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
|
# file openpyxl/shared/xmltools.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
"""Shared xml tools.
Shortcut functions taken from:
http://lethain.com/entry/2009/jan/22/handling-very-large-csv-and-xml-files-in-python/
"""
# Python stdlib imports
from xml.sax.xmlreader import AttributesNSImpl
from xml.sax.saxutils import XMLGenerator
try:
from xml.etree.ElementTree import ElementTree, Element, SubElement, \
QName, fromstring, tostring
except ImportError:
from cElementTree import ElementTree, Element, SubElement, \
QName, fromstring, tostring
# package imports
from .. import __name__ as prefix
def get_document_content(xml_node):
"""Print nicely formatted xml to a string."""
pretty_indent(xml_node)
return tostring(xml_node, 'utf-8')
def pretty_indent(elem, level=0):
"""Format xml with nice indents and line breaks."""
i = "\n" + level * " "
if len(elem):
if not elem.text or not elem.text.strip():
elem.text = i + " "
if not elem.tail or not elem.tail.strip():
elem.tail = i
for elem in elem:
pretty_indent(elem, level + 1)
if not elem.tail or not elem.tail.strip():
elem.tail = i
else:
if level and (not elem.tail or not elem.tail.strip()):
elem.tail = i
def start_tag(doc, name, attr=None, body=None, namespace=None):
"""Wrapper to start an xml tag."""
if attr is None:
attr = {}
# name = bytes(name, 'utf-8')
# if namespace is not None:
# namespace = bytes(namespace, 'utf-8')
attr_vals = {}
attr_keys = {}
for key, val in attr.items():
# if key is not None:
# key = bytes(key, 'utf-8')
# if val is not None:
# val = bytes(val, 'utf-8')
key_tuple = (namespace, key)
attr_vals[key_tuple] = val
attr_keys[key_tuple] = key
attr2 = AttributesNSImpl(attr_vals, attr_keys)
doc.startElementNS((namespace, name), name, attr2)
if body:
doc.characters(body)
def end_tag(doc, name, namespace=None):
"""Wrapper to close an xml tag."""
doc.endElementNS((namespace, name), name)
def tag(doc, name, attr=None, body=None, namespace=None):
"""Wrapper to print xml tags and comments."""
if attr is None:
attr = {}
start_tag(doc, name, attr, body, namespace)
end_tag(doc, name, namespace)
|
