1 |
/********************************************************************** |
2 |
tokenst.cpp - Tokenize a string. |
3 |
|
4 |
Copyright (C) 1998-2001 by OpenEye Scientific Software, Inc. |
5 |
Some portions Copyright (C) 2001-2005 by Geoffrey R. Hutchison |
6 |
|
7 |
This file is part of the Open Babel project. |
8 |
For more information, see <http://openbabel.sourceforge.net/> |
9 |
|
10 |
This program is free software; you can redistribute it and/or modify |
11 |
it under the terms of the GNU General Public License as published by |
12 |
the Free Software Foundation version 2 of the License. |
13 |
|
14 |
This program is distributed in the hope that it will be useful, |
15 |
but WITHOUT ANY WARRANTY; without even the implied warranty of |
16 |
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
17 |
GNU General Public License for more details. |
18 |
***********************************************************************/ |
19 |
|
20 |
#ifdef WIN32 |
21 |
#pragma warning (disable : 4786) |
22 |
#endif |
23 |
|
24 |
#include <algorithm> |
25 |
#include <vector> |
26 |
#include <string> |
27 |
|
28 |
#include "config.h" |
29 |
|
30 |
using namespace std; |
31 |
/* |
32 |
OBAPI bool tokenize(vector<string> &, const char *, const char *); |
33 |
OBAPI char *trim_spaces(char *string); |
34 |
OBAPI bool tokenize(vector<string> &vcr, string &s, const char *delimstr,int limit=-1); |
35 |
*/ |
36 |
namespace OpenBabel |
37 |
{ |
38 |
|
39 |
//! Break a string (supplied as the second argument) into tokens, returned |
40 |
//! in the first argument. Tokens are determined by the delimiters supplied |
41 |
//! (defaults to whitespace (i.e., spaces, tabs, newlines) |
42 |
OBAPI bool tokenize(vector<string> &vcr, const char *buf, const char *delimstr) |
43 |
{ |
44 |
vcr.clear(); |
45 |
string s = buf; |
46 |
s += "\n"; |
47 |
size_t startpos=0,endpos=0; |
48 |
|
49 |
for (;;) |
50 |
{ |
51 |
startpos = s.find_first_not_of(delimstr,startpos); |
52 |
endpos = s.find_first_of(delimstr,startpos); |
53 |
|
54 |
if (endpos <= s.size() && startpos <= s.size()) |
55 |
vcr.push_back(s.substr(startpos,endpos-startpos)); |
56 |
else |
57 |
break; |
58 |
|
59 |
startpos = endpos+1; |
60 |
} |
61 |
|
62 |
return(true); |
63 |
} |
64 |
|
65 |
//! Trim any trailing spaces at the end of the supplied string. |
66 |
OBAPI char *trim_spaces(char *string) |
67 |
{ |
68 |
int length; |
69 |
|
70 |
length = strlen(string); |
71 |
if (length == 0) |
72 |
return string; |
73 |
|
74 |
while ((length > 0) && (string[0] == ' ')) |
75 |
{ |
76 |
string++; |
77 |
--length; |
78 |
} |
79 |
|
80 |
if (length > 0) |
81 |
{ |
82 |
while ((length > 0) && (string[length-1] == ' ')) |
83 |
{ |
84 |
string[length-1] = '\0'; |
85 |
--length; |
86 |
} |
87 |
} |
88 |
|
89 |
return(string); |
90 |
} |
91 |
|
92 |
//! Break a string (supplied as the second argument) into tokens, returned |
93 |
//! in the first argument. Tokens are determined by the delimiters supplied |
94 |
//! (defaults to whitespace (i.e., spaces, tabs, newlines) |
95 |
//! Only breaks at most 'limit' tokens and the last item in the vector may |
96 |
//! include un-parsed tokens. |
97 |
OBAPI bool tokenize(vector<string> &vcr, string &s, const char *delimstr, int limit) |
98 |
{ |
99 |
vcr.clear(); |
100 |
size_t startpos=0,endpos=0; |
101 |
|
102 |
int matched=0; |
103 |
unsigned int s_size = s.size(); |
104 |
for (;;) |
105 |
{ |
106 |
startpos = s.find_first_not_of(delimstr,startpos); |
107 |
endpos = s.find_first_of(delimstr,startpos); |
108 |
if (endpos <= s_size && startpos <= s_size) |
109 |
{ |
110 |
vcr.push_back(s.substr(startpos,endpos-startpos)); |
111 |
|
112 |
matched++; |
113 |
if (matched == limit) |
114 |
{ |
115 |
startpos = endpos+1; |
116 |
vcr.push_back(s.substr(startpos,s_size)); |
117 |
break; |
118 |
} |
119 |
} |
120 |
else |
121 |
{ |
122 |
if (startpos < s_size) |
123 |
vcr.push_back(s.substr(startpos,s_size-startpos)); |
124 |
break; |
125 |
} |
126 |
|
127 |
startpos = endpos+1; |
128 |
} |
129 |
return(true); |
130 |
} |
131 |
|
132 |
OBAPI void Trim(string& txt) |
133 |
{ |
134 |
string::size_type pos = txt.find_last_not_of(" \t\n\r"); |
135 |
if(pos!=string::npos) |
136 |
txt.erase(pos+1); |
137 |
else |
138 |
txt.erase(); |
139 |
|
140 |
pos = txt.find_first_not_of(" \t\n\r"); |
141 |
if(pos!=string::npos) |
142 |
txt.erase(0, pos); |
143 |
else |
144 |
txt.erase(); |
145 |
} |
146 |
|
147 |
} // end namespace OpenBabel |
148 |
|
149 |
//! \file tokenst.cpp |
150 |
//! \brief Tokenize a string. |