int main (int argc, char *argv[])
{
Array intervals;
Interval *currInterval;
SubInterval *currSubInterval;
int h,i,j;
Array seqs;
Seq *currSeq,testSeq;
int index;
Stringa buffer;
Array geneTranscriptEntries;
Texta geneTranscriptIds;
Array alterations;
Alteration *currAlteration,*nextAlteration;
char *proteinSequenceBeforeIndel;
char *proteinSequenceAfterIndel;
int numDisabledTranscripts;
Stringa disabledTranscripts;
int seqLength,refLength,altLength;
char *sequenceBeforeIndel = NULL;
int overlapMode;
int numOverlaps;
int sizeIndel,indelOffset;
int overlap;
Array coordinates;
VcfEntry *currVcfEntry;
VcfGenotype *currVcfGenotype;
int position;
Texta alternateAlleles;
int flag1,flag2;
if (argc != 3) {
usage ("%s <annotation.interval> <annotation.fa>",argv[0]);
}
intervalFind_addIntervalsToSearchSpace (argv[1],0);
geneTranscriptEntries = util_getGeneTranscriptEntries (intervalFind_getAllIntervals ());
seq_init ();
fasta_initFromFile (argv[2]);
seqs = fasta_readAllSequences (0);
fasta_deInit ();
arraySort (seqs,(ARRAYORDERF)util_sortSequencesByName);
buffer = stringCreate (100);
disabledTranscripts = stringCreate (100);
alterations = arrayCreate (100,Alteration);
vcf_init ("-");
stringPrintf (buffer,"##INFO=<ID=VA,Number=.,Type=String,Description=\"Variant Annotation, %s\">",argv[1]);
vcf_addComment (string (buffer));
puts (vcf_writeMetaData ());
puts (vcf_writeColumnHeaders ());
while (currVcfEntry = vcf_nextEntry ()) {
if (vcf_isInvalidEntry (currVcfEntry)) {
continue;
}
flag1 = 0;
flag2 = 0;
position = currVcfEntry->position - 1; // make zero-based
alternateAlleles = vcf_getAlternateAlleles (currVcfEntry);
for (h = 0; h < arrayMax (alternateAlleles); h++) {
refLength = strlen (currVcfEntry->referenceAllele);
altLength = strlen (textItem (alternateAlleles,h));
sizeIndel = abs (refLength - altLength);
indelOffset = MAX (refLength,altLength) - 1;
util_clearAlterations (alterations);
intervals = intervalFind_getOverlappingIntervals (currVcfEntry->chromosome,position,position + indelOffset);
for (i = 0; i < arrayMax (intervals); i++) {
currInterval = arru (intervals,i,Interval*);
overlapMode = OVERLAP_NONE;
numOverlaps = 0;
for (j = 0; j < arrayMax (currInterval->subIntervals); j++) {
currSubInterval = arrp (currInterval->subIntervals,j,SubInterval);
overlap = rangeIntersection (position,position + indelOffset,currSubInterval->start,currSubInterval->end);
if (currSubInterval->start <= position && (position + indelOffset) < currSubInterval->end) {
overlapMode = OVERLAP_FULLY_CONTAINED;
numOverlaps++;
}
else if (j == 0 && overlap > 0 && position < currSubInterval->start) {
overlapMode = OVERLAP_START;
numOverlaps++;
}
else if (j == (arrayMax (currInterval->subIntervals) - 1) && overlap > 0 && (position + indelOffset) >= currSubInterval->end) {
overlapMode = OVERLAP_END;
numOverlaps++;
}
else if (overlap > 0 && overlap <= indelOffset) {
overlapMode = OVERLAP_SPLICE;
numOverlaps++;
}
}
if (overlapMode == OVERLAP_NONE) {
continue;
}
currAlteration = arrayp (alterations,arrayMax (alterations),Alteration);
if (numOverlaps > 1) {
util_addAlteration (currAlteration,currInterval->name,"multiExonHit",currInterval,position,0);
continue;
}
else if (numOverlaps == 1 && overlapMode == OVERLAP_SPLICE) {
util_addAlteration (currAlteration,currInterval->name,"spliceOverlap",currInterval,position,0);
continue;
}
else if (numOverlaps == 1 && overlapMode == OVERLAP_START) {
util_addAlteration (currAlteration,currInterval->name,"startOverlap",currInterval,position,0);
continue;
}
else if (numOverlaps == 1 && overlapMode == OVERLAP_END) {
util_addAlteration (currAlteration,currInterval->name,"endOverlap",currInterval,position,0);
continue;
}
else if (numOverlaps == 1 && overlapMode == OVERLAP_FULLY_CONTAINED && altLength > refLength) {
if ((sizeIndel % 3) == 0) {
util_addAlteration (currAlteration,currInterval->name,"insertionNFS",currInterval,position,0);
}
else {
util_addAlteration (currAlteration,currInterval->name,"insertionFS",currInterval,position,0);
}
}
else if (numOverlaps == 1 && overlapMode == OVERLAP_FULLY_CONTAINED && altLength < refLength) {
if ((sizeIndel % 3) == 0) {
util_addAlteration (currAlteration,currInterval->name,"deletionNFS",currInterval,position,0);
}
else {
util_addAlteration (currAlteration,currInterval->name,"deletionFS",currInterval,position,0);
}
}
else if (numOverlaps == 1 && overlapMode == OVERLAP_FULLY_CONTAINED && altLength == refLength) {
util_addAlteration (currAlteration,currInterval->name,"substitution",currInterval,position,0);
}
else {
die ("Unexpected type: %d %s %s %s",
currVcfEntry->position,currVcfEntry->chromosome,
currVcfEntry->referenceAllele,currVcfEntry->alternateAllele);
}
if ((sizeIndel % 3) != 0 && altLength != refLength) {
continue;
}
// Only run the remaining block of code if the indel is fully contained (insertion or deletion) AND does not cause a frameshift OR
// if it is a substitution that is fully contained in the coding sequence
stringPrintf (buffer,"%s|%s|%c|",currInterval->name,currInterval->chromosome,currInterval->strand);
for (j = 0; j < arrayMax (currInterval->subIntervals); j++) {
currSubInterval = arrp (currInterval->subIntervals,j,SubInterval);
stringAppendf (buffer,"%d|%d%s",currSubInterval->start,currSubInterval->end,j < arrayMax (currInterval->subIntervals) - 1 ? "|" : "");
}
testSeq.name = hlr_strdup (string (buffer));
if (!arrayFind (seqs,&testSeq,&index,(ARRAYORDERF)util_sortSequencesByName)) {
die ("Expected to find %s in seqs",string (buffer));
}
hlr_free (testSeq.name);
currSeq = arrp (seqs,index,Seq);
strReplace (&sequenceBeforeIndel,currSeq->sequence);
seqLength = strlen (sequenceBeforeIndel);
coordinates = util_getCoordinates (currInterval);
// arraySort (coordinates,(ARRAYORDERF)util_sortCoordinatesByChromosomeAndTranscriptPosition); Array is already sorted by definition
j = 0;
stringClear (buffer);
while (j < seqLength) {
if (util_getGenomicCoordinate (coordinates,j,currVcfEntry->chromosome) == position) {
if (altLength > refLength) {
stringCat (buffer,textItem (alternateAlleles,h));
j++;
continue;
}
else if (altLength < refLength) {
stringCatChar (buffer,sequenceBeforeIndel[j]);
j = j + refLength - altLength + 1;
continue;
}
else {
stringCat (buffer,textItem (alternateAlleles,h));
j = j + altLength;
continue;
}
}
stringCatChar (buffer,sequenceBeforeIndel[j]);
j++;
}
util_destroyCoordinates (coordinates);
proteinSequenceBeforeIndel = hlr_strdup (util_translate (currInterval,sequenceBeforeIndel));
proteinSequenceAfterIndel = hlr_strdup (util_translate (currInterval,string (buffer)));
addSubstitution (currAlteration,proteinSequenceBeforeIndel,proteinSequenceAfterIndel,indelOffset);
hlr_free (proteinSequenceBeforeIndel);
hlr_free (proteinSequenceAfterIndel);
}
if (arrayMax (alterations) == 0) {
continue;
}
arraySort (alterations,(ARRAYORDERF)util_sortAlterationsByGeneIdAndType);
stringClear (buffer);
i = 0;
while (i < arrayMax (alterations)) {
currAlteration = arrp (alterations,i,Alteration);
stringAppendf (buffer,"%s%d:%s:%s:%c:%s",stringLen (buffer) == 0 ? "" : ",",h + 1,currAlteration->geneName,currAlteration->geneId,currAlteration->strand,currAlteration->type);
stringClear (disabledTranscripts);
if (currAlteration->substitution[0] != '\0') {
stringAppendf (disabledTranscripts,"%s:%s:%d_%d_%s",currAlteration->transcriptName,currAlteration->transcriptId,currAlteration->transcriptLength,currAlteration->relativePosition,currAlteration->substitution);
}
else if (strEqual (currAlteration->type,"multiExonHit") || strEqual (currAlteration->type,"spliceOverlap") ||
strEqual (currAlteration->type,"startOverlap") || strEqual (currAlteration->type,"endOverlap")) {
stringAppendf (disabledTranscripts,"%s:%s:%d",currAlteration->transcriptName,currAlteration->transcriptId,currAlteration->transcriptLength);
}
else {
stringAppendf (disabledTranscripts,"%s:%s:%d_%d",currAlteration->transcriptName,currAlteration->transcriptId,currAlteration->transcriptLength,currAlteration->relativePosition);
}
numDisabledTranscripts = 1;
j = i + 1;
while (j < arrayMax (alterations)) {
nextAlteration = arrp (alterations,j,Alteration);
if (strEqual (currAlteration->geneId,nextAlteration->geneId) &&
strEqual (currAlteration->type,nextAlteration->type)) {
if (nextAlteration->substitution[0] != '\0') {
stringAppendf (disabledTranscripts,":%s:%s:%d_%d_%s",nextAlteration->transcriptName,nextAlteration->transcriptId,nextAlteration->transcriptLength,nextAlteration->relativePosition,nextAlteration->substitution);
}
else if (strEqual (nextAlteration->type,"multiExonHit") || strEqual (nextAlteration->type,"spliceOverlap") ||
strEqual (nextAlteration->type,"startOverlap") || strEqual (nextAlteration->type,"endOverlap")) {
stringAppendf (disabledTranscripts,":%s:%s:%d",nextAlteration->transcriptName,nextAlteration->transcriptId,nextAlteration->transcriptLength);
}
else {
stringAppendf (disabledTranscripts,":%s:%s:%d_%d",nextAlteration->transcriptName,nextAlteration->transcriptId,nextAlteration->transcriptLength,nextAlteration->relativePosition);
}
numDisabledTranscripts++;
}
else {
break;
}
j++;
}
i = j;
geneTranscriptIds = util_getTranscriptIdsForGeneId (geneTranscriptEntries,currAlteration->geneId);
stringAppendf (buffer,":%d/%d:%s",numDisabledTranscripts,arrayMax (geneTranscriptIds),string (disabledTranscripts));
}
if (flag1 == 0) {
printf ("%s\t%d\t%s\t%s\t%s\t%s\t%s\t%s;VA=",
currVcfEntry->chromosome,currVcfEntry->position,currVcfEntry->id,
currVcfEntry->referenceAllele,currVcfEntry->alternateAllele,
currVcfEntry->quality,currVcfEntry->filter,currVcfEntry->info);
flag1 = 1;
}
printf ("%s%s",flag2 == 1 ? "," : "",string (buffer));
flag2 = 1;
}
if (flag1 == 1) {
for (i = 0; i < arrayMax (currVcfEntry->genotypes); i++) {
currVcfGenotype = arrp (currVcfEntry->genotypes,i,VcfGenotype);
if (i == 0) {
printf ("\t%s\t",currVcfEntry->genotypeFormat);
}
printf ("%s%s%s%s",currVcfGenotype->genotype,
currVcfGenotype->details[0] != '\0' ? ":" : "",
currVcfGenotype->details[0] != '\0' ? currVcfGenotype->details : "",
i < arrayMax (currVcfEntry->genotypes) - 1 ? "\t" : "");
}
puts ("");
}
}
vcf_deInit ();
return 0;
}
float gradepointForGrade( char* grade ) {
// expects grade as a string
// returns float value for corresponding grade point
float gpa = 0.00;
if ( (strEqual(grade, "A+")) ) { gpa = 4.00; }
else if ( (strEqual(grade, "A")) ) { gpa = 4.00; }
else if ( (strEqual(grade, "A-")) ) { gpa = 3.70; }
else if ( (strEqual(grade, "B+")) ) { gpa = 3.33; }
else if ( (strEqual(grade, "B")) ) { gpa = 3.00; }
else if ( (strEqual(grade, "B-")) ) { gpa = 2.70; }
else if ( (strEqual(grade, "C+")) ) { gpa = 2.30; }
else if ( (strEqual(grade, "C")) ) { gpa = 2.00; }
else if ( (strEqual(grade, "C-")) ) { gpa = 1.70; }
else if ( (strEqual(grade, "D+")) ) { gpa = 1.30; }
else if ( (strEqual(grade, "D")) ) { gpa = 1.00; }
else if ( (strEqual(grade, "D-")) ) { gpa = 0.70; }
else {
println( "Grade %s not recognized. ", grade );
gpa = 0.00;
}
return gpa;
}
int main (int argc, char *argv[])
{
FILE* ftmp = NULL;
if ((Conf = confp_open(getenv("FUSIONSEQ_CONFPATH"))) == NULL)
return EXIT_FAILURE;
cgiInit();
cgiHeader("text/html");
if (argc == 3) {
GfrEntry *currGE;
Stringa buffer;
GfrPairCount *currGEPC;
GfrInterRead *currGIR;
int i;
puts ("<html>");
puts ("<head>");
html_printGenericStyleSheet (12);
puts ("<title>geneFusions Details</title>\n");
puts ("</head>");
puts ("<body>");
buffer = stringCreate (100);
stringPrintf (buffer, "%s/%s.gfr", confp_get(Conf, "WEB_DATA_DIR"),argv[1]);
gfr_init (string (buffer));
while (currGE = gfr_nextEntry ()){
fflush( stdout );
