Grammalecte  Diff

                hDst.write("  > {0[1]:>8} : {0[0]}\n".format(elem))

    def writeDictionary (self, spDst, dTplVars, nMode, bSimplified):
        "Écrire le fichier dictionnaire (.dic)"
        echo(' * Dictionnaire >> [ {}.dic ] ({})'.format(dTplVars['asciiName'], dTplVars['subDicts']))
        nEntry = 0
        for oEntry in self.lEntry:
            if oEntry.di in dTplVars['subDicts']:
            if oEntry.di in dTplVars['subDicts'] and " " not in oEntry.lemma:
                nEntry += 1
        with open(spDst+'/'+dTplVars['asciiName']+'.dic', 'w', encoding='utf-8', newline="\n") as hDst:
            hDst.write(str(nEntry)+"\n")
            for oEntry in self.lEntry:
                if oEntry.di in dTplVars['subDicts']:
                    hDst.write(oEntry.getEntryLine(self, nMode, bSimplified))
                if oEntry.di in dTplVars['subDicts'] and " " not in oEntry.lemma:
                    hDst.write(oEntry.getHunspellLine(self, nMode, bSimplified))

    def writeAffixes (self, spDst, dTplVars, nMode, bSimplified):
        "Écrire le fichier des affixes (.aff)"
        echo(' * Dictionnaire >> [ {}.aff ]'.format(dTplVars['asciiName']))
        info = "# This Source Code Form is subject to the terms of the Mozilla Public\n" + \
               "# License, v. 2.0. If a copy of the MPL was not distributed with this\n" + \
               "# file, You can obtain one at http://mozilla.org/MPL/2.0/.\n\n" + \

        self.iD = '0'

        # autres
        self.comment = ''
        self.err = ''
        self.nFlexions = 0
        self.lFlexions = []
        self.sRadical = ''
        self.sStem = ''
        self.nOccur = 0
        self.nAKO = -1   # Average known occurrences
        self.fFreq = 0
        self.oldFq = ''

        sLine = sLine.rstrip(" \n")
        # commentaire
        if '#' in sLine:
            sLine, comment = sLine.split('#', 1)
            self.comment = comment.strip()
        # éléments de la ligne
        elems = sLine.split()
        elems = sLine.split("\t")
        nElems = len(elems)
        # lemme et drapeaux
        firstElems = elems[0].split('/')
        self.lemma = firstElems[0]
        self.flags = firstElems[1]  if len(firstElems) > 1  else ''
        # morph
        for i in range(1, nElems):

        if re.search(r"\s$", self.lemma):
            sErr += 'espace en fin de lemme'
        if re.match(r"v[0123]", self.po) and not re.match(r"[eas_][ix_][tx_][nx_][pqreuvx_][mx_][ex_z][ax_z]\b", self.po[2:]):
            sErr += 'verbe inconnu: ' + self.po
        if (re.match(r"S[*.]", self.flags) and re.search("[sxz]$", self.lemma)) or (re.match(r"X[*.]", self.flags) and not re.search("[ul]$", self.lemma)):
            sErr += 'drapeau inutile'
        if self.iz == '' and re.match(r"[SXAI](?!=)", self.flags) and self.po:
            sErr += '[is]'
            sErr += '[is] vide'
        if re.match(r"pl|sg|inv", self.iz):
            sErr += '[is]'
            sErr += '[is] incomplet'
        if re.match(r"[FW]", self.flags) and re.search(r"epi|mas|fem|inv|sg|pl", self.iz):
            sErr += '[is]'
            sErr += '[is] incohérent'
        if re.match(r"[FW]", self.flags) and re.search(r"[^eë]$", self.lemma):
            sErr += "fin de lemme inapproprié"
        if re.match(r".\*", self.flags) and re.match(r"[bcdfgjklmnpqrstvwxz]", self.lemma):
            sErr += 'drapeau pour lemme commençant par une voyelle'
        if re.search(r"pl|sg|inv", self.iz) and re.match(r"[SXAIFW](?!=)", self.flags):
            sErr += '[is]'
            sErr += '[is] incohérent'
        if re.search(r"nom|adj", self.po) and re.match(r"(?i)[aâàäáeéèêëiîïíìoôöóòuûüúù]", self.lemma) and re.match("[SFWXAI][.]", self.flags) \
           and "pel" not in self.lx:
            sErr += 'le drapeau derait finir avec *'
        if not self.flags and self.iz.endswith(("mas", "fem", "epi")):
            sErr += '[is] incomplet'
        if self.flags.startswith(("a", "b", "c", "d")) and not self.lemma.endswith("er"):
            sErr += "drapeau pour verbe du 1ᵉʳ groupe sur un lemme non conforme"

