/usr/share/pyshared/openpyxl/writer/dump_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 | # file openpyxl/writer/straight_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
"""Write worksheets to xml representations in an optimized way"""
import datetime
import os
from openpyxl.shared.compat import OrderedDict
from openpyxl.cell import get_column_letter, Cell
from openpyxl.worksheet import Worksheet
from openpyxl.shared.xmltools import (XMLGenerator, start_tag, end_tag, tag)
from openpyxl.shared.date_time import SharedDate
from openpyxl.shared.ooxml import MAX_COLUMN, MAX_ROW
from openpyxl.shared import NUMERIC_TYPES
from openpyxl.shared.exc import WorkbookAlreadySaved
from openpyxl.shared.compat import NamedTemporaryFile
from openpyxl.writer.excel import ExcelWriter
from openpyxl.writer.strings import write_string_table
from openpyxl.writer.styles import StyleWriter
from openpyxl.style import Style, NumberFormat
from openpyxl.shared.ooxml import (ARC_SHARED_STRINGS, PACKAGE_WORKSHEETS)
STYLES = {'datetime' : {'type':Cell.TYPE_NUMERIC,
'style':'1'},
'string':{'type':Cell.TYPE_STRING,
'style':'0'},
'numeric':{'type':Cell.TYPE_NUMERIC,
'style':'0'},
'formula':{'type':Cell.TYPE_FORMULA,
'style':'0'},
'boolean':{'type':Cell.TYPE_BOOL,
'style':'0'},
}
DESCRIPTORS_CACHE_SIZE = 50
DATETIME_STYLE = Style()
DATETIME_STYLE.number_format.format_code = NumberFormat.FORMAT_DATE_YYYYMMDD2
BOUNDING_BOX_PLACEHOLDER = 'A1:%s%d' % (get_column_letter(MAX_COLUMN), MAX_ROW)
def create_temporary_file(suffix=''):
fobj = NamedTemporaryFile(mode='w+', suffix=suffix, prefix='openpyxl.', delete=False)
filename = fobj.name
return filename
class DumpWorksheet(Worksheet):
"""
.. warning::
You shouldn't initialize this yourself, use :class:`openpyxl.workbook.Workbook` constructor instead,
with `optimized_write = True`.
"""
def __init__(self, parent_workbook, title):
Worksheet.__init__(self, parent_workbook, title)
self._max_col = 0
self._max_row = 0
self._parent = parent_workbook
self._fileobj_header_name = create_temporary_file(suffix='.header')
self._fileobj_content_name = create_temporary_file(suffix='.content')
self._fileobj_name = create_temporary_file()
self._shared_date = SharedDate()
self._string_builder = self._parent.strings_table_builder
def get_temporary_file(self, filename):
if filename in self._descriptors_cache:
fobj = self._descriptors_cache[filename]
# re-insert the value so it does not get evicted
# from cache soon
del self._descriptors_cache[filename]
self._descriptors_cache[filename] = fobj
return fobj
else:
if filename is None:
raise WorkbookAlreadySaved('this workbook has already been saved '
'and cannot be modified or saved anymore.')
fobj = open(filename, 'r+')
self._descriptors_cache[filename] = fobj
if len(self._descriptors_cache) > DESCRIPTORS_CACHE_SIZE:
filename, fileobj = self._descriptors_cache.popitem(last=False)
fileobj.close()
return fobj
@property
def _descriptors_cache(self):
try:
return self._parent._local_data.cache
except AttributeError:
self._parent._local_data.cache = OrderedDict()
return self._parent._local_data.cache
@property
def filename(self):
return self._fileobj_name
@property
def _temp_files(self):
return (self._fileobj_content_name,
self._fileobj_header_name,
self._fileobj_name)
def _unset_temp_files(self):
self._fileobj_header_name = None
self._fileobj_content_name = None
self._fileobj_name = None
def write_header(self):
fobj = self.get_temporary_file(filename=self._fileobj_header_name)
doc = XMLGenerator(fobj, 'utf-8')
start_tag(doc, 'worksheet',
{'xml:space': 'preserve',
'xmlns': 'http://schemas.openxmlformats.org/spreadsheetml/2006/main',
'xmlns:r': 'http://schemas.openxmlformats.org/officeDocument/2006/relationships'})
start_tag(doc, 'sheetPr')
tag(doc, 'outlinePr',
{'summaryBelow': '1',
'summaryRight': '1'})
end_tag(doc, 'sheetPr')
tag(doc, 'dimension', {'ref': 'A1:%s' % (self.get_dimensions())})
start_tag(doc, 'sheetViews')
start_tag(doc, 'sheetView', {'workbookViewId': '0'})
tag(doc, 'selection', {'activeCell': 'A1',
'sqref': 'A1'})
end_tag(doc, 'sheetView')
end_tag(doc, 'sheetViews')
tag(doc, 'sheetFormatPr', {'defaultRowHeight': '15'})
start_tag(doc, 'sheetData')
def close(self):
self._close_content()
self._fileobj = self.get_temporary_file(filename=self._fileobj_name)
self._write_fileobj(self._fileobj_header_name)
self._write_fileobj(self._fileobj_content_name)
self._fileobj.close()
def _write_fileobj(self, fobj_name):
fobj = self.get_temporary_file(filename=fobj_name)
fobj.flush()
fobj.seek(0)
while True:
chunk = fobj.read(4096)
if not chunk:
break
self._fileobj.write(chunk)
fobj.close()
self._fileobj.flush()
def _close_content(self):
doc = self._get_content_generator()
end_tag(doc, 'sheetData')
end_tag(doc, 'worksheet')
def get_dimensions(self):
if not self._max_col or not self._max_row:
return 'A1'
else:
return '%s%d' % (get_column_letter(self._max_col), (self._max_row))
def _get_content_generator(self):
""" XXX: this is ugly, but it allows to resume writing the file
even after the handle is closed"""
# when I'll recreate the XMLGenerator, it will start writing at the
# begining of the file, erasing previously entered rows, so we have
# to move to the end of the file before adding new tags
handle = self.get_temporary_file(filename=self._fileobj_content_name)
handle.seek(0, 2)
doc = XMLGenerator(out=handle)
return doc
def append(self, row):
"""
:param row: iterable containing values to append
:type row: iterable
"""
doc = self._get_content_generator()
self._max_row += 1
span = len(row)
self._max_col = max(self._max_col, span)
row_idx = self._max_row
attrs = {'r': '%d' % row_idx,
'spans': '1:%d' % span}
start_tag(doc, 'row', attrs)
for col_idx, cell in enumerate(row):
if cell is None:
continue
coordinate = '%s%d' % (get_column_letter(col_idx + 1), row_idx)
attributes = {'r': coordinate}
if isinstance(cell, bool):
dtype = 'boolean'
elif isinstance(cell, NUMERIC_TYPES):
dtype = 'numeric'
elif isinstance(cell, (datetime.datetime, datetime.date)):
dtype = 'datetime'
cell = self._shared_date.datetime_to_julian(cell)
attributes['s'] = STYLES[dtype]['style']
elif cell and cell[0] == '=':
dtype = 'formula'
else:
dtype = 'string'
cell = self._string_builder.add(cell)
if dtype != 'formula':
attributes['t'] = STYLES[dtype]['type']
start_tag(doc, 'c', attributes)
if dtype == 'formula':
tag(doc, 'f', body='%s' % cell[1:])
tag(doc, 'v')
elif dtype == 'boolean':
tag(doc, 'v', body='%d' % cell)
else:
tag(doc, 'v', body='%s' % cell)
end_tag(doc, 'c')
end_tag(doc, 'row')
def save_dump(workbook, filename):
writer = ExcelDumpWriter(workbook)
writer.save(filename)
return True
class ExcelDumpWriter(ExcelWriter):
def __init__(self, workbook):
self.workbook = workbook
self.style_writer = StyleDumpWriter(workbook)
self.style_writer._style_list.append(DATETIME_STYLE)
def _write_string_table(self, archive):
shared_string_table = self.workbook.strings_table_builder.get_table()
archive.writestr(ARC_SHARED_STRINGS,
write_string_table(shared_string_table))
return shared_string_table
def _write_worksheets(self, archive, shared_string_table, style_writer):
for i, sheet in enumerate(self.workbook.worksheets):
sheet.write_header()
sheet.close()
archive.write(sheet.filename, PACKAGE_WORKSHEETS + '/sheet%d.xml' % (i + 1))
for filename in sheet._temp_files:
del sheet._descriptors_cache[filename]
os.remove(filename)
sheet._unset_temp_files()
class StyleDumpWriter(StyleWriter):
def _get_style_list(self, workbook):
return []
|