fix: remove nested .git folders, re-add as normal directories

This commit is contained in:
2026-03-22 17:50:47 -05:00
parent f55c7e47c9
commit 6b7eec67b8
1870 changed files with 4170168 additions and 3 deletions
+307
View File
@@ -0,0 +1,307 @@
#!/usr/bin/env python3
"""
Analyze ConnectWise API call logs.
Looks for the most recent log file in cw-api-logs/ by default,
or accepts an explicit path as an argument.
Usage:
python3 analyze-cw-calls.py # latest file in cw-api-logs/
python3 analyze-cw-calls.py cw-api-logs/specific.jsonl
"""
import json
import sys
import os
import glob
import statistics
from collections import Counter, defaultdict
from datetime import datetime, timedelta
# ── Colours ──────────────────────────────────────────────────────────────────
RED = "\033[91m"
GREEN = "\033[92m"
YELLOW = "\033[93m"
CYAN = "\033[96m"
BOLD = "\033[1m"
DIM = "\033[2m"
RESET = "\033[0m"
def colour_duration(ms: float) -> str:
if ms >= 10_000:
return f"{RED}{ms:,.0f}ms{RESET}"
if ms >= 5_000:
return f"{YELLOW}{ms:,.0f}ms{RESET}"
return f"{GREEN}{ms:,.0f}ms{RESET}"
def header(title: str) -> str:
return f"\n{BOLD}{CYAN}{'' * 60}\n {title}\n{'' * 60}{RESET}"
# ── Resolve log file ────────────────────────────────────────────────────────
def find_latest_log() -> str:
"""Find the most recent .jsonl file in cw-api-logs/."""
log_dir = os.path.join(os.getcwd(), "cw-api-logs")
files = sorted(glob.glob(os.path.join(log_dir, "*.jsonl")))
if not files:
print(f"{RED}No log files found in cw-api-logs/{RESET}")
print(f"Run {BOLD}bun run dev:log{RESET} to start logging CW API calls.")
sys.exit(1)
return files[-1]
if len(sys.argv) > 1:
log_path = sys.argv[1]
else:
log_path = find_latest_log()
print(f"{DIM}Reading: {log_path}{RESET}")
entries = []
parse_errors = 0
with open(log_path) as f:
for line in f:
line = line.strip()
if not line:
continue
try:
entries.append(json.loads(line))
except json.JSONDecodeError:
parse_errors += 1
if not entries:
print("No entries found. Check the log file path.")
sys.exit(1)
# ── Derived fields ───────────────────────────────────────────────────────────
durations = [e["durationMs"] for e in entries]
errors = [e for e in entries if e.get("error")]
successes = [e for e in entries if not e.get("error")]
timestamps = [datetime.fromisoformat(e["timestamp"].replace("Z", "+00:00")) for e in entries]
time_span = (timestamps[-1] - timestamps[0]) if len(timestamps) > 1 else timedelta(0)
# Normalise the URL to a route pattern for grouping
def normalise_url(url: str) -> str:
parts = url.split("?")[0].rstrip("/").split("/")
normalised = []
for p in parts:
if p.isdigit():
normalised.append(":id")
else:
normalised.append(p)
return "/".join(normalised)
# ── 1. Overview ──────────────────────────────────────────────────────────────
print(header("OVERVIEW"))
print(f" Log file : {log_path}")
print(f" Total calls : {BOLD}{len(entries):,}{RESET}")
print(f" Successes : {GREEN}{len(successes):,}{RESET}")
print(f" Failures : {RED}{len(errors):,}{RESET} ({len(errors)/len(entries)*100:.1f}%)")
print(f" Time span : {time_span}")
if time_span.total_seconds() > 0:
rps = len(entries) / time_span.total_seconds()
print(f" Avg req/sec : {rps:.2f}")
if parse_errors:
print(f" Parse errors : {YELLOW}{parse_errors}{RESET}")
# ── 2. Duration stats ───────────────────────────────────────────────────────
print(header("DURATION STATS (all calls)"))
sorted_dur = sorted(durations)
p50 = sorted_dur[len(sorted_dur) * 50 // 100]
p90 = sorted_dur[len(sorted_dur) * 90 // 100]
p95 = sorted_dur[len(sorted_dur) * 95 // 100]
p99 = sorted_dur[len(sorted_dur) * 99 // 100]
print(f" Min : {colour_duration(min(durations))}")
print(f" Max : {colour_duration(max(durations))}")
print(f" Mean : {colour_duration(statistics.mean(durations))}")
print(f" Median (p50) : {colour_duration(p50)}")
print(f" p90 : {colour_duration(p90)}")
print(f" p95 : {colour_duration(p95)}")
print(f" p99 : {colour_duration(p99)}")
print(f" Std dev : {statistics.stdev(durations):,.0f}ms" if len(durations) > 1 else "")
# Duration buckets
buckets = {"<500ms": 0, "500ms-1s": 0, "1-3s": 0, "3-5s": 0, "5-10s": 0, "10-20s": 0, "20s+": 0}
for d in durations:
if d < 500: buckets["<500ms"] += 1
elif d < 1000: buckets["500ms-1s"] += 1
elif d < 3000: buckets["1-3s"] += 1
elif d < 5000: buckets["3-5s"] += 1
elif d < 10000: buckets["5-10s"] += 1
elif d < 20000: buckets["10-20s"] += 1
else: buckets["20s+"] += 1
print(f"\n {BOLD}Distribution:{RESET}")
max_bar = 40
max_count = max(buckets.values()) if buckets else 1
for label, count in buckets.items():
bar_len = int(count / max_count * max_bar) if max_count else 0
pct = count / len(durations) * 100
bar = "" * bar_len
clr = GREEN if "500" in label or "<" in label else (YELLOW if "1-3" in label or "3-5" in label else RED)
print(f" {label:>10s} {clr}{bar}{RESET} {count:>5,} ({pct:5.1f}%)")
# ── 3. Errors breakdown ─────────────────────────────────────────────────────
print(header("ERROR BREAKDOWN"))
if not errors:
print(f" {GREEN}No errors! 🎉{RESET}")
else:
error_codes = Counter()
for e in errors:
err_str = e.get("error", "unknown")
code = err_str.split(":")[0] if ":" in err_str else err_str
error_codes[code] += 1
for code, count in error_codes.most_common():
print(f" {RED}{code:<30s}{RESET} {count:>5,} ({count/len(entries)*100:.1f}%)")
# Errored URLs
errored_urls = Counter(normalise_url(e["url"]) for e in errors)
print(f"\n {BOLD}Top errored endpoints:{RESET}")
for url, count in errored_urls.most_common(10):
print(f" {count:>5,} {url}")
# ── 4. Slowest individual calls ─────────────────────────────────────────────
print(header("TOP 20 SLOWEST CALLS"))
slowest = sorted(entries, key=lambda e: e["durationMs"], reverse=True)[:20]
for i, e in enumerate(slowest, 1):
status = e.get("status") or f"{RED}ERR{RESET}"
err_tag = f" {RED}[{e['error'].split(':')[0]}]{RESET}" if e.get("error") else ""
print(f" {i:>2}. {colour_duration(e['durationMs']):>20s} {e['method']:>4s} {e['url'][:60]:<60s} {DIM}{status}{RESET}{err_tag}")
# ── 5. Per-endpoint stats ───────────────────────────────────────────────────
print(header("PER-ENDPOINT STATS (by route pattern)"))
by_route = defaultdict(list)
for e in entries:
route = normalise_url(e["url"])
by_route[route].append(e)
# Sort by total time spent descending (most impactful)
route_stats = []
for route, calls in by_route.items():
durs = [c["durationMs"] for c in calls]
errs = sum(1 for c in calls if c.get("error"))
sorted_d = sorted(durs)
route_stats.append({
"route": route,
"count": len(calls),
"errors": errs,
"total_ms": sum(durs),
"mean": statistics.mean(durs),
"p50": sorted_d[len(sorted_d) * 50 // 100],
"p95": sorted_d[len(sorted_d) * 95 // 100],
"max": max(durs),
})
route_stats.sort(key=lambda r: r["total_ms"], reverse=True)
