#!/bin/sh
# merge-import.sh - harvest a not-yet-fragmented branch's changelog into fragments, then rebuild views.
#
# 合并旧格式分支（如 master）后用它：把对方旧格式 changelog 条目收割成 fragment
# （只补 entries/ 里还没有的 ID，绝不覆盖已有 fragment），重建四个视图，并报告丢失的 ID。
#
# Usage:
#   sh .cursor/changelog/tools/merge-import.sh            # harvest from working-tree (post union-merge)
#   sh .cursor/changelog/tools/merge-import.sh master     # harvest directly from a ref

set -e
REF="${1:-}"
export PYTHONIOENCODING=utf-8

ROOT=$(git rev-parse --show-toplevel 2>/dev/null) || { echo "not inside a git repository"; exit 1; }
cd "$ROOT"

CL=".cursor/changelog"
TOOLS="$CL/tools"

if command -v python >/dev/null 2>&1; then PY=python
elif command -v python3 >/dev/null 2>&1; then PY=python3
else echo "python not found"; exit 1; fi

ids_of() {
  [ -f "$1" ] || return 0
  grep -oE "^### \[(CL-[^]]+)\]" "$1" | sed -E 's/^### \[(CL-[^]]+)\]/\1/' | sort -u
}

VIEWS="changelog-full.md changelog-recent.md changelog-headlines.md"
TMP=$(mktemp -d)
trap 'rm -rf "$TMP"' EXIT

if [ -n "$REF" ]; then
  echo "harvest source: ref '$REF'"
  for f in $VIEWS; do
    git show "$REF:$CL/$f" > "$TMP/$f" 2>/dev/null || true
  done
else
  echo "harvest source: working-tree (post union-merge)"
  for f in $VIEWS; do
    [ -f "$CL/$f" ] && cp -f "$CL/$f" "$TMP/$f"
  done
fi

SRC_IDS=$(ids_of "$TMP/changelog-full.md")
SRC_COUNT=$(printf '%s\n' "$SRC_IDS" | grep -c . || true)
echo "source entries: $SRC_COUNT"

# parse source into staging fragments (temp/entries/legacy)
"$PY" "$TOOLS/migrate_changelog.py" "$TMP" >/dev/null

# existing fragment ids in the real repo (filename stem == id)
mkdir -p "$CL/entries/legacy"
added=0
if [ -d "$TMP/entries/legacy" ]; then
  for frag in "$TMP/entries/legacy"/*.md; do
    [ -e "$frag" ] || continue
    base=$(basename "$frag")
    id="${base%.md}"
    if ! find "$CL/entries" -name "$base" | grep -q .; then
      cp -f "$frag" "$CL/entries/legacy/$base"
      added=$((added+1))
    fi
  done
fi
echo "new fragments imported: $added"

# rebuild views
"$PY" "$TOOLS/changelog_build.py"

# verify
NOW_IDS=$(ids_of "$CL/changelog-full.md")
missing=$(comm -23 <(printf '%s\n' "$SRC_IDS") <(printf '%s\n' "$NOW_IDS") || true)
if [ -n "$missing" ]; then
  echo "WARNING: source ids missing after rebuild:"
  printf '  %s\n' $missing
  exit 2
fi
NOW_COUNT=$(printf '%s\n' "$NOW_IDS" | grep -c . || true)
echo "OK: all $SRC_COUNT source entries present. total now: $NOW_COUNT."
echo "next: git add -A; git commit"