mirror of
https://github.com/swarm-game/swarm.git
synced 2024-10-05 20:19:09 +03:00
autopopulate spellchecker (#1749)
Builds upon #1587. Extract all symbol names that are not native to the current project and insert them into our own custom spell checking dictionary's "words" list. The premise is that symbols that *are* native to our project should be spellchecked, but foreign symbols that constitute unrecognized dictionary words are presumably intentionally spelled that way. # Convention Manually-added words (i.e. for names in code that we've written for this project) will go into `.vscode/settings.json`. The automatically generated word list from third-party packages goes into `cspell.json`. # Usage scripts/spellcheck/autopopulate-spellchecker.sh
This commit is contained in:
parent
42d4e54797
commit
9f5c165fd8
37
.vscode/settings.json
vendored
37
.vscode/settings.json
vendored
@ -16,92 +16,63 @@
|
|||||||
"antiquotation",
|
"antiquotation",
|
||||||
"antiquoted",
|
"antiquoted",
|
||||||
"antiquoting",
|
"antiquoting",
|
||||||
"assocs",
|
|
||||||
"autoplay",
|
"autoplay",
|
||||||
"Bifunctor",
|
|
||||||
"bimap",
|
|
||||||
"Blackhole",
|
"Blackhole",
|
||||||
"Blackholes",
|
"Blackholes",
|
||||||
"bquote",
|
"bquote",
|
||||||
"Bytestring",
|
"Bytestring",
|
||||||
"callsite",
|
"callsite",
|
||||||
"cata",
|
|
||||||
"CESK",
|
|
||||||
"Cmds",
|
"Cmds",
|
||||||
"Colour",
|
|
||||||
"Combinators",
|
|
||||||
"conv",
|
"conv",
|
||||||
"Corasick",
|
"Corasick",
|
||||||
"datatypes",
|
"datatypes",
|
||||||
"determinator",
|
"determinator",
|
||||||
"determinators",
|
"determinators",
|
||||||
"distrib",
|
|
||||||
"eithers",
|
"eithers",
|
||||||
"elems",
|
|
||||||
"ents",
|
"ents",
|
||||||
"floorplan",
|
"floorplan",
|
||||||
"Focusable",
|
"Focusable",
|
||||||
"foldl",
|
|
||||||
"foldr",
|
|
||||||
"Gameplay",
|
"Gameplay",
|
||||||
"Hashable",
|
|
||||||
"hifi",
|
"hifi",
|
||||||
"HLINT",
|
"HLINT",
|
||||||
"homomorphic",
|
"homomorphic",
|
||||||
"hsep",
|
|
||||||
"Ixed",
|
|
||||||
"JSONE",
|
"JSONE",
|
||||||
"Keymap",
|
"Keymap",
|
||||||
"kolor",
|
"kolor",
|
||||||
"leaderboard",
|
"leaderboard",
|
||||||
"mappend",
|
|
||||||
"mconcat",
|
|
||||||
"mempty",
|
|
||||||
"Monoid",
|
|
||||||
"multiset",
|
"multiset",
|
||||||
"multiworld",
|
"multiworld",
|
||||||
|
"notif",
|
||||||
"objs",
|
"objs",
|
||||||
"omni",
|
"omni",
|
||||||
"Parameterizable",
|
"Parameterizable",
|
||||||
"parens",
|
"parens",
|
||||||
"pathfinding",
|
"pathfinding",
|
||||||
"Perlin",
|
|
||||||
"perp",
|
|
||||||
"playfield",
|
"playfield",
|
||||||
"Polytype",
|
"Polytype",
|
||||||
"polytypes",
|
"polytypes",
|
||||||
"pparens",
|
"pparens",
|
||||||
"prec",
|
"prec",
|
||||||
"precomputation",
|
"precomputation",
|
||||||
"Precompute",
|
|
||||||
"preprocess",
|
"preprocess",
|
||||||
"prereq",
|
"prereq",
|
||||||
"prereqs",
|
"prereqs",
|
||||||
"Prettyprinter",
|
|
||||||
"preuse",
|
|
||||||
"previewable",
|
"previewable",
|
||||||
"pushable",
|
"pushable",
|
||||||
"quasiquoter",
|
"quasiquoter",
|
||||||
"quasiquoters",
|
"quasiquoters",
|
||||||
"sconcat",
|
"reqs",
|
||||||
"scrollability",
|
"scrollability",
|
||||||
"selfdestruct",
|
"selfdestruct",
|
||||||
"Semigroup",
|
|
||||||
"snoc",
|
|
||||||
"Splittable",
|
|
||||||
"squote",
|
"squote",
|
||||||
"SRGB",
|
|
||||||
"struct",
|
"struct",
|
||||||
"Structs",
|
"Structs",
|
||||||
"Subdir",
|
"Subdir",
|
||||||
"Substate",
|
|
||||||
"subrecord",
|
"subrecord",
|
||||||
"subterms",
|
"subterms",
|
||||||
"subtyping",
|
"subtyping",
|
||||||
"Subworld",
|
"Subworld",
|
||||||
"subworlds",
|
"subworlds",
|
||||||
"succ",
|
|
||||||
"reqs",
|
|
||||||
"teleporting",
|
"teleporting",
|
||||||
"Tiebreaking",
|
"Tiebreaking",
|
||||||
"toplevel",
|
"toplevel",
|
||||||
@ -112,13 +83,9 @@
|
|||||||
"typeclass",
|
"typeclass",
|
||||||
"ucata",
|
"ucata",
|
||||||
"Unchainable",
|
"Unchainable",
|
||||||
"uncurry",
|
|
||||||
"unequip",
|
"unequip",
|
||||||
"unfoldr",
|
|
||||||
"uniplate",
|
|
||||||
"unranked",
|
"unranked",
|
||||||
"Unwalkable",
|
"Unwalkable",
|
||||||
"unwords",
|
|
||||||
"upperleft",
|
"upperleft",
|
||||||
"vals",
|
"vals",
|
||||||
"verbed",
|
"verbed",
|
||||||
|
1455
cspell.json
Normal file
1455
cspell.json
Normal file
File diff suppressed because it is too large
Load Diff
@ -3,4 +3,4 @@
|
|||||||
SCRIPT_DIR=$( cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd )
|
SCRIPT_DIR=$( cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd )
|
||||||
cd $SCRIPT_DIR/..
