int main(int argc, char **argv)
{
/* Variable Declarations */
AjPFile inf = NULL;
AjPFile outf = NULL;
AjPStr line = NULL; /* Line from inf */
AjPStr option = NULL;
AjBool doall = AJFALSE;
AjBool doend = AJFALSE;
AjBool doexcess = AJFALSE;
/* ACD File Processing */
embInit("nospace", argc, argv);
inf = ajAcdGetInfile("infile");
outf = ajAcdGetOutfile("outfile");
option = ajAcdGetListSingle("menu");
if(ajStrMatchC(option, "all"))
doall = ajTrue;
else if(ajStrMatchC(option, "end"))
doend = ajTrue;
else if(ajStrMatchC(option, "excess"))
doexcess = ajTrue;
/* Application logic */
line = ajStrNew();
while(ajReadline(inf,&line))
{
if(doall)
ajStrRemoveWhite(&line);
else if(doend)
ajStrTrimWhiteEnd(&line);
else if(doexcess)
ajStrRemoveWhiteExcess(&line);
ajFmtPrintF(outf, "%S\n", line);
}
/* Memory management and exit */
ajFileClose(&inf);
ajFileClose(&outf);
ajStrDel(&line);
ajStrDel(&option);
embExit();
return 0;
}
static AjPTable jaspscan_ReadFamList(const AjPStr jaspdir)
{
AjPTable ret = NULL;
AjPStr lfile = NULL;
AjPStr line = NULL;
AjPStr key = NULL;
AjPStr str = NULL;
PJspmat info = NULL;
AjPFile inf = NULL;
const char *p = NULL;
const char *q = NULL;
lfile = ajStrNew();
line = ajStrNew();
str = ajStrNew();
ajFmtPrintS(&lfile,"%S%s%s",jaspdir,SLASH_STRING,J_LIST);
inf = ajDatafileNewInNameS(lfile);
if(!inf)
ajFatal("Matrix list file %S not found",lfile);
ret = ajTablestrNewLen(JASPTAB_GUESS);
while(ajReadlineTrim(inf,&line))
{
info = jaspscan_infonew();
ajFmtScanS(line,"%S%S",&info->id,&info->num);
p = ajStrGetPtr(line);
while(*p !='\t')
++p;
++p;
while(*p != '\t')
++p;
++p;
q = p;
while(*q != '\t')
++q;
ajStrAssignSubC(&info->name,p,0,q-p-1);
++q;
p = q;
while(*q != ';')
++q;
ajStrAssignSubC(&info->klass,p,0,q-p-1);
ajStrRemoveWhiteExcess(&info->klass);
p = q+1;
while(*p)
{
q = p;
while(* q && *q != ';')
++q;
ajStrAssignSubC(&str,p,0,q-p-1);
ajStrRemoveWhiteExcess(&str);
jaspscan_coretoken(info, str);
if(!*q)
p = q;
else
p = q +1;
}
key = ajStrNew();
ajStrAssignS(&key,info->id);
ajTablePut(ret,(void *)key,(void *) info);
}
ajFileClose(&inf);
ajStrDel(&lfile);
ajStrDel(&line);
ajStrDel(&str);
return ret;
}
/* @funcstatic seqwords_TermsRead *********************************************
**
** Read the next Terms object from a file in embl-like format. The search
** terms are modified with a leading and trailing space.
**
** @param [r] inf [AjPFile] Input file stream
** @param [w] thys [AjPTerms*] Terms object
**
** @return [AjBool] True on succcess
** @@
*****************************************************************************/
static AjBool seqwords_TermsRead(AjPFile inf,
AjPTerms *thys)
{
AjPStr line =NULL; /* Line of text. */
AjPStr temp =NULL;
AjPList list_terms =NULL; /* List of keywords for a scop node*/
AjBool ok =ajFalse;
AjPStr type = NULL;
/* Memory management */
(*thys)=seqwords_TermsNew();
list_terms = ajListstrNew();
line = ajStrNew();
type = ajStrNew();
/* Read first line. */
ok = ajReadlineTrim(inf,&line);
while(ok && !ajStrPrefixC(line,"//"))
{
if(ajStrPrefixC(line,"XX"))
{
ok = ajReadlineTrim(inf,&line);
continue;
}
else if(ajStrPrefixC(line,"TY"))
{
ajFmtScanS(line, "%*s %S", &type);
if(ajStrMatchC(type, "SCOP"))
(*thys)->Type = ajSCOP;
else if(ajStrMatchC(type, "CATH"))
(*thys)->Type = ajCATH;
}
else if(ajStrPrefixC(line,"CL"))
{
ajStrAssignC(&(*thys)->Class,ajStrGetPtr(line)+3);
ajStrRemoveWhiteExcess(&(*thys)->Class);
}
else if(ajStrPrefixC(line,"AR"))
{
ajStrAssignC(&(*thys)->Architecture,ajStrGetPtr(line)+3);
ajStrRemoveWhiteExcess(&(*thys)->Architecture);
}
else if(ajStrPrefixC(line,"TP"))
{
ajStrAssignC(&(*thys)->Topology,ajStrGetPtr(line)+3);
ajStrRemoveWhiteExcess(&(*thys)->Topology);
}
else if(ajStrPrefixC(line,"FO"))
{
ajStrAssignC(&(*thys)->Fold,ajStrGetPtr(line)+3);
while(ajReadlineTrim(inf,&line))
{
if(ajStrPrefixC(line,"XX"))
break;
ajStrAppendC(&(*thys)->Fold,ajStrGetPtr(line)+3);
}
ajStrRemoveWhiteExcess(&(*thys)->Fold);
