-
Notifications
You must be signed in to change notification settings - Fork 1
/
ramp.c
1722 lines (1538 loc) · 56.2 KB
/
ramp.c
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
/***************************************************************************
RAMP
Non sequential parser for mzXML files
and mzData files, too!
-------------------
begin : Wed Oct 10
copyright : (C) 2003 by Pedrioli Patrick, ISB, Proteomics
email : [email protected]
additional work for C++, >2GB files in WIN32, and portability (C) 2004 by Brian Pratt, Insilicos LLC
additional work for mzData input (C) 2005 Brian Pratt Insilicos LLC
***************************************************************************/
/***************************************************************************
* This program is free software; you can redistribute it and/or modify *
* it under the terms of the GNU Library or "Lesser" General Public *
* License (LGPL) as published by the Free Software Foundation; *
* either version 2 of the License, or (at your option) any later *
* version. *
***************************************************************************/
#define _O_BINARY O_BINARY // for gcc under Cygwin
#define _O_RDONLY O_RDONLY // for gcc under Cygwin
#include "ramp.h"
#include "base64.h"
#include "time.h"
#include "zlib.h"
#define SIZE_BUF 512
#if defined __LITTLE_ENDIAN
#define swapbytes(x) ntohl(x) /* use system byteswap (ntohl is a noop on bigendian systems) */
#else
uint32_t swapbytes(uint32_t x) {
return ((x & 0x000000ffU) << 24) |
((x & 0x0000ff00U) << 8) |
((x & 0x00ff0000U) >> 8) |
((x & 0xff000000U) >> 24);
}
#endif
uint64_t swapbytes64(uint64_t x) {
return ((((uint64_t)swapbytes((uint32_t)(x & 0xffffffffU)) << 32) |
(uint64_t)swapbytes((uint32_t)(x >> 32))));
}
/****************************************************************
* Utility functions *
***************************************************************/
static char *findquot(const char *cp) { /* " and ' are both valid attribute delimiters */
char *result = strchr(cp,'\"');
if (!result) {
result = strchr(cp,'\'');
}
return result;
}
static int isquot(const char c) { /* " and ' are both valid attribute delimiters */
return ('\"'==c)||('\''==c);
}
static int setTagValue(const char* text,
char* storage,
int maxlen,
const char* lead);
const char* skipspace(const char* pStr)
{
while (isspace(*pStr))
pStr++;
if (*pStr == '\0')
return NULL;
return pStr;
}
static void getIsLittleEndian(const char *buf, int *result) {
const char *p = strstr(buf,"byteOrder");
if (p) {
p = findquot(p);
if (p++) {
*result = (0!=strncmp(p,"network",7));
}
}
// leave *result alone if we don't see anything!
}
/**************************************************
* open and close files *
**************************************************/
RAMPFILE *rampOpenFile(const char *filename) {
RAMPFILE *result = (RAMPFILE *)calloc(1,sizeof(RAMPFILE));
if (result) {
int bOK;
#ifndef _LARGEFILE_SOURCE
result->fileHandle = open(filename,_O_BINARY|_O_RDONLY);
bOK = (result->fileHandle >= 0);
#else
result->fileHandle = fopen(filename,"rb");
bOK = (result->fileHandle != NULL);
#endif
if (!bOK) {
free(result);
result = NULL;
} else {
char buf[1024];
buf[sizeof(buf)-1] = 0;
while (!ramp_feof(result)) {
ramp_fgets(buf,sizeof(buf)-1,result);
if (strstr(buf,"<msRun")) {
result->bIsMzData = 0;
break;
} else if (strstr(buf,"<mzData")) {
result->bIsMzData = 1;
break;
}
}
ramp_fseek(result,0,SEEK_SET); // rewind
// now set up the element tags we seek
}
}
return result;
}
void rampCloseFile(RAMPFILE *pFI) {
if (pFI) {
#ifndef _LARGEFILE_SOURCE
close(pFI->fileHandle);
#else
fclose(pFI->fileHandle);
#endif
free(pFI);
}
}
/**************************************************
* fgets() for win32 long files *
* TODO: this could be a LOT more efficient...
