164 lines
5.3 KiB
Python
164 lines
5.3 KiB
Python
"""
|
|
REPL 模式文件内容搜索工具
|
|
支持正则或纯文本搜索，默认搜索当前目录
|
|
"""
|
|
import os
|
|
import re
|
|
import sys
|
|
|
|
# 硬编码排除目录
|
|
EXCLUDE_DIRS = {
|
|
'.git', '.vs', 'node_modules', '__pycache__', '.idea',
|
|
'miniprogram_npm', '_backup_pre_redesign',
|
|
}
|
|
|
|
# 排除的文件扩展名
|
|
EXCLUDE_EXTS = {
|
|
'.png', '.jpg', '.jpeg', '.gif', '.svg', '.ico', '.bmp',
|
|
'.mp3', '.mp4', '.wav', '.avi',
|
|
'.zip', '.rar', '.7z', '.tar', '.gz',
|
|
'.exe', '.dll', '.so', '.dylib',
|
|
'.pyc', '.pyo', '.class', '.o', '.obj',
|
|
'.db', '.sqlite', '.vsidx',
|
|
}
|
|
|
|
# 默认搜索根目录
|
|
DEFAULT_ROOT = os.path.dirname(os.path.abspath(__file__))
|
|
|
|
|
|
def should_skip(dirpath):
|
|
"""判断目录是否应跳过"""
|
|
parts = dirpath.replace('\\', '/').split('/')
|
|
return any(p in EXCLUDE_DIRS for p in parts)
|
|
|
|
|
|
def search(pattern, root=DEFAULT_ROOT, use_regex=True, max_results=50):
|
|
"""搜索文件内容"""
|
|
try:
|
|
if use_regex:
|
|
compiled = re.compile(pattern, re.IGNORECASE)
|
|
except re.error as e:
|
|
print(f' 正则语法错误: {e}')
|
|
return
|
|
|
|
count = 0
|
|
for dirpath, dirnames, filenames in os.walk(root):
|
|
# 就地修改 dirnames 以跳过排除目录
|
|
dirnames[:] = [d for d in dirnames if d not in EXCLUDE_DIRS]
|
|
|
|
for fname in filenames:
|
|
ext = os.path.splitext(fname)[1].lower()
|
|
if ext in EXCLUDE_EXTS:
|
|
continue
|
|
|
|
fpath = os.path.join(dirpath, fname)
|
|
relpath = os.path.relpath(fpath, root)
|
|
try:
|
|
with open(fpath, 'r', encoding='utf-8', errors='ignore') as f:
|
|
for lineno, line in enumerate(f, 1):
|
|
line_stripped = line.rstrip('\n\r')
|
|
if use_regex:
|
|
match = compiled.search(line_stripped)
|
|
if match:
|
|
highlight = line_stripped[:match.start()] + \
|
|
f'>>> {match.group()} <<<' + \
|
|
line_stripped[match.end():]
|
|
print(f' {relpath}:{lineno} {highlight}')
|
|
count += 1
|
|
else:
|
|
if pattern.lower() in line_stripped.lower():
|
|
print(f' {relpath}:{lineno} {line_stripped}')
|
|
count += 1
|
|
|
|
if count >= max_results:
|
|
print(f'\n ... 已达上限 {max_results} 条，停止')
|
|
return
|
|
except (PermissionError, OSError):
|
|
continue
|
|
|
|
if count == 0:
|
|
print(' 未找到匹配内容')
|
|
else:
|
|
print(f'\n 共 {count} 条匹配')
|
|
|
|
|
|
def main():
|
|
print('=== 文件内容搜索工具 ===')
|
|
print(f'搜索根目录: {DEFAULT_ROOT}')
|
|
print(f'排除目录: {EXCLUDE_DIRS}')
|
|
print()
|
|
print('命令:')
|
|
print(' /regex <pattern> 正则搜索')
|
|
print(' /text <text> 纯文本搜索')
|
|
print(' /max <n> 设置结果上限(默认50)')
|
|
print(' /dir <path> 切换搜索目录')
|
|
print(' /help 显示帮助')
|
|
print(' /quit 退出')
|
|
print()
|
|
print('直接输入内容默认使用正则搜索')
|
|
print()
|
|
|
|
root = DEFAULT_ROOT
|
|
use_regex = True
|
|
max_results = 50
|
|
|
|
while True:
|
|
try:
|
|
raw = input('find> ').strip()
|
|
except (EOFError, KeyboardInterrupt):
|
|
print('\n再见')
|
|
break
|
|
|
|
if not raw:
|
|
continue
|
|
|
|
if raw == '/quit':
|
|
print('再见')
|
|
break
|
|
|
|
if raw == '/help':
|
|
print(' /regex <pattern> 正则搜索')
|
|
print(' /text <text> 纯文本搜索')
|
|
print(' /max <n> 设置结果上限')
|
|
print(' /dir <path> 切换搜索目录')
|
|
print(' /help 显示帮助')
|
|
print(' /quit 退出')
|
|
print(' 直接输入内容默认使用正则搜索')
|
|
continue
|
|
|
|
if raw.startswith('/regex '):
|
|
pattern = raw[7:].strip()
|
|
if pattern:
|
|
search(pattern, root, use_regex=True, max_results=max_results)
|
|
continue
|
|
|
|
if raw.startswith('/text '):
|
|
pattern = raw[6:].strip()
|
|
if pattern:
|
|
search(pattern, root, use_regex=False, max_results=max_results)
|
|
continue
|
|
|
|
if raw.startswith('/max '):
|
|
try:
|
|
max_results = int(raw[5:].strip())
|
|
print(f' 结果上限设为 {max_results}')
|
|
except ValueError:
|
|
print(' 请输入数字')
|
|
continue
|
|
|
|
if raw.startswith('/dir '):
|
|
new_dir = raw[5:].strip()
|
|
if os.path.isdir(new_dir):
|
|
root = os.path.abspath(new_dir)
|
|
print(f' 搜索目录切换为: {root}')
|
|
else:
|
|
print(f' 目录不存在: {new_dir}')
|
|
continue
|
|
|
|
# 默认正则搜索
|
|
search(raw, root, use_regex=use_regex, max_results=max_results)
|
|
|
|
|
|
if __name__ == '__main__':
|
|
main()
|