}
else if(ajStrPrefixC(line,"SF"))
{
ajStrAssignC(&(*thys)->Superfamily,ajStrGetPtr(line)+3);
while(ajReadlineTrim(inf,&line))
{
if(ajStrPrefixC(line,"XX"))
break;
ajStrAppendC(&(*thys)->Superfamily,ajStrGetPtr(line)+3);
}
ajStrRemoveWhiteExcess(&(*thys)->Superfamily);
}
else if(ajStrPrefixC(line,"FA"))
{
ajStrAssignC(&(*thys)->Family,ajStrGetPtr(line)+3);
while(ajReadlineTrim(inf,&line))
{
if(ajStrPrefixC(line,"XX"))
break;
ajStrAppendC(&(*thys)->Family,ajStrGetPtr(line)+3);
}
ajStrRemoveWhiteExcess(&(*thys)->Family);
}
else if(ajStrPrefixC(line,"TE"))
{
/* Copy and clean up term. */
temp = ajStrNew();
ajStrAssignC(&temp,ajStrGetPtr(line)+3);
ajStrRemoveWhiteExcess(&temp);
/* Append a leading and trailing space to search term*/
ajStrAppendK(&temp, ' ');
ajStrInsertC(&temp, 0, " ");
/* Add the current term to the list. */
ajListstrPush(list_terms,temp);
}
ok = ajReadlineTrim(inf,&line);
}
if(!ok)
{
/* Clean up. */
ajListstrFree(&list_terms);
ajStrDel(&line);
/* Return. */
return ajFalse;
}
/* Convert the AjPList of terms to array of AjPSeq's. */
if(!((*thys)->N=ajListstrToarray((AjPList)list_terms,&(*thys)->Keywords)))
ajWarn("Zero sized list of terms passed into seqwords_TermsRead");
/* Clean up. Free the list (not the nodes!). */
ajListstrFree(&list_terms);
ajStrDel(&line);
ajStrDel(&type);
return ajTrue;
}
int main(int argc, char **argv)
{
AjPSeqall nucseq; /* input nucleic sequences */
AjPSeqset protseq; /* input aligned protein sequences */
AjPSeqout seqout;
AjPSeq nseq; /* next nucleic sequence to align */
const AjPSeq pseq; /* next protein sequence use in alignment */
AjPTrn trnTable;
AjPSeq pep; /* translation of nseq */
AjPStr tablelist;
ajint table;
AjPSeqset outseqset; /* set of aligned nucleic sequences */
ajint proteinseqcount = 0;
AjPStr degapstr = NULL;
/* used to check if it matches with START removed */
AjPStr degapstr2 = NULL;
AjPStr codon = NULL; /* holds temporary codon to check if is START */
char aa; /* translated putative START codon */
ajint type; /* returned type of the putative START codon */
/* start position of guide protein in translation */
ajlong pos = 0;
AjPSeq newseq = NULL; /* output aligned nucleic sequence */
ajint frame;
embInit("tranalign", argc, argv);
nucseq = ajAcdGetSeqall("asequence");
protseq = ajAcdGetSeqset("bsequence");
tablelist = ajAcdGetListSingle("table");
seqout = ajAcdGetSeqoutset("outseq");
outseqset = ajSeqsetNew();
degapstr = ajStrNew();
/* initialise the translation table */
ajStrToInt(tablelist, &table);
trnTable = ajTrnNewI(table);
ajSeqsetFill(protseq);
while(ajSeqallNext(nucseq, &nseq))
{
if((pseq = ajSeqsetGetseqSeq(protseq, proteinseqcount++)) == NULL)
ajErr("No guide protein sequence available for "
"nucleic sequence %S",
ajSeqGetNameS(nseq));
ajDebug("Aligning %S and %S\n",
ajSeqGetNameS(nseq), ajSeqGetNameS(pseq));
/* get copy of pseq string with no gaps */
ajStrAssignS(°apstr, ajSeqGetSeqS(pseq));
ajStrRemoveGap(°apstr);
/*
** for each translation frame look for subset of pep that
** matches pseq
*/
for(frame = 1; frame <4; frame++)
{
ajDebug("trying frame %d\n", frame);
pep = ajTrnSeqOrig(trnTable, nseq, frame);
degapstr2 = ajStrNew();
ajStrAssignRef(°apstr2, degapstr);
pos = ajStrFindCaseS(ajSeqGetSeqS(pep), degapstr);
/*
** we might have a START codon that should be translated as 'M'
** we need to check if there is a match after a possible START
** codon
*/
if(pos == -1 && ajStrGetLen(degapstr) > 1 &&
(ajStrGetPtr(degapstr)[0] == 'M' ||
ajStrGetPtr(degapstr)[0] == 'm'))
{
/* see if pep minus the first character is a match */
ajStrCutStart(°apstr2, 1);
pos = ajStrFindCaseS(ajSeqGetSeqS(pep), degapstr2);
/*
** pos is >= 1 if we have a match that is after the first
** residue
*/
if(pos >= 1)
{
/* point back at the putative START Methionine */
pos--;
/* test if first codon is a START */
codon = ajStrNew();
ajStrAssignSubS(&codon, ajSeqGetSeqS(nseq),
(pos*3)+frame-1, (pos*3)+frame+2);
