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
|
from __future__ import annotations
import logging
import os
import posixpath
from typing import TYPE_CHECKING, Any, Mapping, MutableMapping, Optional, Union
from urllib.parse import unquote as urlunquote
from urllib.parse import urljoin, urlsplit, urlunsplit
from xml.etree.ElementTree import Element
import markdown
from markdown.extensions import Extension
from markdown.treeprocessors import Treeprocessor
from markdown.util import AMP_SUBSTITUTE
from mkdocs.structure.files import File, Files
from mkdocs.structure.toc import get_toc
from mkdocs.utils import get_build_date, get_markdown_title, meta
if TYPE_CHECKING:
from mkdocs.config.defaults import MkDocsConfig
from mkdocs.structure.nav import Section
from mkdocs.structure.toc import TableOfContents
log = logging.getLogger(__name__)
class Page:
def __init__(
self, title: Optional[str], file: File, config: Union[MkDocsConfig, Mapping[str, Any]]
) -> None:
file.page = self
self.file = file
self.title = title
# Navigation attributes
self.parent = None
self.children = None
self.previous_page = None
self.next_page = None
self.active = False
self.update_date = get_build_date()
self._set_canonical_url(config.get('site_url', None))
self._set_edit_url(
config.get('repo_url', None), config.get('edit_uri'), config.get('edit_uri_template')
)
# Placeholders to be filled in later in the build process.
self.markdown = None
self.content = None
self.toc = [] # type: ignore
self.meta = {}
def __eq__(self, other) -> bool:
return (
isinstance(other, self.__class__)
and self.title == other.title
and self.file == other.file
)
def __repr__(self):
title = f"'{self.title}'" if (self.title is not None) else '[blank]'
url = self.abs_url or self.file.url
return f"Page(title={title}, url='{url}')"
def _indent_print(self, depth=0):
return '{}{}'.format(' ' * depth, repr(self))
title: Optional[str]
"""Contains the Title for the current page."""
markdown: Optional[str]
"""The original Markdown content from the file."""
content: Optional[str]
"""The rendered Markdown as HTML, this is the contents of the documentation."""
toc: TableOfContents
"""An iterable object representing the Table of contents for a page. Each item in
the `toc` is an [`AnchorLink`][mkdocs.structure.toc.AnchorLink]."""
meta: MutableMapping[str, Any]
"""A mapping of the metadata included at the top of the markdown page."""
@property
def url(self) -> str:
"""The URL of the page relative to the MkDocs `site_dir`."""
return '' if self.file.url in ('.', './') else self.file.url
file: File
"""The documentation [`File`][mkdocs.structure.files.File] that the page is being rendered from."""
abs_url: Optional[str]
"""The absolute URL of the page from the server root as determined by the value
assigned to the [site_url][] configuration setting. The value includes any
subdirectory included in the `site_url`, but not the domain. [base_url][] should
not be used with this variable."""
canonical_url: Optional[str]
"""The full, canonical URL to the current page as determined by the value assigned
to the [site_url][] configuration setting. The value includes the domain and any
subdirectory included in the `site_url`. [base_url][] should not be used with this
variable."""
@property
def active(self) -> bool:
"""When `True`, indicates that this page is the currently viewed page. Defaults to `False`."""
return self.__active
@active.setter
def active(self, value: bool):
"""Set active status of page and ancestors."""
self.__active = bool(value)
if self.parent is not None:
self.parent.active = bool(value)
@property
def is_index(self) -> bool:
return self.file.name == 'index'
@property
def is_top_level(self) -> bool:
return self.parent is None
edit_url: Optional[str]
"""The full URL to the source page in the source repository. Typically used to
provide a link to edit the source page. [base_url][] should not be used with this
variable."""
@property
def is_homepage(self) -> bool:
"""Evaluates to `True` for the homepage of the site and `False` for all other pages."""
return self.is_top_level and self.is_index and self.file.url in ('.', './', 'index.html')
previous_page: Optional[Page]
"""The [page][mkdocs.structure.pages.Page] object for the previous page or `None`.
The value will be `None` if the current page is the first item in the site navigation
or if the current page is not included in the navigation at all."""
next_page: Optional[Page]
"""The [page][mkdocs.structure.pages.Page] object for the next page or `None`.
The value will be `None` if the current page is the last item in the site navigation
or if the current page is not included in the navigation at all."""
parent: Optional[Section]
"""The immediate parent of the page in the site navigation. `None` if the
page is at the top level."""
children: None = None
"""Pages do not contain children and the attribute is always `None`."""
is_section: bool = False
"""Indicates that the navigation object is a "section" object. Always `False` for page objects."""
is_page: bool = True
"""Indicates that the navigation object is a "page" object. Always `True` for page objects."""
is_link: bool = False
"""Indicates that the navigation object is a "link" object. Always `False` for page objects."""
