UCommon
tokenizer.h
Go to the documentation of this file.
1// Copyright (C) 1999-2005 Open Source Telecom Corporation.
2// Copyright (C) 2006-2014 David Sugar, Tycho Softworks.
3// Copyright (C) 2015 Cherokees of Idaho.
4//
5// This program is free software; you can redistribute it and/or modify
6// it under the terms of the GNU General Public License as published by
7// the Free Software Foundation; either version 2 of the License, or
8// (at your option) any later version.
9//
10// This program is distributed in the hope that it will be useful,
11// but WITHOUT ANY WARRANTY; without even the implied warranty of
12// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
13// GNU General Public License for more details.
14//
15// You should have received a copy of the GNU Lesser General Public License
16// along this program. If not, see <http://www.gnu.org/licenses/>.
17//
18// As a special exception, you may use this file as part of a free software
19// library without restriction. Specifically, if other files instantiate
20// templates or use macros or inline functions from this file, or you compile
21// this file and link it with other files to produce an executable, this
22// file does not by itself cause the resulting executable to be covered by
23// the GNU General Public License. This exception does not however
24// invalidate any other reasons why the executable file might be covered by
25// the GNU General Public License.
26//
27// This exception applies only to the code released under the name GNU
28// Common C++. If you copy code from other releases into a copy of GNU
29// Common C++, as the General Public License permits, the exception does
30// not apply to the code that you add in this way. To avoid misleading
31// anyone as to the status of such modified files, you must delete
32// this exception notice from them.
33//
34// If you write modifications of your own for GNU Common C++, it is your choice
35// whether to permit this exception to apply to your modifications.
36// If you do not wish that, delete this exception notice.
37//
38
44#ifndef COMMONCPP_TOKENIZER_H_
45#define COMMONCPP_TOKENIZER_H_
46
47#ifndef COMMONCPP_CONFIG_H_
48#include <commoncpp/config.h>
49#endif
50
51#ifndef COMMONCPP_THREAD_H_
52#include <commoncpp/thread.h>
53#endif
54
55#ifndef COMMMONCPP_EXCEPTION_H_
56#include <commoncpp/exception.h>
57#endif
58
59namespace ost {
60
104class __EXPORT StringTokenizer {
105public:
111 static const char * const SPACE;
112
122 // maybe move more global ?
124
129 class __EXPORT iterator {
130 friend class StringTokenizer; // access our private constructors
131 private:
132 const StringTokenizer *myTok; // my StringTokenizer
133 const char *start; // start of current token
134 const char *tokEnd; // end of current token (->nxDelimiter)
135 const char *endp; // one before next token
136 char *token; // allocated token, if requested
137
138 // for initialization of the itEnd iterator
139 iterator(const StringTokenizer &tok, const char *end)
140 : myTok(&tok),tokEnd(0),endp(end),token(0) {}
141
142 iterator(const StringTokenizer &tok)
143 : myTok(&tok),tokEnd(0),endp(myTok->str-1),token(0) {
144 ++(*this); // init first token.
145 }
146
147 public:
148 iterator() : myTok(0),start(0),tokEnd(0),endp(0),token(0) {}
149
150 // see also: comment in implementation of operator++
151 virtual ~iterator()
152 { if (token) *token='\0'; delete [] token; }
153
157 // everything, but not responsible for the allocated token.
158 iterator(const iterator& i) :
159 myTok(i.myTok),start(i.start),tokEnd(i.tokEnd),
160 endp(i.endp),token(0) {}
161
165 // everything, but not responsible for the allocated token.
167 myTok = i.myTok;
168 start = i.start; endp = i.endp; tokEnd = i.tokEnd;
169 if ( token )
170 delete [] token;
171 token = 0;
172 return *this;
173 }
174
179
188 const char* operator*() THROWS (NoSuchElementException);
189
196 inline char nextDelimiter() const
197 {return (tokEnd) ? *tokEnd : '\0';}
198
203 // only compare the end-position. speed.
204 inline bool operator == (const iterator &other) const
205 {return (endp == other.endp);}
206
211 // only compare the end position. speed.
212 inline bool operator != (const iterator &other) const
213 {return (endp != other.endp);}
214 };
215private:
216 friend class StringTokenizer::iterator;
217 const char *str;
218 const char *delim;
219 bool skipAll, trim;
220 iterator itEnd;
221
222public:
261 StringTokenizer (const char *str,
262 const char *delim,
263 bool skipAllDelim = false,
264 bool trim = false);
265
275 StringTokenizer (const char *s);
276
281 {return iterator(*this);}
282
287 void setDelimiters (const char *d)
288 {delim = d;}
289
294 iterator begin(const char *d) {
295 delim = d;
296 return iterator(*this);
297 }
298
302 const iterator& end() const
303 {return itEnd;}
304};
305
306} // namespace ost
307
308#endif
309
GNU Common C++ exception model base classes.
Splits delimited string into tokens.
Definition tokenizer.h:104
void setDelimiters(const char *d)
changes the set of delimiters used in subsequent iterations.
Definition tokenizer.h:287
static const char *const SPACE
a delimiter string containing all usual whitespace delimiters.
Definition tokenizer.h:111
iterator begin() const
returns the begin iterator
Definition tokenizer.h:280
StringTokenizer(const char *str, const char *delim, bool skipAllDelim=false, bool trim=false)
creates a new StringTokenizer for a string and a given set of delimiters.
const iterator & end() const
the iterator marking the end.
Definition tokenizer.h:302
StringTokenizer(const char *s)
create a new StringTokenizer which splits the input string at whitespaces.
iterator begin(const char *d)
returns a begin iterator with an alternate set of delimiters.
Definition tokenizer.h:294
Exception thrown, if someone tried to read beyond the end of the tokens.
Definition tokenizer.h:123
The input forward iterator for tokens.
Definition tokenizer.h:129
iterator(const iterator &i)
copy constructor.
Definition tokenizer.h:158
iterator & operator++()
shifts this iterator to the next token in the string.
iterator & operator=(const iterator &i)
assignment operator.
Definition tokenizer.h:166
Common C++ thread class and sychronization objects.