Overview
| Comment: | [build] separate dictionary builder from make.py |
|---|---|
| Downloads: | Tarball | ZIP archive | SQL archive |
| Timelines: | family | ancestors | descendants | both | trunk | build |
| Files: | files | file ages | folders |
| SHA3-256: |
03448dc173fd9dfae33d9b65b3c00036 |
| User & Date: | olr on 2017-06-23 12:19:55 |
| Other Links: | manifest | tags |
Context
|
2017-06-23
| ||
| 12:55 | [build] change arguments order for dictionary building check-in: 4bc364b3ac user: olr tags: trunk, build | |
| 12:19 | [build] separate dictionary builder from make.py check-in: 03448dc173 user: olr tags: trunk, build | |
| 08:04 | [fr] faux positif concernant les nombres suivant un déterminant pluriel check-in: 469f8c6d69 user: olr tags: trunk, fr | |
Changes
Modified gc_lang/fr/config.ini from [649530543c] to [5ccf0657e5].
| ︙ | ︙ | |||
12 13 14 15 16 17 18 19 20 21 22 23 24 25 | description = Correcteur grammatical pour le français. extras = README_fr.txt logo = logo.png # lexicon source lexicon_src = lexicons/French.lex # binary dictionary name py_binary_dic = French.bdic js_binary_dic = French.json # Finite state automaton compression: 1, 2 (experimental) or 3 (experimental) fsa_method = 1 # stemming method: S for suffixes only, A for prefixes and suffixes stemming_method = S | > | 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 | description = Correcteur grammatical pour le français. extras = README_fr.txt logo = logo.png # lexicon source lexicon_src = lexicons/French.lex # binary dictionary name dic_name = French py_binary_dic = French.bdic js_binary_dic = French.json # Finite state automaton compression: 1, 2 (experimental) or 3 (experimental) fsa_method = 1 # stemming method: S for suffixes only, A for prefixes and suffixes stemming_method = S |
| ︙ | ︙ |
Added lex_build.py version [e2774a881f].
> > > > > > > > > > > > > > > > > > > > > > > > > > > > > | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 |
#!python3
# Lexicon builder
from distutils import dir_util
import grammalecte.dawg as fsa
from grammalecte.ibdawg import IBDAWG
def build (spfSrc, sLangName, sDicName, cStemmingMethod, nCompressMethod, bJSON=False):
"transform a text lexicon as a binary indexable dictionary"
oDAWG = fsa.DAWG(spfSrc, sLangName, cStemmingMethod)
dir_util.mkpath("grammalecte/_dictionaries")
oDAWG.writeInfo("grammalecte/_dictionaries/" + sDicName + ".info.txt")
oDAWG.createBinary("grammalecte/_dictionaries/" + sDicName + ".bdic", int(nCompressMethod))
if bJSON:
dir_util.mkpath("grammalecte-js/_dictionaries")
oDic = IBDAWG(sDicName + ".bdic")
#oDic.writeAsJSObject("gc_lang/"+sLang+"/modules-js/dictionary.js")
oDic.writeAsJSObject("grammalecte-js/_dictionaries/" + sDicName + ".json")
def main ():
print("todo")
if __name__ == '__main__':
main()
|
Modified make.py from [418a36d3bb] to [993f7b57c8].
| ︙ | ︙ | |||
310 311 312 313 314 315 316 |
try:
build_data_module = importlib.import_module("gc_lang."+sLang+".build_data")
except ImportError:
print("# Error. Couldn’t import file build_data.py in folder gc_lang/"+sLang)
if build_data_module:
build_data_module.before('gc_lang/'+sLang, dVars, xArgs.javascript)
if xArgs.dict or not os.path.exists("grammalecte/_dictionaries"):
| < < | | < < < < < < < < | 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 |
try:
build_data_module = importlib.import_module("gc_lang."+sLang+".build_data")
except ImportError:
print("# Error. Couldn’t import file build_data.py in folder gc_lang/"+sLang)
if build_data_module:
build_data_module.before('gc_lang/'+sLang, dVars, xArgs.javascript)
if xArgs.dict or not os.path.exists("grammalecte/_dictionaries"):
import lex_build
lex_build.build(dVars['lexicon_src'], dVars['lang_name'], dVars['dic_name'], dVars['stemming_method'], int(dVars['fsa_method']), xArgs.javascript)
if build_data_module:
build_data_module.after('gc_lang/'+sLang, dVars, xArgs.javascript)
# make
sVersion = create(sLang, xConfig, xArgs.install, xArgs.javascript, )
# tests
|
| ︙ | ︙ |