uucsv.py

import csv
import codecs
import io #was cStringIO in Python2


def UnicodeDictReader(utf8_data, **kwargs):
    list_of_dicts = []
    csv_reader = csv.DictReader(utf8_data, **kwargs)
    for row in csv_reader:
        #add_keys = {(key,value) for key, value in row.items()}
        #dict_list = (dict(add_keys)) #converts each row into a separate dict that is not joined nor iterable
        list_of_dicts.append(dict(row))
        yield list_of_dicts

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 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)

    def __next__(self):
        row = next(self.reader)
        return [s for s in row]

    def __iter__(self):
        return self

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 = io.StringIO() #https://stackoverflow.com/questions/13120127/how-can-i-use-io-stringio-with-the-csv-module
        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") for s in row])
        # Fetch UTF-8 output from the queue ...
        data = self.queue.getvalue()
        #data = data.decode("utf-8") #string objects already are decoded #AttributeError: 'str' object has no attribute 'decode'
        # ... 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)