**************************************************/
#ifndef _LARGEFILE_SOURCE
char *ramp_fgets(char *buf,int len,RAMPFILE *handle) {
int nread=0;
int chunk;
ramp_fileoffset_t pos = ramp_ftell(handle);
buf[--len]=0; // nullterm for safety
chunk = max(len/4,1); // usually all that's needed is a short read
while (nread <= len) {
char *newline;
int nread_now = ramp_fread(buf+nread,chunk,handle);
buf[nread+nread_now] = 0;
if (!nread_now) {
return nread?buf:NULL;
}
newline = strchr(buf+nread,'\n');
if (newline) {
*newline = 0;
ramp_fseek(handle,pos+(newline-buf)+1,SEEK_SET); // so next read is at next line
break;
}
nread+=nread_now;
if (nread >= len) {
break;
}
// apparently we need bigger reads
chunk = len-nread;
}
return buf;
}
#endif
/****************************************************************
* Find the Offset of the index *
***************************************************************/
ramp_fileoffset_t getIndexOffset(RAMPFILE *pFI)
{
int i;
ramp_fileoffset_t indexOffset, indexOffsetOffset;
char indexOffsetTemp[SIZE_BUF+1], buf;
if (pFI->bIsMzData) {
return -1; // no index in mzData
}
for (indexOffsetOffset = -120; indexOffsetOffset++ < 0 ;)
{
char seekbuf[SIZE_BUF+1];
char *target = "<indexOffset>";
int nread;
ramp_fseek(pFI, indexOffsetOffset, SEEK_END);
nread = ramp_fread(seekbuf, strlen(target), pFI);
seekbuf[nread] = '\0';
if (!strcmp(seekbuf, target))
{
break;
}
}
if (indexOffsetOffset >= 0) {
return -1; // no answer
}
indexOffset = ramp_ftell(pFI);
i = 0;
while (ramp_fread(&buf, 1, pFI) && buf != '<')
{
indexOffsetTemp[i] = buf;
i++;
}
indexOffsetTemp[i] = '\0';
if (sizeof(ramp_fileoffset_t)==8)
indexOffset = (atoll(indexOffsetTemp));
else
indexOffset = (atol(indexOffsetTemp));
// now test this
ramp_fseek(pFI, indexOffset, SEEK_SET);
ramp_fread(indexOffsetTemp, sizeof(indexOffsetTemp), pFI);
indexOffsetTemp[sizeof(indexOffsetTemp)-1] = 0;
if (!strstr(indexOffsetTemp,"<index")) {
indexOffset = -1; // broken somehow
}
return indexOffset;
}
/****************************************************************
* Reads the Scan index in a list *
* Returns pScanIndex which becomes property of the caller *
* pScanIndex is -1 terminated *
***************************************************************/
char buf[SIZE_BUF*16];
ramp_fileoffset_t *readIndex(RAMPFILE *pFI,
ramp_fileoffset_t indexOffset,
int *iLastScan)
{
int n;
int reallocSize = 8000; /* initial # of scan indexes to expect */
char *beginScanOffset;
ramp_fileoffset_t *pScanIndex=NULL;
int retryLoop;
char* s;
for (retryLoop = 2;retryLoop--;) {
n = 1; // ramp is one based
*iLastScan = 0;
free(pScanIndex);
if ((indexOffset < 0) || (retryLoop==0)) { // derive the index by inspection
// no index found, derive it
const char *scantag = pFI->bIsMzData?"<spectrum id":"<scan";
int taglen = (int)strlen(scantag);
ramp_fileoffset_t index = 0;
pScanIndex = (ramp_fileoffset_t *)malloc( sizeof(ramp_fileoffset_t)*reallocSize); // allocate space for the scan index info
if (!pScanIndex) {
printf("Cannot allocate memory\n");
return NULL;
}
ramp_fseek(pFI,0,SEEK_SET);
buf[sizeof(buf)-1] = 0;
while ((int)ramp_fread(buf,sizeof(buf)-1,pFI)>taglen) {
char *find;
char *look=buf;
int nread;
while (NULL != (find = strstr(look,scantag))) {
pScanIndex[n++] = index+(find-buf); // ramp is 1-based
(*iLastScan)++;
look = find+taglen;
if (reallocSize<=n) {
reallocSize+=500;
pScanIndex = (ramp_fileoffset_t *)realloc(pScanIndex, sizeof(ramp_fileoffset_t)*reallocSize); // allocate space for the scan index info
if (!pScanIndex) {
printf("Cannot allocate memory\n");
return NULL;
}
}
}
nread = strlen(look)+(look-buf);
if (*look && strchr(scantag,buf[nread-1])) { // check last char of buffer
// possible that next scantag overhangs end of buffer
ramp_fseek(pFI,-taglen,SEEK_CUR); // so next get includes it
}
index = ramp_ftell(pFI);
}
break; // no need to retry
} else { // read the index out of the file (then check it!)
