Python difflib库实现文本差异比较与合并实战指南

import difflib

text1 = "Python is great for data analysis."
text2 = "Python is great for web development and data analysis."

# 创建 SequenceMatcher 对象
matcher = difflib.SequenceMatcher(None, text1, text2)

# 计算相似度比率 (0.0 到 1.0)
ratio = matcher.ratio()
print(f"相似度比率: {ratio:.2f}")  # 输出: 相似度比率: 0.78

# 获取匹配块
# 每个块是一个三元组 (i, j, n)，表示 text1[i:i+n] == text2[j:j+n]
matching_blocks = matcher.get_matching_blocks()
print("匹配块:")
for block in matching_blocks:
    i, j, n = block
    if n:  # 忽略长度为 0 的块
        print(f"  text1[{i}:{i+n}] == text2[{j}:{j+n}] -> '{text1[i:i+n]}'")

a = ["apple", "banana", "cherry", "date"]
b = ["apple", "blueberry", "cherry", "elderberry"]

matcher = difflib.SequenceMatcher(None, a, b)
opcodes = matcher.get_opcodes()

print("操作码 (tag, i1, i2, j1, j2):")
for tag, i1, i2, j1, j2 in opcodes:
    print(f"  {tag:7} a[{i1}:{i2}] -> b[{j1}:{j2}]", end=" ")
    if tag == 'equal':
        print(f" (内容相同: {a[i1:i2]})")
    elif tag == 'replace':
        print(f" (将 {a[i1:i2]} 替换为 {b[j1:j2]})")
    elif tag == 'delete':
        print(f" (删除 {a[i1:i2]})")
    elif tag == 'insert':
        print(f" (插入 {b[j1:j2]})")

from difflib import Differ

text1_lines = [
    "def hello_world():",
    "    print('Hello, World!')",
    "    return True"
]
text2_lines = [
    "def hello_world():",
    "    print('Hello, Python!')",
    "    x = 1 + 2",
    "    return True"
]

d = Differ()
diff = list(d.compare(text1_lines, text2_lines))

print("Differ 比较结果:")
for line in diff:
    # 根据前缀添加颜色或样式（此处用符号表示）
    if line.startswith('-'):
        print(f"\033[91m{line}\033[0m")  # 红色表示删除
    elif line.startswith('+'):
        print(f"\033[92m{line}\033[0m")  # 绿色表示新增
    elif line.startswith('?'):
        print(f"\033[93m{line}\033[0m")  # 黄色表示行内变化提示
    else:
        print(line)

from difflib import unified_diff
import sys

# 假设我们有两个版本的代码片段
original = """def calculate_sum(a, b):
    result = a + b
    print(f"The sum is {result}")
    return result
"""

modified = """def calculate_sum(a, b):
    # 计算两数之和
    total = a + b
    print(f"The sum is {total}")
    return total
"""

diff_lines = unified_diff(
    original.splitlines(keepends=True),
    modified.splitlines(keepends=True),
    fromfile='original.py',
    tofile='modified.py',
    lineterm='\n'  # 确保行尾是换行符
)

print("Unified Diff 格式:")
sys.stdout.writelines(diff_lines)

from difflib import context_diff

diff = context_diff(
    a=original.splitlines(keepends=True),
    b=modified.splitlines(keepends=True),
    fromfile='old_version',
    tofile='new_version',
)

print("Context Diff 格式 (前几行):")
for i, line in enumerate(diff):
    if i > 15:  # 只打印一部分
        break
    print(line, end='')

from difflib import HtmlDiff

html_diff = HtmlDiff(wrapcolumn=60)  # wrapcolumn 可控制换行宽度

# 生成 HTML 表格
html_table = html_diff.make_table(
    fromlines=original.splitlines(),
    tolines=modified.splitlines(),
    fromdesc='原始版本',
    todesc='修改版本',
    context=True,  # 显示上下文
    numlines=3     # 上下文的行数
)

# 生成完整 HTML 页面
full_html = html_diff.make_file(
    fromlines=original.splitlines(),
    tolines=modified.splitlines(),
    fromdesc='Original',
    todesc='Modified'
)

