{{ message }}
Repository navigation
Expand file tree
/
Copy pathfenced_code.py
More file actions
202 lines (171 loc) · 8.72 KB
/
Copy pathfenced_code.py
File metadata and controls
202 lines (171 loc) · 8.72 KB
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
# Fenced Code Extension for Python Markdown
# =========================================
# This extension adds Fenced Code Blocks to Python-Markdown.
# See https://Python-Markdown.github.io/extensions/fenced_code_blocks
# for documentation.
# Original code Copyright 2007-2008 [Waylan Limberg](https://github.com/waylan).
# All changes Copyright 2008-2014 The Python Markdown Project
# License: [BSD](https://opensource.org/licenses/bsd-license.php)
"""
This extension adds Fenced Code Blocks to Python-Markdown.
See the [documentation](https://Python-Markdown.github.io/extensions/fenced_code_blocks)
for details.
"""
from __future__ import annotations
from textwrap import dedent
from . import Extension
from ..preprocessors import Preprocessor
from .codehilite import CodeHilite, CodeHiliteExtension, parse_hl_lines
from .attr_list import get_attrs_and_remainder, sanitize_name, AttrListExtension
from ..util import parseBoolValue
from ..serializers import _escape_attrib_html
import re
from typing import TYPE_CHECKING, Any, Iterable
if TYPE_CHECKING: # pragma: no cover
from markdown import Markdown
class FencedCodeExtension(Extension):
def __init__(self, **kwargs):
self.config = {
'lang_prefix': ['language-', 'Prefix prepended to the language. Default: "language-"']
}
""" Default configuration options. """
super().__init__(**kwargs)
def extendMarkdown(self, md):
"""
Register the processor.
| Class Instance | Registry | Name | Priority |
| --------------------------------------------------------------------------- | ---------------------------------------------------------------- | ------ | :------: |
| [`FencedBlockPreprocessor`][markdown.extensions.fenced_code.FencedBlockPreprocessor] | [`blockprocessors`][markdown.blockprocessors.build_block_parser] | `fenced_code_block` | `25` |
"""
# flake8: noqa: E501 50-52
md.registerExtension(self)
md.preprocessors.register(FencedBlockPreprocessor(md, self.getConfigs()), 'fenced_code_block', 25)
class FencedBlockPreprocessor(Preprocessor):
""" Find and extract fenced code blocks. """
FENCED_BLOCK_RE = re.compile(
dedent(r'''
(?P<fence>^(?:~{3,}|`{3,}))[ ]* # opening fence
((\{(?P<attrs>[^\n]*)\})| # (optional {attrs} or
(\.?(?P<lang>[\w#.+-]*)[ ]*)? # optional (.)lang
(hl_lines=(?P<quot>"|')(?P<hl_lines>.*?)(?P=quot)[ ]*)?) # optional hl_lines)
\n # newline (end of opening fence)
(?P<code>.*?)(?<=\n) # the code block
(?P=fence)[ ]*$ # closing fence
'''),
re.MULTILINE | re.DOTALL | re.VERBOSE
)
def __init__(self, md: Markdown, config: dict[str, Any]):
super().__init__(md)
self.config = config
self.checked_for_deps = False
self.codehilite_conf: dict[str, Any] = {}
self.use_attr_list = False
# List of options to convert to boolean values
self.bool_options = [
'linenums',
'guess_lang',
'noclasses',
'use_pygments'
]
def run(self, lines: list[str]) -> list[str]:
""" Match and store Fenced Code Blocks in the `HtmlStash`. """
# Check for dependent extensions
if not self.checked_for_deps:
for ext in self.md.registeredExtensions:
if isinstance(ext, CodeHiliteExtension):
self.codehilite_conf = ext.getConfigs()
if isinstance(ext, AttrListExtension):
self.use_attr_list = True
self.checked_for_deps = True
text = "\n".join(lines)
index = 0
while 1:
m = self.FENCED_BLOCK_RE.search(text, index)
if m:
lang, id, classes, config = None, '', [], {}
if m.group('attrs'):
attrs, remainder = get_attrs_and_remainder(m.group('attrs'))
if remainder: # Does not have correctly matching curly braces, so the syntax is invalid.
index = m.end('attrs') # Explicitly skip over this, to prevent an infinite loop.
continue
id, classes, config = self.handle_attrs(attrs)
if len(classes):
lang = classes.pop(0)
else:
if m.group('lang'):
lang = m.group('lang')
if m.group('hl_lines'):
# Support `hl_lines` outside of `attrs` for backward-compatibility
config['hl_lines'] = parse_hl_lines(m.group('hl_lines'))
# If `config` is not empty, then the `codehighlite` extension
# is enabled, so we call it to highlight the code
if self.codehilite_conf and self.codehilite_conf['use_pygments'] and config.get('use_pygments', True):
local_config = self.codehilite_conf.copy()
local_config.update(config)
# Combine classes with `cssclass`. Ensure `cssclass` is at end
# as Pygments appends a suffix under certain circumstances.
# Ignore ID as Pygments does not offer an option to set it.
if classes:
local_config['css_class'] = '{} {}'.format(
' '.join(classes),
local_config['css_class']
)
highliter = CodeHilite(
m.group('code'),
lang=lang,
style=local_config.pop('pygments_style', 'default'),
**local_config
)
code = highliter.hilite(shebang=False)
else:
id_attr = lang_attr = class_attr = kv_pairs = ''
if lang:
prefix = self.config.get('lang_prefix', 'language-')
lang_attr = f' class="{prefix}{_escape_attrib_html(lang)}"'
if classes:
class_attr = f' class="{_escape_attrib_html(" ".join(classes))}"'
if id:
id_attr = f' id="{_escape_attrib_html(id)}"'
if self.use_attr_list and config and not config.get('use_pygments', False):
# Only assign key/value pairs to code element if `attr_list` extension is enabled, key/value
# pairs were defined on the code block, and the `use_pygments` key was not set to `True`. The
# `use_pygments` key could be either set to `False` or not defined. It is omitted from output.
kv_pairs = ''.join(
f' {sanitize_name(k)}="{_escape_attrib_html(v)}"'
for k, v in config.items() if k != 'use_pygments'
)
code = self._escape(m.group('code'))
code = f'<pre{id_attr}{class_attr}><code{lang_attr}{kv_pairs}>{code}</code></pre>'
placeholder = self.md.htmlStash.store(code)
text = f'{text[:m.start()]}\n{placeholder}\n{text[m.end():]}'
# Continue from after the replaced text in the next iteration.
index = m.start() + 1 + len(placeholder)
else:
break
return text.split("\n")
def handle_attrs(self, attrs: Iterable[tuple[str, str]]) -> tuple[str, list[str], dict[str, Any]]:
""" Return tuple: `(id, [list, of, classes], {configs})` """
id = ''
classes = []
configs = {}
for k, v in attrs:
if k == 'id':
id = v
elif k == '.':
classes.append(v)
elif k == 'hl_lines':
configs[k] = parse_hl_lines(v)
elif k in self.bool_options:
configs[k] = parseBoolValue(v, fail_on_errors=False, preserve_none=True)
else:
configs[k] = v
return id, classes, configs
def _escape(self, txt: str) -> str:
""" basic html escaping """
txt = txt.replace('&', '&')
txt = txt.replace('<', '<')
txt = txt.replace('>', '>')
txt = txt.replace('"', '"')
return txt
def makeExtension(**kwargs): # pragma: no cover
return FencedCodeExtension(**kwargs)
You can’t perform that action at this time.