ocr_verify/ocr_validator_layout.py

#!/usr/bin/env python3
"""
OCR验证工具的布局管理模块
包含标准布局、滚动布局、紧凑布局的实现
"""

import streamlit as st
from pathlib import Path
from PIL import Image
from typing import Dict, List, Optional
import plotly.graph_objects as go
from typing import Tuple

from ocr_validator_utils import (
    rotate_image_and_coordinates,
    get_ocr_tool_rotation_config,
)

from ocr_validator_file_utils import (
    convert_html_table_to_markdown, 
    parse_html_tables,
    draw_bbox_on_image,
    detect_image_orientation_by_opencv  # 新增导入
)

class OCRLayoutManager:
    """OCR布局管理器"""
    
    def __init__(self, validator):
        self.validator = validator
        self.config = validator.config
        self._rotated_image_cache = {}
        self._cache_max_size = 10
        self._orientation_cache = {}  # 缓存方向检测结果
        self.rotated_angle = 0.0  # 自动检测的旋转角度缓存
        self.show_all_boxes = False
        self.fit_to_container = False
        self.zoom_level = 1.0
    
    def clear_image_cache(self):
        """清理所有图像缓存"""
        self._rotated_image_cache.clear()
        
    def clear_cache_for_image(self, image_path: str):
        """清理指定图像的所有缓存"""
        keys_to_remove = [key for key in self._rotated_image_cache.keys() if key.startswith(image_path)]
        for key in keys_to_remove:
            del self._rotated_image_cache[key]
    
    def get_cache_info(self) -> dict:
        """获取缓存信息"""
        return {
            'cache_size': len(self._rotated_image_cache),
            'cached_images': list(self._rotated_image_cache.keys()),
            'max_size': self._cache_max_size
        }
    
    def _manage_cache_size(self):
        """管理缓存大小，超出限制时清理最旧的缓存"""
        if len(self._rotated_image_cache) > self._cache_max_size:
            # 删除最旧的缓存项（FIFO策略）
            oldest_key = next(iter(self._rotated_image_cache))
            del self._rotated_image_cache[oldest_key]
    
    def detect_and_suggest_rotation(self, image_path: str) -> Dict:
        """检测并建议图片旋转角度"""
        if image_path in self._orientation_cache:
            return self._orientation_cache[image_path]
        
        # 使用自动检测功能
        detection_result = detect_image_orientation_by_opencv(image_path)
        
        # 缓存结果
        self._orientation_cache[image_path] = detection_result
        return detection_result
    
    def get_rotation_angle(self) -> float:
        """获取旋转角度 - 增强版本支持自动检测"""
        # 如果没有预设角度，优先人工设置
        if hasattr(self, 'rotated_angle') and self.rotated_angle != 0:
            return self.rotated_angle

        # 尝试从OCR数据中获取（PPStructV3等）
        if self.validator.ocr_data:
            for item in self.validator.ocr_data:
                if isinstance(item, dict) and 'rotation_angle' in item:
                    return item['rotation_angle']
        
        # 如果没有预设角度，尝试自动检测
        if hasattr(self, 'rotated_angle'):
            return self.rotated_angle
        
        return 0.0
    
    def load_and_rotate_image(self, image_path: str) -> Optional[Image.Image]:
        """加载并根据需要旋转图像"""
        if not image_path or not Path(image_path).exists():
            return None
            
        # 检查缓存
        rotation_angle = self.get_rotation_angle()
        cache_key = f"{image_path}_{rotation_angle}"
        
        if cache_key in self._rotated_image_cache:
            return self._rotated_image_cache[cache_key]
        
        try:
            image = Image.open(image_path)
            
            # 如果需要旋转
            if rotation_angle != 0:
                # 获取OCR工具的旋转配置
                rotation_config = get_ocr_tool_rotation_config(self.validator.ocr_data, self.config)
                
