php - Programmatically determine whether to describe an object with "a" or "an"?

Question

I have a database of nouns (ex "house", "exclamation point", "apple") that I need to output and describe in my application. It's hard to put together a natural-sounding sentence to describe an item without using "a" or "an" - "a house is BIG", "an exclamation point is SMALL", etc.

Is there any function, library, or hack i can use in PHP to determine whether it is more appropriate to describe any given noun with A or AN?

Answer 1

I needed this for a C# project so here's the C# port of 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", "^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";
}