from copy import copy
from shutil import copyfile
import shelve
+import json
#from dialog import BugDialog
import logging
indices_simi = [u'cooccurrence' ,'pourcentage de cooccurrence',u'Russel',u'Jaccard', 'Kulczynski1', 'Kulczynski2', 'Mountford', 'Fager', 'simple matching', 'Hamman', 'Faith', 'Tanimoto', 'Dice', 'Phi', 'Stiles', 'Michael', 'Mozley', 'Yule', 'Yule2', 'Ochiai', 'Simpson', 'Braun-Blanquet','Chi-squared', 'Phi-squared', 'Tschuprow', 'Cramer', 'Pearson', 'binomial']
+
+def open_folder(folder):
+ if sys.platform == "win32":
+ os.startfile(folder)
+ else:
+ opener ="open" if sys.platform == "darwin" else "xdg-open"
+ call([opener, folder])
+
+def normpath_win32(path) :
+ if not sys.platform == 'win32' :
+ return path
+ while '\\\\' in path :
+ path = path.replace('\\\\', '\\')
+ if path.startswith('\\') and not path.startswith('\\\\') :
+ path = '\\' + path
+ return path
+
class TGen :
def __init__(self, path = None, encoding = 'utf8'):
self.path = path
def __getitem__(self, key):
return self.tgen[key]
- def read(self, path):
+ def read(self, path = None):
+ if path is None :
+ path = self.path
with codecs.open(path, 'r', self.encoding) as f :
tgen = f.read()
tgen = [line.split('\t') for line in tgen.splitlines()]
def writetable(self, pathout, tgens, totocc):
etoiles = totocc.keys()
+ etoiles.sort()
with open(pathout, 'w') as f :
line = '\t'.join([u'tgens'] + etoiles) + '\n'
f.write(line.encode(self.encoding))
while totname + `i` in tgens :
i += 1
totname = totname + `i`
- line = '\t'.join([totname] + [`totocc[et]` for et in etoiles])
+ line = '\t'.join([totname] + [`totocc[et]` for et in etoiles]) + '\n'
f.write(line.encode(self.encoding))
class History :
d['history'] = self.history
d['matrix'] = self.matrix
d.close()
-
+
def add(self, analyse) :
log.info('add to history %s' % analyse.get('corpus_name', 'pas un corpus'))
tosave = {'uuid' : analyse['uuid'], 'ira': analyse['ira'], 'type' : analyse['type']}
self.matrix[self.ordermatrix[tosave['matrix']]]['analyses'].append(tosave)
self.write()
self.read()
-
+
def addmultiple(self, analyses) :
log.info('add multiple')
for analyse in analyses :
def rmtab(self, analyse) :
del self.opened[analyse['uuid']]
+ def update(self, analyse) :
+ if 'matrix_name' in analyse :
+ self.matrixanalyse[analyse['uuid']].update(analyse)
+ elif 'corpus_name' in analyse :
+ self.corpus[analyse['uuid']].update(analyse)
+ elif 'corpus' in analyse :
+ self.analyses[analyse['uuid']].update(analyse)
+ else :
+ toupdate = [an for an in self.matrixanalyse[analyse['matrix']]['analyses'] if an['uuid'] == analyse['uuid']]
+ toupdate[0].update(analyse)
+ self.write()
+ self.read()
+
def clean(self) :
corpustodel = [corpus for corpus in self.history if not os.path.exists(corpus['ira'])]
print corpustodel
for analyse in anatodel :
print 'cleaning :', analyse['name']
self.delete(analyse)
-
+
def __str__(self) :
return str(self.history)
def __init__(self, configfile=None, diff = None, parametres = None) :
self.configfile = configfile
self.conf = ConfigParser()
+
if configfile is not None :
+ configfile = normpath_win32(configfile)
self.conf.readfp(codecs.open(configfile, 'r', 'utf8'))
self.parametres = {}
if parametres is not None :
if 'type' not in parametres :
parametres['type'] = section
return parametres
-
+
def makeoptions(self, sections, parametres, outfile = None) :
txt = ''
for i, section in enumerate(sections) :
txt += '%s = %s\n' % (option, `parametres[i][option]`)
if outfile is None :
outfile = self.configfile
- with codecs.open(outfile, 'w', 'utf8') as f :
- f.write(txt)
+ outfile = normpath_win32(outfile)
+ with open(outfile, 'w') as f :
+ f.write(txt.encode('utf8'))
#self.conf.write(f)
def totext(self, parametres) :
class BugDialog(wx.Dialog):
def __init__(self, *args, **kwds):
# begin wxGlade: MyDialog.__init__
- kwds["style"] = wx.DEFAULT_DIALOG_STYLE
+ kwds["style"] = wx.DEFAULT_DIALOG_STYLE | wx.STAY_ON_TOP
kwds["size"] = wx.Size(500, 200)
wx.Dialog.__init__(self, *args, **kwds)
self.SetTitle(kwds['title'])
# begin wxGlade: MyDialog.__set_properties
self.SetMinSize(wx.Size(500, 200))
self.text_ctrl_1.SetMinSize(wx.Size(500, 200))
-
+
# end wxGlade
def __do_layout(self):
return [i, int(line[0]), int(line[1]), float(line[2]), float(line[3]), line[6], line[4], line[5]]
def ReadProfileAsDico(File, Alceste=False, encoding = sys.getdefaultencoding()):
- #print 'lecture des profils : ReadProfileAsDico'
- #if Alceste :
- # print 'lecture du dictionnaire de type'
- # dictlem = {}
- # for line in parent.corpus.lem_type_list :
- # dictlem[line[0]] = line[1]
dictlem = {}
print 'lecture des profiles'
- #encoding = sys.getdefaultencoding()
FileReader = codecs.open(File, 'r', encoding)
Filecontent = FileReader.readlines()
FileReader.close()
return '\n\n'.join(proflist)
def formatExceptionInfo(maxTBlevel=5):
- cla, exc, trbk = sys.exc_info()
- try :
- excName = cla.__name__
- except :
- excName = 'None'
- try:
- excArgs = exc.args[0]
- except :
- excArgs = "<no args>"
- excTb = traceback.format_tb(trbk, maxTBlevel)
- return (excName, excArgs, excTb)
+ cla, exc, trbk = sys.exc_info()
+ try :
+ excName = cla.__name__
+ except :
+ excName = 'None'
+ try:
+ excArgs = exc.args[0]
+ except :
+ excArgs = "<no args>"
+ excTb = traceback.format_tb(trbk, maxTBlevel)
+ return (excName, excArgs, excTb)
#fonction des etudiants de l'iut
'EmptyText' : u"Texte vide (probablement un problème de formatage du corpus). Le problème est apparu à la ligne ",
'CorpusEncoding' : u"Problème d'encodage.",
'TextBeforeTextMark' : u"Problème de formatage : du texte avant le premier marqueur de texte (****). Le problème est survenu à la ligne ",
+ 'MissingAnalyse' : u'Aucun fichier à cet emplacement :\n',
}
def BugReport(parent, error = None):
txt += u'*************************************\n'
txt += '\n'.join(excTb).replace(' ', ' ')
txt += excName + '\n'
- txt += exc
+ txt += `exc`
title = "Bug"
dial = BugDialog(parent, **{'title' : title})
else :
parent.lexique = ReadDicoAsDico(filein)
else :
- parent.lexique = {}
+ if filein is None :
+ parent.lexique = {}
+ else :
+ parent.lexique = ReadDicoAsDico(filein)
def ReadList(filein, encoding = sys.getdefaultencoding(), sep = ';'):
#file = open(filein)
else :
return True
+
+def launchcommand(mycommand):
+ Popen(mycommand)
+
def print_liste(filename,liste):
with open(filename,'w') as f :
for graph in liste :
- f.write(';'.join(graph)+'\n')
+ f.write(';'.join(graph).encode(sys.getdefaultencoding())+'\n')
def read_list_file(filename, encoding = sys.getdefaultencoding()):
with codecs.open(filename,'rU', encoding) as f :
content=f.readlines()
ncontent=[line.replace('\n','').split(';') for line in content if line.strip() != '']
return ncontent
-
-
-
def progressbar(self, maxi) :
- if 'parent' in dir(self) :
- parent = self.parent
- else :
- parent = self
- return wx.ProgressDialog("Traitements",
+ ira = wx.GetApp().GetTopWindow()
+ parent = ira
+ try :
+ maxi = int(maxi)
+ except :
+ maxi = 1
+ prog = wx.ProgressDialog("Traitements",
"Veuillez patienter...",
maximum=maxi,
parent=parent,
style=wx.PD_APP_MODAL | wx.PD_AUTO_HIDE | wx.PD_ELAPSED_TIME | wx.PD_CAN_ABORT
)
-
+ prog.SetSize((400,150))
+ #prog.SetIcon(ira._icon)
+ return prog
def treat_var_mod(variables) :
var_mod = {}
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'_')