type = ajTrnCodonstrTypeS(trnTable, codon, &aa);
if(type != 1)
{
/* first codon is not a valid START, force a mismatch */
pos = -1;
}
ajStrDel(&codon);
}
else
{
/* force 'pos == 0' to be treated as a mismatch */
pos = -1;
}
}
ajStrDel(°apstr2);
ajSeqDel(&pep);
if(pos != -1)
break;
}
if(pos == -1)
ajErr("Guide protein sequence %S not found in nucleic sequence %S",
ajSeqGetNameS(pseq), ajSeqGetNameS(nseq));
else
{
ajDebug("got a match with frame=%d\n", frame);
/* extract the coding region of nseq with gaps */
newseq = ajSeqNew();
ajSeqSetNuc(newseq);
ajSeqAssignNameS(newseq, ajSeqGetNameS(nseq));
ajSeqAssignDescS(newseq, ajSeqGetDescS(nseq));
tranalign_AddGaps(newseq, nseq, pseq, (pos*3)+frame-1);
/* output the gapped nucleic sequence */
ajSeqsetApp(outseqset, newseq);
ajSeqDel(&newseq);
}
ajStrRemoveWhiteExcess(°apstr);
}
ajSeqoutWriteSet(seqout, outseqset);
ajSeqoutClose(seqout);
ajTrnDel(&trnTable);
ajSeqsetDel(&outseqset);
ajStrDel(°apstr);
ajStrDel(°apstr2);
ajSeqallDel(&nucseq);
ajSeqDel(&nseq);
ajSeqoutDel(&seqout);
ajSeqsetDel(&protseq);
ajStrDel(&tablelist);
embExit();
return 0;
}
AjPMatrixf ajMatrixfNewFile(const AjPStr filename)
{
AjPMatrixf ret = NULL;
AjPStr *orderstring = NULL;
AjPStr buffer = NULL;
AjPStr firststring = NULL;
AjPStr reststring = NULL;
const AjPStr tok = NULL;
ajint len = 0;
ajint i = 0;
ajint l = 0;
ajint k = 0;
ajint cols = 0;
ajint rows = 0;
const char *ptr = NULL;
AjPFile file = NULL;
AjBool first = ajTrue;
float **matrix = NULL;
float *templine = NULL;
float minval = -1.0;
AjPList rlabel_list = NULL;
AjPStr *rlabel_arr = NULL;
#ifndef WIN32
static const char *delimstr = " :\t\n";
#else
static const char *delimstr = " :\t\n\r";
#endif
rlabel_list = ajListNew();
firststring = ajStrNew();
reststring = ajStrNew();
file = ajDatafileNewInNameS(filename);
if(!file)
{
ajStrDel(&firststring);
ajStrDel(&reststring);
return NULL;
}
/* Read row labels */
while(ajReadline(file,&buffer))
{
ptr = ajStrGetPtr(buffer);
#ifndef WIN32
if(*ptr != '#' && *ptr != '\n')
#else
if(*ptr != '#' && *ptr != '\n' && *ptr != '\r')
#endif
{
if(first)
first = ajFalse;
else
{
ajFmtScanC(ptr, "%S", &firststring);
ajListPushAppend(rlabel_list, firststring);
firststring = ajStrNew();
}
}
}
first = ajTrue;
ajStrDel(&firststring);
rows = ajListToarray(rlabel_list, (void ***) &rlabel_arr);
ajFileSeek(file, 0, 0);
while(ajReadline(file,&buffer))
{
ajStrRemoveWhiteExcess(&buffer);
ptr = ajStrGetPtr(buffer);
if(*ptr && *ptr != '#')
{
if(first)
{
cols = ajStrParseCountC(buffer,delimstr);
AJCNEW0(orderstring, cols);
for(i=0; i<cols; i++)
orderstring[i] = ajStrNew();
tok = ajStrParseC(buffer, " :\t\n");
ajStrAssignS(&orderstring[l++], tok);
while((tok = ajStrParseC(NULL, " :\t\n")))
ajStrAssignS(&orderstring[l++], tok);
first = ajFalse;
ret = ajMatrixfNewAsym(orderstring, cols,
rlabel_arr, rows,
filename);
matrix = ret->Matrixf;
}
else
{
ajFmtScanC(ptr, "%S", &firststring);
/* JISON 19/7/4
k = ajSeqcvtGetCodeK(ret->Cvt,
ajStrGetCharFirst(firststring)); */
k = ajSeqcvtGetCodeS(ret->Cvt, firststring);
len = MAJSTRGETLEN(firststring);
ajStrAssignSubC(&reststring, ptr, len, -1);
/*
** Must discard the first string (label) and use
** reststring otherwise ajArrFloatLine would fail (it
** cannot convert a string to a float)
**
** Use cols,1,cols in below because although 2nd and
** subsequent lines have one more string in them (the
** residue label in the 1st column) we've discarded that
** from the string that's passed
*/
templine = ajArrFloatLine(reststring,delimstr,1,cols);
for(i=0; i<cols; i++)
{
if(templine[i] < minval)
minval = templine[i];
/* JISON 19/7/4
matrix[k][ajSeqcvtGetCodeK(ret->Cvt,
ajStrGetCharFirst(orderstring[i]))]
= templine[i]; */
matrix[k][ajSeqcvtGetCodeAsymS(ret->Cvt,
orderstring[i])]
= templine[i];
}
AJFREE(templine);
}
}
}
ajDebug("fill rest with minimum value %d\n", minval);
ajFileClose(&file);
ajStrDel(&buffer);
for(i=0; i<cols; i++)
