Merge pull request #242 from ARGA-Genomes/argparserKwargs

Argparser Kwargs

Author: christopher-mangion

src/lib/data/argParser.py

@@ -18,7 +18,7 @@ def __init__(self, description: str = "", reprepareHelp: str = "Force redoing so
     def addArgument(self, *args, **kwargs) -> None:
         self._parser.add_argument(*args, **kwargs)
 
-    def parseArgs(self, *args, kwargsDict: bool = False, **kwargs) -> tuple[list[BasicDB], list[Flag], Namespace | dict]:
+    def parseArgs(self, *args, **kwargs) -> tuple[list[BasicDB], list[Flag], Namespace]:
         parsedArgs = self._parser.parse_args(*args, **kwargs)
 
         sources = self._manager.matchSources(self._extract(parsedArgs, "source"))
@@ -31,11 +31,14 @@ def parseArgs(self, *args, kwargsDict: bool = False, **kwargs) -> tuple[list[Bas
         flags = [flag for key, flag in Flag._value2member_map_.items() if self._extract(parsedArgs, key)]
         constructedSources = self._manager.constructDBs(sources)
 
-        return constructedSources, flags, parsedArgs.__dict__ if kwargsDict else parsedArgs
+        return constructedSources, flags, parsedArgs
 
     def addMutuallyExclusiveGroup(self, *args, **kwargs) -> _MutuallyExclusiveGroup:
         return self._parser.add_mutually_exclusive_group(*args, **kwargs)
 
+    def convertDict(self, ns: Namespace) -> dict:
+        return ns.__dict__
+
     def _extract(self, namespace: Namespace, attribute: str) -> any:
         attr = getattr(namespace, attribute)
         delattr(namespace, attribute)

src/tools/convert.py

@@ -7,6 +7,6 @@
         reprepareHelp="Force retrieval of map",
     )
 
-    sources, flags, kwargs = parser.parseArgs()
+    sources, flags, args = parser.parseArgs()
     for source in sources:
         source.create(Step.CONVERSION, flags)

src/tools/download.py

@@ -7,6 +7,6 @@
         reprepareHelp="Force retrieval of download information"
     )
 
-    sources, flags, kwargs = parser.parseArgs()
+    sources, flags, args = parser.parseArgs()
     for source in sources:
         source.create(Step.DOWNLOADING, flags)

src/tools/package.py

@@ -3,6 +3,6 @@
 if __name__ == '__main__':
     parser = ArgParser(description="Package converted data")
 
-    sources, flags, kwargs = parser.parseArgs()
+    sources, flags, args = parser.parseArgs()
     for source in sources:
         source.package()

src/tools/process.py

@@ -4,6 +4,6 @@
 if __name__ == '__main__':
     parser = ArgParser(description="Prepare for DwC conversion")
 
-    sources, flags, kwargs = parser.parseArgs()
+    sources, flags, args = parser.parseArgs()
     for source in sources:
         source.create(Step.PROCESSING, flags)

src/tools/purgeSource.py

@@ -6,7 +6,7 @@
     parser = ArgParser(description="Clean up source to save space")
     parser.addArgument("-r", "--raw", action="store_true", help="Clear raw/downloaded files too")
 
-    sources, flags, kwargs = parser.parseArgs()
+    sources, flags, args = parser.parseArgs()
     for source in sources:
         dataDir = source.baseDir / "data"
 

src/tools/sampleConversion.py

@@ -12,9 +12,9 @@
     columnGroup.add_argument("-m", "--mapped", action="store_true", help="Get only mapped fields")
     columnGroup.add_argument("-U", "--unmapped", action="store_true", help="Get only unmapped fields")
 
