PlantAI-rag-new/tooling/compile/compile_qa.sh

#!/usr/bin/env bash
# Compile the QA V1.1.73 runtime surface into stripped Cython extensions.
set -euo pipefail
umask 027

SOURCE_ROOT="${1:?Usage: $0 <source-root> <output-dir> [python]}"
OUTPUT_DIR="${2:?Usage: $0 <source-root> <output-dir> [python]}"
PYTHON="${3:-python3}"
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
VISIBILITY_TOOL="${ELF_VISIBILITY_TOOL:-$SCRIPT_DIR/tools/elf_visibility.py}"
ENTRY_SCRIPT="scripts/qa_v1_1_73_server.py"

SOURCE_ROOT="$(realpath "$SOURCE_ROOT")"
OUTPUT_DIR="$(realpath -m "$OUTPUT_DIR")"

[[ -d "$SOURCE_ROOT" ]] || { echo "QA source directory missing: $SOURCE_ROOT" >&2; exit 2; }
[[ -x "$PYTHON" ]] || { echo "Python is not executable: $PYTHON" >&2; exit 2; }
[[ -f "$VISIBILITY_TOOL" ]] || { echo "ELF visibility tool missing: $VISIBILITY_TOOL" >&2; exit 2; }
for command_name in gcc strip rsync; do command -v "$command_name" >/dev/null; done

case "$OUTPUT_DIR" in
  "/"|"$(realpath -m "$HOME")"|"$SOURCE_ROOT")
    echo "Unsafe output directory: $OUTPUT_DIR" >&2
    exit 2
    ;;
esac
[[ ! -e "$OUTPUT_DIR" ]] || {
  echo "Output already exists; refusing to overwrite: $OUTPUT_DIR" >&2
  exit 2
}

mkdir -p \
  "$OUTPUT_DIR/scripts" \
  "$OUTPUT_DIR/src/rag/qa_v1_1_73" \
  "$OUTPUT_DIR/src/rag/retrieval" \
  "$OUTPUT_DIR/src/rag/dual_kb_taxonomy_rag" \
  "$OUTPUT_DIR/configs/rag"

echo "[QA 1/6] Copying the audited runtime surface"
install -m 0750 "$SOURCE_ROOT/$ENTRY_SCRIPT" "$OUTPUT_DIR/$ENTRY_SCRIPT"
rsync -a --include='*.py' --exclude='*' \
  "$SOURCE_ROOT/src/rag/qa_v1_1_73/" "$OUTPUT_DIR/src/rag/qa_v1_1_73/"
rsync -a --include='*.py' --exclude='*' \
  "$SOURCE_ROOT/src/rag/retrieval/" "$OUTPUT_DIR/src/rag/retrieval/"
install -m 0640 \
  "$SOURCE_ROOT/src/rag/dual_kb_taxonomy_rag/entity_alias.py" \
  "$OUTPUT_DIR/src/rag/dual_kb_taxonomy_rag/entity_alias.py"
# 2026-08-31 主项目新增:normalized_release.py(backend_guard 校验 + 图适配器)
[[ -f "$SOURCE_ROOT/src/rag/normalized_release.py" ]] && install -m 0640 \
  "$SOURCE_ROOT/src/rag/normalized_release.py" \
  "$OUTPUT_DIR/src/rag/normalized_release.py"
for relative in \
  configs/rag/entity_alias.yaml \
  configs/rag/relation_taxonomy.yaml \
  pyproject.toml \
  requirements.txt \
  requirements-rag.txt
do
  if [[ -f "$SOURCE_ROOT/$relative" ]]; then
    install -D -m 0640 "$SOURCE_ROOT/$relative" "$OUTPUT_DIR/$relative"
  fi
done

