Source code for sphinx.builders.gettext

"""
    sphinx.builders.gettext
    ~~~~~~~~~~~~~~~~~~~~~~~

    The MessageCatalogBuilder class.

    :copyright: Copyright 2007-2019 by the Sphinx team, see AUTHORS.
    :license: BSD, see LICENSE for details.
"""

from codecs import open
from collections import defaultdict, OrderedDict
from datetime import datetime, tzinfo, timedelta
from os import path, walk, getenv
from time import time
from typing import Any, Dict, Iterable, Generator, List, Set, Tuple, Union
from uuid import uuid4

from docutils import nodes
from docutils.nodes import Element

from sphinx import addnodes
from sphinx import package_dir
from sphinx.application import Sphinx
from sphinx.builders import Builder
from sphinx.domains.python import pairindextypes
from sphinx.errors import ThemeError
from sphinx.locale import __
from sphinx.util import split_index_msg, logging, status_iterator
from sphinx.util.console import bold  # type: ignore
from sphinx.util.i18n import CatalogInfo, docname_to_domain
from sphinx.util.nodes import extract_messages, traverse_translatable_index
from sphinx.util.osutil import ensuredir, canon_path
from sphinx.util.tags import Tags
from sphinx.util.template import SphinxRenderer

if False:
    # For type annotation
    from typing import DefaultDict  # for python3.5.1

logger = logging.getLogger(__name__)

POHEADER = r"""
# SOME DESCRIPTIVE TITLE.
# Copyright (C) %(copyright)s
# This file is distributed under the same license as the %(project)s package.
# FIRST AUTHOR <[email protected]>, YEAR.
#
#, fuzzy
msgid ""
msgstr ""
"Project-Id-Version: %(project)s %(version)s\n"
"Report-Msgid-Bugs-To: \n"
"POT-Creation-Date: %(ctime)s\n"
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
"Last-Translator: FULL NAME <[email protected]>\n"
"Language-Team: LANGUAGE <[email protected]>\n"
"MIME-Version: 1.0\n"
"Content-Type: text/plain; charset=UTF-8\n"
"Content-Transfer-Encoding: 8bit\n"

"""[1:]  # RemovedInSphinx40Warning


class Message:
    """An entry of translatable message."""
    def __init__(self, text: str, locations: List[Tuple[str, int]], uuids: List[str]):
        self.text = text
        self.locations = locations
        self.uuids = uuids


class Catalog:
    """Catalog of translatable messages."""

    def __init__(self) -> None:
        self.messages = []  # type: List[str]
                            # retain insertion order, a la OrderedDict
        self.metadata = OrderedDict()   # type: Dict[str, List[Tuple[str, int, str]]]
                                        # msgid -> file, line, uid

    def add(self, msg: str, origin: Union[Element, "MsgOrigin"]) -> None:
        if not hasattr(origin, 'uid'):
            # Nodes that are replicated like todo don't have a uid,
            # however i18n is also unnecessary.
            return
        if msg not in self.metadata:  # faster lookup in hash
            self.messages.append(msg)
            self.metadata[msg] = []
        self.metadata[msg].append((origin.source, origin.line, origin.uid))  # type: ignore

    def __iter__(self) -> Generator[Message, None, None]:
        for message in self.messages:
            positions = [(source, line) for source, line, uuid in self.metadata[message]]
            uuids = [uuid for source, line, uuid in self.metadata[message]]
            yield Message(message, positions, uuids)


class MsgOrigin:
    """
    Origin holder for Catalog message origin.
    """

    def __init__(self, source: str, line: int) -> None:
        self.source = source
        self.line = line
        self.uid = uuid4().hex


class GettextRenderer(SphinxRenderer):
    def __init__(self, template_path: str = None) -> None:
        if template_path is None:
            template_path = path.join(package_dir, 'templates', 'gettext')
        super().__init__(template_path)

        def escape(s: str) -> str:
            s = s.replace('\\', r'\\')
            s = s.replace('"', r'\"')
            return s.replace('\n', '\\n"\n"')

        # use texescape as escape filter
        self.env.filters['e'] = escape
        self.env.filters['escape'] = escape


class I18nTags(Tags):
    """Dummy tags module for I18nBuilder.

    To translate all text inside of only nodes, this class
    always returns True value even if no tags are defined.
    """
    def eval_condition(self, condition: Any) -> bool:
        return True


class I18nBuilder(Builder):
    """
    General i18n builder.
    """
    name = 'i18n'
    versioning_method = 'text'
    versioning_compare = None   # type: bool
                                # be set by `gettext_uuid`
    use_message_catalog = False

    def init(self) -> None:
        super().init()
        self.env.set_versioning_method(self.versioning_method,
                                       self.env.config.gettext_uuid)
        self.tags = I18nTags()
        self.catalogs = defaultdict(Catalog)  # type: DefaultDict[str, Catalog]

    def get_target_uri(self, docname: str, typ: str = None) -> str:
        return ''

    def get_outdated_docs(self) -> Set[str]:
        return self.env.found_docs

    def prepare_writing(self, docnames: Set[str]) -> None:
        return

    def compile_catalogs(self, catalogs: Set[CatalogInfo], message: str) -> None:
        return

