src/utils/StringUtils.cpp

/*
 * Copyright (c) 2005 The University of Notre Dame. All Rights Reserved.
 *
 * The University of Notre Dame grants you ("Licensee") a
 * non-exclusive, royalty free, license to use, modify and
 * redistribute this software in source and binary code form, provided
 * that the following conditions are met:
 *
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 *
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in the
 *    documentation and/or other materials provided with the
 *    distribution.
 *
 * This software is provided "AS IS," without a warranty of any
 * kind. All express or implied conditions, representations and
 * warranties, including any implied warranty of merchantability,
 * fitness for a particular purpose or non-infringement, are hereby
 * excluded.  The University of Notre Dame and its licensors shall not
 * be liable for any damages suffered by licensee as a result of
 * using, modifying or distributing the software or its
 * derivatives. In no event will the University of Notre Dame or its
 * licensors be liable for any lost revenue, profit or data, or for
 * direct, indirect, special, consequential, incidental or punitive
 * damages, however caused and regardless of the theory of liability,
 * arising out of the use of or inability to use software, even if the
 * University of Notre Dame has been advised of the possibility of
 * such damages.
 *
 * SUPPORT OPEN SCIENCE!  If you use OpenMD or its source code in your
 * research, please cite the appropriate papers when you publish your
 * work.  Good starting points are:
 *                                                                      
 * [1]  Meineke, et al., J. Comp. Chem. 26, 252-271 (2005).             
 * [2]  Fennell & Gezelter, J. Chem. Phys. 124, 234104 (2006).          
 * [3]  Sun, Lin & Gezelter, J. Chem. Phys. 128, 24107 (2008).          
 * [4]  Vardeman & Gezelter, in progress (2009).                        
 */

#include <algorithm> 
#include <stdlib.h>
#include "utils/StringUtils.hpp"

namespace OpenMD {
  std::string UpperCase(const std::string& S) {
    std::string uc = S;
    unsigned int n = uc.size();
    for (unsigned int j = 0; j < n; j++) {   
      char sj = uc[j];
      if (sj >= 'a' && sj <= 'z') uc[j] = (char)(sj - ('a' - 'A'));
    }
    return uc;
  }

  std::string LowerCase(const std::string& S) {
    std::string lc = S;
    unsigned int n = lc.size();
    for (unsigned int j = 0; j < n; j++) {
      char sj = lc[j];
      if (sj >= 'A' && sj <= 'Z') lc[j] = (char)(sj + ('a' - 'A'));
    }
    return lc;
  }

  char* trimSpaces(char *str) {
    size_t len;
    char *right, *left;

    if (strlen(str) == 0) return(str);
  
    /* Trim whitespace from left side */
    for (left = str; isspace(*left); left++);

    /* Trim whitespace from right side */
    if ((len = strlen(left)))
      {
        right = left + (len - 1);
      
        while (isspace(*right))
          {
            *right = '\0';
            right--;
          }
      }

    /* Only do the str copy if there were spaces to the left */
    if (left != str)
      strcpy(str, left);
  
    return (str);
  }

  int findBegin(std::istream &theStream, const char* startText ){
    const int MAXLEN = 1024;
    char readLine[MAXLEN];   
    int foundText = 0;
    int lineNum;
    char* the_token;
    char* eof_test;

    // rewind the stream
    theStream.seekg (0, std::ios::beg);
    lineNum = 0;
  
    if (!theStream.eof()) {
      theStream.getline(readLine, MAXLEN);
      lineNum++;
    } else {
      printf( "Error fast forwarding stream: stream is empty.\n");
      return -1;
    }
  
    while ( !foundText ) {
    
      if (theStream.eof()) {
        printf("Error fast forwarding stream at line %d: "
               "stream ended unexpectedly.\n", lineNum);
        return -1;
      }
    
      the_token = strtok( readLine, " ,;\t" );
      if ( the_token != NULL)
        if (!strcasecmp("begin", the_token)) {
          the_token = strtok( NULL, " ,;\t" );
          if ( the_token != NULL){
            foundText = !strcasecmp( startText, the_token );
          }
        }
    
      if (!foundText) {
        if (!theStream.eof()) {
          theStream.getline(readLine, MAXLEN);
          lineNum++;
        } else {
          printf( "Error fast forwarding stream at line %d: "
                  "stream ended unexpectedly.\n", lineNum);
          return -1;
        }
      }
    }
    return lineNum;
  }

  int countTokens(char *line, char *delimiters) {
    /* PURPOSE: RETURN A COUNT OF THE NUMBER OF TOKENS ON THE LINE. */
  
    char *working_line;   /* WORKING COPY OF LINE. */
    int ntokens;          /* NUMBER OF TOKENS FOUND IN LINE. */
    char *strtok_ptr;     /* POINTER FOR STRTOK. */

    strtok_ptr= working_line= strdup(line);

    ntokens=0;
    while (strtok(strtok_ptr,delimiters)!=NULL)
      {
        ntokens++;
        strtok_ptr=NULL;
      }

    free(working_line);
    return(ntokens);
  }

  int isEndLine(char *line) {
    char *working_line;
    char *foo;
  
    working_line = strdup(line);
  
    foo = strtok(working_line, " ,;\t");

    if (foo != NULL) {

      if (!strcasecmp(foo, "end")) return 1;