struct ScanHeaderStruct scanHeader; // for test of index integrity
int indexOK=1; // until we show otherwise
if ((pScanIndex = (ramp_fileoffset_t *) malloc(reallocSize * sizeof(ramp_fileoffset_t))) == NULL) {
printf("Cannot allocate memory\n");
return NULL;
}
ramp_fseek(pFI, indexOffset, SEEK_SET);
s = ramp_fgets(buf, SIZE_BUF, pFI);
while( s!=NULL && !strstr( buf , "<offset" ) ) {
s = ramp_fgets(buf, SIZE_BUF, pFI);
}
if (s == NULL)
break; // end of file reached.
while (!strstr(buf, "/index")) {
if ((beginScanOffset = (char *) (strstr(buf, ">"))) == NULL) {
ramp_fgets(buf, SIZE_BUF, pFI);
continue;
}
beginScanOffset++;
if (sizeof(ramp_fileoffset_t)==8) {
pScanIndex[n] = atoll(beginScanOffset);
} else {
pScanIndex[n] = atol(beginScanOffset);
}
n++;
(*iLastScan)++;
if (n == reallocSize) {
ramp_fileoffset_t *pTmp;
reallocSize = reallocSize + 500;
pTmp = (ramp_fileoffset_t*) realloc(pScanIndex, reallocSize*sizeof(ramp_fileoffset_t));
if (pTmp==NULL) {
printf("Cannot allocate memory\n");
return NULL;
} else {
pScanIndex=pTmp;
}
}
ramp_fgets(buf, SIZE_BUF, pFI);
}
if (n) {
// OK, now test that to see if it's a good index or not
readHeader(pFI,pScanIndex[1],&scanHeader);
if (scanHeader.acquisitionNum == -1) { // first
indexOK = 0; // bogus index
free(pScanIndex);
pScanIndex = NULL;
}
if (indexOK && (n>1)) { // middle
readHeader(pFI,pScanIndex[n/2],&scanHeader);
if (scanHeader.acquisitionNum == -1) {
indexOK = 0; // bogus index
free(pScanIndex);
pScanIndex = NULL;
}
}
if (indexOK && (n>1)) { // last
readHeader(pFI,pScanIndex[n-1],&scanHeader);
if (scanHeader.acquisitionNum == -1) {
indexOK = 0; // bogus index
free(pScanIndex);
pScanIndex = NULL;
}
}
}
if (indexOK) {
break; // no retry
}
} // end if we claim to have an index
} // end for retryloop
pScanIndex[n] = -1;
return (pScanIndex);
}
// helper func for reading mzData
const char *findMzDataTagValue(const char *pStr, const char *tag) {
const char *find = strstr(pStr,tag);
if (find) {
find = strstr(find+1,"value=");
if (find) {
find = findquot(find);
if (find) {
find++; // pointing at value string
}
}
}
return find;
}
/*
* Reads a time string, returns time in seconds.
