[PATCH 2/2] Add a script to check whether week, first_weekday, first_workday in glibc agrees with CLDR.

Carlos O'Donell carlos@redhat.com
Fri Nov 20 14:31:55 GMT 2026


On 9/23/26 5:38 AM, Mike FABIAN wrote:
> See: https://github.com/unicode-org/cldr/blob/main/common/supplemental/supplementalData.xml
> 
> Run of check script:
> 
> $ ./cldr_week_data_check.py ../../../cldr/common/supplemental/supplementalData.xml '../locales/*_[A-Z][A-Z]'

Note this excludes '@' modifiers?

> $
> 
> If the the data in CLDR and glibc agrees, this script prints nothing.
> 
> If there are differences it prints warnings like for example:
> 
> $ ./cldr_week_data_check.py /local/mfabian/src/cldr/common/supplemental/supplementalData.xml '../locales/*_[A-Z][A-Z]'
> WARNING ru_UA: LC_TIME copied from ru_RU but expected CLDR minDays differs.
> $ ./cldr_week_data_check.py /local/mfabian/src/cldr/common/supplemental/supplementalData.xml '../locales/*_[A-Z][A-Z]'
> WARNING: ru_UA: week MINWEEKLEN = 4, CLDR minDays = 1

Reviewed.

Looking forward to v2.

