Update changelog, add tests, fix argument naming errors, add test data

CHANGELOG.md

@@ -43,7 +43,8 @@
     - `samtools/samtools_index`: Index SAM/BAM/CRAM files (PR #35).
     - `samtools/samtools_sort`: Sort SAM/BAM/CRAM files (PR #36).
     - `samtools/samtools_stats`: Reports alignment summary statistics for a BAM file (PR #39).
-    - `samtools/samtools_stats`: Indexes FASTA files to enable random access to fasta and fastq files (PR #41).
+    - `samtools/samtools_faidx`: Indexes FASTA files to enable random access to fasta and fastq files (PR #41).
+    - `samtools/samtools_fastq`: Converts a SAM/BAM/CRAM file to FASTQ (PR #49).
 
 * `falco`: A C++ drop-in replacement of FastQC to assess the quality of sequence read data (PR #43).
 

src/samtools/samtools_fastq/config.vsh.yaml

@@ -1,6 +1,6 @@
 name: samtools_fastq
 namespace: samtools
-description: convert a SAM/BAM/CRAM file to FASTQ.
+description: Converts a SAM, BAM or CRAM to FASTQ format.
 keywords: [fastq, bam, sam, cram]
 links:
   homepage: https://www.htslib.org/
@@ -23,6 +23,7 @@ argument_groups:
         type: file
         description: output FASTQ file
         required: true
+        direction: output
   - name: Options
     arguments:
       - name: --no_suffix
@@ -58,29 +59,33 @@ argument_groups:
           TAGLIST can be blank or * to indicate all tags should be copied to the output. If using *, 
           be careful to quote it to avoid unwanted shell expansion.
       - name: --read1
-        alternatives: "-1"
+        alternatives: -1
         type: file
         description: |
           Write reads with the READ1 FLAG set (and READ2 not set) to FILE instead of outputting them. 
           If the -s option is used, only paired reads will be written to this file.
+        direction: output
       - name: --read2
-        alternatives: "-2"
+        alternatives: -2
         type: file
         description: |
           Write reads with the READ2 FLAG set (and READ1 not set) to FILE instead of outputting them. 
           If the -s option is used, only paired reads will be written to this file.
+        direction: output
       - name: --output_reads
         alternatives: -o
         type: file
         description: |
           Write reads with either READ1 FLAG or READ2 flag set to FILE instead of outputting them to stdout. 
           This is equivalent to -1 FILE -2 FILE.
+        direction: output
       - name: --output_reads_both
         alternatives: -0
         type: file
         description: |
           Write reads where the READ1 and READ2 FLAG bits set are either both set or both unset to FILE 
           instead of outputting them.
+        direction: output
       - name: --filter_flags
         alternatives: -f
         type: integer
@@ -90,17 +95,17 @@ argument_groups:
           (i.e. /^0[0-7]+/).
         default: 0
       - name: --excl_flags
-        alternatives: "-F"
-        type: integer
+        alternatives: -F
+        type: string
         description: |
           Do not output alignments with any bits set in INT present in the FLAG field. INT can be specified 
           in hex by beginning with `0x' (i.e. /^0x[0-9A-F]+/) or in octal by beginning with `0' 
           (i.e. /^0[0-7]+/). This defaults to 0x900 representing filtering of secondary and 
           supplementary alignments.
         default: 0x900
       - name: --incl_flags
-        alternatives: "--rf"
-        type: integer
+        alternatives: --rf
+        type: string
         description: |
           Only output alignments with any bits set in INT present in the FLAG field. INT can be specified 
           in hex by beginning with `0x' (i.e. /^0x[0-9A-F]+/), in octal by beginning with `0' 

src/samtools/samtools_fastq/test.sh

@@ -1,36 +1,96 @@
 #!/bin/bash
 
 test_dir="${meta_resources_dir}/test_data"
-out_dir="${meta_resources_dir}/tmp"
+out_dir="${meta_resources_dir}/out_data"
 
 ############################################################################################
 
-## example 1: samtools fastq -0 /dev/null in_name.bam > all_reads.fq
-## example 2: samtools fastq -0 /dev/null -s single.fq -N in_name.bam > paired.fq
-## example 3: samtools fastq with fasta output??
-## example 4: samtools fastq with compressed input?
-## example 5: samtools fastq with no suffix?
+echo ">>> Test 1: Convert all reads from a bam file to fastq format"
+"$meta_executable" \
+  --input "$test_dir/a.bam" \
+  --output "$out_dir/a.fq"
+
+echo ">>> Check if output file exists"
+[ ! -f "$out_dir/a.fq" ] && echo "Output file a.fq does not exist" && exit 1
 
+echo ">>> Check if output is empty"
+[ ! -s "$out_dir/a.fq" ] && echo "Output file a.fq is empty" && exit 1
+
+echo ">>> Check if output matches expected output"
+diff "$out_dir/a.fq" "$test_dir/a.fq" || 
+  (echo "Output file a.fq does not match expected output" && exit 1)
 
-echo ">>> Test 1: Sorting a BAM file"
+rm "$out_dir/a.fq"
 
