Grammalecte  Check-in [e052fe4727]

Overview
Comment:[core] code cleaning (pylint)
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | core | rg
Files: files | file ages | folders
SHA3-256: e052fe47270676f0b3f2f74f3bb04887ac23e345ba6d67c853668c073b3ecaf4
User & Date: olr on 2018-06-24 15:48:44
Other Links: branch diff | manifest | tags
Context
2018-06-24
16:19
[build] make.py: code cleaning (pylint) check-in: 6839c99323 user: olr tags: build, rg
15:48
[core] code cleaning (pylint) check-in: e052fe4727 user: olr tags: core, rg
14:49
[core] code cleaning (pylint) check-in: f1726135a3 user: olr tags: core, rg
Changes

Modified gc_core/py/lang_core/gc_options.py from [49f53da949] to [c84731594a].

1
2
3
4
5
6
7
8

9
10
11
12
13
14
15

16
17
18
19
20
21
22
1
2
3
4
5
6
7

8
9
10
11
12
13
14

15
16
17
18
19
20
21
22







-
+






-
+







"""
Grammar checker default options
"""

# generated code, do not edit

def getUI (sLang):
	"returns dictionary of UI labels"
    "returns dictionary of UI labels"
    if sLang in _dOptLabel:
        return _dOptLabel[sLang]
    return _dOptLabel["fr"]


def getOptions (sContext="Python"):
	"returns dictionary of options"
    "returns dictionary of options"
    if sContext in dOpt:
        return dOpt[sContext]
    return dOpt["Python"]


lStructOpt = ${lStructOpt}

Modified gc_core/py/text.py from [9c937ea8e6] to [137c7cc30f].

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
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







-
+






-
+








-
+















-
+







        return ""
    lGrammErrs = sorted(aGrammErrs, key=lambda d: d["nStart"])
    lSpellErrs = sorted(aSpellErrs, key=lambda d: d['nStart'])
    sText = ""
    nOffset = 0
    for sLine in wrap(sParagraph, nWidth): # textwrap.wrap(sParagraph, nWidth, drop_whitespace=False)
        sText += sLine + "\n"
        ln = len(sLine)
        nLineLen = len(sLine)
        sErrLine = ""
        nLenErrLine = 0
        nGrammErr = 0
        nSpellErr = 0
        for dErr in lGrammErrs:
            nStart = dErr["nStart"] - nOffset
            if nStart < ln:
            if nStart < nLineLen:
                nGrammErr += 1
                if nStart >= nLenErrLine:
                    sErrLine += " " * (nStart - nLenErrLine) + "^" * (dErr["nEnd"] - dErr["nStart"])
                    nLenErrLine = len(sErrLine)
            else:
                break
        for dErr in lSpellErrs:
            nStart = dErr['nStart'] - nOffset
            if nStart < ln:
            if nStart < nLineLen:
                nSpellErr += 1
                nEnd = dErr['nEnd'] - nOffset
                if nEnd > len(sErrLine):
                    sErrLine += " " * (nEnd - len(sErrLine))
                sErrLine = sErrLine[:nStart] + "°" * (nEnd - nStart) + sErrLine[nEnd:]
            else:
                break
        if sErrLine:
            sText += sErrLine + "\n"
        if nGrammErr:
            sText += getReadableErrors(lGrammErrs[:nGrammErr], nWidth)
            del lGrammErrs[0:nGrammErr]
        if nSpellErr:
            sText += getReadableErrors(lSpellErrs[:nSpellErr], nWidth, True)
            del lSpellErrs[0:nSpellErr]
        nOffset += ln
        nOffset += nLineLen
    return sText


def getReadableErrors (lErrs, nWidth, bSpell=False):
    "Returns lErrs errors as readable errors"
    sErrors = ""
    for dErr in lErrs:
97
98
99
100
101
102
103
104

105
106
107


108
109

110
111
112


113
114
115
116
117
118
119
97
98
99
100
101
102
103

104
105


106
107
108

109
110


111
112
113
114
115
116
117
118
119







-
+

-
-
+
+

-
+

-
-
+
+







    return sErrors


def getReadableError (dErr, bSpell=False):
    "Returns an error dErr as a readable error"
    try:
        if bSpell:
            s = u"* {nStart}:{nEnd}  # {sValue}:".format(**dErr)
            sText = u"* {nStart}:{nEnd}  # {sValue}:".format(**dErr)
        else:
            s = u"* {nStart}:{nEnd}  # {sLineId} / {sRuleId}:\n".format(**dErr)
            s += "  " + dErr.get("sMessage", "# error : message not found")
            sText = u"* {nStart}:{nEnd}  # {sLineId} / {sRuleId}:\n".format(**dErr)
            sText += "  " + dErr.get("sMessage", "# error : message not found")
        if dErr.get("aSuggestions", None):
            s += "\n  > Suggestions : " + " | ".join(dErr.get("aSuggestions", "# error : suggestions not found"))
            sText += "\n  > Suggestions : " + " | ".join(dErr.get("aSuggestions", "# error : suggestions not found"))
        if dErr.get("URL", None):
            s += "\n  > URL: " + dErr["URL"]
        return s
            sText += "\n  > URL: " + dErr["URL"]
        return sText
    except KeyError:
        return u"* Non-compliant error: {}".format(dErr)


def createParagraphWithLines (lLine):
    "Returns a text as merged lines and a set of data about lines (line_number_y, start_x, end_x)"
    sText = ""

Modified gc_lang/fr/modules/conj.py from [0febaa97ab] to [258383e97f].