    def keyTriNat (self):
        return (self.lemma.translate(CHARMAP), self.flags, self.po)

    def keyTriNum (self):
        return (self.lemma, self.flags, self.po)

    def getEntryLine (self, oDict, nMode, bSimplified=False):
        sLine = self.lemma
    def getHunspellLine (self, oDict, nMode, bSimplified=False):
        sLine = self.lemma.replace("’", "'")
        if self.flags:
            sLine += '/'
            sLine += self.flags  if not oDict.bShortenTags or bSimplified  else oDict.dAF[self.flags]
        if bSimplified:
            return sLine.replace("()", "") + "\n"
        if nMode > 0:
            sMorph = self.getMorph(nMode)

                if not sMorph.endswith((" mas", " fem", " epi")):
                    self.lFlexions.append( Flexion(self, sFlex, sMorph, sDic) )
                    self.nFlexions += 1
                else:
                    #echo(sFlex + " " + sMorph + ", ")
                    pass
        # Drapeaux dont le lemme féminin doit être remplacé par le masculin dans la gestion des formes fléchies
        if self.st:
            self.sStem = self.st
        else:
        if self.flags.startswith(("F.", "F*", "W.", "W*")):
            # recherche de la forme masculine
            for t in lTuples:
                sMorph = self.clean(t[1])
                if sMorph.endswith('mas') or sMorph.endswith('mas sg') or sMorph.endswith('mas inv'):
                    self.sRadical = t[0]
        else:
            self.sRadical = self.lemma
            if self.flags.startswith(("F.", "F*", "W.", "W*")):
                # recherche de la forme masculine
                for t in lTuples:
                    sMorph = self.clean(t[1])
                    if sMorph.endswith(('mas', 'mas sg', 'mas inv')):
                        self.sStem = t[0]
            else:
                self.sStem = self.lemma
        # Tag duplicates
        d = {}
        for oFlex in self.lFlexions:
            d[oFlex.sFlexion] = d.get(oFlex.sFlexion, 0) + 1
        for oFlex in self.lFlexions:
            oFlex.nDup = d[oFlex.sFlexion]

            sOccurs += t[1] + "\t"
        return "id\tFlexion\tLemme\tÉtiquettes\tMétagraphe (β)\tMetaphone2\tNotes\tSémantique\tÉtymologie\tSous-dictionnaire\t" + sOccurs + "Total occurrences\tDoublons\tMultiples\tFréquence\tIndice de fréquence\n"

    def __str__ (self, oStatsLex):
        sOccurs = ''
        for v in oStatsLex.dFlexions[self.sFlexion]:
            sOccurs += str(v) + "\t"
        return "{0.oEntry.iD}\t{0.sFlexion}\t{0.oEntry.sRadical}\t{0.sMorph}\t{0.metagfx}\t{0.metaph2}\t{0.oEntry.lx}\t{0.oEntry.se}\t{0.oEntry.et}\t{0.oEntry.di}{2}\t{1}{0.nOccur}\t{0.nDup}\t{0.nMulti}\t{0.fFreq:.15f}\t{0.cFq}\n".format(self, sOccurs, "/"+self.cDic if self.cDic != "*" else "")
        return "{0.oEntry.iD}\t{0.sFlexion}\t{0.oEntry.sStem}\t{0.sMorph}\t{0.metagfx}\t{0.metaph2}\t{0.oEntry.lx}\t{0.oEntry.se}\t{0.oEntry.et}\t{0.oEntry.di}{2}\t{1}{0.nOccur}\t{0.nDup}\t{0.nMulti}\t{0.fFreq:.15f}\t{0.cFq}\n".format(self, sOccurs, "/"+self.cDic if self.cDic != "*" else "")

    @classmethod
    def simpleHeader (cls):
        return "# :POS ;LEX ~SEM =FQ /DIC\n"

    def getGrammarCheckerRepr (self):
        return "{0.sFlexion}\t{0.oEntry.lemma}\t{1}\n".format(self, self._getSimpleTags())