    }
 
    return 0;
  }
  
  std::string OpenMD_itoa(int value, unsigned int base) {    
    const char digitMap[] = "0123456789abcdef"; 
    std::string buf;

    if (base == 0 || base > 16) {      
      return buf;
    }

    if (value == 0) {
      buf = "0";
      return buf;
    }
    
    // Take care negative int:
        
    std::string sign;    
    int _value = value; 
    if (value < 0) {
      _value = -value;
      sign = "-";
    }

    // Translating number to string with base:
    for (int i = 30; _value && i ; --i) {
      buf = digitMap[ _value % base ] + buf;
      _value /= base;
    }
    return sign.append(buf);
  }


  std::string getPrefix(const std::string& str) {
    return str.substr(0, str.rfind('.'));
  }

  std::string getSuffix(const std::string& str) {
    return str.substr(0, str.find('.'));
  }
  
  bool isInteger(const std::string& str) {
    
    bool result = false;
    
    std::string::const_iterator i = str.begin();    
    if (i != str.end() && (*i == '+' || *i == '-' || std::isdigit(*i) )) {
      ++i;        
      while (i != str.end() && std::isdigit(*i))
        ++i;
      if (i == str.end())
        result = true;
    }
    
    return result;
  }

  bool CaseInsensitiveEquals(const char ch1, const char ch2) {
    return std::toupper((unsigned char)ch1) == std::toupper((unsigned char)ch2);
  }
  
  size_t CaseInsensitiveFind(const std::string& str1, const std::string& str2) {
    std::string::const_iterator pos = std::search(str1.begin(), str1.end(), str2.begin(), str2.end(), CaseInsensitiveEquals);
    if (pos == str1.end())
      return std::string::npos;
    else
      return pos - str1.begin();
  }
  
  /**
   *    memparse - parse a string with mem suffixes into a number
   *    @ptr: Where parse begins
   *    @retptr: (output) Pointer to next char after parse completes
   *
   *    Parses a string into a number.  The number stored at @ptr is
   *    potentially suffixed with %K (for kilobytes, or 1024 bytes),
   *    %M (for megabytes, or 1048576 bytes), or %G (for gigabytes, or
   *    1073741824).  If the number is suffixed with K, M, or G, then
   *    the return value is the number multiplied by one kilobyte, one
   *    megabyte, or one gigabyte, respectively.
   */  
  unsigned long long memparse (char *ptr,  char **retptr) {
    unsigned long long ret = strtoull (ptr, retptr, 0);
    
    switch (**retptr) {
    case 'G':
    case 'g':
      ret <<= 10;
    case 'M':
    case 'm':
      ret <<= 10;
    case 'K':
    case 'k':
      ret <<= 10;
      (*retptr)++;
    default:
      break;
    }
    return ret;
  }
  
