X-Git-Url: http://iramuteq.org/git?p=iramuteq;a=blobdiff_plain;f=functions.py;h=2d72b4c8bca717a1bb5119535c97e271d87e919f;hp=417e91700cae28c4103697a29d1e51d2ca2e7ec2;hb=287f9e72c3e3d666b016dff0fa3dc39419adfcc2;hpb=f24454f5d67c621e94a76410a1e8e9a83c0c138b diff --git a/functions.py b/functions.py index 417e917..2d72b4c 100644 --- a/functions.py +++ b/functions.py @@ -21,6 +21,7 @@ import datetime from copy import copy from shutil import copyfile import shelve +import json #from dialog import BugDialog import logging @@ -30,6 +31,23 @@ 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 @@ -39,7 +57,9 @@ class TGen : 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()] @@ -55,6 +75,7 @@ class TGen : 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)) @@ -98,7 +119,7 @@ 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']} @@ -141,7 +162,7 @@ class History : 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 : @@ -178,6 +199,19 @@ 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 @@ -188,7 +222,7 @@ class History : for analyse in anatodel : print 'cleaning :', analyse['name'] self.delete(analyse) - + def __str__(self) : return str(self.history) @@ -196,7 +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 : @@ -228,7 +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) : @@ -252,8 +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) : @@ -278,7 +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']) @@ -294,7 +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): @@ -363,15 +400,8 @@ 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() @@ -405,17 +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 @@ -480,6 +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): @@ -506,7 +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}) @@ -543,7 +574,10 @@ 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(), sep = ';'): #file = open(filein) @@ -655,37 +689,37 @@ 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 - - - def progressbar(self, maxi) : - if 'parent' in dir(self) : - parent = self.parent - else : - parent = self + ira = wx.GetApp().GetTopWindow() + parent = ira try : - print '###horrible hack progressbar' maxi = int(maxi) except : maxi = 1 - return wx.ProgressDialog("Traitements", + 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 = {} @@ -695,7 +729,7 @@ def treat_var_mod(variables) : 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'_') @@ -729,9 +763,34 @@ def doconcorde(corpus, uces, mots, uci = False) : 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))