X-Git-Url: http://iramuteq.org/git?p=iramuteq;a=blobdiff_plain;f=functions.py;h=b41c483545574ab9670bb31f9f4dfb00a1c9284d;hp=f2b57df94923c5e82df69d89cec5ede64eb692a0;hb=b4ab59a79dbc62d4234778e793c05718648c6775;hpb=8e68628ab2d388b0a60350be5f5ceca505fbfa8a diff --git a/functions.py b/functions.py index f2b57df..b41c483 100644 --- a/functions.py +++ b/functions.py @@ -2,7 +2,7 @@ # -*- coding: utf-8 -*- #Author: Pierre Ratinaud #Copyright (c) 2008-2012 Pierre Ratinaud -#Lisense: GNU/GPL +#License: GNU/GPL import wx import re @@ -21,6 +21,7 @@ import datetime from copy import copy from shutil import copyfile import shelve +import json #from dialog import BugDialog import logging @@ -30,12 +31,72 @@ log = logging.getLogger('iramuteq') 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 + self.tgen = {} + self.encoding = encoding + + def __getitem__(self, key): + return self.tgen[key] + + 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()] + tgen = dict([[line[0], line[1:]] for line in tgen]) + self.tgen = tgen + self.path = path + + def write(self, path = None): + if path is None : + path = self.path + with open(path, 'w') as f : + f.write('\n'.join(['\t'.join([val] + self.tgen[val]) for val in self.tgen]).encode(self.encoding)) + + 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)) + for t in tgens : + line = '\t'.join([t] + [`tgens[t][et]` for et in etoiles]) + '\n' + f.write(line.encode(self.encoding)) + i = 0 + totname = 'total' + while totname + `i` in tgens : + i += 1 + totname = totname + `i` + line = '\t'.join([totname] + [`totocc[et]` for et in etoiles]) + '\n' + f.write(line.encode(self.encoding)) + class History : def __init__(self, filein, syscoding = 'utf8') : self.filein = filein self.syscoding = syscoding - self.corpora = {} + self.corpus = {} self.openedcorpus = {} + self.openedmatrix = {} self.orph = [] self.analyses = {} self.history = [] @@ -50,6 +111,7 @@ class History : self.corpus = dict([[corpus['uuid'], corpus] for corpus in self.history]) self.analyses = dict([[analyse['uuid'], analyse] for corpus in self.history for analyse in corpus.get('analyses', [])]) self.matrixanalyse = dict([[mat['uuid'], mat] for mat in self.matrix]) + self.ordermatrix = dict([[matrix['uuid'], i] for i, matrix in enumerate(self.matrix)]) d.close() def write(self) : @@ -57,10 +119,13 @@ 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']} + if tosave['uuid'] in self.corpus : + log.info('problem : this uuid is already in history : %s' % tosave['uuid']) + return if analyse.get('corpus', False) : if analyse['uuid'] in self.analyses : return @@ -76,17 +141,28 @@ class History : self.orph.append(tosave) else : tosave['corpus_name'] = analyse['corpus_name'] + #self.ordercorpus[tosave['uuid']] = len(history) + #self.corpus[tosave['uuid']] = analyse self.history.append(tosave) self.write() self.read() def addMatrix(self, analyse) : - tosave = {'uuid' : analyse['uuid'], 'ira': analyse['ira'], 'type' : analyse['type']} - tosave['name'] = analyse['name'] + tosave = analyse + #tosave['matrix_name'] = analyse['matrix_name'] + tosave['analyses'] = [] self.matrix.append(tosave) self.write() self.read() + def addMatrixAnalyse(self, analyse) : + tosave = {'uuid' : analyse['uuid'], 'ira': analyse['ira'], 'type' : analyse['type'], 'matrix' : analyse['matrix']} + tosave['name'] = analyse['name'] + if tosave['matrix'] in self.ordermatrix : + 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 : @@ -108,6 +184,7 @@ class History : self.history.pop(self.ordercorpus[analyse['uuid']]) if analyse['uuid'] in self.openedcorpus : del self.openedcorpus[analyse['uuid']] + log.info('delete corpus : %s' % analyse['uuid']) elif analyse['uuid'] in self.analyses : todel = [i for i, ana in enumerate(self.corpus[analyse['corpus']]['analyses']) if ana['uuid'] == analyse['uuid']][0] self.history[self.ordercorpus[analyse['corpus']]]['analyses'].pop(todel) @@ -121,7 +198,31 @@ class History : 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 corpus