Preserve Discord timestamp tags in message
All checks were successful
Test and build Docker image / docker (push) Successful in 1m30s
All checks were successful
Test and build Docker image / docker (push) Successful in 1m30s
This commit is contained in:
parent
f1d3204930
commit
b19927af0f
2 changed files with 213 additions and 48 deletions
|
|
@ -3,6 +3,7 @@ from __future__ import annotations
|
|||
import html
|
||||
import json
|
||||
import logging
|
||||
import re
|
||||
from dataclasses import dataclass
|
||||
|
||||
from bs4 import BeautifulSoup
|
||||
|
|
@ -18,6 +19,8 @@ from discord_rss_bot.settings import get_reader
|
|||
|
||||
logger: logging.Logger = logging.getLogger(__name__)
|
||||
|
||||
DISCORD_TIMESTAMP_TAG_RE: re.Pattern[str] = re.compile(r"<t:\d+(?::[tTdDfFrRsS])?>")
|
||||
|
||||
|
||||
@dataclass(slots=True)
|
||||
class CustomEmbed:
|
||||
|
|
@ -51,6 +54,68 @@ def try_to_replace(custom_message: str, template: str, replace_with: str) -> str
|
|||
return custom_message
|
||||
|
||||
|
||||
def _preserve_discord_timestamp_tags(text: str) -> tuple[str, dict[str, str]]:
|
||||
"""Replace Discord timestamp tags with placeholders before markdown conversion.
|
||||
|
||||
Args:
|
||||
text: The text to replace tags in.
|
||||
|
||||
Returns:
|
||||
The text with Discord timestamp tags replaced by placeholders and a mapping of placeholders to original tags.
|
||||
"""
|
||||
replacements: dict[str, str] = {}
|
||||
|
||||
def replace_match(match: re.Match[str]) -> str:
|
||||
placeholder: str = f"DISCORDTIMESTAMPPLACEHOLDER{len(replacements)}"
|
||||
replacements[placeholder] = match.group(0)
|
||||
return placeholder
|
||||
|
||||
return DISCORD_TIMESTAMP_TAG_RE.sub(replace_match, text), replacements
|
||||
|
||||
|
||||
def _restore_discord_timestamp_tags(text: str, replacements: dict[str, str]) -> str:
|
||||
"""Restore preserved Discord timestamp tags after markdown conversion.
|
||||
|
||||
Args:
|
||||
text: The text to restore tags in.
|
||||
replacements: A mapping of placeholders to original Discord timestamp tags.
|
||||
|
||||
Returns:
|
||||
The text with placeholders replaced by the original Discord timestamp tags.
|
||||
"""
|
||||
for placeholder, original_value in replacements.items():
|
||||
text = text.replace(placeholder, original_value)
|
||||
return text
|
||||
|
||||
|
||||
def format_entry_html_for_discord(text: str) -> str:
|
||||
"""Convert entry HTML to Discord-friendly markdown while preserving Discord timestamp tags.
|
||||
|
||||
Args:
|
||||
text: The HTML text to format.
|
||||
|
||||
Returns:
|
||||
The formatted text with Discord timestamp tags preserved.
|
||||
"""
|
||||
if not text:
|
||||
return ""
|
||||
|
||||
unescaped_text: str = html.unescape(text)
|
||||
protected_text, replacements = _preserve_discord_timestamp_tags(unescaped_text)
|
||||
formatted_text: str = markdownify(
|
||||
html=protected_text,
|
||||
strip=["img", "table", "td", "tr", "tbody", "thead"],
|
||||
escape_misc=False,
|
||||
heading_style="ATX",
|
||||
)
|
||||
|
||||
if "[https://" in formatted_text or "[https://www." in formatted_text:
|
||||
formatted_text = formatted_text.replace("[https://", "[")
|
||||
formatted_text = formatted_text.replace("[https://www.", "[")
|
||||
|
||||
return _restore_discord_timestamp_tags(formatted_text, replacements)
|
||||
|
||||
|
||||
def replace_tags_in_text_message(entry: Entry) -> str:
|
||||
"""Replace tags in custom_message.
