Grammalecte  Changes On Branch ceaa0c6eaedd327e

Hide Diff Patch Side-by-Side Diff

Changes In Branch Lexicographe Through [ceaa0c6eae] Excluding Merge-Ins

This is equivalent to a diff from 4ffad6e596 to ceaa0c6eae

2017-11-01
09:20
[fr] data: locutions check-in: 144b46f14c user: olr tags: Lexicographe, fr
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
2017-10-29
11:19
Détection des locutions dans le lexicographe check-in: 47ddd1a06d user: IllusionPerdu tags: Lexicographe
2017-10-28
19:58
[build][fr] build_data: code cleaning check-in: ba1b8fe0e2 user: olr tags: build, fr, trunk
13:47
[build][fr] rename locutions files check-in: 4ffad6e596 user: olr tags: build, fr, trunk
13:17
[build][fr] data: locutions check-in: e356116b6e user: olr tags: build, fr, trunk

Modified gc_core/js/text.js from [9bf91b3594] to [abcdad5f85]. 

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

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














-
+




-
+








// JavaScript
/*jslint esversion: 6*/
/*global require,exports*/

"use strict";


if (typeof(require) !== 'undefined') {
    var helpers = require("resource://grammalecte/helpers.js");
}


var text = {
    getParagraph: function* (sText) {
    getParagraph: function* (sText, sSepParagraph = "\n") {
        // generator: returns paragraphs of text
        let iStart = 0;
        let iEnd = 0;
        sText = sText.replace("\r\n", "\n").replace("\r", "\n");
        while ((iEnd = sText.indexOf("\n", iStart)) !== -1) {
        while ((iEnd = sText.indexOf(sSepParagraph, iStart)) !== -1) {
            yield sText.slice(iStart, iEnd);
            iStart = iEnd + 1;
        }
        yield sText.slice(iStart);
    },

    wrap: function* (sText, nWidth=80) {
︙
41
42
43
44
45
46
47
48

49
50
51
52
53
54
55

41
42
43
44
45
46
47

48
49
50
51
52
53
54
55








-
+








        }
        yield sText;
    },

    getReadableError: function (oErr) {
        // Returns an error oErr as a readable error
        try {
            let sResult = "\n* " + oErr['nStart'] + ":" + oErr['nEnd'] 
            let sResult = "\n* " + oErr['nStart'] + ":" + oErr['nEnd']
                        + "  # " + oErr['sLineId'] + "  # " + oErr['sRuleId'] + ":\n";
            sResult += "  " + oErr["sMessage"];
            if (oErr["aSuggestions"].length > 0) {
                sResult += "\n  > Suggestions : " + oErr["aSuggestions"].join(" | ");
            }
            if (oErr["URL"] !== "") {
                sResult += "\n  > URL: " + oErr["URL"];
︙

Modified gc_lang/fr/build_data.py from [1ffed9614b] to [732462dec8]. 

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
30
31
32
33
34
35

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
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48










+





+














+
+
+
+
+
+
+
+
+
+
+








#!python3

# FRENCH DATA BUILDER
#
# by Olivier R.
# License: MPL 2

import json
import os
import itertools

import grammalecte.ibdawg as ibdawg
from grammalecte.echo import echo
from grammalecte.str_transform import defineSuffixCode
import grammalecte.fr.conj as conj
import grammalecte.tokenizer as tkz


class cd:
    """Context manager for changing the current working directory"""
    def __init__ (self, newPath):
        self.newPath = os.path.expanduser(newPath)

    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):
︙
45
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

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
134








-
-
-
+
+
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+








                "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()):
    nStop = 0
    for n, sLine in enumerate(readFile(sp+"/data/dictConj.txt")):
            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)
        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:
︙
167
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

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
250








-
-
-
-
-
+
+
+
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+








    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()):
    lTag = []
    lTagMasPl = []
    for n, sLine in enumerate(readFile(sp+"/data/dictDecl.txt")):
            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)
        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" + \
︙
254
255
256
257
258
259
260
261

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

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
301
302
303
304








-
+






-
-
-
-
+
+
+
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
-
-
-
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+








                '    "dMasForm": ' +  json.dumps(dMasForm, ensure_ascii=False) + "\n}"
        open(sp+"/modules-js/mfsp_data.json", "w", encoding="utf-8", newline="\n").write(sCode)


def makePhonetTable (sp, bJS=False):
    print("> Correspondances phonétiques ", end="")
    print("(Python et JavaScript)"  if bJS  else "(Python seulement)")
    

    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():
    # set of homophonic words
    lSet = []
    for sLine in readFile(sp+"/data/phonet_simil.txt"):
            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)))
        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)))
                #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)
    # 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)
︙
307
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
335
336
337
338
339
340
341
342

