1 | /* |
---|
2 | * ORXONOX - the hottest 3D action shooter ever to exist |
---|
3 | * > www.orxonox.net < |
---|
4 | * |
---|
5 | * |
---|
6 | * License notice: |
---|
7 | * |
---|
8 | * This program is free software; you can redistribute it and/or |
---|
9 | * modify it under the terms of the GNU General Public License |
---|
10 | * as published by the Free Software Foundation; either version 2 |
---|
11 | * of the License, or (at your option) any later version. |
---|
12 | * |
---|
13 | * This program is distributed in the hope that it will be useful, |
---|
14 | * but WITHOUT ANY WARRANTY; without even the implied warranty of |
---|
15 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
---|
16 | * GNU General Public License for more details. |
---|
17 | * |
---|
18 | * You should have received a copy of the GNU General Public License |
---|
19 | * along with this program; if not, write to the Free Software |
---|
20 | * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. |
---|
21 | * |
---|
22 | * Author: |
---|
23 | * Christian Meyer |
---|
24 | * Co-authors: |
---|
25 | * Benjamin Grauer |
---|
26 | * Fabian 'x3n' Landau |
---|
27 | * |
---|
28 | |
---|
29 | // splitLine |
---|
30 | // STL string tokenizer |
---|
31 | // |
---|
32 | // Created by Clemens Wacha. |
---|
33 | // Version 1.0 |
---|
34 | // Copyright (c) 2005 Clemens Wacha. All rights reserved. |
---|
35 | |
---|
36 | * Extended by Fabian 'x3n' Landau by the SL_PARENTHESES mode. |
---|
37 | */ |
---|
38 | |
---|
39 | /** |
---|
40 | @file |
---|
41 | @ingroup String |
---|
42 | @brief A helper class to split a string into several tokens. |
---|
43 | |
---|
44 | @anchor SubStringExample |
---|
45 | |
---|
46 | The class SubString can be used to split an std::string into multiple tokens, using |
---|
47 | a delimiter. SubString allows different options, for example to remove whitespaces |
---|
48 | around the delimiters or different safe-mode chars, like quotation marks and braces. |
---|
49 | |
---|
50 | You can access the tokens of the SubString using the [] operator like an array. |
---|
51 | SubString also supports to join the tokens (or a subset of the tokens) again using |
---|
52 | @ref orxonox::SubString::join() "join()". It's even possible to get a subset of the |
---|
53 | SubString as another SubString using @ref orxonox::SubString::subSet() "subSet()". |
---|
54 | |
---|
55 | Example: |
---|
56 | @code |
---|
57 | std::string text = "This is a test, \"Hello \\\" World\" and vector {1, 2, 3}"; |
---|
58 | SubString tokens(text, SubString::WhiteSpaces, "", false, '\\', true, '"', true, '{', '}', true, '\0'); |
---|
59 | |
---|
60 | for (size_t i = 0; i < tokens.size(); ++i) |
---|
61 | orxout() << i << ": " << tokens[i] << endl; |
---|
62 | @endcode |
---|
63 | |
---|
64 | The output of this code is: |
---|
65 | - 0: This |
---|
66 | - 1: is |
---|
67 | - 2: a |
---|
68 | - 3: test, |
---|
69 | - 4: Hello " World |
---|
70 | - 5: and |
---|
71 | - 6: vector |
---|
72 | - 7: 1, 2, 3 |
---|
73 | |
---|
74 | The string was split using the delimiter " ". A string between quotation mark is not |
---|
75 | split, the same holds for strings between '{' and '}'. Note how the quotation marks and |
---|
76 | the braces were removed from the tokens, because the corresponding argument is 'true'. |
---|
77 | |
---|
78 | Also note that the comma after "test" in token 3 is still there - it is neither part of the |
---|
79 | delimiters SubString::WhiteSpaces nor part of the delimiterNeighbours parameter, so it |
---|
80 | remains a part of the token. |
---|
81 | */ |
---|
82 | |
---|
83 | #ifndef __SubString_H__ |
---|
84 | #define __SubString_H__ |
---|
85 | |
---|
86 | #include "UtilPrereqs.h" |
---|
87 | |
---|
88 | #include <vector> |
---|
89 | #include <string> |
---|
90 | |
---|
91 | namespace orxonox |
---|
92 | { |
---|
93 | /** |
---|
94 | @brief A class that splits a string into multiple tokens using different options. |
---|
95 | |
---|
96 | The string is split into multiple tokens using a delimiter. Different options like |
---|
97 | escape character, quotation marks, and more can be used to satisfy your needs. |
---|
98 | |
---|
99 | See @ref SubStringExample "this description" for an example. |
---|
100 | */ |
---|
101 | class _UtilExport SubString |
---|
102 | { |
---|
103 | /// An enumerator for the internal state of the parser |
---|
104 | enum class SPLIT_LINE_STATE |
---|
105 | { |
---|
106 | NORMAL, //!< Normal state |
---|
107 | ESCAPE, //!< After an escape character |
---|
108 | SAFEMODE, //!< In safe mode (usually between quotation marks). |
---|
109 | SAFEESCAPE, //!< In safe mode with the internal escape character, that escapes even the savemode character. |
---|
110 | COMMENT, //!< In Comment mode. |
---|
111 | PARENTHESES, //!< Between parentheses (usually '{' and '}') |
---|
112 | PARENTHESESESCAPE, //!< Between parentheses with the internal escape character, that escapes even the closing parenthesis character. |
---|
113 | }; |
---|
114 | |
---|
115 | public: |
---|
116 | SubString(); |
---|
117 | SubString(const std::string& line, |
---|
118 | const std::string& delimiters = SubString::WhiteSpaces, |
---|
119 | const std::string& delimiterNeighbours = "", |
