DiskReaderWriter.py 2.03 KB
Newer Older
liukaiwen's avatar
liukaiwen committed
1
2
import os
from magic_pdf.io.AbsReaderWriter import AbsReaderWriter
liukaiwen's avatar
liukaiwen committed
3
from loguru import logger
liukaiwen's avatar
liukaiwen committed
4
5
6
7


MODE_TXT = "text"
MODE_BIN = "binary"
liukaiwen's avatar
liukaiwen committed
8
class DiskReaderWriter(AbsReaderWriter):
liukaiwen's avatar
liukaiwen committed
9

liukaiwen's avatar
liukaiwen committed
10
11
12
13
    def __init__(self, parent_path, encoding='utf-8'):
        self.path = parent_path
        self.encoding = encoding

liukaiwen's avatar
liukaiwen committed
14
15
16
17
18
19
20
21
22
23
    def read(self, path, mode=MODE_TXT):
        if os.path.isabs(path):
            abspath = path
        else:
            abspath = os.path.join(self.path, path)
        if not os.path.exists(abspath):
            logger.error(f"文件 {abspath} 不存在")
            raise Exception(f"文件 {abspath} 不存在")
        if mode == MODE_TXT:
            with open(abspath, 'r', encoding = self.encoding) as f:
liukaiwen's avatar
liukaiwen committed
24
                return f.read()
liukaiwen's avatar
liukaiwen committed
25
26
        elif mode == MODE_BIN:
            with open(abspath, 'rb') as f:
liukaiwen's avatar
liukaiwen committed
27
28
29
30
                return f.read()
        else:
            raise ValueError("Invalid mode. Use 'text' or 'binary'.")

liukaiwen's avatar
liukaiwen committed
31
32
33
34
35
36
37
38
39
    def write(self, content, path, mode=MODE_TXT):
        if os.path.isabs(path):
            abspath = path
        else:
            abspath = os.path.join(self.path, path)
        if mode == MODE_TXT:
            with open(abspath, 'w', encoding=self.encoding) as f:
                f.write(content)
                logger.info(f"内容已成功写入 {abspath}")
liukaiwen's avatar
liukaiwen committed
40

liukaiwen's avatar
liukaiwen committed
41
42
43
44
        elif mode == MODE_BIN:
            with open(abspath, 'wb') as f:
                f.write(content)
                logger.info(f"内容已成功写入 {abspath}")
liukaiwen's avatar
liukaiwen committed
45
46
47
        else:
            raise ValueError("Invalid mode. Use 'text' or 'binary'.")

liukaiwen's avatar
liukaiwen committed
48
49
    def read_jsonl(self, path: str, byte_start=0, byte_end=None, encoding='utf-8'):
        return self.read(path)
liukaiwen's avatar
liukaiwen committed
50
51
52

# 使用示例
if __name__ == "__main__":
liukaiwen's avatar
liukaiwen committed
53
54
    file_path = "io/example.txt"
    drw = DiskReaderWriter("D:\projects\papayfork\Magic-PDF\magic_pdf")
liukaiwen's avatar
liukaiwen committed
55
56

    # 写入内容到文件
liukaiwen's avatar
liukaiwen committed
57
    drw.write(b"Hello, World!", path="io/example.txt", mode="binary")
liukaiwen's avatar
liukaiwen committed
58
59

    # 从文件读取内容
liukaiwen's avatar
liukaiwen committed
60
    content = drw.read(path=file_path)
liukaiwen's avatar
liukaiwen committed
61
    if content:
liukaiwen's avatar
liukaiwen committed
62
        logger.info(f"从 {file_path} 读取的内容: {content}")
liukaiwen's avatar
liukaiwen committed
63
64