WIP update bcftbx CLI applicances to use refactored libraries

bcftbx/cli/analyse_solid_run.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 #
 #     analyse_solid_run.py: analyse and report on SOLiD sequencer runs
-#     Copyright (C) University of Manchester 2011-2021 Peter Briggs
+#     Copyright (C) University of Manchester 2011-2026 Peter Briggs
 
 """
 Provides functionality for analysing a SOLiD run, to verify and report data
@@ -22,10 +22,10 @@
 import argparse
 import logging
 logging.basicConfig(format="%(levelname)s %(message)s")
-from ..SolidData import SolidRun
-from ..SolidData import list_run_directories
-from ..Experiment import Experiment
-from ..Md5sum import md5sum
+from ..platforms.solid.data import RunDir
+from ..platforms.solid.data import list_run_directories
+from ..platforms.solid.experiment import Experiment
+from ..utils.checksums import md5sum
 from ..Spreadsheet import Spreadsheet
 from .. import get_version
 
@@ -41,7 +41,7 @@ def report_run(solid_runs,report_paths=False):
     etc.
 
     Arguments:
-      solid_runs: a list or tuple of SolidRun objects to report.
+      solid_runs: a list or tuple of 'RunDir' objects to report.
       report_paths: if True then also report the full paths for the
         primary data files for each library.
     """
@@ -104,7 +104,7 @@ def write_spreadsheet(solid_runs,spreadsheet):
     input.
 
     Arguments:
-      solid_runs: a list or tuple of SolidRun objects to report.
+      solid_runs: a list or tuple of 'RunDir' objects to report.
       spreadsheet: the name of the XLS-format spreadsheet to write
         the data
     """
@@ -234,13 +234,13 @@ def write_spreadsheet(solid_runs,spreadsheet):
 def suggest_analysis_layout(solid_runs):
     """Generate a bash script to build the analysis directory scheme
 
-    Given a set of SolidRuns, print a set of script commands for running the
+    Given a set of 'RunDir' instances, print a set of script commands for running the
     build_analysis_dir.py program to create and populate the analysis directories.
 
     The script can be edited before being executed by the user.
 
     Arguments:
-      solid_runs: a list of SolidRun objects.
+      solid_runs: a list of RunDir objects.
     """
     print("#!/bin/sh\n#\n# Script commands to build analysis directory structure")
     for run in solid_runs:
@@ -267,7 +267,7 @@ def suggest_analysis_layout(solid_runs):
 def suggest_rsync_command(solid_runs):
     """Generate a bash script to rsync data to another location
 
-    Given a set of SolidRuns, print a set of script commands for running rsync
+    Given a set of 'RunDir' instances, print a set of script commands for running rsync
     to copy the data directories to another location.
 
     The script should be edited before being executed by the user.
@@ -285,7 +285,7 @@ def suggest_rsync_command(solid_runs):
 def verify_runs(solid_dirs):
     """Do basic verification checks on SOLiD run directories
 
-    For each SOLiD run directory, create a SolidRun object and check for the
+    For each SOLiD run directory, create a 'RunDir' object and check for the
     expected sample and library directories, and that primary data files
     (csfasta and qual) have been assigned and exist.
 
@@ -303,7 +303,7 @@ def verify_runs(solid_dirs):
     for solid_dir in solid_dirs:
         # Initialise
         run_status = 0
-        run = SolidRun(solid_dir)
+        run = RunDir(solid_dir)
         if not run.verify():
             run_status = 1
         print("%s:" % run.run_name,)
@@ -341,7 +341,7 @@ def copy_data(solid_runs,library_defns):
     The files are copied to the current directory.
 
     Arguments:
-      solid_runs: list of populated SolidRun objects
+      solid_runs: list of populated 'RunDir' objects
       library_defns: list of library definition strings (see above
         for syntax/format)
     """
@@ -388,7 +388,7 @@ def gzip_data(solid_runs,library_defns):
     Gzipped copies of the files are made in the current directory.
 
     Arguments:
-      solid_runs: list of populated SolidRun objects
+      solid_runs: list of populated 'RunDir' objects
       library_defns: list of library definition strings (see above
         for syntax/format)
     """
@@ -449,7 +449,7 @@ def md5_checksums(solid_runs,library_defns):
     Md5 sums are calculated and printed for each matching primary data file.
 
     Arguments:
-      solid_runs: list of populated SolidRun objects
+      solid_runs: list of populated 'RunDir' objects
       library_defns: list of library definition strings (see above
         for syntax/format)
     """
@@ -609,7 +609,7 @@ def main():
     # Get the run information
     solid_runs = []
     for solid_dir in solid_dirs:
-        run = SolidRun(solid_dir)
+        run = RunDir(solid_dir)
         if not run:
             logging.error("Error extracting run data for %s" % solid_dir)
             sys.exit(1)

bcftbx/cli/best_exons.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 #
 #     best_exons.py: pick 'best' exons for gene symbols and average data
-#     Copyright (C) University of Manchester 2013-2021 Peter Briggs
+#     Copyright (C) University of Manchester 2013-2026 Peter Briggs
 #
 ########################################################################
 
@@ -54,15 +54,14 @@
 # Imports
 #########################################################################
 
-from builtins import str
 import sys
 import os
 import io
 import argparse
 import logging
 from operator import attrgetter
-from bcftbx.TabFile import TabFileIterator
-from bcftbx.utils import OrderedDictionary
+from bcftbx.io.tabular import TabFileIterator
+from bcftbx.utils.collections import OrderedDictionary
 from .. import get_version
 
 ########################################################################

bcftbx/cli/extract_reads.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 #
 #     extract_reads.py: write random subsets of read records from input files
-#     Copyright (C) University of Manchester 2012-2021 Peter Briggs
+#     Copyright (C) University of Manchester 2012-2026 Peter Briggs
 #
 
