Changes In Branch multid Through [62304c0cd5] Excluding Merge-Ins
This is equivalent to a diff from 62c389aedf to 62304c0cd5
|
2018-02-16
| ||
| 15:46 | [fx][graphspell] merge multid: multi-dictionaries > editable personal dictionary check-in: 607d532bca user: olr tags: trunk, new_feature, fx, graphspell | |
|
2018-02-13
| ||
| 15:44 | [core][cli][server][graphspell][fx] use spellchecker instead of ibdawg check-in: 18db5d65f0 user: olr tags: cli, core, server, fx, graphspell, multid | |
| 14:26 | [core] use spellchecker instead of ibdawg directly check-in: 62304c0cd5 user: olr tags: core, multid | |
| 14:25 | [graphspell][js] ibdawg: remove useless var in constructor check-in: 1b2e823757 user: olr tags: graphspell, multid | |
| 13:39 | [core][js] multi-dictionaries check-in: d8959f76a4 user: olr tags: core, multid | |
| 13:38 | [graphspell][js] rename vars check-in: 62c389aedf user: olr tags: trunk, graphspell | |
| 10:47 | [graphspell][js] spellchecker wrapper for ibdawg check-in: c989c20101 user: olr tags: trunk, graphspell | |
Modified compile_rules.py from [7fa2e820bf] to [9bd1433006].
| ︙ | ︙ | |||
52 53 54 55 56 57 58 |
s = re.sub(r"textarea0\(\s*", 'look(sx, ', s) # textarea0(s)
s = re.sub(r"before0_chk1\(\s*", 'look_chk1(dDA, sx[:m.start()], 0, ', s) # before0_chk1(s)
s = re.sub(r"after0_chk1\(\s*", 'look_chk1(dDA, sx[m.end():], m.end(), ', s) # after0_chk1(s)
s = re.sub(r"textarea0_chk1\(\s*", 'look_chk1(dDA, sx, 0, ', s) # textarea0_chk1(s)
s = re.sub(r"isEndOfNG\(\s*\)", 'isEndOfNG(dDA, s[m.end():], m.end())', s) # isEndOfNG(s)
s = re.sub(r"isNextNotCOD\(\s*\)", 'isNextNotCOD(dDA, s[m.end():], m.end())', s) # isNextNotCOD(s)
s = re.sub(r"isNextVerb\(\s*\)", 'isNextVerb(dDA, s[m.end():], m.end())', s) # isNextVerb(s)
| | | 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 |
s = re.sub(r"textarea0\(\s*", 'look(sx, ', s) # textarea0(s)
s = re.sub(r"before0_chk1\(\s*", 'look_chk1(dDA, sx[:m.start()], 0, ', s) # before0_chk1(s)
s = re.sub(r"after0_chk1\(\s*", 'look_chk1(dDA, sx[m.end():], m.end(), ', s) # after0_chk1(s)
s = re.sub(r"textarea0_chk1\(\s*", 'look_chk1(dDA, sx, 0, ', s) # textarea0_chk1(s)
s = re.sub(r"isEndOfNG\(\s*\)", 'isEndOfNG(dDA, s[m.end():], m.end())', s) # isEndOfNG(s)
s = re.sub(r"isNextNotCOD\(\s*\)", 'isNextNotCOD(dDA, s[m.end():], m.end())', s) # isNextNotCOD(s)
s = re.sub(r"isNextVerb\(\s*\)", 'isNextVerb(dDA, s[m.end():], m.end())', s) # isNextVerb(s)
s = re.sub(r"\bspell *[(]", '_oSpellChecker.isValid(', s)
s = re.sub(r"[\\](\d+)", 'm.group(\\1)', s)
return s
def uppercase (s, sLang):
"(flag i is not enough): converts regex to uppercase regex: 'foo' becomes '[Ff][Oo][Oo]', but 'Bar' becomes 'B[Aa][Rr]'."