if (!strEqual (currGE->id,argv[2])) {
continue;
}
printf ("<h1>Detailed summary for potential gene fusion candidate</h1><br>");
puts ("<table border=0 cellpadding=10>");
puts ("<tr align=left valign=top>");
puts ("<td width=400>");
puts ("<h2>Summary information</h2><br>");
printf ("<b>Identifier</b>: %s<br><br>\n",currGE->id);
printf ("<b>Number of inter paired-end reads</b>: %d<br><br>\n",currGE->numInter);
printf ("<b>Type</b>: %s<br><br>\n",currGE->fusionType);
stringPrintf(buffer, "%s/GFF/%s.gff", confp_get(Conf, "WEB_DATA_DIR"),currGE->id);
ftmp = fopen( string(buffer), "r" ); // displaying this only if data are present
if (ftmp) {
printf("<b>Connected Reads</b>: <a href=%s&hgt.customText=%s/GFF/%s.gff target=blank>UCSC connectivity graph</a><br>\n",
htmlLinker_generateLinkToGenomeBrowserAtUCSC ("hg18","vertebrate","human",
currGE->chromosomeTranscript1,
currGE->startTranscript1 - atoi(confp_get(Conf, "UCSC_GENOME_BROWSER_FLANKING_REGION")),
currGE->endTranscript2 + atoi(confp_get(Conf, "UCSC_GENOME_BROWSER_FLANKING_REGION"))),
confp_get(Conf, "WEB_DATA_LINK"),currGE->id);
fclose( ftmp );
}
puts ("</td>");
puts ("<td>");
puts ("<h2>Transcript connectivity graph</h2>");
printf ("<img src=%s/IMAGES/%s.jpg alt=geneFusionImage>\n", confp_get(Conf, "WEB_DATA_LINK"), currGE->id);
puts ("</td>");
puts ("<td>");
puts ("<h2>Transcript connectivity table</h2><br>");
puts ("<table border=0>");
puts ("<tr align=left>");
puts ("<th width=200>Pair Type</th>");
puts ("<th width=200>Entry transcript 1</th>");
puts ("<th width=200>Entry transcript 2</th>");
puts ("<th width=200>Counts</th>");
puts ("</tr>");
fflush( stdout );
for (i = 0; i < arrayMax (currGE->pairCounts); i++) {
currGEPC = arrp (currGE->pairCounts,i,GfrPairCount);
printf ("<tr><td>%s</td><td>%s</td><td>%s</td><td>%.2f</td></tr>\n",
getPairTypeName(currGEPC->pairType),
getEntryNumber(currGEPC->number1, currGEPC->pairType, 1),
getEntryNumber(currGEPC->number2, currGEPC->pairType, 2),
currGEPC->count);
}
puts ("</table>");
puts ("</td>");
puts ("</tr>");
puts ("</table>");
puts ("<br>");
puts ("<h2>Transcript information</h2><br>");
puts ("<table border=1 cellpadding=10 width=\"80%\">");
puts ("<tr align=left>");
puts ("<th width=\"20%\"></th>");
puts ("<th><font color='blue'>Transcript 1</font></th>");
puts ("<th><font color='orange'>Transcript 2</font></th>");
puts ("</tr>");
puts ("<tr align=left>");
puts ("<td width=\"20%\"><b>Gene symbol(s)</b></td>");
printf ("<td width=\"30%%\"><font color='blue'>%s</font></td>\n",processString (currGE->geneSymbolTranscript1));
printf ("<td width=\"30%%\"><font color='orange'>%s</font></td>\n",processString (currGE->geneSymbolTranscript2));
puts ("</tr>");
puts ("<tr align=left>");
puts ("<td width=\"20%\"><b>Coordinates</b></td>");
printf ("<td width=\"30%%\">%s:%d-%d</td>\n",currGE->chromosomeTranscript1,currGE->startTranscript1,currGE->endTranscript1);
printf ("<td width=\"30%%\">%s:%d-%d</td>\n",currGE->chromosomeTranscript2,currGE->startTranscript2,currGE->endTranscript2);
puts ("</tr>");
puts ("<tr align=left>");
puts ("<td width=\"20%\"><b>Strand</b></td>");
printf ("<td width=\"30%%\">%c</td>\n",currGE->strandTranscript1);
printf ("<td width=\"30%%\">%c</td>\n",currGE->strandTranscript2);
puts ("</tr>");
puts ("<tr align=left>");
puts ("<td width=\"20%\"><b>Gene description(s)</b></td>");
printf ("<td width=\"30%%\">%s</td>\n",processString (currGE->descriptionTranscript1));
printf ("<td width=\"30%%\">%s</td>\n",processString (currGE->descriptionTranscript2));
puts ("</tr>");
puts ("<tr align=left>");
puts ("<td width=\"20%\"><b>Number of exons</b></td>");
printf ("<td width=\"30%%\">%d</td>\n",currGE->numExonsTranscript1);
printf ("<td width=\"30%%\">%d</td>\n",currGE->numExonsTranscript2);
puts ("</tr>");
puts ("<tr align=left>");
puts ("<td width=\"20%\"><b>Number of intra paired-end reads</b></td>");
printf ("<td width=\"30%%\">%d</td>\n",currGE->numIntra1);
printf ("<td width=\"30%%\">%d</td>\n",currGE->numIntra2);
puts ("</tr>");
puts ("<tr align=left>");
puts ("<td width=\"20%\"><b>Links</b></td>");
printf ("<td width=\"30%%\">[<a href=%s&hgt.customText=%s/BED/%s_1.bed target=blank>UCSC genome browser</a>] [<a href=%s/FASTA/%s_1.fasta>FASTA file</a>]<br></td>\n",
htmlLinker_generateLinkToGenomeBrowserAtUCSC ("hg18","vertebrate","human",
currGE->chromosomeTranscript1,
currGE->startTranscript1 - atoi(confp_get(Conf, "UCSC_GENOME_BROWSER_FLANKING_REGION")),
currGE->endTranscript1 + atoi(confp_get(Conf, "UCSC_GENOME_BROWSER_FLANKING_REGION"))),
confp_get(Conf, "WEB_DATA_LINK"),
currGE->id,
confp_get(Conf, "WEB_DATA_LINK"),
currGE->id);
printf ("<td width=\"30%%\">[<a href=%s&hgt.customText=%s/BED/%s_2.bed target=blank>UCSC genome browser</a>] [<a href=%s/FASTA/%s_2.fasta>FASTA file</a>]<br></td></tr>\n",
htmlLinker_generateLinkToGenomeBrowserAtUCSC ("hg18","vertebrate","human",
currGE->chromosomeTranscript2,
currGE->startTranscript2 - atoi(confp_get(Conf, "UCSC_GENOME_BROWSER_FLANKING_REGION")),
currGE->endTranscript2 + atoi(confp_get(Conf, "UCSC_GENOME_BROWSER_FLANKING_REGION"))),
confp_get(Conf, "WEB_DATA_LINK"),
currGE->id,
confp_get(Conf, "WEB_DATA_LINK"),
currGE->id);
puts ("<tr align=left>");
puts ("<td width=\"20%\"><b>Expression</b></td>");
stringPrintf(buffer, "%s/BGRS/%s_%s.bgr.gz",
confp_get(Conf, "WEB_DATA_DIR"),
argv[1],
currGE->chromosomeTranscript1);
ftmp = fopen( string(buffer), "r" ); // displaying this only if data are present
puts("<td width=\"30%\">");
if( ftmp ) {
printf ("[<a href=%s&hgt.customText=%s/BGRS/%s_%s.bgr.gz target=blank>Expression %s</a>]",
htmlLinker_generateLinkToGenomeBrowserAtUCSC ("hg18","vertebrate","human",
currGE->chromosomeTranscript1,
currGE->startTranscript1 - atoi(confp_get(Conf, "UCSC_GENOME_BROWSER_FLANKING_REGION")),