print(f" {'Route':<55s} {'Count':>6s} {'Errs':>5s} {'Mean':>8s} {'p50':>8s} {'p95':>8s} {'Max':>8s} {'Total':>10s}")
print(f" {'' * 55} {'' * 6} {'' * 5} {'' * 8} {'' * 8} {'' * 8} {'' * 8} {'' * 10}")
for r in route_stats[:25]:
err_str = f"{RED}{r['errors']}{RESET}" if r['errors'] else f"{DIM}0{RESET}"
print(
f" {r['route']:<55s} {r['count']:>6,} {err_str:>14s} "
f"{r['mean']:>7,.0f}ms {r['p50']:>7,.0f}ms {r['p95']:>7,.0f}ms "
f"{r['max']:>7,.0f}ms {r['total_ms']/1000:>8,.1f}s"
)
# ── 6. HTTP method breakdown ────────────────────────────────────────────────
print(header("BY HTTP METHOD"))
by_method = defaultdict(list)
for e in entries:
by_method[e["method"]].append(e["durationMs"])
print(f" {'Method':<8s} {'Count':>7s} {'Mean':>9s} {'p95':>9s} {'Max':>9s}")
print(f" {'' * 8} {'' * 7} {'' * 9} {'' * 9} {'' * 9}")
for method in sorted(by_method.keys()):
durs = by_method[method]
sd = sorted(durs)
print(
f" {method:<8s} {len(durs):>7,} "
f"{statistics.mean(durs):>8,.0f}ms "
f"{sd[len(sd)*95//100]:>8,.0f}ms "
f"{max(durs):>8,.0f}ms"
)
# ── 7. Timeline (calls per minute) ──────────────────────────────────────────
if time_span.total_seconds() > 60:
print(header("TIMELINE (per-minute throughput & errors)"))
by_minute = defaultdict(lambda: {"count": 0, "errors": 0, "dur_sum": 0})
for e in entries:
ts = e["timestamp"][:16] # YYYY-MM-DDTHH:MM
by_minute[ts]["count"] += 1
by_minute[ts]["dur_sum"] += e["durationMs"]
if e.get("error"):
by_minute[ts]["errors"] += 1
for minute in sorted(by_minute.keys()):
m = by_minute[minute]
avg = m["dur_sum"] / m["count"] if m["count"] else 0
err_part = f" {RED}({m['errors']} errs){RESET}" if m["errors"] else ""
bar = "" * min(m["count"] // 5, 50)
avg_clr = colour_duration(avg)
print(f" {minute} {m['count']:>5,} reqs avg {avg_clr:>20s} {bar}{err_part}")
# ── 8. Concurrency hotspots ─────────────────────────────────────────────────
print(header("CONCURRENCY HOTSPOTS (calls starting within 100ms of each other)"))
ts_ms = [int(t.timestamp() * 1000) for t in timestamps]
bursts = []
i = 0
while i < len(ts_ms):
j = i
while j < len(ts_ms) - 1 and ts_ms[j + 1] - ts_ms[j] < 100:
j += 1
burst_size = j - i + 1
if burst_size >= 5:
burst_entries = entries[i:j + 1]
avg_dur = statistics.mean(e["durationMs"] for e in burst_entries)
bursts.append((burst_size, entries[i]["timestamp"], avg_dur, burst_entries))
i = j + 1
bursts.sort(key=lambda b: b[0], reverse=True)
if bursts:
print(f" Found {len(bursts)} burst(s) of ≥5 concurrent requests\n")
for size, ts, avg, _ in bursts[:10]:
print(f" {YELLOW}{size:>3} concurrent{RESET} at {ts} avg {colour_duration(avg)}")
else:
print(f" {GREEN}No major concurrency bursts detected.{RESET}")
# ── 9. Summary / recommendations ────────────────────────────────────────────
print(header("SUMMARY"))
err_rate = len(errors) / len(entries) * 100
slow_5s = sum(1 for d in durations if d >= 5000)
slow_pct = slow_5s / len(entries) * 100
if err_rate > 5:
print(f" {RED}⚠ Error rate is {err_rate:.1f}% — CW API is struggling{RESET}")
elif err_rate > 1:
print(f" {YELLOW}⚠ Error rate is {err_rate:.1f}% — some instability{RESET}")
else:
print(f" {GREEN}✓ Error rate is {err_rate:.1f}% — acceptable{RESET}")
if slow_pct > 10:
print(f" {RED}{slow_5s:,} calls ({slow_pct:.1f}%) took >5s — CW is slow or rate-limiting{RESET}")
elif slow_pct > 2:
print(f" {YELLOW}{slow_5s:,} calls ({slow_pct:.1f}%) took >5s{RESET}")
else:
print(f" {GREEN}✓ Only {slow_5s:,} calls ({slow_pct:.1f}%) over 5s{RESET}")
if bursts:
max_burst = max(b[0] for b in bursts)
print(f" {YELLOW}⚠ Max concurrency burst: {max_burst} simultaneous requests — consider lowering CONCURRENCY{RESET}")
total_time_s = sum(durations) / 1000
print(f"\n Total wall-clock time spent waiting on CW: {BOLD}{total_time_s:,.1f}s{RESET} ({total_time_s/60:,.1f} min)")
print()
+441
View File
@@ -0,0 +1,441 @@
#!/usr/bin/env python3
import argparse
import json
from collections import Counter, defaultdict
from dataclasses import dataclass
from datetime import datetime, timezone
from pathlib import Path
from typing import Any
def parse_iso(value: str | None) -> datetime | None:
if not value:
return None
normalized = value.replace("Z", "+00:00")
try:
return datetime.fromisoformat(normalized)
except ValueError:
return None
def first_non_empty(*values: Any) -> str:
for value in values:
if value is None:
continue
if isinstance(value, str) and value.strip() == "":
continue
return str(value)
return "unknown"
def top_lines(counter: Counter[str], limit: int) -> list[str]:
return [f"{k}: {v}" for k, v in counter.most_common(limit)]
def fmt_pct(part: int, total: int) -> str:
if total == 0:
return "0.0%"
return f"{(part / total) * 100:.1f}%"
def human_duration(start: datetime | None, end: datetime | None) -> str:
if start is None or end is None:
return "unknown"
delta = end - start
total_seconds = int(delta.total_seconds())
hours, remainder = divmod(total_seconds, 3600)
minutes, seconds = divmod(remainder, 60)
return f"{hours}h {minutes}m {seconds}s"
def truncate(value: str, max_len: int = 90) -> str:
if len(value) <= max_len:
return value
return value[: max_len - 1] + ""
def add_section(lines: list[str], title: str) -> None:
lines.append("")
lines.append(title)
lines.append("-" * len(title))
def supports_color(enabled: bool) -> bool:
return enabled
def paint(text: str, code: str, use_color: bool) -> str:
if not use_color:
return text
return f"\033[{code}m{text}\033[0m"
def good_bad_neutral(value: str, state: str, use_color: bool) -> str:
if state == "good":
return paint(value, "32", use_color)
if state == "bad":
return paint(value, "31", use_color)
return paint(value, "36", use_color)
def add_ranked_counter(
lines: list[str],
title: str,
counter: Counter[str],
top_n: int,
total: int,
truncate_labels: bool = False,
) -> None:
lines.append(f"{title}")
items = counter.most_common(top_n)
if not items:
lines.append(" (no data)")
return
for index, (key, count) in enumerate(items, start=1):
label = truncate(key) if truncate_labels else key
lines.append(f" {index:>2}. {label:<90} {count:>4} {fmt_pct(count, total):>6}")
def stream_row_summary(row: dict[str, Any], use_color: bool, max_path: int) -> str:
request = row.get("request") or {}
response = row.get("response") or {}
body_parsed = request.get("bodyParsed") or {}
entity_parsed = request.get("entityParsed") or {}
summary = request.get("summary") or {}
timestamp = parse_iso(row.get("timestamp"))
time_label = timestamp.astimezone(timezone.utc).strftime("%H:%M:%S") if timestamp else "--:--:--"
method = first_non_empty(request.get("method"))
path = first_non_empty(request.get("path"))
endpoint = path.split("?", 1)[0]
status_code = first_non_empty(response.get("status"))
event_type = first_non_empty(body_parsed.get("Type"), summary.get("type"))
action = first_non_empty(
body_parsed.get("Action"),
summary.get("action"),
