feat: add frame class extraction and formatting for media files

This commit is contained in:
sHa
2025-12-25 05:13:56 +00:00
parent 4e7cf94d58
commit 37efdf60d3
7 changed files with 224 additions and 61 deletions

View File

@@ -31,4 +31,42 @@ SOURCE_DICT = {
'DVDRip': ['DVDRip', 'DVD-Rip', 'DVDRIP'], 'DVDRip': ['DVDRip', 'DVD-Rip', 'DVDRIP'],
'HDTV': ['HDTV'], 'HDTV': ['HDTV'],
'BluRay': ['BluRay', 'BLURAY', 'Blu-ray'], 'BluRay': ['BluRay', 'BLURAY', 'Blu-ray'],
}
FRAME_CLASSES = {
'480p': {
'nominal_height': 480,
'typical_widths': [640, 704, 720],
'description': 'Standard Definition (SD) - DVD quality'
},
'576p': {
'nominal_height': 576,
'typical_widths': [720, 768],
'description': 'PAL Standard Definition (SD) - European DVD quality'
},
'720p': {
'nominal_height': 720,
'typical_widths': [1280],
'description': 'High Definition (HD) - 720p HD'
},
'1080p': {
'nominal_height': 1080,
'typical_widths': [1920],
'description': 'Full High Definition (FHD) - 1080p HD'
},
'1440p': {
'nominal_height': 1440,
'typical_widths': [2560],
'description': 'Quad High Definition (QHD) - 1440p 2K'
},
'2160p': {
'nominal_height': 2160,
'typical_widths': [3840],
'description': 'Ultra High Definition (UHD) - 2160p 4K'
},
'4320p': {
'nominal_height': 4320,
'typical_widths': [7680],
'description': 'Ultra High Definition (UHD) - 4320p 8K'
}
} }

View File

@@ -27,14 +27,22 @@ class MediaExtractor:
"""Extract video source from filename""" """Extract video source from filename"""
return FilenameExtractor.extract_source(file_path) return FilenameExtractor.extract_source(file_path)
def extract_resolution(self, file_path: Path) -> str | None: def extract_frame_class(self, file_path: Path) -> str | None:
"""Extract resolution from media info or filename""" """Extract frame class from media info or filename"""
# Try media info first # Try media info first
resolution = self.mediainfo_extractor.extract_resolution(file_path) frame_class = self.mediainfo_extractor.extract_frame_class(file_path)
if resolution: if frame_class:
return resolution return frame_class
# Fallback to filename # Fallback to filename
return FilenameExtractor.extract_resolution(file_path) return FilenameExtractor.extract_frame_class(file_path)
def extract_resolution(self, file_path: Path) -> str | None:
"""Extract actual video resolution (WIDTHxHEIGHT) from media info"""
return self.mediainfo_extractor.extract_resolution(file_path)
def extract_aspect_ratio(self, file_path: Path) -> str | None:
"""Extract video aspect ratio from media info"""
return self.mediainfo_extractor.extract_aspect_ratio(file_path)
def extract_hdr(self, file_path: Path) -> str | None: def extract_hdr(self, file_path: Path) -> str | None:
"""Extract HDR info from media info""" """Extract HDR info from media info"""
@@ -54,7 +62,9 @@ class MediaExtractor:
'title': self.extract_title(file_path), 'title': self.extract_title(file_path),
'year': self.extract_year(file_path), 'year': self.extract_year(file_path),
'source': self.extract_source(file_path), 'source': self.extract_source(file_path),
'frame_class': self.extract_frame_class(file_path),
'resolution': self.extract_resolution(file_path), 'resolution': self.extract_resolution(file_path),
'aspect_ratio': self.extract_aspect_ratio(file_path),
'hdr': self.extract_hdr(file_path), 'hdr': self.extract_hdr(file_path),
'audio_langs': self.extract_audio_langs(file_path), 'audio_langs': self.extract_audio_langs(file_path),
'metadata': self.extract_metadata(file_path) 'metadata': self.extract_metadata(file_path)

