clitool 0.4.1 documentation

clitool._unicodecsv

Contents

Source code for clitool._unicodecsv

# -*- coding: utf-8 -*-

"""
This file is for Python 2.7.
And all classes are from `Python Official Document`_.

.. _`Python Official Document`: http://docs.python.org/library/csv.html

More sophisticated implementation is available on "csvkit_" module.

.. _csvkit: http://pypi.python.org/pypi/csvkit
"""

import codecs
import csv

from six import PY3
if PY3:
    import io as cStringIO
else:
    import cStringIO


[docs]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
[docs] def next(self): return self.reader.next().encode("utf-8")
[docs]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)
[docs] def next(self): row = self.reader.next() return [unicode(s, "utf-8") for s in row]
def __iter__(self): return self
[docs]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): # 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)()
[docs] def writerow(self, 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)
[docs] def writerows(self, rows): for row in rows: self.writerow(row) # vim: set et ts=4 sw=4 cindent fileencoding=utf-8 :

Contents