Assisted-by: LLM

> $
> ---
>   .../unicode-gen/cldr_week_data_check.py       | 258 ++++++++++++++++++
>   1 file changed, 258 insertions(+)
>   create mode 100755 localedata/unicode-gen/cldr_week_data_check.py
> 
> diff --git a/localedata/unicode-gen/cldr_week_data_check.py b/localedata/unicode-gen/cldr_week_data_check.py
> new file mode 100755
> index 0000000000..5dada02603
> --- /dev/null
> +++ b/localedata/unicode-gen/cldr_week_data_check.py
> @@ -0,0 +1,258 @@
> +#!/usr/bin/python3
> +# Copyright (C) 2026 Free Software Foundation, Inc.
> +# Copyright The GNU Toolchain Authors.
> +# This file is part of the GNU C Library.
> +#
> +# The GNU C Library is free software; you can redistribute it and/or
> +# modify it under the terms of the GNU Lesser General Public
> +# License as published by the Free Software Foundation; either
> +# version 2.1 of the License, or (at your option) any later version.
> +#
> +# The GNU C Library is distributed in the hope that it will be useful,
> +# but WITHOUT ANY WARRANTY; without even the implied warranty of
> +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
> +# Lesser General Public License for more details.
> +#
> +# You should have received a copy of the GNU Lesser General Public
> +# License along with the GNU C Library; if not, see
> +# <https://www.gnu.org/licenses/>.
> +'''
> +This script compares the week data in cldr/common/supplemental/supplementalData.xml
> +with the week data in the glibc locales.
> +'''
> +import glob
> +import re
> +import sys
> +import xml.etree.ElementTree as ET
> +from pathlib import Path
> +
> +# CLDR names -> glibc LC_TIME day numbers.
> +# glibc's day list is:
> +#   1 = Sunday
> +#   2 = Monday
> +#   3 = Tuesday
> +#   4 = Wednesday
> +#   5 = Thursday
> +#   6 = Friday
> +#   7 = Saturday
> +DAY_NUMBERS = {
> +    'sun': 1,
> +    'mon': 2,
> +    'tue': 3,
> +    'wed': 4,
> +    'thu': 5,
> +    'fri': 6,
> +    'sat': 7,
> +}
> +
> +def parse_territories(value: str) -> list[str]:
> +    '''Split a CLDR territories attribute into territory codes.'''
> +    return value.split()
> +
> +def parse_week_data(xml_file: Path) -> tuple[
> +    dict[str, int],
> +    dict[str, int],
> +    dict[str, int],
> +    dict[str, int],
> +]:
> +    '''Parse CLDR supplementalData.xml weekData.'''
> +    tree = ET.parse(xml_file)
> +    root = tree.getroot()
> +    week_data = root.find('.//weekData')
> +    if week_data is None:
> +        raise ValueError('Could not find <weekData>')
> +    min_days: dict[str, int] = {}
> +    first_day: dict[str, int] = {}
> +    weekend_start: dict[str, int] = {}
> +    weekend_end: dict[str, int] = {}
> +    for element in week_data:
> +        # Ignore entries such as:
> +        #
> +        #   <firstDay ... alt="variant" .../>
> +        #
> +        # We want the normal/default CLDR data.
> +        if 'alt' in element.attrib:
> +            continue
> +        territories = parse_territories(element.get('territories', ''))
> +        if element.tag == 'minDays':
> +            count = int(element.attrib['count'])
> +            for territory in territories:
> +                min_days[territory] = count
> +        elif element.tag in {'firstDay', 'weekendStart', 'weekendEnd'}:
> +            day = element.attrib['day']
> +            try:
> +                day_number = DAY_NUMBERS[day]
> +            except KeyError as exc:
> +                raise ValueError(f'Unknown CLDR day: {day!r}') from exc
> +            target = {
> +                'firstDay': first_day,
> +                'weekendStart': weekend_start,
> +                'weekendEnd': weekend_end,
> +            }[element.tag]
> +
> +            for territory in territories:
> +                target[territory] = day_number
> +        else:
> +            # Ignore other weekData elements if CLDR adds any in future.
> +            continue
> +    return min_days, first_day, weekend_start, weekend_end
> +
> +def extract_lc_time(text: str) -> str | None:
> +    '''Return the contents of the LC_TIME section.'''
> +    match = re.search(r'(?ms)^LC_TIME\b(.*?)(?=^END LC_TIME\b)', text)
> +    if match is None:
> +        return None
> +    return match.group(1)
> +
> +def parse_lc_time(lc_time: str) -> tuple[str | None, int | None, int | None, int | None]:
> +    '''
> +    Parse copy, week, first_weekday, and first_workday
> +    from an LC_TIME section.
> +
> +    Returns:
> +        (copy_locale, min_days, first_weekday, first_workday)
> +    '''
> +    copy_match = re.search(r'(?m)^\s*copy\s+"([^"]+)"', lc_time)
> +    copy_locale = copy_match.group(1) if copy_match else None
> +    week_match = re.search(r"(?m)^\s*week\s+([^#\n]+)", lc_time)
> +    min_days = None
> +    if week_match:
> +        fields = week_match.group(1).strip().split(";")
> +        if len(fields) != 3:
> +            print('WARNING: malformed week line:', week_match.group(0).strip())
> +        else:
> +            try:
> +                min_days = int(fields[2])
> +            except ValueError:
> +                print('WARNING: invalid MINWEEKLEN in:', week_match.group(0).strip())
> +    first_weekday_match = re.search(r'(?m)^\s*first_weekday\s+(\d+)', lc_time)
> +    first_weekday = (
> +        int(first_weekday_match.group(1))
> +        if first_weekday_match
> +        else None
> +    )
> +    first_workday_match = re.search(r'(?m)^\s*first_workday\s+(\d+)', lc_time)
> +    first_workday = (
> +        int(first_workday_match.group(1))
> +        if first_workday_match
> +        else None
> +    )
> +    return (copy_locale, min_days, first_weekday, first_workday)
> +
> +def expected_value(
> +    values: dict[str, int],
> +    territory: str,
> +) -> int:
> +    '''Get a CLDR value, using territory 001 as the default.'''
> +    return values.get(territory, values['001'])
> +
> +def expected_first_workday(
> +    weekend_end: dict[str, int],
> +    territory: str,
> +) -> int:
> +    '''
> +    The first workday is the day after CLDR weekendEnd.
> +
> +    With glibc day numbers:
> +        Sunday    = 1
> +        ...
> +        Saturday  = 7
> +    '''
> +    end_day = expected_value(weekend_end, territory)
> +    return end_day % 7 + 1
> +
> +def check_locale(
> +    filename: str,
> +    *,
> +    min_days: dict[str, int],
> +    first_day: dict[str, int],
> +    weekend_end: dict[str, int],
> +) -> None:
> +    '''Check one glibc locale file.'''
> +    path = Path(filename)
> +    # For *_CC locale names, the territory is the final two characters.
> +    # Examples:
> +    #   pt_PT -> PT
> +    #   chr_US -> US
> +    #   ber_MA -> MA
> +    territory = path.name[-2:]
> +    text = path.read_text(encoding='utf-8')

OK. Abort if non-UTF-8. We promise UTF-8 today in all locale files.

