Add log file and log level options, optimize code for speed, and update Julia version

Author: adkinsrs

CHANGELOG.md

@@ -4,6 +4,8 @@
 
 * FEATURE - Adding --no_output_header option to not print the header line in output. Useful for when you want to pipe this output to another tool.
 * FEATURE - Adding --exclude_regions option to exclude any regions found in a passed-in BED file.
+* FEATURE - Adding --log_file and --log_level options to display or hide log messages of varying severity. Note that currently --log_level=DEBUG will print the line number, as I haven't figured out how to disable that for debug-level messages yet.
+* Optimized some pieces of code for speed (thanks Github Copilot). This should increase the speed where a GFF feature has 100,000s of overlaps with the BAM alignments
 
 ## v1.8.3
 

Dockerfile

@@ -1,5 +1,5 @@
 # Wanted to do the alpine version but that tag does not support arm64 (Mac M1) architecture
-FROM julia:1.9
+FROM julia:1.7
 LABEL maintainer="Shaun Adkins ([email protected])"
 
 RUN mkdir -p /opt/FADU

README.md

@@ -17,17 +17,18 @@ Most current available quantification tools for transcriptomics analyses have be
 
 ## Current FADU release
 
-v1.8.3
+v1.9
 
 ## Requirements
 
-Julia - v1.4.2 or later
+Julia - v1.7 or later
 
 ### Packages
 
 NOTE: Packages installation instructions can be found at https://docs.julialang.org/en/v1.4/stdlib/Pkg/index.html#Getting-Started-1
 
 * ArgParse
+* Logging
 * BGZFStreams.jl - v0.3.0
 * GenomicFeatures.jl - v2.0.0
 * GFF3 - v0.2.0
@@ -165,6 +166,11 @@ optional arguments:
                         on multimapped read depth. Only applies if
                         --remove_multimapped flag is not passed (is
                         disabled) (type: Int64, default: 1)
+  --log_level LEVEL     Set the log level.  Options are: DEBUG, INFO,
+                        WARNING, ERROR, CRITICAL. (default: "INFO")
+  --log_file /path/to/logfile.log
+                        Path to log file.  If not specified, log
+                        messages will be printed to STDERR.
   --version             show version information and exit
   -h, --help            show this help message and exit
 ```

docs/index.md

@@ -17,17 +17,18 @@ Most current available quantification tools for transcriptomics analyses have be
 
 ## Current FADU release
 
-v1.8.3
+v1.9
 
 ## Requirements
 
-Julia - v1.4.2 or later
+Julia - v1.7 or later
 
 ### Packages
 
 NOTE: Packages installation instructions can be found at https://docs.julialang.org/en/v1.4/stdlib/Pkg/index.html#Getting-Started-1
 
 * ArgParse
+* Logging
 * BGZFStreams.jl - v0.3.0
 * GenomicFeatures.jl - v2.0.0
 * GFF3 - v0.2.0
@@ -166,6 +167,11 @@ optional arguments:
                         on multimapped read depth. Only applies if
                         --remove_multimapped flag is not passed (is
                         disabled) (type: Int64, default: 1)
+  --log_level LEVEL     Set the log level.  Options are: DEBUG, INFO,
+                        WARNING, ERROR, CRITICAL. (default: "INFO")
+  --log_file /path/to/logfile.log
+                        Path to log file.  If not specified, log
+                        messages will be printed to STDERR.
   --version             show version information and exit
   -h, --help            show this help message and exit
 ```

fadu.jl

@@ -22,6 +22,7 @@ By: Shaun Adkins ([email protected])
 
 # The macro on modules and functions makes the code available to all worker processes
 using ArgParse
+using Logging
 using XAM: BAM, SAM
 using GenomicFeatures
 using GFF3
@@ -150,27 +151,54 @@ function parse_commandline()
             arg_type = Int
             range_tester = (x->x>0)
             dest_name = "em_iter"
+        "--log_level"
+            help = "Set the log level.  Options are: DEBUG, INFO, WARNING, ERROR, CRITICAL."
+            default = "INFO"
+            metavar = "LEVEL"
+            range_tester = (x->x in ["DEBUG", "INFO", "WARNING", "ERROR"])
+        "--log_file"
+            help = "Path to log file.  If not specified, log messages will be printed to STDERR."
+            metavar = "/path/to/logfile.log"
 
     # Will not add log_file or debug options for now
     end
     # Converts the ArgParseSettings object into key/value pairs
     return parse_args(s)
 end
 
+function setup_logger(args)
+    """Set up logging."""
+    stream = args["log_file"] === nothing ? stderr : open(args["log_file"], "w")
+    logleveldict = Dict("DEBUG" => -1000, "INFO" => 0, "WARNING" => 1000, "ERROR" => 2000)
+    loglevel = get(logleveldict, uppercase(args["log_level"]), 0)
+    logger = ConsoleLogger(stream, loglevel)
+    global_logger(logger)
+    # TODO: prevent debug messages from printing the file and line number
+
+end
+
 function validate_args(args)
     """Validate the passed arguments."""
-    isfile(args["gff3_file"]) || throw(SystemError("GFF3 file does not seem to exist. Please check supplied path."))
-    isfile(args["bam_file"]) || throw(SystemError("BAM file does not seem to exist. Please check supplied path."))
+    @info("Validating arguments...")
+    isfile(args["bam_file"]) || error("BAM file does not exist. Please check supplied path")
+    isfile(args["gff3_file"]) || error("GFF3 file does not exist. Please check supplied path")
     if !isdir(args["output_dir"])
-        @debug("Creating output directory")
+        @info("Creating output directory at ", args["output_dir"])
         mkdir(args["output_dir"])
     end
-    args["stranded"] in ["yes", "no", "reverse"] || error("--stranded argument must be either 'yes', 'no', or 'reverse'.")
 end
 
 function main()
     args = parse_commandline()
-    #validate_args(args)
+    setup_logger(args)
+
+    try
+        validate_args(args)
+    catch e
+        @error(e)
+        exit(1)
+    end
+
     @info("Parsed args:")
     for (arg,val) in args
         @info("  $arg  =>  $val")

fadu_pkgs/Project.toml

@@ -10,7 +10,7 @@ BGZFStreams = "28d598bf-9b8f-59f1-b38c-5a06b4a0f5e6"
 GFF3 = "af1dc308-cb6b-11e8-32f0-31192efa90f6"
 GenomicFeatures = "899a7d2d-5c61-547b-bef9-6698a8d05446"
 Indexes = "4ffb77ac-cb80-11e8-1b35-4b78cc642f6d"
-Pkg = "44cfe95a-1eb2-52ea-b672-e2afdf69b78f"
+Logging = "56ddb016-857b-54e1-b83d-db4d58db5568"
 StructArrays = "09ab397b-f2b6-538f-b94a-2f83cf4a842a"
 XAM = "d759349c-bcba-11e9-07c2-5b90f8f05f7c"
 
@@ -22,4 +22,4 @@ GenomicFeatures = "2.0.0"
 Indexes = "0.1.1"
 StructArrays = "0.4.4"
 XAM = "0.2.6"
-julia = "1.4.2"
+julia = "1.7"