mirror of
https://github.com/alpmestan/taggy.git
synced 2024-10-26 16:01:39 +03:00
141 lines
4.6 KiB
Plaintext
141 lines
4.6 KiB
Plaintext
name: taggy
|
|
version: 0.2.1
|
|
synopsis: Efficient and simple HTML/XML parsing library
|
|
description:
|
|
/taggy/ is a simple package for parsing HTML (and should work with XML)
|
|
written on top of the <http://hackage.haskell.org/package/attoparsec attoparsec>
|
|
library, which makes it one of the most efficient (space and time consumption wise)
|
|
on hackage.
|
|
.
|
|
This is the root module of /taggy/. It reexports everything
|
|
from the package. See each module's docs for details about
|
|
the functions and types involved in /taggy/.
|
|
.
|
|
While we've been testing the parser on /many/ pages, it may still
|
|
be a bit rough around the edges. Let us know on <http://github.com/alpmestan/taggy/issues github>
|
|
if you have any problem.
|
|
.
|
|
If you like to look at your HTML through
|
|
various optical instruments, feel free to take a look at
|
|
the companion <http://hackage.haskell.org/package/taggy-lens taggy-lens>
|
|
package we've put up together. It makes HTML parsing a piece of cake.
|
|
.
|
|
If you want to parse a document as list of tags
|
|
and go through it as some kind of stream by just picking
|
|
what you need, head to "Text.Taggy.Parser" and take
|
|
a look at 'Text.Taggy.Parser.taggyWith' and
|
|
'Text.Taggy.Parser.run'.
|
|
.
|
|
If you want to parse the document as a DOM tree and
|
|
traverse it to find the information you need,
|
|
use 'Text.Taggy.DOM.parseDOM'. This is especially useful
|
|
when used in conjunction with <http://hackage.haskell.org/package/taggy-lens taggy-lens>.
|
|
.
|
|
If you build some HTML manually
|
|
or just transform some existing DOM tree
|
|
and want to turn it into a 'Data.Text.Lazy.Text'
|
|
head to "Text.Taggy.Renderer" and look at 'Text.Taggy.Renderer.render'.
|
|
homepage: http://github.com/alpmestan/taggy
|
|
license: BSD3
|
|
license-file: LICENSE
|
|
author: Alp Mestanogullari, Vikram Verma
|
|
maintainer: alpmestan@gmail.com
|
|
copyright: 2014 Alp Mestanogullari, Vikram Verma
|
|
category: Text, Web
|
|
build-type: Simple
|
|
extra-source-files: html_files/*.html
|
|
data-files: html_files/*.html
|
|
cabal-version: >=1.10
|
|
|
|
library
|
|
exposed-modules: Text.Taggy,
|
|
Text.Taggy.DOM,
|
|
Text.Taggy.Entities,
|
|
Text.Taggy.Parser,
|
|
Text.Taggy.Renderer
|
|
Text.Taggy.Types
|
|
other-modules:
|
|
build-depends: base >=4.6 && <5,
|
|
blaze-html >= 0.7,
|
|
blaze-markup >= 0.6,
|
|
text >= 1,
|
|
attoparsec >=0.11,
|
|
vector >=0.7,
|
|
unordered-containers >= 0.2
|
|
hs-source-dirs: src
|
|
default-language: Haskell2010
|
|
ghc-options: -Wall -O2 -fno-warn-unused-do-bind -funbox-strict-fields
|
|
ghc-prof-options: -Wall -O2 -fno-warn-unused-do-bind -funbox-strict-fields -prof -auto-all
|
|
|
|
executable taggy
|
|
main-is: taggy.hs
|
|
hs-source-dirs: example
|
|
build-depends: base >=4.5 && <5,
|
|
text >= 1,
|
|
attoparsec >=0.12,
|
|
taggy
|
|
ghc-options: -Wall -O2 -fno-warn-unused-do-bind
|
|
ghc-prof-options: -Wall -prof -auto-all -O2 -fno-warn-unused-do-bind -rtsopts "-with-rtsopts=-sstderr -p"
|
|
default-language: Haskell2010
|
|
|
|
benchmark taggytagsoup
|
|
main-is: vs-tagsoup.hs
|
|
hs-source-dirs: bench
|
|
ghc-options: -O2 -funbox-strict-fields
|
|
type: exitcode-stdio-1.0
|
|
build-depends: base >= 4 && < 5,
|
|
text >=1,
|
|
attoparsec >=0.12,
|
|
taggy,
|
|
tagsoup,
|
|
criterion,
|
|
vector
|
|
default-language: Haskell2010
|
|
|
|
test-suite unit
|
|
type:
|
|
exitcode-stdio-1.0
|
|
ghc-options:
|
|
-Wall -O -fno-warn-unused-do-bind
|
|
hs-source-dirs:
|
|
src, tests/unit
|
|
main-is:
|
|
Spec.hs
|
|
build-depends:
|
|
base == 4.*
|
|
, blaze-html
|
|
, blaze-markup
|
|
, text
|
|
, hspec
|
|
, hspec-attoparsec
|
|
, vector
|
|
, attoparsec
|
|
, unordered-containers
|
|
default-language:
|
|
Haskell2010
|
|
|
|
test-suite integration
|
|
type:
|
|
exitcode-stdio-1.0
|
|
ghc-options:
|
|
-Wall -O -fno-warn-unused-do-bind
|
|
hs-source-dirs:
|
|
src, tests/integration
|
|
main-is:
|
|
Main.hs
|
|
build-depends:
|
|
base == 4.*
|
|
, blaze-html
|
|
, blaze-markup
|
|
, directory
|
|
, text
|
|
, hspec >= 1.11
|
|
, hspec-attoparsec
|
|
, vector
|
|
, attoparsec
|
|
, unordered-containers
|
|
other-modules:
|
|
Paths_taggy
|
|
default-language:
|
|
Haskell2010
|