fix: close validator and path edge cases

This commit is contained in:
haelyra
2026-08-29 15:36:59 -04:00
parent 703163275d
commit 1bdda4bdac
6 changed files with 101 additions and 18 deletions
+3 -6
View File
@@ -58,9 +58,6 @@ if [[ ! "$evaluated_at" =~ ^[0-9]{4}-[0-9]{2}-[0-9]{2}T[0-9]{2}:[0-9]{2}:[0-9]{2
exit 1
fi
# Pre-extract known paths from results.json once (O(1) lookup per file instead of O(n*m))
known_paths=$(jq -r '.skills[].path' "$RESULTS_JSON" 2>/dev/null)
tmpdir=$(mktemp -d)
# Use a function to avoid embedding $tmpdir in a quoted string (prevents injection
# if TMPDIR were crafted to contain shell metacharacters).
@@ -90,9 +87,9 @@ process_dir() {
mtime=$(date -u -r "$file" +%Y-%m-%dT%H:%M:%SZ)
dp="${file/#$HOME/~}"
# Check if this file is known to results.json (exact whole-line match to
# avoid substring false-positives, e.g. "python-patterns" matching "python-patterns-v2").
if echo "$known_paths" | grep -qxF "$dp"; then
# Keep path comparison structured so literal newlines remain part of one
# JSON string instead of becoming ambiguous line-delimited records.
if jq -e --arg path "$dp" '.skills | any(.path == $path)' "$RESULTS_JSON" >/dev/null 2>&1; then
is_new="false"
# Known file: only emit if mtime changed (ISO 8601 string comparison is safe)
[[ "$mtime" > "$evaluated_at" ]] || continue
+13 -6
View File
@@ -134,12 +134,19 @@ scan_dir_to_json() {
name=$(extract_field "$file" "name")
desc=$(extract_field "$file" "description")
mtime=$(date -u -r "$file" +%Y-%m-%dT%H:%M:%SZ)
# Use awk exact field match to avoid substring false-positives from grep -F.
# uniq -c output format: " N /path/to/file" — path is always field 2.
u7=$(echo "$obs_7d_counts" | awk -v f="$file" '$2 == f {print $1}' | head -1)
u7="${u7:-0}"
u30=$(echo "$obs_30d_counts" | awk -v f="$file" '$2 == f {print $1}' | head -1)
u30="${u30:-0}"
if [[ "$file" == *$'\n'* ]]; then
# The aggregated fast path is line-delimited. Preserve unusual paths by
# falling back to the structured JSON matcher for this record.
u7=$(count_obs "$file" "$c7")
u30=$(count_obs "$file" "$c30")
else
# Use awk exact field match to avoid substring false-positives from grep -F.
# uniq -c output format: " N /path/to/file" — path is always field 2.
u7=$(echo "$obs_7d_counts" | awk -v f="$file" '$2 == f {print $1}' | head -1)
u7="${u7:-0}"
u30=$(echo "$obs_30d_counts" | awk -v f="$file" '$2 == f {print $1}' | head -1)
u30="${u30:-0}"
fi
dp="${file/#$HOME/~}"
jq -n \