Add app-level logging

autosub/audioProcessing.py

@@ -2,10 +2,13 @@
 # -*- coding: utf-8 -*-
 
 import sys
+import logger
 import subprocess
 import numpy as np
 from os.path import basename
 
+_logger = logger.setup_applevel_logger(__name__)
+
 def extract_audio(input_file, audio_file_name):
     """Extract audio from input video file and save to audio/ in root dir
 
@@ -18,9 +21,9 @@ def extract_audio(input_file, audio_file_name):
         command = ["ffmpeg", "-hide_banner", "-loglevel", "warning", "-i", input_file, "-ac", "1", "-ar", "16000",
                    "-vn", "-f", "wav", audio_file_name]
         ret = subprocess.run(command).returncode
-        print("Extracted audio to audio/{}".format(basename(audio_file_name)))
+        _logger.info(f"Extracted audio to audio/{basename(audio_file_name)}")
     except Exception as e:
-        print("Error: ", str(e))
+        _logger.error(str(e))
         sys.exit(1)
 
 

autosub/logger.py

@@ -0,0 +1,21 @@
+import sys
+import logging
+
+APP_NAME = "AutoSub"
+
+def setup_applevel_logger(logger_name = APP_NAME, file_name=None): 
+    logger = logging.getLogger(logger_name)
+    logger.setLevel(logging.INFO)
+    formatter = logging.Formatter("[%(levelname)s] %(message)s") #%(name)s |
+    sh = logging.StreamHandler(sys.stdout)
+    sh.setFormatter(formatter)
+    logger.handlers.clear()
+    logger.addHandler(sh)
+    if file_name:
+        fh = logging.FileHandler(file_name)
+        fh.setFormatter(formatter)
+        logger.addHandler(fh)
+    return logger
+
+def get_logger(module_name):    
+   return logging.getLogger(APP_NAME).getChild(module_name)

autosub/main.py

@@ -5,6 +5,7 @@
 import re
 import sys
 import wave
+import logger
 import argparse
 
 import numpy as np
@@ -15,6 +16,7 @@
 from audioProcessing import extract_audio
 from segmentAudio import remove_silent_segments
 
+_logger = logger.setup_applevel_logger(__name__)
 
 # Line count for SRT file
 line_count = 1
@@ -96,7 +98,7 @@ def main():
     args = parser.parse_args()
 
     #print(sys.argv[0:])
-    print("ARGS:", args)
+    _logger.info(f"ARGS: {args}")
 
     ds_model = get_model(args, "model")
     ds_scorer = get_model(args, "scorer")
@@ -105,18 +107,18 @@ def main():
         create_model(ds_model, ds_scorer) 
         if args.file is not None:
             if not os.path.isfile(args.file):
-                print(f"Invalid file: {args.file}")
+                _logger.warn(f"Invalid file: {args.file}")
         sys.exit(0)
 
     if args.file is not None:
         if os.path.isfile(args.file):
             input_file = args.file
-            print(f"Input file: {args.file}")
+            _logger.info(f"Input file: {args.file}")
         else:
-            print(f"Invalid file: {args.file}")
+            _logger.error(f"Invalid file: {args.file}")
             sys.exit(1)
     else:
-        print("Error. One or more of --file or --dry-run are required.")
+        _logger.error("One or more of --file or --dry-run are required")
         sys.exit(1)
 
     base_directory = os.getcwd()
@@ -141,14 +143,14 @@ def main():
     clean_folder(audio_directory)
     extract_audio(input_file, audio_file_name)
 
-    print("Splitting on silent parts in audio file")
+    _logger.info("Splitting on silent parts in audio file")
     remove_silent_segments(audio_file_name)
 
     audiofiles = [file for file in os.listdir(audio_directory) if file.startswith(video_prefix)]
     audiofiles = sort_alphanumeric(audiofiles)
     audiofiles.remove(os.path.basename(audio_file_name))
 
-    print("\nRunning inference:")
+    _logger.info("Running inference...")
     ds = create_model(ds_model, ds_scorer) 
 
     for filename in tqdm(audiofiles):
@@ -157,7 +159,7 @@ def main():
 
     for format in output_file_handle_dict:
         file_handle = output_file_handle_dict[format]
-        print(format.upper(), "file saved to", file_handle.name)
+        _logger.info(f"{format.upper()}, file saved to, {file_handle.name}")
         file_handle.close()
 
 

autosub/segmentAudio.py

@@ -2,13 +2,16 @@
 # -*- coding: utf-8 -*-
 
 import os
+import logger
 import numpy as np
 
 import trainAudio as TA
 from pydub import AudioSegment
 import featureExtraction as FE
 import scipy.io.wavfile as wavfile
 
+_logger = logger.setup_applevel_logger(__name__)
+
 
 def read_audio_file(input_file):
     """This function returns a numpy array that stores the audio samples of a
@@ -35,7 +38,7 @@ def read_audio_file(input_file):
                 temp_signal.append(data[chn::audiofile.channels])
             signal = np.array(temp_signal).T
     except:
-        print("Error: file not found or other I/O error. (DECODING FAILED)")
+        _logger.error("File not found or other I/O error. (DECODING FAILED)")
 
     if signal.ndim == 2 and signal.shape[1] == 1:
         signal = signal.flatten()

autosub/utils.py

@@ -5,8 +5,11 @@
 import os
 import sys
 import shutil
+import logger
 from deepspeech import Model
 
+_logger = logger.setup_applevel_logger(__name__)
+
 def sort_alphanumeric(data):
     """Sort function to sort os.listdir() alphanumerically
     Helps to process audio files sequentially after splitting
@@ -35,7 +38,7 @@ def clean_folder(folder):
             elif os.path.isdir(file_path):
                 shutil.rmtree(file_path)
         except Exception as e:
-            print(f"Failed to delete {file_path}. Reason: {e}")
+            _logger.warn(f"Failed to delete {file_path}. Reason: {e}")
 
 def get_model(args, arg_name):
     """Will prioritze supplied arguments but if not, try to find files
@@ -55,31 +58,31 @@ def get_model(args, arg_name):
     if arg is not None:
         model = os.path.abspath(arg)
         if not os.path.isfile(model):
-            print(f"Error. Supplied file {arg} doesn't exist. Please supply a valid {arg_name} file via the --{arg_name} flag.")
+            _logger.error(f"Supplied file {arg} doesn't exist. Please supply a valid {arg_name} file via the --{arg_name} flag")
             sys.exit(1)
     else:
         models = [file for file in os.listdir() if file.endswith(arg_extension)]
         num_models = len(models)
 
         if num_models == 0:
-            print(f"Warning no {arg_name}s specified via --{arg_name} and none found in local directory. Please run getmodel.sh to get some.")
+            _logger.warn(f"No {arg_name}s specified via --{arg_name} and none found in local directory. Please run getmodel.sh to get some")
             if arg_name == 'model':
-                print("Error: Must have pbmm model. Exiting")
+                _logger.error("Must specify pbmm model")
                 sys.exit(1)
             else:
                 model = ''
         elif num_models != 1: 
-            print(f"Warning. Detected {num_models} {arg_name} files in local dir")
+            _logger.warn(f"Detected {num_models} {arg_name} files in local dir")
             if arg_name == 'model':
-                print("Must specify pbmm model. Exiting")
+                _logger.error("Must specify pbmm model")
                 sys.exit(1)
             else:
-                print("Please specify scorer using --scorer")
+                _logger.warn("Please specify scorer using --scorer")
                 model = ''
         else:
             model = os.path.abspath(models[0])                    
 
-    print(f"{arg_name.capitalize()}: {model}")
+    _logger.info(f"{arg_name.capitalize()}: {model}")
     return(model)
 
 def create_model(model, scorer):
@@ -93,11 +96,11 @@ def create_model(model, scorer):
     try:
         ds = Model(model)
     except:
-        print("Invalid model file. Exiting")
+        _logger.error("Invalid model file")
         sys.exit(1)
 
     try:
         ds.enableExternalScorer(scorer)
     except:
-        print("Invalid scorer file. Running inference using only model file")
+        _logger.warn("Invalid scorer file. Running inference using only model file")
     return(ds)