request.get("query", {}).get("params", {}).get("action"),
)
item_id = first_non_empty(body_parsed.get("ID"), summary.get("id"), request.get("query", {}).get("inferredId"))
actor = first_non_empty(
request.get("query", {}).get("params", {}).get("memberId"),
summary.get("entityUpdatedBy"),
entity_parsed.get("UpdatedBy"),
)
entity_status = first_non_empty(entity_parsed.get("StatusName"), summary.get("entityStatus"))
endpoint_label = truncate(endpoint, max_path)
status_state = "good" if status_code.startswith("2") else "bad"
status_colored = good_bad_neutral(status_code, status_state, use_color)
event_colored = paint(f"{event_type}.{action}", "36", use_color)
endpoint_colored = paint(endpoint_label, "94", use_color)
return (
f"[{time_label}] {method:<4} {endpoint_colored:<20} "
f"{status_colored:>3} {event_colored:<22} "
f"id={item_id:<7} actor={truncate(actor, 16):<16} status={truncate(entity_status, 22)}"
)
def endpoint_stream_summary(log_path: Path, use_color: bool, max_path: int) -> str:
lines: list[str] = []
lines.append(paint("ENDPOINT STREAM (chronological)", "1;95", use_color))
lines.append(paint("────────────────────────────────────────────────────────────────────────────────────────────", "90", use_color))
count = 0
invalid = 0
with log_path.open("r", encoding="utf-8") as handle:
for raw_line in handle:
line = raw_line.strip()
if not line:
continue
try:
row = json.loads(line)
except json.JSONDecodeError:
invalid += 1
continue
lines.append(stream_row_summary(row, use_color=use_color, max_path=max_path))
count += 1
lines.append(paint("────────────────────────────────────────────────────────────────────────────────────────────", "90", use_color))
lines.append(
f"events={count} invalid={good_bad_neutral(str(invalid), 'good' if invalid == 0 else 'bad', use_color)}"
)
return "\n".join(lines)
@dataclass
class LogStats:
total_rows: int = 0
parsed_rows: int = 0
invalid_rows: int = 0
earliest: datetime | None = None
latest: datetime | None = None
methods: Counter[str] = None # type: ignore[assignment]
paths: Counter[str] = None # type: ignore[assignment]
endpoint_roots: Counter[str] = None # type: ignore[assignment]
response_statuses: Counter[str] = None # type: ignore[assignment]
event_types: Counter[str] = None # type: ignore[assignment]
actions: Counter[str] = None # type: ignore[assignment]
type_action_combo: Counter[str] = None # type: ignore[assignment]
company_ids: Counter[str] = None # type: ignore[assignment]
source_members: Counter[str] = None # type: ignore[assignment]
actor_members: Counter[str] = None # type: ignore[assignment]
entity_updated_by: Counter[str] = None # type: ignore[assignment]
requests_by_hour: Counter[str] = None # type: ignore[assignment]
requests_by_minute: Counter[str] = None # type: ignore[assignment]
endpoint_by_hour: dict[str, Counter[str]] = None # type: ignore[assignment]
def __post_init__(self) -> None:
self.methods = Counter()
self.paths = Counter()
self.endpoint_roots = Counter()
self.response_statuses = Counter()
self.event_types = Counter()
self.actions = Counter()
self.type_action_combo = Counter()
self.company_ids = Counter()
self.source_members = Counter()
self.actor_members = Counter()
self.entity_updated_by = Counter()
self.requests_by_hour = Counter()
self.requests_by_minute = Counter()
self.endpoint_by_hour = defaultdict(Counter)
def add_timestamp(self, timestamp: datetime | None) -> None:
if timestamp is None:
return
self.earliest = timestamp if self.earliest is None else min(self.earliest, timestamp)
self.latest = timestamp if self.latest is None else max(self.latest, timestamp)
hour_bucket = timestamp.astimezone(timezone.utc).strftime("%Y-%m-%d %H:00 UTC")
minute_bucket = timestamp.astimezone(timezone.utc).strftime("%Y-%m-%d %H:%M UTC")
self.requests_by_hour[hour_bucket] += 1
self.requests_by_minute[minute_bucket] += 1
def summarize(self, top_n: int, busiest_n: int, use_color: bool) -> str:
duration_line = human_duration(self.earliest, self.latest)
time_range_line = "unknown"
if self.earliest and self.latest:
time_range_line = f"{self.earliest.isoformat()}{self.latest.isoformat()}"
total_requests = self.parsed_rows
success_count = self.response_statuses.get("200", 0)
success_pct = fmt_pct(success_count, sum(self.response_statuses.values()))
invalid_state = "good" if self.invalid_rows == 0 else "bad"
top_endpoints = self.endpoint_roots.most_common(2)
top_users = self.actor_members.most_common(3)
top_minutes = self.requests_by_minute.most_common(busiest_n)
lines: list[str] = []
lines.append(paint("WEBHOOK SNAPSHOT", "1;95", use_color))
lines.append(paint("────────────────────────────────────────────────────────", "90", use_color))
lines.append(
" "
+ paint("Rows", "1;97", use_color)
+ f": {self.total_rows:<4} "
+ paint("Parsed", "1;97", use_color)
+ f": {self.parsed_rows:<4} "
+ paint("Invalid", "1;97", use_color)
+ f": {good_bad_neutral(str(self.invalid_rows), invalid_state, use_color)}"
)
lines.append(
" "
+ paint("Window", "1;97", use_color)
+ f": {duration_line:<12} "
+ paint("Success", "1;97", use_color)
+ f": {good_bad_neutral(success_pct, 'good' if success_count else 'neutral', use_color)}"
)
lines.append(" " + paint("UTC Range", "1;97", use_color) + f": {time_range_line}")
lines.append("")
lines.append(paint("Top Endpoints", "1;94", use_color))
if top_endpoints:
for endpoint, count in top_endpoints:
lines.append(f"{endpoint:<14} {count:>4} ({fmt_pct(count, total_requests)})")
if not top_endpoints:
lines.append(" • (no data)")
lines.append("")
lines.append(paint("Most Active Users (query memberId)", "1;94", use_color))
if top_users:
for user, count in top_users:
lines.append(f"{user:<18} {count:>4} ({fmt_pct(count, total_requests)})")
if not top_users:
lines.append(" • (no data)")
lines.append("")
lines.append(paint("Busiest Minutes", "1;94", use_color))
if top_minutes:
for minute, count in top_minutes:
lines.append(f"{minute:<22} {count:>3}")
if not top_minutes:
lines.append(" • (no data)")
lines.append("")
lines.append(paint("Request Mix", "1;94", use_color))
method_line = ", ".join([f"{k}:{v}" for k, v in self.methods.most_common(3)]) or "(no data)"
event_line = ", ".join([f"{k}:{v}" for k, v in self.event_types.most_common(3)]) or "(no data)"
action_line = ", ".join([f"{k}:{v}" for k, v in self.actions.most_common(3)]) or "(no data)"
lines.append(f" • Methods : {method_line}")
lines.append(f" • Types : {event_line}")
lines.append(f" • Actions : {action_line}")
lines.append("")
lines.append(paint("Status Codes", "1;94", use_color))
if self.response_statuses:
status_total = sum(self.response_statuses.values())
for status, count in self.response_statuses.most_common(5):
state = "good" if status.startswith("2") else "bad"
status_label = good_bad_neutral(status, state, use_color)
