docsbuild-scripts/build_docs.py at main · python/docsbuild-scripts · GitHub

History

executable file

1591 lines (1359 loc) · 53.1 KB

Raw

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

371

372

373

374

375

376

377

378

379

380

381

382

383

384

385

386

387

388

389

390

391

392

393

394

395

396

397

398

399

400

401

402

403

404

405

406

407

408

409

410

411

412

413

414

415

416

417

418

419

420

421

422

423

424

425

426

427

428

429

430

431

432

433

434

435

436

437

438

439

440

441

442

443

444

445

446

447

448

449

450

451

452

453

454

455

456

457

458

459

460

461

462

463

464

465

466

467

468

469

470

471

472

473

474

475

476

477

478

479

480

481

482

483

484

485

486

487

488

489

490

491

492

493

494

495

496

497

498

499

500

501

502

503

504

505

506

507

508

509

510

511

512

513

514

515

516

517

518

519

520

521

522

523

524

525

526

527

528

529

530

531

532

533

534

535

536

537

538

539

540

541

542

543

544

545

546

547

548

549

550

551

552

553

554

555

556

557

558

559

560

561

562

563

564

565

566

567

568

569

570

571

572

573

574

575

576

577

578

579

580

581

582

583

584

585

586

587

588

589

590

591

592

593

594

595

596

597

598

599

600

601

602

603

604

605

606

607

608

609

610

611

612

613

614

615

616

617

618

619

620

621

622

623

624

625

626

627

628

629

630

631

632

633

634

635

636

637

638

639

640

641

642

643

644

645

646

647

648

649

650

651

652

653

654

655

656

657

658

659

660

661

662

663

664

665

666

667

668

669

670

671

672

673

674

675

676

677

678

679

680

681

682

683

684

685

686

687

688

689

690

691

692

693

694

695

696

697

698

699

700

701

702

703

704

705

706

707

708

709

710

711

712

713

714

715

716

717

718

719

720

721

722

723

724

725

726

727

728

729

730

731

732

733

734

735

736

737

738

739

740

741

742

743

744

745

746

747

748

749

750

751

752

753

754

755

756

757

758

759

760

761

762

763

764

765

766

767

768

769

770

771

772

773

774

775

776

777

778

779

780

781

782

783

784

785

786

787

788

789

790

791

792

793

794

795

796

797

798

799

800

801

802

803

804

805

806

807

808

809

810

811

812

813

814

815

816

817

818

819

820

821

822

823

824

825

826

827

828

829

830

831

832

833

834

835

836

837

838

839

840

841

842

843

844

845

846

847

848

849

850

851

852

853

854

855

856

857

858

859

860

861

862

863

864

865

866

867

868

869

870

871

872

873

874

875

876

877

878

879

880

881

882

883

884

885

886

887

888

889

890

891

892

893

894

895

896

897

898

899

900

901

902

903

904

905

906

907

908

909

910

911

912

913

914

915

916

917

918

919

920

921

922

923

924

925

926

927

928

929

930

931

932

933

934

935

936

937

938

939

940

941

942

943

944

945

946

947

948

949

950

951

952

953

954

955

956

957

958

959

960

961

962

963

964

965

966

967

968

969

970

971

972

973

974

975

976

977

978

979

980

981

982

983

984

985

986

987

988

989

990

991

992

993

994

995

996

997

998

999

1000

#!/usr/bin/env python3

"""Build the Python docs for various branches and various languages.

Without any arguments builds docs for all active versions and

languages.

Environment variables for:

- `SENTRY_DSN` (Error reporting)

- `FASTLY_SERVICE_ID` / `FASTLY_TOKEN` (CDN purges)

- `PYTHON_DOCS_ENABLE_ANALYTICS` (Enable Plausible for online docs)

are read from the site configuration path for your platform

(/etc/xdg/docsbuild-scripts on linux) if available,

and can be overriden by writing a file to the user config dir

for your platform ($HOME/.config/docsbuild-scripts on linux).

