From 4cd3a0b59d33ea9d6918f2ab1b900722008707a9 Mon Sep 17 00:00:00 2001
From: Adam Taylor <adam.taylor@sagebase.org>
Date: Tue, 24 Oct 2023 08:59:48 +0000
Subject: [PATCH 1/3] Update filename regex

---
 HTAN.model.csv | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/HTAN.model.csv b/HTAN.model.csv
index 3d32f5cc..d3d07998 100644
--- a/HTAN.model.csv
+++ b/HTAN.model.csv
@@ -5,7 +5,7 @@ Sequencing,Module for next generation sequencing assays,,,,FALSE,Assay,,,
 Component,"Category of metadata (e.g. Diagnosis, Biospecimen, scRNA-seq Level 1, etc.); provide the same one for all items/rows.",,,,TRUE,,,https://w3id.org/biolink/vocab/category,
 Patient,HTAN patient,,"Component, HTAN Participant ID",,FALSE,Individual Organism,"Demographics, Family History, Exposure, Follow Up, Diagnosis, Therapy, Molecular Test",,
 File,A type of Information Content Entity specific to OS,,,,FALSE,Information Content Entity,,https://w3id.org/biolink/vocab/DataFile,
-Filename,Name of a file,,,,TRUE,,,,regex search ^.+\/\S*$
+Filename,Name of a file,,,,TRUE,,,,regex search ^(([a-zA-Z0-9\_\-\.\+\(\'\)\ ]+/)[a-zA-Z0-9\_\-\.\+\(\'\)]+)$
 File Format,"Format of a file (e.g. txt, csv, fastq, bam, etc.)","hdf5, bedgraph, idx, idat, bam, bai, excel, powerpoint, tif, tiff, OME-TIFF, png, doc, pdf, fasta, fastq, sam, vcf, bcf, maf, bed, chp, cel, sif, tsv, csv, txt, plink, bigwig, wiggle, gct, bgzip, zip, seg, html, mov, hyperlink, svs, md, flagstat, gtf, raw, msf, rmd, bed narrowPeak, bed broadPeak, bed gappedPeak, avi, pzfx, fig, xml, tar, R script, abf, bpm, dat, jpg, locs, Sentrix descriptor file, Python script, sav, gzip, sdf, RData, hic, ab1, 7z, gff3, json, sqlite, svg, sra, recal, tranches, mtx, tagAlign, dup, DICOM, czi, mex, cloupe, am, cell am, mpg, m, mzML,scn, dcc, rcc, pkc",,,TRUE,,,,
 Checksum,MD5 checksum of the BAM file,,,,TRUE,Information Content Entity,,,
 HTAN Data File ID,Self-identifier for this data file - HTAN ID of this file HTAN ID SOP (eg HTANx_yyy_zzz),,,,TRUE,File,,https://docs.google.com/document/d/1podtPP8L1UNvVxx9_c_szlDcU1f8n7bige6XA_GoRVM/edit?usp=sharing,

From 5e5e7abde584b7ea9eb38047b2c7cee9962aaa8f Mon Sep 17 00:00:00 2001
From: Adam Taylor <adam.taylor@sagebase.org>
Date: Tue, 24 Oct 2023 09:09:31 +0000
Subject: [PATCH 2/3] Refine regex

---
 HTAN.model.csv | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/HTAN.model.csv b/HTAN.model.csv
index d3d07998..d2f6bd3d 100644
--- a/HTAN.model.csv
+++ b/HTAN.model.csv
@@ -5,7 +5,7 @@ Sequencing,Module for next generation sequencing assays,,,,FALSE,Assay,,,
 Component,"Category of metadata (e.g. Diagnosis, Biospecimen, scRNA-seq Level 1, etc.); provide the same one for all items/rows.",,,,TRUE,,,https://w3id.org/biolink/vocab/category,
 Patient,HTAN patient,,"Component, HTAN Participant ID",,FALSE,Individual Organism,"Demographics, Family History, Exposure, Follow Up, Diagnosis, Therapy, Molecular Test",,
 File,A type of Information Content Entity specific to OS,,,,FALSE,Information Content Entity,,https://w3id.org/biolink/vocab/DataFile,
-Filename,Name of a file,,,,TRUE,,,,regex search ^(([a-zA-Z0-9\_\-\.\+\(\'\)\ ]+/)[a-zA-Z0-9\_\-\.\+\(\'\)]+)$
+Filename,Name of a file,,,,TRUE,,,,regex search ^(([a-zA-Z0-9\_\-\.\+\(\'\)\ ]+\/)+[a-zA-Z0-9\_\-\.\+\(\'\)]+)$
 File Format,"Format of a file (e.g. txt, csv, fastq, bam, etc.)","hdf5, bedgraph, idx, idat, bam, bai, excel, powerpoint, tif, tiff, OME-TIFF, png, doc, pdf, fasta, fastq, sam, vcf, bcf, maf, bed, chp, cel, sif, tsv, csv, txt, plink, bigwig, wiggle, gct, bgzip, zip, seg, html, mov, hyperlink, svs, md, flagstat, gtf, raw, msf, rmd, bed narrowPeak, bed broadPeak, bed gappedPeak, avi, pzfx, fig, xml, tar, R script, abf, bpm, dat, jpg, locs, Sentrix descriptor file, Python script, sav, gzip, sdf, RData, hic, ab1, 7z, gff3, json, sqlite, svg, sra, recal, tranches, mtx, tagAlign, dup, DICOM, czi, mex, cloupe, am, cell am, mpg, m, mzML,scn, dcc, rcc, pkc",,,TRUE,,,,
 Checksum,MD5 checksum of the BAM file,,,,TRUE,Information Content Entity,,,
 HTAN Data File ID,Self-identifier for this data file - HTAN ID of this file HTAN ID SOP (eg HTANx_yyy_zzz),,,,TRUE,File,,https://docs.google.com/document/d/1podtPP8L1UNvVxx9_c_szlDcU1f8n7bige6XA_GoRVM/edit?usp=sharing,

From 9fe1809be0c08f12f2c95f5a95758a1c5ab00a63 Mon Sep 17 00:00:00 2001
From: adamjtaylor <adamjtaylor@users.noreply.github.com>
Date: Tue, 24 Oct 2023 09:20:33 +0000
Subject: [PATCH 3/3] GitHub Action: convert *.model.csv to *.model.jsonld

---
 HTAN.model.jsonld | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/HTAN.model.jsonld b/HTAN.model.jsonld
index 7d89472d..b653ebb5 100644
--- a/HTAN.model.jsonld
+++ b/HTAN.model.jsonld
@@ -2476,7 +2476,7 @@
             "sms:displayName": "Filename",
             "sms:required": "sms:true",
             "sms:validationRules": [
-                "regex search ^.+\\/\\S*$"
+                "regex search ^(([a-zA-Z0-9\\_\\-\\.\\+\\(\\'\\)\\ ]+\\/)+[a-zA-Z0-9\\_\\-\\.\\+\\(\\'\\)]+)$"
             ]
         },
         {