Das deutsche Python-Forum

Code: Alles auswählen

u''.join(r_data)

Code: Alles auswählen

Traceback (most recent call last):
  File "dauCMS.py", line 156, in ?
    main()
  File "dauCMS.py", line 137, in main
    dau_parser.parse_files()
  File "parser.py", line 190, in parse_files
    for token in self.lexer(u''.join(r_data)):
UnicodeDecodeError: 'ascii' codec can't decode byte 0xe4 in position 0: ordinal not in range(128)

Code: Alles auswählen

# Inhalt einlesen
                r_data = open(self.project_path+data_file, 'r').read()

                try:
                    # Inhalt parsen
                    data = ''
                    for token in self.lexer(u''.join(r_data)):
                        data += token.data

Code: Alles auswählen

     f = open(self.project_path+data_file, 'r')
     
     try:
         # Inhalt parsen
         r_data = f.read()
         data = ''
         for token in self.lexer(u''.join(r_data)):
             data += token.data
         # An irgendeiner stelle in dieser Funktion explizit die Datei schließen!
         f.close()

Code: Alles auswählen

str_ = u"üöß"
str2 = str(str_)

Code: Alles auswählen

    str2 = str(str_)
UnicodeEncodeError: 'ascii' codec can't encode characters in position 0-2: ordinal not in range(128)

Code: Alles auswählen

 dau_parser = MainParser(
	                        syntax_list = syntax_list,
	                        project = opts['project'],
	                        template = opts['template'],
	        )

Code: Alles auswählen

class MainParser:
	    def __init__(self, project, template, lexer):

Code: Alles auswählen

str_ = "üöß"
str2 = u"".join(str_)

Code: Alles auswählen

   str2 = u"".join(str_)
UnicodeDecodeError: 'ascii' codec can't decode byte 0xc3 in position 0: ordinal not in range(128)

Code: Alles auswählen

str_ = u"üöß"
str2 = u"".join(str_)

Code: Alles auswählen

str_ = 'öÖäÄüÜ'
str2 = unicode(str_)

Code: Alles auswählen

UnicodeDecodeError: 'ascii' codec can't decode byte 0xc3 in position 0: ordinal not in range(128)

Code: Alles auswählen

import codecs
f = codecs.open("c:\foobar.txt", "iso-8859-1")

Code: Alles auswählen

str_ = "üöß"
str2 = str_.decode('utf-8')

Code: Alles auswählen

#!/usr/bin/env python
# -*- coding: utf-8 -*-
import sys, codecs

stdout_encoding = sys.stdout.encoding or sys.getfilesystemencoding()

str_ = "üöß"
str2 = str_.decode('utf-8')
print str2.encode(stdout_encoding) # -> üöß

Code: Alles auswählen

                # Inhalt einlesen
                r_data = open(self.project_path+data_file, 'r').read()
                if not isinstance(r_data, unicode):
                    r_data = r_data.decode('iso-8859-1')
                else:
                    print 'nöööö'

Code: Alles auswählen

                    try:
                        # geparsten Inhalt nach self.rendered_project_name schreiben
                        # FIXME: " data_file[:4] " -- it's not realy a good resolution...
                        # it's stupid if 'data_file' doesn't end with '.txt'
                        to_write = open(self.rendered_project_path+data_file[:-4]+'.html', 'w')
                        to_write.write(tmp_to_write)
                        to_write.close()
                    except Exception, e:
                        raise ParserError('Error while writing file %s ' % data_file,  e )

Code: Alles auswählen

parser.ParserError: 
An error is ocured:
Error while writing file dokumentation.txt 
'ascii' codec can't encode character u'\xe4' in position 970: ordinal not in range(128)

Code: Alles auswählen

 
                    if self.template_to_render == None:
                        tmp_to_write = data
                    else:
                        tmp_to_write = open('%s/templates/%s/%s.html' %(sys.path[0],\
                                                    self.template_to_render,\
                                                    self.template_to_render),'r').read()

Code: Alles auswählen

 if isinstance(r_data, str):
                            tmp_to_write = tmp_to_write.decode('iso-8859-1')

Code: Alles auswählen

import locale
print locale.getpreferredencoding()

Code: Alles auswählen

>>> f = file("J://Ablage//irgendeinedatei.txt", "r")
>>> bytestring = f.read()
>>> unicodestring = f.read().decode(locale.getpreferredencoding())
>>> f.close()
>>>

Code: Alles auswählen

>>> import codecs
>>> import locale
>>> f = codecs.open("J://Ablage//irgendeinedatei.txt", mode='w', encoding = locale.getpreferredencoding())
>>> f.write(u"löüäßßßß") # hier wissen wir genau, dass es ein UNICODE-String ist. :-)
>>> f.close()
>>>