The contents of the file is parsed as toml:

```toml

[env]

SENTRY_DSN = "https://0a0a0a0a0a0a0a0a0a0a0a@sentry.io/69420"

FASTLY_SERVICE_ID = "deadbeefdeadbeefdead"

FASTLY_TOKEN = "secureme!"

PYTHON_DOCS_ENABLE_ANALYTICS = "1"

```

Languages are stored in `config.toml` while versions are discovered

from peps.python.org (generated by `python-releases.toml`).

-q selects "quick build", which means to build only HTML.

Translations are fetched from GitHub repositories according to PEP

545. `--languages` allows selecting translations, like `--languages

en` to just build the English documents.

This script was originally created by Georg Brandl in March 2010.

Modified by Benjamin Peterson to do CDN cache invalidation.

Modified by Julien Palard to build translations.

"""

from __future__ import annotations

import argparse

import concurrent.futures

import dataclasses

import datetime as dt

import filecmp

import json

import logging

import logging.handlers

import os

import re

import shlex

import shutil

import stat

import subprocess

import sys

import venv

from bisect import bisect_left as bisect

from contextlib import contextmanager, suppress

from pathlib import Path

from string import Template

from time import perf_counter, sleep

from urllib.parse import urljoin

import jinja2

import platformdirs

import tomlkit

import urllib3

import zc.lockfile

TYPE_CHECKING = False

if TYPE_CHECKING:

from collections.abc import Collection, Iterator, Sequence, Set

from typing import Literal

try:

from os import EX_OK

from os import EX_SOFTWARE as EX_FAILURE

except ImportError:

EX_OK, EX_FAILURE = 0, 1

try:

import sentry_sdk

except ImportError:

sentry_sdk = None

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

@dataclasses.dataclass(frozen=True, slots=True)

class Versions:

_seq: Sequence[Version]

def __iter__(self) -> Iterator[Version]:

return iter(self._seq)

def __reversed__(self) -> Iterator[Version]:

return reversed(self._seq)

@classmethod

def from_json(cls, data: dict) -> Versions:

"""Load versions from the devguide's JSON representation."""

permitted = ", ".join(sorted(Version.STATUSES | Version.SYNONYMS.keys()))

versions = []

for name, release in data.items():

branch = release["branch"]

status = release["status"]

if status in Version.SKIP_STATUSES:

logging.info("Skipping %s with status %r", name, status)

continue

status = Version.SYNONYMS.get(status, status)

if status not in Version.STATUSES:

logging.warning(

"Saw invalid version status %r, expected to be one of %s. Context: %s",

status,

permitted,

release,

)

continue

versions.append(Version(name=name, status=status, branch_or_tag=branch))

return cls(sorted(versions, key=Version.as_tuple))

def filter(self, branches: Sequence[str] = ()) -> Sequence[Version]:

"""Filter the given versions.

If *branches* is given, only *versions* matching *branches* are returned.

Else all live versions are returned (this means no EOL and no

security-fixes branches).

"""

if branches:

branches = frozenset(branches)

return [v for v in self if {v.name, v.branch_or_tag} & branches]

return [v for v in self if v.status not in {"EOL", "security-fixes"}]

@property

def current_stable(self) -> Version:

"""Find the current stable CPython version."""

return max((v for v in self if v.status == "stable"), key=Version.as_tuple)

@property

def current_dev(self) -> Version:

"""Find the current CPython version in development."""

return max(self, key=Version.as_tuple)

@dataclasses.dataclass(frozen=True, kw_only=True, slots=True)

class Version:

"""Represents a CPython version and its documentation build dependencies."""

name: str

status: Literal[

"in development",

"pre-release",

"stable",

"security-fixes",

"EOL",

]

branch_or_tag: str

STATUSES = {

"in development",

"pre-release",

"stable",

"security-fixes",

"EOL",

}

# Statuses for versions we don't build docs for at all.

SKIP_STATUSES = {"planned"}

# Those synonyms map branch status vocabulary found in the devguide

# with our vocabulary.

SYNONYMS = {

"feature": "in development",

"bugfix": "stable",

"security": "security-fixes",

"end-of-life": "EOL",

"prerelease": "pre-release",

}

def __eq__(self, other: Version) -> bool:

return self.name == other.name

@property

def requirements(self) -> list[str]:

"""Generate the right requirements for this version.

Since CPython 3.8 a Doc/requirements.txt file can be used.

