Source code for tornado.locale

# Copyright 2009 Facebook
# 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
# 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.

"""Translation methods for generating localized strings.

To load a locale and generate a translated string::

    user_locale = tornado.locale.get("es_LA")
    print(user_locale.translate("Sign out"))

`tornado.locale.get()` returns the closest matching locale, not necessarily the
specific locale you requested. You can support pluralization with
additional arguments to `~Locale.translate()`, e.g.::

    people = [...]
    message = user_locale.translate(
        "%(list)s is online", "%(list)s are online", len(people))
    print(message % {"list": user_locale.list(people)})

The first string is chosen if ``len(people) == 1``, otherwise the second
string is chosen.

Applications should call one of `load_translations` (which uses a simple
CSV format) or `load_gettext_translations` (which uses the ``.mo`` format
supported by `gettext` and related tools).  If neither method is called,
the `Locale.translate` method will simply return the original string.

import codecs
import csv
import datetime
import gettext
import glob
import os
import re

from tornado import escape
from tornado.log import gen_log

from tornado._locale_data import LOCALE_NAMES

from typing import Iterable, Any, Union, Dict, Optional

_default_locale = "en_US"
_translations = {}  # type: Dict[str, Any]
_supported_locales = frozenset([_default_locale])
_use_gettext = False