View File

@@ -1,11 +1,19 @@
import re import re
from pathlib import Path from pathlib import Path
from ..constants import SOURCE_DICT from ..constants import SOURCE_DICT, FRAME_CLASSES
class FilenameExtractor: class FilenameExtractor:
"""Class to extract information from filename""" """Class to extract information from filename"""
@staticmethod
def _get_frame_class_from_height(height: int) -> str:
"""Get frame class from video height using FRAME_CLASSES constant"""
for frame_class, info in FRAME_CLASSES.items():
if height == info['nominal_height']:
return frame_class
return 'Unclassified'
@staticmethod @staticmethod
def extract_title(file_path: Path) -> str | None: def extract_title(file_path: Path) -> str | None:
"""Extract movie title from filename""" """Extract movie title from filename"""
@@ -40,20 +48,11 @@ class FilenameExtractor:
return None return None
@staticmethod @staticmethod
def extract_resolution(file_path: Path) -> str | None: def extract_frame_class(file_path: Path) -> str | None:
"""Extract resolution from filename (e.g., 2160p, 1080p, 720p)""" """Extract frame class from filename (480p, 720p, 1080p, 2160p, etc.)"""
file_name = file_path.name file_name = file_path.name
match = re.search(r'(\d{3,4})[pi]', file_name, re.IGNORECASE) match = re.search(r'(\d{3,4})[pi]', file_name, re.IGNORECASE)
if match: if match:
height = int(match.group(1)) height = int(match.group(1))
if height >= 2160: return FilenameExtractor._get_frame_class_from_height(height)
return '2160p' return 'Unclassified'
elif height >= 1080:
return '1080p'
elif height >= 720:
return '720p'
elif height >= 480:
return '480p'
else:
return f'{height}p'
return None

View File

@@ -1,6 +1,7 @@
from pathlib import Path from pathlib import Path
from pymediainfo import MediaInfo from pymediainfo import MediaInfo
from collections import Counter from collections import Counter
from ..constants import FRAME_CLASSES
class MediaInfoExtractor: class MediaInfoExtractor:
@@ -13,24 +14,49 @@ class MediaInfoExtractor:
'zh': 'chi', 'und': 'und' 'zh': 'chi', 'und': 'und'
} }
def extract_resolution(self, file_path: Path) -> str | None: def _get_frame_class_from_height(self, height: int) -> str:
"""Extract resolution from media info""" """Get frame class from video height using FRAME_CLASSES constant"""
for frame_class, info in FRAME_CLASSES.items():
if height == info['nominal_height']:
return frame_class
return 'Unclassified'
def extract_frame_class(self, file_path: Path) -> str | None:
"""Extract frame class from media info (480p, 720p, 1080p, etc.)"""
try: try:
media_info = MediaInfo.parse(file_path) media_info = MediaInfo.parse(file_path)
video_tracks = [t for t in media_info.tracks if t.track_type == 'Video'] video_tracks = [t for t in media_info.tracks if t.track_type == 'Video']
if video_tracks: if video_tracks:
height = getattr(video_tracks[0], 'height', None) height = getattr(video_tracks[0], 'height', None)
if height: if height:
if height >= 2160: return self._get_frame_class_from_height(height)
return '2160p' except:
elif height >= 1080: pass
return '1080p' return 'Unclassified'
elif height >= 720:
return '720p' def extract_resolution(self, file_path: Path) -> str | None:
elif height >= 480: """Extract actual video resolution (WIDTHxHEIGHT) from media info"""
return '480p' try:
else: media_info = MediaInfo.parse(file_path)
return f'{height}p' video_tracks = [t for t in media_info.tracks if t.track_type == 'Video']
if video_tracks:
width = getattr(video_tracks[0], 'width', None)
height = getattr(video_tracks[0], 'height', None)
if width and height:
return f"{width}x{height}"
except:
pass
return None
def extract_aspect_ratio(self, file_path: Path) -> str | None:
"""Extract video aspect ratio from media info"""
try:
media_info = MediaInfo.parse(file_path)
video_tracks = [t for t in media_info.tracks if t.track_type == 'Video']
if video_tracks:
aspect_ratio = getattr(video_tracks[0], 'display_aspect_ratio', None)
if aspect_ratio:
return str(aspect_ratio)
except: except:
pass pass
return None return None