}
Revision:	1654
Committed:	Wed Sep 28 19:40:45 2011 UTC (13 years, 7 months ago) by gezelter
File size:	7993 byte(s)
Log Message:	fixed a compile bug for PGI
#	User	Rev	Content
1	gezelter	406	/*
2	gezelter	246	* Copyright (c) 2005 The University of Notre Dame. All Rights Reserved.
3			*
4			* The University of Notre Dame grants you ("Licensee") a
5			* non-exclusive, royalty free, license to use, modify and
6			* redistribute this software in source and binary code form, provided
7			* that the following conditions are met:
8			*
9	gezelter	1390	* 1. Redistributions of source code must retain the above copyright
10	gezelter	246	* notice, this list of conditions and the following disclaimer.
11			*
12	gezelter	1390	* 2. Redistributions in binary form must reproduce the above copyright
13	gezelter	246	* notice, this list of conditions and the following disclaimer in the
14			* documentation and/or other materials provided with the
15			* distribution.
16			*
17			* This software is provided "AS IS," without a warranty of any
18			* kind. All express or implied conditions, representations and
19			* warranties, including any implied warranty of merchantability,
20			* fitness for a particular purpose or non-infringement, are hereby
21			* excluded. The University of Notre Dame and its licensors shall not
22			* be liable for any damages suffered by licensee as a result of
23			* using, modifying or distributing the software or its
24			* derivatives. In no event will the University of Notre Dame or its
25			* licensors be liable for any lost revenue, profit or data, or for
26			* direct, indirect, special, consequential, incidental or punitive
27			* damages, however caused and regardless of the theory of liability,
28			* arising out of the use of or inability to use software, even if the
29			* University of Notre Dame has been advised of the possibility of
30			* such damages.
31	gezelter	1390	*
32			* SUPPORT OPEN SCIENCE! If you use OpenMD or its source code in your
33			* research, please cite the appropriate papers when you publish your
34			* work. Good starting points are:
35			*
36			* [1] Meineke, et al., J. Comp. Chem. 26, 252-271 (2005).
37			* [2] Fennell & Gezelter, J. Chem. Phys. 124, 234104 (2006).
38			* [3] Sun, Lin & Gezelter, J. Chem. Phys. 128, 24107 (2008).
39			* [4] Vardeman & Gezelter, in progress (2009).
40	gezelter	246	*/
41	tim	1024
42			#include <algorithm>
43	gezelter	1654	#include <stdlib.h>
44	tim	3	#include "utils/StringUtils.hpp"
45	gezelter	2
46	gezelter	1390	namespace OpenMD {
47	gezelter	406	std::string UpperCase(const std::string& S) {
48			std::string uc = S;
49			unsigned int n = uc.size();
50			for (unsigned int j = 0; j < n; j++) {
51			char sj = uc[j];
52			if (sj >= 'a' && sj <= 'z') uc[j] = (char)(sj - ('a' - 'A'));
53			}
54			return uc;
55	gezelter	2	}
56
57	gezelter	406	std::string LowerCase(const std::string& S) {
58			std::string lc = S;
59			unsigned int n = lc.size();
60			for (unsigned int j = 0; j < n; j++) {
61			char sj = lc[j];
62			if (sj >= 'A' && sj <= 'Z') lc[j] = (char)(sj + ('a' - 'A'));
63			}
64			return lc;
65	gezelter	2	}
66	gezelter	97
67	gezelter	406	char* trimSpaces(char *str) {
68			size_t len;
69			char right, left;
70	chrisfen	105
71	gezelter	406	if (strlen(str) == 0) return(str);
72	chrisfen	105
73	gezelter	406	/* Trim whitespace from left side */
74			for (left = str; isspace(*left); left++);
75	chrisfen	105
76	gezelter	406	/* Trim whitespace from right side */
77			if ((len = strlen(left)))
78			{
79			right = left + (len - 1);
80	chrisfen	105
81	gezelter	406	while (isspace(*right))
82			{
83			*right = '\0';
84			right--;
85			}
86			}
87	chrisfen	105
88	gezelter	406	/* Only do the str copy if there were spaces to the left */
89			if (left != str)
90			strcpy(str, left);
91	chrisfen	105
92	gezelter	406	return (str);
93			}
94	chrisfen	105
95	skuang	1305	int findBegin(std::istream &theStream, const char* startText ){
96	gezelter	406	const int MAXLEN = 1024;
97			char readLine[MAXLEN];
98			int foundText = 0;
99			int lineNum;
100			char* the_token;
101			char* eof_test;
102	gezelter	97
103	gezelter	406	// rewind the stream
104			theStream.seekg (0, std::ios::beg);
105			lineNum = 0;
106	gezelter	97
107	gezelter	406	if (!theStream.eof()) {
108			theStream.getline(readLine, MAXLEN);
109			lineNum++;
110			} else {
111			printf( "Error fast forwarding stream: stream is empty.\n");
112	gezelter	97	return -1;
113			}
114	gezelter	406
115			while ( !foundText ) {
116	chrisfen	105
117	gezelter	406	if (theStream.eof()) {
118			printf("Error fast forwarding stream at line %d: "
119			"stream ended unexpectedly.\n", lineNum);