ajStrDel(&orderstring[i]);
AJFREE(orderstring);
ajDebug("read matrix file %S\n", filename);
ajStrDel(&firststring);
ajStrDel(&reststring);
for(i=0; i<rows; i++)
ajStrDel(&rlabel_arr[i]);
AJFREE(rlabel_arr);
ajListFree(&rlabel_list);
return ret;
}
AjPMatrix ajMatrixNewFile(const AjPStr filename)
{
AjPMatrix ret = NULL;
AjPStr buffer = NULL;
const AjPStr tok = NULL;
AjPStr firststring = NULL;
AjPStr *orderstring = NULL;
AjPFile file = NULL;
AjBool first = ajTrue;
const char *ptr = NULL;
ajint **matrix = NULL;
ajint minval = -1;
ajint i = 0;
ajint l = 0;
ajint k = 0;
ajint cols = 0;
ajint rows = 0;
ajint *templine = NULL;
AjPList rlabel_list = NULL;
AjPStr *rlabel_arr = NULL;
#ifndef WIN32
static const char *delimstr = " :\t\n";
#else
static const char *delimstr = " :\t\n\r";
#endif
rlabel_list = ajListNew();
firststring = ajStrNew();
file = ajDatafileNewInNameS(filename);
if(!file)
{
ajStrDel(&firststring);
ajListFree(&rlabel_list);
return NULL;
}
/* Read row labels */
while(ajReadline(file,&buffer))
{
ptr = ajStrGetPtr(buffer);
#ifndef WIN32
if(*ptr != '#' && *ptr != '\n')
#else
if(*ptr != '#' && *ptr != '\n' && *ptr != '\r')
#endif
{
if(first)
first = ajFalse;
else
{
ajFmtScanC(ptr, "%S", &firststring);
ajListPushAppend(rlabel_list, firststring);
firststring = ajStrNew();
}
}
}
first = ajTrue;
ajStrDel(&firststring);
rows = ajListToarray(rlabel_list, (void ***) &rlabel_arr);
ajFileSeek(file, 0, 0);
while(ajReadline(file,&buffer))
{
ajStrRemoveWhiteExcess(&buffer);
ptr = ajStrGetPtr(buffer);
if(*ptr && *ptr != '#')
{
if(first)
{
cols = ajStrParseCountC(buffer,delimstr);
AJCNEW0(orderstring, cols);
for(i=0; i<cols; i++)
orderstring[i] = ajStrNew();
tok = ajStrParseC(buffer, " :\t\n");
ajStrAssignS(&orderstring[l++], tok);
while((tok = ajStrParseC(NULL, " :\t\n")))
ajStrAssignS(&orderstring[l++], tok);
first = ajFalse;
ret = ajMatrixNewAsym(orderstring, cols,
rlabel_arr, rows,
filename);
matrix = ret->Matrix;
}
else
{
ajFmtScanC(ptr, "%S", &firststring);
/* JISON 19/7/4
k = ajSeqcvtGetCodeK(ret->Cvt, ajStrGetCharFirst(firststring)); */
k = ajSeqcvtGetCodeS(ret->Cvt, firststring);
/*
** cols+1 is used below because 2nd and subsequent lines have
** one more string in them (the residue label)
*/
templine = ajArrIntLine(buffer,delimstr,2,cols+1);
for(i=0; i<cols; i++)
{
if(templine[i] < minval)
minval = templine[i];
/* JISON 19/7/4
matrix[k][ajSeqcvtGetCodeK(ret->Cvt,
ajStrGetCharFirst(orderstring[i]))]
= templine[i]; */
matrix[k][ajSeqcvtGetCodeAsymS(ret->Cvt,
orderstring[i])]
= templine[i];
}
AJFREE(templine);
}
}
}
ajDebug("fill rest with minimum value %d\n", minval);
ajFileClose(&file);
ajStrDel(&buffer);
for(i=0; i<cols; i++)
ajStrDel(&orderstring[i]);
AJFREE(orderstring);
ajDebug("read matrix file %S\n", filename);
ajStrDel(&firststring);
for(i=0; i<rows; i++)
ajStrDel(&rlabel_arr[i]);
AJFREE(rlabel_arr);
ajListFree(&rlabel_list);
return ret;
}
static AjBool resourceoutWriteWebpage(AjPFile outf, const AjPResource resource)
{
AjPResquery tmpqry = NULL;
AjPResterm resterm = NULL;
AjPStr snstr = NULL;
AjPStr tmpstr = NULL;
AjPStr tmpurl = NULL;
AjPStr tmpid = NULL;
AjPStr tmpname = NULL;
AjPStr tmpqid = NULL;
AjPStr tmpqname = NULL;
AjPStr tmpqterm = NULL;
AjIList iter = NULL;
AjIList iterq = NULL;
ajuint i = 0;
AjPStrTok handle = NULL;
AjPStrTok namehandle = NULL;
AjPStrTok termhandle = NULL;
const char* biourl = "http://bioportal.bioontology.org/ontologies/45846";
if(!outf)
return ajFalse;
ajFmtPrintF(outf,
"<!DOCTYPE HTML PUBLIC "
"\"-//W3C//DTD HTML 4.01 Transitional//EN\">\n");
ajFmtPrintF(outf,
"<html>\n");
ajFmtPrintF(outf,
"<head>\n");
ajFmtPrintF(outf,
"<meta http-equiv=\"Content-Type\" "
"content=\"text/html;charset=UTF-8\" />\n");
ajFmtPrintF(outf,
"<title>Bioinformatics Data Resource Catalogue</title>\n");
ajFmtPrintF(outf,
"</head>\n\n\n");
ajFmtPrintF(outf,
"<body bgcolor=\"#ffffff\">\n");
ajFmtPrintF(outf,
"<!-- ID -->\n");
if(ajStrGetLen(resource->Url))