# 将 HTML 保存到文件，方便查看
with open('diff_report.html', 'w', encoding='utf-8') as f:
    f.write(full_html)

print("HTML 差异报告已生成到 'diff_report.html'，请在浏览器中打开查看。")

from difflib import get_close_matches

candidates = ['apple', 'application', 'apply', 'appliance', 'banana', 'cherry']
word = 'appel'

# 找出前3个最相似的词
matches = get_close_matches(word, candidates, n=3, cutoff=0.6)
print(f"与 '{word}' 最相似的词: {matches}")
# 输出: 与 'appel' 最相似的词: ['apple', 'apply', 'application']

# 应用场景：命令行工具的命令纠错
available_commands = ['start', 'stop', 'status', 'restart', 'config']
user_input = 'statu'
suggestion = get_close_matches(user_input, available_commands, n=1, cutoff=0.5)
if suggestion:
    print(f"您想输入的是 '{suggestion[0]}' 吗？")

import difflib
import string

def ignore_punctuation_and_space(s):
    """移除标点和空格"""
    return s.translate(str.maketrans('', '', string.punctuation + ' '))

text1 = "Hello, world!"
text2 = "Hello world"

matcher = difflib.SequenceMatcher(
    lambda x: x in " ,!",  # isjunk 函数：认为空格、逗号、叹号是“垃圾”
    text1,
    text2
)
print(f"忽略部分字符后的相似度: {matcher.ratio():.2f}")  # 可能更高

# 另一种方式：预处理文本
clean1 = ignore_punctuation_and_space(text1)
clean2 = ignore_punctuation_and_space(text2)
matcher2 = difflib.SequenceMatcher(None, clean1, clean2)
print(f"完全清理后的相似度: {matcher2.ratio():.2f}")

#!/usr/bin/env python3
"""
file_diff_tool.py - 一个简单的文件差异比较工具
用法: python file_diff_tool.py <file1> <file2> [--format {unified,context,html}]
"""

import difflib
import argparse
import sys

def compare_files(file1_path, file2_path, diff_format='unified'):
    """比较两个文件并输出差异"""
    try:
        with open(file1_path, 'r', encoding='utf-8') as f1, \
             open(file2_path, 'r', encoding='utf-8') as f2:
            lines1 = f1.readlines()
            lines2 = f2.readlines()
    except FileNotFoundError as e:
        print(f"错误: 文件未找到 - {e}", file=sys.stderr)
        return False
    except UnicodeDecodeError:
        print("错误: 文件编码可能不是 UTF-8，请尝试其他编码。", file=sys.stderr)
        return False

    if diff_format == 'unified':
        diff_lines = difflib.unified_diff(
            lines1, lines2,
            fromfile=file1_path,
            tofile=file2_path,
            lineterm='\n'
        )
        sys.stdout.writelines(diff_lines)
    elif diff_format == 'context':
        diff_lines = difflib.context_diff(
            lines1, lines2,
            fromfile=file1_path,
            tofile=file2_path,
            lineterm='\n'
        )
        sys.stdout.writelines(diff_lines)
    elif diff_format == 'html':
        html_diff = difflib.HtmlDiff()
        html_content = html_diff.make_file(
            lines1, lines2,
            fromdesc=file1_path,
            todesc=file2_path,
            context=True
        )
        output_file = f"diff_{file1_path}_{file2_path}.html"
        with open(output_file, 'w', encoding='utf-8') as f:
            f.write(html_content)
        print(f"HTML 差异报告已生成: {output_file}")
    else:
        print(f"不支持的格式: {diff_format}", file=sys.stderr)
        return False

    return True

def main():
    parser = argparse.ArgumentParser(description='比较两个文本文件的差异')
    parser.add_argument('file1', help='第一个文件路径')
    parser.add_argument('file2', help='第二个文件路径')
    parser.add_argument('--format', choices=['unified', 'context', 'html'],
                        default='unified', help='差异输出格式 (默认: unified)')
    args = parser.parse_args()

    success = compare_files(args.file1, args.file2, args.format)
    sys.exit(0 if success else 1)

if __name__ == '__main__':
    main()

import difflib

# 两段STM32链接脚本文本（和Rust示例一致）
old_text = """STM32 linker script stack config
.stack ALIGN(4) :
{
    _estack = .;
    . += STACK_SIZE;
} > RAM
Support float only
"""

new_text = """STM32 linker script stack config
.stack ALIGN(8) :
{
    _estack = .;
    . += STACK_SIZE;
} > RAM
Support float & double with 8-byte align
"""