171
172
173
174
175
176
177
178

179
180
181
182
183
184
185
171
172
173
174
175
176
177

178
179
180
181
182
183
184
185







-
+







        self._sRawInfo = getVtyp(sVerbPattern)
        self.sInfo = self._readableInfo()
        self.bProWithEn = (self._sRawInfo[5] == "e")
        self._tTags = _getTags(sVerbPattern)
        if not self._tTags:
            raise ValueError("Unknown verb.")
        self._tTagsAux = _getTags(self.sVerbAux)
        self.cGroup = self._sRawInfo[0];
        self.cGroup = self._sRawInfo[0]
        self.dConj = {
            ":Y": {
                "label": "Infinitif",
                ":": sVerb,
            },
            ":P": {
                "label": "Participe présent",

Modified gc_lang/fr/modules/cregex.py from [f9eb3691d3] to [4b9e99ff72].

99
100
101
102
103
104
105

106
107
108
109
110
111
112
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113







+







    if mbMas(l1) and not mbMas(l2):
        return False
    if mbFem(l1) and not mbFem(l2):
        return False
    return True

def checkConjVerb (lMorph, sReqConj):
    "returns True if <sReqConj> in <lMorph>"
    return any(sReqConj in s  for s in lMorph)

def getGender (lMorph):
    "returns gender of word (':m', ':f', ':e' or empty string)."
    sGender = ""
    for sMorph in lMorph:
        m = Gender.search(sMorph)
195
196
197
198
199
200
201
202

203
204
205
206
207
208


209
210
211
212
213
214
215
196
197
198
199
200
201
202

203
204
205
206
207


208
209
210
211
212
213
214
215
216







-
+




-
-
+
+








def mbNomAdj (lMorph):
    "returns True if one morphology is “nom” or “adjectif”"
    return any(NA.search(s)  for s in lMorph)

def mbNomNotAdj (lMorph):
    "returns True if one morphology is “nom”, but not “adjectif”"
    b = False
    bResult = False
    for s in lMorph:
        if ":A" in s:
            return False
        if ":N" in s:
            b = True
    return b
            bResult = True
    return bResult

def mbPpasNomNotAdj (lMorph):
    "returns True if one morphology is “nom” or “participe passé”, but not “adjectif”"
    return any(PNnotA.search(s)  for s in lMorph)

def mbVconj (lMorph):
    "returns True if one morphology is “nom” or “verbe conjugué”"

Modified gc_lang/fr/modules/lexicographe.py from [a9b878f391] to [175c38852d].

154
155
156
157
158
159
160

161
162
163
164
165
166
167
168

169
170
171
172
173
174
175
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177







+








+







    "m'en": " (me) pronom personnel objet + (en) pronom adverbial",
    "t'en": " (te) pronom personnel objet + (en) pronom adverbial",
    "s'en": " (se) pronom personnel objet + (en) pronom adverbial",
}


class Lexicographe:
    "Lexicographer - word analyzer"

    def __init__ (self, oSpellChecker):
        self.oSpellChecker = oSpellChecker
        self._zElidedPrefix = re.compile("(?i)^([dljmtsncç]|quoiqu|lorsqu|jusqu|puisqu|qu)['’](.+)")
        self._zCompoundWord = re.compile("(?i)(\\w+)-((?:les?|la)-(?:moi|toi|lui|[nv]ous|leur)|t-(?:il|elle|on)|y|en|[mts][’'](?:y|en)|les?|l[aà]|[mt]oi|leur|lui|je|tu|ils?|elles?|on|[nv]ous)$")
        self._zTag = re.compile("[:;/][\\w*][^:;/]*")

    def analyzeWord (self, sWord):
        "returns a tuple (a list of morphologies, a set of verb at infinitive form)"
        try:
            if not sWord:
                return (None, None)
            if sWord.count("-") > 4:
                return (["élément complexe indéterminé"], None)
            if sWord.isdigit():
                return (["nombre"], None)
193
194
195
196
197
198
199
200

201
202
203
204
205
206

207
208
209
210
211
212
213
195
196
197
198
199
200
201

202
203
204
205
206
207
208
209
210
211
212
213
214
215
216







-
+






+







                aMorph.append( "{} : {}".format(sWord, self.formatTags(lMorph[0])) )
            else:
                aMorph.append( "{} :  inconnu du dictionnaire".format(sWord) )
            # suffixe d’un mot composé
            if m2:
                aMorph.append( "-{} : {}".format(m2.group(2), self._formatSuffix(m2.group(2).lower())) )
            # Verbes
            aVerb = set([ s[1:s.find(" ")]  for s in lMorph  if ":V" in s ])
            aVerb = set([ s[1:s.find("/")]  for s in lMorph  if ":V" in s ])
            return (aMorph, aVerb)
        except:
            traceback.print_exc()
            return (["#erreur"], None)

    def formatTags (self, sTags):
        "returns string: readable tags"
        sRes = ""
        sTags = re.sub("(?<=V[1-3])[itpqnmr_eaxz]+", "", sTags)
        sTags = re.sub("(?<=V0[ea])[itpqnmr_eaxz]+", "", sTags)
        for m in self._zTag.finditer(sTags):
            sRes += _dTAGS.get(m.group(0), " [{}]".format(m.group(0)))[0]
        if sRes.startswith(" verbe") and not sRes.endswith("infinitif"):
            sRes += " [{}]".format(sTags[1:sTags.find(" ")])