how/script/data_processing/run_graph_pipeline.sh

#!/bin/bash
# 图谱构建与可视化流程（步骤5-9）
#
# 依赖前置步骤（1-4）已执行完成：
#   1. extract_feature_categories.py
#   2. extract_features_from_posts.py
#   3. extract_current_posts.py
#   4. match_inspiration_features.py
#
# 本脚本执行：
#   5. filter_how_results.py      - 过滤how解构结果
#   6. extract_nodes_and_edges.py - 提取节点和边
#   7. build_persona_tree.py      - 构建人设树
#   8. build_match_graph.py       - 构建匹配图谱
#   9. build_post_tree.py         - 构建帖子树
#  10. visualize_match_graph.py   - 生成可视化HTML
#
# 使用方式：
#   ./run_graph_pipeline.sh              # 使用默认账号
#   ./run_graph_pipeline.sh 阿里多多酱    # 指定账号
#   ACCOUNT_NAME=xxx ./run_graph_pipeline.sh

set -e  # 遇到错误立即退出

# 获取脚本所在目录的绝对路径
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
PROJECT_ROOT="$(cd "$SCRIPT_DIR/../.." && pwd)"

cd "$PROJECT_ROOT"

# 颜色定义
GREEN='\033[0;32m'
RED='\033[0;31m'
YELLOW='\033[1;33m'
BLUE='\033[0;34m'
NC='\033[0m'

print_info() { echo -e "${BLUE}[INFO]${NC} $1"; }
print_success() { echo -e "${GREEN}[SUCCESS]${NC} $1"; }
print_error() { echo -e "${RED}[ERROR]${NC} $1"; }
print_step() { echo -e "${YELLOW}[$1]${NC} $2"; }

# 执行单个步骤
run_step() {
    local step_num=$1
    local step_name=$2
    local script_name=$3

    print_step "$step_num/6" "$step_name"

    if python "script/data_processing/$script_name"; then
        print_success "$step_name 完成"
        echo ""
        return 0
    else
        print_error "$step_name 失败"
        return 1
    fi
}

# 主处理函数
process_account() {
    local account_name=$1

    echo ""
    echo "=========================================="
    echo "图谱构建与可视化流程"
    echo "账号: $account_name"
    echo "项目: $PROJECT_ROOT"
    echo "=========================================="
    echo ""

    # 设置环境变量
    export ACCOUNT_NAME="$account_name"

    # 步骤5: 过滤how解构结果
    run_step 1 "过滤how解构结果" "filter_how_results.py" || return 1

    # 步骤6: 提取节点和边
    run_step 2 "提取节点和边" "extract_nodes_and_edges.py" || return 1

    # 步骤7: 构建人设树
    run_step 3 "构建人设树" "build_persona_tree.py" || return 1

    # 步骤8: 构建匹配图谱
    run_step 4 "构建匹配图谱" "build_match_graph.py" || return 1

    # 步骤9: 构建帖子树
    run_step 5 "构建帖子树" "build_post_tree.py" || return 1

    # 步骤10: 生成可视化HTML
    run_step 6 "生成可视化HTML" "visualize_match_graph.py" || return 1

    echo "=========================================="
    print_success "图谱构建与可视化流程完成！"
    echo "=========================================="
}

# 获取默认账号
get_default_account() {
    python -c "
import json
from pathlib import Path
config_file = Path('config/accounts.json')
with open(config_file) as f:
    config = json.load(f)
print(config.get('default_account', ''))
"
}

# 主逻辑
main() {
    local account_name=""

    # 解析参数
    if [ -n "$1" ]; then
        account_name="$1"
    elif [ -n "$ACCOUNT_NAME" ]; then
        account_name="$ACCOUNT_NAME"
    else
        account_name=$(get_default_account)
        if [ -z "$account_name" ]; then
            print_error "未指定账号，请通过参数或环境变量指定"
            echo "用法: $0 <账号名>"
            exit 1
        fi
        print_info "使用默认账号: $account_name"
    fi

    process_account "$account_name"
}

main "$@"