                # st.info(f"🔄 检测到文档旋转角度: {rotation_angle}°，正在处理图像和坐标...")
                # st.info(f"📋 OCR工具配置: 坐标{'已预旋转' if rotation_config['coordinates_are_pre_rotated'] else '需要旋转'}")
                
                # 判断是否需要旋转坐标
                if rotation_config['coordinates_are_pre_rotated']:
                    # 图片的角度与坐标的角度不一致，比如PPStructV3，图片0度，坐标已旋转270度
                    # 这种情况下，只需要旋转图片，坐标不变
                    # PPStructV3: 坐标已经是旋转后的，只旋转图像
                    img_rotation_angle = (rotation_angle + self.rotated_angle) % 360
                    if img_rotation_angle == 270:
                        rotated_image = image.rotate(-90, expand=True)  # 顺时针90度
                    elif img_rotation_angle == 90:
                        rotated_image = image.rotate(90, expand=True)   # 逆时针90度
                    elif img_rotation_angle == 180:
                        rotated_image = image.rotate(180, expand=True)  # 180度
                    else:
                        rotated_image = image.rotate(-img_rotation_angle, expand=True)
                    
                    if self.rotated_angle == 0:
                        # 坐标不需要变换，因为JSON中已经是正确的坐标
                        self._rotated_image_cache[cache_key] = rotated_image
                        self._manage_cache_size()
                        return rotated_image

                    image = rotated_image  # 继续使用旋转后的图像进行后续处理
                
                # Dots OCR: 需要同时旋转图像和坐标
                # 收集所有bbox坐标
                all_bboxes = []
                text_to_bbox_map = {}  # 记录文本到bbox索引的映射
                
                bbox_index = 0
                for text, info_list in self.validator.text_bbox_mapping.items():
                    text_to_bbox_map[text] = []
                    for info in info_list:
                        all_bboxes.append(info['bbox'])
                        text_to_bbox_map[text].append(bbox_index)
                        bbox_index += 1
                
                # 旋转图像和坐标
                rotated_image, rotated_bboxes = rotate_image_and_coordinates(
                    image, rotation_angle, all_bboxes, 
                    rotate_coordinates=not rotation_config['coordinates_are_pre_rotated']
                )
                
                # 更新bbox映射 - 使用映射关系确保正确对应
                for text, bbox_indices in text_to_bbox_map.items():
                    for i, bbox_idx in enumerate(bbox_indices):
                        if bbox_idx < len(rotated_bboxes) and i < len(self.validator.text_bbox_mapping[text]):
                            self.validator.text_bbox_mapping[text][i]['bbox'] = rotated_bboxes[bbox_idx]
                
                # 缓存结果
                self._rotated_image_cache[cache_key] = rotated_image
                self._manage_cache_size()
                return rotated_image
                    
            else:
                # 无需旋转，直接缓存原图
                self._rotated_image_cache[cache_key] = image
                self._manage_cache_size()  # 检查并管理缓存大小
                return image
                
        except Exception as e:
            st.error(f"❌ 图像加载失败: {e}")
            return None

    def render_content_by_mode(self, content: str, render_mode: str, font_size: int, container_height: int, layout_type: str):
        """根据渲染模式显示内容 - 增强版本"""
        if content is None or render_mode is None:
            return
            
        if render_mode == "HTML渲染":
            # 增强的HTML渲染样式，支持横向滚动
            content_style = f"""
            <style>
            .{layout_type}-content-display {{
                height: {container_height}px;
                overflow-x: auto;
                overflow-y: auto;
                font-size: {font_size}px !important;
                line-height: 1.4;
                color: #333333 !important;
                background-color: #fafafa !important;
                padding: 10px;
                border-radius: 5px;
                border: 1px solid #ddd;
                max-width: 100%;
            }}
            