View File

@@ -9,34 +9,72 @@ from ..utils import detect_file_type
class MediaFormatter: class MediaFormatter:
"""Class to format media data for display""" """Class to format media data for display"""
def format_file_info(self, file_path: Path, rename_data: dict) -> str: def format_file_info_panel(self, file_path: Path, rename_data: dict) -> str:
"""Format complete file information for display""" """Format file information for the file info panel"""
output = []
# Panel title
output.append("[bold blue]FILE INFO[/bold blue]")
output.append("") # Empty line for spacing
# Get file stats # Get file stats
size_full = SizeFormatter.format_size_full(file_path.stat().st_size) size_full = SizeFormatter.format_size_full(file_path.stat().st_size)
date_formatted = DateFormatter.format_modification_date(file_path.stat().st_mtime) date_formatted = DateFormatter.format_modification_date(file_path.stat().st_mtime)
# Get extension info # Get extension info
ext_name = ExtensionExtractor.get_extension_name(file_path) ext_name = ExtensionExtractor.get_extension_name(file_path)
ext_desc = ExtensionExtractor.get_extension_description(ext_name) ext_desc = ExtensionExtractor.get_extension_description(ext_name)
meta_type, meta_desc = detect_file_type(file_path) meta_type, meta_desc = detect_file_type(file_path)
match = ExtensionFormatter.check_extension_match(ext_name, meta_type) match = ExtensionFormatter.check_extension_match(ext_name, meta_type)
ext_info = ExtensionFormatter.format_extension_info(ext_name, ext_desc, meta_type, meta_desc, match) ext_info = ExtensionFormatter.format_extension_info(ext_name, ext_desc, meta_type, meta_desc, match)
file_name = file_path.name file_name = file_path.name
# Build basic info output.append(f"[bold blue]Path:[/bold blue] {str(file_path)}")
full_info = f"[bold blue]Path:[/bold blue] {str(file_path)}\n\n" output.append(f"[bold green]Size:[/bold green] {size_full}")
full_info += f"[bold green]Size:[/bold green] {size_full}\n" output.append(f"[bold cyan]File:[/bold cyan] {file_name}")
full_info += f"[bold cyan]File:[/bold cyan] {file_name}\n" output.append(f"[bold magenta]Modified:[/bold magenta] {date_formatted}")
full_info += f"{ext_info}\n" output.append(f"{ext_info}")
full_info += f"[bold magenta]Modified:[/bold magenta] {date_formatted}"
return "\n".join(output)
# Extra metadata
extra_text = self._format_extra_metadata(rename_data['metadata']) def format_filename_extraction_panel(self, rename_data: dict) -> str:
if extra_text: """Format filename extraction data for the filename panel"""
full_info += f"\n\n{extra_text}" output = []
output.append("[bold yellow]FILENAME EXTRACTION[/bold yellow]")
return full_info output.append("") # Empty line for spacing
output.append(f"[yellow]Title:[/yellow] {rename_data.get('title', 'Not found')}")
output.append(f"[yellow]Year:[/yellow] {rename_data.get('year', 'Not found')}")
output.append(f"[yellow]Source:[/yellow] {rename_data.get('source', 'Not found')}")
output.append(f"[yellow]Frame Class:[/yellow] {rename_data.get('frame_class', 'Not found')}")
return "\n".join(output)
def format_metadata_extraction_panel(self, rename_data: dict) -> str:
"""Format metadata extraction data for the metadata panel"""
output = []
output.append("[bold cyan]METADATA EXTRACTION[/bold cyan]")
output.append("") # Empty line for spacing
metadata = rename_data.get('metadata', {})
if metadata.get('duration'):
output.append(f"[cyan]Duration:[/cyan] {metadata['duration']:.1f} seconds")
if metadata.get('title'):
output.append(f"[cyan]Title:[/cyan] {metadata['title']}")
if metadata.get('artist'):
output.append(f"[cyan]Artist:[/cyan] {metadata['artist']}")
if not any(key in metadata for key in ['duration', 'title', 'artist']):
output.append("[dim]No metadata found[/dim]")
return "\n".join(output) if output else "[dim]No metadata found[/dim]"
def format_mediainfo_extraction_panel(self, rename_data: dict) -> str:
"""Format media info extraction data for the mediainfo panel"""
output = []
output.append("[bold green]MEDIA INFO EXTRACTION[/bold green]")
output.append("") # Empty line for spacing
output.append(f"[green]Resolution:[/green] {rename_data.get('resolution', 'Not found')}")
output.append(f"[green]Aspect Ratio:[/green] {rename_data.get('aspect_ratio', 'Not found')}")
output.append(f"[green]HDR:[/green] {rename_data.get('hdr', 'Not found')}")
output.append(f"[green]Audio Languages:[/green] {rename_data.get('audio_langs', 'Not found')}")
return "\n".join(output)
def format_proposed_name(self, rename_data: dict, ext_name: str) -> str: def format_proposed_name(self, rename_data: dict, ext_name: str) -> str:
"""Format the proposed filename""" """Format the proposed filename"""
@@ -49,8 +87,8 @@ class MediaFormatter:
proposed_parts.append(rename_data['source']) proposed_parts.append(rename_data['source'])
tags = [] tags = []
if rename_data['resolution']: if rename_data['frame_class'] and rename_data['frame_class'] != 'Unclassified':
tags.append(rename_data['resolution']) tags.append(rename_data['frame_class'])
if rename_data['hdr']: if rename_data['hdr']:
tags.append(rename_data['hdr']) tags.append(rename_data['hdr'])
if rename_data['audio_langs']: if rename_data['audio_langs']:
@@ -66,7 +104,9 @@ class MediaFormatter:
lines.append(f"Movie title: {rename_data['title'] or 'Unknown'}") lines.append(f"Movie title: {rename_data['title'] or 'Unknown'}")
lines.append(f"Year: {rename_data['year'] or 'Unknown'}") lines.append(f"Year: {rename_data['year'] or 'Unknown'}")
lines.append(f"Video source: {rename_data['source'] or 'Unknown'}") lines.append(f"Video source: {rename_data['source'] or 'Unknown'}")
lines.append(f"Frame class: {rename_data['frame_class'] or 'Unknown'}")
lines.append(f"Resolution: {rename_data['resolution'] or 'Unknown'}") lines.append(f"Resolution: {rename_data['resolution'] or 'Unknown'}")
lines.append(f"Aspect ratio: {rename_data['aspect_ratio'] or 'Unknown'}")
lines.append(f"HDR: {rename_data['hdr'] or 'No'}") lines.append(f"HDR: {rename_data['hdr'] or 'No'}")
lines.append(f"Audio langs: {rename_data['audio_langs'] or 'None'}") lines.append(f"Audio langs: {rename_data['audio_langs'] or 'None'}")
lines.append(f"Proposed filename: {proposed_name}") lines.append(f"Proposed filename: {proposed_name}")

View File

@@ -1,6 +1,44 @@
class ResolutionFormatter: class ResolutionFormatter:
"""Class for formatting video resolutions""" """Class for formatting video resolutions and frame classes"""
@staticmethod
def get_frame_class_from_resolution(resolution: str) -> str:
"""Convert resolution string (WIDTHxHEIGHT) to frame class (480p, 720p, etc.)"""
if not resolution:
return 'Unclassified'
try:
# Extract height from WIDTHxHEIGHT format
if 'x' in resolution:
height = int(resolution.split('x')[1])
else:
# Try to extract number directly
import re
match = re.search(r'(\d{3,4})', resolution)
if match:
height = int(match.group(1))
else:
return 'Unclassified'
if height == 4320:
return '4320p'
elif height >= 2160:
return '2160p'
elif height >= 1440:
return '1440p'
elif height >= 1080:
return '1080p'
elif height >= 720:
return '720p'
elif height >= 576:
return '576p'
elif height >= 480:
return '480p'
else:
return 'Unclassified'
except (ValueError, IndexError):
return 'Unclassified'
@staticmethod @staticmethod
def format_resolution_p(height: int) -> str: def format_resolution_p(height: int) -> str:
"""Format resolution as 2160p, 1080p, etc.""" """Format resolution as 2160p, 1080p, etc."""
@@ -14,7 +52,7 @@ class ResolutionFormatter:
return '480p' return '480p'
else: else:
return f'{height}p' return f'{height}p'
@staticmethod @staticmethod
def format_resolution_dimensions(width: int, height: int) -> str: def format_resolution_dimensions(width: int, height: int) -> str:
"""Format resolution as WIDTHxHEIGHT""" """Format resolution as WIDTHxHEIGHT"""

View File

@@ -1,6 +1,7 @@
import pytest import pytest
from pathlib import Path from pathlib import Path
from ..extractors.filename_extractor import FilenameExtractor from ..extractors.filename_extractor import FilenameExtractor
from ..constants import FRAME_CLASSES
def load_test_filenames(): def load_test_filenames():
@@ -17,6 +18,9 @@ def test_extract_title(filename):
"""Test title extraction from filename""" """Test title extraction from filename"""
file_path = Path(filename) file_path = Path(filename)
title = FilenameExtractor.extract_title(file_path) title = FilenameExtractor.extract_title(file_path)
# Print filename and extracted title clearly
print(f"\nFilename: \033[1;36m{filename}\033[0m")
print(f"Extracted title: \033[1;32m{title}\033[0m")
# For now, just check it's not None and is string # For now, just check it's not None and is string
assert isinstance(title, str) or title is None assert isinstance(title, str) or title is None
@@ -39,15 +43,23 @@ def test_extract_source(filename):
"""Test source extraction from filename""" """Test source extraction from filename"""
file_path = Path(filename) file_path = Path(filename)
source = FilenameExtractor.extract_source(file_path) source = FilenameExtractor.extract_source(file_path)
# Print filename and extracted source clearly
print(f"\nFilename: \033[1;36m{filename}\033[0m")
print(f"Extracted source: \033[1;32m{source}\033[0m")
# Source should be None or string # Source should be None or string
assert isinstance(source, str) or source is None assert isinstance(source, str) or source is None
@pytest.mark.parametrize("filename", load_test_filenames()) @pytest.mark.parametrize("filename", load_test_filenames())
def test_extract_resolution(filename): def test_extract_frame_class(filename):
"""Test resolution extraction from filename""" """Test frame class extraction from filename"""
file_path = Path(filename) file_path = Path(filename)
resolution = FilenameExtractor.extract_resolution(file_path) frame_class = FilenameExtractor.extract_frame_class(file_path)
# Resolution should be None or string like '2160p' # Print filename and extracted frame class clearly
if resolution: print(f"\nFilename: \033[1;36m{filename}\033[0m")
assert 'p' in resolution or 'i' in resolution print(f"Extracted frame_class: \033[1;32m{frame_class}\033[0m")
# Frame class should be a string
assert isinstance(frame_class, str)
# Should be one of the valid frame classes or 'Unclassified'
valid_classes = set(FRAME_CLASSES.keys()) | {'Unclassified'}
assert frame_class in valid_classes