File size: 4,358 Bytes
5f5a27c | 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 | import re
import string
from typing import Any, Dict, Tuple, Union
from .util import escape_url
PREVENT_BACKSLASH = r"(?<!\\)(?:\\\\)*"
PUNCTUATION = r"[" + re.escape(string.punctuation) + r"]"
LINK_LABEL = r"(?:[^\\\[\]]|\\.){0,500}"
LINK_BRACKET_START = re.compile(r"[ \t]*\n?[ \t]*<")
LINK_BRACKET_RE = re.compile(r"<([^<>\n\\\x00]*)>")
LINK_HREF_BLOCK_RE = re.compile(r"[ \t]*\n?[ \t]*([^\s]+)(?:\s|$)")
LINK_HREF_INLINE_RE = re.compile(
r"[ \t]*\n?[ \t]*([^ \t\n]*?)(?:[ \t\n]|"
r"(?:" + PREVENT_BACKSLASH + r"\)))"
)
LINK_TITLE_RE = re.compile(
r"[ \t\n]+("
r'"(?:\\' + PUNCTUATION + r'|[^"\x00])*"|' # "title"
r"'(?:\\" + PUNCTUATION + r"|[^'\x00])*'" # 'title'
r")"
)
PAREN_END_RE = re.compile(r"\s*\)")
HTML_TAGNAME = r"[A-Za-z][A-Za-z0-9-]*"
HTML_ATTRIBUTES = (
r"(?:\s+[A-Za-z_:][A-Za-z0-9_.:-]*"
r'(?:\s*=\s*(?:[^ !"\'=<>`]+|\'[^\']*?\'|"[^\"]*?"))?)*'
)
BLOCK_TAGS = (
"address",
"article",
"aside",
"base",
"basefont",
"blockquote",
"body",
"caption",
"center",
"col",
"colgroup",
"dd",
"details",
"dialog",
"dir",
"div",
"dl",
"dt",
"fieldset",
"figcaption",
"figure",
"footer",
"form",
"frame",
"frameset",
"h1",
"h2",
"h3",
"h4",
"h5",
"h6",
"head",
"header",
"hr",
"html",
"iframe",
"legend",
"li",
"link",
"main",
"menu",
"menuitem",
"meta",
"nav",
"noframes",
"ol",
"optgroup",
"option",
"p",
"param",
"section",
"source",
"summary",
"table",
"tbody",
"td",
"tfoot",
"th",
"thead",
"title",
"tr",
"track",
"ul",
)
PRE_TAGS = ("pre", "script", "style", "textarea")
_INLINE_LINK_LABEL_RE = re.compile(LINK_LABEL + r"\]")
_INLINE_SQUARE_BRACKET_RE = re.compile(PREVENT_BACKSLASH + r"[\[\]]")
_ESCAPE_CHAR_RE = re.compile(r"\\(" + PUNCTUATION + r")")
def unescape_char(text: str) -> str:
return _ESCAPE_CHAR_RE.sub(r"\1", text)
def parse_link_text(src: str, pos: int) -> Union[Tuple[str, int], Tuple[None, None]]:
level = 1
found = False
start_pos = pos
while pos < len(src):
m = _INLINE_SQUARE_BRACKET_RE.search(src, pos)
if not m:
break
pos = m.end()
marker = m.group(0)
if marker == "]":
level -= 1
if level == 0:
found = True
break
else:
level += 1
if found:
text = src[start_pos : pos - 1]
return text, pos
return None, None
def parse_link_label(src: str, start_pos: int) -> Union[Tuple[str, int], Tuple[None, None]]:
m = _INLINE_LINK_LABEL_RE.match(src, start_pos)
if m:
label = m.group(0)[:-1]
return label, m.end()
return None, None
def parse_link_href(src: str, start_pos: int, block: bool = False) -> Union[Tuple[str, int], Tuple[None, None]]:
m = LINK_BRACKET_START.match(src, start_pos)
if m:
start_pos = m.end() - 1
m = LINK_BRACKET_RE.match(src, start_pos)
if m:
return m.group(1), m.end()
return None, None
if block:
m = LINK_HREF_BLOCK_RE.match(src, start_pos)
else:
m = LINK_HREF_INLINE_RE.match(src, start_pos)
if not m:
return None, None
end_pos = m.end()
href = m.group(1)
if block and src[end_pos - 1] == href[-1]:
return href, end_pos
return href, end_pos - 1
def parse_link_title(src: str, start_pos: int, max_pos: int) -> Union[Tuple[str, int], Tuple[None, None]]:
m = LINK_TITLE_RE.match(src, start_pos, max_pos)
if m:
title = m.group(1)[1:-1]
title = unescape_char(title)
return title, m.end()
return None, None
def parse_link(src: str, pos: int) -> Union[Tuple[Dict[str, Any], int], Tuple[None, None]]:
href, href_pos = parse_link_href(src, pos)
if href is None:
return None, None
assert href_pos is not None
title, title_pos = parse_link_title(src, href_pos, len(src))
next_pos = title_pos or href_pos
m = PAREN_END_RE.match(src, next_pos)
if not m:
return None, None
href = unescape_char(href)
attrs = {"url": escape_url(href)}
if title:
attrs["title"] = title
return attrs, m.end()
|