
dest = m.slice(1,-1);
inlines.push({
t: 'Link',
label: [{ t: 'Text', c: dest }],
destination: encodeURI(unescape(dest)) });
return true;
} else {
return false;
}
};
// Attempt to parse a raw HTML tag.
var parseHtmlTag = function(inlines) {
var m = this.match(reHtmlTag);
if (m) {
inlines.push({ t: 'Html', c: m });
return true;
} else {
return false;
}
};
// Scan a sequence of characters with code cc, and return information about
// the number of delimiters and whether they are positioned such that
// they can open and/or close emphasis or strong emphasis. A utility
// function for strong/emph parsing.
var scanDelims = function(cc) {
var numdelims = 0;
var first_close_delims = 0;
var char_before, char_after, cc_after;
var startpos = this.pos;
char_before = this.pos === 0 ? '\n' :
this.subject.charAt(this.pos - 1);
while (this.peek() === cc) {
numdelims++;
this.pos++;
}
cc_after = this.peek();
if (cc_after === -1) {
char_after = '\n';
} else {
char_after = fromCodePoint(cc_after);
}
var can_open = numdelims > 0 && !(/\s/.test(char_after));
var can_close = numdelims > 0 && !(/\s/.test(char_before));
if (cc === C_UNDERSCORE) {
can_open = can_open && !((/[a-z0-9]/i).test(char_before));
can_close = can_close && !((/[a-z0-9]/i).test(char_after));
}
this.pos = startpos;
return { numdelims: numdelims,
can_open: can_open,
can_close: can_close };
};
var Emph = function(ils) {
return {t: 'Emph', c: ils};
};
var Strong = function(ils) {
return {t: 'Strong', c: ils};
};
var Str = function(s) {
return {t: 'Text', c: s};
};
// Attempt to parse emphasis or strong emphasis.
var parseEmphasis = function(cc,inlines) {
var res = this.scanDelims(cc);
var numdelims = res.numdelims;
var startpos = this.pos;
if (numdelims === 0) {
return false;
}
this.pos += numdelims;
inlines.push(Str(this.subject.slice(startpos, this.pos)));
// Add entry to stack for this opener
this.delimiters = { cc: cc,
numdelims: numdelims,
pos: inlines.length - 1,
previous: this.delimiters,
next: null,
can_open: res.can_open,
can_close: res.can_close};
if (this.delimiters.previous !== null) {
this.delimiters.previous.next = this.delimiters;
}
return true;
};
var removeDelimiter = function(delim) {
if (delim.previous !== null) {
delim.previous.next = delim.next;
}
if (delim.next === null) {
// top of stack
this.delimiters = delim.previous;
} else {
delim.next.previous = delim.previous;
}
};
var removeGaps = function(inlines) {
// remove gaps from inlines
var i, j;
j = 0;
for (i = 0 ; i < inlines.length; i++) {
if (inlines[i] !== null) {
inlines[j] = inlines[i];
j++;
}
}
inlines.splice(j);
};
var processEmphasis = function(inlines, stack_bottom) {
var opener, closer;
var opener_inl, closer_inl;
var nextstack, tempstack;
var use_delims;
var contents;
var tmp;
var emph;
var i,j;
// find first closer above stack_bottom:
closer = this.delimiters;
while (closer !== null && closer.previous !== stack_bottom) {
closer = closer.previous;
}
// move forward, looking for closers, and handling each
while (closer !== null) {
if (closer.can_close && (closer.cc === C_UNDERSCORE || closer.cc === C_ASTERISK)) {
// found emphasis closer. now look back for first matching opener:
opener = closer.previous;
while (opener !== null && opener !== stack_bottom) {
if (opener.cc === closer.cc && opener.can_open) {
break;
}
opener = opener.previous;
}
if (opener !== null && opener !== stack_bottom) {
// calculate actual number of delimiters used from this closer
if (closer.numdelims < 3 || opener.numdelims < 3) {
use_delims = closer.numdelims <= opener.numdelims ?
closer.numdelims : opener.numdelims;
} else {
use_delims = closer.numdelims % 2 === 0 ? 2 : 1;
}
opener_inl = inlines[opener.pos];
closer_inl = inlines[closer.pos];
// remove used delimiters from stack elts and inlines
opener.numdelims -= use_delims;
closer.numdelims -= use_delims;
opener_inl.c = opener_inl.c.slice(0, opener_inl.c.length - use_delims);
closer_inl.c = closer_inl.c.slice(0, closer_inl.c.length - use_delims);
// build contents for new emph element
contents = inlines.slice(opener.pos + 1, closer.pos);
removeGaps(contents);
emph = use_delims === 1 ? Emph(contents) : Strong(contents);
// insert into list of inlines
inlines[opener.pos + 1] = emph;
for (i = opener.pos + 2; i < closer.pos; i++) {
inlines[i] = null;
}
// remove elts btw opener and closer in delimiters stack
tempstack = closer.previous;
while (tempstack !== null && tempstack !== opener) {
nextstack = tempstack.previous;
this.removeDelimiter(tempstack);
tempstack = nextstack;
}
// if opener has 0 delims, remove it and the inline
if (opener.numdelims === 0) {
inlines[opener.pos] = null;
this.removeDelimiter(opener);
}
if (closer.numdelims === 0) {
inlines[closer.pos] = null;
tempstack = closer.next;
this.removeDelimiter(closer);
closer = tempstack;
}
} else {
closer = closer.next;
}
} else {
closer = closer.next;
}
}
removeGaps(inlines);
// remove all delimiters
while (this.delimiters != stack_bottom) {
this.removeDelimiter(this.delimiters);
}
};
// Attempt to parse link title (sans quotes), returning the string
// or null if no match.
var parseLinkTitle = function() {
var title = this.match(reLinkTitle);
if (title) {
// chop off quotes from title and unescape:
return unescapeString(title.substr(1, title.length - 2));
} else {
return null;
}
};
// Attempt to parse link destination, returning the string or
// null if no match.
var parseLinkDestination = function() {
var res = this.match(reLinkDestinationBraces);
if (res) { // chop off surrounding <..>:
return encodeURI(unescape(unescapeString(res.substr(1, res.length - 2))));
} else {
res = this.match(reLinkDestination);
if (res !== null) {
return encodeURI(unescape(unescapeString(res)));
} else {
return null;
}
}
};
// Attempt to parse a link label, returning number of characters parsed.
var parseLinkLabel = function() {
var match = this.match(/^\[(?:[^\\\[\]]|\\[\[\]]){0,1000}\]/);
return match === null ? 0 : match.length;
};
// Parse raw link label, including surrounding [], and return
// inline contents. (Note: this is not a method of InlineParser.)
var parseRawLabel = function(s) {
// note: parse without a refmap; we don't want links to resolve
// in nested brackets!
return new InlineParser().parse(s.substr(1, s.length - 2), {});
};
// Add open bracket to delimiter stack and add a Str to inlines.
var parseOpenBracket = function(inlines) {
var startpos = this.pos;
this.pos += 1;
inlines.push(Str("["));
// Add entry to stack for this opener
this.delimiters = { cc: C_OPEN_BRACKET,
numdelims: 1,
pos: inlines.length - 1,
previous: this.delimiters,
next: null,
can_open: true,
can_close: false,
index: startpos };
if (this.delimiters.previous !== null) {
this.delimiters.previous.next = this.delimiters;
}
return true;
};
// IF next character is [, and ! delimiter to delimiter stack and
// add a Str to inlines. Otherwise just add a Str.
var parseBang = function(inlines) {
var startpos = this.pos;
this.pos += 1;
if (this.peek() === C_OPEN_BRACKET) {
this.pos += 1;
inlines.push(Str("!["));
// Add entry to stack for this opener
this.delimiters = { cc: C_BANG,
numdelims: 1,
pos: inlines.length - 1,
previous: this.delimiters,
next: null,
can_open: true,
can_close: false,
index: startpos + 1 };
if (this.delimiters.previous !== null) {
this.delimiters.previous.next = this.delimiters;
}
} else {
inlines.push(Str("!"));
}
return true;
};
// Try to match close bracket against an opening in the delimiter
// stack. Add either a link or image, or a plain [ character,
// to the inlines stack. If there is a matching delimiter,
// remove it from the delimiter stack.
var parseCloseBracket = function(inlines) {
var startpos;
var is_image;
var dest;
var title;
var matched = false;
var link_text;
var i;
var opener, closer_above, tempstack;
this.pos += 1;
startpos = this.pos;
// look through stack of delimiters for a [ or !
opener = this.delimiters;
while (opener !== null) {
if (opener.cc === C_OPEN_BRACKET || opener.cc === C_BANG) {
break;
}
opener = opener.previous;
}
if (opener === null) {
// no matched opener, just return a literal
inlines.push(Str("]"));
return true;
}
// If we got here, open is a potential opener
is_image = opener.cc === C_BANG;
// instead of copying a slice, we null out the
// parts of inlines that don't correspond to link_text;
// later, we'll collapse them. This is awkward, and could
// be simplified if we made inlines a linked list rather than
// an array:
link_text = inlines.slice(0);
for (i = 0; i < opener.pos + 1; i++) {
link_text[i] = null;
}
// Check to see if we have a link/image
// Inline link?
if (this.peek() === C_OPEN_PAREN) {
this.pos++;
if (this.spnl() &&
((dest = this.parseLinkDestination()) !== null) &&
this.spnl() &&
// make sure there's a space before the title:
(/^\s/.test(this.subject.charAt(this.pos - 1)) &&
(title = this.parseLinkTitle() || '') || true) &&
this.spnl() &&
this.match(/^\)/)) {
matched = true;
}
} else {
// Next, see if there's a link label
var savepos = this.pos;
this.spnl();
var beforelabel = this.pos;
n = this.parseLinkLabel();
if (n === 0 || n === 2) {
// empty or missing second label
reflabel = this.subject.slice(opener.index, startpos);
} else {
reflabel = this.subject.slice(beforelabel, beforelabel + n);
}
if (n === 0) {
// If shortcut reference link, rewind before spaces we skipped.
this.pos = savepos;
}
// lookup rawlabel in refmap
var link = this.refmap[normalizeReference(reflabel)];
if (link) {
dest = link.destination;
title = link.title;
matched = true;
}
}
if (matched) {
this.processEmphasis(link_text, opener.previous);
// remove the part of inlines that became link_text.
// see note above on why we need to do this instead of splice:
for (i = opener.pos; i < inlines.length; i++) {
inlines[i] = null;
}
// processEmphasis will remove this and later delimiters.
// Now, for a link, we also remove earlier link openers.
// (no links in links)
if (!is_image) {
opener = this.delimiters;
closer_above = null;
while (opener !== null) {
if (opener.cc === C_OPEN_BRACKET) {
if (closer_above) {
closer_above.previous = opener.previous;
} else {
this.delimiters = opener.previous;
}
} else {
closer_above = opener;
}
opener = opener.previous;
}
}
inlines.push({t: is_image ? 'Image' : 'Link',
destination: dest,
title: title,
label: link_text});
return true;
} else { // no match
this.removeDelimiter(opener); // remove this opener from stack
this.pos = startpos;
inlines.push(Str("]"));
return true;
}
};
// Attempt to parse an entity, return Entity object if successful.
var parseEntity = function(inlines) {
var m;
if ((m = this.match(reEntityHere))) {
inlines.push({ t: 'Text', c: entityToChar(m) });
return true;
} else {
return false;
}
};
// Parse a run of ordinary characters, or a single character with
// a special meaning in markdown, as a plain string, adding to inlines.
var parseString = function(inlines) {
var m;
if ((m = this.match(reMain))) {
inlines.push({ t: 'Text', c: m });
return true;
} else {
return false;
}
};
// Parse a newline. If it was preceded by two spaces, return a hard
// line break; otherwise a soft line break.
var parseNewline = function(inlines) {
var m = this.match(/^ *\n/);
if (m) {
if (m.length > 2) {
inlines.push({ t: 'Hardbreak' });
} else if (m.length > 0) {
inlines.push({ t: 'Softbreak' });
}
return true;
}
return false;
};
// Attempt to parse an image. If the opening '!' is not followed
// by a link, return a literal '!'.
var parseImage = function(inlines) {
if (this.match(/^!/)) {
var link = this.parseLink(inlines);
if (link) {
inlines[inlines.length - 1].t = 'Image';
return true;
} else {
inlines.push({ t: 'Text', c: '!' });
return true;
}
} else {
return false;
}
};
// Attempt to parse a link reference, modifying refmap.
var parseReference = function(s, refmap) {
this.subject = s;
this.pos = 0;
this.label_nest_level = 0;
var rawlabel;
var dest;
var title;
var matchChars;
var startpos = this.pos;
var match;
// label:
matchChars = this.parseLinkLabel();
if (matchChars === 0) {
return 0;
} else {
rawlabel = this.subject.substr(0, matchChars);
}
// colon:
if (this.peek() === C_COLON) {
this.pos++;
} else {
this.pos = startpos;
return 0;
}
// link url
this.spnl();
dest = this.parseLinkDestination();
if (dest === null || dest.length === 0) {
this.pos = startpos;
return 0;
}
var beforetitle = this.pos;
this.spnl();
title = this.parseLinkTitle();
if (title === null) {
title = '';
// rewind before spaces
this.pos = beforetitle;
}
// make sure we're at line end:
if (this.match(/^ *(?:\n|$)/) === null) {
this.pos = startpos;
return 0;
}
var normlabel = normalizeReference(rawlabel);
if (!refmap[normlabel]) {
refmap[normlabel] = { destination: dest, title: title };
}
return this.pos - startpos;
};
// Parse the next inline element in subject, advancing subject position.
// On success, add the result to the inlines list, and return true.
// On failure, return false.
var parseInline = function(inlines) {
var startpos = this.pos;
var origlen = inlines.length;
var c = this.peek();
if (c === -1) {
return false;
}
var res;
switch(c) {
case C_NEWLINE:
case C_SPACE:
res = this.parseNewline(inlines);
break;
case C_BACKSLASH:
res = this.parseBackslash(inlines);
break;
case C_BACKTICK:
res = this.parseBackticks(inlines);
break;
case C_ASTERISK:
case C_UNDERSCORE:
res = this.parseEmphasis(c, inlines);
break;
case C_OPEN_BRACKET:
res = this.parseOpenBracket(inlines);
break;
case C_BANG:
res = this.parseBang(inlines);
break;
case C_CLOSE_BRACKET:
res = this.parseCloseBracket(inlines);
break;
case C_LESSTHAN:
res = this.parseAutolink(inlines) || this.parseHtmlTag(inlines);
break;
case C_AMPERSAND:
res = this.parseEntity(inlines);
break;
default:
res = this.parseString(inlines);
break;
}
if (!res) {
this.pos += 1;
inlines.push({t: 'Text', c: fromCodePoint(c)});
}
return true;
};
// Parse s as a list of inlines, using refmap to resolve references.
var parseInlines = function(s, refmap) {
this.subject = s;
this.pos = 0;
this.refmap = refmap || {};
this.delimiters = null;
var inlines = [];
while (this.parseInline(inlines)) {
}
this.processEmphasis(inlines, null);
return inlines;
};
// The InlineParser object.
function InlineParser(){
return {
subject: '',
label_nest_level: 0, // used by parseLinkLabel method
delimiters: null, // used by parseEmphasis method
pos: 0,
refmap: {},
match: match,
peek: peek,
spnl: spnl,
unescapeString: unescapeString,
parseBackticks: parseBackticks,
parseBackslash: parseBackslash,
parseAutolink: parseAutolink,
parseHtmlTag: parseHtmlTag,
scanDelims: scanDelims,
parseEmphasis: parseEmphasis,
parseLinkTitle: parseLinkTitle,
parseLinkDestination: parseLinkDestination,
parseLinkLabel: parseLinkLabel,
parseOpenBracket: parseOpenBracket,
parseCloseBracket: parseCloseBracket,
parseBang: parseBang,
parseEntity: parseEntity,
parseString: parseString,
parseNewline: parseNewline,
parseReference: parseReference,
parseInline: parseInline,
processEmphasis: processEmphasis,
removeDelimiter: removeDelimiter,
parse: parseInlines
};
}
module.exports = InlineParser;

25
outside/commonmark/js/package.json Normal file
View File

@ -0,0 +1,25 @@
{ "name": "commonmark",
"description": "a strongly specified, highly compatible variant of Markdown",
"version": "0.12.0",
"homepage": "http://commonmark.org",
"keywords":
[ "markdown",
"commonmark",
"md",
"stmd" ],
"repository":
{ "type": "git",
"url": "https://github.com/jgm/CommonMark.git" },
"author": "John MacFarlane",
"bugs": { "url": "https://github.com/jgm/CommonMark/issues" },
"license": "BSD-3-Clause",
"main": "./lib/index.js",
"bin": { "commonmark": "./bin/commonmark" },
"scripts": { "test": "node ./test.js" },
"directories": {
"lib": "./lib"
},
"engines": {
"node": "*"
}
}

