summaryrefslogtreecommitdiffstats
path: root/modules/freetype2/tests/scripts/download-test-fonts.py
blob: 52b742e22ca616899adc32ddc3308906cb5a8c4d (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
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
#!/usr/bin/env python3

"""Download test fonts used by the FreeType regression test programs.  These
will be copied to $FREETYPE/tests/data/ by default."""

import argparse
import collections
import hashlib
import io
import os
import requests
import sys
import zipfile

from typing import Callable, List, Optional, Tuple

# The list of download items describing the font files to install.  Each
# download item is a dictionary with one of the following schemas:
#
# - File item:
#
#      file_url
#        Type: URL string.
#        Required: Yes.
#        Description: URL to download the file from.
#
#      install_name
#        Type: file name string
#        Required: No
#        Description: Installation name for the font file, only provided if
#          it must be different from the original URL's basename.
#
#      hex_digest
#        Type: hexadecimal string
#        Required: No
#        Description: Digest of the input font file.
#
# - Zip items:
#
#   These items correspond to one or more font files that are embedded in a
#   remote zip archive.  Each entry has the following fields:
#
#      zip_url
#        Type: URL string.
#        Required: Yes.
#        Description: URL to download the zip archive from.
#
#      zip_files
#        Type: List of file entries (see below)
#        Required: Yes
#        Description: A list of entries describing a single font file to be
#          extracted from the archive
#
# Apart from that, some schemas are used for dictionaries used inside
# download items:
#
# - File entries:
#
#   These are dictionaries describing a single font file to extract from an
#   archive.
#
#      filename
#        Type: file path string
#        Required: Yes
#        Description: Path of source file, relative to the archive's
#          top-level directory.
#
#      install_name
#        Type: file name string
#        Required: No
#        Description: Installation name for the font file; only provided if
#          it must be different from the original filename value.
#
#      hex_digest
#        Type: hexadecimal string
#        Required: No
#        Description: Digest of the input source file
#
_DOWNLOAD_ITEMS = [
    {
        "zip_url": "https://github.com/python-pillow/Pillow/files/6622147/As.I.Lay.Dying.zip",
        "zip_files": [
            {
                "filename": "As I Lay Dying.ttf",
                "install_name": "As.I.Lay.Dying.ttf",
                "hex_digest": "ef146bbc2673b387",
            },
        ],
    },
]


def digest_data(data: bytes):
    """Compute the digest of a given input byte string, which are the first
    8 bytes of its sha256 hash."""
    m = hashlib.sha256()
    m.update(data)
    return m.digest()[:8]


def check_existing(path: str, hex_digest: str):
    """Return True if |path| exists and matches |hex_digest|."""
    if not os.path.exists(path) or hex_digest is None:
        return False

    with open(path, "rb") as f:
        existing_content = f.read()

    return bytes.fromhex(hex_digest) == digest_data(existing_content)


def install_file(content: bytes, dest_path: str):
    """Write a byte string to a given destination file.

    Args:
      content: Input data, as a byte string
      dest_path: Installation path
    """
    parent_path = os.path.dirname(dest_path)
    if not os.path.exists(parent_path):
        os.makedirs(parent_path)

    with open(dest_path, "wb") as f:
        f.write(content)


def download_file(url: str, expected_digest: Optional[bytes] = None):
    """Download a file from a given URL.

    Args:
      url: Input URL
      expected_digest: Optional digest of the file
        as a byte string
    Returns:
      URL content as binary string.
    """
    r = requests.get(url, allow_redirects=True)
    content = r.content
    if expected_digest is not None:
        digest = digest_data(r.content)
        if digest != expected_digest:
            raise ValueError(
                "%s has invalid digest %s (expected %s)"
                % (url, digest.hex(), expected_digest.hex())
            )

    return content


def extract_file_from_zip_archive(
    archive: zipfile.ZipFile,
    archive_name: str,
    filepath: str,
    expected_digest: Optional[bytes] = None,
):
    """Extract a file from a given zipfile.ZipFile archive.

