/* Set HTTP user header */
static void x_SetupUserHeader (
SConnNetInfo* net_info,
const char* appName,
EMIME_Type type,
EMIME_SubType subtype,
EMIME_Encoding encoding
)
{
const char* userAgentName = NULL;
char user_header [MAX_CONTENT_TYPE_LEN + 80];
/* content-type if specified */
if (type < eMIME_T_Unknown) {
VERIFY( MIME_ComposeContentTypeEx (type, subtype, encoding,
user_header, MAX_CONTENT_TYPE_LEN) );
ConnNetInfo_OverrideUserHeader (net_info, user_header);
}
/* allow the user to specify a prog. name, otherwise get it from elsewhere */
if (StringHasNoText (appName)) {
const char* progName = GetProgramName();
if (StringHasNoText (progName)) {
char path [PATH_MAX];
Nlm_ProgramPath (path, sizeof (path));
userAgentName = StringRChr (path, DIRDELIMCHR);
if (userAgentName)
++userAgentName;
} else
userAgentName = progName;
} else
userAgentName = appName;
if (StringDoesHaveText (userAgentName)) {
sprintf (user_header, "User-Agent: %.80s\r\n", userAgentName);
ConnNetInfo_ExtendUserHeader (net_info, user_header);
}
}
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;
}
/** GET_MATRIX_PATH callback to find the path to a specified matrix.
* Looks first in current directory, then one specified by
* .ncbirc, then in local data directory, then env
* variables.
* @param matrix_name name of the matrix (e.g., BLOSUM50) [in]
* @param is_prot protein matrix if TRUE [in]
* @return path to matrix if found, or NULL.
*/
static char*
s_BlastFindMatrixPath(const char* matrix_name, Boolean is_prot)
{
char* matrix_path = NULL; /* return value. */
char buf_path[PATH_MAX]; /* Used for path without matrix filename. */
char buf_full[PATH_MAX]; /* used for full path with filename. */
char* ptr = NULL;
if (matrix_name == NULL)
return NULL;
/* current directory */
if (Nlm_FileLength((char*) matrix_name) > 0)
{
char buf_path_2[PATH_MAX];
Nlm_ProgramPath(buf_path, PATH_MAX);
ptr = StringRChr (buf_path, DIRDELIMCHR);
if (ptr != NULL)
*ptr = '\0';
sprintf(buf_path_2, "%s%s", buf_path, DIRDELIMSTR);
matrix_path = StringSave(buf_path_2);
return matrix_path;
}
/* local data directory. */
sprintf(buf_full, "data%s%s", DIRDELIMSTR, matrix_name);
if (Nlm_FileLength(buf_full) > 0)
{
char buf_path_2[PATH_MAX];
Nlm_ProgramPath(buf_path, PATH_MAX);
ptr = StringRChr (buf_path, DIRDELIMCHR);
if (ptr != NULL)
*ptr = '\0';
sprintf(buf_path_2, "%s%sdata%s", buf_path, DIRDELIMSTR, DIRDELIMSTR);
matrix_path = StringSave(buf_path_2);
return matrix_path;
}
if(FindPath("ncbi", "ncbi", "data", buf_path, PATH_MAX)) {
sprintf(buf_full, "%s%s", buf_path, matrix_name);
if(FileLength(buf_full) > 0) {
matrix_path = StringSave(buf_path);
return matrix_path;
