From 950484a674899699de1f1313b902c12f1fd17490 Mon Sep 17 00:00:00 2001
From: Jazz Turner-Baggs <473256+jazzz@users.noreply.github.com>
Date: Tue, 2 Jun 2026 21:08:53 -0700
Subject: [PATCH] Add logging helper scripts

---
 align_logs.py     | 58 +++++++++++++++++++++++++++++++++++++++++++++++
 normalize_logs.py | 34 +++++++++++++++++++++++++++
 process_logs.sh   | 19 ++++++++++++++++
 3 files changed, 111 insertions(+)
 create mode 100644 align_logs.py
 create mode 100755 normalize_logs.py
 create mode 100755 process_logs.sh

diff --git a/align_logs.py b/align_logs.py
new file mode 100644
index 0000000..5e0ee94
--- /dev/null
+++ b/align_logs.py
@@ -0,0 +1,58 @@
+#!/usr/bin/env python3
+"""
+Usage: python3 align_logs.py <reference_file> <target_file>
+
+Translates identifiers in target_file to match reference_file,
+based on order of first appearance. Output is the translated target_file.
+Mapping is printed to stderr.
+"""
+import re
+import sys
+
+PATTERNS = [
+    ('app',         re.compile(r'(?<=app=")([^"]+)(?=")')),
+    ('proposal_id', re.compile(r'(?<=proposal_id=)(\d+)')),
+    ('conversation',re.compile(r'(?<=conversation=")([^"]+)(?=")')),
+    ('convo',       re.compile(r'(?<=convo=")([^"]+)(?=")')),
+]
+
+def extract_ordered(lines, pattern):
+    seen, seen_set = [], set()
+    for line in lines:
+        for m in pattern.finditer(line):
+            v = m.group(1)
+            if v not in seen_set:
+                seen.append(v)
+                seen_set.add(v)
+    return seen
+
+def build_mapping(ref_lines, tgt_lines):
+    mapping = {}
+    for name, pat in PATTERNS:
+        ref_vals = extract_ordered(ref_lines, pat)
+        tgt_vals = extract_ordered(tgt_lines, pat)
+        for tgt, ref in zip(tgt_vals, ref_vals):
+            if tgt != ref:
+                mapping[tgt] = ref
+                print(f"  [{name}] {tgt} -> {ref}", file=sys.stderr)
+    return mapping
+
+def apply_mapping(lines, mapping):
+    if not mapping:
+        return lines
+    keys = sorted(mapping, key=len, reverse=True)
+    pat = re.compile('|'.join(re.escape(k) for k in keys))
+    return [pat.sub(lambda m: mapping[m.group(0)], line) for line in lines]
+
+if len(sys.argv) != 3:
+    print(f"Usage: {sys.argv[0]} <reference_file> <target_file>", file=sys.stderr)
+    sys.exit(1)
+
+with open(sys.argv[1]) as f:
+    ref_lines = f.readlines()
+with open(sys.argv[2]) as f:
+    tgt_lines = f.readlines()
+
+mapping = build_mapping(ref_lines, tgt_lines)
+for line in apply_mapping(tgt_lines, mapping):
+    print(line, end="")
diff --git a/normalize_logs.py b/normalize_logs.py
new file mode 100755
index 0000000..de1e363
--- /dev/null
+++ b/normalize_logs.py
@@ -0,0 +1,34 @@
+#!/usr/bin/env python3
+import re
+import sys
+from datetime import datetime
+
+TIMESTAMP_RE = re.compile(r'^(\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}\.\d+Z)')
+
+def parse_ts(s):
+    return datetime.strptime(s, "%Y-%m-%dT%H:%M:%S.%fZ")
+
+def fmt_offset(ms):
+    if ms < 1000:
+        return f"+{ms:7.0f}ms"
+    else:
+        return f"+{ms/1000:7.3f}s "
+
+lines = sys.stdin.readlines()
+base = None
+
+for line in lines:
+    m = TIMESTAMP_RE.match(line)
+    if not m:
+        print(line, end="")
+        continue
+
+    ts = parse_ts(m.group(1))
+    if base is None:
+        base = ts
+
+    delta_us = (ts - base).total_seconds() * 1_000_000
+    rounded_ms = round(delta_us / 5000) * 5
+
+    rest = line[m.end():]
+    print(f"{fmt_offset(rounded_ms)}  {rest}", end="")
diff --git a/process_logs.sh b/process_logs.sh
new file mode 100755
index 0000000..cca6bec
--- /dev/null
+++ b/process_logs.sh
@@ -0,0 +1,19 @@
+#!/bin/bash
+set -e
+
+if [ "$#" -ne 2 ]; then
+    echo "Usage: $0 <file1> <file2>" >&2
+    exit 1
+fi
+
+FILE1="$1"
+FILE2="$2"
+SCRIPTS="$(dirname "$0")"
+
+NORM1=$(python3 "$SCRIPTS/normalize_logs.py" < "$FILE1")
+NORM2=$(python3 "$SCRIPTS/normalize_logs.py" < "$FILE2")
+
+ALIGNED2=$(python3 "$SCRIPTS/align_logs.py" <(echo "$NORM1") <(echo "$NORM2") 2>/dev/null)
+
+echo "$NORM1" > "$FILE1"
+echo "$ALIGNED2" > "$FILE2"