I need this for a C# project, so here is the Python code mentioned above. Make sure to include using System.Text.RegularExpressions; in your source file.

private string GetIndefiniteArticle(string noun_phrase)
{
    string word = null;
    var m = Regex.Match(noun_phrase, @"\w+");
    if (m.Success)
        word = m.Groups[0].Value;
    else
        return "an";

    var wordi = word.ToLower();
    foreach (string anword in new string[] { "euler", "heir", "honest", "hono" })
        if (wordi.StartsWith(anword))
            return "an";

    if (wordi.StartsWith("hour") && !wordi.StartsWith("houri"))
        return "an";

    var char_list = new char[] { 'a', 'e', 'd', 'h', 'i', 'l', 'm', 'n', 'o', 'r', 's', 'x' };
    if (wordi.Length == 1)
    {
        if (wordi.IndexOfAny(char_list) == 0)
            return "an";
        else
            return "a";
    }

    if (Regex.Match(word, "(?!FJO|[HLMNS]Y.|RY[EO]|SQU|(F[LR]?|[HL]|MN?|N|RH?|S[CHKLMNPTVW]?|X(YL)?)[AEIOU])[FHLMNRSX][A-Z]").Success)
        return "an";

    foreach (string regex in new string[] { "^e[uw]", "^onc?e\b", "^uni([^nmd]|mo)", "^u[bcfhjkqrst][aeiou]" })
    {
        if (Regex.IsMatch(wordi, regex))
            return "a";
    }

    if (Regex.IsMatch(word, "^U[NK][AIEO]"))
        return "a";
    else if (word == word.ToUpper())
    {
        if (wordi.IndexOfAny(char_list) == 0)
            return "an";
        else
            return "a";
    }

    if (wordi.IndexOfAny(new char[] { 'a', 'e', 'i', 'o', 'u' }) == 0)
        return "an";

    if (Regex.IsMatch(wordi, "^y(b[lor]|cl[ea]|fere|gg|p[ios]|rou|tt)"))
        return "an";

    return "a";
}

Like +0

Add Reply 关闭回复

P粉764785924

reply

What you want is to identify the appropriate indefinite article. Lingua::EN::Inflect is a Perl module that performs well. I've extracted the relevant code and pasted it below. It's just a bunch of cases and some regular expressions, so porting to PHP shouldn't be difficult. A friend ported it to Python If anyone is interested, click here .

# 2. INDEFINITE ARTICLES

# THIS PATTERN MATCHES STRINGS OF CAPITALS STARTING WITH A "VOWEL-SOUND"
# CONSONANT FOLLOWED BY ANOTHER CONSONANT, AND WHICH ARE NOT LIKELY
# TO BE REAL WORDS (OH, ALL RIGHT THEN, IT'S JUST MAGIC!)

my $A_abbrev = q{
(?! FJO | [HLMNS]Y.  | RY[EO] | SQU
  | ( F[LR]? | [HL] | MN? | N | RH? | S[CHKLMNPTVW]? | X(YL)?) [AEIOU])
[FHLMNRSX][A-Z]
};

# THIS PATTERN CODES THE BEGINNINGS OF ALL ENGLISH WORDS BEGINING WITH A
# 'y' FOLLOWED BY A CONSONANT. ANY OTHER Y-CONSONANT PREFIX THEREFORE
# IMPLIES AN ABBREVIATION.

my $A_y_cons = 'y(b[lor]|cl[ea]|fere|gg|p[ios]|rou|tt)';

# EXCEPTIONS TO EXCEPTIONS

my $A_explicit_an = enclose join '|',
(
    "euler",
    "hour(?!i)", "heir", "honest", "hono",
);

my $A_ordinal_an = enclose join '|',
(
    "[aefhilmnorsx]-?th",
);

my $A_ordinal_a = enclose join '|',
(
    "[bcdgjkpqtuvwyz]-?th",
);

sub A {
    my ($str, $count) = @_;
    my ($pre, $word, $post) = ( $str =~ m/\A(\s*)(?:an?\s+)?(.+?)(\s*)\Z/i );
    return $str unless $word;
    my $result = _indef_article($word,$count);
    return $pre.$result.$post;
}

sub AN { goto &A }

sub _indef_article {
    my ( $word, $count ) = @_;

    $count = $persistent_count
        if !defined($count) && defined($persistent_count);

    return "$count $word"
        if defined $count && $count!~/^($PL_count_one)$/io;

    # HANDLE USER-DEFINED VARIANTS

    my $value;
    return "$value $word"
        if defined($value = ud_match($word, @A_a_user_defined));

    # HANDLE ORDINAL FORMS

    $word =~ /^($A_ordinal_a)/i         and return "a $word";
    $word =~ /^($A_ordinal_an)/i        and return "an $word";

    # HANDLE SPECIAL CASES

    $word =~ /^($A_explicit_an)/i       and return "an $word";
    $word =~ /^[aefhilmnorsx]$/i        and return "an $word";
    $word =~ /^[bcdgjkpqtuvwyz]$/i      and return "a $word";


    # HANDLE ABBREVIATIONS

    $word =~ /^($A_abbrev)/ox           and return "an $word";
    $word =~ /^[aefhilmnorsx][.-]/i     and return "an $word";
    $word =~ /^[a-z][.-]/i              and return "a $word";

    # HANDLE CONSONANTS

    $word =~ /^[^aeiouy]/i              and return "a $word";

    # HANDLE SPECIAL VOWEL-FORMS

    $word =~ /^e[uw]/i                  and return "a $word";
    $word =~ /^onc?e\b/i                and return "a $word";
    $word =~ /^uni([^nmd]|mo)/i         and return "a $word";
    $word =~ /^ut[th]/i                 and return "an $word";
    $word =~ /^u[bcfhjkqrst][aeiou]/i   and return "a $word";

    # HANDLE SPECIAL CAPITALS

    $word =~ /^U[NK][AIEO]?/            and return "a $word";

    # HANDLE VOWELS

    $word =~ /^[aeiou]/i                and return "an $word";

    # HANDLE y... (BEFORE CERTAIN CONSONANTS IMPLIES (UNNATURALIZED) "i.." SOUND)

    $word =~ /^($A_y_cons)/io           and return "an $word";

    # OTHERWISE, GUESS "a"
    return "a $word";
}

Like +0

Add Reply 关闭回复

P粉764785924

reply