 """
@@ -19,18 +19,14 @@
 # Imports
 #######################################################################
 
-from builtins import str
-from builtins import range
 import sys
 import os
 import io
-import gzip
 import argparse
 import random
-import re
-from ..ngsutils import getreads
-from ..ngsutils import getreads_subset
-from ..ngsutils import getreads_regex
+from ..utils.ngs import getreads
+from ..utils.ngs import getreads_subset
+from ..utils.ngs import getreads_regex
 from .. import get_version
 
 #######################################################################

bcftbx/cli/fastq_strand.py

@@ -1,15 +1,13 @@
 #!/usr/bin/env python
 #
 #     fastq_strand.py: determine strandedness of fastq pair using STAR
-#     Copyright (C) University of Manchester 2017-2022 Peter Briggs
+#     Copyright (C) University of Manchester 2017-2026 Peter Briggs
 #
 
 #######################################################################
 # Imports
 #######################################################################
 
-from builtins import str
-from builtins import range
 import sys
 import os
 import io
@@ -19,9 +17,9 @@
 import subprocess
 import shutil
 import logging
-from ..utils import find_program
-from ..ngsutils import getreads
-from ..ngsutils import getreads_subset
+from ..utils.os import find_program
+from ..utils.ngs import getreads
+from ..utils.ngs import getreads_subset
 from ..qc.report import strip_ngs_extensions
 from .. import get_version
 

bcftbx/cli/make_macs_xls.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 #
 #     make_macs_xls.py: Convert MACS output file to XLS spreadsheet
-#     Copyright (C) University of Manchester 2011-2021 Peter Briggs
+#     Copyright (C) University of Manchester 2011-2026 Peter Briggs
 #
 
 
@@ -23,7 +23,6 @@
 # Imports
 #######################################################################
 
-from builtins import str
 import os
 import io
 import sys
@@ -32,7 +31,7 @@
 # Configure logging output
 logging.basicConfig(format="[%(levelname)s] %(message)s")
 
-from ..TabFile import TabFile
+from ..io.tabular import TabFile
 from ..Spreadsheet import Workbook
 from .. import get_version
 
@@ -84,7 +83,7 @@ def main():
             header.append(line.strip())
         else:
             # Data
-            data.append(tabdata=line.strip())
+            data.append(line.strip())
     fp.close()
 
     # Temporarily remove first line
@@ -114,19 +113,19 @@ def main():
     data.sort(lambda line: line['-10*log10(pvalue)'],reverse=True)
 
     # Restore first line
-    data.insert(0,tabdata=header_line)
+    data.insert(0, header_line)
 
     # Insert "order" column
-    data.appendColumn("order")
+    data.append_column("order")
     # Perhaps confusingly must also insert initial value "#order"
     data[0]['order'] = "#order"
     for i in range(1,len(data)):
         data[i]['order'] = i
     # Reorder columns to put it at the start
-    data = data.reorderColumns(['order','chr','start','end','length','summit','tags',
-                                '-10*log10(pvalue)','fold_enrichment','FDR(%)'])
+    data = data.reorder(['order','chr','start','end','length','summit','tags',
+                         '-10*log10(pvalue)','fold_enrichment','FDR(%)'])
 
-    # Legnds text
+    # Legends text
     legends_text = """order\tSorting order Pvalue and FE
 chr\tChromosome location of binding region
 start\tStart coordinate of binding region

bcftbx/cli/md5checker.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 #
 #     md5checker.py: check files and directories using md5 checksums
-#     Copyright (C) University of Manchester 2012-2022 Peter Briggs
+#     Copyright (C) University of Manchester 2012-2026 Peter Briggs
 #
 
 """
@@ -20,9 +20,9 @@
 import io
 import argparse
 import logging
-from ..Md5sum import md5sum
-from ..Md5sum import Md5CheckReporter
-from ..Md5sum import Md5Checker
+from ..utils.checksums import md5sum
+from ..utils.checksums import Md5CheckReporter
+from ..utils.checksums import Md5Checker
 from .. import get_version
 
 #######################################################################

bcftbx/cli/prep_sample_sheet.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 #
 #     prep_sample_sheet.py: prepare sample sheet file for Illumina sequencers
-#     Copyright (C) University of Manchester 2012-2025 Peter Briggs
+#     Copyright (C) University of Manchester 2012-2026 Peter Briggs
 
 """
 Prepare sample sheet file for Illumina sequencers.
@@ -18,8 +18,8 @@
 import pydoc
 from ..platforms.illumina.samplesheet import SampleSheet
 from ..platforms.illumina.samplesheet import SampleSheetPredictor
-from ..utils import parse_lanes
-from ..utils import parse_named_lanes
+from ..utils.parser import parse_lanes
+from ..utils.parser import parse_named_lanes
 from .. import get_version
 
 #######################################################################

bcftbx/cli/split_fastq.py

@@ -1,23 +1,22 @@
 #!/usr/bin/env python
 #
 #     split_fastq.py: split Fastq by lane
-#     Copyright (C) University of Manchester 2018-2025 Peter Briggs
+#     Copyright (C) University of Manchester 2018-2026 Peter Briggs
 #
 
 #######################################################################
 # Imports
 #######################################################################
 
-from builtins import str
 import argparse
 import re
 import os
 import io
 from ..platforms.illumina.utils import IlluminaFastq
 from ..platforms.illumina.exceptions import IlluminaError
-from ..utils import parse_lanes
-from ..ngsutils import getreads
-from ..ngsutils import getreads_regex
+from ..utils.parser import parse_lanes
+from ..utils.ngs import getreads
+from ..utils.ngs import getreads_regex
 from .. import get_version
 
 #######################################################################