From b47307323d5c273e8c6c2fb585a2e85da2ac3982 Mon Sep 17 00:00:00 2001
From: "Richard C. Burhans" <rico@bx.psu.edu>
Date: Tue, 10 Sep 2024 15:48:32 -0400
Subject: [PATCH 1/2] adding a new test, small updates

---
 tools/ncbi_egapx/macros.xml     |  2 +-
 tools/ncbi_egapx/ncbi_egapx.xml | 55 ++++++++++++++++++++-------------
 2 files changed, 34 insertions(+), 23 deletions(-)

diff --git a/tools/ncbi_egapx/macros.xml b/tools/ncbi_egapx/macros.xml
index e65c0d2..1878963 100644
--- a/tools/ncbi_egapx/macros.xml
+++ b/tools/ncbi_egapx/macros.xml
@@ -5,7 +5,7 @@
         </requirements>
     </xml>
     <token name="@TOOL_VERSION@">0.2-alpha</token>
-    <token name="@VERSION_SUFFIX@">1</token>
+    <token name="@VERSION_SUFFIX@">2</token>
     <token name="@PROFILE@">22.05</token>
     <xml name="edam_ontology">
         <edam_operations>
diff --git a/tools/ncbi_egapx/ncbi_egapx.xml b/tools/ncbi_egapx/ncbi_egapx.xml
index 00c03d7..df6fb6d 100644
--- a/tools/ncbi_egapx/ncbi_egapx.xml
+++ b/tools/ncbi_egapx/ncbi_egapx.xml
@@ -9,44 +9,44 @@
     #if str($cond_input_style.input_style) == "history":
       #set yamlconfig = $yamlin
     #else:
-      #set yamlconfig = 'egapx.yaml'
-      rm -rf 'egapx.yaml' &&
-      touch 'egapx.yaml' &&
-      echo '# yaml generated by ncbi_egapx.xml' >> egapx.yaml &&
-      echo 'taxid:  $taxid' >> egapx.yaml &&
+      #set yamlconfig = "egapx.yaml"
+      rm -rf '$yamlconfig' &&
+      touch '$yamlconfig' &&
+      echo '# yaml generated by ncbi_egapx.xml' >> '$yamlconfig' &&
+      echo 'taxid:  $taxid' >> '$yamlconfig' &&
       #if str($reference_genome.genome_type_select) == "indexed":
-        echo 'genome:  $reference_genome.genome.fields.path' >> 'egapx.yaml' &&
+        echo 'genome:  $reference_genome.genome.fields.path' >> '$yamlconfig' &&
       #elif str($reference_genome.genome_type_select) == "history"
-        echo 'genome:  $reference_genome.genome'  >> 'egapx.yaml' &&
+        echo 'genome:  $reference_genome.genome'  >> '$yamlconfig' &&
       #else:
-        echo 'genome:  $reference_genome.uri' >> 'egapx.yaml' &&
+        echo 'genome:  $reference_genome.uri'  >> '$yamlconfig' &&
       #end if
-      echo 'reads:' >> 'egapx.yaml' &&
+      echo 'reads:' >> '$yamlconfig' &&
       #if str($condrnaseq.rna_type_select) == "history":
         #for $r in $rnaseq:
-          echo '  - $r'  >> 'egapx.yaml' &&
+          echo '  - $r'  >> '$yamlconfig' &&
         #end for
       #else:
         #set rs = $rnaseq.split()
         #set rsplit = [x.strip() for x in $rs]
         #for $r in $rsplit:
-          echo '  - $r'  >> 'egapx.yaml' &&
+          echo '  - $r'  >> '$yamlconfig' &&
         #end for
       #end if
       #if len($xtra.strip()) > 0:
-        #set lxtra = $xtra.split('\n')
+        #set lxtra = $xtra.split("\n")
         #for row in $lxtra:
-            echo '$row' >> 'egapx.yaml' &&
+            echo '$row' >> '$yamlconfig' &&
         #end for
       #end if
-      echo '' >> 'egapx.yaml' &&
+      echo '' >> '$yamlconfig' &&
       echo "Calculated contents of egapx yaml" &&
-      cat 'egapx.yaml' &&
+      cat '$yamlconfig' &&
     #end if
     source /galaxy/env.bash &&
     echo \${PATH} &&
     ln -s /galaxy/egapx/egapx_config &&
-    python3 /galaxy/egapx/ui/egapx.py '$yamlconfig' -e galaxy  -o 'egapx_out'
+    python3 /galaxy/egapx/ui/egapx.py '$yamlconfig' -e galaxy -o 'egapx_out'
     ]]></command>
     <inputs>
     <conditional name="cond_input_style">
@@ -61,14 +61,14 @@
       <when value="fillform">
           <param name="taxid" type="text" optional="false" label="NCBI Taxon ID" help="Used to identify the HMM model files needed"/>
           <conditional name="reference_genome">
-            <param name="genome_type_select" type="select" label="Reference genome source for mapping supplied RNA-seq reads" 
+            <param name="genome_type_select" type="select" label="Reference genome source for mapping supplied RNA-seq reads"
               help="Select a built in, history or remote URI for the reference genome fasta">
                 <option value="indexed">Use a Galaxy server built-in genome</option>
                 <option value="history" selected="True">Use a genome fasta file from the current history</option>