ajFmtPrintF(outf,
"<center><h1><a href=\"%S\">%S</a></h1></center>\n",
resource->Url, resource->Id);
else
ajFmtPrintF(outf,
"<center><h1>%S</h1></center>\n",
resource->Id);
ajFmtPrintF(outf,
"<!-- Name -->\n");
ajFmtPrintF(outf,
"<center><h2>%S</h2> </center>\n",
resource->Name);
ajFmtPrintF(outf,
"<!-- Desc -->\n");
ajFmtPrintF(outf,
"<p><i>%S</i></p>\n",
resource->Desc);
ajFmtPrintF(outf,
"<table>\n");
ajFmtPrintF(outf,
"<!-- ID -->\n");
ajFmtPrintF(outf,
" <tr align=\"left\"><th>ID</th><td>%S</td></tr>\n",
resource->Id);
ajFmtPrintF(outf,
"<!-- IDalt or omit -->\n");
if(ajListGetLength(resource->Idalt))
{
ajFmtPrintF(outf,
" <tr align=\"left\"><th>IDalt</th><td>");
i = 0;
iter = ajListIterNew(resource->Idalt);
while((tmpstr = ajListstrIterGet(iter)))
{
if(i++)
ajFmtPrintF(outf, ", ");
ajFmtPrintF(outf, "%S", tmpstr);
}
ajListIterDel(&iter);
ajFmtPrintF(outf,
"</td></tr>\n");
}
if(ajStrGetLen(resource->Acc))
{
ajFmtPrintF(outf,
"<!-- ACC or omit -->\n");
ajFmtPrintF(outf,
" <tr align=\"left\"><th>Acc</th><td>%S</td></tr>\n",
resource->Acc);
}
if(ajStrGetLen(resource->Url))
ajFmtPrintF(outf,
" <tr align=\"left\"><th>Home</th><td>"
"<a href=\"%S\">%S</a></td></tr>\n",
resource->Url, resource->Url);
if(ajListGetLength(resource->Edamtpc))
{
ajFmtPrintF(outf,
"<!-- EDAMtpc -->\n");
iter = ajListIterNew(resource->Edamtpc);
while((resterm = ajListIterGet(iter)))
{
ajStrAssignS(&tmpid, resterm->Id);
ajStrCutBraces(&tmpid);
ajStrFmtPercentEncodeC(&tmpid, " /()");
ajFmtPrintF(outf,
" <tr align=\"left\"><th>EDAM topic</th><td>"
"<a href=\"%s?p=terms&conceptid=EDAM%%3A%S\">%S</a>"
"</td></tr>\n",
biourl, tmpid, resterm->Name);
}
ajListIterDel(&iter);
}
ajFmtPrintF(outf,
"<!-- Cat or omit -->\n");
if(ajListGetLength(resource->Cat))
{
iter = ajListIterNew(resource->Cat);
while((tmpstr = ajListstrIterGet(iter)))
ajFmtPrintF(outf,
" <tr align=\"left\"><th>Category</th>"
"<td>%S</td></tr>\n",
tmpstr);
ajListIterDel(&iter);
}
ajFmtPrintF(outf,
"<!-- Taxon (comma-separated list) -->\n");
ajFmtPrintF(outf,
" <tr align=\"left\"><th>Taxon</th><td>");
i = 0;
iter = ajListIterNew(resource->Taxon);
while((resterm = ajListIterGet(iter)))
{
if(i++)
ajFmtPrintF(outf, ", ");
ajFmtPrintF(outf,
"<a href=\"http://www.ncbi.nlm.nih.gov/Taxonomy/Browser/"
"wwwtax.cgi?id=%S\">%S</a>",
resterm->Id, resterm->Name);
}
ajListIterDel(&iter);
ajFmtPrintF(outf,
"</td></tr>\n");
ajFmtPrintF(outf,
"<!-- URLlink or omit -->\n");
if(ajStrGetLen(resource->Urllink))
ajFmtPrintF(outf,
"<tr align=\"left\"><th>Linking</th><td>"
"<a href=\"%S\">%S</a></td></tr>\n",
resource->Urllink, resource->Urllink);
ajFmtPrintF(outf,
"<!-- URLrest or omit -->\n");
if(ajStrGetLen(resource->Urlrest))
ajFmtPrintF(outf,
"<tr align=\"left\"><th>REST</th><td>"
"<a href=\"%S\">%S</a></td></tr>\n",
resource->Urlrest, resource->Urlrest);
ajFmtPrintF(outf,
"<!-- URLsoap or omit -->\n");
if(ajStrGetLen(resource->Urlsoap))
ajFmtPrintF(outf,
"<tr align=\"left\"><th>SOAP</th><td>"
"<a href=\"%S\">%S</a></td></tr>\n",
resource->Urlsoap, resource->Urlsoap);
ajFmtPrintF(outf,
"<!-- Xref - omit ! -->\n");
ajFmtPrintF(outf,
"</table>\n");
ajFmtPrintF(outf,
"<!-- Query or omit, free-text comments given in {} --> \n");
if(ajListGetLength(resource->Query))
{
ajFmtPrintF(outf,
"<h3>Available data</h3>\n");
ajFmtPrintF(outf,
"<table>\n");
ajFmtPrintF(outf,
" <thead>\n");
ajFmtPrintF(outf,
" <tr align=\"left\">\n");
ajFmtPrintF(outf,
" <th>Data</th>\n");
ajFmtPrintF(outf,
" <th>Format</th>\n");
ajFmtPrintF(outf,
" <th>Query</th>\n");
ajFmtPrintF(outf,
" <th>Link</th>\n");
ajFmtPrintF(outf,
" </tr>\n");
ajFmtPrintF(outf,
" </thead>\n");
ajFmtPrintF(outf,
" <tbody>\n");
iter = ajListIterNew(resource->Query);
while((tmpqry = ajListIterGet(iter)))
{
ajStrAssignS(&tmpname, tmpqry->Datatype);
ajStrCutBraces(&tmpname);
ajStrFmtPercentEncodeC(&tmpname, " /()");
ajFmtPrintF(outf,
" <tr>\n");
ajFmtPrintF(outf,
" <td>"
"<a href=\"%s?"
