X-Git-Url: http://www.iramuteq.org/git?a=blobdiff_plain;f=functions.py;h=3472b77d411a60567df32abdc2f4df7f1aba0854;hb=refs%2Fheads%2F3.0;hp=1a6d5235fb461335e6331c34a93d679e2399cdce;hpb=82dde3ff5f415750e7968fcacf8b0b7d18d2ce53;p=iramuteq
diff --git a/functions.py b/functions.py
index 1a6d523..add77d8 100755
--- a/functions.py
+++ b/functions.py
@@ -50,7 +50,7 @@ def open_folder(folder):
else:
opener ="open" if sys.platform == "darwin" else "xdg-open"
#call([opener, folder])
- call(["%s %s &" % (opener, folder)], shell=True)
+ call(["%s '%s' &" % (opener, folder)], shell=True)
def normpath_win32(path) :
if not sys.platform == 'win32' :
@@ -83,13 +83,13 @@ class TGen :
def write(self, path = None):
if path is None :
path = self.path
- with open(path, 'w') as f :
+ with open(path, 'w', encoding='utf8') as f :
f.write('\n'.join(['\t'.join([val] + self.tgen[val]) for val in self.tgen]))
def writetable(self, pathout, tgens, totocc):
etoiles = list(totocc.keys())
etoiles.sort()
- with open(pathout, 'w') as f :
+ with open(pathout, 'w', encoding='utf8') as f :
line = '\t'.join(['tgens'] + etoiles) + '\n'
f.write(line)
for t in tgens :
@@ -117,7 +117,9 @@ class History :
self.read()
def read(self) :
- d = shelve.open(self.filein)
+ with open(self.filein, 'r') as fjson :
+ d = json.load(fjson)
+# d = shelve.open(self.filein, protocol=1)
self.history = d.get('history', [])
self.matrix = d.get('matrix', [])
self.ordercorpus = dict([[corpus['uuid'], i] for i, corpus in enumerate(self.history)])
@@ -125,13 +127,16 @@ class 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()
+# d.close()
def write(self) :
- d = shelve.open(self.filein)
+ d = {}
d['history'] = self.history
d['matrix'] = self.matrix
- d.close()
+ with open(self.filein, 'w') as f :
+ f.write(json.dumps(d, indent=4, default=str))
+ #d = shelve.open(self.filein, protocol=1)
+ #d.close()
def add(self, analyse) :
log.info('add to history %s' % analyse.get('corpus_name', 'pas un corpus'))
@@ -384,7 +389,7 @@ class DoConf :
def write_tab(tab, fileout) :
- csvWriter = csv.writer(open(fileout, 'w'), delimiter=';', quoting = csv.QUOTE_NONNUMERIC)
+ csvWriter = csv.writer(open(fileout, 'w', newline='', encoding='utf8'), delimiter=';', quoting = csv.QUOTE_NONNUMERIC)
csvWriter.writerows(tab)
class BugDialog(wx.Dialog):
@@ -428,7 +433,7 @@ def CreateIraFile(DictPathOut, clusternb, corpname='corpus_name', section = 'ana
AnalyseConf.set(section, 'clusternb', clusternb)
AnalyseConf.set(section, 'corpus_name', corpname)
- fileout = open(DictPathOut['ira'], 'w')
+ fileout = open(DictPathOut['ira'], 'w', encoding='utf8')
AnalyseConf.write(fileout)
fileout.close()
@@ -511,10 +516,10 @@ def treat_line_alceste(i, line) :
line[5] = str(float(line[5].replace(',', '.')))[0:7]
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()):
+def ReadProfileAsDico(File, Alceste=False, encoding = 'utf8'):
dictlem = {}
print('lecture des profiles')
- FileReader = codecs.open(File, 'r', encoding)
+ FileReader = open(File, 'r', encoding='utf8')
Filecontent = FileReader.readlines()
FileReader.close()
DictProfile = {}
@@ -674,7 +679,7 @@ def PlaySound(parent):
print('pas de son')
def ReadDicoAsDico(dicopath):
- with codecs.open(dicopath, 'r', 'UTF8') as f:
+ with open(dicopath, 'r', encoding='UTF8') as f:
content = f.readlines()
lines = [line.rstrip('\n\r').replace('\n', '').replace('"', '').split('\t') for line in content if line != '']
return dict([[line[0], line[1:]] for line in lines])
@@ -691,9 +696,9 @@ def ReadLexique(parent, lang = 'french', filein = None):
else :