|
||||
|
||||
|
|
@ -73,30 +138,8 @@ def replace_tags_in_text_message(entry: Entry) -> str:
|
|||
|
||||
first_image: str = get_first_image(summary, content)
|
||||
|
||||
# Unescape HTML entities (e.g., <h1> becomes <h1>) before converting to markdown
|
||||
summary = html.unescape(summary)
|
||||
content = html.unescape(content)
|
||||
|
||||
summary = markdownify(
|
||||
html=summary,
|
||||
strip=["img", "table", "td", "tr", "tbody", "thead"],
|
||||
escape_misc=False,
|
||||
heading_style="ATX",
|
||||
)
|
||||
content = markdownify(
|
||||
html=content,
|
||||
strip=["img", "table", "td", "tr", "tbody", "thead"],
|
||||
escape_misc=False,
|
||||
heading_style="ATX",
|
||||
)
|
||||
|
||||
if "[https://" in content or "[https://www." in content:
|
||||
content = content.replace("[https://", "[")
|
||||
content = content.replace("[https://www.", "[")
|
||||
|
||||
if "[https://" in summary or "[https://www." in summary:
|
||||
summary = summary.replace("[https://", "[")
|
||||
summary = summary.replace("[https://www.", "[")
|
||||
summary = format_entry_html_for_discord(summary)
|
||||
content = format_entry_html_for_discord(content)
|
||||
|
||||
feed_added: str = feed.added.strftime("%Y-%m-%d %H:%M:%S") if feed.added else "Never"
|
||||
feed_last_exception: str = feed.last_exception.value_str if feed.last_exception else ""
|
||||
|
|
@ -208,30 +251,8 @@ def replace_tags_in_embed(feed: Feed, entry: Entry) -> CustomEmbed:
|
|||
|
||||
first_image: str = get_first_image(summary, content)
|
||||
|
||||
# Unescape HTML entities (e.g., <h1> becomes <h1>) before converting to markdown
|
||||
summary = html.unescape(summary)
|
||||
content = html.unescape(content)
|
||||
|
||||
summary = markdownify(
|
||||
html=summary,
|
||||
strip=["img", "table", "td", "tr", "tbody", "thead"],
|
||||
escape_misc=False,
|
||||
heading_style="ATX",
|
||||
)
|
||||
content = markdownify(
|
||||
html=content,
|
||||
strip=["img", "table", "td", "tr", "tbody", "thead"],
|
||||
escape_misc=False,
|
||||
heading_style="ATX",
|
||||
)
|
||||
|
||||
if "[https://" in content or "[https://www." in content:
|
||||
content = content.replace("[https://", "[")
|
||||
content = content.replace("[https://www.", "[")
|
||||
|
||||
if "[https://" in summary or "[https://www." in summary:
|
||||
summary = summary.replace("[https://", "[")
|
||||
summary = summary.replace("[https://www.", "[")
|
||||
summary = format_entry_html_for_discord(summary)
|
||||
content = format_entry_html_for_discord(content)
|
||||
|
||||
feed_added: str = feed.added.strftime("%Y-%m-%d %H:%M:%S") if feed.added else "Never"
|
||||
feed_last_updated: str = feed.last_updated.strftime("%Y-%m-%d %H:%M:%S") if feed.last_updated else "Never"
|
||||
|
|
|
|||
144
tests/test_custom_message.py
Normal file
144
tests/test_custom_message.py
Normal file
|
|
@ -0,0 +1,144 @@
|
|||
from __future__ import annotations
|
||||
|
||||
import typing
|
||||
from types import SimpleNamespace
|
||||
from unittest.mock import MagicMock
|
||||
from unittest.mock import patch
|
||||
|
||||
import pytest
|
||||
|
||||
from discord_rss_bot.custom_message import CustomEmbed
|
||||
from discord_rss_bot.custom_message import format_entry_html_for_discord
|
||||
from discord_rss_bot.custom_message import replace_tags_in_embed
|
||||
from discord_rss_bot.custom_message import replace_tags_in_text_message
|
||||
|
||||
if typing.TYPE_CHECKING:
|
||||
from reader import Entry
|
||||
|
||||
# https://docs.discord.com/developers/reference#message-formatting
|
||||
TIMESTAMP_FORMATS: tuple[str, ...] = (
|
||||
"<t:1773461490>",
|
||||
"<t:1773461490:F>",
|
||||
"<t:1773461490:f>",
|
||||
"<t:1773461490:D>",
|
||||
"<t:1773461490:d>",
|
||||
"<t:1773461490:t>",
|
||||
"<t:1773461490:T>",
|
||||
"<t:1773461490:R>",
|
||||
"<t:1773461490:s>",
|
||||
"<t:1773461490:S>",
|
||||
)
|
||||
|
||||
|
||||
def make_feed() -> SimpleNamespace:
|
||||
return SimpleNamespace(
|
||||
added=None,
|
||||
author="Feed Author",
|
||||
last_exception=None,
|
||||
last_updated=None,
|
||||
link="https://example.com/feed",
|
||||
