nf-core · delfiterradas · Jul 30, 2026 · Jul 30, 2026 · Jul 30, 2026 · Jul 30, 2026
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -9,6 +9,7 @@ Initial release of nf-core/datasync, created with the [nf-core](https://nf-co.re
 
 ### `Added`
 
+- [[#74](https://github.com/nf-core/datasync/pull/74)] - Implement warning and `--download` parameter when working with remote directories and SHA checksums ([@delfiterradas](https://github.com/delfiterradas), review by [@atrigila](https://github.com/atrigila) and [@antoniasaracco](https://github.com/antoniasaracco)).
 - [[#67](https://github.com/nf-core/datasync/pull/67)] - Copy only files which are successfully validated ([@delfiterradas](https://github.com/delfiterradas), review by [@atrigila](https://github.com/atrigila) and [@antoniasaracco](https://github.com/antoniasaracco)).
 - [[#57](https://github.com/nf-core/datasync/pull/57)] - Add nf-tests with edge cases([@atrigila](https://github.com/atrigila), review by [@delfiterradas](https://github.com/delfiterradas)).
 - [[#55](https://github.com/nf-core/datasync/pull/55)] - Add subdirectories with sample id to results. Improvements to MultiQC report (width of columns, sections and sub-section headers)colors to multiqc results and display first errors in tables ([@atrigila](https://github.com/atrigila), review by [@delfiterradas](https://github.com/delfiterradas)).

diff --git a/assets/schema_input.json b/assets/schema_input.json
@@ -26,13 +26,13 @@
             "checksum_md5": {
                 "type": "string",
                 "format": "file-path",
-                "pattern": "^\\S+\\.(csv|tsv)$",
+                "pattern": "^\\S+\\.(tsv|txt|md5)$",
                 "errorMessage": "Checksum_md5 cannot contain spaces"
             },
             "checksum_sha": {
                 "type": "string",
                 "format": "file-path",
-                "pattern": "^\\S+\\.(csv|tsv)$",
+                "pattern": "^\\S+\\.(tsv|txt|sha256)$",
                 "errorMessage": "Checksum_sha cannot contain spaces"
             }
         },

diff --git a/conf/modules.config b/conf/modules.config
@@ -18,6 +18,25 @@ process {
         saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
     ]
 
+    withName: 'RCLONE_CHECKSUM' {
+        tag = { "${meta.id}_${hash}" }
+        ext.args = {
+            def base_args = [
+                '--no-check-certificate',
+                "--one-way"
+            ]
+            if (params.download && meta.check_format == 'sha') {
+                base_args.add("--download")
+            }
+            base_args.join(' ')
+        }
+        publishDir = [
+            path: { "${params.outdir}/rclone/checksum/${meta.id}" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+        ]
+    }
+
     withName: 'RCLONE_COPY' {
         ext.args = {
             def base_args = [
@@ -58,22 +77,6 @@ process {
         ]
     }
 
-    withName: 'RCLONE_CHECKSUM' {
-        tag = { "${meta.id}_${hash}" }
-        ext.args = {
-            def base_args = [
-                '--no-check-certificate',
-                "--one-way"
-            ]
-            base_args.join(' ')
-        }
-        publishDir = [
-            path: { "${params.outdir}/rclone/checksum/${meta.id}" },
-            mode: params.publish_dir_mode,
-            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
-        ]
-    }
-
     withName: 'MULTIQC' {
         ext.args = {
             def args = ['--custom-css-file */multiqc_custom.css']

diff --git a/conf/test_full.config b/conf/test_full.config
@@ -20,6 +20,7 @@ params {
     input = params.pipelines_testdata_base_path + "test-data/samplesheet_full.csv"
 
     //Rclone options
-    rclone_config = params.pipelines_testdata_base_path + "test-data/rclone.conf"
+    rclone_config  = params.pipelines_testdata_base_path + "test-data/rclone.conf"
     rclone_dry_run = true
+    download       = true
 }
diff --git a/nextflow.config b/nextflow.config
@@ -24,6 +24,7 @@ params {
     rclone_config               = null
     rclone_dry_run              = false
     copy_matching_only          = false
+    download                    = false
 
