Grammalecte  Check-in [4f84e0d1c1]

Overview
Comment:[fr][build] contrôle amélioré des entrées du dictionnaire Hunspell
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | trunk | fr | build
Files: files | file ages | folders
SHA3-256: 4f84e0d1c1a9f71ae9411cd8822c400b5de7c37825b8afc3afeb26212f2f2c69
User & Date: olr on 2025-12-12 14:53:52
Other Links: manifest | tags
Context
2025-12-12
14:53
[fr][build] contrôle amélioré des entrées du dictionnaire Hunspell Leaf check-in: 4f84e0d1c1 user: olr tags: trunk, fr, build
2025-12-06
21:37
[fr] fichier des affixes: commentaires check-in: 24336b82aa user: olr tags: trunk, fr
Changes
Hide Diffs Unified Diffs Ignore Whitespace Patch

Modified gc_lang/fr/dictionnaire/genfrdic.py from [fce132f18a] to [3f7c9cfb70].

︙︙
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676

        self.ph = ''
        # champs annexes
        self.lx = ''
        self.se = ''
        self.et = ''
        self.di = '*'
        self.fq = ''
        self.iD = '0' # hunspell attribute: id

        # autres
        self.comment = ''
        self.err = ''
        self.nFlexions = 0
        self.lFlexions = []
        self.sStem = ''








|








662
663
664
665
666
667
668
669
670
671
672
673
674
675
676

        self.ph = ''
        # champs annexes
        self.lx = ''
        self.se = ''
        self.et = ''
        self.di = '*'
        self.fq = ''
        self.iD = '0' # hunspell attribute: id. Since the DB has been lost, useless.

        # autres
        self.comment = ''
        self.err = ''
        self.nFlexions = 0
        self.lFlexions = []
        self.sStem = ''
︙︙
721
722
723
724
725
726
727

728
729
730
731
732
733

734
735












736
737
738
739
740
741
742
743
744
745


746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761

            echo("   @ : " + self.lemma)

    def __str__ (self):
        return "{0.lemma}/{0.flags} {1}".format(self, self.getMorph(2))

    def check (self):
        sErr = ''

        if self.lemma == '':
            sErr += 'lemme vide'
        if re.match(r"^\s", self.lemma):
            sErr += 'premier caractère un espace @ <' + self.lemma + '>'
        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> vide'
        if re.match(r"pl|sg|inv", self.iz):
            sErr += '<is> incomplet'
        if re.match(r"[FW]", self.flags) and re.search(r"epi|mas|fem|inv|sg|pl", self.iz):
            sErr += '<is> incohérent'
        if re.search(r"pl|sg|inv", self.iz) and re.match(r"[SXAIFW](?!=)", self.flags):
            sErr += '<is> incohérent'


        if self.iz.endswith(("mas", "fem", "epi")) and (not self.flags or not self.flags.startswith(("S", "X", "F", "W", "A", "I", "U"))):
            sErr += '<is> incomplet'
        if self.flags.startswith(("a0", "b0", "c0", "d0")) and not self.lemma.endswith("er"):
            sErr += "drapeau pour verbe du 1ᵉʳ groupe sur un lemme non conforme"
        if self.flags.startswith("f") and not self.lemma.endswith(("ir", "ïr")):
            sErr += "drapeau pour verbe du 2ᵉ groupe sur un lemme non conforme"
        if sErr:
            echo('   error -  id: ' + self.iD, end = "")
            echo('  ' + sErr + '  in  ' + self.__str__())

    def setTagsFrom (self, oEnt):
        self.po = oEnt.po
        self.iz = oEnt.iz
        self.ds = oEnt.ds
        self.ts = oEnt.ts
        self.ip = oEnt.ip








>

|

|

|
>

|
>
>
>
>
>
>
>
>
>
>
>
>
|
|

|

|

|
|
|
>
>

|
<
<
|
|

<
|








721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763


764
765
766

767
768
769
770
771
772
773
774

            echo("   @ : " + self.lemma)

    def __str__ (self):
        return "{0.lemma}/{0.flags} {1}".format(self, self.getMorph(2))

    def check (self):
        sErr = ''
        # lemme
        if self.lemma == '':
            sErr += ' > lemme vide'
        if re.match(r"^\s", self.lemma):
            sErr += ' > espace en début de lemme <' + self.lemma + '>'
        if re.search(r"\s$", self.lemma):
            sErr += ' > espace en fin de lemme <' + self.lemma + '>'
        # verbe
        if re.match(r"v[0123]", self.po) and not re.match(r"[eas_][ix_][tx_][nx_][pqreuvx_][mx_][ex_z][ax_z]\b", self.po[2:]):
            sErr += ' > verbe mal étiqueté: ' + self.po
        if re.match(r"[abcdf]0", self.flags):
            if not re.search(r"p[+.]", self.flags):
                sErr += ' > verbe sans participe passé: ' + self.po
            if "()" not in self.flags:
                sErr += ' > drapeau () manquant'
            if re.match(r"v...t", self.po) and "p+" not in self.flags:
                sErr += ' > drapeau p+ absent sur un verbe étiqueté transitif'
        if self.flags.startswith(("a0", "b0", "c0", "d0")) and not self.lemma.endswith("er"):
            sErr += " > drapeau pour verbe du 1ᵉʳ groupe sur un lemme qui ne finit pas par -er"
        if self.flags.startswith("f") and not self.lemma.endswith(("ir", "ïr")):
            sErr += " > drapeau pour verbe du 2ᵉ groupe sur un lemme qui ne finit pas par -ir"
        # nom / adj
        if (re.match(r"S[.+]", self.flags) and re.search("[sxz]$", 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 += ' > étiquette <is> vide'
        if re.match(r"pl|sg|inv", self.iz):
            sErr += ' > étiquettes <is> incomplètes, genre non spécifié (mas/fem/epi)'
        if re.match(r"[FW]", self.flags) and re.search(r"epi|mas|fem|inv|sg|pl", self.iz):
            sErr += ' > étiquettes <is> incohérentes'
        if re.search(r"pl|sg|inv", self.iz) and re.match(r"[SXAIFGW](?!=)", self.flags):
            sErr += ' > étiquettes <is> incohérentes '
        if re.search(r"pl|sg|inv", self.iz) and re.match(r"[SXAIFGW](?!=)", self.flags):
            sErr += ' > étiquettes <is> incohérentes '
        if self.iz.endswith(("mas", "fem", "epi")) and (not self.flags or not self.flags.startswith(("S", "X", "F", "W", "A", "I", "U"))):
            sErr += ' > étiquettes <is> incomplètes'


        if re.match(r"[SXAIFGW](?!=)", self.flags) and "()" not in self.flags:
            sErr += ' > drapeau () manquant'
        if sErr:

            echo(f"   erreur {sErr}   sur   " + self.__str__())

    def setTagsFrom (self, oEnt):
        self.po = oEnt.po
        self.iz = oEnt.iz
        self.ds = oEnt.ds
        self.ts = oEnt.ts
        self.ip = oEnt.ip
︙︙

Fossil 2.24 [8be0372c10] 2024-04-23 13:25:26
This page was generated in about 0.008s