sij/khoj
1
0
Fork 0
mirror of https://github.com/khoj-ai/khoj.git synced 2024-11-23 15:38:55 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions 5

Fix adding file path instead of stem to markdown entries

Browse source
This commit is contained in:
Debanjum Singh Solanky 2024-03-31 18:03:17 +05:30
parent 720139c3c1
commit ad4fa4b2f4
2 changed files with 3 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

5
src/khoj/processor/content/markdown/markdown_to_entries.py
View file

@ -142,13 +142,12 @@ class MarkdownToEntries(TextToEntries):
entry_filename = urllib3.util.parse_url(raw_filename).url
else:
entry_filename = str(Path(raw_filename))
stem = Path(raw_filename).stem
heading = parsed_entry.splitlines()[0] if re.search("^#+\s", parsed_entry) else ""
# Append base filename to compiled entry for context to model
# Increment heading level for heading entries and make filename as its top level heading
prefix = f"# {stem}\n#" if heading else f"# {stem}\n"
compiled_entry = f"{entry_filename}\n{prefix}{parsed_entry}"
prefix = f"# {entry_filename}\n#" if heading else f"# {entry_filename}\n"
compiled_entry = f"{prefix}{parsed_entry}"
entries.append(
Entry(
compiled=compiled_entry,

2
tests/test_markdown_to_entries.py
View file

@ -16,7 +16,7 @@ def test_extract_markdown_with_no_headings(tmp_path):
data = {
f"{tmp_path}": entry,
}
expected_heading = f"# {tmp_path.stem}"
expected_heading = f"# {tmp_path}"
# Act
# Extract Entries from specified Markdown files