bvandeusen/FabledScribe
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 50 Wiki Activity

feat(rss): remove article content character cap

Browse Source 
Trafilatura extracts only article body text (typically 2K–15K chars),
so storing the full content is safe without an artificial ceiling.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Bryan Van Deusen
2026-04-05 19:32:17 -04:00
parent 9dd4178774
commit f7d54a15c0
2 changed files with 9 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/test_rss_service.py
+7 -5
View File
@@ -16,14 +16,16 @@ def test_extract_item_fields():
assert item["content"] == "A summary"
def test_extract_item_truncates_content():
"""extract_item() should truncate content to CONTENT_MAX_CHARS."""
from fabledassistant.services.rss import extract_item, CONTENT_MAX_CHARS
def test_extract_item_does_not_truncate_content():
"""extract_item() should store content without truncation."""
from fabledassistant.services.rss import extract_item
long_text = "x" * 100_000
entry = MagicMock()
entry.get = lambda k, d="": {"summary": "x" * (CONTENT_MAX_CHARS + 1000), "title": "", "link": "", "id": "g"}.get(k, d)
entry.get = lambda k, d="": {"summary": long_text, "title": "", "link": "", "id": "g"}.get(k, d)
entry.content = []
entry.published_parsed = None
item = extract_item(entry)
assert len(item["content"]) == CONTENT_MAX_CHARS
assert len(item["content"]) == 100_000
def test_extract_item_prefers_content_over_summary():