static void CommentFieldsToDialog (DialoG d, Pointer data)
{
TagListPtr tlp;
ValNodePtr fields, vnp;
CharPtr str;
tlp = (TagListPtr) GetObjectExtra (d);
if (tlp == NULL) {
return;
}
fields = (ValNodePtr) data;
tlp->vnp = ValNodeFreeData (tlp->vnp);
SendMessageToDialog (tlp->dialog, VIB_MSG_RESET);
for (vnp = fields; vnp != NULL; vnp = vnp->next) {
str = TagStringFromFieldRule (vnp->data.ptrvalue);
if (str != NULL) {
ValNodeAddPointer (&(tlp->vnp), 0, str);
}
}
SendMessageToDialog (tlp->dialog, VIB_MSG_REDRAW);
tlp->max = MAX ((Int2) 0, (Int2) (ValNodeLen (tlp->vnp) - tlp->rows));
CorrectBarMax (tlp->bar, tlp->max);
CorrectBarPage (tlp->bar, tlp->rows - 1, tlp->rows - 1);
if (tlp->max > 0) {
SafeShow (tlp->bar);
} else {
SafeHide (tlp->bar);
}
}
void FreeCSAN(PCSAN pcsanThis)
{
if (pcsanThis->next) FreeCSAN(pcsanThis->next);
if (pcsanThis->pcSeqName) MemFree(pcsanThis->pcSeqName);
if (pcsanThis->pvnSeqAlnPart) ValNodeFreeData(pcsanThis->pvnSeqAlnPart);
if (pcsanThis->pcSeqAln) MemFree(pcsanThis->pcSeqAln);
return;
}
static ValNodePtr FetchItemFieldValuesFree (ValNodePtr field_values)
{
ValNodePtr vnp;
for (vnp = field_values; vnp != NULL; vnp = vnp->next) {
vnp->data.ptrvalue = ValNodeFreeData (vnp->data.ptrvalue);
}
field_values = ValNodeFree (field_values);
return field_values;
}
static void DoReleaseFile (CharPtr inputFile, Boolean binary, Boolean compressed, FILE *fp, AsnIoPtr aop, AsnTypePtr atp_se)
{
ScanData sd;
StringSetPtr ssp;
ValNodePtr vnp;
fprintf (fp, "\n***** %s *****\n\n", inputFile);
sd.fp = fp;
sd.aop = aop;
sd.atp_se = atp_se;
StringCpy (sd.buf, "?");
sd.bulk = FALSE;
sd.cgList = NULL;
sd.lcList = NULL;
sd.impCdsCount = 0;
sd.recordCount = 0;
ScanBioseqSetRelease (inputFile, binary, compressed, (Pointer) &sd, DoRecord);
for (vnp = sd.cgList; vnp != NULL; vnp = vnp->next) {
ssp = (StringSetPtr) vnp->data.ptrvalue;
if (ssp == NULL) continue;
fprintf (sd.fp, "CG - %s (%ld) - %s\n", ssp->firstID, (long) ssp->count, ssp->text);
}
for (vnp = sd.lcList; vnp != NULL; vnp = vnp->next) {
ssp = (StringSetPtr) vnp->data.ptrvalue;
if (ssp == NULL) continue;
fprintf (sd.fp, "LC - %s (%ld) - %s\n", ssp->firstID, (long) ssp->count, ssp->text);
}
if (sd.impCdsCount != 0) {
fprintf (sd.fp, "IC - (%ld)\n", (long) sd.impCdsCount);
}
sd.cgList = ValNodeFreeData (sd.cgList);
sd.lcList = ValNodeFreeData (sd.lcList);
fprintf (fp, "\n\n!!!!! %s - %ld records !!!!!\n\n", inputFile, (long) sd.recordCount);
}
/******************************************************************
*
* free_cvp_list(cvp_list)
* free a list of CodonVectorPtr
*
******************************************************************/
NLM_EXTERN ValNodePtr free_cvp_list(ValNodePtr cvp_list)
{
ValNodePtr next;
CodonVectorPtr cvp;
Int2 i;
while(cvp_list)
{
next = cvp_list->next;
cvp_list->next = NULL;
cvp = cvp_list->data.ptrvalue;
for(i=0; i<3; ++i)
MemFree(cvp->buf[i]);
SeqIdFree(cvp->sip);
ValNodeFreeData(cvp_list);
cvp_list = next;
}
return NULL;
}
Int2 Main (void)
{
AsnIoPtr aop = NULL;
AsnModulePtr amp;
AsnTypePtr atp_bss, atp_ss, atp_se;
BioseqSet bss;
FILE *fp;
ValNodePtr head, vnp;
Char path [PATH_MAX];
CharPtr progname, str, subfile;
ErrSetFatalLevel (SEV_MAX);
ErrClearOptFlags (EO_SHOW_USERSTR);
UseLocalAsnloadDataAndErrMsg ();
ErrPathReset ();
if (! AllObjLoad ()) {
Message (MSG_FATAL, "AllObjLoad failed");
return 1;
}
if (! SubmitAsnLoad ()) {
Message (MSG_FATAL, "SubmitAsnLoad failed");
return 1;
}
if (! SeqCodeSetLoad ()) {
Message (MSG_FATAL, "SeqCodeSetLoad failed");
return 1;
}
if (! GeneticCodeTableLoad ()) {
Message (MSG_FATAL, "GeneticCodeTableLoad failed");
return 1;
}
MemSet ((Pointer) &bss, 0, sizeof (BioseqSet));
amp = AsnAllModPtr ();
if (amp == NULL) {
Message (MSG_FATAL, "Unable to load AsnAllModPtr");
return 1;
}
atp_bss = AsnFind ("Bioseq-set");
if (atp_bss == NULL) {
Message (MSG_FATAL, "Unable to find ASN.1 type Bioseq-set");
return 1;
}
atp_ss = AsnFind ("Bioseq-set.seq-set");
if (atp_ss == NULL) {
Message (MSG_FATAL, "Unable to find ASN.1 type Bioseq-set.seq-set");
return 1;
}
atp_se = AsnFind ("Bioseq-set.seq-set.E");
if (atp_se == NULL) {
Message (MSG_FATAL, "Unable to find ASN.1 type Bioseq-set.seq-set.E");
return 1;
}
ProgramPath (path, sizeof (path));
progname = StringRChr (path, DIRDELIMCHR);
if (progname != NULL) {
progname++;
} else {
progname = "idcleanscan";
}
if (! GetArgs (progname, sizeof (myargs) / sizeof (Args), myargs)) {
return 0;
}
fp = FileOpen (myargs [o_argOutputFile].strvalue, "a");
if (fp == NULL) {
Message (MSG_FATAL, "FileOpen failed");
return 1;
}
if (StringHasNoText (myargs [p_argInputPath].strvalue)) {
str = myargs [i_argInputFile].strvalue;
if (! StringHasNoText (str)) {
DoReleaseFile (str, myargs [b_argBinaryFile].intvalue, myargs [c_argCompressed].intvalue, fp, aop, NULL);
}
} else {
head = DirCatalog (myargs [p_argInputPath].strvalue);
if (! StringHasNoText (myargs [s_argSubset].strvalue)) {
aop = AsnIoOpen (myargs [s_argSubset].strvalue, /* "wb" */ "w");
AsnOpenStruct (aop, atp_bss, (Pointer) &bss);
AsnOpenStruct (aop, atp_ss, (Pointer) bss.seq_set);
/*
av.intvalue = BioseqseqSet_class_genbank;
AsnWrite (aop, atp_cls, &av);
*/
}
for (vnp = head; vnp != NULL; vnp = vnp->next) {
if (vnp->choice == 0) {
str = (CharPtr) vnp->data.ptrvalue;
if (! StringHasNoText (str)) {
subfile = myargs [x_argFileSelect].strvalue;
if (StringHasNoText (subfile) || StringStr (str, subfile) != NULL) {
#ifdef OS_UNIX
/* printf ("%s\n", str); */
#endif
DoReleaseFile (str, myargs [b_argBinaryFile].intvalue, myargs [c_argCompressed].intvalue, fp, aop, atp_se);
}
}
}
}
if (aop != NULL) {
AsnCloseStruct (aop, atp_ss, (Pointer) bss.seq_set);
AsnCloseStruct (aop, atp_bss, (Pointer) &bss);
AsnIoClose (aop);
}
ValNodeFreeData (head);
}
FileClose (fp);
return 0;
}
static void DoGraphs (BioseqPtr bsp, Pointer userdata)
{
Byte bases [400];
ByteStorePtr bs;
Int2 ctr, i, j, val;
Int4 curroffset = 0, gphlen = 0, seqlen = 0, slplen,
bslen, min = INT4_MAX, max = INT4_MIN,
NsWithScore, ACGTsWithoutScore;
DeltaSeqPtr dsp;
Uint2 entityID, olditemid = 0, olditemtype = 0,
numdsp = 0, numsgp = 0;
GphItemPtr gip;
ValNodePtr head, vnp;
Boolean noErrors = TRUE;
Uint1 residue;
ScanDataPtr sdp;
SeqGraphPtr sgp;
SeqIntPtr sintp;
SeqLocPtr slocp;
SeqLitPtr slp;
SeqPortPtr spp;
Char str [128];
if (bsp == NULL) return;
if (! ISA_na (bsp->mol)) return;
if (SeqMgrGetParentOfPart (bsp, NULL) != NULL) return;
sdp = (ScanDataPtr) userdata;
entityID = ObjMgrGetEntityIDForPointer (bsp);
head = GetSeqGraphsOnBioseq (entityID, bsp);
if (head == NULL) return;
for (vnp = head; vnp != NULL; vnp = vnp->next) {
gip = (GphItemPtr) vnp->data.ptrvalue;
if (gip == NULL) continue;
sgp = gip->sgp;
min = MIN ((Int4) min, (Int4) sgp->min.intvalue);
max = MAX ((Int4) max, (Int4) sgp->max.intvalue);
if (sgp->min.intvalue < 0 || sgp->min.intvalue > 100) {
sprintf (str, "Graph min (%ld) out of range", (long) sgp->min.intvalue);
PrintGraphMessage (bsp, sdp, str, NULL);
noErrors = FALSE;
}
if (sgp->max.intvalue < 0 || sgp->max.intvalue > 100) {
sprintf (str, "Graph max (%ld) out of range", (long) sgp->max.intvalue);
PrintGraphMessage (bsp, sdp, str, NULL);
noErrors = FALSE;
}
gphlen += sgp->numval;
bs = (ByteStorePtr) sgp->values;
if (bs != NULL) {
bslen = BSLen (bs);
if (sgp->numval != bslen) {
sprintf (str, "SeqGraph (%ld) and ByteStore (%ld) length mismatch", (long) sgp->numval, (long) bslen);
PrintGraphMessage (bsp, sdp, str, NULL);
noErrors = FALSE;
}
}
}
if (bsp->repr == Seq_repr_raw) {
seqlen = bsp->length;
} else if (bsp->repr == Seq_repr_delta) {
for (dsp = (DeltaSeqPtr) (bsp->seq_ext); dsp != NULL; dsp = dsp->next) {
switch (dsp->choice) {
case 1 :
slocp = (SeqLocPtr) dsp->data.ptrvalue;
if (slocp == NULL) break;
if (slocp->choice != SEQLOC_NULL) {
seqlen += SeqLocLen (slocp);
}
break;
case 2 :
slp = (SeqLitPtr) dsp->data.ptrvalue;
if (slp == NULL || slp->seq_data == NULL) break;
seqlen += slp->length;
break;
default :
break;
}
}
}
if (seqlen != gphlen) {
sprintf (str, "SeqGraph (%ld) and Bioseq (%ld) length mismatch", (long) gphlen, (long) seqlen);
PrintGraphMessage (bsp, sdp, str, NULL);
noErrors = FALSE;
}
if (bsp->repr == Seq_repr_delta) {
for (dsp = (DeltaSeqPtr) (bsp->seq_ext), vnp = head;
dsp != NULL && vnp != NULL; dsp = dsp->next) {
gip = (GphItemPtr) vnp->data.ptrvalue;
if (gip == NULL) continue;
sgp = gip->sgp;
if (sgp == NULL) continue;
switch (dsp->choice) {
case 1 :
slocp = (SeqLocPtr) dsp->data.ptrvalue;
if (slocp != NULL && slocp->choice != SEQLOC_NULL) {
slplen = SeqLocLen (slocp);
curroffset += slplen;
if (sgp->numval != slplen) {
sprintf (str, "SeqGraph (%ld) and SeqLoc (%ld) length mismatch", (long) sgp->numval, (long) slplen);
PrintGraphMessage (bsp, sdp, str, NULL);
noErrors = FALSE;
}
numdsp++;
if (vnp != NULL) {
vnp = vnp->next;
numsgp++;
}
}
break;
case 2 :
slp = (SeqLitPtr) dsp->data.ptrvalue;
if (slp != NULL && slp->seq_data != NULL) {
if (sgp->numval != slp->length) {
sprintf (str, "SeqGraph (%ld) and SeqLit (%ld) length mismatch", (long) sgp->numval, (long) slp->length);
PrintGraphMessage (bsp, sdp, str, NULL);
noErrors = FALSE;
}
slocp = sgp->loc;
if (slocp != NULL && slocp->choice == SEQLOC_INT) {
sintp = (SeqIntPtr) slocp->data.ptrvalue;
if (sintp != NULL) {
if (sintp->from != curroffset) {
sprintf (str, "SeqGraph (%ld) and SeqLit (%ld) start do not coincide", (long) sintp->from, (long) curroffset);
PrintGraphMessage (bsp, sdp, str, NULL);
noErrors = FALSE;
}
if (sintp->to != slp->length + curroffset - 1) {
sprintf (str, "SeqGraph (%ld) and SeqLit (%ld) stop do not coincide", (long) sintp->to, (long) (slp->length + curroffset - 1));
PrintGraphMessage (bsp, sdp, str, NULL);
noErrors = FALSE;
}
}
}
numdsp++;
if (vnp != NULL) {
vnp = vnp->next;
numsgp++;
}
}
if (slp != NULL) {
curroffset += slp->length;
}
break;
default :
break;
}
}
if (numdsp != numsgp) {
sprintf (str, "Different number of SeqGraph (%d) and SeqLit (%d) components", (int) numsgp, (int) numdsp);
PrintGraphMessage (bsp, sdp, str, NULL);
noErrors = FALSE;
}
}
for (vnp = head; vnp != NULL; vnp = vnp->next) {
gip = (GphItemPtr) vnp->data.ptrvalue;
if (gip == NULL) continue;
sgp = gip->sgp;
if (sgp == NULL) continue;
spp = SeqPortNewByLoc (sgp->loc, Seq_code_iupacna);
if (spp == NULL) continue;
slplen = SeqLocLen (sgp->loc);
if (bsp->repr == Seq_repr_delta || bsp->repr == Seq_repr_virtual) {
SeqPortSet_do_virtual (spp, TRUE);
}
bs = (ByteStorePtr) sgp->values;
BSSeek (bs, 0, SEEK_SET);
j = 0;
val = 0;
ctr = SeqPortRead (spp, bases, sizeof (bases));
i = 0;
residue = (Uint1) bases [i];
NsWithScore = 0;
ACGTsWithoutScore = 0;
while (residue != SEQPORT_EOF && j < sgp->numval) {
if (IS_residue (residue)) {
val = (Int2) BSGetByte (bs);
j++;
switch (residue) {
case 'A' :
case 'C' :
case 'G' :
case 'T' :
if (val == 0) {
ACGTsWithoutScore++;
}
break;
case 'N' :
if (val > 0) {
NsWithScore++;
}
break;
default :
break;
}
}
i++;
if (i >= ctr) {
i = 0;
ctr = SeqPortRead (spp, bases, sizeof (bases));
if (ctr < 0) {
bases [0] = -ctr;
} else if (ctr < 1) {
bases [0] = SEQPORT_EOF;
}
}
residue = (Uint1) bases [i];
}
if (ACGTsWithoutScore > 0) {
sprintf (str, "%ld ACGT bases have zero score value", (long) ACGTsWithoutScore);
PrintGraphMessage (bsp, sdp, str, NULL);
noErrors = FALSE;
}
if (NsWithScore > 0) {
sprintf (str, "%ld N bases have positive score value", (long) NsWithScore);
PrintGraphMessage (bsp, sdp, str, NULL);
noErrors = FALSE;
}
SeqPortFree (spp);
}
if (noErrors) {
PrintGraphMessage (bsp, sdp, "Quality scores okay", NULL);
}
ValNodeFreeData (head);
}
Int2 Main (void)
{
CharPtr base, directory, organism, ptr;
Boolean altstart, findorf, flatfile, validate;
ValNodePtr head, vnp;
ErrSetFatalLevel (SEV_MAX);
ErrClearOptFlags (EO_SHOW_USERSTR);
UseLocalAsnloadDataAndErrMsg ();
ErrPathReset ();
if (! AllObjLoad ()) {
Message (MSG_FATAL, "AllObjLoad failed");
return 1;
}
if (! SubmitAsnLoad ()) {
Message (MSG_FATAL, "SubmitAsnLoad failed");
return 1;
}
if (! SeqCodeSetLoad ()) {
Message (MSG_FATAL, "SeqCodeSetLoad failed");
return 1;
}
if (! GeneticCodeTableLoad ()) {
Message (MSG_FATAL, "GeneticCodeTableLoad failed");
return 1;
}
if (! FeatDefSetLoad ()) {
Message (MSG_FATAL, "FeatDefSetLoad failed");
return 1;
}
if (! GetArgs ("sgd2asn", sizeof (myargs) / sizeof (Args), myargs)) {
return 0;
}
directory = (CharPtr) myargs [0].strvalue;
base = (CharPtr) myargs [1].strvalue;
organism = (CharPtr) myargs [2].strvalue;
findorf = (Boolean) myargs [3].intvalue;
altstart = (Boolean) myargs [4].intvalue;
validate = (Boolean) myargs [5].intvalue;
flatfile = (Boolean) myargs [6].intvalue;
if (! StringHasNoText (base)) {
ptr = StringStr (base, ".fsa");
if (ptr != NULL) {
*ptr = '\0';
ProcessOneRecord (directory, base, organism, findorf, altstart, validate, flatfile);
}
} else {
head = DirCatalog (directory);
for (vnp = head; vnp != NULL; vnp = vnp->next) {
if (vnp->choice == 0) {
base = (CharPtr) vnp->data.ptrvalue;
if (! StringHasNoText (base)) {
ptr = StringStr (base, ".fsa");
if (ptr != NULL) {
*ptr = '\0';
ProcessOneRecord (directory, base, organism, findorf, altstart, validate, flatfile);
}
}
}
}
ValNodeFreeData (head);
}
return 0;
}
static void ProcessOneRecord (
CharPtr directory,
CharPtr base,
CharPtr organism,
Boolean findorf,
Boolean altstart,
Boolean validate,
Boolean flatfile
)
{
BioSourcePtr biop = NULL;
BioseqPtr bsp;
Uint2 datatype, entityID;
Int2 genCode;
MolInfoPtr mip;
SeqAnnotPtr sap;
SeqEntryPtr sep;
SeqFeatPtr sfp;
SqnTagPtr stp;
CharPtr ttl;
ValNodePtr vnp;
Message (MSG_POST, "Processing %s\n", base);
bsp = (BioseqPtr) ReadOneFile (directory, base, "fsa", &datatype);
if (bsp == NULL || datatype != OBJ_BIOSEQ) {
ObjMgrFree (datatype, (Pointer) bsp);
return;
}
if (bsp->mol == Seq_mol_na) {
bsp->mol = Seq_mol_dna;
}
vnp = ValNodeExtract (&(bsp->descr), Seq_descr_title);
if (vnp != NULL) {
ttl = (CharPtr) vnp->data.ptrvalue;
if (ttl != NULL) {
stp = SqnTagParse (ttl);
if (stp != NULL) {
biop = OldParseTitleIntoBioSource (stp, bsp, organism);
}
SqnTagFree (stp);
}
ValNodeFreeData (vnp);
}
if (biop == NULL) {
biop = OldParseTitleIntoBioSource (NULL, bsp, organism);
}
if (biop != NULL) {
SeqDescrAddPointer (&(bsp->descr), Seq_descr_source, (Pointer) biop);
}
mip = MolInfoNew ();
if (mip != NULL) {
mip->biomol = MOLECULE_TYPE_GENOMIC;
SeqDescrAddPointer (&(bsp->descr), Seq_descr_molinfo, (Pointer) mip);
}
entityID = ObjMgrRegister (datatype, (Pointer) bsp);
sep = GetBestTopParentForData (entityID, bsp);
genCode = SeqEntryToGeneticCode (sep, NULL, NULL, 0);
if (findorf) {
AnnotateBestOrf (bsp, genCode, altstart);
}
sap = (SeqAnnotPtr) ReadOneFile (directory, base, "tbl", &datatype);
if (sap != NULL && datatype == OBJ_SEQANNOT && sap->type == 1) {
sap->next = bsp->annot;
bsp->annot = sap;
} else {
ObjMgrFree (datatype, (Pointer) sap);
}
/* for parsed in features or best ORF, promote CDS products to protein bioseq */
for (sap = bsp->annot; sap != NULL; sap = sap->next) {
if (sap->type == 1) {
SetEmptyGeneticCodes (sap, genCode);
sfp = (SeqFeatPtr) sap->data;
PromoteXrefs (sfp, bsp, entityID);
}
}
sep = GetTopSeqEntryForEntityID (entityID);
if (sep != NULL) {
SeriousSeqEntryCleanup (sep, NULL, NULL);
WriteOneFile (directory, base, "sqn", sep);
if (validate || flatfile) {
SeqMgrIndexFeatures (entityID, 0);
}
if (validate) {
Message (MSG_POST, "Validating %s\n", base);
ValidateOneFile (directory, base, "val", sep);
}
if (flatfile) {
Message (MSG_POST, "Flatfile %s\n", base);
sep = FindNucSeqEntry (sep);
FlatfileOneFile (directory, base, "gbf", sep);
}
}
ObjMgrFreeByEntityID (entityID);
}
NLM_EXTERN Nlm_Int4 Nlm_DirExplore (
Nlm_CharPtr directory,
Nlm_CharPtr filter,
Nlm_CharPtr suffix,
Nlm_Boolean recurse,
Nlm_DirExpProc proc,
Nlm_VoidPtr userdata
)
{
Nlm_Int4 count = 0;
Nlm_Char file [FILENAME_MAX], path [PATH_MAX];
Nlm_CharPtr ptr, str;
ValNodePtr head, vnp;
if (proc == NULL) return 0;
if (Nlm_StringHasNoText (directory) /* || Nlm_StringHasNoText (suffix) */ ) return 0;
/* get list of all files in source directory */
head = Nlm_DirCatalog (directory);
for (vnp = head; vnp != NULL; vnp = vnp->next) {
if (vnp->choice == 0) {
str = (Nlm_CharPtr) vnp->data.ptrvalue;
if (! Nlm_StringHasNoText (str)) {
/* check filename for indicated suffix */
ptr = Nlm_StringStr (str, suffix);
if (ptr != NULL) {
/* make sure detected suffix is really at end of filename */
if (Nlm_StringCmp (ptr, suffix) == 0) {
*ptr = '\0';
} else {
ptr = NULL;
}
}
if (Nlm_StringHasNoText (suffix) || ptr != NULL) {
Nlm_StringNCpy_0 (path, directory, sizeof (path));
sprintf (file, "%s%s", str, suffix);
Nlm_FileBuildPath (path, NULL, file);
/* check full path/file name for desired filter */
if (Nlm_StringHasNoText (filter) || Nlm_StringStr (path, filter) != NULL) {
/* process file that satisfies optional filter and suffix constraints */
proc (path, userdata);
count++;
}
}
}
} else if (vnp->choice == 1 && recurse) {
/* recurse into subdirectory */
Nlm_StringNCpy_0 (path, directory, sizeof (path));
str = (Nlm_CharPtr) vnp->data.ptrvalue;
Nlm_FileBuildPath (path, str, NULL);
count += Nlm_DirExplore (path, filter, suffix, recurse, proc, userdata);
}
}
/* clean up file list */
ValNodeFreeData (head);
return count;
}
/* return -1 on failure, 0 on success */
static Int4 FileRecurse (
CharPtr directory,
InputStreamPtr isp,
OutputStreamPtr osp,
AsnStreamPtr asp,
Int4Ptr gap_sizes
)
{
Char path [PATH_MAX];
CharPtr ptr;
CharPtr str;
ValNodePtr head, vnp;
CharPtr orig_dir, orig_base;
Int4 rval = 0;
/* get list of all files in source directory */
head = DirCatalog (directory);
for (vnp = head; vnp != NULL; vnp = vnp->next) {
if (vnp->choice == 0) {
str = (CharPtr) vnp->data.ptrvalue;
if (StringDoesHaveText (str)) {
/* does filename have desired substring? */
ptr = StringStr (str, osp->suffix);
if (ptr != NULL) {
/* make sure detected suffix is really at end of filename */
if (StringCmp (ptr, osp->suffix) == 0) {
*ptr = '\0';
/* process file that has desired suffix (usually .fsa) */
osp->base = str;
orig_dir = isp->directory;
isp->directory = directory;
orig_base = isp->base;
isp->base = str;
if (isp->is_binary) {
rval |= ProcessStream (isp, osp, asp, gap_sizes);
} else {
rval |= ProcessOneRecord (directory, osp, gap_sizes);
}
isp->directory = orig_dir;
isp->base = orig_base;
osp->base = NULL;
}
}
}
} else if (vnp->choice == 1) {
/* recurse into subdirectory */
StringNCpy_0 (path, directory, sizeof (path));
str = (CharPtr) vnp->data.ptrvalue;
FileBuildPath (path, str, NULL);
rval |= FileRecurse (path, isp, osp, asp, gap_sizes);
}
}
/* clean up file list */
ValNodeFreeData (head);
return rval;
}
Int2 Main (void)
{
CharPtr base, directory, outfile, suffix, ptr;
BioseqSetPtr bssp;
ValNodePtr head, vnp;
SeqEntryPtr sep;
SeqSubmitPtr ssp;
/* standard setup */
ErrSetFatalLevel (SEV_MAX);
ErrClearOptFlags (EO_SHOW_USERSTR);
UseLocalAsnloadDataAndErrMsg ();
ErrPathReset ();
/* finish resolving internal connections in ASN.1 parse tables */
if (! AllObjLoad ()) {
Message (MSG_FATAL, "AllObjLoad failed");
return 1;
}
if (! SubmitAsnLoad ()) {
Message (MSG_FATAL, "SubmitAsnLoad failed");
return 1;
}
if (! FeatDefSetLoad ()) {
Message (MSG_FATAL, "FeatDefSetLoad failed");
return 1;
}
if (! SeqCodeSetLoad ()) {
Message (MSG_FATAL, "SeqCodeSetLoad failed");
return 1;
}
if (! GeneticCodeTableLoad ()) {
Message (MSG_FATAL, "GeneticCodeTableLoad failed");
return 1;
}
/* process command line arguments */
if (! GetArgs ("subfuse", sizeof (myargs) / sizeof (Args), myargs)) {
return 0;
}
directory = (CharPtr) myargs [p_argInputPath].strvalue;
outfile = (CharPtr) myargs [o_argOutputFile].strvalue;
suffix = (CharPtr) myargs [x_argSuffix].strvalue;
bssp = BioseqSetNew ();
if (bssp == NULL) return 0;
bssp->_class = BioseqseqSet_class_genbank;
sep = SeqEntryNew ();
if (sep == NULL) return 0;
sep->choice = 2;
sep->data.ptrvalue = (Pointer) bssp;
ssp = SeqSubmitNew ();
if (ssp == NULL) return 0;
ssp->datatype = 1;
ssp->data = (Pointer) sep;
/* get list of all files in source directory */
head = DirCatalog (directory);
for (vnp = head; vnp != NULL; vnp = vnp->next) {
if (vnp->choice == 0) {
base = (CharPtr) vnp->data.ptrvalue;
if (! StringHasNoText (base)) {
ptr = StringStr (base, suffix);
if (ptr != NULL) {
*ptr = '\0';
Message (MSG_POST, "Processing %s\n", base);
ProcessOneRecord (ssp, bssp, directory, base, suffix);
}
}
}
}
/* clean up file list */
ValNodeFreeData (head);
/* write output file */
WriteOneSubmission (outfile, ssp);
return 0;
}
Int2 Main (void)
{
Int2 argcount;
Boolean flagHaveNet;
Int4 gi;
SeqEntryPtr sep;
ComPatPtr cpp, cpph = NULL;
SeqAlignPtr sap, sapn;
StdSegPtr ssp;
SeqLocPtr slp, slpn;
Int4 start, stop;
FILE *fiop;
Char fastafile[256], namesfile[256];
CharPtr title;
CharPtr taxon;
FloatHi mw;
ValNodePtr namelist = NULL;
static CharPtr pattern_file = "ncbipros.dat";
static CharPtr protease_file = "ncbiendo.dat";
static CharPtr names_file = "ncbipnam.dat";
static GatherScope gs;
GatherScopePtr gsp;
static Gather_PBS gpbs;
Gather_PBSPtr gpbsp;
#ifndef NO_TAX_NET
Int4 i;
static Char taxdata[8];
static Gather_TaxId gti;
Gather_TaxIdPtr gtip;
#endif
#ifndef NO_TAX_NET
Int2 ia=4, ib=5, ic=6, id=7, ie=8, ig=9, ih=10, ii=11;
#else
Int2 ib=4, ic=5, id=6, ie=7, ig=8, ih=9, ii=10;
#endif
argcount = sizeof (myargs) / sizeof (Args);
if (!GetArgs ("ProSiteSearch", argcount, myargs))
return 1;
if (myargs[0].intvalue == 0 && myargs[1].strvalue == NULL)
{
ErrPostEx (SEV_ERROR, TOP_ERROR, 100,
"No gi or FastA file given :: for help : srchaa -");
ErrShow ();
exit (1);
}
gsp = &gs;
#ifndef NO_TAX_NET
gtip = >i;
#endif
gpbsp = &gpbs;
MemSet ((Pointer) gsp, 0, sizeof (GatherScope));
MemSet ((Pointer) gsp->ignore, (int) (TRUE),
(size_t) (OBJ_MAX * sizeof (Boolean)));
gsp->ignore[OBJ_SEQDESC] = TRUE;
gsp->ignore[OBJ_BIOSEQ] = FALSE;
gpbsp->bsp = NULL;
gi = myargs[0].intvalue;
if (myargs[1].strvalue != NULL)
StrCpy (fastafile, myargs[1].strvalue);
else
fastafile[0] = '\0';
if (gi > 0)
{
if (!EntrezInit ("srchaa", FALSE, &flagHaveNet))
{
ErrPostEx (SEV_ERROR, TOP_ERROR, 102,
"Entrez init failed");
ErrShow ();
exit (1);
}
}
#ifndef NO_TAX_NET
if (myargs[ia].intvalue)
{
if (!TaxArchInit ())
{
ErrPostEx (SEV_ERROR, TOP_ERROR, 103,
"Taxonomy init failed");
ErrShow ();
exit (1);
}
}
#endif
fiop = NULL;
if (gi > 0)
{
sep = EntrezSeqEntryGet (gi, SEQENTRY_READ_BIOSEQ);
}
else
{
if ((fiop = FileOpen (fastafile, "r")) == NULL)
{
ErrPostEx (SEV_ERROR, TOP_ERROR, 103,
"Failed to open FastA file: %s", fastafile);
ErrShow ();
exit (1);
}
sep = FastaToSeqEntry (fiop, FALSE);
}
if (sep == NULL)
{
ErrPostEx (SEV_ERROR, TOP_ERROR, 104,
"No seqentry found");
ErrShow ();
exit (1);
}
while (sep != NULL)
{
gsp->ignore[OBJ_SEQDESC] = TRUE;
gsp->ignore[OBJ_BIOSEQ] = FALSE;
gpbsp->bsp = NULL;
gpbsp->gi = gi;
GatherSeqEntry (sep, (Pointer) gpbsp, GetBioseq, (Pointer) gsp);
taxon = NULL;
#ifndef NO_TAX_NET
if (myargs[ia].intvalue)
{
for (i = 0; i < 8; i++)
taxdata[i] = '-';
taxon = taxdata;
gsp->ignore[OBJ_SEQDESC] = FALSE;
gsp->ignore[OBJ_BIOSEQ] = TRUE;
gtip->taxid = 0;
GatherSeqEntry (sep, (Pointer) gtip, GetTaxId, (Pointer) gsp);
if (gtip->taxid != 0)
WhatOrg (gtip->taxid, taxon);
else
taxon = NULL;
}
#endif
if (gpbsp->bsp != NULL)
{
if (ISA_aa (gpbsp->bsp->mol))
{
if (cpph == NULL)
{
namesfile[0] = '\0';
if (myargs[id].intvalue)
StrCpy (namesfile, names_file);
if (myargs[ie].strvalue != NULL)
StrCpy (namesfile, myargs[ie].strvalue);
if (myargs[ig].strvalue != NULL)
{
if ((cpph = CompilePattern (myargs[ig].strvalue, 1)) != NULL)
StrCpy (cpph->name, "User Pattern");
}
else
{
namelist = ReadPatternNames (namesfile);
if (myargs[ib].intvalue)
cpph = ReadPrositePattern (protease_file,
(Boolean) myargs[2].intvalue,
myargs[3].intvalue,
taxon, NULL);
else
cpph = ReadPrositePattern (pattern_file,
(Boolean) myargs[2].intvalue,
myargs[3].intvalue,
taxon, namelist);
}
}
if (!(Boolean) myargs[ih].intvalue)
{
title = FastaTitle (gpbsp->bsp, ">", NULL);
printf ("%s\n", title);
MemFree (title);
}
cpp = cpph;
while (cpp != NULL)
{
sap = PatternMatchBioseq (gpbsp->bsp, cpp,
(Int4)myargs[ii].intvalue);
if (myargs[ib].intvalue)
{
printf (">%s\n", cpp->name);
if (sap != NULL)
printf (" Start Stop M.W.\n");
}
if (myargs[ib].intvalue)
{
EmbedMolecularWeightInfo (sap, gpbsp->bsp);
if (myargs[ic].intvalue)
URK_SeqAlignSortByMolWt (&sap);
while (sap != NULL)
{
ssp = (StdSegPtr) sap->segs;
slp = ssp->loc;
start = SeqLocStart (slp);
stop = SeqLocStop (slp);
mw = ssp->scores->value.realvalue;
printf ("%8ld %8ld %9.2f\n",
(long) start+1, (long) stop+1, mw);
sapn = sap->next;
SeqAlignFree (sap);
sap = sapn;
}
}
else
{
slp = MatchSa2Sl (&sap);
if (myargs[ih].intvalue && slp != NULL)
{
title = FastaTitle (gpbsp->bsp, ">", NULL);
printf ("%s\n", title);
MemFree (title);
}
while (slp != NULL)
{
start = SeqLocStart (slp);
stop = SeqLocStop (slp);
printf ("%8ld %8ld %s\n",
(long) start+1, (long) stop+1, cpp->name);
slpn = slp->next;
SeqLocFree (slp);
slp = slpn;
}
}
cpp = cpp->nextpattern;
}
}
else
{
ErrPostEx (SEV_ERROR, TOP_ERROR, 106,
"Not a protein bioseq");
ErrShow ();
exit (1);
}
}
else
{
ErrPostEx (SEV_ERROR, TOP_ERROR, 105,
"No bioseq found");
ErrShow ();
exit (1);
}
SeqEntryFree (sep);
sep = NULL;
if (fiop != NULL)
sep = FastaToSeqEntry (fiop, FALSE);
}
ComPatFree (cpph);
ValNodeFreeData (namelist);
FileClose (fiop);
if (gi > 0)
EntrezFini ();
#ifndef NO_TAX_NET
if (myargs[ia].intvalue)
TaxArchFini ();
#endif
return 0;
}
/*******************************************************************************
Function : DDV_GetRulerForEditor()
Purpose : create the ruler for the editor. This new descriptor is created
using the descriptor of the viewer.
Return value : an allocated data block ready for use by the editor. Null if
failure
*******************************************************************************/
NLM_EXTERN ValNodePtr DDV_GetRulerForEditor(ValNodePtr descr_head,Int4 from_disp,
Int4 to_disp)
{
DDVRulerDescrPtr drdp,prev_drdp,new_drdp;
ValNodePtr vnp2,vnp3,vnpDesc;
Int4 cumulDecr,drdp_size,beginCopy,endCopy,drdp_start_ali;
Boolean bPop;
cumulDecr=0;
vnpDesc=NULL;
prev_drdp=NULL;
for(vnp2=descr_head;vnp2!=NULL;vnp2=vnp2->next){
drdp=(DDVRulerDescrPtr)vnp2->data.ptrvalue;
drdp_size=drdp->disp_stop-drdp->disp_start+1;
/*not yet in the region of interest ?*/
if (drdp->disp_stop<from_disp) {
cumulDecr+=drdp_size;
continue;
}
beginCopy=_max_(from_disp,drdp->disp_start);
endCopy=_min_(drdp->disp_stop,to_disp);
if (drdp->bUnAligned==FALSE)
drdp_start_ali=drdp->align_start+(beginCopy-drdp->disp_start);
else
drdp_start_ali=(Int4)-1;
/*in order to merge nodes of same type, i keep track of
the previous populated drdp node. Same style==yes, then
just extend to the right the previous node*/
if (prev_drdp){
if (prev_drdp->bUnAligned==drdp->bUnAligned){
prev_drdp->disp_stop=endCopy;
bPop=TRUE;
}
else{
bPop=FALSE;
}
}
else{
bPop=FALSE;
}
if (!bPop){
new_drdp=(DDVRulerDescrPtr)MemNew(sizeof(DDVRulerDescr));
if (!new_drdp) goto erreur;
new_drdp->disp_start=beginCopy;
new_drdp->disp_stop=endCopy;
new_drdp->align_start=drdp_start_ali;
new_drdp->bUnAligned=drdp->bUnAligned;
if (!vnpDesc){
vnp3=ValNodeAddPointer(&vnpDesc,0,(Pointer)new_drdp);
}
else{
vnp3=ValNodeAddPointer(&vnp3,0,(Pointer)new_drdp);
}
prev_drdp=new_drdp;
}
if (drdp->disp_stop>=to_disp) break;
cumulDecr+=drdp_size;
}
return(vnpDesc);
erreur:
if (vnpDesc)
ValNodeFreeData(vnpDesc);
return(NULL);
}
