Add robust header validation and logging to submit_study.py.

bin/submit_study.py

@@ -80,12 +80,21 @@ def submit_xml(
         "Content-Type": "application/xml",
         "Accept": "application/xml",
     }
-    resp = requests.post(
-        url, data=xml_bytes,
-        headers=headers, auth=auth, timeout=120,
-    )
-    resp.raise_for_status()
-    return ET.fromstring(resp.content)
+    try:
+        resp = requests.post(
+            url, data=xml_bytes,
+            headers=headers, auth=auth, timeout=120,
+        )
+        resp.raise_for_status()
+    except requests.exceptions.RequestException as e:
+        logger.error(f"Network error: Could not reach ENA server. Details: {e}")
+        sys.exit(1)
+
+    try:
+        return ET.fromstring(resp.content)
+    except ET.ParseError:
+        logger.error("The ENA server returned an invalid response (not XML).")
+        sys.exit(1)
 
 
 # -----------------------------------------------------------
@@ -251,6 +260,24 @@ def load_and_validate_input_file(
         raises ValueError.
     """
     ext = Path(filepath).suffix.lower()
+
+    if ext in [".csv", ".tsv"]:
+        delimiter = "," if ext == ".csv" else "\t"
+        with open(filepath, "r", encoding="utf-8") as f:
+            header_line = f.readline()
+            if not header_line:
+                raise ValueError(f"File {filepath} is empty.")
+
+            # Clean up headers (strip quotes and whitespace)
+            headers = [h.strip().replace('"', '') for h in header_line.split(delimiter)]
+            missing = [f for f in _REQUIRED_FIELDS if f not in headers]
+
+            if missing:
+                # Use the logger you set up earlier!
+                logger.error(f"Missing required columns in {ext} file: {', '.join(missing)}")
+                raise ValueError(f"Missing columns: {', '.join(missing)}")
+    # --------------------------------------------------------
+
     if ext == ".json":
         records = extract_records_from_json(filepath)
     elif ext == ".csv":
@@ -619,13 +646,17 @@ def main(
     write_results(results, output)
 
     logger.info("=" * 60)
-    logger.info("SUBMISSION SUMMARY")
+    logger.info("SUBMISSION SUMMARY - COMPLETED SUCCESSFULLY")
+    logger.info("Environment: %s", env_label)
+    logger.info("Total Studies Processed: %d", len(studies))
     logger.info("  Submitted (ADD): %d", len(results["submitted"]))
+
     for submission in results["submitted"]:
-        alias = submission["alias"]
-        accession = submission["accession"]
-        external_accession = submission["external_accession"]
-        logger.info(f"    {alias} -> {accession} ({external_accession})")
+        alias = submission.get("alias", "Unknown")
+        accession = submission.get("accession", "Pending")
+        # Using .get() here makes it robust against missing dictionary keys
+        logger.info(f"    {alias} -> {accession}")
+
     logger.info("=" * 60)
 
 

main.nf

@@ -38,7 +38,6 @@ workflow NFCORE_SEQSUBMIT {
     //
     // WORKFLOW: Run pipeline
     //
-    // Depending on the input type (mags/bins or metagenomic_assemblies), one or the another workflow will be triggered
     if (params.mode == "mags" || params.mode == "bins") {
         GENOMESUBMIT (
             samplesheet,
@@ -77,12 +76,35 @@ workflow NFCORE_SEQSUBMIT {
             params.webincli_mode
         )
         ch_multiqc_report = ASSEMBLYSUBMIT.out.multiqc_report
-    }
-
+    } else if (params.mode == "reads") {
+        GENOMESUBMIT (
+            samplesheet,
+            params.multiqc_config,
+            params.multiqc_logo,
+            params.multiqc_methods_description,
+            params.outdir,
+            params.mode,
+            params.submission_study,
+            params.study_metadata,
+            params.trna_limit,
+            params.rrna_limit,
+            params.checkm2_db,
+            params.checkm2_db_download_id,
+            params.cat_db,
+            params.cat_db_download_id,
+            params.centre_name,
+            params.upload_tpa,
+            params.test_upload,
+            params.webin_cli_version,
+            params.webincli_mode
+        )
+        ch_multiqc_report = GENOMESUBMIT.out.multiqc_report
+    }                                                          // ← closes the if/else chain
 
