# -*- coding: utf-8 -*-
#Author: Pierre Ratinaud
#Copyright (c) 2008-2012 Pierre Ratinaud
-#Lisense: GNU/GPL
+#License: GNU/GPL
import wx
import re
def rmtab(self, analyse) :
del self.opened[analyse['uuid']]
+
+ def clean(self) :
+ corpustodel = [corpus for corpus in self.history if not os.path.exists(corpus['ira'])]
+ print corpustodel
+ for corpus in corpustodel :
+ print 'cleaning :', corpus['corpus_name']
+ self.delete(corpus, corpus = True)
def __str__(self) :
return str(self.history)
FileReader.close()
DictProfile = {}
count = 0
- rows = [row.replace('\n', '').replace("'", '').replace('\"', '').replace(',', '.').replace('\r','').split(';') for row in Filecontent]
+ #rows = [row.replace('\n', '').replace("'", '').replace('\"', '').replace(',', '.').replace('\r','').split(';') for row in Filecontent]
+ rows = [row.replace('\n', '').replace("'", '').replace('\"', '').replace('\r','').split(';') for row in Filecontent]
rows.pop(0)
ClusterNb = rows[0][2]
rows.pop(0)
def treat_var_mod(variables) :
var_mod = {}
- for variable in variables :
- if u'_' in variable :
- forme = variable.split(u'_')
- var = forme[0]
- mod = forme[1]
- if not var in var_mod :
- var_mod[var] = [variable]
- else :
- if not mod in var_mod[var] :
- var_mod[var].append(variable)
+ variables = list(set(variables))
+ varmod = [variable.split('_') for variable in variables]
+ vars = list(set([var[0] for var in varmod if len(var) >=2]))
+ for var in vars :
+ mods = ['_'.join(v) for v in varmod if v[0] == var]
+ var_mod[var] = mods
+
+# for variable in variables :
+# if u'_' in variable :
+# forme = variable.split(u'_')
+# var = forme[0]
+# mod = forme[1]
+# if not var in var_mod :
+# var_mod[var] = [variable]
+# else :
+# if not mod in var_mod[var] :
+# var_mod[var].append(variable)
return var_mod
+
+def doconcorde(corpus, uces, mots, uci = False) :
+ if not uci :
+ ucestxt1 = [row for row in corpus.getconcorde(uces)]
+ else :
+ ucestxt1 = [row for row in corpus.getuciconcorde(uces)]
+ ucestxt1 = dict(ucestxt1)
+ ucestxt = []
+ ucis_txt = []
+ listmot = [corpus.getlems()[lem].formes for lem in mots]
+ listmot = [corpus.getforme(fid).forme for lem in listmot for fid in lem]
+ mothtml = ['<font color=red><b>'+mot+'</b></font>' for mot in listmot]
+ dmots = dict(zip(listmot, mothtml))
+ for uce in uces :
+ ucetxt = ucestxt1[uce].split()
+ ucetxt = ' '.join([dmots.get(mot, mot) for mot in ucetxt])
+ if not uci :
+ ucis_txt.append('<p><b>' + ' '.join(corpus.ucis[corpus.getucefromid(uce).uci].etoiles) + '</b></p>')
+ else :
+ ucis_txt.append('<p><b>' + ' '.join(corpus.ucis[uce].etoiles) + '</b></p>')
+ ucestxt.append(ucetxt)
+ return ucis_txt, ucestxt
+
+
+def getallstcarac(corpus, analyse) :
+ pathout = PathOut(analyse['ira'])
+ profils = ReadProfileAsDico(pathout['PROFILE_OUT'], Alceste, self.encoding)
+ print profils