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
|
# coding=utf-8
from __future__ import unicode_literals
import base64
import random
from . import documents, results, html_paths, images
from .html_generation import HtmlGenerator, satisfy_html_path
def convert_document_element_to_html(element,
style_map=None,
convert_image=None,
convert_underline=None,
id_prefix=None):
if style_map is None:
style_map = []
if id_prefix is None:
id_prefix = str(random.randint(0, 1000000000000000))
html_generator = HtmlGenerator()
converter = DocumentConverter(style_map,
convert_image=convert_image,
convert_underline=convert_underline,
id_prefix=id_prefix)
converter.convert_element_to_html(element, html_generator,)
html_generator.end_all()
return results.Result(html_generator.html_string(), converter.messages)
class DocumentConverter(object):
def __init__(self, style_map, convert_image, convert_underline, id_prefix):
self.messages = []
self._style_map = style_map
self._id_prefix = id_prefix
self._note_references = []
self._converters = {
documents.Document: self._convert_document,
documents.Paragraph: self._convert_paragraph,
documents.Run: self._convert_run,
documents.Text: self._convert_text,
documents.Hyperlink: self._convert_hyperlink,
documents.Tab: self._convert_tab,
documents.Table: self._convert_table,
documents.TableRow: self._convert_table_row,
documents.TableCell: self._convert_table_cell,
documents.LineBreak: self._line_break,
documents.Image: convert_image or images.inline(self._convert_image),
documents.NoteReference: self._convert_note_reference,
documents.Note: self._convert_note,
}
self._convert_underline = convert_underline
def convert_element_to_html(self, element, html_generator):
self._converters[type(element)](element, html_generator)
def _convert_document(self, document, html_generator):
self._convert_elements_to_html(document.children, html_generator)
html_generator.end_all()
html_generator.start("ol")
notes = [
document.notes.resolve(reference)
for reference in self._note_references
]
self._convert_elements_to_html(notes, html_generator)
html_generator.end()
def _convert_paragraph(self, paragraph, html_generator):
html_path = self._find_html_path_for_paragraph(paragraph)
satisfy_html_path(html_generator, html_path)
self._convert_elements_to_html(paragraph.children, html_generator)
def _convert_run(self, run, html_generator):
run_generator = HtmlGenerator()
html_path = self._find_html_path_for_run(run)
if html_path:
satisfy_html_path(run_generator, html_path)
if run.is_bold:
run_generator.start("strong")
if run.is_italic:
run_generator.start("em")
if run.vertical_alignment == documents.VerticalAlignment.superscript:
run_generator.start("sup")
if run.vertical_alignment == documents.VerticalAlignment.subscript:
run_generator.start("sub")
if run.is_underline and self._convert_underline is not None:
self._convert_underline(run_generator)
self._convert_elements_to_html(run.children, run_generator)
run_generator.end_all()
html_generator.append(run_generator)
def _convert_text(self, text, html_generator):
html_generator.text(text.value)
def _convert_hyperlink(self, hyperlink, html_generator):
html_generator.start("a", {"href": hyperlink.href})
self._convert_elements_to_html(hyperlink.children, html_generator)
html_generator.end()
def _convert_tab(self, tab, html_generator):
html_generator.text("\t")
def _convert_table(self, table, html_generator):
html_generator.end_all()
html_generator.start("table")
self._convert_elements_to_html(table.children, html_generator)
html_generator.end()
def _convert_table_row(self, table_row, html_generator):
html_generator.start("tr")
self._convert_elements_to_html(table_row.children, html_generator)
html_generator.end()
def _convert_table_cell(self, table_cell, html_generator):
html_generator.start("td", always_write=True)
for child in table_cell.children:
child_generator = HtmlGenerator()
self.convert_element_to_html(child, child_generator)
child_generator.end_all()
html_generator.append(child_generator)
html_generator.end()
def _line_break(self, line_break, html_generator):
html_generator.self_closing("br")
def _convert_image(self, image):
with image.open() as image_bytes:
encoded_src = base64.b64encode(image_bytes.read()).decode("ascii")
return {
"src": "data:{0};base64,{1}".format(image.content_type, encoded_src)
}
def _convert_note_reference(self, note_reference, html_generator):
html_generator.start("sup")
html_generator.start("a", {
"href": "#" + self._note_html_id(note_reference),
"id": self._note_ref_html_id(note_reference),
})
self._note_references.append(note_reference);
note_number = len(self._note_references)
html_generator.text("[{0}]".format(note_number))
html_generator.end()
html_generator.end()
def _convert_note(self, note, html_generator):
html_generator.start("li", {"id": self._note_html_id(note)})
note_generator = HtmlGenerator()
self._convert_elements_to_html(note.body, note_generator)
note_generator.text(" ")
note_generator.start("a", {"href": "#" + self._note_ref_html_id(note)})
note_generator.text(_up_arrow)
note_generator.end_all()
html_generator.append(note_generator)
html_generator.end()
def _convert_elements_to_html(self, elements, html_generator):
for element in elements:
self.convert_element_to_html(element, html_generator)
def _find_html_path_for_paragraph(self, paragraph):
default = html_paths.path([html_paths.element("p", fresh=True)])
return self._find_html_path(paragraph, "paragraph", default)
def _find_html_path_for_run(self, run):
return self._find_html_path(run, "run", default=None)
def _find_html_path(self, element, element_type, default):
for style in self._style_map:
document_matcher = style.document_matcher
if _document_matcher_matches(document_matcher, element, element_type):
return style.html_path
if element.style_id is not None:
self.messages.append(results.warning(
"Unrecognised {0} style: {1} (Style ID: {2})".format(
element_type, element.style_name, element.style_id)
))
return default
def _note_html_id(self, note):
return "{0}-{1}-{2}".format(self._id_prefix, note.note_type, note.note_id)
def _note_ref_html_id(self, note):
return "{0}-{1}-ref-{2}".format(self._id_prefix, note.note_type, note.note_id)
def _document_matcher_matches(matcher, element, element_type):
return (
matcher.element_type == element_type and (
matcher.style_id is None or
matcher.style_id == element.style_id
) and (
matcher.style_name is None or
matcher.style_name == element.style_name
) and (
element_type != "paragraph" or
matcher.numbering is None or
matcher.numbering == element.numbering
)
)
_up_arrow = "↑"
|