312
313
314
315
316
317
318



319
320
321







322
323
324
325
326
327
328
329
330
331

332
333
334

335
336
337
338
339
340
341
342
343
344
345
346
347
348








-
-
-
+
+
+
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+


-
+


-
+














        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:
        dLocutions = {}
        for sLine in hSrc.readlines():
    dLocGraph = {}
    oTokenizer = tkz.Tokenizer("fr")
    for sLine in itertools.chain(readFile(sp+"/data/locutions.txt"), readFile(sp+"/data/locutions_vrac.txt")):
            if not sLine.startswith("#") and sLine.strip():
                lElem = sLine.strip().split()
                dCur = dLocutions
                for sWord in lElem:
                    if sWord not in dCur:
                        dCur[sWord] = {}
                    dCur = dCur[sWord]
        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(dLocutions) + "\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(dLocutions, ensure_ascii=False))
        open(sp+"/modules-js/locutions_data.json", "w", encoding="utf-8", newline="\n").write(json.dumps(dLocGraph, ensure_ascii=False))


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)
    makeLocutions(spLaunch, bJS)

Modified gc_lang/fr/data/locutions.txt from [190d018874] to [0eb5a79076]. 

1
2
3
4
5
6
7
8























1
2
3
4
5
6
7
8
9
10
11
12
13
14

-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+

à califourchon
à cœur joie
à cœur ouvert
à corps perdu
à perte de vue
à visage découvert
par ailleurs
par acquit de conscience
à califourchon	:LW
à contrecœur	:LW
à cœur joie	:LW
à cœur ouvert	:LW
à corps perdu	:LW
à bâtons rompus	:LW
à perte de vue	:LW
à visage découvert	:LW
à vue d’œil	:LW
à l’aveuglette	:LW
ad hominem	:LW
en tout et pour tout	:LW
par ailleurs	:LW
par acquit de conscience	:LW

Added gc_lang/fr/data/locutions_vrac.txt version [a7ffc6f8bf].

Modified gc_lang/fr/modules-js/lexicographe.js from [08da929c5c] to [d63c8f768b]. 

1
2
3
4
5
6
7
8
9
10
11
12

13
14
15
16

17
18
19
20
21
22
23

1
2
3
4
5
6
7
8
9
10
11

12
13
14
15

16
17
18
19
20
21
22
23












-
+



-
+








// Grammalecte - Lexicographe
// License: MPL 2
/*jslint esversion: 6*/
/*global require,exports*/

"use strict";

${string}
${map}


if (typeof(require) !== 'undefined') {
if (typeof (require) !== 'undefined') {
    var helpers = require("resource://grammalecte/helpers.js");
}

const _dTAGS = new Map ([
const _dTAGS = new Map([
    [':G', "[mot grammatical]"],
    [':N', " nom,"],
    [':A', " adjectif,"],
    [':M1', " prénom,"],
    [':M2', " patronyme,"],
    [':MP', " nom propre,"],
    [':W', " adverbe,"],
︙
44
45
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

44
45
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








-
+



















-
+








    [':Os', " pronom personnel sujet,"],
    [':Oo', " pronom personnel objet,"],
    [':C',  " conjonction,"],
    [':Ĉ',  " conjonction (él.),"],
    [':Cc', " conjonction de coordination,"],
    [':Cs', " conjonction de subordination,"],
    [':Ĉs', " conjonction de subordination (él.),"],
    

    [':Ŵ', " locution adverbiale (él.),"],
    [':Ñ', " locution nominale (él.),"],
    [':Â', " locution adjectivale (él.),"],
    [':Ṽ', " locution verbale (él.),"],
    [':Ŕ', " locution prépositive (él.),"],
    [':Ĵ', " locution interjective (él.),"],

    [':Zp', " préfixe,"],
    [':Zs', " suffixe,"],

    [':V1', " verbe (1ᵉʳ gr.),"],
    [':V2', " verbe (2ᵉ gr.),"],
    [':V3', " verbe (3ᵉ gr.),"],
    [':V0e', " verbe,"],
    [':V0a', " verbe,"],

    [':O1', " 1ʳᵉ pers.,"],
    [':O2', " 2ᵉ pers.,"],
    [':O3', " 3ᵉ pers.,"],
    

    [':e', " épicène"],
    [':m', " masculin"],
    [':f', " féminin"],
    [':s', " singulier"],
    [':p', " pluriel"],
    [':i', " invariable"],
︙
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

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
178
179
180
181
182
183
184
185
186
187
188
189
190

191
192
193
194
195
196
197
198








+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-
+















-
+









-
+


-
+



-
+


















-
+








    ['/C', " {classique}"],
    ['/M', ""],
    ['/R', " {réforme}"],
    ['/A', ""],
    ['/X', ""]
]);

const _dLocTAGS = new Map([
    [':LN', "locution nominale"],
    [':LA', "locution adjectivale"],
    [':LV', "locution verbale"],
    [':LW', "locution adverbiale"],
    [':LR', "locution prépositive"],
    [':LO', "locution pronominale"],
    [':LC', "locution conjonctive"],
    [':LJ', "locution interjective"],

