Compute checksum for each input file

.gitignore

@@ -8,3 +8,4 @@ testing*
 *.pyc
 null/
 .lineage/
+.nf-test*

CHANGELOG.md

@@ -9,6 +9,8 @@ Initial release of nf-core/datasync, created with the [nf-core](https://nf-co.re
 
 ### `Added`
 
+- [[#31](https://github.com/nf-core/datasync/pull/31)] - Compute checksum for each input file ([@delfiterradas](https://github.com/delfiterradas), review by [@atrigila](https://github.com/atrigila)).
+
 ### `Fixed`
 
 ### `Dependencies`

assets/samplesheet.csv

@@ -1,3 +1,3 @@
-sample,fastq_1,fastq_2
-SAMPLE_PAIRED_END,/path/to/fastq/files/AEG588A1_S1_L002_R1_001.fastq.gz,/path/to/fastq/files/AEG588A1_S1_L002_R2_001.fastq.gz
-SAMPLE_SINGLE_END,/path/to/fastq/files/AEG588A4_S4_L003_R1_001.fastq.gz,
+sample,input
+human_grch38_sequence,s3://ngi-igenomes/igenomes/Homo_sapiens/NCBI/GRCh38/Sequence/WholeGenomeFasta/
+test_fastq,https://github.com/nf-core/test-datasets/raw/71ac9e72555f901d2864ccb27d534933411e3ed4/data/genomics/sarscov2/illumina/fastq/test2_1.fastq.gz

assets/schema_input.json

@@ -13,21 +13,12 @@
                 "errorMessage": "Sample name must be provided and cannot contain spaces",
                 "meta": ["id"]
             },
-            "fastq_1": {
+            "input": {
                 "type": "string",
-                "format": "file-path",
-                "exists": true,
-                "pattern": "^([\\S\\s]*\\/)?[^\\s\\/]+\\.f(ast)?q\\.gz$",
-                "errorMessage": "FastQ file for reads 1 must be provided, cannot contain spaces and must have extension '.fq.gz' or '.fastq.gz'"
-            },
-            "fastq_2": {
-                "type": "string",
-                "format": "file-path",
-                "exists": true,
-                "pattern": "^([\\S\\s]*\\/)?[^\\s\\/]+\\.f(ast)?q\\.gz$",
-                "errorMessage": "FastQ file for reads 2 cannot contain spaces and must have extension '.fq.gz' or '.fastq.gz'"
+                "pattern": "^\\S+$",
+                "errorMessage": "Input path must be provided and cannot contain spaces"
             }
         },
-        "required": ["sample", "fastq_1"]
+        "required": ["sample", "input"]
     }
 }

conf/test.config

@@ -25,6 +25,6 @@ params {
     // Input data
     // TODO nf-core: Specify the paths to your test data on nf-core/test-datasets
     // TODO nf-core: Give any required params for the test so that command line flags are not needed
-    input  = params.pipelines_testdata_base_path + 'viralrecon/samplesheet/samplesheet_test_illumina_amplicon.csv'// Genome references
+    input = "${projectDir}/assets/samplesheet.csv"
     genome = 'R64-1-1'
 }

modules.json

@@ -10,10 +10,20 @@
                         "git_sha": "6d46786420b4d7bc88eba026eb389c0c5535d120",
                         "installed_by": ["modules"]
                     },
+                    "md5sum": {
+                        "branch": "master",
+                        "git_sha": "6d46786420b4d7bc88eba026eb389c0c5535d120",
+                        "installed_by": ["modules"]
+                    },
                     "multiqc": {
                         "branch": "master",
                         "git_sha": "008f9d3e61209bf995edac3ba531f54e269e1215",
                         "installed_by": ["modules"]
+                    },
+                    "shasum": {
+                        "branch": "master",
+                        "git_sha": "ef2ee0358c7d03231834aeac816991aeb20debd7",
+                        "installed_by": ["modules"]
                     }
                 }
             },