update

poetry.lock

@@ -667,6 +667,31 @@ files = [
     {file = "llvmlite-0.39.1.tar.gz", hash = "sha256:b43abd7c82e805261c425d50335be9a6c4f84264e34d6d6e475207300005d572"},
 ]
 
+[[package]]
+name = "markdown-it-py"
+version = "2.2.0"
+description = "Python port of markdown-it. Markdown parsing, done right!"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "markdown-it-py-2.2.0.tar.gz", hash = "sha256:7c9a5e412688bc771c67432cbfebcdd686c93ce6484913dccf06cb5a0bea35a1"},
+    {file = "markdown_it_py-2.2.0-py3-none-any.whl", hash = "sha256:5a35f8d1870171d9acc47b99612dc146129b631baf04970128b568f190d0cc30"},
+]
+
+[package.dependencies]
+mdurl = ">=0.1,<1.0"
+
+[package.extras]
+benchmarking = ["psutil", "pytest", "pytest-benchmark"]
+code-style = ["pre-commit (>=3.0,<4.0)"]
+compare = ["commonmark (>=0.9,<1.0)", "markdown (>=3.4,<4.0)", "mistletoe (>=1.0,<2.0)", "mistune (>=2.0,<3.0)", "panflute (>=2.3,<3.0)"]
+linkify = ["linkify-it-py (>=1,<3)"]
+plugins = ["mdit-py-plugins"]
+profiling = ["gprof2dot"]
+rtd = ["attrs", "myst-parser", "pyyaml", "sphinx", "sphinx-copybutton", "sphinx-design", "sphinx_book_theme"]
+testing = ["coverage", "pytest", "pytest-cov", "pytest-regressions"]
+
 [[package]]
 name = "markupsafe"
 version = "2.1.2"
@@ -727,16 +752,28 @@ files = [
     {file = "MarkupSafe-2.1.2.tar.gz", hash = "sha256:abcabc8c2b26036d62d4c746381a6f7cf60aafcc653198ad678306986b09450d"},
 ]
 
+[[package]]
+name = "mdurl"
+version = "0.1.2"
+description = "Markdown URL utilities"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "mdurl-0.1.2-py3-none-any.whl", hash = "sha256:84008a41e51615a49fc9966191ff91509e3c40b939176e643fd50a5c2196b8f8"},
+    {file = "mdurl-0.1.2.tar.gz", hash = "sha256:bb413d29f5eea38f31dd4754dd7377d4465116fb207585f97bf925588687c1ba"},
+]
+
 [[package]]
 name = "mpai-cae-arp"
-version = "0.2.1"
+version = "0.2.3"
 description = "The MPAI CAE-ARP software API"
 category = "main"
 optional = false
 python-versions = ">=3.10,<4.0"
 files = [
-    {file = "mpai_cae_arp-0.2.1-py3-none-any.whl", hash = "sha256:20bea510346e620d202acf340d055d5906b332738fbf4eed8ce637b52c0b3b85"},
-    {file = "mpai_cae_arp-0.2.1.tar.gz", hash = "sha256:9a36a913ca91bb5ecedd44d3edb9230e1af46b8eaed4650ba957b6144bd3eba9"},
+    {file = "mpai_cae_arp-0.2.3-py3-none-any.whl", hash = "sha256:d2d1225310474582e5697499fffa1140cf2d28fc2cb4fdad402446d146aa6e9e"},
+    {file = "mpai_cae_arp-0.2.3.tar.gz", hash = "sha256:d5cc6df1708678dfe2dddf76a124a6d13eebd4da2360d4d88963c4be43221236"},
 ]
 
 [package.dependencies]
@@ -1078,7 +1115,7 @@ email = ["email-validator (>=1.0.3)"]
 name = "pygments"
 version = "2.14.0"
 description = "Pygments is a syntax highlighting package written in Python."
-category = "dev"
+category = "main"
 optional = false
 python-versions = ">=3.6"
 files = [
@@ -1253,6 +1290,25 @@ idna = {version = "*", optional = true, markers = "extra == \"idna2008\""}
 [package.extras]
 idna2008 = ["idna"]
 