[docs]def get(*locale_codes: str) -> "Locale": """Returns the closest match for the given locale codes. We iterate over all given locale codes in order. If we have a tight or a loose match for the code (e.g., "en" for "en_US"), we return the locale. Otherwise we move to the next code in the list. By default we return ``en_US`` if no translations are found for any of the specified locales. You can change the default locale with `set_default_locale()`. """ return Locale.get_closest(*locale_codes)
[docs]def set_default_locale(code: str) -> None: """Sets the default locale. The default locale is assumed to be the language used for all strings in the system. The translations loaded from disk are mappings from the default locale to the destination locale. Consequently, you don't need to create a translation file for the default locale. """ global _default_locale global _supported_locales _default_locale = code _supported_locales = frozenset(list(_translations.keys()) + [_default_locale])
[docs]def load_translations(directory: str, encoding: Optional[str] = None) -> None: """Loads translations from CSV files in a directory. Translations are strings with optional Python-style named placeholders (e.g., ``My name is %(name)s``) and their associated translations. The directory should have translation files of the form ``LOCALE.csv``, e.g. ``es_GT.csv``. The CSV files should have two or three columns: string, translation, and an optional plural indicator. Plural indicators should be one of "plural" or "singular". A given string can have both singular and plural forms. For example ``%(name)s liked this`` may have a different verb conjugation depending on whether %(name)s is one name or a list of names. There should be two rows in the CSV file for that string, one with plural indicator "singular", and one "plural". For strings with no verbs that would change on translation, simply use "unknown" or the empty string (or don't include the column at all). The file is read using the `csv` module in the default "excel" dialect. In this format there should not be spaces after the commas. If no ``encoding`` parameter is given, the encoding will be detected automatically (among UTF-8 and UTF-16) if the file contains a byte-order marker (BOM), defaulting to UTF-8 if no BOM is present. Example translation ``es_LA.csv``:: "I love you","Te amo" "%(name)s liked this","A %(name)s les gustó esto","plural" "%(name)s liked this","A %(name)s le gustó esto","singular" .. versionchanged:: 4.3 Added ``encoding`` parameter. Added support for BOM-based encoding detection, UTF-16, and UTF-8-with-BOM. """ global _translations global _supported_locales _translations = {} for path in os.listdir(directory): if not path.endswith(".csv"): continue locale, extension = path.split(".") if not re.match("[a-z]+(_[A-Z]+)?$", locale): gen_log.error( "Unrecognized locale %r (path: %s)", locale, os.path.join(directory, path), ) continue full_path = os.path.join(directory, path) if encoding is None: # Try to autodetect encoding based on the BOM. with open(full_path, "rb") as bf: data = if data in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE): encoding = "utf-16" else: # utf-8-sig is "utf-8 with optional BOM". It's discouraged # in most cases but is common with CSV files because Excel # cannot read utf-8 files without a BOM. encoding = "utf-8-sig" # python 3: csv.reader requires a file open in text mode. # Specify an encoding to avoid dependence on $LANG environment variable. with open(full_path, encoding=encoding) as f: _translations[locale] = {} for i, row in enumerate(csv.reader(f)): if not row or len(row) < 2: continue row = [escape.to_unicode(c).strip() for c in row] english, translation = row[:2] if len(row) > 2: plural = row[2] or "unknown" else: plural = "unknown" if plural not in ("plural", "singular", "unknown"): gen_log.error( "Unrecognized plural indicator %r in %s line %d", plural, path, i + 1, ) continue _translations[locale].setdefault(plural, {})[english] = translation _supported_locales = frozenset(list(_translations.keys()) + [_default_locale]) gen_log.debug("Supported locales: %s", sorted(_supported_locales))
[docs]def load_gettext_translations(directory: str, domain: str) -> None: """Loads translations from `gettext`'s locale tree Locale tree is similar to system's ``/usr/share/locale``, like:: {directory}/{lang}/LC_MESSAGES/{domain}.mo Three steps are required to have your app translated: 1. Generate POT translation file:: xgettext --language=Python --keyword=_:1,2 -d mydomain file2.html etc 2. Merge against existing POT file:: msgmerge old.po mydomain.po > new.po 3. Compile:: msgfmt mydomain.po -o {directory}/pt_BR/LC_MESSAGES/ """ global _translations global _supported_locales global _use_gettext _translations = {} for filename in glob.glob( os.path.join(directory, "*", "LC_MESSAGES", domain + ".mo") ): lang = os.path.basename(os.path.dirname(os.path.dirname(filename))) try: _translations[lang] = gettext.translation( domain, directory, languages=[lang] ) except Exception as e: gen_log.error("Cannot load translation for '%s': %s", lang, str(e)) continue _supported_locales = frozenset(list(_translations.keys()) + [_default_locale]) _use_gettext = True gen_log.debug("Supported locales: %s", sorted(_supported_locales))
[docs]def get_supported_locales() -> Iterable[str]: """Returns a list of all the supported locale codes.""" return _supported_locales
[docs]class Locale(object): """Object representing a locale. After calling one of `load_translations` or `load_gettext_translations`, call `get` or `get_closest` to get a Locale object. """ _cache = {} # type: Dict[str, Locale]
[docs] @classmethod def get_closest(cls, *locale_codes: str) -> "Locale": """Returns the closest match for the given locale code.""" for code in locale_codes: if not code: continue code = code.replace("-", "_") parts = code.split("_") if len(parts) > 2: continue elif len(parts) == 2: code = parts[0].lower() + "_" + parts[1].upper() if code in _supported_locales: return cls.get(code) if parts[0].lower() in _supported_locales: return cls.get(parts[0].lower()) return cls.get(_default_locale)
[docs] @classmethod def get(cls, code: str) -> "Locale": """Returns the Locale for the given locale code. If it is not supported, we raise an exception. """ if code not in cls._cache: assert code in _supported_locales translations = _translations.get(code, None) if translations is None: locale = CSVLocale(code, {}) # type: Locale elif _use_gettext: locale = GettextLocale(code, translations) else: locale = CSVLocale(code, translations) cls._cache[code] = locale return cls._cache[code]
def __init__(self, code: str) -> None: self.code = code = LOCALE_NAMES.get(code, {}).get("name", "Unknown") self.rtl = False for prefix in ["fa", "ar", "he"]: if self.code.startswith(prefix): self.rtl = True break # Initialize strings for date formatting _ = self.translate self._months = [ _("January"), _("February"), _("March"), _("April"), _("May"), _("June"), _("July"), _("August"), _("September"), _("October"), _("November"), _("December"), ] self._weekdays = [ _("Monday"), _("Tuesday"), _("Wednesday"), _("Thursday"), _("Friday"), _("Saturday"), _("Sunday"), ]
[docs] def translate( self, message: str, plural_message: Optional[str] = None, count: Optional[int] = None, ) -> str: """Returns the translation for the given message for this locale. If ``plural_message`` is given, you must also provide ``count``. We return ``plural_message`` when ``count != 1``, and we return the singular form for the given message when ``count == 1``. """ raise NotImplementedError()
def pgettext( self, context: str, message: str, plural_message: Optional[str] = None, count: Optional[int] = None, ) -> str: raise NotImplementedError()
[docs] def format_date( self, date: Union[int, float, datetime.datetime], gmt_offset: int = 0, relative: bool = True, shorter: bool = False, full_format: bool = False, ) -> str: """Formats the given date. By default, we return a relative time (e.g., "2 minutes ago"). You can return an absolute date string with ``relative=False``. You can force a full format date ("July 10, 1980") with ``full_format=True``. This method is primarily intended for dates in the past. For dates in the future, we fall back to full format. .. versionchanged:: 6.4 Aware `datetime.datetime` objects are now supported (naive datetimes are still assumed to be UTC). """ if isinstance(date, (int, float)): date = datetime.datetime.fromtimestamp(date, datetime.timezone.utc) if date.tzinfo is None: date = date.replace(tzinfo=datetime.timezone.utc) now = if date > now: if relative and (date - now).seconds < 60: # Due to click skew, things are some things slightly # in the future. Round timestamps in the immediate # future down to now in relative mode. date = now else: # Otherwise, future dates always use the full format. full_format = True local_date = date - datetime.timedelta(minutes=gmt_offset) local_now = now - datetime.timedelta(minutes=gmt_offset) local_yesterday = local_now - datetime.timedelta(hours=24) difference = now - date seconds = difference.seconds days = difference.days _ = self.translate format = None if not full_format: if relative and days == 0: if seconds < 50: return _("1 second ago", "%(seconds)d seconds ago", seconds) % { "seconds": seconds } if seconds < 50 * 60: minutes = round(seconds / 60.0) return _("1 minute ago", "%(minutes)d minutes ago", minutes) % { "minutes": minutes } hours = round(seconds / (60.0 * 60)) return _("1 hour ago", "%(hours)d hours ago", hours) % {"hours": hours} if days == 0: format = _("%(time)s") elif days == 1 and == and relative: format = _("yesterday") if shorter else _("yesterday at %(time)s") elif days < 5: format = _("%(weekday)s") if shorter else _("%(weekday)s