/usr/share/pyshared/openpyxl/reader/iter_worksheet.py is in python-openpyxl 1.7.0+ds1-1.
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 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 | # file openpyxl/reader/iter_worksheet.py
# Copyright (c) 2010-2011 openpyxl
#
# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the "Software"), to deal
# in the Software without restriction, including without limitation the rights
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:
#
# The above copyright notice and this permission notice shall be included in
# all copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
# THE SOFTWARE.
#
# @license: http://www.opensource.org/licenses/mit-license.php
# @author: see AUTHORS file
""" Iterators-based worksheet reader
*Still very raw*
"""
import warnings
import operator
from itertools import groupby
from openpyxl.worksheet import Worksheet
from openpyxl.cell import (coordinate_from_string, get_column_letter, Cell,
column_index_from_string)
from openpyxl.reader.style import read_style_table, NumberFormat
from openpyxl.shared.date_time import SharedDate
from openpyxl.reader.worksheet import read_dimension
from openpyxl.shared.compat import unicode
from openpyxl.shared.ooxml import (MIN_COLUMN, MAX_COLUMN, PACKAGE_WORKSHEETS,
MAX_ROW, MIN_ROW, ARC_STYLE)
from openpyxl.shared.compat import iterparse, xrange
from zipfile import ZipFile
import re
import tempfile
import zlib
import zipfile
import struct
TYPE_NULL = Cell.TYPE_NULL
MISSING_VALUE = None
RE_COORDINATE = re.compile('^([A-Z]+)([0-9]+)$')
SHARED_DATE = SharedDate()
_COL_CONVERSION_CACHE = dict((get_column_letter(i), i) for i in xrange(1, 18279))
def column_index_from_string(str_col, _col_conversion_cache=_COL_CONVERSION_CACHE):
# we use a function argument to get indexed name lookup
return _col_conversion_cache[str_col]
del _COL_CONVERSION_CACHE
RAW_ATTRIBUTES = ['row', 'column', 'coordinate', 'internal_value', 'data_type', 'style_id', 'number_format']
try:
from collections import namedtuple
BaseRawCell = namedtuple('RawCell', RAW_ATTRIBUTES)
except ImportError:
warnings.warn("""Unable to import 'namedtuple' module, this may cause memory issues when using optimized reader. Please upgrade your Python installation to 2.6+""")
class BaseRawCell(object):
def __init__(self, *args):
assert len(args) == len(RAW_ATTRIBUTES)
for attr, val in zip(RAW_ATTRIBUTES, args):
setattr(self, attr, val)
def _replace(self, **kwargs):
self.__dict__.update(kwargs)
return self
formatter = NumberFormat()
class RawCell(BaseRawCell):
"""Optimized version of the :class:`openpyxl.cell.Cell`, using named tuples.
Useful attributes are:
* row
* column
* coordinate
* internal_value
You can also access if needed:
* data_type
* number_format
"""
@property
def is_date(self):
return formatter.is_date_format(self.number_format)
def iter_rows(workbook_name, sheet_name, xml_source, shared_date, string_table, range_string='', row_offset=0, column_offset=0):
archive = get_archive_file(workbook_name)
source = xml_source
if range_string:
min_col, min_row, max_col, max_row = get_range_boundaries(range_string, row_offset, column_offset)
else:
min_col, min_row, max_col, max_row = read_dimension(xml_source=source)
min_col = column_index_from_string(min_col)
max_col = column_index_from_string(max_col) + 1
max_row += 6
style_table = read_style_table(archive.read(ARC_STYLE))
source.seek(0)
p = iterparse(source)
return get_squared_range(p, min_col, min_row, max_col, max_row, string_table, style_table, shared_date)
def get_rows(p, min_column=MIN_COLUMN, min_row=MIN_ROW, max_column=MAX_COLUMN, max_row=MAX_ROW):
return groupby(get_cells(p, min_row, min_column, max_row, max_column), operator.attrgetter('row'))
def get_cells(p, min_row, min_col, max_row, max_col, _re_coordinate=RE_COORDINATE):
for _event, element in p:
if element.tag == '{http://schemas.openxmlformats.org/spreadsheetml/2006/main}c':
coord = element.get('r')
column_str, row = _re_coordinate.match(coord).groups()
row = int(row)
column = column_index_from_string(column_str)
if min_col <= column <= max_col and min_row <= row <= max_row:
data_type = element.get('t', 'n')
style_id = element.get('s')
value = element.findtext('{http://schemas.openxmlformats.org/spreadsheetml/2006/main}v')
yield RawCell(row, column_str, coord, value, data_type, style_id, None)
if element.tag == '{http://schemas.openxmlformats.org/spreadsheetml/2006/main}v':
continue
element.clear()
def get_range_boundaries(range_string, row=0, column=0):
if ':' in range_string:
min_range, max_range = range_string.split(':')
min_col, min_row = coordinate_from_string(min_range)
max_col, max_row = coordinate_from_string(max_range)
min_col = column_index_from_string(min_col) + column
max_col = column_index_from_string(max_col) + column
min_row += row
max_row += row
else:
min_col, min_row = coordinate_from_string(range_string)
min_col = column_index_from_string(min_col)
max_col = min_col + 1
max_row = min_row
return (min_col, min_row, max_col, max_row)