82
outside/commonmark/js/test.js Executable file
View File

@ -0,0 +1,82 @@
#!/usr/bin/env node
var fs = require('fs');
var commonmark = require('./lib/index.js');
var ansi = require('./ansi/ansi');
var cursor = ansi(process.stdout);
var writer = new commonmark.HtmlRenderer();
var reader = new commonmark.DocParser();
var passed = 0;
var failed = 0;
var showSpaces = function(s) {
var t = s;
return t.replace(/\t/g,'→')
.replace(/ /g,'␣');
};
fs.readFile('spec.txt', 'utf8', function(err, data) {
if (err) {
return console.log(err);
}
var i;
var examples = [];
var current_section = "";
var example_number = 0;
var tests = data
.replace(/\r\n?/g, "\n") // Normalize newlines for platform independence
.replace(/^<!-- END TESTS -->(.|[\n])*/m, '');
tests.replace(/^\.\n([\s\S]*?)^\.\n([\s\S]*?)^\.$|^#{1,6} *(.*)$/gm,
function(_,markdownSubmatch,htmlSubmatch,sectionSubmatch){
if (sectionSubmatch) {
current_section = sectionSubmatch;
} else {
example_number++;
examples.push({markdown: markdownSubmatch,
html: htmlSubmatch,
section: current_section,
number: example_number});
}
});
current_section = "";
console.time("Elapsed time");
for (i = 0; i < examples.length; i++) {
var example = examples[i];
if (example.section !== current_section) {
if (current_section !== '') {
cursor.write('\n');
}
current_section = example.section;
cursor.reset().write(current_section).reset().write(' ');
}
var actual = writer.renderBlock(reader.parse(example.markdown.replace(/→/g, '\t')));
if (actual === example.html) {
passed++;
cursor.green().write('✓').reset();
} else {
failed++;
cursor.write('\n');
cursor.red().write('✘ Example ' + example.number + '\n');
cursor.cyan();
cursor.write('=== markdown ===============\n');
cursor.write(showSpaces(example.markdown));
cursor.write('=== expected ===============\n');
cursor.write(showSpaces(example.html));
cursor.write('=== got ====================\n');
cursor.write(showSpaces(actual));
cursor.reset();
}
}
cursor.write('\n' + passed.toString() + ' tests passed, ' +
failed.toString() + ' failed.\n');
console.timeEnd("Elapsed time");
});

5
outside/commonmark/man/CMakeLists.txt Normal file
View File

@ -0,0 +1,5 @@
INSTALL(FILES ${CMAKE_CURRENT_SOURCE_DIR}/man1/cmark.1
DESTINATION share/man/man1)
INSTALL(FILES ${CMAKE_CURRENT_SOURCE_DIR}/man3/cmark.3
DESTINATION share/man/man3)

102
outside/commonmark/man/make_man_page.py Normal file
View File

@ -0,0 +1,102 @@
#!/usr/bin/env python
# Creates a man page from a C file.
# Comments beginning with `/**` are treated as Groff man, except that
# 'this' is converted to \fIthis\fR, and ''this'' to \fBthis\fR.
# Non-blank lines immediately following a man page comment are treated
# as function signatures or examples and parsed into .Ft, .Fo, .Fa, .Fc. The
# immediately preceding man documentation chunk is printed after the example
# as a comment on it.
# That's about it!
import sys, re, os
from datetime import date
comment_start_re = re.compile('^\/\*\* ?')
comment_delim_re = re.compile('^[/ ]\** ?')
comment_end_re = re.compile('^ \**\/')
function_re = re.compile('^ *(?:CMARK_EXPORT\s+)?(?P<type>(?:const\s+)?\w+(?:\s*[*])?)\s*(?P<name>\w+)\s*\((?P<args>[^)]*)\)')
blank_re = re.compile('^\s*$')
macro_re = re.compile('CMARK_EXPORT *')
typedef_start_re = re.compile('typedef.*{$')
typedef_end_re = re.compile('}')
single_quote_re = re.compile("(?<!\w)'([^']+)'(?!\w)")
double_quote_re = re.compile("(?<!\w)''([^']+)''(?!\w)")
def handle_quotes(s):
return re.sub(double_quote_re, '\\\\fB\g<1>\\\\fR', re.sub(single_quote_re, '\\\\fI\g<1>\\\\fR', s))
typedef = False
mdlines = []
chunk = []
sig = []
if len(sys.argv) > 1:
sourcefile = sys.argv[1]
else:
print("Usage: make_man_page.py sourcefile")
exit(1)
with open(sourcefile, 'r') as cmarkh:
state = 'default'
for line in cmarkh:
# state transition
oldstate = state
if comment_start_re.match(line):
state = 'man'
elif comment_end_re.match(line) and state == 'man':
continue
elif comment_delim_re.match(line) and state == 'man':
state = 'man'
elif not typedef and blank_re.match(line):
state = 'default'
elif typedef and typedef_end_re.match(line):
typedef = False
elif state == 'man':
state = 'signature'
typedef = typedef_start_re.match(line)
# handle line
if state == 'man':
chunk.append(handle_quotes(re.sub(comment_delim_re, '', line)))
elif state == 'signature':
ln = re.sub(macro_re, '', line)
if typedef or not re.match(blank_re, ln):
sig.append(ln)
elif oldstate == 'signature' and state != 'signature':
if len(mdlines) > 0 and mdlines[-1] != '\n':
mdlines.append('\n')
rawsig = ''.join(sig)
m = function_re.match(rawsig)
if m:
mdlines.append('\\fI' + m.group('type') + '\\fR' + ' ')
mdlines.append('\\fB' + m.group('name') + '\\fR' + '(')
first = True
for argument in re.split(',', m.group('args')):
if not first:
mdlines.append(', ')
first = False
mdlines.append('\\fI' + argument.strip() + '\\fR')
mdlines.append(')\n')
else:
mdlines.append('.nf\n\\f[C]\n.RS 0n\n')
mdlines += sig
mdlines.append('.RE\n\\f[]\n.fi\n')
if len(mdlines) > 0 and mdlines[-1] != '\n':
mdlines.append('\n')
mdlines.append('.PP\n')
mdlines += chunk
chunk = []
sig = []
elif oldstate == 'man' and state != 'signature':
if len(mdlines) > 0 and mdlines[-1] != '\n':
mdlines.append('\n')
mdlines += chunk # add man chunk
chunk = []
mdlines.append('\n')
sys.stdout.write('.TH ' + os.path.basename(sourcefile).replace('.h','') + ' 3 "' + date.today().strftime('%B %d, %Y') + '" "LOCAL" "Library Functions Manual"\n')
sys.stdout.write(''.join(mdlines))

31
outside/commonmark/man/man1/cmark.1 Normal file
View File

@ -0,0 +1,31 @@
.TH "cmark" "1" "November 30, 2014" "LOCAL" "General Commands Manual"
.SH "NAME"
\fBcmark\fR
\- convert CommonMark formatted text to HTML
.SH "SYNOPSIS"
.HP 6n
\fBcmark\fR
[\fB\-\-ast\fR]
file*
.SH "DESCRIPTION"
\fBcmark\fR
acts as a pipe, reading from
\fRstdin\fR
or from the specified files and writing to
\fRstdout\fR.
It converts Markdown formatted plain text to HTML, using the conventions
described in the CommonMark spec.
If multiple files are specified, the contents of the files are simply
concatenated before parsing.
.SH "OPTIONS"
.TP 12n
\-\--ast
Print an abstract syntax tree instead of HTML.
.TP 12n
\-\-help
Print usage information.
.TP 12n
\-\-version
Print version.
.SH "AUTHORS"
John MacFarlane

275
outside/commonmark/man/man3/cmark.3 Normal file
View File

@ -0,0 +1,275 @@
.TH cmark 3 "December 05, 2014" "LOCAL" "Library Functions Manual"
.SH NAME
.B cmark
\- CommonMark parsing, manipulating, and rendering
.SH SIMPLE INTERFACE
.nf
\f[C]
.RS 0n
#define CMARK_VERSION "0.1"
.RE
\f[]
.fi
.PP
Current version of library.
\fIchar *\fR \fBcmark_markdown_to_html\fR(\fIconst char *text\fR, \fIint len\fR)
.PP
Convert \fItext\fR (assumed to be a UTF-8 encoded string with length
\fIlen\fR from CommonMark Markdown to HTML, returning a null-terminated,
UTF-8-encoded string.
.SH NODE STRUCTURE
.nf
\f[C]
.RS 0n
typedef enum {
/* Block */
CMARK_NODE_DOCUMENT,
CMARK_NODE_BLOCK_QUOTE,
CMARK_NODE_LIST,
CMARK_NODE_LIST_ITEM,
CMARK_NODE_CODE_BLOCK,
CMARK_NODE_HTML,
CMARK_NODE_PARAGRAPH,
CMARK_NODE_HEADER,
CMARK_NODE_HRULE,
CMARK_NODE_REFERENCE_DEF,
CMARK_NODE_FIRST_BLOCK = CMARK_NODE_DOCUMENT,
CMARK_NODE_LAST_BLOCK = CMARK_NODE_REFERENCE_DEF,
/* Inline */
CMARK_NODE_TEXT,
CMARK_NODE_SOFTBREAK,
CMARK_NODE_LINEBREAK,
CMARK_NODE_INLINE_CODE,
CMARK_NODE_INLINE_HTML,
CMARK_NODE_EMPH,
CMARK_NODE_STRONG,
CMARK_NODE_LINK,
CMARK_NODE_IMAGE,
CMARK_NODE_FIRST_INLINE = CMARK_NODE_TEXT,
CMARK_NODE_LAST_INLINE = CMARK_NODE_IMAGE,
} cmark_node_type;
.RE
\f[]
.fi
.PP
.nf
\f[C]
.RS 0n
typedef enum {
CMARK_NO_LIST,
CMARK_BULLET_LIST,
CMARK_ORDERED_LIST
} cmark_list_type;
.RE
\f[]
.fi
.PP
.nf
\f[C]
.RS 0n
typedef enum {
CMARK_PERIOD_DELIM,
CMARK_PAREN_DELIM
} cmark_delim_type;
.RE
\f[]
.fi
.PP
.SH CREATING AND DESTROYING NODES
\fIcmark_node*\fR \fBcmark_node_new\fR(\fIcmark_node_type type\fR)
.PP
\fIvoid\fR \fBcmark_node_free\fR(\fIcmark_node *node\fR)
.PP
\fIcmark_node*\fR \fBcmark_node_next\fR(\fIcmark_node *node\fR)
.PP
.SH TREE TRAVERSAL
\fIcmark_node*\fR \fBcmark_node_previous\fR(\fIcmark_node *node\fR)
.PP
\fIcmark_node*\fR \fBcmark_node_parent\fR(\fIcmark_node *node\fR)
.PP
\fIcmark_node*\fR \fBcmark_node_first_child\fR(\fIcmark_node *node\fR)
.PP
\fIcmark_node*\fR \fBcmark_node_last_child\fR(\fIcmark_node *node\fR)
.PP
.SH ACCESSORS
\fIcmark_node_type\fR \fBcmark_node_get_type\fR(\fIcmark_node *node\fR)
.PP
\fIconst char*\fR \fBcmark_node_get_string_content\fR(\fIcmark_node *node\fR)
.PP
\fIint\fR \fBcmark_node_set_string_content\fR(\fIcmark_node *node\fR, \fIconst char *content\fR)
.PP
\fIint\fR \fBcmark_node_get_header_level\fR(\fIcmark_node *node\fR)
.PP
\fIint\fR \fBcmark_node_set_header_level\fR(\fIcmark_node *node\fR, \fIint level\fR)
.PP
\fIcmark_list_type\fR \fBcmark_node_get_list_type\fR(\fIcmark_node *node\fR)
.PP
\fIint\fR \fBcmark_node_set_list_type\fR(\fIcmark_node *node\fR, \fIcmark_list_type type\fR)
.PP
\fIint\fR \fBcmark_node_get_list_start\fR(\fIcmark_node *node\fR)
.PP
\fIint\fR \fBcmark_node_set_list_start\fR(\fIcmark_node *node\fR, \fIint start\fR)
.PP
\fIint\fR \fBcmark_node_get_list_tight\fR(\fIcmark_node *node\fR)
.PP
\fIint\fR \fBcmark_node_set_list_tight\fR(\fIcmark_node *node\fR, \fIint tight\fR)
.PP
\fIconst char*\fR \fBcmark_node_get_fence_info\fR(\fIcmark_node *node\fR)
.PP
\fIint\fR \fBcmark_node_set_fence_info\fR(\fIcmark_node *node\fR, \fIconst char *info\fR)
.PP
\fIconst char*\fR \fBcmark_node_get_url\fR(\fIcmark_node *node\fR)
.PP
\fIint\fR \fBcmark_node_set_url\fR(\fIcmark_node *node\fR, \fIconst char *url\fR)
.PP
\fIconst char*\fR \fBcmark_node_get_title\fR(\fIcmark_node *node\fR)
.PP
\fIint\fR \fBcmark_node_set_title\fR(\fIcmark_node *node\fR, \fIconst char *title\fR)
.PP
\fIint\fR \fBcmark_node_get_start_line\fR(\fIcmark_node *node\fR)
.PP
\fIint\fR \fBcmark_node_get_start_column\fR(\fIcmark_node *node\fR)
.PP
\fIint\fR \fBcmark_node_get_end_line\fR(\fIcmark_node *node\fR)
.PP
.SH TREE MANIPULATION
\fIvoid\fR \fBcmark_node_unlink\fR(\fIcmark_node *node\fR)
.PP
\fIint\fR \fBcmark_node_insert_before\fR(\fIcmark_node *node\fR, \fIcmark_node *sibling\fR)
.PP
\fIint\fR \fBcmark_node_insert_after\fR(\fIcmark_node *node\fR, \fIcmark_node *sibling\fR)
.PP
\fIint\fR \fBcmark_node_prepend_child\fR(\fIcmark_node *node\fR, \fIcmark_node *child\fR)
.PP
\fIint\fR \fBcmark_node_append_child\fR(\fIcmark_node *node\fR, \fIcmark_node *child\fR)
.PP
.SH PARSING
\fIcmark_parser *\fR \fBcmark_parser_new\fR(\fI\fR)
.PP
\fIvoid\fR \fBcmark_parser_free\fR(\fIcmark_parser *parser\fR)
.PP
\fIcmark_node *\fR \fBcmark_parser_finish\fR(\fIcmark_parser *parser\fR)
.PP
\fIvoid\fR \fBcmark_parser_feed\fR(\fIcmark_parser *parser\fR, \fIconst char *buffer\fR, \fIsize_t len\fR)
.PP
\fIcmark_node *\fR \fBcmark_parse_document\fR(\fIconst char *buffer\fR, \fIsize_t len\fR)
.PP
\fIcmark_node *\fR \fBcmark_parse_file\fR(\fIFILE *f\fR)
.PP
.SH RENDERING
\fIchar *\fR \fBcmark_render_ast\fR(\fIcmark_node *root\fR)
.PP
\fIchar *\fR \fBcmark_render_html\fR(\fIcmark_node *root\fR)
.PP
.SH AUTHORS
John MacFarlane, Vicent Marti, Kārlis Gaņģis, Nick Wellnhofer.

22
outside/commonmark/mkcasefold.pl Normal file
View File

@ -0,0 +1,22 @@
binmode STDOUT;
print(" switch (c) {\n");
my $lastchar = "";
while (<STDIN>) {
if (/^[A-F0-9]/ and / [CF]; /) {
my ($char, $type, $subst) = m/([A-F0-9]+); ([CF]); ([^;]+)/;
if ($char eq $lastchar) {
break;
}
my @subst = $subst =~ m/(\w+)/g;
printf(" case 0x%s:\n", $char);
foreach (@subst) {
printf(" bufpush(0x%s);\n", $_);
}
printf(" break;\n");
$lastchar = $char;
}
}
printf(" default:\n");
printf(" bufpush(c);\n");
print(" }\n");

1
outside/commonmark/nmake.bat Normal file
View File

@ -0,0 +1 @@
@nmake.exe /nologo /f Makefile.nmake %*

6971
outside/commonmark/spec.txt Normal file
View File

File diff suppressed because it is too large Load Diff

17
outside/commonmark/spec2js.js Executable file
View File

@ -0,0 +1,17 @@
#!/usr/bin/env node
var fs = require('fs');
var util = require('util');
fs.readFile('spec.txt', 'utf8', function(err, data) {
if (err) {
return console.log(err);
}
var examples = [];
data.replace(/^\.\n([\s\S]*?)^\.\n([\s\S]*?)^\.$/gm,
function(_,x,y){
examples.push({markdown: x, html: y});
});
console.log(util.inspect(examples, { depth: null }));
console.warn(examples.length + ' examples');
});

36
outside/commonmark/spec2md.pl Normal file
View File

@ -0,0 +1,36 @@
#!/usr/bin/env perl
use strict;
use warnings;
my $stage = 0;
my $example = 0;
my @match;
my $section = "";
while (<STDIN>) {
if (/^\.$/) {
if ($stage == 0) {
$example++;
print "\n<div class=\"example\" id=\"example-$example\" data-section=\"$section\">\n";
print "<div class=\"examplenum\"><a href=\"#example-$example\">Example $example</a>&nbsp;&nbsp;<a class=\"dingus\" title=\"open in interactive dingus\">(interact)</a></div>\n\n";
print "````````````````````````````````````````````````````````` markdown\n";
} elsif ($stage == 1) {
print "`````````````````````````````````````````````````````````\n\n";
print "````````````````````````````````````````````````````````` html\n";
} elsif ($stage == 2) {
print "`````````````````````````````````````````````````````````\n\n";
print "</div>\n\n";
} else {
die "Encountered unknown stage $stage";
}
$stage = ($stage + 1) % 3;
} else {
if ($stage == 0 && (@match = ($_ =~ /^#{1,6} *(.*)/))) {
$section = $match[0];
}
if ($stage != 0) {
$_ =~ s/ /␣/g;
}
print $_;
}
}