                 <option value="uri">Provide a remote web link URI ("https://...") pointing at the required genome reference fasta file</option>
             </param>
             <when value="indexed">
-                <param name="genome" type="select" optional="false" label="Select a built in reference genome or custom genome" 
+                <param name="genome" type="select" optional="true" label="Select a built in reference genome or custom genome"
                   help="If not listed, add a custom genome or use a reference genome from the history">
                     <options from_data_table="all_fasta">
                         <validator message="No genomes are available " type="no_options"/>
@@ -76,10 +76,10 @@
                 </param>
             </when>
             <when value="history">
-                <param name="genome" type="data" format="fasta" optional="false" label="Select the reference genome fasta from the current history"/>
+                <param name="genome" type="data" optional="true" format="fasta" label="Select the reference genome fasta from the current history"/>
             </when>
             <when value="uri">
-                <param name="uri" type="text" label="URI pointing to the reference genome fasta file" help=""/>
+                <param name="uri" type="text" optional="false" label="URI pointing to the reference genome fasta file" help=""/>
             </when>
           </conditional>
           <conditional name="condrnaseq">
@@ -88,7 +88,7 @@
                 <option value="history">Select one or more RNA-seq fastq datasets from the current history</option>
             </param>
             <when value="history">
-              <param name="rnaseq" type="data" format="fastqsanger, fastqsanger.gz" optional="false" multiple="true" 
+              <param name="rnaseq" type="data" format="fastqsanger, fastqsanger.gz" optional="false" multiple="true"
                 label="Select multiple RNA-seq fastqsanger inputs from the current history" help="All selected rna-seq fastqsanger will be added to the yaml for egapx configuration"/>
             </when>
             <when value="list">
@@ -98,7 +98,7 @@
                 </param>
             </when>
           </conditional>
-          <param name="xtra" type="text" area="true" optional="true" label="Additional yaml to append to the egapx.yaml configuration"
+          <param name="xtra" type="text" area="true" label="Additional yaml to append to the egapx.yaml configuration"
                     help="Not normally needed but useful for testing additional configuration elements">
             <sanitizer invalid_char="">
                   <valid initial="string.printable">
@@ -115,9 +115,20 @@
     </outputs>
     <tests>
       <test expect_test_failure="true">
+        <param name="input_style" value="history"/>
         <param name="yamlin" value="input.yaml"/>
         <output_collection name="egapx_out" type="list" count="8"/>
       </test>
+      <test expect_test_failure="true">
+        <param name="input_style" value="fillform"/>
+        <param name="taxid" value="6954"/>
+        <param name="genome_type_select" value="uri"/>
+        <param name="uri" value="https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/020/809/275/GCF_020809275.1_ASM2080927v1/GCF_020809275.1_ASM2080927v1_genomic.fna.gz"/>
+        <param name="rna_type_select" value="list"/>
+        <param name="rnaseq" value="https://ftp.ncbi.nlm.nih.gov/genomes/TOOLS/EGAP/sample_data/Dermatophagoides_farinae_small/SRR8506572.1 https://ftp.ncbi.nlm.nih.gov/genomes/TOOLS/EGAP/sample_data/Dermatophagoides_farinae_small/SRR8506572.2 https://ftp.ncbi.nlm.nih.gov/genomes/TOOLS/EGAP/sample_data/Dermatophagoides_farinae_small/SRR9005248.1 https://ftp.ncbi.nlm.nih.gov/genomes/TOOLS/EGAP/sample_data/Dermatophagoides_farinae_small/SRR9005248.2"/>
+        <param name="xtra" value="proteins: []&#10;hmm: https://ftp.ncbi.nlm.nih.gov/genomes/TOOLS/EGAP/gnomon/hmm_parameters/6956.params&#10;tasks:&#10;  star_wnode:&#10;    star_wnode: -cpus-per-worker 4"/>
+        <output_collection name="egapx_out" type="list" count="8"/>
+      </test>
     </tests>
   <help><![CDATA[
 Galaxy tool wrapping the Eukaryotic Genome Annotation Pipeline (EGAPx)

