codon/stdlib/getopt.codon

"""
Parser for command line options.

This module helps scripts to parse the command line arguments in
sys.argv.  It supports the same conventions as the Unix getopt()
function (including the special meanings of arguments of the form `-'
and `--').  Long options similar to those supported by GNU software
may be used as well via an optional third argument.  This module
provides two functions and an exception:

getopt() -- Parse command line options
gnu_getopt() -- Like getopt(), but allow option and non-option arguments
to be intermixed.
GetoptError -- exception (class) raised with 'opt' attribute, which is the
option involved with the exception.

Adapted from https://raw.githubusercontent.com/python/cpython/2.7/Lib/getopt.py
"""

import os


class GetoptError:
    _hdr: ExcHeader

    def __init__(self):
        self._hdr = ('GetoptError', '', '', '', 0, 0)

    def __init__(self, message: str):
        self._hdr = ('GetoptError', message, '', '', 0, 0)

    @property
    def message(self):
        return self._hdr.msg


# Return:
#   has_arg?
#   full option name
def long_has_args(opt: str, longopts: List[str]):
    possibilities = [o for o in longopts if o.startswith(opt)]
    if not possibilities:
        raise GetoptError(f'option --{opt} not recognized')
    # Is there an exact match?
    if opt in possibilities:
        return False, opt
    elif opt + '=' in possibilities:
        return True, opt
    # No exact match, so better be unique.
    if len(possibilities) > 1:
        # XXX since possibilities contains all valid continuations, might be
        # nice to work them into the error msg
        raise GetoptError(f'option --{opt} not a unique prefix')
    assert len(possibilities) == 1
    unique_match = possibilities[0]
    has_arg = unique_match.endswith('=')
    if has_arg:
        unique_match = unique_match[:-1]
    return has_arg, unique_match


def do_longs(opts: List[Tuple[str, str]], opt: str, longopts: List[str], args: List[str]):
    optarg = ""
    try:
        i = opt.index('=')
        opt, optarg = opt[:i], opt[i+1:]
    except ValueError:
        pass

    has_arg, opt = long_has_args(opt, longopts)
    if has_arg:
        if optarg == "":
            if not args:
                raise GetoptError(f'option --{opt} requires argument')
            optarg, args = args[0], args[1:]
    elif optarg != "":
        raise GetoptError(f'option --{opt} must not have an argument')
    opts.append(('--' + opt, optarg))
    return opts, args


def short_has_arg(opt: str, shortopts: str):
    for i in range(len(shortopts)):
        if opt == shortopts[i] != ':':
            return shortopts.startswith(':', i+1)
    raise GetoptError(f'option -{opt} not recognized')


def do_shorts(opts: List[Tuple[str, str]], optstring: str, shortopts: str, args: List[str]):
    while optstring != '':
        opt, optstring = optstring[0], optstring[1:]
        optarg = ''
        if short_has_arg(opt, shortopts):
            if optstring == '':
                if not args:
                    raise GetoptError(f'option -{opt} requires argument')
                optstring, args = args[0], args[1:]
            optarg, optstring = optstring, ''
        opts.append(('-' + opt, optarg))
    return opts, args


def getopt(
    args: List[str],
    shortopts: str,
    longopts: List[str] = []
):
    """
    Parses command line options and parameter list.  args is the
    argument list to be parsed, without the leading reference to the
    running program.  Typically, this means "sys.argv[1:]".  shortopts
    is the string of option letters that the script wants to
    recognize, with options that require an argument followed by a
    colon (i.e., the same format that Unix getopt() uses).  If
    specified, longopts is a list of strings with the names of the
    long options which should be supported.  The leading '--'
    characters should not be included in the option name.  Options
    which require an argument should be followed by an equal sign
    ('=').

    The return value consists of two elements: the first is a list of
    (option, value) pairs; the second is the list of program arguments
    left after the option list was stripped (this is a trailing slice
    of the first argument).  Each option-and-value pair returned has
    the option as its first element, prefixed with a hyphen (e.g.,
    '-x'), and the option argument as its second element, or an empty
    string if the option has no argument.  The options occur in the
    list in the same order in which they were found, thus allowing
    multiple occurrences.  Long and short options may be mixed.

    NOTES:
    This function works like the above-mentioned getopt(), except that GNU style scanning
    mode is used by default. This means that option and non-option
    arguments may be intermixed. The getopt() function stops
    processing options as soon as a non-option argument is
    encountered.
    If the first character of the option string is `+', or if the
    environment variable POSIXLY_CORRECT is set, then option
    processing stops as soon as a non-option argument is encountered.
    """

    opts = []
    prog_args = []

    # Allow options after non-option arguments?
    all_options_first = False
    if shortopts.startswith('+'):
        shortopts = shortopts[1:]
        all_options_first = True
    elif "POSIXLY_CORRECT" in os.environ:
        all_options_first = True

    while args:
        if args[0] == '--':
            prog_args += args[1:]
            break

        if args[0][:2] == '--':
            opts, args = do_longs(opts, args[0][2:], longopts, args[1:])
        elif args[0][:1] == '-' and args[0] != '-':
            opts, args = do_shorts(opts, args[0][1:], shortopts, args[1:])
        else:
            if all_options_first:
                prog_args += args
                break
            else:
                prog_args.append(args[0])
                args = args[1:]

    return opts, prog_args