[ADAM-1481] Refactor ADAMContext loadXxx methods for consistency

adam-apis/src/main/scala/org/bdgenomics/adam/apis/java/JavaADAMContext.scala

@@ -52,15 +52,15 @@ class JavaADAMContext(val ac: ADAMContext) extends Serializable {
   }
 
   /**
-   * Loads in sequence fragments.
+   * Loads in nucleotide contig fragments.
    *
    * Can load from FASTA or from Parquet encoded NucleotideContigFragments.
    *
    * @param pathName Path to load the file from.
    * @return Returns a NucleotideContigFragment RDD.
    */
-  def loadSequences(pathName: java.lang.String): NucleotideContigFragmentRDD = {
-    ac.loadSequences(pathName)
+  def loadContigFragments(pathName: java.lang.String): NucleotideContigFragmentRDD = {
+    ac.loadContigFragments(pathName)
   }
 
   /**
@@ -84,7 +84,7 @@ class JavaADAMContext(val ac: ADAMContext) extends Serializable {
   }
 
   /**
-   * Loads in a coverage file. This method can load BED, NarrowPeak, GFF3, GTF/GFF2, IntervalList and ADAM files.
+   * Loads in a coverage file. This method can load BED6/12, NarrowPeak, GFF3, GTF/GFF2, IntervalList and ADAM files.
    *
    * @param pathName Path to load the file from.
    * @return Returns a Coverage RDD.

adam-apis/src/test/java/org/bdgenomics/adam/apis/java/JavaADAMContigConduit.java

@@ -38,6 +38,6 @@ public static NucleotideContigFragmentRDD conduit(final NucleotideContigFragment
 
         // create a new adam context and load the file
         JavaADAMContext jac = new JavaADAMContext(ac);
-        return jac.loadSequences(fileName);
+        return jac.loadContigFragments(fileName);
     }
 }

adam-apis/src/test/scala/org/bdgenomics/adam/apis/java/JavaADAMContextSuite.scala

@@ -39,7 +39,7 @@ class JavaADAMContextSuite extends ADAMFunSuite {
 
   sparkTest("can read and write a small FASTA file") {
     val path = copyResource("chr20.250k.fa.gz")
-    val aRdd = sc.loadSequences(path)
+    val aRdd = sc.loadContigFragments(path)
     assert(aRdd.jrdd.count() === 26)
 
     val newRdd = JavaADAMContigConduit.conduit(aRdd, sc)

adam-cli/src/main/scala/org/bdgenomics/adam/cli/ADAM2Fasta.scala

@@ -50,7 +50,7 @@ class ADAM2Fasta(val args: ADAM2FastaArgs) extends BDGSparkCommand[ADAM2FastaArg
   override def run(sc: SparkContext): Unit = {
 
     log.info("Loading ADAM nucleotide contig fragments from disk.")
-    val contigFragments = sc.loadSequences(args.inputPath)
+    val contigFragments = sc.loadContigFragments(args.inputPath)
 
     log.info("Merging fragments and writing FASTA to disk.")
     val contigs = contigFragments.mergeFragments()

adam-cli/src/main/scala/org/bdgenomics/adam/cli/CountContigKmers.scala

@@ -49,7 +49,7 @@ class CountContigKmers(protected val args: CountContigKmersArgs) extends BDGSpar
   def run(sc: SparkContext) {
 
     // read from disk
-    val fragments = sc.loadSequences(args.inputPath)
+    val fragments = sc.loadContigFragments(args.inputPath)
 
     // count kmers
     val countedKmers = fragments.countKmers(args.kmerLength)