in corpustodel : + print 'cleaning :', corpus['corpus_name'] + self.delete(corpus, corpus = True) + anatodel = [analyse for corpus in self.history for analyse in corpus.get('analyses', []) if not os.path.exists(analyse.get('ira', '/'))] + for analyse in anatodel : + print 'cleaning :', analyse['name'] + self.delete(analyse) + def __str__(self) : return str(self.history) @@ -129,7 +230,9 @@ class DoConf : 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 : @@ -161,7 +264,7 @@ class DoConf : if 'type' not in parametres : parametres['type'] = section return parametres - + def makeoptions(self, sections, parametres, outfile = None) : txt = '' for i, section in enumerate(sections) : @@ -185,8 +288,9 @@ class DoConf : 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) : @@ -211,7 +315,7 @@ def write_tab(tab, fileout) : 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']) @@ -227,7 +331,7 @@ class BugDialog(wx.Dialog): # 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): @@ -296,21 +400,15 @@ def treat_line_alceste(i, line) : 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() 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) @@ -337,17 +435,17 @@ def GetTxtProfile(dictprofile, cluster_size) : 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 = "" - 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 = "" + excTb = traceback.format_tb(trbk, maxTBlevel) + return (excName, excArgs, excTb) #fonction des etudiants de l'iut @@ -412,6 +510,7 @@ exceptions = {'paragrapheOT' : u"Un problème de formatage (présence d'un marqu '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): @@ -429,7 +528,7 @@ def BugReport(parent, error = None): txt = exc else : if exc in exceptions : - txt = exceptions[mss] + txt = exceptions[exc] else : txt = exc title = "Information" @@ -438,7 +537,7 @@ 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}) @@ -465,12 +564,8 @@ def PlaySound(parent): def ReadDicoAsDico(dicopath): with codecs.open(dicopath, 'r', 'UTF8') as f: content = f.readlines() - dico = {} - for line in content : - if line[0] != u'': - line = line.replace(u'\n', '').replace('"', '').split('\t') - dico[line[0]] = line[1:] - return dico + lines = [line.rstrip('\n\r').replace(u'\n', '').replace('"', '').split('\t') for line in content if line != u''] + return dict([[line[0], line[1:]] for line in lines]) def ReadLexique(parent, lang = 'french', filein = None): if lang != 'other' : @@ -479,20 +574,26 @@ def ReadLexique(parent, lang = 'french', filein = None): 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()): +def ReadList(filein, encoding = sys.getdefaultencoding(), sep = ';'): #file = open(filein) - file = codecs.open(filein, 'r', encoding) - content = file.readlines() - file.close() + with codecs.open(filein, 'r', encoding) as f : + content = f.read() + content = [line.replace('\n', '').replace('\r','').replace('\"', '').replace(',', '.').split(sep) for line in content.splitlines()] + #file = codecs.open(filein, 'r', encoding) + #content = file.readlines() + #file.close() first = content.pop(0) - first = first.replace('\n', '').replace('\r','').replace('\"', '').split(';') + #first = first.replace('\n', '').replace('\r','').replace('\"', '').split(sep) dict = {} i = 0 for line in content: - line = line.replace('\n', '').replace('\r','').replace('\"', '').replace(',', '.') - line = line.split(';') + #line = line.replace('\n', '').replace('\r','').replace('\"', '').replace(',', '.') + #line = line.split(';') nline = [line[0]] for val in line[1:]: if val == u'NA' : @@ -519,7 +620,6 @@ def exec_rcode(rpath, rcode, wait = True, graph = False): if sys.platform == 'darwin' : try : macversion = platform.mac_ver()[0].split('.') - print macversion if int(macversion[1]) < 5 : needX11 = True else : @@ -528,18 +628,21 @@ def exec_rcode(rpath, rcode, wait = True, graph = False): needX11 = False rpath = rpath.replace('\\','\\\\') + env = os.environ.copy() + if sys.platform == 'darwin' and 'LC_ALL' not in env: + env['LC_ALL'] = 'en_US.UTF-8' if not graph : if wait : if sys.platform == 'win32': error = call(["%s" % rpath, "--vanilla","--slave","-f", "%s" % rcode]) else : - error = call([rpath, '--vanilla','--slave',"-f %s" % rcode]) + error = call([rpath, '--slave', "--vanilla", "-f %s" % rcode, "--encoding=UTF-8"], env = env) return error else : if sys.platform == 'win32': pid = Popen(["%s" % rpath, '--vanilla','--slave','-f', "%s" % rcode]) else : - pid = Popen([rpath, '--vanilla','--slave',"-f %s" % rcode], stderr = PIPE) + pid = Popen([rpath, '--slave', "--vanilla", "-f %s" % rcode, "--encoding=UTF-8"], stderr = PIPE, env = env) return pid else : if wait : @@ -547,18 +650,18 @@ def exec_rcode(rpath, rcode, wait = True, graph = False): error = call(["%s" % rpath, '--vanilla','--slave','-f', "%s" % rcode]) elif sys.platform == 'darwin' and needX11: os.environ['DISPLAY'] = ':0.0' - error = call([rpath, '--vanilla','--slave',"-f %s" % rcode]) + error = call([rpath, '--vanilla','--slave',"-f %s" % rcode, "--encoding=UTF-8"], env = env) else : - error = call([rpath, '--vanilla','--slave',"-f %s" % rcode]) + error = call([rpath, '--vanilla','--slave',"-f %s" % rcode, "--encoding=UTF-8"], env = env) return error else : if sys.platform == 'win32': pid = Popen(["%s" % rpath, '--vanilla','--slave','-f', "%s" % rcode]) elif sys.platform == 'darwin' and needX11: os.environ['DISPLAY'] = ':0.0' - pid = Popen([rpath, '--vanilla','--slave',"-f %s" % rcode], stderr = PIPE) + pid = Popen([rpath, '--vanilla','--slave',"-f %s" % rcode, "--encoding=UTF-8"], stderr = PIPE, env = env) else : - pid = Popen([rpath, '--vanilla','--slave',"-f %s" % rcode], stderr = PIPE) + pid = Popen([rpath, '--vanilla','--slave',"-f %s" % rcode, "--encoding=UTF-8"], stderr = PIPE, env = env) return pid def check_Rresult(parent, pid) : @@ -586,90 +689,244 @@ def check_Rresult(parent, pid) : 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 - -class MessageImage(wx.Frame): - def __init__(self, parent,title, size): - wx.Frame.__init__ ( self, parent, id = wx.ID_ANY, title = title, pos = wx.DefaultPosition, size = size, style = wx.DEFAULT_FRAME_STYLE ) - self.SetSizeHintsSz( wx.DefaultSize, wx.DefaultSize ) - self.imageFile = False - self.imagename = u"chi_classe.png" - self.HtmlPage = wx.html.HtmlWindow(self, -1) - self.HtmlPage.SetMinSize(size) - if "gtk2" in wx.PlatformInfo: - self.HtmlPage.SetStandardFonts() - self.HtmlPage.SetFonts('Courier', 'Courier') - - self.button_1 = wx.Button(self, wx.ID_CANCEL) - self.button_2 = wx.Button(self, wx.ID_SAVE) - self.Bind(wx.EVT_BUTTON, self.OnCloseMe, self.button_1) - self.Bind(wx.EVT_BUTTON, self.OnSaveImage, self.button_2) - self.do_layout() - - def do_layout(self): - self.sizer_1 = wx.BoxSizer(wx.VERTICAL) - self.sizer_2 = wx.BoxSizer(wx.HORIZONTAL) - self.sizer_1.Add(self.HtmlPage, 2, wx.EXPAND, 0) - - self.m_sdbSizer1 = wx.StdDialogButtonSizer() - self.m_sdbSizer1.AddButton( self.button_2 ) - self.m_sdbSizer1.AddButton( self.button_1 ) - self.m_sdbSizer1.Realize() - self.sizer_1.Add(self.m_sdbSizer1, 0, wx.EXPAND, 5) - self.SetSizer(self.sizer_1) - self.Layout() - self.sizer_1.Fit( self ) - - def addsaveimage(self, imageFile) : - self.imageFile = imageFile - - def OnCloseMe(self, event): - self.Destroy() - - def OnSaveImage(self, event) : - dlg = wx.FileDialog( - self, message="Enregistrer sous...", defaultDir=os.getcwd(), - defaultFile= self.imagename, wildcard="png|*.png", style=wx.SAVE | wx.OVERWRITE_PROMPT - ) - dlg.SetFilterIndex(2) - dlg.CenterOnParent() - if dlg.ShowModal() == wx.ID_OK: - path = dlg.GetPath() - copyfile(self.imageFile, path) - 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 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 = ['%s' % mot 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('

' + ' '.join(corpus.ucis[corpus.getucefromid(uce).uci].etoiles) + '

') + else : + ucis_txt.append('

' + ' '.join(corpus.ucis[uce].etoiles) + '

') + 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'))