Grammalecte  Check-in [1ab530ddfa]

Overview
Comment:merge trunk
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | multid
Files: files | file ages | folders
SHA3-256: 1ab530ddfac19eb0c9aecd0dda29161575148d965fdd4bb0b36fe7395bb31777
User & Date: olr on 2018-02-25 15:39:48
Other Links: branch diff | manifest | tags
Context
2018-02-25
21:55
[lo] update: lexicon editor check-in: 89b74dbf1b user: olr tags: lo, multid
15:39
merge trunk check-in: 1ab530ddfa user: olr tags: multid
08:54
[fr][bug] ocr: problème de casse pour la suggestion <Il/il> check-in: f9c4613c61 user: olr tags: fr, trunk
08:47
[lo] lexicon editor check-in: 5a1baacbbb user: olr tags: lo, multid, new_feature
Changes

Modified gc_lang/fr/oxt/Lexicographer/Enumerator.py from [753041f6b5] to [8bc3897863].

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
..
52
53
54
55
56
57
58

59
60
61
62
63
64
65
...
116
117
118
119
120
121
122
123
124
125
126
127
128
129

130
131
132
133
134
135
136
...
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
...
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
...
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
# Dictionary Options
# by Olivier R.
# License: MPL 2

import unohelper
import uno
import traceback

import helpers
import enum_strings
import grammalecte.graphspell as sc

from com.sun.star.task import XJobExecutor
from com.sun.star.awt import XActionListener
from com.sun.star.beans import PropertyValue


def hexToRBG (sHexa):
    r = int(sHexa[:2], 16)
    g = int(sHexa[2:4], 16)
    b = int(sHexa[4:], 16)
    return (r & 255) << 16 | (g & 255) << 8 | (b & 255)
................................................................................
        self.ctx = ctx
        self.xSvMgr = self.ctx.ServiceManager
        self.xDesktop = self.xSvMgr.createInstanceWithContext("com.sun.star.frame.Desktop", self.ctx)
        self.xDocument = self.xDesktop.getCurrentComponent()
        self.xContainer = None
        self.xDialog = None
        self.oSpellChecker = None


    def _addWidget (self, name, wtype, x, y, w, h, **kwargs):
        xWidget = self.xDialog.createInstance('com.sun.star.awt.UnoControl%sModel' % wtype)
        xWidget.Name = name
        xWidget.PositionX = x
        xWidget.PositionY = y
        xWidget.Width = w
................................................................................
        nY2 = nY1 + 225

        nWidth = self.xDialog.Width - 20
        nHeight = 10

        # List
        self._addWidget("list_section", 'FixedLine', nX, nY1, nWidth, nHeight, Label = self.dUI.get("list_section", "#err"), FontDescriptor = xFDTitle)
        self._addWidget('count_button', 'Button', nX, nY1+12, 70, 10, Label = self.dUI.get('count_button', "#err"))
        self._addWidget('count2_button', 'Button', nX+75, nY1+12, 70, 10, Label = self.dUI.get('count2_button', "#err"))
        self._addWidget('unknown_button', 'Button', nX+150, nY1+12, 70, 10, Label = self.dUI.get('unknown_button', "#err"))
        self.xGridModel = self._addGrid("list_grid", nX, nY1+25, nWidth, 180, [
            {"Title": self.dUI.get("words", "#err"), "ColumnWidth": 175},
            {"Title": "Occurrences", "ColumnWidth": 45}
        ])

        self._addWidget('num_of_entries', 'FixedText', nX, nY1+210, 60, nHeight, Label = self.dUI.get('num_of_entries', "#err"), Align = 2)
        self.xNumWord = self._addWidget('num_of_entries_res', 'FixedText', nX+65, nY1+210, 30, nHeight, Label = "—")
        self._addWidget('tot_of_entries', 'FixedText', nX+100, nY1+210, 60, nHeight, Label = self.dUI.get('tot_of_entries', "#err"), Align = 2)
        self.xTotWord = self._addWidget('tot_of_entries_res', 'FixedText', nX+165, nY1+210, 30, nHeight, Label = "—")
        
        # Tag
        # Note: the only way to group RadioButtons is to create them successively
................................................................................
        self.xNoAccent = self._addWidget('noaccentuation', 'RadioButton', nX+155, nY2+12, 40, nHeight, Label = self.dUI.get('noaccentuation', "#err"))

        self.xTag = self._addWidget('tag_button', 'Button', self.xDialog.Width-40, nY2+10, 30, 11, Label = self.dUI.get('tag_button', "#err"), FontDescriptor = xFDTitle, TextColor = 0x005500)
        
