...

[iramuteq] / iracmd.py

diff --git a/iracmd.py b/iracmd.py
index abf8ce2..aefb09d 100644 (file)
--- a/iracmd.py
+++ b/iracmd.py
@@ -2,7 +2,7 @@
 # -*- coding: utf-8 -*-
 #Author: Pierre Ratinaud
 #Copyright (c) 2010 Pierre Ratinaud
 # -*- coding: utf-8 -*-
 #Author: Pierre Ratinaud
 #Copyright (c) 2010 Pierre Ratinaud

-#Lisense: GNU/GPL
+#License: GNU/GPL

 
 import os
 from optparse import OptionParser
 
 import os
 from optparse import OptionParser


@@ -11,16 +11,19 @@ reload(sys)
 import locale
 import codecs
 sys.setdefaultencoding(locale.getpreferredencoding())
 import locale
 import codecs
 sys.setdefaultencoding(locale.getpreferredencoding())

-from chemins import ConstructConfigPath, ConstructDicoPath, ConstructRscriptsPath
-from functions import ReadLexique, DoConf, History
+from chemins import ConstructConfigPath, ConstructDicoPath, ConstructRscriptsPath, PathOut
+from functions import ReadLexique, DoConf, History, ReadDicoAsDico

 from ConfigParser import *
 #######################################
 #from textchdalc import AnalyseAlceste
 #from textdist import PamTxt
 #from textafcuci import AfcUci
 from ConfigParser import *
 #######################################
 #from textchdalc import AnalyseAlceste
 #from textdist import PamTxt
 #from textafcuci import AfcUci

+from textreinert import Reinert
+from corpus import Corpus, copycorpus, BuildFromAlceste, BuildSubCorpus

 from textaslexico import Lexico
 from textstat import Stat
 from tools import SubCorpus
 from textaslexico import Lexico
 from textstat import Stat
 from tools import SubCorpus

+from textsimi import SimiTxt

 import tempfile
 ######################################
 import logging
 import tempfile
 ######################################
 import logging


@@ -32,9 +35,7 @@ log.addHandler(ch)
 log.setLevel(logging.DEBUG)
 #######################################
 
 log.setLevel(logging.DEBUG)
 #######################################
 

-log.debug('----------TEST corpusNG-----------------')
-from analysetxt import Alceste,  gramact, gramsup
-from corpusNG import *
+

 
 #cmd = iracmd.CmdLine(args=['-f','/home/pierre/workspace/iramuteq/corpus/lru2.txt','-t','alceste'])
 
 
 #cmd = iracmd.CmdLine(args=['-f','/home/pierre/workspace/iramuteq/corpus/lru2.txt','-t','alceste'])
 


@@ -46,7 +47,8 @@ else:
 UserConfigPath = os.path.abspath(os.path.join(user_home, '.iramuteq'))
 
 class CmdLine :
 UserConfigPath = os.path.abspath(os.path.join(user_home, '.iramuteq'))
 
 class CmdLine :

-    def __init__(self, args = None) :
+    def __init__(self, args = None, AppliPath = None, parametres = None) :
+        AppliPath = AppliPath

         self.DictPath = ConstructDicoPath(AppliPath)
         self.ConfigPath = ConstructConfigPath(UserConfigPath)
         self.syscoding = sys.getdefaultencoding()
         self.DictPath = ConstructDicoPath(AppliPath)
         self.ConfigPath = ConstructConfigPath(UserConfigPath)
         self.syscoding = sys.getdefaultencoding()


@@ -58,6 +60,8 @@ class CmdLine :
         self.pref = RawConfigParser()
         self.pref.read(self.ConfigPath['preferences'])
         self.history = History(os.path.join(UserConfigPath, 'history.db'))
         self.pref = RawConfigParser()
         self.pref.read(self.ConfigPath['preferences'])
         self.history = History(os.path.join(UserConfigPath, 'history.db'))