    [':B', " cardinal"],
    [':e', " épicène"],
    [':m', " masculin"],
    [':f', " féminin"],
    [':s', " singulier"],
    [':p', " pluriel"],
    [':i', " invariable"],
    ['/L', " {latin}"]
]);
const _dLocVERB = new Map([
    ['i', " intransitif"],
    ['n', " transitif indirect"],
    ['t', " transitif direct"],
    ['p', " pronominal"],
    ['m', " impersonnel"],
]);

const _dPFX = new Map ([
const _dPFX = new Map([
    ['d', "(de), déterminant épicène invariable"],
    ['l', "(le/la), déterminant masculin/féminin singulier"],
    ['j', "(je), pronom personnel sujet, 1ʳᵉ pers., épicène singulier"],
    ['m', "(me), pronom personnel objet, 1ʳᵉ pers., épicène singulier"],
    ['t', "(te), pronom personnel objet, 2ᵉ pers., épicène singulier"],
    ['s', "(se), pronom personnel objet, 3ᵉ pers., épicène singulier/pluriel"],
    ['n', "(ne), adverbe de négation"],
    ['c', "(ce), pronom démonstratif, masculin singulier/pluriel"],
    ['ç', "(ça), pronom démonstratif, masculin singulier"],
    ['qu', "(que), conjonction de subordination"],
    ['lorsqu', "(lorsque), conjonction de subordination"],
    ['quoiqu', "(quoique), conjonction de subordination"],
    ['jusqu', "(jusque), préposition"]
]);

const _dAD = new Map ([
const _dAD = new Map([
    ['je', " pronom personnel sujet, 1ʳᵉ pers. sing."],
    ['tu', " pronom personnel sujet, 2ᵉ pers. sing."],
    ['il', " pronom personnel sujet, 3ᵉ pers. masc. sing."],
    ['on', " pronom personnel sujet, 3ᵉ pers. sing. ou plur."],
    ['elle', " pronom personnel sujet, 3ᵉ pers. fém. sing."],
    ['nous', " pronom personnel sujet/objet, 1ʳᵉ pers. plur."],
    ['vous', " pronom personnel sujet/objet, 2ᵉ pers. plur."],
    ['ils', " pronom personnel sujet, 3ᵉ pers. masc. plur."],
    ['elles', " pronom personnel sujet, 3ᵉ pers. masc. plur."],
    

    ["là", " particule démonstrative"],
    ["ci", " particule démonstrative"],
    

    ['le', " COD, masc. sing."],
    ['la', " COD, fém. sing."],
    ['les', " COD, plur."],
        

    ['moi', " COI (à moi), sing."],
    ['toi', " COI (à toi), sing."],
    ['lui', " COI (à lui ou à elle), sing."],
    ['nous2', " COI (à nous), plur."],
    ['vous2', " COI (à vous), plur."],
    ['leur', " COI (à eux ou à elles), plur."],

    ['y', " pronom adverbial"],
    ["m'y", " (me) pronom personnel objet + (y) pronom adverbial"],
    ["t'y", " (te) pronom personnel objet + (y) pronom adverbial"],
    ["s'y", " (se) pronom personnel objet + (y) pronom adverbial"],

    ['en', " pronom adverbial"],
    ["m'en", " (me) pronom personnel objet + (en) pronom adverbial"],
    ["t'en", " (te) pronom personnel objet + (en) pronom adverbial"],
    ["s'en", " (se) pronom personnel objet + (en) pronom adverbial"]
]);

const _dSeparator = new Map ([
const _dSeparator = new Map([
    ['.', "point"],
    ['·', "point médian"],
    ['…', "points de suspension"],
    [':', "deux-points"],
    [';', "point-virgule"],
    [',', "virgule"],
    ['?', "point d’interrogation"],
︙
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
250
251









252
253
254
255
256

257
258
259
260
261
262
263

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
250
251
252

253
254
255
256
257
258
259

260
261
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


301
302
303
304
305
306




307
308
309
310
311
312
313
314
315
316
317
318


319
320
321
322
323
324
325
326








-
+

+
+
+
-
-
-
+
+
+
+




-
+




+
+
+
-
+
+


+
+
-
+
+
+


+
+
-
+
+
+



+
+
+
-
+
+


+
+
-
+
+
+

-
+

+
+
+
-
-
-
+
+
+


-
-
+
+

+
+
-
-
-
+
+
+
+



-
-
+
+


+
+
-
-
-
-
+
+
+
+
+
+
+
+
+



-
-
+








    ['<', "inférieur à"],
    ['>', "supérieur à"],
]);


class Lexicographe {

    constructor (oDict) {
    constructor (oDict, oTokenizer, oLocGraph) {
        this.oDict = oDict;
        this.oTokenizer = oTokenizer;
        this.oLocGraph = JSON.parse(oLocGraph);

