static void DoTitle (SeqDescrPtr vnp, Pointer userdata)
{
Char ch;
CharPtr ptr, str, tmp;
ScanDataPtr sdp;
if (vnp->choice != Seq_descr_title) return;
str = (CharPtr) vnp->data.ptrvalue;
if (StringHasNoText (str)) return;
sdp = (ScanDataPtr) userdata;
tmp = str;
ptr = StringStr (tmp, "complete ");
while (ptr != NULL) {
tmp = ptr + 9;
ch = *tmp;
while (ch != '\0' && (! (IS_WHITESP (ch)))) {
tmp++;
ch = *tmp;
}
if (ch == '\0') return;
if (StringNICmp (tmp, " genome", 7) == 0) {
tmp [7] = '\0';
RecordTitle (sdp, ptr);
return;
} else if (StringNICmp (tmp, " DNA", 4) == 0) {
tmp [4] = '\0';
RecordTitle (sdp, ptr);
return;
} else if (StringNICmp (tmp, " sequence", 9) == 0) {
tmp [9] = '\0';
RecordTitle (sdp, ptr);
return;
}
ptr = StringStr (tmp, "complete ");
}
if (StringStr (str, "genome DNA") != NULL) {
RecordTitle (sdp, "genome DNA");
return;
}
if (sdp->bulk) return;
if (StringStr (str, "genomic DNA") != NULL) {
RecordTitle (sdp, "genomic DNA");
return;
}
}
static void ExciseProteinIDLine (CharPtr line)
{
CharPtr protein_id_line_start = NULL, protein_id_line_end;
if (StringHasNoText (line))
{
return;
}
protein_id_line_start = StringStr (line, "\n\t\t\tprotein_id\t");
if (protein_id_line_start == NULL)
{
return;
}
protein_id_line_end = StringChr (protein_id_line_start + 1, '\n');
if (protein_id_line_end == NULL)
{
return;
}
while (*protein_id_line_end != 0)
{
*protein_id_line_start = *protein_id_line_end;
protein_id_line_start ++;
protein_id_line_end ++;
}
*protein_id_line_start = 0;
}
DocUid LIBCALL MMDBEvalPDB(CharPtr str)
{
Entrez2BooleanReplyPtr e2br;
Entrez2IdListPtr e2id;
Entrez2RequestPtr e2rq;
Entrez2ReplyPtr e2ry;
Char tmp [61];
Uint4 uid = 0;
if (str == NULL) return 0;
StringNCpy_0 (tmp, str, sizeof (tmp) - 10);
if (StringStr (tmp, "[ACCN]") == NULL) {
StringCat (tmp, " [ACCN]");
}
e2rq = EntrezCreateBooleanRequest (TRUE, FALSE, "Structure", tmp,
0, 0, NULL, 1, 0);
if (e2rq == NULL) return 0;
e2ry = EntrezSynchronousQuery (e2rq);
e2rq = Entrez2RequestFree (e2rq);
if (e2ry == NULL) return 0;
e2br = EntrezExtractBooleanReply (e2ry);
if (e2br == NULL) return 0;
if (e2br->count > 0) {
e2id = e2br->uids;
if (e2id != NULL && e2id->num > 0 && e2id->uids != NULL) {
BSSeek (e2id->uids, 0, SEEK_SET);
uid = Nlm_BSGetUint4 (e2id->uids);
}
}
Entrez2BooleanReplyFree (e2br);
return uid;
/*
LinkSetPtr plsLink = NULL;
DocUid duUID = 0;
if ((!str)) return (DocUid) 0;
plsLink = EntrezTLEvalString(str, (DocType) TYP_ST,
(DocField) FLD_ACCN, NULL, NULL);
if (plsLink != NULL && plsLink->num > 0 && plsLink->uids != NULL)
{
duUID = plsLink->uids[0];
}
LinkSetFree(plsLink);
return duUID;
*/
}
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;
}
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 Boolean s_ProcessOtherLine (AliConfigInfoPtr configPtr,
CharPtr otherStr,
AlignFileDataPtr fileInfoPtr)
{
CharPtr strPtr;
CharPtr tmpStr;
/* Check for datatype declaration */
if (((strPtr = StringStr (otherStr, "datatype")) != NULL) ||
((strPtr = StringStr (otherStr, "DATATYPE")) != NULL) ||
((strPtr = StringStr (otherStr, "Datatype")) != NULL))
{
tmpStr = s_OtherGetValue(strPtr);
if (StringICmp (tmpStr, "DNA") == 0)
configPtr->declaredInfo.dataType = ALI_DATA_NUCLEOTIDE;
else
configPtr->declaredInfo.dataType = ALI_DATA_PROTEIN;
MemFree (tmpStr);
}
/* Check for interleaved/contiguous */
if (((strPtr = StringStr (otherStr, "INTERLEAVED")) != NULL) ||