+        print 'CLEAN HISTORY'
+#        self.history.clean()

 
         parser = OptionParser()
     
 
         parser = OptionParser()
     


@@ -81,7 +85,6 @@ class CmdLine :
             config = DoConf(os.path.abspath(options.configfile)).getoptions()
         elif options.filename and options.type_analyse :
             config = DoConf(self.ConfigPath[options.type_analyse]).getoptions()
             config = DoConf(os.path.abspath(options.configfile)).getoptions()
         elif options.filename and options.type_analyse :
             config = DoConf(self.ConfigPath[options.type_analyse]).getoptions()

-            #self.ConfigPath[options.type_analyse] = os.path.abspath(options.configfile)

         elif options.read and options.type_analyse :
             config = DoConf(self.ConfigPath[options.type_analyse]).getoptions()
         elif options.read :
         elif options.read and options.type_analyse :
             config = DoConf(self.ConfigPath[options.type_analyse]).getoptions()
         elif options.read :


@@ -92,15 +95,17 @@ class CmdLine :
             print 'rien a faire'
             return
 
             print 'rien a faire'
             return
 

-        #self.history.write()
-        if options.filename or options.read :#or options.build:
+        if options.filename or options.read :

             self.corpus_encodage = options.encodage
             self.corpus_lang = options.language
             self.corpus_encodage = options.encodage
             self.corpus_lang = options.language

-                
+            self.keys = DoConf(self.ConfigPath['key']).getoptions()
+ 

 
 

-            #print 'PAS DE CODECS POUR CABLE'

             ReadLexique(self, lang = options.language)
             self.expressions = ReadDicoAsDico(self.DictPath.get(options.language + '_exp', 'french_exp'))
             ReadLexique(self, lang = options.language)
             self.expressions = ReadDicoAsDico(self.DictPath.get(options.language + '_exp', 'french_exp'))

+            gramact = [k for k in self.keys if self.keys[k] == 1]
+            gramsup = [k for k in self.keys if self.keys[k] == 2]
+

             if options.filename :
                 self.filename = os.path.abspath(options.filename)
                 if options.corpusconfigfile is not None :
             if options.filename :
                 self.filename = os.path.abspath(options.filename)
                 if options.corpusconfigfile is not None :


@@ -121,31 +126,39 @@ class CmdLine :
                 else :
                     self.history.add(corpus.parametres)
                     corpus = copycorpus(corpus)
                 else :
                     self.history.add(corpus.parametres)
                     corpus = copycorpus(corpus)

-
-                #with codecs.open(self.filename, 'r', self.corpus_encodage) as f:

             elif options.read :
                 corpus = Corpus(self, parametres = DoConf(options.read).getoptions('corpus'), read = options.read)
                 corpus.parametres['pathout'] = os.path.dirname(os.path.abspath(options.read))
                 pathout = os.path.dirname(os.path.dirname(os.path.abspath(options.read)))
                 self.corpus = corpus
             elif options.read :
                 corpus = Corpus(self, parametres = DoConf(options.read).getoptions('corpus'), read = options.read)
                 corpus.parametres['pathout'] = os.path.dirname(os.path.abspath(options.read))
                 pathout = os.path.dirname(os.path.dirname(os.path.abspath(options.read)))
                 self.corpus = corpus

+                print self.corpus
+                corpus.parametres['pathout'] = '/home/pierre/fac/etudiant/verdier/corpus20_corpus_2/test2'
+                BuildSubCorpus(corpus, parametres = {'fromthem' : True, 'theme' : [u'-*thématique_idéal']})

 
             if corpus is not None :
                 corpus.conn_all()
 
             if corpus is not None :
                 corpus.conn_all()

-                corpus = SubCorpus(self, corpus, [0,1,2,3,4,5,6,7])
-                corpus.conn_all()
+                #corpus = SubCorpus(self, corpus, [0,1,2,3,4,5,6,7])
+                #corpus.conn_all()

                 corpus.make_lems()
                 corpus.parse_active(gramact, gramsup)
                 corpus.make_lems()
                 corpus.parse_active(gramact, gramsup)

