ocr_platform/ocr_validator/streamlit_ocr_validator.py

#!/usr/bin/env python3
"""
基于Streamlit的OCR可视化校验工具（主入口）
"""

import streamlit as st
from pathlib import Path
import json
import sys

# 添加 ocr_platform 根目录到 Python 路径（用于导入 ocr_utils）
# 使用 resolve() 确保路径是绝对路径，避免相对路径导致的 IndexError
_file_path = Path(__file__).resolve()
ocr_platform_root = _file_path.parents[1]  # streamlit_ocr_validator.py -> ocr_validator -> ocr_platform
if str(ocr_platform_root) not in sys.path:
    sys.path.insert(0, str(ocr_platform_root))

from streamlit_validator_core import StreamlitOCRValidator
from streamlit_validator_ui import (
    setup_page_config, create_data_source_selector, message_box
)
from streamlit_validator_table import display_html_table_as_dataframe
from streamlit_validator_cross import (
    cross_validation_dialog, show_batch_cross_validation_results_dialog
)
from streamlit_validator_result import display_single_page_cross_validation
from ocr_validator_utils import get_data_source_display_name
from config_manager import load_config  # 🎯 使用新配置管理器


def reset_cross_validation_results():
    """重置交叉验证结果"""
    if 'cross_validation_batch_result' in st.session_state:
        st.session_state.cross_validation_batch_result = None
        print("🔄 数据源已变更，交叉验证结果已清空")


def main():
    """主应用"""
    # 🎯 初始化配置管理器
    if 'config_manager' not in st.session_state:
        try:
            st.session_state.config_manager = load_config(config_dir="config")
            # 🎯 生成 OCRValidator 所需的配置
            st.session_state.validator_config = st.session_state.config_manager.to_validator_config()
            print("✅ 配置管理器初始化成功")
            print(f"📄 发现 {len(st.session_state.config_manager.list_documents())} 个文档配置")
            print(f"🔧 发现 {len(st.session_state.config_manager.list_ocr_tools())} 个 OCR 工具")
        except Exception as e:
            st.error(f"❌ 配置加载失败: {e}")
            st.stop()
    
    config_manager = st.session_state.config_manager
    validator_config = st.session_state.validator_config
    
    # 初始化应用
    if 'validator' not in st.session_state:
        # 🎯 直接传递配置字典给 OCRValidator
        validator = StreamlitOCRValidator(config_dict=validator_config)
        st.session_state.validator = validator
        setup_page_config(validator_config)
        
        # 页面标题
        st.title(validator_config['ui']['page_title'])
        
        # 初始化数据源追踪
        st.session_state.current_ocr_source = validator.current_source_key
        st.session_state.current_verify_source = validator.verify_source_key
    else:
        validator = st.session_state.validator
    
    if 'selected_text' not in st.session_state:
        st.session_state.selected_text = None
        st.session_state.compact_search_query = None
    if 'marked_errors' not in st.session_state:
        st.session_state.marked_errors = set()
    
    # 数据源选择器
    create_data_source_selector(validator)
    
    # ✅ 检测数据源是否变更
    ocr_source_changed = False
    verify_source_changed = False
    
    if 'current_ocr_source' in st.session_state:
        if st.session_state.current_ocr_source != validator.current_source_key:
            ocr_source_changed = True
            st.session_state.current_ocr_source = validator.current_source_key
            print(f"🔄 OCR数据源已切换到: {validator.current_source_key}")
    
    if 'current_verify_source' in st.session_state:
        if st.session_state.current_verify_source != validator.verify_source_key:
            verify_source_changed = True
            st.session_state.current_verify_source = validator.verify_source_key
            print(f"🔄 验证数据源已切换到: {validator.verify_source_key}")
    
    # ✅ 如果任一数据源变更，清空交叉验证结果
    if ocr_source_changed or verify_source_changed:
        reset_cross_validation_results()
        
        # 显示提示信息
        if ocr_source_changed and verify_source_changed:
            st.info("ℹ️ OCR数据源和验证数据源已变更，请重新运行交叉验证")
        elif ocr_source_changed:
            st.info("ℹ️ OCR数据源已变更，请重新运行交叉验证")
        elif verify_source_changed:
            st.info("ℹ️ 验证数据源已变更，请重新运行交叉验证")
    
