File size: 3,797 Bytes
7b6ee4d
e84d35a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7b6ee4d
 
e84d35a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d835db2
e84d35a
 
 
 
 
 
 
 
 
7b6ee4d
e84d35a
 
 
 
 
 
 
 
7b6ee4d
e84d35a
 
 
 
 
 
 
 
 
 
 
 
 
 
7b6ee4d
 
 
 
 
e84d35a
 
 
 
 
 
 
 
 
 
 
7b6ee4d
 
e84d35a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
"""Load file content to text.

Check encoding and load a file to text.

Win
Linux
    apt install libmagic1

py -3.8 -m pip install python-magic-bin
py -3.8 -m pip install python-magic

import magic
magic.from_file("testdata/test.pdf")

original load_textrev
refer to load_paras.py
"""
# pylint: disable=line-too-long, unused-variable, unused-import

from typing import Optional, Union  # noqa
from pathlib import Path
import cchardet

from logzero import logger

# from detect_file import detect_file


def loadtext(filepath: Union[Path, str] = "") -> str:
    """Load file context to text.

    Check encoding and load a file to text.
    """
    filepath = Path(filepath)
    if not filepath.is_file():
        logger.error(" file [%s] does not exist or is not a file.", filepath)
        # return None
        raise Exception(f" file [{filepath}] does not exist or is not a file.")

    # encoding = detect_file(filepath)
    encoding = cchardet.detect(filepath.read_bytes()).get("encoding", "utf8")

    if encoding is None:
        raise Exception("cchardet.detect says it's not a text file.")

    # cchardet: 'GB18030', no need for errors="ignore"
    try:
        text = filepath.read_text(encoding=encoding, errors="ignore")
    except Exception as exc:
        logger.error(" Opening %s resulted in errors: %s", filepath, exc)
        raise

    return text


def test1():
    r"""Tests default file.

    defaultdir = r'D:\dl\Dropbox\mat-dir\snippets-mat\pyqt'
    defaultfile = r'notes pyqt tkinter tktable.txt'
    """
    text = loadtext()
    # eq_(2283, len(text))
    # eq_(2283, len(text))

    # del text
    if text:
        assert len(text) == 86423


def testgb():
    r"""Tests shuangyu_ku\txt-books\19部世界名著中英文对照版TXT."""
    file = (
        r"C:\dl\Dropbox\shuangyu_ku\txt-books\19部世界名著中英文对照版TXT"
        r"\爱丽丝漫游奇境记.txt"
    )
    text = loadtext(file)
    if text:
        # assert len(text) == 190913
        assert len(text) == 188760

    text0 = "ALICE'S ADVENTURES IN WONDERLAND\n CHAPTER  01  Down the Rabbit-Hole\n CHAPTER  02  The Pool of Tears\n CHAPTER  03  A Caucus-Race and a Long Tale\n CHAPTER  04  The Rabbit Sends in a Little Bill\n CHAPTER  05  Advice from a Caterpillar\n CHAPTER  06  Pig and Pepper\n CHAPTER  07  A Mad Tea-Party\n CHAPTER  08  The Queen's Croquet-Ground\n CHAPTER  09  The Mock Turtle's Story \n CHAPTER  10  The Lobster Quadrille\n CHAPTER  11  Who Stole the Tarts?\n CHAPTER  12  Alice's Evidence\n\n\n 爱 丽 丝 漫 游 奇 境 记 \n\n 第01章 "  # NOQA

    if text:
        assert text0 == text[:500]


def test_utf_16le():
    r"""Test  'E:\\beta_final_version\\build\\test_files\\files_for_testing_import\\Folding_Beijing_12.txt'."""
    # file = 'E:\\beta_final_version\\build\\test_files\\files_for_testing_import\\Folding_Beijing_12.txt'  # NOQA
    file = r"C:\dl\Dropbox\mat-dir\snippets-mat\pyqt\Sandbox\hp_beta-version_files\test_files\files_for_testing_import\Folding_Beijing_12.txt"  # NOQA
    file = r"C:\dl\Dropbox\mat-dir\pyqt\Sandbox\hp_beta-version_files\test_files\files_for_testing_import\Folding_Beijing_12.txt"

    text = loadtext(file)
    if text:
        assert len(text) == 117871

    # text0 = '\ufeffFolding Beijing\t北京折叠\n"by Hao Jingfang, translated by Ken Liu"\t郝景芳\n# 1.\t# 1\n"At ten of five in the m'  # NOQA
    text0 = r'Folding Beijing\t北京折叠\n"by Hao Jingfang, translated by Ken Liu"\t郝景芳\n# 1.\t# 1\n"At ten of five in the mo'  # NOQA
    text2 = 'Folding Beijing\t\xe5\x8c\x97\xe4\xba\xac\xe6\x8a\x98\xe5\x8f\xa0\r\n"by Hao Jingfang, translated by Ken Liu"\t\xe9\x83\x9d\xe6\x99\xaf\xe8\x8a\xb3\r\n# 1.\t# 1\r\n"At ten of five in the mo'

    del text2

    # if text: assert text0 == text[:100]