        this._zElidedPrefix = new RegExp ("^([dljmtsncç]|quoiqu|lorsqu|jusqu|puisqu|qu)['’](.+)", "i");
        this._zCompoundWord = new RegExp ("([a-zA-Zà-ö0-9À-Öø-ÿØ-ßĀ-ʯ]+)-((?:les?|la)-(?:moi|toi|lui|[nv]ous|leur)|t-(?:il|elle|on)|y|en|[mts][’'](?:y|en)|les?|l[aà]|[mt]oi|leur|lui|je|tu|ils?|elles?|on|[nv]ous)$", "i");
        this._zTag = new RegExp ("[:;/][a-zA-Zà-ö0-9À-Öø-ÿØ-ßĀ-ʯ*][^:;/]*", "g");
        this._zElidedPrefix = new RegExp("^([dljmtsncç]|quoiqu|lorsqu|jusqu|puisqu|qu)['’](.+)", "i");
        this._zCompoundWord = new RegExp("([a-zA-Zà-ö0-9À-Öø-ÿØ-ßĀ-ʯ]+)-((?:les?|la)-(?:moi|toi|lui|[nv]ous|leur)|t-(?:il|elle|on)|y|en|[mts][’'](?:y|en)|les?|l[aà]|[mt]oi|leur|lui|je|tu|ils?|elles?|on|[nv]ous)$", "i");
        this._zTag = new RegExp("[:;/][a-zA-Zà-ö0-9À-Öø-ÿØ-ßĀ-ʯ*Ṽ][^:;/]*", "g");
        this._zLocTag = new RegExp("(:L[A-Z])([a-z].?)?(.*)");
    }

    getInfoForToken (oToken) {
        // Token: .sType, .sValue, .nStart, .nEnd
        // return a list [type, token_string, values]
        // return a object {sType, sValue, aLabel}
        let m = null;
        try {
            switch (oToken.sType) {
                case 'SEPARATOR':
                    return {
                        sType: oToken.sType,
                        sValue: oToken.sValue,
                    return { sType: oToken.sType, sValue: oToken.sValue, aLabel: [_dSeparator.gl_get(oToken.sValue, "caractère indéterminé")] };
                        aLabel: [_dSeparator.gl_get(oToken.sValue, "caractère indéterminé")]
                    };
                    break;
                case 'NUM':
                    return {
                        sType: oToken.sType,
                    return { sType: oToken.sType, sValue: oToken.sValue, aLabel: ["nombre"] };
                        sValue: oToken.sValue,
                        aLabel: ["nombre"]
                    };
                    break;
                case 'LINK':
                    return {
                        sType: oToken.sType,
                    return { sType: oToken.sType, sValue: oToken.sValue.slice(0,40)+"…", aLabel: ["hyperlien"] };
                        sValue: oToken.sValue.slice(0, 40) + "…",
                        aLabel: ["hyperlien"]
                    };
                    break;
                case 'ELPFX':
                    let sTemp = oToken.sValue.replace("’", "").replace("'", "").replace("`", "").toLowerCase();
                    return {
                        sType: oToken.sType,
                        sValue: oToken.sValue,
                    return { sType: oToken.sType, sValue: oToken.sValue, aLabel: [_dPFX.gl_get(sTemp, "préfixe élidé inconnu")] };
                        aLabel: [_dPFX.gl_get(sTemp, "préfixe élidé inconnu")]
                    };
                    break;
                case 'FOLDER':
                    return {
                        sType: oToken.sType,
                    return { sType: oToken.sType, sValue: oToken.sValue.slice(0,40)+"…", aLabel: ["dossier"] };
                        sValue: oToken.sValue.slice(0, 40) + "…",
                        aLabel: ["dossier"]
                    };
                    break;
                case 'WORD': 
                case 'WORD':
                    if (oToken.sValue.gl_count("-") > 4) {
                        return {
                            sType: "COMPLEX",
                            sValue: oToken.sValue,
                        return { sType: "COMPLEX", sValue: oToken.sValue, aLabel: ["élément complexe indéterminé"] };
                    }
                    else if (this.oDict.isValidToken(oToken.sValue)) {
                            aLabel: ["élément complexe indéterminé"]
                        };
                    } else if (this.oDict.isValidToken(oToken.sValue)) {
                        let lMorph = this.oDict.getMorph(oToken.sValue);
                        let aElem = [];
                        for (let s of lMorph){
                            if (s.includes(":"))  aElem.push( this._formatTags(s) );
                        for (let s of lMorph) {
                            if (s.includes(":")) aElem.push(this._formatTags(s));
                        }
                        return {
                            sType: oToken.sType,
                        return { sType: oToken.sType, sValue: oToken.sValue, aLabel: aElem};
                    }
                    else if (m = this._zCompoundWord.exec(oToken.sValue)) {
                            sValue: oToken.sValue,
                            aLabel: aElem
                        };
                    } else if (m = this._zCompoundWord.exec(oToken.sValue)) {
                        // mots composés
                        let lMorph = this.oDict.getMorph(m[1]);
                        let aElem = [];
                        for (let s of lMorph){
                            if (s.includes(":"))  aElem.push( this._formatTags(s) );
                        for (let s of lMorph) {
                            if (s.includes(":")) aElem.push(this._formatTags(s));
                        }
                        aElem.push("-" + m[2] + ": " + this._formatSuffix(m[2].toLowerCase()));
                        return {
                            sType: oToken.sType,
                        return { sType: oToken.sType, sValue: oToken.sValue, aLabel: aElem };
                    }
                    else {
                        return { sType: "UNKNOWN", sValue: oToken.sValue, aLabel: ["inconnu du dictionnaire"] };
                            sValue: oToken.sValue,
                            aLabel: aElem
                        };
                    } else {
                        return {
                            sType: "UNKNOWN",
                            sValue: oToken.sValue,
                            aLabel: ["inconnu du dictionnaire"]
                        };
                    }
                    break;
            }
        }
        catch (e) {
        } catch (e) {
            helpers.logerror(e);
        }
        return null;
    }