sUp = ""
|
| ︙ | ︙ |
Modified gc_core/js/lang_core/gc_engine.js from [2f5e964b5d] to [dcb651b444].
| ︙ | ︙ | |||
34 35 36 37 38 39 40 | } // data let _sAppContext = ""; // what software is running let _dOptions = null; let _aIgnoredRules = new Set(); | | | 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 |
}
// data
let _sAppContext = ""; // what software is running
let _dOptions = null;
let _aIgnoredRules = new Set();
let _oSpellChecker = null;
let _dAnalyses = new Map(); // cache for data from dictionary
var gc_engine = {
//// Informations
|
| ︙ | ︙ | |||
318 319 320 321 322 323 324 |
},
//// Initialization
load: function (sContext="JavaScript", sPath="") {
try {
if (typeof(require) !== 'undefined') {
| | | | | | 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 |
},
//// Initialization
load: function (sContext="JavaScript", sPath="") {
try {
if (typeof(require) !== 'undefined') {
var spellchecker = require("resource://grammalecte/graphspell/spellchecker.js");
_oSpellChecker = new spellchecker.SpellChecker("${lang}", "", "${dic_filename}.json");
} else {
_oSpellChecker = new SpellChecker("${lang}", sPath, "${dic_filename}.json");
}
_sAppContext = sContext;
_dOptions = gc_options.getOptions(sContext).gl_shallowCopy(); // duplication necessary, to be able to reset to default
}
catch (e) {
helpers.logerror(e);
}
},
getDictionary: function () {
return _oSpellChecker;
},
//// Options
setOption: function (sOpt, bVal) {
if (_dOptions.has(sOpt)) {
_dOptions.set(sOpt, bVal);
|
| ︙ | ︙ | |||
386 387 388 389 390 391 392 |
helpers.echo("DA: " + dDA.get(aWord[0]));
}
helpers.echo("FSA: " + _dAnalyses.get(aWord[1]));
return true;
}
function _storeMorphFromFSA (sWord) {
| | | | | 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 |
helpers.echo("DA: " + dDA.get(aWord[0]));
}
helpers.echo("FSA: " + _dAnalyses.get(aWord[1]));
return true;
}
function _storeMorphFromFSA (sWord) {
// retrieves morphologies list from _oSpellChecker -> _dAnalyses
//helpers.echo("register: "+sWord + " " + _oSpellChecker.getMorph(sWord).toString())
_dAnalyses.set(sWord, _oSpellChecker.getMorph(sWord));
return !!_dAnalyses.get(sWord);
}
function morph (dDA, aWord, sPattern, bStrict=true, bNoWord=false) {
// analyse a tuple (position, word), return true if sPattern in morphologies (disambiguation on)
if (!aWord) {
//helpers.echo("morph: noword, returns " + bNoWord);
|
| ︙ | ︙ |
Modified gc_core/py/lang_core/gc_engine.py from [9fc11201d4] to [e36972dc16].