     // Boilerplate options
     outdir                       = null

diff --git a/nextflow_schema.json b/nextflow_schema.json
@@ -60,6 +60,12 @@
                     "description": "Only copy files that matched their provided input checksums.",
                     "fa_icon": "fas fa-eye",
                     "help_text": "If set, the pipeline will only copy files that were correctly validated and will skip any file that did not match their input checksum."
+                },
+                "download": {
+                    "type": "boolean",
+                    "description": "Download remote files for sha256 checksum verification.",
+                    "fa_icon": "fas fa-eye",
+                    "help_text": "If set, rclone checksum will download remote files for any sample for which a shasum file was provided."
                 }
             }
         },

diff --git a/tests/edge.nf.test b/tests/edge.nf.test
@@ -12,6 +12,7 @@ nextflow_pipeline {
             params {
                 input = "https://raw.githubusercontent.com/nf-core/test-datasets/refs/heads/datasync/test-data/samplesheet_edge.csv"
                 outdir = "$outputDir"
+                download = true
             }
         }
 
@@ -41,6 +42,7 @@ nextflow_pipeline {
                 input = "https://raw.githubusercontent.com/nf-core/test-datasets/refs/heads/datasync/test-data/samplesheet_edge.csv"
                 outdir = "$outputDir"
                 copy_matching_only = true
+                download = true
             }
         }
 

diff --git a/tests/edge.nf.test.snap b/tests/edge.nf.test.snap
@@ -25,6 +25,7 @@
                 "multiqc/multiqc_data/multiqc_data.json",
                 "multiqc/multiqc_data/multiqc_rclone_check.txt",
                 "multiqc/multiqc_data/multiqc_rclone_checksum_md5.txt",
+                "multiqc/multiqc_data/multiqc_rclone_checksum_sha.txt",
                 "multiqc/multiqc_data/multiqc_samplesheet.txt",
                 "multiqc/multiqc_data/multiqc_software_versions.txt",
                 "multiqc/multiqc_data/multiqc_sources.txt",
@@ -51,6 +52,8 @@
                 "rclone/checksum/Illumina_annotation_missing/Illumina_annotation_missing.match.txt",
                 "rclone/checksum/Illumina_annotation_missing/Illumina_annotation_missing.missing_on_dst.txt",
                 "rclone/checksum/Illumina_annotation_sha_only",
+                "rclone/checksum/Illumina_annotation_sha_only/Illumina_annotation_sha_only.combined.txt",
+                "rclone/checksum/Illumina_annotation_sha_only/Illumina_annotation_sha_only.differ.txt",
                 "rclone/checksum/Illumina_annotation_sha_only/Illumina_annotation_sha_only.exit_code.txt",
                 "rclone/copy",
                 "rclone/copy/Illumina_annotation_incorrect-rclone-copy.log",
@@ -60,10 +63,11 @@
                 "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
                 "multiqc_rclone_check.txt:md5,4b2a6990836593f69e8e81a82c3daf42",
                 "multiqc_rclone_checksum_md5.txt:md5,cf92203df21f04ddf8315fc606812e0b",
+                "multiqc_rclone_checksum_sha.txt:md5,8d38305a4ad03c7ea18aa9827d34a396",
                 "multiqc_samplesheet.txt:md5,bbfc817ff43c49cde14a2b33f46b5ae5"
             ]
         ],
-        "timestamp": "2026-07-28T21:45:08.268780076",
+        "timestamp": "2026-07-30T20:44:41.242808343",
         "meta": {
             "nf-test": "0.9.5",
             "nextflow": "26.04.1"
@@ -95,6 +99,7 @@
                 "multiqc/multiqc_data/multiqc_data.json",
                 "multiqc/multiqc_data/multiqc_rclone_check.txt",
                 "multiqc/multiqc_data/multiqc_rclone_checksum_md5.txt",
+                "multiqc/multiqc_data/multiqc_rclone_checksum_sha.txt",
                 "multiqc/multiqc_data/multiqc_samplesheet.txt",
                 "multiqc/multiqc_data/multiqc_software_versions.txt",
                 "multiqc/multiqc_data/multiqc_sources.txt",
@@ -124,6 +129,8 @@
                 "rclone/checksum/Illumina_annotation_missing/Illumina_annotation_missing.match.txt",
                 "rclone/checksum/Illumina_annotation_missing/Illumina_annotation_missing.missing_on_dst.txt",
                 "rclone/checksum/Illumina_annotation_sha_only",
+                "rclone/checksum/Illumina_annotation_sha_only/Illumina_annotation_sha_only.combined.txt",
+                "rclone/checksum/Illumina_annotation_sha_only/Illumina_annotation_sha_only.differ.txt",
                 "rclone/checksum/Illumina_annotation_sha_only/Illumina_annotation_sha_only.exit_code.txt",
                 "rclone/copy",
                 "rclone/copy/Illumina_annotation_incorrect-rclone-copy.log",
@@ -134,10 +141,11 @@
                 "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
                 "multiqc_rclone_check.txt:md5,c8f13c10aa4f0e4b356c5c08a9ae7ee9",
                 "multiqc_rclone_checksum_md5.txt:md5,cf92203df21f04ddf8315fc606812e0b",
+                "multiqc_rclone_checksum_sha.txt:md5,8d38305a4ad03c7ea18aa9827d34a396",
                 "multiqc_samplesheet.txt:md5,bbfc817ff43c49cde14a2b33f46b5ae5"
             ]
         ],
-        "timestamp": "2026-07-22T22:01:06.286788462",
+        "timestamp": "2026-07-30T20:44:11.000298059",
         "meta": {
             "nf-test": "0.9.5",
             "nextflow": "26.04.1"

