Mercurial > repos > siyuan > prada
comparison pyPRADA_1.2/tools/bwa-0.5.7-mh/kseq.h @ 0:acc2ca1a3ba4
Uploaded
author | siyuan |
---|---|
date | Thu, 20 Feb 2014 00:44:58 -0500 |
parents | |
children |
comparison
equal
deleted
inserted
replaced
-1:000000000000 | 0:acc2ca1a3ba4 |
---|---|
1 /* The MIT License | |
2 | |
3 Copyright (c) 2008, by Heng Li <lh3@sanger.ac.uk> | |
4 | |
5 Permission is hereby granted, free of charge, to any person obtaining | |
6 a copy of this software and associated documentation files (the | |
7 "Software"), to deal in the Software without restriction, including | |
8 without limitation the rights to use, copy, modify, merge, publish, | |
9 distribute, sublicense, and/or sell copies of the Software, and to | |
10 permit persons to whom the Software is furnished to do so, subject to | |
11 the following conditions: | |
12 | |
13 The above copyright notice and this permission notice shall be | |
14 included in all copies or substantial portions of the Software. | |
15 | |
16 THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, | |
17 EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF | |
18 MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND | |
19 NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS | |
20 BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN | |
21 ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN | |
22 CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE | |
23 SOFTWARE. | |
24 */ | |
25 | |
26 #ifndef AC_KSEQ_H | |
27 #define AC_KSEQ_H | |
28 | |
29 #include <ctype.h> | |
30 #include <string.h> | |
31 #include <stdlib.h> | |
32 | |
33 #define __KS_TYPE(type_t) \ | |
34 typedef struct __kstream_t { \ | |
35 char *buf; \ | |
36 int begin, end, is_eof; \ | |
37 type_t f; \ | |
38 } kstream_t; | |
39 | |
40 #define ks_eof(ks) ((ks)->is_eof && (ks)->begin >= (ks)->end) | |
41 #define ks_rewind(ks) ((ks)->is_eof = (ks)->begin = (ks)->end = 0) | |
42 | |
43 #define __KS_BASIC(type_t, __bufsize) \ | |
44 static inline kstream_t *ks_init(type_t f) \ | |
45 { \ | |
46 kstream_t *ks = (kstream_t*)calloc(1, sizeof(kstream_t)); \ | |
47 ks->f = f; \ | |
48 ks->buf = (char*)malloc(__bufsize); \ | |
49 return ks; \ | |
50 } \ | |
51 static inline void ks_destroy(kstream_t *ks) \ | |
52 { \ | |
53 if (ks) { \ | |
54 free(ks->buf); \ | |
55 free(ks); \ | |
56 } \ | |
57 } | |
58 | |
59 #define __KS_GETC(__read, __bufsize) \ | |
60 static inline int ks_getc(kstream_t *ks) \ | |
61 { \ | |
62 if (ks->is_eof && ks->begin >= ks->end) return -1; \ | |
63 if (ks->begin >= ks->end) { \ | |
64 ks->begin = 0; \ | |
65 ks->end = __read(ks->f, ks->buf, __bufsize); \ | |
66 if (ks->end < __bufsize) ks->is_eof = 1; \ | |
67 if (ks->end == 0) return -1; \ | |
68 } \ | |
69 return (int)ks->buf[ks->begin++]; \ | |
70 } | |
71 | |
72 #ifndef KSTRING_T | |
73 #define KSTRING_T kstring_t | |
74 typedef struct __kstring_t { | |
75 size_t l, m; | |
76 char *s; | |
77 } kstring_t; | |
78 #endif | |
79 | |
80 #ifndef kroundup32 | |
81 #define kroundup32(x) (--(x), (x)|=(x)>>1, (x)|=(x)>>2, (x)|=(x)>>4, (x)|=(x)>>8, (x)|=(x)>>16, ++(x)) | |
82 #endif | |
83 | |
84 #define __KS_GETUNTIL(__read, __bufsize) \ | |
85 static int ks_getuntil(kstream_t *ks, int delimiter, kstring_t *str, int *dret) \ | |
86 { \ | |
87 if (dret) *dret = 0; \ | |
88 str->l = 0; \ | |
89 if (ks->begin >= ks->end && ks->is_eof) return -1; \ | |
90 for (;;) { \ | |
91 int i; \ | |
92 if (ks->begin >= ks->end) { \ | |
93 if (!ks->is_eof) { \ | |
94 ks->begin = 0; \ | |
95 ks->end = __read(ks->f, ks->buf, __bufsize); \ | |
96 if (ks->end < __bufsize) ks->is_eof = 1; \ | |
97 if (ks->end == 0) break; \ | |
98 } else break; \ | |
99 } \ | |
100 if (delimiter) { \ | |
101 for (i = ks->begin; i < ks->end; ++i) \ | |
102 if (ks->buf[i] == delimiter) break; \ | |
103 } else { \ | |
104 for (i = ks->begin; i < ks->end; ++i) \ | |
105 if (isspace(ks->buf[i])) break; \ | |
106 } \ | |
