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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415
|
from __future__ import annotations
import contextlib
from docutils import nodes
from docutils.utils.code_analyzer import Lexer
try:
from commonmark import Parser
except ImportError:
from CommonMark import Parser # >= 0.5.6
try:
from commonmark.node import Node
except ImportError:
from CommonMark.node import Node
def custom_walker(node, space=''):
"""
A convenience function to ease debugging.
It will print the node structure that's returned from CommonMark.
The usage would be something like:
>>> content = Parser().parse('Some big text block\n===================\n\nwith content\n')
>>> custom_walker(content)
document
heading
text Some big text block
paragraph
text with content
Spaces are used to convey nesting
"""
txt = ''
with contextlib.suppress(Exception):
txt = node.literal
if txt is None or txt == '':
print(f'{space}{node.t}')
else:
print(f'{space}{node.t}\t{txt}')
cur = node.first_child
if cur:
while cur is not None:
custom_walker(cur, space + ' ')
cur = cur.nxt
def paragraph(node):
"""
Process a paragraph, which includes all content under it
"""
text = ''
if node.string_content is not None:
text = node.string_content
o = nodes.paragraph('', ' '.join(text))
o.line = node.sourcepos[0][0]
for n in markdown(node):
o.append(n)
return o
def text(node):
"""
Text in a paragraph
"""
return nodes.Text(node.literal)
def hardbreak(node):
"""
A <br /> in html or "\n" in ascii
"""
return nodes.Text('\n')
def softbreak(node):
"""
A line ending or space.
"""
return nodes.Text('\n')
def reference(node):
"""
A hyperlink. Note that alt text doesn't work,
since there's no apparent way to do that in docutils
"""
o = nodes.reference()
o['refuri'] = node.destination
if node.title:
o['name'] = node.title
for n in markdown(node):
o += n
return o
def emphasis(node):
"""
An italicized section
"""
o = nodes.emphasis()
for n in markdown(node):
o += n
return o
def strong(node):
"""
A bolded section
"""
o = nodes.strong()
for n in markdown(node):
o += n
return o
def literal(node):
"""
Inline code
"""
rendered = []
try:
if node.info is not None:
rendered = [
node.inline(classes=_[0], text=_[1])
for _ in Lexer(node.literal, node.info, tokennames='long')
]
except Exception:
pass
classes = ['code']
if node.info is not None:
classes.append(node.info)
if len(rendered) > 0:
o = nodes.literal(classes=classes)
for element in rendered:
o += element
else:
o = nodes.literal(text=node.literal, classes=classes)
for n in markdown(node):
o += n
return o
def literal_block(node):
"""
A block of code
"""
rendered = []
try:
if node.info is not None:
rendered = [
node.inline(classes=_[0], text=_[1])
for _ in Lexer(node.literal, node.info, tokennames='long')
]
except Exception:
pass
classes = ['code']
if node.info is not None:
classes.append(node.info)
if len(rendered) > 0:
o = nodes.literal_block(classes=classes)
for element in rendered:
o += element
else:
o = nodes.literal_block(text=node.literal, classes=classes)
o.line = node.sourcepos[0][0]
for n in markdown(node):
o += n
return o
def raw(node):
"""
Add some raw html (possibly as a block)
"""
o = nodes.raw(node.literal, node.literal, format='html')
if node.sourcepos is not None:
o.line = node.sourcepos[0][0]
for n in markdown(node):
o += n
return o
def transition(node):
"""
An <hr> tag in html. This has no children
"""
return nodes.transition()
def title(node):
"""
A title node. It has no children
"""
return nodes.title(node.first_child.literal, node.first_child.literal)
def section(node):
"""
A section in reStructuredText, which needs a title (the first child)
This is a custom type
"""
title = '' # All sections need an id
if node.first_child is not None and node.first_child.t == 'heading':
title = node.first_child.first_child.literal
o = nodes.section(ids=[title], names=[title])
for n in markdown(node):
o += n
return o
def block_quote(node):
"""
A block quote
"""
o = nodes.block_quote()
o.line = node.sourcepos[0][0]
for n in markdown(node):
o += n
