Grammalecte  Check-in [496180aadf]

Overview
Comment:[graphspell] char_player: don’t remove double <e> in simplifyWord
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | trunk | graphspell
Files: files | file ages | folders
SHA3-256: 496180aadf8ac29acfcca49aec48603edaf4ec26b5fd868022807571bdc14a0b
User & Date: olr on 2018-06-09 13:30:24
Other Links: manifest | tags
Context
2018-06-10
09:49
[fx] gc panel ui, tooltip: action block under suggestions block check-in: c6a845b16f user: olr tags: fx, trunk
2018-06-09
13:30
[graphspell] char_player: don’t remove double <e> in simplifyWord check-in: 496180aadf user: olr tags: graphspell, trunk
13:25
[graphspell][js] char_player: simplifyWord -> code clarification check-in: 0d6362e947 user: olr tags: graphspell, trunk
Changes

Modified graphspell-js/char_player.js from [ee4109e576] to [626d7d161b].

28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
        ['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 = "";
        let i = 1;
        for (let c of sWord) {
            if (c != sWord.slice(i, i+1)) {
                sNewWord += c;
            }
            i++;
        }
        return sNewWord.replace(/eau/g, "o").replace(/au/g, "o").replace(/ai/g, "e").replace(/ei/g, "e").replace(/ph/g, "f");
    },








|



|







28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
        ['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 = "";
        let i = 1;
        for (let c of sWord) {
            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, "e").replace(/ei/g, "e").replace(/ph/g, "f");
    },

Modified graphspell/char_player.py from [73eee3ee03] to [0a316c953c].

25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
})

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 != sWord[i:i+1]:
            sNewWord += c
    return sNewWord.replace("eau", "o").replace("au", "o").replace("ai", "e").replace("ei", "e").replace("ph", "f")


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







|







25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
})

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", "e").replace("ei", "e").replace("ph", "f")


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