    _formatTags (sTags) {
        let sRes = "";
︙
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

338
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
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484








+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+












-
+

-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+




        if (!sRes) {
            sRes = "#Erreur. Étiquette inconnue : [" + sTags + "]";
            helpers.echo(sRes);
            return sRes;
        }
        return sRes.gl_trimRight(",");
    }

    _formatTagsLoc (sTags) {
        let sRes = "";
        let oTagsVerb = this._zLocTag.exec(sTags);
        sTags = oTagsVerb[1]+oTagsVerb[3];
        let m;
        while ((m = this._zTag.exec(sTags)) !== null) {
            sRes += _dLocTAGS.get(m[0]);
            if (m[0] == ':LV' && oTagsVerb[2]){
                oTagsVerb[2].split(/(?!$)/u).forEach(function(sKey) {
                    sRes += _dLocVERB.get(sKey);
                });
            }
            if (sRes.length > 100) {
                break;
            }
        }
        if (!sRes) {
            sRes = "#Erreur. Étiquette inconnue : [" + sTags + "]";
            helpers.echo(sRes);
            return sRes;
        }
        return sRes.gl_trimRight(",");
    }

    _formatSuffix (s) {
        if (s.startsWith("t-")) {
            return "“t” euphonique +" + _dAD.get(s.slice(2));
        }
        if (!s.includes("-")) {
            return _dAD.get(s.replace("’", "'"));
        }
        if (s.endsWith("ous")) {
            s += '2';
        }
        let nPos = s.indexOf("-");
        return _dAD.get(s.slice(0, nPos)) + " +" + _dAD.get(s.slice(nPos+1));
        return _dAD.get(s.slice(0, nPos)) + " +" + _dAD.get(s.slice(nPos + 1));
    }
}



    getListOfTokens (sText, bInfo=true) {
        let aElem = [];
        if (sText !== "") {
            for (let oToken of this.oTokenizer.genTokens(sText)) {
                if (bInfo) {
                    let aRes = this.getInfoForToken(oToken);
                    if (aRes) {
                        aElem.push(aRes);
                    }
                } else if (oToken.sType !== "SPACE") {
                    aElem.push(oToken);
                }
            }
        }
        return aElem;
    }

    generateInfoForTokenList (lToken) {
        let aElem = [];
        for (let oToken of lToken) {
            let aRes = this.getInfoForToken(oToken);
            if (aRes) {
                aElem.push(aRes);
            }
        }
        return aElem;
    }

    getListOfTokensReduc (sText, bInfo=true) {
        let aTokenList = this.getListOfTokens(sText.replace("'", "’").trim(), false);
        let iKey = 0;
        let aElem = [];
        do {
            let oToken = aTokenList[iKey];
            let sMorphLoc = '';
            let aTokenTempList = [oToken];
            if (oToken.sType == "WORD" || oToken.sType == "ELPFX"){
                let iKeyTree = iKey + 1;
                let oLocNode = this.oLocGraph[oToken.sValue.toLowerCase()];
                while (oLocNode) {
                    let oTokenNext = aTokenList[iKeyTree];
                    iKeyTree++;
                    if (oTokenNext) {
                        oLocNode = oLocNode[oTokenNext.sValue.toLowerCase()];
                    }
                    if (oLocNode && iKeyTree <= aTokenList.length) {
                        sMorphLoc = oLocNode[":"];
                        aTokenTempList.push(oTokenNext);
                    } else {
                        break;
                    }
                }
            }

