88
89
90
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
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
|
# read lexicon
nStop = 0
for n, sLine in enumerate(readFile(sp+"/data/dictConj.txt")):
nTab = sLine.count("\t")
if nTab == 1:
# new entry
sLemma, sVinfo = sLine.split("\t")
dConj = { ":P": { ":P": "" },
":Q": { ":m:s": "", ":f:s": "", ":m:p": "", ":f:p": "" },
":Ip": { ":1s": "", ":2s": "", ":3s": "", ":1p": "", ":2p": "", ":3p": "", ":1ś": "" },
":Iq": { ":1s": "", ":2s": "", ":3s": "", ":1p": "", ":2p": "", ":3p": "" },
":Is": { ":1s": "", ":2s": "", ":3s": "", ":1p": "", ":2p": "", ":3p": "" },
":If": { ":1s": "", ":2s": "", ":3s": "", ":1p": "", ":2p": "", ":3p": "" },
":K": { ":1s": "", ":2s": "", ":3s": "", ":1p": "", ":2p": "", ":3p": "" },
":Sp": { ":1s": "", ":2s": "", ":3s": "", ":1p": "", ":2p": "", ":3p": "", ":1ś": "" },
":Sq": { ":1s": "", ":2s": "", ":3s": "", ":1p": "", ":2p": "", ":3p": "", ":1ś": "" },
":E": { ":2s": "", ":1p": "", ":2p": "" }
}
if sVinfo not in lVinfo:
dVinfo[sVinfo] = nVinfo
lVinfo.append(sVinfo)
nVinfo += 1
# looking for names derivating from verb
for sMorph in oDict.getMorph(sLemma):
if ":N" in sMorph:
dVerbNames[sLemma] = { sLemma }
break
elif nTab == 2:
# flexion
_, sTag, sFlex = sLine.split("\t")
if sTag.count(" ") == 0:
if sTag == "ppre":
dConj[":P"][":P"] = defineSuffixCode(sLemma, sFlex)
else:
try:
mode, g = sTag.split(maxsplit=1)
mode = dTrad[mode]
g = dTrad[g]
if dConj[mode][g] == "":
dConj[mode][g] = defineSuffixCode(sLemma, sFlex)
else:
# comment gérer les autres graphies ?
pass
except:
echo(sLemma, " - ", sTag, " - non géré: ", mode, " / ", g)
# looking for names derivating from verb
for sMorph in oDict.getMorph(sFlex):
if ":N" in sMorph:
if sLemma not in dVerbNames:
dVerbNames[sLemma] = { sFlex }
else:
dVerbNames[sLemma].add(sFlex)
break
elif sLine == "$":
# we store the dictionary of rules for this lemma
if dConj[":Ip"][":1ś"] == "2è":
dConj[":Ip"][":1ś"] = "2é"
elif sLemma == "pouvoir":
dConj[":Ip"][":1ś"] = "6uis"
lConjTags = []
for sTense in [":P", ":Q", ":Ip", ":Iq", ":Is", ":If", ":K", ":Sp", ":Sq", ":E"]:
bFound = False
for i, d in enumerate(dPatternList[sTense]):
if dConj[sTense] == d:
bFound = True
lConjTags.append(i)
break
if not bFound:
lConjTags.append(len(dPatternList[sTense]))
dPatternList[sTense].append(dConj[sTense])
tConjTags = tuple(lConjTags)
if tConjTags not in lTags:
dTags[tConjTags] = nTags
lTags.append(tConjTags)
nTags += 1
dVerb[sLemma] = (dVinfo[sVinfo], dTags[tConjTags])
else:
print("# Error - unknown line", n)
for sLemma, aNames in dVerbNames.items():
dVerbNames[sLemma] = tuple(aNames) # convert set to tuple
## write file for Python
sCode = "## generated data (do not edit)\n\n" + \
"# Informations about verbs\n" + \
"lVtyp = " + str(lVinfo) + "\n\n" + \
"# indexes of tenses in _dPatternConj\n" + \
"lTags = " + str(lTags) + "\n\n" + \
|
|
|
|
|
|
|
|
|
<
|
>
|
>
|
|
|
|
|
88
89
90
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
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
|
# read lexicon
nStop = 0
for n, sLine in enumerate(readFile(sp+"/data/dictConj.txt")):
nTab = sLine.count("\t")
if nTab == 1:
# new entry
sInfi, sVinfo = sLine.split("\t")
dConj = { ":P": { ":P": "" },
":Q": { ":m:s": "", ":f:s": "", ":m:p": "", ":f:p": "" },
":Ip": { ":1s": "", ":2s": "", ":3s": "", ":1p": "", ":2p": "", ":3p": "", ":1ś": "" },
":Iq": { ":1s": "", ":2s": "", ":3s": "", ":1p": "", ":2p": "", ":3p": "" },
":Is": { ":1s": "", ":2s": "", ":3s": "", ":1p": "", ":2p": "", ":3p": "" },
":If": { ":1s": "", ":2s": "", ":3s": "", ":1p": "", ":2p": "", ":3p": "" },
":K": { ":1s": "", ":2s": "", ":3s": "", ":1p": "", ":2p": "", ":3p": "" },
":Sp": { ":1s": "", ":2s": "", ":3s": "", ":1p": "", ":2p": "", ":3p": "", ":1ś": "" },
":Sq": { ":1s": "", ":2s": "", ":3s": "", ":1p": "", ":2p": "", ":3p": "", ":1ś": "" },
":E": { ":2s": "", ":1p": "", ":2p": "" }
}
if sVinfo not in lVinfo:
dVinfo[sVinfo] = nVinfo
lVinfo.append(sVinfo)
nVinfo += 1
# looking for names derivating from verb
for sMorph in oDict.getMorph(sInfi):
if ":N" in sMorph:
dVerbNames[sInfi] = { sInfi }
break
elif nTab == 2:
# flexion
_, sTag, sFlex = sLine.split("\t")
if sTag.count(" ") == 0:
if sTag == "ppre":
dConj[":P"][":P"] = defineSuffixCode(sInfi, sFlex)
else:
try:
mode, g = sTag.split(maxsplit=1)
mode = dTrad[mode]
g = dTrad[g]
if dConj[mode][g] == "":
dConj[mode][g] = defineSuffixCode(sInfi, sFlex)
else:
# comment gérer les autres graphies ?
pass
except:
echo(sInfi, " - ", sTag, " - non géré: ", mode, " / ", g)
# looking for names derivating from verb
for sMorph in oDict.getMorph(sFlex):
if ":N" in sMorph:
if sInfi not in dVerbNames:
dVerbNames[sInfi] = set()
dVerbNames[sInfi].add(sFlex)
sLemma = sMorph[1:sMorph.find("/")]
if sFlex != sLemma:
dVerbNames[sInfi].add(sLemma)
elif sLine == "$":
# we store the dictionary of rules for this lemma
if dConj[":Ip"][":1ś"] == "2è":
dConj[":Ip"][":1ś"] = "2é"
elif sInfi == "pouvoir":
dConj[":Ip"][":1ś"] = "6uis"
lConjTags = []
for sTense in [":P", ":Q", ":Ip", ":Iq", ":Is", ":If", ":K", ":Sp", ":Sq", ":E"]:
bFound = False
for i, d in enumerate(dPatternList[sTense]):
if dConj[sTense] == d:
bFound = True
lConjTags.append(i)
break
if not bFound:
lConjTags.append(len(dPatternList[sTense]))
dPatternList[sTense].append(dConj[sTense])
tConjTags = tuple(lConjTags)
if tConjTags not in lTags:
dTags[tConjTags] = nTags
lTags.append(tConjTags)
nTags += 1
dVerb[sInfi] = (dVinfo[sVinfo], dTags[tConjTags])
else:
print("# Error - unknown line", n)
for sInfi, aNames in dVerbNames.items():
dVerbNames[sInfi] = tuple(aNames) # convert set to tuple
## write file for Python
sCode = "## generated data (do not edit)\n\n" + \
"# Informations about verbs\n" + \
"lVtyp = " + str(lVinfo) + "\n\n" + \
"# indexes of tenses in _dPatternConj\n" + \
"lTags = " + str(lTags) + "\n\n" + \
|
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
|
## write file for JavaScript
sCode = "{\n" + \
' "dWord": ' + json.dumps(dWord, ensure_ascii=False) + ",\n" + \
' "lSet": ' + json.dumps(lSet, ensure_ascii=False) + ",\n" + \
' "dMorph": ' + json.dumps(dMorph, ensure_ascii=False) + "\n}"
open(sp+"/modules-js/phonet_data.json", "w", encoding="utf-8", newline="\n").write(sCode)
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]
dCur["_:_"] = sTag
sCode = "# generated data (do not edit)\n\n" + \
"dLocutions = " + str(dLocGraph) + "\n"
open(sp+"/modules/locutions_data.py", "w", encoding="utf-8", newline="\n").write(sCode)
if bJS:
open(sp+"/modules-js/locutions_data.json", "w", encoding="utf-8", newline="\n").write(json.dumps(dLocGraph, ensure_ascii=False))
#makeLocutions(spLaunch, bJS)
|
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
|
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
|
## write file for JavaScript
sCode = "{\n" + \
' "dWord": ' + json.dumps(dWord, ensure_ascii=False) + ",\n" + \
' "lSet": ' + json.dumps(lSet, ensure_ascii=False) + ",\n" + \
' "dMorph": ' + json.dumps(dMorph, ensure_ascii=False) + "\n}"
open(sp+"/modules-js/phonet_data.json", "w", encoding="utf-8", newline="\n").write(sCode)
def before (spLaunch, dVars, bJS=False):
print("========== Build Hunspell dictionaries ==========")
makeDictionaries(spLaunch, dVars['oxt_version'])
def after (spLaunch, dVars, bJS=False):
print("========== Build French data ==========")
makeMfsp(spLaunch, bJS)
makeConj(spLaunch, bJS)
makePhonetTable(spLaunch, bJS)
|