# Namespace/package markers are intentionally left as minimal Python files.
touch \
  "$OUTPUT_DIR/scripts/__init__.py" \
  "$OUTPUT_DIR/src/__init__.py" \
  "$OUTPUT_DIR/src/rag/__init__.py" \
  "$OUTPUT_DIR/src/rag/dual_kb_taxonomy_rag/__init__.py"

echo "[QA 2/6] Discovering Python modules"
PY_FILES=()
while IFS= read -r -d '' path; do PY_FILES+=("$path"); done \
  < <(find "$OUTPUT_DIR" -type f -name '*.py' \
      -not -path "*/$ENTRY_SCRIPT" \
      -not -name '__init__.py' -print0)
TOTAL="${#PY_FILES[@]}"
(( TOTAL > 0 )) || { echo "No QA modules selected for compilation" >&2; exit 3; }

INCLUDE_PY="$("$PYTHON" -c 'import sysconfig; print(sysconfig.get_config_var("INCLUDEPY") or "")')"
EXT_SUFFIX="$("$PYTHON" -c 'import sysconfig; print(sysconfig.get_config_var("EXT_SUFFIX") or ".so")')"
[[ -n "$INCLUDE_PY" ]] || { echo "Python INCLUDEPY is empty" >&2; exit 3; }

echo "[QA 3/6] Cython preflight ($TOTAL modules)"
COUNT=0
CYTHON_FAILURES=0
for py_file in "${PY_FILES[@]}"; do
  COUNT=$((COUNT + 1))
  directory="$(dirname "$py_file")"
  module="$(basename "$py_file" .py)"
  c_file="$directory/$module.c"
  echo "  [$COUNT/$TOTAL] ${py_file#"$OUTPUT_DIR"/}"
  if ! "$PYTHON" -m cython -3 \
      --directive always_allow_keywords=true,annotation_typing=False \
      --no-docstrings "$py_file" -o "$c_file"; then
    CYTHON_FAILURES=$((CYTHON_FAILURES + 1))
  fi
done
(( CYTHON_FAILURES == 0 )) || {
  echo "QA Cython preflight failed: modules=$CYTHON_FAILURES" >&2
  exit 3
}

echo "[QA 4/6] GCC hidden visibility + strip ($TOTAL modules)"
COUNT=0
for py_file in "${PY_FILES[@]}"; do
  COUNT=$((COUNT + 1))
  directory="$(dirname "$py_file")"
  module="$(basename "$py_file" .py)"
  c_file="$directory/$module.c"
  so_file="$directory/$module$EXT_SUFFIX"
  echo "  [$COUNT/$TOTAL] ${py_file#"$OUTPUT_DIR"/}"
  gcc -shared -pthread -fPIC -O2 -fvisibility=hidden \
    -I"$INCLUDE_PY" -o "$so_file" "$c_file"
  strip --strip-unneeded "$so_file"
  "$PYTHON" -B "$VISIBILITY_TOOL" \
    --hide-non-pyinit --check "$so_file" >/dev/null
  rm -f -- "$c_file" "$py_file"
done

echo "[QA 5/6] Restoring package markers"
while IFS= read -r -d '' directory; do
  if find "$directory" -maxdepth 1 -type f \( -name '*.so' -o -name '*.py' \) -print -quit | grep -q .; then
    [[ -f "$directory/__init__.py" ]] || touch "$directory/__init__.py"
  fi
done < <(find "$OUTPUT_DIR" -type d -print0)

echo "[QA 6/6] Final checks"
SO_COUNT="$(find "$OUTPUT_DIR" -type f -name '*.so' | wc -l)"
[[ "$SO_COUNT" -eq "$TOTAL" ]] || {
  echo "QA count mismatch: selected=$TOTAL produced=$SO_COUNT" >&2
  exit 4
}
if find "$OUTPUT_DIR" -type f -name '*.c' -print -quit | grep -q .; then
  echo "Generated C source remains in output" >&2
  exit 4
fi

echo "QA compile+harden complete: modules=$SO_COUNT output=$OUTPUT_DIR"