klbr/khoj
1
0
Fork 0
mirror of https://github.com/khoaliber/khoj.git synced 2026-03-06 13:22:12 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix grep files tool to work with line start, end anchors

Browse Source 
Previously line start, end anchors would just work if the whole file
started or ended with the regex pattern rather than matching by line.

Fix it to work like a standard grep tool and match by line start, end.
This commit is contained in:
Debanjum
2025-08-08 15:20:28 -07:00
parent a79025ee93
commit 0e1615acc8
2 changed files with 284 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
src/khoj/routers/helpers.py
View File

@@ -3002,7 +3002,7 @@ async def grep_files(
lines_after = lines_after or 0
try:
regex = re.compile(regex_pattern, re.IGNORECASE)
regex = re.compile(regex_pattern, re.IGNORECASE | re.MULTILINE)
except re.error as e:
yield {
"query": _generate_query(0, 0, path_prefix, regex_pattern, lines_before, lines_after),
@@ -3012,7 +3012,14 @@ async def grep_files(
return
try:
file_matches = await FileObjectAdapters.aget_file_objects_by_regex(user, regex_pattern, path_prefix)
# Make db pushdown filters more permissive by removing line anchors
# The precise line-anchored matching will be done in Python stage
db_pattern = regex_pattern
db_pattern = re.sub(r"\(\?\w*\)", "", db_pattern) # Remove inline flags like (?i), (?m), (?im)
db_pattern = re.sub(r"^\^", "", db_pattern) # Remove ^ at regex pattern start
db_pattern = re.sub(r"\$$", "", db_pattern) # Remove $ at regex pattern end
file_matches = await FileObjectAdapters.aget_file_objects_by_regex(user, db_pattern, path_prefix)
line_matches = []
for file_object in file_matches: