/*****************************************************************************
*
* PubEquivAsnRead(aip, atp)
* atp is the current type (if identifier of a parent struct)
* assumption is readIdent has occurred
* if atp == NULL, then assumes it stands alone and read ident
* has not occurred.
*
*****************************************************************************/
NLM_EXTERN ValNodePtr LIBCALL PubEquivAsnRead (AsnIoPtr aip, AsnTypePtr orig)
{
DataVal av;
AsnTypePtr atp, oldtype;
ValNodePtr anp=NULL, cit, curr;
Boolean first;
if (! loaded)
{
if (! PubAsnLoad())
return anp;
}
if (aip == NULL)
return anp;
first = TRUE;
if (orig == NULL) /* PubEquiv ::= (self contained) */
oldtype = AsnReadId(aip, amp, PUB_EQUIV);
else
oldtype = AsnLinkType(orig, PUB_EQUIV); /* link in local tree */
if (oldtype == NULL) return anp;
if (AsnReadVal(aip, oldtype, &av) <= 0) /* read START_STRUCT */
goto erret;
atp = oldtype;
curr = NULL;
anp = NULL;
while ((atp = AsnReadId(aip, amp, atp)) != oldtype)
{
if (atp == NULL) goto erret;
cit = PubAsnRead(aip, atp);
if (cit == NULL) goto erret;
if (first)
{
anp = cit;
first = FALSE;
}
else
{
curr->next = cit;
}
curr = cit;
}
if (AsnReadVal(aip, oldtype, &av) <= 0) /* read END_STRUCT for SET OF */
goto erret;
ret:
AsnUnlinkType(orig); /* unlink local tree */
return anp;
erret:
anp = PubEquivFree(anp);
goto ret;
}
NLM_EXTERN ValNodePtr LIBCALL AsnGenericValNodeSetAsnRead (
AsnIoPtr aip,
AsnModulePtr amp,
AsnTypePtr orig,
BoolPtr isError,
AsnReadFunc readfunc,
AsnOptFreeFunc freefunc
)
{
AsnTypePtr atp = orig, start_atp;
DataVal av;
Pointer val;
ValNodePtr vnp, head = NULL, last = NULL;
if (isError != NULL) {
*isError = FALSE;
}
if (aip == NULL || readfunc == NULL || freefunc == NULL) return NULL;
if (AsnReadVal (aip, atp, &av) <= 0) goto erret; /* read START STRUCT */
start_atp = orig;
atp = start_atp;
while ((atp = AsnReadId (aip, amp, atp)) != start_atp) {
val = (Pointer) readfunc (aip, atp);
if (val == NULL) goto erret;
vnp = ValNodeAddPointer (&last, 0, val);
if (head == NULL) {
head = vnp;
}
last = vnp;
}
if (AsnReadVal (aip, atp, &av) <= 0) goto erret; /* read END STRUCT */
ret:
return (Pointer) head;
erret:
head = AsnGenericValNodeSetFree (head, freefunc);
if (isError != NULL) {
*isError = TRUE;
}
goto ret;
}
NLM_EXTERN Pointer LIBCALL AsnGenericChoiceSeqOfAsnRead (AsnIoPtr aip, AsnModulePtr amp, AsnTypePtr orig, BoolPtr isError, AsnReadFunc readfunc, AsnOptFreeFunc freefunc)
{
AsnTypePtr start_atp;
ValNodePtr current;
ValNodePtr head = NULL;
ValNodePtr prev = NULL;
AsnTypePtr atp = orig;
DataVal av;
if (isError != NULL)
*isError = FALSE;
if (aip == NULL)
return NULL;
if (AsnReadVal (aip, atp, &av) <= 0) /* START_STRUCT */
goto erret;
start_atp = atp;
while ((atp = AsnReadId (aip, amp, atp)) != start_atp) {
if (atp == NULL)
goto erret;
current = (ValNodePtr) readfunc (aip, atp);
if (current == NULL)
goto erret;
if (head == NULL)
head = current;
else
prev->next = current;
prev = current;
}
if (AsnReadVal (aip, atp, &av) <= 0) /* END_STRUCT */
goto erret;
ret:
return (Pointer) head;
erret:
head = (ValNodePtr) freefunc (head);
if (isError != NULL)
*isError = TRUE;
