Grammalecte  Check-in [2aa5cb1dba]

Overview
Comment:[graphspell] word simplifcation: apostrophes and hyphens
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | trunk | graphspell
Files: files | file ages | folders
SHA3-256: 2aa5cb1dba36c45055bc1085d1e2657e9e62f66ae15bd4982615b6d024e1347c
User & Date: olr on 2020-09-11 08:19:36
Other Links: manifest | tags
Context
2020-09-11
09:22
[fr] ajustements: regex -> tokens check-in: 6f370ea507 user: olr tags: trunk, fr
08:19
[graphspell] word simplifcation: apostrophes and hyphens check-in: 2aa5cb1dba user: olr tags: trunk, graphspell
07:05
[fx] gce_worker bug: remove useless code check-in: 169418beed user: olr tags: trunk, fx
Changes

Modified graphspell-js/str_transform.js from [8eb8f4c63c] to [4c4ee6009e].

42
43
44
45
46
47
48
49



50
51
52
53
54
55
56
42
43
44
45
46
47
48

49
50
51
52
53
54
55
56
57
58







-
+
+
+







        ['ä', 'a'],  ['ê', 'é'],  ['í', 'i'],  ['ó', 'o'],  ['ü', 'u'],  ['ý', 'y'],
        ['á', 'a'],  ['ë', 'é'],  ['ì', 'i'],  ['ò', 'o'],  ['ú', 'u'],  ['ỳ', 'y'],
        ['ā', 'a'],  ['ē', 'é'],  ['ī', 'i'],  ['ō', 'o'],  ['ū', 'u'],  ['ȳ', 'y'],
        ['ç', 'c'],  ['ñ', 'n'],
        ['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"],
        ["₀", "0"], ["₁", "1"], ["₂", "2"], ["₃", "3"], ["₄", "4"], ["₅", "5"], ["₆", "6"], ["₇", "7"], ["₈", "8"], ["₉", "9"]
        ["₀", "0"], ["₁", "1"], ["₂", "2"], ["₃", "3"], ["₄", "4"], ["₅", "5"], ["₆", "6"], ["₇", "7"], ["₈", "8"], ["₉", "9"],
        ["’", ""], ["'", ""], ["ʼ", ""], ["‘", ""], ["‛", ""], ["´", ""], ["`", ""], ["′", ""], ["‵", ""], ["՚", ""], ["ꞌ", ""], ["Ꞌ", ""],
        ["-", ""]
    ]),

    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 = "";

Modified graphspell/str_transform.py from [fea83aad08] to [e27e70d363].

34
35
36
37
38
39
40
41



42
43
44
45
46
47
48
34
35
36
37
38
39
40

41
42
43
44
45
46
47
48
49
50







-
+
+
+







    'ä': 'a',  'ê': 'é',  'í': 'i',  'ó': 'o',  'ü': 'u',  'ý': 'y',
    'á': 'a',  'ë': 'é',  'ì': 'i',  'ò': 'o',  'ú': 'u',  'ỳ': 'y',
    'ā': 'a',  'ē': 'é',  'ī': 'i',  'ō': 'o',  'ū': 'u',  'ȳ': 'y',
    'ç': 'c',  'ñ': 'n',
    '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",
    "₀": "0", "₁": "1", "₂": "2", "₃": "3", "₄": "4", "₅": "5", "₆": "6", "₇": "7", "₈": "8", "₉": "9"
    "₀": "0", "₁": "1", "₂": "2", "₃": "3", "₄": "4", "₅": "5", "₆": "6", "₇": "7", "₈": "8", "₉": "9",
    "’": "", "'": "", "ʼ": "", "‘": "", "‛": "", "´": "", "`": "", "′": "", "‵": "", "՚": "", "ꞌ": "", "Ꞌ": "",
    "-": ""
})

def simplifyWord (sWord):
    "word simplication before calculating distance between words"
    sWord = sWord.lower().translate(_xTransCharsForSimplification)
    sNewWord = ""
    for i, c in enumerate(sWord, 1):