dataimport/csv.py
author Sylvain Thénault <sylvain.thenault@logilab.fr>
Fri, 26 Jun 2015 11:15:25 +0200
changeset 10513 7bec01a59f92
child 10589 7c23b7de2b8d
child 11404 98eebbe3de23
permissions -rw-r--r--
[dataimport] dispatch and deprecate old code previously, the whole dataimport.py content has been copied in dataimport/__init__.py, then dataimport/importer.py API has been introduced. Following these changes, this cset: * dispatch __init__ code into sub-modules * dispatch unittest_dataimport accordingly * deprecates functions and classes that are deprecated by the new API Related to #5414753.

# copyright 2003-2015 LOGILAB S.A. (Paris, FRANCE), all rights reserved.
# contact http://www.logilab.fr/ -- mailto:contact@logilab.fr
#
# This file is part of CubicWeb.
#
# CubicWeb is free software: you can redistribute it and/or modify it under the
# terms of the GNU Lesser General Public License as published by the Free
# Software Foundation, either version 2.1 of the License, or (at your option)
# any later version.
#
# CubicWeb is distributed in the hope that it will be useful, but WITHOUT
# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
# FOR A PARTICULAR PURPOSE.  See the GNU Lesser General Public License for more
# details.
#
# You should have received a copy of the GNU Lesser General Public License along
# with CubicWeb.  If not, see <http://www.gnu.org/licenses/>.
"""Functions to help importing CSV data"""

from __future__ import absolute_import

import csv as csvmod
import warnings
import os.path as osp

from logilab.common import shellutils


def count_lines(stream_or_filename):
    if isinstance(stream_or_filename, basestring):
        f = open(stream_or_filename)
    else:
        f = stream_or_filename
        f.seek(0)
    for i, line in enumerate(f):
        pass
    f.seek(0)
    return i+1


def ucsvreader_pb(stream_or_path, encoding='utf-8', delimiter=',', quotechar='"',
                  skipfirst=False, withpb=True, skip_empty=True, separator=None,
                  quote=None):
    """same as :func:`ucsvreader` but a progress bar is displayed as we iter on rows"""
    if separator is not None:
        delimiter = separator
        warnings.warn("[3.20] 'separator' kwarg is deprecated, use 'delimiter' instead")
    if quote is not None:
        quotechar = quote
        warnings.warn("[3.20] 'quote' kwarg is deprecated, use 'quotechar' instead")
    if isinstance(stream_or_path, basestring):
        if not osp.exists(stream_or_path):
            raise Exception("file doesn't exists: %s" % stream_or_path)
        stream = open(stream_or_path)
    else:
        stream = stream_or_path
    rowcount = count_lines(stream)
    if skipfirst:
        rowcount -= 1
    if withpb:
        pb = shellutils.ProgressBar(rowcount, 50)
    for urow in ucsvreader(stream, encoding, delimiter, quotechar,
                           skipfirst=skipfirst, skip_empty=skip_empty):
        yield urow
        if withpb:
            pb.update()
    print ' %s rows imported' % rowcount


def ucsvreader(stream, encoding='utf-8', delimiter=',', quotechar='"',
               skipfirst=False, ignore_errors=False, skip_empty=True,
               separator=None, quote=None):
    """A csv reader that accepts files with any encoding and outputs unicode
    strings

    if skip_empty (the default), lines without any values specified (only
    separators) will be skipped. This is useful for Excel exports which may be
    full of such lines.
    """
    if separator is not None:
        delimiter = separator
        warnings.warn("[3.20] 'separator' kwarg is deprecated, use 'delimiter' instead")
    if quote is not None:
        quotechar = quote
        warnings.warn("[3.20] 'quote' kwarg is deprecated, use 'quotechar' instead")
    it = iter(csvmod.reader(stream, delimiter=delimiter, quotechar=quotechar))
    if not ignore_errors:
        if skipfirst:
            it.next()
        for row in it:
            decoded = [item.decode(encoding) for item in row]
            if not skip_empty or any(decoded):
                yield decoded
    else:
        if skipfirst:
            try:
                row = it.next()
            except csvmod.Error:
                pass
        # Safe version, that can cope with error in CSV file
        while True:
            try:
                row = it.next()
            # End of CSV, break
            except StopIteration:
                break
            # Error in CSV, ignore line and continue
            except csvmod.Error:
                continue
            decoded = [item.decode(encoding) for item in row]
            if not skip_empty or any(decoded):
                yield decoded