((strPtr = StringStr (otherStr, "interleaved")) != NULL) ||
((strPtr = StringStr (otherStr, "Interleaved")) != NULL))
configPtr->declaredInfo.contigOrInter = ALI_INTERLEAVED;
else if (((strPtr = StringStr (otherStr, "CONTIGUOUS")) != NULL) ||
((strPtr = StringStr (otherStr, "contiguous")) != NULL) ||
((strPtr = StringStr (otherStr, "Contiguous")) != NULL))
configPtr->declaredInfo.contigOrInter = ALI_CONTIGUOUS;
/* Check for dimensions */
if (((strPtr = StringStr (otherStr, "NTAX")) != NULL) ||
((strPtr = StringStr (otherStr, "ntax")) != NULL) ||
((strPtr = StringStr (otherStr, "nTax")) != NULL))
{
tmpStr = s_OtherGetValue (strPtr);
configPtr->declaredInfo.idCount = atoi(tmpStr);
MemFree (tmpStr);
}
if (((strPtr = StringStr (otherStr, "NCHAR")) != NULL) ||
((strPtr = StringStr (otherStr, "nchar")) != NULL) ||
((strPtr = StringStr (otherStr, "nChar")) != NULL))
{
tmpStr = s_OtherGetValue (strPtr);
configPtr->declaredInfo.seqLength = atoi(tmpStr);
MemFree (tmpStr);
}
/* Check for definition of missing character */
if (((strPtr = StringStr (otherStr, "MISSING")) != NULL) ||
((strPtr = StringStr (otherStr, "missing")) != NULL) ||
((strPtr = StringStr (otherStr, "Missing")) != NULL))
{
tmpStr = s_OtherGetValue(strPtr);
configPtr->missingChar = (CharPtr) MemNew (2);
sprintf (configPtr->missingChar, "%c", tmpStr[0]);
MemFree (tmpStr);
/* If the new missing char conflicts with the */
/* gap or unaligned char, then blank them out */
/* to give the new one precedence. */
if (StringICmp (configPtr->missingChar, configPtr->gapChar) == 0)
StringCpy (configPtr->gapChar, "");
if (StringICmp (configPtr->missingChar, configPtr->unalignedChar) == 0)
StringCpy (configPtr->unalignedChar, "");
}
/* Check for definition of gap character */
if (((strPtr = StringStr (otherStr, "GAP")) != NULL) ||
((strPtr = StringStr (otherStr, "gap")) != NULL) ||
((strPtr = StringStr (otherStr, "Gap")) != NULL))
{
tmpStr = s_OtherGetValue(strPtr);
configPtr->gapChar = (CharPtr) MemNew (2);
sprintf (configPtr->gapChar, "%c", tmpStr[0]);
MemFree (tmpStr);
/* If the new gap char conflicts with the missing */
/* or unaligned char, then blank them out to give */
/* the new one precedence. */
if (StringICmp (configPtr->gapChar, configPtr->missingChar) == 0)
StringCpy (configPtr->missingChar, "");
if (StringICmp (configPtr->gapChar, configPtr->unalignedChar) == 0)
StringCpy (configPtr->unalignedChar, "");
}
/* Check for definition of unaligned character */
if (((strPtr = StringStr (otherStr, "UNALIGNED")) != NULL) ||
((strPtr = StringStr (otherStr, "unaligned")) != NULL) ||
((strPtr = StringStr (otherStr, "Unaligned")) != NULL))
{
tmpStr = s_OtherGetValue(strPtr);
configPtr->unalignedChar = (CharPtr) MemNew (2);
sprintf (configPtr->unalignedChar, "%c", tmpStr[0]);
MemFree (tmpStr);
/* If the new unaligned char conflicts with the */
/* gap or missing char, then blank them out to */
/* give the new one precedence. */
if (StringICmp (configPtr->unalignedChar, configPtr->gapChar) == 0)
StringCpy (configPtr->gapChar, "");
if (StringICmp (configPtr->unalignedChar, configPtr->missingChar) == 0)
StringCpy (configPtr->missingChar, "");
}
/* Return successfully */
return TRUE;
}
/* 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;
}
static Boolean LIBCALLBACK FirstVecScreenCallback (
CONN conn,
Nlm_VoidPtr userdata,
EIO_Status status
)
{
VQueuePtr cqp;
FILE *fp;
Char line [256];