-    sources, flags, kwargs = parser.parseArgs()
-    suffix = ".tsv" if kwargs.tsv else ".csv"
-    delim = "\t" if kwargs.tsv else ","
+    sources, flags, args = parser.parseArgs()
+    suffix = ".tsv" if args.tsv else ".csv"
+    delim = "\t" if args.tsv else ","
 
     for source in sources:
         source._prepare(Step.CONVERSION, flags)
@@ -26,22 +26,22 @@
             continue
 
         outputFolder = lastConversionFile.name
-        if kwargs.mapped:
+        if args.mapped:
             outputFolder += "_mapped"
-        elif kwargs.unmapped:
+        elif args.unmapped:
             outputFolder += "_unmapped"
         outputFolder += "_example"
 
         stackedFile = StackedFile(lastConversionFile)
-        df = next(stackedFile.loadDataFrameIterator(rows=kwargs.entries))
+        df = next(stackedFile.loadDataFrameIterator(rows=args.entries))
 
         folderPath = source.exampleDir / outputFolder
         folderPath.mkdir(exist_ok=True)
 
         dummpyMap = Map({})
 
         for event in df.columns.levels[0]:
-            if (kwargs.mapped and event == dummpyMap._unmappedLabel) or (kwargs.unmapped and event != dummpyMap._unmappedLabel):
+            if (args.mapped and event == dummpyMap._unmappedLabel) or (args.unmapped and event != dummpyMap._unmappedLabel):
                 continue
 
             fileName = f"{event}{suffix}"

src/tools/samplePreConversion.py

@@ -52,8 +52,8 @@ def _collectRecords(iterator: Generator[pd.DataFrame, None, None], entryLimit: i
     parser.addArgument('-f', '--firstrow', type=int, default=0, help="First row offset for reading data")
     parser.addArgument('-r', '--rows', type=int, help="Maximum amount of rows to read from file")
 
-    sources, flags, kwargs = parser.parseArgs()
-    entryLimit = kwargs.entries
+    sources, flags, args = parser.parseArgs()
+    entryLimit = args.entries
 
     for source in sources:
         outputDir = source.exampleDir
@@ -67,12 +67,12 @@ def _collectRecords(iterator: Generator[pd.DataFrame, None, None], entryLimit: i
             print(f"File {stageFile.path} does not exist, please run all required downloading/processing.")
             continue
 
-        seed = kwargs.seed if kwargs.seed >= 0 else random.randrange(2**32 - 1) # Max value for pandas seed
+        seed = args.seed if args.seed >= 0 else random.randrange(2**32 - 1) # Max value for pandas seed
         random.seed(seed)
-        outputPath = outputDir / f"{source.name}_{'fields' if kwargs.ignoreRecord else 'records'}_{kwargs.chunksize}_{seed}.tsv"
+        outputPath = outputDir / f"{source.name}_{'fields' if args.ignoreRecord else 'records'}_{args.chunksize}_{seed}.tsv"
 
-        dfIterator = stageFile.readIterator(kwargs.chunksize, on_bad_lines="skip", low_memory=False)
-        df = _collectFields(dfIterator, kwargs.entries, seed) if kwargs.ignoreRecord else _collectRecords(dfIterator, kwargs.entries, seed)
+        dfIterator = stageFile.readIterator(args.chunksize, on_bad_lines="skip", low_memory=False)
+        df = _collectFields(dfIterator, args.entries, seed) if args.ignoreRecord else _collectRecords(dfIterator, args.entries, seed)
 
         df = dff.removeSpaces(df)
         df.index += 1 # Increment index so output is 1-indexed numbers

src/tools/update.py

@@ -5,9 +5,9 @@
     parser = ArgParser(description="Run update on data source")
     parser.addArgument("-f", "--force", action="store_true", help="Force update regardless of config")
 
-    sources, flags, kwargs = parser.parseArgs()
+    sources, flags, args = parser.parseArgs()
     for source in sources:
-        if not source.checkUpdateReady() and not kwargs.force:
+        if not source.checkUpdateReady() and not args.force:
             logging.info(f"Data source '{source}' is not ready for update.")
             continue