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
|
# file openpyxl/reader/worksheet.py
# Copyright (c) 2010 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: Eric Gazoni
"""Reader for a single worksheet."""
# Python stdlib imports
try:
from xml.etree.cElementTree import iterparse
except ImportError:
from xml.etree.ElementTree import iterparse
from io import StringIO
# package imports
from ..cell import Cell, coordinate_from_string
from ..worksheet import Worksheet
def _get_xml_iter(xml_source):
if not hasattr(xml_source, 'name'):
return StringIO(xml_source)
else:
xml_source.seek(0)
return xml_source
def read_dimension(xml_source):
source = _get_xml_iter(xml_source)
it = iterparse(source)
for event, element in it:
if element.tag == '{http://schemas.openxmlformats.org/spreadsheetml/2006/main}dimension':
ref = element.get('ref')
if ':' in ref:
min_range, max_range = ref.split(':')
else:
min_range = max_range = ref
min_col, min_row = coordinate_from_string(min_range)
max_col, max_row = coordinate_from_string(max_range)
return min_col, min_row, max_col, max_row
else:
element.clear()
return None
def filter_cells(xxx_todo_changeme):
(event, element) = xxx_todo_changeme
return element.tag == '{http://schemas.openxmlformats.org/spreadsheetml/2006/main}c'
def fast_parse(ws, xml_source, string_table, style_table):
source = _get_xml_iter(xml_source)
it = iterparse(source)
for event, element in filter(filter_cells, it):
value = element.findtext('{http://schemas.openxmlformats.org/spreadsheetml/2006/main}v')
if value is not None:
coordinate = element.get('r')
data_type = element.get('t', 'n')
style_id = element.get('s')
if data_type == Cell.TYPE_STRING:
value = string_table.get(int(value))
ws.cell(coordinate).value = value
if style_id is not None:
ws._styles[coordinate] = style_table.get(int(style_id))
# to avoid memory exhaustion, clear the item after use
element.clear()
from ..reader.iter_worksheet import IterableWorksheet
def read_worksheet(xml_source, parent, preset_title, string_table,
style_table, workbook_name = None, sheet_codename = None):
"""Read an xml worksheet"""
if workbook_name and sheet_codename:
ws = IterableWorksheet(parent, preset_title, workbook_name,
sheet_codename, xml_source)
else:
ws = Worksheet(parent, preset_title)
fast_parse(ws, xml_source, string_table, style_table)
return ws
|
