1 | #region License Information
|
---|
2 | /* HeuristicLab
|
---|
3 | * Copyright (C) 2002-2013 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
|
---|
4 | *
|
---|
5 | * This file is part of HeuristicLab.
|
---|
6 | *
|
---|
7 | * HeuristicLab is free software: you can redistribute it and/or modify
|
---|
8 | * it under the terms of the GNU General Public License as published by
|
---|
9 | * the Free Software Foundation, either version 3 of the License, or
|
---|
10 | * (at your option) any later version.
|
---|
11 | *
|
---|
12 | * HeuristicLab is distributed in the hope that it will be useful,
|
---|
13 | * but WITHOUT ANY WARRANTY; without even the implied warranty of
|
---|
14 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
---|
15 | * GNU General Public License for more details.
|
---|
16 | *
|
---|
17 | * You should have received a copy of the GNU General Public License
|
---|
18 | * along with HeuristicLab. If not, see <http://www.gnu.org/licenses/>.
|
---|
19 | */
|
---|
20 | #endregion
|
---|
21 |
|
---|
22 | using System;
|
---|
23 | using System.Collections.Generic;
|
---|
24 | using System.Linq;
|
---|
25 | using System.Text.RegularExpressions;
|
---|
26 |
|
---|
27 | namespace HeuristicLab.Grammars {
|
---|
28 | using Sequence = IEnumerable<string>;
|
---|
29 |
|
---|
30 | public class Grammar : IGrammar {
|
---|
31 | private Dictionary<string, List<Sequence>> rules = new Dictionary<string, List<Sequence>>();
|
---|
32 | private HashSet<string> allSymbols = new HashSet<string>();
|
---|
33 |
|
---|
34 | public string StartSymbol { get; set; }
|
---|
35 | public IEnumerable<string> TerminalSymbols { get { return allSymbols.Except(NonTerminalSymbols); } }
|
---|
36 | public IEnumerable<string> NonTerminalSymbols { get { return rules.Keys; } }
|
---|
37 | public IEnumerable<string> Symbols { get { return allSymbols; } }
|
---|
38 |
|
---|
39 | public Grammar(string startSymbol) {
|
---|
40 | this.StartSymbol = startSymbol;
|
---|
41 | }
|
---|
42 |
|
---|
43 | public int NumberOfAlternatives(string ntSymbol) {
|
---|
44 | return rules[ntSymbol].Count;
|
---|
45 | }
|
---|
46 |
|
---|
47 | public IEnumerable<Sequence> GetAlternatives(string ntSymbol) {
|
---|
48 | return rules[ntSymbol].AsReadOnly();
|
---|
49 | }
|
---|
50 |
|
---|
51 | public Sequence GetAlternative(string ntSymbol, int index) {
|
---|
52 | return rules[ntSymbol][index];
|
---|
53 | }
|
---|
54 |
|
---|
55 | public void AddProductionRule(string ntSymbol, Sequence production) {
|
---|
56 | List<Sequence> l;
|
---|
57 | if (!rules.TryGetValue(ntSymbol, out l)) {
|
---|
58 | l = new List<Sequence>();
|
---|
59 | rules.Add(ntSymbol, l);
|
---|
60 |
|
---|
61 | allSymbols.Add(ntSymbol); // register new nt-symbol
|
---|
62 | }
|
---|
63 | l.Add(production);
|
---|
64 |
|
---|
65 | foreach (var s in production) allSymbols.Add(s); // register all symbols in the production
|
---|
66 | }
|
---|
67 |
|
---|
68 | private static Regex ruleExpr = new Regex(@"\s*(?<ntSymbol>\w+)\s*->\s*(?<alternative>\w+(?:\s+\w+)*)(?:\s*\|\s*(?<alternative>\w+(?:\s+\w+)*))*");
|
---|
69 | private static Regex empty = new Regex(@"^\s*$");
|
---|
70 | public static IGrammar FromString(string gStr) {
|
---|
71 | var lines = gStr.Split(new string[] { Environment.NewLine }, StringSplitOptions.RemoveEmptyEntries);
|
---|
72 | lines = lines.Where(l => !empty.IsMatch(l)).ToArray(); // remove empty lines
|
---|
73 |
|
---|
74 | // first line is the rule for the start-symbol
|
---|
75 | var m = ruleExpr.Match(lines.First());
|
---|
76 | var startSymbol = m.Groups["ntSymbol"].Value;
|
---|
77 | var g = new Grammar(startSymbol);
|
---|
78 | foreach (var alt in m.Groups["alternative"].Captures) {
|
---|
79 | g.AddProductionRule(startSymbol, alt.ToString().Split(new char[] { ' ' }, StringSplitOptions.RemoveEmptyEntries));
|
---|
80 | }
|
---|
81 | foreach (var line in lines.Skip(1)) {
|
---|
82 | m = ruleExpr.Match(line);
|
---|
83 | var ntSymbol = m.Groups["ntSymbol"].Value;
|
---|
84 | foreach (var alt in m.Groups["alternative"].Captures) {
|
---|
85 | g.AddProductionRule(ntSymbol, alt.ToString().Split(new char[] { ' ' }, StringSplitOptions.RemoveEmptyEntries));
|
---|
86 | }
|
---|
87 | }
|
---|
88 | return g;
|
---|
89 | }
|
---|
90 | }
|
---|
91 | } |
---|