"p=terms&conceptid=EDAM%%3A%S\">%S</a></td>\n",
biourl, tmpname, tmpqry->Datatype);
ajStrAssignS(&tmpname, tmpqry->Format);
ajStrCutBraces(&tmpname);
ajStrFmtPercentEncodeC(&tmpname, " /()");
ajFmtPrintF(outf,
" <td>"
"<a href=\"%s?"
"p=terms&conceptid=EDAM%%3A%S\">%S</a></td>\n",
biourl, tmpname, tmpqry->Format);
ajStrAssignS(&tmpname, tmpqry->Term);
ajStrCutBraces(&tmpname);
ajStrFmtPercentEncodeC(&tmpname, " /()");
ajFmtPrintF(outf,
" <td>"
"<a href=\"%s?"
"p=terms&conceptid=EDAM%%3A%S\">%S</a></td>\n",
biourl, tmpname, tmpqry->Term);
ajFmtPrintF(outf,
" <td>%S</td>\n",
tmpqry->Url);
ajFmtPrintF(outf,
" </tr>\n\n");
}
ajListIterDel(&iter);
ajFmtPrintF(outf,
" </tbody>\n");
ajFmtPrintF(outf,
"</table>\n");
}
ajFmtPrintF(outf,
"<!-- Example or omit -->\n");
if(ajListGetLength(resource->Example))
{
ajFmtPrintF(outf,
"<h3>Example queries</h3>\n");
ajFmtPrintF(outf,
"<table>\n");
ajFmtPrintF(outf,
" <thead>\n");
ajFmtPrintF(outf,
" <tr align=\"left\">\n");
ajFmtPrintF(outf,
" <th>Data</th>\n");
ajFmtPrintF(outf,
" <th>Format</th>\n");
ajFmtPrintF(outf,
" <th>Query</th>\n");
ajFmtPrintF(outf,
" <th>Example</th>\n");
ajFmtPrintF(outf,
" </tr>\n");
ajFmtPrintF(outf,
" </thead>\n");
ajFmtPrintF(outf,
" <tbody>\n");
iter = ajListIterNew(resource->Example);
while((tmpstr = ajListstrIterGet(iter)))
{
ajStrTokenAssignC(&handle, tmpstr, "|");
ajStrTokenNextParse(handle, &tmpid);
ajStrRemoveWhiteExcess(&tmpid);
ajStrTokenNextParse(handle, &tmpname);
ajStrRemoveWhiteExcess(&tmpname);
iterq = ajListIterNew(resource->Query);
while((tmpqry = ajListIterGet(iterq)))
{
if(!ajStrMatchS(tmpid, tmpqry->Term))
continue;
ajStrAssignS(&tmpqid, tmpqry->Datatype);
ajStrCutBraces(&tmpqid);
ajStrFmtPercentEncodeC(&tmpqid, " /()");
ajFmtPrintF(outf,
" <tr>\n");
ajFmtPrintF(outf,
" <td>"
"<a href=\"%s?"
"p=terms&conceptid=EDAM%%3A%S\">%S</a></td>\n",
biourl, tmpqid, tmpqry->Datatype); /* datatype */
ajStrAssignS(&tmpqid, tmpqry->Format);
ajStrCutBraces(&tmpqid);
ajStrFmtPercentEncodeC(&tmpqid, " /()");
ajFmtPrintF(outf,
" <td>"
"<a href=\"%s?"
"p=terms&conceptid=EDAM%%3A%S\">%S</a></td>\n",
biourl, tmpqid, tmpqry->Format); /* format */
ajStrAssignS(&tmpurl, tmpqry->Url);
ajStrAssignS(&tmpqid, tmpqry->Term);
ajStrCutBraces(&tmpqid);
ajStrFmtPercentEncodeC(&tmpqid, " /()");
i = 0;
ajStrTokenAssignC(&handle, tmpid, ";");
ajStrTokenAssignC(&namehandle, tmpname, ";");
ajStrTokenAssignC(&termhandle, tmpqry->Term, ";");
ajFmtPrintF(outf,
" <td>");
while(ajStrTokenNextParse(handle, &tmpqid))
{
ajStrTokenNextParse(namehandle, &tmpqname);
ajStrTokenNextParse(termhandle, &tmpqterm);
if(i)
ajFmtPrintF(outf,
"; ");
ajStrRemoveWhiteExcess(&tmpqid);
ajStrCutBraces(&tmpqid);
ajFmtPrintF(outf,
"<a href=\"%s?"
