[Zip_Column_Content] Resolve overwriting of identical filenames (#1009)

* no overwritting in zip

* simplification improvements

* docs version

* adding file translation tracking

* adding header

* output docs

* wf docs

Author: awh082834

docs/assets/tables/all_outputs.tsv

@@ -379,6 +379,7 @@ fastqc_raw2_html	File	An HTML file that provides a graphical visualization of ra
 fastqc_version	String	Version of fastqc software used	Freyja_FASTQ, TheiaCoV_Illumina_PE, TheiaCoV_Illumina_SE, TheiaEuk_Illumina_PE, TheiaMeta_Illumina_PE, TheiaProk_Illumina_PE, TheiaProk_Illumina_SE
 fetch_srr_accession_analysis_date	String	The date the fetch_srr_accession analysis was run.	Fetch_SRR_Accession
 fetch_srr_accession_version	String	The version of the fetch_srr_accession workflow.	Fetch_SRR_Accession
+file_translations	File	A tracking file to use for referencing original filenames and paths when identical files are indexed.	Zip_Column_Content
 filtered_contigs_metrics	File	File containing metrics of contigs filtered	TheiaEuk_Illumina_PE, TheiaEuk_ONT, TheiaProk_Illumina_PE, TheiaProk_Illumina_SE, TheiaProk_ONT
 flu_A_315675_resistance	String	resistance mutations to A_315675	TheiaCoV_FASTA, TheiaCoV_Illumina_PE, TheiaCoV_ONT
 flu_amantadine_resistance	String	resistance mutations to amantadine	TheiaCoV_FASTA, TheiaCoV_Illumina_PE, TheiaCoV_ONT

docs/assets/tables/all_workflows.tsv

@@ -48,4 +48,4 @@ Name	Description	Applicable Kingdom	Workflow Level	Workflow Type	Command-line Co
 [**Transfer_Column_Content**](../workflows/data_export/transfer_column_content.md)	Transfer contents of a specified Terra data table column for many samples ("entities") to a GCP storage bucket location	[Any taxa](../../workflows_overview/workflows_kingdom.md#any-taxa)	Set-level	[Exporting Data from Terra](../../workflows_overview/workflows_type.md#exporting-data-from-terra)	Yes	v1.3.0	[Transfer_Column_Content_PHB](https://dockstore.org/workflows/github.com/theiagen/public_health_bioinformatics/Transfer_Column_Content_PHB:main?tab=info)
 [**Usher**](../workflows/phylogenetic_placement/usher.md)	Use UShER to rapidly and accurately place your samples on any existing phylogenetic tree	Monkeypox virus, SARS-CoV-2, [Viral](../../workflows_overview/workflows_kingdom.md#viral)	Sample-level, Set-level	[Phylogenetic Placement](../../workflows_overview/workflows_type.md#phylogenetic-placement)	Yes	v2.1.0	[Usher_PHB](https://dockstore.org/workflows/github.com/theiagen/public_health_bioinformatics/Usher_PHB:main?tab=info)
 [**VADR_Update**](../workflows/genomic_characterization/vadr_update.md)	Update VADR assignments	HAV, Influenza, Monkeypox virus, RSV-A, RSV-B, SARS-CoV-2, [Viral](../../workflows_overview/workflows_kingdom.md#viral), WNV	Sample-level	[Genomic Characterization](../../workflows_overview/workflows_type.md#genomic-characterization)	Yes	v4.0.0	[VADR_Update_PHB](https://dockstore.org/workflows/github.com/theiagen/public_health_bioinformatics/VADR_Update_PHB:main?tab=info)
-[**Zip_Column_Content**](../workflows/data_export/zip_column_content.md)	Zip contents of a specified Terra data table column for many samples ("entities")	[Any taxa](../../workflows_overview/workflows_kingdom.md#any-taxa)	Set-level	[Exporting Data from Terra](../../workflows_overview/workflows_type.md#exporting-data-from-terra)	Yes	v2.1.0	[Zip_Column_Content_PHB](https://dockstore.org/workflows/github.com/theiagen/public_health_bioinformatics/Zip_Column_Content_PHB:main?tab=info)
+[**Zip_Column_Content**](../workflows/data_export/zip_column_content.md)	Zip contents of a specified Terra data table column for many samples ("entities")	[Any taxa](../../workflows_overview/workflows_kingdom.md#any-taxa)	Set-level	[Exporting Data from Terra](../../workflows_overview/workflows_type.md#exporting-data-from-terra)	Yes	vX.X.X	[Zip_Column_Content_PHB](https://dockstore.org/workflows/github.com/theiagen/public_health_bioinformatics/Zip_Column_Content_PHB:main?tab=info)

docs/workflows/data_export/zip_column_content.md

@@ -10,6 +10,8 @@ title: Zip_Column_Content
 
 This workflow will create a zip file containing all of the items from a given column in a Terra Data Table. This is useful when you want to share a collection of result files.
 
+If a column contains files that do not have unique filenames then an index will be appended to identical filenames. Original file paths and names are preserved and referenced within the `file_translations.tsv` output. 
+
 ### Inputs
 
 This workflow runs on the _set_ level.

tasks/utilities/file_handling/task_zip_files.wdl

@@ -16,17 +16,45 @@ task zip_files {
   command <<<
     file_array=(~{sep=' ' files_to_zip})
     mkdir ~{zipped_file_name}
+    echo -e "origin_path\tnew_path" > file_translations.tsv
 
-    # move files oto a single directory before zipping
-    for index in ${!file_array[@]}; do
-      file=${file_array[$index]}
-      mv ${file} ~{zipped_file_name}
+    # move files into a single directory before zipping
+    for file in "${file_array[@]}"; do
+    
+      echo "DEBUG: Pulling $file"
+      if [ -f "$file" ]; then
+        echo "DEBUG: $file exists"
+        filename=$(basename "$file") # Extract the filename (e.g., test.tsv)
+        dest="~{zipped_file_name}/$filename"
+
+        # Counter is always set to 1 so that if there are 
+        # other duplicated filenames they will be counted as well.
+        counter=1
+
+        echo "DEBUG: Checking for $file in $dest"
+        # Check for duplicate files in the destination
+        while [ -e "$dest" ]; do 
+          echo "DEBUG: Duplicate filename found, adding a file index for differentiation."
+          dest="~{zipped_file_name}/${filename%.*}_${counter}.${filename##*.}"
+          echo "DEBUG: New filename ${filename%.*}_${counter}.${filename##*.}"
+          ((counter++))
+        done
+
+        # Move the file to the destination with the new name
+        # If loop is not entered, filename will remain unchanged. 
+        mv "$file" "$dest"
+        echo -e "$file\t$dest" >> file_translations.tsv
+
+      else
+        echo "File not found: $file"
+      fi
     done
     
     zip -r ~{zipped_file_name}.zip ~{zipped_file_name}
    >>>
   output {
     File zipped_files = "~{zipped_file_name}.zip"
+    File file_translations = "file_translations.tsv"
   }
   runtime {
     docker: "~{docker_image}"

workflows/utilities/file_handling/wf_zip_column.wdl

@@ -22,5 +22,6 @@ workflow zip_column_content {
     String zip_column_content_analysis_date = version_capture.date
 
     File zipped_files = zip_files.zipped_files
+    File file_translations = zip_files.file_translations
   }
 }