+############################################################################################
+
+echo ">>> Test 2: Convert all reads from a sam file to fastq format"
 "$meta_executable" \
-  --input "$test_dir/a.bam" \
-  --output "$test_dir/a.sorted.bam"
+  --input "$test_dir/a.sam" \
+  --output "$out_dir/a.fq"
 
 echo ">>> Check if output file exists"
-[ ] \
-    && echo "Output file a.sorted.bam does not exist" && exit 1
+[ ! -f "$out_dir/a.fq" ] && echo "Output file a.fq does not exist" && exit 1
 
 echo ">>> Check if output is empty"
+[ ! -s "$out_dir/a.fq" ] && echo "Output file a.fq is empty" && exit 1
 
 echo ">>> Check if output matches expected output"
+diff "$out_dir/a.fq" "$test_dir/a.fq" || 
+  (echo "Output file a.fq does not match expected output" && exit 1)
 
+rm "$out_dir/a.fq"
 
 ############################################################################################
 
+echo ">>> Test 3: Output reads from bam file to separate files"
+
+"$meta_executable" \
+  --input "$test_dir/a.bam" \
+  --read1 "$out_dir/a.1.fq" \
+  --read2 "$out_dir/a.2.fq" \
+  --output "$out_dir/a.fq"
+
+echo ">>> Check if output files exist"
+[ ! -f "$out_dir/a.1.fq" ] && echo "Output file a.1.fq does not exist" && exit 1
+[ ! -f "$out_dir/a.2.fq" ] && echo "Output file a.2.fq does not exist" && exit 1
+[ ! -f "$out_dir/a.fq" ] && echo "Output file a.fq does not exist" && exit 1
+
+echo ">>> Check if output files are empty"
+[ ! -s "$out_dir/a.1.fq" ] && echo "Output file a.1.fq is empty" && exit 1
+[ ! -s "$out_dir/a.2.fq" ] && echo "Output file a.2.fq is empty" && exit 1
+# output should be empty since input has no singleton reads
+
+echo ">>> Check if output files match expected output"
+diff "$out_dir/a.1.fq" "$test_dir/a.1.fq" || 
+  (echo "Output file a.1.fq does not match expected output" && exit 1)
+diff "$out_dir/a.2.fq" "$test_dir/a.2.fq" ||
+  (echo "Output file a.2.fq does not match expected output" && exit 1)
+
+rm "$out_dir/a.1.fq" "$out_dir/a.2.fq" "$out_dir/a.fq"
+
 ############################################################################################
 
+echo ">>> Test 4: Output only forward reads from bam file to fastq format"
+
+"$meta_executable" \
+  --input "$test_dir/a.sam" \
+  --excl_flags "0x80" \
+  --output "$out_dir/half.fq"
+
+echo ">>> Check if output file exists"
+[ ! -f "$out_dir/half.fq" ] && echo "Output file half.fq does not exist" && exit 1
+
+echo ">>> Check if output is empty"
+[ ! -s "$out_dir/half.fq" ] && echo "Output file half.fq is empty" && exit 1
+
+echo ">>> Check if output matches expected output"
+diff "$out_dir/half.fq" "$test_dir/half.fq" || 
+  (echo "Output file half.fq does not match expected output" && exit 1)
+
+rm "$out_dir/half.fq"
+
+############################################################################################
 
 echo "All tests succeeded!"
 exit 0

src/samtools/samtools_fastq/test_data/a.1.fq

@@ -0,0 +1,12 @@
+@a1
+AAAAAAAAAA
++
+**********
+@b1
+AAAAAAAAAA
++
+**********
+@c1
+AAAAAAAAAA
++
+**********

src/samtools/samtools_fastq/test_data/a.2.fq

@@ -0,0 +1,12 @@
+@a1
+AAAAAAAAAA
++
+**********
+@b1
+AAAAAAAAAA
++
+**********
+@c1
+AAAAAAAAAA
++
+**********

src/samtools/samtools_fastq/test_data/a.fq

@@ -0,0 +1,24 @@
+@a1/1
+AAAAAAAAAA
++
+**********
+@b1/1
+AAAAAAAAAA
++
+**********
+@c1/1
+AAAAAAAAAA
++
+**********
+@a1/2
+AAAAAAAAAA
++
+**********
+@b1/2
+AAAAAAAAAA
++
+**********
+@c1/2
+AAAAAAAAAA
++
+**********

src/samtools/samtools_fastq/test_data/half.fq

@@ -0,0 +1,12 @@
+@a1/1
+AAAAAAAAAA
++
+**********
+@b1/1
+AAAAAAAAAA
++
+**********
+@c1/1
+AAAAAAAAAA
++
+**********

src/samtools/samtools_fastq/test_data/script.sh

@@ -5,4 +5,7 @@ if [ ! -d /tmp/fastq_source ]; then
   git clone --depth 1 --single-branch --branch master https://github.com/snakemake/snakemake-wrappers.git /tmp/fastq_source
 fi
 
-cp -r /tmp/fastq_source/bio/samtools/fastx/test/*.sam src/samtools/samtools_fastq/test_data/
+cp -r /tmp/fastq_source/bio/samtools/fastx/test/*.sam src/samtools/samtools_fastq/test_data/
+cp -r /tmp/fastq_source/bio/samtools/fastq/interleaved/test/mapped/*.bam src/samtools/samtools_fastq/test_data/
+cp -r /tmp/fastq_source/bio/samtools/fastq/interleaved/test/reads/*.fq src/samtools/samtools_fastq/test_data/
+cp -r /tmp/fastq_source/bio/samtools/fastq/separate/test/reads/*.fq src/samtools/samtools_fastq/test_data/