Grammalecte  Check-in [0d2727274d]

Many hyperlinks are disabled.
Use anonymous login to enable hyperlinks.

Overview
Comment:[graphspell] ibdawg: suggestions for trailing numbers -> exponent
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | trunk | graphspell
Files: files | file ages | folders
SHA3-256:0d2727274d5b1169aa7878d97dfabc13ef7b4a96b0be2adf313bbdac50b92914
User & Date: olr 2019-03-04 09:50:09
Context
2019-03-04
14:31
[graphspell] ibdawg: better suggestions when splitting check-in: aefcee1f12 user: olr tags: graphspell, trunk
09:50
[graphspell] ibdawg: suggestions for trailing numbers -> exponent check-in: 0d2727274d user: olr tags: graphspell, trunk
09:48
[fx][bug] init: set this check-in: 7abad73bbb user: olr tags: fx, trunk
Changes

Changes to graphspell-js/char_player.js.

25
26
27
28
29
30
31
32

33
34
35
36
37
38
39
..
42
43
44
45
46
47
48












49
50
51
52
53
54
55
        ['à', 'a'],  ['é', 'e'],  ['î', 'i'],  ['ô', 'o'],  ['û', 'u'],  ['ÿ', 'i'],  ['y', 'i'],
        ['â', 'a'],  ['è', 'e'],  ['ï', 'i'],  ['ö', 'o'],  ['ù', 'u'],  ['ŷ', 'i'],
        ['ä', 'a'],  ['ê', 'e'],  ['í', 'i'],  ['ó', 'o'],  ['ü', 'u'],  ['ý', 'i'],
        ['á', 'a'],  ['ë', 'e'],  ['ì', 'i'],  ['ò', 'o'],  ['ú', 'u'],  ['ỳ', 'i'],
        ['ā', 'a'],  ['ē', 'e'],  ['ī', 'i'],  ['ō', 'o'],  ['ū', 'u'],  ['ȳ', 'i'],
        ['ç', 'c'],  ['ñ', 'n'],  ['k', 'q'],  ['w', 'v'],
        ['œ', 'oe'], ['æ', 'ae'],
        ['ſ', 's'],  ['ffi', 'ffi'],  ['ffl', 'ffl'],  ['ff', 'ff'],  ['ſt', 'ft'],  ['fi', 'fi'],  ['fl', 'fl'],  ['st', 'st']

    ]),

    simplifyWord: function (sWord) {
        // word simplication before calculating distance between words
        sWord = sWord.toLowerCase();
        sWord = [...sWord].map(c => this._xTransCharsForSimplification.gl_get(c, c)).join('');
        let sNewWord = "";
................................................................................
            if (c == 'e' || c != sWord.slice(i, i+1)) {  // exception for <e> to avoid confusion between crée / créai
                sNewWord += c;
            }
            i++;
        }
        return sNewWord.replace(/eau/g, "o").replace(/au/g, "o").replace(/ai/g, "ẽ").replace(/ei/g, "ẽ").replace(/ph/g, "f");
    },













    aVowel: new Set("aáàâäāeéèêëēiíìîïīoóòôöōuúùûüūyýỳŷÿȳœæAÁÀÂÄĀEÉÈÊËĒIÍÌÎÏĪOÓÒÔÖŌUÚÙÛÜŪYÝỲŶŸȲŒÆ"),
    aConsonant: new Set("bcçdfghjklmnñpqrstvwxzBCÇDFGHJKLMNÑPQRSTVWXZ"),
    aDouble: new Set("bcdfjklmnprstzBCDFJKLMNPRSTZ"),  // letters that may be used twice successively


    // Similar chars







|
>







 







>
>
>
>
>
>
>
>
>
>
>
>







25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
..
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
        ['à', 'a'],  ['é', 'e'],  ['î', 'i'],  ['ô', 'o'],  ['û', 'u'],  ['ÿ', 'i'],  ['y', 'i'],
        ['â', 'a'],  ['è', 'e'],  ['ï', 'i'],  ['ö', 'o'],  ['ù', 'u'],  ['ŷ', 'i'],
        ['ä', 'a'],  ['ê', 'e'],  ['í', 'i'],  ['ó', 'o'],  ['ü', 'u'],  ['ý', 'i'],
        ['á', 'a'],  ['ë', 'e'],  ['ì', 'i'],  ['ò', 'o'],  ['ú', 'u'],  ['ỳ', 'i'],
        ['ā', 'a'],  ['ē', 'e'],  ['ī', 'i'],  ['ō', 'o'],  ['ū', 'u'],  ['ȳ', 'i'],
        ['ç', 'c'],  ['ñ', 'n'],  ['k', 'q'],  ['w', 'v'],
        ['œ', 'oe'], ['æ', 'ae'],
        ['ſ', 's'],  ['ffi', 'ffi'],  ['ffl', 'ffl'],  ['ff', 'ff'],  ['ſt', 'ft'],  ['fi', 'fi'],  ['fl', 'fl'],  ['st', 'st'],
        ["⁰", "0"], ["¹", "1"], ["²", "2"], ["³", "3"], ["⁴", "4"], ["⁵", "5"], ["⁶", "6"], ["⁷", "7"], ["⁸", "8"], ["⁹", "9"]
    ]),

    simplifyWord: function (sWord) {
        // word simplication before calculating distance between words
        sWord = sWord.toLowerCase();
        sWord = [...sWord].map(c => this._xTransCharsForSimplification.gl_get(c, c)).join('');
        let sNewWord = "";
................................................................................
            if (c == 'e' || c != sWord.slice(i, i+1)) {  // exception for <e> to avoid confusion between crée / créai
                sNewWord += c;
            }
            i++;
        }
        return sNewWord.replace(/eau/g, "o").replace(/au/g, "o").replace(/ai/g, "ẽ").replace(/ei/g, "ẽ").replace(/ph/g, "f");
    },