In case the Doc/requirements.txt is absent or wrong (a

sub-dependency broke), use this function to override it.

See https://github.com/python/cpython/issues/91294

See https://github.com/python/cpython/issues/91483

"""

dependencies = [

"-rrequirements.txt",

"jieba", # To improve zh search.

"PyStemmer~=2.2.0", # To improve performance for word stemming.

]

if self.as_tuple() >= (3, 11):

return dependencies

if self.as_tuple() >= (3, 8):

# Restore the imghdr module for Python 3.8-3.10.

# Use setuptools with pkg_resources

return dependencies + ["standard-imghdr", "setuptools<82"]

# Requirements/constraints for Python 3.7 and older, pre-requirements.txt

reqs = [

"alabaster<0.7.12",

"blurb<1.2",

"docutils<=0.17.1",

"jieba",

"jinja2<3.1",

"python-docs-theme<=2023.3.1",

"sphinxcontrib-applehelp<=1.0.2",

"sphinxcontrib-devhelp<=1.0.2",

"sphinxcontrib-htmlhelp<=2.0",

"sphinxcontrib-jsmath<=1.0.1",

"sphinxcontrib-qthelp<=1.0.3",

"sphinxcontrib-serializinghtml<=1.1.5",

"standard-imghdr",

]

if self.name in {"3.7", "3.6", "2.7"}:

return reqs + ["sphinx==2.3.1"]

if self.name == "3.5":

return reqs + ["sphinx==1.8.4", "standard-pipes"]

raise ValueError("unreachable")

@property

def changefreq(self) -> str:

"""Estimate this version change frequency, for the sitemap."""

return {"EOL": "never", "security-fixes": "yearly"}.get(self.status, "daily")

def as_tuple(self) -> tuple[int, ...]:

"""This version name as tuple, for easy comparisons."""

return version_to_tuple(self.name)

@property

def url(self) -> str:

"""The doc URL of this version in production."""

return f"https://docs.python.org/{self.name}/"

@property

def title(self) -> str:

"""The title of this version's doc, for the sidebar."""

return f"Python {self.name} ({self.status})"

@property

def picker_label(self) -> str:

"""Forge the label of a version picker."""

if self.status == "in development":

return f"dev ({self.name})"

if self.status == "pre-release":

return f"pre ({self.name})"

return self.name

@dataclasses.dataclass(frozen=True, slots=True)

class Languages:

_seq: Sequence[Language]

def __iter__(self) -> Iterator[Language]:

return iter(self._seq)

def __reversed__(self) -> Iterator[Language]:

return reversed(self._seq)

@classmethod

def from_json(cls, defaults: dict, languages: dict) -> Languages:

default_translated_name = defaults.get("translated_name", "")

default_in_prod = defaults.get("in_prod", True)

default_sphinxopts = defaults.get("sphinxopts", [])

default_html_only = defaults.get("html_only", False)

langs = [

Language(

iso639_tag=iso639_tag,

name=section["name"],

translated_name=section.get("translated_name", default_translated_name),

in_prod=section.get("in_prod", default_in_prod),

sphinxopts=section.get("sphinxopts", default_sphinxopts),

html_only=section.get("html_only", default_html_only),

)

for iso639_tag, section in languages.items()

]

return cls(langs)

def filter(self, language_tags: Sequence[str] = ()) -> Sequence[Language]:

"""Filter a sequence of languages according to --languages."""

if language_tags:

language_tags = frozenset(language_tags)

return [l for l in self if l.tag in language_tags] # NoQA: E741

return list(self)

@dataclasses.dataclass(order=True, frozen=True, kw_only=True)

class Language:

iso639_tag: str

name: str

translated_name: str

in_prod: bool

sphinxopts: Sequence[str]

html_only: bool = False

@property

def tag(self) -> str:

return self.iso639_tag.replace("_", "-").lower()

@property

def switcher_label(self) -> str:

if self.translated_name:

return f"{self.name} | {self.translated_name}"

return self.name

@dataclasses.dataclass(frozen=True, kw_only=True, slots=True)

class BuildMetadata:

