{{ message }}
forked from google/magika
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathcheck_documentation.py
More file actions
370 lines (311 loc) · 12.3 KB
/
Copy pathcheck_documentation.py
File metadata and controls
370 lines (311 loc) · 12.3 KB
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
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
# Copyright 2025 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""Performs a number of sanity checks on Magika's documentation."""
from __future__ import annotations
import json
import re
import sys
from dataclasses import dataclass
from pathlib import Path
import click
import requests
from packaging.version import Version
REPO_ROOT_DIR = Path(__file__).parent.parent.parent
assert REPO_ROOT_DIR.is_dir() and (REPO_ROOT_DIR / ".git").is_dir()
IGNORE_PREFIX_PATTERNS = [
".mypy_cache",
".pytest_cache",
".ruff_cache",
"python/.venv",
"python/dist",
"website/node_modules",
"website/dist",
"js/node_modules",
"js/dist",
"website-ng/node_modules",
"website-ng/dist",
]
@click.command()
@click.option("-v", "--verbose", is_flag=True)
def main(verbose: bool) -> None:
with_errors = False
success = check_versions_are_up_to_date()
if not success:
with_errors = True
success = check_markdown_links(verbose)
if not success:
with_errors = True
if with_errors:
print("There was at least one error.")
sys.exit(1)
print("Everything looks good.")
def check_versions_are_up_to_date() -> bool:
"""Checks that the mentioned latest versions and models are up to date.
Returns True if everything is good, False otherwise."""
# Actual last versions and models
rust_cli_latest_stable_version = get_max_stable_version_for_crate("magika-cli")
rust_lib_latest_stable_version = get_max_stable_version_for_crate("magika")
rust_default_model_name = get_rust_default_model_name()
python_latest_stable_version = get_python_latest_stable_version()
python_default_model_name = get_python_default_model_name()
javascript_latest_stable_version = get_latest_version_for_npm_package("magika")
javascript_default_model_name = get_javascript_default_model_name()
demo_model_name = get_demo_model_name()
expected_table = [
(rust_cli_latest_stable_version, rust_default_model_name),
(python_latest_stable_version, python_default_model_name),
(javascript_latest_stable_version, javascript_default_model_name),
(rust_lib_latest_stable_version, rust_default_model_name),
("-", demo_model_name),
("-", "-"),
]
# Extract documented last versions and models
bindings_overview_path = (
REPO_ROOT_DIR
/ "website-ng"
/ "src"
/ "content"
/ "docs"
/ "cli-and-bindings"
/ "overview.md"
)
assert bindings_overview_path.is_file()
lines = bindings_overview_path.read_text().splitlines()
parsed_table = []
for line in lines:
# This is a hack to parse the table in the binding's overview, but it is
# simple and self-contained enough to not cause problems. And we'll
# notice immediately if things break.
if line.startswith("| ["):
cols = line.split("|")
latest_version = cols[3].strip(" `")
default_model = cols[4].strip()
if default_model != "-":
default_model = default_model.split("]")[0].split("[")[1].strip(" `")
parsed_table.append((latest_version, default_model))
if expected_table == parsed_table:
return True
else:
print(
f"ERROR: Found stale information in binding's overview table:\n{expected_table=}\n{parsed_table=}"
)
return False
def get_python_latest_stable_version() -> str:
res = requests.get("https://pypi.org/pypi/magika/json")
assert res.status_code == 200
latest_stable_version = res.json().get("info", {}).get("version", None)
assert latest_stable_version is not None
return latest_stable_version
def get_python_default_model_name() -> str:
magika_path = REPO_ROOT_DIR / "python" / "src" / "magika" / "magika.py"
return extract_one_match_with_regex_from_file(
magika_path, '_DEFAULT_MODEL_NAME = "([a-zA-Z0-9_]+)"'
)
def get_javascript_default_model_name() -> str:
magika_path = REPO_ROOT_DIR / "js" / "magika.ts"
return extract_one_match_with_regex_from_file(
magika_path, 'static MODEL_VERSION = "([a-zA-Z0-9_]+)";'
)
def get_demo_model_name() -> str:
"""Get the model name used by the demo."""
demo_path = (
REPO_ROOT_DIR / "website-ng" / "src" / "components" / "MagikaDemo.svelte"
)
return extract_one_match_with_regex_from_file(
demo_path, 'const MAGIKA_MODEL_VERSION = "([a-zA-Z0-9_]+)";'
)
def get_rust_default_model_name() -> str:
model_symlink_path = REPO_ROOT_DIR / "rust" / "gen" / "model"
assert model_symlink_path.is_symlink()
return model_symlink_path.readlink().name
def check_markdown_links(verbose: bool) -> bool:
"""Checks that links in Markdown files are OK. Returns True if everything is
good, False otherwise."""
