Grammalecte  Check-in [1a082eec4e]

Overview
Comment:[build][fr] build_data: readFile as a generator
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | fr | build | Lexicographe
Files: files | file ages | folders
SHA3-256: 1a082eec4e46c799b26a996b64b200b54a8e5687fc14e5b6b25360be2a2bd28f
User & Date: olr on 2017-11-01 08:16:55
Other Links: branch diff | manifest | tags
Context
2017-11-01
08:22
[build][fr] build_data: add locutions_vrac.txt for unchecked locutions check-in: ceaa0c6eae user: olr tags: Lexicographe, build, fr
08:16
[build][fr] build_data: readFile as a generator check-in: 1a082eec4e user: olr tags: Lexicographe, build, fr
2017-10-31
21:05
Optimisation mineur check-in: 1a7c706a66 user: IllusionPerdu tags: Lexicographe, fr
Changes

Modified gc_lang/fr/build_data.py from [f2198525f4] to [39bc8d4153].

23
24
25
26
27
28
29











30
31
32
33
34
35
36
..
46
47
48
49
50
51
52
53
54
55
56

57
58
59
60
61
62
63
64
65
66
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
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
...
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
195
196
197
198
199
200
201
202
203
204
205
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
...
262
263
264
265
266
267
268
269
270
271
272
273

274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
...
308
309
310
311
312
313
314
315
316
317
318
319

320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
    def __enter__ (self):
        self.savedPath = os.getcwd()
        os.chdir(self.newPath)

    def __exit__ (self, etype, value, traceback):
        os.chdir(self.savedPath)













def makeDictionaries (sp, sVersion):
    with cd(sp+"/dictionnaire"):
        os.system("genfrdic.py -s -gl -v "+sVersion)


def makeConj (sp, bJS=False):
................................................................................
                "spre": ":Sp", "simp": ":Sq",
                "cond": ":K", "impe": ":E",
                "1sg": ":1s", "2sg": ":2s", "3sg": ":3s", "1pl": ":1p", "2pl": ":2p", "3pl": ":3p", "1isg": ":1ś",
                "mas sg": ":Q1", "mas pl": ":Q2", "mas inv": ":Q1", "fem sg": ":Q3", "fem pl": ":Q4", "epi inv": ":Q1"
            }

    # read lexicon
    with open(sp+"/data/dictConj.txt", 'r', encoding='utf-8') as hSrc:
        nStop = 0
        for n, line in enumerate(hSrc.readlines()):
            line = line.strip()

            nTab = line.count("\t")
            if nTab == 1:
                # new entry
                sLemma, sVtyp = line.split("\t")
                dConj = {   ":PQ": { ":P": "", ":Q1": "", ":Q2": "", ":Q3": "", ":Q4": ""},
                            ":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 sVtyp not in lVtyp:
                    dVtyp[sVtyp] = nVtyp
                    lVtyp.append(sVtyp)
                    nVtyp += 1
            elif nTab == 2:
                # flexion
                _, sTag, sFlex = line.split("\t")
                if sTag.count(" ") == 0:
                    if sTag == "ppre":
                        dConj[":PQ"][":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:
                        print(sLemma.encode("utf-8").decode("ascii"), " - ", sTag, " - non géré: ", mode, " / ", g)
            elif line == "$":
                # 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 key in [":PQ", ":Ip", ":Iq", ":Is", ":If", ":K", ":Sp", ":Sq", ":E"]:
                    bFound = False
                    for i, d in enumerate(dPatternList[key]):
                        if dConj[key] == d:
                            bFound = True
                            lConjTags.append(i)
                            break
                    if not bFound:
                        lConjTags.append(len(dPatternList[key]))
                        dPatternList[key].append(dConj[key])
                tConjTags = tuple(lConjTags)
                if tConjTags not in lTags:
                    dTags[tConjTags] = nTags
                    lTags.append(tConjTags)
                    nTags += 1
                dVerb[sLemma] = (dVtyp[sVtyp], dTags[tConjTags])
            else:
                print("# Error - unknown line #", n)

