Hello.
I am writing a program that reads in a text file, extracts each of the
words and replaces a different document with the words. It works great
until it encounter a non-english letter.
I have tried the following:
self.f = codecs.open(ordliste, 'r', 'utf-8')
where I open the first file.
And
en = unicode(en)
en = en.encode('utf-8')
as well as
en = en.decode('iso-8859-1')
where
each word is entered from the document.
But, still, I get this error:
UnicodeDecodeError: 'ascii' codec can't decode byte 0xe5 in position 17:
ordinal not in range(128)
As well as this:
UnicodeDecodeError: 'utf8' codec can't decode bytes in position 168-170:
invalid data
if I skips the second part.
What is wrong? How can I fix this? I am using ActiveState Python 2.3 and
WinXp.
Thanks in advance...
This is the whole source:
from win32com.client import Dispatch
import time
import codecs
class oversett:
def __init__(self, ordliste, dokument):
objWord = Dispatch("Word.Application")
self.f = codecs.open(ordliste, 'r', 'utf-8')
#self.f = open(ordliste)
objDoc = objWord.Documents.Open(dokument)
self.objSelection = objWord.Selection
def kjor(self):
s = time.clock()
wdReplaceAll = 2
wdFindContinue = 1
t = 1
for i in self.f.readlines():
en = i.split('\t')[0]
#en = str(en).decode('iso-8859-1')
#en = en.decode('iso-8859-1')
en = unicode(en)
en = en.encode('utf-8')
print en
to = i.split('\t')[1]
#to = str(to).decode('iso-8859-1')
#to = to.decode('iso-8859-1')
to = unicode(to)
to = to.encode('utf-8')
t = t + 1
if t % 1000 == 0:
print t
try:
self.objSelection.Find.Execute(en, False, True, False,
False, True, True, wdFindContinue, True, to, wdReplaceAll,
False, False, False, False)
except UnicodeEncodeError:
print 'pokker'
except:
pass
print time.clock() - s
if __name__ == '__main__':
n = oversett('c:/ordliste.txt','c:/foo.doc')
n.kjor()
--
This email has been scanned for viruses & spam by Decna as - www.decna.no
Denne e-posten er sjekket for virus & spam av Decna as - www.decna.no
_______________________________________________
Tutor maillist - Tutor@python.org
http://mail.python.org/mailman/listinfo/tutor
