diff options
| -rw-r--r-- | Doc/lib/libcsv.tex | 46 |
1 files changed, 35 insertions, 11 deletions
diff --git a/Doc/lib/libcsv.tex b/Doc/lib/libcsv.tex index d220345..65053c7 100644 --- a/Doc/lib/libcsv.tex +++ b/Doc/lib/libcsv.tex @@ -456,44 +456,68 @@ def utf_8_encoder(unicode_csv_data): yield line.encode('utf-8') \end{verbatim} -The classes below work just like the \class{csv.reader} and -\class{csv.writer} classes, but they add an \var{encoding} parameter -to allow for encoded files: +For all other encodings the following \class{UnicodeReader} and +\class{UnicodeWriter} classes can be used. They take an additional +\var{encoding} parameter in their constructor and make sure that the data +passes the real reader or writer encoded as UTF-8: \begin{verbatim} -import csv +import csv, codecs, cStringIO -class UnicodeReader: +class UTF8Recoder: + """ + Iterator that reads an encoded stream and reencodes the input to UTF-8 + """ + def __init__(self, f, encoding): + self.reader = codecs.getreader(encoding)(f) + def __iter__(self): + return self + + def next(self): + return self.reader.next().encode("utf-8") + +class UnicodeReader: """ A CSV reader which will iterate over lines in the CSV file "f", which is encoded in the given encoding. """ def __init__(self, f, dialect=csv.excel, encoding="utf-8", **kwds): + f = UTF8Recoder(f, encoding) self.reader = csv.reader(f, dialect=dialect, **kwds) - self.encoding = encoding def next(self): row = self.reader.next() - return [unicode(s, self.encoding) for s in row] + return [unicode(s, "utf-8") for s in row] def __iter__(self): return self class UnicodeWriter: - """ A CSV writer which will write rows to CSV file "f", which is encoded in the given encoding. """ def __init__(self, f, dialect=csv.excel, encoding="utf-8", **kwds): - self.writer = csv.writer(f, dialect=dialect, **kwds) - self.encoding = encoding + # Redirect output to a queue + self.queue = cStringIO.StringIO() + self.writer = csv.writer(self.queue, dialect=dialect, **kwds) + self.stream = f + self.encoder = codecs.getincrementalencoder(encoding)() def writerow(self, row): - self.writer.writerow([s.encode(self.encoding) for s in row]) + self.writer.writerow([s.encode("utf-8") for s in row]) + # Fetch UTF-8 output from the queue ... + data = self.queue.getvalue() + data = data.decode("utf-8") + # ... and reencode it into the target encoding + data = self.encoder.encode(data) + # write to the target stream + self.stream.write(data) + # empty queue + self.queue.truncate(0) def writerows(self, rows): for row in rows: |