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
+
+def read_chd(filein, fileout):
+ with open(filein, 'r') as f :
+ content = f.read()
+ #content = [line[3:].replace('"',"").replace(' ','') for line in content.splitlines()]
+ content = [line.split('\t') for line in content.splitlines()]
+ chd = {'name':1, 'children':[]}
+ mere={}
+ for i, line in enumerate(content) :
+ if i == 0 :
+ chd['children'] = [{'name': line[1],'size' : content[i+1][0]}, {'name':line[2], 'size': content[i+1][1]}]
+ mere[line[1]] = chd['children'][0]
+ mere[line[2]] = chd['children'][1]
+ elif not i % 2 :
+ if 'children' in mere[line[0]]:
+ mere[line[0]]['children'].append({'name': line[1],'size' : content[i+1][0]})
+ mere[line[1]] = mere[line[0]]['children'][-1]
+ mere[line[0]]['children'].append({'name': line[2],'size' : content[i+1][1]})
+ mere[line[2]] = mere[line[0]]['children'][-1]
+ else :
+ mere[line[0]]['children'] = [{'name': line[1],'size' : content[i+1][0]}, {'name':line[2], 'size': content[i+1][1]}]
+ mere[line[1]] = mere[line[0]]['children'][-2]
+ mere[line[2]] = mere[line[0]]['children'][-1]
+ with open(fileout, 'w') as f :
+ f.write(json.dumps(chd))
+
+
+translation_languages = {"Afrikaans":"af", "Albanian":"sq", "Amharic":"am", "Arabic":"ar", "Armenian":"hy", "Azeerbaijani":"az", "Basque":"eu", "Belarusian":"be", "Bengali":"bn", "Bosnian":"bs", "Bulgarian":"bg", "Catalan":"ca", "Cebuano":"ceb", "Chichewa":"ny", "Chinese (Simplified)":"zh-CN", "Chinese (Traditional)":"zh-TW", "Corsican":"co", "Croatian":"hr", "Czech":"cs", "Danish":"da", "Dutch":"nl", "English":"en", "Esperanto":"eo", "Estonian":"et", "Filipino":"tl", "Finnish":"fi", "French":"fr", "Frisian":"fy", "Galician":"gl", "Georgian":"ka", "German":"de", "Greek":"el", "Gujarati":"gu", "Haitian Creole":"ht", "Hausa":"ha", "Hawaiian":"haw", "Hebrew":"iw", "Hindi":"hi", "Hmong":"hmn ", "Hungarian":"hu", "Icelandic":"is", "Igbo":"ig", "Indonesian":"id", "Irish":"ga", "Italian":"it", "Japanese":"ja", "Javanese":"jw", "Kannada":"kn", "Kazakh":"kk", "Khmer":"km", "Korean":"ko", "Kurdish":"ku", "Kyrgyz":"ky", "Lao":"lo", "Latin":"la", "Latvian":"lv", "Lithuanian":"lt", "Luxembourgish":"lb", "Macedonian":"mk", "Malagasy":"mg", "Malay":"ms", "Malayalam":"ml", "Maltese":"mt", "Maori":"mi", "Marathi":"mr", "Mongolian":"mn", "Burmese":"my", "Nepali":"ne", "Norwegian":"no", "Pashto":"ps", "Persian":"fa", "Polish":"pl", "Portuguese":"pt", "Punjabi":"ma", "Romanian":"ro", "Russian":"ru", "Samoan":"sm", "Scots Gaelic":"gd", "Serbian":"sr", "Sesotho":"st", "Shona":"sn", "Sindhi":"sd", "Sinhala":"si", "Slovak":"sk", "Slovenian":"sl", "Somali":"so", "Spanish":"es", "Sundanese":"su", "Swahili":"sw", "Swedish":"sv", "Tajik":"tg", "Tamil":"ta", "Telugu":"te", "Thai":"th", "Turkish":"tr", "Ukrainian":"uk", "Urdu":"ur", "Uzbek":"uz", "Vietnamese":"vi", "Welsh":"cy", "Xhosa":"xh", "Yiddish":"yi", "Yoruba":"yo", "Zulu":"zu", }
+
+
+def gettranslation(words, lf, lt) :
+ import urllib2
+ import json
+ agent = {'User-Agent':
+ "Mozilla/4.0 (\
+ compatible;\
+ MSIE 6.0;\
+ Windows NT 5.1;\
+ SV1;\
+ .NET CLR 1.1.4322;\
+ .NET CLR 2.0.50727;\
+ .NET CLR 3.0.04506.30\
+ )"}
+ base_link = "https://translate.googleapis.com/translate_a/single?client=gtx&sl=%s&tl=%s&dt=t&q=%s"
+ print len(words)
+ totrans = urllib2.quote('\n'.join(words).encode('utf8'))
+ link = base_link % (lf, lt, totrans)
+ request = urllib2.Request(link, headers=agent)
+ raw_data = urllib2.urlopen(request).read()
+ data = json.loads(raw_data)
+ return [line[0].decode('utf8').replace(u"'", u'_').replace(u' | ', u'|').replace(u' ', u'_').replace(u'-',u'_').replace(u'\n','') for line in data[0]]
+
+def makenprof(prof, trans, deb=0) :
