1 | /* |
---|
2 | orxonox - the future of 3D-vertical-scrollers |
---|
3 | |
---|
4 | Copyright (C) 2004 orx |
---|
5 | |
---|
6 | This program is free software; you can redistribute it and/or modify |
---|
7 | it under the terms of the GNU General Public License as published by |
---|
8 | the Free Software Foundation; either version 2, or (at your option) |
---|
9 | any later version. |
---|
10 | |
---|
11 | ### File Specific: |
---|
12 | main-programmer: Christian Meyer |
---|
13 | co-programmer: Benjamin Grauer |
---|
14 | |
---|
15 | 2005-06-10: some naming conventions |
---|
16 | |
---|
17 | // |
---|
18 | // splitLine |
---|
19 | // STL string tokenizer |
---|
20 | // |
---|
21 | // Created by Clemens Wacha. |
---|
22 | // Version 1.0 |
---|
23 | // Copyright (c) 2005 Clemens Wacha. All rights reserved. |
---|
24 | // |
---|
25 | |
---|
26 | */ |
---|
27 | |
---|
28 | |
---|
29 | /** |
---|
30 | * breaks a string into parts that were initially seperated by comma |
---|
31 | * @param string the string to break into substrings |
---|
32 | */ |
---|
33 | |
---|
34 | #include "substring.h" |
---|
35 | |
---|
36 | #include <string.h> |
---|
37 | #include <cassert> |
---|
38 | |
---|
39 | SubString::SubString(const std::string& string, char splitter) |
---|
40 | { |
---|
41 | char split[2]; |
---|
42 | split[0] = splitter; |
---|
43 | split[1] = '\0'; |
---|
44 | SubString::splitLine(this->strings, this->offsets, |
---|
45 | string, split); |
---|
46 | } |
---|
47 | |
---|
48 | /** |
---|
49 | * Splits a String into a Substring removing all whiteSpaces |
---|
50 | * @param string the String to Split |
---|
51 | * @param whiteSpaces MUST BE __TRUE__ |
---|
52 | * |
---|
53 | */ |
---|
54 | SubString::SubString(const std::string& string, bool whiteSpaces) |
---|
55 | { |
---|
56 | SubString::splitLine(this->strings, this->offsets, |
---|
57 | string); |
---|
58 | } |
---|
59 | SubString::SubString(const std::string& string, const std::string& splitters, char escapeChar,char safemode_char, char comment_char) |
---|
60 | { |
---|
61 | SubString::splitLine(this->strings, this->offsets, |
---|
62 | string, splitters, escapeChar, safemode_char); |
---|
63 | } |
---|
64 | |
---|
65 | /** |
---|
66 | * An empty String |
---|
67 | */ |
---|
68 | const std::string SubString::emptyString = ""; |
---|
69 | |
---|
70 | |
---|
71 | |
---|
72 | unsigned int SubString::split(const std::string& string, char splitter) |
---|
73 | { |
---|
74 | this->offsets.clear(); |
---|
75 | this->strings.clear(); |
---|
76 | char split[2]; |
---|
77 | split[0] = splitter; |
---|
78 | split[1] = '\0'; |
---|
79 | SubString::splitLine(this->strings, this->offsets, string, split); |
---|
80 | return strings.size(); |
---|
81 | } |
---|
82 | |
---|
83 | |
---|
84 | /** |
---|
85 | * Splits a String into a Substring removing all whiteSpaces |
---|
86 | * @param string the String to Split |
---|
87 | * @param whiteSpaces MUST BE __TRUE__ |
---|
88 | * |
---|
89 | */ |
---|
90 | unsigned int SubString::split(const std::string& string, bool whiteSpaces) |
---|
91 | { |
---|
92 | this->offsets.clear(); |
---|
93 | this->strings.clear(); |
---|
94 | SubString::splitLine(this->strings, this->offsets, string); |
---|
95 | return strings.size(); |