*/
static double rampReadTime(RAMPFILE *pFI,const char *pStr) {
double t=0;
if (pFI->bIsMzData) {
const char *tag = findMzDataTagValue(pStr, "TimeInMinutes");
if (tag) {
t = 60.0*atof(tag);
} else if (NULL!=(tag = findMzDataTagValue(pStr, "TimeInSeconds"))) { // von Steffan Neumann
t = atof(tag);
}
} else if (!sscanf(pStr, "PT%lfS", &t)) { // usually this is elapsed run time
/* but could be stored in for PxYxMxDTxHxMxS */
struct tm fullTime; // apologies to those working after January 18, 19:14:07, 2038
double secondsFrac=0;
int bDate = 1;
while (!isquot(*++pStr)) {
double val;
if ('T'==*pStr) {
pStr++;
bDate = 0; // we're into the minutes:seconds portion
}
val = atof(pStr);
while (('.'==*pStr)||isdigit(*pStr)) {
pStr++;
}
switch (*pStr) {
case 'Y':
fullTime.tm_year = (int)val-1900; // years since 1900
break;
case 'M':
if (bDate) {
fullTime.tm_mon = (int)val-1; // range 0-11
} else {
fullTime.tm_min = (int)val; // range 0-59
}
break;
case 'D':
fullTime.tm_mday = (int)val; // range 1-31
break;
case 'H':
fullTime.tm_hour = (int)val; // range 0-23
break;
case 'S':
fullTime.tm_sec = (int)val;
secondsFrac = val-(double)fullTime.tm_sec;
break;
}
}
t = (double)mktime(&fullTime)+secondsFrac;
}
return t;
}
/*
* helper func for faster parsing
*/
const char *matchAttr(const char *where,const char *attr,int len) {
const char *look = where; // we assume this is pointed at '=', look back at attr
while (len--) {
if (*--look != attr[len]) {
return NULL; // no match
}
}
return where+2; // point past ="
}
//
// helper function to deal with mzdata with no newlines - breaks
// lines up at </...>
//
static char *ramp_nextTag(char *buf, int buflen, RAMPFILE *pFI) {
char *result;
buf[buflen-1]=1; // so we can detect full buffer read
result = ramp_fgets(buf,buflen,pFI);
if (result && !buf[buflen-1]) { // no newline found
char *closer = strstr(buf+1,"</");
if (closer) {
*closer = 0; // temp. nullterm
ramp_fseek(pFI,(1+closer-buf)-buflen,SEEK_CUR); // reposition for next read
}
}
return result;
}
/*
* Reads scan header information.
* !! THE STREAM IS NOT RESET AT THE INITIAL POSITION BEFORE
* RETURNING !
*/
void readHeader(RAMPFILE *pFI,
ramp_fileoffset_t lScanIndex, // look here
struct ScanHeaderStruct *scanHeader)
{
char stringBuf[SIZE_BUF];
char *pStr2;
ramp_fseek(pFI, lScanIndex, SEEK_SET);
/*
* initialize defaults
*/
memset(scanHeader,0,sizeof(struct ScanHeaderStruct)); // mostly we want 0's
#define LOWMZ_UNINIT 1.111E6
scanHeader->lowMZ = LOWMZ_UNINIT;
scanHeader->acquisitionNum = -1;
scanHeader->seqNum = -1;
if (pFI->bIsMzData) {
int bHasPrecursor = 0;
while (ramp_nextTag(stringBuf, SIZE_BUF, pFI))
{
const char *attrib;
const char *pStr;
const char *closeTag = strstr(stringBuf, "</spectrumSettings>");
// find each attribute in stringBuf
for (attrib=stringBuf-1;NULL!=(attrib=strchr(attrib+1,'='));) {
if (closeTag && (closeTag < attrib)) {
break; // into data territory now
}
if ((pStr = matchAttr(attrib, "spectrum id",11))) {
sscanf(pStr, "%d", &(scanHeader->acquisitionNum));
//} else if ((pStr = matchAttr(attrib, "basePeakMz",10))) {
// sscanf(pStr, "%lf", &(scanHeader->basePeakMZ));
//} else if ((pStr = matchAttr(attrib, "totIonCurrent",13))) {
// sscanf(pStr, "%lf", &(scanHeader->totIonCurrent));
//} else if ((pStr = matchAttr(attrib, "basePeakIntensity",17))) {
// sscanf(pStr, "%lf", &(scanHeader->basePeakIntensity));
} else if ((pStr = matchAttr(attrib, "msLevel",7))) {
sscanf(pStr, "%d", &(scanHeader->msLevel));
//} else if ((pStr = matchAttr(attrib, "length",6))) { get this from array element
// sscanf(pStr, "%d", &(scanHeader->peaksCount));
} else if ((pStr = findMzDataTagValue(attrib,"TimeInMinutes"))) {
scanHeader->retentionTime = rampReadTime(pFI,stringBuf);
} else if ((pStr = matchAttr(attrib, "mzRangeStart",12))) {
sscanf(pStr, "%lf", &(scanHeader->lowMZ));
} else if ((pStr = matchAttr(attrib, "mzRangeStop",11))) {
sscanf(pStr, "%lf", &(scanHeader->highMZ));
} else if ((pStr = findMzDataTagValue(attrib, "ScanMode"))) {
if ((pStr2 = (char *) findquot(pStr))) {
memcpy(&(scanHeader->scanType), pStr, pStr2-pStr);
scanHeader->scanType[pStr2-pStr] = '\0';
}
}
}
if (closeTag) {
break; // into data territory now
}
}
do {
/*
* read precursor info
*/
const char *pStr,*pStr2;
if ((pStr = (char *) strstr(stringBuf, "<precursorList")))
{
bHasPrecursor = 1;
} else if ((pStr = (char *) strstr(stringBuf, "</precursorList")))
{
bHasPrecursor = 0;
}
if (bHasPrecursor) { // in precursor section
if (NULL!=(pStr2 = (char *) strstr(stringBuf, "spectrumRef=")))
{
sscanf(pStr2 + 13, "%d", &(scanHeader->precursorScanNum));
}
if (NULL!=(pStr2 = findMzDataTagValue(stringBuf,"ChargeState")))
{
scanHeader->precursorCharge = atoi(pStr2);
}
if (NULL!=(pStr2 = findMzDataTagValue(stringBuf,"MassToChargeRatio")))
{
scanHeader->precursorMZ = atoi(pStr2);
}
if (NULL!=(pStr2 = findMzDataTagValue(stringBuf,"mz")))
{
scanHeader->precursorMZ = atoi(pStr2);
}
}
if (strstr(stringBuf, "</spectrumDesc>")) {
break; // into data territory now
}
if (strstr(stringBuf, "</precursorList>")) {
break; // into data territory now
}
} while (ramp_nextTag(stringBuf, SIZE_BUF, pFI));
// now read peaks count
do {
if (strstr(stringBuf, "ArrayBinary>")) {
do {
char *cp=strstr(stringBuf,"length=");
if (cp) {
scanHeader->peaksCount = atoi(cp+8);
break;
}
} while (ramp_nextTag(stringBuf, SIZE_BUF, pFI));
break;
}
} while (ramp_nextTag(stringBuf, SIZE_BUF, pFI));
} else { // mzXML
while (ramp_fgets(stringBuf, SIZE_BUF, pFI))
{
const char *attrib;
const char *pStr;
// find each attribute in stringBuf
for (attrib=stringBuf-1;NULL!=(attrib=strchr(attrib+1,'='));) {
if ((pStr = matchAttr(attrib, "num",3))) {
sscanf(pStr, "%d", &(scanHeader->acquisitionNum));
} else if ((pStr = matchAttr(attrib, "basePeakMz",10))) {
sscanf(pStr, "%lf", &(scanHeader->basePeakMZ));
} else if ((pStr = matchAttr(attrib, "totIonCurrent",13))) {
sscanf(pStr, "%lf", &(scanHeader->totIonCurrent));
} else if ((pStr = matchAttr(attrib, "basePeakIntensity",17))) {
sscanf(pStr, "%lf", &(scanHeader->basePeakIntensity));
} else if ((pStr = matchAttr(attrib, "msLevel",7))) {
sscanf(pStr, "%d", &(scanHeader->msLevel));
} else if ((pStr = matchAttr(attrib, "peaksCount",10))) {
sscanf(pStr, "%d", &(scanHeader->peaksCount));
} else if ((pStr = matchAttr(attrib, "retentionTime",13))) {
scanHeader->retentionTime = rampReadTime(pFI,pStr);
} else if ((pStr = matchAttr(attrib, "lowMz",5))) {
sscanf(pStr, "%lf", &(scanHeader->lowMZ));
} else if ((pStr = matchAttr(attrib, "highMz",6))) {
sscanf(pStr, "%lf", &(scanHeader->highMZ));
