#!/usr/bin/env bash
set -euo pipefail
SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
ROOT_DIR="$(cd "$SCRIPT_DIR/.." && pwd)"
OUT_FILE="${1:-$ROOT_DIR/docs/code-stats-report.html}"
TMP_DIR="$(mktemp -d)"
cleanup() {
rm -rf "$TMP_DIR"
}
trap cleanup EXIT
cd "$ROOT_DIR"
if ! git rev-parse --is-inside-work-tree >/dev/null 2>&1; then
echo "Error: this script must run inside a git repository."
exit 1
fi
# 1) Snapshot LOC from tracked files.
while IFS= read -r -d '' file; do
if [ -f "$file" ]; then
wc -l "$file"
fi
done < <(git ls-files -z) > "$TMP_DIR/wc_all.txt"
awk -v out_by_ext="$TMP_DIR/loc_by_ext.tsv" -v out_totals="$TMP_DIR/loc_totals.tsv" '
{
lines = $1
$1 = ""
sub(/^ +/, "")
file = $0
n = split(file, parts, "/")
base = parts[n]
ext = base
if (index(base, ".") > 0) {
sub(/.*\./, "", ext)
} else {
ext = "[noext]"
}
ext_lines[ext] += lines
ext_files[ext] += 1
files += 1
lines_all += lines
}
END {
for (e in ext_lines) {
printf "%s\t%d\t%d\n", e, ext_files[e], ext_lines[e] > out_by_ext
}
source_lines = 0
source_files = 0
doc_lines = 0
doc_files = 0
cfg_lines = 0
cfg_files = 0
for (e in ext_lines) {
if (e ~ /^(ts|tsx|js|jsx|mjs|cjs|py|css|scss|html|sh)$/) {
source_lines += ext_lines[e]
source_files += ext_files[e]
}
if (e == "md") {
doc_lines += ext_lines[e]
doc_files += ext_files[e]
}
if (e ~ /^(json|json5|yaml|yml|xsd)$/) {
cfg_lines += ext_lines[e]
cfg_files += ext_files[e]
}
}
printf "files\t%d\nlines\t%d\nsource_files\t%d\nsource_lines\t%d\ndoc_files\t%d\ndoc_lines\t%d\nconfig_files\t%d\nconfig_lines\t%d\n", files, lines_all, source_files, source_lines, doc_files, doc_lines, cfg_files, cfg_lines > out_totals
}
' "$TMP_DIR/wc_all.txt"
# 2) Contribution by author (email-normalized).
git log --all --no-merges --numstat --format='@@@%aN|%aE' | awk -v out="$TMP_DIR/author_by_email.tsv" '
BEGIN { FS = "\t" }
/^@@@/ {
split(substr($0, 4), h, /\|/)
name = h[1]
email = h[2]
id = email
if (!(id in display)) {
display[id] = name " <" email ">"
}
commits[id] += 1
next
}
NF == 3 && $1 ~ /^[0-9]+$/ && $2 ~ /^[0-9]+$/ {
adds[id] += $1
dels[id] += $2
}
END {
for (k in commits) {
printf "%s\t%d\t%d\t%d\t%d\n", display[k], commits[k], adds[k] + 0, dels[k] + 0, (adds[k] - dels[k]) + 0 > out
}
}
'
sort -t $'\t' -k3,3nr "$TMP_DIR/author_by_email.tsv" > "$TMP_DIR/author_by_email.sorted.tsv"
awk -F '\t' -v out="$TMP_DIR/author_human_share.tsv" '
$1 !~ /checkpointer@noreply|dependabot\[bot\]/ {
total_commits += $2
total_adds += $3
rows[++n] = $0
}
END {
for (i = 1; i <= n; i++) {
split(rows[i], f, "\t")
add_pct = (total_adds > 0) ? (f[3] / total_adds * 100) : 0
commit_pct = (total_commits > 0) ? (f[2] / total_commits * 100) : 0
printf "%s\t%d\t%d\t%d\t%d\t%.2f%%\t%.2f%%\n", f[1], f[2], f[3], f[4], f[5], add_pct, commit_pct > out
}
}
' "$TMP_DIR/author_by_email.sorted.tsv"