    # 如果没有可用的数据源，提前返回
    if not validator.all_sources:
        st.warning("⚠️ 未找到任何数据源，请检查配置文件")
        
        # 🎯 显示配置信息帮助调试
        with st.expander("🔍 配置信息", expanded=True):
            st.write("**已加载的文档:**")
            docs = config_manager.list_documents()
            if docs:
                for doc in docs:
                    doc_config = config_manager.get_document(doc)
                    st.write(f"- **{doc}**")
                    st.write(f"  - 基础目录: `{doc_config.base_dir}`")
                    st.write(f"  - OCR 结果: {len([r for r in doc_config.ocr_results if r.enabled])} 个已启用")
            else:
                st.write("无")
            
            st.write("**已加载的 OCR 工具:**")
            tools = config_manager.list_ocr_tools()
            if tools:
                for tool in tools:
                    tool_config = config_manager.get_ocr_tool(tool)
                    st.write(f"- **{tool_config.name}** (`{tool}`)")
            else:
                st.write("无")
            
            st.write("**配置文件路径:**")
            st.code(str(config_manager.config_dir / "global.yaml"))
            
            st.write("**生成的数据源:**")
            data_sources = config_manager.get_data_sources()
            if data_sources:
                for ds in data_sources:
                    st.write(f"- `{ds.name}`")
                    st.write(f"  - 工具: {ds.ocr_tool}")
                    st.write(f"  - 结果目录: {ds.ocr_out_dir}")
                    st.write(f"  - 图片目录: {ds.src_img_dir}")
            else:
                st.write("无")
        
        st.stop()
    
    # 文件选择区域
    with st.container(height=75, horizontal=True, horizontal_alignment='left', gap="medium"):
        if 'selected_file_index' not in st.session_state:
            st.session_state.selected_file_index = 0
            st.session_state.file_selectbox = 0
            
        if validator.display_options:
            # 确保 selected_file_index 在有效范围内
            if st.session_state.selected_file_index >= len(validator.display_options):
                st.session_state.selected_file_index = 0
                st.session_state.file_selectbox = 0
            
            # 使用独立的 key 给 selectbox，避免 Streamlit 锁定 selected_file_index
            # 在创建 selectbox 之前，同步 file_selectbox 的值到 selected_file_index
            if 'file_selectbox' not in st.session_state:
                st.session_state.file_selectbox = st.session_state.selected_file_index
            elif st.session_state.file_selectbox != st.session_state.selected_file_index:
                # 如果 selected_file_index 被外部更新（如通过页码输入），同步到 file_selectbox
                st.session_state.file_selectbox = st.session_state.selected_file_index
            
            selected_index = st.selectbox(
                "选择OCR结果文件", 
                range(len(validator.display_options)),
                format_func=lambda i: validator.display_options[i],
                index=st.session_state.selected_file_index,
                key="file_selectbox",
                label_visibility="collapsed"
            )
            
            # 手动同步 selectbox 的值到 selected_file_index
            if selected_index != st.session_state.selected_file_index:
                st.session_state.selected_file_index = selected_index
            
            selected_file = validator.file_paths[selected_index]
            current_page = validator.file_info[selected_index]['page']
            
            # 初始化或同步页码值
            if 'page_input_value' not in st.session_state:
                st.session_state.page_input_value = current_page
            
            # 如果当前页码与 session_state 中的值不一致，更新 session_state
            # 这会在下拉框改变或通过其他方式改变文件时同步页码
            if current_page != st.session_state.page_input_value:
                st.session_state.page_input_value = current_page
            
            page_input = st.number_input(
                "输入页码", 
                placeholder="输入页码", 
                label_visibility="collapsed",
                min_value=1, 
                max_value=len(validator.display_options), 
                value=st.session_state.page_input_value, 
                step=1,
                key="page_input"
            )
            
            # 更新 session_state 中的页码值
            if page_input != st.session_state.page_input_value:
                st.session_state.page_input_value = page_input
            
            if page_input != current_page:
                for i, info in enumerate(validator.file_info):
                    if info['page'] == page_input:
                        # 更新 selected_file_index，selectbox 会在下一个运行周期自动同步
                        st.session_state.selected_file_index = i
                        selected_file = validator.file_paths[i]
                        # 同步页码值
                        st.session_state.page_input_value = page_input
                        st.rerun()
                        break

            if (st.session_state.selected_file_index >= 0
                and validator.selected_file_index != st.session_state.selected_file_index
                and selected_file):
                validator.selected_file_index = st.session_state.selected_file_index
                st.session_state.validator.load_ocr_data(selected_file)
                
                current_source_name = get_data_source_display_name(validator.current_source_config)
                st.success(f"✅ 已加载 {current_source_name} - 第{validator.file_info[st.session_state.selected_file_index]['page']}页")
                st.rerun()
        else:
            st.warning("当前数据源中未找到OCR结果文件")