37
outside/commonmark/specfilter.hs Executable file
View File

@ -0,0 +1,37 @@
#!/usr/bin/env runhaskell
import Text.Pandoc.JSON
import Text.Pandoc.Walk
main = toJSONFilter go
where go :: Pandoc -> Pandoc
go = walk exampleDivs . walk anchors
exampleDivs :: Block -> Block
exampleDivs (Div (ident, ["example"], kvs)
[ d@(Div (_,["examplenum"],_) _),
c1@(CodeBlock (_,["markdown"],_) _),
c2@(CodeBlock (_,["html"],_) _)
]) = Div (ident, ["example"], kvs)
[ rawtex "\\begin{minipage}[t]{\\textwidth}\n{\\scriptsize "
, d
, rawtex "\\vspace{-1em}}"
, rawtex "\\begin{minipage}[t]{0.49\\textwidth}\n\\definecolor{shadecolor}{gray}{0.85}\n"
, addBreaks c1
, rawtex "\\end{minipage}\n\\hfill\n\\begin{minipage}[t]{0.49\\textwidth}\n\\definecolor{shadecolor}{gray}{0.95}\n"
, addBreaks c2
, rawtex "\\end{minipage}\n\\end{minipage}"
]
where rawtex = RawBlock (Format "latex")
addBreaks (CodeBlock attrs code) = CodeBlock attrs $ addBreaks' code
addBreaks' code =
if length code > 49
then take 49 code ++ ('\n':addBreaks' (drop 49 code))
else code
exampleDivs x = x
anchors :: Inline -> Inline
anchors (RawInline (Format "html") ('<':'a':' ':'i':'d':'=':'"':xs)) =
RawInline (Format "latex") ("\\hyperdef{}{" ++ lab ++ "}{\\label{" ++ lab ++ "}}")
where lab = takeWhile (/='"') xs
anchors x = x

144
outside/commonmark/src/CMakeLists.txt Normal file
View File

@ -0,0 +1,144 @@
cmake_minimum_required(VERSION 2.8)
set(LIBRARY "libcmark")
set(HEADERS
cmark.h
parser.h
buffer.h
node.h
chunk.h
references.h
debug.h
bench.h
utf8.h
scanners.h
inlines.h
html/html_unescape.h
html/houdini.h
)
set(LIBRARY_SOURCES
cmark.c
node.c
blocks.c
inlines.c
print.c
scanners.c
scanners.re
utf8.c
buffer.c
references.c
html/html.c
html/html_unescape.gperf
html/houdini_href_e.c
html/houdini_html_e.c
html/houdini_html_u.c
${HEADERS}
)
#set(PROGRAM "cmark")
#set(PROGRAM_SOURCES
# ${LIBRARY_SOURCES}
# main.c
# )
include_directories(. html ${CMAKE_CURRENT_BINARY_DIR})
include_directories(../../../i)
set(RE2C re2c)
if (MSVC)
file(TO_NATIVE_PATH ${CMAKE_CURRENT_SOURCE_DIR} DOS_CURRENT_SOURCE_DIR)
add_custom_command( OUTPUT ${CMAKE_CURRENT_SOURCE_DIR}/scanners.c
DEPENDS ${CMAKE_CURRENT_SOURCE_DIR}/scanners.re
COMMAND ${RE2C} --case-insensitive -b -i
--no-generation-date
-o ${DOS_CURRENT_SOURCE_DIR}\\scanners.c
${DOS_CURRENT_SOURCE_DIR}\\scanners.re )
else(MSVC)
add_custom_command( OUTPUT ${CMAKE_CURRENT_SOURCE_DIR}/scanners.c
DEPENDS ${CMAKE_CURRENT_SOURCE_DIR}/scanners.re
COMMAND ${RE2C} --case-insensitive -b -i
--no-generation-date
-o ${CMAKE_CURRENT_SOURCE_DIR}/scanners.c
${CMAKE_CURRENT_SOURCE_DIR}/scanners.re )
endif(MSVC)
include (GenerateExportHeader)
#add_executable(${PROGRAM} ${PROGRAM_SOURCES})
#add_compiler_export_flags()
#
## Disable the PUBLIC declarations when compiling the executable:
#set_target_properties(${PROGRAM} PROPERTIES
# COMPILE_FLAGS -DCMARK_STATIC_DEFINE)
# Check integrity of node structure when compiled as debug:
set(CMAKE_C_FLAGS_DEBUG "${CMAKE_C_FLAGS_DEBUG} -DCMARK_DEBUG_NODES")
if (${CMAKE_MAJOR_VERSION} GREATER 1 AND ${CMAKE_MINOR_VERSION} GREATER 8)
set(CMAKE_C_VISIBILITY_PRESET hidden)
set(CMAKE_VISIBILITY_INLINES_HIDDEN 1)
elseif(CMAKE_COMPILER_IS_GNUCC OR "${CMAKE_CXX_COMPILER_ID}" STREQUAL "Clang")
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -fvisibility=hidden")
endif ()
# SHARED add_library(${LIBRARY} SHARED ${LIBRARY_SOURCES})
add_library(${LIBRARY} STATIC ${LIBRARY_SOURCES})
set_target_properties(${LIBRARY}
PROPERTIES OUTPUT_NAME "cmark")
set_property(TARGET ${LIBRARY}
APPEND PROPERTY MACOSX_RPATH true)
generate_export_header(${LIBRARY}
BASE_NAME ${PROJECT_NAME})
#if (MSVC)
# set_property(TARGET ${PROGRAM}
# APPEND PROPERTY LINK_FLAGS /INCREMENTAL:NO)
#endif(MSVC)
#install(TARGETS ${PROGRAM} # SHARED ${LIBRARY}
# RUNTIME DESTINATION bin
# LIBRARY DESTINATION lib
# )
install(FILES cmark.h ${CMAKE_CURRENT_BINARY_DIR}/cmark_export.h
DESTINATION include
)
# Feature tests
include(CheckIncludeFile)
include(CheckCSourceCompiles)
CHECK_INCLUDE_FILE(stdbool.h HAVE_STDBOOL_H)
CHECK_C_SOURCE_COMPILES(
"int main() { __builtin_expect(0,0); return 0; }"
HAVE___BUILTIN_EXPECT)
CHECK_C_SOURCE_COMPILES("
int f(void) __attribute__ (());
int main() { return 0; }
" HAVE___ATTRIBUTE__)
CONFIGURE_FILE(
${CMAKE_CURRENT_SOURCE_DIR}/config.h.in
${CMAKE_CURRENT_BINARY_DIR}/config.h)
# Always compile with warnings
if(MSVC)
# Force to always compile with W4
if(CMAKE_CXX_FLAGS MATCHES "/W[0-4]")
string(REGEX REPLACE "/W[0-4]" "/W4" CMAKE_C_FLAGS "${CMAKE_C_FLAGS}")
else()
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} /W4")
endif()
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} /wd4127 /wd4244 /wd4267 /wd4706 /wd4800 /D_CRT_SECURE_NO_WARNINGS")
elseif(CMAKE_COMPILER_IS_GNUCC OR "${CMAKE_CXX_COMPILER_ID}" STREQUAL "Clang")
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -Wall -std=c99 -pedantic")
endif()
# Compile as C++ under MSVC
if(MSVC)
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} /TP")
endif()
if($ENV{TIMER})
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -DTIMER=1")
endif($ENV{TIMER})

27
outside/commonmark/src/bench.h Normal file
View File

@ -0,0 +1,27 @@
#ifndef CMARK_BENCH_H
#define CMARK_BENCH_H
#include <stdio.h>
#include <time.h>
#ifdef TIMER
float _cmark_start_time;
float _cmark_end_time;
float _cmark_save_time;
#define start_timer() \
_cmark_save_time = _cmark_start_time; \
_cmark_start_time = (float)clock()/CLOCKS_PER_SEC
#define end_timer(M) \
_cmark_end_time = (float)clock()/CLOCKS_PER_SEC; \
fprintf(stderr, "[TIME] (%s:%d) %4.f ns " M "\n", __FILE__, \
__LINE__, (_cmark_end_time - _cmark_start_time) * 1000000); \
_cmark_start_time = _cmark_save_time;
#else
#define start_timer()
#define end_timer(M)
#endif
#endif