            .{layout_type}-content-display table {{
                width: 100%;  /* 修改：从100%改为auto，让表格自适应内容 */
                border-collapse: collapse;
                margin: 10px 0;
                white-space: nowrap;  /* 修改：允许文字换行 */
                /* table-layout: auto; *?  /* 新增：自动表格布局 */
            }}
            
            .{layout_type}-content-display th,
            .{layout_type}-content-display td {{
                border: 1px solid #ddd;
                padding: 8px;
                text-align: left;
                /* 移除：min-width固定限制 */
                max-width: 300px;     /* 新增：设置最大宽度避免过宽 */
                word-wrap: break-word; /* 新增：长单词自动换行 */
                word-break: break-all; /* 新增：允许在任意字符间换行 */
                vertical-align: top;   /* 新增：顶部对齐 */
            }}
            
            .{layout_type}-content-display th {{
                background-color: #f5f5f5;
                position: sticky;
                top: 0;
                z-index: 1;
                font-weight: bold;    /* 新增：表头加粗 */
            }}
            
            /* 新增：针对数字列的特殊处理 */
            .{layout_type}-content-display td.number {{
                text-align: right;
                white-space: nowrap;
                font-family: 'Monaco', 'Menlo', monospace;
            }}
            
            /* 新增：针对短文本列的处理 */
            .{layout_type}-content-display td.short-text {{
                white-space: nowrap;
                min-width: 80px;
            }}
            
            .{layout_type}-content-display img {{
                max-width: 100%;
                height: auto;
                border-radius: 4px;
                margin: 10px 0;
            }}
        
            /* 新增：响应式表格 */
            @media (max-width: 768px) {{
                .{layout_type}-content-display table {{
                    font-size: {max(font_size-2, 8)}px;
                }}
                .{layout_type}-content-display th,
                .{layout_type}-content-display td {{
                    padding: 4px;
                    max-width: 150px;
                }}
            }}

            .highlight-text {{
                background-color: #ffeb3b !important;
                padding: 2px 4px;
                border-radius: 3px;
                cursor: pointer;
                color: #333333 !important;
            }}
            
            .selected-highlight {{
                background-color: #4caf50 !important;
                color: white !important;
            }}
            </style>
            """
            st.markdown(content_style, unsafe_allow_html=True)
            st.markdown(f'<div class="{layout_type}-content-display">{content}</div>', unsafe_allow_html=True)
            
        elif render_mode == "Markdown渲染":
            converted_content = convert_html_table_to_markdown(content)
            st.markdown(converted_content, unsafe_allow_html=True)
            
        elif render_mode == "DataFrame表格":
            if '<table' in content.lower():
                self.validator.display_html_table_as_dataframe(content)
            else:
                st.info("当前内容中没有检测到HTML表格")
                st.markdown(content, unsafe_allow_html=True)
        else:  # 原始文本
            st.text_area(
                "MD内容预览",
                content,
                height=300,
                key=f"{layout_type}_text_area"
            )

    def create_compact_layout(self, config: Dict):
        """创建紧凑的对比布局"""
        # 主要内容区域
        layout = config['styles']['layout']
        font_size = config['styles'].get('font_size', 10)
        container_height = layout.get('default_height', 600)
        zoom_level = layout.get('default_zoom', 1.0)
        layout_type = "compact"

        left_col, right_col = st.columns([layout['content_width'], layout['sidebar_width']], vertical_alignment='top', border=True)

        with left_col:
            # 快速定位文本选择器 - 增强版（搜索+下拉）
            if self.validator.text_bbox_mapping:
                # 搜索输入框
                search_col, select_col = st.columns([1, 2])
                
                # 初始化session state
                if "compact_search_query" not in st.session_state:
                    st.session_state.compact_search_query = None
                
                with search_col:
                    search_query = st.text_input(
                        "搜索文本",
                        placeholder="输入关键词...",
                        value=st.session_state.compact_search_query,
                        key=f"{layout_type}_search_input",
                        label_visibility="collapsed"
                    )
                    # 更新session state
                    st.session_state.compact_search_query = search_query
                