|
cd $SCRIPT_DIR/..
|
||||||
|
|
||||||
fourmolu --mode=inplace src app test
|
fourmolu --mode=inplace src app test scripts
|
45
scripts/spellcheck/autopopulate-spellchecker.sh
Executable file
45
scripts/spellcheck/autopopulate-spellchecker.sh
Executable file
@ -0,0 +1,45 @@
|
|||||||
|
#!/bin/bash -e
|
||||||
|
|
||||||
|
# This script lives 2 levels deep in the directory structure.
|
||||||
|
# Ensure its commands get run at the toplevel.
|
||||||
|
SCRIPT_DIR=$( cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd )
|
||||||
|
cd $SCRIPT_DIR/../..
|
||||||
|
|
||||||
|
|
||||||
|
# First, install hiedb:
|
||||||
|
#
|
||||||
|
# cabal install hiedb
|
||||||
|
#
|
||||||
|
# Then, generate *.hie files:
|
||||||
|
#
|
||||||
|
# cp hie.yaml.stack hie.yaml
|
||||||
|
# stack build --fast
|
||||||
|
|
||||||
|
DBNAME=hie.sqlite
|
||||||
|
hiedb --database $DBNAME index .hie
|
||||||
|
|
||||||
|
WORDS_TMPFILE_UNSORTED=$(mktemp --suffix .words)
|
||||||
|
|
||||||
|
# First, get all variable names that originate from external packages.
|
||||||
|
# Exclude names that contain symbols other than underscore or apostrophe or do not contain any letters.
|
||||||
|
sqlite3 $DBNAME "SELECT substr(sym, 3) FROM (SELECT DISTINCT occ AS sym FROM refs WHERE unit NOT IN (SELECT DISTINCT unit FROM mods)) ORDER BY sym" | grep -v "[^[:alnum:]_']" | grep "[[:alpha:]]" > $WORDS_TMPFILE_UNSORTED
|
||||||
|
|
||||||
|
# Next, append the individual "conids" extracted from all "modids" that originate from external packages.
|
||||||
|
# See definition of "conid" and "monid" here:
|
||||||
|
# https://www.haskell.org/onlinereport/haskell2010/haskellch5.html
|
||||||
|
sqlite3 $DBNAME "SELECT DISTINCT mod FROM refs WHERE unit NOT IN (SELECT DISTINCT unit FROM mods)" | scripts/spellcheck/split-module-names.hs >> $WORDS_TMPFILE_UNSORTED
|
||||||
|
|
||||||
|
WORDS_TMPFILE=$(mktemp --suffix .words)
|
||||||
|
sort -u $WORDS_TMPFILE_UNSORTED > $WORDS_TMPFILE
|
||||||
|
rm $WORDS_TMPFILE_UNSORTED
|
||||||
|
|
||||||
|
CSPELL_TMPFILE=$(mktemp --suffix .cspell)
|
||||||
|
CSPELL_FILEPATH=cspell.json
|
||||||
|
|
||||||
|
# Now, stuff the sorted list of names into the cspell JSON file word list.
|
||||||
|
jq '.words = $newWords' --slurpfile newWords <(jq --raw-input --null-input 'inputs' $WORDS_TMPFILE) $CSPELL_FILEPATH > $CSPELL_TMPFILE
|
||||||
|
|
||||||
|
# Overwrite the original with the modified version.
|
||||||
|
mv $CSPELL_TMPFILE $CSPELL_FILEPATH
|
||||||
|
|
||||||
|
rm $WORDS_TMPFILE
|
28
scripts/spellcheck/split-module-names.hs
Executable file
28
scripts/spellcheck/split-module-names.hs
Executable file
@ -0,0 +1,28 @@
|
|||||||
|
#!/usr/bin/env stack
|
||||||
|
{- stack script --resolver lts-21.25
|
||||||
|
--package data-ordlist
|
||||||
|
--package split
|
||||||
|
-}
|
||||||
|
|
||||||
|
import Data.List.Ordered (nubSort)
|
||||||
|
import Data.List.Split (splitOn)
|
||||||
|
|
||||||
|
-- |
|
||||||
|
-- Extracts all "conids" from a list of "modids".
|
||||||
|
-- (see definitions here: https://www.haskell.org/onlinereport/haskell2010/haskellch5.html )
|
||||||
|
--
|
||||||
|
-- E.g., takes lines of the following form:
|
||||||
|
--
|
||||||
|
-- Data.Text
|
||||||
|
-- Control.Arrow
|
||||||
|
--
|
||||||
|
-- and produces a flattened list of words:
|
||||||
|
--
|
||||||
|
-- Arrow
|
||||||
|
-- Control
|
||||||
|
-- Data
|
||||||
|
-- Text
|
||||||
|
splitParts = unlines . nubSort . concatMap (splitOn ".") . lines
|
||||||
|
|
||||||
|
main :: IO ()
|
||||||
|
main = interact splitParts
|
Loading…
Reference in New Issue
Block a user