changeset 6:7521d865e770 draft default tip

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/splitfasta commit 49709e680f90372edd2b8a2715d95e5949641afa

--- a/splitFasta.xml	Mon Sep 21 15:40:14 2020 +0000
+++ b/splitFasta.xml	Tue Jan 14 21:52:36 2025 +0000
@@ -1,4 +1,4 @@
-<tool id="rbc_splitfasta" name="Split Fasta" version="0.4.0">
+<tool id="rbc_splitfasta" name="Split Fasta" version="0.5.0" profile="23.0">
     <description>files into a collection</description>
     <requirements>
         <requirement type="package" version="1.76">biopython</requirement>
@@ -6,9 +6,9 @@
     <command detect_errors="aggressive">
     <![CDATA[
         #if $splitmode.splitmode_select == "each":
-            python $__tool_directory__/split_fasta.py '$inputFile'
+            python $__tool_directory__/split_fasta.py --records '$inputFile.metadata.sequences' --limit "\${GALAXY_FILE_LIMIT:-0}" '$inputFile'
         #else if $splitmode.splitmode_select == "chunks":
-            python $__tool_directory__/split_fasta.py '$inputFile' $splitmode.num_chunks
+            python $__tool_directory__/split_fasta.py --records '$inputFile.metadata.sequences' --limit "\${GALAXY_FILE_LIMIT:-0}" --num-chunks '$splitmode.num_chunks' '$inputFile'
         #end if
     ]]></command>
     <inputs>

--- a/split_fasta.py	Mon Sep 21 15:40:14 2020 +0000
+++ b/split_fasta.py	Tue Jan 14 21:52:36 2025 +0000
@@ -1,50 +1,61 @@
 #!/usr/bin/env python
 
+import argparse
 import os
-import sys
+
 from Bio import SeqIO
 
-num_chunks = 0
-if len(sys.argv) == 3:
-    num_chunks = int(sys.argv[2])
-    input_filename = sys.argv[1]
-elif len(sys.argv) == 2:
-    input_filename = sys.argv[1]
-else:
-    exit("Usage: split_fasta.py <input_filename> [<num_chunks>]")
+parser = argparse.ArgumentParser()
+parser.add_argument("--records", type=int, default=None)
+parser.add_argument("--limit", type=int, default=None)
+parser.add_argument("--num-chunks", type=int, default=0)
+parser.add_argument("input_file")
+args = parser.parse_args()
 
-os.mkdir('splits')
+input_filename = args.input_file
+num_chunks = args.num_chunks
+record_count = args.records
+record_limit = args.limit
 
-if num_chunks != 0:
-    # if splitting into chunks we need to count how many records are in the
-    # input file
+os.mkdir("splits")
+
+if record_limit and num_chunks > record_limit:
+    exit(f"ERROR: Requested number of chunks {num_chunks} exceeds limit {record_limit}")
+
+if not record_count and (num_chunks != 0 or record_limit):
+    # if no count is provided and if splitting into chunks or a limit is set, we need to count how many records are in the input file
     record_count = 0
     with open(input_filename) as input_file:
         for line in input_file:
-            if line.lstrip().startswith('>'):
+            if line.lstrip().startswith(">"):
                 record_count += 1
 
+if num_chunks != 0:
     records_per_chunk = round(float(record_count) / num_chunks)
 
+if record_limit and record_count > record_limit:
+    exit(f"ERROR: Number of sequences {record_count} exceeds limit {record_limit}")
+
 count = 1
 with open(input_filename) as input_file:
 
     chunk_record_count = 0  # how many lines have we written to the output file
     records = []
-    for record in SeqIO.parse(input_file, 'fasta'):
+    for record in SeqIO.parse(input_file, "fasta"):
         records.append(record)
-        if num_chunks == 0 or (count < num_chunks and
-           len(records) >= records_per_chunk):
+        if num_chunks == 0 or (
+            count < num_chunks and len(records) >= records_per_chunk
+        ):
             if num_chunks == 0:
-                output_filename = os.path.join('splits', record.id)
+                output_filename = os.path.join("splits", record.id)
             else:
-                output_filename = os.path.join('splits', 'part{}'.format(count))
-            SeqIO.write(records, output_filename, 'fasta')
+                output_filename = os.path.join("splits", "part{}".format(count))
+            SeqIO.write(records, output_filename, "fasta")
             count += 1
             records = []
 
     if records:
         # this only applies for the mode where input file is
         # split into chunks
-        output_filename = os.path.join('splits', 'part{}'.format(count))
-        SeqIO.write(records, output_filename, 'fasta')
+        output_filename = os.path.join("splits", "part{}".format(count))
+        SeqIO.write(records, output_filename, "fasta")