import html
import re
import time
from itertools import takewhile
from urllib.parse import quote
from features.format import SHARED, formatted
from features.row_links.formatters import Mention, named
CODE_SPAN = re.compile(r"`([^`]+)`")
BOLD = re.compile(r"\*\*(.+?)\*\*")
ITALIC = re.compile(r"(?])\bhttps?://[^\s<>\"']+[^\s<>\"'.,;:)]")
LIST_ITEM = re.compile(r"^\s*(?:[-*]|(\d+)\.)\s+(.*)$")
HEADING = re.compile(r"^(#{1,4})\s+(.*)$")
FENCES = ("```", "~~~")
PICTURES = (".png", ".jpg", ".jpeg", ".gif", ".webp")
EXPORTED = "."
class Page:
def __init__(self, root: str, scope: set[str], record=None):
self.root, self.scope, self.record = root, scope, record
def title(self, text: str) -> str:
return html.escape(formatted(text, self.record, SHARED))
def href(self, ref: str) -> str:
env, _, row = ref.rpartition("/")
if env:
return f"{self.root}/{quote(ref, safe='')}"
kind, _, n = row.partition(":")
return f"{self.root}/{kind}/{n}"
def file_href(self, ref: str, name: str) -> str:
env, _, row = ref.rpartition("/")
if env:
return f"{self.root}/files/{quote(ref, safe='')}/{quote(name, safe='')}"
kind, _, n = row.partition(":")
return f"{self.root}/files/{kind}/{n}/{quote(name, safe='')}"
def refs(self, text: str) -> str:
names, pattern = named()
def linked(m) -> str:
said = Mention.of(m, names)
ref = said.ref(said.numbers[0])
return f'{m.group(0)}' if ref in self.scope else m.group(0)
return pattern.sub(linked, text)
def inline(self, text: str) -> str:
spans = []
def kept(m) -> str:
spans.append(f"{html.escape(m.group(1))}")
return f"\x00{len(spans) - 1}\x00"
text = html.escape(CODE_SPAN.sub(kept, text), quote=False)
text = LINK.sub(lambda m: f'{m.group(1)}', text)
text = URL.sub(lambda m: f'{m.group(0)}', text)
text = self.refs(ITALIC.sub(r"\1", BOLD.sub(r"\1", text)))
return re.sub("\x00(\\d+)\x00", lambda m: spans[int(m.group(1))], text)
def markdown(self, text: str) -> str:
out, lines, i = [], text.replace("\r", "").split("\n"), 0
while i < len(lines):
line = lines[i]
if line.startswith(FENCES):
fence, body, i = line[:3], [], i + 1
while i < len(lines) and not lines[i].startswith(fence):
body.append(lines[i])
i += 1
out.append(f"
{html.escape(chr(10).join(body))}
")
i += 1
continue
if not line.strip():
i += 1
continue
heading = HEADING.match(line)
if heading:
level = min(6, len(heading.group(1)) + 2)
out.append(f"{self.inline(heading.group(2))}")
i += 1
continue
if LIST_ITEM.match(line):
ordered = bool(LIST_ITEM.match(line).group(1))
items = []
while i < len(lines) and LIST_ITEM.match(lines[i]):
items.append(f"
{self.inline(LIST_ITEM.match(lines[i]).group(2))}
")
i += 1
tag = "ol" if ordered else "ul"
out.append(f"<{tag}>{''.join(items)}")
continue
if line.startswith(">"):
quoted = []
while i < len(lines) and lines[i].startswith(">"):
quoted.append(lines[i].lstrip("> "))
i += 1
out.append(f"
{self.inline(' '.join(quoted))}
")
continue
if line.lstrip().startswith("|"):
block = list(takewhile(lambda row: row.lstrip().startswith("|"), lines[i:]))
i += len(block)
out.append(self.table(block))
continue
paragraph = []
while i < len(lines) and lines[i].strip() and not (lines[i].startswith((*FENCES, ">")) or HEADING.match(lines[i]) or LIST_ITEM.match(lines[i])):
paragraph.append(lines[i].strip())
i += 1
out.append(f"
{self.inline(' '.join(paragraph))}
")
return "\n".join(out)
def table(self, block: list[str]) -> str:
rows = [[c.strip() for c in line.strip().strip("|").split("|")] for line in block]
shown = [cells for cells in rows if not all(set(c) <= set("-: ") for c in cells)]
return "
')
if r.brief:
parts.append(self.markdown(r.brief))
for section in r.sections:
parts.append(f"
{self.title(section.get('title', ''))}
")
parts.append(self.markdown(section.get("body", "")))
pictures = [name for name in r.files if name.lower().endswith(PICTURES)]
for name in pictures:
parts.append(f'')
others = [name for name in r.files if name not in pictures]
if others:
items = "".join(f'