lines.append(f"{status_label}: {count} ({fmt_pct(count, status_total)})")
if not self.response_statuses:
lines.append(" • (no data)")
return "\n".join(lines)
def update_stats(stats: LogStats, row: dict[str, Any]) -> None:
timestamp = parse_iso(row.get("timestamp"))
stats.add_timestamp(timestamp)
request = row.get("request") or {}
response = row.get("response") or {}
body_parsed = request.get("bodyParsed") or {}
entity_parsed = request.get("entityParsed") or {}
method = first_non_empty(request.get("method"))
path = first_non_empty(request.get("path"))
endpoint_root = path.split("?", 1)[0]
status = first_non_empty(response.get("status"))
event_type = first_non_empty(
body_parsed.get("Type"),
request.get("summary", {}).get("type"),
)
action = first_non_empty(
body_parsed.get("Action"),
request.get("summary", {}).get("action"),
request.get("query", {}).get("params", {}).get("action"),
)
combo = f"{event_type}:{action}"
source_member = first_non_empty(
body_parsed.get("MemberId"),
request.get("summary", {}).get("memberId"),
)
actor_member = first_non_empty(
request.get("query", {}).get("params", {}).get("memberId"),
request.get("summary", {}).get("entityUpdatedBy"),
)
updated_by = first_non_empty(
entity_parsed.get("UpdatedBy"),
request.get("summary", {}).get("entityUpdatedBy"),
)
company_id = first_non_empty(body_parsed.get("CompanyId"), request.get("headers", {}).get("companyname"))
stats.methods[method] += 1
stats.paths[path] += 1
stats.endpoint_roots[endpoint_root] += 1
stats.response_statuses[status] += 1
stats.event_types[event_type] += 1
stats.actions[action] += 1
stats.type_action_combo[combo] += 1
stats.company_ids[company_id] += 1
stats.source_members[source_member] += 1
stats.actor_members[actor_member] += 1
stats.entity_updated_by[updated_by] += 1
if timestamp:
bucket = timestamp.astimezone(timezone.utc).strftime("%Y-%m-%d %H:00 UTC")
stats.endpoint_by_hour[endpoint_root][bucket] += 1
def analyze_file(log_path: Path) -> LogStats:
stats = LogStats()
with log_path.open("r", encoding="utf-8") as handle:
for raw_line in handle:
line = raw_line.strip()
if not line:
continue
stats.total_rows += 1
try:
row = json.loads(line)
except json.JSONDecodeError:
stats.invalid_rows += 1
continue
stats.parsed_rows += 1
update_stats(stats, row)
return stats
def main() -> None:
parser = argparse.ArgumentParser(
description="Analyze webhook JSONL logs by users, time, and request types."
)
parser.add_argument("log_file", help="Path to JSONL log file")
parser.add_argument("--top", type=int, default=10, help="Top N entries per section (default: 10)")
parser.add_argument(
"--busiest-minutes",
type=int,
default=5,
help="How many top minute buckets to show (default: 5)",
)
parser.add_argument(
"--no-color",
action="store_true",
help="Disable ANSI colors",
)
parser.add_argument(
"--endpoint-stream",
action="store_true",
help="Show chronological one-line summary per webhook, similar to live test webserver logs",
)
parser.add_argument(
"--max-path",
type=int,
default=18,
help="Max endpoint width in stream mode before truncation (default: 18)",
)
args = parser.parse_args()
log_path = Path(args.log_file)
if not log_path.exists() or not log_path.is_file():
raise SystemExit(f"Log file not found: {log_path}")
use_color = supports_color(not args.no_color)
if args.endpoint_stream:
print(endpoint_stream_summary(log_path, use_color=use_color, max_path=max(args.max_path, 10)))
return
stats = analyze_file(log_path)
print(
stats.summarize(
top_n=max(args.top, 1),
busiest_n=max(args.busiest_minutes, 1),
use_color=use_color,
)
)
if __name__ == "__main__":
main()
+900
View File
@@ -0,0 +1,900 @@
#!/usr/bin/env python3
"""
Generate a print-friendly PDF report from the latest test-webserver log file.
Usage:
python3 generate_log_report.py [optional_log_file_path]
If no path is given, the script finds the latest test-webserver-*.jsonl
file in ../cw-api-logs/.
"""
import json
import os
import sys
import glob
from datetime import datetime, timezone
from collections import Counter, defaultdict
from reportlab.lib import colors
from reportlab.lib.pagesizes import LETTER
from reportlab.lib.styles import getSampleStyleSheet, ParagraphStyle
from reportlab.lib.units import inch
from reportlab.lib.enums import TA_CENTER, TA_LEFT
from reportlab.platypus import (
SimpleDocTemplate,
Paragraph,
Spacer,
Table,
TableStyle,
PageBreak,
HRFlowable,
KeepTogether,
)
from reportlab.graphics.shapes import Drawing, String
from reportlab.graphics.charts.piecharts import Pie
from reportlab.graphics.charts.barcharts import VerticalBarChart
# ─── Print-friendly color palette ─────────────────────────────────────────────
# Minimal ink: white backgrounds, thin borders, dark text, subtle accents
HEADER_BG = colors.HexColor("#2c3e50") # Dark header (used sparingly)
ACCENT = colors.HexColor("#2980b9") # Muted blue
ACCENT_2 = colors.HexColor("#27ae60") # Muted green
ACCENT_3 = colors.HexColor("#8e44ad") # Muted purple
WHITE = colors.white
GRAY_50 = colors.HexColor("#fafafa")
GRAY_100 = colors.HexColor("#f5f5f5")
GRAY_200 = colors.HexColor("#e0e0e0")
GRAY_400 = colors.HexColor("#bdbdbd")
GRAY_600 = colors.HexColor("#757575")
GRAY_800 = colors.HexColor("#424242")
GRAY_900 = colors.HexColor("#212121")
# Pie/chart fills — muted, distinguishable in B&W too
PIE_COLORS = [
colors.HexColor("#5b9bd5"), # steel blue
colors.HexColor("#ed7d31"), # soft orange
colors.HexColor("#a5a5a5"), # gray
colors.HexColor("#ffc000"), # amber
colors.HexColor("#70ad47"), # olive green
colors.HexColor("#4472c4"), # darker blue
colors.HexColor("#c55a11"), # brown
colors.HexColor("#7030a0"), # purple
]
# ─── Helpers ──────────────────────────────────────────────────────────────────
def find_latest_log(base_dir):
pattern = os.path.join(base_dir, "test-webserver-*.jsonl")
files = sorted(glob.glob(pattern))
if not files:
raise FileNotFoundError(f"No test-webserver log files found in {base_dir}")
return files[-1]
def parse_log(path):
entries = []
with open(path, "r") as f:
for line in f:
line = line.strip()
if not line:
continue
try:
entries.append(json.loads(line))
except json.JSONDecodeError:
continue
return entries
def fmt_ts(iso_str):
try:
dt = datetime.fromisoformat(iso_str.replace("Z", "+00:00"))
return dt.strftime("%Y-%m-%d %H:%M:%S UTC")
except Exception:
return str(iso_str)
def duration_str(seconds):
if seconds < 60:
return f"{seconds:.1f}s"
minutes = seconds / 60
if minutes < 60:
return f"{minutes:.1f}m"
hours = minutes / 60
return f"{hours:.1f}h"
def truncate(s, max_len=50):
s = str(s)
return s if len(s) <= max_len else s[: max_len - 3] + "..."
def resolve_actor(entry):
"""
Derive the actor exactly like testWebserver.ts does:
entityUpdatedBy ?? query.params.memberId ?? summary.memberId ?? "-"
The summary is already stored in request.summary in the log.
