Index: gc_lang/fr/config.ini
==================================================================
--- gc_lang/fr/config.ini
+++ gc_lang/fr/config.ini
@@ -14,12 +14,15 @@
extras = README_fr.txt
logo = logo.png
# main dictionary
lexicon_src = lexicons/French.lex
-dic_filename = fr
-dic_name = French
+dic_filenames = fr-allvars,fr-classic,fr-reform
+dic_name = Français,Français (Classique/Moderne),Français (Réforme 1990)
+dic_filter = ,[*CMPX]$,[*RPX]$
+dic_default_filename_py = fr-allvars
+dic_default_filename_js = fr-allvars
# extended dictionary
lexicon_extended_src = lexicons/French.extended.lex
dic_extended_filename = fr.extended
dic_extended_name = Français - dictionnaire étendu
# community dictionary
Index: gc_lang/fr/dictionnaire/genfrdic.py
==================================================================
--- gc_lang/fr/dictionnaire/genfrdic.py
+++ gc_lang/fr/dictionnaire/genfrdic.py
@@ -61,18 +61,10 @@
'mozAsciiName': 'fr-FR-classic',
'subDicts': '*MCX',
'mozId': 'fr-dicollecte-classique',
'description': "Dictionnaire français “Classique”" }
-dCLASSIQUEX = { 'name': 'DICTIONNAIRE ORTHOGRAPHIQUE FRANÇAIS “CLASSIQUE ÉTENDU”',
- 'shortname': '“Classique étendu”',
- 'asciiName': 'fr-classique-ext',
- 'mozAsciiName': 'fr-FR-classic-ext',
- 'subDicts': '*MCX',
- 'mozId': 'fr-dicollecte-classique-ext',
- 'description': "Dictionnaire français “Classique étendu”" }
-
dREFORME1990 = { 'name': 'DICTIONNAIRE ORTHOGRAPHIQUE FRANÇAIS “RÉFORME 1990”',
'shortname': '“Réforme 1990”',
'asciiName': 'fr-reforme1990',
'mozAsciiName': 'fr-FR-reform',
'subDicts': '*RX',
Index: gc_lang/fr/modules/tests.py
==================================================================
--- gc_lang/fr/modules/tests.py
+++ gc_lang/fr/modules/tests.py
@@ -22,11 +22,11 @@
class TestDictionary (unittest.TestCase):
@classmethod
def setUpClass (cls):
- cls.oDic = IBDAWG("${dic_filename}.bdic")
+ cls.oDic = IBDAWG("${dic_main_filename_py}")
def test_lookup (self):
for sWord in ["branche", "Émilie"]:
self.assertTrue(self.oDic.lookup(sWord), sWord)
Index: gc_lang/fr/oxt/ContextMenu/ContextMenu.py
==================================================================
--- gc_lang/fr/oxt/ContextMenu/ContextMenu.py
+++ gc_lang/fr/oxt/ContextMenu/ContextMenu.py
@@ -129,11 +129,11 @@
oGC = self.ctx.ServiceManager.createInstanceWithContext("org.openoffice.comp.pyuno.Lightproof.grammalecte", self.ctx)
if hasattr(oGC, "getSpellChecker"):
# https://bugs.documentfoundation.org/show_bug.cgi?id=97790
oSpellChecker = oGC.getSpellChecker()
else:
- oSpellChecker = SpellChecker("${lang}", "${dic_filename}.bdic")
+ oSpellChecker = SpellChecker("${lang}", "fr-allvars.bdic")
if not oLexicographe:
oLexicographe = lxg.Lexicographe(oSpellChecker)
except:
traceback.print_exc()
Index: gc_lang/fr/oxt/Graphspell.py
==================================================================
--- gc_lang/fr/oxt/Graphspell.py
+++ gc_lang/fr/oxt/Graphspell.py
@@ -63,11 +63,11 @@
try:
personal_dic = json.loads(sPersonalDicJSON)
except:
print("Graphspell: wrong personal_dic")
traceback.print_exc()
- self.oGraphspell = SpellChecker("fr", "fr.bdic", "", "", personal_dic)
+ self.oGraphspell = SpellChecker("fr", "fr-allvars.bdic", "", "", personal_dic)
self.loadHunspell()
# print("Graphspell: init done")
except:
print("Graphspell: init failed")
traceback.print_exc()
Index: gc_lang/fr/rules.grx
==================================================================
--- gc_lang/fr/rules.grx
+++ gc_lang/fr/rules.grx
@@ -11496,11 +11496,11 @@
TEST: Tu ne {{ment}} jamais.
TEST: Tu {{a}} mal ?
TEST: Tu ne le lui {{prend}} pas.
TEST: Tu ne m’{{attendra}} pas.
-TEST: toi qui n’y {{connait}} rien, ne nous ennuie pas avec tes théories.
+TEST: toi qui n’y {{connaît}} rien, ne nous ennuie pas avec tes théories.
## 3sg
__[i]/conj(conj_il)__
(?<!t’)(il) +({w_1}) @@0,$
Index: graphspell/dawg.py
==================================================================
--- graphspell/dawg.py
+++ graphspell/dawg.py
@@ -12,10 +12,12 @@
import sys
import os
import collections
import json
import time
+import re
+import traceback
from . import str_transform as st
from .progressbar import ProgressBar
@@ -61,10 +63,11 @@
try:
zFilter = re.compile(sSelectFilterRegex) if sSelectFilterRegex else None
except:
print(" # Error. Wrong filter regex. Filter ignored.")
