feat: clean pdf fitz text
This commit is contained in:
		
							parent
							
								
									a88a42799f
								
							
						
					
					
						commit
						ab879ca4b7
					
				@ -1,5 +1,5 @@
 | 
			
		||||
from predict import predict_no_ui
 | 
			
		||||
from toolbox import CatchException, report_execption, write_results_to_file, predict_no_ui_but_counting_down
 | 
			
		||||
from toolbox import CatchException, report_execption, write_results_to_file, predict_no_ui_but_counting_down, clean_text
 | 
			
		||||
fast_debug = False
 | 
			
		||||
 | 
			
		||||
 | 
			
		||||
@ -11,6 +11,7 @@ def 解析PDF(file_manifest, project_folder, top_p, temperature, chatbot, histor
 | 
			
		||||
            file_content = ""
 | 
			
		||||
            for page in doc:
 | 
			
		||||
                file_content += page.get_text()
 | 
			
		||||
            file_content = clean_text(file_content)
 | 
			
		||||
            print(file_content)
 | 
			
		||||
 | 
			
		||||
        prefix = "接下来请你逐文件分析下面的论文文件,概括其内容" if index==0 else ""
 | 
			
		||||
 | 
			
		||||
							
								
								
									
										58
									
								
								toolbox.py
									
									
									
									
									
								
							
							
						
						
									
										58
									
								
								toolbox.py
									
									
									
									
									
								
							@ -235,4 +235,60 @@ def clear_line_break(txt):
 | 
			
		||||
    txt = txt.replace('\n', ' ')
 | 
			
		||||
    txt = txt.replace('  ', ' ')
 | 
			
		||||
    txt = txt.replace('  ', ' ')
 | 
			
		||||
    return txt
 | 
			
		||||
    return txt
 | 
			
		||||
 | 
			
		||||
import re
 | 
			
		||||
import unicodedata
 | 
			
		||||
 | 
			
		||||
def is_paragraph_break(match):
 | 
			
		||||
    """
 | 
			
		||||
    根据给定的匹配结果来判断换行符是否表示段落分隔。
 | 
			
		||||
    如果换行符前为句子结束标志(句号,感叹号,问号),且下一个字符为大写字母,则换行符更有可能表示段落分隔。
 | 
			
		||||
    也可以根据之前的内容长度来判断段落是否已经足够长。
 | 
			
		||||
    """
 | 
			
		||||
    prev_char, next_char = match.groups()
 | 
			
		||||
 | 
			
		||||
    # 句子结束标志
 | 
			
		||||
    sentence_endings = ".!?"
 | 
			
		||||
 | 
			
		||||
    # 设定一个最小段落长度阈值
 | 
			
		||||
    min_paragraph_length = 140
 | 
			
		||||
 | 
			
		||||
    if prev_char in sentence_endings and next_char.isupper() and len(match.string[:match.start(1)]) > min_paragraph_length:
 | 
			
		||||
        return "\n\n" 
 | 
			
		||||
    else:
 | 
			
		||||
        return " "
 | 
			
		||||
 | 
			
		||||
def normalize_text(text):
 | 
			
		||||
    """
 | 
			
		||||
    通过把连字(ligatures)等文本特殊符号转换为其基本形式来对文本进行归一化处理。
 | 
			
		||||
    例如,将连字 "fi" 转换为 "f" 和 "i"。
 | 
			
		||||
    """
 | 
			
		||||
    # 对文本进行归一化处理,分解连字
 | 
			
		||||
    normalized_text = unicodedata.normalize("NFKD", text)
 | 
			
		||||
 | 
			
		||||
    # 替换其他特殊字符
 | 
			
		||||
    cleaned_text = re.sub(r'[^\x00-\x7F]+', '', normalized_text)
 | 
			
		||||
 | 
			
		||||
    return cleaned_text
 | 
			
		||||
 | 
			
		||||
def clean_text(raw_text):
 | 
			
		||||
    """
 | 
			
		||||
    对从 PDF 提取出的原始文本进行清洗和格式化处理。
 | 
			
		||||
    1. 对原始文本进行归一化处理。
 | 
			
		||||
    2. 替换跨行的连词,例如 “Espe-\ncially” 转换为 “Especially”。
 | 
			
		||||
    3. 根据 heuristic 规则判断换行符是否是段落分隔,并相应地进行替换。
 | 
			
		||||
    """
 | 
			
		||||
    # 对文本进行归一化处理
 | 
			
		||||
    normalized_text = normalize_text(raw_text)
 | 
			
		||||
 | 
			
		||||
    # 替换跨行的连词
 | 
			
		||||
    text = re.sub(r'(\w+-\n\w+)', lambda m: m.group(1).replace('-\n', ''), normalized_text)
 | 
			
		||||
 | 
			
		||||
    # 根据前后相邻字符的特点,找到原文本中的换行符
 | 
			
		||||
    newlines = re.compile(r'(\S)\n(\S)')
 | 
			
		||||
 | 
			
		||||
    # 根据 heuristic 规则,用空格或段落分隔符替换原换行符
 | 
			
		||||
    final_text = re.sub(newlines, lambda m: m.group(1) + is_paragraph_break(m) + m.group(2), text)
 | 
			
		||||
 | 
			
		||||
    return final_text.strip()
 | 
			
		||||
		Loading…
	
	
			
			x
			
			
		
	
		Reference in New Issue
	
	Block a user