# 按行切分成列表
old_lines = old_text.splitlines()
new_lines = new_text.splitlines()

print("=" * 60)
print("1. 简易行对比（ndiff，带 +/- 标记）")
print("=" * 60)
diff_ndiff = difflib.ndiff(old_lines, new_lines)
for line in diff_ndiff:
    # 标记说明：- 删除行、+新增行、 不变行、?字符改动提示
    if line.startswith("-"):
        print(f"\033[31m{line}\033[0m")  # 红色删除
    elif line.startswith("+"):
        print(f"\033[32m{line}\033[0m")  # 绿色新增
    else:
        print(line)

print("\n" + "=" * 60)
print("2. Git风格 unified 补丁格式（可保存为.patch文件）")
print("=" * 60)
# context=2 上下文显示2行
unified_diff = difflib.unified_diff(old_lines, new_lines, fromfile="original.ld", tofile="modified.ld", n=2)
patch_content = "\n".join(unified_diff)
print(patch_content)

# 保存补丁到文件
with open("stack_align.patch", "w", encoding="utf-8") as f:
    f.write(patch_content)
print("\n补丁已保存至 stack_align.patch")

print("\n" + "=" * 60)
print("3. 单行内字符级精细对比（SequenceMatcher）")
print("=" * 60)
# 对比改动行：ALIGN(4) → ALIGN(8)
old_line = ".stack ALIGN(4) :"
new_line = ".stack ALIGN(8) :"
sm = difflib.SequenceMatcher(None, old_line, new_line)

output = []
for tag, i1, i2, j1, j2 in sm.get_opcodes():
    if tag == "equal":
        output.append(old_line[i1:i2])
    elif tag == "delete":
        output.append(f"\033[31;9m{old_line[i1:i2]}\033[0m")
    elif tag == "insert":
        output.append(f"\033[32;1m{new_line[j1:j2]}\033[0m")
    elif tag == "replace":
        output.append(f"\033[31;9m{old_line[i1:i2]}\033[0m")
        output.append(f"\033[32;1m{new_line[j1:j2]}\033[0m")
print("原行对比高亮：", "".join(output))

print("\n" + "=" * 60)
print("4. 生成HTML可视化对比页面")
print("=" * 60)
html_diff = difflib.HtmlDiff(wrapcolumn=80)
html_page = html_diff.make_file(old_lines, new_lines, fromdesc="原始ld脚本", todesc="修改后ld脚本")
with open("diff_view.html", "w", encoding="utf-8") as f:
    f.write(html_page)
print("可视化对比页面已保存 diff_view.html，浏览器打开即可查看")

============================================================
1. 简易行对比（ndiff，带 +/- 标记）
============================================================
  STM32 linker script stack config
- .stack ALIGN(4) :
?              ^
+ .stack ALIGN(8) :
?              ^
  {
      _estack = .;
      . += STACK_SIZE;
  } > RAM
- Support float only
+ Support float & double with 8-byte align
============================================================
2. Git风格 unified 补丁格式（可保存为.patch文件）
============================================================
--- original.ld
+++ modified.ld
@@ -1,7 +1,7 @@
 STM32 linker script stack config
-.stack ALIGN(4) :
+.stack ALIGN(8) :
 {
     _estack = .;
     . += STACK_SIZE;
 } > RAM
-Support float only
+Support float & double with 8-byte align
补丁已保存至 stack_align.patch
============================================================
3. 单行内字符级精细对比（SequenceMatcher）
============================================================
原行对比高亮： .stack ALIGN(48) :
============================================================
4. 生成HTML可视化对比页面
============================================================
可视化对比页面已保存 diff_view.html，浏览器打开即可查看
进程已结束，退出代码为 0