unicodecsv.py

import csv
import codecs


class UTF8Recoder(object):
    """
    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(object):
    """
    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-sig", **kwds):
        f = UTF8Recoder(f, encoding)
        self.reader = csv.reader(f, dialect=dialect, **kwds)

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

    def __iter__(self):
        return self

    @property
    def fieldnames(self):
        return self.reader.fieldnames


if __name__ == '__main__':
    import sys
    if len(sys.argv) == 1:
        print sys.argv, 'filename.csv'
        sys.exit(1)

    for filename in sys.argv[1:]:
        print filename + ":"
        reader = UnicodeReader(open(filename, 'r'))
        for i, row in enumerate(reader):
            print u'|'.join(row)