subtitle="",
|
||||
title="Example Feed",
|
||||
updated=None,
|
||||
updates_enabled=True,
|
||||
url="https://example.com/feed.xml",
|
||||
user_title="",
|
||||
version="atom10",
|
||||
)
|
||||
|
||||
|
||||
def make_entry(summary: str) -> SimpleNamespace:
|
||||
feed: SimpleNamespace = make_feed()
|
||||
return SimpleNamespace(
|
||||
added=None,
|
||||
author="Entry Author",
|
||||
content=[],
|
||||
feed=feed,
|
||||
feed_url=feed.url,
|
||||
id="entry-1",
|
||||
important=False,
|
||||
link="https://example.com/entry-1",
|
||||
published=None,
|
||||
read=False,
|
||||
read_modified=None,
|
||||
summary=summary,
|
||||
title="Entry Title",
|
||||
updated=None,
|
||||
)
|
||||
|
||||
|
||||
@pytest.mark.parametrize("timestamp_tag", TIMESTAMP_FORMATS)
|
||||
def test_format_entry_html_for_discord_preserves_timestamp_tags(timestamp_tag: str) -> None:
|
||||
escaped_timestamp_tag: str = timestamp_tag.replace("<", "<").replace(">", ">")
|
||||
html_summary: str = f"<p>Starts: 2026-03-13 23:30 UTC ({escaped_timestamp_tag})</p>"
|
||||
|
||||
rendered: str = format_entry_html_for_discord(html_summary)
|
||||
|
||||
assert timestamp_tag in rendered
|
||||
assert "DISCORDTIMESTAMPPLACEHOLDER" not in rendered
|
||||
|
||||
|
||||
def test_format_entry_html_for_discord_empty_text_returns_empty_string() -> None:
|
||||
rendered: str = format_entry_html_for_discord("")
|
||||
assert not rendered
|
||||
|
||||
|
||||
def test_format_entry_html_for_discord_cleans_markdownified_https_link_text() -> None:
|
||||
html_summary: str = "[https://example.com](https://example.com)"
|
||||
|
||||
rendered: str = format_entry_html_for_discord(html_summary)
|
||||
|
||||
assert "[example.com](https://example.com)" in rendered
|
||||
assert "[https://example.com]" not in rendered
|
||||
|
||||
|
||||
def test_format_entry_html_for_discord_does_not_preserve_invalid_timestamp_style() -> None:
|
||||
invalid_timestamp: str = "<t:1773461490:Z>"
|
||||
html_summary: str = f"<p>Invalid style ({invalid_timestamp.replace('<', '<').replace('>', '>')})</p>"
|
||||
|
||||
rendered: str = format_entry_html_for_discord(html_summary)
|
||||
|
||||
assert invalid_timestamp not in rendered
|
||||
|
||||
|
||||
@patch("discord_rss_bot.custom_message.get_custom_message")
|
||||
@patch("discord_rss_bot.custom_message.get_reader")
|
||||
def test_replace_tags_in_text_message_preserves_timestamp_tags(
|
||||
mock_get_reader: MagicMock,
|
||||
mock_get_custom_message: MagicMock,
|
||||
) -> None:
|
||||
mock_get_reader.return_value = MagicMock()
|
||||
mock_get_custom_message.return_value = "{{entry_summary}}"
|
||||
summary_parts: list[str] = [
|
||||
f"<p>Format {index}: ({timestamp_tag.replace('<', '<').replace('>', '>')})</p>"
|
||||
for index, timestamp_tag in enumerate(TIMESTAMP_FORMATS, start=1)
|
||||
]
|
||||
entry_ns: SimpleNamespace = make_entry("".join(summary_parts))
|
||||
|
||||
entry: Entry = typing.cast("Entry", entry_ns)
|
||||
rendered: str = replace_tags_in_text_message(entry)
|
||||
|
||||
for timestamp_tag in TIMESTAMP_FORMATS:
|
||||
assert timestamp_tag in rendered
|
||||
|
||||
|
||||
@patch("discord_rss_bot.custom_message.get_embed")
|
||||
@patch("discord_rss_bot.custom_message.get_reader")
|
||||
def test_replace_tags_in_embed_preserves_timestamp_tags(
|
||||
mock_get_reader: MagicMock,
|
||||
mock_get_embed: MagicMock,
|
||||
) -> None:
|
||||
mock_get_reader.return_value = MagicMock()
|
||||
mock_get_embed.return_value = CustomEmbed(description="{{entry_summary}}")
|
||||
summary_parts: list[str] = [
|
||||
f"<p>Format {index}: ({timestamp_tag.replace('<', '<').replace('>', '>')})</p>"
|
||||
for index, timestamp_tag in enumerate(TIMESTAMP_FORMATS, start=1)
|
||||
]
|
||||
entry_ns: SimpleNamespace = make_entry("".join(summary_parts))
|
||||
|
||||
entry: Entry = typing.cast("Entry", entry_ns)
|
||||
|
||||
embed: CustomEmbed = replace_tags_in_embed(entry_ns.feed, entry)
|
||||
|
||||
for timestamp_tag in TIMESTAMP_FORMATS:
|
||||
assert timestamp_tag in embed.description
|
||||
Loading…
Add table
Add a link
Reference in a new issue