This repository has been archived by the owner on Apr 28, 2019. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 2
/
Tokenizer.cs
91 lines (88 loc) · 3.5 KB
/
Tokenizer.cs
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
/*
* Vha.AOML
* Copyright (C) 2010-2011 Remco van Oosterhout
* See Credits.txt for all aknowledgements.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; version 2 of the License only.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307
* USA
*/
using System.Text.RegularExpressions;
namespace Vha.AOML
{
public class Tokenizer
{
/// <summary>
/// Loads and tokenizes a string.
/// Calling this method will clear the state of this object and make any previous returned values invalid.
/// </summary>
/// <param name="text">The string to be tokenized</param>
public TokenCollection Parse(string aoml)
{
// Replace 'other' newline characters
aoml = aoml.Replace("\r\n", "\n");
aoml = aoml.Replace("\n\r", "\n");
// Tokenize
TokenCollection tokens = new TokenCollection();
int offset = 0;
while (offset < aoml.Length)
{
// Check for identifiers
Match identifier = this.identifierRegex.Match(aoml, offset);
if (identifier != null)
{
tokens.Add(TokenType.Identifier, identifier.Value, ref offset);
continue;
}
// Check for characters
switch (aoml[offset])
{
case '<':
tokens.Add(TokenType.TagBegin, "<", ref offset);
break;
case '>':
tokens.Add(TokenType.TagEnd, ">", ref offset);
break;
case ' ':
tokens.Add(TokenType.WhiteSpace, " ", ref offset);
break;
case '\t':
tokens.Add(TokenType.WhiteSpace, "\t", ref offset);
break;
case '\n':
tokens.Add(TokenType.LineBreak, "\n", ref offset);
break;
case '\'':
tokens.Add(TokenType.SingleQuote, "'", ref offset);
break;
case '"':
tokens.Add(TokenType.DoubleQuote, "\"", ref offset);
break;
case '=':
tokens.Add(TokenType.Equal, "=", ref offset);
break;
case '/':
tokens.Add(TokenType.Slash, "/", ref offset);
break;
default:
tokens.Add(TokenType.Text, aoml[offset].ToString(), ref offset);
break;
}
}
return tokens;
}
#region Private
private Regex identifierRegex = new Regex("^[a-z][a-z0-9_\\-]*", RegexOptions.IgnoreCase);
#endregion
}
}