⚡ Bolt: scripts/ci/redact_sensitive_log.py 성능 개선

.jules/bolt.md

@@ -43,3 +43,6 @@
 ## 2026-07-09 - Avoid N+1 API blocking in SBOM aggregator
 **Learning:** The `collect_inventories` function in `scripts/ci/sbom_inventory_aggregator.py` was fetching SBOMs from the GitHub dependency graph synchronously for every repository in the organization. For large organizations (up to 500 repos), this N+1 network/CLI bottleneck significantly stalled the aggregation workflow.
 **Action:** Use `concurrent.futures.ThreadPoolExecutor` to fetch SBOMs concurrently when multiple repositories are provided, bounded by a `max_workers` limit (e.g., 10) to avoid overwhelming the CLI/API, while preserving the fast serial path for single-item inputs.
+## 2026-07-28 - Fast-Path Chunking for Linear Text Scanners
+**Learning:** In linear parsing functions like `_redact_assignments` that iterate char-by-char, appending a single character to a list and continuing the loop causes measurable O(N^2) overhead due to tight loop overhead and high volume of list append ops. Scanning ahead and appending non-matching text as single string slices (e.g. `output.append(text[start:cursor])`) substantially reduces this overhead and provides a fast path. Also, compiling multiple token matching regexes into a single combined regex using `|` eliminates redundant function calls for each text fragment.
+**Action:** When writing linear text scanners, batch unmatched text using an inner loop and string slicing rather than appending character-by-character. Combine multiple regex replacements acting on the same text into a single regex with `|` whenever feasible.

scripts/ci/redact_sensitive_log.py

@@ -24,11 +24,11 @@
     r"[^\s\"'\\]+",
     re.IGNORECASE,
 )
-PROVIDER_TOKEN_RES = (
-    re.compile(r"\b(?:gh[pousr]_[A-Za-z0-9_]{20,}|github_pat_[A-Za-z0-9_]{20,})\b"),
-    re.compile(r"\bsk-[A-Za-z0-9_-]{20,}\b"),
-    re.compile(r"\bxox[baprs]-[A-Za-z0-9-]{20,}\b"),
-    re.compile(r"\bAKIA[0-9A-Z]{16}\b"),
+PROVIDER_TOKEN_RE = re.compile(
+    r"\b(?:gh[pousr]_[A-Za-z0-9_]{20,}|github_pat_[A-Za-z0-9_]{20,}|"
+    r"sk-[A-Za-z0-9_-]{20,}|"
+    r"xox[baprs]-[A-Za-z0-9-]{20,}|"
+    r"AKIA[0-9A-Z]{16})\b"
 )
 
 
@@ -99,14 +99,21 @@ def _redact_assignments(text: str) -> str:
     """Redact sensitive key/value assignments without backtracking regexes."""
     output: list[str] = []
     cursor = 0
-    while cursor < len(text):
+    length = len(text)
+    while cursor < length:
         match = _consume_sensitive_assignment(text, cursor)
         if match is None:
-            output.append(text[cursor])
+            start_cursor = cursor
             cursor += 1
-            continue
-        replacement, cursor = match
-        output.append(replacement)
+            while cursor < length:
+                match = _consume_sensitive_assignment(text, cursor)
+                if match is not None:
+                    break
+                cursor += 1
+            output.append(text[start_cursor:cursor])
+        if match is not None:
+            replacement, cursor = match
+            output.append(replacement)
     return "".join(output)
 
 
@@ -115,8 +122,7 @@ def _redact_unstructured(text: str) -> str:
     cleaned = _redact_assignments(text)
     cleaned = BEARER_RE.sub(lambda match: f"{match.group('prefix')}{REDACTED}", cleaned)
     cleaned = JWT_RE.sub(REDACTED, cleaned)
-    for pattern in PROVIDER_TOKEN_RES:
-        cleaned = pattern.sub(REDACTED, cleaned)
+    cleaned = PROVIDER_TOKEN_RE.sub(REDACTED, cleaned)
     return cleaned