Files
our-claude-skills/custom-skills/32-notion-writer/code/scripts/md_translate.py
2026-06-27 11:13:31 +09:00

122 lines
4.4 KiB
Python
Raw Blame History

This file contains invisible Unicode characters
This file contains invisible Unicode characters that are indistinguishable to humans but may be processed differently by a computer. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
#!/usr/bin/env python3
"""Translate the notion-writer markdown dialect into Notion enhanced
markdown for the markdown write engine. Pure functions, no I/O."""
from __future__ import annotations
import re
from typing import List
# NOTE: `notion_writer` is imported lazily inside _translate_mentions to avoid
# a circular import (notion_writer imports this module at its top level).
# Skill alert type -> (emoji, Notion enhanced-markdown background color)
CALLOUT_MAP = {
"NOTE": ("", "blue_bg"),
"TIP": ("💡", "green_bg"),
"IMPORTANT": ("☝️", "purple_bg"),
"WARNING": ("⚠️", "yellow_bg"),
"CAUTION": ("🚨", "red_bg"),
}
_ALERT_RE = re.compile(r'^\s*\[!(NOTE|TIP|IMPORTANT|WARNING|CAUTION)\]\s*$')
_MENTION_RE = re.compile(r'@\[([^\]]+)\]\(([^)\s]+)\)')
def _translate_mentions(text: str) -> str:
from notion_writer import extract_notion_id, format_id_with_dashes # lazy: breaks import cycle
def repl(m: "re.Match") -> str:
title, target = m.group(1), m.group(2)
page_id = extract_notion_id(target)
if page_id:
return (f'<mention-page url="{format_id_with_dashes(page_id)}">'
f'{title}</mention-page>')
return f"@{title}"
return _MENTION_RE.sub(repl, text)
def _indent(lines: List[str]) -> List[str]:
return ["\t" + ln if ln.strip() else ln for ln in lines]
def translate(content: str) -> str:
lines = content.split("\n")
out: List[str] = []
i = 0
while i < len(lines):
line = lines[i]
# Callout: > [!TYPE] then contiguous > body lines
if line.lstrip().startswith(">"):
body_first = line.lstrip()[1:].strip()
alert = _ALERT_RE.match(body_first)
if alert:
emoji, color = CALLOUT_MAP[alert.group(1)]
i += 1
body: List[str] = []
while i < len(lines) and lines[i].lstrip().startswith(">"):
body.append(lines[i].lstrip()[1:].lstrip())
i += 1
out.append(f'<callout icon="{emoji}" color="{color}">')
out.extend(_indent([_translate_mentions(b) for b in body]))
out.append("</callout>")
continue
# Columns: ::: columns / ::: column / :::
# State machine: "::: column" opens a column; ":::" closes a column
# when one is open, otherwise closes the wrapper. The Pandoc layout
# emits N "::: column" opens, N ":::" column-closes, then one final
# ":::" wrapper-close.
if line.strip() == "::: columns":
i += 1
cols: List[List[str]] = []
cur: List[str] = None
while i < len(lines):
s = lines[i].strip()
if s == "::: column":
if cur is not None:
cols.append(cur)
cur = []
i += 1
elif s == ":::":
if cur is not None: # close the open column
cols.append(cur)
cur = None
i += 1
else: # close the wrapper
i += 1
break
else:
if cur is not None:
cur.append(lines[i])
i += 1
out.append("<columns>")
for col in cols:
out.append("\t<column>")
out.extend(_indent(_indent(
[_translate_mentions(c) for c in col])))
out.append("\t</column>")
out.append("</columns>")
continue
# Toggle: <details><summary>..</summary> body </details>
if line.strip() == "<details>":
out.append("<details>")
i += 1
if i < len(lines) and lines[i].lstrip().startswith("<summary>"):
out.append(lines[i].strip())
i += 1
body = []
while i < len(lines) and lines[i].strip() != "</details>":
body.append(_translate_mentions(lines[i]))
i += 1
out.extend(_indent(body))
out.append("</details>")
if i < len(lines): # skip closing </details>
i += 1
continue
out.append(_translate_mentions(line))
i += 1
return "\n".join(out)