From dcd3fdbbf9ede0ce96965b77dec7ba0460608f28 Mon Sep 17 00:00:00 2001
From: "Richard C. Burhans" <rico@bx.psu.edu>
Date: Tue, 10 Sep 2024 16:58:42 -0400
Subject: [PATCH 2/2] updated to support all_fasta data table

---
 tools/ncbi_egapx/ncbi_egapx.xml                |  2 +-
 .../ncbi_egapx/tool-data/all_fasta.loc.sample  | 18 ++++++++++++++++++
 .../ncbi_egapx/tool_data_table_conf.xml.sample |  7 +++++++
 3 files changed, 26 insertions(+), 1 deletion(-)
 create mode 100644 tools/ncbi_egapx/tool-data/all_fasta.loc.sample
 create mode 100644 tools/ncbi_egapx/tool_data_table_conf.xml.sample

diff --git a/tools/ncbi_egapx/ncbi_egapx.xml b/tools/ncbi_egapx/ncbi_egapx.xml
index df6fb6d..3a93675 100644
--- a/tools/ncbi_egapx/ncbi_egapx.xml
+++ b/tools/ncbi_egapx/ncbi_egapx.xml
@@ -76,7 +76,7 @@
                 </param>
             </when>
             <when value="history">
-                <param name="genome" type="data" optional="true" format="fasta" label="Select the reference genome fasta from the current history"/>
+                <param name="genome" type="data" format="fasta" optional="false" label="Select the reference genome fasta from the current history"/>
             </when>
             <when value="uri">
                 <param name="uri" type="text" optional="false" label="URI pointing to the reference genome fasta file" help=""/>
diff --git a/tools/ncbi_egapx/tool-data/all_fasta.loc.sample b/tools/ncbi_egapx/tool-data/all_fasta.loc.sample
new file mode 100644
index 0000000..1a5a28d
--- /dev/null
+++ b/tools/ncbi_egapx/tool-data/all_fasta.loc.sample
@@ -0,0 +1,18 @@
+#This file lists the locations and dbkeys of all the fasta files
+#under the "genome" directory (a directory that contains a directory
+#for each build). The script extract_fasta.py will generate the file
+#all_fasta.loc. This file has the format (white space characters are
+#TAB characters):
+#
+#<unique_build_id>	<dbkey>	<display_name>	<file_path>
+#
+#So, all_fasta.loc could look something like this:
+#
+#apiMel3	apiMel3	Honeybee (Apis mellifera): apiMel3	/path/to/genome/apiMel3/apiMel3.fa
+#hg19canon	hg19	Human (Homo sapiens): hg19 Canonical	/path/to/genome/hg19/hg19canon.fa
+#hg19full	hg19	Human (Homo sapiens): hg19 Full	/path/to/genome/hg19/hg19full.fa
+#
+#Your all_fasta.loc file should contain an entry for each individual
+#fasta file. So there will be multiple fasta files for each build,
+#such as with hg19 above.
+#
diff --git a/tools/ncbi_egapx/tool_data_table_conf.xml.sample b/tools/ncbi_egapx/tool_data_table_conf.xml.sample
new file mode 100644
index 0000000..d5c59b9
--- /dev/null
+++ b/tools/ncbi_egapx/tool_data_table_conf.xml.sample
@@ -0,0 +1,7 @@
+<tables>
+    <!-- Locations of all fasta files under genome directory -->
+    <table name="all_fasta" comment_char="#">
+        <columns>value, dbkey, name, path</columns>
+        <file path="tool-data/all_fasta.loc" />
+    </table>
+</tables>