adam-core/src/main/scala/org/bdgenomics/adam/util/FileExtensions.scala

@@ -0,0 +1,145 @@
+/**
+ * Licensed to Big Data Genomics (BDG) under one
+ * or more contributor license agreements.  See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership.  The BDG licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License.  You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.bdgenomics.adam.util
+
+/**
+ * Match path names to file extensions.
+ */
+object FileExtensions {
+
+  /**
+   * @param pathName The path name to match.
+   * @return Returns true if the path name matches a 2bit format file extension.
+   */
+  private[adam] def is2BitExt(pathName: String): Boolean = {
+    pathName.endsWith(".2bit")
+  }
+
+  /**
+   * @param pathName The path name to match.
+   * @return Returns true if the path name matches a BAM/CRAM/SAM format file extension.
+   */
+  private[adam] def isBamExt(pathName: String): Boolean = {
+    pathName.endsWith(".bam") ||
+      pathName.endsWith(".cram") ||
+      pathName.endsWith(".sam")
+  }
+
+  /**
+   * @param pathName The path name to match.
+   * @return Returns true if the path name matches a BED6/12 format file extension.
+   */
+  private[adam] def isBedExt(pathName: String): Boolean = {
+    pathName.endsWith(".bed") ||
+      pathName.endsWith(".bed.gz") ||
+      pathName.endsWith(".bed.bz2")
+  }
+
+  /**
+   * @param pathName The path name to match.
+   * @return Returns true if the path name matches a FASTA format file extension.
+   */
+  private[adam] def isFastaExt(pathName: String): Boolean = {
+    pathName.endsWith(".fa") ||
+      pathName.endsWith(".fa.gz") ||
+      pathName.endsWith(".fa.bz2") ||
+      pathName.endsWith(".fasta") ||
+      pathName.endsWith(".fasta.gz") ||
+      pathName.endsWith(".fasta.bz2")
+  }
+
+  /**
+   * @param pathName The path name to match.
+   * @return Returns true if the path name matches a FASTQ format file extension.
+   */
+  private[adam] def isFastqExt(pathName: String): Boolean = {
+    pathName.endsWith(".fq") ||
+      pathName.endsWith(".fq.gz") ||
+      pathName.endsWith(".fq.bz2") ||
+      pathName.endsWith(".fastq") ||
+      pathName.endsWith(".fastq.gz") ||
+      pathName.endsWith(".fastq.bz2")
+  }
+
+  /**
+   * @param pathName The path name to match.
+   * @return Returns true if the path name matches a GFF3 format file extension.
+   */
+  private[adam] def isGff3Ext(pathName: String): Boolean = {
+    pathName.endsWith(".gff3") ||
+      pathName.endsWith(".gff3.gz") ||
+      pathName.endsWith(".gff3.bz2")
+  }
+
+  /**
+   * @param pathName The path name to match.
+   * @return Returns true if the path name matches a GFF2/GTF format file extension.
+   */
+  private[adam] def isGtfExt(pathName: String): Boolean = {
+    pathName.endsWith(".gff") ||
+      pathName.endsWith(".gff.gz") ||
+      pathName.endsWith(".gff.bz2") ||
+      pathName.endsWith(".gtf") ||
+      pathName.endsWith(".gtf.gz") ||
+      pathName.endsWith(".gtf.bz2")
+  }
+
+  /**
+   * @param pathName The path name to match.
+   * @return Returns true if the path name matches an interleaved FASTQ format file extension.
+   */
+  private[adam] def isInterleavedFastqExt(pathName: String): Boolean = {
+    pathName.endsWith(".ifq") ||
+      pathName.endsWith(".ifq.gz") ||
+      pathName.endsWith(".ifq.bz2")
+  }
+
+  /**
+   * @param pathName The path name to match.
+   * @return Returns true if the path name matches an IntervalList format file extension.
+   */
+  private[adam] def isIntervalListExt(pathName: String): Boolean = {
+    pathName.endsWith(".interval_list") ||
+      pathName.endsWith(".interval_list.gz") ||
+      pathName.endsWith(".interval_list.bz2")
+  }
+
+  /**
+   * @param pathName The path name to match.
+   * @return Returns true if the path name matches a NarrowPeak format file extension.
+   */
+  private[adam] def isNarrowPeakExt(pathName: String): Boolean = {
+    pathName.endsWith(".narrowpeak") ||
+      pathName.endsWith(".narrowpeak.gz") ||
+      pathName.endsWith(".narrowpeak.bz2") ||
+      pathName.endsWith(".narrowPeak") ||
+      pathName.endsWith(".narrowPeak.gz") ||
+      pathName.endsWith(".narrowPeak.bz2")
+  }
+
+  /**
+   * @param pathName The path name to match.
+   * @return Returns true if the path name matches a VCF format file extension.
+   */
+  private[adam] def isVcfExt(pathName: String): Boolean = {
+    pathName.endsWith(".vcf") ||
+      pathName.endsWith(".vcf.gz") ||
+      pathName.endsWith(".vcf.bgzf") ||
+      pathName.endsWith(".vcf.bgz")
+  }
+}

adam-core/src/test/scala/org/bdgenomics/adam/converters/FastaConverterSuite.scala

@@ -209,7 +209,7 @@ class FastaConverterSuite extends ADAMFunSuite {
 
   sparkTest("convert reference fasta file") {
     //Loading "human_g1k_v37_chr1_59kb.fasta"
-    val referenceSequences = sc.loadSequences(chr1File, maximumFragmentLength = 10).rdd.collect()
+    val referenceSequences = sc.loadContigFragments(chr1File, maximumFragmentLength = 10).rdd.collect()
     assert(referenceSequences.forall(_.getContig.getContigName.toString == "1"))
     assert(referenceSequences.slice(0, referenceSequences.length - 2).forall(_.getFragmentSequence.length == 10))