} else if ((scanHeader->lowMZ==LOWMZ_UNINIT) &&
((pStr = matchAttr(attrib, "startMz",7)))) {
sscanf(pStr, "%lf", &(scanHeader->lowMZ));
} else if ((!scanHeader->highMZ) &&
((pStr = matchAttr(attrib, "endMz",5)))) {
sscanf(pStr, "%lf", &(scanHeader->highMZ));
} else if ((pStr = matchAttr(attrib, "scanType", 8))) {
if ((pStr2 = (char *) findquot(pStr))) {
memcpy(&(scanHeader->scanType), pStr, sizeof(char)*((pStr2-pStr)));
scanHeader->scanType[pStr2-pStr] = '\0';
}
} else if ((pStr = matchAttr(attrib, "collisionEnergy", 15))) {
sscanf(pStr, "%lf", &(scanHeader->collisionEnergy));
}
}
/*
* read precursor mass
*/
if ((pStr = (char *) strstr(stringBuf, "<precursorMz ")))
{
if ((pStr2 = (char *) strstr(stringBuf, "precursorScanNum=")))
sscanf(pStr2 + 18, "%d", &(scanHeader->precursorScanNum));
if ((pStr2 = (char *) strstr(pStr, "precursorCharge=")))
sscanf(pStr2 + 17, "%d", &(scanHeader->precursorCharge));
if ((pStr2 = (char *) strstr(pStr, "precursorIntensity=")))
sscanf(pStr2 + 20, "%lf", &(scanHeader->precursorIntensity));
/*
* Find end of tag.
*/
while (!(pStr = strchr(pStr, '>')))
{
ramp_fgets(stringBuf, SIZE_BUF, pFI);
pStr = stringBuf;
if ((pStr2 = (char *) strstr(stringBuf, "precursorScanNum=")))
sscanf(pStr2 + 18, "%d", &(scanHeader->precursorScanNum));
if ((pStr2 = (char *) strstr(pStr, "precursorCharge=")))
sscanf(pStr2 + 17, "%d", &(scanHeader->precursorCharge));
if ((pStr2 = (char *) strstr(pStr, "precursorIntensity=")))
sscanf(pStr2 + 20, "%lf", &(scanHeader->precursorIntensity));
}
pStr++; // Skip >
/*
* Skip past white space.
*/
while (!(pStr = skipspace(pStr)))
{
ramp_fgets(stringBuf, SIZE_BUF, pFI);
pStr = stringBuf;
}
sscanf(pStr, "%lf<", &(scanHeader->precursorMZ));
// printf("precursorMass = %lf\n", scanHeader->precursorMZ);
}
if (strstr(stringBuf, "<peaks")) {
break; // into data territory now
}
}
} // end else mzXML
if (!scanHeader->retentionTime) {
scanHeader->retentionTime = scanHeader->acquisitionNum; // just some unique nonzero value
}
scanHeader->seqNum = scanHeader->acquisitionNum; // default sequence number
scanHeader->filePosition = lScanIndex;
}
/****************************************************************
* Reads the MS level of the scan. *
* !! THE STREAM IS NOT RESET AT THE INITIAL POSITION BEFORE *
* RETURNING !! *
***************************************************************/
int readMsLevel(RAMPFILE *pFI,
ramp_fileoffset_t lScanIndex)
{
int msLevelLen;
char stringBuf[SIZE_BUF+1];
char szLevel[12];
char *beginMsLevel, *endMsLevel;
ramp_fseek(pFI, lScanIndex, SEEK_SET);
ramp_fgets(stringBuf, SIZE_BUF, pFI);
while (!(beginMsLevel = (char *) strstr(stringBuf, "msLevel=")))
{
ramp_fgets(stringBuf, SIZE_BUF, pFI);
}
beginMsLevel += 9; // We need to move the length of msLevel="
endMsLevel = (char *) findquot(beginMsLevel);
msLevelLen = endMsLevel - beginMsLevel;
strncpy(szLevel, beginMsLevel, msLevelLen);
szLevel[msLevelLen] = '\0';
return atoi(szLevel);
}
/****************************************************************
* Reads startMz and endMz of the scan. *
* Returns 1.E6 if startMz was not set.*
* !! THE STREAM IS NOT RESET AT THE INITIAL POSITION BEFORE *
* RETURNING !! *
***************************************************************/
double readStartMz(RAMPFILE *pFI,