        # Progress bar
        self.xProgressBar = self._addWidget('progress_bar', 'ProgressBar', nX, self.xDialog.Height-25, 160, 14)
        self.xProgressBar.ProgressValueMin = 0
        self.xProgressBar.ProgressValueMax = 1 # to calculate

        # Close
        self._addWidget('close_button', 'Button', self.xDialog.Width-60, self.xDialog.Height-25, 50, 14, Label = self.dUI.get('close_button', "#err"), FontDescriptor = xFDTitle, TextColor = 0x550000)

        # container
        self.xContainer = self.xSvMgr.createInstanceWithContext('com.sun.star.awt.UnoControlDialog', self.ctx)
        self.xContainer.setModel(self.xDialog)
................................................................................
            elif xActionEvent.ActionCommand == "CountByLemma":
                self.count(self.dUI.get("lemmas", "#err"), bByLemma=True)
                self.xTag.Enabled = False
            elif xActionEvent.ActionCommand == "UnknownWords":
                self.count(self.dUI.get("unknown_words", "#err"), bOnlyUnknownWords=True)
                self.xTag.Enabled = True
            elif xActionEvent.ActionCommand == "Tag":
                nRow = self.xGridControl.getCurrentRow()
                if nRow == -1:
                    return

                sWord = self.xGridModel.GridDataModel.getCellData(0, nRow)
                if not sWord:
                    return
                sAction = ""
                if self.xUnderline.State:
                    sAction = "underline"
                elif self.xNoUnderline.State:
                    sAction = "nounderline"
                elif self.xAccent.State:
                    sAction = "accentuation"
                elif self.xNoAccent.State:
                    sAction = "noaccentuation"
                self.tagText(sWord, sAction)
            elif xActionEvent.ActionCommand == "Close":
                self.xContainer.endExecute()
        except:
            traceback.print_exc()
    
    # XJobExecutor
    def trigger (self, args):
................................................................................
            i += 1
            nTotOccur += w
        self.xProgressBar.ProgressValue = self.xProgressBar.ProgressValueMax
        self.xNumWord.Label = str(i)
        self.xTotWord.Label = nTotOccur

    @_waitPointer
    def tagText (self, sWord, sAction=""):
        if not sAction:
            return
        self.xProgressBar.ProgressValueMax = self._countParagraph()
        self.xProgressBar.ProgressValue = 0


        xCursor = self.xDocument.Text.createTextCursor()
        #helpers.xray(xCursor)
        xCursor.gotoStart(False)
        xCursor.gotoEndOfParagraph(True)
        sParagraph = xCursor.getString()
        if sWord in sParagraph:
            self._tagParagraph(sWord, xCursor, sAction)
        self.xProgressBar.ProgressValue += 1
        while xCursor.gotoNextParagraph(False):
            xCursor.gotoEndOfParagraph(True)
            sParagraph = xCursor.getString()
            if sWord in sParagraph:
                self._tagParagraph(sWord, xCursor, sAction)
            self.xProgressBar.ProgressValue += 1
        self.xProgressBar.ProgressValue = self.xProgressBar.ProgressValueMax

    def _tagParagraph (self, sWord, xCursor, sAction):
        xCursor.gotoStartOfParagraph(False)
        while xCursor.gotoNextWord(False):
            if xCursor.isStartOfWord():
                xCursor.gotoEndOfWord(True)
                if sWord == xCursor.getString():







                    if sAction == "underline":
                        xCursor.CharBackColor = hexToRBG("AA0000")
                    elif sAction == "nounderline":
                        xCursor.CharBackColor = hexToRBG("FFFFFF")
                    elif sAction == "accentuation":
                        xCursor.CharStyleName = "Emphasis"
                    elif sAction == "noaccentuation":
                        #xCursor.CharStyleName = "Default Style"     # doesn’t work
                        xCursor.setPropertyToDefault("CharStyleName")



#g_ImplementationHelper = unohelper.ImplementationHelper()
#g_ImplementationHelper.addImplementation(Enumerator, 'net.grammalecte.enumerator', ('com.sun.star.task.Job',))
|













<







 







>







 







|
|
|
|
|
|
<
>







 







|







 







|
<

>
|
<
<









|







 







|




>
>

<

<
<
<
|
<

<
<
<
|
<


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




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

15
16
17
18
19
20
21
..
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
...
116
117
118
119
120
121
122
123
124
125
126
127
128

