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 | |
---|
19 | /** |
---|
20 | * breaks a string into parts that were initially seperated by comma |
---|
21 | * @param string the string to break into substrings |
---|
22 | */ |
---|
23 | |
---|
24 | #include "substring.h" |
---|
25 | |
---|
26 | #include <string.h> |
---|
27 | #include <cassert> |
---|
28 | |
---|
29 | SubString::SubString(const std::string& string, char splitter) |
---|
30 | { |
---|
31 | char split[2]; |
---|
32 | split[0] = splitter; |
---|
33 | split[1] = '\0'; |
---|
34 | SubString::splitLine(this->strings, this->offsets, |
---|
35 | string, split); |
---|
36 | } |
---|
37 | |
---|
38 | |
---|
39 | /** |
---|
40 | * Splits a String into a Substring removing all whiteSpaces |
---|
41 | * @param string the String to Split |
---|
42 | * @param whiteSpaces MUST BE __TRUE__ |
---|
43 | * |
---|
44 | */ |
---|
45 | SubString::SubString(const std::string& string, bool whiteSpaces) |
---|
46 | { |
---|
47 | SubString::splitLine(this->strings, this->offsets, |
---|
48 | string); |
---|
49 | } |
---|
50 | |
---|
51 | SubString::SubString(const std::string& string, const std::string& splitters, char escapeChar,char safemode_char, char comment_char) |
---|
52 | { |
---|
53 | SubString::splitLine(this->strings, this->offsets, |
---|
54 | string, splitters, escapeChar, safemode_char); |
---|
55 | } |
---|
56 | |
---|
57 | |
---|
58 | /** |
---|
59 | * splits line into tokens and stores them in ret. Supports delimiters, escape characters, |
---|
60 | * ignores special characters between safemode_char and between comment_char and linend '\n'. |
---|
61 | * |
---|
62 | * @returns SPLIT_LINE_STATE the parser was in when returning |
---|
63 | */ |
---|
64 | SPLIT_LINE_STATE SubString::splitLine(std::vector<std::string>& ret, std::vector<unsigned int>& offsets, |
---|
65 | const std::string& line, const std::string& delimiters, |
---|
66 | char escape_char, char safemode_char, char comment_char, |
---|
67 | SPLIT_LINE_STATE start_state) |
---|
68 | { |
---|
69 | SPLIT_LINE_STATE state = start_state; |
---|
70 | unsigned int i = 0; |
---|
71 | std::string token; |
---|
72 | |
---|
73 | if(start_state != SL_NORMAL && ret.size() > 0) |
---|
74 | { |
---|
75 | token = ret[ret.size()-1]; |
---|
76 | ret.pop_back(); |
---|
77 | } |
---|
78 | |
---|
79 | while(i < line.size()) |
---|
80 | { |
---|
81 | switch(state) |
---|
82 | { |
---|
83 | case SL_NORMAL: |
---|
84 | if(line[i] == escape_char) |
---|
85 | { |
---|
86 | state = SL_ESCAPE; |
---|
87 | } |
---|
88 | else if(line[i] == safemode_char) |
---|
89 | { |
---|
90 | state = SL_SAFEMODE; |
---|
91 | } |
---|
92 | else if(line[i] == comment_char) |
---|
93 | { |
---|
94 | /// FINISH |
---|
95 | if(token.size() > 0) |
---|
96 | { |
---|
97 | ret.push_back(token); |
---|
98 | offsets.push_back(i); |
---|
99 | token.clear(); |
---|
100 | } |
---|
101 | token += line[i]; // EAT |
---|
102 | state = SL_COMMENT; |
---|
103 | } |
---|
104 | else if(delimiters.find(line[i]) != std::string::npos) |
---|
105 | { |
---|
106 | // line[i] is a delimiter |
---|
107 | /// FINISH |
---|
108 | if(token.size() > 0) |
---|
109 | { |
---|
110 | ret.push_back(token); |
---|
111 | offsets.push_back(i); |
---|
112 | token.clear(); |
---|
113 | } |
---|
114 | } |
---|
115 | else |