+[[package]]
+name = "rich"
+version = "13.3.3"
+description = "Render rich text, tables, progress bars, syntax highlighting, markdown and more to the terminal"
+category = "main"
+optional = false
+python-versions = ">=3.7.0"
+files = [
+    {file = "rich-13.3.3-py3-none-any.whl", hash = "sha256:540c7d6d26a1178e8e8b37e9ba44573a3cd1464ff6348b99ee7061b95d1c6333"},
+    {file = "rich-13.3.3.tar.gz", hash = "sha256:dc84400a9d842b3a9c5ff74addd8eb798d155f36c1c91303888e0a66850d2a15"},
+]
+
+[package.dependencies]
+markdown-it-py = ">=2.2.0,<3.0.0"
+pygments = ">=2.13.0,<3.0.0"
+
+[package.extras]
+jupyter = ["ipywidgets (>=7.5.1,<9)"]
+
 [[package]]
 name = "ruff"
 version = "0.0.261"
@@ -1936,4 +1992,4 @@ files = [
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.10"
-content-hash = "0c3763c54b9876a9c5ca29c18660439e1f2b09f42cd2cb009114d52a89d94e9f"
+content-hash = "dfd9dd13f5970323abae96a9b68c21a666a0befb4d9111bf1c12bdfb832ee332"

pyproject.toml

@@ -8,8 +8,9 @@ readme = "README.md"
 
 [tool.poetry.dependencies]
 python = "^3.10"
-mpai-cae-arp = "^0.2.1"
+mpai-cae-arp = "^0.2.3"
 numpy = "1.23.3"
+rich = "^13.3.3"
 
 
 [tool.poetry.group.docs.dependencies]

src/cli.py

+import argparse
+import os
+import time
+from rich.console import Console
 import segment_finder as sf
 
+from mpai_cae_arp.types.irregularity import IrregularityFile
+
+
+def get_args() -> argparse.Namespace:
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--working-directory", "-w", help="Working directory", required=True)
+    parser.add_argument("--files-name", "-f", nargs="+", help="Files name", required=True)
+    return parser.parse_args()
+
+
+def exit_with_error(error_message: str, console) -> None:
+    console.print(f"[red bold]Error: {error_message}")
+    quit(os.EX_USAGE)
+
+
+def main():
+    args = get_args()
+    console = Console()
+    console.print("[bold]Welcome to ARP Audio Analyzer!")
+    
+    working_directory = args.working_directory
+    files_name = args.files_name
+
+    with console.status("Reading input files...", spinner="dots"):
+        time.sleep(1)
+        audio_src = os.path.join(working_directory, "PreservationAudioFile", f"{files_name[0]}.wav")
+        video_src = os.path.join(working_directory, "PreservationAudioVisualFile", f"{files_name[0]}.mov")
+
+        console.log(audio_src)
+        console.log(video_src)
+        
+        audio_exists = os.path.exists(audio_src)
+        video_exists = os.path.exists(video_src)
+
+        match audio_exists, video_exists:
+            case True, True:
+                console.print("[green]Input files found!")
+            case False, True:
+                exit_with_error("Audio file not found!", console)
+            case True, False:
+                exit_with_error("Video file not found!", console)
+            case False, False:
+                exit_with_error("Input files not found!", console)
+
+    # create irregularity file 1
+    with console.status("Creating irregularity file 1...", spinner="dots"):
+        irreg1 = sf.create_irreg_file(audio_src, video_src)
+
+    # create irregularity file 2
+    with console.status("Creating irregularity file 2...", spinner="dots"):
+        video_irreg_1 = {}
+        irreg2 = sf.merge_irreg_files(irreg1, IrregularityFile.from_json(video_irreg_1))
+
+    with console.status("Extracting audio irregularities...", spinner="bouncingBall"):
+        sf.extract_audio_irregularities(audio_src, irreg2, working_directory)
+
+    # classify audio irregularities
+
+    console.print("[green bold]Success!")
+
+
 if __name__ == "__main__":
-    print(sf.create_irreg_file("test.wav", "test.mp4"))
\ No newline at end of file
+    main()

