X-Git-Url: http://iramuteq.org/git?p=iramuteq;a=blobdiff_plain;f=corpus.py;h=ee80d9e8fc60f2d7b05e26dd807e3417a15ed3ea;hp=cd6c36467b587157ab7bbc3b36a3c2efd5edf608;hb=74255fdad5e1a929fe9b199b0d58fdd185ad3c58;hpb=e531d59ce2d8f72dfc3138446db913af1f20b134 diff --git a/corpus.py b/corpus.py index cd6c364..ee80d9e 100644 --- a/corpus.py +++ b/corpus.py @@ -434,7 +434,7 @@ class Corpus : f.write(guce.encode(self.parametres['syscoding']) + '\n\n') def export_classe(self, outf, classe, lem = False) : - sts = self.lc[classe] + sts = self.lc[classe - 1] res = self.getconcorde(sts) self.make_iduces() with open(outf, 'w') as f : @@ -1081,7 +1081,7 @@ class BuildCorpus : def firstclean(self, txt) : txt = txt.replace(u'’',"'") txt = txt.replace(u'œ', u'oe') - return txt.replace('...',u' £$£ ').replace('?',' ? ').replace('.',' . ').replace('!', ' ! ').replace(',',' , ').replace(';', ' ; ').replace(':',' : ').replace(u'…', ' £$£ ') + return txt.replace('...',u' £$£ ').replace('?',' ? ').replace('.',' . ').replace('!', ' ! ').replace(',',' , ').replace(';', ' ; ').replace(':',' : ').replace(u'…', u' £$£ ') def make_cleans(self, txt) : for clean in self.cleans :