1 2 3 4 5 6 7 8 9 10 | # Grammalecte # Grammar checker engine import re import sys import os import traceback #import unicodedata from itertools import chain | | | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 |
# Grammalecte
# Grammar checker engine
import re
import sys
import os
import traceback
#import unicodedata
from itertools import chain
from ..graphspell.spellchecker import SpellChecker
from ..graphspell.echo import echo
from . import gc_options
__all__ = [ "lang", "locales", "pkg", "name", "version", "author", \
"load", "parse", "getDictionary", \
"setOption", "setOptions", "getOptions", "getDefaultOptions", "getOptionsLabels", "resetOptions", "displayOptions", \
|
| ︙ | ︙ | |||
30 31 32 33 34 35 36 | _rules = None # module gc_rules # data _sAppContext = "" # what software is running _dOptions = None _aIgnoredRules = set() | | | 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 |
_rules = None # module gc_rules
# data
_sAppContext = "" # what software is running
_dOptions = None
_aIgnoredRules = set()
_oSpellChecker = None
_dAnalyses = {} # cache for data from dictionary
#### Parsing
def parse (sText, sCountry="${country_default}", bDebug=False, dOptions=None, bContext=False):
|
| ︙ | ︙ | |||
284 285 286 287 288 289 290 |
#import lightproof_handler_${implname} as opt
_createError = _createWriterError
except ImportError:
_createError = _createDictError
def load (sContext="Python"):
| | | | 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 |
#import lightproof_handler_${implname} as opt
_createError = _createWriterError
except ImportError:
_createError = _createDictError
def load (sContext="Python"):
global _oSpellChecker
global _sAppContext
global _dOptions
try:
_oSpellChecker = SpellChecker("${lang}", "${dic_filename}.bdic")
_sAppContext = sContext
_dOptions = dict(gc_options.getOptions(sContext)) # duplication necessary, to be able to reset to default
except:
traceback.print_exc()
def setOption (sOpt, bVal):
|
| ︙ | ︙ | |||
330 331 332 333 334 335 336 |
def resetOptions ():
global _dOptions
_dOptions = dict(gc_options.getOptions(_sAppContext))
def getDictionary ():
| | | 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 |
def resetOptions ():
global _dOptions
_dOptions = dict(gc_options.getOptions(_sAppContext))
def getDictionary ():
return _oSpellChecker
def _getRules (bParagraph):
try:
if not bParagraph:
return _rules.lSentenceRules
return _rules.lParagraphRules
|
| ︙ | ︙ | |||
394 395 396 397 398 399 400 |
if tWord[0] in dDA:
echo("DA: " + str(dDA[tWord[0]]))
echo("FSA: " + str(_dAnalyses[tWord[1]]))
return True
def _storeMorphFromFSA (sWord):
| | | | 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 |
if tWord[0] in dDA:
echo("DA: " + str(dDA[tWord[0]]))
echo("FSA: " + str(_dAnalyses[tWord[1]]))
return True
def _storeMorphFromFSA (sWord):
"retrieves morphologies list from _oSpellChecker -> _dAnalyses"
global _dAnalyses
_dAnalyses[sWord] = _oSpellChecker.getMorph(sWord)
return True if _dAnalyses[sWord] else False
def morph (dDA, tWord, sPattern, bStrict=True, bNoWord=False):
"analyse a tuple (position, word), return True if sPattern in morphologies (disambiguation on)"
if not tWord:
return bNoWord
|
| ︙ | ︙ |
Modified gc_lang/fr/modules-js/gce_suggestions.js from [d955978cbc] to [0c31bc1a27].
| ︙ | ︙ | |||
206 207 208 209 210 211 212 |
} else if (sGender == ":f") {
return suggFemPlur(sFlex);
}
}
let aSugg = new Set();
if (!sFlex.includes("-")) {
if (sFlex.endsWith("l")) {
| | | | | | | | | 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 |
} else if (sGender == ":f") {
return suggFemPlur(sFlex);
}
}
let aSugg = new Set();
if (!sFlex.includes("-")) {
if (sFlex.endsWith("l")) {
if (sFlex.endsWith("al") && sFlex.length > 2 && _oSpellChecker.isValid(sFlex.slice(0,-1)+"ux")) {
aSugg.add(sFlex.slice(0,-1)+"ux");
}
if (sFlex.endsWith("ail") && sFlex.length > 3 && _oSpellChecker.isValid(sFlex.slice(0,-2)+"ux")) {
aSugg.add(sFlex.slice(0,-2)+"ux");
}
}
if (_oSpellChecker.isValid(sFlex+"s")) {
aSugg.add(sFlex+"s");
}
if (_oSpellChecker.isValid(sFlex+"x")) {
aSugg.add(sFlex+"x");
}
}
if (mfsp.hasMiscPlural(sFlex)) {
mfsp.getMiscPlural(sFlex).forEach(function(x) { aSugg.add(x); });
}
if (aSugg.size > 0) {
return Array.from(aSugg).join("|");
}
return "";
}
function suggSing (sFlex) {
// returns singular forms assuming sFlex is plural
if (sFlex.includes("-")) {
return "";
}
let aSugg = new Set();
if (sFlex.endsWith("ux")) {
if (_oSpellChecker.isValid(sFlex.slice(0,-2)+"l")) {
aSugg.add(sFlex.slice(0,-2)+"l");
}
if (_oSpellChecker.isValid(sFlex.slice(0,-2)+"il")) {
aSugg.add(sFlex.slice(0,-2)+"il");
}
}
if (_oSpellChecker.isValid(sFlex.slice(0,-1))) {
aSugg.add(sFlex.slice(0,-1));
}
if (aSugg.size > 0) {
return Array.from(aSugg).join("|");
}
return "";
}
|
| ︙ | ︙ |
Modified gc_lang/fr/modules/gce_suggestions.py from [50fbeb414d] to [79835965e4].