                # 构建选项列表
                text_options = ["请选择文本..."]
                text_display = ["请选择文本..."]
                
                for text, info_list in self.validator.text_bbox_mapping.items():
                    # 如果有搜索条件，进行过滤
                    if search_query and search_query.strip():
                        if search_query.lower() not in text.lower():
                            continue  # 跳过不匹配的项
                    
                    text_options.append(text)
                    
                    # 检查是否是表格单元格
                    if info_list and isinstance(info_list[0], dict):
                        first_info = info_list[0]
                        if 'row' in first_info and 'col' in first_info:
                            display_text = f"[R{first_info['row']},C{first_info['col']}] {text}"
                            if len(display_text) > 47:
                                display_text = display_text[:44] + "..."
                        else:
                            display_text = text[:47] + "..." if len(text) > 50 else text
                    else:
                        display_text = text[:47] + "..." if len(text) > 50 else text
                        
                    text_display.append(display_text)
                
                # 显示匹配数量
                if search_query and search_query.strip():
                    st.caption(f"找到 {len(text_options)-1} 个匹配项")
                
                # 确定默认选中的索引
                default_index = 0
                if st.session_state.selected_text and st.session_state.selected_text in text_options:
                    default_index = text_options.index(st.session_state.selected_text)
                
                with select_col:
                    selected_index = st.selectbox(
                        "快速定位文本",
                        range(len(text_options)),
                        index=default_index,
                        format_func=lambda x: text_display[x] if x < len(text_display) else "",
                        label_visibility="collapsed",
                        key=f"{layout_type}_quick_text_selector"
                    )
                
                if selected_index > 0:
                    st.session_state.selected_text = text_options[selected_index]
        
            # 处理并显示OCR内容 - 只高亮选中的文本
            if self.validator.md_content:
                highlighted_content = self.validator.md_content
                
                # 只高亮选中的文本
                if st.session_state.selected_text:
                    selected_text = st.session_state.selected_text
                    if len(selected_text) > 2:
                        highlighted_content = highlighted_content.replace(
                            selected_text,
                            f'<span class="highlight-text selected-highlight" title="{selected_text}">{selected_text}</span>'
                        )
                
                self.render_content_by_mode(highlighted_content, "HTML渲染", font_size, container_height, layout_type)
        
        with right_col:
            # 修复的对齐图片显示
            self.create_aligned_image_display(zoom_level, "compact")
    
    def create_aligned_image_display(self, zoom_level: float = 1.0, layout_type: str = "aligned"):
        """创建响应式图片显示"""
    
        # st.header("🖼️ 原图标注")
        
        # 图片控制选项
        col1, col2, col3, col4, col5 = st.columns(5, vertical_alignment="center", border= False)

        with col1:
            # 判断{layout_type}_show_all_boxes是否有值，如果有值直接使用，否则默认False
            # if f"{layout_type}_show_all_boxes" not in st.session_state:
            #     st.session_state[f"{layout_type}_show_all_boxes"] = False

            show_all_boxes = st.checkbox(
                "显示所有框",
                # value=st.session_state[f"{layout_type}_show_all_boxes"],
                value = self.show_all_boxes,
                key=f"{layout_type}_show_all_boxes"
            )
            if show_all_boxes != self.show_all_boxes:
                self.show_all_boxes = show_all_boxes

        with col2:
            if st.button("🔄 旋转90度", type="secondary", key=f"{layout_type}_manual_angle"):
                self.rotated_angle = (self.rotated_angle + 90) % 360
                # 需要清除图片缓存，以及text_bbox_mapping中的bbox
                self.clear_image_cache()
                self.validator.process_data()
                st.rerun()
                
        with col3:
            # 显示当前角度状态
            current_angle = self.get_rotation_angle()
            st.metric("当前角度", f"{current_angle}°", label_visibility="collapsed")