120			return -1;
121	chrisfen	105	}
122
123	gezelter	406	the_token = strtok( readLine, " ,;\t" );
124			if ( the_token != NULL)
125			if (!strcasecmp("begin", the_token)) {
126			the_token = strtok( NULL, " ,;\t" );
127			if ( the_token != NULL){
128			foundText = !strcasecmp( startText, the_token );
129			}
130			}
131
132			if (!foundText) {
133			if (!theStream.eof()) {
134			theStream.getline(readLine, MAXLEN);
135			lineNum++;
136			} else {
137			printf( "Error fast forwarding stream at line %d: "
138			"stream ended unexpectedly.\n", lineNum);
139			return -1;
140			}
141	gezelter	97	}
142			}
143	gezelter	406	return lineNum;
144	gezelter	97	}
145
146	gezelter	406	int countTokens(char line, char delimiters) {
147			/* PURPOSE: RETURN A COUNT OF THE NUMBER OF TOKENS ON THE LINE. */
148	gezelter	97
149	gezelter	406	char working_line; / WORKING COPY OF LINE. */
150			int ntokens; /* NUMBER OF TOKENS FOUND IN LINE. */
151			char strtok_ptr; / POINTER FOR STRTOK. */
152	gezelter	97
153	gezelter	406	strtok_ptr= working_line= strdup(line);
154	gezelter	97
155	gezelter	406	ntokens=0;
156			while (strtok(strtok_ptr,delimiters)!=NULL)
157			{
158			ntokens++;
159			strtok_ptr=NULL;
160			}
161	gezelter	97
162	gezelter	406	free(working_line);
163			return(ntokens);
164			}
165	gezelter	97
166	gezelter	406	int isEndLine(char *line) {
167			char *working_line;
168			char *foo;
169	gezelter	97
170	gezelter	406	working_line = strdup(line);
171	gezelter	97
172	gezelter	406	foo = strtok(working_line, " ,;\t");
173	gezelter	97
174	gezelter	406	if (foo != NULL) {
175	gezelter	107
176	gezelter	406	if (!strcasecmp(foo, "end")) return 1;
177	gezelter	107
178	gezelter	406	}
179
180			return 0;
181	gezelter	107	}
182	gezelter	406
183	gezelter	1390	std::string OpenMD_itoa(int value, unsigned int base) {
184	gezelter	406	const char digitMap[] = "0123456789abcdef";
185			std::string buf;
186	gezelter	246
187	gezelter	406	if (base == 0 \|\| base > 16) {
188			return buf;
189			}
190	gezelter	246
191	gezelter	406	if (value == 0) {
192			buf = "0";
193			return buf;
194			}
195
196			// Take care negative int:
197
198			std::string sign;
199			int _value = value;
200			if (value < 0) {
201			_value = -value;
202			sign = "-";
203			}
204	gezelter	246
205	gezelter	406	// Translating number to string with base:
206			for (int i = 30; _value && i ; --i) {
207			buf = digitMap[ _value % base ] + buf;
208			_value /= base;
209			}
210			return sign.append(buf);
211			}
212
213
214			std::string getPrefix(const std::string& str) {
215			return str.substr(0, str.rfind('.'));
216			}
217
218			std::string getSuffix(const std::string& str) {
219	gezelter	246	return str.substr(0, str.find('.'));
220	gezelter	406	}
221	gezelter	1629
222			bool isInteger(const std::string& str) {
223
224	tim	838	bool result = false;
225	gezelter	1629
226	tim	838	std::string::const_iterator i = str.begin();
227			if (i != str.end() && (i == '+' \|\| i == '-' \|\| std::isdigit(*i) )) {
228	gezelter	1629	++i;
229			while (i != str.end() && std::isdigit(*i))
230			++i;
231			if (i == str.end())
232			result = true;
233	tim	838	}
234
235			return result;
236	gezelter	1629	}
237	tim	838
238	gezelter	1629	bool CaseInsensitiveEquals(const char ch1, const char ch2) {
239			return std::toupper((unsigned char)ch1) == std::toupper((unsigned char)ch2);
240			}
241
242			size_t CaseInsensitiveFind(const std::string& str1, const std::string& str2) {
243			std::string::const_iterator pos = std::search(str1.begin(), str1.end(), str2.begin(), str2.end(), CaseInsensitiveEquals);
244			if (pos == str1.end())
245			return std::string::npos;
246			else
247			return pos - str1.begin();
248			}
249
250			/**
251			* memparse - parse a string with mem suffixes into a number
252			* @ptr: Where parse begins
253			* @retptr: (output) Pointer to next char after parse completes
254			*
255			* Parses a string into a number. The number stored at @ptr is
256			* potentially suffixed with %K (for kilobytes, or 1024 bytes),
257			* %M (for megabytes, or 1048576 bytes), or %G (for gigabytes, or
258			* 1073741824). If the number is suffixed with K, M, or G, then
259			* the return value is the number multiplied by one kilobyte, one
260			* megabyte, or one gigabyte, respectively.
261			*/
262			unsigned long long memparse (char ptr, char *retptr) {
263			unsigned long long ret = strtoull (ptr, retptr, 0);
264
265			switch (**retptr) {
266			case 'G':
267			case 'g':
268			ret <<= 10;
269			case 'M':
270			case 'm':
271			ret <<= 10;
272			case 'K':
273			case 'k':
274			ret <<= 10;
275			(*retptr)++;
276			default:
277			break;
278			}
279			return ret;
280			}
281
282	tim	838	}