897
outside/commonmark/src/blocks.c Normal file
View File

@ -0,0 +1,897 @@
#include <stdlib.h>
#include <assert.h>
#include <stdio.h>
#include <ctype.h>
#include "config.h"
#include "parser.h"
#include "cmark.h"
#include "node.h"
#include "references.h"
#include "utf8.h"
#include "scanners.h"
#include "inlines.h"
#include "html/houdini.h"
#include "buffer.h"
#include "debug.h"
#define CODE_INDENT 4
#define peek_at(i, n) (i)->data[n]
static void
S_parser_feed(cmark_parser *parser, const unsigned char *buffer, size_t len,
bool eof);
static void
S_process_line(cmark_parser *parser, const unsigned char *buffer,
size_t bytes);
static cmark_node* make_block(cmark_node_type tag, int start_line, int start_column)
{
cmark_node* e;
e = (cmark_node *)calloc(1, sizeof(*e));
if(e != NULL) {
e->type = tag;
e->open = true;
e->start_line = start_line;
e->start_column = start_column;
e->end_line = start_line;
strbuf_init(&e->string_content, 32);
}
return e;
}
// Create a root document cmark_node.
static cmark_node* make_document()
{
cmark_node *e = make_block(NODE_DOCUMENT, 1, 1);
return e;
}
cmark_parser *cmark_parser_new()
{
cmark_parser *parser = (cmark_parser*)malloc(sizeof(cmark_parser));
cmark_node *document = make_document();
strbuf *line = (strbuf*)malloc(sizeof(strbuf));
strbuf *buf = (strbuf*)malloc(sizeof(strbuf));
cmark_strbuf_init(line, 256);
cmark_strbuf_init(buf, 0);
parser->refmap = cmark_reference_map_new();
parser->root = document;
parser->current = document;
parser->line_number = 0;
parser->curline = line;
parser->linebuf = buf;
return parser;
}
void cmark_parser_free(cmark_parser *parser)
{
cmark_strbuf_free(parser->curline);
free(parser->curline);
cmark_strbuf_free(parser->linebuf);
free(parser->linebuf);
cmark_reference_map_free(parser->refmap);
free(parser);
}
static void finalize(cmark_parser *parser, cmark_node* b, int line_number);
// Returns true if line has only space characters, else false.
static bool is_blank(strbuf *s, int offset)
{
while (offset < s->size) {
switch (s->ptr[offset]) {
case '\n':
return true;
case ' ':
offset++;
break;
default:
return false;
}
}
return true;
}
static inline bool can_contain(cmark_node_type parent_type, cmark_node_type child_type)
{
return ( parent_type == NODE_DOCUMENT ||
parent_type == NODE_BLOCK_QUOTE ||
parent_type == NODE_LIST_ITEM ||
(parent_type == NODE_LIST && child_type == NODE_LIST_ITEM) );
}
static inline bool accepts_lines(cmark_node_type block_type)
{
return (block_type == NODE_PARAGRAPH ||
block_type == NODE_HEADER ||
block_type == NODE_CODE_BLOCK);
}
static void add_line(cmark_node* cmark_node, chunk *ch, int offset)
{
assert(cmark_node->open);
strbuf_put(&cmark_node->string_content, ch->data + offset, ch->len - offset);
}
static void remove_trailing_blank_lines(strbuf *ln)
{
int i;
for (i = ln->size - 1; i >= 0; --i) {
unsigned char c = ln->ptr[i];
if (c != ' ' && c != '\t' && c != '\r' && c != '\n')
break;
}
if (i < 0) {
strbuf_clear(ln);
return;
}
i = strbuf_strchr(ln, '\n', i);
if (i >= 0)
strbuf_truncate(ln, i);
}
// Check to see if a cmark_node ends with a blank line, descending
// if needed into lists and sublists.
static bool ends_with_blank_line(cmark_node* cmark_node)
{
if (cmark_node->last_line_blank) {
return true;
}
if ((cmark_node->type == NODE_LIST || cmark_node->type == NODE_LIST_ITEM) && cmark_node->last_child) {
return ends_with_blank_line(cmark_node->last_child);
} else {
return false;
}
}
// Break out of all containing lists
static int break_out_of_lists(cmark_parser *parser, cmark_node ** bptr, int line_number)
{
cmark_node *container = *bptr;
cmark_node *b = parser->root;
// find first containing NODE_LIST:
while (b && b->type != NODE_LIST) {
b = b->last_child;
}
if (b) {
while (container && container != b) {
finalize(parser, container, line_number);
container = container->parent;
}
finalize(parser, b, line_number);
*bptr = b->parent;
}
return 0;
}
static void finalize(cmark_parser *parser, cmark_node* b, int line_number)
{
int firstlinelen;
int pos;
cmark_node* item;
cmark_node* subitem;
if (!b->open)
return; // don't do anything if the cmark_node is already closed
b->open = false;
if (line_number > b->start_line) {
b->end_line = line_number - 1;
} else {
b->end_line = line_number;
}
switch (b->type) {
case NODE_PARAGRAPH:
while (strbuf_at(&b->string_content, 0) == '[' &&
(pos = cmark_parse_reference_inline(&b->string_content, parser->refmap))) {
strbuf_drop(&b->string_content, pos);
}
if (is_blank(&b->string_content, 0)) {
b->type = NODE_REFERENCE_DEF;
}
break;
case NODE_CODE_BLOCK:
if (!b->as.code.fenced) { // indented code
remove_trailing_blank_lines(&b->string_content);
strbuf_putc(&b->string_content, '\n');
break;
} else {
// first line of contents becomes info
firstlinelen = strbuf_strchr(&b->string_content, '\n', 0);
houdini_unescape_html_f(
&b->as.code.info,
b->string_content.ptr,
firstlinelen
);
strbuf_drop(&b->string_content, firstlinelen + 1);
strbuf_trim(&b->as.code.info);
strbuf_unescape(&b->as.code.info);
break;
}
case NODE_LIST: // determine tight/loose status
b->as.list.tight = true; // tight by default
item = b->first_child;
while (item) {
// check for non-final non-empty list item ending with blank line:
if (item->last_line_blank && item->next) {
b->as.list.tight = false;
break;
}
// recurse into children of list item, to see if there are
// spaces between them:
subitem = item->first_child;
while (subitem) {
if (ends_with_blank_line(subitem) &&
(item->next || subitem->next)) {
b->as.list.tight = false;
break;
}
subitem = subitem->next;
}
if (!(b->as.list.tight)) {
break;
}
item = item->next;
}
break;
default:
break;
}
}
// Add a cmark_node as child of another. Return pointer to child.
static cmark_node* add_child(cmark_parser *parser, cmark_node* parent,
cmark_node_type block_type, int start_line, int start_column)
{
assert(parent);
// if 'parent' isn't the kind of cmark_node that can accept this child,
// then back up til we hit a cmark_node that can.
while (!can_contain(parent->type, block_type)) {
finalize(parser, parent, start_line);
parent = parent->parent;
}
cmark_node* child = make_block(block_type, start_line, start_column);
child->parent = parent;
if (parent->last_child) {
parent->last_child->next = child;
child->prev = parent->last_child;
} else {
parent->first_child = child;
child->prev = NULL;
}
parent->last_child = child;
return child;
}
typedef struct BlockStack {
struct BlockStack *previous;
cmark_node *next_sibling;
} block_stack;
// Walk through cmark_node and all children, recursively, parsing
// string content into inline content where appropriate.
static void process_inlines(cmark_node* cur, cmark_reference_map *refmap)
{
block_stack* stack = NULL;
block_stack* newstack = NULL;
while (cur != NULL) {
switch (cur->type) {
case NODE_PARAGRAPH:
case NODE_HEADER:
cmark_parse_inlines(cur, refmap);
break;
default:
break;
}
if (cur->first_child) {
newstack = (block_stack*)malloc(sizeof(block_stack));
if (newstack == NULL) break;
newstack->previous = stack;
stack = newstack;
stack->next_sibling = cur->next;
cur = cur->first_child;
} else {
cur = cur->next;
}
while (cur == NULL && stack != NULL) {
cur = stack->next_sibling;
newstack = stack->previous;
free(stack);
stack = newstack;
}
}
while (stack != NULL) {
newstack = stack->previous;
free(stack);
stack = newstack;
}
}
// Attempts to parse a list item marker (bullet or enumerated).
// On success, returns length of the marker, and populates
// data with the details. On failure, returns 0.
static int parse_list_marker(chunk *input, int pos, cmark_list **dataptr)
{
unsigned char c;
int startpos;
cmark_list *data;
startpos = pos;
c = peek_at(input, pos);
if ((c == '*' || c == '-' || c == '+') && !scan_hrule(input, pos)) {
pos++;
if (!isspace(peek_at(input, pos))) {
return 0;
}
data = (cmark_list *)calloc(1, sizeof(*data));
if(data == NULL) {
return 0;
} else {
data->marker_offset = 0; // will be adjusted later
data->list_type = CMARK_BULLET_LIST;
data->bullet_char = c;
data->start = 1;
data->delimiter = CMARK_PERIOD_DELIM;
data->tight = false;
}
} else if (isdigit(c)) {
int start = 0;
do {
start = (10 * start) + (peek_at(input, pos) - '0');
pos++;
} while (isdigit(peek_at(input, pos)));
c = peek_at(input, pos);
if (c == '.' || c == ')') {
pos++;
if (!isspace(peek_at(input, pos))) {
return 0;
}
data = (cmark_list *)calloc(1, sizeof(*data));
if(data == NULL) {
return 0;
} else {
data->marker_offset = 0; // will be adjusted later
data->list_type = CMARK_ORDERED_LIST;
data->bullet_char = 0;
data->start = start;
data->delimiter = (c == '.' ? CMARK_PERIOD_DELIM : CMARK_PAREN_DELIM);
data->tight = false;
}
} else {
return 0;
}
} else {
return 0;
}
*dataptr = data;
return (pos - startpos);
}
// Return 1 if list item belongs in list, else 0.
static int lists_match(cmark_list *list_data, cmark_list *item_data)
{
return (list_data->list_type == item_data->list_type &&
list_data->delimiter == item_data->delimiter &&
// list_data->marker_offset == item_data.marker_offset &&
list_data->bullet_char == item_data->bullet_char);
}
static cmark_node *finalize_document(cmark_parser *parser)
{
while (parser->current != parser->root) {
finalize(parser, parser->current, parser->line_number);
parser->current = parser->current->parent;
}
finalize(parser, parser->root, parser->line_number);
process_inlines(parser->root, parser->refmap);
return parser->root;
}
cmark_node *cmark_parse_file(FILE *f)
{
unsigned char buffer[4096];
cmark_parser *parser = cmark_parser_new();
size_t bytes;
cmark_node *document;
while ((bytes = fread(buffer, 1, sizeof(buffer), f)) > 0) {
bool eof = bytes < sizeof(buffer);
S_parser_feed(parser, buffer, bytes, eof);
if (eof) {
break;
}
}
document = cmark_parser_finish(parser);
cmark_parser_free(parser);
return document;
}
cmark_node *cmark_parse_document(const char *buffer, size_t len)
{
cmark_parser *parser = cmark_parser_new();
cmark_node *document;
S_parser_feed(parser, (const unsigned char *)buffer, len, true);
document = cmark_parser_finish(parser);
cmark_parser_free(parser);
return document;
}
void
cmark_parser_feed(cmark_parser *parser, const char *buffer, size_t len)
{
S_parser_feed(parser, (const unsigned char *)buffer, len, false);
}
static void
S_parser_feed(cmark_parser *parser, const unsigned char *buffer, size_t len,
bool eof)
{
const unsigned char *end = buffer + len;
while (buffer < end) {
const unsigned char *eol
= (const unsigned char *)memchr(buffer, '\n',
end - buffer);
size_t line_len;
if (eol) {
line_len = eol + 1 - buffer;
}
else if (eof) {
line_len = end - buffer;
}
else {
strbuf_put(parser->linebuf, buffer, end - buffer);
break;
}
if (parser->linebuf->size > 0) {
strbuf_put(parser->linebuf, buffer, line_len);
S_process_line(parser, parser->linebuf->ptr,
parser->linebuf->size);
strbuf_clear(parser->linebuf);
}
else {
S_process_line(parser, buffer, line_len);
}
buffer += line_len;
}
}
static void chop_trailing_hashtags(chunk *ch)
{
int n, orig_n;
chunk_rtrim(ch);
orig_n = n = ch->len - 1;
// if string ends in space followed by #s, remove these:
while (n >= 0 && peek_at(ch, n) == '#')
n--;
// Check for a be a space before the final #s:
if (n != orig_n && n >= 0 && peek_at(ch, n) == ' ') {
ch->len = n;
chunk_rtrim(ch);
}
}
static void
S_process_line(cmark_parser *parser, const unsigned char *buffer, size_t bytes)
{
cmark_node* last_matched_container;
int offset = 0;
int matched = 0;
int lev = 0;
int i;
cmark_list *data = NULL;
bool all_matched = true;
cmark_node* container;
cmark_node* cur = parser->current;
bool blank = false;
int first_nonspace;
int indent;
chunk input;
utf8proc_detab(parser->curline, buffer, bytes);
// Add a newline to the end if not present:
// TODO this breaks abstraction:
if (parser->curline->ptr[parser->curline->size - 1] != '\n') {
strbuf_putc(parser->curline, '\n');
}
input.data = parser->curline->ptr;
input.len = parser->curline->size;
// container starts at the document root.
container = parser->root;
parser->line_number++;
// for each containing cmark_node, try to parse the associated line start.
// bail out on failure: container will point to the last matching cmark_node.
while (container->last_child && container->last_child->open) {
container = container->last_child;
first_nonspace = offset;
while (peek_at(&input, first_nonspace) == ' ') {
first_nonspace++;
}
indent = first_nonspace - offset;
blank = peek_at(&input, first_nonspace) == '\n';
if (container->type == NODE_BLOCK_QUOTE) {
matched = indent <= 3 && peek_at(&input, first_nonspace) == '>';
if (matched) {
offset = first_nonspace + 1;
if (peek_at(&input, offset) == ' ')
offset++;
} else {
all_matched = false;
}
} else if (container->type == NODE_LIST_ITEM) {
if (indent >= container->as.list.marker_offset +
container->as.list.padding) {
offset += container->as.list.marker_offset +
container->as.list.padding;
} else if (blank) {
offset = first_nonspace;
} else {
all_matched = false;
}
} else if (container->type == NODE_CODE_BLOCK) {
if (!container->as.code.fenced) { // indented
if (indent >= CODE_INDENT) {
offset += CODE_INDENT;
} else if (blank) {
offset = first_nonspace;
} else {
all_matched = false;
}
} else {
// skip optional spaces of fence offset
i = container->as.code.fence_offset;
while (i > 0 && peek_at(&input, offset) == ' ') {
offset++;
i--;
}
}
} else if (container->type == NODE_HEADER) {
// a header can never contain more than one line
all_matched = false;
if (blank) {
container->last_line_blank = true;
}
} else if (container->type == NODE_HTML) {
if (blank) {
container->last_line_blank = true;
all_matched = false;
}
} else if (container->type == NODE_PARAGRAPH) {
if (blank) {
container->last_line_blank = true;
all_matched = false;
}
}
if (!all_matched) {
container = container->parent; // back up to last matching cmark_node
break;
}
}
last_matched_container = container;
// check to see if we've hit 2nd blank line, break out of list:
if (blank && container->last_line_blank) {
break_out_of_lists(parser, &container, parser->line_number);
}
// unless last matched container is code cmark_node, try new container starts:
while (container->type != NODE_CODE_BLOCK &&
container->type != NODE_HTML) {
first_nonspace = offset;
while (peek_at(&input, first_nonspace) == ' ')
first_nonspace++;
indent = first_nonspace - offset;
blank = peek_at(&input, first_nonspace) == '\n';
if (indent >= CODE_INDENT) {
if (cur->type != NODE_PARAGRAPH && !blank) {
offset += CODE_INDENT;
container = add_child(parser, container, NODE_CODE_BLOCK, parser->line_number, offset + 1);
container->as.code.fenced = false;
container->as.code.fence_char = 0;
container->as.code.fence_length = 0;
container->as.code.fence_offset = 0;
strbuf_init(&container->as.code.info, 0);
} else { // indent > 4 in lazy line
break;
}
} else if (peek_at(&input, first_nonspace) == '>') {
offset = first_nonspace + 1;
// optional following character
if (peek_at(&input, offset) == ' ')
offset++;
container = add_child(parser, container, NODE_BLOCK_QUOTE, parser->line_number, offset + 1);
} else if ((matched = scan_atx_header_start(&input, first_nonspace))) {
offset = first_nonspace + matched;
container = add_child(parser, container, NODE_HEADER, parser->line_number, offset + 1);
int hashpos = chunk_strchr(&input, '#', first_nonspace);
int level = 0;
while (peek_at(&input, hashpos) == '#') {
level++;
hashpos++;
}
container->as.header.level = level;
container->as.header.setext = false;
} else if ((matched = scan_open_code_fence(&input, first_nonspace))) {
container = add_child(parser, container, NODE_CODE_BLOCK, parser->line_number, first_nonspace + 1);
container->as.code.fenced = true;
container->as.code.fence_char = peek_at(&input, first_nonspace);
container->as.code.fence_length = matched;
container->as.code.fence_offset = first_nonspace - offset;
strbuf_init(&container->as.code.info, 0);
offset = first_nonspace + matched;
} else if ((matched = scan_html_block_tag(&input, first_nonspace))) {
container = add_child(parser, container, NODE_HTML, parser->line_number, first_nonspace + 1);
// note, we don't adjust offset because the tag is part of the text
} else if (container->type == NODE_PARAGRAPH &&
(lev = scan_setext_header_line(&input, first_nonspace)) &&
// check that there is only one line in the paragraph:
strbuf_strrchr(&container->string_content, '\n',
strbuf_len(&container->string_content) - 2) < 0) {
container->type = NODE_HEADER;
container->as.header.level = lev;
container->as.header.setext = true;
offset = input.len - 1;
} else if (!(container->type == NODE_PARAGRAPH && !all_matched) &&
(matched = scan_hrule(&input, first_nonspace))) {
// it's only now that we know the line is not part of a setext header:
container = add_child(parser, container, NODE_HRULE, parser->line_number, first_nonspace + 1);
finalize(parser, container, parser->line_number);
container = container->parent;
offset = input.len - 1;
} else if ((matched = parse_list_marker(&input, first_nonspace, &data))) {
// compute padding:
offset = first_nonspace + matched;
i = 0;
while (i <= 5 && peek_at(&input, offset + i) == ' ') {
i++;
}
// i = number of spaces after marker, up to 5
if (i >= 5 || i < 1 || peek_at(&input, offset) == '\n') {
data->padding = matched + 1;
if (i > 0) {
offset += 1;
}
} else {
data->padding = matched + i;
offset += i;
}
// check container; if it's a list, see if this list item
// can continue the list; otherwise, create a list container.
data->marker_offset = indent;
if (container->type != NODE_LIST ||
!lists_match(&container->as.list, data)) {
container = add_child(parser, container, NODE_LIST, parser->line_number,
first_nonspace + 1);
memcpy(&container->as.list, data, sizeof(*data));
}
// add the list item
container = add_child(parser, container, NODE_LIST_ITEM, parser->line_number,
first_nonspace + 1);
/* TODO: static */
memcpy(&container->as.list, data, sizeof(*data));
free(data);
} else {
break;
}
if (accepts_lines(container->type)) {
// if it's a line container, it can't contain other containers
break;
}
}
// what remains at offset is a text line. add the text to the
// appropriate container.
first_nonspace = offset;
while (peek_at(&input, first_nonspace) == ' ')
first_nonspace++;
indent = first_nonspace - offset;
blank = peek_at(&input, first_nonspace) == '\n';
// cmark_node quote lines are never blank as they start with >
// and we don't count blanks in fenced code for purposes of tight/loose
// lists or breaking out of lists. we also don't set last_line_blank
// on an empty list item.
container->last_line_blank = (blank &&
container->type != NODE_BLOCK_QUOTE &&
container->type != NODE_HEADER &&
(container->type != NODE_CODE_BLOCK &&
container->as.code.fenced) &&
!(container->type == NODE_LIST_ITEM &&
container->first_child == NULL &&
container->start_line == parser->line_number));
cmark_node *cont = container;
while (cont->parent) {
cont->parent->last_line_blank = false;
cont = cont->parent;
}
if (cur != last_matched_container &&
container == last_matched_container &&
!blank &&
cur->type == NODE_PARAGRAPH &&
strbuf_len(&cur->string_content) > 0) {
add_line(cur, &input, offset);
} else { // not a lazy continuation
// finalize any blocks that were not matched and set cur to container:
while (cur != last_matched_container) {
finalize(parser, cur, parser->line_number);
cur = cur->parent;
assert(cur != NULL);
}
if (container->type == NODE_CODE_BLOCK &&
!container->as.code.fenced) {
add_line(container, &input, offset);
} else if (container->type == NODE_CODE_BLOCK &&
container->as.code.fenced) {
matched = 0;
if (indent <= 3 &&
peek_at(&input, first_nonspace) == container->as.code.fence_char) {
int fence_len = scan_close_code_fence(&input, first_nonspace);
if (fence_len > container->as.code.fence_length)
matched = 1;
}
if (matched) {
// if closing fence, don't add line to container; instead, close it:
finalize(parser, container, parser->line_number);
container = container->parent; // back up to parent
} else {
add_line(container, &input, offset);
}
} else if (container->type == NODE_HTML) {
add_line(container, &input, offset);
} else if (blank) {
// ??? do nothing
} else if (container->type == NODE_HEADER) {
chop_trailing_hashtags(&input);
add_line(container, &input, first_nonspace);
finalize(parser, container, parser->line_number);
container = container->parent;
} else if (accepts_lines(container->type)) {
add_line(container, &input, first_nonspace);
} else if (container->type != NODE_HRULE &&
container->type != NODE_HEADER) {
// create paragraph container for line
container = add_child(parser, container, NODE_PARAGRAPH, parser->line_number, first_nonspace + 1);
add_line(container, &input, first_nonspace);
} else {
assert(false);
}
parser->current = container;
}
strbuf_clear(parser->curline);
}
cmark_node *cmark_parser_finish(cmark_parser *parser)
{
if (parser->linebuf->size) {
S_process_line(parser, parser->linebuf->ptr,
parser->linebuf->size);
strbuf_clear(parser->linebuf);
}
finalize_document(parser);
strbuf_free(parser->curline);
#if CMARK_DEBUG_NODES
if (cmark_node_check(parser->root, stderr)) {
abort();
}
#endif
return parser->root;
}

375
outside/commonmark/src/buffer.c Normal file
View File

@ -0,0 +1,375 @@
#include <stdarg.h>
#include <ctype.h>
#include <string.h>
#include <assert.h>
#include <string.h>
#include <stdio.h>
#include <stdlib.h>
#include "buffer.h"
/* Used as default value for strbuf->ptr so that people can always
* assume ptr is non-NULL and zero terminated even for new strbufs.
*/
unsigned char cmark_strbuf__initbuf[1];
unsigned char cmark_strbuf__oom[1];
#define ENSURE_SIZE(b, d) \
if ((d) > buf->asize && strbuf_grow(b, (d)) < 0) \
return -1;
#ifndef MIN
#define MIN(x,y) ((x<y) ? x : y)
#endif
void cmark_strbuf_init(strbuf *buf, int initial_size)
{
buf->asize = 0;
buf->size = 0;
buf->ptr = cmark_strbuf__initbuf;
if (initial_size)
cmark_strbuf_grow(buf, initial_size);
}
int cmark_strbuf_try_grow(strbuf *buf, int target_size, bool mark_oom)
{
unsigned char *new_ptr;
int new_size;
if (buf->ptr == cmark_strbuf__oom)
return -1;
if (target_size <= buf->asize)
return 0;
if (buf->asize == 0) {
new_size = target_size;
new_ptr = NULL;
} else {
new_size = buf->asize;
new_ptr = buf->ptr;
}
/* grow the buffer size by 1.5, until it's big enough
* to fit our target size */
while (new_size < target_size)
new_size = (new_size << 1) - (new_size >> 1);
/* round allocation up to multiple of 8 */
new_size = (new_size + 7) & ~7;
new_ptr = (unsigned char *)realloc(new_ptr, new_size);
if (!new_ptr) {
if (mark_oom)
buf->ptr = cmark_strbuf__oom;
return -1;
}
buf->asize = new_size;
buf->ptr = new_ptr;
/* truncate the existing buffer size if necessary */
if (buf->size >= buf->asize)
buf->size = buf->asize - 1;
buf->ptr[buf->size] = '\0';
return 0;
}
int cmark_strbuf_grow(cmark_strbuf *buf, int target_size)
{
return cmark_strbuf_try_grow(buf, target_size, true);
}
bool cmark_strbuf_oom(const cmark_strbuf *buf)
{
return (buf->ptr == cmark_strbuf__oom);
}
size_t cmark_strbuf_len(const cmark_strbuf *buf)
{
return buf->size;
}
void cmark_strbuf_free(strbuf *buf)
{
if (!buf) return;
if (buf->ptr != cmark_strbuf__initbuf && buf->ptr != cmark_strbuf__oom)
free(buf->ptr);
cmark_strbuf_init(buf, 0);
}
void cmark_strbuf_clear(strbuf *buf)
{
buf->size = 0;
if (buf->asize > 0)
buf->ptr[0] = '\0';
}
int cmark_strbuf_set(strbuf *buf, const unsigned char *data, int len)
{
if (len <= 0 || data == NULL) {
cmark_strbuf_clear(buf);
} else {
if (data != buf->ptr) {
ENSURE_SIZE(buf, len + 1);
memmove(buf->ptr, data, len);
}
buf->size = len;
buf->ptr[buf->size] = '\0';
}
return 0;
}
int cmark_strbuf_sets(strbuf *buf, const char *string)
{
return cmark_strbuf_set(buf,
(const unsigned char *)string,
string ? strlen(string) : 0);
}
int cmark_strbuf_putc(strbuf *buf, int c)
{
ENSURE_SIZE(buf, buf->size + 2);
buf->ptr[buf->size++] = c;
buf->ptr[buf->size] = '\0';
return 0;
}
int cmark_strbuf_put(strbuf *buf, const unsigned char *data, int len)
{
if (len <= 0)
return 0;
ENSURE_SIZE(buf, buf->size + len + 1);
memmove(buf->ptr + buf->size, data, len);
buf->size += len;
buf->ptr[buf->size] = '\0';
return 0;
}
int cmark_strbuf_puts(strbuf *buf, const char *string)
{
return cmark_strbuf_put(buf, (const unsigned char *)string, strlen(string));
}
int cmark_strbuf_vprintf(strbuf *buf, const char *format, va_list ap)
{
const int expected_size = buf->size + (strlen(format) * 2);
int len;
ENSURE_SIZE(buf, expected_size);
while (1) {
len = vsnprintf(
(char *)buf->ptr + buf->size,
buf->asize - buf->size,
format, ap
);
if (len < 0) {
free(buf->ptr);
buf->ptr = cmark_strbuf__oom;
return -1;
}
if (len + 1 <= buf->asize - buf->size) {
buf->size += len;
break;
}
ENSURE_SIZE(buf, buf->size + len + 1);
}
return 0;
}
int cmark_strbuf_printf(strbuf *buf, const char *format, ...)
{
int r;
va_list ap;
va_start(ap, format);
r = cmark_strbuf_vprintf(buf, format, ap);
va_end(ap);
return r;
}
void cmark_strbuf_copy_cstr(char *data, int datasize, const strbuf *buf)
{
int copylen;
assert(data && datasize && buf);
data[0] = '\0';
if (buf->size == 0 || buf->asize <= 0)
return;
copylen = buf->size;
if (copylen > datasize - 1)
copylen = datasize - 1;
memmove(data, buf->ptr, copylen);
data[copylen] = '\0';
}
void cmark_strbuf_swap(strbuf *buf_a, strbuf *buf_b)
{
strbuf t = *buf_a;
*buf_a = *buf_b;
*buf_b = t;
}
unsigned char *cmark_strbuf_detach(strbuf *buf)
{
unsigned char *data = buf->ptr;
if (buf->asize == 0 || buf->ptr == cmark_strbuf__oom) {
/* return an empty string */
return (unsigned char *)calloc(1, 1);
}
cmark_strbuf_init(buf, 0);
return data;
}
void cmark_strbuf_attach(strbuf *buf, unsigned char *ptr, int asize)
{
cmark_strbuf_free(buf);
if (ptr) {
buf->ptr = ptr;
buf->size = strlen((char *)ptr);
if (asize)
buf->asize = (asize < buf->size) ? buf->size + 1 : asize;
else /* pass 0 to fall back on strlen + 1 */
buf->asize = buf->size + 1;
} else {
cmark_strbuf_grow(buf, asize);
}
}
int cmark_strbuf_cmp(const strbuf *a, const strbuf *b)
{
int result = memcmp(a->ptr, b->ptr, MIN(a->size, b->size));
return (result != 0) ? result :
(a->size < b->size) ? -1 : (a->size > b->size) ? 1 : 0;
}
int cmark_strbuf_strchr(const strbuf *buf, int c, int pos)
{
const unsigned char *p = (unsigned char *)memchr(buf->ptr + pos, c, buf->size - pos);
if (!p)
return -1;
return (int)(p - (const unsigned char *)buf->ptr);
}
int cmark_strbuf_strrchr(const strbuf *buf, int c, int pos)
{
int i;
for (i = pos; i >= 0; i--) {
if (buf->ptr[i] == (unsigned char) c)
return i;
}
return -1;
}
void cmark_strbuf_truncate(strbuf *buf, int len)
{
if (len < buf->size) {
buf->size = len;
buf->ptr[buf->size] = '\0';
}
}
void cmark_strbuf_drop(strbuf *buf, int n)
{
if (n > 0) {
buf->size = buf->size - n;
if (buf->size)
memmove(buf->ptr, buf->ptr + n, buf->size);
buf->ptr[buf->size] = '\0';
}
}
void cmark_strbuf_rtrim(strbuf *buf)
{
if (!buf->size)
return;
while (buf->size > 0) {
if (!isspace(buf->ptr[buf->size - 1]))
break;
buf->size--;
}
buf->ptr[buf->size] = '\0';
}
void cmark_strbuf_trim(strbuf *buf)
{
int i = 0;
if (!buf->size)
return;
while (i < buf->size && isspace(buf->ptr[i]))
i++;
cmark_strbuf_drop(buf, i);
cmark_strbuf_rtrim(buf);
}
// Destructively modify string, collapsing consecutive
// space and newline characters into a single space.
void cmark_strbuf_normalize_whitespace(strbuf *s)
{
bool last_char_was_space = false;
int r, w;
for (r = 0, w = 0; r < s->size; ++r) {
switch (s->ptr[r]) {
case ' ':
case '\n':
if (last_char_was_space)
break;
s->ptr[w++] = ' ';
last_char_was_space = true;
break;
default:
s->ptr[w++] = s->ptr[r];
last_char_was_space = false;
}
}
cmark_strbuf_truncate(s, w);
}
// Destructively unescape a string: remove backslashes before punctuation chars.
extern void cmark_strbuf_unescape(strbuf *buf)
{
int r, w;
for (r = 0, w = 0; r < buf->size; ++r) {
if (buf->ptr[r] == '\\' && ispunct(buf->ptr[r + 1]))
continue;
buf->ptr[w++] = buf->ptr[r];
}
cmark_strbuf_truncate(buf, w);
}

