Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

feat : reduce htslib dependency #180

Merged
merged 1 commit into from
Oct 27, 2023
Merged

feat : reduce htslib dependency #180

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 0 additions & 1 deletion build.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -198,7 +198,6 @@ def _extra_compile_args_for_pxblat():
base_library_link_args: list[str] = []
external_libraries = [
"z",
"hts",
"ssl",
"crypto",
"m",
Expand Down
154 changes: 79 additions & 75 deletions src/pxblat/extc/src/core/linefile.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,7 @@
#include "localmem.h"
#include "cheapcgi.h"
#include "udc.h"
#include "htslib/tbx.h"
// #include "htslib/tbx.h"

char *getFileNameFromHdrSig(char *m)
/* Check if header has signature of supported compression stream,
Expand Down Expand Up @@ -237,34 +237,35 @@ if (tbiFileOrUrl==NULL)
else
safef(tbiName, sizeof(tbiName), "%s", tbiFileOrUrl);

htsFile *htsFile = hts_open(fileOrUrl, "r");
if (htsFile == NULL)
{
warn("Unable to open \"%s\"", fileOrUrl);
return NULL;
}
tbx_t *tabix;
if ((tabix = tbx_index_load2(fileOrUrl, tbiName)) == NULL)
{
warn("Unable to load tabix index from \"%s\"", tbiName);
if (tabix)
ti_close(tabix);
tabix = NULL;
return NULL;
}
// HACK: reduce htslib dependencies <10-26-23> Yangyang Li
// htsFile *htsFile = hts_open(fileOrUrl, "r");
// if (htsFile == NULL)
// {
// warn("Unable to open \"%s\"", fileOrUrl);
// return NULL;
// }
// tbx_t *tabix;
// if ((tabix = tbx_index_load2(fileOrUrl, tbiName)) == NULL)
// {
// warn("Unable to load tabix index from \"%s\"", tbiName);
// if (tabix)
// ti_close(tabix);
// tabix = NULL;
// return NULL;
// }
struct lineFile *lf = needMem(sizeof(struct lineFile));
lf->fileName = cloneString(fileOrUrl);
lf->fd = -1;
lf->bufSize = 64 * 1024;
lf->buf = needMem(lf->bufSize);
lf->zTerm = zTerm;
lf->tabix = tabix;
lf->htsFile = htsFile;
kstring_t *kline;
AllocVar(kline);
kline->s = malloc(8192);
lf->kline = kline;
lf->tabixIter = tbx_itr_queryi(tabix, HTS_IDX_REST, 0, 0);
// lf->fileName = cloneString(fileOrUrl);
// lf->fd = -1;
// lf->bufSize = 64 * 1024;
// lf->buf = needMem(lf->bufSize);
// lf->zTerm = zTerm;
// lf->tabix = tabix;
// lf->htsFile = htsFile;
// kstring_t *kline;
// AllocVar(kline);
// kline->s = malloc(8192);
// lf->kline = kline;
// lf->tabixIter = tbx_itr_queryi(tabix, HTS_IDX_REST, 0, 0);
return lf;
}