    Args:
      archive: Input ZipFile objec.
      archive_name: Archive name or URL, only used to generate a
        human-readable error message.

      filepath: Input filepath in archive.
      expected_digest: Optional digest for the file.
    Returns:
      A new File instance corresponding to the extract file.
    Raises:
      ValueError if expected_digest is not None and does not match the
      extracted file.
    """
    file = archive.open(filepath)
    if expected_digest is not None:
        digest = digest_data(archive.open(filepath).read())
        if digest != expected_digest:
            raise ValueError(
                "%s in zip archive at %s has invalid digest %s (expected %s)"
                % (filepath, archive_name, digest.hex(), expected_digest.hex())
            )
    return file.read()


def _get_and_install_file(
    install_path: str,
    hex_digest: Optional[str],
    force_download: bool,
    get_content: Callable[[], bytes],
) -> bool:
    if not force_download and hex_digest is not None \
      and os.path.exists(install_path):
        with open(install_path, "rb") as f:
            content: bytes = f.read()
        if bytes.fromhex(hex_digest) == digest_data(content):
            return False

    content = get_content()
    install_file(content, install_path)
    return True


def download_and_install_item(
    item: dict, install_dir: str, force_download: bool
) -> List[Tuple[str, bool]]:
    """Download and install one item.

    Args:
      item: Download item as a dictionary, see above for schema.
      install_dir: Installation directory.
      force_download: Set to True to force download and installation, even
        if the font file is already installed with the right content.

    Returns:
      A list of (install_name, status) tuples, where 'install_name' is the
      file's installation name under 'install_dir', and 'status' is a
      boolean that is True to indicate that the file was downloaded and
      installed, or False to indicate that the file is already installed
      with the right content.
    """
    if "file_url" in item:
        file_url = item["file_url"]
        install_name = item.get("install_name", os.path.basename(file_url))
        install_path = os.path.join(install_dir, install_name)
        hex_digest = item.get("hex_digest")

        def get_content():
            return download_file(file_url, hex_digest)

        status = _get_and_install_file(
            install_path, hex_digest, force_download, get_content
        )
        return [(install_name, status)]

    if "zip_url" in item:
        # One or more files from a zip archive.
        archive_url = item["zip_url"]
        archive = zipfile.ZipFile(io.BytesIO(download_file(archive_url)))

        result = []
        for f in item["zip_files"]:
            filename = f["filename"]
            install_name = f.get("install_name", filename)
            hex_digest = f.get("hex_digest")

            def get_content():
                return extract_file_from_zip_archive(
                    archive,
                    archive_url,
                    filename,
                    bytes.fromhex(hex_digest) if hex_digest else None,
                )

            status = _get_and_install_file(
                os.path.join(install_dir, install_name),
                hex_digest,
                force_download,
                get_content,
            )
            result.append((install_name, status))

        return result

    else:
        raise ValueError("Unknown download item schema: %s" % item)


def main():
    parser = argparse.ArgumentParser(description=__doc__)

    # Assume this script is under tests/scripts/ and tests/data/
    # is the default installation directory.
    install_dir = os.path.normpath(
        os.path.join(os.path.dirname(__file__), "..", "data")
    )

    parser.add_argument(
        "--force",
        action="store_true",
        default=False,
        help="Force download and installation of font files",
    )

    parser.add_argument(
        "--install-dir",
        default=install_dir,
        help="Specify installation directory [%s]" % install_dir,
    )

    args = parser.parse_args()

    for item in _DOWNLOAD_ITEMS:
        for install_name, status in download_and_install_item(
            item, args.install_dir, args.force
        ):
            print("%s %s" % (install_name,
                             "INSTALLED" if status else "UP-TO-DATE"))

    return 0


if __name__ == "__main__":
    sys.exit(main())

# EOF