opencc-sys 0.5.0+1.4.0

OpenCC bindings for Rust
Documentation 
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
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131

import json
import os
import zipfile

_this_dir = os.path.dirname(os.path.abspath(__file__))
_opencc_rootdir = os.path.abspath(os.path.join(_this_dir, '..', '..'))
_testcases_path = os.path.join(_opencc_rootdir, 'test', 'testcases', 'testcases.json')

_TEXT_ZIP_CONFIG = """{
  "name": "Python Resource Zip Test",
  "segmentation": {
    "type": "mmseg",
    "dict": {
      "type": "text",
      "file": "STPhrases.txt"
    }
  },
  "conversion_chain": [
    {
      "dict": {
        "type": "group",
        "dicts": [
          {
            "type": "text",
            "file": "STPhrases.txt"
          },
          {
            "type": "text",
            "file": "STCharacters.txt"
          }
        ]
      }
    },
    {
      "dict": {
        "type": "text",
        "file": "TWPhrases.txt"
      }
    }
  ]
}
"""


def _write_resource_zip(path: str) -> None:
    with zipfile.ZipFile(path, 'w', compression=zipfile.ZIP_STORED) as archive:
        archive.writestr('s2twp.json', _TEXT_ZIP_CONFIG)
        archive.writestr('STPhrases.txt', "打印机\t印表機\n")
        archive.writestr('STCharacters.txt', "鼠\t鼠\n标\t標\n")
        archive.writestr('TWPhrases.txt', "鼠標\t滑鼠\n")


def test_import():
    import opencc  # noqa


def test_init_delete_converter():
    import opencc

    for config in opencc.CONFIGS:
        converter = opencc.OpenCC(config)
        del converter


def test_conversion():
    import opencc
    import re
    from collections import defaultdict

    with open(_testcases_path, 'r', encoding='utf-8') as f:
        content = f.read()
    
    # Strip comments and trailing commas
    pattern = re.compile(r'"(?:[^"\\]|\\.)*"|(/\*[\s\S]*?\*/|//.*)|(,\s*(?=[\]}]))')
    clean_content = pattern.sub(lambda m: "" if (m.group(1) or m.group(2)) else m.group(0), content)
    parsed = json.loads(clean_content)

    # Group test cases by configuration
    config_cases = defaultdict(list)
    for case in parsed.get('cases', []):
        input_text = case.get('input')
        expected = case.get('expected', {})
        if not input_text or not isinstance(expected, dict):
            continue
        for cfg, ans in expected.items():
            config_cases[cfg].append((input_text, ans))

    # Run conversions config-by-config, reusing the converter instance
    for cfg, cases in config_cases.items():
        converter = opencc.OpenCC(f'{cfg}.json')
        for input_text, ans in cases:
            assert converter.convert(input_text) == ans, \
                'Failed to convert {} for {} -> {}'.format(cfg, input_text, ans)


def test_include_tofu_risk_dictionaries_option():
    import opencc

    assert opencc.OpenCC('t2s.json').convert('㑮') == '𫝈'
    assert opencc.OpenCC(
        't2s.json',
        include_tofu_risk_dictionaries=False,
    ).convert('㑮') == '㑮'


def test_resource_zip_text_dictionary_support(tmp_path):
    import opencc

    resource_zip = tmp_path / 'opencc-resources.zip'
    _write_resource_zip(str(resource_zip))
    converter = opencc.OpenCC(
        's2twp.json',
        resource_zip=str(resource_zip),
    )
    assert converter.convert('打印机和鼠标') == '印表機和滑鼠'


def test_builtin_config_stem_is_normalized():
    import opencc

    assert opencc.OpenCC('s2t').convert('汉字') == '漢字'


def test_custom_config_path_without_json_extension_is_preserved():
    import opencc

    assert opencc._normalize_config_name('custom-config') == 'custom-config'
    assert opencc._normalize_config_name('custom-config.jsonc') == 'custom-config.jsonc'
    assert opencc._normalize_config_name('./s2t') == './s2t'
    assert opencc._normalize_config_name('configs/s2t') == 'configs/s2t'
    assert opencc._normalize_config_name(r'configs\s2t') == r'configs\s2t'