# 3) Contribution by author/day/hour.
git log --all --no-merges --numstat --date=format:'%Y-%m-%d|%H' --format='@@@%aE|%ad' | awk -v out="$TMP_DIR/author_day_hour_summary.tsv" '
BEGIN { FS = "\t" }
/^@@@/ {
split(substr($0, 4), h, /\|/)
email = h[1]
day = h[2]
hour = h[3]
key = email "\t" day "\t" hour
commits[key] += 1
next
}
NF == 3 && $1 ~ /^[0-9]+$/ && $2 ~ /^[0-9]+$/ {
adds[key] += $1
dels[key] += $2
}
END {
for (k in commits) {
split(k, f, "\t")
a = adds[k] + 0
d = dels[k] + 0
printf "%s\t%s\t%s\t%d\t%d\t%d\t%d\n", f[1], f[2], f[3], commits[k], a, d, (a - d) > out
}
}
'
awk -F '\t' -v out="$TMP_DIR/day_summary_human.tsv" '
$1 !~ /checkpointer@noreply|dependabot\[bot\]/ {
day = $2
commits[day] += $4
adds[day] += $5
dels[day] += $6
if (!(day in min_hour) || $3 < min_hour[day]) {
min_hour[day] = $3
}
if (!(day in max_hour) || $3 > max_hour[day]) {
max_hour[day] = $3
}
}
END {
for (d in commits) {
printf "%s\t%d\t%d\t%d\t%d\t%s\t%s\n", d, commits[d], adds[d], dels[d], adds[d] - dels[d], min_hour[d], max_hour[d] > out
}
}
' "$TMP_DIR/author_day_hour_summary.tsv"
sort -t $'\t' -k1,1 "$TMP_DIR/day_summary_human.tsv" -o "$TMP_DIR/day_summary_human.tsv"
awk -F '\t' -v out="$TMP_DIR/hour_summary_human.tsv" '
$1 !~ /checkpointer@noreply|dependabot\[bot\]/ {
hour = $3
commits[hour] += $4
adds[hour] += $5
dels[hour] += $6
}
END {
for (i = 0; i < 24; i++) {
h = sprintf("%02d", i)
a = adds[h] + 0
d = dels[h] + 0
printf "%s\t%d\t%d\t%d\t%d\n", h, commits[h] + 0, a, d, a - d > out
}
}
' "$TMP_DIR/author_day_hour_summary.tsv"
sort -t $'\t' -k1,1 "$TMP_DIR/hour_summary_human.tsv" -o "$TMP_DIR/hour_summary_human.tsv"
awk -F '\t' -v out="$TMP_DIR/day_peak_hour_human.tsv" '
$1 !~ /checkpointer@noreply|dependabot\[bot\]/ {
key = $2 "\t" $3
commits[key] += $4
adds[key] += $5
dels[key] += $6
}
END {
for (k in adds) {
split(k, parts, "\t")
day = parts[1]
hour = parts[2]
if (!(day in max_adds) || adds[k] > max_adds[day]) {
max_adds[day] = adds[k]
best_hour[day] = hour
best_commits[day] = commits[k]
best_dels[day] = dels[k]
}
}
for (d in max_adds) {
printf "%s\t%s\t%d\t%d\t%d\n", d, best_hour[d], best_commits[d], max_adds[d], best_dels[d] > out
}
}
' "$TMP_DIR/author_day_hour_summary.tsv"
sort -t $'\t' -k1,1 "$TMP_DIR/day_peak_hour_human.tsv" -o "$TMP_DIR/day_peak_hour_human.tsv"
mkdir -p "$(dirname "$OUT_FILE")"
# 4) Render standalone HTML.
{
cat <<'HTML_HEAD'
Super Multica 代码贡献统计
HTML_TAIL
} > "$OUT_FILE"
echo "Report generated: $OUT_FILE"