Char path [PATH_MAX];
CharPtr rid;
CharPtr rtoe;
CharPtr str;
long int val;
/* read rID or failure message */
cqp = (VQueuePtr) userdata;
TmpNam (path);
fp = FileOpen (path, "w");
QUERY_CopyResultsToFile (conn, fp);
FileClose (fp);
fp = FileOpen (path, "r");
str = ReadALine (line, sizeof (line), fp);
while (str != NULL) {
if (! StringHasNoText (line)) {
if (line [0] == '>') {
if (StringNICmp (line, ">Vector", 7) == 0) {
rid = StringStr (line, "RID: ");
if (rid != NULL) {
rid += 5;
rtoe = StringStr (rid, " RTOE: ");
if (rtoe != NULL) {
*rtoe = '\0';
rtoe += 7;
StringNCpy_0 (cqp->rid, rid, sizeof (cqp->rid));
if (sscanf (rtoe, "%ld", &val) == 1) {
cqp->estTime = (time_t) val;
cqp->secondsToWait = (Int2) val + 2;
} else {
cqp->secondsToWait = 15;
}
if (cqp->secondsToWait > 15) {
cqp->secondsToWait = 15;
}
if (cqp->announceproc != NULL) {
cqp->announceproc (rid, cqp->seqid, (Int2) val);
}
}
} else if (StringStr (line, "FAILED") != NULL) {
cqp->done = TRUE;
if (cqp->resultproc != NULL) {
cqp->resultproc (NULL, cqp->userdata, cqp->rid, cqp->seqid, FALSE);
}
}
} else if (StringNICmp (line, ">Message", 8) == 0) {
str = ReadALine (line, sizeof (line), fp);
while (str != NULL && StringNCmp (line, "//", 2) != 0) {
Message (MSG_POST, "%s\n", str);
if (StringStr (line, "FAILURE") != NULL) {
cqp->done = TRUE;
}
str = ReadALine (line, sizeof (line), fp);
}
}
}
}
str = ReadALine (line, sizeof (line), fp);
}
FileClose (fp);
FileRemove (path);
return TRUE;
}
static Boolean LIBCALLBACK SecondVecScreenCallback (
CONN conn,
Nlm_VoidPtr userdata,
EIO_Status status
)
{
VQueuePtr cqp;
FILE *fp;
Char line [256];
Char path [PATH_MAX];
CharPtr rid;
CharPtr sttus;
CharPtr str;
Boolean success = FALSE;
Boolean waiting = FALSE;
/* look for waiting, failure, or success */
cqp = (VQueuePtr) userdata;
TmpNam (path);
fp = FileOpen (path, "w");
QUERY_CopyResultsToFile (conn, fp);
FileClose (fp);
fp = FileOpen (path, "r");
str = ReadALine (line, sizeof (line), fp);
while (str != NULL) {
if (! StringHasNoText (line)) {
if (line [0] == '>') {
if (StringNICmp (line, ">Vector", 7) == 0) {
rid = StringStr (line, "RID: ");
if (rid != NULL) {
rid += 5;
sttus = StringStr (rid, " Status: ");
if (sttus != NULL) {
*sttus = '\0';
sttus += 9;
if (StringCmp (cqp->rid, rid) != 0) {
ErrPostEx (SEV_ERROR, 0, 0, "RID mismatch '%s' vs '%s'", cqp->rid, rid);
cqp->done = TRUE;
} else if (StringStr (sttus, "FAILED") != NULL) {
cqp->done = TRUE;
} else if (StringStr (sttus, "unknown") != NULL) {
ErrPostEx (SEV_ERROR, 0, 0, "RID unknown '%s'", rid);
cqp->done = TRUE;
} else if (StringStr (sttus, "SUCCESS") != NULL) {
success = TRUE;
} else if (StringStr (sttus, "WAITING") != NULL) {
waiting = TRUE;
/*
Message (MSG_POST, "WAITING");
*/
}
}
}
} else if (StringNICmp (line, ">Message", 8) == 0) {
str = ReadALine (line, sizeof (line), fp);
while (str != NULL && StringNCmp (line, "//", 2) != 0) {
Message (MSG_POST, "%s\n", str);
if (StringStr (line, "FAILURE") != NULL) {
if (! waiting) {
cqp->done = TRUE;
}
}
str = ReadALine (line, sizeof (line), fp);
}
}
}
}
str = ReadALine (line, sizeof (line), fp);
}
FileClose (fp);
if (success) {
cqp->resultproc (path, cqp->userdata, cqp->rid, cqp->seqid, success);
cqp->done = TRUE;
} else if (cqp->done) {
cqp->resultproc (NULL, cqp->userdata, cqp->rid, cqp->seqid, success);
}
FileRemove (path);
return TRUE;
}
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;
}
