Mercurial > repos > calkan > mrsfast

comparison mrsfast-2.3.0.2/RefGenome.c @ 0:ec628ba33878 default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded source code for mrsFAST
author calkan
date Tue, 21 Feb 2012 10:39:28 -0500
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:ec628ba33878
1 /*
2 * Copyright (c) <2008 - 2009>, University of Washington, Simon Fraser University
3 * All rights reserved.
4 *
5 * Redistribution and use in source and binary forms, with or without modification,
6 * are permitted provided that the following conditions are met:
7 *
8 * Redistributions of source code must retain the above copyright notice, this list
9 * of conditions and the following disclaimer.
10 * - Redistributions in binary form must reproduce the above copyright notice, this
11 * list of conditions and the following disclaimer in the documentation and/or other
12 * materials provided with the distribution.
13 * - Neither the name of the <ORGANIZATION> nor the names of its contributors may be
14 * used to endorse or promote products derived from this software without specific
15 * prior written permission.
16 *
17 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
18 * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
19 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
20 * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
21 * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
22 * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
23 * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
24 * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
25 * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
26 * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
27 * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
28 */
29
30 /*
31 * Author : Faraz Hach
32 * Email : fhach AT cs DOT sfu
33 * Last Update : 2009-12-08
34 */
35
36
37 #include <stdio.h>
38 #include <stdlib.h>
39 #include <string.h>
40 #include <ctype.h>
41 #include "Common.h"
42 #include "RefGenome.h"
43
44 FILE *_rg_fp;
45 char *_rg_gen;
46 char *_rg_name;
47 int _rg_offset;
48 int _rg_contGen;
49
50 /**********************************************/
51 int initLoadingRefGenome(char *fileName)
52 {
53 char ch;
54 _rg_fp = fileOpen (fileName, "r");
55 if (fscanf(_rg_fp, "%c", &ch))
56 {
57 if (ch == '>')
58 {
59 _rg_contGen = 0;
60 _rg_offset = 0;
61 _rg_gen = getMem(CONTIG_MAX_SIZE);
62 _rg_name = getMem(CONTIG_NAME_SIZE);
63 return 1;
64 }
65 }
66 return 0;
67 }
68 /**********************************************/
69 void finalizeLoadingRefGenome()
70 {
71 freeMem(_rg_gen, CONTIG_MAX_SIZE);
72 freeMem(_rg_name, CONTIG_NAME_SIZE);
73 fclose(_rg_fp);
74 }
75 /**********************************************/
76 int loadRefGenome(char **refGen, char **refGenName, int *refGenOff)
77 {
78 char ch;
79 int i;
80 int returnVal = 0;
81 int actualSize=0;
82 int size;
83 char *tmp;
84
85 // New Conting
86 if (!_rg_contGen)
87 {
88 size = 0;
89 tmp = fgets(_rg_name, SEQ_MAX_LENGTH, _rg_fp);
90 int k;
91 for (k=0; k<strlen(_rg_name);k++)
92 {
93 if (_rg_name[k] == ' ')
94 {
95 _rg_name[k]='\0';
96 break;
97 }
98 }
99
100 }
101 else
102 {
103 size=strlen(_rg_gen);
104 for( i = 0 ; i < CONTIG_OVERLAP ; i++ )
105 {
106
107 _rg_gen[i] = _rg_gen[size-CONTIG_OVERLAP+i];
108 if (_rg_gen[i] != 'N')
109 actualSize++;
110 }
111 size = CONTIG_OVERLAP;
112 }
113 while( fscanf(_rg_fp, "%c", &ch) > 0 )
114 {
115 if (ch == '>')
116 {
117 _rg_contGen = 0;
118 returnVal = 1;
119 break;
120 }
121 else if (!isspace(ch))
122 {
123 ch = toupper(ch);
124 _rg_gen[size++] = ch;
125 if (ch != 'N')
126 {
127 actualSize++;
128 }
129 if (actualSize == CONTIG_SIZE || size == CONTIG_MAX_SIZE)
130 {
131 _rg_contGen = 1;
132 returnVal=1;
133 break;
134 }
135 }
136
137 }
138
139 _rg_gen[size] = '\0';
140 for (i=strlen(_rg_name)-1; i >= 0; i--)
141 if (!isspace(_rg_name[i]))
142 break;
143 _rg_name[i+1] = '\0';
144
145 *refGenOff = _rg_offset;
146 *refGenName = _rg_name;
147 *refGen = _rg_gen;
148
149 if (_rg_contGen == 1)
150 {
151 _rg_offset += size-CONTIG_OVERLAP;
152 }
153 else
154 {
155 _rg_offset = 0;
156 }
157
158
159 return returnVal;
160 }
161 /**********************************************/