Grammalecte  Check-in [08e1343285]

Overview
Comment:[graphspell] token valid if begins with a digit or if contains a <·>
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | trunk | graphspell
Files: files | file ages | folders
SHA3-256: 08e1343285a4f58413452087054c8ce3998e5ac741a0a48674568abf57ebc5cb
User & Date: olr on 2018-04-20 06:32:06
Other Links: manifest | tags
Context
2018-04-20
10:50
[graphspell][py][bug] wrong variable name check-in: b0efed0687 user: olr tags: trunk, graphspell
06:32
[graphspell] token valid if begins with a digit or if contains a <·> check-in: 08e1343285 user: olr tags: trunk, graphspell
2018-04-19
11:01
[fr][bug] indentation -> espaces check-in: cee7f78a8e user: olr tags: trunk, fr
Changes

Modified graphspell-js/ibdawg.js from [1da88bd86f] to [81f8cf0a21].

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
        }
        if (sToken.includes("-")) {
            if (sToken.gl_count("-") > 4) {
                return true;
            }
            return sToken.split("-").every(sWord  =>  this.isValid(sWord)); 
        }



        return false;
    }

    isValid (sWord) {
        // checks if sWord is valid (different casing tested if the first letter is a capital)
        if (!sWord) {
            return null;
        }
        if (sWord.includes("’")) { // ugly hack
            sWord = sWord.replace("’", "'");
        }
        if (this.lookup(sWord)) {
            return true;
        }
        if (sWord.gl_isDigit()) {
            return true;
        }
        if (sWord.charAt(0).gl_isUpperCase()) {
            if (sWord.length > 1) {
                if (sWord.gl_isTitle()) {
                    return !!this.lookup(sWord.toLowerCase());
                }
                if (sWord.gl_isUpperCase()) {
                    if (this.bOptNumSigle) {
                        return true;
                    }
                    return !!(this.lookup(sWord.toLowerCase()) || this.lookup(sWord.gl_toCapitalize()));
                }
                return !!this.lookup(sWord.slice(0, 1).toLowerCase() + sWord.slice(1));
            } else {
                return !!this.lookup(sWord.toLowerCase());
            }



        }
        return false;
    }

    _convBytesToInteger (aBytes) {
        // Byte order = Big Endian (bigger first)
        let nVal = 0;







>
>
>














<
<
<















>
>
>







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
        }
        if (sToken.includes("-")) {
            if (sToken.gl_count("-") > 4) {
                return true;
            }
            return sToken.split("-").every(sWord  =>  this.isValid(sWord)); 
        }
        if (sToken.includes("·")) {
            return true;
        }
        return false;
    }

    isValid (sWord) {
        // checks if sWord is valid (different casing tested if the first letter is a capital)
        if (!sWord) {
            return null;
        }
        if (sWord.includes("’")) { // ugly hack
            sWord = sWord.replace("’", "'");
        }
        if (this.lookup(sWord)) {
            return true;
        }



        if (sWord.charAt(0).gl_isUpperCase()) {
            if (sWord.length > 1) {
                if (sWord.gl_isTitle()) {
                    return !!this.lookup(sWord.toLowerCase());
                }
                if (sWord.gl_isUpperCase()) {
                    if (this.bOptNumSigle) {
                        return true;
                    }
                    return !!(this.lookup(sWord.toLowerCase()) || this.lookup(sWord.gl_toCapitalize()));
                }
                return !!this.lookup(sWord.slice(0, 1).toLowerCase() + sWord.slice(1));
            } else {
                return !!this.lookup(sWord.toLowerCase());
            }
        }
        if (sWord.slice(0,1).gl_isDigit()) {
            return true;
        }
        return false;
    }

    _convBytesToInteger (aBytes) {
        // Byte order = Big Endian (bigger first)
        let nVal = 0;

Modified graphspell/ibdawg.py from [81e3b2e579] to [61d7128b52].

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
        sToken = cp.spellingNormalization(sToken)
        if self.isValid(sToken):
            return True
        if "-" in sToken:
            if sToken.count("-") > 4:
                return True
            return all(self.isValid(sWord)  for sWord in sToken.split("-"))


        return False

    def isValid (self, sWord):
        "checks if <sWord> is valid (different casing tested if the first letter is a capital)"
        if not sWord:
            return None
        if "’" in sWord: # ugly hack
            sWord = sWord.replace("’", "'")
        if self.lookup(sWord):
            return True
        if sWord.isdigit():
            return True
        if sWord[0:1].isupper():
            if len(sWord) > 1:
                if sWord.istitle():
                    return self.lookup(sWord.lower())
                if sWord.isupper():
                    if self.bOptNumSigle:
                        return True
                    return self.lookup(sWord.lower()) or self.lookup(sWord.capitalize())
                return self.lookup(sWord[:1].lower() + sWord[1:])
            else:
                return self.lookup(sWord.lower())


        return False

    def lookup (self, sWord):
        "returns True if <sWord> in dictionary (strict verification)"
        iAddr = 0
        for c in sWord:
            if c not in self.dChar:







>
>










<
<











>
>







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
        sToken = cp.spellingNormalization(sToken)
        if self.isValid(sToken):
            return True
        if "-" in sToken:
            if sToken.count("-") > 4:
                return True
            return all(self.isValid(sWord)  for sWord in sToken.split("-"))
        if "·" in sWord:
            return True
        return False

    def isValid (self, sWord):
        "checks if <sWord> is valid (different casing tested if the first letter is a capital)"
        if not sWord:
            return None
        if "’" in sWord: # ugly hack
            sWord = sWord.replace("’", "'")
        if self.lookup(sWord):
            return True


        if sWord[0:1].isupper():
            if len(sWord) > 1:
                if sWord.istitle():
                    return self.lookup(sWord.lower())
                if sWord.isupper():
                    if self.bOptNumSigle:
                        return True
                    return self.lookup(sWord.lower()) or self.lookup(sWord.capitalize())
                return self.lookup(sWord[:1].lower() + sWord[1:])
            else:
                return self.lookup(sWord.lower())
        if sWord[0:1].isdigit():
            return True
        return False

    def lookup (self, sWord):
        "returns True if <sWord> in dictionary (strict verification)"
        iAddr = 0
        for c in sWord:
            if c not in self.dChar: