Overview
| Comment: | [fr] locutions: màj du build |
|---|---|
| Downloads: | Tarball | ZIP archive | SQL archive |
| Timelines: | family | ancestors | descendants | both | fr | Lexicographe |
| Files: | files | file ages | folders |
| SHA3-256: |
854ccdff143b524ebe89d564be9a8dac |
| User & Date: | olr on 2017-11-04 07:31:34 |
| Other Links: | branch diff | manifest | tags |
Context
|
2017-11-04
| ||
| 09:49 | [fr] locutions: tri et corrections check-in: 68fbc93bb9 user: olr tags: fr, Lexicographe | |
| 07:31 | [fr] locutions: màj du build check-in: 854ccdff14 user: olr tags: fr, Lexicographe | |
| 07:27 | [fr] locutions: nouveaux fichiers check-in: 0645dffbea user: olr tags: fr, Lexicographe | |
Changes
Modified gc_lang/fr/build_data.py from [1e628c0406] to [1c5ad0c32d].
| ︙ | ︙ | |||
30 31 32 33 34 35 36 37 38 39 40 41 42 43 |
def readFile (spf):
if os.path.isfile(spf):
with open(spf, "r", encoding="utf-8") as hSrc:
for sLine in hSrc:
sLine = sLine.strip()
if sLine and not sLine.startswith("#"):
yield sLine
else:
raise OSError("# Error. File not found or not loadable: " + spf)
def makeDictionaries (sp, sVersion):
| > > | 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 |
def readFile (spf):
if os.path.isfile(spf):
with open(spf, "r", encoding="utf-8") as hSrc:
for sLine in hSrc:
sLine = sLine.strip()
if sLine == "__END__":
break
if sLine and not sLine.startswith("#"):
yield sLine
else:
raise OSError("# Error. File not found or not loadable: " + spf)
def makeDictionaries (sp, sVersion):
|
| ︙ | ︙ | |||
314 315 316 317 318 319 320 |
def makeLocutions (sp, bJS=False):
"compile list of locutions in JSON"
print("> Locutions ", end="")
print("(Python et JavaScript)" if bJS else "(Python seulement)")
dLocGraph = {}
oTokenizer = tkz.Tokenizer("fr")
| | | > > > > > | | 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 |
def makeLocutions (sp, bJS=False):
"compile list of locutions in JSON"
print("> Locutions ", end="")
print("(Python et JavaScript)" if bJS else "(Python seulement)")
dLocGraph = {}
oTokenizer = tkz.Tokenizer("fr")
for sLine in itertools.chain(readFile(sp+"/data/locutions_adverbiales.txt"), \
readFile(sp+"/data/locutions_prépositives.txt"), \
readFile(sp+"/data/locutions_conjonctives.txt"), \
readFile(sp+"/data/locutions_pronominales.txt"), \
readFile(sp+"/data/locutions_adjectivales.txt"), \
readFile(sp+"/data/locutions_interjectives.txt"), \
readFile(sp+"/data/locutions_nominales.txt"), \
readFile(sp+"/data/locutions_verbales.txt")):
dCur = dLocGraph
sLoc, sTag = sLine.split("\t")
for oToken in oTokenizer.genTokens(sLoc.strip()):
sWord = oToken["sValue"]
if sWord not in dCur:
dCur[sWord] = {}
dCur = dCur[sWord]
|
| ︙ | ︙ |