"p=terms&conceptid=EDAM%%3A%S\">%S</a>",
biourl, tmpqid, tmpqterm); /* id term */
ajFmtPrintS(&snstr, "%%s%u", (i+1));
ajStrExchangeSS(&tmpurl, snstr, tmpqname);
i++;
}
ajFmtPrintF(outf,
"</td>\n");
ajFmtPrintS(&snstr, "%%s");
ajStrExchangeSS(&tmpurl, snstr, tmpname);
ajFmtPrintF(outf,
" <td><a href=\"%S\">%S</a></td>\n",
tmpurl, tmpname); /* url, exampleid */
ajFmtPrintF(outf,
" </tr>\n");
}
ajListIterDel(&iterq);
}
ajListIterDel(&iter);
ajFmtPrintF(outf,
" </tbody>\n");
ajFmtPrintF(outf,
"</table>\n");
}
ajFmtPrintF(outf, "\n\n</body></html>\n");
ajStrDel(&tmpid);
ajStrDel(&tmpname);
ajStrDel(&tmpurl);
ajStrDel(&tmpqid);
ajStrDel(&tmpqname);
ajStrDel(&tmpqterm);
ajStrDel(&snstr);
ajStrTokenDel(&handle);
ajStrTokenDel(&namehandle);
ajStrTokenDel(&termhandle);
return ajTrue;
}
static AjBool dbxflat_ParseGenbank(EmbPBtreeEntry entry, AjPFile inf)
{
AjPStr line = NULL;
ajlong pos = 0L;
AjBool ret = ajTrue;
AjPStr sumline = NULL;
line = ajStrNewC("");
sumline = ajStrNew();
while(!ajStrPrefixC(line,"//") && ret)
{
if(ajStrPrefixC(line,"LOCUS"))
{
entry->fpos = pos;
ajFmtScanS(line,"%*S%S",&entry->id);
}
if(svfield)
if(ajStrPrefixC(line,"VERSION"))
embBtreeGenBankAC(line,svfield->data);
if(accfield)
if(ajStrPrefixC(line,"ACCESSION"))
embBtreeGenBankAC(line,accfield->data);
if(keyfield)
if(ajStrPrefixC(line,"KEYWORDS"))
{
ajStrAssignS(&sumline,line);
ret = ajReadlineTrim(inf,&line);
while(ret && *MAJSTRGETPTR(line)==' ')
{
ajStrAppendS(&sumline,line);
ret = ajReadlineTrim(inf,&line);
}
ajStrRemoveWhiteExcess(&sumline);
embBtreeGenBankKW(sumline,keyfield->data,keyfield->len);
continue;
}
if(desfield)
if(ajStrPrefixC(line,"DEFINITION"))
{
ajStrAssignS(&sumline,line);
ret = ajReadlineTrim(inf,&line);
while(ret && *MAJSTRGETPTR(line)==' ')
{
ajStrAppendS(&sumline,line);
ret = ajReadlineTrim(inf,&line);
}
ajStrRemoveWhiteExcess(&sumline);
embBtreeGenBankDE(sumline,desfield->data,desfield->len);
continue;
}
if(orgfield)
if(ajStrPrefixC(line,"SOURCE"))
{
ret = ajReadlineTrim(inf,&line);
ajStrAppendC(&line,";");
while(ret && *MAJSTRGETPTR(line)==' ')
{
ajStrAppendS(&sumline,line);
ret = ajReadlineTrim(inf,&line);
}
ajStrRemoveWhiteExcess(&sumline);
embBtreeGenBankTX(sumline,orgfield->data,orgfield->len);
continue;
}
pos = ajFileResetPos(inf);
if(!ajReadlineTrim(inf,&line))
ret = ajFalse;
}
ajStrDel(&line);
ajStrDel(&sumline);
return ret;
}
static AjBool dbxflat_ParseGenbank(EmbPBtreeEntry entry, AjPFile inf)
{
AjPStr line = NULL;
ajlong pos = 0L;
AjBool ret = ajTrue;
AjPStr sumline = NULL;
line = ajStrNewC("");
sumline = ajStrNew();
while(!ajStrPrefixC(line,"//") && ret)
{
if(ajStrPrefixC(line,"LOCUS"))
{
entry->fpos = pos;
ajFmtScanS(line,"%*S%S",&entry->id);
}
if(entry->do_sv)
if(ajStrPrefixC(line,"VERSION"))
embBtreeGenBankAC(line,entry->sv);
if(entry->do_accession)
if(ajStrPrefixC(line,"ACCESSION"))
embBtreeGenBankAC(line,entry->ac);
if(entry->do_keyword)
if(ajStrPrefixC(line,"KEYWORDS"))
{
ajStrAssignS(&sumline,line);
ret = ajReadlineTrim(inf,&line);
while(ret && *MAJSTRGETPTR(line)==' ')
{
ajStrAppendS(&sumline,line);
ret = ajReadlineTrim(inf,&line);
}
ajStrRemoveWhiteExcess(&sumline);
embBtreeGenBankKW(sumline,entry->kw,entry->kwlen);
continue;
}
if(entry->do_description)
if(ajStrPrefixC(line,"DEFINITION"))
{
ajStrAssignS(&sumline,line);
ret = ajReadlineTrim(inf,&line);
while(ret && *MAJSTRGETPTR(line)==' ')