at %(time)s") elif days < 334: # 11mo, since confusing for same month last year format = ( _("%(month_name)s %(day)s") if shorter else _("%(month_name)s %(day)s at %(time)s") ) if format is None: format = ( _("%(month_name)s %(day)s, %(year)s") if shorter else _("%(month_name)s %(day)s, %(year)s at %(time)s") ) tfhour_clock = self.code not in ("en", "en_US", "zh_CN") if tfhour_clock: str_time = "%d:%02d" % (local_date.hour, local_date.minute) elif self.code == "zh_CN": str_time = "%s%d:%02d" % ( ("\u4e0a\u5348", "\u4e0b\u5348")[local_date.hour >= 12], local_date.hour % 12 or 12, local_date.minute, ) else: str_time = "%d:%02d %s" % ( local_date.hour % 12 or 12, local_date.minute, ("am", "pm")[local_date.hour >= 12], ) return format % { "month_name": self._months[local_date.month - 1], "weekday": self._weekdays[local_date.weekday()], "day": str(, "year": str(local_date.year), "time": str_time, }
[docs] def format_day( self, date: datetime.datetime, gmt_offset: int = 0, dow: bool = True ) -> bool: """Formats the given date as a day of week. Example: "Monday, January 22". You can remove the day of week with ``dow=False``. """ local_date = date - datetime.timedelta(minutes=gmt_offset) _ = self.translate if dow: return _("%(weekday)s, %(month_name)s %(day)s") % { "month_name": self._months[local_date.month - 1], "weekday": self._weekdays[local_date.weekday()], "day": str(, } else: return _("%(month_name)s %(day)s") % { "month_name": self._months[local_date.month - 1], "day": str(, }
[docs] def list(self, parts: Any) -> str: """Returns a comma-separated list for the given list of parts. The format is, e.g., "A, B and C", "A and B" or just "A" for lists of size 1. """ _ = self.translate if len(parts) == 0: return "" if len(parts) == 1: return parts[0] comma = " \u0648 " if self.code.startswith("fa") else ", " return _("%(commas)s and %(last)s") % { "commas": comma.join(parts[:-1]), "last": parts[len(parts) - 1], }
[docs] def friendly_number(self, value: int) -> str: """Returns a comma-separated number for the given integer.""" if self.code not in ("en", "en_US"): return str(value) s = str(value) parts = [] while s: parts.append(s[-3:]) s = s[:-3] return ",".join(reversed(parts))
[docs]class CSVLocale(Locale): """Locale implementation using tornado's CSV translation format.""" def __init__(self, code: str, translations: Dict[str, Dict[str, str]]) -> None: self.translations = translations super().__init__(code) def translate( self, message: str, plural_message: Optional[str] = None, count: Optional[int] = None, ) -> str: if plural_message is not None: assert count is not None if count != 1: message = plural_message message_dict = self.translations.get("plural", {}) else: message_dict = self.translations.get("singular", {}) else: message_dict = self.translations.get("unknown", {}) return message_dict.get(message, message) def pgettext( self, context: str, message: str, plural_message: Optional[str] = None, count: Optional[int] = None, ) -> str: if self.translations: gen_log.warning("pgettext is not supported by CSVLocale") return self.translate(message, plural_message, count)
[docs]class GettextLocale(Locale): """Locale implementation using the `gettext` module.""" def __init__(self, code: str, translations: gettext.NullTranslations) -> None: self.ngettext = translations.ngettext self.gettext = translations.gettext # self.gettext must exist before __init__ is called, since it # calls into self.translate super().__init__(code) def translate( self, message: str, plural_message: Optional[str] = None, count: Optional[int] = None, ) -> str: if plural_message is not None: assert count is not None return self.ngettext(message, plural_message, count) else: return self.gettext(message)
[docs] def pgettext( self, context: str, message: str, plural_message: Optional[str] = None, count: Optional[int] = None, ) -> str: """Allows to set context for translation, accepts plural forms. Usage example:: pgettext("law", "right") pgettext("good", "right") Plural message example:: pgettext("organization", "club", "clubs", len(clubs)) pgettext("stick", "club", "clubs", len(clubs)) To generate POT file with context, add following options to step 1 of `load_gettext_translations` sequence:: xgettext [basic options] --keyword=pgettext:1c,2 --keyword=pgettext:1c,2,3 .. versionadded:: 4.2 """ if plural_message is not None: assert count is not None msgs_with_ctxt = ( "%s%s%s" % (context, CONTEXT_SEPARATOR, message), "%s%s%s" % (context, CONTEXT_SEPARATOR, plural_message), count, ) result = self.ngettext(*msgs_with_ctxt) if CONTEXT_SEPARATOR in result: # Translation not found result = self.ngettext(message, plural_message, count) return result else: msg_with_ctxt = "%s%s%s" % (context, CONTEXT_SEPARATOR, message) result = self.gettext(msg_with_ctxt) if CONTEXT_SEPARATOR in result: # Translation not found result = message return result