diff_text.py

# from difflib import unified_diff
from difflib import SequenceMatcher

SEPERATOR = "\n\n\n=====以下為教案變更內容=====\n\n\n"

def compare_text(text1, text2):
    """
    Compare two text strings and return their differences in a human-readable format.
    
    Args:
        text1 (str): Original text string
        text2 (str): New text string
        
    Returns:
        str: Human-readable formatted differences
    """
    if not text1:
        return text2
    
    if text1 == text2:
        return text2
    
    # Split the texts into lines
    text1_lines = text1.splitlines()
    text2_lines = text2.splitlines()
    
    # Create a more readable diff output
    output = []
    # Add the full text2 content
    output.append(text2)
    
    # Add a separator line
    output.append(SEPERATOR)
    
    
    matcher = SequenceMatcher(None, text1_lines, text2_lines)
    for op, i1, i2, j1, j2 in matcher.get_opcodes():
        # if op == 'equal':
        #     # For unchanged sections, just add them without markers
        #     for line in text2_lines[j1:j2]:
        #         output.append(line)
        if op == 'replace':
            # Show both removed and added content
            output.append("\n【修改前】")
            for line in text1_lines[i1:i2]:
                output.append(f"- {line}")
            output.append("\n【修改後】")
            for line in text2_lines[j1:j2]:
                output.append(f"+ {line}")
        elif op == 'delete':
            # Show removed content
            output.append("\n【已移除】")
            for line in text1_lines[i1:i2]:
                output.append(f"- {line}")
        elif op == 'insert':
            # Show added content
            output.append("\n【新增內容】")
            for line in text2_lines[j1:j2]:
                output.append(f"+ {line}")
    
    return "\n".join(output)

def extract_modified_sections(compared_text):
    """
    Extract the part of the compared text that appears before the SEPERATOR line.
    
    Args:
        compared_text (str): The text returned by compare_text function
        
    Returns:
        str: The content before the SEPERATOR line
    """
    if not compared_text:
        return ""
    
    # Split by the separator and return the first part
    parts = compared_text.split(SEPERATOR, 1)
    if len(parts) > 0:
        return parts[0]
    return ""