mirror/nanobot
1
0
Fork 0
mirror of https://github.com/HKUDS/nanobot.git synced 2026-05-04 00:35:58 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(msteams): normalize nbsp in inbound text

Browse Source
This commit is contained in:
T3chC0wb0y 2026-04-24 17:56:07 -05:00 committed by Xubin Ren
parent 722d935d37
commit fd3d7ea752
2 changed files with 20 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
nanobot/channels/msteams.py
View File

@ -312,10 +312,12 @@ class MSTeamsChannel(BaseChannel):
"""Extract the user-authored text from a Teams activity.""" """Extract the user-authored text from a Teams activity."""
text = str(activity.get("text") or "") text = str(activity.get("text") or "")
text = self._strip_possible_bot_mention(text) text = self._strip_possible_bot_mention(text)
text = self._normalize_html_whitespace(text)
channel_data = activity.get("channelData") or {} channel_data = activity.get("channelData") or {}
reply_to_id = str(activity.get("replyToId") or "").strip() reply_to_id = str(activity.get("replyToId") or "").strip()
normalized_preview = html.unescape(text).replace("&rsquo", "’").strip() normalized_preview = html.unescape(text).replace("&rsquo", "’").strip()
normalized_preview = normalized_preview.replace("\xa0", " ")
normalized_preview = normalized_preview.replace("\r\n", "\n").replace("\r", "\n") normalized_preview = normalized_preview.replace("\r\n", "\n").replace("\r", "\n")
preview_lines = [line.strip() for line in normalized_preview.split("\n")] preview_lines = [line.strip() for line in normalized_preview.split("\n")]
while preview_lines and not preview_lines[0]: while preview_lines and not preview_lines[0]:
@ -335,9 +337,15 @@ class MSTeamsChannel(BaseChannel):
cleaned = re.sub(r"(?:\r?\n){3,}", "\n\n", cleaned) cleaned = re.sub(r"(?:\r?\n){3,}", "\n\n", cleaned)
return cleaned.strip() return cleaned.strip()
def _normalize_html_whitespace(self, text: str) -> str:
"""Normalize common HTML whitespace/entities from Teams into plain text spacing."""
normalized = html.unescape(text).replace("&rsquo", "’")
normalized = normalized.replace("\xa0", " ")
return normalized
def _normalize_teams_reply_quote(self, text: str) -> str: def _normalize_teams_reply_quote(self, text: str) -> str:
"""Normalize Teams quoted replies into a compact structured form.""" """Normalize Teams quoted replies into a compact structured form."""
cleaned = html.unescape(text).replace("&rsquo", "’").strip() cleaned = self._normalize_html_whitespace(text).strip()
if not cleaned: if not cleaned:
return "" return ""

11
tests/test_msteams.py
View File

@ -261,6 +261,17 @@ def test_sanitize_inbound_text_keeps_normal_inline_message(make_channel):
assert ch._sanitize_inbound_text(activity) == "normal inline message" assert ch._sanitize_inbound_text(activity) == "normal inline message"
def test_sanitize_inbound_text_normalizes_nbsp_entities(make_channel):
ch = make_channel()
activity = {
"text": "Hello from Teams",
"channelData": {},
}
assert ch._sanitize_inbound_text(activity) == "Hello from Teams"
def test_sanitize_inbound_text_normalizes_reply_wrapper_without_reply_metadata(make_channel): def test_sanitize_inbound_text_normalizes_reply_wrapper_without_reply_metadata(make_channel):
ch = make_channel() ch = make_channel()