unicode_csv.py

""" Unicode handling for csv
"""

import csv
import codecs
import cStringIO

class UTF8Recoder:
    """ Iterator to read an encoded stream and reencode 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 to iterate over lines in the CSV file "f", 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.line_num = self.reader.line_num

    def next(self):
        row = self.reader.next()
        return [unicode(s, "utf-8") for s in row]

    def __iter__(self):
        return self


class UnicodeWriter:
    """ A CSV writer to write rows to CSV file "f", encoded in the given 
        encoding.
    """

    def __init__(self, f, dialect=csv.excel, encoding="utf-8", **kwds):
        # Redirect output to a queue
        self.queue = cStringIO.StringIO()
        self.writer = csv.writer(self.queue, dialect=dialect, **kwds)
        self.stream = f
        self.encoding = encoding
        self.encoder = codecs.getincrementalencoder(encoding)()

    def writerow(self, row):
        self.writer.writerow([unicode(s).encode("utf-8") for s in row])
        # Fetch UTF-8 output from the queue ...
        data = self.queue.getvalue()
        if self.encoding is not "utf-8":
            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:
            self.writerow(row)


reader = UnicodeReader
writer = UnicodeWriter
Sniffer = csv.Sniffer
Dialect = csv.Dialect