    def write_doc(self, docname: str, doctree: nodes.document) -> None:
        catalog = self.catalogs[docname_to_domain(docname, self.config.gettext_compact)]

        for toctree in self.env.tocs[docname].traverse(addnodes.toctree):
            for node, msg in extract_messages(toctree):
                node.uid = ''  # type: ignore  # Hack UUID model
                catalog.add(msg, node)

        for node, msg in extract_messages(doctree):
            catalog.add(msg, node)

        if 'index' in self.env.config.gettext_additional_targets:
            # Extract translatable messages from index entries.
            for node, entries in traverse_translatable_index(doctree):
                for typ, msg, tid, main, key_ in entries:
                    for m in split_index_msg(typ, msg):
                        if typ == 'pair' and m in pairindextypes.values():
                            # avoid built-in translated message was incorporated
                            # in 'sphinx.util.nodes.process_index_entry'
                            continue
                        catalog.add(m, node)


# determine tzoffset once to remain unaffected by DST change during build
timestamp = time()
tzdelta = datetime.fromtimestamp(timestamp) - \
    datetime.utcfromtimestamp(timestamp)
# set timestamp from SOURCE_DATE_EPOCH if set
# see https://reproducible-builds.org/specs/source-date-epoch/
source_date_epoch = getenv('SOURCE_DATE_EPOCH')
if source_date_epoch is not None:
    timestamp = float(source_date_epoch)
    tzdelta = timedelta(0)


class LocalTimeZone(tzinfo):
    def __init__(self, *args, **kw) -> None:
        super().__init__(*args, **kw)  # type: ignore
        self.tzdelta = tzdelta

    def utcoffset(self, dt: datetime) -> timedelta:
        return self.tzdelta

    def dst(self, dt: datetime) -> timedelta:
        return timedelta(0)


ltz = LocalTimeZone()


def should_write(filepath: str, new_content: str):
    if not path.exists(filepath):
        return True
    try:
        with open(filepath, encoding='utf-8') as oldpot:
            old_content = oldpot.read()
            old_header_index = old_content.index('"POT-Creation-Date:')
            new_header_index = new_content.index('"POT-Creation-Date:')
            old_body_index = old_content.index('"PO-Revision-Date:')
            new_body_index = new_content.index('"PO-Revision-Date:')
            return ((old_content[:old_header_index] != new_content[:new_header_index]) or
                    (new_content[new_body_index:] != old_content[old_body_index:]))
    except ValueError:
        pass

    return True


[docs]class MessageCatalogBuilder(I18nBuilder): """ Builds gettext-style message catalogs (.pot files). """ name = 'gettext' epilog = __('The message catalogs are in %(outdir)s.') def init(self) -> None: super().init() self.create_template_bridge() self.templates.init(self) def _collect_templates(self) -> Set[str]: template_files = set() for template_path in self.config.templates_path: tmpl_abs_path = path.join(self.app.srcdir, template_path) for dirpath, dirs, files in walk(tmpl_abs_path): for fn in files: if fn.endswith('.html'): filename = canon_path(path.join(dirpath, fn)) template_files.add(filename) return template_files def _extract_from_template(self) -> None: files = list(self._collect_templates()) files.sort() logger.info(bold(__('building [%s]: ') % self.name), nonl=True) logger.info(__('targets for %d template files'), len(files)) extract_translations = self.templates.environment.extract_translations for template in status_iterator(files, __('reading templates... '), "purple", len(files), self.app.verbosity): try: with open(template, encoding='utf-8') as f: context = f.read() for line, meth, msg in extract_translations(context): origin = MsgOrigin(template, line) self.catalogs['sphinx'].add(msg, origin) except Exception as exc: raise ThemeError('%s: %r' % (template, exc)) def build(self, docnames: Iterable[str], summary: str = None, method: str = 'update') -> None: # NOQA self._extract_from_template() super().build(docnames, summary, method) def finish(self) -> None: super().finish() context = { 'version': self.config.version, 'copyright': self.config.copyright, 'project': self.config.project, 'ctime': datetime.fromtimestamp(timestamp, ltz).strftime('%Y-%m-%d %H:%M%z'), 'display_location': self.config.gettext_location, 'display_uuid': self.config.gettext_uuid, } for textdomain, catalog in status_iterator(self.catalogs.items(), __("writing message catalogs... "), "darkgreen", len(self.catalogs), self.app.verbosity, lambda textdomain__: textdomain__[0]): # noop if config.gettext_compact is set ensuredir(path.join(self.outdir, path.dirname(textdomain))) context['messages'] = list(catalog) content = GettextRenderer().render('message.pot_t', context) pofn = path.join(self.outdir, textdomain + '.pot') if should_write(pofn, content): with open(pofn, 'w', encoding='utf-8') as pofile: pofile.write(content)
def setup(app: Sphinx) -> Dict[str, Any]: app.add_builder(MessageCatalogBuilder) app.add_config_value('gettext_compact', True, 'gettext') app.add_config_value('gettext_location', True, 'gettext') app.add_config_value('gettext_uuid', False, 'gettext') app.add_config_value('gettext_auto_build', True, 'env') app.add_config_value('gettext_additional_targets', [], 'env') return { 'version': 'builtin', 'parallel_read_safe': True, 'parallel_write_safe': True, }