{
ajStrAppendS(&sumline,line);
ret = ajReadlineTrim(inf,&line);
}
ajStrRemoveWhiteExcess(&sumline);
embBtreeGenBankDE(sumline,entry->de,entry->delen);
continue;
}
if(entry->do_taxonomy)
if(ajStrPrefixC(line,"SOURCE"))
{
ret = ajReadlineTrim(inf,&line);
ajStrAppendC(&line,";");
while(ret && *MAJSTRGETPTR(line)==' ')
{
ajStrAppendS(&sumline,line);
ret = ajReadlineTrim(inf,&line);
}
ajStrRemoveWhiteExcess(&sumline);
embBtreeGenBankTX(sumline,entry->tx,entry->txlen);
continue;
}
pos = ajFileResetPos(inf);
if(!ajReadlineTrim(inf,&line))
ret = ajFalse;
}
ajStrDel(&line);
ajStrDel(&sumline);
return ret;
}
EmbPPropAmino* embPropEaminoRead(AjPFile mfptr)
{
AjPStr line = NULL;
AjPStr token = NULL;
AjBool firstline;
const char *p;
ajuint i;
ajint n;
EmbPPropAmino *ret;
line = ajStrNew();
token = ajStrNew();
firstline = ajTrue;
AJCNEW0(ret,EMBPROPSIZE);
for(i=0; i < EMBPROPSIZE; ++i)
AJNEW0(ret[i]);
while(ajReadline(mfptr, &line))
{
ajStrRemoveWhiteExcess(&line);
p = ajStrGetPtr(line);
if(*p=='#' || *p=='!' || !*p)
continue;
if(firstline)
{
if(!ajStrPrefixC(line,"aa"))
ajFatal("Incorrect (old?) format amino data file");
firstline = ajFalse;
continue;
}
ajFmtScanS(line,"%S",&token);
ajStrFmtUpper(&token);
if(ajStrGetLen(token) != 1)
ajFatal("Amino file line doesn't begin with a single character");
i = ajBasecodeToInt((ajint) *ajStrGetPtr(token));
if(i == 27)
ajFatal("Amino file line doesn't begin with a single A->Z (%S)",
line);
n = ajFmtScanS(line,"%*s%d%d%d%d%d%d%f%d%d%d",
&ret[i]->tiny,
&ret[i]->sm_all,
&ret[i]->aliphatic,
&ret[i]->aromatic,
&ret[i]->nonpolar,
&ret[i]->polar,
&ret[i]->charge,
&ret[i]->pve,
&ret[i]->nve,
&ret[i]->extcoeff);
if(n!= 10)
ajFatal("Only %d columns in amino file - expected %d",n+1,11);
}
ajStrDel(&line);
ajStrDel(&token);
return ret;
}
EmbPPropMolwt* embPropEmolwtRead(AjPFile mfptr)
{
AjPStr line = NULL;
AjPStr token = NULL;
AjBool firstline;
const char *p;
ajuint i;
ajint n;
EmbPPropMolwt *ret;
line = ajStrNew();
token = ajStrNew();
firstline = ajTrue;
AJCNEW0(ret,EMBPROPSIZE+2);
for(i=0; i < EMBPROPSIZE+2; ++i)
AJNEW0(ret[i]);
while(ajReadline(mfptr, &line))
{
ajStrRemoveWhiteExcess(&line);
p = ajStrGetPtr(line);
if(*p=='#' || *p=='!' || !*p)
continue;
if(firstline)
{
if(!ajStrPrefixC(line,"Mol"))
ajFatal("Incorrect format molwt file: '%S'", line);
firstline = ajFalse;
continue;
}
ajFmtScanS(line,"%S",&token);
ajStrFmtUpper(&token);
if(ajStrGetLen(token) != 1)
{
if(ajStrPrefixC(token,"HYDROGEN"))
{
if(ajFmtScanS(line,"%*s%lf%lf",
&ret[EMBPROPHINDEX]->average,
&ret[EMBPROPHINDEX]->mono) != 2)
ajFatal("Bad format hydrogen data line");
}
else if(ajStrPrefixC(token,"OXYGEN"))
{
if(ajFmtScanS(line,"%*s%lf%lf",
&ret[EMBPROPOINDEX]->average,
&ret[EMBPROPOINDEX]->mono) != 2)
ajFatal("Bad format oxygen data line");
}
else if(ajStrPrefixC(token,"WATER"))
{
if(ajFmtScanS(line,"%*s%lf%lf",
&ret[EMBPROPWINDEX]->average,
&ret[EMBPROPWINDEX]->mono) != 2)
ajFatal("Bad format water data line");
}
else
ajFatal("Unknown molwt token %S",token);
continue;
}
i = ajBasecodeToInt((ajint) *ajStrGetPtr(token));
if(i == 27)
ajFatal("Molwt file line doesn't begin with a single A->Z (%S)",
line);
n = ajFmtScanS(line,"%*s%lf%lf",
&ret[i]->average,
&ret[i]->mono);
if(n != 2)
ajFatal("Only %d columns in amino file - expected %d",n,3);
}
ajStrDel(&line);
ajStrDel(&token);
return ret;
}