} else {
char alphabet_type[3]; /* aa or nt */
if (is_prot)
Nlm_StringNCpy(alphabet_type, "aa", 2);
else
Nlm_StringNCpy(alphabet_type, "nt", 2);
alphabet_type[2] = NULLB;
sprintf(buf_full, "%s%s%s%s", buf_path,
alphabet_type, DIRDELIMSTR, matrix_name);
if(FileLength(buf_full) > 0)
{
matrix_path = StringSave(buf_path);
return matrix_path;
}
}
}
return NULL;
}
Int2 Main(void)
{
Char app [64];
CharPtr directory;
CharPtr ptr;
Char sfx [32];
OutputStreamData osd;
InputStreamData isd;
AsnStreamData asd;
Int4 gap_sizes[2];
Int4 rval = 0;
Int4 u_eq = 0, u_gteq = -1, k_eq = 0, k_gteq = -1;
/* 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;
}
SetUpAsnStreamData (&asd);
/* initialize OuputStreamData */
MemSet (&osd, 0, sizeof (osd));
/* initialize InputStreamData */
MemSet (&isd, 0, sizeof (isd));
/* initialize gap_sizes */
gap_sizes[0] = 0;
gap_sizes[1] = 0;
/* process command line arguments */
sprintf (app, "raw2delt %s", RAW2DELT_APPLICATION);
if (! GetArgs (app, sizeof (myargs) / sizeof (Args), myargs)) {
return 0;
}
u_eq = (Int4) myargs [u_argEqUnknownGap].intvalue;
u_gteq = (Int4) myargs [U_argGTEqUnknownGap].intvalue;
k_eq = (Int4) myargs [k_argEqUnknownGap].intvalue;
k_gteq = (Int4) myargs [K_argGtEqUnknownGap].intvalue;
if (u_eq < 1 && u_gteq < 1 && k_eq < 1 && k_gteq < 1) {
Message (MSG_FATAL, "Must specify values for at least one of -u, -U, -k, -K");
return 1;
} else if (u_eq > -1 && u_gteq > -1) {
Message (MSG_FATAL, "May only specify value for -u or -U, not both");
return 1;
} else if (k_eq > -1 && k_gteq > -1) {
Message (MSG_FATAL, "May only specify value for -k or -K, not both");
return 1;
}
if (u_eq > 0) {
gap_sizes[0] = u_eq;
} else if (u_gteq > 0) {
gap_sizes[0] = 0 - u_gteq;
}
if (k_eq > 0) {
gap_sizes[1] = k_eq;
} else if (k_gteq > 0) {
gap_sizes[1] = 0 - k_gteq;
}
if (gap_sizes[0] == gap_sizes[1]) {
Message (MSG_FATAL, "Cannot specify the same size for known and unknown length gaps");
return 1;
}
directory = (CharPtr) myargs [p_argInputPath].strvalue;
osd.results_dir = (CharPtr) myargs [r_argOutputPath].strvalue;
if (StringHasNoText (osd.results_dir)) {
osd.results_dir = NULL;
}
osd.suffix = (CharPtr) myargs [x_argSuffix].strvalue;
osd.outsuffix = (CharPtr) myargs [s_argOutSuffix].strvalue;
osd.base = (CharPtr) myargs [i_argInputFile].strvalue;
osd.outfile = (CharPtr) myargs [o_argOutputFile].strvalue;
if (StringHasNoText (osd.outfile)) {
osd.outfile = NULL;
}
osd.is_binary = (Boolean) myargs [d_argOutputBinary].intvalue;
if (osd.base == "stdin") {
osd.base = NULL;
}
/* if we don't have an output directory or an output file, and the user hasn't provided an
* output suffix, add a default.
