chore(migration): rename-aware filter-repo extraction driver

docs/marketplace-polyrepo-migration/migration/10-extract.sh

@@ -0,0 +1,80 @@
+#!/usr/bin/env bash
+# Step 3 — Rename-aware extraction driver.
+# Given a target key from plugin-map.json, clones the dedicated mirror ($WORK/_mirror, built by
+# 00-preflight.sh — never the working checkout, R4/M6) into $WORK/<key>, runs a SINGLE git filter-repo
+# pass composing --path / --path-rename (both names for renamed plugins, F1) + the deterministic
+# ms-ai-architect blob strip (F3), then strips carried-over tags and re-creates exactly one annotated
+# tag v<version> at the rewritten HEAD (F5). Idempotent (wipes $WORK/<key> first). NULL push (D8).
+#
+# Renamed plugins are extracted under BOTH historical names (F1), driven by plugin-map.json:
+#   voyage ← ultraplan-local, llm-security ← llm-security-copilot, linkedin-studio ← linkedin-thought-leadership.
+# A single-path filter would silently drop the pre-rename history, so the map carries >=2 --path entries each.
+#
+# Usage: 10-extract.sh <target-key>     (e.g. voyage, llm-security, playground-design-system)
+# Override WORK= to relocate the workspace (default /tmp/polyrepo-migration).
+set -euo pipefail
+
+KEY="${1:-}"
+[ -n "$KEY" ] || { echo "usage: 10-extract.sh <target-key>" >&2; exit 2; }
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+MAP="$SCRIPT_DIR/plugin-map.json"
+WORK="${WORK:-/tmp/polyrepo-migration}"
+MIRROR="$WORK/_mirror"
+DEST="$WORK/$KEY"
+
+fail() { printf 'EXTRACT FAIL: %s\n' "$*" >&2; exit 1; }
+
+[ -f "$MAP" ] || fail "plugin-map.json missing at $MAP"
+python3 -c "import json,sys; m=json.load(open('$MAP')); sys.exit(0 if '$KEY' in m['targets'] else 1)" \
+  || fail "unknown target '$KEY' (not in plugin-map.json)"
+
+# Self-heal: if the mirror is absent, run preflight to build it (extraction never reads the working checkout).
+if [ ! -e "$MIRROR/HEAD" ] && [ ! -d "$MIRROR/.git" ]; then
+  echo "  mirror absent → running preflight to build it"
+  WORK="$WORK" bash "$SCRIPT_DIR/00-preflight.sh" >/dev/null
+fi
+[ -e "$MIRROR/HEAD" ] || [ -d "$MIRROR/.git" ] || fail "mirror still absent after preflight: $MIRROR"
+
+# Compose the filter-repo arg list from the map (one arg per line → bash 3.2 array).
+ARGS_FILE="$(mktemp)"
+python3 - "$MAP" "$KEY" >"$ARGS_FILE" <<'PY'
+import json, sys
+m = json.load(open(sys.argv[1]))
+t = m["targets"][sys.argv[2]]
+out = []
+for p in t["paths"]:
+    out += ["--path", p]
+for old, new in t.get("path_renames", {}).items():
+    out += ["--path-rename", old + ":" + new]
+if t.get("blob_strip"):
+    if t.get("blob_strip_safe"):
+        out += ["--strip-blobs-bigger-than", "1M"]
+    else:
+        # Surgical fallback (unreached while blob_strip_safe is true): drop only the screenshots.
+        out += ["--path-glob", "!plugins/ms-ai-architect/playground/screenshots/*"]
+for a in out:
+    print(a)
+PY
+FR_ARGS=()
+while IFS= read -r line; do FR_ARGS+=("$line"); done <"$ARGS_FILE"
+rm -f "$ARGS_FILE"
+
+TAG="$(python3 -c "import json; print(json.load(open('$MAP'))['targets']['$KEY']['tag'])")"
+
+# Fresh --no-local clone from the mirror, then the single composing filter-repo pass.
+rm -rf "$DEST"
+git clone --no-local --quiet "$MIRROR" "$DEST"
+git -C "$DEST" filter-repo --force "${FR_ARGS[@]}"
+
+# F5: strip every carried-over tag, re-create exactly one annotated tag at the rewritten HEAD.
+OLD_TAGS="$(git -C "$DEST" tag)"
+if [ -n "$OLD_TAGS" ]; then
+  printf '%s\n' "$OLD_TAGS" | while IFS= read -r tg; do
+    [ -n "$tg" ] && git -C "$DEST" tag -d "$tg" >/dev/null
+  done
+fi
+git -C "$DEST" tag -a "$TAG" -m "Release $TAG (extracted from ktg-plugin-marketplace monorepo)"
+
+COMMITS="$(git -C "$DEST" rev-list --count HEAD)"
+echo "EXTRACT OK $KEY → $DEST ($COMMITS commits, tag $TAG)"