chore: initialize pixi

.gitattributes

@@ -1 +1,3 @@
 /src/ccbr_tools/templates/mkdocs-fnl/docs/custom-overrides/** linguist-vendored true
+# SCM syntax highlighting & preventing 3-way merges
+pixi.lock merge=binary linguist-language=YAML linguist-generated=true -diff

.gitignore

@@ -175,3 +175,6 @@ cython_debug/
 #  and can be added to the global gitignore or merged into this file.  For a more nuclear
 #  option (not recommended) you can uncomment the following to ignore the entire idea folder.
 #.idea/
+# pixi environments
+.pixi/*
+!.pixi/config.toml

.pre-commit-config.yaml

@@ -5,7 +5,8 @@ exclude: |
       ^.*.svg|
       ^assets/|
       ^src/ccbr_tools/templates/mkdocs-fnl/docs/custom-overrides/|
-      ^tests/data/
+      ^tests/data/|
+      ^pixi.lock
    )
 ci:
   skip: [detect-absolute-paths]

scripts/extract_value_from_json.py

@@ -1,6 +1,6 @@
 #!/usr/bin/env python
-import json
 import argparse
+import json
 
 parser = argparse.ArgumentParser(description="extract value for key from JSON")
 parser.add_argument("-j", dest="json", required=True, help="input JSON file")

scripts/extract_value_from_yaml.py

@@ -1,7 +1,8 @@
 #!/usr/bin/env python
-import yaml
 import argparse
 
+import yaml
+
 parser = argparse.ArgumentParser(description="extract value for key from YAML")
 parser.add_argument("-y", dest="yaml", required=True, help="input YAML file")
 parser.add_argument(

scripts/filter_bam_by_readids.py

@@ -1,7 +1,8 @@
 #!/usr/bin/env python
-import pysam
 import argparse
 
+import pysam
+
 parser = argparse.ArgumentParser(description="Filter BAM by readids")
 parser.add_argument(
     "--inputBAM", dest="inputBAM", type=str, required=True, help="input BAM file"

scripts/filter_fastq_by_readids_highmem.py

@@ -1,8 +1,9 @@
 #!/usr/bin/env python3
-import HTSeq
 import argparse
 import os
 
+import HTSeq
+
 
 def get_sname(s):
     """Return the sample name from the input path."""

scripts/filter_fastq_by_readids_highmem_pe.py

@@ -1,8 +1,9 @@
 #!/usr/bin/env python
-import HTSeq
 import argparse
 import os
 
+import HTSeq
+
 
 def get_sname(s):
     """Return the sample name from the input path."""

src/ccbr_tools/GSEA/deg2gs.py

@@ -20,15 +20,16 @@
 __version__ = "1.1"
 __copyright__ = "No copyright protection, can be used freely"
 
-import sys
+import argparse
+import datetime
 import os
 import re
-import datetime
+import sys
+from argparse import RawTextHelpFormatter
+
 import pandas as pd
 
-import argparse
-from argparse import RawTextHelpFormatter
-from .ncbr_huse import send_update, err_out
+from .ncbr_huse import err_out, send_update
 
 
 ####################################
@@ -190,9 +191,7 @@ def main():
         log.write(" ".join(sys.argv) + "\n")
         log.write("deg2gs.py version " + __version__ + "\n")
         log.write(
-            "Exporting genes to {}, n={}, p={}, q={}, ".format(
-                outfile.name, nhits, pvalue, qvalue
-            )
+            f"Exporting genes to {outfile.name}, n={nhits}, p={pvalue}, q={qvalue}, "
         )
         log.flush()
 
@@ -214,9 +213,7 @@ def main():
     #
     if df.shape[1] != len(in_cols):
         errMsg = (
-            '\nYour input file does not match the expected format "{}".\n'.format(
-                fformat
-            )
+            f'\nYour input file does not match the expected format "{fformat}".\n'
             + "Please check the file or the selected format and try again\n."
         )
         if keepLog:
@@ -229,7 +226,7 @@ def main():
 
     # split the ensemblID|Gene if necessary
     if fformat == "topTable":  # and method == 'gsea':
-        df["gene"] = [re.sub("^.*\|", "", i) for i in df.index.values.tolist()]
+        df["gene"] = [re.sub(r"^.*\|", "", i) for i in df.index.values.tolist()]
 
     # Filter the df to the p-values, FDR, and number of hits specified
     df = filter_by_p(df, nhits, pvalue, qvalue)
@@ -253,11 +250,11 @@ def main():
     # Close out the log file
     #
     if keepLog:
-        send_update("deg2gs.py successfully completed.  {} written.".format(fname), log)
+        send_update(f"deg2gs.py successfully completed.  {fname} written.", log)
         send_update(str(datetime.datetime.now()) + "\n", log)
         log.close()
     else:
-        print("deg2gs.py successfully completed.  {} written.".format(fname))
+        print(f"deg2gs.py successfully completed.  {fname} written.")
 
 
 if __name__ == "__main__":

src/ccbr_tools/GSEA/multitext2excel.py

@@ -18,23 +18,22 @@
 __copyright__ = "No copyright protection, can be used freely"
 
 # import csv
-import sys
-import os
-import re
-import datetime
-import pandas as pd
-import glob
-
 # import scipy
 # import numpy
-
 import argparse
+import datetime
+import glob
+import os
+import re
+import sys
 from argparse import RawTextHelpFormatter
+
+import pandas as pd
+
 from .ncbr_huse import (
     send_update,
 )
 