parent.lexique = ReadDicoAsDico(filein)
-def ReadList(filein, encoding = sys.getdefaultencoding(), sep = ';'):
+def ReadList(filein, encoding = 'utf8', sep = ';'):
#file = open(filein)
- with codecs.open(filein, 'r', encoding) as f :
+ with open(filein, 'r', encoding='utf8') 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)
@@ -805,11 +810,12 @@ def launchcommand(mycommand):
Popen(mycommand)
def print_liste(filename,liste):
- with open(filename,'w') as f :
+ with open(filename,'w', encoding='utf8') as f :
for graph in liste :
f.write(';'.join(graph) +'\n')
-def read_list_file(filename, encoding = sys.getdefaultencoding()):
- with codecs.open(filename,'r', encoding) as f:
+
+def read_list_file(filename, encoding = 'utf8'):
+ with open(filename,'r', encoding='utf8') as f:
content=f.readlines()
ncontent=[line.replace('\n','').split(';') for line in content if line.strip() != '']
return ncontent
@@ -854,7 +860,7 @@ def treat_var_mod(variables) :
# var_mod[var].append(variable)
return var_mod
-def doconcorde(corpus, uces, mots, uci = False) :
+def doconcorde(corpus, uces, mots, uci = False, fontsize=16) :
if not uci :
ucestxt1 = [row for row in corpus.getconcorde(uces)]
else :
@@ -866,21 +872,23 @@ def doconcorde(corpus, uces, mots, uci = False) :
listmot = [corpus.getforme(fid).forme for lem in listmot for fid in lem]
mothtml = ['%s' % mot for mot in listmot]
dmots = dict(list(zip(listmot, mothtml)))
+ presfont = '' % fontsize
+ font = '' % fontsize
for uce in uces :
ucetxt = ucestxt1[uce].split()
ucetxt = ' '.join([dmots.get(mot, mot) for mot in ucetxt])
if not uci :
uciid = corpus.getucefromid(uce).uci
- ucis_txt.append('' + ' '.join(corpus.ucis[corpus.getucefromid(uce).uci].etoiles) + ' *%i_%i
' % (uciid, uce, uciid, uce))
+ ucis_txt.append(presfont + ' '.join(corpus.ucis[corpus.getucefromid(uce).uci].etoiles) + ' *%i_%i
' % (uciid, uce, uciid, uce))
else :
- ucis_txt.append('' + ' '.join(corpus.ucis[uce].etoiles) + '
')
- ucestxt.append(ucetxt)
+ ucis_txt.append(presfont + ' '.join(corpus.ucis[uce].etoiles) + '')
+ ucestxt.append(font + ucetxt + '')
return ucis_txt, ucestxt
def getallstcarac(corpus, analyse) :
pathout = PathOut(analyse['ira'])
- profils = ReadProfileAsDico(pathout['PROFILE_OUT'], Alceste, self.encoding)
+ profils = ReadProfileAsDico(pathout['PROFILE_OUT'], Alceste, 'utf8')
print(profils)
def read_chd(filein, fileout):
@@ -1016,7 +1024,7 @@ def translateprofile(corpus, dictprofile, lf='it', lt='fr', maxword = 50) :
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 :
+ with open(dictpathout['translations.txt'], 'r', encoding='utf8') as f :
translist = f.read()
translist = [line.split('\t') for line in translist.splitlines()]
else :
@@ -1034,13 +1042,13 @@ def write_translation_profile(prof, lems, language, dictpathout) :
elif line[0] == '*****' :
rest[i] = ['*****','*','*', '*', '*', '*']
toprint += rest
- with open(dictpathout['translation_profile_%s.csv' % language], 'w') as f :
+ with open(dictpathout['translation_profile_%s.csv' % language], 'w', encoding='utf8') as f :
f.write('\n'.join([';'.join(line) for line in toprint]))
- with open(dictpathout['translation_words_%s.csv' % language], 'w') as f :
+ with open(dictpathout['translation_words_%s.csv' % language], 'w', encoding='utf8') as f :
f.write('\n'.join(['\t'.join([val, lems[val]]) for val in lems]))
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 :
+ with open(dictpathout['translations.txt'], 'w', encoding='utf8') as f :
f.write('\n'.join(['\t'.join(line) for line in translist]))
def makesentidict(infile, language) :