diff --git a/tests/main_full.nf.test.snap b/tests/main_full.nf.test.snap
@@ -25,6 +25,7 @@
                 "multiqc/multiqc_data/multiqc_data.json",
                 "multiqc/multiqc_data/multiqc_rclone_check.txt",
                 "multiqc/multiqc_data/multiqc_rclone_checksum_md5.txt",
+                "multiqc/multiqc_data/multiqc_rclone_checksum_sha.txt",
                 "multiqc/multiqc_data/multiqc_samplesheet.txt",
                 "multiqc/multiqc_data/multiqc_software_versions.txt",
                 "multiqc/multiqc_data/multiqc_sources.txt",
@@ -39,7 +40,6 @@
                 "rclone/checksum",
                 "rclone/checksum/demultiplex",
                 "rclone/checksum/demultiplex/demultiplex.combined.txt",
-                "rclone/checksum/demultiplex/demultiplex.exit_code.txt",
                 "rclone/checksum/demultiplex/demultiplex.match.txt",
                 "rclone/copy",
                 "rclone/copy/demultiplex-rclone-copy.log"
@@ -48,10 +48,11 @@
                 "multiqc_citations.txt:md5,4c806e63a283ec1b7e78cdae3a923d4f",
                 "multiqc_rclone_check.txt:md5,03a73f087a286ec6580aada2a5db2e7c",
                 "multiqc_rclone_checksum_md5.txt:md5,d7c7dd71a9ff75955dd0e508d1ad9968",
+                "multiqc_rclone_checksum_sha.txt:md5,03a73f087a286ec6580aada2a5db2e7c",
                 "multiqc_samplesheet.txt:md5,00788a52d1a014c12ac4ed554b0b44ca"
             ]
         ],
-        "timestamp": "2026-07-22T22:01:43.699965019",
+        "timestamp": "2026-07-30T20:46:20.306063412",
         "meta": {
             "nf-test": "0.9.5",
             "nextflow": "26.04.1"

diff --git a/workflows/datasync.nf b/workflows/datasync.nf
@@ -38,6 +38,15 @@ workflow DATASYNC {
     ch_samplesheet = ch_samplesheet.multiMap {
         meta, input_path, output_path, md5, sha ->
 
+            if (sha && input_path.contains('://')) {
+                if (params.download) {
+                    log.warn("The `--download` parameter is enabled. RCLONE_CHECKSUM will download remote files. Make sure this is what you want, as it may incur substantial cloud costs !")
+                } else {
+                    log.error("A SHA checksum file was provided, but `--download` is not enabled. Rclone cannot verify SHA checksums for remote files without downloading them. Enable `--download` to proceed.")
+                    System.exit(1)
+                }
+            }
+
             def source = file(input_path)
 
             def source_uri = source.toUriString()