@property
def ancestors(self):
if self.parent is None:
return []
return [self.parent] + self.parent.ancestors
def _set_canonical_url(self, base: Optional[str]) -> None:
if base:
if not base.endswith('/'):
base += '/'
self.canonical_url = canonical_url = urljoin(base, self.url)
self.abs_url = urlsplit(canonical_url).path
else:
self.canonical_url = None
self.abs_url = None
def _set_edit_url(
self,
repo_url: Optional[str],
edit_uri: Optional[str] = None,
edit_uri_template: Optional[str] = None,
) -> None:
if edit_uri or edit_uri_template:
src_uri = self.file.src_uri
if edit_uri_template:
noext = posixpath.splitext(src_uri)[0]
edit_uri = edit_uri_template.format(path=src_uri, path_noext=noext)
else:
assert edit_uri is not None and edit_uri.endswith('/')
edit_uri += src_uri
if repo_url:
# Ensure urljoin behavior is correct
if not edit_uri.startswith(('?', '#')) and not repo_url.endswith('/'):
repo_url += '/'
else:
try:
parsed_url = urlsplit(edit_uri)
if not parsed_url.scheme or not parsed_url.netloc:
log.warning(
f"edit_uri: {edit_uri!r} is not a valid URL, it should include the http:// (scheme)"
)
except ValueError as e:
log.warning(f"edit_uri: {edit_uri!r} is not a valid URL: {e}")
self.edit_url = urljoin(repo_url or '', edit_uri)
else:
self.edit_url = None
def read_source(self, config: MkDocsConfig) -> None:
source = config['plugins'].run_event('page_read_source', page=self, config=config)
if source is None:
try:
with open(self.file.abs_src_path, encoding='utf-8-sig', errors='strict') as f:
source = f.read()
except OSError:
log.error(f'File not found: {self.file.src_path}')
raise
except ValueError:
log.error(f'Encoding error reading file: {self.file.src_path}')
raise
self.markdown, self.meta = meta.get_data(source)
self._set_title()
def _set_title(self) -> None:
"""
Set the title for a Markdown document.
Check these in order and use the first that returns a valid title:
- value provided on init (passed in from config)
- value of metadata 'title'
- content of the first H1 in Markdown content
- convert filename to title
"""
if self.title is not None:
return
if 'title' in self.meta:
self.title = self.meta['title']
return
assert self.markdown is not None
title = get_markdown_title(self.markdown)
if title is None:
if self.is_homepage:
title = 'Home'
else:
title = self.file.name.replace('-', ' ').replace('_', ' ')
# Capitalize if the filename was all lowercase, otherwise leave it as-is.
if title.lower() == title:
title = title.capitalize()
self.title = title
def render(self, config: MkDocsConfig, files: Files) -> None:
"""
Convert the Markdown source file to HTML as per the config.
"""
extensions = [_RelativePathExtension(self.file, files), *config['markdown_extensions']]
md = markdown.Markdown(
extensions=extensions,
extension_configs=config['mdx_configs'] or {},
)
assert self.markdown is not None
self.content = md.convert(self.markdown)
self.toc = get_toc(getattr(md, 'toc_tokens', []))
class _RelativePathTreeprocessor(Treeprocessor):
def __init__(self, file: File, files: Files) -> None:
self.file = file
self.files = files
def run(self, root: Element) -> Element:
"""
Update urls on anchors and images to make them relative
Iterates through the full document tree looking for specific
tags and then makes them relative based on the site navigation
"""
for element in root.iter():
if element.tag == 'a':
key = 'href'
elif element.tag == 'img':
key = 'src'
else:
continue
url = element.get(key)
assert url is not None
new_url = self.path_to_url(url)
element.set(key, new_url)
return root
def path_to_url(self, url: str) -> str:
scheme, netloc, path, query, fragment = urlsplit(url)
if (
scheme
or netloc
or not path
or url.startswith('/')
or url.startswith('\\')
or AMP_SUBSTITUTE in url
or '.' not in os.path.split(path)[-1]
):
# Ignore URLs unless they are a relative link to a source file.
# AMP_SUBSTITUTE is used internally by Markdown only for email.
# No '.' in the last part of a path indicates path does not point to a file.
return url
# Determine the filepath of the target.
target_uri = posixpath.join(posixpath.dirname(self.file.src_uri), urlunquote(path))
target_uri = posixpath.normpath(target_uri).lstrip('/')
# Validate that the target exists in files collection.
target_file = self.files.get_file_from_path(target_uri)
if target_file is None:
log.warning(
f"Documentation file '{self.file.src_uri}' contains a link to "
f"'{target_uri}' which is not found in the documentation files."
)
return url
path = target_file.url_relative_to(self.file)
components = (scheme, netloc, path, query, fragment)
return urlunsplit(components)
class _RelativePathExtension(Extension):
"""
The Extension class is what we pass to markdown, it then
registers the Treeprocessor.
"""
def __init__(self, file: File, files: Files) -> None:
self.file = file
self.files = files
def extendMarkdown(self, md: markdown.Markdown) -> None:
relpath = _RelativePathTreeprocessor(self.file, self.files)
md.treeprocessors.register(relpath, "relpath", 0)
|