Grammalecte  Diff

Differences From Artifact [638f8d8cdf]:

To Artifact [dbd02131cc]:


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

14
15
16
17
18
19
20
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
55
56
57
58
59
60






























61
62
63
64
65
66
67
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
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
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102













+


















+














+
+
+















+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+







# Spellchecker
# Wrapper for the IBDAWG class.
# Useful to check several dictionaries at once.

# To avoid iterating over a pile of dictionaries, it is assumed that 3 are enough:
# - the main dictionary, bundled with the package
# - the extended dictionary, added by an organization
# - the personal dictionary, created by the user for its own convenience


import traceback

from . import ibdawg
from . import tokenizer


dDefaultDictionaries = {
    "fr": "fr.bdic",
    "en": "en.bdic"
}


class SpellChecker ():

    def __init__ (self, sLangCode, sfMainDic="", sfExtendedDic="", sfPersonalDic=""):
        "returns True if the main dictionary is loaded"
        self.sLangCode = sLangCode
        if not sfMainDic:
            sfMainDic = dDefaultDictionaries.get(sLangCode, "")
        self.oMainDic = self._loadDictionary(sfMainDic, True)
        self.oExtendedDic = self._loadDictionary(sfExtendedDic)
        self.oPersonalDic = self._loadDictionary(sfPersonalDic)
        self.oTokenizer = None

    def _loadDictionary (self, sfDictionary, bNecessary=False):
        "returns an IBDAWG object"
        if not sfDictionary:
            return None
        try:
            return ibdawg.IBDAWG(sfDictionary)
        except Exception as e:
            if bNecessary:
                raise Exception(str(e), "Error: <" + sfDictionary + "> not loaded.")
            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"
        self.oExtendedDic = self._loadDictionary(sfDictionary)
        return bool(self.oExtendedDic)

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

    # parse text functions

    def parseParagraph (self, sText, bSpellSugg=False):
        if not self.oTokenizer:
            self.loadTokenizer()
        aSpellErrs = []
        for dToken in self.oTokenizer.genTokens(sText):
            if dToken['sType'] == "WORD" and not self.isValidToken(dToken['sValue']):
                if bSpellSugg:
                    dToken['aSuggestions'] = []
                    for lSugg in self.suggest(dToken['sValue']):
                        dToken['aSuggestions'].extend(lSugg)
                aSpellErrs.append(dToken)
        return aSpellErrs

    def countWordsOccurrences (self, sText, bByLemma=False, bOnlyUnknownWords=False, dWord={}):
        if not self.oTokenizer:
            self.loadTokenizer()
        for dToken in self.oTokenizer.genTokens(sText):
            if dToken['sType'] == "WORD":
                if bOnlyUnknownWords:
                    if not self.isValidToken(dToken['sValue']):
                        dWord[dToken['sValue']] = dWord.get(dToken['sValue'], 0) + 1
                else:
                    if not bByLemma:
                        dWord[dToken['sValue']] = dWord.get(dToken['sValue'], 0) + 1
                    else:
                        for sLemma in self.getLemma(dToken['sValue']):
                            dWord[sLemma] = dWord.get(sLemma, 0) + 1
        return dWord

    # IBDAWG functions

    def isValidToken (self, sToken):
        "checks if sToken is valid (if there is hyphens in sToken, sToken is split, each part is checked)"
        if self.oMainDic.isValidToken(sToken):
            return True
96
97
98
99
100
101
102



103
104
105
106
107
108
109
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147







+
+
+







        lResult = self.oMainDic.getMorph(sWord)
        if self.oExtendedDic:
            lResult.extend(self.oExtendedDic.getMorph(sWord))
        if self.oPersonalDic:
            lResult.extend(self.oPersonalDic.getMorph(sWord))
        return lResult

    def getLemma (self, sWord):
        return set([ s[1:s.find(" ")]  for s in self.getMorph(sWord) ])

    def suggest (self, sWord, nSuggLimit=10):
        "generator: returns 1, 2 or 3 lists of suggestions"
        yield self.oMainDic.suggest(sWord, nSuggLimit)
        if self.oExtendedDic:
            yield self.oExtendedDic.suggest(sWord, nSuggLimit)
        if self.oPersonalDic:
            yield self.oPersonalDic.suggest(sWord, nSuggLimit)