ramp_fileoffset_t lScanIndex)
{
char stringBuf[SIZE_BUF+1];
double startMz = 1.E6;
char *pStr;
const char *tag = pFI->bIsMzData?"mzRangeStart":"startMz";
ramp_fseek(pFI, lScanIndex, SEEK_SET);
while (ramp_fgets(stringBuf, SIZE_BUF, pFI))
{
if (strstr(stringBuf, pFI->bIsMzData?"</spectrumDesc":"<peaks"))
break; // ran to end
if ((pStr = strstr(stringBuf, tag))){
sscanf(pStr + strlen(tag)+2, "%lf", &startMz);
break;
}
}
return startMz;
}
/****************************************************************
* Reads startMz and endMz of the scan. *
* Returns 1.E6 if startMz was not set. *
* !! THE STREAM IS NOT RESET AT THE INITIAL POSITION BEFORE *
* RETURNING !! *
***************************************************************/
double readEndMz(RAMPFILE *pFI,
ramp_fileoffset_t lScanIndex)
{
char stringBuf[SIZE_BUF+1];
double endMz = 0.0;
char *pStr;
const char *tag = pFI->bIsMzData?"mzRangeStop":"endMz";
ramp_fseek(pFI, lScanIndex, SEEK_SET);
while (ramp_fgets(stringBuf, SIZE_BUF, pFI))
{
if (strstr(stringBuf, pFI->bIsMzData?"</spectrumDesc":"<peaks"))
break; // ran to end
if ((pStr = strstr(stringBuf, tag))){
sscanf(pStr + strlen(tag)+2, "%lf", &endMz);
break;
}
}
return endMz;
}
#define N_EXT_TYPES 4
static char *data_ext[N_EXT_TYPES]={".mzXML",".mzData",".mzxml",".mzdata"};
// construct a filename in inbuf from a basename, adding .mzXML or .mzData as exists
// returns inbuf, or NULL if neither .mzXML or .mzData file exists
char *rampConstructInputFileName(char *inbuf,int inbuflen,const char *basename_in) {
return rampConstructInputPath(inbuf, inbuflen, "", basename_in);
}
char *rampConstructInputPath(char *inbuf,int inbuflen,const char *dir,const char *basename_in) {
char *result = NULL;
int i;
char *basename = (char *)basename_in;
char *tmpbuf = (char *)malloc(strlen(dir) + strlen(basename) + 20);
char *append;
if (basename_in==inbuf) { // same pointer
basename = (char *)malloc(inbuflen);
strncpy(basename,basename_in,inbuflen);
}
strcpy(tmpbuf, dir);
strcat(tmpbuf, basename);
append = tmpbuf + strlen(tmpbuf);
for (i=0;i<N_EXT_TYPES;i++) {
FILE *test;
strcpy(append,data_ext[i]);
test = fopen(tmpbuf,"r");
if (test != NULL) {
if (result) { // conflict! both mzXML and mzData are present
if (strcasecmp(tmpbuf,result)) { // win32 isn't case sensitive
printf("found both %s and %s, using %s\n",
tmpbuf,result,result);
}
} else { // found file, copy the constructed name
result = strdup(tmpbuf);
}
fclose(test);
}
}
if (!result) { // failed - caller can complain about lack of .mzXML
strcpy(append,data_ext[0]);
result = strdup(tmpbuf);
}
if (basename_in==inbuf) { // same pointer
free(basename);
}
free(tmpbuf);
if ((int) strlen(result) < inbuflen) {
strcpy(inbuf, result);
free(result);
result = inbuf;
} else {
printf("buffer too small for file %s\n",
result);
free(result);
result = NULL;
}
return result;
}
// return NULL if fname is not of extension type we handle,
// otherwise return pointer to .ext
char *rampValidFileType(const char *fname) {
char *result;
int i;
for (i = N_EXT_TYPES;i--;) {
result = strrchr(fname,'.');
if (result && !strcasecmp(result,data_ext[i])) {
break;
}
result = NULL; // try again
}
return result;
}
// remove the filename .ext, if found
// return NULL if no .ext found, else return fname
char *rampTrimBaseName(char *fname) {