currGE->endTranscript1 + atoi(confp_get(Conf, "UCSC_GENOME_BROWSER_FLANKING_REGION"))),
confp_get(Conf, "WEB_DATA_LINK"),
argv[1],
currGE->chromosomeTranscript1,
currGE->chromosomeTranscript1);
fclose(ftmp);
}
puts("</td>");
stringPrintf(buffer, "%s/BGRS/%s_%s.bgr.gz", confp_get(Conf, "WEB_DATA_DIR"),argv[1],currGE->chromosomeTranscript2);
ftmp = fopen( string(buffer), "r" ); // displaying this only if data are present
puts("<td width=\"30%\">");
if( ftmp ) {
printf ("[<a href=%s&hgt.customText=%s/BGRS/%s_%s.bgr.gz target=blank>Expression %s</a>]",
htmlLinker_generateLinkToGenomeBrowserAtUCSC ("hg18","vertebrate","human",
currGE->chromosomeTranscript2,
currGE->startTranscript2 - atoi(confp_get(Conf, "UCSC_GENOME_BROWSER_FLANKING_REGION")),
currGE->endTranscript2 + atoi(confp_get(Conf, "UCSC_GENOME_BROWSER_FLANKING_REGION"))),
confp_get(Conf, "WEB_DATA_LINK"),
argv[1],
currGE->chromosomeTranscript2,
currGE->chromosomeTranscript2);
fclose(ftmp);
}
puts("</td>");
puts("</tr>");
puts ("</table><br><br>");
puts ("<h2>Breakpoint analysis</h2><br>");
puts ("<table border=1 width=\"80%\" cellpadding=10><thead><tr><th>Orientation</th><th>Alignments</th><th colspan=2>Breakpoints</th></tr></thead><tbody>");
puts ("<tr><td>Orientation AB</td>");
if (currGE->strandTranscript1=='+') {
currGE->strandTranscript2=='+' ? stringPrintf(buffer, "AB_trans1F_trans2F") : stringPrintf(buffer, "AB_trans1F_trans2R");
} else if( currGE->strandTranscript1 == '-') {
currGE->strandTranscript2=='+' ? stringPrintf(buffer, "AB_trans1R_trans2F") : stringPrintf(buffer, "AB_trans1R_trans2R");
} else {
die("Strand informatation is not correct (transcript 1): %c", currGE->strandTranscript1);
}
printf ("<td align=center><a href=%s/ALIGNMENTS/%s_AB_breakPointAlignments.txt><img src=%s/IMAGES/%s.png></img> AB</a></td>",
confp_get(Conf, "WEB_DATA_LINK"),
currGE->id,
confp_get(Conf, "WEB_DATA_LINK"),
string(buffer));
printf ("<td align=center><a href=%s&hgt.customText=%s/WIGS/%s_AB_breakPointsTranscript1.wig target=blank>Breakpoints transcript 1 UCSC Genome Browser</a></td>",
htmlLinker_generateLinkToGenomeBrowserAtUCSC ("hg18","vertebrate","human",
currGE->chromosomeTranscript1,
currGE->startTranscript1 - atoi(confp_get(Conf, "UCSC_GENOME_BROWSER_FLANKING_REGION")),
currGE->endTranscript1 + atoi(confp_get(Conf, "UCSC_GENOME_BROWSER_FLANKING_REGION"))),
confp_get(Conf, "WEB_DATA_LINK"),
currGE->id);
printf ("<td align=center><a href=%s&hgt.customText=%s/WIGS/%s_AB_breakPointsTranscript2.wig target=blank>Breakpoints transcript 2 UCSC Genome Browser</a></td></tr>",
htmlLinker_generateLinkToGenomeBrowserAtUCSC ("hg18","vertebrate","human",
currGE->chromosomeTranscript2,
currGE->startTranscript2 - atoi(confp_get(Conf, "UCSC_GENOME_BROWSER_FLANKING_REGION")),
currGE->endTranscript2 + atoi(confp_get(Conf, "UCSC_GENOME_BROWSER_FLANKING_REGION"))),
confp_get(Conf, "WEB_DATA_LINK"),
currGE->id);
fflush(stdout);
puts ("<tr><td>Orientation BA</td>");
if (currGE->strandTranscript1 == '+') {
currGE->strandTranscript2=='+' ? stringPrintf(buffer, "BA_trans1F_trans2F") : stringPrintf(buffer, "BA_trans1F_trans2R");
} else if( currGE->strandTranscript1 == '-') {
currGE->strandTranscript2=='+' ? stringPrintf(buffer, "BA_trans1R_trans2F") : stringPrintf(buffer, "BA_trans1R_trans2R");
} else {
die("Strand informatation is not correct (transcript2): %c", currGE->strandTranscript2);
}
printf ("<td align=center><a href=%s/ALIGNMENTS/%s_BA_breakPointAlignments.txt><img src=%s/IMAGES/%s.png></img> BA</a></td>",
confp_get(Conf, "WEB_DATA_LINK"),
currGE->id,
confp_get(Conf, "WEB_DATA_LINK"),
string(buffer));
printf ("<td align=center><a href=%s&hgt.customText=%s/WIGS/%s_BA_breakPointsTranscript2.wig target=blank>Breakpoints transcript 2 UCSC Genome Browser</a></td>",
htmlLinker_generateLinkToGenomeBrowserAtUCSC ("hg18","vertebrate","human",
currGE->chromosomeTranscript2,
currGE->startTranscript2 - atoi(confp_get(Conf, "UCSC_GENOME_BROWSER_FLANKING_REGION")),
currGE->endTranscript2 + atoi(confp_get(Conf, "UCSC_GENOME_BROWSER_FLANKING_REGION"))),
confp_get(Conf, "WEB_DATA_LINK"),
currGE->id);
printf ("<td align=center><a href=%s&hgt.customText=%s/WIGS/%s_BA_breakPointsTranscript1.wig target=blank>Breakpoints transcript 1 UCSC Genome Browser</a></td></tr>",
htmlLinker_generateLinkToGenomeBrowserAtUCSC ("hg18","vertebrate","human",
currGE->chromosomeTranscript1,
currGE->startTranscript1 - atoi(confp_get(Conf, "UCSC_GENOME_BROWSER_FLANKING_REGION")),
currGE->endTranscript1 + atoi(confp_get(Conf, "UCSC_GENOME_BROWSER_FLANKING_REGION"))),
confp_get(Conf, "WEB_DATA_LINK"),
currGE->id);
puts ("</tbody></table>");
puts ("<br><br><br>");
fflush(stdout);
puts ("<h2>Read coordinates</h2><br>");
puts ("<table border=0>");
puts ("<tr align=left>");
puts ("<th width=\"10%\">Pair Type</th>");
puts ("<th width=\"10%\">Entry Transcript 1</th>");
puts ("<th width=\"10%\">Read start transcript 1</th>");
puts ("<th width=\"10%\">Read end transcript 1</th>");
puts ("<th width=\"10%\">Entry Transcript 2</th>");
puts ("<th width=\"10%\">Read start transcript 2</th>");
puts ("<th width=\"10%\">Read end transcript 2</th>");
puts ("</tr>");
for (i = 0; i < arrayMax (currGE->interReads); i++) {
currGIR = arrp (currGE->interReads,i,GfrInterRead);
printf ("<tr><td>%s</td><td>%s</td><td>%d</td><td>%d</td><td>%s</td><td>%d</td><td>%d</td></tr>\n",
getPairTypeName(currGIR->pairType),
getEntryNumber(currGIR->number1, currGIR->pairType, 1),
currGIR->readStart1,currGIR->readEnd1,
getEntryNumber(currGIR->number2,currGIR->pairType, 2),
currGIR->readStart2,
currGIR->readEnd2);
}
puts ("</table><br><br><br>");
puts ("</body>");
puts ("</html>");
fflush (stdout);
}
}
confp_close(Conf);
return EXIT_SUCCESS;
}
int
main (int argc, char * argv[])
{
setbuf(stdout, NULL); // Make stdout unbuffered.