129
130
131
132
133
134
135
136
...
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
...
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
...
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
# Enumerator of Words
# by Olivier R.
# License: MPL 2

import unohelper
import uno
import traceback

import helpers
import enum_strings
import grammalecte.graphspell as sc

from com.sun.star.task import XJobExecutor
from com.sun.star.awt import XActionListener



def hexToRBG (sHexa):
    r = int(sHexa[:2], 16)
    g = int(sHexa[2:4], 16)
    b = int(sHexa[4:], 16)
    return (r & 255) << 16 | (g & 255) << 8 | (b & 255)
................................................................................
        self.ctx = ctx
        self.xSvMgr = self.ctx.ServiceManager
        self.xDesktop = self.xSvMgr.createInstanceWithContext("com.sun.star.frame.Desktop", self.ctx)
        self.xDocument = self.xDesktop.getCurrentComponent()
        self.xContainer = None
        self.xDialog = None
        self.oSpellChecker = None
        self.oTokenizer = None

    def _addWidget (self, name, wtype, x, y, w, h, **kwargs):
        xWidget = self.xDialog.createInstance('com.sun.star.awt.UnoControl%sModel' % wtype)
        xWidget.Name = name
        xWidget.PositionX = x
        xWidget.PositionY = y
        xWidget.Width = w
................................................................................
        nY2 = nY1 + 225

        nWidth = self.xDialog.Width - 20
        nHeight = 10

        # List
        self._addWidget("list_section", 'FixedLine', nX, nY1, nWidth, nHeight, Label = self.dUI.get("list_section", "#err"), FontDescriptor = xFDTitle)
        self._addWidget('count_button', 'Button', nX, nY1+12, 70, 11, Label = self.dUI.get('count_button', "#err"))
        self._addWidget('count2_button', 'Button', nX+75, nY1+12, 70, 11, Label = self.dUI.get('count2_button', "#err"))
        self._addWidget('unknown_button', 'Button', nX+150, nY1+12, 70, 11, Label = self.dUI.get('unknown_button', "#err"))
        self.xGridModel = self._addGrid("list_grid", nX, nY1+25, nWidth, 181, \
            [ {"Title": self.dUI.get("words", "#err"), "ColumnWidth": 175}, {"Title": "Occurrences", "ColumnWidth": 45} ], \
            SelectionModel = uno.Enum("com.sun.star.view.SelectionType", "MULTI") \

        )
        self._addWidget('num_of_entries', 'FixedText', nX, nY1+210, 60, nHeight, Label = self.dUI.get('num_of_entries', "#err"), Align = 2)
        self.xNumWord = self._addWidget('num_of_entries_res', 'FixedText', nX+65, nY1+210, 30, nHeight, Label = "—")
        self._addWidget('tot_of_entries', 'FixedText', nX+100, nY1+210, 60, nHeight, Label = self.dUI.get('tot_of_entries', "#err"), Align = 2)
        self.xTotWord = self._addWidget('tot_of_entries_res', 'FixedText', nX+165, nY1+210, 30, nHeight, Label = "—")
        
        # Tag
        # Note: the only way to group RadioButtons is to create them successively
................................................................................
        self.xNoAccent = self._addWidget('noaccentuation', 'RadioButton', nX+155, nY2+12, 40, nHeight, Label = self.dUI.get('noaccentuation', "#err"))

        self.xTag = self._addWidget('tag_button', 'Button', self.xDialog.Width-40, nY2+10, 30, 11, Label = self.dUI.get('tag_button', "#err"), FontDescriptor = xFDTitle, TextColor = 0x005500)
        
        # Progress bar
        self.xProgressBar = self._addWidget('progress_bar', 'ProgressBar', nX, self.xDialog.Height-25, 160, 14)
        self.xProgressBar.ProgressValueMin = 0
        self.xProgressBar.ProgressValueMax = 1 # to calculate later

        # Close
        self._addWidget('close_button', 'Button', self.xDialog.Width-60, self.xDialog.Height-25, 50, 14, Label = self.dUI.get('close_button', "#err"), FontDescriptor = xFDTitle, TextColor = 0x550000)