---|
96 | } |
---|
97 | |
---|
98 | unsigned int SubString::split(const std::string& string, const std::string& splitters, char escapeChar,char safemode_char, char comment_char) |
---|
99 | { |
---|
100 | this->offsets.clear(); |
---|
101 | this->strings.clear(); |
---|
102 | SubString::splitLine(this->strings, this->offsets, |
---|
103 | string, splitters, escapeChar, safemode_char); |
---|
104 | return strings.size(); |
---|
105 | } |
---|
106 | |
---|
107 | |
---|
108 | /** |
---|
109 | * @brief splits line into tokens and stores them in ret. |
---|
110 | * @param ret the Array, where the Splitted strings will be stored in |
---|
111 | * @param offsets an Array of Offsets, here the distance from the inputstring |
---|
112 | * to the beginning of the current token is stored |
---|
113 | * @param line the inputLine to split |
---|
114 | * @param delimiters a String of Delimiters (here the input will be splitted) |
---|
115 | * @param escape_char: Escape carater (escapes splitters) |
---|
116 | * @param safemode_char: the beginning of the safemode is marked with this |
---|
117 | * @param comment_char: the beginning of a comment is marked with this: (until the end of a Line) |
---|
118 | * @param start_state: the Initial state on how to parse the String. |
---|
119 | * @returns SPLIT_LINE_STATE the parser was in when returning |
---|
120 | * |
---|
121 | * Supports delimiters, escape characters, |
---|
122 | * ignores special characters between safemode_char and between comment_char and linend '\n'. |
---|
123 | * |
---|
124 | */ |
---|
125 | SPLIT_LINE_STATE SubString::splitLine(std::vector<std::string>& ret, std::vector<unsigned int>& offsets, |
---|
126 | const std::string& line, const std::string& delimiters, |
---|
127 | char escape_char, char safemode_char, char comment_char, |
---|
128 | SPLIT_LINE_STATE start_state) |
---|
129 | { |
---|
130 | SPLIT_LINE_STATE state = start_state; |
---|
131 | unsigned int i = 0; |
---|
132 | std::string token; |
---|
133 | |
---|
134 | if(start_state != SL_NORMAL && ret.size() > 0) |
---|
135 | { |
---|
136 | token = ret[ret.size()-1]; |
---|
137 | ret.pop_back(); |
---|
138 | } |
---|
139 | |
---|
140 | while(i < line.size()) |
---|
141 | { |
---|
142 | switch(state) |
---|
143 | { |
---|
144 | case SL_NORMAL: |
---|
145 | if(line[i] == escape_char) |
---|
146 | { |
---|
147 | state = SL_ESCAPE; |
---|
148 | } |
---|
149 | else if(line[i] == safemode_char) |
---|
150 | { |
---|
151 | state = SL_SAFEMODE; |
---|
152 | } |
---|
153 | else if(line[i] == comment_char) |
---|
154 | { |
---|
155 | /// FINISH |
---|
156 | if(token.size() > 0) |
---|
157 | { |
---|
158 | ret.push_back(token); |
---|
159 | offsets.push_back(i); |
---|
160 | token.clear(); |
---|
161 | } |
---|
162 | token += line[i]; // EAT |
---|
163 | state = SL_COMMENT; |
---|
164 | } |
---|
165 | else if(delimiters.find(line[i]) != std::string::npos) |
---|
166 | { |
---|
167 | // line[i] is a delimiter |
---|
168 | /// FINISH |
---|
169 | if(token.size() > 0) |
---|
170 | { |
---|
171 | ret.push_back(token); |
---|
172 | offsets.push_back(i); |
---|
173 | token.clear(); |
---|
174 | } |
---|
175 | } |
---|
176 | else |
---|
177 | { |
---|
178 | token += line[i]; // EAT |
---|
179 | } |