-
 ####################################
 #
 # Functions
@@ -150,11 +149,7 @@ def main():
         sheet_name = re.sub(indir + "/", "", filename).split(splitter)[0]
         if firstsplitter != "":
             sheet_name = sheet_name.split(firstsplitter)[1]
-        print(
-            "Writing data from input file: {} to output tab: {}".format(
-                filename, sheet_name
-            )
-        )
+        print(f"Writing data from input file: {filename} to output tab: {sheet_name}")
 
         # Read in the data
         df = pd.read_csv(filename, sep=delimiter, header=0, encoding="unicode_escape")
@@ -169,7 +164,7 @@ def main():
     # Close out the log file
     #
     send_update(
-        "multitext2excel.py successfully completed.  {} written.".format(outfile.name),
+        f"multitext2excel.py successfully completed.  {outfile.name} written.",
         log,
     )
     send_update(str(datetime.datetime.now()) + "\n", log)

src/ccbr_tools/GSEA/ncbr_huse.py

@@ -10,10 +10,10 @@
 __version__ = "1.0.0"
 __copyright__ = "none"
 
-import sys
 import os
 import re
 import subprocess
+import sys
 
 try:
     import MySQLdb
@@ -139,27 +139,19 @@ def pause_for_input(txt, contkey="y", quitkey="q", log=None):
             err_out("User elected to quit.  Exiting...\n", log)
 
         # if none, just return the input
-        if contkey is None:
-            result = answer
-
-        # if there is a contkey, then be sure it is correctly typed
-        elif answer == contkey:
+        if contkey is None or answer == contkey:
             result = answer
 
         else:
             # give them additional help and increment the answer count
-            reminder = "Note: only {} to continue and {} to quit are valid options.\nPlease try again.\n".format(
-                contkey, quitkey
-            )
+            reminder = f"Note: only {contkey} to continue and {quitkey} to quit are valid options.\nPlease try again.\n"
             if answer_cnt == 0:
                 txt = "\n" + txt + "\n" + reminder
 
             # Otherwise 3 strikes and exit from the loop
             if answer_cnt == 2:
                 err_out(
-                    "User failed to continue ({}) or quit ({}) three times in a row.  Exiting...".format(
-                        contkey, quitkey
-                    ),
+                    f"User failed to continue ({contkey}) or quit ({quitkey}) three times in a row.  Exiting...",
                     log,
                 )
 

src/ccbr_tools/__main__.py

@@ -2,20 +2,19 @@
 Entry point for CCBR Tools
 """
 
-import click
 import cffconvert.cli.cli
+import click
 
 from .pkg_util import (
+    CustomClickGroup,
     get_project_scripts,
     get_version,
     print_citation,
     repo_base,
-    CustomClickGroup,
 )
 from .send_email import send_email_msg
-from .templates import use_quarto_ext, get_quarto_extensions
 from .software import install as install_software
-
+from .templates import get_quarto_extensions, use_quarto_ext
 
 all_scripts = "All installed tools:\n" + "\n".join(
     [f"  {cmd}" for cmd in get_project_scripts()]
@@ -37,7 +36,6 @@ def cli():
 
     https://ccbr.github.io/Tools/
     """
-    pass
 
 
 @click.command()

src/ccbr_tools/gb2gtf.py

@@ -9,8 +9,9 @@
 # Usage:python gb2gtf.py sequence.gb  > sequence.gtf
 
 import sys
-from Bio import SeqIO
+
 import Bio
+from Bio import SeqIO
 
 
 def main():

src/ccbr_tools/github.py

@@ -10,6 +10,7 @@
 """
 
 import warnings
+
 from .pkg_util import get_url_json
 
 
@@ -64,7 +65,7 @@ def get_user_info(user_login):
     try:
         user_info = get_url_json(url)
     except ConnectionError as e:
-        warnings.warn(f"Could not retrieve user info for {user_login}. {str(e)}")
+        warnings.warn(f"Could not retrieve user info for {user_login}. {e!s}")
     return user_info
 
 

src/ccbr_tools/homologfinder/hf.py

@@ -25,13 +25,14 @@
 
 import argparse
 import importlib.resources
-import pandas as pd
 import sys
 
+import pandas as pd
+
 
 def exit_w_msg(message):
     """Gracefully exit with proper message"""
-    print("{} : EXITING!!".format(__file__))
+    print(f"{__file__} : EXITING!!")
     print(message)
     sys.exit()
 
@@ -42,7 +43,6 @@ def check_help(parser):
         print(__doc__)
         parser.print_help()
         parser.exit()
-    return
 
 
 def collect_args():
@@ -54,7 +54,7 @@ def collect_args():
 
     # add version
     parser.add_argument(
-        "-v", "--version", action="version", version="%(prog)s {}".format(__version__)
+        "-v", "--version", action="version", version=f"%(prog)s {__version__}"
     )
 
     # add joblist

src/ccbr_tools/hooks/__main__.py

@@ -3,9 +3,10 @@
 """
 
 import click
+
 from ..pkg_util import (
-    get_version,
     CustomClickGroup,
+    get_version,
 )
 from .detect_absolute_paths import detect_absolute_paths
 from .sync_nextflow_version import sync_nextflow_version
@@ -25,7 +26,6 @@ def cli():
 
     https://ccbr.github.io/Tools/hooks
     """
-    pass
 
 
 cli.add_command(detect_absolute_paths)

src/ccbr_tools/intersect.py

@@ -7,7 +7,6 @@
     intersect file1 file2
 """
 
-from __future__ import print_function
 import sys