d9741ac7fe00ba4e2cc38bb8baab8c8b2ae6eec6 galt Fri Feb 13 18:23:42 2026 -0800 Updated the following seven utilities bigBedToBed, bigMafToMafj, bigWigToWig, bigWigToBedGraph, bigGenePredToGenePred, bigPslToPsl, bigChainToChain, added support for multiple -range parameters that uses and validates Marks desired bed and position values, in a new callback function in the library bigBedCmdSupport.c. Also added the ability to quickly check allowed chromosomes so users see and error when specifying incorrect chromsome names, and it works with all the filter options. These utils also have a new -skipChromCheck option that users can use if the want to skip the check. These have no tests. I will make tests for these soon. refs #28109, #36925 diff --git src/utils/bigBedToBed/bigBedToBed.c src/utils/bigBedToBed/bigBedToBed.c index 6f8dfca462a..73d9421de8c 100644 --- src/utils/bigBedToBed/bigBedToBed.c +++ src/utils/bigBedToBed/bigBedToBed.c @@ -8,146 +8,168 @@ #include "options.h" #include "localmem.h" #include "udc.h" #include "bigBed.h" #include "asParse.h" #include "obscure.h" #include "bigBedCmdSupport.h" #include "basicBed.h" char *clChrom = NULL; int clStart = -1; int clEnd = -1; char *clBed = NULL; char *clPos = NULL; +struct slName *clRange = NULL; boolean header = FALSE; boolean tsv = FALSE; +struct hash *chromHash = NULL; +boolean skipChromCheck = FALSE; struct lm *lm = NULL; void usage() /* Explain usage and exit. */ { errAbort( "bigBedToBed v1 - Convert from bigBed to ascii bed format.\n" "usage:\n" " bigBedToBed input.bb output.bed\n" "options:\n" " -chrom=chr1 - if set restrict output to given chromosome\n" " -start=N - if set, restrict output to only that over start 0 based coordiate\n" " -end=N - if set, restrict output to only that under end\n" + " -range=\"chrom start end\" - if set, restrict output to only that within range from start to end. \n" + " This range start is a half-open 0-based coordinate like used in BED files. \n" + " -range=chrom:start-end - if set, restrict output to only that within range from start to end. \n" + " This range start is a 1-based start position. \n" + " Do not use range with chrom, start, and/or end options. \n" + " -range may be specified multiple times for multiple ranges. \n" " -bed=in.bed - restrict output to all regions in a BED file\n" " -positions=in.pos - restrict output to all regions in a position file with 1-based start\n" " -udcDir=/dir/to/cache - place to put cache for remote bigBed/bigWigs\n" " -header - output a autoSql-style header (starts with '#').\n" " -tsv - output a TSV header (without '#').\n" + " -skipChromCheck - skip checking chrom name.\n" ); } static struct optionSpec options[] = { {"chrom", OPTION_STRING}, {"start", OPTION_INT}, {"end", OPTION_INT}, {"bed", OPTION_STRING}, + {"range", OPTION_STRING|OPTION_MULTI}, {"positions", OPTION_STRING}, {"udcDir", OPTION_STRING}, {"header", OPTION_BOOLEAN}, {"tsv", OPTION_BOOLEAN}, + {"skipChromCheck", OPTION_BOOLEAN}, {NULL, 0}, }; static void processChromChunk(struct bbiFile *bbi, char *chromName, int start, int end, char *bedName, FILE *f) { int itemsLeft = 0; // Zero actually means no limit.... struct bigBedInterval *interval, *intervalList = bigBedIntervalQuery(bbi, chromName, start, end, itemsLeft, lm); for (interval = intervalList; interval != NULL; interval = interval->next) { fprintf(f, "%s\t%u\t%u", chromName, interval->start, interval->end); char *rest = interval->rest; if (rest != NULL) fprintf(f, "\t%s\n", rest); else fprintf(f, "\n"); } } void bigBedToBed(char *inFile, char *outFile) /* bigBedToBed - Convert from bigBed to ascii bed format.. */ { struct bbiFile *bbi = bigBedFileOpen(inFile); FILE *f = mustOpen(outFile, "w"); +struct bbiChromInfo *chrom, *chromList = bbiChromList(bbi); +if (!skipChromCheck) + chromHash = makeChromHash(chromList); if (header) bigBedCmdOutputHeader(bbi, f); else if (tsv) bigBedCmdOutputTsvHeader(bbi, f); if (clBed != NULL) { - genericBigToNonBigFromBed(bbi, clBed, f, &processChromChunk); - return; + genericBigToNonBigFromBed(bbi, chromHash, clBed, f, &processChromChunk); } -if (clPos != NULL) +else if (clPos != NULL) { - genericBigToNonBigFromPos(bbi, clPos, f, &processChromChunk); - return; + genericBigToNonBigFromPos(bbi, chromHash, clPos, f, &processChromChunk); } - +else if (clRange != NULL) + { + genericBigToNonBigFromRange(bbi, chromHash, f, clRange, &processChromChunk); + } +else + { boolean chromFound = FALSE; -struct bbiChromInfo *chrom, *chromList = bbiChromList(bbi); for (chrom = chromList; chrom != NULL; chrom = chrom->next) { if (clChrom != NULL && !sameString(clChrom, chrom->name)) continue; chromFound = TRUE; char *chromName = chrom->name; int start = 0, end = chrom->size; if (clStart >= 0) start = clStart; if (clEnd >= 0) { end = clEnd; if (end > chrom->size) end = chrom->size; } if (start > end) errAbort("invalid range, start=%d > end=%d", start, end); processChromChunk(bbi, chromName, start, end, NULL, f); } -if (clChrom && !chromFound) - errAbort("specified chrom %s not found in maf", clChrom); + if (clChrom && !chromFound && !skipChromCheck) + errAbort("specified chrom %s not found in bigBed", clChrom); + } bbiChromInfoFreeList(&chromList); carefulClose(&f); bbiFileClose(&bbi); } int main(int argc, char *argv[]) /* Process command line. */ { lm = lmInit(0); optionInit(&argc, argv, options); clChrom = optionVal("chrom", clChrom); clStart = optionInt("start", clStart); clEnd = optionInt("end", clEnd); +clRange =optionMultiVal("range", clRange); + clBed = optionVal("bed", clBed); clPos = optionVal("positions", clPos); + udcSetDefaultDir(optionVal("udcDir", udcDefaultDir())); header = optionExists("header"); tsv = optionExists("tsv"); +skipChromCheck = optionExists("skipChromCheck"); if (header & tsv) errAbort("can't specify both -header and -tsv"); if (argc != 3) usage(); -if ((clBed || clPos) && (clChrom || (clStart >= 0) || (clEnd >= 0))) - errAbort("-bed or -positions can not be used with -chrom -start or -end options"); -if (clBed && clPos) - errAbort("-bed and -positions can not be used together"); +if ((clBed || clPos || clRange) && (clChrom || (clStart >= 0) || (clEnd >= 0))) + errAbort("-bed or -positions or -range can not be used with -chrom -start or -end options"); +if ((clBed && clPos) || (clBed && clRange) || (clPos && clRange)) + errAbort("-bed, -positions, and -range can not be used together"); bigBedToBed(argv[1], argv[2]); lmCleanup(&lm); if (verboseLevel() > 1) printVmPeak(); return 0; }