---|
120 | bool bAllowEmptyEntries=false, |
---|
121 | char escapeChar ='\\', |
---|
122 | bool bRemoveEscapeChar = true, |
---|
123 | char safemodeChar = '"', |
---|
124 | bool bRemoveSafemodeChar = true, |
---|
125 | char openparenthesisChar = '{', |
---|
126 | char closeparenthesisChar = '}', |
---|
127 | bool bRemoveParenthesisChars = true, |
---|
128 | char commentChar = '\0'); |
---|
129 | SubString(size_t argc, const char** argv); |
---|
130 | SubString(const SubString& other, size_t begin, size_t length = std::string::npos); |
---|
131 | ~SubString(); |
---|
132 | |
---|
133 | // operate on the SubString |
---|
134 | SubString& operator=(const SubString& other); |
---|
135 | bool operator==(const SubString& other) const; |
---|
136 | bool compare(const SubString& other, size_t length = std::string::npos) const; |
---|
137 | SubString operator+(const SubString& other) const; |
---|
138 | SubString& operator+=(const SubString& other); |
---|
139 | /// Appends the tokens of another SubString to this. @return This SubString. |
---|
140 | inline SubString& append(const SubString& other) { return (*this += other); } |
---|
141 | |
---|
142 | ///////////////////////////////////////// |
---|
143 | // Split and Join the any String. /////// |
---|
144 | size_t split(const std::string& line, |
---|
145 | const std::string& delimiters = SubString::WhiteSpaces, |
---|
146 | const std::string& delimiterNeighbours = "", |
---|
147 | bool bAllowEmptyEntries = false, |
---|
148 | char escapeChar ='\\', |
---|
149 | bool bRemoveEscapeChar = true, |
---|
150 | char safemodeChar = '"', |
---|
151 | bool bRemoveSafemodeChar = true, |
---|
152 | char openparenthesisChar = '{', |
---|
153 | char closeparenthesisChar = '}', |
---|
154 | bool bRemoveParenthesisChars = true, |
---|
155 | char commentChar = '\0'); |
---|
156 | |
---|
157 | std::string join(const std::string& delimiter = " ") const; |
---|
158 | //////////////////////////////////////// |
---|
159 | |
---|
160 | // retrieve a SubSet from the String |
---|
161 | SubString subSet(size_t begin, size_t length = std::string::npos) const; |
---|
162 | |
---|
163 | // retrieve Information from within |
---|
164 | /// Returns true if the SubString is empty |
---|
165 | inline bool empty() const { return this->tokens_.empty(); } |
---|
166 | /// Returns the number of tokens stored in this SubString |
---|
167 | inline size_t size() const { return this->tokens_.size(); } |
---|
168 | /// Returns the i'th token from the subset of strings @param index The index of the requested token |
---|
169 | inline const std::string& operator[](size_t index) const { return this->tokens_[index]; } |
---|
170 | /// Returns the i'th token from the subset of strings @param index The index of the requested token |
---|
171 | inline const std::string& getString(size_t index) const { return (*this)[index]; } |
---|
172 | /// Returns all tokens as std::vector |
---|
173 | inline const std::vector<std::string>& getAllStrings() const { return this->tokens_; } |
---|
174 | /// Returns true if the token is in safemode. @param index The index of the token |
---|
175 | inline bool isInSafemode(size_t index) const { return this->bTokenInSafemode_[index]; } |
---|
176 | /// Returns the front of the list of tokens. |
---|
177 | inline const std::string& front() const { return this->tokens_.front(); } |
---|
178 | /// Returns the back of the list of tokens. |
---|
179 | inline const std::string& back() const { return this->tokens_.back(); } |
---|
180 | /// Removes the back of the list of tokens. |
---|
181 | inline void pop_back() { this->tokens_.pop_back(); this->bTokenInSafemode_.pop_back(); } |
---|
182 | |
---|
183 | void debug() const; |
---|
184 | |
---|
185 | public: |
---|
186 | static const std::string WhiteSpaces; ///< All whitespaces (usually used as delimiters or delimiterNeighbours |
---|
187 | static const std::string WhiteSpacesWithComma; ///< All whitespaces and the comma (usually used as delimiters) |
---|
188 | static const SubString NullSubString; ///< An empty SubString |
---|
189 | |
---|
190 | private: |
---|
191 | // the almighty algorithm. |
---|
192 | static SPLIT_LINE_STATE splitLine(std::vector<std::string>& tokens, |
---|
193 | std::vector<bool>& bTokenInSafemode, |
---|
194 | const std::string& line, |
---|
195 | const std::string& delimiters = SubString::WhiteSpaces, |
---|
196 | const std::string& delimiterNeighbours = "", |
---|
197 | bool bAllowEmptyEntries = false, |
---|
198 | char escapeChar = '\\', |
---|
199 | bool bRemoveEscapeChar = true, |
---|
200 | char safemodeChar = '"', |
---|
201 | bool bRemoveSafemodeChar = true, |
---|
202 | char openparenthesisChar = '{', |
---|
203 | char closeparenthesisChar = '}', |
---|
204 | bool bRemoveParenthesisChars = true, |
---|
205 | char commentChar = '\0', |
---|
206 | SPLIT_LINE_STATE start_state = SPLIT_LINE_STATE::NORMAL); |
---|
207 | |
---|
208 | std::vector<std::string> tokens_; ///< The tokens after splitting the input line |
---|
209 | std::vector<bool> bTokenInSafemode_; ///< Saves for each token if it was in safe mode (between quotation marks or parenthesis) |
---|
210 | }; |
---|
211 | } |
---|
212 | |
---|
213 | #endif /* __SubString_H__ */ |
---|