Skip to content

Commit f02670b

Browse files
TCLamnidisTCLamnidis
committed
update test
1 parent 2871ab5 commit f02670b

2 files changed

Lines changed: 95 additions & 123 deletions

File tree

‎tests/shortdna.nf.test‎

Lines changed: 23 additions & 32 deletions
Original file line numberDiff line numberDiff line change
@@ -47,13 +47,23 @@ nextflow_pipeline {
4747
'**/mapped_reads_gc-content_distribution.txt',
4848
'**/mapped_reads_nucleotide_content.txt',
4949
'**/genome_gc_content_per_window.png',
50-
'**/*.{svg,pdf,html,png}',
50+
'**/*.{svg,pdf,html,png,json}',
5151
'**/DamageProfiler.log',
52-
'**/3p_freq_misincorporations.txt',
52+
'**/{3,5}p_freq_misincorporations.txt',
5353
'**/DNA_comp_genome.txt',
5454
'**/DNA_composition_sample.txt',
5555
'**/misincorporation.txt',
5656
'**/genome_results.txt',
57+
'**/3pGtoA_freq.txt',
58+
'**/5pCtoT_freq.txt',
59+
'**/lgdistribution.txt',
60+
'**/*c_curve.txt',
61+
"**/coverage_across_reference.txt",
62+
"**/coverage_histogram.txt",
63+
"**/duplication_rate_histogram.txt",
64+
"**/genome_fraction_coverage.txt",
65+
"**/mapping_quality_across_reference.txt",
66+
"**/mapping_quality_histogram.txt",
5767
]
5868

5969
// Check that no files are missing/added
@@ -64,13 +74,13 @@ nextflow_pipeline {
6474
def stable_content_authentication = getAllFilesFromDir("$outputDir/authentication" , includeDir: false , ignore: unstable_patterns_auth , ignoreFile: null , include: ['*', '**/*'] )
6575
def stable_name_authentication = getAllFilesFromDir("$outputDir/authentication" , includeDir: false , ignore: null , ignoreFile: null , include: unstable_patterns_auth)
6676

67-
// Deduplication - TODO -> snapshot both lists are empty!?
68-
def stable_content_deduplication = getAllFilesFromDir("$outputDir/deduplication" , includeDir: false , ignore: null , ignoreFile: null , include: ['**/*.flagstat'] )
69-
def stable_name_deduplication = getAllFilesFromDir("$outputDir/deduplication" , includeDir: false , ignore: null , ignoreFile: null , include: ['**/*.{bam,bai}'] )
77+
// Deduplication
78+
// NOTE: even the flagstats are unstable, so we only check the names
79+
def stable_name_deduplication = getAllFilesFromDir("$outputDir/deduplication" , includeDir: false , ignore: null , ignoreFile: null , include: ['**/*'] )
7080

7181
// Final_bams
72-
def stable_content_final_bams = getAllFilesFromDir("$outputDir/final_bams" , includeDir: false , ignore: null , ignoreFile: null , include: ['**/*.flagstat'] )
73-
def stable_name_final_bams = getAllFilesFromDir("$outputDir/final_bams" , includeDir: false , ignore: null , ignoreFile: null , include: ['**/*.{bam,bai}'] )
82+
// NOTE: BAMs are unstable, since upstream BAMs are unstable.
83+
def stable_name_final_bams = getAllFilesFromDir("$outputDir/final_bams" , includeDir: false , ignore: null , ignoreFile: null , include: ['**/*'] )
7484

7585
// Mapping (incl. bam_input flasgstat)
7686
def stable_content_mapping = getAllFilesFromDir("$outputDir/mapping" , includeDir: false , ignore: null , ignoreFile: null , include: ['**/*.flagstat'] )
@@ -82,10 +92,8 @@ nextflow_pipeline {
8292
def stable_name_preprocessing = getAllFilesFromDir("$outputDir/preprocessing" , includeDir: false , ignore: null , ignoreFile: null , include: ['**/*.{zip,log,html}'] )
8393