gameNumberT gNumber;
bool option_ForceReplace = false;
bool option_PreGameComments = true;
uint pgnFileSize = 0;
char *progname = argv[0];
fileNameT fname;
fileNameT baseName;
uint argsleft = argc - 1;
char ** nextArg = argv + 1;
// Parse command-line argments:
while (argsleft > 0 && nextArg[0][0] == '-') {
if (! strCompare (*nextArg, "-f")) {
option_ForceReplace = true;
} else if (! strCompare (*nextArg, "-x")) {
option_PreGameComments = false;
} else {
usage (progname);
}
argsleft--;
nextArg++;
}
if (argsleft != 1 && argsleft != 2) {
usage (progname);
}
char * pgnName = *nextArg;
MFile pgnFile;
pgnFileSize = fileSize (pgnName, "");
// Ensure positive file size counter to avoid division by zero:
if (pgnFileSize < 1) {
pgnFileSize = 1;
}
// Make baseName from pgnName if baseName is not provided:
if (argsleft == 1) {
strCopy (baseName, pgnName);
// If a gzip file, remove two suffixes, the first being ".gz":
const char * lastSuffix = strFileSuffix (baseName);
if (lastSuffix != NULL && strEqual (lastSuffix, GZIP_SUFFIX)) {
strTrimFileSuffix (baseName);
}
// Trim the ".pgn" suffix:
strTrimFileSuffix (baseName);
} else {
strCopy (baseName, nextArg[1]);
}
// Check for existing database, avoid overwriting it:
if (! option_ForceReplace) {
if (fileSize (baseName, INDEX_SUFFIX) > 0) {
// Scid index file already exists:
fprintf (stderr, "%s: database already exists: %s\n", progname,
baseName);
fprintf (stderr, "You can use: %s -f %s to overwrite"
" the existing database.\n", progname, pgnName);
exit(1);
}
}
if (pgnFile.Open (pgnName, FMODE_ReadOnly) != OK) {
fprintf (stderr, "%s: could not open file %s\n", progname, pgnName);
exit(1);
}
// Try opening the log file:
strCopy (fname, baseName);
strAppend (fname, ".err");
FILE * logFile = fopen (fname, "w");
if (logFile == NULL) {
fprintf (stderr, "%s: could not open log file: %s\n", progname, fname);
exit(1);
}
printf ("Converting file %s to Scid database %s:\n", pgnName, baseName);
printf ("Errors/warnings will be written to %s.\n\n", fname);
scid_Init();
GFile * gameFile = new GFile;
if ((gameFile->Create (baseName, FMODE_WriteOnly)) != OK) {
fprintf (stderr, "%s: could not create the file %s%s\n",
progname, baseName, GFILE_SUFFIX);
fprintf (stderr, "The file may already exist and be read-only, or\n");
fprintf (stderr, "you may not have permission to create this file.\n");
exit(1);
}
NameBase * nb = new NameBase;
Index * idx = new Index;
IndexEntry * ie = new IndexEntry;
idx->SetFileName (baseName);
idx->CreateIndexFile (FMODE_WriteOnly);
Game * game = new Game;
ProgBar progBar(stdout);
progBar.Start();
ByteBuffer *bbuf = new ByteBuffer;
bbuf->SetBufferSize (BBUF_SIZE); // 32768
PgnParser pgnParser (&pgnFile);
pgnParser.SetErrorFile (logFile);
pgnParser.SetPreGameText (option_PreGameComments);
// TODO: Add command line option for ignored tags, rather than
// just hardcoding PlyCount as the only ignored tag.
pgnParser.AddIgnoredTag ("PlyCount");
// Add each game found to the database:
while (pgnParser.ParseGame(game) != ERROR_NotFound) {
ie->Init();
if (idx->AddGame (&gNumber, ie) != OK) {
fprintf (stderr, "\nLimit of %d games reached!\n", MAX_GAMES);
exit(1);
}
// Add the names to the namebase:
idNumberT id = 0;
if (nb->AddName (NAME_PLAYER, game->GetWhiteStr(), &id) != OK) {
fatalNameError (NAME_PLAYER);
}
nb->IncFrequency (NAME_PLAYER, id, 1);
ie->SetWhite (id);
if (nb->AddName (NAME_PLAYER, game->GetBlackStr(), &id) != OK) {
fatalNameError (NAME_PLAYER);
}
nb->IncFrequency (NAME_PLAYER, id, 1);
ie->SetBlack (id);
if (nb->AddName (NAME_EVENT, game->GetEventStr(), &id) != OK) {
fatalNameError (NAME_EVENT);
}
nb->IncFrequency (NAME_EVENT, id, 1);
ie->SetEvent (id);
if (nb->AddName (NAME_SITE, game->GetSiteStr(), &id) != OK) {
fatalNameError (NAME_SITE);
}
nb->IncFrequency (NAME_SITE, id, 1);
ie->SetSite (id);
if (nb->AddName (NAME_ROUND, game->GetRoundStr(), &id) != OK) {
fatalNameError (NAME_ROUND);
}
nb->IncFrequency (NAME_ROUND, id, 1);
ie->SetRound (id);
bbuf->Empty();
if (game->Encode (bbuf, ie) != OK) {
fprintf (stderr, "Fatal error encoding game!\n");
abort();
}
uint offset = 0;
if (gameFile->AddGame (bbuf, &offset) != OK) {
fprintf (stderr, "Fatal error writing game file!\n");
abort();
}
ie->SetOffset (offset);
ie->SetLength (bbuf->GetByteCount());
idx->WriteEntries (ie, gNumber, 1);
// Update the progress bar:
if (! (gNumber % 100)) {
int bytesSeen = pgnParser.BytesUsed();
int percentDone = 1 + ((bytesSeen) * 100 / pgnFileSize);
progBar.Update (percentDone);
}
}
uint t = 0; // = time(0);
nb->SetTimeStamp(t);
nb->SetFileName (baseName);
if (nb->WriteNameFile() != OK) {
fprintf (stderr, "Fatal error writing name file!\n");
exit(1);
}
progBar.Finish();
printf ("\nDatabase `%s': %d games, %d players, %d events, %d sites.\n",
baseName, idx->GetNumGames(), nb->GetNumNames (NAME_PLAYER),
nb->GetNumNames (NAME_EVENT), nb->GetNumNames (NAME_SITE));
fclose (logFile);
if (pgnParser.ErrorCount() > 0) {
printf ("There were %u errors or warnings; ", pgnParser.ErrorCount());
printf ("examine the file \"%s.err\"\n", baseName);
} else {
printf ("There were no warnings or errors.\n");
removeFile (baseName, ".err");
}
gameFile->Close();
idx->CloseIndexFile();
// If there is a tree cache file for this database, it is out of date:
removeFile (baseName, TREEFILE_SUFFIX);
#ifdef ASSERTIONS
printf("%d asserts were tested\n", numAsserts);
#endif
return 0;
}
int main (int argc, char *argv[])
{
char *queryString;