Expand All @@ -276,29 +277,29 @@ if (lf->tabix == NULL)
errAbort("lineFileSetTabixRegion: lf->tabix is NULL. Did you open lf with lineFileTabixMayOpen?");
if (seqName == NULL)
return FALSE;
int tabixSeqId = ti_get_tid(lf->tabix, seqName);
if (tabixSeqId < 0 && startsWith("chr", seqName))
// We will get some files that have chr-less Ensembl chromosome names:
tabixSeqId = ti_get_tid(lf->tabix, seqName+strlen("chr"));
// Allow SARS-CoV-2 VCF to use GenBank or RefSeq ID instead of our chromified RefSeq ID:
if (tabixSeqId < 0 && sameString(seqName, "NC_045512v2"))
{
tabixSeqId = ti_get_tid(lf->tabix, "MN908947.3");
if (tabixSeqId < 0)
tabixSeqId = ti_get_tid(lf->tabix, "NC_045512.2");
}
if (tabixSeqId < 0)
return FALSE;
ti_iter_t *iter = ti_queryi((tbx_t *)lf->tabix, tabixSeqId, start, end);
if (iter == NULL)
return FALSE;
if (lf->tabixIter != NULL)
ti_iter_destroy(lf->tabixIter);
lf->tabixIter = iter;
lf->bytesInBuf = 0;
lf->lineIx = -1;
lf->lineStart = 0;
lf->lineEnd = 0;
// int tabixSeqId = ti_get_tid(lf->tabix, seqName);
// if (tabixSeqId < 0 && startsWith("chr", seqName))
// // We will get some files that have chr-less Ensembl chromosome names:
// tabixSeqId = ti_get_tid(lf->tabix, seqName+strlen("chr"));
// // Allow SARS-CoV-2 VCF to use GenBank or RefSeq ID instead of our chromified RefSeq ID:
// if (tabixSeqId < 0 && sameString(seqName, "NC_045512v2"))
// {
// tabixSeqId = ti_get_tid(lf->tabix, "MN908947.3");
// if (tabixSeqId < 0)
// tabixSeqId = ti_get_tid(lf->tabix, "NC_045512.2");
// }
// if (tabixSeqId < 0)
// return FALSE;
// ti_iter_t *iter = ti_queryi((tbx_t *)lf->tabix, tabixSeqId, start, end);
// if (iter == NULL)
// return FALSE;
// if (lf->tabixIter != NULL)
// ti_iter_destroy(lf->tabixIter);
// lf->tabixIter = iter;
// lf->bytesInBuf = 0;
// lf->lineIx = -1;
// lf->lineStart = 0;
// lf->lineEnd = 0;
return TRUE;
}

Expand Down Expand Up @@ -561,25 +562,27 @@ if (lf->udcFile)

if (lf->tabix != NULL && lf->tabixIter != NULL)
{

// HACK: reduce htslib dependencies <10-26-23> Yangyang Li
// Just use line-oriented ti_read:
int lineSize = 0;
lineSize = tbx_itr_next(lf->htsFile, lf->tabix, lf->tabixIter, lf->kline);
if (lineSize == -1)
return FALSE;
lf->bufOffsetInFile = -1;
lf->bytesInBuf = lineSize;
lf->lineIx = -1;
lf->lineStart = 0;
lf->lineEnd = lineSize;
if (lineSize > lf->bufSize)
// shouldn't be! but just in case:
lineFileExpandBuf(lf, lineSize * 2);
kstring_t *kline = lf->kline;
safecpy(lf->buf, lf->bufSize, kline->s);
*retStart = lf->buf;
if (retSize != NULL)
*retSize = lineSize;
return TRUE;
// int lineSize = 0;
// lineSize = tbx_itr_next(lf->htsFile, lf->tabix, lf->tabixIter, lf->kline);
// if (lineSize == -1)
// return FALSE;
// lf->bufOffsetInFile = -1;
// lf->bytesInBuf = lineSize;
// lf->lineIx = -1;
// lf->lineStart = 0;
// lf->lineEnd = lineSize;
// if (lineSize > lf->bufSize)
// // shouldn't be! but just in case:
// lineFileExpandBuf(lf, lineSize * 2);
// kstring_t *kline = lf->kline;
// safecpy(lf->buf, lf->bufSize, kline->s);
// *retStart = lf->buf;
// if (retSize != NULL)
// *retSize = lineSize;
// return TRUE;
}

char *buf = lf->buf;
Expand Down Expand Up @@ -717,12 +720,13 @@ if ((lf = *pLf) != NULL)
}
else if (lf->tabix != NULL)
{
if (lf->tabixIter != NULL)
ti_iter_destroy(lf->tabixIter);
ti_close(lf->tabix);
hts_close(lf->htsFile);
kstring_t *kline = lf->kline;
free(kline->s);
// HACK: reduce htslib dependencies <10-26-23> Yangyang Li
// if (lf->tabixIter != NULL)
// ti_iter_destroy(lf->tabixIter);
// ti_close(lf->tabix);
// hts_close(lf->htsFile);
// kstring_t *kline = lf->kline;
// free(kline->s);
}
else if (lf->udcFile != NULL)
udcFileClose(&lf->udcFile);
Expand Down
Loading