8494
// Genotyping
85-
def stable_content_genotyping = getAllFilesFromDir("$outputDir/genotyping" , includeDir: false , ignore: ['**/*.{tbi,vcf.gz}'] , ignoreFile: null , include: ['**/*'] )
86-
def stable_name_genotyping = getAllFilesFromDir("$outputDir/genotyping" , includeDir: false , ignore: null , ignoreFile: null , include: ['**/*.tbi'] )
87-
// We need to collect the vcfs separately to run more specific md5sum checks on the header (contnts are unstable due to same reasons as BAMs, explained above).
88-
def genotyping_vcfs = getAllFilesFromDir("$outputDir/genotyping" , includeDir: false , ignore: null , ignoreFile: null , include: ['**/*.vcf.gz'] )
95+
// NOTE: single file is created, with unstable content due to unstable BAM input.
96+
def stable_name_genotyping = getAllFilesFromDir("$outputDir/genotyping" , includeDir: false , ignore: null , ignoreFile: null , include: ['**/*.glf.gz'] )
8997

9098
// Metagenomics
9199
def stable_content_metagenomics = getAllFilesFromDir("$outputDir/metagenomics" , includeDir: false , ignore: ['**/*.biom', '**/*table.tsv'] , ignoreFile: null , include: ['**/*'] )
@@ -108,30 +116,13 @@ nextflow_pipeline {
108116
// NOTE: Keep the order of the sections in the alphanumeric order of the output directories.
109117
// Each section should first check stable_content, stable_name second (if applicable).
110118
{ assert snapshot( stable_content_authentication , stable_name_authentication*.name ).match("authentication") },
111-
{ assert snapshot( stable_content_deduplication , stable_name_deduplication*.name ).match("deduplication") },
112-
{ assert snapshot( stable_content_final_bams , stable_name_final_bams*.name ).match("final_bams") },
119+
{ assert snapshot( stable_name_deduplication*.name ).match("deduplication") },
120+
{ assert snapshot( stable_name_final_bams*.name ).match("final_bams") },
113121
// NOTE: The snapshot section for mapping cannot be named 'mapping'. See https://github.com/askimed/nf-test/issues/279
114122
{ assert snapshot( stable_content_mapping , stable_name_mapping*.name ).match("mapping_output") },
115123
{ assert snapshot( stable_content_preprocessing , stable_name_preprocessing*.name ).match("preprocessing") },
116-
{ assert snapshot( stable_content_readfiltering , stable_name_readfiltering*.name ).match("read_filtering") },
117-
{ assert snapshot( stable_content_genotyping , stable_name_genotyping*.name ).match("genotyping") },
118-
// Additional checks on the genotyping VCFs for content. Specifically the md5sums of the header FORMAT and INFO lines
119-
{ assert snapshot(
120-
genotyping_vcfs.collect {
121-
file ->
122-
def vcf_head = path(file.toString()).vcf.header
123-
// The header contains lines in the "OTHER" category, which contain a timestamp, so we need to filter those out, then calculate md5sums.
124-
def header_md5 = [
125-
vcf_head.getFormatHeaderLines().toString(),
126-
vcf_head.getInfoHeaderLines().toString(),
127-
vcf_head.getFilterLines().toString(),
128-
vcf_head.getIDHeaderLines().toString(),
129-
vcf_head.getGenotypeSamples().toString(),
130-
vcf_head.getContigLines().toString(),
131-
].join(' ').md5()
132-
file.getName() + ":header_md5," + header_md5
133-
}
134-
).match("genotyping_vcfs")},
124+
// { assert snapshot( stable_content_readfiltering , stable_name_readfiltering*.name ).match("read_filtering") },
125+
{ assert snapshot( stable_name_genotyping*.name ).match("genotyping") },
135126
{ assert snapshot( stable_content_metagenomics , stable_name_metagenomics*.name ).match("metagenomics") },
136127
{ assert snapshot( stable_name_multiqc*.name ).match("multiqc") },
137128

0 commit comments

Comments
 (0)
⚡