    _xTransNumbersToExponent: new Map([
        ["0", "⁰"], ["1", "¹"], ["2", "²"], ["3", "³"], ["4", "⁴"], ["5", "⁵"], ["6", "⁶"], ["7", "⁷"], ["8", "⁸"], ["9", "⁹"]
    ]),

    numbersToExponent: function (sWord) {
        let sNewWord = "";
        for (let c of sWord) {
            sNewWord += this._xTransNumbersToExponent.gl_get(c, c);
        }
        return sNewWord;
    },

    aVowel: new Set("aáàâäāeéèêëēiíìîïīoóòôöōuúùûüūyýỳŷÿȳœæAÁÀÂÄĀEÉÈÊËĒIÍÌÎÏĪOÓÒÔÖŌUÚÙÛÜŪYÝỲŶŸȲŒÆ"),
    aConsonant: new Set("bcçdfghjklmnñpqrstvwxzBCÇDFGHJKLMNÑPQRSTVWXZ"),
    aDouble: new Set("bcdfjklmnprstzBCDFJKLMNPRSTZ"),  // letters that may be used twice successively


    // Similar chars

Changes to graphspell-js/ibdawg.js.

341
342
343
344
345
346
347






348
349
350
351
352
353
354
            return aSugg.map( (sSugg) => { return sPfx + sSugg + sSfx; } );
        }
        //console.timeEnd("Suggestions for " + sWord);
        return aSugg;
    }

    _splitSuggest (oSuggResult, sWord) {






        for (let cSplitter of "'’") {
            if (sWord.includes(cSplitter)) {
                let [sWord1, sWord2] = sWord.split(cSplitter, 2);
                if (this.isValid(sWord1) && this.isValid(sWord2)) {
                    oSuggResult.addSugg(sWord1+" "+sWord2);
                }
            }







>
>
>
>
>
>







341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
            return aSugg.map( (sSugg) => { return sPfx + sSugg + sSfx; } );
        }
        //console.timeEnd("Suggestions for " + sWord);
        return aSugg;
    }

    _splitSuggest (oSuggResult, sWord) {
        // split trailing numbers
        let m = /^([a-zA-Zà-öÀ-Ö_ø-ÿØ-ßĀ-ʯfi-st][a-zA-Zà-öÀ-Ö_ø-ÿØ-ßĀ-ʯfi-st-]+)([0-9]+)$/.exec(sWord);
        if (m) {
            oSuggResult.addSugg(m[1] + " " + char_player.numbersToExponent(m[2]));
        }
        // split at apostrophes
        for (let cSplitter of "'’") {
            if (sWord.includes(cSplitter)) {
                let [sWord1, sWord2] = sWord.split(cSplitter, 2);
                if (this.isValid(sWord1) && this.isValid(sWord2)) {
                    oSuggResult.addSugg(sWord1+" "+sWord2);
                }
            }

Changes to graphspell/char_player.py.

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
    'â': 'a',  'è': 'e',  'ï': 'i',  'ö': 'o',  'ù': 'u',  'ŷ': 'i',
    'ä': 'a',  'ê': 'e',  'í': 'i',  'ó': 'o',  'ü': 'u',  'ý': 'i',
    'á': 'a',  'ë': 'e',  'ì': 'i',  'ò': 'o',  'ú': 'u',  'ỳ': 'i',
    'ā': 'a',  'ē': 'e',  'ī': 'i',  'ō': 'o',  'ū': 'u',  'ȳ': 'i',
    'ç': 'c',  'ñ': 'n',  'k': 'q',  'w': 'v',
    'œ': 'oe',  'æ': 'ae',
    'ſ': 's',  'ffi': 'ffi',  'ffl': 'ffl',  'ff': 'ff',  'ſt': 'ft',  'fi': 'fi',  'fl': 'fl',  'st': 'st',

})

def simplifyWord (sWord):
    "word simplication before calculating distance between words"
    sWord = sWord.lower().translate(_xTransCharsForSimplification)
    sNewWord = ""
    for i, c in enumerate(sWord, 1):
        if c == 'e' or c != sWord[i:i+1]:  # exception for <e> to avoid confusion between crée / créai
            sNewWord += c
    return sNewWord.replace("eau", "o").replace("au", "o").replace("ai", "ẽ").replace("ei", "ẽ").replace("ph", "f")










aVowel = set("aáàâäāeéèêëēiíìîïīoóòôöōuúùûüūyýỳŷÿȳœæAÁÀÂÄĀEÉÈÊËĒIÍÌÎÏĪOÓÒÔÖŌUÚÙÛÜŪYÝỲŶŸȲŒÆ")
aConsonant = set("bcçdfghjklmnñpqrstvwxzBCÇDFGHJKLMNÑPQRSTVWXZ")
aDouble = set("bcdfjklmnprstzBCDFJKLMNPRSTZ")  # letters that may be used twice successively