def get_archive_file(archive_name):
return ZipFile(archive_name, 'r')
def get_xml_source(archive_file, sheet_name):
return archive_file.read('%s/%s' % (PACKAGE_WORKSHEETS, sheet_name))
def get_missing_cells(row, columns):
return dict([(column, RawCell(row, column, '%s%s' % (column, row), MISSING_VALUE, TYPE_NULL, None, None)) for column in columns])
def get_squared_range(p, min_col, min_row, max_col, max_row, string_table, style_table, shared_date):
expected_columns = [get_column_letter(ci) for ci in xrange(min_col, max_col)]
current_row = min_row
for row, cells in get_rows(p, min_row=min_row, max_row=max_row, min_column=min_col, max_column=max_col):
full_row = []
if current_row < row:
for gap_row in xrange(current_row, row):
dummy_cells = get_missing_cells(gap_row, expected_columns)
yield tuple([dummy_cells[column] for column in expected_columns])
current_row = row
temp_cells = list(cells)
retrieved_columns = dict([(c.column, c) for c in temp_cells])
missing_columns = list(set(expected_columns) - set(retrieved_columns.keys()))
replacement_columns = get_missing_cells(row, missing_columns)
for column in expected_columns:
if column in retrieved_columns:
cell = retrieved_columns[column]
if cell.style_id is not None:
style = style_table[int(cell.style_id)]
cell = cell._replace(number_format=style.number_format.format_code) #pylint: disable-msg=W0212
if cell.internal_value is not None:
if cell.data_type in Cell.TYPE_STRING:
cell = cell._replace(internal_value=unicode(string_table[int(cell.internal_value)])) #pylint: disable-msg=W0212
elif cell.data_type == Cell.TYPE_BOOL:
cell = cell._replace(internal_value=cell.internal_value == '1')
elif cell.is_date:
cell = cell._replace(internal_value=shared_date.from_julian(float(cell.internal_value)))
elif cell.data_type == Cell.TYPE_NUMERIC:
cell = cell._replace(internal_value=float(cell.internal_value))
elif cell.data_type in(Cell.TYPE_INLINE, Cell.TYPE_FORMULA_CACHE_STRING):
cell = cell._replace(internal_value=unicode(cell.internal_value))
full_row.append(cell)
else:
full_row.append(replacement_columns[column])
current_row = row + 1
yield tuple(full_row)
#------------------------------------------------------------------------------
class IterableWorksheet(Worksheet):
def __init__(self, parent_workbook, title, workbook_name,
sheet_codename, xml_source, string_table):
Worksheet.__init__(self, parent_workbook, title)
self._workbook_name = workbook_name
self._sheet_codename = sheet_codename
self._xml_source = xml_source
self._string_table = string_table
min_col, min_row, max_col, max_row = read_dimension(xml_source=xml_source)
self._max_row = max_row
self._max_column = max_col
self._dimensions = '%s%s:%s%s' % (min_col, min_row, max_col, max_row)
self._shared_date = SharedDate(base_date=parent_workbook.excel_base_date)
def iter_rows(self, range_string='', row_offset=0, column_offset=0):
""" Returns a squared range based on the `range_string` parameter,
using generators.
:param range_string: range of cells (e.g. 'A1:C4')
:type range_string: string
:param row: row index of the cell (e.g. 4)
:type row: int
:param column: column index of the cell (e.g. 3)
:type column: int
:rtype: generator
"""
return iter_rows(workbook_name=self._workbook_name,
sheet_name=self._sheet_codename,
xml_source=self._xml_source,
range_string=range_string,
row_offset=row_offset,
column_offset=column_offset,
shared_date=self._shared_date,
string_table=self._string_table)
def cell(self, *args, **kwargs):
raise NotImplementedError("use 'iter_rows()' instead")
def range(self, *args, **kwargs):
raise NotImplementedError("use 'iter_rows()' instead")
def calculate_dimension(self):
return self._dimensions
def get_highest_column(self):
return column_index_from_string(self._max_column)
def get_highest_row(self):
return self._max_row
def unpack_worksheet(archive, filename):
temp_file = tempfile.TemporaryFile(mode='rb+', prefix='openpyxl.', suffix='.unpack.temp')
zinfo = archive.getinfo(filename)
if zinfo.compress_type == zipfile.ZIP_STORED:
decoder = None
elif zinfo.compress_type == zipfile.ZIP_DEFLATED:
decoder = zlib.decompressobj(-zlib.MAX_WBITS)
else:
raise zipfile.BadZipFile("Unrecognized compression method")
archive.fp.seek(_get_file_offset(archive, zinfo))
bytes_to_read = zinfo.compress_size
while True:
buff = archive.fp.read(min(bytes_to_read, 102400))
if not buff:
break
bytes_to_read -= len(buff)
if decoder:
buff = decoder.decompress(buff)
temp_file.write(buff)
return temp_file
def _get_file_offset(archive, zinfo):
try:
return zinfo.file_offset
except AttributeError:
# From http://stackoverflow.com/questions/3781261/how-to-simulate-zipfile-open-in-python-2-5
# Seek over the fixed size fields to the "file name length" field in
# the file header (26 bytes). Unpack this and the "extra field length"
# field ourselves as info.extra doesn't seem to be the correct length.
archive.fp.seek(zinfo.header_offset + 26)
file_name_len, extra_len = struct.unpack("<HH", archive.fp.read(4))
return zinfo.header_offset + 30 + file_name_len + extra_len
|