http-accept-language.py

import functools
import re

accept_language_re = re.compile(
    r"""
        ([A-Za-z]{1,8}(?:-[A-Za-z0-9]{1,8})*|\*)      # "en", "en-au", "x-y-z", "es-419", "*"
        (?:\s*;\s*q=(0(?:\.\d{,3})?|1(?:\.0{,3})?))?  # Optional "q=1.00", "q=0.8"
        (?:\s*,\s*|$)                                 # Multiple accepts per header.
        """,
    re.VERBOSE,
)


@functools.lru_cache(maxsize=1000)
def parse_accept_lang_header(lang_string):
    """
    Parse the lang_string, which is the body of an HTTP Accept-Language
    header, and return a tuple of (lang, q-value), ordered by 'q' values.
    Return an empty tuple if there are any format errors in lang_string.
    """
    result = []
    pieces = accept_language_re.split(lang_string.lower())
    if pieces[-1]:
        return ()
    for i in range(0, len(pieces) - 1, 3):
        first, lang, priority = pieces[i : i + 3]
        if first:
            return ()
        if priority:
            priority = float(priority)
        else:
            priority = 1.0
        result.append((lang, priority))
    result.sort(key=lambda k: k[1], reverse=True)
    return tuple(result)