Python UTF-16 CSV reader

Question

I have a UTF-16 CSV file which I have to read. Python csv module does not seem to support UTF-16.

I am using python 2.7.2. CSV files I need to parse are huge size running into several GBs of data.

Answers for John Machin questions below

print repr(open('test.csv', 'rb').read(100))

Output with test.csv having just abc as content

'\xff\xfea\x00b\x00c\x00'

I think csv file got created on windows machine in USA. I am using Mac OSX Lion.

If I use code provided by phihag and test.csv containing one record.

sample test.csv content used. Below is print repr(open('test.csv', 'rb').read(1000)) output

'\xff\xfe1\x00,\x002\x00,\x00G\x00,\x00S\x00,\x00H\x00 \x00f\x00\xfc\x00r\x00 \x00e\x00 \x00\x96\x00 \x00m\x00 \x00\x85\x00,\x00,\x00I\x00\r\x00\n\x00'

Code by phihag

import codecs
import csv
with open('test.csv','rb') as f:
      sr = codecs.StreamRecoder(f,codecs.getencoder('utf-8'),codecs.getdecoder('utf-8'),codecs.getreader('utf-16'),codecs.getwriter('utf-16'))      
      for row in csv.reader(sr):
         print row

Output of the above code

['1', '2', 'G', 'S', 'H f\xc3\xbcr e \xc2\x96 m \xc2\x85']
['', '', 'I']

expected output is

['1', '2', 'G', 'S', 'H f\xc3\xbcr e \xc2\x96 m \xc2\x85','','I']

Answer 1

At the moment, the csv module does not support UTF-16.

In Python 3.x, csv expects a text-mode file and you can simply use the encoding parameter of open to force another encoding:

# Python 3.x only
import csv
with open('utf16.csv', 'r', encoding='utf16') as csvf:
    for line in csv.reader(csvf):
        print(line) # do something with the line

In Python 2.x, you can recode the input:

# Python 2.x only
import codecs
import csv

class Recoder(object):
    def __init__(self, stream, decoder, encoder, eol='\r\n'):
        self._stream = stream
        self._decoder = decoder if isinstance(decoder, codecs.IncrementalDecoder) else codecs.getincrementaldecoder(decoder)()
        self._encoder = encoder if isinstance(encoder, codecs.IncrementalEncoder) else codecs.getincrementalencoder(encoder)()
        self._buf = ''
        self._eol = eol
        self._reachedEof = False

    def read(self, size=None):
        r = self._stream.read(size)
        raw = self._decoder.decode(r, size is None)
        return self._encoder.encode(raw)

    def __iter__(self):
        return self

    def __next__(self):
        if self._reachedEof:
            raise StopIteration()
        while True:
            line,eol,rest = self._buf.partition(self._eol)
            if eol == self._eol:
                self._buf = rest
                return self._encoder.encode(line + eol)
            raw = self._stream.read(1024)
            if raw == '':
                self._decoder.decode(b'', True)
                self._reachedEof = True
                return self._encoder.encode(self._buf)
            self._buf += self._decoder.decode(raw)
    next = __next__

    def close(self):
        return self._stream.close()

with open('test.csv','rb') as f:
    sr = Recoder(f, 'utf-16', 'utf-8')

    for row in csv.reader(sr):
        print (row)

open and codecs.open require the file to start with a BOM. If it doesn't (or you're on Python 2.x), you can still convert it in memory, like this:

try:
    from io import BytesIO
except ImportError: # Python < 2.6
    from StringIO import StringIO as BytesIO
import csv
with open('utf16.csv', 'rb') as binf:
    c = binf.read().decode('utf-16').encode('utf-8')
for line in csv.reader(BytesIO(c)):
    print(line) # do something with the line