| ︙ | ︙ | |||
155 156 157 158 159 160 161 |
if sGender == ":m":
return suggMasPlur(sFlex)
elif sGender == ":f":
return suggFemPlur(sFlex)
aSugg = set()
if "-" not in sFlex:
if sFlex.endswith("l"):
| | | | | | | | | 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 |
if sGender == ":m":
return suggMasPlur(sFlex)
elif sGender == ":f":
return suggFemPlur(sFlex)
aSugg = set()
if "-" not in sFlex:
if sFlex.endswith("l"):
if sFlex.endswith("al") and len(sFlex) > 2 and _oSpellChecker.isValid(sFlex[:-1]+"ux"):
aSugg.add(sFlex[:-1]+"ux")
if sFlex.endswith("ail") and len(sFlex) > 3 and _oSpellChecker.isValid(sFlex[:-2]+"ux"):
aSugg.add(sFlex[:-2]+"ux")
if _oSpellChecker.isValid(sFlex+"s"):
aSugg.add(sFlex+"s")
if _oSpellChecker.isValid(sFlex+"x"):
aSugg.add(sFlex+"x")
if mfsp.hasMiscPlural(sFlex):
aSugg.update(mfsp.getMiscPlural(sFlex))
if aSugg:
return "|".join(aSugg)
return ""
def suggSing (sFlex):
"returns singular forms assuming sFlex is plural"
if "-" in sFlex:
return ""
aSugg = set()
if sFlex.endswith("ux"):
if _oSpellChecker.isValid(sFlex[:-2]+"l"):
aSugg.add(sFlex[:-2]+"l")
if _oSpellChecker.isValid(sFlex[:-2]+"il"):
aSugg.add(sFlex[:-2]+"il")
if _oSpellChecker.isValid(sFlex[:-1]):
aSugg.add(sFlex[:-1])
if aSugg:
return "|".join(aSugg)
return ""
def suggMasSing (sFlex, bSuggSimil=False):
|
| ︙ | ︙ |
Modified gc_lang/fr/webext/gce_worker.js from [2a64cce6de] to [30916bedcd].