            if (sMorphLoc) {
                let sValue = '';
                for (let oTokenWord of aTokenTempList) {
                    sValue += oTokenWord.sValue+' ';
                }
                let oTokenLocution = {
                    'nStart': aTokenTempList[0].nStart,
                    'nEnd': aTokenTempList[aTokenTempList.length-1].nEnd,
                    'sType': "LOC",
                    'sValue': sValue.replace('’ ','’').trim(),
                    'aSubToken': aTokenTempList
                };
                if (bInfo) {
                    let aFormatedTag = [];
                    for (let sTagLoc of sMorphLoc.split('|') ){
                        aFormatedTag.push( this._formatTagsLoc(sTagLoc) );
                    }
                    aElem.push({
                        sType: oTokenLocution.sType,
                        sValue: oTokenLocution.sValue,
                        aLabel: aFormatedTag,
                        aSubElem: this.generateInfoForTokenList(aTokenTempList)
                    });
                } else {
                    aElem.push(oTokenLocution);
                }
                iKey = iKey + aTokenTempList.length;
            } else {
                if (bInfo) {
                    let aRes = this.getInfoForToken(oToken);
                    if (aRes) {
                        aElem.push(aRes);
                    }
                } else {
                    aElem.push(oToken);
                }
                iKey++;
            }
        } while (iKey < aTokenList.length);
        return aElem;
    }
}


if (typeof(exports) !== 'undefined') {
    exports.Lexicographe = Lexicographe;
}

Modified gc_lang/fr/modules-js/locutions_data.json from [12115cc355] to [18410d013e]. 

1



1

-
+

{"à": {"califourchon": {}, "cœur": {"joie": {}, "ouvert": {}}, "corps": {"perdu": {}}, "perte": {"de": {"vue": {}}}, "visage": {"découvert": {}}}, "par": {"ailleurs": {}, "acquit": {"de": {"conscience": {}}}}}
{"à": {"califourchon": {":": ":Ŵ"}, "contrecœur": {":": ":Ŵ"}, "cœur": {"joie": {":": ":Ŵ"}, "ouvert": {":": ":Ŵ"}}, "corps": {"perdu": {":": ":Ŵ"}}, "bâtons": {"rompus": {":": ":Ŵ"}}, "perte": {"de": {"vue": {":": ":Ŵ"}}}, "visage": {"découvert": {":": ":Ŵ"}}, "vue": {"d’": {"œil": {":": ":Ŵ"}}}, "l’": {"aveuglette": {":": ":Ŵ"}}}, "ad": {"hominem": {":": ":Ŵ"}}, "en": {"tout": {"et": {"pour": {"tout": {":": ":Ŵ"}}}}}, "par": {"ailleurs": {":": ":Ŵ"}, "acquit": {"de": {"conscience": {":": ":Ŵ"}}}}}

Modified gc_lang/fr/modules/locutions_data.py from [4e9754ba4b] to [02f99ec70a]. 

1
2
3


1
2

3



-
+

# generated data (do not edit)

dLocutions = {'à': {'califourchon': {}, 'cœur': {'joie': {}, 'ouvert': {}}, 'corps': {'perdu': {}}, 'perte': {'de': {'vue': {}}}, 'visage': {'découvert': {}}}, 'par': {'ailleurs': {}, 'acquit': {'de': {'conscience': {}}}}}
dLocutions = {'à': {'califourchon': {':': ':Ŵ'}, 'contrecœur': {':': ':Ŵ'}, 'cœur': {'joie': {':': ':Ŵ'}, 'ouvert': {':': ':Ŵ'}}, 'corps': {'perdu': {':': ':Ŵ'}}, 'bâtons': {'rompus': {':': ':Ŵ'}}, 'perte': {'de': {'vue': {':': ':Ŵ'}}}, 'visage': {'découvert': {':': ':Ŵ'}}, 'vue': {'d’': {'œil': {':': ':Ŵ'}}}, 'l’': {'aveuglette': {':': ':Ŵ'}}}, 'ad': {'hominem': {':': ':Ŵ'}}, 'en': {'tout': {'et': {'pour': {'tout': {':': ':Ŵ'}}}}}, 'par': {'ailleurs': {':': ':Ŵ'}, 'acquit': {'de': {'conscience': {':': ':Ŵ'}}}}}

Modified gc_lang/fr/webext/content_scripts/panel_lxg.css from [58f7a11f55] to [06d2a8ca5d]. 

1
2
3
4
5
6
7
8
9
10
11
12
13


14
15
16
17
18
19
20

1
2
3
4
5
6
7
8
9
10
11


12
13
14
15
16
17
18
19
20












-
-
+
+








/*
    Lexicographer
*/
#grammalecte_lxg_panel_content {
    padding: 5px;
    font-size: 13px;
}

.grammalecte_lxg_list_of_tokens {
    margin: 5px 0 10px 0;
    padding: 10px;
    background-color: hsla(0, 0%, 96%, 1);
    border-radius: 2px;
    background-color: hsla(0, 0%, 95%, 1);
    border-radius: 5px;
}

.grammalecte_lxg_list_num {
    float: right;
    margin: -12px 0 5px 10px;
    padding: 5px 10px;
    font-weight: bold;
︙
31
32
33
34
35
36
37











