Created
November 29, 2009 23:46
-
-
Save chrisforbes/245134 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
using System; | |
using System.Collections.Generic; | |
using System.Linq; | |
using System.Text; | |
using System.Text.RegularExpressions; | |
namespace MultiRegex | |
{ | |
class Program | |
{ | |
static void Main(string[] args) | |
{ | |
var mr = new MultiRegex(new Dictionary<string, string>() | |
{ | |
{ @"(\d+)", "number" }, | |
{ @"\b([a-zA-Z_][a-zA-Z0-9_]+)\b", "ident" }, | |
{ @";", "punct" }, | |
}); | |
var input = "76 trombones led the big parade;" + | |
"With a 110 cornets close at hand ..."; | |
var toks = ParseWithMulti(mr, input); | |
foreach( var t in toks ) | |
Console.WriteLine(t); | |
} | |
static IEnumerable<string> ParseWithMulti(MultiRegex mr, string input) | |
{ | |
var index = 0; | |
while( index < input.Length ) | |
{ | |
var m = mr.Match(input, index); | |
if (m == null) yield break; | |
yield return m.tag; | |
index = m.m.Index + m.m.Length; | |
} | |
} | |
} | |
class MultiRegex | |
{ | |
readonly Regex r; | |
public MultiRegex(Dictionary<string, string> vs) | |
{ | |
r = new Regex(vs | |
.Select(v => "(?<{0}>{1})".F(v.Value, v.Key)) | |
.JoinWith("|")); | |
} | |
public MultiMatch Match(string s) { return Match(s, 0); } | |
public MultiMatch Match(string s, int start) | |
{ | |
var m = r.Match(s, start); | |
if (!m.Success) return null; | |
var namedGroups = r.GetGroupNames().Where(g => !char.IsDigit(g[0])); | |
var tag = namedGroups | |
.Select(x => new { t = x, g = m.Groups[x] }) | |
.Where(g => g.g.Success) | |
.OrderBy(g => g.g.Index) | |
.FirstOrDefault(); | |
if (tag == null) return null; | |
return new MultiMatch(m, tag.t); | |
} | |
} | |
class MultiMatch | |
{ | |
public readonly Match m; | |
public readonly string tag; | |
public MultiMatch(Match m, string tag) | |
{ | |
this.m = m; | |
this.tag = tag; | |
} | |
} | |
static class Exts | |
{ | |
public static string F( this string f, params object[] args ) | |
{ | |
return string.Format( f, args ); | |
} | |
public static string JoinWith<T>(this IEnumerable<T> ts, string sep) | |
{ | |
return string.Join(sep, ts.Select(t => t.ToString()).ToArray()); | |
} | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment