struct lineFile *lineFileMayOpen(char *fileName, bool zTerm)
/* Try and open up a lineFile. */
{
if (sameString(fileName, "stdin"))
return lineFileStdin(zTerm);
else if (getDecompressor(fileName) != NULL)
return lineFileDecompress(fileName, zTerm);
else
{
int fd = open(fileName, O_RDONLY);
if (fd == -1)
return NULL;
return lineFileAttach(fileName, zTerm, fd);
}
}
void checkSymlinkTargetType(char *inputList)
/* Check out the symlink to determine its type. */
{
struct lineFile *lf = NULL;
if (startsWith("stdin",inputList))
lf = lineFileStdin(TRUE);
else
lf = lineFileOpen(inputList, TRUE);
char *line = NULL;
while (lineFileNext(lf, &line, NULL))
{
// find creates paths starting with ./ in the current dir.
if (startsWith("./", line))
line += 2; // skip over it
verbose(3, "%s\n", line);
showSymlinkType(line, prefix);
}
lineFileClose(&lf);
}
int *readInConservationVals(char *fileName)
/* Open up the file and read in the conservation scores.
return an array indexed by base position with the conservation
scores. Free with freez() */
{
struct lineFile *lf = NULL;
int *scores = NULL;
int chromSize = optionInt("chromSize", 0);
int i = 0;
char *words[2];
if(chromSize == 0)
errAbort("Can't have chromSize set to 0.");
warn("Reading in conservation");
setMaxAlloc(sizeof(*scores)*chromSize+1);
AllocArray(scores, chromSize);
/* Make empty data be -1, a not possible score. */
for(i = 0; i < chromSize; i++)
scores[i] = -1;
/* Open up our conservation file. */
if(sameString(fileName, "stdin"))
lf = lineFileStdin(TRUE);
else
lf = lineFileOpen(fileName, TRUE);
dotForUserInit( chromSize/10 > 1 ? chromSize/10 : 1);
while(lineFileNextRow(lf, words, ArraySize(words)))
{
scores[atoi(words[0])] = round(atof(words[1]) * FLOAT_CHEAT);
dotForUser();
}
lineFileClose(&lf);
warn("Done");
return scores;
}
void ffaToFa(char *inFile, char *outDir, char *outTabName)
/* convert Greg Schulers .ffa fasta files to our .fa files */
{
struct lineFile *in;
FILE *out = NULL, *tab;
int lineSize;
char *line;
char ucscName[128];
char path[512];
static char lastPath[512];
int outFileCount = 0;
struct hash *uniqClone = newHash(16);
struct hash *uniqFrag = newHash(19);
boolean ignore = FALSE;
makeDir(outDir);
errLog = mustOpen("ffaToFa.err", "w");
tab = mustOpen(outTabName, "w");
printf("Converting %s", inFile);
fflush(stdout);
if (sameString(inFile, "stdin"))
in = lineFileStdin(TRUE);
else
in = lineFileOpen(inFile, TRUE);
while (lineFileNext(in, &line, &lineSize))
{
if (line[0] == '>')
{
ignore = FALSE;
gsToUcsc(line+1, ucscName);
faRecNameToFaFileName(outDir, ucscName, path);
if (hashLookup(uniqFrag, ucscName))
{
ignore = TRUE;
warn("Duplicate %s in %s, ignoring all but first",
ucscName, inFile);
}
else
{
hashAdd(uniqFrag, ucscName, NULL);
}
if (!sameString(path, lastPath))
{
strcpy(lastPath, path);
carefulClose(&out);
if (hashLookup(uniqClone, path))
{
warn("Duplicate %s in %s ignoring all but first",
ucscName, inFile);
}
else
{
hashAdd(uniqClone, path, NULL);
out = mustOpen(path, "w");
++outFileCount;
if ((outFileCount&7) == 0)
{
putc('.', stdout);
fflush(stdout);
}
}
}
if (out != NULL && !ignore)
{
fprintf(out, ">%s\n", ucscName);
fprintf(tab, "%s\t%s\n", ucscName, line+1);
}
}
else
{
if (out != NULL && !ignore)
{
fputs(line, out);
fputc('\n', out);
}
}
}
carefulClose(&out);
fclose(tab);
lineFileClose(&in);
printf("Made %d .fa files in %s\n", outFileCount, outDir);
}