src/segment_finder.py

+import os
+import tempfile
 from uuid import uuid4
 import numpy as np
 
 from mpai_cae_arp.audio import AudioWave, Noise
+from mpai_cae_arp.files import File, FileType
 from mpai_cae_arp.types.irregularity import Irregularity, IrregularityFile, Source
-from mpai_cae_arp.time import frames_to_seconds
+from mpai_cae_arp.time import frames_to_seconds, seconds_to_frames
 
+temp_dir = tempfile.gettempdir()
+TMP_CHANNELS_MAP = os.path.join(temp_dir, "channels_map.json")
 
 def calculate_offset(audio: AudioWave, video: AudioWave) -> float:
     """
@@ -29,30 +34,67 @@ def calculate_offset(audio: AudioWave, video: AudioWave) -> float:
     return lags[lag_idx] / audio.samplerate
 
 
-def foo(audio_src) -> list[Irregularity]:
-    input = AudioWave.from_file(audio_src)
+def get_irregularities_from_audio(audio_src: AudioWave) -> list[Irregularity]:
     input_channels: list[AudioWave] = []
-    for channel in input.channels:
-        input_channels.append(input.get_channel(channel))
+    for channel in audio_src.channels:
+        input_channels.append(audio_src.get_channel(channel))
+
+    channels_map = {}
 
     irreg_list: list[Irregularity] = []
-    for audio in input_channels:
+    for idx, audio in enumerate(input_channels):
         for _, noise_list in audio.get_silence_slices([
             Noise("A", -50, -63),
             Noise("B", -63, -69),
             Noise("C", -69, -72)],
             length=500).items():
             for start, _ in noise_list:
+                id = uuid4()
                 irreg_list.append(
                     Irregularity(
-                        uuid=uuid4(),
+                        uuid=id,
                         source=Source.AUDIO,
                         time_label=frames_to_seconds(start, audio.samplerate)
                     )
                 )
+                channels_map[id] = idx
+
+    File(TMP_CHANNELS_MAP, FileType.JSON).write_content(channels_map)
 
     return irreg_list
 
-def create_irreg_file(audio_src, video_src) -> IrregularityFile:
-    offset = calculate_offset(AudioWave.from_file(audio_src), video_src)
-    return IrregularityFile(foo(audio_src), offset=offset)
+
+def create_irreg_file(audio_src: str, video_src: str) -> IrregularityFile:
+
+    audio = AudioWave.from_file(audio_src, bufferize=True)
+    
+    offset = calculate_offset(audio, video_src)
+    return IrregularityFile(get_irregularities_from_audio(audio), offset=offset)
+
+
+def merge_irreg_files(
+    file1: IrregularityFile,
+    file2: IrregularityFile) -> IrregularityFile:
+    new_file = IrregularityFile(
+        irregularities=file1.irregularities + file2.irregularities,
+        offset=np.argmax([file1.offset, file2.offset]))
+
+    new_file.irregularities.sort(key=lambda x: x.time_label)
+
+    return new_file
+
+
+def extract_audio_irregularities(
+    audio: AudioWave,
+    irreg_file: IrregularityFile,
+    path: str) -> None:
+    channels_map = File(TMP_CHANNELS_MAP, FileType.JSON).get_content()
+    for irreg in irreg_file.irregularities:
+        if irreg.source == Source.AUDIO:
+            chunk = audio.get_channel(channels_map[irreg.irregularity_ID])[
+                seconds_to_frames(
+                    irreg.time_label, audio.samplerate
+                ):seconds_to_frames(
+                    irreg.time_label, audio.samplerate)+audio.samplerate//2]
+            chunk.save(f"{path}/AudioBlocks/{irreg.irregularity_ID}.wav")
+    os.remove(TMP_CHANNELS_MAP)