VLC v1 finished, improve on instructions, improve on infra

desktop_env/evaluators/getters/__init__.py

@@ -1,3 +1,4 @@
 from .file import get_cloud_file, get_vm_file, get_cache_file
 from .misc import get_rule
+from .info import get_vm_screen_size, get_vm_window_size, get_vm_wallpaper
 from .vlc import get_vlc_playing_info, get_vlc_config

desktop_env/evaluators/metrics/README.md

@@ -95,6 +95,12 @@ with sync_playwright() as playwright:
 
 
 ## VLC Media Player
+
+### Bugs fix
+One thing on Ubuntu need to do, enter into the `meida`>`convert/save`>select files>`convert/save`
+Then enter the profile of `Audio - MP3`, change the profile for mp3, section audiocodec from "MP3" to "MPEG Audio"
+Otherwise the mp3 file will be created but with 0 bytes. It's a bug of VLC.
+
 ### Setting Up VLC's HTTP Interface
 
 To enable and use the HTTP interface in VLC Media Player for remote control and status checks, follow these steps:

desktop_env/evaluators/metrics/__init__.py

@@ -5,5 +5,5 @@ from .docs import compare_font_names, compare_subscript_contains, has_page_numbe
 from .docs import is_first_line_centered, check_file_exists, compare_contains_image
 from .pdf import check_pdf_pages
 from .libreoffice import check_libre_locale
-from .vlc import is_vlc_playing, is_vlc_recordings_folder
+from .vlc import is_vlc_playing, is_vlc_recordings_folder, is_vlc_fullscreen, compare_images, compare_audios, compare_videos
 from .general import check_csv

desktop_env/evaluators/metrics/vlc.py

@@ -7,7 +7,10 @@ from xml.etree import ElementTree
 import acoustid
 import cv2
 import imagehash
+from skimage.metrics import structural_similarity as ssim
+import librosa
 from PIL import Image
+import numpy as np
 
 logger = logging.getLogger("desktopenv.metrics.vlc")
 
@@ -57,24 +60,79 @@ def is_vlc_recordings_folder(actual_config_path: str, rule: Dict[str, str]) -> f
                 current_path = line.split('=')[-1].strip()
                 # Compare with the Desktop path
                 if current_path == expected_recording_file_path:
-                    return True
+                    return 1
                 else:
-                    return False
+                    return 0
             # The configuration key was not found in the file
-            return False
+            return 0
     except FileNotFoundError:
         logger.error("VLC configuration file not found.")
-        return False
+        return 0
     except Exception as e:
         logger.error(f"An error occurred: {e}")
-        return False
+        return 0
 
 
 def is_vlc_fullscreen(actual_window_size, screen_size):
     if actual_window_size['width'] == screen_size['width'] and actual_window_size['height'] == screen_size['height']:
-        return True
+        return 1
     else:
-        return False
+        return 0
+
+
+def compare_images(image1_path, image2_path):
+    # You would call this function with the paths to the two images you want to compare:
+    # score = compare_images('path_to_image1', 'path_to_image2')
+    # print("Similarity score:", score)
+
+    # Open the images and convert to grayscale
+    image1 = Image.open(image1_path).convert('L')
+    image2 = Image.open(image2_path).convert('L')
+
+    # Resize images to the smaller one's size for comparison
+    image1_size = image1.size
+    image2_size = image2.size
+    new_size = min(image1_size, image2_size)
+
+    image1 = image1.resize(new_size, Image.Resampling.LANCZOS)
+    image2 = image2.resize(new_size, Image.Resampling.LANCZOS)
+
+    # Convert images to numpy arrays
+    image1_array = np.array(image1)
+    image2_array = np.array(image2)
+
+    # Calculate SSIM between two images
+    similarity_index = ssim(image1_array, image2_array)
+
+    return similarity_index
+
+
+def compare_audios(audio_path_1, audio_path_2, max_distance=1000):
+    """
+    Compare two audio files and return a similarity score in the range [0, 1].
+    audio_path_1, audio_path_2: paths to the audio files to compare
+    max_distance: an empirically determined maximum expected DTW distance
+    """
+    # Example Usage:
+    # similarity = compare_audios_simple('path_to_audio1.mp3', 'path_to_audio2.mp3')
+    # print(f'Similarity Score: {similarity}')
+
+    # Convert to common format if necessary and load audio
+    y1, sr1 = librosa.load(audio_path_1)
+    y2, sr2 = librosa.load(audio_path_2)
+
+    # Extract MFCC features
+    mfcc1 = librosa.feature.mfcc(y=y1, sr=sr1)
+    mfcc2 = librosa.feature.mfcc(y=y2, sr=sr2)
+
+    # Compute Dynamic Time Warping distance
+    distance, path = librosa.sequence.dtw(mfcc1.T, mfcc2.T)
+
+    # Normalize distance to get a similarity score
+    normalized_distance = np.mean(distance) / max_distance
+    similarity_score = 1 - min(normalized_distance, 1)  # Ensure the score is within [0, 1]
+
+    return similarity_score
 
 
 def compare_videos(video_path1, video_path2, max_frames_to_check=100, threshold=5):