*/
if (osd.results_dir == NULL && osd.outfile == NULL && StringHasNoText (osd.outsuffix)) {
osd.outsuffix = ".delta";
}
isd.is_binary = (Boolean) myargs [b_argInputBinary].intvalue;
isd.is_seqentry = (Boolean) myargs [e_argInputSeqEntry].intvalue;
isd.directory = directory;
isd.base = osd.base;
isd.suffix = osd.suffix;
if (StringDoesHaveText (osd.outfile)) {
osd.aip = AsnIoOpen (osd.outfile, "w");
if (osd.aip == NULL) {
Message (MSG_FATAL, "Unable to open output file");
return 1;
}
} else {
if (StringHasNoText (osd.results_dir)) {
osd.results_dir = directory;
}
/* if we're putting the results in a separate directory, strip the directory name from the output base */
if (!StringHasNoText (osd.results_dir) && !StringHasNoText (osd.base)) {
#ifdef OS_MSWIN
ptr = StringRChr (osd.base, '\\');
#else
ptr = StringRChr (osd.base, '/');
#endif;
if (ptr != NULL) {
osd.base = ptr + 1;
}
}
}
if (StringHasNoText(directory) && StringHasNoText(osd.base)) {
rval = ProcessStream (&isd, &osd, &asd, gap_sizes);
} else if (StringDoesHaveText (osd.base)) {
ptr = StringRChr (osd.base, '.');
sfx[0] = '\0';
if (ptr != NULL) {
StringNCpy_0 (sfx, ptr, sizeof (sfx));
*ptr = '\0';
}
osd.suffix = sfx;
isd.suffix = sfx;
if (isd.is_binary) {
rval = ProcessStream (&isd, &osd, &asd, gap_sizes);
} else {
rval = ProcessOneRecord (directory, &osd, gap_sizes);
}
} else {
rval = FileRecurse (directory, &isd, &osd, &asd, gap_sizes);
}
if (osd.aip != NULL) {
AsnIoFlush (osd.aip);
AsnIoClose (osd.aip);
}
return rval;
}
PCSAN LIBCALL LoadCSAN(CharPtr pcFile)
{
FILE *f;
Char fullpath [PATH_MAX];
CharPtr ptr;
PCSAN pcsanHead = NULL;
PCSAN pcsanTemp = NULL;
Char pcBuf[250];
CharPtr ppcParse[125];
CharPtr pcTemp = NULL;
CharPtr pcTest = NULL;
CharPtr pcSeqPart = NULL;
ValNodePtr pvn = NULL;
long int val = 0;
Int4 i = 0;
Int4 iString = 0;
Int4 iLen =0;
Int4 iWC =0;
Int4 iWL = 0;
Int4 iGi = 0;
if (!pcFile) return(NULL);
ProgramPath (fullpath, sizeof (fullpath) - 1);
ptr = StringRChr (fullpath, DIRDELIMCHR);
if (ptr != NULL) {
*ptr = '\0';
}
/* printf("FULLPATH[%s]\n",IsNullStr(fullpath)); */
FileBuildPath (fullpath, NULL, pcFile);
/* printf("FULLPATH[%s]\n",IsNullStr(fullpath)); */
if ((f = FileOpen (fullpath, "r")) == NULL)
{
if (FindPath ("NCBI", "NCBI", "DATA", fullpath, sizeof (fullpath) - 1))
{
FileBuildPath (fullpath, NULL, pcFile);
f = FileOpen (fullpath, "r");
if (f == NULL)
{
ErrPost(CTX_NCBIOBJ, 1, "Couldn't open [%s] in LoadCSA", IsNullStr(fullpath));
return (NULL);
}
}
else
{
ErrPost(CTX_NCBIOBJ, 1, "FindPath failed in LoadNeighbors");
return (NULL);
}
}
do /* get each line, tokenize into ppcParse */
{
pcBuf[0] = '\0';
pcTest = fgets(pcBuf, (size_t)250, f);
/* printf("[%s]\n",IsNullStr(pcTest)); */
if (pcTest)
{
iLen = StringLen(pcTest);
/* Break into words delimited by whitespace or "|" */
/* gi|123456| */
/* printf("LineLength %d\n",(int) iLen); */
for (i=0; i < 125; i++) ppcParse[i] = NULL;
pcTemp = pcTest;