> +    lc_time = extract_lc_time(text)
> +    if lc_time is None:
> +        print(f'WARNING: {path.name}: no LC_TIME section')
> +        return

If you exit without checking CLDR, this should be printed as a script error.

Suggest:
f'ERROR: ...'

Suggest:
Function should return non-zero exit code and propagate up.

> +    (
> +        copy_locale,
> +        locale_min_days,
> +        locale_first_weekday,
> +        locale_first_workday,
> +    ) = parse_lc_time(lc_time)
> +    expected_min_days = expected_value(min_days, territory)
> +    expected_first_weekday = expected_value(first_day, territory)
> +    expected_workday = expected_first_workday(weekend_end, territory)
> +    if copy_locale is not None:
> +        copy_territory = copy_locale[-2:]

Assumes locale with territory?

> +        if expected_min_days != expected_value(min_days, copy_territory):
> +            print(f'WARNING {path.name}: LC_TIME copied from {copy_locale} but expected CLDR minDays differs.')
> +        if expected_first_weekday != expected_value(first_day, copy_territory):
> +            print(f'WARNING {path.name}: LC_TIME copied from {copy_locale} but expected CLDR firstDay differs.')
> +        if expected_workday != expected_first_workday(weekend_end, copy_territory):
> +            print(f'WARNING {path.name}: LC_TIME copied from {copy_locale} but expected CLDR weekendEnd differs.')

Add ":" to each WARNING for consistent grepping.

> +        return
> +    # Check that all three values exist.
> +    missing = []
> +    if locale_min_days is None:
> +        missing.append('week')
> +    if locale_first_weekday is None:
> +        missing.append('first_weekday')
> +    if locale_first_workday is None:
> +        missing.append('first_workday')
> +    if missing:
> +        print(f'WARNING: {path.name}: missing ' + ', '.join(missing))
> +        return

OK. We return before the CLDR comparison check, but we do that because the script doesn't
assume any default as present in ld-time.c. Which is fine because it keeps the script from
having to track the defaults.

Suggest:
f'ERROR: {path.name}: missing (default used)'

Since this is an error from the script's perspective and we can't recover unless we copy
the defaults into here and compare against them.

Suggest:
Function should return non-zero exit code and propagate up.

> +    if locale_min_days != expected_min_days:
> +        print(f'WARNING: {path.name}: '
> +              f'week MINWEEKLEN = {locale_min_days}, '
> +              f'CLDR minDays = {expected_min_days}')
> +    if locale_first_weekday != expected_first_weekday:
> +        print(f'WARNING: {path.name}: '
> +              f'first_weekday = {locale_first_weekday}, '
> +              f'CLDR firstDay = {expected_first_weekday}')
> +    if locale_first_workday != expected_workday:
> +        print(f'WARNING: {path.name}: '
> +              f'first_workday = {locale_first_workday}, '
> +              f'CLDR weekendEnd implies {expected_workday}')
> +
> +def main() -> None:
> +    if len(sys.argv) != 3:
> +        print(f'usage: {sys.argv[0]} '
> +              "supplementalData.xml 'locales/*_[A-Z][A-Z]'",
> +              file=sys.stderr)
> +        sys.exit(2)
> +    xml_file = Path(sys.argv[1])
> +    locale_pattern = sys.argv[2]
> +    (
> +        min_days,
> +        first_day,
> +        weekend_start,
> +        weekend_end,
> +    ) = parse_week_data(xml_file)
> +    # Make sure CLDR has its 001 defaults.
> +    for name, values in (
> +        ('min_days', min_days),
> +        ('first_day', first_day),
> +        ('weekend_start', weekend_start),
> +        ('weekend_end', weekend_end),
> +    ):
> +        if '001' not in values:
> +            raise ValueError(f'{name} has no CLDR 001 default')

Add comment that glibc doesn't use weekend_start, but that we parse
the CLDR data just to make sure it's well formed.

> +    for filename in sorted(glob.glob(locale_pattern)):
> +        check_locale(
> +            filename,
> +            min_days=min_days,
> +            first_day=first_day,
> +            weekend_end=weekend_end,
> +        )
> +

We should be able to put this into a check and use 0 for success, non-zero for failure.

> +if __name__ == '__main__':
> +    main()


-- 
Cheers,
Carlos.



More information about the Libc-alpha mailing list