return o
def image(node):
"""
An image element
The first child is the alt text. reStructuredText can't handle titles
"""
o = nodes.image(uri=node.destination)
if node.first_child is not None:
o['alt'] = node.first_child.literal
return o
def list_item(node):
"""
An item in a list
"""
o = nodes.list_item()
for n in markdown(node):
o += n
return o
def list_node(node):
"""
A list (numbered or not)
For numbered lists, the suffix is only rendered as . in html
"""
if node.list_data['type'] == 'bullet':
o = nodes.bullet_list(bullet=node.list_data['bullet_char'])
else:
o = nodes.enumerated_list(
suffix=node.list_data['delimiter'],
enumtype='arabic',
start=node.list_data['start'],
)
for n in markdown(node):
o += n
return o
def markdown(node):
"""
Returns a list of nodes, containing CommonMark nodes converted to docutils nodes
"""
cur = node.first_child
# Go into each child, in turn
output = []
while cur is not None:
t = cur.t
if t == 'paragraph':
output.append(paragraph(cur))
elif t == 'text':
output.append(text(cur))
elif t == 'softbreak':
output.append(softbreak(cur))
elif t == 'linebreak':
output.append(hardbreak(cur))
elif t == 'link':
output.append(reference(cur))
elif t == 'heading':
output.append(title(cur))
elif t == 'emph':
output.append(emphasis(cur))
elif t == 'strong':
output.append(strong(cur))
elif t == 'code':
output.append(literal(cur))
elif t == 'code_block':
output.append(literal_block(cur))
elif t == 'html_inline' or t == 'html_block':
output.append(raw(cur))
elif t == 'block_quote':
output.append(block_quote(cur))
elif t == 'thematic_break':
output.append(transition(cur))
elif t == 'image':
output.append(image(cur))
elif t == 'list':
output.append(list_node(cur))
elif t == 'item':
output.append(list_item(cur))
elif t == 'MDsection':
output.append(section(cur))
else:
print(f'Received unhandled type: {t}. Full print of node:')
cur.pretty()
cur = cur.nxt
return output
def finalize_section(section):
"""
Correct the nxt and parent for each child
"""
cur = section.first_child
last = section.last_child
if last is not None:
last.nxt = None
while cur is not None:
cur.parent = section
cur = cur.nxt
def nest_sections(block, level=1):
"""
Sections aren't handled by CommonMark at the moment.
This function adds sections to a block of nodes.
'title' nodes with an assigned level below 'level' will be put in a child section.
If there are no child nodes with titles of level 'level' then nothing is done
"""
cur = block.first_child
if cur is not None:
children = []
# Do we need to do anything?
nest = False
while cur is not None:
if cur.t == 'heading' and cur.level == level:
nest = True
break
cur = cur.nxt
if not nest:
return
section = Node('MDsection', 0)
section.parent = block
cur = block.first_child
while cur is not None:
if cur.t == 'heading' and cur.level == level:
# Found a split point, flush the last section if needed
if section.first_child is not None:
finalize_section(section)
children.append(section)
section = Node('MDsection', 0)
nxt = cur.nxt
# Avoid adding sections without titles at the start
if section.first_child is None:
if cur.t == 'heading' and cur.level == level:
section.append_child(cur)
else:
children.append(cur)
else:
section.append_child(cur)
cur = nxt
# If there's only 1 child then don't bother
if section.first_child is not None:
finalize_section(section)
children.append(section)
block.first_child = None
block.last_child = None
next_level = level + 1
for child in children:
# Handle nesting
if child.t == 'MDsection':
nest_sections(child, level=next_level)
# Append
if block.first_child is None:
block.first_child = child
else:
block.last_child.nxt = child
child.parent = block
child.nxt = None
child.prev = block.last_child
block.last_child = child
def parse_markdown_block(text):
"""
Parses a block of text, returning a list of docutils nodes
>>> parse_markdown_block("Some\n====\n\nblock of text\n\nHeader\n======\n\nblah\n")
[]
"""
block = Parser().parse(text)
# CommonMark can't nest sections, so do it manually
nest_sections(block)
return markdown(block)
|