ocr_verify/comparator/paragraph_comparator.py

from typing import Dict, List
# ✅ 兼容相对导入和绝对导入
try:
    from .text_processor import TextProcessor
    from .similarity_calculator import SimilarityCalculator
except ImportError:
    from text_processor import TextProcessor
    from similarity_calculator import SimilarityCalculator

class ParagraphComparator:
    """段落比较"""
    
    def __init__(self):
        self.text_processor = TextProcessor()
        self.calculator = SimilarityCalculator()
        self.paragraph_match_threshold = 80
        self.content_similarity_threshold = 95
        self.max_paragraph_window = 6
    
    def compare_paragraphs(self, paras1: List[str], paras2: List[str]) -> List[Dict]:
        """改进的段落匹配算法"""
        differences = []
        
        # 预处理
        normalized_paras1 = [self.text_processor.normalize_text_for_comparison(p) for p in paras1]
        normalized_paras2 = [self.text_processor.normalize_text_for_comparison(p) for p in paras2]
        
        original_paras1 = [self.text_processor.strip_markdown_formatting(p) for p in paras1]
        original_paras2 = [self.text_processor.strip_markdown_formatting(p) for p in paras2]
        
        used_paras1 = set()
        used_paras2 = set()
        
        start_index2 = 0
        last_match_index2 = 0
        
        for window_size1 in range(1, min(self.max_paragraph_window, len(normalized_paras1) + 1)):
            for i in range(len(normalized_paras1) - window_size1 + 1):
                if any(idx in used_paras1 for idx in range(i, i + window_size1)):
                    continue
                
                combined_normalized1 = "".join(normalized_paras1[i:i+window_size1])
                combined_original1 = "".join(original_paras1[i:i+window_size1])
                
                best_match = self._find_best_match(
                    combined_normalized1, 
                    normalized_paras2,
                    start_index2,
                    last_match_index2,
                    used_paras2
                )
                
                if best_match and best_match['similarity'] >= self.paragraph_match_threshold:
                    matched_indices = best_match['indices']
                    last_match_index2 = matched_indices[-1]
                    start_index2 = last_match_index2 + 1
                    
                    for idx in range(i, i + window_size1):
                        used_paras1.add(idx)
                    for idx in matched_indices:
                        used_paras2.add(idx)
                    
                    combined_original2 = "".join([original_paras2[idx] for idx in matched_indices])
                    
                    # 检查标点差异
                    punctuation_diffs = self.calculator.check_punctuation_differences(
                        combined_original1, 
                        combined_original2,
                        self.text_processor.normalize_punctuation
                    )
                    
                    if punctuation_diffs:
                        diff_description = []
                        for pdiff in punctuation_diffs:
                            diff_description.append(
                                f"位置{pdiff['position']}: '{pdiff['char1']}' vs '{pdiff['char2']}'"
                            )
                        
                        differences.append({
                            'type': 'paragraph_punctuation',
                            'position': f'段落{i+1}' + (f'-{i+window_size1}' if window_size1 > 1 else ''),
                            'file1_value': combined_original1,
                            'file2_value': combined_original2,
                            'description': f'段落全角半角标点差异: {"; ".join(diff_description)}',
                            'punctuation_differences': punctuation_diffs,
                            'similarity': 100.0,
                            'severity': 'low'
                        })
                    
                    elif best_match['similarity'] < self.content_similarity_threshold:
                        severity = 'low' if best_match['similarity'] >= 90 else 'medium'
                        differences.append({
                            'type': 'paragraph',
                            'position': f'段落{i+1}' + (f'-{i+window_size1}' if window_size1 > 1 else ''),
                            'file1_value': combined_original1,
                            'file2_value': combined_original2,
                            'description': f'段落内容差异 (相似度: {best_match["similarity"]:.1f}%)',
                            'similarity': best_match['similarity'],
                            'severity': severity
                        })
        
        # 处理未匹配的段落
        for i, para in enumerate(original_paras1):
            if i not in used_paras1:
                differences.append({
                    'type': 'paragraph',
                    'position': f'段落{i+1}',
                    'file1_value': para,
                    'file2_value': "",
                    'description': '文件1中独有的段落',
                    'similarity': 0.0,
                    'severity': 'medium'
                })
        
        for j, para in enumerate(original_paras2):
            if j not in used_paras2:
                differences.append({
                    'type': 'paragraph',
                    'position': f'段落{j+1}',
                    'file1_value': "",
                    'file2_value': para,
                    'description': '文件2中独有的段落',
                    'similarity': 0.0,
                    'severity': 'medium'
                })
        
        return differences
    
    def _find_best_match(self, target_text: str, paras2: List[str], 
                        start_index: int, last_match_index: int,
                        used_paras2: set) -> Dict:
        """改进的段落匹配方法"""
        search_start = last_match_index - 1
        unused_count = 0
        
        while search_start >= 0:
            if search_start not in used_paras2:
                unused_count += 1
            if unused_count >= self.max_paragraph_window:
                break
            search_start -= 1
        
        if search_start < 0:
            search_start = 0
            while search_start < start_index and search_start in used_paras2:
                search_start += 1
        
        search_end = min(start_index + self.max_paragraph_window, len(paras2))
        best_match = None
        
        for window_size in range(1, self.max_paragraph_window + 1):
            for j in range(search_start, search_end):
                if any(idx in used_paras2 for idx in range(j, min(j + window_size, len(paras2)))):
                    continue
                
                if j + window_size > len(paras2):
                    break
                
                combined_para2 = "".join(paras2[j:j+window_size])
                
                if target_text == combined_para2:
                    similarity = 100.0
                else:
                    similarity = self.calculator.calculate_text_similarity(target_text, combined_para2)
                
                if not best_match or similarity > best_match['similarity']:
                    best_match = {
                        'text': combined_para2,
                        'similarity': similarity,
                        'indices': list(range(j, j + window_size))
                    }
                    
                    if similarity == 100.0:
                        return best_match
        
        if best_match is None:
            return {
                'text': '',
                'similarity': 0.0,
                'indices': []
            }
        
        return best_match