177
outside/commonmark/src/buffer.h Normal file
View File

@ -0,0 +1,177 @@
#ifndef CMARK_BUFFER_H
#define CMARK_BUFFER_H
#include <stddef.h>
#include <stdarg.h>
#include "config.h"
#include "cmark_export.h"
#ifdef __cplusplus
extern "C" {
#endif
typedef struct {
unsigned char *ptr;
int asize, size;
} cmark_strbuf;
CMARK_EXPORT
extern unsigned char cmark_strbuf__initbuf[];
CMARK_EXPORT
extern unsigned char cmark_strbuf__oom[];
#define CMARK_GH_BUF_INIT { cmark_strbuf__initbuf, 0, 0 }
/**
* Initialize a strbuf structure.
*
* For the cases where GH_BUF_INIT cannot be used to do static
* initialization.
*/
CMARK_EXPORT
void cmark_strbuf_init(cmark_strbuf *buf, int initial_size);
/**
* Attempt to grow the buffer to hold at least `target_size` bytes.
*
* If the allocation fails, this will return an error. If mark_oom is true,
* this will mark the buffer as invalid for future operations; if false,
* existing buffer content will be preserved, but calling code must handle
* that buffer was not expanded.
*/
CMARK_EXPORT
int cmark_strbuf_try_grow(cmark_strbuf *buf, int target_size, bool mark_oom);
/**
* Grow the buffer to hold at least `target_size` bytes.
*
* If the allocation fails, this will return an error and the buffer will be
* marked as invalid for future operations, invaliding contents.
*
* @return 0 on success or -1 on failure
*/
CMARK_EXPORT
int cmark_strbuf_grow(cmark_strbuf *buf, int target_size);
CMARK_EXPORT
void cmark_strbuf_free(cmark_strbuf *buf);
CMARK_EXPORT
void cmark_strbuf_swap(cmark_strbuf *buf_a, cmark_strbuf *buf_b);
/**
* Test if there have been any reallocation failures with this strbuf.
*
* Any function that writes to a strbuf can fail due to memory allocation
* issues. If one fails, the strbuf will be marked with an OOM error and
* further calls to modify the buffer will fail. Check strbuf_oom() at the
* end of your sequence and it will be true if you ran out of memory at any
* point with that buffer.
*
* @return false if no error, true if allocation error
*/
CMARK_EXPORT
bool cmark_strbuf_oom(const cmark_strbuf *buf);
CMARK_EXPORT
size_t cmark_strbuf_len(const cmark_strbuf *buf);
CMARK_EXPORT
int cmark_strbuf_cmp(const cmark_strbuf *a, const cmark_strbuf *b);
CMARK_EXPORT
void cmark_strbuf_attach(cmark_strbuf *buf, unsigned char *ptr, int asize);
CMARK_EXPORT
unsigned char *cmark_strbuf_detach(cmark_strbuf *buf);
CMARK_EXPORT
void cmark_strbuf_copy_cstr(char *data, int datasize, const cmark_strbuf *buf);
static inline const char *cmark_strbuf_cstr(const cmark_strbuf *buf)
{
return (char *)buf->ptr;
}
#define cmark_strbuf_at(buf, n) ((buf)->ptr[n])
/*
* Functions below that return int value error codes will return 0 on
* success or -1 on failure (which generally means an allocation failed).
* Using a strbuf where the allocation has failed with result in -1 from
* all further calls using that buffer. As a result, you can ignore the
* return code of these functions and call them in a series then just call
* strbuf_oom at the end.
*/
CMARK_EXPORT
int cmark_strbuf_set(cmark_strbuf *buf, const unsigned char *data, int len);
CMARK_EXPORT
int cmark_strbuf_sets(cmark_strbuf *buf, const char *string);
CMARK_EXPORT
int cmark_strbuf_putc(cmark_strbuf *buf, int c);
CMARK_EXPORT
int cmark_strbuf_put(cmark_strbuf *buf, const unsigned char *data, int len);
CMARK_EXPORT
int cmark_strbuf_puts(cmark_strbuf *buf, const char *string);
CMARK_EXPORT
int cmark_strbuf_printf(cmark_strbuf *buf, const char *format, ...)
CMARK_ATTRIBUTE((format (printf, 2, 3)));
CMARK_EXPORT
int cmark_strbuf_vprintf(cmark_strbuf *buf, const char *format, va_list ap);
CMARK_EXPORT
void cmark_strbuf_clear(cmark_strbuf *buf);
CMARK_EXPORT
int cmark_strbuf_strchr(const cmark_strbuf *buf, int c, int pos);
CMARK_EXPORT
int cmark_strbuf_strrchr(const cmark_strbuf *buf, int c, int pos);
CMARK_EXPORT
void cmark_strbuf_drop(cmark_strbuf *buf, int n);
CMARK_EXPORT
void cmark_strbuf_truncate(cmark_strbuf *buf, int len);
CMARK_EXPORT
void cmark_strbuf_rtrim(cmark_strbuf *buf);
CMARK_EXPORT
void cmark_strbuf_trim(cmark_strbuf *buf);
CMARK_EXPORT
void cmark_strbuf_normalize_whitespace(cmark_strbuf *s);
CMARK_EXPORT
void cmark_strbuf_unescape(cmark_strbuf *s);
// Convenience macros
#define strbuf cmark_strbuf
#define strbuf__initbuf cmark_strbuf__initbuf
#define strbuf__oom cmark_strbuf__oom
#define GH_BUF_INIT CMARK_GH_BUF_INIT
#define strbuf_init cmark_strbuf_init
#define strbuf_try_grow cmark_strbuf_try_grow
#define strbuf_grow cmark_strbuf_grow
#define strbuf_free cmark_strbuf_free
#define strbuf_swap cmark_strbuf_swap
#define strbuf_oom cmark_strbuf_oom
#define strbuf_len cmark_strbuf_len
#define strbuf_cmp cmark_strbuf_cmp
#define strbuf_attach cmark_strbuf_attach
#define strbuf_detach cmark_strbuf_detach
#define strbuf_copy_cstr cmark_strbuf_copy_cstr
#define strbuf_at cmark_strbuf_at
#define strbuf_set cmark_strbuf_set
#define strbuf_sets cmark_strbuf_sets
#define strbuf_putc cmark_strbuf_putc
#define strbuf_put cmark_strbuf_put
#define strbuf_puts cmark_strbuf_puts
#define strbuf_printf cmark_strbuf_printf
#define strbuf_vprintf cmark_strbuf_vprintf
#define strbuf_clear cmark_strbuf_clear
#define strbuf_strchr cmark_strbuf_strchr
#define strbuf_strrchr cmark_strbuf_strrchr
#define strbuf_drop cmark_strbuf_drop
#define strbuf_truncate cmark_strbuf_truncate
#define strbuf_rtrim cmark_strbuf_rtrim
#define strbuf_trim cmark_strbuf_trim
#define strbuf_normalize_whitespace cmark_strbuf_normalize_whitespace
#define strbuf_unescape cmark_strbuf_unescape
#ifdef __cplusplus
}
#endif
#endif

2637
outside/commonmark/src/case_fold_switch.inc Normal file
View File

File diff suppressed because it is too large Load Diff

122
outside/commonmark/src/chunk.h Normal file
View File

@ -0,0 +1,122 @@
#ifndef CMARK_CHUNK_H
#define CMARK_CHUNK_H
#include <string.h>
#include <ctype.h>
#include <stdlib.h>
#include <assert.h>
#include "buffer.h"
typedef struct {
unsigned char *data;
int len;
int alloc; // also implies a NULL-terminated string
} cmark_chunk;
static inline void cmark_chunk_free(cmark_chunk *c)
{
if (c->alloc)
free(c->data);
c->data = NULL;
c->alloc = 0;
c->len = 0;
}
static inline void cmark_chunk_ltrim(cmark_chunk *c)
{
assert(!c->alloc);
while (c->len && isspace(c->data[0])) {
c->data++;
c->len--;
}
}
static inline void cmark_chunk_rtrim(cmark_chunk *c)
{
while (c->len > 0) {
if (!isspace(c->data[c->len - 1]))
break;
c->len--;
}
}
static inline void cmark_chunk_trim(cmark_chunk *c)
{
cmark_chunk_ltrim(c);
cmark_chunk_rtrim(c);
}
static inline int cmark_chunk_strchr(cmark_chunk *ch, int c, int offset)
{
const unsigned char *p = (unsigned char *)memchr(ch->data + offset, c, ch->len - offset);
return p ? (int)(p - ch->data) : ch->len;
}
static inline const char *cmark_chunk_to_cstr(cmark_chunk *c)
{
unsigned char *str;
if (c->alloc) {
return (char *)c->data;
}
str = (unsigned char *)malloc(c->len + 1);
if(str != NULL) {
memcpy(str, c->data, c->len);
str[c->len] = 0;
}
c->data = str;
c->alloc = 1;
return (char *)str;
}
static inline void cmark_chunk_set_cstr(cmark_chunk *c, const char *str)
{
if (c->alloc) {
free(c->data);
}
c->len = strlen(str);
c->data = (unsigned char *)malloc(c->len + 1);
c->alloc = 1;
memcpy(c->data, str, c->len + 1);
}
static inline cmark_chunk cmark_chunk_literal(const char *data)
{
cmark_chunk c = {(unsigned char *)data, data ? strlen(data) : 0, 0};
return c;
}
static inline cmark_chunk cmark_chunk_dup(const cmark_chunk *ch, int pos, int len)
{
cmark_chunk c = {ch->data + pos, len, 0};
return c;
}
static inline cmark_chunk cmark_chunk_buf_detach(cmark_strbuf *buf)
{
cmark_chunk c;
c.len = buf->size;
c.data = cmark_strbuf_detach(buf);
c.alloc = 1;
return c;
}
// Convenience macros
#define chunk cmark_chunk
#define chunk_free cmark_chunk_free
#define chunk_ltrim cmark_chunk_ltrim
#define chunk_rtrim cmark_chunk_rtrim
#define chunk_trim cmark_chunk_trim
#define chunk_strchr cmark_chunk_strchr
#define chunk_to_cstr cmark_chunk_to_cstr
#define chunk_literal cmark_chunk_literal
#define chunk_dup cmark_chunk_dup
#define chunk_buf_detach cmark_chunk_buf_detach
#endif

21
outside/commonmark/src/cmark.c Normal file
View File

@ -0,0 +1,21 @@
#include <stdlib.h>
#include <assert.h>
#include <stdio.h>
#include "node.h"
#include "html/houdini.h"
#include "cmark.h"
#include "buffer.h"
char *cmark_markdown_to_html(const char *text, int len)
{
cmark_node *doc;
char *result;
doc = cmark_parse_document(text, len);
result = cmark_render_html(doc);
cmark_node_free(doc);
return result;
}