        # container
        self.xContainer = self.xSvMgr.createInstanceWithContext('com.sun.star.awt.UnoControlDialog', self.ctx)
        self.xContainer.setModel(self.xDialog)
................................................................................
            elif xActionEvent.ActionCommand == "CountByLemma":
                self.count(self.dUI.get("lemmas", "#err"), bByLemma=True)
                self.xTag.Enabled = False
            elif xActionEvent.ActionCommand == "UnknownWords":
                self.count(self.dUI.get("unknown_words", "#err"), bOnlyUnknownWords=True)
                self.xTag.Enabled = True
            elif xActionEvent.ActionCommand == "Tag":
                if not self.xGridControl.hasSelectedRows():

                    return
                lRow = self.xGridControl.getSelectedRows()
                aWord = set([ self.xGridModel.GridDataModel.getCellData(0, n)  for n in lRow ])


                sAction = ""
                if self.xUnderline.State:
                    sAction = "underline"
                elif self.xNoUnderline.State:
                    sAction = "nounderline"
                elif self.xAccent.State:
                    sAction = "accentuation"
                elif self.xNoAccent.State:
                    sAction = "noaccentuation"
                self.tagText(aWord, sAction)
            elif xActionEvent.ActionCommand == "Close":
                self.xContainer.endExecute()
        except:
            traceback.print_exc()
    
    # XJobExecutor
    def trigger (self, args):
................................................................................
            i += 1
            nTotOccur += w
        self.xProgressBar.ProgressValue = self.xProgressBar.ProgressValueMax
        self.xNumWord.Label = str(i)
        self.xTotWord.Label = nTotOccur

    @_waitPointer
    def tagText (self, aWord, sAction=""):
        if not sAction:
            return
        self.xProgressBar.ProgressValueMax = self._countParagraph()
        self.xProgressBar.ProgressValue = 0
        if not self.oTokenizer:
            self.oTokenizer = self.oSpellChecker.getTokenizer()
        xCursor = self.xDocument.Text.createTextCursor()

        xCursor.gotoStart(False)



        self._tagParagraph(xCursor, aWord, sAction)

        while xCursor.gotoNextParagraph(False):



            self._tagParagraph(xCursor, aWord, sAction)

        self.xProgressBar.ProgressValue = self.xProgressBar.ProgressValueMax

    def _tagParagraph (self, xCursor, aWord, sAction):



        xCursor.gotoEndOfParagraph(True)
        sParagraph = xCursor.getString()
        xCursor.gotoStartOfParagraph(False)
        nPos = 0
        for dToken in self.oTokenizer.genTokens(sParagraph):
            if dToken["sValue"] in aWord:
                xCursor.goRight(dToken["nStart"]-nPos, False) # start of token
                nPos = dToken["nEnd"]
                xCursor.goRight(nPos-dToken["nStart"], True) # end of token
                if sAction == "underline":
                    xCursor.CharBackColor = hexToRBG("AA0000")
                elif sAction == "nounderline":
                    xCursor.CharBackColor = hexToRBG("FFFFFF")
                elif sAction == "accentuation":
                    xCursor.CharStyleName = "Emphasis"
                elif sAction == "noaccentuation":
                    #xCursor.CharStyleName = "Default Style"     # doesn’t work
                    xCursor.setPropertyToDefault("CharStyleName")
        self.xProgressBar.ProgressValue += 1


#g_ImplementationHelper = unohelper.ImplementationHelper()
#g_ImplementationHelper.addImplementation(Enumerator, 'net.grammalecte.enumerator', ('com.sun.star.task.Job',))

Modified gc_lang/fr/oxt/Lexicographer/enum_strings.py from [fd05286777] to [4648cd7ebd].

3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
..
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
        return dStrings[sLang]
    return dStrings["fr"]

dStrings = {
    "fr": {
        "title": "Grammalecte · Recenseur de mots",
        
        "list_section": "Calcul des occurrences des mots",
        "count_button": "Compter tout",
        "count2_button": "Compter par lemme",
        "unknown_button": "Mots inconnus",
        "num_of_entries": "Nombre d’entrées :",
        "tot_of_entries": "Total des entrées :",

        "words": "Mots",
................................................................................
        "accentuation": "Accentuation",
        "noaccentuation": "Aucun",
        "tag_button": "Taguer",

        "close_button": "Fermer",
    },
    "en": {
        "title": "Grammalecte · Enumerator of Words",

        "list_section": "Words",
        "count_button": "Count all",
        "count2_button": "Count by lemma",
        "unknown_button": "Unknown words",
        "num_of_entries": "Number of entries:",
        "tot_of_entries": "Total of words:",

        "words": "Words",







|







 







|

|







3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
..
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
        return dStrings[sLang]
    return dStrings["fr"]

dStrings = {
    "fr": {
        "title": "Grammalecte · Recenseur de mots",
        
        "list_section": "Énumération des occurrences",
        "count_button": "Compter tout",
        "count2_button": "Compter par lemme",
        "unknown_button": "Mots inconnus",
        "num_of_entries": "Nombre d’entrées :",
        "tot_of_entries": "Total des entrées :",

        "words": "Mots",
................................................................................
        "accentuation": "Accentuation",
        "noaccentuation": "Aucun",
        "tag_button": "Taguer",

        "close_button": "Fermer",
    },
    "en": {
        "title": "Grammalecte · Enumerator of words",

        "list_section": "Occurrences enumeration",
        "count_button": "Count all",
        "count2_button": "Count by lemma",
        "unknown_button": "Unknown words",
        "num_of_entries": "Number of entries:",
        "tot_of_entries": "Total of words:",

        "words": "Words",

Modified gc_lang/fr/rules.grx from [29eda24584] to [4b78e905cb].

