doc_parsing_utils.py — fastapi Source File

Source Code

import re
from typing import TypedDict, Union

CODE_INCLUDE_RE = re.compile(r"^\{\*\s*(\S+)\s*(.*)\*\}$")
CODE_INCLUDE_PLACEHOLDER = "<CODE_INCLUDE>"

HEADER_WITH_PERMALINK_RE = re.compile(r"^(#{1,6}) (.+?)(\s*\{\s*#.*\s*\})?\s*$")
HEADER_LINE_RE = re.compile(r"^(#{1,6}) (.+?)(?:\s*\{\s*(#.*)\s*\})?\s*$")

TIANGOLO_COM = "https://fastapi.tiangolo.com"
ASSETS_URL_PREFIXES = ("/img/", "/css/", "/js/")

MARKDOWN_LINK_RE = re.compile(
    r"(?<!\\)(?<!\!)"  # not an image ![...] and not escaped \[...]
    r"\[(?P<text>.*?)\]"  # link text (non-greedy)
    r"\("
    r"(?P<url>[^)\s]+)"  # url (no spaces and `)`)
    r'(?:\s+["\'](?P<title>.*?)["\'])?'  # optional title in "" or ''
    r"\)"
    r"(?:\s*\{(?P<attrs>[^}]*)\})?"  # optional attributes in {}
)

HTML_LINK_RE = re.compile(r"<a\s+[^>]*>.*?</a>")
HTML_LINK_TEXT_RE = re.compile(r"<a\b([^>]*)>(.*?)</a>")
HTML_LINK_OPEN_TAG_RE = re.compile(r"<a\b([^>]*)>")
HTML_ATTR_RE = re.compile(r'(\w+)\s*=\s*([\'"])(.*?)\2')

CODE_BLOCK_LANG_RE = re.compile(r"^`{3,4}([\w-]*)", re.MULTILINE)

SLASHES_COMMENT_RE = re.compile(
    r"^(?P<code>.*?)(?P<comment>(?:(?<= )// .*)|(?:^// .*))?$"
)

HASH_COMMENT_RE = re.compile(r"^(?P<code>.*?)(?P<comment>(?:(?<= )# .*)|(?:^# .*))?$")


class CodeIncludeInfo(TypedDict):
    line_no: int
    line: str


class HeaderPermalinkInfo(TypedDict):
    line_no: int
    hashes: str
    title: str
    permalink: str


class MarkdownLinkInfo(TypedDict):
    line_no: int
    url: str
    text: str
    title: Union[str, None]
    attributes: Union[str, None]
    full_match: str


class HTMLLinkAttribute(TypedDict):
    name: str
    quote: str
// ... (674 more lines)