summaryrefslogtreecommitdiffstats
path: root/src/uscxml/transform/Trie.cpp
blob: 8e3aff30c96a4be82a4e04eea227abc29237286b (plain)
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
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
/**
 *  @file
 *  @author     2012-2014 Stefan Radomski (stefan.radomski@cs.tu-darmstadt.de)
 *  @copyright  Simplified BSD
 *
 *  @cond
 *  This program is free software: you can redistribute it and/or modify
 *  it under the terms of the FreeBSD license as published by the FreeBSD
 *  project.
 *
 *  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.
 *
 *  You should have received a copy of the FreeBSD license along with this
 *  program. If not, see <http://www.opensource.org/licenses/bsd-license>.
 *  @endcond
 */

#include "Trie.h"
#include <iostream>
#include <boost/algorithm/string.hpp>

namespace uscxml {

Trie::Trie() {
	root = new TrieNode();
	lastIndex = 0;
}

Trie::Trie(const std::string& seperator) : seperator(seperator) {
	root = new TrieNode();
	lastIndex = 0;
}

Trie::~Trie() {
	delete root;
}

TrieNode::TrieNode() : hasWord(false) {}

TrieNode::~TrieNode() {
	std::map<std::string, TrieNode*>::iterator childIter = childs.begin();
	while(childIter != childs.end()) {
		delete childIter->second;
		childIter++;
	}
}

size_t Trie::getNextToken(const std::string& word, size_t offset, std::string& token) {
	if (offset == std::string::npos || offset >= word.length()) {
		token = "";
		return std::string::npos;
	}
	if (seperator.size() > 0) {
		size_t sepPos = word.find(seperator, offset);
		if (sepPos == offset) // starts with a seperator
			return getNextToken(word, offset + seperator.length(), token);
		if (sepPos == std::string::npos) {
			token = word.substr(offset, word.length() - offset);
		} else {
			token = word.substr(offset, sepPos - offset);
			sepPos += seperator.length();
		}
		return sepPos;
	}
	token = word[offset];
	return offset + 1;
}

std::string Trie::escapeWord(const std::string& word) {
	std::string identifier = word;
	boost::replace_all(identifier, ".", "_");
	return identifier;
}

void Trie::addWord(const std::string& word) {
	TrieNode* currNode = root;

	std::string prefix;
	size_t offset = 0;

	for(;;) {
		offset = getNextToken(word, offset, prefix);

		if (prefix.size() > 0) {
			if (currNode->childs.find(prefix) == currNode->childs.end())
				currNode->childs[prefix] = new TrieNode();
			currNode = currNode->childs[prefix];
		}

		if (offset == std::string::npos)
			break;
	}
	if (!currNode->hasWord) {
		currNode->index = lastIndex++;
		currNode->value = word;
		currNode->identifier = escapeWord(word);
		currNode->hasWord = true;
	}
}

TrieNode* Trie::getNodeWithPrefix(const std::string& prefix) {
	std::string token;
	size_t offset = 0;

	TrieNode* currNode = root;

	for(;;) {
		offset = getNextToken(prefix, offset, token);
		if (currNode->childs.find(token) == currNode->childs.end()) {
			if (token.size() > 0)
				currNode = NULL;
			break;
		} else {
			currNode = currNode->childs[token];
		}
	}
	return currNode;
}

std::list<TrieNode*> Trie::getWordsWithPrefix(const std::string& prefix) {
	std::list<TrieNode*> nodes;
	TrieNode* prefixNode = getNodeWithPrefix(prefix);

	if (prefixNode) {
		nodes = getChildsWithWords(prefixNode);
	}

	return nodes;
}

std::list<TrieNode*> Trie::getChildsWithWords(TrieNode* node) {
	std::list<TrieNode*> nodes;
	if (node->hasWord) {
		nodes.push_back(node);
	}

	std::map<std::string, TrieNode*>::iterator childIter = node->childs.begin();
	while(childIter != node->childs.end()) {
		std::list<TrieNode*> otherChilds = getChildsWithWords(childIter->second);
		nodes.merge(otherChilds);
		childIter++;
	}

	return nodes;
}

void TrieNode::dump(int indent) {
	std::string padding;
	for (size_t i = 0; i < indent; i++) {
		padding += "  ";
	}

	std::map<std::string, TrieNode*>::iterator childIter = childs.begin();
	while(childIter != childs.end()) {
		std::cout << padding << childIter->first;
		if (childIter->second->hasWord) {
			std::cout << " (word)";
		}
		std::cout << std::endl;
		childIter->second->dump(indent + 1);
		childIter++;
	}
}

void Trie::dump() {
	if (root->hasWord)
		std::cout << "(word)" << std::endl;
	root->dump();
}

}