        with col4:
            if st.button("↺ 重置角度", key=f"{layout_type}_reset_angle"):
                self.rotated_angle = 0.0
                st.success("已重置旋转角度")
                # 需要清除图片缓存，以及text_bbox_mapping中的bbox
                self.clear_image_cache()
                self.validator.process_data()
                st.rerun()
 
        with col5:
            if st.button("🧹 清除选择", key=f"{layout_type}_clear_selection"):
                # 清除选中的文本
                st.session_state.selected_text = None
                # 清除搜索框内容
                st.session_state.compact_search_query = None
                st.rerun()

        # 使用增强的图像加载方法
        image = self.load_and_rotate_image(self.validator.image_path)
        
        if image:
            try:
                resized_image, all_boxes, selected_boxes = self.zoom_image(image, self.zoom_level)
                # 创建交互式图片
                fig = self.create_resized_interactive_plot(resized_image, selected_boxes, self.zoom_level, all_boxes)

                plot_config = {
                    'displayModeBar': True,
                    'modeBarButtonsToRemove': ['zoom2d', 'select2d', 'lasso2d', 'autoScale2d'],
                    'scrollZoom': True,
                    'doubleClick': 'reset',
                    'responsive': False,  # 关键：禁用响应式，使用固定尺寸
                    'toImageButtonOptions': {
                        'format': 'png',
                        'filename': 'ocr_image',
                        'height': None,  # 使用当前高度
                        'width': None,   # 使用当前宽度
                        'scale': 1
                    }
                }
                
                st.plotly_chart(
                    fig, 
                    width='content',
                    config=plot_config,
                    key=f"{layout_type}_plot"
                )
                        
            except Exception as e:
                st.error(f"❌ 图片处理失败: {e}")
                st.exception(e)
        else:
            st.error("未找到对应的图片文件")
            if self.validator.image_path:
                st.write(f"期望路径: {self.validator.image_path}")

    # st.markdown('</div>', unsafe_allow_html=True)

    def zoom_image(self, image: Image.Image, current_zoom: float) -> Tuple[Image.Image, List[List[int]], List[List[int]]]:
        """缩放图像"""
        # 根据缩放级别调整图片大小
        new_width = int(image.width * current_zoom)
        new_height = int(image.height * current_zoom)
        resized_image = image.resize((new_width, new_height), Image.Resampling.LANCZOS)

        # 计算选中的bbox
        selected_boxes = []
        if st.session_state.selected_text and st.session_state.selected_text in self.validator.text_bbox_mapping:
            info_list = self.validator.text_bbox_mapping[st.session_state.selected_text]
            for info in info_list:
                if 'bbox' in info:
                    bbox = info['bbox']
                    selected_box = [int(coord * current_zoom) for coord in bbox]
                    selected_boxes.append(selected_box)

        # 收集所有框
        all_boxes = []
        if self.show_all_boxes:
            for text, info_list in self.validator.text_bbox_mapping.items():
                for info in info_list:
                    bbox = info['bbox']
                    if len(bbox) >= 4:
                        scaled_bbox = [coord * current_zoom for coord in bbox]
                        all_boxes.append(scaled_bbox)

        return resized_image, all_boxes, selected_boxes

    def _add_bboxes_to_plot(self, fig: go.Figure, bboxes: List[List[int]], image_height: int, 
                           line_color: str = "blue", line_width: int = 1, 
                           fill_color: str = "rgba(0, 100, 200, 0.2)"):
        """
        在plotly图表上添加边界框
        
        Args:
            fig: plotly图表对象
            bboxes: 边界框列表，每个bbox格式为[x1, y1, x2, y2]
            image_height: 图片高度，用于Y轴坐标转换
            line_color: 边框线颜色
            line_width: 边框线宽度
            fill_color: 填充颜色（RGBA格式）
        """
        if not bboxes or len(bboxes) == 0:
            return
            
        for bbox in bboxes:
            if len(bbox) < 4:
                continue
                
            x1, y1, x2, y2 = bbox[:4]
            