if ((Conf = confp_open(getenv("FUSIONSEQ_CONFPATH"))) == NULL)
return EXIT_FAILURE;
cgiInit();
cgiHeader("text/html");
queryString = cgiGet2Post();
if (queryString[0] == '\0') {
puts ("<html>");
puts ("<head>");
html_printGenericStyleSheet (12);
puts ("<title>geneFusions</title>\n");
puts ("</head>");
puts ("<body>");
puts ("<h1>Identification of potential gene fusions using paired-end reads</h1><br><br>");
printf ("<form action=%s/geneFusions_cgi method=get>", confp_get(Conf, "WEB_URL_CGI"));
puts ("<b>Data prefix</b>: ");
puts ("<input type=text name=prefix>");
puts ("<br><br><br>");
puts ("<b>Minimum number of paired-end reads connecting two genes</b>: ");
puts ("<select name=minNum>");
puts ("<option value=2>2");
puts ("<option value=3>3");
puts ("<option value=5 selected>5");
puts ("<option value=10>10");
puts ("</select>");
puts ("<br><br><br>");
puts ("<b>Type of gene fusion</b>: ");
puts ("<select name=type>");
puts ("<option value=read-through>Read-through events");
puts ("<option value=cis>Cis events");
puts ("<option value=intra>Intra-chromosomal events");
puts ("<option value=same>Genes on the same chromosome");
puts ("<option value=inter>Genes on different chromosomes");
puts ("<option value=all selected>All potential gene fusions");
puts ("</select>");
puts ("<br><br><br>");
puts ("<input type=submit value=Submit>");
puts ("<input type=reset value=Reset>");
puts ("</form>");
puts ("</body>");
puts ("</html>");
fflush (stdout);
}
else {
int first;
Stringa item = stringCreate (20);
Stringa value = stringCreate (20);
char *iPtr,*vPtr,*prefix,*type;
int minNum;
first = 1;
cgiGetInit ();
while (cgiGetNextPair (&first,item,value)) {
iPtr = string (item);
vPtr = string (value);
if (strEqual (iPtr,"prefix")) {
prefix = hlr_strdup (vPtr);
}
if (strEqual (iPtr,"type")) {
type = hlr_strdup (vPtr);
}
if (strEqual (iPtr,"minNum")) {
minNum = atoi (vPtr);
}
}
generateOutput (prefix,type,minNum);
}
confp_close(Conf);
return EXIT_SUCCESS;
}
static void generateOutput (char* prefix, char* typeSelected, int minNum)
{
GfrEntry *currGE;
Stringa buffer;
char *pos;
puts ("<html>");
puts ("<head>");
puts ("<title>Results - Gene Fusions</title>");
html_printGenericStyleSheet (12);
puts ("</head>");
puts ("<body>");
if (prefix[0] == '\0') {
die ("Invalid prefix");
}
printf ("<h1>Results - %s</h1><br><br><br>",prefix);
buffer = stringCreate(50);
//Chromosome expression, if present
LineStream ls;
char* chrSignal=NULL;
stringPrintf(buffer, "ls -1 %s/BGRS/%s_chr*.bgr.gz 2> /dev/null",
confp_get(Conf, "WEB_DATA_DIR"),
prefix);
ls = ls_createFromPipe(string(buffer));
int countCol = 0;
puts ("Expression signal: ");
fflush(stdout);
while( chrSignal = ls_nextLine(ls)) {
char* chrTmp = stringBetween( prefix, ".bgr.gz", chrSignal );
chrTmp++;
int flankingRegion = atoi(confp_get(Conf, "UCSC_GENOME_BROWSER_FLANKING_REGION"));
char* link = htmlLinker_generateLinkToGenomeBrowserAtUCSC(
"hg18","vertebrate", "human", chrTmp, flankingRegion,
50000000 + flankingRegion);
printf ("[<a href=%s&hgt.customText=%s/BGRS/%s_%s.bgr.gz target='blank'>%s</a>] ",
link, confp_get(Conf, "WEB_DATA_LINK"), prefix, chrTmp, chrTmp);
if (countCol > 10) {
puts( "<BR>" );
countCol=0;
}
countCol++;
}
if( countCol==0) puts( "No data available yet" );
ls_destroy(ls);
puts ("<br><br>");
puts ("For a definition of SPER, DASPER and RESPER see <a href=http://rnaseq.gersteinlab.org/fusionseq/>FusionSeq</a>");
puts ("<br><br>");
puts ("<br><table border=0 width=100% align=center cellpadding=10>");
puts ("<tr align=left>");
puts ("<th>SPER</th>");
puts ("<th>DASPER</th>");
puts ("<th>RESPER</th>");
puts ("<th>Number of inter paired-end reads</th>");
puts ("<th>Type</th>");
puts ("<th>Genomic coordinates</th>");
puts ("<th>Gene symbol</th>");
puts ("<th>Description</th>");
puts ("<th>Genomic coordinates</th>");
puts ("<th>Gene symbol</th>");
puts ("<th>Description</th>");
puts ("<th></th>");
puts ("</tr>");
fflush(stdout);
stringPrintf (buffer,"%s/%s.gfr", confp_get(Conf, "WEB_DATA_DIR"), prefix);
gfr_init (string (buffer));
int countElements = 0;
while (currGE = gfr_nextEntry ()) {
if (currGE->numInter < minNum) {
continue;
}
if (strEqual (typeSelected,"all") || strEqual (currGE->fusionType,typeSelected) ||
( strEqual(currGE->fusionType,"cis") && strEqual( typeSelected,"same") ) ||
( strEqual(currGE->fusionType,"read-through") && strEqual( typeSelected,"same") ) ) {
if (pos = strchr (currGE->descriptionTranscript1,'|')) {
*pos = '\0';
}
if (pos = strchr (currGE->descriptionTranscript2,'|')) {
*pos = '\0';
}
puts ("<tr>");
printf ("<td align=left>%1.3f</td>\n",currGE->SPER);
printf ("<td align=left>%1.3f</td>\n",currGE->DASPER);
printf ("<td align=left>%1.3f</td>\n",currGE->RESPER);
printf ("<td align=left>%d</td>\n",currGE->numInter);
printf ("<td align=left>%s</td>\n",currGE->fusionType);
printf ("<td align=left><a href=%s target=blank>%s:%d-%d</a></td>\n",
htmlLinker_generateLinkToGenomeBrowserAtUCSC ("hg18","vertebrate","human",
currGE->chromosomeTranscript1,
currGE->startTranscript1 - atoi(confp_get(Conf, "UCSC_GENOME_BROWSER_FLANKING_REGION")),
currGE->endTranscript1 + atoi(confp_get(Conf, "UCSC_GENOME_BROWSER_FLANKING_REGION"))),
currGE->chromosomeTranscript1,currGE->startTranscript1,currGE->endTranscript1);
printf ("<td align=left>%s</td>\n",processString (currGE->geneSymbolTranscript1));
printf ("<td align=left>%s</td>\n",currGE->descriptionTranscript1);
