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
|
import os
from .. import results, lists
from .document_xml import read_document_xml_element
from .content_types_xml import empty_content_types, read_content_types_xml_element
from .relationships_xml import read_relationships_xml_element, Relationships
from .numbering_xml import read_numbering_xml_element, Numbering
from .styles_xml import read_styles_xml_element, Styles
from .notes_xml import create_footnotes_reader, create_endnotes_reader
from .comments_xml import create_comments_reader
from .files import Files
from . import body_xml, office_xml
from ..zips import open_zip
_empty_result = results.success([])
def read(fileobj):
zip_file = open_zip(fileobj, "r")
body_readers = _body_readers(getattr(fileobj, "name", None), zip_file)
return results.combine([
_read_notes(zip_file, body_readers),
_read_comments(zip_file, body_readers),
]).bind(lambda referents:
_read_document(zip_file, body_readers, notes=referents[0], comments=referents[1])
)
def _read_notes(zip_file, body_readers):
read_footnotes_xml = create_footnotes_reader(body_readers("footnotes"))
footnotes = _try_read_entry_or_default(
zip_file, "word/footnotes.xml", read_footnotes_xml, default=_empty_result)
read_endnotes_xml = create_endnotes_reader(body_readers("endnotes"))
endnotes = _try_read_entry_or_default(
zip_file, "word/endnotes.xml", read_endnotes_xml, default=_empty_result)
return results.combine([footnotes, endnotes]).map(lists.flatten)
def _read_comments(zip_file, body_readers):
return _try_read_entry_or_default(
zip_file,
"word/comments.xml",
create_comments_reader(body_readers("comments")),
default=_empty_result,
)
def _read_document(zip_file, body_readers, notes, comments):
package_relationships = _try_read_entry_or_default(
zip_file,
"_rels/.rels",
read_relationships_xml_element,
default=Relationships.EMPTY,
)
document_filename = _find_document_filename(zip_file, package_relationships)
with zip_file.open(document_filename) as document_fileobj:
document_xml = office_xml.read(document_fileobj)
return read_document_xml_element(
document_xml,
body_reader=body_readers("document"),
notes=notes,
comments=comments,
)
def _find_document_filename(zip_file, relationships):
office_document_type = "http://schemas.openxmlformats.org/officeDocument/2006/relationships/officeDocument"
targets = [
target.lstrip("/")
for target in relationships.find_targets_by_type(office_document_type)
] + ["word/document.xml"]
valid_targets = list(filter(lambda target: zip_file.exists(target), targets))
if len(valid_targets) == 0:
return None
else:
return valid_targets[0]
def _body_readers(document_path, zip_file):
content_types = _try_read_entry_or_default(
zip_file,
"[Content_Types].xml",
read_content_types_xml_element,
empty_content_types,
)
numbering = _try_read_entry_or_default(
zip_file, "word/numbering.xml", read_numbering_xml_element, default=Numbering({}))
styles = _try_read_entry_or_default(
zip_file,
"word/styles.xml",
read_styles_xml_element,
Styles.EMPTY,
)
def for_name(name):
relationships_path = "word/_rels/{0}.xml.rels".format(name)
relationships = _try_read_entry_or_default(
zip_file, relationships_path, read_relationships_xml_element,
default=Relationships.EMPTY)
return body_xml.reader(
numbering=numbering,
content_types=content_types,
relationships=relationships,
styles=styles,
docx_file=zip_file,
files=Files(None if document_path is None else os.path.dirname(document_path)),
)
return for_name
def _try_read_entry_or_default(zip_file, name, reader, default):
if zip_file.exists(name):
with zip_file.open(name) as fileobj:
return reader(office_xml.read(fileobj))
else:
return default
|