---|
116 | { |
---|
117 | token += line[i]; // EAT |
---|
118 | } |
---|
119 | break; |
---|
120 | case SL_ESCAPE: |
---|
121 | if(line[i] == 'n') token += '\n'; |
---|
122 | else if(line[i] == 't') token += '\t'; |
---|
123 | else if(line[i] == 'v') token += '\v'; |
---|
124 | else if(line[i] == 'b') token += '\b'; |
---|
125 | else if(line[i] == 'r') token += '\r'; |
---|
126 | else if(line[i] == 'f') token += '\f'; |
---|
127 | else if(line[i] == 'a') token += '\a'; |
---|
128 | else if(line[i] == '?') token += '\?'; |
---|
129 | else token += line[i]; // EAT |
---|
130 | state = SL_NORMAL; |
---|
131 | break; |
---|
132 | case SL_SAFEMODE: |
---|
133 | if(line[i] == safemode_char) |
---|
134 | { |
---|
135 | state = SL_NORMAL; |
---|
136 | } |
---|
137 | else if(line[i] == escape_char) |
---|
138 | { |
---|
139 | state = SL_SAFEESCAPE; |
---|
140 | } |
---|
141 | else |
---|
142 | { |
---|
143 | token += line[i]; // EAT |
---|
144 | } |
---|
145 | break; |
---|
146 | case SL_SAFEESCAPE: |
---|
147 | if(line[i] == 'n') token += '\n'; |
---|
148 | else if(line[i] == 't') token += '\t'; |
---|
149 | else if(line[i] == 'v') token += '\v'; |
---|
150 | else if(line[i] == 'b') token += '\b'; |
---|
151 | else if(line[i] == 'r') token += '\r'; |
---|
152 | else if(line[i] == 'f') token += '\f'; |
---|
153 | else if(line[i] == 'a') token += '\a'; |
---|
154 | else if(line[i] == '?') token += '\?'; |
---|
155 | else token += line[i]; // EAT |
---|
156 | state = SL_SAFEMODE; |
---|
157 | break; |
---|
158 | case SL_COMMENT: |
---|
159 | if(line[i] == '\n') |
---|
160 | { |
---|
161 | /// FINISH |
---|
162 | if(token.size() > 0) |
---|
163 | { |
---|
164 | ret.push_back(token); |
---|
165 | offsets.push_back(i); |
---|
166 | token.clear(); |
---|
167 | } |
---|
168 | state = SL_NORMAL; |
---|
169 | } |
---|
170 | else |
---|
171 | { |
---|
172 | token += line[i]; // EAT |
---|
173 | } |
---|
174 | break; |
---|
175 | default: |
---|
176 | // nothing |
---|
177 | break; |
---|
178 | } |
---|
179 | i++; |
---|
180 | } |
---|
181 | |
---|
182 | /// FINISH |
---|
183 | if(token.size() > 0) |
---|
184 | { |
---|
185 | ret.push_back(token); |
---|
186 | offsets.push_back(i); |
---|
187 | token.clear(); |
---|
188 | } |
---|
189 | return(state); |
---|
190 | } |
---|
191 | |
---|
192 | /** |
---|
193 | * removes the object from memory |
---|
194 | */ |
---|
195 | SubString::~SubString() |
---|
196 | { } |
---|
197 | |
---|
198 | /** |
---|
199 | * get a particular substring's offset |
---|
200 | * @param i the ID of the substring to get the offset from |
---|
201 | * @returns the offset or NULL if an invalid ID was given |
---|
202 | */ |
---|
203 | unsigned int SubString::getOffset(unsigned int i) |
---|
204 | { |
---|
205 | if( i < this->offsets.size() && i >= 0) |
---|
206 | return this->offsets[i]; |
---|
207 | else |
---|
208 | return 0; |
---|
209 | } |
---|
210 | |
---|
211 | /** |
---|
212 | * Some nice debug information about this SubString |
---|
213 | */ |
---|
214 | void SubString::debug() const |
---|
215 | { |
---|
216 | printf("Substring-information::count=%d ::", this->strings.size()); |
---|
217 | for (unsigned int i = 0; i < this->strings.size(); i++) |
---|
218 | printf("s%d='%s'::", i, this->strings[i].c_str()); |
---|
219 | printf("\n"); |
---|
220 | } |
---|