|
1
|
|
|
#!/usr/bin/env python |
|
2
|
|
|
|
|
3
|
|
|
""" |
|
4
|
|
|
Pandoc filter for including file in code block. |
|
5
|
|
|
""" |
|
6
|
|
|
|
|
7
|
|
|
from collections.abc import Iterable |
|
8
|
|
|
from typing import Any |
|
9
|
|
|
|
|
10
|
|
|
from panflute import CodeBlock, Doc, Element, debug, run_filters |
|
11
|
|
|
|
|
12
|
|
|
|
|
13
|
|
|
def parse_include(parsed: dict[str, Any], name: str, value: str) -> None: |
|
14
|
|
|
""" |
|
15
|
|
|
Extract include information from attributes. |
|
16
|
|
|
|
|
17
|
|
|
Arguments |
|
18
|
|
|
--------- |
|
19
|
|
|
parsed |
|
20
|
|
|
A dictionnary of attributes |
|
21
|
|
|
name |
|
22
|
|
|
attribute name |
|
23
|
|
|
value |
|
24
|
|
|
attribute value |
|
25
|
|
|
""" |
|
26
|
|
|
if name == "include": |
|
27
|
|
|
try: |
|
28
|
|
|
with open(value, encoding="utf-8") as stream: |
|
29
|
|
|
file_content = stream.readlines() |
|
30
|
|
|
parsed["content"] = file_content |
|
31
|
|
|
parsed["include"] = value |
|
32
|
|
|
except OSError: |
|
33
|
|
|
debug("[WARNING] pandoc-codeblock-include: " + value + " not found") |
|
34
|
|
|
except UnicodeDecodeError: |
|
35
|
|
|
debug( |
|
36
|
|
|
"[WARNING] pandoc-codeblock-include: file " |
|
37
|
|
|
+ value |
|
38
|
|
|
+ " is not encoded in utf-8" |
|
39
|
|
|
) |
|
40
|
|
|
|
|
41
|
|
|
|
|
42
|
|
|
def parse_start_from(parsed: dict[str, Any], name: str, value: str) -> None: |
|
43
|
|
|
""" |
|
44
|
|
|
Extract startFrom information from attributes. |
|
45
|
|
|
|
|
46
|
|
|
Arguments |
|
47
|
|
|
--------- |
|
48
|
|
|
parsed |
|
49
|
|
|
A dictionnary of attributes |
|
50
|
|
|
name |
|
51
|
|
|
attribute name |
|
52
|
|
|
value |
|
53
|
|
|
attribute value |
|
54
|
|
|
""" |
|
55
|
|
|
if name == "startFrom": |
|
56
|
|
|
try: |
|
57
|
|
|
parsed["start_from"] = int(value) - 1 |
|
58
|
|
|
except ValueError: |
|
59
|
|
|
debug( |
|
60
|
|
|
"[WARNING] pandoc-codeblock-include: " |
|
61
|
|
|
+ value |
|
62
|
|
|
+ " is not a correct integer" |
|
63
|
|
|
) |
|
64
|
|
|
|
|
65
|
|
|
|
|
66
|
|
|
def parse_end_at(parsed: dict[str, Any], name: str, value: str) -> None: |
|
67
|
|
|
""" |
|
68
|
|
|
Extract information from attributes. |
|
69
|
|
|
|
|
70
|
|
|
Arguments |
|
71
|
|
|
--------- |
|
72
|
|
|
parsed |
|
73
|
|
|
A dictionnary of attributes |
|
74
|
|
|
name |
|
75
|
|
|
attribute name |
|
76
|
|
|
value |
|
77
|
|
|
attribute value |
|
78
|
|
|
""" |
|
79
|
|
|
if name == "endAt": |
|
80
|
|
|
try: |
|
81
|
|
|
parsed["end_at"] = int(value) |
|
82
|
|
|
except ValueError: |
|
83
|
|
|
debug( |
|
84
|
|
|
"[WARNING] pandoc-codeblock-include: " |
|
85
|
|
|
+ value |
|
86
|
|
|
+ " is not a correct integer" |
|
87
|
|
|
) |
|
88
|
|
|
|
|
89
|
|
|
|
|
90
|
|
|
def parse_attributes(items: Iterable[tuple[str, str]]) -> dict[str, str]: |
|
91
|
|
|
""" |
|
92
|
|
|
Extract usefull information from attributes. |
|
93
|
|
|
|
|
94
|
|
|
Arguments |
|
95
|
|
|
--------- |
|
96
|
|
|
items |
|
97
|
|
|
element attributes |
|
98
|
|
|
|
|
99
|
|
|
Returns |
|
100
|
|
|
------- |
|
101
|
|
|
dict[str, str] |