        "ipre": ":Ip", "iimp": ":Iq", "ipsi": ":Is", "ifut": ":If",
        "spre": ":Sp", "simp": ":Sq", "cond": ":K", "impe": ":E",
        "1sg": ":1s", "1isg": ":1ś", "1jsg": ":1ŝ", "2sg": ":2s", "3sg": ":3s", "1pl": ":1p", "2pl": ":2p", "3pl": ":3p", "3pl!": ":3p!",
        "prepv": ":Rv", "prep": ":R", "loc.prep": ":Ŕ",
        "detpos": ":Dp", "detdem": ":Dd", "detind": ":Di", "detneg": ":Dn", "detex": ":De", "det": ":D",
        "advint": ":U",
        "prodem": ":Od", "proind": ":Oi", "proint": ":Ot", "proneg": ":On", "prorel": ":Or", "proadv": ":Ow",
        "properobj": ":Oo", "propersuj": ":Os", "1pe": ":O1", "2pe": ":O2", "3pe": ":O3",
        "properobj": ":Oo", "propersuj": ":Os", "1pe": ":O1", "2pe": ":O2", "3pe": ":O3", "preverb": ":Ov",
        "cjco": ":Cc", "cjsub": ":Cs", "cj": ":C", "loc.cj": ":Ĉ", "loc.cjsub": ":Ĉs",
        "prn": ":M1", "patr": ":M2", "loc.patr": ":Ḿ2", "npr": ":MP", "nompr": ":NM",
        "pfx": ":Zp", "sfx": ":Zs",
        "div": ":H",
        "err": ":#",
        # LEX
        "symb": ";S"

            s += "/" + self.oEntry.di
        return s

    def keyTriNat (self):
        return (self.sFlexion.translate(CHARMAP), self.sMorph)

    def keyFreq (self):
        return (100-self.fFreq, self.oEntry.sRadical, self.sFlexion)
        return (100-self.fFreq, self.oEntry.sStem, self.sFlexion)

    def keyOcc (self):
        return (self.nOccur, self.oEntry.sRadical, self.sFlexion)
        return (self.nOccur, self.oEntry.sStem, self.sFlexion)

    def keyIdx (self):
        return self.oEntry.iD

    def keyFlexion (self):
        return self.sFlexion

                hDst.write(str(t)+"\n")
            for e in self.dFlexions.items():
                hDst.write("{} - {}\n".format(e[0], e[1]))



def main ():

    xParser = argparse.ArgumentParser()
    xParser.add_argument("-v", "--verdic", help="set dictionary version, i.e. 5.4", type=str, default="X.Y.z")
    xParser.add_argument("-m", "--mode", help="0: no tags,  1: Hunspell tags (default),  2: All tags", type=int, choices=[0, 1, 2], default=1)
    xParser.add_argument("-u", "--uncompress", help="do not use Hunspell compression", action="store_true")
    xParser.add_argument("-s", "--simplify", help="no virtual lemmas", action="store_true")
    xParser.add_argument("-sv", "--spellvariants", help="generate spell variants", action="store_true")
    xParser.add_argument("-gl", "--grammalecte", help="copy generated files to Grammalecte folders", action="store_true")

    oFrenchDict.calculateStats(oStatsLex, spfStats)

    ### écriture des paquets
    echo("Création des paquets...")

    spLexiconDestGL = "../../../lexicons"  if xArgs.grammalecte  else ""
    spLibreOfficeExtDestGL = "../oxt/Dictionnaires/dictionaries"  if xArgs.grammalecte  else ""
    spMozillaExtDestGL = ""  # les dictionnaires pour Hunspell ne sont plus utilisés pour l’instant dans Firefox / Thunderbird
    spMozillaExtDestGL = ""  if xArgs.grammalecte  else "" # no more Hunspell dictionaries in Mozilla extensions for now
    spDataDestGL = "../data"  if xArgs.grammalecte  else ""

    if not xArgs.uncompress:
        oFrenchDict.defineAbreviatedTags(xArgs.mode, spfStats)
    oFrenchDict.createFiles(spBuild, [dMODERNE, dTOUTESVAR, dCLASSIQUE, dREFORME1990], xArgs.mode, xArgs.simplify)
    oFrenchDict.createLexiconPackages(spBuild, xArgs.verdic, oStatsLex, spLexiconDestGL)
    oFrenchDict.createFileIfqForDB(spBuild)