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
|
from .. import documents
from .. import results
from .. import lists
from .xmlparser import node_types
def read_document_xml_element(element, numbering=None):
reader = _create_reader(numbering)
return reader(element)
def _create_reader(numbering):
_handlers = {}
_ignored_elements = set([
"w:bookmarkStart",
"w:bookmarkEnd",
"w:sectPr",
"w:proofErr",
"w:lastRenderedPageBreak",
"w:commentRangeStart",
"w:commentRangeEnd",
"w:commentReference",
"w:del"
])
def handler(name):
def add(func):
_handlers[name] = func
return add
@handler("w:t")
def text(element):
return results.success(documents.Text(_inner_text(element)))
@handler("w:r")
def run(element):
properties = element.find_child_or_null("w:rPr")
style_name = properties \
.find_child_or_null("w:rStyle") \
.attributes.get("w:val")
is_bold = properties.find_child("w:b")
is_italic = properties.find_child("w:i")
return _read_xml_elements(element.children) \
.map(lambda children: documents.run(
children=children,
style_name=style_name,
is_bold=is_bold,
is_italic=is_italic,
))
@handler("w:p")
def paragraph(element):
properties = element.find_child_or_null("w:pPr")
style_name = properties \
.find_child_or_null("w:pStyle") \
.attributes.get("w:val")
numbering_properties = properties.find_child("w:numPr")
if numbering_properties is None:
numbering = None
else:
numbering = _read_numbering_properties(numbering_properties)
return _read_xml_elements(element.children) \
.map(lambda children: documents.paragraph(
children=children,
style_name=style_name,
numbering=numbering,
))
def _read_numbering_properties(element):
num_id = element.find_child("w:numId").attributes["w:val"]
level_index = element.find_child("w:ilvl").attributes["w:val"]
return numbering.find_level(num_id, level_index)
@handler("w:body")
def body(element):
return _read_xml_elements(element.children)
@handler("w:document")
def document(element):
body_element = _find_child(element, "w:body")
return _read_xml_elements(body_element.children) \
.map(documents.document)
@handler("w:tab")
def tab(element):
return results.success(documents.tab())
@handler("w:ins")
def ins(element):
return _read_xml_elements(element.children)
def read(element):
handler = _handlers.get(element.name)
if handler is None:
if element.name not in _ignored_elements:
warning = results.warning("An unrecognised element was ignored: {0}".format(element.name))
return results.Result(None, [warning])
else:
return results.success(None)
else:
return handler(element)
def _read_xml_elements(elements):
return results.combine(map(read, elements)) \
.map(lambda values: lists.collect(values))
return read
def _find(predicate, iterable):
for item in iterable:
if predicate(item):
return item
def _find_child(element, name):
return _find(lambda child: child.name == name, element.children)
def _inner_text(node):
if node.node_type == node_types.text:
return node.value
else:
return "".join(_inner_text(child) for child in node.children)
|