38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54

55
56
57
58



59
60
61
62
63
64
65

31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
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








+
+
+
+
+
+
+
+
+
+
+
















-
+




+
+
+








    border-radius: 5px;
    text-align: center;
    font-size: 20px;
}

.grammalecte_lxg_token_block  {
    margin: 4px 0;
}
.grammalecte_lxg_token_subblock {
    margin: 2px 0 2px 20px;
    padding: 5px;
    border-left: 4px solid hsl(150, 30%, 70%);
    background-color: hsl(210, 10%, 90%);
    border-radius: 2px;
}
.grammalecte_lxg_token_descr {
    margin: 1px;
    padding: 1px;
}
.grammalecte_lxg_token {
    display: inline-block;
    background-color: hsl(150, 0%, 50%);
    color: hsl(0, 0%, 96%);
    padding: 2px 5px;
    border-radius: 2px;
    text-decoration: none;
    font-weight: bold;
}
.grammalecte_lxg_token_colon {
    display: inline-block;
    padding: 2px 5px;
    color: hsl(0, 0%, 50%);
}
.grammalecte_lxg_morph_list {
    padding: 2px 0 10px 20px;
    padding: 2px 0 2px 20px;
}
.grammalecte_lxg_morph_elem {
    color: hsl(0, 0%, 0%);
}
.grammalecte_lxg_token_LOC {
    background-color: hsla(150, 50%, 30%, 1);
}
.grammalecte_lxg_token_WORD {
    background-color: hsla(150, 50%, 50%, 1);
}
.grammalecte_lxg_token_ELPFX {
    background-color: hsla(150, 30%, 50%, 1);
}
.grammalecte_lxg_token_UNKNOWN {
︙

Modified gc_lang/fr/webext/content_scripts/panel_lxg.js from [d3537b8dce] to [524fe4ff4b].

︙
25
26
27
28
29
30
31
32

33
34

35
36
37
38
39




40
41

42


































43
44
45
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

25
26
27
28
29
30
31

32
33

34
35




36
37
38
39
40

41
42
43
44
45
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








-
+

-
+

-
-
-
-
+
+
+
+

-
+

+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+






-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-







    }

    addMessage (sMessage) {
        let xNode = oGrammalecte.createNode("div", {className: "grammalecte_panel_message", textContent: sMessage});
        this._xContentNode.appendChild(xNode);
    }

    addListOfTokens (lTokens) {
    addListOfTokens (lToken) {
        try {
            if (lTokens) {
            if (lToken) {
                this._nCount += 1;
                let xNodeDiv = oGrammalecte.createNode("div", {className: "grammalecte_lxg_list_of_tokens"});
                xNodeDiv.appendChild(oGrammalecte.createNode("div", {className: "grammalecte_lxg_list_num", textContent: this._nCount}));
                for (let oToken of lTokens) {
                    xNodeDiv.appendChild(this._createTokenNode(oToken));
                let xTokenList = oGrammalecte.createNode("div", {className: "grammalecte_lxg_list_of_tokens"});
                xTokenList.appendChild(oGrammalecte.createNode("div", {className: "grammalecte_lxg_list_num", textContent: this._nCount}));
                for (let oToken of lToken) {
                    xTokenList.appendChild(this._createTokenBlock(oToken));
                }
                this._xContentNode.appendChild(xNodeDiv);
                this._xContentNode.appendChild(xTokenList);
            }
        }
        catch (e) {
            showError(e);
        }
    }

    _createTokenBlock (oToken) {
        let xTokenBlock = oGrammalecte.createNode("div", {className: "grammalecte_lxg_token_block"});
        xTokenBlock.appendChild(this._createTokenDescr(oToken));
        if (oToken.aSubElem) {
            let xSubBlock = oGrammalecte.createNode("div", {className: "grammalecte_lxg_token_subblock"});
            for (let oSubElem of oToken.aSubElem) {
                xSubBlock.appendChild(this._createTokenDescr(oSubElem));
            }
            xTokenBlock.appendChild(xSubBlock);
        }
        return xTokenBlock;
    }

    _createTokenDescr (oToken) {
        try {
            let xTokenDescr = oGrammalecte.createNode("div", {className: "grammalecte_lxg_token_descr"});
            xTokenDescr.appendChild(oGrammalecte.createNode("div", {className: "grammalecte_lxg_token grammalecte_lxg_token_" + oToken.sType, textContent: oToken.sValue}));
            xTokenDescr.appendChild(oGrammalecte.createNode("div", {className: "grammalecte_lxg_token_colon", textContent: ":"}));
            if (oToken.aLabel.length === 1) {
                xTokenDescr.appendChild(document.createTextNode(oToken.aLabel[0]));
            } else {
                let xMorphList = oGrammalecte.createNode("div", {className: "grammalecte_lxg_morph_list"});
                for (let sLabel of oToken.aLabel) {
                    xMorphList.appendChild(oGrammalecte.createNode("div", {className: "grammalecte_lxg_morph_elem", textContent: "• " + sLabel}));
                }
                xTokenDescr.appendChild(xMorphList);
            }
            return xTokenDescr;
        }
        catch (e) {
            showError(e);
        }
    }

