Merge pull request #151 from CCBR/use-tools-pkg

Use tools package

pyproject.toml

@@ -36,6 +36,7 @@ classifiers = [
 requires-python = ">=3.11"
 dependencies = [
     "argparse",
+    "ccbr_tools@git+https://github.com/CCBR/Tools",
     "Click >= 8.1.3",
     "PySimpleGui < 5",
     "snakemake >= 7.32, < 8",

src/renee/__main__.py

@@ -12,7 +12,6 @@
 """
 
 # Python standard library
-from __future__ import print_function
 from shutil import copy
 import json
 import os
@@ -22,22 +21,22 @@
 
 # 3rd party imports from pypi
 import argparse
-
-# local imports
-from .cache import get_sif_cache_dir
-from .run import run
-from .dryrun import dryrun
-from .gui import launch_gui
-from .conditions import fatal
-from .util import (
+from ccbr_tools.pipeline.util import (
     get_hpcname,
     get_tmp_dir,
     get_genomes_list,
-    get_version,
     check_python_version,
     _cp_r_safe_,
-    orchestrate,
 )
+from ccbr_tools.pipeline.cache import get_sif_cache_dir
+
+# local imports
+from .run import run
+from .dryrun import dryrun
+from .gui import launch_gui
+from .conditions import fatal
+from .util import renee_base, get_version
+from .orchestrate import orchestrate
 
 # Pipeline Metadata and globals
 RENEE_PATH = os.path.dirname(
@@ -398,9 +397,11 @@ def build(sub_args):
                 )
             )
     elif sub_args.mode == "slurm":
-        jobid = (
-            open(os.path.join(sub_args.output, "logfiles", "bjobid.log")).read().strip()
-        )
+        with open(
+            os.path.join(sub_args.output, "logfiles", "bjobid.log"), "r"
+        ) as infile:
+            jobid = infile.read().strip()
+
         if int(masterjob.returncode) == 0:
             print("Successfully submitted master job: ", end="")
         else:
@@ -770,7 +771,12 @@ def parsed_arguments(name, description):
         {2}{3}Prebuilt genome+annotation combos:{4}
           {5}
         """.format(
-            "renee", __version__, c.bold, c.url, c.end, list(get_genomes_list())
+            "renee",
+            __version__,
+            c.bold,
+            c.url,
+            c.end,
+            list(get_genomes_list(repo_base=renee_base)),
         )
     )
 
@@ -817,7 +823,9 @@ def parsed_arguments(name, description):
         "--genome",
         required=True,
         type=lambda option: str(
-            genome_options(subparser_run, option, get_genomes_list())
+            genome_options(
+                subparser_run, option, get_genomes_list(repo_base=renee_base)
+            )
         ),
         help=argparse.SUPPRESS,
     )
@@ -1126,7 +1134,12 @@ def parsed_arguments(name, description):
         {2}{3}Prebuilt genome+annotation combos:{4}
           {5}
         """.format(
-            "renee", __version__, c.bold, c.url, c.end, list(get_genomes_list())
+            "renee",
+            __version__,
+            c.bold,
+            c.url,
+            c.end,
+            list(get_genomes_list(repo_base=renee_base)),
         )
     )
 

src/renee/gui.py

@@ -7,17 +7,16 @@
 import sys
 from tkinter import Tk
 
-from .util import (
+from ccbr_tools.pipeline.util import (
     get_genomes_dict,
     get_tmp_dir,
-    get_shared_resources_dir,
-    renee_base,
-    get_version,
-    get_singularity_cachedir,
     get_hpcname,
 )
-from .cache import get_sif_cache_dir
-from .run import run_in_context
+from ccbr_tools.pipeline.cache import get_sif_cache_dir, get_singularity_cachedir
+from ccbr_tools.shell import exec_in_context
+
+from .util import get_version, renee_base, get_shared_resources_dir
+from .run import run
 
 # TODO: get rid of  all the global variables
 # TODO: let's use a tmp dir and put these files there instead. see for inspiration:https://github.com/CCBR/RENEE/blob/16d13dca1d5f0f43c7dfda379efb882a67635d17/tests/test_cache.py#L14-L28
@@ -27,7 +26,7 @@
 
 def launch_gui(sub_args, debug=True):
     # get drop down genome+annotation options
-    jsons = get_genomes_dict(error_on_warnings=True)
+    jsons = get_genomes_dict(repo_base=renee_base, error_on_warnings=True)
     genome_annotation_combinations = list(jsons.keys())
     genome_annotation_combinations.sort()
     if debug:
@@ -191,7 +190,7 @@ def launch_gui(sub_args, debug=True):
                 threads=2,
             )
             # execute dry run and capture stdout/stderr
-            allout = run_in_context(run_args)
+            allout = exec_in_context(run, run_args)
             sg.popup_scrolled(
                 allout,
                 title="Dryrun:STDOUT/STDERR",
@@ -211,7 +210,7 @@ def launch_gui(sub_args, debug=True):
             if ch == "Yes":
                 run_args.dry_run = False
                 # execute live run
-                allout = run_in_context(run_args)
+                allout = exec_in_context(run, run_args)
                 sg.popup_scrolled(
                     allout,
                     title="Dryrun:STDOUT/STDERR",