---|
180 | break; |
---|
181 | case SL_ESCAPE: |
---|
182 | if(line[i] == 'n') token += '\n'; |
---|
183 | else if(line[i] == 't') token += '\t'; |
---|
184 | else if(line[i] == 'v') token += '\v'; |
---|
185 | else if(line[i] == 'b') token += '\b'; |
---|
186 | else if(line[i] == 'r') token += '\r'; |
---|
187 | else if(line[i] == 'f') token += '\f'; |
---|
188 | else if(line[i] == 'a') token += '\a'; |
---|
189 | else if(line[i] == '?') token += '\?'; |
---|
190 | else token += line[i]; // EAT |
---|
191 | state = SL_NORMAL; |
---|
192 | break; |
---|
193 | case SL_SAFEMODE: |
---|
194 | if(line[i] == safemode_char) |
---|
195 | { |
---|
196 | state = SL_NORMAL; |
---|
197 | } |
---|
198 | else if(line[i] == escape_char) |
---|
199 | { |
---|
200 | state = SL_SAFEESCAPE; |
---|
201 | } |
---|
202 | else |
---|
203 | { |
---|
204 | token += line[i]; // EAT |
---|
205 | } |
---|
206 | break; |
---|
207 | case SL_SAFEESCAPE: |
---|
208 | if(line[i] == 'n') token += '\n'; |
---|
209 | else if(line[i] == 't') token += '\t'; |
---|
210 | else if(line[i] == 'v') token += '\v'; |
---|
211 | else if(line[i] == 'b') token += '\b'; |
---|
212 | else if(line[i] == 'r') token += '\r'; |
---|
213 | else if(line[i] == 'f') token += '\f'; |
---|
214 | else if(line[i] == 'a') token += '\a'; |
---|
215 | else if(line[i] == '?') token += '\?'; |
---|
216 | else token += line[i]; // EAT |
---|
217 | state = SL_SAFEMODE; |
---|
218 | break; |
---|
219 | case SL_COMMENT: |
---|
220 | if(line[i] == '\n') |
---|
221 | { |
---|
222 | /// FINISH |
---|
223 | if(token.size() > 0) |
---|
224 | { |
---|
225 | ret.push_back(token); |
---|
226 | offsets.push_back(i); |
---|
227 | token.clear(); |
---|
228 | } |
---|
229 | state = SL_NORMAL; |
---|
230 | } |
---|
231 | else |
---|
232 | { |
---|
233 | token += line[i]; // EAT |
---|
234 | } |
---|
235 | break; |
---|
236 | default: |
---|
237 | // nothing |
---|
238 | break; |
---|
239 | } |
---|
240 | i++; |
---|
241 | } |
---|
242 | |
---|
243 | /// FINISH |
---|
244 | if(token.size() > 0) |
---|
245 | { |
---|
246 | ret.push_back(token); |
---|
247 | offsets.push_back(i); |
---|
248 | token.clear(); |
---|
249 | } |
---|
250 | return(state); |
---|
251 | } |
---|
252 | |
---|
253 | /** |
---|
254 | * removes the object from memory |
---|
255 | */ |
---|
256 | SubString::~SubString() |
---|
257 | { } |
---|
258 | |
---|
259 | /** |
---|
260 | * get a particular substring's offset |
---|
261 | * @param i the ID of the substring to get the offset from |
---|
262 | * @returns the offset or NULL if an invalid ID was given |
---|
263 | */ |
---|
264 | unsigned int SubString::getOffset(unsigned int i) |
---|
265 | { |
---|
266 | if( i < this->offsets.size() && i >= 0) |
---|
267 | return this->offsets[i]; |
---|
268 | else |
---|
269 | return 0; |
---|
270 | } |
---|
271 | |
---|
272 | /** |
---|
273 | * Some nice debug information about this SubString |
---|
274 | */ |
---|
275 | void SubString::debug() const |
---|
276 | { |
---|
277 | printf("Substring-information::count=%d ::", this->strings.size()); |
---|
278 | for (unsigned int i = 0; i < this->strings.size(); i++) |
---|
279 | printf("s%d='%s'::", i, this->strings[i].c_str()); |
---|
280 | printf("\n"); |
---|
281 | } |
---|