ppcParse[0] = pcTest;
iWC = 1;
while ((*pcTemp != '\0') && (iWC < 125))
{
if ((*pcTemp == '|') || (*pcTemp == ' ') || (*pcTemp == '\t') || (*pcTemp == '\n'))
{
*pcTemp = '\0'; /* terminate current word */
do {
pcTemp++; /* skip whitespace to next word */
} while ((*pcTemp == '|') || (*pcTemp == ' ') || (*pcTemp == '\t') || (*pcTemp == '\n'));
ppcParse[iWC] = pcTemp; /* start next word */
iWC++;
}
else
pcTemp++;
}
/* DEBUG TEST */
/* for (i=0; i<125; i++)
if (ppcParse[i] != NULL)
{
printf("%ld/%ld [%s]\n",i,iWC, IsNullStr(ppcParse[i]));
} */
/* If ppcParse[0] is "gi" then this is a VALID sequence line and the last
word parsed is the sequence */
if (ppcParse[0][0] != '\0')
{
iWL = StringLen(ppcParse[0]);
if (iWL == 2)
if (((ppcParse[0][0] == 'g') ||
(ppcParse[0][0] == 'G')) &&
((ppcParse[0][1] == 'i') ||
(ppcParse[0][1] == 'I')))
{
/* next word should be GI */
iGi = 0;
if (StrToInt4 (ppcParse[1], &iGi))
{
/* printf("GI is (%ld)\n",iGi); */
if (iGi == 0) goto parserr;
/* find the 2nd last string = sequence */
/* last string is stripped off line terminator, by the way... */
iString=2; /* start after GI */
while (ppcParse[iString+1] != NULL)
{ /* iString is the LAST sting - line terminator */
iString++;
}
pcsanTemp = pcsanHead;
while (pcsanTemp)
{ /* look for existing pcsan */
if (iGi == pcsanTemp->iGi)
{
break;
}
pcsanTemp = pcsanTemp->next;
}
if (!pcsanTemp) /* otherwise add a new one */
{
pcsanTemp = NewCSAN();
pcsanTemp->next = pcsanHead;
pcsanHead = pcsanTemp; /* put at head of list */
pcsanTemp->iGi = iGi;
}
/* Initialize fields */
pcSeqPart = NULL;
pcSeqPart = StringSave(ppcParse[iString-1]);
/* printf("SEQ [%ld]= [%s]\n",(long) iString-1, IsNullStr(pcSeqPart)); */
ValNodeAddStr(&pcsanTemp->pvnSeqAlnPart, 0, pcSeqPart);
} /* if GI */
} /* if line starts with GI */
} /* if line starts with a word */
} /* if pcTest */
} while (pcTest);
printf("REPORT\n");
pcsanTemp = pcsanHead;
while (pcsanTemp)
{
printf("GI = [%ld]\n", (long) pcsanTemp->iGi);
pvn = pcsanTemp->pvnSeqAlnPart;
while (pvn)
{
printf(">%s<\n",(char *) IsNullStr(pvn->data.ptrvalue));
pvn = pvn->next;
}
pcsanTemp = pcsanTemp->next;
}
FileClose(f);
return pcsanHead;
parserr:
FileClose(f);
ErrPostEx(SEV_FATAL,0,0, "Error in input format \n");
FreeCSAN(pcsanHead);
return NULL;
}
Int2 Main (void)
{
Int2 db = -1;
Int2 i;
Boolean makeCDS;
Char path [PATH_MAX];
CharPtr progname;
FILE *fp;
Int2 rsult;
ErrSetFatalLevel (SEV_MAX);
ErrClearOptFlags (EO_SHOW_USERSTR);
UseLocalAsnloadDataAndErrMsg ();
ErrPathReset ();
if (! AllObjLoad ()) {
Message (MSG_FATAL, "AllObjLoad failed");
return 1;
}
if (! SeqCodeSetLoad ()) {
Message (MSG_FATAL, "SeqCodeSetLoad failed");
return 1;
}
if (! GeneticCodeTableLoad ()) {
Message (MSG_FATAL, "GeneticCodeTableLoad failed");
return 1;
}
ProgramPath (path, sizeof (path));
progname = StringRChr (path, DIRDELIMCHR);
if (progname != NULL) {
progname++;
} else {
progname = "fetchent";
}
