Joins a bunch of CSVs, sends the single joined CSV to STDOUT

join_csv.py

#!/usr/bin/env python

"""
Joins a bunch of CSVs, sends the single joined CSV to STDOUT
"""

import codecs, csv, sys

try:
    import cStringIO as StringIO
except ImportError:
    import StringIO

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

class UnicodeCSVWriter:
    """
    A CSV writer which will write rows to CSV file "f",
    which is encoded in the given encoding.
    
    Adapted from http://docs.python.org/library/csv.html#examples
    """
    
    def __init__(self, f, dialect=csv.excel, encoding="utf-8", **kwds):
        # Redirect output to a queue
        self.queue = StringIO.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("utf-8") if hasattr(s, "encode") else s 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:
            self.writerow(row)
    

def join_csv(*files):
    headers_written = False
    writer = UnicodeCSVWriter(sys.stdout)
    for file in files:
        reader = UnicodeCSVReader(open(file))
        headers = reader.next()
        if not headers_written:
            writer.writerow(headers)
            headers_written = True
        writer.writerows(reader)

if __name__ == "__main__":
    join_csv(*sys.argv[1:])