aboutsummaryrefslogtreecommitdiff
path: root/src/hydrilla/util/_util.py
blob: 815b7fd1df4eaab7f86583348b106ad2db5feba2 (about) (plain)
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
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
# SPDX-License-Identifier: AGPL-3.0-or-later

# Building Hydrilla packages.
#
# This file is part of Hydrilla
#
# Copyright (C) 2021, 2022 Wojtek Kosior
#
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU Affero General Public License as
# published by the Free Software Foundation, either version 3 of the
# License, or (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU Affero General Public License for more details.
#
# You should have received a copy of the GNU Affero General Public License
# along with this program.  If not, see <https://www.gnu.org/licenses/>.
#
#
# I, Wojtek Kosior, thereby promise not to sue for violation of this
# file's license. Although I request that you do not make use this code
# in a proprietary program, I am not going to enforce this in court.

# Enable using with Python 3.7.
from __future__ import annotations

import re
import json
import locale
import gettext

from pathlib import Path
from typing import Optional, Union

from jsonschema import RefResolver, Draft7Validator

here = Path(__file__).resolve().parent

class UnknownSchemaError(Exception):
    """
    Exception used to record problems with JSON documents for which not even
    the appropriate validation schema could be determined.
    """
    pass

_strip_comment_re = re.compile(r'''
^ # match from the beginning of each line
( # catch the part before '//' comment
  (?: # this group matches either a string or a single out-of-string character
    [^"/] |
    "
    (?: # this group matches any in-a-string character
      [^"\\] |          # match any normal character
      \\[^u] |          # match any escaped character like '\f' or '\n'
      \\u[a-fA-F0-9]{4} # match an escape
    )*
    "
  )*
)
# expect either end-of-line or a comment:
# * unterminated strings will cause matching to fail
# * bad comment (with '/' instead of '//') will be indicated by second group
#   having length 1 instead of 2 or 0
(//?|$)
''', re.VERBOSE)

def strip_json_comments(text: str) -> str:
    """
    Accept JSON text with optional C++-style ('//') comments and return the text
    with comments removed. Consecutive slashes inside strings are handled
    properly. A spurious single slash ('/') shall generate an error. Errors in
    JSON itself shall be ignored.
    """
    processed = 0
    stripped_text = []
    for line in text.split('\n'):
        match = _strip_comment_re.match(line)

        if match is None: # unterminated string
            # ignore this error, let json module report it
            stripped = line
        elif len(match[2]) == 1:
            raise json.JSONDecodeError(_('bad_comment'), text,
                                       processed + len(match[1]))
        else:
            stripped = match[1]

        stripped_text.append(stripped)
        processed += len(line) + 1

    return '\n'.join(stripped_text)

def normalize_version(ver: list[int]) -> list[int]:
    """Strip right-most zeroes from 'ver'. The original list is not modified."""
    new_len = 0
    for i, num in enumerate(ver):
        if num != 0:
            new_len = i + 1

    return ver[:new_len]

def parse_version(ver_str: str) -> list[int]:
    """
    Convert 'ver_str' into an array representation, e.g. for ver_str="4.6.13.0"
    return [4, 6, 13, 0].
    """
    return [int(num) for num in ver_str.split('.')]

def version_string(ver: list[int], rev: Optional[int]=None) -> str:
    """
    Produce version's string representation (optionally with revision), like:
        1.2.3-5
    No version normalization is performed.
    """
    return '.'.join([str(n) for n in ver]) + ('' if rev is None else f'-{rev}')

schemas = {}
for series_dir in (here.parent / 'schemas').glob('*.x'):
    for path in series_dir.glob("*.schema.json"):
        schema = json.loads(path.read_text())
        schemas[schema['$id']] = schema

common_schema_filename = 'common_definitions-1.schema.json'
common_schema_path = here.parent / "schemas" / common_schema_filename

def validator_for(schema: Union[str, dict]) -> Draft7Validator:
    """
    Prepare a validator for the provided schema.

    Other schemas under '../schemas' can be referenced.
    """
    if isinstance(schema, str):
        schema = schemas[f'https://hydrilla.koszko.org/schemas/{schema}']

    resolver = RefResolver(
        base_uri=schema['$id'],
        referrer=schema,
        handlers={'https': lambda uri: schemas[uri]}
    )

    return Draft7Validator(schema, resolver=resolver)

_major_version_re = re.compile(r'''
-
(?P<major>[1-9][0-9]*)
(?: # this repeated group matches the remaining version numbers
  \.
  (?:[1-9][0-9]*|0)
)*
\.schema\.json
$
''', re.VERBOSE)

def load_instance_from_file(path: Path) -> tuple[dict, Optional[int]]:
    """
    Open a file and load its contents as a JSON document (with additional
    '//' comments support). Then parse its "$schema" property (if present)
    and return a tuple of the document instance and the major number of
    schema version.

    If no schema version number can be extracted, None is used instead.
    """
    instance = json.loads(strip_json_comments(path.read_text()))
    major = None

    if type(instance) is dict and type(instance.get('$schema')) is str:
        match = _major_version_re.search(instance.get('$schema'))
        major = match and int(match.group('major'))

    return instance, major

def translation(localedir: Union[Path, str], lang: Optional[str]=None) \
    -> gettext.GNUTranslations:
    """
    Configure translations for domain 'hydrilla-messages' and return the object
    that represents them.

    If `lang` is set, look for translations for `lang`. Otherwise, try to
    determine system's default language and use that.
    """
    # https://stackoverflow.com/questions/3425294/how-to-detect-the-os-default-language-in-python
    # But I am not going to surrender to Microbugs' nonfree, crappy OS to test
    # it, to the lines inside try: may fail.
    if lang is None:
        try:
            from ctypes.windll import kernel32 as windll
            lang = locale.windows_locale[windll.GetUserDefaultUILanguage()]
        except:
            lang = locale.getdefaultlocale()[0] or 'en_US'

    localedir = Path(localedir)
    if not (localedir / lang).is_dir():
        lang = 'en_US'

    return gettext.translation('hydrilla-messages', localedir=localedir,
                               languages=[lang])

_ = translation(here.parent / 'builder' / 'locales').gettext