/* GetArgs is a portable way of obtaining arguments */
if (! GetArgs (progname, NUMARG, myargs)) {
Message (MSG_FATAL, "GetArgs failed");
return 1;
}
/* Map database argument to TYP_XX value */
for (i = 0; databases [i] != NULL; i++) {
if (StringICmp (myargs [0].strvalue, databases [i]) == 0) {
db = i;
}
}
/* Convert M, P, or N alternative database symbols to proper code */
if (db >= 3 && db <= 5) {
db -= 3;
}
if (db < 0 || db > 2) {
Message (MSG_FATAL, "Database must be ML, AA, or NT");
return 1;
}
if (! EntrezInit (progname, FALSE, NULL)) {
Message (MSG_FATAL, "EntrezInit failed");
return 1;
}
fp = FileOpen (myargs [2].strvalue, "w");
if (fp == NULL) {
Message (MSG_FATAL, "FileOpen failed");
return 1;
}
makeCDS = (Boolean) myargs [3].intvalue;
if (makeCDS && db != TYP_NT) {
Message (MSG_ERROR, "Coding region extraction inappropriate");
makeCDS = FALSE;
}
rsult = ProcessQuery (db, myargs [1].strvalue, makeCDS, fp);
FileClose (fp);
EntrezFini ();
return rsult;
}
/*****************************************************************************
*
* PrintTemplateSetPtr PrintTemplateSetLoad()
* loads PrintTemplates
* If path== NULL, looks for "prt.prt" in the "data" directory
*
*****************************************************************************/
static Boolean PrintTemplateSetLoadInt ( CharPtr path, Boolean verbose )
{
AsnIoPtr aip;
FILE *f;
Boolean retval;
Char filename [80];
Char fullpath [PATH_MAX];
CharPtr ptr;
ErrSev lastLevel;
aip = NULL;
if (path != NULL && *path != '\0' && StringRChr (path, DIRDELIMCHR) != NULL) {
StringNCpy (fullpath, path, sizeof (fullpath) - 1);
if ((aip = AsnIoOpen (fullpath, "r")) == NULL) {
if (verbose) {
ErrPost(CTX_NCBIOBJ, 1, "Couldn't open [%s]", fullpath);
}
return FALSE;
}
} else {
if (path != NULL && *path != '\0') {
StringNCpy (filename, path, sizeof (filename) - 1);
} else {
StringCpy (filename, "prt.prt");
}
ProgramPath (fullpath, sizeof (fullpath) - 1);
ptr = StringRChr (fullpath, DIRDELIMCHR);
if (ptr != NULL) {
*ptr = '\0';
}
FileBuildPath (fullpath, NULL, filename);
/* silence SEV_INFO errors from FileOpen() */
if ((lastLevel = ErrGetMessageLevel()) < SEV_WARNING)
ErrSetMessageLevel (SEV_WARNING);
if ((f = FileOpen (fullpath, "r")) == NULL) {
ErrSetMessageLevel (lastLevel);
if (FindPath ("NCBI", "NCBI", "DATA", fullpath, sizeof (fullpath) - 1)) {
FileBuildPath (fullpath, NULL, filename);
if ((aip = AsnIoOpen (fullpath, "r")) == NULL) {
if (verbose) {
ErrPost(CTX_NCBIOBJ, 1, "Couldn't open [%s]", fullpath);
}
return FALSE;
}
} else {
if (verbose) {
ErrPost(CTX_NCBIOBJ, 1, "FindPath failed in PrintTemplateSetLoad - ncbi configuration file missing or incorrect");
}
return FALSE;
}
} else {
ErrSetMessageLevel (lastLevel);
FileClose (f);
if ((aip = AsnIoOpen(fullpath, "r")) == NULL) {
if (verbose) {
ErrPost(CTX_NCBIOBJ, 1, "Couldn't open [%s]", fullpath);
}
return FALSE;
}
}
}
retval = PrintTemplateSetAsnRead(aip);
AsnIoClose(aip);
return retval;
}