"""
req = entry.get("request", {})
summary = req.get("summary") or {}
query = req.get("query") or {}
params = query.get("params") or {}
return str(
summary.get("entityUpdatedBy")
or params.get("memberId")
or summary.get("memberId")
or "-"
)
# ─── Analysis ─────────────────────────────────────────────────────────────────
def analyze(entries):
stats = {}
timestamps = []
for e in entries:
ts = e.get("timestamp")
if ts:
try:
timestamps.append(datetime.fromisoformat(ts.replace("Z", "+00:00")))
except Exception:
pass
timestamps.sort()
stats["total_entries"] = len(entries)
stats["first_ts"] = timestamps[0] if timestamps else None
stats["last_ts"] = timestamps[-1] if timestamps else None
stats["duration_seconds"] = (
(timestamps[-1] - timestamps[0]).total_seconds() if len(timestamps) >= 2 else 0
)
# Global counters
methods = Counter()
paths = Counter()
statuses = Counter()
actions = Counter()
types = Counter()
actors = Counter()
companies = Counter()
entity_ids = set()
stages = Counter()
ratings = Counter()
hourly_buckets = Counter()
minute_buckets = Counter()
for e in entries:
req = e.get("request", {})
resp = e.get("response", {})
bp = req.get("bodyParsed") or {}
entity = req.get("entityParsed") or bp.get("Entity") or {}
methods[req.get("method", "?")] += 1
raw_path = req.get("path", "?").split("?")[0]
paths[raw_path] += 1
statuses[resp.get("status", "?")] += 1
actions[bp.get("Action", "?")] += 1
types[bp.get("Type", "?")] += 1
actor = resolve_actor(e)
actors[actor] += 1
if isinstance(entity, dict):
cn = entity.get("CompanyName")
if cn:
companies[cn] += 1
eid = entity.get("Id")
if eid is not None:
entity_ids.add(eid)
stage = entity.get("StageName")
if stage:
stages[stage] += 1
rating = entity.get("Rating")
if rating:
ratings[rating] += 1
ts_str = e.get("timestamp")
if ts_str:
try:
dt = datetime.fromisoformat(ts_str.replace("Z", "+00:00"))
hourly_buckets[dt.strftime("%H:00")] += 1
minute_buckets[dt.strftime("%H:%M")] += 1
except Exception:
pass
# ── Per-actor deep stats ──
actor_details = defaultdict(lambda: {
"count": 0,
"actions": Counter(),
"types": Counter(),
"companies": Counter(),
"entity_ids": set(),
"stages": Counter(),
"ratings": Counter(),
"timestamps": [],
"statuses": Counter(),
"paths": Counter(),
"member_ids": Counter(),
"sales_reps": Counter(),
"total_estimated": 0.0,
})
for e in entries:
req = e.get("request", {})
resp = e.get("response", {})
bp = req.get("bodyParsed") or {}
entity = req.get("entityParsed") or bp.get("Entity") or {}
summary = req.get("summary") or {}
actor = resolve_actor(e)
ad = actor_details[actor]
ad["count"] += 1
ad["actions"][bp.get("Action", "?")] += 1
ad["types"][bp.get("Type", "?")] += 1
ad["statuses"][resp.get("status", "?")] += 1
raw_path = req.get("path", "?").split("?")[0]
ad["paths"][raw_path] += 1
# Track which MemberIds triggered callbacks for this actor
mid = bp.get("MemberId")
if mid:
ad["member_ids"][mid] += 1
ts_str = e.get("timestamp")
if ts_str:
try:
ad["timestamps"].append(datetime.fromisoformat(ts_str.replace("Z", "+00:00")))
except Exception:
pass
if isinstance(entity, dict):
cn = entity.get("CompanyName")
if cn:
ad["companies"][cn] += 1
eid = entity.get("Id")
if eid is not None:
ad["entity_ids"].add(eid)
stage = entity.get("StageName")
if stage:
ad["stages"][stage] += 1
rating = entity.get("Rating")
if rating:
ad["ratings"][rating] += 1
et = entity.get("EstimatedTotal")
if et is not None:
ad["total_estimated"] += float(et)
pr = entity.get("PrimarySalesRep")
if pr:
ad["sales_reps"][pr] += 1
# Compute per-actor derived stats
for aid, ad in actor_details.items():
ad["timestamps"].sort()
if len(ad["timestamps"]) >= 2:
dur = (ad["timestamps"][-1] - ad["timestamps"][0]).total_seconds()
ad["duration_seconds"] = dur
ad["events_per_minute"] = ad["count"] / (dur / 60) if dur > 0 else ad["count"]
else:
ad["duration_seconds"] = 0
ad["events_per_minute"] = ad["count"]
ad["first_ts"] = ad["timestamps"][0] if ad["timestamps"] else None
ad["last_ts"] = ad["timestamps"][-1] if ad["timestamps"] else None
stats["actor_details"] = dict(actor_details)
stats["methods"] = methods
stats["paths"] = paths
stats["statuses"] = statuses
stats["actions"] = actions
stats["types"] = types
stats["actors"] = actors
stats["companies"] = companies
stats["entity_ids"] = entity_ids
stats["stages"] = stages
stats["ratings"] = ratings
stats["hourly_buckets"] = hourly_buckets
stats["minute_buckets"] = minute_buckets
if stats["duration_seconds"] > 0:
stats["events_per_minute"] = len(entries) / (stats["duration_seconds"] / 60)
else:
stats["events_per_minute"] = len(entries)
return stats
# ─── PDF building ─────────────────────────────────────────────────────────────
def build_styles():
ss = getSampleStyleSheet()
ss.add(ParagraphStyle(
"ReportTitle", parent=ss["Title"], fontSize=24, textColor=WHITE,
spaceAfter=4, fontName="Helvetica-Bold", alignment=TA_CENTER,
))
ss.add(ParagraphStyle(
"ReportSubtitle", parent=ss["Normal"], fontSize=11, textColor=GRAY_400,
spaceAfter=2, fontName="Helvetica", alignment=TA_CENTER,
))
ss.add(ParagraphStyle(
"SectionHeader", parent=ss["Heading1"], fontSize=16, textColor=GRAY_900,
spaceBefore=14, spaceAfter=6, fontName="Helvetica-Bold",
))
ss.add(ParagraphStyle(
"SubHeader", parent=ss["Heading2"], fontSize=12, textColor=GRAY_800,
spaceBefore=10, spaceAfter=4, fontName="Helvetica-Bold",
))
ss.add(ParagraphStyle(
"BodyText2", parent=ss["Normal"], fontSize=9, textColor=GRAY_800,