+ traceback.print_exc()
zFilter = None
# read lexicon
if type(src) is str:
iterable = readFile(src)
@@ -97,10 +100,11 @@
if not aEntry:
raise ValueError("# Error. Empty lexicon")
# Preparing DAWG
print(" > Preparing list of words")
+ print(" Filter: " + (sSelectFilterRegex or "[None]"))
lVal = lChar + lAff + lTag
lWord = [ [dChar[c] for c in sFlex] + [iAff+nChar] + [iTag+nChar+nAff] for sFlex, iAff, iTag in aEntry ]
aEntry = None
# Dictionary of arc values occurrency, to sort arcs of each node
Index: lex_build.py
==================================================================
--- lex_build.py
+++ lex_build.py
@@ -7,13 +7,13 @@
import graphspell.dawg as fsa
from graphspell.ibdawg import IBDAWG
-def build (spfSrc, sLangCode, sLangName, sfDict, bJSON=False, sDicName="", cStemmingMethod="S", nCompressMethod=1):
+def build (spfSrc, sLangCode, sLangName, sfDict, bJSON=False, sDicName="", sFilter="", cStemmingMethod="S", nCompressMethod=1):
"transform a text lexicon as a binary indexable dictionary"
- oDAWG = fsa.DAWG(spfSrc, cStemmingMethod, sLangCode, sLangName, sDicName)
+ oDAWG = fsa.DAWG(spfSrc, cStemmingMethod, sLangCode, sLangName, sDicName, sFilter)
dir_util.mkpath("graphspell/_dictionaries")
oDAWG.writeInfo("graphspell/_dictionaries/" + sfDict + ".info.txt")
oDAWG.writeBinary("graphspell/_dictionaries/" + sfDict + ".bdic", int(nCompressMethod))
if bJSON:
dir_util.mkpath("graphspell-js/_dictionaries")
Index: make.py
==================================================================
--- make.py
+++ make.py
@@ -314,11 +314,11 @@
dVars["dic_extended_filename_js"] = ""
dVars["dic_community_filename_py"] = ""
dVars["dic_community_filename_js"] = ""
dVars["dic_personal_filename_py"] = ""
dVars["dic_personal_filename_js"] = ""
- lDict = [ ("main", dVars['dic_filename']) ]
+ lDict = [ ("main", s) for s in dVars['dic_filenames'].split(",") ]
if bExtendedDict:
lDict.append(("extended", dVars['dic_extended_filename']))
if bCommunityDict:
lDict.append(("community", dVars['dic_community_filename']))
if bPersonalDict:
@@ -330,32 +330,39 @@
buildDictionary(dVars, sType, bJavaScript)
print(spfPyDic)
file_util.copy_file(spfPyDic, "grammalecte/graphspell/_dictionaries")
dVars['dic_'+sType+'_filename_py'] = sFileName + '.bdic'
if bJavaScript:
+ print(spfJSDic)
file_util.copy_file(spfJSDic, "grammalecte-js/graphspell/_dictionaries")
dVars['dic_'+sType+'_filename_js'] = sFileName + '.json'
+ dVars['dic_main_filename_py'] = dVars['dic_default_filename_py'] + ".bdic"
+ dVars['dic_main_filename_js'] = dVars['dic_default_filename_js'] + ".json"
def buildDictionary (dVars, sType, bJavaScript=False):
if sType == "main":
spfLexSrc = dVars['lexicon_src']
- sfDictDst = dVars['dic_filename']
- sDicName = dVars['dic_name']
- elif sType == "extended":
- spfLexSrc = dVars['lexicon_extended_src']
- sfDictDst = dVars['dic_extended_filename']
- sDicName = dVars['dic_extended_name']
- elif sType == "community":
- spfLexSrc = dVars['lexicon_community_src']
- sfDictDst = dVars['dic_community_filename']
- sDicName = dVars['dic_community_name']
- elif sType == "personal":
- spfLexSrc = dVars['lexicon_personal_src']
- sfDictDst = dVars['dic_personal_filename']
- sDicName = dVars['dic_personal_name']
- lex_build.build(spfLexSrc, dVars['lang'], dVars['lang_name'], sfDictDst, bJavaScript, sDicName, dVars['stemming_method'], int(dVars['fsa_method']))
+ l_sfDictDst = dVars['dic_filenames'].split(",")
+ l_sDicName = dVars['dic_name'].split(",")
+ l_sFilter = dVars['dic_filter'].split(",")
+ for sfDictDst, sDicName, sFilter in zip(l_sfDictDst, l_sDicName, l_sFilter):
+ lex_build.build(spfLexSrc, dVars['lang'], dVars['lang_name'], sfDictDst, bJavaScript, sDicName, sFilter, dVars['stemming_method'], int(dVars['fsa_method']))
+ else:
+ if sType == "extended":
+ spfLexSrc = dVars['lexicon_extended_src']
+ sfDictDst = dVars['dic_extended_filename']
+ sDicName = dVars['dic_extended_name']
+ elif sType == "community":
+ spfLexSrc = dVars['lexicon_community_src']
+ sfDictDst = dVars['dic_community_filename']
+ sDicName = dVars['dic_community_name']
+ elif sType == "personal":
+ spfLexSrc = dVars['lexicon_personal_src']
+ sfDictDst = dVars['dic_personal_filename']
+ sDicName = dVars['dic_personal_name']
+ lex_build.build(spfLexSrc, dVars['lang'], dVars['lang_name'], sfDictDst, bJavaScript, sDicName, "", dVars['stemming_method'], int(dVars['fsa_method']))
def main ():
print("Python: " + sys.version)