#!/usr/bin/python
# -*-coding:utf-8 -*-

# 本目录下内容相同的文件仅保留首个批量处理脚本，注意不理会文件名，比如a.jpg与b.jpg,就只会保留a.jpg
# 注意，不处理子级目录

import os
import sys

if 2 != len(sys.argv):
    print('请输入要处理目录')
    exit(1)

dir_path = sys.argv.pop()
dir_path = os.path.abspath(dir_path)

if not os.path.isdir(dir_path):
    print('路径必须选择目录类型')
    exit()

dup_append_name = '重复文件.'
dir_name = os.path.basename(dir_path)
os.chdir(dir_path)
fp = os.listdir('.')
dup_num = 0

for p in fp:
    # 文件可能被删除了
    if not os.path.exists(p):
        continue

    if not os.path.isfile(p):
        print('%s 不是文件，跳过' % p)
        continue

    size = os.path.getsize(p)
    max_m = 100

    if size > 1024 * 1024 * max_m:
        print('%s 文件大小 %s 已经超过%sM，不处理' % (p, size, max_m))
        continue

    new_files = os.listdir('.')

    for np in new_files:
        # 当前待比较的文件跳过
        if np == p:
            continue
        fc = pc = None

        # noinspection PyBroadException
        try:
            fc = open(np, 'rb')
            fc_b = fc.read()
            fc.close()
            pc = open(p, 'rb')
            p_b = pc.read()
            pc.close()

            if p_b == fc_b:
                new_rn = '%s%s' % (dup_append_name, np)
                os.rename(np, new_rn)
                print('重复的文件 %s 被重命名成 %s' % (np, new_rn))
                dup_num += 1

        except Exception:
            print('比较内容时出错：')
            raise
        finally:
            if fc:
                # noinspection PyBroadException
                try:
                    fc.close()
                except Exception:
                    pass

            if pc:
                # noinspection PyBroadException
                try:
                    pc.close()
                except Exception:
                    pass

print('发现 %s 个重复文件，重复的文件名前将会被追加"%s"' % (dup_num, dup_append_name))
print('done')