343
outside/commonmark/src/cmark.h Normal file
View File

@ -0,0 +1,343 @@
#ifndef CMARK_H
#define CMARK_H
#include <stdio.h>
#include "cmark_export.h"
#ifdef __cplusplus
extern "C" {
#endif
/** .SH NAME
*
* .B cmark
* \- CommonMark parsing, manipulating, and rendering
*/
/** .SH SIMPLE INTERFACE
*/
/** Current version of library.
*/
#define CMARK_VERSION "0.1"
/** Convert 'text' (assumed to be a UTF-8 encoded string with length
* 'len' from CommonMark Markdown to HTML, returning a null-terminated,
* UTF-8-encoded string.
*/
CMARK_EXPORT
char *cmark_markdown_to_html(const char *text, int len);
/** .SH NODE STRUCTURE
*/
/**
*/
typedef enum {
/* Block */
CMARK_NODE_DOCUMENT,
CMARK_NODE_BLOCK_QUOTE,
CMARK_NODE_LIST,
CMARK_NODE_LIST_ITEM,
CMARK_NODE_CODE_BLOCK,
CMARK_NODE_HTML,
CMARK_NODE_PARAGRAPH,
CMARK_NODE_HEADER,
CMARK_NODE_HRULE,
CMARK_NODE_REFERENCE_DEF,
CMARK_NODE_FIRST_BLOCK = CMARK_NODE_DOCUMENT,
CMARK_NODE_LAST_BLOCK = CMARK_NODE_REFERENCE_DEF,
/* Inline */
CMARK_NODE_TEXT,
CMARK_NODE_SOFTBREAK,
CMARK_NODE_LINEBREAK,
CMARK_NODE_INLINE_CODE,
CMARK_NODE_INLINE_HTML,
CMARK_NODE_EMPH,
CMARK_NODE_STRONG,
CMARK_NODE_LINK,
CMARK_NODE_IMAGE,
CMARK_NODE_FIRST_INLINE = CMARK_NODE_TEXT,
CMARK_NODE_LAST_INLINE = CMARK_NODE_IMAGE,
} cmark_node_type;
/**
*/
typedef enum {
CMARK_NO_LIST,
CMARK_BULLET_LIST,
CMARK_ORDERED_LIST
} cmark_list_type;
/**
*/
typedef enum {
CMARK_PERIOD_DELIM,
CMARK_PAREN_DELIM
} cmark_delim_type;
typedef struct cmark_node cmark_node;
typedef struct cmark_parser cmark_parser;
/**
* .SH CREATING AND DESTROYING NODES
*/
/**
*/
CMARK_EXPORT cmark_node*
cmark_node_new(cmark_node_type type);
/**
*/
CMARK_EXPORT void
cmark_node_free(cmark_node *node);
/**
* .SH TREE TRAVERSAL
*/
CMARK_EXPORT cmark_node*
cmark_node_next(cmark_node *node);
/**
*/
CMARK_EXPORT cmark_node*
cmark_node_previous(cmark_node *node);
/**
*/
CMARK_EXPORT cmark_node*
cmark_node_parent(cmark_node *node);
/**
*/
CMARK_EXPORT cmark_node*
cmark_node_first_child(cmark_node *node);
/**
*/
CMARK_EXPORT cmark_node*
cmark_node_last_child(cmark_node *node);
/**
* .SH ACCESSORS
*/
/**
*/
CMARK_EXPORT cmark_node_type
cmark_node_get_type(cmark_node *node);
/**
*/
CMARK_EXPORT const char*
cmark_node_get_string_content(cmark_node *node);
/**
*/
CMARK_EXPORT int
cmark_node_set_string_content(cmark_node *node, const char *content);
/**
*/
CMARK_EXPORT int
cmark_node_get_header_level(cmark_node *node);
/**
*/
CMARK_EXPORT int
cmark_node_set_header_level(cmark_node *node, int level);
/**
*/
CMARK_EXPORT cmark_list_type
cmark_node_get_list_type(cmark_node *node);
/**
*/
CMARK_EXPORT int
cmark_node_set_list_type(cmark_node *node, cmark_list_type type);
/**
*/
CMARK_EXPORT int
cmark_node_get_list_start(cmark_node *node);
/**
*/
CMARK_EXPORT int
cmark_node_set_list_start(cmark_node *node, int start);
/**
*/
CMARK_EXPORT int
cmark_node_get_list_tight(cmark_node *node);
/**
*/
CMARK_EXPORT int
cmark_node_set_list_tight(cmark_node *node, int tight);
/**
*/
CMARK_EXPORT const char*
cmark_node_get_fence_info(cmark_node *node);
/**
*/
CMARK_EXPORT int
cmark_node_set_fence_info(cmark_node *node, const char *info);
/**
*/
CMARK_EXPORT const char*
cmark_node_get_url(cmark_node *node);
/**
*/
CMARK_EXPORT int
cmark_node_set_url(cmark_node *node, const char *url);
/**
*/
CMARK_EXPORT const char*
cmark_node_get_title(cmark_node *node);
/**
*/
CMARK_EXPORT int
cmark_node_set_title(cmark_node *node, const char *title);
/**
*/
CMARK_EXPORT int
cmark_node_get_start_line(cmark_node *node);
/**
*/
CMARK_EXPORT int
cmark_node_get_start_column(cmark_node *node);
/**
*/
CMARK_EXPORT int
cmark_node_get_end_line(cmark_node *node);
/**
* .SH TREE MANIPULATION
*/
/**
*/
CMARK_EXPORT void
cmark_node_unlink(cmark_node *node);
/**
*/
CMARK_EXPORT int
cmark_node_insert_before(cmark_node *node, cmark_node *sibling);
/**
*/
CMARK_EXPORT int
cmark_node_insert_after(cmark_node *node, cmark_node *sibling);
/**
*/
CMARK_EXPORT int
cmark_node_prepend_child(cmark_node *node, cmark_node *child);
/**
*/
CMARK_EXPORT int
cmark_node_append_child(cmark_node *node, cmark_node *child);
/**
* .SH PARSING
*/
/**
*/
CMARK_EXPORT
cmark_parser *cmark_parser_new();
/**
*/
CMARK_EXPORT
void cmark_parser_free(cmark_parser *parser);
/**
*/
CMARK_EXPORT
cmark_node *cmark_parser_finish(cmark_parser *parser);
/**
*/
CMARK_EXPORT
void cmark_parser_feed(cmark_parser *parser, const char *buffer, size_t len);
/**
*/
CMARK_EXPORT
cmark_node *cmark_parse_document(const char *buffer, size_t len);
/**
*/
CMARK_EXPORT
cmark_node *cmark_parse_file(FILE *f);
/**
* .SH RENDERING
*/
/**
*/
CMARK_EXPORT
char *cmark_render_ast(cmark_node *root);
/**
*/
CMARK_EXPORT
char *cmark_render_html(cmark_node *root);
/** .SH AUTHORS
*
* John MacFarlane, Vicent Marti, Kārlis Gaņģis, Nick Wellnhofer.
*/
#ifndef CMARK_NO_SHORT_NAMES
#define NODE_DOCUMENT CMARK_NODE_DOCUMENT
#define NODE_BLOCK_QUOTE CMARK_NODE_BLOCK_QUOTE
#define NODE_LIST CMARK_NODE_LIST
#define NODE_LIST_ITEM CMARK_NODE_LIST_ITEM
#define NODE_CODE_BLOCK CMARK_NODE_CODE_BLOCK
#define NODE_HTML CMARK_NODE_HTML
#define NODE_PARAGRAPH CMARK_NODE_PARAGRAPH
#define NODE_HEADER CMARK_NODE_HEADER
#define NODE_HRULE CMARK_NODE_HRULE
#define NODE_REFERENCE_DEF CMARK_NODE_REFERENCE_DEF
#define NODE_TEXT CMARK_NODE_TEXT
#define NODE_SOFTBREAK CMARK_NODE_SOFTBREAK
#define NODE_LINEBREAK CMARK_NODE_LINEBREAK
#define NODE_INLINE_CODE CMARK_NODE_INLINE_CODE
#define NODE_INLINE_HTML CMARK_NODE_INLINE_HTML
#define NODE_EMPH CMARK_NODE_EMPH
#define NODE_STRONG CMARK_NODE_STRONG
#define NODE_LINK CMARK_NODE_LINK
#define NODE_IMAGE CMARK_NODE_IMAGE
#define NODE_LINK_LABEL CMARK_NODE_LINK_LABEL
#define BULLET_LIST CMARK_BULLET_LIST
#define ORDERED_LIST CMARK_ORDERED_LIST
#define PERIOD_DELIM CMARK_PERIOD_DELIM
#define PAREN_DELIM CMARK_PAREN_DELIM
#endif
#ifdef __cplusplus
}
#endif
#endif

49
outside/commonmark/src/config.h.in Normal file
View File

@ -0,0 +1,49 @@
#cmakedefine HAVE_STDBOOL_H
#ifdef HAVE_STDBOOL_H
#include <stdbool.h>
#elif !defined(__cplusplus)
typedef char bool;
#endif
#cmakedefine HAVE___BUILTIN_EXPECT
#cmakedefine HAVE___ATTRIBUTE__
#ifdef HAVE___ATTRIBUTE__
#define CMARK_ATTRIBUTE(list) __attribute__ (list)
#else
#define CMARK_ATTRIBUTE(list)
#endif
#if 1
#ifndef U3_ALL
#define U3_ALL
#define malloc(a) u3a_malloc(a)
#define calloc(a,b) u3a_calloc(a,b)
#define realloc(a,b) u3a_realloc(a,b)
#define free(a) u3a_free(a)
/* From i/n/a.h
*/
/* u3a_malloc(): aligned storage measured in bytes.
*/
void*
u3a_malloc(size_t len_i);
/* u3a_calloc(): aligned storage measured in bytes.
*/
void*
u3a_calloc(size_t num_i, size_t len_i);
/* u3a_realloc(): aligned realloc in bytes.
*/
void*
u3a_realloc(void* lag_v, size_t len_i);
/* u3a_free(): free for aligned malloc.
*/
void
u3a_free(void* tox_v);
#endif
#endif

36
outside/commonmark/src/debug.h Normal file
View File

@ -0,0 +1,36 @@
#ifndef CMARK_DEBUG_H
#define CMARK_DEBUG_H
#include <stdio.h>
#include <errno.h>
#include <string.h>
#ifdef NDEBUG
#define debug(M, ...)
#else
#define debug(M, ...) \
fprintf(stderr, "DEBUG %s:%d: " M "\n", __FILE__, __LINE__, ##__VA_ARGS__)
#endif
#define clean_errno() (errno == 0 ? "None" : strerror(errno))
#define log_err(M, ...) \
fprintf(stderr, "[ERROR] (%s:%d: errno: %s) " M "\n", __FILE__, __LINE__, \
clean_errno(), ##__VA_ARGS__)
#define log_warn(M, ...) \
fprintf(stderr, "[WARN] (%s:%d: errno: %s) " M "\n", __FILE__, __LINE__, \
clean_errno(), ##__VA_ARGS__)
#define log_info(M, ...) fprintf(stderr, "[INFO] (%s:%d) " M "\n", __FILE__, \
__LINE__, ##__VA_ARGS__)
#define check(A, M, ...) \
if(!(A)) { log_err(M, ##__VA_ARGS__); errno=0; goto error; }
#define sentinel(M, ...) \
{ log_err(M, ##__VA_ARGS__); errno=0; goto error; }
#define check_debug(A, M, ...) \
if(!(A)) { debug(M, ##__VA_ARGS__); errno=0; goto error; }
#endif

52
outside/commonmark/src/html/houdini.h Normal file
View File

@ -0,0 +1,52 @@
#ifndef CMARK_HOUDINI_H
#define CMARK_HOUDINI_H
#ifdef __cplusplus
extern "C" {
#endif
#include <stdint.h>
#include "config.h"
#include "buffer.h"
#ifdef HAVE___BUILTIN_EXPECT
# define likely(x) __builtin_expect((x),1)
# define unlikely(x) __builtin_expect((x),0)
#else
# define likely(x) (x)
# define unlikely(x) (x)
#endif
#ifdef HOUDINI_USE_LOCALE
# define _isxdigit(c) isxdigit(c)
# define _isdigit(c) isdigit(c)
#else
/*
* Helper _isdigit methods -- do not trust the current locale
* */
# define _isxdigit(c) (strchr("0123456789ABCDEFabcdef", (c)) != NULL)
# define _isdigit(c) ((c) >= '0' && (c) <= '9')
#endif
#define HOUDINI_ESCAPED_SIZE(x) (((x) * 12) / 10)
#define HOUDINI_UNESCAPED_SIZE(x) (x)
extern size_t houdini_unescape_ent(strbuf *ob, const uint8_t *src, size_t size);
extern int houdini_escape_html(strbuf *ob, const uint8_t *src, size_t size);
extern int houdini_escape_html0(strbuf *ob, const uint8_t *src, size_t size, int secure);
extern int houdini_unescape_html(strbuf *ob, const uint8_t *src, size_t size);
extern void houdini_unescape_html_f(strbuf *ob, const uint8_t *src, size_t size);
extern int houdini_escape_xml(strbuf *ob, const uint8_t *src, size_t size);
extern int houdini_escape_uri(strbuf *ob, const uint8_t *src, size_t size);
extern int houdini_escape_url(strbuf *ob, const uint8_t *src, size_t size);
extern int houdini_escape_href(strbuf *ob, const uint8_t *src, size_t size);
extern int houdini_unescape_uri(strbuf *ob, const uint8_t *src, size_t size);
extern int houdini_unescape_url(strbuf *ob, const uint8_t *src, size_t size);
extern int houdini_escape_js(strbuf *ob, const uint8_t *src, size_t size);
extern int houdini_unescape_js(strbuf *ob, const uint8_t *src, size_t size);
#ifdef __cplusplus
}
#endif
#endif

107
outside/commonmark/src/html/houdini_href_e.c Normal file
View File

@ -0,0 +1,107 @@
#include <assert.h>
#include <stdio.h>
#include <string.h>
#include "html/houdini.h"
/*
* The following characters will not be escaped:
*
* -_.+!*'(),%#@?=;:/,+&$ alphanum
*
* Note that this character set is the addition of:
*
* - The characters which are safe to be in an URL
* - The characters which are *not* safe to be in
* an URL because they are RESERVED characters.
*
* We asume (lazily) that any RESERVED char that
* appears inside an URL is actually meant to
* have its native function (i.e. as an URL
* component/separator) and hence needs no escaping.
*
* There are two exceptions: the chacters & (amp)
* and ' (single quote) do not appear in the table.
* They are meant to appear in the URL as components,
* yet they require special HTML-entity escaping
* to generate valid HTML markup.
*
* All other characters will be escaped to %XX.
*
*/
static const char HREF_SAFE[] = {
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 1, 0, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 0, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 1,
0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
};
int
houdini_escape_href(strbuf *ob, const uint8_t *src, size_t size)
{
static const uint8_t hex_chars[] = "0123456789ABCDEF";
size_t i = 0, org;
uint8_t hex_str[3];
hex_str[0] = '%';
while (i < size) {
org = i;
while (i < size && HREF_SAFE[src[i]] != 0)
i++;
if (likely(i > org))
strbuf_put(ob, src + org, i - org);
/* escaping */
if (i >= size)
break;
switch (src[i]) {
/* amp appears all the time in URLs, but needs
* HTML-entity escaping to be inside an href */
case '&':
strbuf_puts(ob, "&amp;");
break;
/* the single quote is a valid URL character
* according to the standard; it needs HTML
* entity escaping too */
case '\'':
strbuf_puts(ob, "&#x27;");
break;
/* the space can be escaped to %20 or a plus
* sign. we're going with the generic escape
* for now. the plus thing is more commonly seen
* when building GET strings */
#if 0
case ' ':
strbuf_putc(ob, '+');
break;
#endif
/* every other character goes with a %XX escaping */
default:
hex_str[1] = hex_chars[(src[i] >> 4) & 0xF];
hex_str[2] = hex_chars[src[i] & 0xF];
strbuf_put(ob, hex_str, 3);
}
i++;
}
return 1;
}

81
outside/commonmark/src/html/houdini_html_e.c Normal file
View File

@ -0,0 +1,81 @@
#include <assert.h>
#include <stdio.h>
#include <string.h>
#include "html/houdini.h"
/**
* According to the OWASP rules:
*
* & --> &amp;
* < --> &lt;
* > --> &gt;
* " --> &quot;
* ' --> &#x27; &apos; is not recommended
* / --> &#x2F; forward slash is included as it helps end an HTML entity
*
*/
static const char HTML_ESCAPE_TABLE[] = {
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 1, 0, 0, 0, 2, 3, 0, 0, 0, 0, 0, 0, 0, 4,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 5, 0, 6, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
};
static const char *HTML_ESCAPES[] = {
"",
"&quot;",
"&amp;",
"&#39;",
"&#47;",
"&lt;",
"&gt;"
};
int
houdini_escape_html0(strbuf *ob, const uint8_t *src, size_t size, int secure)
{
size_t i = 0, org, esc = 0;
while (i < size) {
org = i;
while (i < size && (esc = HTML_ESCAPE_TABLE[src[i]]) == 0)
i++;
if (i > org)
strbuf_put(ob, src + org, i - org);
/* escaping */
if (unlikely(i >= size))
break;
/* The forward slash is only escaped in secure mode */
if ((src[i] == '/' || src[i] == '\'') && !secure) {
strbuf_putc(ob, src[i]);
} else {
strbuf_puts(ob, HTML_ESCAPES[esc]);
}
i++;
}
return 1;
}
int
houdini_escape_html(strbuf *ob, const uint8_t *src, size_t size)
{
return houdini_escape_html0(ob, src, size, 1);
}

112
outside/commonmark/src/html/houdini_html_u.c Normal file
View File

@ -0,0 +1,112 @@
#include <assert.h>
#include <stdio.h>
#include <string.h>
#include "buffer.h"
#include "houdini.h"
#include "utf8.h"
#include "html_unescape.h"
size_t
houdini_unescape_ent(strbuf *ob, const uint8_t *src, size_t size)
{
size_t i = 0;
if (size > 3 && src[0] == '#') {
int codepoint = 0;
if (_isdigit(src[1])) {
for (i = 1; i < size && _isdigit(src[i]); ++i) {
int cp = (codepoint * 10) + (src[i] - '0');
if (cp < codepoint)
return 0;
codepoint = cp;
}
}
else if (src[1] == 'x' || src[1] == 'X') {
for (i = 2; i < size && _isxdigit(src[i]); ++i) {
int cp = (codepoint * 16) + ((src[i] | 32) % 39 - 9);
if (cp < codepoint)
return 0;
codepoint = cp;
}
}
if (i < size && src[i] == ';' && codepoint) {
utf8proc_encode_char(codepoint, ob);
return i + 1;
}
}
else {
if (size > MAX_WORD_LENGTH)
size = MAX_WORD_LENGTH;
for (i = MIN_WORD_LENGTH; i < size; ++i) {
if (src[i] == ' ')
break;
if (src[i] == ';') {
const struct html_ent *entity = find_entity((char *)src, i);
if (entity != NULL) {
strbuf_put(ob, entity->utf8, entity->utf8_len);
return i + 1;
}
break;
}
}
}
return 0;
}
int
houdini_unescape_html(strbuf *ob, const uint8_t *src, size_t size)
{
size_t i = 0, org, ent;
while (i < size) {
org = i;
while (i < size && src[i] != '&')
i++;
if (likely(i > org)) {
if (unlikely(org == 0)) {
if (i >= size)
return 0;
strbuf_grow(ob, HOUDINI_UNESCAPED_SIZE(size));
}
strbuf_put(ob, src + org, i - org);
}
/* escaping */
if (i >= size)
break;
i++;
ent = houdini_unescape_ent(ob, src + i, size - i);
i += ent;
/* not really an entity */
if (ent == 0)
strbuf_putc(ob, '&');
}
return 1;
}
void houdini_unescape_html_f(strbuf *ob, const uint8_t *src, size_t size)
{
if (!houdini_unescape_html(ob, src, size))
strbuf_put(ob, src, size);
}

