Files
ola5doc/content/.stversions/leo-martin/sources/pattern__premier-essai~20171216-162925.py

49 lines
1.5 KiB
Python
Raw Permalink Blame History

This file contains invisible Unicode characters
This file contains invisible Unicode characters that are indistinguishable to humans but may be processed differently by a computer. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
#!/usr/bin/env python
# -*- coding: utf-8 -*-
#from __future__ import unicode_literals
from pattern.fr import parse, split
texte_brut = u"Le petit chat rugit alors que l'esclave humain tarde à accomplir sa tâche de nourrissage du maître et seigneur."
texte = parse( texte_brut )
def imprimer_structure_mot ( mot ):
'''imprime la structure de la phrase'''
print 'index : ' + str( mot.index )
print 'string : ' + str( mot.string )
print '_custom_tags : ' + str( mot._custom_tags )
print 'sentence : ' + str( mot.sentence )
print 'pnp : ' + str( mot.pnp )
print 'chunk : ' + str( mot.chunk )
print 'lemma : ' + str( mot.lemma )
print 'type : ' + str( mot.type )
for phrase in split( texte ):
print phrase
'''
print "——————————"
print "mots :"
print phrase.words
print "——————————"
print "groupes de mots :"
print phrase.chunks
print "——————————"
print "structure, phrase :"
print phrase.__dict__.keys()
print "——————————"
print "structure, mot :"
print phrase.words[0].__dict__.keys()
print "——————————"
print "structure, chunk (groupe de mots) :"
print phrase.chunks[0].__dict__.keys()
'''
'''
for mot in phrase.words:
# print mot.__dict__.keys()
print "---"
imprimer_structure_mot( mot )
# imprimer_la_structure_de_la_phrase( phrase.words[0] )
'''