Add typing throughout code base

.gitignore

@@ -1,3 +1,7 @@
+# Data folders
+input/
+output/
+
 # Byte-compiled / optimized / DLL files
 __pycache__/
 *.py[cod]

bpm_novariant.py

@@ -2,7 +2,7 @@
 from os.path import join, splitext, dirname, realpath
 import shutil
 
-def get_folders_to_delete():
+def get_folders_to_delete() -> list[str]:
 	to_delete  = []
 	dir_path = dirname(realpath(__file__))
 	print(dir_path)

smdatatools/common/cli_options.py

@@ -17,11 +17,11 @@ def read_TXTtoData(filepath: str) -> DataHandler:
         data.note_data = InputProcessor.parse_txt_input(istr)
         return data
 
-    def write_DatatoSM(data: DataHandler, filepath: str):
+    def write_DatatoSM(data: DataHandler, filepath: str) -> None:
         filename = strip_filename(filepath)
         ostr = OutputProcessor.pregenerate_sm_output(filename, data.processed_data)
         write_file(ostr, filepath)
 
-    def write_DatatoTXT(data: DataHandler, filepath: str):
+    def write_DatatoTXT(data: DataHandler, filepath: str) -> None:
         ostr = OutputProcessor.pregenerate_txt_output(data.note_data)
         write_file(ostr, filepath)

smdatatools/common/file_utils.py

@@ -2,17 +2,17 @@
 from os.path import join, split, splitext
 from re import sub
 
-def read_file(filename):
+def read_file(filename: str) -> list[str]:
     file_data = []
     with open(filename, encoding='ascii', errors='ignore') as f:
         file_data = f.read().splitlines()
     return file_data
 
-def write_file(output_data, filename):
+def write_file(output_data: str, filename: str) -> None:
     with open(filename, 'w') as f:
         f.write(output_data)
 
-def strip_filename(filename):
+def strip_filename(filename: str) -> str:
     '''
     Strips file path
     Strips file extension
@@ -23,7 +23,7 @@ def strip_filename(filename):
     tail = splitext(tail)[0]
     return sub(' ', '_', sub('[^a-z0-9-_ ]', '', tail.lower()))
 
-def collect_filenames(input_dir: str, extensions: list):
+def collect_filenames(input_dir: str, extensions: list[str]) -> list[str]:
     filenames = []
     for root, dirs, files in walk(input_dir):
         for filename in files:
@@ -32,15 +32,15 @@ def collect_filenames(input_dir: str, extensions: list):
                 filenames.append(join(root, filename).replace("\\","/"))
     return filenames
 
-def getFilePaths(input_dir: list, extensions: list):
+def getFilePaths(input_dir: list[str], extensions: list[str]) -> list[str]:
     filepaths = collect_filenames(input_dir, extensions)
 
     if '.sm' in extensions:
         checkFilePaths(filepaths)
 
     return filepaths
 
-def checkFilePaths(sm_filepaths):
+def checkFilePaths(sm_filepaths: list[str]) -> None:
     # checks for static bpm in the .sm file
     # and removes filepath from list if not
     for sm_file in sm_filepaths:

smdatatools/components/measure.py

@@ -3,7 +3,7 @@
 
 class Measure:
 
-    def calculate_timing(measure, measure_index, bpm, offset):
+    def calculate_timing(measure: list[str], measure_index: int, bpm: float, offset: float) -> str:
         # calculate time in seconds for each line in the measure:
         #   BPM       = beats/minute -> BPS = beats/second = BPM/60
         #   measure   = 4 beats = 4 * 1/4th notes     = 1 note
@@ -30,7 +30,7 @@ def find_gcd(note_positions) -> int:
 
         return int(gcd_gap)
 
-    def generate_measure(notes, note_positions) -> list[str]:
+    def generate_measure(notes: list[str], note_positions: list[int]) -> list[str]:
 
         # we'll want to trim as much output as possible
         # by reducing the measure size
@@ -46,7 +46,7 @@ def generate_measure(notes, note_positions) -> list[str]:
 
         return generated_measure
 
-    def fit_notes_to_measure(notes, timings, seconds_1_256) -> list[str]:
+    def fit_notes_to_measure(notes: list[str], timings: list[float], seconds_1_256: float) -> list[str]:
         # if no data is passed, generate current measure
         # as "empty" with the smallest size
         if not notes or not timings:
@@ -78,7 +78,7 @@ def fit_notes_to_measure(notes, timings, seconds_1_256) -> list[str]:
 
         return measure
 
-    def place_notes(notes_and_timings, bpm) -> list:
+    def place_notes(notes_and_timings: list[str], bpm: float) -> list[str]:
         placed_notes = []
         if not notes_and_timings:
             return placed_notes

smdatatools/data_processing/data_handler.py

@@ -14,7 +14,7 @@ def __init__(self, filepath):
         self.processed_data = defaultdict(list)
         self.valid = True
 
-    def process_data_to_sm_format(self):
+    def process_data_to_sm_format(self) -> None:
 
         self.processed_data['title'] = self.note_data['title']
         self.processed_data['bpm'] = float(self.note_data['bpm'])

smdatatools/data_processing/input_processor.py

@@ -5,10 +5,10 @@
 
 class InputProcessor:
 
-    def convert_note(line):                                                      
+    def convert_note(line: str) -> str:                                                      
         return sub('4', '1', sub('[MKLF]', '0', line))    #replaces extra notes: M, K, L, F; replaces 4 note
 
-    def parse_sm_input(sm_file):
+    def parse_sm_input(sm_file: list[str]) -> tuple[dict[str, dict[str or list[str]] or float or int ], bool]:
         note_data = defaultdict(list)
         note_data['notes'] = defaultdict(list) # notes are paired with each difficulty
         current_difficulty = ''
@@ -75,7 +75,7 @@ def parse_sm_input(sm_file):
 
         return note_data, valid
 
-    def parse_txt_input(txt_file):
+    def parse_txt_input(txt_file: list[str]) -> dict[str, dict[str or list[str]] or float or int ]:
         note_data = defaultdict(list)
         note_data['notes'] = defaultdict(list)
         current_difficulty = ''