fix: prevent Telegram 400 from local markdown links (#214)

src/takopi/telegram/render.py

@@ -3,6 +3,7 @@ from __future__ import annotations
 import re
 from dataclasses import dataclass
 from typing import Any
+from urllib.parse import urlparse
 
 from markdown_it import MarkdownIt
 from sulguk import transform_html
@@ -78,10 +79,29 @@ def render_markdown(md: str) -> tuple[str, list[dict[str, Any]]]:
 
     text = _BULLET_RE.sub(r"\1-", rendered.text)
 
-    entities = [dict(e) for e in rendered.entities]
+    entities = _sanitize_entities(rendered.entities)
     return text, entities
 
 
+def _sanitize_entities(entities: list[Any]) -> list[dict[str, Any]]:
+    sanitized: list[dict[str, Any]] = []
+    for raw in entities:
+        entity = dict(raw)
+        if entity.get("type") == "text_link":
+            url = entity.get("url")
+            if not isinstance(url, str) or not _is_supported_text_link_url(url):
+                continue
+        sanitized.append(entity)
+    return sanitized
+
+
+def _is_supported_text_link_url(url: str) -> bool:
+    parsed = urlparse(url)
+    if parsed.scheme in {"http", "https"} and bool(parsed.netloc):
+        return True
+    return parsed.scheme == "tg" and (bool(parsed.netloc) or bool(parsed.path))
+
+
 def _split_line_ending(line: str) -> tuple[str, str]:
     if line.endswith("\r\n"):
         return line[:-2], "\r\n"

tests/test_rendering.py

@@ -22,6 +22,22 @@ def test_render_markdown_code_fence_language_is_string() -> None:
     assert any(e.get("type") == "code" for e in entities)
 
 
+def test_render_markdown_drops_local_text_links() -> None:
+    text, entities = render_markdown("[/tmp/file.py#L12](/tmp/file.py#L12)")
+
+    assert "/tmp/file.py#L12" in text
+    assert not any(e.get("type") == "text_link" for e in entities)
+
+
+def test_render_markdown_keeps_https_text_links() -> None:
+    _, entities = render_markdown("[docs](https://example.com/path)")
+
+    assert any(
+        e.get("type") == "text_link" and e.get("url") == "https://example.com/path"
+        for e in entities
+    )
+
+
 def test_render_markdown_keeps_ordered_numbering_with_unindented_sub_bullets() -> None:
     md = (
         "1. Tune maker\n"