    # convert tuples to bytes string
    # si ça merde, toute la partie conversion peut être supprimée
    # lBytesTags = []
    # for t in lTags:
    #     b = b""
    #     for n in t:
................................................................................
    print("(Python et JavaScript)"  if bJS  else "(Python seulement)")
    aPlurS = set()
    dTag = {}
    lTagMasForm = []
    lTagMiscPlur = []
    dMiscPlur = {}
    dMasForm = {}
    # read lexicon
    with open(sp+"/data/dictDecl.txt", 'r', encoding='utf-8') as hSrc:
        lTag = []
        lTagMasPl = []
        for n, line in enumerate(hSrc.readlines()):
            line = line.strip()

            nTab = line.count("\t")
            if nTab == 1:
                # new entry
                lTag.clear()
                lTagMasPl.clear()
                sLemma, sFlags = line.split("\t")
                if sFlags.startswith("S"):
                    cType = "s"
                elif sFlags.startswith("X"):
                    cType = "p"
                elif sFlags.startswith("A"):
                    cType = "p"
                elif sFlags.startswith("I"):
                    cType = "p"
                elif sFlags.startswith("F"):
                    cType = "m"
                elif sFlags.startswith("W"):
                    cType = "m"
                else:
                    cType = "?"
                    print(" > inconnu : " + sFlags)
            elif nTab == 2:
                if cType == "s":
                    continue
                _, sFlexTags, sFlex = line.split("\t")
                if cType == "p":
                    if sFlexTags.endswith("pl"):
                        lTag.append(defineSuffixCode(sLemma, sFlex))
                elif cType == "m":
                    if sFlexTags.endswith("mas sg") or sFlexTags.endswith("mas inv"):
                        lTag.append(defineSuffixCode(sLemma, sFlex))
                    if sFlexTags.endswith("mas pl"):
                        lTagMasPl.append(defineSuffixCode(sLemma, sFlex))
                else:
                    print("erreur: " + cType)
            elif line == "$":
                if cType == "s":
                    aPlurS.add(sLemma)
                elif cType == "p":
                    sTag = "|".join(lTag)
                    if sTag not in dTag:
                        dTag[sTag] = len(lTagMiscPlur)
                        lTagMiscPlur.append(sTag)
                    dMiscPlur[sLemma] = dTag[sTag]
                elif cType == "m":
                    sTag = "|".join(lTag)
                    if lTagMasPl:
                        sTag += "/" + "|".join(lTagMasPl)
                    if sTag not in dTag:
                        dTag[sTag] = len(lTagMasForm)
                        lTagMasForm.append(sTag)
                    dMasForm[sLemma] = dTag[sTag]
                else:
                    print("unknown tag: " + ctype)
            else:
                print("# Error - unknown line #", n)

    ## write file for Python
    sCode = "# generated data (do not edit)\n\n" + \
            "# list of affix codes\n" + \
            "lTagMiscPlur = " + str(lTagMiscPlur) + "\n" + \
            "lTagMasForm = " + str(lTagMasForm) + "\n\n" + \
            "# dictionary of words with uncommon plurals (-x, -ux, english, latin and italian plurals) and tags to generate them\n" + \
................................................................................

    try:
        oDict = ibdawg.IBDAWG("French.bdic")
    except:
        traceback.print_exc()
        return

    with open(sp+"/data/phonet_simil.txt", 'r', encoding='utf-8') as hSrc:
        # set of homophonic words
        lSet = []
        for sLine in hSrc.readlines():
            if not sLine.startswith("#") and sLine.strip():

                lWord = sLine.strip().split()
                aMore = set()
                for sWord in lWord:
                    if sWord.endswith("er") and conj.isVerb(sWord):
                        aMore = aMore.union(conj.getConjSimilInfiV1(sWord))
                lWord.extend(list(aMore))
                lSet.append(sorted(set(lWord)))
                #print(lWord)
        # dictionary of words
        dWord = {}
        for i, aSet in enumerate(lSet):
            for sWord in aSet:
                if oDict.lookup(sWord):
                    dWord[sWord] = i  # warning, what if word in several sets?
                else:
                    echo("Mot inconnu : " + sWord)
        # dictionary of morphologies
        dMorph = {}
        for sWord in dWord:
            dMorph[sWord] = oDict.getMorph(sWord)