with_errors = False
for path in enumerate_markdown_files_in_dir(Path(".")):
if verbose:
print(f"Analyzing file: {path}")
for ui in extract_uris_infos_from_file(
path,
verbose=verbose,
):
if not ui.is_valid:
with_errors = True
print(
f"ERROR: {path.relative_to(REPO_ROOT_DIR)} has non-valid uri: {ui.uri}"
)
# For python/README.md (which is used on pypi), we also check that
# the URIs are either pointing to an external resource or are pure
# anchors.
if str(path.relative_to(REPO_ROOT_DIR)) == "python/README.md":
if not ui.is_external and not ui.is_pure_anchor:
with_errors = True
print(
f"ERROR: {path.relative_to(REPO_ROOT_DIR)}, in python/, has a non-external uri: {ui.uri}"
)
# Same for js/README.md, which ends up on npm.
if str(path.relative_to(REPO_ROOT_DIR)) == "js/README.md":
if not ui.is_external and not ui.is_pure_anchor:
with_errors = True
print(
f"ERROR: {path.relative_to(REPO_ROOT_DIR)}, in python/, has a non-external uri: {ui.uri}"
)
success = with_errors is False
return success
def enumerate_markdown_files_in_dir(rel_dir: Path) -> list[Path]:
if rel_dir.is_absolute():
print(f"{rel_dir} is not relative")
sys.exit(1)
a_dir = REPO_ROOT_DIR / rel_dir
assert a_dir.is_dir()
paths: list[Path] = []
for path in sorted(a_dir.rglob("*.md")):
should_ignore = False
for exclude_prefix_pattern in IGNORE_PREFIX_PATTERNS:
if str(path.relative_to(REPO_ROOT_DIR)).startswith(exclude_prefix_pattern):
should_ignore = True
break
if not should_ignore:
paths.append(path)
return paths
def extract_uris_infos_from_file(path: Path, verbose: bool) -> list[UriInfo]:
uri_regex = r"\[.*?\]\((.*?)\)"
uris: list[str] = re.findall(uri_regex, path.read_text())
uris_infos: list[UriInfo] = []
for uri in uris:
if verbose:
print(f"Analyzing uri: {uri}")
is_external = uri.startswith("http://") or uri.startswith("https://")
is_valid = None
is_pure_anchor = None
is_insecure = None
if is_external:
# We treat links pointing to our own repo in a special way. For
# simplicity, we only deal with links pointing to the main branch.
repo_main_prefix_url = "https://github.com/google/magika/blob/main/"
if uri.startswith(repo_main_prefix_url):
rel_path = uri.removeprefix(repo_main_prefix_url)
assert rel_path.find("#") == -1, (
"Local links with anchors not supported yet"
)
abs_path = REPO_ROOT_DIR / rel_path
is_valid = abs_path.is_file()
else:
# We mark any other external link as valid, as actually checking
# it's too much of a pain.
is_valid = True
is_pure_anchor = False
if uri.startswith("http://"):
is_insecure = True
print(f"WARNING: {uri} is not using https")
else:
is_insecure = False
else:
is_insecure = False
if uri.startswith("#"):
is_valid = True
is_pure_anchor = True
else:
is_pure_anchor = False
if Path(uri).is_absolute():
website_files_dir = (
REPO_ROOT_DIR
/ "website-ng"
/ "src"
/ "content"
/ "docs"
/ uri.removeprefix("/magika/")
)
md_path = website_files_dir.with_suffix(".md")
mdx_path = website_files_dir.with_suffix(".mdx")
public_path = (
REPO_ROOT_DIR / "website-ng" / "public" / Path(uri).name
)
if (
website_files_dir.is_dir()
or md_path.is_file()
or mdx_path.is_file()
or public_path.is_file()
):
is_valid = True
else:
is_valid = False
else:
if uri.find("#") >= 0:
# This URI is not a pure anchor, but it does have an
# anchor. We remove it so that we can check whether the
# file exists or not.
rel_file_path = uri.split("#")[0]
else:
rel_file_path = uri
abs_path = path.parent / rel_file_path
is_valid = abs_path.is_file() or abs_path.is_dir()
assert is_valid is not None
assert is_pure_anchor is not None
assert is_insecure is not None
uris_infos.append(
UriInfo(
uri=uri,
is_external=is_external,
is_valid=is_valid,
is_pure_anchor=is_pure_anchor,
is_insecure=is_insecure,
)
)
return uris_infos
def get_max_stable_version_for_crate(crate_name: str) -> str:
url = f"https://index.crates.io/{crate_name[0:2]}/{crate_name[2:4]}/{crate_name}"
r = requests.get(url)
assert r.status_code == 200
stable_versions = []
for line in r.text.strip().split("\n"):
if not line:
continue
data = json.loads(line)
if data.get("yanked", False):
continue
v = Version(data["vers"])
if not v.is_prerelease:
stable_versions.append(v)
assert stable_versions
stable_versions.sort()
return str(stable_versions[-1])
def get_latest_version_for_npm_package(package_name: str) -> str:
url = f"https://registry.npmjs.org/{package_name}/latest"
r = requests.get(url)
crate_info = r.json()
return crate_info["version"]
def extract_one_match_with_regex_from_file(path: Path, regex: str) -> str:
"""Extract one (and only one!) match with a regex from a file.
Raises an error in case of zero or more than one hits.
"""
assert path.is_file()
matching_str = None
for line in path.read_text().splitlines():
m = re.fullmatch(regex, line.strip())
if m:
# If we already found something, there is a bug somewhere
assert matching_str is None
matching_str = m.group(1)
assert matching_str is not None
return matching_str
@dataclass(kw_only=True)
class UriInfo:
uri: str
is_external: bool
is_valid: bool
is_pure_anchor: bool
is_insecure: bool
if __name__ == "__main__":
main()
You can’t perform that action at this time.