+ nprof=[]
+ if deb == 0 :
+ nprof.append(prof[0])
+ for i, val in enumerate(trans) :
+ line = prof[deb+i+1][:]
+ line[6] = val
+ nprof.append(line)
+ return nprof
+
+def treatempty(val) :
+ if val.strip() == '' :
+ return '_'
+ else :
+ return val
+
+def translateprofile(corpus, dictprofile, lf='it', lt='fr') :
+ nprof = {}
+ lems = {}
+ for i in range(len(dictprofile)) :
+ prof = dictprofile[`i+1`]
+ try :
+ lenact = prof.index([u'*****', u'*', u'*', u'*', u'*', u'*', '', ''])
+ lensup = -1
+ except ValueError:
+ try :
+ lenact = prof.index([u'*', u'*', u'*', u'*', u'*', u'*', '', ''])
+ lensup = 0
+ except ValueError:
+ lenact = len(prof)
+ lensup = 0
+ try :
+ lensup += prof.index([u'*', u'*', u'*', u'*', u'*', u'*', '', ''])
+ lensup = lensup - lenact
+ except ValueError:
+ lensup += len(prof) - lenact
+ if lenact != 0 :
+ if lenact > 400 :
+ nlenact = 400
+ else :
+ nlenact = lenact
+ actori = [line[6] for line in prof[1:nlenact]]
+ act = [val.replace(u'_', u' ') for val in actori]
+ act = gettranslation(act, lf, lt)
+ for j, val in enumerate(actori) :
+ if act[j] not in lems :
+ lems[act[j]] = val
+ else :
+ while act[j] in lems :
+ act[j] = act[j] + u"+"
+ lems[act[j]] = val
+ nprof[`i+1`] = makenprof(prof, act)
+
+ if lensup != 0 :
+ if lensup > 400 :
+ nlensup = 400
+ else :
+ nlensup = lensup
+ supori = [line[6] for line in prof[(1+lenact):(lenact+nlensup)]]
+ sup = [val.replace(u'_', u' ') for val in supori]
+ sup = [treatempty(val) for val in sup]
+ sup = gettranslation(sup, lf, lt)
+ for j, val in enumerate(supori) :
+ if sup[j] not in lems :
+ lems[sup[j]] = val
+ else :
+ while sup[j] in lems :
+ sup[j] = sup[j] + u"+"
+ lems[sup[j]] = val
+ nprof[`i+1`].append([u'*****', u'*', u'*', u'*', u'*', u'*', '', ''])
+ nprof[`i+1`] += makenprof(prof, sup, deb=lenact)
+
+ try :
+ lenet = prof.index([u'*', u'*', u'*', u'*', u'*', u'*', '', ''])
+ nprof[`i+1`].append([u'*', u'*', u'*', u'*', u'*', u'*', '', ''])
+ nprof[`i+1`] += prof[(lenet+1):]
+ except :
+ pass
+ return nprof, lems
+
+
+def write_translation_profile(prof, lems, language, dictpathout) :
+ if os.path.exists(dictpathout['translations.txt']) :
+ with codecs.open(dictpathout['translations.txt'], 'r', 'utf8') as f :
+ translist = f.read()
+ translist = [line.split('\t') for line in translist.splitlines()]
+ else :
+ translist = []
+ toprint = []
+ toprint.append(['','','','','',''])
+ toprint.append([u'***', u'nb classes', `len(prof)`, u'***', '', ''])
+ for i in range(len(prof)) :
+ toprint.append([u'**', u'classe', `i+1`, u'**', '', ''])
+ toprint.append([u'****'] + prof[`i+1`][0] + [u'****'])
+ rest = [[`line[1]`, `line[2]`, `line[3]`, `line[4]`, line[6], line[7].replace('< 0,0001', '0.00009').replace('NS (','').replace(')','')] for line in prof[`i+1`][1:]]
+ for i, line in enumerate(prof[`i+1`][1:]) :
+ if line[0] == u'*' :
+ rest[i] = [u'*', u'*', u'*', u'*', u'*', u'*']
+ elif line[0] == u'*****' :
+ rest[i] = [u'*****',u'*',u'*', u'*', u'*', u'*']
+ toprint += rest
+ with open(dictpathout['translation_profile_%s.csv' % language], 'w') as f :
+ f.write('\n'.join([';'.join(line) for line in toprint]).encode('utf8'))
+ with open(dictpathout['translation_words_%s.csv' % language], 'w') as f :
+ f.write('\n'.join(['\t'.join([val, lems[val]]) for val in lems]).encode('utf8'))
+ if 'translation_profile_%s.csv' % language not in [val[0] for val in translist] :
+ translist.append(['translation_profile_%s.csv' % language, 'translation_words_%s.csv' % language])
+ with open(dictpathout['translations.txt'], 'w') as f :
+ f.write('\n'.join(['\t'.join(line) for line in translist]).encode('utf8'))
projects / iramuteq / blobdiff