            # 转换为Plotly坐标系（翻转Y轴）
            # JSON格式: 原点在左上角, y向下增加
            # Plotly格式: 原点在左下角, y向上增加
            plot_x1 = x1
            plot_x2 = x2
            plot_y1 = image_height - y2  # JSON的y2(底部) -> Plotly的底部
            plot_y2 = image_height - y1  # JSON的y1(顶部) -> Plotly的顶部
            
            fig.add_shape(
                type="rect",
                x0=plot_x1, y0=plot_y1,
                x1=plot_x2, y1=plot_y2,
                line=dict(color=line_color, width=line_width),
                fillcolor=fill_color,
            )

    def create_resized_interactive_plot(self, image: Image.Image, selected_boxes: List[List[int]], 
                                       zoom_level: float, all_boxes: List[List[int]]) -> go.Figure:
        """创建可调整大小的交互式图片 - 修复容器溢出问题"""
        fig = go.Figure()
        
        # 添加图片 - Plotly坐标系，原点在左下角
        fig.add_layout_image(
            dict(
                source=image,
                xref="x", yref="y",
                x=0, y=image.height,  # 图片左下角在Plotly坐标系中的位置
                sizex=image.width, 
                sizey=image.height,
                sizing="stretch", 
                opacity=1.0, 
                layer="below",
                yanchor="top"  # 确保图片顶部对齐
            )
        )
        
        # 显示所有bbox（淡蓝色）
        if all_boxes:
            self._add_bboxes_to_plot(
                fig=fig,
                bboxes=all_boxes,
                image_height=image.height,
                line_color="blue",
                line_width=1,
                fill_color="rgba(0, 100, 200, 0.2)"
            )

        # 高亮显示选中的bbox（红色）
        if selected_boxes:
            self._add_bboxes_to_plot(
                fig=fig,
                bboxes=selected_boxes,
                image_height=image.height,
                line_color="red",
                line_width=3,
                fill_color="rgba(255, 0, 0, 0.3)"
            )
    
        # 修复：优化显示尺寸计算
        max_display_width = 1500
        max_display_height = 1000
        
        # 计算合适的显示尺寸，保持宽高比
        aspect_ratio = image.width / image.height
        
        if self.fit_to_container:
            # 自适应容器模式
            if aspect_ratio > 1:  # 宽图
                display_width = min(max_display_width, image.width)
                display_height = int(display_width / aspect_ratio)
            else:  # 高图
                display_height = min(max_display_height, image.height)
                display_width = int(display_height * aspect_ratio)
            
            # 确保不会太小
            display_width = max(display_width, 800)
            display_height = max(display_height, 600)
        else:
            # 固定尺寸模式，但仍要考虑容器限制
            display_width = min(image.width, max_display_width)
            display_height = min(image.height, max_display_height)
        
        # 设置布局 - 关键修改
        fig.update_layout(
            width=display_width,
            height=display_height,
            
            margin=dict(l=0, r=0, t=0, b=0),
            showlegend=False,
            plot_bgcolor='white',
            dragmode="pan",
            
            # 关键：让图表自适应容器
            # autosize=True,  # 启用自动调整大小
            
            xaxis=dict(
                visible=False,
                range=[0, image.width],
                constrain="domain",
                fixedrange=False,
                autorange=False,
                showgrid=False,
                zeroline=False,
            ),
            
            # 修复：Y轴设置，确保范围正确
            yaxis=dict(
                visible=False,
                range=[0, image.height],  # 确保Y轴范围从0到图片高度
                constrain="domain",
                scaleanchor="x",
                scaleratio=1,
                fixedrange=False,
                autorange=False,
                showgrid=False,
                zeroline=False
            )
        )
        
        return fig