spaceAfter=3, fontName="Helvetica", leading=13,
))
ss.add(ParagraphStyle(
"SmallGray", parent=ss["Normal"], fontSize=8, textColor=GRAY_600,
spaceAfter=2, fontName="Helvetica",
))
ss.add(ParagraphStyle(
"KPIValue", parent=ss["Normal"], fontSize=20, textColor=GRAY_900,
fontName="Helvetica-Bold", alignment=TA_CENTER, leading=24,
))
ss.add(ParagraphStyle(
"KPILabel", parent=ss["Normal"], fontSize=8, textColor=GRAY_600,
fontName="Helvetica", alignment=TA_CENTER, spaceAfter=2,
))
ss.add(ParagraphStyle(
"BannerText", parent=ss["Normal"], fontSize=9, textColor=WHITE,
fontName="Helvetica-Bold", spaceAfter=1,
))
return ss
def make_header_banner(ss, log_path, stats):
elements = []
fname = os.path.basename(log_path)
banner_data = [[
Paragraph("Webhook Log Report", ss["ReportTitle"]),
], [
Paragraph(fname, ss["ReportSubtitle"]),
], [
Paragraph(
f"Generated {datetime.now(timezone.utc).strftime('%Y-%m-%d %H:%M UTC')}",
ss["ReportSubtitle"],
),
]]
banner = Table(banner_data, colWidths=[7.0 * inch])
banner.setStyle(TableStyle([
("BACKGROUND", (0, 0), (-1, -1), HEADER_BG),
("ALIGN", (0, 0), (-1, -1), "CENTER"),
("TOPPADDING", (0, 0), (0, 0), 20),
("BOTTOMPADDING", (0, -1), (-1, -1), 16),
("LEFTPADDING", (0, 0), (-1, -1), 20),
("RIGHTPADDING", (0, 0), (-1, -1), 20),
]))
elements.append(banner)
elements.append(Spacer(1, 14))
return elements
def make_kpi_card(label, value):
ss = build_styles()
card_data = [[
Paragraph(str(value), ss["KPIValue"]),
], [
Paragraph(label, ss["KPILabel"]),
]]
card = Table(card_data, colWidths=[1.6 * inch], rowHeights=[28, 16])
card.setStyle(TableStyle([
("BACKGROUND", (0, 0), (-1, -1), GRAY_100),
("ALIGN", (0, 0), (-1, -1), "CENTER"),
("VALIGN", (0, 0), (-1, -1), "MIDDLE"),
("TOPPADDING", (0, 0), (-1, -1), 6),
("BOTTOMPADDING", (0, 0), (-1, -1), 4),
("BOX", (0, 0), (-1, -1), 0.5, GRAY_200),
]))
return card
def make_kpi_row(cards_data):
cards = [make_kpi_card(label, value) for label, value in cards_data]
row = Table([cards], colWidths=[1.75 * inch] * len(cards))
row.setStyle(TableStyle([
("ALIGN", (0, 0), (-1, -1), "CENTER"),
("VALIGN", (0, 0), (-1, -1), "TOP"),
]))
return row
def make_table(title, counter, ss, max_rows=15):
"""Generic table from a Counter — light styling for print."""
elements = []
elements.append(Paragraph(title, ss["SubHeader"]))
items = counter.most_common(max_rows)
if not items:
elements.append(Paragraph("<i>No data</i>", ss["BodyText2"]))
return elements
total = sum(counter.values())
header = ["Item", "Count", "%"]
rows = [header]
for name, count in items:
pct = (count / total * 100) if total else 0
rows.append([truncate(str(name), 45), f"{count:,}", f"{pct:.1f}%"])
t = Table(rows, colWidths=[3.6 * inch, 1.0 * inch, 0.8 * inch])
t.setStyle(TableStyle([
("BACKGROUND", (0, 0), (-1, 0), GRAY_800),
("TEXTCOLOR", (0, 0), (-1, 0), WHITE),
("FONTNAME", (0, 0), (-1, 0), "Helvetica-Bold"),
("FONTSIZE", (0, 0), (-1, 0), 9),
("FONTSIZE", (0, 1), (-1, -1), 9),
("FONTNAME", (0, 1), (-1, -1), "Helvetica"),
("BOTTOMPADDING", (0, 0), (-1, 0), 6),
("TOPPADDING", (0, 0), (-1, 0), 6),
("GRID", (0, 0), (-1, -1), 0.4, GRAY_200),
("ROWBACKGROUNDS", (0, 1), (-1, -1), [WHITE, GRAY_50]),
("ALIGN", (1, 0), (2, -1), "CENTER"),
("VALIGN", (0, 0), (-1, -1), "MIDDLE"),
("LEFTPADDING", (0, 0), (-1, -1), 8),
("RIGHTPADDING", (0, 0), (-1, -1), 8),
("TOPPADDING", (0, 1), (-1, -1), 3),
("BOTTOMPADDING", (0, 1), (-1, -1), 3),
]))
elements.append(t)
return elements
def make_pie_chart(title, counter, width=280, height=190):
items = counter.most_common(8)
if not items:
return Spacer(1, 1)
d = Drawing(width, height)
d.add(String(width / 2, height - 12, title,
fontSize=10, fontName="Helvetica-Bold",
fillColor=GRAY_900, textAnchor="middle"))
pie = Pie()
pie.x = 50
pie.y = 10
pie.width = 110
pie.height = 110
pie.data = [v for _, v in items]
pie.labels = [truncate(str(k), 18) for k, _ in items]
pie.sideLabels = True
pie.slices.strokeWidth = 0.5
pie.slices.strokeColor = WHITE
for i in range(len(items)):
pie.slices[i].fillColor = PIE_COLORS[i % len(PIE_COLORS)]
pie.slices[i].fontName = "Helvetica"
pie.slices[i].fontSize = 7
pie.slices[i].labelRadius = 1.35
d.add(pie)
return d
def make_timeline_chart(minute_buckets, width=500, height=150):
if not minute_buckets:
return Spacer(1, 1)
sorted_keys = sorted(minute_buckets.keys())
if len(sorted_keys) > 40:
step = max(1, len(sorted_keys) // 40)
sampled_keys = sorted_keys[::step]
else:
sampled_keys = sorted_keys
values = [minute_buckets[k] for k in sampled_keys]
d = Drawing(width, height)
d.add(String(width / 2, height - 10, "Event Timeline (by minute)",
fontSize=10, fontName="Helvetica-Bold",
fillColor=GRAY_900, textAnchor="middle"))
chart = VerticalBarChart()
chart.x = 50
chart.y = 25
chart.width = width - 80
chart.height = height - 50
chart.data = [values]
chart.categoryAxis.categoryNames = sampled_keys
chart.categoryAxis.labels.angle = 45
chart.categoryAxis.labels.fontSize = 6
chart.categoryAxis.labels.fontName = "Helvetica"
chart.categoryAxis.labels.dy = -5
chart.valueAxis.labels.fontSize = 7
chart.valueAxis.labels.fontName = "Helvetica"
chart.valueAxis.valueMin = 0
chart.bars[0].fillColor = GRAY_600
chart.bars[0].strokeColor = None
chart.barWidth = max(2, int((width - 100) / len(values) * 0.7))
d.add(chart)
return d
def build_actor_activity_section(stats, ss):
"""Per-actor deep-dive. Actor = entityUpdatedBy ?? query.memberId ?? summary.memberId."""