char *ext = rampValidFileType(fname);
if (ext) {
*ext = 0; // trim the extension
}
return ext?fname:NULL;
}
/****************************************************************
* READS the number of peaks. *
* !! THE STREAM IS NOT RESET AT THE INITIAL POSITION BEFORE *
* RETURNING !! *
***************************************************************/
int readPeaksCount(RAMPFILE *pFI,
ramp_fileoffset_t lScanIndex)
{
char *stringBuf=(char *)malloc(SIZE_BUF+1);
char *beginPeaksCount, *peaks;
int result = 0;
const char *tag = pFI->bIsMzData?"length=":"peaksCount=";
ramp_fileoffset_t in_lScanIndex = lScanIndex;
ramp_fseek(pFI, lScanIndex, SEEK_SET);
// Get the num of peaks in the scan and allocate the space we need
ramp_nextTag(stringBuf, SIZE_BUF, pFI);
while (!(beginPeaksCount = (char *) strstr(stringBuf, tag)))
{
lScanIndex = ramp_ftell(pFI);
ramp_nextTag(stringBuf, SIZE_BUF, pFI);
}
// We need to move forward the length of the tag
beginPeaksCount += (strlen(tag)+1);
result = atoi(beginPeaksCount);
// mext call is probably to read the <peaks> section, position there if needed
if (pFI->bIsMzData) {
ramp_fseek(pFI, in_lScanIndex, SEEK_SET);
} else {
peaks = strstr(stringBuf,"<peaks");
if (peaks) {
ramp_fseek(pFI, lScanIndex+(peaks-stringBuf), SEEK_SET);
}
}
free(stringBuf);
return result;
}
/****************************************************************
* READS the base64 encoded list of peaks. *
* Return a RAMPREAL* that becomes property of the caller! *
* The list is terminated by -1 *
* !! THE STREAM IS NOT RESET AT THE INITIAL POSITION BEFORE *
* RETURNING !! *
***************************************************************/
RAMPREAL *readPeaks(RAMPFILE *pFI,
ramp_fileoffset_t lScanIndex)
{
int n=0;
int peaksCount=0;
int peaksLen; // The length of the base64 section
int precision = 0;
RAMPREAL *pPeaks = NULL;
RAMPREAL *pPeaksDeRuled = NULL;
int endtest = 1;
int weAreLittleEndian = *((char *)&endtest);
char *pData = NULL;
char *pBeginData;
char *pDecoded = NULL;
char buf[1000];
buf[sizeof(buf)-1] = 0;
if (pFI->bIsMzData) {
// intensity and mz are written in two different arrays
int bGotInten = 0;
int bGotMZ = 0;
ramp_fseek(pFI,lScanIndex,SEEK_SET);
while ((!(bGotInten && bGotMZ)) &&
ramp_nextTag(buf,sizeof(buf)-1,pFI)) {
int isArray = 0;
int isInten = 0;
int isLittleEndian = 0;
int byteOrderOK;
if (strstr(buf,"<mzArrayBinary")) {
isArray = bGotMZ = 1;
} else if (strstr(buf,"<intenArrayBinary")) {
isArray = isInten = bGotInten = 1;
}
if (isArray) {
int partial,triplets,bytes;
const char *datastart;
// now determine peaks count, precision
while (!(datastart= (char *) strstr(buf, "<data")))
{
ramp_nextTag(buf, sizeof(buf)-1, pFI);
}
// find precision="xx"
if( !(pBeginData = strstr( buf , "precision=" )))
{
precision = 32; // default value
} else { // we found declaration
precision = atoi(findquot(pBeginData)+1);
}
// find length="xx"
if((!peaksCount) && (pBeginData = strstr( buf , "length=" )))
{
peaksCount = atoi(findquot(pBeginData)+1);
}
if (peaksCount <= 0)
{ // No peaks in this scan!!
return NULL;
}
// find endian="xx"
if((pBeginData = strstr( buf , "endian=" )))
{
isLittleEndian = !strncmp("little",findquot(pBeginData)+1,6);
}
// find close of <data>
while( !(pBeginData = strstr( datastart , ">" )))