_version: Version

_language: Language

@property

def sphinxopts(self) -> Sequence[str]:

return self._language.sphinxopts

@property

def iso639_tag(self) -> str:

return self._language.iso639_tag

@property

def html_only(self) -> bool:

return self._language.html_only or not self._language.in_prod

@property

def url(self):

"""The URL of this version in production."""

if self.is_translation:

return f"https://docs.python.org/{self.version}/{self.language}/"

return f"https://docs.python.org/{self.version}/"

@property

def branch_or_tag(self) -> str:

return self._version.branch_or_tag

@property

def status(self) -> str:

return self._version.status

@property

def is_eol(self) -> bool:

return self._version.status == "EOL"

@property

def dependencies(self) -> list[str]:

return self._version.requirements

@property

def version(self):

return self._version.name

@property

def version_tuple(self):

return self._version.as_tuple()

@property

def language(self):

return self._language.tag

@property

def is_translation(self):

return self.language != "en"

@property

def slug(self) -> str:

return f"{self.language}/{self.version}"

@property

def venv_name(self) -> str:

return f"venv-{self.version}"

@property

def locale_repo_url(self) -> str:

return f"https://github.com/python/python-docs-{self.language}.git"

def run(

cmd: Sequence[str | Path], cwd: Path | None = None

) -> subprocess.CompletedProcess:

"""Like subprocess.run, with logging before and after the command execution."""

cmd = list(map(str, cmd))

cmdstring = shlex.join(cmd)

logging.debug("Run: '%s'", cmdstring)

result = subprocess.run(

cmd,

cwd=cwd,

stdin=subprocess.PIPE,

stderr=subprocess.STDOUT,

stdout=subprocess.PIPE,

encoding="utf-8",

errors="backslashreplace",

check=False,

)

if result.returncode:

# Log last 20 lines, those are likely the interesting ones.

logging.error(

"Run: '%s' KO:\n%s",

cmdstring,

"\n".join(f" {line}" for line in result.stdout.split("\n")[-20:]),

)

result.check_returncode()

return result

def run_with_logging(cmd: Sequence[str | Path], cwd: Path | None = None) -> None:

"""Like subprocess.check_call, with logging before the command execution."""

cmd = list(map(str, cmd))

logging.debug("Run: '%s'", shlex.join(cmd))

with subprocess.Popen(

cmd,

cwd=cwd,

stdin=subprocess.PIPE,

stderr=subprocess.STDOUT,

stdout=subprocess.PIPE,

encoding="utf-8",

) as p:

try:

for line in p.stdout or ():

logging.debug(">>>> %s", line.rstrip())

except:

p.kill()

raise

if return_code := p.poll():

raise subprocess.CalledProcessError(return_code, cmd[0])

def changed_files(left: Path, right: Path) -> int:

"""Compute the number of different files in the two directory trees."""

def traverse(dircmp_result: filecmp.dircmp) -> int:

changed = len(dircmp_result.diff_files)

changed += sum(map(traverse, dircmp_result.subdirs.values()))

return changed

return traverse(filecmp.dircmp(left, right))

@dataclasses.dataclass

class Repository:

"""Git repository abstraction for our specific needs."""

remote: str

directory: Path

def run(self, *args: str) -> subprocess.CompletedProcess:

"""Run git command in the clone repository."""

return run(("git", "-C", self.directory) + args)

def get_ref(self, pattern: str) -> str:

"""Return the reference of a given tag or branch."""

try:

# Maybe it's a branch

return self.run("show-ref", "-s", f"origin/{pattern}").stdout.strip()

except subprocess.CalledProcessError:

# Maybe it's a tag

return self.run("show-ref", "-s", f"tags/{pattern}").stdout.strip()

def fetch(self) -> subprocess.CompletedProcess:

"""Try (and retry) to run git fetch."""

try:

return self.run("fetch")

except subprocess.CalledProcessError as err:

logging.error("'git fetch' failed (%s), retrying...", err.stderr)

sleep(5)

return self.run("fetch")

def switch(self, branch_or_tag: str) -> None:

"""Reset and cleans the repository to the given branch or tag."""

self.run("reset", "--hard", self.get_ref(branch_or_tag), "--")

self.run("clean", "-dfqx")

def clone(self) -> bool:

"""Maybe clone the repository, if not already cloned."""

if (self.directory / ".git").is_dir():

return False # Already cloned

logging.info("Cloning %s into %s", self.remote, self.directory)

self.directory.mkdir(mode=0o775, parents=True, exist_ok=True)

run(("git", "clone", self.remote, self.directory))

return True

def update(self) -> None:

self.clone() or self.fetch()

def version_to_tuple(version: str) -> tuple[int, ...]:

"""Transform a version string to a tuple, for easy comparisons."""

return tuple(int(part) for part in version.split("."))

def tuple_to_version(version_tuple: tuple[int, ...]) -> str:

"""Reverse version_to_tuple."""

return ".".join(str(part) for part in version_tuple)

def locate_nearest_version(

available_versions: Collection[str], target_version: str

) -> str:

"""Look for the nearest version of target_version in available_versions.

Versions are to be given as tuples, like (3, 7) for 3.7.

>>> locate_nearest_version(["2.7", "3.6", "3.7", "3.8"], "3.9")

'3.8'

>>> locate_nearest_version(["2.7", "3.6", "3.7", "3.8"], "3.5")

'3.6'

>>> locate_nearest_version(["2.7", "3.6", "3.7", "3.8"], "2.6")

'2.7'

>>> locate_nearest_version(["2.7", "3.6", "3.7", "3.8"], "3.10")

'3.8'

>>> locate_nearest_version(["2.7", "3.6", "3.7", "3.8"], "3.7")

'3.7'

"""

available_versions_tuples = sorted(map(version_to_tuple, set(available_versions)))

target_version_tuple = version_to_tuple(target_version)

try:

found = available_versions_tuples[

bisect(available_versions_tuples, target_version_tuple)

]

except IndexError:

found = available_versions_tuples[-1]

return tuple_to_version(found)

@contextmanager

def edit(file: Path):

"""Context manager to edit a file "in place", use it as:

with edit("/etc/hosts") as (i, o):

for line in i:

o.write(line.replace("localhoat", "localhost"))

"""

temporary = file.with_name(file.name + ".tmp")

with suppress(FileNotFoundError):

temporary.unlink()

with open(file, encoding="UTF-8") as input_file:

with open(temporary, "w", encoding="UTF-8") as output_file:

yield input_file, output_file

temporary.rename(file)

@contextmanager

def wait_for_lock(

path: Path, timeout: float = 600, poll_interval: float = 10

) -> Iterator[None]:

"""Context manager to hold *path* as a lock file, waiting up to *timeout* seconds for it."""

deadline = perf_counter() + timeout

while True:

try:

lock = zc.lockfile.LockFile(path)

break

except zc.lockfile.LockError as err:

if perf_counter() >= deadline:

raise TimeoutError(

f"Gave up waiting for lock {path.name} after {timeout} seconds"

) from err

logging.info("Waiting for lock %s...", path.name)

sleep(poll_interval)

try:

yield

finally:

lock.close()

def setup_switchers(script_content: bytes, html_root: Path) -> None:

"""Setup cross-links between CPython versions:

- Cross-link various languages in a language switcher

- Cross-link various versions in a version switcher

"""

switchers_path = html_root / "_static" / "switchers.js"

switchers_path.write_bytes(script_content)

for file in html_root.glob("**/*.html"):

depth = len(file.relative_to(html_root).parts) - 1

src = f"{'../' * depth}_static/switchers.js"

script = f' <script type="text/javascript" src="{src}"></script>\n'

with edit(file) as (ifile, ofile):

for line in ifile:

if line == script:

continue

if line == " </body>\n":

ofile.write(script)

ofile.write(line)

def head(text: str, lines: int = 10) -> str:

"""Return the first *lines* lines from the given text."""

return "\n".join(text.split("\n")[:lines])

def version_info() -> None:

"""Handler for --version."""

try:

platex_version = head(

subprocess.check_output(("platex", "--version"), text=True),

lines=3,

)

except FileNotFoundError:

platex_version = "Not installed."

try:

xelatex_version = head(

subprocess.check_output(("xelatex", "--version"), text=True),

lines=2,

)

except FileNotFoundError:

xelatex_version = "Not installed."