2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
    <<- \0.endswith("s") ->> Ils|ils                                                                # Erreur de numérisation ?
    <<- __else__ ->> Il|il                                                                          # Erreur de numérisation ?

TEST: __ocr__ {{Us}} arrive demain.


# il / i1 / if / 11
__[i]/ocr(ocr_il_ils3)__
    [i1][1f]s?
    <<- not \0.endswith("s") ->> Il|il                                                              # Erreur de numérisation ?
    <<- __else__ ->> Ils|ils                                                                        # Erreur de numérisation ?

TEST: __ocr__ {{i1s}} en savent beaucoup trop pour leur propre bien.


# fa / la







|
|







2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
    <<- \0.endswith("s") ->> Ils|ils                                                                # Erreur de numérisation ?
    <<- __else__ ->> Il|il                                                                          # Erreur de numérisation ?

TEST: __ocr__ {{Us}} arrive demain.


# il / i1 / if / 11
__[s]/ocr(ocr_il_ils3)__
    [iI1][1f]s?
    <<- not \0.endswith("s") ->> Il|il                                                              # Erreur de numérisation ?
    <<- __else__ ->> Ils|ils                                                                        # Erreur de numérisation ?

TEST: __ocr__ {{i1s}} en savent beaucoup trop pour leur propre bien.


# fa / la

Modified graphspell-js/spellchecker.js from [7b8a526c88] to [a4e4ee731d].

66
67
68
69
70
71
72







73
74
75
76
77
78
79
    loadTokenizer () {
        if (typeof(tokenizer) !== 'undefined') {
            this.oTokenizer = new tokenizer.Tokenizer(this.sLangCode);
        } else {
            this.oTokenizer = new Tokenizer(this.sLangCode);
        }
    }








    setMainDictionary (dictionary) {
        // returns true if the dictionary is loaded
        this.oMainDic = this._loadDictionary(dictionary);
        return Boolean(this.oMainDic);
    }








>
>
>
>
>
>
>







66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
    loadTokenizer () {
        if (typeof(tokenizer) !== 'undefined') {
            this.oTokenizer = new tokenizer.Tokenizer(this.sLangCode);
        } else {
            this.oTokenizer = new Tokenizer(this.sLangCode);
        }
    }

    getTokenizer () {
        if (!this.oTokenizer) {
            this.loadTokenizer();
        }
        return this.oTokenizer;
    }

    setMainDictionary (dictionary) {
        // returns true if the dictionary is loaded
        this.oMainDic = this._loadDictionary(dictionary);
        return Boolean(this.oMainDic);
    }

Modified graphspell/spellchecker.py from [dbd02131cc] to [4787045da6].

44
45
46
47
48
49
50





51
52
53
54
55
56
57
            print("Error: <" + sfDictionary + "> not loaded.")
            traceback.print_exc()
            return None

    def loadTokenizer (self):
        self.oTokenizer = tokenizer.Tokenizer(self.sLangCode)






    def setMainDictionary (self, sfDictionary):
        "returns True if the dictionary is loaded"
        self.oMainDic = self._loadDictionary(sfDictionary)
        return bool(self.oMainDic)
            
    def setExtendedDictionary (self, sfDictionary):
        "returns True if the dictionary is loaded"







>
>
>
>
>







44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
            print("Error: <" + sfDictionary + "> not loaded.")
            traceback.print_exc()
            return None

    def loadTokenizer (self):
        self.oTokenizer = tokenizer.Tokenizer(self.sLangCode)

    def getTokenizer (self):
        if not self.oTokenizer:
            self.loadTokenizer()
        return self.oTokenizer

    def setMainDictionary (self, sfDictionary):
        "returns True if the dictionary is loaded"
        self.oMainDic = self._loadDictionary(sfDictionary)
        return bool(self.oMainDic)
            
    def setExtendedDictionary (self, sfDictionary):
        "returns True if the dictionary is loaded"