357
outside/commonmark/src/html/html.c Normal file
View File

@ -0,0 +1,357 @@
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include <assert.h>
#include "config.h"
#include "cmark.h"
#include "node.h"
#include "buffer.h"
#include "html/houdini.h"
// Functions to convert cmark_nodes to HTML strings.
static bool
finish_node(strbuf *html, cmark_node *node, bool tight);
static void escape_html(strbuf *dest, const unsigned char *source, int length)
{
if (length < 0)
length = strlen((char *)source);
houdini_escape_html0(dest, source, (size_t)length, 0);
}
static void escape_href(strbuf *dest, const unsigned char *source, int length)
{
if (length < 0)
length = strlen((char *)source);
houdini_escape_href(dest, source, (size_t)length);
}
static inline void cr(strbuf *html)
{
if (html->size && html->ptr[html->size - 1] != '\n')
strbuf_putc(html, '\n');
}
// Convert the inline children of a node to a plain string.
static void inlines_to_plain_html(strbuf *html, cmark_node* node)
{
cmark_node* cur = node->first_child;
if (cur == NULL) {
return;
}
while (true) {
switch(cur->type) {
case NODE_TEXT:
case NODE_INLINE_CODE:
case NODE_INLINE_HTML:
escape_html(html, cur->as.literal.data, cur->as.literal.len);
break;
case NODE_LINEBREAK:
case NODE_SOFTBREAK:
strbuf_putc(html, ' ');
break;
default:
break;
}
if (cur->first_child) {
cur = cur->first_child;
continue;
}
next_sibling:
if (cur->next) {
cur = cur->next;
continue;
}
cur = cur->parent;
if (cur == node) {
break;
}
goto next_sibling;
}
}
// Convert a cmark_node to HTML.
static void node_to_html(strbuf *html, cmark_node *node)
{
cmark_node *cur;
char start_header[] = "<h0>";
bool tight = false;
bool visit_children;
strbuf *info;
if (node == NULL) {
return;
}
cur = node;
while (true) {
// Only NODE_IMAGE wants to skip its children.
visit_children = true;
switch(cur->type) {
case NODE_DOCUMENT:
break;
case NODE_PARAGRAPH:
if (!tight) {
cr(html);
strbuf_puts(html, "<p>");
}
break;
case NODE_BLOCK_QUOTE:
cr(html);
strbuf_puts(html, "<blockquote>\n");
// BLOCK_QUOTE doesn't use any of the 'as' structs,
// so the 'list' member can be used to store the
// current value of 'tight'.
cur->as.list.tight = tight;
tight = false;
break;
case NODE_LIST_ITEM:
cr(html);
strbuf_puts(html, "<li>");
break;
case NODE_LIST: {
cmark_list *list = &cur->as.list;
bool tmp;
// make sure a list starts at the beginning of the line:
cr(html);
if (list->list_type == CMARK_BULLET_LIST) {
strbuf_puts(html, "<ul>\n");
}
else if (list->start == 1) {
strbuf_puts(html, "<ol>\n");
}
else {
strbuf_printf(html, "<ol start=\"%d\">\n",
list->start);
}
// Store the current value of 'tight' by swapping.
tmp = list->tight;
list->tight = tight;
tight = tmp;
break;
}
case NODE_HEADER:
cr(html);
start_header[2] = '0' + cur->as.header.level;
strbuf_puts(html, start_header);
break;
case NODE_CODE_BLOCK:
info = &cur->as.code.info;
cr(html);
if (&cur->as.code.fence_length == 0
|| strbuf_len(info) == 0) {
strbuf_puts(html, "<pre><code>");
}
else {
int first_tag = strbuf_strchr(info, ' ', 0);
if (first_tag < 0)
first_tag = strbuf_len(info);
strbuf_puts(html,
"<pre><code class=\"language-");
escape_html(html, info->ptr, first_tag);
strbuf_puts(html, "\">");
}
escape_html(html, cur->string_content.ptr, cur->string_content.size);
break;
case NODE_HTML:
cr(html);
strbuf_put(html, cur->string_content.ptr, cur->string_content.size);
break;
case NODE_HRULE:
cr(html);
strbuf_puts(html, "<hr />\n");
break;
case NODE_REFERENCE_DEF:
break;
case NODE_TEXT:
escape_html(html, cur->as.literal.data, cur->as.literal.len);
break;
case NODE_LINEBREAK:
strbuf_puts(html, "<br />\n");
break;
case NODE_SOFTBREAK:
strbuf_putc(html, '\n');
break;
case NODE_INLINE_CODE:
strbuf_puts(html, "<code>");
escape_html(html, cur->as.literal.data, cur->as.literal.len);
break;
case NODE_INLINE_HTML:
strbuf_put(html,
cur->as.literal.data,
cur->as.literal.len);
break;
case NODE_LINK:
strbuf_puts(html, "<a href=\"");
if (cur->as.link.url)
escape_href(html, cur->as.link.url, -1);
if (cur->as.link.title) {
strbuf_puts(html, "\" title=\"");
escape_html(html, cur->as.link.title, -1);
}
strbuf_puts(html, "\">");
break;
case NODE_IMAGE:
strbuf_puts(html, "<img src=\"");
if (cur->as.link.url)
escape_href(html, cur->as.link.url, -1);
strbuf_puts(html, "\" alt=\"");
inlines_to_plain_html(html, cur);
if (cur->as.link.title) {
strbuf_puts(html, "\" title=\"");
escape_html(html, cur->as.link.title, -1);
}
strbuf_puts(html, "\" />");
visit_children = false;
break;
case NODE_STRONG:
strbuf_puts(html, "<strong>");
break;
case NODE_EMPH:
strbuf_puts(html, "<em>");
break;
default:
assert(false);
}
if (visit_children && cur->first_child) {
cur = cur->first_child;
continue;
}
next_sibling:
tight = finish_node(html, cur, tight);
if (cur == node) {
break;
}
if (cur->next) {
cur = cur->next;
continue;
}
cur = cur->parent;
goto next_sibling;
}
}
// Returns the restored value of 'tight'.
static bool
finish_node(strbuf *html, cmark_node *node, bool tight)
{
char end_header[] = "</h0>\n";
switch (node->type) {
case NODE_PARAGRAPH:
if (!tight) {
strbuf_puts(html, "</p>\n");
}
break;
case NODE_BLOCK_QUOTE: {
cmark_list *list = &node->as.list;
strbuf_puts(html, "</blockquote>\n");
// Restore old 'tight' value.
tight = list->tight;
list->tight = false;
break;
}
case NODE_LIST_ITEM:
strbuf_puts(html, "</li>\n");
break;
case NODE_LIST: {
cmark_list *list = &node->as.list;
bool tmp;
strbuf_puts(html,
list->list_type == CMARK_BULLET_LIST ?
"</ul>\n" : "</ol>\n");
// Restore old 'tight' value.
tmp = tight;
tight = list->tight;
list->tight = tmp;
break;
}
case NODE_HEADER:
end_header[3] = '0' + node->as.header.level;
strbuf_puts(html, end_header);
break;
case NODE_CODE_BLOCK:
strbuf_puts(html, "</code></pre>\n");
break;
case NODE_INLINE_CODE:
strbuf_puts(html, "</code>");
break;
case NODE_LINK:
strbuf_puts(html, "</a>");
break;
case NODE_STRONG:
strbuf_puts(html, "</strong>");
break;
case NODE_EMPH:
strbuf_puts(html, "</em>");
break;
default:
break;
}
return tight;
}
char *cmark_render_html(cmark_node *root)
{
char *result;
strbuf html = GH_BUF_INIT;
node_to_html(&html, root);
result = (char *)strbuf_detach(&html);
strbuf_free(&html);
return result;
}