    _createTokenNode (oToken) {
        let xTokenNode = oGrammalecte.createNode("div", {className: "grammalecte_lxg_token_block"});
        xTokenNode.appendChild(oGrammalecte.createNode("div", {className: "grammalecte_lxg_token grammalecte_lxg_token_" + oToken.sType, textContent: oToken.sValue}));
        xTokenNode.appendChild(oGrammalecte.createNode("div", {className: "grammalecte_lxg_token_colon", textContent: ":"}));
        if (oToken.aLabel.length === 1) {
            xTokenNode.appendChild(document.createTextNode(oToken.aLabel[0]));
        } else {
            let xTokenList = oGrammalecte.createNode("div", {className: "grammalecte_lxg_morph_list"});
            for (let sLabel of oToken.aLabel) {
                xTokenList.appendChild(oGrammalecte.createNode("div", {className: "grammalecte_lxg_morph_elem", textContent: "• " + sLabel}));
            }
            xTokenNode.appendChild(xTokenList);
        }
        return xTokenNode;
    }

    setHidden (sClass, bHidden) {
        for (let xNode of document.getElementsByClassName(sClass)) {
            xNode.hidden = bHidden;
        }
    }
}

Modified gc_lang/fr/webext/gce_worker.js from [ad4b1695da] to [ac6f473dd4].

︙
136
137
138
139
140
141
142

143
144
145
146
147
148
149

136
137
138
139
140
141
142
143
144
145
146
147
148
149
150








+









let bInitDone = false;

let oDict = null;
let oTokenizer = null;
let oLxg = null;
let oTest = null;
let oLocution = null;


/*
    Technical note:
    This worker don’t work as a PromiseWorker (which returns a promise),  so when we send request
    to this worker, we can’t wait the return of the answer just after the request made.
    The answer is received by the background in another function (onmessage).
︙
158
159
160
161
162
163
164




165

166
167
168
169
170
171
172
173
174
175
176

159
160
161
162
163
164
165
166
167
168
169

170
171
172
173

174
175
176
177
178
179
180








+
+
+
+
-
+



-








            conj.init(helpers.loadFile(sExtensionPath + "/grammalecte/fr/conj_data.json"));
            phonet.init(helpers.loadFile(sExtensionPath + "/grammalecte/fr/phonet_data.json"));
            mfsp.init(helpers.loadFile(sExtensionPath + "/grammalecte/fr/mfsp_data.json"));
            //console.log("[Worker] Modules have been initialized…");
            gc_engine.load(sContext, sExtensionPath+"grammalecte/_dictionaries");
            oDict = gc_engine.getDictionary();
            oTest = new TestGrammarChecking(gc_engine, sExtensionPath+"/grammalecte/fr/tests_data.json");
            oTokenizer = new Tokenizer("fr");

            oLocution =  helpers.loadFile(sExtensionPath + "/grammalecte/fr/locutions_data.json");

            oLxg = new Lexicographe(oDict);
            oLxg = new Lexicographe(oDict, oTokenizer, oLocution);
            if (dOptions !== null) {
                gc_engine.setOptions(dOptions);
            }
            oTokenizer = new Tokenizer("fr");
            //tests();
            bInitDone = true;
        } else {
            console.log("[Worker] Already initialized…")
        }
        // we always retrieve options from the gc_engine, for setOptions filters obsolete options
        postMessage(createResponse("init", gc_engine.getOptions(), dInfo, true));
︙
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309

310
311
312
313
314
315
316
317
318

298
299
300
301
302
303
304









305
306
307
308
309
310
311
312
313
314








-
-
-
-
-
-
-
-
-
+











// Lexicographer

function getListOfTokens (sText, dInfo={}) {
    try {
        for (let sParagraph of text.getParagraph(sText)) {
            if (sParagraph.trim() !== "") {
                let aElem = [];
                let aRes = null;
                for (let oToken of oTokenizer.genTokens(sParagraph)) {
                    aRes = oLxg.getInfoForToken(oToken);
                    if (aRes) {
                        aElem.push(aRes);
                    }
                }
                postMessage(createResponse("getListOfTokens", aElem, dInfo, false));
                postMessage(createResponse("getListOfTokens", oLxg.getListOfTokensReduc(sParagraph, true), dInfo, false));
            }
        }
        postMessage(createResponse("getListOfTokens", null, dInfo, true));
    }
    catch (e) {
        helpers.logerror(e);
        postMessage(createResponse("getListOfTokens", createErrorResult(e, "no tokens"), dInfo, true, true));
    }
}

Fossil 2.24 [8be0372c10] 2024-04-23 13:25:26
This page was generated in about 0.057s