print(

f"""

# platex

{platex_version}

# xelatex

{xelatex_version}

"""

)

@dataclasses.dataclass

class DocBuilder:

"""Builder for a CPython version and a language."""

build_meta: BuildMetadata

cpython_repo: Repository

docs_by_version_content: bytes

switchers_content: bytes

built_venvs: set[Path]

build_root: Path

www_root: Path

select_output: Literal["no-html", "only-html", "only-html-en"] | None

quick: bool

group: str

log_directory: Path

skip_cache_invalidation: bool

theme: str

@property

def html_only(self) -> bool:

return (

self.select_output in {"only-html", "only-html-en"}

or self.quick

or self.build_meta.html_only

)

@property

def includes_html(self) -> bool:

"""Does the build we are running include HTML output?"""

return self.select_output != "no-html"

def run(self, http: urllib3.PoolManager, force_build: bool) -> bool | None:

"""Build and publish a Python doc, for a language, and a version."""

start_time = perf_counter()

start_timestamp = dt.datetime.now(tz=dt.UTC).replace(microsecond=0)

logging.info("Running.")

try:

if self.build_meta.html_only and not self.includes_html:

logging.info("Skipping non-HTML build (language is HTML-only).")

return None # skipped

self.cpython_repo.switch(self.build_meta.branch_or_tag)

if self.build_meta.is_translation:

self.clone_translation()

if trigger_reason := self.should_rebuild(force_build):

self.build_venv()

self.build()

self.copy_build_to_webroot(http)

self.save_state(

build_start=start_timestamp,

build_duration=perf_counter() - start_time,

trigger=trigger_reason,

)

else:

return None # skipped

except TimeoutError as err:

# Another builder held the publish lock for too long; the docs

# were built fine and will be published on the next run.

logging.error("%s", err)

if sentry_sdk:

sentry_sdk.capture_exception(err)

return False

except Exception as err:

logging.exception("Badly handled exception, human, please help.")

if sentry_sdk:

sentry_sdk.capture_exception(err)

return False

return True

@property

def locale_dir(self) -> Path:

return self.build_root / self.build_meta.version / "locale"

@property

def checkout(self) -> Path:

"""Path to CPython git clone."""

return self.build_root / _checkout_name(self.select_output)

def clone_translation(self) -> None:

self.translation_repo.update()

self.translation_repo.switch(self.translation_branch)

@property

def translation_repo(self) -> Repository:

"""See PEP 545 for translations repository naming convention."""

locale_clone_dir = self.locale_dir / self.build_meta.iso639_tag / "LC_MESSAGES"

return Repository(self.build_meta.locale_repo_url, locale_clone_dir)

@property

def translation_branch(self) -> str:

"""Some CPython versions may be untranslated, being either too old or

too new.

This function looks for remote branches on the given repo, and

returns the name of the nearest existing branch.

It could be enhanced to also search for tags.

"""

remote_branches = self.translation_repo.run("branch", "-r").stdout

branches = re.findall(r"/([0-9]+\.[0-9]+)$", remote_branches, re.M)

return locate_nearest_version(branches, self.build_meta.version)

def build(self) -> None:

"""Build this version/language doc."""

logging.info("Build start.")

start_time = perf_counter()

sphinxopts = list(self.build_meta.sphinxopts)

if self.build_meta.is_translation:

sphinxopts.extend((

f"-D locale_dirs={self.locale_dir}",

f"-D language={self.build_meta.iso639_tag}",

"-D gettext_compact=0",

"-D translation_progress_classes=1",

))

if self.build_meta.is_eol:

sphinxopts.append("-D html_context.outdated=1")

if self.build_meta.status in ("in development", "pre-release"):

maketarget = "autobuild-dev"

else:

maketarget = "autobuild-stable"

if self.html_only:

maketarget += "-html"

logging.info("Running make %s", maketarget)

python = self.venv / "bin" / "python"

sphinxbuild = self.venv / "bin" / "sphinx-build"

blurb = self.venv / "bin" / "blurb"

if self.includes_html:

site_url = self.build_meta.url

# Define a tag to enable opengraph socialcards previews

# (used in Doc/conf.py and requires matplotlib)

sphinxopts += (

"-t create-social-cards",

f"-D ogp_site_url={site_url}",

)

if self.build_meta.version_tuple < (3, 8):