    # write file for Python
    sCode = "# generated data (do not edit)\n\n" + \
            "dWord = " + str(dWord) + "\n\n" + \
            "lSet = " + str(lSet) + "\n\n" + \
            "dMorph = " + str(dMorph) + "\n"
    open(sp+"/modules/phonet_data.py", "w", encoding="utf-8", newline="\n").write(sCode)
................................................................................
        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)")
    with open(sp+"/data/locutions.txt", 'r', encoding='utf-8') as hSrc:
        dLocGraph = {}
        oTokenizer = tkz.Tokenizer("fr")
        for sLine in hSrc.readlines():
            if not sLine.startswith("#") and sLine.strip():

                dCur = dLocGraph
                sLoc, sTag = sLine.strip().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))








>
>
>
>
>
>
>
>
>
>
>







 







<
|
<
<
>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|







 







<
<
|
|
<
<
>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|







 







<
|
|
<
<
>
|
|
|
|
|
|
|
<
|
|
|
|
|
|
|
|
|
|
|
|







 







<
|
|
<
<
>
|
|
|
|
|
|
|
|







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
..
57
58
59
60
61
62
63

64


65
66
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
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
...
177
178
179
180
181
182
183


184
185


186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
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
...
268
269
270
271
272
273
274

275
276


277
278
279
280
281
282
283
284

285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
...
311
312
313
314
315
316
317

318
319


320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
    def __enter__ (self):
        self.savedPath = os.getcwd()
        os.chdir(self.newPath)

    def __exit__ (self, etype, value, traceback):
        os.chdir(self.savedPath)


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):
    with cd(sp+"/dictionnaire"):
        os.system("genfrdic.py -s -gl -v "+sVersion)


def makeConj (sp, bJS=False):
................................................................................
                "spre": ":Sp", "simp": ":Sq",
                "cond": ":K", "impe": ":E",
                "1sg": ":1s", "2sg": ":2s", "3sg": ":3s", "1pl": ":1p", "2pl": ":2p", "3pl": ":3p", "1isg": ":1ś",
                "mas sg": ":Q1", "mas pl": ":Q2", "mas inv": ":Q1", "fem sg": ":Q3", "fem pl": ":Q4", "epi inv": ":Q1"
            }

    # read lexicon

    nStop = 0


    for n, sLine in enumerate(readFile(sp+"/data/dictConj.txt")):
        nTab = sLine.count("\t")
        if nTab == 1:
            # new entry
            sLemma, sVtyp = sLine.split("\t")
            dConj = {   ":PQ": { ":P": "", ":Q1": "", ":Q2": "", ":Q3": "", ":Q4": ""},
                        ":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 sVtyp not in lVtyp:
                dVtyp[sVtyp] = nVtyp
                lVtyp.append(sVtyp)
                nVtyp += 1
        elif nTab == 2:
            # flexion
            _, sTag, sFlex = sLine.split("\t")
            if sTag.count(" ") == 0:
                if sTag == "ppre":
                    dConj[":PQ"][":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:
                    print(sLemma.encode("utf-8").decode("ascii"), " - ", sTag, " - non géré: ", mode, " / ", g)
        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 key in [":PQ", ":Ip", ":Iq", ":Is", ":If", ":K", ":Sp", ":Sq", ":E"]:
                bFound = False
                for i, d in enumerate(dPatternList[key]):
                    if dConj[key] == d:
                        bFound = True
                        lConjTags.append(i)
                        break
                if not bFound:
                    lConjTags.append(len(dPatternList[key]))
                    dPatternList[key].append(dConj[key])
            tConjTags = tuple(lConjTags)
            if tConjTags not in lTags:
                dTags[tConjTags] = nTags
                lTags.append(tConjTags)
                nTags += 1
            dVerb[sLemma] = (dVtyp[sVtyp], dTags[tConjTags])
        else:
            print("# Error - unknown line #", n)