elements = []
elements.append(PageBreak())
elements.append(Paragraph("Actor Activity Deep Dive", ss["SectionHeader"]))
elements.append(HRFlowable(width="100%", thickness=1, color=GRAY_400, spaceAfter=4))
elements.append(Paragraph(
'The <b>actor</b> is resolved as: <i>entityUpdatedBy → query.memberId → summary.memberId</i>. '
'This is the person or system that caused the change in ConnectWise.',
ss["SmallGray"],
))
elements.append(Spacer(1, 10))
actor_details = stats.get("actor_details", {})
if not actor_details:
elements.append(Paragraph("<i>No actor data available.</i>", ss["BodyText2"]))
return elements
sorted_actors = sorted(actor_details.items(), key=lambda x: -x[1]["count"])
# Actor distribution pie chart
actor_counter = Counter({aid: ad["count"] for aid, ad in sorted_actors})
elements.append(make_pie_chart("Events by Actor", actor_counter, width=350, height=210))
elements.append(Spacer(1, 10))
for idx, (aid, ad) in enumerate(sorted_actors):
# Actor header — slim dark bar
banner_data = [[
Paragraph(
f'<font size="12"><b>{aid}</b></font>'
f'&nbsp;&nbsp;&nbsp;'
f'<font size="9" color="#cccccc">{ad["count"]:,} events</font>',
ss["BannerText"],
),
]]
banner = Table(banner_data, colWidths=[7.0 * inch])
banner.setStyle(TableStyle([
("BACKGROUND", (0, 0), (-1, -1), HEADER_BG),
("TOPPADDING", (0, 0), (-1, -1), 7),
("BOTTOMPADDING", (0, 0), (-1, -1), 7),
("LEFTPADDING", (0, 0), (-1, -1), 12),
]))
elements.append(banner)
# KPI row
kpi = make_kpi_row([
("Events", f"{ad['count']:,}"),
("Entities", f"{len(ad['entity_ids']):,}"),
("Companies", f"{len(ad['companies']):,}"),
("Evts/Min", f"{ad['events_per_minute']:.1f}"),
])
elements.append(kpi)
elements.append(Spacer(1, 4))
# Info grid
first_str = ad["first_ts"].strftime("%Y-%m-%d %H:%M:%S") if ad["first_ts"] else ""
last_str = ad["last_ts"].strftime("%Y-%m-%d %H:%M:%S") if ad["last_ts"] else ""
dur = duration_str(ad["duration_seconds"])
est = ad["total_estimated"]
mid_str = ", ".join(f"{k} ({v})" for k, v in ad["member_ids"].most_common(5)) if ad["member_ids"] else ""
sr_str = ", ".join(f"{k} ({v})" for k, v in ad["sales_reps"].most_common(5)) if ad["sales_reps"] else ""
info_rows = [
[
Paragraph('<font color="#757575">First Event</font>', ss["BodyText2"]),
Paragraph(f'<b>{first_str}</b>', ss["BodyText2"]),
Paragraph('<font color="#757575">Last Event</font>', ss["BodyText2"]),
Paragraph(f'<b>{last_str}</b>', ss["BodyText2"]),
],
[
Paragraph('<font color="#757575">Active Duration</font>', ss["BodyText2"]),
Paragraph(f'<b>{dur}</b>', ss["BodyText2"]),
Paragraph('<font color="#757575">Total Est. Value</font>', ss["BodyText2"]),
Paragraph(f'<b>${est:,.2f}</b>', ss["BodyText2"]),
],
[
Paragraph('<font color="#757575">Callback Members</font>', ss["BodyText2"]),
Paragraph(f'{truncate(mid_str, 40)}', ss["BodyText2"]),
Paragraph('<font color="#757575">Sales Reps</font>', ss["BodyText2"]),
Paragraph(f'{truncate(sr_str, 40)}', ss["BodyText2"]),
],
]
info_table = Table(info_rows, colWidths=[1.3 * inch, 2.1 * inch, 1.3 * inch, 2.1 * inch])
info_table.setStyle(TableStyle([
("BACKGROUND", (0, 0), (-1, -1), GRAY_50),
("TOPPADDING", (0, 0), (-1, -1), 4),
("BOTTOMPADDING", (0, 0), (-1, -1), 4),
("LEFTPADDING", (0, 0), (-1, -1), 8),
("GRID", (0, 0), (-1, -1), 0.3, GRAY_200),
]))
elements.append(info_table)
elements.append(Spacer(1, 6))
# Breakdown tables
if ad["types"]:
elements.extend(make_table(f"{aid} — Entity Types", ad["types"], ss, max_rows=8))
elements.append(Spacer(1, 6))
if ad["companies"]:
elements.extend(make_table(f"{aid} — Companies", ad["companies"], ss, max_rows=10))
elements.append(Spacer(1, 6))
if ad["stages"]:
elements.extend(make_table(f"{aid} — Stages", ad["stages"], ss, max_rows=8))
elements.append(Spacer(1, 6))
if ad["ratings"]:
elements.extend(make_table(f"{aid} — Ratings", ad["ratings"], ss, max_rows=8))
elements.append(Spacer(1, 6))
# Entity IDs
if ad["entity_ids"]:
id_list = sorted(ad["entity_ids"])
id_str = ", ".join(str(i) for i in id_list[:30])
if len(id_list) > 30:
id_str += f" ... (+{len(id_list) - 30} more)"
elements.append(Paragraph(f"{aid} — Entity IDs Touched", ss["SubHeader"]))
elements.append(Paragraph(f'<font size="8">{id_str}</font>', ss["BodyText2"]))
elements.append(Spacer(1, 6))
# Divider
if idx < len(sorted_actors) - 1:
elements.append(Spacer(1, 4))
elements.append(HRFlowable(width="100%", thickness=0.5, color=GRAY_200, spaceAfter=4))
elements.append(Spacer(1, 4))
return elements
def build_summary_log_table(entries, ss, max_rows=30):
elements = []
elements.append(PageBreak())
elements.append(Paragraph("Event Summary", ss["SectionHeader"]))
elements.append(HRFlowable(width="100%", thickness=1, color=GRAY_400, spaceAfter=6))
elements.append(Paragraph(
f"Aggregated view of {len(entries):,} webhook events — grouped by entity.",
ss["SmallGray"],
))
elements.append(Spacer(1, 8))
entity_groups = defaultdict(lambda: {
"count": 0, "name": "", "company": "",
"actions": Counter(), "actors": set(),
"est_total": None,
})
for e in entries:
req = e.get("request", {})
bp = req.get("bodyParsed") or {}
entity = req.get("entityParsed") or bp.get("Entity") or {}
if not isinstance(entity, dict):
continue
eid = entity.get("Id")
if eid is None:
continue
eg = entity_groups[eid]
eg["count"] += 1
eg["name"] = entity.get("OpportunityName") or entity.get("CompanyName") or eg["name"]
eg["company"] = entity.get("CompanyName") or eg["company"]
eg["actions"][bp.get("Action", "?")] += 1
actor = resolve_actor(e)
eg["actors"].add(actor)
et = entity.get("EstimatedTotal")
if et is not None:
eg["est_total"] = et
sorted_entities = sorted(entity_groups.items(), key=lambda x: -x[1]["count"])
header = ["ID", "Entity Name", "Company", "Events", "Actions", "Actors", "Est. Total"]
rows = [header]
for eid, eg in sorted_entities[:max_rows]:
actions_str = ", ".join(f"{a}({c})" for a, c in eg["actions"].most_common(3))
actors_str = ", ".join(sorted(eg["actors"]))
total_str = f"${eg['est_total']:,.2f}" if eg["est_total"] is not None else ""
rows.append([
str(eid),
truncate(eg["name"], 28),
truncate(eg["company"], 18),
f"{eg['count']:,}",
truncate(actions_str, 24),
truncate(actors_str, 18),
total_str,
])
t = Table(rows, colWidths=[0.45 * inch, 1.7 * inch, 1.1 * inch, 0.55 * inch, 1.2 * inch, 1.0 * inch, 0.8 * inch])
t.setStyle(TableStyle([
