Skip to content

Proposal: handling UCSC 2bit sequences as ReferenceFile #1417

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
lindenb wants to merge 12 commits into
base: master
Choose a base branch
from
Open

Proposal: handling UCSC 2bit sequences as ReferenceFile #1417

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
12 commits
Select commit Hold shift + click to select a range
337931a
works
lindenb Aug 17, 2019
82da4e3
implements FastaFile
lindenb Aug 17, 2019
19412b9
fix dict order
lindenb Aug 17, 2019
a24959b
truncate names
lindenb Aug 17, 2019
69530b6
test
lindenb Aug 17, 2019
70b78e2
misc
lindenb Aug 20, 2019
4b4d842
using SeekableStream
lindenb Sep 10, 2019
1907d02
fix ioexception
lindenb Sep 10, 2019
3cff49e
fix error in test
lindenb Sep 17, 2019
adb0c25
fix error in test
lindenb Sep 17, 2019
8fa7787
fix error in test
lindenb Sep 17, 2019
a8919d9
fix bug in tests
lindenb Sep 19, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 0 additions & 3 deletions src/main/java/htsjdk/samtools/reference/IndexedFastaSequenceFile.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,14 +28,11 @@
import htsjdk.samtools.SAMSequenceDictionary;
import htsjdk.samtools.seekablestream.ReadableSeekableStreamByteChannel;
import htsjdk.samtools.seekablestream.SeekableStream;
import htsjdk.samtools.util.BlockCompressedInputStream;
import htsjdk.samtools.util.IOUtil;

import java.io.BufferedInputStream;
import java.io.File;
import java.io.FileNotFoundException;
import java.io.IOException;
import java.io.InputStream;
import java.nio.ByteBuffer;
import java.nio.channels.FileChannel;
import java.nio.channels.SeekableByteChannel;
Expand Down
25 changes: 18 additions & 7 deletions src/main/java/htsjdk/samtools/reference/ReferenceSequenceFileFactory.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,6 @@
package htsjdk.samtools.reference;

import htsjdk.samtools.SAMException;
import htsjdk.samtools.util.BlockCompressedInputStream;
import htsjdk.samtools.util.GZIIndex;
import htsjdk.samtools.SAMFileHeader;
import htsjdk.samtools.SAMSequenceDictionary;
Expand All @@ -35,15 +34,11 @@
import htsjdk.samtools.util.FileExtensions;
import htsjdk.samtools.util.IOUtil;

import java.io.BufferedInputStream;
import java.io.File;
import java.io.FileNotFoundException;
import java.io.IOException;
import java.io.InputStream;
import java.nio.file.Files;
import java.nio.file.Path;
import java.util.Collections;
import java.util.HashSet;
import java.util.Set;

/**
Expand Down Expand Up @@ -131,8 +126,18 @@ public static ReferenceSequenceFile getReferenceSequenceFile(final Path path, fi
* @param preferIndexed if true attempt to return an indexed reader that supports non-linear traversal, else return the non-indexed reader
*/
public static ReferenceSequenceFile getReferenceSequenceFile(final Path path, final boolean truncateNamesAtWhitespace, final boolean preferIndexed) {
// 2bit sequences
if (path.getFileName().toString().endsWith(FileExtensions.TWOBIT)) {
try {
return new TwoBitSequenceFile(path, truncateNamesAtWhitespace);
} catch (final IOException e) {
throw new SAMException("Error opening .2bit : " + path, e);
}
}

// this should thrown an exception if the fasta file is not supported
getFastaExtension(path);

// Using faidx requires truncateNamesAtWhitespace
if (truncateNamesAtWhitespace && preferIndexed && canCreateIndexedFastaReader(path)) {
try {
Expand All @@ -150,6 +155,7 @@ public static ReferenceSequenceFile getReferenceSequenceFile(final Path path, fi
*
* <p>For a FASTA file to be indexed, it requires to have:
* <ul>
* <li>A '.2bit' extension</li>
* <li>Associated .fai index ({@link FastaSequenceIndex}).</li>
* <li>Associated .gzi index if it is block-compressed ({@link GZIIndex}).</li>
* </ul>
Expand All @@ -160,9 +166,14 @@ public static ReferenceSequenceFile getReferenceSequenceFile(final Path path, fi
public static boolean canCreateIndexedFastaReader(final Path fastaFile) {
// this should thrown an exception if the fasta file is not supported
getFastaExtension(fastaFile);


if (!Files.exists(fastaFile)) return false;

// 2bit file
if (fastaFile.getFileName().toString().endsWith(FileExtensions.TWOBIT)) return true;

// both the FASTA file should exists and the .fai index should exist
if (Files.exists(fastaFile) && Files.exists(getFastaIndexFileName(fastaFile))) {
if (Files.exists(getFastaIndexFileName(fastaFile))) {
// open the file for checking for block-compressed input
try {
// if it is bgzip, it requires the .gzi index
Expand Down
Loading