2131
outside/commonmark/src/html/html_unescape.gperf Normal file
View File

File diff suppressed because it is too large Load Diff

9736
outside/commonmark/src/html/html_unescape.h Normal file
View File

File diff suppressed because it is too large Load Diff

987
outside/commonmark/src/inlines.c Normal file
View File

@ -0,0 +1,987 @@
#include <stdlib.h>
#include <string.h>
#include <stdio.h>
#include <ctype.h>
#include "config.h"
#include "node.h"
#include "parser.h"
#include "references.h"
#include "cmark.h"
#include "html/houdini.h"
#include "utf8.h"
#include "scanners.h"
#include "inlines.h"
// Macros for creating various kinds of simple.
#define make_str(s) make_literal(CMARK_NODE_TEXT, s)
#define make_code(s) make_literal(CMARK_NODE_INLINE_CODE, s)
#define make_raw_html(s) make_literal(CMARK_NODE_INLINE_HTML, s)
#define make_linebreak() make_simple(CMARK_NODE_LINEBREAK)
#define make_softbreak() make_simple(CMARK_NODE_SOFTBREAK)
#define make_emph() make_simple(CMARK_NODE_EMPH)
#define make_strong() make_simple(CMARK_NODE_STRONG)
typedef struct delimiter {
struct delimiter *previous;
struct delimiter *next;
cmark_node *inl_text;
unsigned char delim_char;
int position;
bool can_open;
bool can_close;
} delimiter;
typedef struct {
chunk input;
int pos;
cmark_reference_map *refmap;
delimiter *last_delim;
} subject;
static delimiter*
S_insert_emph(subject *subj, delimiter *opener, delimiter *closer);
static int parse_inline(subject* subj, cmark_node * parent);
static void subject_from_buf(subject *e, strbuf *buffer,
cmark_reference_map *refmap);
static int subject_find_special_char(subject *subj);
static unsigned char *cmark_clean_autolink(chunk *url, int is_email)
{
strbuf buf = GH_BUF_INIT;
chunk_trim(url);
if (url->len == 0)
return NULL;
if (is_email)
strbuf_puts(&buf, "mailto:");
houdini_unescape_html_f(&buf, url->data, url->len);
return strbuf_detach(&buf);
}
static inline cmark_node *make_link(cmark_node *label, unsigned char *url, unsigned char *title)
{
cmark_node* e = (cmark_node *)calloc(1, sizeof(*e));
if(e != NULL) {
e->type = CMARK_NODE_LINK;
e->first_child = label;
e->last_child = label;
e->as.link.url = url;
e->as.link.title = title;
e->next = NULL;
label->parent = e;
}
return e;
}
static inline cmark_node* make_autolink(cmark_node* label, cmark_chunk url, int is_email)
{
return make_link(label, cmark_clean_autolink(&url, is_email), NULL);
}
// Create an inline with a literal string value.
static inline cmark_node* make_literal(cmark_node_type t, cmark_chunk s)
{
cmark_node * e = (cmark_node *)calloc(1, sizeof(*e));
if(e != NULL) {
e->type = t;
e->as.literal = s;
e->next = NULL;
e->prev = NULL;
e->parent = NULL;
e->first_child = NULL;
e->last_child = NULL;
// These fields aren't used for inlines:
e->start_line = 0;
e->start_column = 0;
e->end_line = 0;
}
return e;
}
// Create an inline with no value.
static inline cmark_node* make_simple(cmark_node_type t)
{
cmark_node* e = (cmark_node *)calloc(1, sizeof(*e));
if(e != NULL) {
e->type = t;
e->next = NULL;
e->prev = NULL;
e->parent = NULL;
e->first_child = NULL;
e->last_child = NULL;
// These fields aren't used for inlines:
e->start_line = 0;
e->start_column = 0;
e->end_line = 0;
}
return e;
}
static unsigned char *bufdup(const unsigned char *buf)
{
unsigned char *new_buf = NULL;
if (buf) {
int len = strlen((char *)buf);
new_buf = (unsigned char *)calloc(len + 1, sizeof(*new_buf));
if(new_buf != NULL) {
memcpy(new_buf, buf, len + 1);
}
}
return new_buf;
}
static void subject_from_buf(subject *e, strbuf *buffer,
cmark_reference_map *refmap)
{
e->input.data = buffer->ptr;
e->input.len = buffer->size;
e->input.alloc = 0;
e->pos = 0;
e->refmap = refmap;
e->last_delim = NULL;
chunk_rtrim(&e->input);
}
static inline int isbacktick(int c)
{
return (c == '`');
}
static inline unsigned char peek_char(subject *subj)
{
return (subj->pos < subj->input.len) ? subj->input.data[subj->pos] : 0;
}
static inline unsigned char peek_at(subject *subj, int pos)
{
return subj->input.data[pos];
}
// Return true if there are more characters in the subject.
static inline int is_eof(subject* subj)
{
return (subj->pos >= subj->input.len);
}
// Advance the subject. Doesn't check for eof.
#define advance(subj) (subj)->pos += 1
// Take characters while a predicate holds, and return a string.
static inline chunk take_while(subject* subj, int (*f)(int))
{
unsigned char c;
int startpos = subj->pos;
int len = 0;
while ((c = peek_char(subj)) && (*f)(c)) {
advance(subj);
len++;
}
return chunk_dup(&subj->input, startpos, len);
}
// Try to process a backtick code span that began with a
// span of ticks of length openticklength length (already
// parsed). Return 0 if you don't find matching closing
// backticks, otherwise return the position in the subject
// after the closing backticks.
static int scan_to_closing_backticks(subject* subj, int openticklength)
{
// read non backticks
unsigned char c;
while ((c = peek_char(subj)) && c != '`') {
advance(subj);
}
if (is_eof(subj)) {
return 0; // did not find closing ticks, return 0
}
int numticks = 0;
while (peek_char(subj) == '`') {
advance(subj);
numticks++;
}
if (numticks != openticklength){
return(scan_to_closing_backticks(subj, openticklength));
}
return (subj->pos);
}
// Parse backtick code section or raw backticks, return an inline.
// Assumes that the subject has a backtick at the current position.
static cmark_node* handle_backticks(subject *subj)
{
chunk openticks = take_while(subj, isbacktick);
int startpos = subj->pos;
int endpos = scan_to_closing_backticks(subj, openticks.len);
if (endpos == 0) { // not found
subj->pos = startpos; // rewind
return make_str(openticks);
} else {
strbuf buf = GH_BUF_INIT;
strbuf_set(&buf, subj->input.data + startpos, endpos - startpos - openticks.len);
strbuf_trim(&buf);
strbuf_normalize_whitespace(&buf);
return make_code(chunk_buf_detach(&buf));
}
}
// Scan ***, **, or * and return number scanned, or 0.
// Advances position.
static int scan_delims(subject* subj, unsigned char c, bool * can_open, bool * can_close)
{
int numdelims = 0;
unsigned char char_before, char_after;
char_before = subj->pos == 0 ? '\n' : peek_at(subj, subj->pos - 1);
while (peek_char(subj) == c) {
numdelims++;
advance(subj);
}
char_after = peek_char(subj);
*can_open = numdelims > 0 && !isspace(char_after);
*can_close = numdelims > 0 && !isspace(char_before);
if (c == '_') {
*can_open = *can_open && !isalnum(char_before);
*can_close = *can_close && !isalnum(char_after);
}
return numdelims;
}
/*
static void print_delimiters(subject *subj)
{
delimiter *delim;
delim = subj->last_delim;
while (delim != NULL) {
printf("Item at %p: %d %d %d next(%p) prev(%p)\n",
delim, delim->delim_char,
delim->can_open, delim->can_close,
delim->next, delim->previous);
delim = delim->previous;
}
}
*/
static void remove_delimiter(subject *subj, delimiter *delim)
{
if (delim == NULL) return;
if (delim->next == NULL) {
// end of list:
assert(delim == subj->last_delim);
subj->last_delim = delim->previous;
} else {
delim->next->previous = delim->previous;
}
if (delim->previous != NULL) {
delim->previous->next = delim->next;
}
free(delim);
}
static void push_delimiter(subject *subj, unsigned char c, bool can_open,
bool can_close, cmark_node *inl_text)
{
delimiter *delim =
(delimiter*)malloc(sizeof(delimiter));
if (delim == NULL) {
return;
}
delim->delim_char = c;
delim->can_open = can_open;
delim->can_close = can_close;
delim->inl_text = inl_text;
delim->previous = subj->last_delim;
delim->next = NULL;
if (delim->previous != NULL) {
delim->previous->next = delim;
}
delim->position = subj->pos;
subj->last_delim = delim;
}
// Parse strong/emph or a fallback.
// Assumes the subject has '_' or '*' at the current position.
static cmark_node* handle_strong_emph(subject* subj, unsigned char c)
{
int numdelims;
cmark_node * inl_text;
bool can_open, can_close;
numdelims = scan_delims(subj, c, &can_open, &can_close);
inl_text = make_str(chunk_dup(&subj->input, subj->pos - numdelims, numdelims));
if (can_open || can_close) {
push_delimiter(subj, c, can_open, can_close, inl_text);
}
return inl_text;
}
static void process_emphasis(subject *subj, delimiter *start_delim)
{
delimiter *closer = subj->last_delim;
delimiter *opener;
// move back to first relevant delim.
while (closer != NULL && closer->previous != start_delim) {
closer = closer->previous;
}
// now move forward, looking for closers, and handling each
while (closer != NULL) {
if (closer->can_close &&
(closer->delim_char == '*' || closer->delim_char == '_')) {
// Now look backwards for first matching opener:
opener = closer->previous;
while (opener != NULL && opener != start_delim) {
if (opener->delim_char == closer->delim_char &&
opener->can_open) {
break;
}
opener = opener->previous;
}
if (opener != NULL && opener != start_delim) {
closer = S_insert_emph(subj, opener, closer);
} else {
closer = closer->next;
}
} else {
closer = closer->next;
}
}
// free all delimiters in list until start_delim:
while (subj->last_delim != start_delim) {
remove_delimiter(subj, subj->last_delim);
}
}
static delimiter*
S_insert_emph(subject *subj, delimiter *opener, delimiter *closer)
{
delimiter *delim, *tmp_delim;
int use_delims;
cmark_node *opener_inl = opener->inl_text;
cmark_node *closer_inl = closer->inl_text;
int opener_num_chars = opener_inl->as.literal.len;
int closer_num_chars = closer_inl->as.literal.len;
cmark_node *tmp, *emph, *first_child, *last_child;
// calculate the actual number of characters used from this closer
if (closer_num_chars < 3 || opener_num_chars < 3) {
use_delims = closer_num_chars <= opener_num_chars ?
closer_num_chars : opener_num_chars;
} else { // closer and opener both have >= 3 characters
use_delims = closer_num_chars % 2 == 0 ? 2 : 1;
}
// remove used characters from associated inlines.
opener_num_chars -= use_delims;
closer_num_chars -= use_delims;
opener_inl->as.literal.len = opener_num_chars;
closer_inl->as.literal.len = closer_num_chars;
// free delimiters between opener and closer
delim = closer->previous;
while (delim != NULL && delim != opener) {
tmp_delim = delim->previous;
remove_delimiter(subj, delim);
delim = tmp_delim;
}
first_child = opener_inl->next;
last_child = closer_inl->prev;
// if opener has 0 characters, remove it and its associated inline
if (opener_num_chars == 0) {
// replace empty opener inline with emph
chunk_free(&(opener_inl->as.literal));
emph = opener_inl;
emph->type = use_delims == 1 ? NODE_EMPH : NODE_STRONG;
// remove opener from list
remove_delimiter(subj, opener);
}
else {
// create new emph or strong, and splice it in to our inlines
// between the opener and closer
emph = use_delims == 1 ? make_emph() : make_strong();
emph->parent = opener_inl->parent;
emph->prev = opener_inl;
opener_inl->next = emph;
}
// push children below emph
emph->next = closer_inl;
closer_inl->prev = emph;
emph->first_child = first_child;
emph->last_child = last_child;
// fix children pointers
first_child->prev = NULL;
last_child->next = NULL;
for (tmp = first_child; tmp != NULL; tmp = tmp->next) {
tmp->parent = emph;
}
// if closer has 0 characters, remove it and its associated inline
if (closer_num_chars == 0) {
// remove empty closer inline
cmark_node_free(closer_inl);
// remove closer from list
tmp_delim = closer->next;
remove_delimiter(subj, closer);
closer = tmp_delim;
}
return closer;
}
// Parse backslash-escape or just a backslash, returning an inline.
static cmark_node* handle_backslash(subject *subj)
{
advance(subj);
unsigned char nextchar = peek_char(subj);
if (ispunct(nextchar)) { // only ascii symbols and newline can be escaped
advance(subj);
return make_str(chunk_dup(&subj->input, subj->pos - 1, 1));
} else if (nextchar == '\n') {
advance(subj);
return make_linebreak();
} else {
return make_str(chunk_literal("\\"));
}
}
// Parse an entity or a regular "&" string.
// Assumes the subject has an '&' character at the current position.
static cmark_node* handle_entity(subject* subj)
{
strbuf ent = GH_BUF_INIT;
size_t len;
advance(subj);
len = houdini_unescape_ent(&ent,
subj->input.data + subj->pos,
subj->input.len - subj->pos
);
if (len == 0)
return make_str(chunk_literal("&"));
subj->pos += len;
return make_str(chunk_buf_detach(&ent));
}
// Like make_str, but parses entities.
// Returns an inline sequence consisting of str and entity elements.
static cmark_node *make_str_with_entities(chunk *content)
{
strbuf unescaped = GH_BUF_INIT;
if (houdini_unescape_html(&unescaped, content->data, (size_t)content->len)) {
return make_str(chunk_buf_detach(&unescaped));
} else {
return make_str(*content);
}
}
// Clean a URL: remove surrounding whitespace and surrounding <>,
// and remove \ that escape punctuation.
unsigned char *cmark_clean_url(chunk *url)
{
strbuf buf = GH_BUF_INIT;
chunk_trim(url);
if (url->len == 0)
return NULL;
if (url->data[0] == '<' && url->data[url->len - 1] == '>') {
houdini_unescape_html_f(&buf, url->data + 1, url->len - 2);
} else {
houdini_unescape_html_f(&buf, url->data, url->len);
}
strbuf_unescape(&buf);
return strbuf_detach(&buf);
}
unsigned char *cmark_clean_title(chunk *title)
{
strbuf buf = GH_BUF_INIT;
unsigned char first, last;
if (title->len == 0)
return NULL;
first = title->data[0];
last = title->data[title->len - 1];
// remove surrounding quotes if any:
if ((first == '\'' && last == '\'') ||
(first == '(' && last == ')') ||
(first == '"' && last == '"')) {
houdini_unescape_html_f(&buf, title->data + 1, title->len - 2);
} else {
houdini_unescape_html_f(&buf, title->data, title->len);
}
strbuf_unescape(&buf);
return strbuf_detach(&buf);
}
// Parse an autolink or HTML tag.
// Assumes the subject has a '<' character at the current position.
static cmark_node* handle_pointy_brace(subject* subj)
{
int matchlen = 0;
chunk contents;
advance(subj); // advance past first <
// first try to match a URL autolink
matchlen = scan_autolink_uri(&subj->input, subj->pos);
if (matchlen > 0) {
contents = chunk_dup(&subj->input, subj->pos, matchlen - 1);
subj->pos += matchlen;
return make_autolink(
make_str_with_entities(&contents),
contents, 0
);
}
// next try to match an email autolink
matchlen = scan_autolink_email(&subj->input, subj->pos);
if (matchlen > 0) {
contents = chunk_dup(&subj->input, subj->pos, matchlen - 1);
subj->pos += matchlen;
return make_autolink(
make_str_with_entities(&contents),
contents, 1
);
}
// finally, try to match an html tag
matchlen = scan_html_tag(&subj->input, subj->pos);
if (matchlen > 0) {
contents = chunk_dup(&subj->input, subj->pos - 1, matchlen + 1);
subj->pos += matchlen;
return make_raw_html(contents);
}
// if nothing matches, just return the opening <:
return make_str(chunk_literal("<"));
}
// Parse a link label. Returns 1 if successful.
// Note: unescaped brackets are not allowed in labels.
// The label begins with `[` and ends with the first `]` character
// encountered. Backticks in labels do not start code spans.
static int link_label(subject* subj, chunk *raw_label)
{
int startpos = subj->pos;
int length = 0;
unsigned char c;
// advance past [
if (peek_char(subj) == '[') {
advance(subj);
} else {
return 0;
}
while ((c = peek_char(subj)) && c != '[' && c != ']') {
if (c == '\\') {
advance(subj);
length++;
if (ispunct(peek_char(subj))) {
advance(subj);
length++;
}
} else {
advance(subj);
length++;
}
if (length > MAX_LINK_LABEL_LENGTH) {
goto noMatch;
}
}
if (c == ']') { // match found
*raw_label = chunk_dup(&subj->input, startpos + 1, subj->pos - (startpos + 1));
advance(subj); // advance past ]
return 1;
}
noMatch:
subj->pos = startpos; // rewind
return 0;
}
// Return a link, an image, or a literal close bracket.
static cmark_node* handle_close_bracket(subject* subj, cmark_node *parent)
{
int initial_pos;
int starturl, endurl, starttitle, endtitle, endall;
int n;
int sps;
cmark_reference *ref;
bool is_image = false;
chunk urlchunk, titlechunk;
unsigned char *url, *title;
delimiter *opener;
delimiter *tmp_delim;
cmark_node *link_text;
cmark_node *inl;
chunk raw_label;
int found_label;
advance(subj); // advance past ]
initial_pos = subj->pos;
// look through list of delimiters for a [ or !
opener = subj->last_delim;
while (opener) {
if (opener->delim_char == '[' || opener->delim_char == '!') {
break;
}
opener = opener->previous;
}
if (opener == NULL) {
return make_str(chunk_literal("]"));
}
// If we got here, we matched a potential link/image text.
is_image = opener->delim_char == '!';
link_text = opener->inl_text->next;
// Now we check to see if it's a link/image.
// First, look for an inline link.
if (peek_char(subj) == '(' &&
((sps = scan_spacechars(&subj->input, subj->pos + 1)) > -1) &&
((n = scan_link_url(&subj->input, subj->pos + 1 + sps)) > -1)) {
// try to parse an explicit link:
starturl = subj->pos + 1 + sps; // after (
endurl = starturl + n;
starttitle = endurl + scan_spacechars(&subj->input, endurl);
// ensure there are spaces btw url and title
endtitle = (starttitle == endurl) ? starttitle :
starttitle + scan_link_title(&subj->input, starttitle);
endall = endtitle + scan_spacechars(&subj->input, endtitle);
if (peek_at(subj, endall) == ')') {
subj->pos = endall + 1;
urlchunk = chunk_dup(&subj->input, starturl, endurl - starturl);
titlechunk = chunk_dup(&subj->input, starttitle, endtitle - starttitle);
url = cmark_clean_url(&urlchunk);
title = cmark_clean_title(&titlechunk);
chunk_free(&urlchunk);
chunk_free(&titlechunk);
goto match;
} else {
goto noMatch;
}
}
// Next, look for a following [link label] that matches in refmap.
// skip spaces
subj->pos = subj->pos + scan_spacechars(&subj->input, subj->pos);
raw_label = chunk_literal("");
found_label = link_label(subj, &raw_label);
if (!found_label || raw_label.len == 0) {
chunk_free(&raw_label);
raw_label = chunk_dup(&subj->input, opener->position,
initial_pos - opener->position - 1);
}
if (!found_label) {
// If we have a shortcut reference link, back up
// to before the spacse we skipped.
subj->pos = initial_pos;
}
ref = cmark_reference_lookup(subj->refmap, &raw_label);
chunk_free(&raw_label);
if (ref != NULL) { // found
url = bufdup(ref->url);
title = bufdup(ref->title);
goto match;
} else {
goto noMatch;
}
noMatch:
// If we fall through to here, it means we didn't match a link:
remove_delimiter(subj, opener); // remove this opener from delimiter list
subj->pos = initial_pos;
return make_str(chunk_literal("]"));
match:
inl = opener->inl_text;
inl->type = is_image ? NODE_IMAGE : NODE_LINK;
chunk_free(&inl->as.literal);
inl->first_child = link_text;
process_emphasis(subj, opener->previous);
inl->as.link.url = url;
inl->as.link.title = title;
inl->next = NULL;
if (link_text) {
cmark_node *tmp;
link_text->prev = NULL;
for (tmp = link_text; tmp->next != NULL; tmp = tmp->next) {
tmp->parent = inl;
}
tmp->parent = inl;
inl->last_child = tmp;
}
parent->last_child = inl;
// process_emphasis will remove this delimiter and all later ones.
// Now, if we have a link, we also want to remove earlier link
// delimiters. (This code can be removed if we decide to allow links
// inside links.)
if (!is_image) {
opener = subj->last_delim;
while (opener != NULL) {
tmp_delim = opener->previous;
if (opener->delim_char == '[') {
remove_delimiter(subj, opener);
}
opener = tmp_delim;
}
}
return NULL;
}
// Parse a hard or soft linebreak, returning an inline.
// Assumes the subject has a newline at the current position.
static cmark_node* handle_newline(subject *subj)
{
int nlpos = subj->pos;
// skip over newline
advance(subj);
// skip spaces at beginning of line
while (peek_char(subj) == ' ') {
advance(subj);
}
if (nlpos > 1 &&
peek_at(subj, nlpos - 1) == ' ' &&
peek_at(subj, nlpos - 2) == ' ') {
return make_linebreak();
} else {
return make_softbreak();
}
}
static int subject_find_special_char(subject *subj)
{
// "\n\\`&_*[]<!"
static const int8_t SPECIAL_CHARS[256] = {
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 0, 1,
1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 };
int n = subj->pos + 1;
while (n < subj->input.len) {
if (SPECIAL_CHARS[subj->input.data[n]])
return n;
n++;
}
return subj->input.len;
}
// Parse an inline, advancing subject, and add it as a child of parent.
// Return 0 if no inline can be parsed, 1 otherwise.
static int parse_inline(subject* subj, cmark_node * parent)
{
cmark_node* new_inl = NULL;
chunk contents;
unsigned char c;
int endpos;
c = peek_char(subj);
if (c == 0) {
return 0;
}
switch(c){
case '\n':
new_inl = handle_newline(subj);
break;
case '`':
new_inl = handle_backticks(subj);
break;
case '\\':
new_inl = handle_backslash(subj);
break;
case '&':
new_inl = handle_entity(subj);
break;
case '<':
new_inl = handle_pointy_brace(subj);
break;
case '*':
case '_':
new_inl = handle_strong_emph(subj, c);
break;
case '[':
advance(subj);
new_inl = make_str(chunk_literal("["));
push_delimiter(subj, '[', true, false, new_inl);
break;
case ']':
new_inl = handle_close_bracket(subj, parent);
break;
case '!':
advance(subj);
if (peek_char(subj) == '[') {
advance(subj);
new_inl = make_str(chunk_literal("!["));
push_delimiter(subj, '!', false, true, new_inl);
} else {
new_inl = make_str(chunk_literal("!"));
}
break;
default:
endpos = subject_find_special_char(subj);
contents = chunk_dup(&subj->input, subj->pos, endpos - subj->pos);
subj->pos = endpos;
// if we're at a newline, strip trailing spaces.
if (peek_char(subj) == '\n') {
chunk_rtrim(&contents);
}
new_inl = make_str(contents);
}
if (new_inl != NULL) {
cmark_node_append_child(parent, new_inl);
}
return 1;
}
// Parse inlines from parent's string_content, adding as children of parent.
extern void cmark_parse_inlines(cmark_node* parent, cmark_reference_map *refmap)
{
subject subj;
subject_from_buf(&subj, &parent->string_content, refmap);
while (!is_eof(&subj) && parse_inline(&subj, parent)) ;
process_emphasis(&subj, NULL);
}
// Parse zero or more space characters, including at most one newline.
static void spnl(subject* subj)
{
bool seen_newline = false;
while (peek_char(subj) == ' ' ||
(!seen_newline &&
(seen_newline = peek_char(subj) == '\n'))) {
advance(subj);
}
}
// Parse reference. Assumes string begins with '[' character.
// Modify refmap if a reference is encountered.
// Return 0 if no reference found, otherwise position of subject
// after reference is parsed.
int cmark_parse_reference_inline(strbuf *input, cmark_reference_map *refmap)
{
subject subj;
chunk lab;
chunk url;
chunk title;
int matchlen = 0;
int beforetitle;
subject_from_buf(&subj, input, NULL);
// parse label:
if (!link_label(&subj, &lab))
return 0;
// colon:
if (peek_char(&subj) == ':') {
advance(&subj);
} else {
return 0;
}
// parse link url:
spnl(&subj);
matchlen = scan_link_url(&subj.input, subj.pos);
if (matchlen) {
url = chunk_dup(&subj.input, subj.pos, matchlen);
subj.pos += matchlen;
} else {
return 0;
}
// parse optional link_title
beforetitle = subj.pos;
spnl(&subj);
matchlen = scan_link_title(&subj.input, subj.pos);
if (matchlen) {
title = chunk_dup(&subj.input, subj.pos, matchlen);
subj.pos += matchlen;
} else {
subj.pos = beforetitle;
title = chunk_literal("");
}
// parse final spaces and newline:
while (peek_char(&subj) == ' ') {
advance(&subj);
}
if (peek_char(&subj) == '\n') {
advance(&subj);
} else if (peek_char(&subj) != 0) {
return 0;
}
// insert reference into refmap
cmark_reference_create(refmap, &lab, &url, &title);
return subj.pos;
}

19
outside/commonmark/src/inlines.h Normal file
View File

@ -0,0 +1,19 @@
#ifndef CMARK_INLINES_H
#define CMARK_INLINES_H
#ifdef __cplusplus
extern "C" {
#endif
unsigned char *cmark_clean_url(cmark_chunk *url);
unsigned char *cmark_clean_title(cmark_chunk *title);
void cmark_parse_inlines(cmark_node* parent, cmark_reference_map *refmap);
int cmark_parse_reference_inline(cmark_strbuf *input, cmark_reference_map *refmap);
#ifdef __cplusplus
}
#endif
#endif

114
outside/commonmark/src/main.c Normal file
View File

@ -0,0 +1,114 @@
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include <errno.h>
#include "config.h"
#include "cmark.h"
#include "debug.h"
#include "bench.h"
void print_usage()
{
printf("Usage: cmark [FILE*]\n");
printf("Options: --help, -h Print usage information\n");
printf(" --ast Print AST instead of HTML\n");
printf(" --version Print version\n");
}
static void print_document(cmark_node *document, bool ast)
{
char *result;
if (ast) {
result = cmark_render_ast(document);
} else {
result = cmark_render_html(document);
}
printf("%s", result);
free(result);
}
int main(int argc, char *argv[])
{
int i, numfps = 0;
bool ast = false;
int *files;
char buffer[4096];
cmark_parser *parser;
size_t bytes;
cmark_node *document;
parser = cmark_parser_new();
files = (int *)malloc(argc * sizeof(*files));
for (i = 1; i < argc; i++) {
if (strcmp(argv[i], "--version") == 0) {
printf("cmark %s", CMARK_VERSION);
printf(" - CommonMark converter (c) 2014 John MacFarlane\n");
exit(0);
} else if ((strcmp(argv[i], "--help") == 0) ||
(strcmp(argv[i], "-h") == 0)) {
print_usage();
exit(0);
} else if (strcmp(argv[i], "--ast") == 0) {
ast = true;
} else if (*argv[i] == '-') {
print_usage();
exit(1);
} else { // treat as file argument
files[numfps++] = i;
}
}
for (i = 0; i < numfps; i++) {
FILE *fp = fopen(argv[files[i]], "r");
if (fp == NULL) {
fprintf(stderr, "Error opening file %s: %s\n",
argv[files[i]], strerror(errno));
exit(1);
}
start_timer();
while ((bytes = fread(buffer, 1, sizeof(buffer), fp)) > 0) {
cmark_parser_feed(parser, buffer, bytes);
if (bytes < sizeof(buffer)) {
break;
}
}
end_timer("processing lines");
fclose(fp);
}
if (numfps == 0) {
/*
document = cmark_parse_file(stdin);
print_document(document, ast);
exit(0);
*/
while ((bytes = fread(buffer, 1, sizeof(buffer), stdin)) > 0) {
cmark_parser_feed(parser, buffer, bytes);
if (bytes < sizeof(buffer)) {
break;
}
}
}
start_timer();
document = cmark_parser_finish(parser);
end_timer("finishing document");
cmark_parser_free(parser);
start_timer();
print_document(document, ast);
end_timer("print_document");
start_timer();
cmark_node_free(document);
end_timer("free_blocks");
free(files);
return 0;
}

Some files were not shown because too many files have changed in this diff Show More