("BACKGROUND", (0, 0), (-1, 0), GRAY_800),
("TEXTCOLOR", (0, 0), (-1, 0), WHITE),
("FONTNAME", (0, 0), (-1, 0), "Helvetica-Bold"),
("FONTSIZE", (0, 0), (-1, 0), 8),
("FONTSIZE", (0, 1), (-1, -1), 8),
("FONTNAME", (0, 1), (-1, -1), "Helvetica"),
("GRID", (0, 0), (-1, -1), 0.3, GRAY_200),
("ROWBACKGROUNDS", (0, 1), (-1, -1), [WHITE, GRAY_50]),
("ALIGN", (0, 0), (0, -1), "CENTER"),
("ALIGN", (3, 0), (3, -1), "CENTER"),
("VALIGN", (0, 0), (-1, -1), "MIDDLE"),
("LEFTPADDING", (0, 0), (-1, -1), 5),
("RIGHTPADDING", (0, 0), (-1, -1), 5),
("TOPPADDING", (0, 1), (-1, -1), 2),
("BOTTOMPADDING", (0, 1), (-1, -1), 2),
]))
elements.append(t)
if len(sorted_entities) > max_rows:
elements.append(Spacer(1, 4))
elements.append(Paragraph(
f'Showing top {max_rows} of {len(sorted_entities)} entities.',
ss["SmallGray"],
))
return elements
def add_page_number(canvas, doc):
canvas.saveState()
canvas.setFillColor(GRAY_800)
canvas.rect(0, 0, LETTER[0], 22, fill=1, stroke=0)
canvas.setFillColor(WHITE)
canvas.setFont("Helvetica", 7)
canvas.drawCentredString(LETTER[0] / 2, 8, f"Page {doc.page}")
canvas.setFillColor(GRAY_400)
canvas.setFont("Helvetica", 7)
canvas.drawString(30, 8, "Optima API · Webhook Log Report")
canvas.drawRightString(LETTER[0] - 30, 8, datetime.now(timezone.utc).strftime("%Y-%m-%d"))
canvas.restoreState()
# ─── Main ─────────────────────────────────────────────────────────────────────
def main():
script_dir = os.path.dirname(os.path.abspath(__file__))
log_dir = os.path.join(script_dir, "..", "cw-api-logs")
if len(sys.argv) > 1:
log_path = sys.argv[1]
else:
log_path = find_latest_log(log_dir)
print(f"📄 Reading log: {log_path}")
entries = parse_log(log_path)
print(f"{len(entries)} entries parsed")
stats = analyze(entries)
ss = build_styles()
log_basename = os.path.splitext(os.path.basename(log_path))[0]
out_path = os.path.join(script_dir, "..", "cw-api-logs", f"{log_basename}-report.pdf")
doc = SimpleDocTemplate(
out_path,
pagesize=LETTER,
leftMargin=0.6 * inch,
rightMargin=0.6 * inch,
topMargin=0.5 * inch,
bottomMargin=0.5 * inch,
)
elements = []
# ── Title Banner ──
elements.extend(make_header_banner(ss, log_path, stats))
# ── Overview ──
elements.append(Paragraph("Overview", ss["SectionHeader"]))
elements.append(HRFlowable(width="100%", thickness=1, color=GRAY_400, spaceAfter=10))
elements.append(make_kpi_row([
("Total Events", f"{stats['total_entries']:,}"),
("Unique Entities", f"{len(stats['entity_ids']):,}"),
("Companies", f"{len(stats['companies']):,}"),
("Duration", duration_str(stats["duration_seconds"])),
]))
elements.append(Spacer(1, 8))
elements.append(make_kpi_row([
("Events / Min", f"{stats['events_per_minute']:.1f}"),
("HTTP Methods", f"{len(stats['methods']):,}"),
("Action Types", f"{len(stats['actions']):,}"),
("Actors", f"{len(stats['actors']):,}"),
]))
elements.append(Spacer(1, 12))
# Time range
if stats["first_ts"] and stats["last_ts"]:
info = [
[
Paragraph('<font color="#757575">First Event</font>', ss["BodyText2"]),
Paragraph(f'<b>{stats["first_ts"].strftime("%Y-%m-%d %H:%M:%S UTC")}</b>', ss["BodyText2"]),
Paragraph('<font color="#757575">Last Event</font>', ss["BodyText2"]),
Paragraph(f'<b>{stats["last_ts"].strftime("%Y-%m-%d %H:%M:%S UTC")}</b>', ss["BodyText2"]),
]
]
ti = Table(info, colWidths=[1.2 * inch, 2.4 * inch, 1.2 * inch, 2.4 * inch])
ti.setStyle(TableStyle([
("BACKGROUND", (0, 0), (-1, -1), GRAY_50),
("TOPPADDING", (0, 0), (-1, -1), 5),
("BOTTOMPADDING", (0, 0), (-1, -1), 5),
("LEFTPADDING", (0, 0), (-1, -1), 8),
("BOX", (0, 0), (-1, -1), 0.4, GRAY_200),
]))
elements.append(ti)
elements.append(Spacer(1, 14))
# ── Charts ──
elements.append(Paragraph("Visual Breakdown", ss["SectionHeader"]))
elements.append(HRFlowable(width="100%", thickness=1, color=GRAY_400, spaceAfter=10))
elements.append(make_timeline_chart(stats["minute_buckets"]))
elements.append(Spacer(1, 12))
pie_row = [[
make_pie_chart("By Action", stats["actions"]),
make_pie_chart("By Type", stats["types"]),
]]
pt = Table(pie_row, colWidths=[3.5 * inch, 3.5 * inch])
pt.setStyle(TableStyle([
("ALIGN", (0, 0), (-1, -1), "CENTER"),
("VALIGN", (0, 0), (-1, -1), "TOP"),
]))
elements.append(pt)
elements.append(Spacer(1, 6))
if len(stats["stages"]) > 1 or len(stats["ratings"]) > 1:
pie_row2 = [[
make_pie_chart("By Stage", stats["stages"]),
make_pie_chart("By Rating", stats["ratings"]),
]]
pt2 = Table(pie_row2, colWidths=[3.5 * inch, 3.5 * inch])
pt2.setStyle(TableStyle([
("ALIGN", (0, 0), (-1, -1), "CENTER"),
("VALIGN", (0, 0), (-1, -1), "TOP"),
]))
elements.append(pt2)
# Actor pie chart
elements.append(Spacer(1, 6))
elements.append(make_pie_chart("By Actor", stats["actors"], width=350, height=210))
# ── General Information ──
elements.append(PageBreak())
elements.append(Paragraph("General Information", ss["SectionHeader"]))
elements.append(HRFlowable(width="100%", thickness=1, color=GRAY_400, spaceAfter=10))
elements.extend(make_table("Response Status Codes", stats["statuses"], ss))
elements.append(Spacer(1, 10))
elements.extend(make_table("HTTP Methods", stats["methods"], ss))
elements.append(Spacer(1, 10))
elements.extend(make_table("Webhook Actions", stats["actions"], ss))
elements.append(Spacer(1, 10))
elements.extend(make_table("Entity Types", stats["types"], ss))
elements.append(Spacer(1, 10))
elements.extend(make_table("Request Paths", stats["paths"], ss))
elements.append(Spacer(1, 10))
elements.extend(make_table("Actors", stats["actors"], ss))
elements.append(Spacer(1, 10))
if stats["companies"]:
elements.extend(make_table("Companies", stats["companies"], ss))
elements.append(Spacer(1, 10))
if stats["stages"]:
elements.extend(make_table("Opportunity Stages", stats["stages"], ss))
elements.append(Spacer(1, 10))
if stats["ratings"]:
elements.extend(make_table("Opportunity Ratings", stats["ratings"], ss))
elements.append(Spacer(1, 10))
elements.extend(make_table("Hourly Distribution", stats["hourly_buckets"], ss))
# ── Actor Deep Dive ──
elements.extend(build_actor_activity_section(stats, ss))
# ── Entity Summary ──
elements.extend(build_summary_log_table(entries, ss, max_rows=30))
# Build
doc.build(elements, onFirstPage=add_page_number, onLaterPages=add_page_number)
print(f"✅ Report generated: {out_path}")
print(f" File size: {os.path.getsize(out_path) / 1024:.1f} KB")
if __name__ == "__main__":
main()