/usr/share/pyshared/weboob/tools/parsers/csvparser.py is in python-weboob-core 0.g-1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 | # -*- coding: utf-8 -*-
# Copyright(C) 2013 Laurent Bachelier
#
# This file is part of weboob.
#
# weboob is free software: you can redistribute it and/or modify
# it under the terms of the GNU Affero General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# weboob 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 Affero General Public License for more details.
#
# You should have received a copy of the GNU Affero General Public License
# along with weboob. If not, see <http://www.gnu.org/licenses/>.
import csv
from .iparser import IParser
class Csv(object):
"""
CSV parser result.
header contains the first row if it is a header
rows contains the raw rows
drows contains the rows with cells indexed by header title
"""
def __init__(self):
self.header = None
self.rows = []
self.drows = []
class CsvParser(IParser):
"""
CSV Parser.
Since CSV files are not normalized, this parser is intended to be derived.
"""
DIALECT = 'excel'
FMTPARAMS = {}
"""
If True, will consider the first line as a header.
This means the rows will be also available as dictionnaries.
"""
HEADER = False
def parse(self, data, encoding=None):
reader = csv.reader(data, dialect=self.DIALECT, **self.FMTPARAMS)
c = Csv()
for row in reader:
row = self.decode_row(row, encoding)
if c.header is None and self.HEADER:
c.header = row
else:
c.rows.append(row)
if c.header:
drow = {}
for i, cell in enumerate(row):
drow[c.header[i]] = cell
c.drows.append(drow)
return c
def decode_row(self, row, encoding):
if encoding:
return [unicode(cell, encoding) for cell in row]
else:
return row
def tostring(self, element):
if not isinstance(element, basestring):
return unicode(element)
return element
|