| ︙ | ︙ | |||
32 33 34 35 36 37 38 39 40 41 42 43 44 45 |
//console.log("[Worker] GC Engine Worker [start]");
//console.log(self);
importScripts("grammalecte/graphspell/helpers.js");
importScripts("grammalecte/graphspell/str_transform.js");
importScripts("grammalecte/graphspell/char_player.js");
importScripts("grammalecte/graphspell/ibdawg.js");
importScripts("grammalecte/text.js");
importScripts("grammalecte/graphspell/tokenizer.js");
importScripts("grammalecte/fr/conj.js");
importScripts("grammalecte/fr/mfsp.js");
importScripts("grammalecte/fr/phonet.js");
importScripts("grammalecte/fr/cregex.js");
importScripts("grammalecte/fr/gc_options.js");
| > | 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 |
//console.log("[Worker] GC Engine Worker [start]");
//console.log(self);
importScripts("grammalecte/graphspell/helpers.js");
importScripts("grammalecte/graphspell/str_transform.js");
importScripts("grammalecte/graphspell/char_player.js");
importScripts("grammalecte/graphspell/ibdawg.js");
importScripts("grammalecte/graphspell/spellchecker.js");
importScripts("grammalecte/text.js");
importScripts("grammalecte/graphspell/tokenizer.js");
importScripts("grammalecte/fr/conj.js");
importScripts("grammalecte/fr/mfsp.js");
importScripts("grammalecte/fr/phonet.js");
importScripts("grammalecte/fr/cregex.js");
importScripts("grammalecte/fr/gc_options.js");
|
| ︙ | ︙ |
Modified graphspell-js/ibdawg.js from [cea88b04de] to [508f46740c].
| ︙ | ︙ | |||
85 86 87 88 89 90 91 |
// INDEXABLE BINARY DIRECT ACYCLIC WORD GRAPH
constructor (param1, sPath="") {
// param1 can be a filename or a object with all the necessary data.
try {
let oData = null;
if (typeof(param1) == "string") {
| < | | 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 |
// INDEXABLE BINARY DIRECT ACYCLIC WORD GRAPH
constructor (param1, sPath="") {
// param1 can be a filename or a object with all the necessary data.
try {
let oData = null;
if (typeof(param1) == "string") {
let sURL = (sPath !== "") ? sPath + "/" + param1 : "resource://grammalecte/graphspell/_dictionaries/"+param1;
oData = JSON.parse(helpers.loadFile(sURL));
} else {
oData = param1;
}
Object.assign(this, oData);
}
catch (e) {
|
| ︙ | ︙ |
Modified graphspell-js/spellchecker.js from [ee0b03faf8] to [cfdad9918e].
| ︙ | ︙ | |||
21 22 23 24 25 26 27 |
const dDefaultDictionaries = new Map([
["fr", "fr.json"],
["en", "en.json"]
]);
| | | < < | < < > | | | < | 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 |
const dDefaultDictionaries = new Map([
["fr", "fr.json"],
["en", "en.json"]
]);
class SpellChecker {
constructor (sLangCode, sPath="", mainDic=null, extentedDic=null, personalDic=null) {
// returns true if the main dictionary is loaded
this.sLangCode = sLangCode;
if (mainDic === null) {
mainDic = dDefaultDictionaries.gl_get(sLangCode, "");
}
this.oMainDic = this._loadDictionary(mainDic, sPath, true);
this.oExtendedDic = this._loadDictionary(extentedDic, sPath);
this.oPersonalDic = this._loadDictionary(personalDic, sPath);
}
_loadDictionary (dictionary, sPath, bNecessary=false) {
// returns an IBDAWG object
if (dictionary === null) {
return null;
}
try {
if (typeof(require) !== 'undefined') {
return new ibdawg.IBDAWG(dictionary); // dictionary can be a filename or a JSON object
} else {
return new IBDAWG(dictionary, sPath); // dictionary can be a filename or a JSON object
}
}
catch (e) {
console.log(e.message);
if (bNecessary) {
throw e.message;
}
return null;
}
}
setMainDictionary (dictionary) {
// returns true if the dictionary is loaded
this.oMainDic = this._loadDictionary(dictionary);
|
| ︙ | ︙ | |||
95 96 97 98 99 100 101 |
return true;
}
return false;
}