goto ret;
}
static Int4 ProcessStream (InputStreamPtr isp, OutputStreamPtr osp, AsnStreamPtr asp, Int4Ptr gap_sizes)
{
AsnTypePtr atp, atp_srch;
AsnIoPtr asn_in, asn_out;
Int4 rval = 0;
SeqEntryPtr sep;
Uint2 entityID;
DataVal av;
if (isp == NULL || osp == NULL || asp == NULL || gap_sizes == NULL) return 1;
asn_in = AsnIoFromInputStream (isp);
asn_out = AsnIoFromOutputStream (osp);
if (isp->is_seqentry) {
atp = asp->atp_se;
atp_srch = asp->atp_se;
}
else {
atp = asp->atp_bss;
atp_srch = asp->atp_bss_se;
}
while ((atp = AsnReadId(asn_in, asp->amp, atp)) != NULL && rval == 0) {
if (atp != atp_srch) {
AsnReadVal(asn_in, atp, &av);
AsnWrite(asn_out, atp, &av);
AsnKillValue(atp, &av);
continue;
}
if ((sep = SeqEntryAsnRead(asn_in, atp)) == NULL) {
Message (MSG_POSTERR, "SeqEntryAsnRead failure");
rval = 1;
} else {
entityID = ObjMgrRegister (OBJ_SEQENTRY, sep);
ProcessSeqEntry (sep, gap_sizes);
if (! SeqEntryAsnWrite(sep, asn_out, atp)) {
Message (MSG_POSTERR, "SeqEntryAsnWrite failure");
rval = 1;
}
AsnIoFlush(asn_out);
ObjMgrFreeByEntityID (entityID);
}
} /* Endwhile, AsnReadId */
AsnIoClose(asn_in);
if (asn_out != osp->aip) {
AsnIoClose(asn_out);
}
return rval;
}
/*****************************************************************************
*
* Main program loop to read, process, write SeqEntrys
*
*****************************************************************************/
Int2 Main(void)
{
AsnIoPtr aipout=NULL, aipin;
AsnTypePtr atp, atp_inst;
AsnModulePtr amp;
DataVal dv;
CharPtr ftype;
BioseqPtr bsp;
/* check command line arguments */
if ( ! GetArgs("asn2xml 1.0",NUMARG, myargs))
return 1;
/* load the sequence alphabets */
/* (and sequence parse trees) */
if (! SeqEntryLoad())
ErrShow();
if (! SubmitAsnLoad())
ErrShow();
if (! SeqCodeSetLoad())
ErrShow();
/* get pointer to all loaded ASN.1 modules */
amp = AsnAllModPtr();
if (amp == NULL)
{
ErrShow();
return 1;
}
if (myargs[1].intvalue)
atp = AsnFind("Seq-entry");
else if (myargs[2].intvalue)
atp = AsnFind("Seq-submit");
else
atp = AsnFind("Bioseq-set"); /* get the initial type pointers */
if (atp == NULL)
{
ErrShow();
return 1;
}
atp_inst = AsnFind("Bioseq.inst");
if (atp_inst == NULL)
{
ErrShow();
return 1;
}
/* open the ASN.1 input file in the right mode */
if ((aipin = AsnIoOpen (myargs[0].strvalue, myargs[3].intvalue?"rb":"r"))
== NULL)
{
ErrPostEx(SEV_ERROR,0,0, "Can't open %s", myargs[0].strvalue);
ErrShow();
return 1;
}
/* open the ASN.1 output file in the right mode */
if (myargs[4].strvalue != NULL) /* output desired? */
{
ftype = "wx";
if ((aipout = AsnIoOpen (myargs[4].strvalue, ftype)) == NULL)
{
ErrPostEx(SEV_ERROR,0,0, "Can't open %s", myargs[4].strvalue);
ErrShow();
return 1;
}
}
/* log errors instead of die */
if (myargs[5].strvalue != NULL)
{
if (! ErrSetLog (myargs[5].strvalue))
{
ErrShow();
return 1;
}
else
ErrSetOpts (ERR_CONTINUE, ERR_LOG_ON);
}
while ((atp = AsnReadId(aipin, amp, atp)) != NULL)
{
if (atp == atp_inst) /* need object loader convert */
{
bsp = BioseqNew(); /* need newly initialized bsp */
BioseqInstAsnRead(bsp, aipin, atp);
BioseqInstAsnWrite(bsp, aipout, atp);
bsp = BioseqFree(bsp);
}
else
{
AsnReadVal(aipin, atp, &dv); /* read it */
AsnWrite(aipout, atp, &dv); /* write it */
AsnKillValue(atp, &dv); /* free it */
}
}
AsnIoClose(aipin);
AsnIoClose(aipout);
return(0);
}
NLM_EXTERN ValNodePtr LIBCALL AsnGenericBaseSeqOfAsnRead (AsnIoPtr aip, AsnModulePtr amp, AsnTypePtr orig, int whichvalslot, BoolPtr isError)
{
AsnTypePtr start_atp;
ValNodePtr current;
ValNodePtr head = NULL;
ValNodePtr prev = NULL;
AsnTypePtr atp = orig;
DataVal av;
if (isError != NULL)
*isError = FALSE;
if (aip == NULL)
return NULL;
if (AsnReadVal (aip, atp, &av) <= 0) /* START_STRUCT */
goto erret;
start_atp = atp;
while ((atp = AsnReadId (aip, amp, atp)) != start_atp) {
if (atp == NULL)
goto erret;
current = ValNodeNew (prev);
if (current == NULL)
goto erret;
switch (whichvalslot) {
case ASNCODE_PTRVAL_SLOT:
case ASNCODE_BYTEVAL_SLOT:
if (AsnReadVal (aip, atp, &av) <= 0)
goto erret;
current->data.ptrvalue = av.ptrvalue;
break;
case ASNCODE_REALVAL_SLOT:
if (AsnReadVal (aip, atp, &av) <= 0)
goto erret;
current->data.realvalue = av.realvalue;
break;
case ASNCODE_INTVAL_SLOT:
if (AsnReadVal (aip, atp, &av) <= 0)
goto erret;
current->data.intvalue = av.intvalue;
break;
case ASNCODE_BIGINTVAL_SLOT:
if (AsnReadVal (aip, atp, &av) <= 0)
goto erret;
current->data.bigintvalue = av.bigintvalue;
break;
case ASNCODE_BOOLVAL_SLOT:
if (AsnReadVal (aip, atp, &av) <= 0)
goto erret;
current->data.boolvalue = av.boolvalue;
break;
}
if (head == NULL)
head = current;
else
prev->next = current;
prev = current;
}
if (AsnReadVal (aip, atp, &av) <= 0) /* END_STRUCT */
goto erret;
ret:
return head;
erret:
head = ValNodeFree (head);
if (isError != NULL)
*isError = TRUE;
goto ret;
}
Int2 Main(void)
{
AsnIoPtr aip;
FILE * aa = NULL, * na = NULL, * ql = NULL;
SeqEntryPtr sep;
SeqSubmitPtr ssp;
AsnTypePtr atp, atp2;
AsnModulePtr amp;
Uint1 group_segs = 0;
Boolean limit_to_genbank,
make_dna,
make_protein,
make_quality,
far_quality,
do_it;
/* check command line arguments */
if ( ! GetArgs("asn2fast",NUMARG, myargs))
return 1;
/* load the sequence alphabets */
/* (and sequence parse trees) */
if (! SeqEntryLoad())
{
ErrShow();
return 1;
}
/* get pointer to all loaded ASN.1 modules */
amp = AsnAllModPtr();
if (amp == NULL)
{
ErrShow();
return 1;
}
if (myargs[11].intvalue) {
if (! SubmitAsnLoad())
Message(MSG_FATAL, "Unable to load parse trees.");
atp2 = AsnFind("Seq-submit");
if (atp2 == NULL)
Message(MSG_FATAL, "Unable to find Seq-submit");
atp = AsnFind("Seq-submit");
if (atp == NULL)
Message(MSG_FATAL, "Unable to find Seq-submit");
} else {
atp = AsnFind("Bioseq-set"); /* get the initial type pointers */
if (atp == NULL)
{
ErrShow();
return 1;
}
atp2 = AsnFind("Bioseq-set.seq-set.E");
if (atp2 == NULL)
{
ErrShow();
return 1;
}
}
make_protein = (Boolean)(myargs[7].intvalue);
make_dna = (Boolean)(myargs[8].intvalue);
make_quality = (Boolean)(myargs[12].intvalue);
far_quality = (Boolean)(myargs[14].intvalue);
/* open the ASN.1 input file in the right mode */
if ((aip = AsnIoOpen (myargs[0].strvalue, myargs[2].intvalue?"rb":"r"))
== NULL)
{
ErrShow();
return 1;
}
/* open the output file */
if ((myargs[3].strvalue != NULL) && (make_protein))