|
102
|
|
|
a mapping containing possible 'content', 'start_from' and 'end_at' |
|
103
|
|
|
""" |
|
104
|
|
|
parsed: dict[str, Any] = {} |
|
105
|
|
|
for name, value in items: |
|
106
|
|
|
parse_include(parsed, name, value) |
|
107
|
|
|
parse_start_from(parsed, name, value) |
|
108
|
|
|
parse_end_at(parsed, name, value) |
|
109
|
|
|
return parsed |
|
110
|
|
|
|
|
111
|
|
|
|
|
112
|
|
|
def inject_content(elem: Element, parsed: dict[str, Any]) -> None: |
|
113
|
|
|
""" |
|
114
|
|
|
Inject parsed attributes into element content. |
|
115
|
|
|
|
|
116
|
|
|
Arguments |
|
117
|
|
|
--------- |
|
118
|
|
|
elem |
|
119
|
|
|
Pandoc element |
|
120
|
|
|
parsed |
|
121
|
|
|
dictionnary of attributes |
|
122
|
|
|
""" |
|
123
|
|
|
start_from = parsed.get("start_from", 0) |
|
124
|
|
|
end_at = parsed.get("end_at", len(parsed["content"])) |
|
125
|
|
|
text = parsed["content"][start_from:end_at] |
|
126
|
|
|
|
|
127
|
|
|
# inject file content in element text |
|
128
|
|
|
try: |
|
129
|
|
|
elem.text = "".join(line.decode("utf8") for line in text) |
|
130
|
|
|
except AttributeError: |
|
131
|
|
|
elem.text = "".join(text) |
|
132
|
|
|
except UnicodeDecodeError: |
|
133
|
|
|
debug( |
|
134
|
|
|
"[WARNING] pandoc-codeblock-include: file " |
|
135
|
|
|
+ parsed["include"] |
|
136
|
|
|
+ " is not encoded in utf-8" |
|
137
|
|
|
) |
|
138
|
|
|
|
|
139
|
|
|
|
|
140
|
|
|
def clear_latex_attributes(elem: Element) -> None: |
|
141
|
|
|
""" |
|
142
|
|
|
Clear LaTeX attributes. |
|
143
|
|
|
|
|
144
|
|
|
Arguments |
|
145
|
|
|
--------- |
|
146
|
|
|
elem |
|
147
|
|
|
current element |
|
148
|
|
|
""" |
|
149
|
|
|
# Clear the attributes else latex will get a problem with the listings |
|
150
|
|
|
for attribute in ("include", "endAt"): |
|
151
|
|
|
if attribute in elem.attributes: |
|
152
|
|
|
del elem.attributes[attribute] |
|
153
|
|
|
|
|
154
|
|
|
|
|
155
|
|
|
def include(elem: Element, doc: Doc) -> None: |
|
156
|
|
|
""" |
|
157
|
|
|
Transform CodeBlock element. |
|
158
|
|
|
|
|
159
|
|
|
Arguments |
|
160
|
|
|
--------- |
|
161
|
|
|
elem |
|
162
|
|
|
current element |
|
163
|
|
|
doc |
|
164
|
|
|
pandoc document |
|
165
|
|
|
""" |
|
166
|
|
|
# Is it a CodeBlock? |
|
167
|
|
|
if isinstance(elem, CodeBlock): |
|
168
|
|
|
parsed = parse_attributes(elem.attributes.items()) |
|
169
|
|
|
if "content" in parsed: |
|
170
|
|
|
inject_content(elem, parsed) |
|
171
|
|
|
if doc.format in ("latex", "beamer"): |
|
172
|
|
|
clear_latex_attributes(elem) |
|
173
|
|
|
|
|
174
|
|
|
|
|
175
|
|
|
def main(doc: Doc | None = None) -> Doc: |
|
176
|
|
|
""" |
|
177
|
|
|
Convert the pandoc document. |
|
178
|
|
|
|
|
179
|
|
|
Arguments |
|
180
|
|
|
--------- |
|
181
|
|
|
doc |
|
182
|
|
|
pandoc document |
|
183
|
|
|
|
|
184
|
|
|
Returns |
|
185
|
|
|
------- |
|
186
|
|
|
Doc |
|
187
|
|
|
The modified pandoc document. |
|
188
|
|
|
""" |
|
189
|
|
|
return run_filters([include], doc=doc) |
|
190
|
|
|
|
|
191
|
|
|
|
|
192
|
|
|
if __name__ == "__main__": |
|
193
|
|
|
main() |
|
194
|
|
|
|