printf ("<td align=left><a href=%s target=blank>%s:%d-%d</a></td>\n",
htmlLinker_generateLinkToGenomeBrowserAtUCSC ("hg18","vertebrate","human",
currGE->chromosomeTranscript2,
currGE->startTranscript2 - atoi(confp_get(Conf, "UCSC_GENOME_BROWSER_FLANKING_REGION")),
currGE->endTranscript2 + atoi(confp_get(Conf, "UCSC_GENOME_BROWSER_FLANKING_REGION"))),
currGE->chromosomeTranscript2,currGE->startTranscript2,currGE->endTranscript2);
printf ("<td align=left>%s</td>\n",processString (currGE->geneSymbolTranscript2));
printf ("<td align=left>%s</td>\n",currGE->descriptionTranscript2);
printf ("<td align=left><a href=%s/showDetails_cgi?%s+%s>Details</a></td>\n", confp_get(Conf, "WEB_URL_CGI"), prefix,currGE->id);
puts ("</tr>");
countElements++;
}
}
gfr_deInit ();
stringDestroy (buffer);
puts ("</table><br><br>");
if( countElements == 0) puts("No fusion candidates can be found satisfying all specified criteria.");
puts ("</body>");
puts ("</html>");
fflush (stdout);
}
int main (int argc, char *argv[])
{
GfrEntry *currGE;
BLEntry *currBLE;
BLEntry currQuery;
FILE *fp;
char *line;
int count;
int countRemoved;
int index;
WordIter w;
Array blackList = arrayCreate(20, BLEntry);
config *Conf;
if ((Conf = confp_open(getenv("FUSIONSEQ_CONFPATH"))) == NULL) {
die("%s:\tCannot find .fusionseqrc: %s", argv[0], getenv("FUSIONSEQ_CONFPATH"));
return EXIT_FAILURE;
}
if( confp_get( Conf, "ANNOTATION_DIR")==NULL ) {
die("%s:\tCannot find ANNOTATION_DIR in the configuration file: %s)", argv[0], getenv("FUSIONSEQ_CONFPATH") );
return EXIT_FAILURE;
}
if( confp_get( Conf, "BLACKLIST_FILENAME")==NULL ) {
die("%s:\tCannot find BLACKLIST_FILENAME in the configuration file: %s)", argv[0], getenv("FUSIONSEQ_CONFPATH") );
return EXIT_FAILURE;
}
Stringa buffer=stringCreate( 100 );
stringPrintf( buffer, "%s/%s", confp_get( Conf, "ANNOTATION_DIR"), confp_get( Conf, "BLACKLIST_FILENAME") );
/* fp = fopen( string( buffer ), "r" );
if( !fp ) die("Unable to open file: %s", string(buffer));
stringDestroy( buffer );
*/
// reading blacklist file
LineStream ls = ls_createFromFile( string(buffer) );
while( line = ls_nextLine(ls) ) {
w = wordIterCreate( line, "\t", 1);
currBLE = arrayp( blackList, arrayMax(blackList), BLEntry);
currBLE->gene1 = hlr_strdup ( wordNext(w) );
currBLE->gene2 = hlr_strdup ( wordNext(w) );
wordIterDestroy(w);
}
//fclose(fp);
ls_destroy( ls );
stringDestroy( buffer );
arraySort( blackList, (ARRAYORDERF) sortBlackListByName1);
// beginFiltering
count = 0;
countRemoved = 0;
gfr_init ("-");
puts (gfr_writeHeader ());
while (currGE = gfr_nextEntry ()) { // reading the gfr
if( currGE->geneSymbolTranscript1 == NULL ) {
die("Gene symbols are not present in the GFR file. Please run gfrAddInfo before gfrBlackListFilter.");
return EXIT_FAILURE;
}
// creating a new query to the black list
currQuery.gene1 = currGE->geneSymbolTranscript1;
currQuery.gene2 = currGE->geneSymbolTranscript2;
if( strEqual( currQuery.gene1 , currQuery.gene2 ) ) {
countRemoved++;
continue;
}
// searching against read_1/read_2
int res = arrayFind( blackList, &currQuery,
&index, (ARRAYORDERF) sortBlackListByName1);
if( !res ) { // not found, then searching against read_2/read_1
currQuery.gene1 = currGE->geneSymbolTranscript2;
currQuery.gene2 = currGE->geneSymbolTranscript1;
res = arrayFind( blackList, &currQuery,
&index, (ARRAYORDERF) sortBlackListByName1 );
if( !res ) { // not found, write the instance to stdout, update the counts
puts (gfr_writeGfrEntry (currGE));
count++;
} else { // found: read2/read1
countRemoved++;
}
} else { //found: read1/read2
countRemoved++;
}
}
gfr_deInit ();
arrayDestroy( blackList );
warn ("%s_BlackListFilter: %s",argv[0], confp_get( Conf, "BLACKLIST_FILENAME"));
warn ("%s_numRemoved: %d",argv[0],countRemoved);
warn ("%s_numGfrEntries: %d",argv[0],count);
confp_close( Conf);
return 0;
}
local int
cmdDoOptDeveloper(String arg)
{
int rc = 0;
if (!arg[0])
rc = -1;
if (strAEqual("trap", arg)) {
cmdTrapFlag = true;
}
else if (strAEqual("check", arg)) {
_dont_assert = false; /* Test assertions. */
stoCtl(StoCtl_Wash, true); /* Initialize of store. */
}
else if (strAEqual("no-fatal", arg))
_fatal_assert = false; /* Make assertions non-fatal. */
else if (strAEqual("runtime", arg))
genSetRuntime();
else if (strEqual("debug", arg))
genSetDebugWanted(true);
else if (strEqual("debugger", arg))
genSetDebuggerWanted(true);
else if (strEqual("depend", arg))
emitSetDependsWanted(true);
else if (strEqual("small-hcodes", arg))
genSetSmallHashCodes(true);
else if (strEqual("lazy-catch", arg))
gfSetLazyCatch(true);
else if (strEqual("dumb-import", arg))
stabSetDumbImport(true);
else if (strEqual("trace-cfuns", arg))
gencSetTraceFuns(true);
else if (strEqual("no-where", arg))
NoWhereHack = true;
else if (strAEqual("runtime-hashcheck", arg))
genSetHashcheck();
else if (strAIsPrefix("keyword", arg)) {
String darg = cmdDGetOptArg(arg, "keyword", NULL);
cmdDoKeywordStatus(darg, true);
}
else if (strAIsPrefix("no-keyword", arg)) {
String darg = cmdDGetOptArg(arg, "no-keyword", NULL);
cmdDoKeywordStatus(darg, false);
}
else if (strEqual("no-negated-tests", arg))
jflowSetNegate(false);
else if (strAEqual("audit", arg))
foamAuditSetAll();
else if (strAEqual("nhash", arg))
genSetAxiomAx(true);
else if (strAEqual("missing-ok", arg))
tiSetSoftMissing(true);
else if (strAEqual("sexpr", arg)) {
cmdSExprFlag = true;
}
else if (strAEqual("seval", arg)) {
cmdSEvalFlag = true;
}
else if (strAEqual("no-gc", arg)) {