107 if (str->m - str->l < i - ks->begin + 1) { \ | |
108 str->m = str->l + (i - ks->begin) + 1; \ | |
109 kroundup32(str->m); \ | |
110 str->s = (char*)realloc(str->s, str->m); \ | |
111 } \ | |
112 memcpy(str->s + str->l, ks->buf + ks->begin, i - ks->begin); \ | |
113 str->l = str->l + (i - ks->begin); \ | |
114 ks->begin = i + 1; \ | |
115 if (i < ks->end) { \ | |
116 if (dret) *dret = ks->buf[i]; \ | |
117 break; \ | |
118 } \ | |
119 } \ | |
120 str->s[str->l] = '\0'; \ | |
121 return str->l; \ | |
122 } | |
123 | |
124 #define KSTREAM_INIT(type_t, __read, __bufsize) \ | |
125 __KS_TYPE(type_t) \ | |
126 __KS_BASIC(type_t, __bufsize) \ | |
127 __KS_GETC(__read, __bufsize) \ | |
128 __KS_GETUNTIL(__read, __bufsize) | |
129 | |
130 #define __KSEQ_BASIC(type_t) \ | |
131 static inline kseq_t *kseq_init(type_t fd) \ | |
132 { \ | |
133 kseq_t *s = (kseq_t*)calloc(1, sizeof(kseq_t)); \ | |
134 s->f = ks_init(fd); \ | |
135 return s; \ | |
136 } \ | |
137 static inline void kseq_rewind(kseq_t *ks) \ | |
138 { \ | |
139 ks->last_char = 0; \ | |
140 ks->f->is_eof = ks->f->begin = ks->f->end = 0; \ | |
141 } \ | |
142 static inline void kseq_destroy(kseq_t *ks) \ | |
143 { \ | |
144 if (!ks) return; \ | |
145 free(ks->name.s); free(ks->comment.s); free(ks->seq.s); free(ks->qual.s); \ | |
146 ks_destroy(ks->f); \ | |
147 free(ks); \ | |
148 } | |
149 | |
150 /* Return value: | |
151 >=0 length of the sequence (normal) | |
152 -1 end-of-file | |
153 -2 truncated quality string | |
154 */ | |
155 #define __KSEQ_READ \ | |
156 static int kseq_read(kseq_t *seq) \ | |
157 { \ | |
158 int c; \ | |
159 kstream_t *ks = seq->f; \ | |
160 if (seq->last_char == 0) { /* then jump to the next header line */ \ | |
161 while ((c = ks_getc(ks)) != -1 && c != '>' && c != '@'); \ | |
162 if (c == -1) return -1; /* end of file */ \ | |
163 seq->last_char = c; \ | |
164 } /* the first header char has been read */ \ | |
165 seq->comment.l = seq->seq.l = seq->qual.l = 0; \ | |
166 if (ks_getuntil(ks, 0, &seq->name, &c) < 0) return -1; \ | |
167 if (c != '\n') ks_getuntil(ks, '\n', &seq->comment, 0); \ | |
168 while ((c = ks_getc(ks)) != -1 && c != '>' && c != '+' && c != '@') { \ | |
169 if (isgraph(c)) { /* printable non-space character */ \ | |
170 if (seq->seq.l + 1 >= seq->seq.m) { /* double the memory */ \ | |
171 seq->seq.m = seq->seq.l + 2; \ | |
172 kroundup32(seq->seq.m); /* rounded to next closest 2^k */ \ | |
173 seq->seq.s = (char*)realloc(seq->seq.s, seq->seq.m); \ | |
174 } \ | |
175 seq->seq.s[seq->seq.l++] = (char)c; \ | |
176 } \ | |
177 } \ | |
178 if (c == '>' || c == '@') seq->last_char = c; /* the first header char has been read */ \ | |
179 seq->seq.s[seq->seq.l] = 0; /* null terminated string */ \ | |
180 if (c != '+') return seq->seq.l; /* FASTA */ \ | |
181 if (seq->qual.m < seq->seq.m) { /* allocate enough memory */ \ | |
182 seq->qual.m = seq->seq.m; \ | |
183 seq->qual.s = (char*)realloc(seq->qual.s, seq->qual.m); \ | |
184 } \ | |
185 while ((c = ks_getc(ks)) != -1 && c != '\n'); /* skip the rest of '+' line */ \ | |
186 if (c == -1) return -2; /* we should not stop here */ \ | |
187 while ((c = ks_getc(ks)) != -1 && seq->qual.l < seq->seq.l) \ | |
188 if (c >= 33 && c <= 127) seq->qual.s[seq->qual.l++] = (unsigned char)c; \ | |
189 seq->qual.s[seq->qual.l] = 0; /* null terminated string */ \ | |
190 seq->last_char = 0; /* we have not come to the next header line */ \ | |
191 if (seq->seq.l != seq->qual.l) return -2; /* qual string is shorter than seq string */ \ | |
192 return seq->seq.l; \ | |
193 } | |
194 | |
195 #define __KSEQ_TYPE(type_t) \ | |
196 typedef struct { \ | |
197 kstring_t name, comment, seq, qual; \ | |
198 int last_char; \ | |
199 kstream_t *f; \ | |
200 } kseq_t; | |
201 | |
202 #define KSEQ_INIT(type_t, __read) \ | |
203 KSTREAM_INIT(type_t, __read, 4096) \ | |
204 __KSEQ_TYPE(type_t) \ | |
205 __KSEQ_BASIC(type_t) \ | |
206 __KSEQ_READ | |
207 | |
208 #endif |