mirror of
https://github.com/kevinveenbirkenbach/computer-playbook.git
synced 2026-11-09 04:06:42 +00:00
kevinveenbirkenbachandClaude Opus 5
6a23926648
Every version whose tree holds a locale/<code>/LC_MESSAGES/docs.po with at least one translation now gets one site per such language next to the English one, built with `-D language=<code> -D html_copy_source=0` after the English site is published. Sphinx reads one docs.po per language (locale_dirs, gettext_compact = "docs"); YAML pages stay untranslated through an extension that runs before the Locale transform. The deployed working tree is built as the unlisted version `deployed` from a snapshot baked into the image, because the git mirror only holds what is pushed to main. The server answers /<version>/<code>/ and /api/languages/<version>, a language without a site is a 404 rather than the English page, and a switcher on every page lists the built languages and keeps the page path. min_storage grows to 13GB for the translated sites. The 47 docs.po catalogs hold the 24869 documentation messages; German is partially machine-translated so far. The raw-docker and primary-domain lints skip .po files, which carry the Markdown's own commands and hosts as translation sources. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
51 lines
1.8 KiB
Python
51 lines
1.8 KiB
Python
from __future__ import annotations
|
|
|
|
import re
|
|
from pathlib import Path
|
|
from typing import Any
|
|
|
|
from ansible.errors import AnsibleError
|
|
from ansible.plugins.lookup import LookupBase
|
|
|
|
from utils.cache.files import read_text
|
|
from utils.i18n.catalog import catalog_path, read_catalog, translations
|
|
|
|
REWRITTEN = re.compile(r"[*`\[\]!<>|#\"'‘’“”]|--|\.\.\.")
|
|
MINIMUM_LENGTH = 30
|
|
|
|
|
|
class LookupModule(LookupBase):
|
|
"""
|
|
Usage:
|
|
{{ lookup('i18n_sample', 'docs', 'de', 'README.md', 5) }}
|
|
|
|
Returns up to ``count`` translated messages of ``domain`` in language
|
|
``code`` whose source occurs verbatim in the repository file
|
|
``source_file``, as ``{source: translation}``. Messages carrying markup,
|
|
quotes, dashes or ellipses are skipped, because the renderer rewrites
|
|
them and a page could never contain them verbatim.
|
|
"""
|
|
|
|
def run(self, terms, variables: dict[str, Any] | None = None, **kwargs):
|
|
if len(terms) != 4:
|
|
raise AnsibleError(
|
|
"lookup('i18n_sample', domain, code, source_file, count) expects exactly 4 terms"
|
|
)
|
|
domain, code, source_file, count = terms
|
|
root = Path(str((variables or {})["playbook_dir"]))
|
|
text = read_text(str(root / str(source_file)))
|
|
path = catalog_path(root, str(code), str(domain))
|
|
sample: dict[str, str] = {}
|
|
if not path.is_file():
|
|
return [sample]
|
|
for (_, source), target in sorted(translations(read_catalog(path)).items()):
|
|
if (
|
|
len(source) >= MINIMUM_LENGTH
|
|
and source in text
|
|
and not REWRITTEN.search(source + target)
|
|
):
|
|
sample[source] = target
|
|
if len(sample) >= int(count):
|
|
break
|
|
return [sample]
|