     emit:
-    multiqc_report = ch_multiqc_report // channel: /path/to/multiqc_report.html
+    multiqc_report = ch_multiqc_report
 }
+
 /*
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
     RUN MAIN WORKFLOW

subworkflows/local/utils_nfcore_seqsubmit_pipeline/main.nf

@@ -55,30 +55,9 @@ workflow PIPELINE_INITIALISATION {
     // Validate parameters and generate parameter summary to stdout
     //
 
-    def before_text = ""
-    def after_text = ""
-    before_text = """
--\033[2m----------------------------------------------------\033[0m-
-                                        \033[0;32m,--.\033[0;30m/\033[0;32m,-.\033[0m
-\033[0;34m        ___     __   __   __   ___     \033[0;32m/,-._.--~\'\033[0m
-\033[0;34m  |\\ | |__  __ /  ` /  \\ |__) |__         \033[0;33m}  {\033[0m
-\033[0;34m  | \\| |       \\__, \\__/ |  \\ |___     \033[0;32m\\`-._,-`-,\033[0m
-                                        \033[0;32m`._,._,\'\033[0m
-\033[0;35m  nf-core/seqsubmit ${workflow.manifest.version}\033[0m
--\033[2m----------------------------------------------------\033[0m-
-"""
-    after_text = """${workflow.manifest.doi ? "\n* The pipeline\n" : ""}${workflow.manifest.doi.tokenize(",").collect { doi -> "    https://doi.org/${doi.trim().replace('https://doi.org/','')}"}.join("\n")}${workflow.manifest.doi ? "\n" : ""}
-* The nf-core framework
-    https://doi.org/10.1038/s41587-020-0439-x
-
-* Software dependencies
-    https://github.com/nf-core/seqsubmit/blob/master/CITATIONS.md
-"""
-    if (monochrome_logs) {
-        before_text = before_text.replaceAll(/\033\[[0-9;]*m/, '')
-    }
-
-    command = "nextflow run ${workflow.manifest.name} -profile <docker/singularity/.../institute> --input samplesheet.csv --outdir <OUTDIR>"
+    def before_text = "--- nf-core/seqsubmit ---"
+    def after_text  = "-------------------------"
+    def command     = "nextflow run nf-core/seqsubmit --input samplesheet.csv --outdir <OUTDIR> --mode <MODE>"
 
     UTILS_NFSCHEMA_PLUGIN (
         workflow,
@@ -92,32 +71,24 @@ workflow PIPELINE_INITIALISATION {
         command
     )
 
-    //
-    // Check config provided to the pipeline
-    //
     UTILS_NFCORE_PIPELINE (
         nextflow_cli_args
     )
 
-    //
-    // Create channel from input file provided through params.input
-    //
-
     if ( mode == "mags" || mode == "bins" ) {
-        ch_samplesheet = channel
-            .fromList(samplesheetToList(input, "${projectDir}/assets/schema_input_genome.json"))
+        ch_samplesheet = channel.fromList(samplesheetToList(input, "${projectDir}/assets/schema_input_genome.json"))
     } else if ( mode == "metagenomic_assemblies" ) {
-        ch_samplesheet = channel
-            .fromList(samplesheetToList(input, "${projectDir}/assets/schema_input_assembly.json"))
+        ch_samplesheet = channel.fromList(samplesheetToList(input, "${projectDir}/assets/schema_input_assembly.json"))
+    } else if ( mode == "reads" ) {
+        ch_samplesheet = channel.fromList(samplesheetToList(input, "${projectDir}/assets/schema_input_genome.json"))
     } else {
-        error("No input was found. Please, point to the location of your samplesheet using --input_genome or --input_assembly")
+        error("No input found")
     }
 
     emit:
     samplesheet = ch_samplesheet
     versions    = ch_versions
 }
-
 /*
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
     SUBWORKFLOW FOR PIPELINE COMPLETION