# Similar chars







>











>
>
>
>
>
>
>
>







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
49
50
51
52
53
54
    'â': 'a',  'è': 'e',  'ï': 'i',  'ö': 'o',  'ù': 'u',  'ŷ': 'i',
    'ä': 'a',  'ê': 'e',  'í': 'i',  'ó': 'o',  'ü': 'u',  'ý': 'i',
    'á': 'a',  'ë': 'e',  'ì': 'i',  'ò': 'o',  'ú': 'u',  'ỳ': 'i',
    'ā': 'a',  'ē': 'e',  'ī': 'i',  'ō': 'o',  'ū': 'u',  'ȳ': 'i',
    'ç': 'c',  'ñ': 'n',  'k': 'q',  'w': 'v',
    'œ': 'oe',  'æ': 'ae',
    'ſ': 's',  'ffi': 'ffi',  'ffl': 'ffl',  'ff': 'ff',  'ſt': 'ft',  'fi': 'fi',  'fl': 'fl',  'st': 'st',
    "⁰": "0", "¹": "1", "²": "2", "³": "3", "⁴": "4", "⁵": "5", "⁶": "6", "⁷": "7", "⁸": "8", "⁹": "9"
})

def simplifyWord (sWord):
    "word simplication before calculating distance between words"
    sWord = sWord.lower().translate(_xTransCharsForSimplification)
    sNewWord = ""
    for i, c in enumerate(sWord, 1):
        if c == 'e' or c != sWord[i:i+1]:  # exception for <e> to avoid confusion between crée / créai
            sNewWord += c
    return sNewWord.replace("eau", "o").replace("au", "o").replace("ai", "ẽ").replace("ei", "ẽ").replace("ph", "f")


_xTransNumbersToExponent = str.maketrans({
    "0": "⁰", "1": "¹", "2": "²", "3": "³", "4": "⁴", "5": "⁵", "6": "⁶", "7": "⁷", "8": "⁸", "9": "⁹"
})

def numbersToExponent (sWord):
    return sWord.translate(_xTransNumbersToExponent)


aVowel = set("aáàâäāeéèêëēiíìîïīoóòôöōuúùûüūyýỳŷÿȳœæAÁÀÂÄĀEÉÈÊËĒIÍÌÎÏĪOÓÒÔÖŌUÚÙÛÜŪYÝỲŶŸȲŒÆ")
aConsonant = set("bcçdfghjklmnñpqrstvwxzBCÇDFGHJKLMNÑPQRSTVWXZ")
aDouble = set("bcdfjklmnprstzBCDFJKLMNPRSTZ")  # letters that may be used twice successively


# Similar chars

Changes to graphspell/ibdawg.py.

310
311
312
313
314
315
316






317
318
319
320
321
322
323
        aSugg = oSuggResult.getSuggestions(nSuggLimit)
        if sSfx or sPfx:
            # we add what we removed
            return list(map(lambda sSug: sPfx + sSug + sSfx, aSugg))
        return aSugg

    def _splitSuggest (self, oSuggResult, sWord):






        for cSplitter in "'’":
            if cSplitter in sWord:
                sWord1, sWord2 = sWord.split(cSplitter, 1)
                if self.isValid(sWord1) and self.isValid(sWord2):
                    oSuggResult.addSugg(sWord1+" "+sWord2)

    def _suggest (self, oSuggResult, sRemain, nMaxSwitch=0, nMaxDel=0, nMaxHardRepl=0, nMaxJump=0, nDist=0, nDeep=0, iAddr=0, sNewWord="", bAvoidLoop=False):







>
>
>
>
>
>







310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
        aSugg = oSuggResult.getSuggestions(nSuggLimit)
        if sSfx or sPfx:
            # we add what we removed
            return list(map(lambda sSug: sPfx + sSug + sSfx, aSugg))
        return aSugg

    def _splitSuggest (self, oSuggResult, sWord):
        # split trailing numbers
        m = re.match(r"(\D+)([0-9]+)$", sWord)
        if m:
            print("ok")
            oSuggResult.addSugg(m.group(1) + " " + cp.numbersToExponent(m.group(2)))
        # split at apostrophes
        for cSplitter in "'’":
            if cSplitter in sWord:
                sWord1, sWord2 = sWord.split(cSplitter, 1)
                if self.isValid(sWord1) and self.isValid(sWord2):
                    oSuggResult.addSugg(sWord1+" "+sWord2)

    def _suggest (self, oSuggResult, sRemain, nMaxSwitch=0, nMaxDel=0, nMaxHardRepl=0, nMaxJump=0, nDist=0, nDeep=0, iAddr=0, sNewWord="", bAvoidLoop=False):