        # ✅ 交叉验证按钮 - 添加数据源检查
        cross_validation_enabled = (
            validator.current_source_key != validator.verify_source_key 
            and validator.image_path 
            and validator.md_content
        )
        
        if st.button(
            "交叉验证", 
            type="primary", 
            icon=":material/compare_arrows:",
            disabled=not cross_validation_enabled,
            help="需要选择不同的OCR数据源和验证数据源" if not cross_validation_enabled else "开始批量交叉验证"
        ):
            cross_validation_dialog(validator)

        # ✅ 查看验证结果按钮 - 检查是否有验证结果
        has_validation_results = (
            'cross_validation_batch_result' in st.session_state 
            and st.session_state.cross_validation_batch_result is not None
        )
        
        if st.button(
            "查看验证结果", 
            type="secondary", 
            icon=":material/quick_reference_all:",
            disabled=not has_validation_results,
            help="暂无验证结果，请先运行交叉验证" if not has_validation_results else "查看批量验证结果"
        ):
            show_batch_cross_validation_results_dialog()

    # 显示当前数据源统计信息
    with st.expander("OCR工具统计信息", expanded=False):
        stats = validator.get_statistics()
        col1, col2, col3, col4, col5 = st.columns(5)
        
        with col1:
            st.metric("📊 总文本块", stats['total_texts'])
        with col2:
            st.metric("🔗 可点击文本", stats['clickable_texts'])
        with col3:
            st.metric("❌ 标记错误", stats['marked_errors'])
        with col4:
            st.metric("✅ 准确率", f"{stats['accuracy_rate']:.1f}%")
        with col5:
            if validator.current_source_config:
                tool_id = validator.current_source_config['ocr_tool']
                # 🎯 从配置管理器获取工具名称
                tool_config = config_manager.get_ocr_tool(tool_id)
                tool_display = tool_config.name if tool_config else tool_id.upper()
                st.metric("🔧 OCR工具", tool_display)
        
        if stats['tool_info']:
            st.write("**详细信息:**", stats['tool_info'])
        
        # 🎯 显示当前文档和 OCR 结果信息
        if validator.current_source_config:
            source_name = validator.current_source_config['name']
            # 解析数据源名称，提取文档名（更精确的解析）
            parts = source_name.split('_', 1)
            doc_name = parts[0] if parts else source_name
            
            doc_config = config_manager.get_document(doc_name)
            if doc_config:
                st.write("**文档信息:**")
                st.write(f"- 文档名称: {doc_config.name}")
                st.write(f"- 基础目录: {doc_config.base_dir}")
                st.write(f"- 可用 OCR 工具: {len([r for r in doc_config.ocr_results if r.enabled])} 个")
    
    # 🎯 添加配置管理面板
    with st.expander("⚙️ 配置管理", expanded=False):
        col1, col2 = st.columns(2)
        
        with col1:
            st.subheader("📄 已加载文档")
            docs = config_manager.list_documents()
            for doc_name in docs:
                doc_config = config_manager.get_document(doc_name)
                enabled_count = len([r for r in doc_config.ocr_results if r.enabled])
                total_count = len(doc_config.ocr_results)
                
                with st.container():
                    st.write(f"✅ **{doc_name}**")
                    st.caption(f"📊 {enabled_count}/{total_count} 工具已启用")
                    
                    # 显示每个 OCR 工具的状态
                    for ocr_result in doc_config.ocr_results:
                        status_icon = "🟢" if ocr_result.enabled else "⚪"
                        tool_config = config_manager.get_ocr_tool(ocr_result.tool)
                        tool_name = tool_config.name if tool_config else ocr_result.tool
                        st.caption(f"  {status_icon} {tool_name} - {ocr_result.description or ocr_result.result_dir}")
        
        with col2:
            st.subheader("🔧 已加载 OCR 工具")
            tools = config_manager.list_ocr_tools()
            for tool_id in tools:
                tool_config = config_manager.get_ocr_tool(tool_id)
                with st.container():
                    st.write(f"🔧 **{tool_config.name}**")
                    st.caption(f"ID: `{tool_id}`")
                    st.caption(f"描述: {tool_config.description}")
    
    tab1, tab2, tab3 = st.tabs(["📄 内容人工检查", "🔍 交叉验证结果", "📊 表格分析"])
    
    with tab1:
        validator.create_compact_layout(validator_config)

    with tab2:
        # ✅ 使用封装的函数显示单页交叉验证结果
        display_single_page_cross_validation(validator, validator_config)

    with tab3:
        st.header("📊 表格数据分析")
        
        if validator.md_content and '<table' in validator.md_content.lower():
            st.subheader("🔍 表格数据预览")
            display_html_table_as_dataframe(validator.md_content)
        else:
            st.info("当前OCR结果中没有检测到表格数据")


if __name__ == "__main__":
    main()