    # convert tuples to bytes string
    # si ça merde, toute la partie conversion peut être supprimée
    # lBytesTags = []
    # for t in lTags:
    #     b = b""
    #     for n in t:
................................................................................
    print("(Python et JavaScript)"  if bJS  else "(Python seulement)")
    aPlurS = set()
    dTag = {}
    lTagMasForm = []
    lTagMiscPlur = []
    dMiscPlur = {}
    dMasForm = {}


    lTag = []
    lTagMasPl = []


    for n, sLine in enumerate(readFile(sp+"/data/dictDecl.txt")):
        nTab = sLine.count("\t")
        if nTab == 1:
            # new entry
            lTag.clear()
            lTagMasPl.clear()
            sLemma, sFlags = sLine.split("\t")
            if sFlags.startswith("S"):
                cType = "s"
            elif sFlags.startswith("X"):
                cType = "p"
            elif sFlags.startswith("A"):
                cType = "p"
            elif sFlags.startswith("I"):
                cType = "p"
            elif sFlags.startswith("F"):
                cType = "m"
            elif sFlags.startswith("W"):
                cType = "m"
            else:
                cType = "?"
                print(" > inconnu : " + sFlags)
        elif nTab == 2:
            if cType == "s":
                continue
            _, sFlexTags, sFlex = sLine.split("\t")
            if cType == "p":
                if sFlexTags.endswith("pl"):
                    lTag.append(defineSuffixCode(sLemma, sFlex))
            elif cType == "m":
                if sFlexTags.endswith("mas sg") or sFlexTags.endswith("mas inv"):
                    lTag.append(defineSuffixCode(sLemma, sFlex))
                if sFlexTags.endswith("mas pl"):
                    lTagMasPl.append(defineSuffixCode(sLemma, sFlex))
            else:
                print("erreur: " + cType)
        elif sLine == "$":
            if cType == "s":
                aPlurS.add(sLemma)
            elif cType == "p":
                sTag = "|".join(lTag)
                if sTag not in dTag:
                    dTag[sTag] = len(lTagMiscPlur)
                    lTagMiscPlur.append(sTag)
                dMiscPlur[sLemma] = dTag[sTag]
            elif cType == "m":
                sTag = "|".join(lTag)
                if lTagMasPl:
                    sTag += "/" + "|".join(lTagMasPl)
                if sTag not in dTag:
                    dTag[sTag] = len(lTagMasForm)
                    lTagMasForm.append(sTag)
                dMasForm[sLemma] = dTag[sTag]
            else:
                print("unknown tag: " + ctype)
        else:
            print("# Error - unknown line #", n)

    ## write file for Python
    sCode = "# generated data (do not edit)\n\n" + \
            "# list of affix codes\n" + \
            "lTagMiscPlur = " + str(lTagMiscPlur) + "\n" + \
            "lTagMasForm = " + str(lTagMasForm) + "\n\n" + \
            "# dictionary of words with uncommon plurals (-x, -ux, english, latin and italian plurals) and tags to generate them\n" + \
................................................................................

    try:
        oDict = ibdawg.IBDAWG("French.bdic")
    except:
        traceback.print_exc()
        return


    # set of homophonic words
    lSet = []


    for sLine in readFile(sp+"/data/phonet_simil.txt"):
        lWord = sLine.split()
        aMore = set()
        for sWord in lWord:
            if sWord.endswith("er") and conj.isVerb(sWord):
                aMore = aMore.union(conj.getConjSimilInfiV1(sWord))
        lWord.extend(list(aMore))
        lSet.append(sorted(set(lWord)))

    # dictionary of words
    dWord = {}
    for i, aSet in enumerate(lSet):
        for sWord in aSet:
            if oDict.lookup(sWord):
                dWord[sWord] = i  # warning, what if word in several sets?
            else:
                echo("Mot inconnu : " + sWord)
    # dictionary of morphologies
    dMorph = {}
    for sWord in dWord:
        dMorph[sWord] = oDict.getMorph(sWord)

    # write file for Python
    sCode = "# generated data (do not edit)\n\n" + \
            "dWord = " + str(dWord) + "\n\n" + \
            "lSet = " + str(lSet) + "\n\n" + \
            "dMorph = " + str(dMorph) + "\n"
    open(sp+"/modules/phonet_data.py", "w", encoding="utf-8", newline="\n").write(sCode)
................................................................................
        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 readFile(sp+"/data/locutions.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))