/* Handled already - no action need be taken here */
}
else if (strAEqual("gc", arg)) {
/* Handled already - no action need be taken here */
cmdGcFlag = true;
}
else if (strAEqual("gcfile", arg)) {
/* Handled already - no action need be taken here */
cmdGcFileFlag = true;
}
else if (strAEqual("loops", arg)) {
optSetLoopOption();
}
else if (strAEqual("emerge-noalias", arg)) {
emSetNoAlias();
}
else if (strAIsPrefix("test", arg)) {
String darg = cmdDGetOptArg(arg, "test", NULL);
testSelf(darg);
exitSuccess();
}
else if (strAIsPrefix("rtcache", arg)) {
String darg = cmdDGetOptArg(arg, "rtcache", NULL);
long rtsize;
extern void gen0SetRtCacheSize(AInt);
sscanf(darg, "%ld", &rtsize);
gen0SetRtCacheSize((AInt)rtsize);
}
else if (strAIsPrefix("D", arg)) {
char sep;
String darg = cmdDGetOptArg(arg, "D", &sep);
rc = cmdDDebug(darg, sep == '+');
}
else if (strAIsPrefix("T", arg)) {
rc = phTraceOption(arg+strlen("T"));
}
else if (strAIsPrefix("name", arg)) {
String darg = cmdDGetOptArg(arg, "name", NULL);
emitSetFileIdName(darg);
}
else if (strAIsPrefix("prefix", arg)) {
String darg = cmdDGetOptArg(arg, "prefix", NULL);
emitSetFileIdPrefix(darg);
}
else if (strAEqual("floatrep", arg)) {
cmdFloatRepFlag = true;
}
else
rc = -1;
return rc;
}
TEST(misc, testConsoleLogic) {
print("******************************************* testConsoleLogic\r\n");
resetConsoleActions();
helpCommand();
char * cmd = "he ha";
ASSERT_EQ(2, findEndOfToken(cmd));
cmd = "\"hee\" ha";
ASSERT_EQ(5, findEndOfToken(cmd));
cmd = "\"h e\" ha";
ASSERT_EQ(5, findEndOfToken(cmd));
strcpy(buffer, "echo");
ASSERT_TRUE(strEqual("echo", unquote(buffer)));
strcpy(buffer, "\"echo\"");
ASSERT_TRUE(strEqual("echo", unquote(buffer))) << "unquote quoted";
char *ptr = validateSecureLine(UNKNOWN_COMMAND);
ASSERT_EQ(0, strcmp(UNKNOWN_COMMAND, ptr));
ASSERT_EQ(10, tokenLength(UNKNOWN_COMMAND));
// handling invalid token should work
strcpy(buffer, "sdasdafasd asd");
handleConsoleLine(buffer);
print("\r\naddConsoleActionI\r\n");
addConsoleActionI("echoi", testEchoI);
strcpy(buffer, "echoi 239");
handleConsoleLine(buffer);
ASSERT_EQ(239, lastInteger);
print("\r\naddConsoleActionI 240 with two spaces\r\n");
strcpy(buffer, "echoi 240");
handleConsoleLine(buffer);
ASSERT_EQ(240, lastInteger);
print("\r\naddConsoleActionII\r\n");
addConsoleActionII("echoii", testEchoII);
strcpy(buffer, "echoii 22 239");
handleConsoleLine(buffer);
ASSERT_EQ(22, lastInteger);
ASSERT_EQ(239, lastInteger2);
print("\r\naddConsoleActionII three spaces\r\n");
strcpy(buffer, "echoii 21 220");
handleConsoleLine(buffer);
ASSERT_EQ(21, lastInteger);
ASSERT_EQ(220, lastInteger2);
print("\r\addConsoleActionSSS\r\n");
addConsoleActionSSS("echosss", testEchoSSS);
strcpy(buffer, "echosss 111 222 333");
handleConsoleLine(buffer);
ASSERT_EQ(111, atoi(lastFirst));
ASSERT_EQ(333, atoi(lastThird));
strcpy(buffer, "echosss \" 1\" 222 333");
handleConsoleLine(buffer);
ASSERT_TRUE(strEqual("\" 1\"", lastFirst));
//addConsoleActionSSS("GPS", testGpsParser);
}
int calc(Vnode* expr, VM* vm, Contexts* contexts, Method** methods){
// Already calculated
if(expr->obj){
return 0;
}
// Variable
if(expr->name){
if(strEqual(expr->name, "assign") || strEqual(expr->name, "$") || strEqual(expr->name, "lamda")){
expr->isMethod = true;
}else{
for(int i = 0; methods[i]; i++){
if(strEqual(expr->name, methods[i]->name)){
expr->isMethod = true;
break;
}
}
}
if(!expr->isMethod){
expr->obj = findFromContexts(contexts, expr->name);
assert(expr->obj, "Error: %s not defined!", expr->name);
}
}
// Calculate
if(expr->childrenNum){
calc(expr->children[0], vm, contexts, methods);
Vnode* firstNode = expr->children[0];
int argNum = expr->childrenNum - 1;
printf("====================== Calc =======================\n");
printf("Calc: %s \n", firstNode->name);
printContexts(contexts);
printf("End : %s\n", firstNode->name);
// Native method
if(firstNode->isMethod){
if(strEqual(firstNode->name, "assign") || strEqual(firstNode->name, "$")){
assert(argNum == 2 && expr->children[1]->name, "Error: Wrong arguments for def!");
char* key = expr->children[1]->name;
calc(expr->children[2], vm, contexts, methods);
Object* value = expr->children[2]->obj;
Context* curr = getTopContext(contexts);
defineInContext(curr, key, value);
}else if(strEqual(firstNode->name, "lamda")){
expr->obj = pushLamda(vm, expr->node);
expr->obj->lamdaId = lamdaNum;
lamdaContexts[lamdaNum] = copyContexts(contexts, NULL);
lamdaNum++;
}else{
for(int i = 0; methods[i]; i++){
if(strEqual(firstNode->name, methods[i]->name)){
Object** args = malloc(sizeof(Object*) * argNum);
for(int i = 0; i < argNum; i++){
calc(expr->children[i+1], vm, contexts, methods);
args[i] = cloneObject(vm, expr->children[i+1]->obj);
}
expr->obj = methods[i]->callee(argNum, args, vm);
break;
}
}
}
return 0;
}
Object* firstVal = firstNode->obj;
// First value
if(firstVal->type != OBJ_LAMDA){
expr->obj = cloneObject(vm, firstVal);
return 0;
}
// Lamda call
// get args
Contexts* cxts = copyContexts(lamdaContexts[firstVal->lamdaId], NULL);
Context* runCxt = newContext();
for(int i = 0; i < argNum; i++){
calc(expr->children[i+1], vm, contexts, methods);
defineInContext(runCxt, firstVal->args[i], cloneObject(vm, expr->children[i+1]->obj));
}
pushContext(cxts, runCxt);
Vnode* vn = getVnode(firstVal->grammarTree->root, vm);
calc(vn, vm, cxts, methods);
expr->obj = vn->obj;
return 0;
}
return 0;
}
int myStrEqual(char* a, char* b) {
return strEqual(a, b);
}
