Update v0.10.6

.readthedocs.yaml

@@ -8,7 +8,7 @@ version: 2
 build:
   os: ubuntu-22.04
   tools:
-    python: "3.11"
+    python: "3.12"
     # You can also specify other tool versions:
     # nodejs: "20"
     # rust: "1.70"
@@ -24,12 +24,12 @@ sphinx:
 
 # Optionally build your docs in additional formats such as PDF and ePub
 # formats:
-#    - pdf
-#    - epub
+#   - pdf
+#   - epub
 
 # Optional but recommended, declare the Python requirements required
 # to build your documentation
 # See https://docs.readthedocs.io/en/stable/guides/reproducible-builds.html
-# python:
-#    install:
-#    - requirements: docs/requirements.txt
+python:
+  install:
+    - requirements: docs/requirements.txt

ChangeLog.md

@@ -1,5 +1,8 @@
 # Changelog
 
+## 0.10.6 (2023-12-26)
+- Added warning messages in `churros` when there are the same raws in `samplelist.txt`.
+
 ## 0.10.5 (2023-12-21)
 - Bug fix in `gen_samplelist.sh`
 

Dockerfiles/Churros/churros

@@ -7,7 +7,7 @@ import argparse
 import pathlib
 import pandas as pd
 
-__version__ = '0.10.4'
+__version__ = '0.10.6'
 
 def print_and_exec_shell(command):
     print (command)
@@ -27,6 +27,38 @@ def check_dir(dir):
         print ("Error: " + dir + " does not exist.")
         exit()
 
+def check_fastq_in_samplelist(samplelist):
+    df = pd.read_csv(samplelist, sep="\t", header=None)
+    df.fillna("", inplace=True)
+    for index, row in df.iterrows():
+        if (len(row)<2 or row[1] == ""):
+            print ("Error: specify fastq file in " + samplelist + ".")
+            exit()
+
+        fq1 = row[1]
+        for fastq in fq1.split(","):
+            check_file(fastq)
+
+        if (len(row)>2): # for paired-end
+            fq2 = row[2]
+            for fastq in fq2.split(","):
+                check_file(fastq)
+
+def check_duplicates(file_path):
+    df = pd.read_csv(file_path, sep='\t', header=None, names=['Col1', 'Col2'])
+
+    duplicates_col1 = df['Col1'].duplicated(keep=False)
+    duplicates_col2 = df['Col2'].duplicated(keep=False)
+
+    if duplicates_col1.any():
+        print("Warning: Duplicate found in column 1")
+        print(df[duplicates_col1]['Col1'].value_counts())
+
+    if duplicates_col2.any():
+        print("Warning: Duplicate found in column 2")
+        print(df[duplicates_col2]['Col2'].value_counts())
+
+
 def get_mapfile_postfix(mapparam):
     post = mapparam.replace(' ', '')
     return post
@@ -146,6 +178,7 @@ def is_exist_input(samplepairlist):
     else:
         return True
 
+
 def exec_churros(args):
     samplelist = args.samplelist
     samplepairlist = args.samplepairlist
@@ -165,6 +198,10 @@ def exec_churros(args):
     samplelist = pathlib.Path(samplelist).resolve()
     samplepairlist = pathlib.Path(samplepairlist).resolve()
 
+    # check samplelist
+    check_fastq_in_samplelist(samplelist)
+    check_duplicates(samplelist)
+
     mapparam = args.mapparam
     post = get_mapfile_postfix(mapparam)
     gt = Ddir + '/genometable.txt'

Dockerfiles/build.sh

@@ -1,4 +1,4 @@
-tag=0.10.5
+tag=0.10.6
 docker build -f Dockerfile.$tag -t rnakato/churros:$tag . #--no-cache
 #docker save -o churros-$tag.tar rnakato/churros:$tag
 #singularity build -F churros.$tag.sif docker-archive://churros-$tag.tar

docs/requirements.txt

@@ -0,0 +1 @@
+sphinx_rtd_theme