isValid (sWord) {
// checks if sWord is valid (different casing tested if the first letter is a capital)
| | | | | | | | | | | 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 |
return true;
}
return false;
}
isValid (sWord) {
// checks if sWord is valid (different casing tested if the first letter is a capital)
if (this.oMainDic.isValid(sWord)) {
return true;
}
if (this.oExtendedDic && this.oExtendedDic.isValid(sWord)) {
return true;
}
if (this.oPersonalDic && this.oPersonalDic.isValid(sWord)) {
return true;
}
return false;
}
lookup (sWord) {
// checks if sWord is in dictionary as is (strict verification)
if (this.oMainDic.lookup(sWord)) {
return true;
}
if (this.oExtendedDic && this.oExtendedDic.lookup(sWord)) {
return true;
}
if (this.oPersonalDic && this.oPersonalDic.lookup(sWord)) {
return true;
}
return false;
}
getMorph (sWord) {
// retrieves morphologies list, different casing allowed
let lResult = this.oMainDic.getMorph(sWord);
if (this.oExtendedDic) {
lResult.extends(this.oExtendedDic.getMorph(sWord));
}
if (this.oPersonalDic) {
lResult.extends(this.oPersonalDic.getMorph(sWord));
}
return lResult;
}
* suggest (sWord, nSuggLimit=10) {
// generator: returns 1,2 or 3 lists of suggestions
yield this.oMainDic.suggest(sWord, nSuggLimit);
|
| ︙ | ︙ |
Modified graphspell/spellchecker.py from [19c7dd4df2] to [781d3c301e].
| ︙ | ︙ | |||
15 16 17 18 19 20 21 |
dDefaultDictionaries = {
"fr": "fr.bdic",
"en": "en.bdic"
}
| | < | 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 |
dDefaultDictionaries = {
"fr": "fr.bdic",
"en": "en.bdic"
}
class SpellChecker ():
def __init__ (self, sLangCode, sfMainDic="", sfExtendedDic="", sfPersonalDic=""):
"returns True if the main dictionary is loaded"
self.sLangCode = sLangCode
if not sfMainDic:
sfMainDic = dDefaultDictionaries.get(sLangCode, "")
self.oMainDic = self._loadDictionary(sfMainDic)
self.oExtendedDic = self._loadDictionary(sfExtendedDic)
self.oPersonalDic = self._loadDictionary(sfPersonalDic)
def _loadDictionary (self, sfDictionary):
"returns an IBDAWG object"
if not sfDictionary:
return None
try:
return ibdawg.IBDAWG(sfDictionary)
|
| ︙ | ︙ | |||
68 69 70 71 72 73 74 |
return True
if self.oPersonalDic and self.oPersonalDic.isValidToken(sToken):
return True
return False
def isValid (self, sWord):
"checks if sWord is valid (different casing tested if the first letter is a capital)"
| | | | | | | | | | | 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 |
return True
if self.oPersonalDic and self.oPersonalDic.isValidToken(sToken):
return True
return False
def isValid (self, sWord):
"checks if sWord is valid (different casing tested if the first letter is a capital)"
if self.oMainDic.isValid(sWord):
return True
if self.oExtendedDic and self.oExtendedDic.isValid(sWord):
return True
if self.oPersonalDic and self.oPersonalDic.isValid(sWord):
return True
return False
def lookup (self, sWord):
"checks if sWord is in dictionary as is (strict verification)"
if self.oMainDic.lookup(sWord):
return True
if self.oExtendedDic and self.oExtendedDic.lookup(sWord):
return True
if self.oPersonalDic and self.oPersonalDic.lookup(sWord):
return True
return False
def getMorph (self, sWord):
"retrieves morphologies list, different casing allowed"
lResult = self.oMainDic.getMorph(sWord)
if self.oExtendedDic:
lResult.extends(self.oExtendedDic.getMorph(sWord))
if self.oPersonalDic:
lResult.extends(self.oPersonalDic.getMorph(sWord))
return lResult
def suggest (self, sWord, nSuggLimit=10):
"generator: returns 1,2 or 3 lists of suggestions"
yield self.oMainDic.suggest(sWord, nSuggLimit)
if self.oExtendedDic:
yield self.oExtendedDic.suggest(sWord, nSuggLimit)
|
| ︙ | ︙ |