# Disable CPython switchers, we handle them now:

text = (self.checkout / "Doc" / "Makefile").read_text(encoding="utf-8")

text = text.replace(" -A switchers=1", "")

(self.checkout / "Doc" / "Makefile").write_text(text, encoding="utf-8")

self.setup_indexsidebar()

if self.build_meta.version_tuple < (3, 10):

# The Makefile is broken, and the fix,

# python/cpython#145571 didn't make it into 3.9 in time

(self.checkout / "Doc" / "dist").mkdir(exist_ok=True)

run_with_logging((

"make",

"-C",

self.checkout / "Doc",

f"PYTHON={python}",

f"SPHINXBUILD={sphinxbuild}",

f"BLURB={blurb}",

f"VENVDIR={self.venv}",

f"SPHINXOPTS={' '.join(sphinxopts)}",

"SPHINXERRORHANDLING=",

maketarget,

))

self.log_directory.mkdir(parents=True, exist_ok=True)

chgrp(self.log_directory, group=self.group, recursive=True)

if self.includes_html:

setup_switchers(

self.switchers_content, self.checkout / "Doc" / "build" / "html"

)

logging.info("Build done (%s).", format_seconds(perf_counter() - start_time))

def build_venv(self) -> None:

"""Build a venv for the specific Python version.

The venv is created at most once per run, reused by later builds

of the same version, and removed at the end of the run: reusing

a venv across runs can silently keep outdated packages, because

pip considers a requirement satisfied when the installed version

number matches, even if the requirement is a direct URL now

pointing at different code.

"""

venv_name = self.build_meta.venv_name

if self.select_output is not None:

# Never share a venv with a concurrent differently-selected

# build, which may recreate it mid-build.

venv_name += f"-{self.select_output}"

venv_path = self.build_root / venv_name

if venv_path in self.built_venvs:

self.venv = venv_path

return

requirements = list(self.build_meta.dependencies)

if self.includes_html:

# opengraph previews

requirements.append("matplotlib>=3")

venv.create(

venv_path,

symlinks=os.name != "nt",

with_pip=True,

clear=True,

upgrade_deps=True,

)

python = venv_path / "bin" / "python"

if (self.checkout / "Doc" / "pylock.toml").is_file():

requirements.remove("-rrequirements.txt")

run(

(python, "-m", "pip", "install", "-rpylock.toml"),

cwd=self.checkout / "Doc",

)

run(

(python, "-m", "pip", "install", self.theme, *requirements),

cwd=self.checkout / "Doc",

)

run((python, "-m", "pip", "freeze", "--all"))

self.built_venvs.add(venv_path)

self.venv = venv_path

def setup_indexsidebar(self) -> None:

"""Copy indexsidebar.html for Sphinx."""

tmpl_src = HERE / "templates"

tmpl_dst = self.checkout / "Doc" / "tools" / "templates"

dbv_path = tmpl_dst / "_docs_by_version.html"

shutil.copy(tmpl_src / "indexsidebar.html", tmpl_dst / "indexsidebar.html")

if not self.build_meta.is_eol:

dbv_path.write_bytes(self.docs_by_version_content)

else:

shutil.copy(tmpl_src / "_docs_by_version.html", dbv_path)

def copy_build_to_webroot(self, http: urllib3.PoolManager) -> None:

"""Copy a given build to the appropriate webroot with appropriate rights."""

logging.info("Publishing start.")

start_time = perf_counter()

self.www_root.mkdir(parents=True, exist_ok=True)

if not self.build_meta.is_translation:

target = self.www_root / self.build_meta.version

else:

language_dir = self.www_root / self.build_meta.language

language_dir.mkdir(parents=True, exist_ok=True)

chgrp(language_dir, group=self.group, recursive=True)

language_dir.chmod(0o775)

target = language_dir / self.build_meta.version

# Builds run concurrently but may publish the same language/version to

# the same directory, so serialise publishes per target.

# Contention is expected, but brief, so wait instead of dying.

with wait_for_lock(

HERE / f"publish-{self.build_meta.language}-{self.build_meta.version}.lock"

target.mkdir(parents=True, exist_ok=True)

try:

target.chmod(0o775)

except PermissionError as err:

logging.warning("Can't change mod of %s: %s", target, str(err))

chgrp(target, group=self.group, recursive=True)

changed = 0

if self.includes_html:

# Copy built HTML files to webroot (default /srv/docs.python.org)

changed += changed_files(

self.checkout / "Doc" / "build" / "html", target

)

logging.info("Copying HTML files to %s", target)

chgrp(

self.checkout / "Doc" / "build" / "html/",

group=self.group,

recursive=True,

)

chmod_make_readable(self.checkout / "Doc" / "build" / "html")

run((

"rsync",

"-a",

"--delete-delay",

"--filter",

"P archives/",

str(self.checkout / "Doc" / "build" / "html") + "/",

target,

))

dist_dir = self.checkout / "Doc" / "dist"

if dist_dir.is_dir():

# Copy archive files to /archives/

logging.debug("Copying dist files.")

chgrp(dist_dir, group=self.group, recursive=True)

chmod_make_readable(dist_dir)

archives_dir = target / "archives"

archives_dir.mkdir(parents=True, exist_ok=True)

archives_dir.chmod(

archives_dir.stat().st_mode | stat.S_IROTH | stat.S_IXOTH

)

chgrp(archives_dir, group=self.group)

changed += 1

for dist_file in dist_dir.iterdir():

shutil.copy2(dist_file, archives_dir / dist_file.name)

changed += 1

logging.info("%s files changed", changed)

if changed and not self.skip_cache_invalidation:

purge_surrogate_key(http, self.build_meta.slug)

logging.info(

"Publishing done (%s).", format_seconds(perf_counter() - start_time)

)

def should_rebuild(self, force: bool) -> str | Literal[False]:

state = self.load_state()

if not state:

logging.info("Should rebuild: no previous state found.")

return "no previous state"

cpython_sha = self.cpython_repo.run("rev-parse", "HEAD").stdout.strip()

if self.build_meta.is_translation:

translation_sha = self.translation_repo.run(

"rev-parse", "HEAD"

).stdout.strip()

if translation_sha != state["translation_sha"]:

logging.info(

"Should rebuild: new translations (from %s to %s)",

state["translation_sha"],

translation_sha,

)

return "new translations"

if cpython_sha != state["cpython_sha"]:

diff = self.cpython_repo.run(

"diff", "--name-only", state["cpython_sha"], cpython_sha

).stdout

if "Doc/" in diff or "Misc/NEWS.d/" in diff:

logging.info(

"Should rebuild: Doc/ has changed (from %s to %s)",

state["cpython_sha"],

cpython_sha,

)

return "Doc/ has changed"

if force:

logging.info("Should rebuild: forced.")

return "forced"

logging.info("Nothing changed, no rebuild needed.")

return False

def load_state(self) -> dict:

if self.select_output is not None:

state_file = self.build_root / f"state-{self.select_output}.toml"

else:

state_file = self.build_root / "state.toml"

try:

return tomlkit.loads(state_file.read_text(encoding="UTF-8"))[

f"/{self.build_meta.slug}/"

]

except (KeyError, FileNotFoundError):

return {}

def save_state(

self, build_start: dt.datetime, build_duration: float, trigger: str

) -> None:

"""Save current CPython sha1 and current translation sha1.

Using this we can deduce if a rebuild is needed or not.

"""

if self.select_output is not None:

state_file = self.build_root / f"state-{self.select_output}.toml"

else:

state_file = self.build_root / "state.toml"

try:

states = tomlkit.parse(state_file.read_text(encoding="UTF-8"))

except FileNotFoundError:

states = tomlkit.document()

View remainder of file in raw view

docsbuild-scripts/build_docs.py at main · python/docsbuild-scripts · GitHub

Uh oh!

Uh oh!

docsbuild-scripts/build_docs.py at main · python/docsbuild-scripts · GitHub

Uh oh!

Uh oh!

Expand file tree

Breadcrumbs

build_docs.py

Latest commit

History

Breadcrumbs

build_docs.py

File metadata and controls