src/renee/initialize.py

@@ -2,9 +2,7 @@
 import re
 import sys
 
-from .util import (
-    _cp_r_safe_,
-)
+from ccbr_tools.pipeline.util import _cp_r_safe_, _sym_safe_
 
 
 def initialize(sub_args, repo_path, output_path):
@@ -51,94 +49,3 @@ def initialize(sub_args, repo_path, output_path):
     inputs = _sym_safe_(input_data=sub_args.input, target=output_path)
 
     return inputs
-
-
-def _sym_safe_(input_data, target):
-    """Creates re-named symlinks for each FastQ file provided
-    as input. If a symlink already exists, it will not try to create a new symlink.
-    If relative source PATH is provided, it will be converted to an absolute PATH.
-    @param input_data <list[<str>]>:
-        List of input files to symlink to target location
-    @param target <str>:
-        Target path to copy templates and required resources
-    @return input_fastqs list[<str>]:
-        List of renamed input FastQs
-    """
-    input_fastqs = []  # store renamed fastq file names
-    for file in input_data:
-        filename = os.path.basename(file)
-        renamed = os.path.join(target, rename(filename))
-        input_fastqs.append(renamed)
-
-        if not os.path.exists(renamed):
-            # Create a symlink if it does not already exist
-            # Follow source symlinks to resolve any binding issues
-            os.symlink(os.path.abspath(os.path.realpath(file)), renamed)
-
-    return input_fastqs
-
-
-def rename(filename):
-    """Dynamically renames FastQ file to have one of the following extensions: *.R1.fastq.gz, *.R2.fastq.gz
-    To automatically rename the fastq files, a few assumptions are made. If the extension of the
-    FastQ file cannot be inferred, an exception is raised telling the user to fix the filename
-    of the fastq files.
-    @param filename <str>:
-        Original name of file to be renamed
-    @return filename <str>:
-        A renamed FastQ filename
-    """
-    # Covers common extensions from SF, SRA, EBI, TCGA, and external sequencing providers
-    # key = regex to match string and value = how it will be renamed
-    extensions = {
-        # Matches: _R[12]_fastq.gz, _R[12].fastq.gz, _R[12]_fq.gz, etc.
-        ".R1.f(ast)?q.gz$": ".R1.fastq.gz",
-        ".R2.f(ast)?q.gz$": ".R2.fastq.gz",
-        # Matches: _R[12]_001_fastq_gz, _R[12].001.fastq.gz, _R[12]_001.fq.gz, etc.
-        # Capture lane information as named group
-        ".R1.(?P<lane>...).f(ast)?q.gz$": ".R1.fastq.gz",
-        ".R2.(?P<lane>...).f(ast)?q.gz$": ".R2.fastq.gz",
-        # Matches: _[12].fastq.gz, _[12].fq.gz, _[12]_fastq_gz, etc.
-        "_1.f(ast)?q.gz$": ".R1.fastq.gz",
-        "_2.f(ast)?q.gz$": ".R2.fastq.gz",
-    }
-
-    if filename.endswith(".R1.fastq.gz") or filename.endswith(".R2.fastq.gz"):
-        # Filename is already in the correct format
-        return filename
-
-    converted = False
-    for regex, new_ext in extensions.items():
-        matched = re.search(regex, filename)
-        if matched:
-            # regex matches with a pattern in extensions
-            converted = True
-            # Try to get substring for named group lane, retain this in new file extension
-            # Come back to this later, I am not sure if this is necessary
-            # That string maybe static (i.e. always the same)
-            # https://support.illumina.com/help/BaseSpace_OLH_009008/Content/Source/Informatics/BS/NamingConvention_FASTQ-files-swBS.htm#
-            try:
-                new_ext = "_{}{}".format(matched.group("lane"), new_ext)
-            except IndexError:
-                pass  # Does not contain the named group lane
-
-            filename = re.sub(regex, new_ext, filename)
-            break  # only rename once
-
-    if not converted:
-        raise NameError(
-            """\n\tFatal: Failed to rename provided input '{}'!
-        Cannot determine the extension of the user provided input file.
-        Please rename the file list above before trying again.
-        Here is example of acceptable input file extensions:
-          sampleName.R1.fastq.gz      sampleName.R2.fastq.gz
-          sampleName_R1_001.fastq.gz  sampleName_R2_001.fastq.gz
-          sampleName_1.fastq.gz       sampleName_2.fastq.gz
-        Please also check that your input files are gzipped?
-        If they are not, please gzip them before proceeding again.
-        """.format(
-                filename
-            )
-        )
-
-    return filename