-                print corpus.getlemconcorde('de').fetchall()
+                #print corpus.getlemconcorde('de').fetchall()

 #            log.warning('ATTENTION gethapaxuces')
 #            MakeUciStat(corpus)
 #            log.warning('ATTENTION gethapaxuces')
 #            MakeUciStat(corpus)

-#            qfqsdf

             #corpus.gethapaxuces()
             #corpus.gethapaxuces()

-            #ucisize = corpus.getucisize()
-            #ucisize = [`val` for val in ucisize]
-            #uciet = [uci.etoiles[1] for uci in corpus.ucis]
-            #res = zip(uciet, ucisize)
-            #with open('ucisize.csv', 'w') as f :
-            #    f.write('\n'.join(['\t'.join(val) for val in res]))
+             #   ucisize = corpus.getucisize()
+             #   ucisize = [`val` for val in ucisize]
+                #uciet = [uci.etoiles[1:] for uci in corpus.ucis]
+                #uceet = [corpus.ucis[uce.uci].etoiles[1:] for uci in corpus.ucis for uce in uci.uces]
+                #print uceet[0:10]
+                #for line in uceet :
+                #    print '\t'.join(line)
+                #res = zip(uciet, ucisize)
+             #   res = [uciet[i] + [ucisize[i]] for i, val in enumerate(uciet)]
+             #   print res[0:10]
+                #ucesize = corpus.getucesize()
+                #print ucesize[0:40]
+                #with open('sentences_size.csv', 'w') as f :
+                #    f.write('\n'.join([`val`  for val in ucesize]))

                 #    self.content = f.read()
                 #self.content = self.content.replace('\r','')
                 if options.type_analyse == 'alceste' :
                 #    self.content = f.read()
                 #self.content = self.content.replace('\r','')
                 if options.type_analyse == 'alceste' :


@@ -155,7 +168,7 @@ class CmdLine :
                     #corpus.read_corpus()
                     #corpus.parse_active(gramact, gramsup)
                     config['type'] = 'alceste'
                     #corpus.read_corpus()
                     #corpus.parse_active(gramact, gramsup)
                     config['type'] = 'alceste'

-                    self.Text = Alceste(self, corpus, parametres = config)
+                    self.Text = Reinert(self, corpus, parametres = config)

                 #    self.Text = AnalyseAlceste(self, cmd = True, big = True)
                     #self.Text = AnalyseAlceste(self, cmd = True)
                 elif options.type_analyse == 'pam' :
                 #    self.Text = AnalyseAlceste(self, cmd = True, big = True)
                     #self.Text = AnalyseAlceste(self, cmd = True)
                 elif options.type_analyse == 'pam' :


@@ -166,10 +179,12 @@ class CmdLine :
                     self.Text = Stat(self, corpus, parametres = {'type':'stat'})
                 elif options.type_analyse == 'spec' :
                     self.Text = Lexico(self, corpus, config = {'type' : 'spec'})
                     self.Text = Stat(self, corpus, parametres = {'type':'stat'})
                 elif options.type_analyse == 'spec' :
                     self.Text = Lexico(self, corpus, config = {'type' : 'spec'})

+                elif options.type_analyse == 'simitxt' :
+                    self.Text = SimiTxt(self, corpus, parametres = parametres)

             #print self.Text.corpus.hours, 'h', self.Text.corpus.minutes,'min', self.Text.corpus.seconds, 's'
 #            self.Text.corpus.make_colored_corpus('colored.html')
 
 if __name__ == '__main__':
     __name__ = 'Main'
             #print self.Text.corpus.hours, 'h', self.Text.corpus.minutes,'min', self.Text.corpus.seconds, 's'
 #            self.Text.corpus.make_colored_corpus('colored.html')
 
 if __name__ == '__main__':
     __name__ = 'Main'

-    CmdLine()
+    CmdLine(AppliPath = AppliPath)