{
if ( (aa = FileOpen (myargs[3].strvalue, "w")) == NULL)
{
ErrShow();
return 1;
}
}
if ((myargs[4].strvalue != NULL) && (make_dna))
{
if ( (na = FileOpen (myargs[4].strvalue, "w")) == NULL)
{
ErrShow();
return 1;
}
}
if ((myargs[13].strvalue != NULL) && (make_quality))
{
if ( (ql = FileOpen (myargs[13].strvalue, "w")) == NULL)
{
ErrShow();
return 1;
}
}
/* log errors instead of die */
if (myargs[5].strvalue != NULL)
{
if (! ErrSetLog (myargs[5].strvalue))
ErrShow();
else
ErrSetOpts (ERR_CONTINUE, ERR_LOG_ON);
}
if (myargs[6].intvalue) /* combine segmented seqs */
{
group_segs = 1;
if (myargs[10].intvalue)
group_segs = 3; /* and instantiate virtuals */
}
limit_to_genbank = (Boolean)(myargs[9].intvalue);
if (myargs [15].intvalue) {
ID1BioseqFetchEnable ("asn2fast", FALSE);
}
if (myargs [16].intvalue) {
LocalSeqFetchInit (FALSE);
}
if ( myargs[1].intvalue) /* read one Seq-entry */
{
sep = SeqEntryAsnRead(aip, NULL);
do_it = TRUE;
if (limit_to_genbank)
do_it = CheckIsGenBank(sep);
if (do_it)
{
if (make_protein)
SeqEntrysToFasta(sep, aa, FALSE, group_segs);
if (make_dna)
SeqEntrysToFasta(sep, na, TRUE, group_segs);
if (make_quality) {
if (far_quality) {
SeqEntryExplore (sep, (Pointer) ql, PrintFarQualScores);
} else {
SeqEntryExplore (sep, (Pointer) ql, PrintQualScores);
}
}
}
SeqEntryFree(sep);
}
else if ( myargs[11].intvalue) /* read Seq-submit's */
{
while ((atp = AsnReadId(aip, amp, atp)) != NULL)
{
if (atp == atp2) /* top level Seq-entry */
{
ssp = SeqSubmitAsnRead(aip, atp);
if (ssp->datatype == 1)
{
sep = (SeqEntryPtr) ssp->data;
do_it = TRUE;
if (limit_to_genbank)
do_it = CheckIsGenBank(sep);
if (do_it)
{
if (make_protein)
SeqEntrysToFasta(sep, aa, FALSE, group_segs);
if (make_dna)
SeqEntrysToFasta(sep, na, TRUE, group_segs);
if (make_quality) {
if (far_quality) {
SeqEntryExplore (sep, (Pointer) ql, PrintFarQualScores);
} else {
SeqEntryExplore (sep, (Pointer) ql, PrintQualScores);
}
}
}
}
SeqSubmitFree(ssp);
}
else
{
AsnReadVal(aip, atp, NULL);
}
}
}
else /* read Seq-entry's from a Bioseq-set */
{
while ((atp = AsnReadId(aip, amp, atp)) != NULL)
{
if (atp == atp2) /* top level Seq-entry */
{
sep = SeqEntryAsnRead(aip, atp);
do_it = TRUE;
if (limit_to_genbank)
do_it = CheckIsGenBank(sep);
if (do_it)
{
if (make_protein)
SeqEntrysToFasta(sep, aa, FALSE, group_segs);
if (make_dna)
SeqEntrysToFasta(sep, na, TRUE, group_segs);
if (make_quality) {
if (far_quality) {
SeqEntryExplore (sep, (Pointer) ql, PrintFarQualScores);
} else {
SeqEntryExplore (sep, (Pointer) ql, PrintQualScores);
}
}
}
SeqEntryFree(sep);
}
else
{
AsnReadVal(aip, atp, NULL);
}
}
}
AsnIoClose(aip);
if (make_protein)
FileClose(aa);
if (make_dna)
FileClose(na);
if (make_quality)
FileClose (ql);
if (myargs [16].intvalue) {
LocalSeqFetchDisable ();
}
if (myargs [15].intvalue) {
ID1BioseqFetchDisable ();
}
return(0);
}
/*****************************************************************************
*
* PubSetAsnRead(aip, atp)
* atp is the current type (if identifier of a parent struct)
* assumption is readIdent has occurred
* if atp == NULL, then assumes it stands alone and read ident
* has not occurred.
*
*****************************************************************************/
NLM_EXTERN ValNodePtr LIBCALL PubSetAsnRead (AsnIoPtr aip, AsnTypePtr orig)
{
DataVal av;
AsnTypePtr atp, settype;
Pointer pnt;
ValNodePtr anp=NULL, cit, curr;
Uint1 choice;
AsnReadFunc func;
Boolean first;
if (! loaded)
{
if (! PubAsnLoad())
return anp;
}
if (aip == NULL)
return anp;
if (orig == NULL) /* PubSet ::= (self contained) */
atp = AsnReadId(aip, amp, PUB_SET);
else
atp = AsnLinkType(orig, PUB_SET); /* link in local tree */
if (atp == NULL) return anp;
anp = ValNodeNew(NULL);
if (anp == NULL) goto erret;
if (AsnReadVal(aip, atp, &av) <= 0) /* read the CHOICE value (nothing) */
goto erret;
settype = AsnReadId(aip, amp, atp); /* find the choice */
if (settype == NULL) goto erret;
if (AsnReadVal(aip, settype, &av) <= 0) /* read START_STRUCT */
goto erret;
if (settype == PUB_SET_pub)
{
choice = 1;
func = (AsnReadFunc) PubAsnRead;
}
else if (settype == PUB_SET_medline)
{
choice = 3;
func = (AsnReadFunc) MedlineEntryAsnRead;
}
else if (settype == PUB_SET_article)
{
choice = 5;
func = (AsnReadFunc) CitArtAsnRead;
}
else if (settype == PUB_SET_journal)
{
choice = 6;
func = (AsnReadFunc) CitJourAsnRead;
}
else if (settype == PUB_SET_book)
{
choice = 7;
func = (AsnReadFunc) CitBookAsnRead;
}
else if (settype == PUB_SET_proc)
{
choice = 8;
func = (AsnReadFunc) CitBookAsnRead;
}
else if (settype == PUB_SET_patent)
{
choice = 9;
func = (AsnReadFunc) CitPatAsnRead;
}
anp->choice = choice;
first = TRUE;
curr = NULL;
while ((atp = AsnReadId(aip, amp, settype)) != settype)
{
if (atp == NULL) goto erret;
pnt = (* func)(aip, atp);
if (pnt == NULL) goto erret;
if (settype == PUB_SET_pub) /* already a Pub */
{
cit = (ValNodePtr)pnt;
}
else /* make into a Pub */
{
cit = ValNodeNew(NULL);
if (cit == NULL) goto erret;
cit->data.ptrvalue = pnt;
cit->choice = choice;
}
if (first)
{
anp->data.ptrvalue = (Pointer)cit;
first = FALSE;
}
else
{
curr->next = cit;
}
curr = cit;
}
if (AsnReadVal(aip, settype, &av) <= 0) /* read END_STRUCT for SET OF */
goto erret;
if (anp == NULL)
ErrPost(CTX_NCBIOBJ, 1, "Empty SET OF Pub. line %ld", aip->linenumber);
ret:
AsnUnlinkType(orig); /* unlink local tree */
return anp;
erret:
anp = PubSetFree(anp);
goto ret;
}
/*****************************************************************************
*
* PubAsnRead(aip, atp)
* atp is the current type (if identifier of a parent struct)
* assumption is readIdent has occurred
* if atp == NULL, then assumes it stands alone and read ident
* has not occurred.
*
*****************************************************************************/
NLM_EXTERN ValNodePtr LIBCALL PubAsnRead (AsnIoPtr aip, AsnTypePtr orig)
{
DataVal av;
AsnTypePtr atp;
ValNodePtr anp=NULL;
Uint1 choice = 0;
AsnReadFunc func = NULL;
if (! loaded)
{
if (! PubAsnLoad())
return anp;
}
if (aip == NULL)
return anp;
if (orig == NULL) /* Pub ::= (self contained) */
atp = AsnReadId(aip, amp, PUB);
else
atp = AsnLinkType(orig, PUB); /* link in local tree */
if (atp == NULL) return anp;
anp = ValNodeNew(NULL);
if (anp == NULL) goto erret;
if (AsnReadVal(aip, atp, &av) <= 0) goto erret; /* read the CHOICE value (nothing) */
atp = AsnReadId(aip, amp, atp); /* find the choice */
if (atp == NULL) goto erret;
if (atp == PUB_gen)
{
choice = 1;
func = (AsnReadFunc) CitGenAsnRead;
}
else if (atp == PUB_sub)
{
choice = 2;
func = (AsnReadFunc) CitSubAsnRead;
}
else if (atp == PUB_medline)
{
choice = 3;
func = (AsnReadFunc) MedlineEntryAsnRead;
}
else if (atp == PUB_muid)
{
choice = 4;
if (AsnReadVal(aip, atp, &anp->data) <= 0) goto erret;
}
else if (atp == PUB_article)
{
choice = 5;
func = (AsnReadFunc) CitArtAsnRead;
}
else if (atp == PUB_journal)
{
choice = 6;
func = (AsnReadFunc) CitJourAsnRead;
}
else if (atp == PUB_book)
{
choice = 7;
func = (AsnReadFunc) CitBookAsnRead;
}
else if (atp == PUB_proc)
{
choice = 8;
func = (AsnReadFunc) CitProcAsnRead;
}
else if (atp == PUB_patent)
{
choice = 9;
func = (AsnReadFunc) CitPatAsnRead;
}
else if (atp == PUB_pat_id)
{
choice = 10;
func = (AsnReadFunc) IdPatAsnRead;
}
else if (atp == PUB_man)
{
choice = 11;
func = (AsnReadFunc) CitLetAsnRead;
}
else if (atp == PUB_equiv)
{
choice = 12;
func = (AsnReadFunc) PubEquivAsnRead;
}
else if (atp == PUB_pmid)
{
choice = 13;
if (AsnReadVal(aip, atp, &anp->data) <= 0) goto erret;
}
anp->choice = choice;
if ((choice != 4) && (choice != 13) && func != NULL)
{
anp->data.ptrvalue = (* func)(aip, atp);
if (anp->data.ptrvalue == NULL) goto erret;
}
ret:
AsnUnlinkType(orig); /* unlink local tree */
return anp;
erret:
anp = PubFree(anp);
goto ret;
}
char *readASNSeq(const short whichEntry, const char *filename,
const long skiplines,
const short format, /* note: this is kASNseqentry or kASNseqset */
long *seqlen, short *nseq,
short *error, char **seqid )
{
AsnIoPtr aip = NULL;
SeqEntryPtr the_set;
AsnTypePtr atp, atp2;
AsnModulePtr amp;
Boolean inIsBinary= FALSE; /* damn, why can't asn routines test this? */
char *seq, stemp[200];
int i, count;
*seqlen= 0;
*nseq= 0;
*error= 0;
seq= NULL;
/*fprintf(stderr,"readASNseq: SeqEntryLoad\n");*/
/* asn dictionary setups */
if (! SeqEntryLoad()) goto errxit; /* sequence alphabets (and sequence parse trees) */
amp = AsnAllModPtr(); /* get pointer to all loaded ASN.1 modules */
if (amp == NULL) goto errxit;
atp = AsnFind("Bioseq-set"); /* get the initial type pointers */
if (atp == NULL) goto errxit;
atp2 = AsnFind("Bioseq-set.seq-set.E");
if (atp2 == NULL) goto errxit;
/* open the ASN.1 input file in the right mode */
/*fprintf(stderr,"readASNseq: AsnIoOpen(%s)\n", filename);*/
if ((aip = AsnIoOpen(filename, inIsBinary?"rb":"r")) == NULL) goto errxit;
for (i=0; i<skiplines; i++) fgets( stemp, 255, aip->fp); /* this may mess up asn routines... */
if (! ErrSetLog ("stderr")) goto errxit;
else ErrSetOpts(ERR_CONTINUE, ERR_LOG_ON); /*?? log errors instead of die */
seq= NULL;
if (format == kASNseqentry) { /* read one Seq-entry */
/*fprintf(stderr,"readASNseq: SeqEntryAsnRead\n");*/
the_set = SeqEntryAsnRead(aip, NULL);
SeqEntryToRaw(the_set, false, whichEntry, nseq, &seq, seqid, seqlen);
SeqEntryFree(the_set);
goto goodexit;
}
else { /* read Seq-entry's from a Bioseq-set */
count = 0;
/*fprintf(stderr,"readASNseq: AsnReadId\n");*/
while ((atp = AsnReadId(aip, amp, atp)) != NULL) {
if (atp == atp2) { /* top level Seq-entry */
the_set = SeqEntryAsnRead(aip, atp);
SeqEntryToRaw(the_set, false, whichEntry, nseq, &seq, seqid, seqlen);
SeqEntryFree(the_set);
if (*nseq >= whichEntry) goto goodexit;
}
else
AsnReadVal(aip, atp, NULL);
count++;
}
}
goodexit:
AsnIoClose(aip);
*error= 0;
return seq;
errxit:
AsnIoClose(aip);
*error= eASNerr;
if (seq) free(seq);
return NULL;
}
/*****************************************************************************
*
* LinkSetAsnRead(aip, atp)
* atp is the current type (if identifier of a parent struct)
* assumption is readIdent has occurred
* if atp == NULL, then assumes it stands alone and read ident
* has not occurred.
*
*****************************************************************************/
NLM_EXTERN LinkSetPtr LIBCALL LinkSetAsnRead (AsnIoPtr aip, AsnTypePtr orig)
{
DataVal av;
AsnTypePtr atp;
LinkSetPtr lsp=NULL;
Int4 num, i;
Int4Ptr ptr;
if (! loaded)
{
if (! AccessAsnLoad())
return lsp;
}
if (aip == NULL)
return lsp;
if (orig == NULL) /* LinkSet ::= (self contained) */
atp = AsnReadId(aip, amp, LINK_SET);
else
atp = AsnLinkType(orig, LINK_SET); /* link in local tree */
if (atp == NULL)
return lsp;
lsp = LinkSetNew();
if (lsp == NULL)
goto erret;
if (AsnReadVal(aip, atp, &av) <= 0) /* read the start struct */
goto erret;
atp = AsnReadId(aip, amp, atp); /* find the num */
if (atp == NULL)
goto erret;
if (AsnReadVal(aip, atp, &av) <= 0) /* get the num */
goto erret;
num = av.intvalue;
lsp->num = num;
atp = AsnReadId(aip, amp, atp); /* start seq of uids */
if (atp == NULL)
goto erret;
if (AsnReadVal(aip, atp, &av) <= 0)
goto erret;
ptr = (Int4Ptr)MemNew((size_t)(sizeof(Int4) * (num + 1))); /* 0 sentinel at end */
if (ptr == NULL)
goto erret;
lsp->uids = ptr;
i = 0;
while ((atp = AsnReadId(aip, amp, atp)) == LINK_SET_uids_E)
{
if (AsnReadVal(aip, atp, &av) <= 0) goto erret;
ptr[i] = av.intvalue;
i++;
if (i > num)
break;
}
if (atp == NULL)
goto erret;
if (i != num)
{
ErrPost(CTX_NCBIOBJ, 0, "Incorrect number of uids in Link-set. line %ld",
aip->linenumber);
goto erret;
}
if (AsnReadVal(aip, atp, &av) <= 0) goto erret; /* end seq of */
atp = AsnReadId(aip, amp, atp);
if (atp == NULL)
goto erret;
if (atp == LINK_SET_weights)
{
if (AsnReadVal(aip, atp, &av) <= 0) goto erret;
ptr = (Int4Ptr)MemNew((size_t)(sizeof(Int4) * (num + 1))); /* 0 sentinel at end */
if (ptr == NULL)
goto erret;
lsp->weights = ptr;
i = 0;
while ((atp = AsnReadId(aip, amp, atp)) == LINK_SET_weights_E)
{
if (AsnReadVal(aip, atp, &av) <= 0) goto erret;
ptr[i] = av.intvalue;
i++;
if (i > num)
break;
}
if (atp == NULL)
goto erret;
if (i != num)
{
ErrPost(CTX_NCBIOBJ, 0, "Incorrect number of weights in Link-set. line %ld",
aip->linenumber);
goto erret;
}
if (AsnReadVal(aip, atp, &av) <= 0) goto erret; /* end seq of */
if ((atp = AsnReadId(aip, amp, atp)) == NULL)
goto erret;
}
if (AsnReadVal(aip, atp, &av) <= 0) goto erret; /* end struct */
ret:
AsnUnlinkType(orig); /* unlink local tree */
return lsp;
erret:
lsp = LinkSetFree(lsp);
goto ret;
}
static void ProcessMultipleRecord (
CharPtr filename,
CSpeedFlagPtr cfp
)
{
AsnIoPtr aip;
AsnTypePtr atp;
BioseqPtr bsp;
Char buf [41];
Uint2 entityID;
FILE *fp;
SeqEntryPtr fsep;
Char longest [41];
Int4 numrecords, x;
SeqEntryPtr sep;
time_t starttime, stoptime, worsttime;
#ifdef OS_UNIX
Char cmmd [256];
CharPtr gzcatprog;
int ret;
Boolean usedPopen = FALSE;
#endif
if (cfp == NULL) return;
if (StringHasNoText (filename)) return;
#ifndef OS_UNIX
if (cfp->compressed) {
Message (MSG_POSTERR, "Can only decompress on-the-fly on UNIX machines");
return;
}
#endif
#ifdef OS_UNIX
if (cfp->compressed) {
gzcatprog = getenv ("NCBI_UNCOMPRESS_BINARY");
if (gzcatprog != NULL) {
sprintf (cmmd, "%s %s", gzcatprog, filename);
} else {
ret = system ("gzcat -h >/dev/null 2>&1");
if (ret == 0) {
sprintf (cmmd, "gzcat %s", filename);
} else if (ret == -1) {
Message (MSG_POSTERR, "Unable to fork or exec gzcat in ScanBioseqSetRelease");
return;
} else {
ret = system ("zcat -h >/dev/null 2>&1");
if (ret == 0) {
sprintf (cmmd, "zcat %s", filename);
} else if (ret == -1) {
Message (MSG_POSTERR, "Unable to fork or exec zcat in ScanBioseqSetRelease");
return;
} else {
Message (MSG_POSTERR, "Unable to find zcat or gzcat in ScanBioseqSetRelease - please edit your PATH environment variable");
return;
}
}
}
fp = popen (cmmd, /* cfp->binary? "rb" : */ "r");
usedPopen = TRUE;
} else {
fp = FileOpen (filename, cfp->binary? "rb" : "r");
}
#else
fp = FileOpen (filename, cfp->binary? "rb" : "r");
#endif
if (fp == NULL) {
Message (MSG_POSTERR, "FileOpen failed for input file '%s'", filename);
return;
}
aip = AsnIoNew (cfp->binary? ASNIO_BIN_IN : ASNIO_TEXT_IN, fp, NULL, NULL, NULL);
if (aip == NULL) {
Message (MSG_ERROR, "AsnIoNew failed for input file '%s'", filename);
return;
}
if (cfp->logfp != NULL) {
fprintf (cfp->logfp, "%s\n\n", filename);
fflush (cfp->logfp);
}
longest [0] = '\0';
worsttime = 0;
numrecords = 0;
atp = cfp->atp_bss;
while ((atp = AsnReadId (aip, cfp->amp, atp)) != NULL) {
if (atp == cfp->atp_se) {
sep = SeqEntryAsnRead (aip, atp);
if (sep != NULL) {
entityID = ObjMgrGetEntityIDForChoice (sep);
fsep = FindNthBioseq (sep, 1);
if (fsep != NULL && fsep->choice == 1) {
bsp = (BioseqPtr) fsep->data.ptrvalue;
if (bsp != NULL) {
SeqIdWrite (bsp->id, buf, PRINTID_FASTA_LONG, sizeof (buf));
if (cfp->logfp != NULL) {
fprintf (cfp->logfp, "%s\n", buf);
fflush (cfp->logfp);
}
}
}
starttime = GetSecs ();
for (x = 0; x < cfp->maxcount; x++) {
DoProcess (sep, entityID, cfp);
}
stoptime = GetSecs ();
if (stoptime - starttime > worsttime) {
worsttime = stoptime - starttime;
StringCpy (longest, buf);
}
numrecords++;
ObjMgrFreeByEntityID (entityID);
}
} else {
AsnReadVal (aip, atp, NULL);
}
}
AsnIoFree (aip, FALSE);
#ifdef OS_UNIX
if (usedPopen) {
pclose (fp);
} else {
FileClose (fp);
}
#else
FileClose (fp);
#endif
if (cfp->logfp != NULL && (! StringHasNoText (longest))) {
fprintf (cfp->logfp, "Longest processing time %ld seconds on %s\n",
(long) worsttime, longest);
fprintf (cfp->logfp, "Total number of records %ld\n", (long) numrecords);
fflush (cfp->logfp);
}
}