cjm-capability-ffmpeg 0.0.25__py3-none-any.whl

cjm_capability_ffmpeg/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.0.25"

cjm_capability_ffmpeg/capability.py

@@ -0,0 +1,400 @@
+"""FFmpeg-based media processing capability implementing the MediaProcessingCapability interface.
+
+Stage 8 (Option C / PILLAR 1c): the tool re-bases onto ToolCapability (pure
+compute). The cache/persist bookends + the (action,input,config)->output_dir
+choice moved OUT to the generic media-processing adapter
+(cjm-media-processing-adapter-interface); the result DTOs live in
+cjm-capability-primitives. The adapter tells each artifact op WHERE to write.
+The ffmpeg helpers under utils/ were lifted from the retired cjm-ffmpeg-utils
+into this capability."""
+
+import json
+import logging
+import os
+import subprocess
+import uuid
+from dataclasses import dataclass, field
+from pathlib import Path
+from typing import Any, Dict, List, Optional, Union
+
+from cjm_capability_ffmpeg.utils.availability import FFMPEG_AVAILABLE
+from cjm_capability_ffmpeg.utils.codec import get_audio_codec
+from cjm_capability_ffmpeg.utils.probe import get_media_duration
+from cjm_capability_ffmpeg.utils.progress import run_ffmpeg_with_progress
+from cjm_capability_ffmpeg.utils.segments import extract_audio_segment
+from cjm_capability_primitives.media_processing import (MediaArtifactResult, MediaMetadata,
+                                                        MediaSegment, MediaSegmentationResult)
+from cjm_substrate.core.capability import ToolCapability
+from cjm_substrate.core.errors import CapabilityInputError
+from cjm_substrate.utils.validation import (config_to_dict, dataclass_to_jsonschema, dict_to_config,
+                                            SCHEMA_DESC, SCHEMA_ENUM, SCHEMA_TITLE)
+
+
+@dataclass
+class FFmpegCapabilityConfig:
+    """Configuration for the FFmpeg processing tool (the HOW knobs only).
+
+    Per-call WHAT-to-produce params (output_format / sample_rate / channels /
+    boundaries) are method arguments the adapter hashes into the cache key, NOT
+    config — only the quality/engine knobs live here. (The fused-era `output_dir`
+    config field is gone: the adapter chooses the output location, stage-8 L6.)"""
+
+    default_audio_format: str = field(
+        default="mp3",
+        metadata={
+            SCHEMA_TITLE: "Default Audio Format",
+            SCHEMA_DESC: "Fallback format for audio extraction when the source codec has no clean container mapping.",
+            SCHEMA_ENUM: ["mp3", "wav", "flac", "aac", "ogg", "m4a"]
+        }
+    )
+
+    default_audio_bitrate: str = field(
+        default="192k",
+        metadata={
+            SCHEMA_TITLE: "Default Audio Bitrate",
+            SCHEMA_DESC: "Bitrate for audio encoding operations (a quality knob; in the adapter cache key via get_current_config).",
+            SCHEMA_ENUM: ["128k", "192k", "256k", "320k"]
+        }
+    )
+
+    prefer_stream_copy: bool = field(
+        default=True,
+        metadata={
+            SCHEMA_TITLE: "Prefer Stream Copy",
+            SCHEMA_DESC: "When possible, copy the audio stream without re-encoding (faster, lossless)."
+        }
+    )
+
+    resampler: str = field(
+        default="soxr",
+        metadata={
+            SCHEMA_TITLE: "Resampler",
+            SCHEMA_DESC: "Audio resampling engine for sample-rate conversion. 'soxr' (libsoxr, high quality, matches librosa's soxr_hq) is preferred over ffmpeg's default 'swr'; needs an ffmpeg built --enable-libsoxr.",
+            SCHEMA_ENUM: ["soxr", "swr"]
+        }
+    )
+
+
+class FFmpegProcessingCapability(ToolCapability):
+    """FFmpeg-based media-processing tool capability (stage 8: pure compute).
+
+    Native-surface model (PILLAR 1c): PURE COMPUTE. The artifact ops
+    (`convert`/`segment_audio`/`extract_audio`) read input, run ffmpeg, and WRITE
+    file(s) into the adapter-supplied `output_dir`, returning typed DTOs;
+    `get_info` probes and returns `MediaMetadata`. The cache-check +
+    output-location choice + persistence live in the generic media-processing
+    adapter (cjm-media-processing-adapter-interface); result DTOs live in
+    cjm-capability-primitives; identity derives from the installed distribution.
+    No `get_plugin_metadata`, no `self.storage`, no in-tool cache, no
+    `execute`/`@capability_action` dispatcher (the task channel routes by method).
+
+    Config = the HOW knobs (resampler engine, bitrate, stream-copy preference,
+    fallback format); the per-call output_format/sample_rate/channels/boundaries
+    are WHAT-to-produce request params the adapter hashes into the cache key.
+    The fused-era `extract_segment` action was DROPPED (no consumer; the HITL
+    audio-chunk read is a future in-memory op, a different shape)."""
+
+    config_class = FFmpegCapabilityConfig
+
+    def __init__(self):
+        """Initialize the FFmpeg processing tool."""
+        self.logger = logging.getLogger(f"{__name__}.{type(self).__name__}")
+        self.config: Optional[FFmpegCapabilityConfig] = None
+
+    @property
+    def name(self) -> str:  # Tool identity, derived from the installed distribution (PILLAR 1c)
+        from importlib.metadata import metadata, packages_distributions
+        dist = (packages_distributions().get(__package__) or [__package__.replace("_", "-")])[0]
+        return metadata(dist)["Name"]
+
+    @property
+    def version(self) -> str:  # Tool version
+        from cjm_capability_ffmpeg import __version__
+        return __version__
+
+    def initialize(self,
+                   config: Optional[Any] = None,  # Configuration dict or None for defaults
+                  ) -> None:
+        """First-time setup. No storage init — the adapter owns the cache (stage 8)."""
+        self.config = dict_to_config(FFmpegCapabilityConfig, config or {})
+        self.logger.info(f"Initialized FFmpeg tool (format={self.config.default_audio_format})")
+
+    def get_config_schema(self) -> Dict[str, Any]:  # JSON Schema for UI form generation
+        """Return the JSON Schema for tool configuration."""
+        return dataclass_to_jsonschema(FFmpegCapabilityConfig)
+
+    def get_current_config(self) -> Dict[str, Any]:  # Current config as dict
+        """Return the current configuration as a dictionary."""
+        return config_to_dict(self.config) if self.config else {}
+
+    def is_available(self) -> bool:  # Whether ffmpeg is installed
+        """Check if ffmpeg is available on this system."""
+        return FFMPEG_AVAILABLE
+
+    # ------------------------------------------------------------------
+    # Private helper
+    # ------------------------------------------------------------------
+
+    def _detect_audio_codec(self,
+                            file_path: str,  # Path to media file
+                           ) -> Optional[str]:  # Audio codec name or None
+        """Detect the audio codec in a media file via ffprobe."""
+        cmd = [
+            'ffprobe', '-v', 'quiet',
+            '-select_streams', 'a:0',
+            '-show_entries', 'stream=codec_name',
+            '-of', 'csv=p=0',
+            file_path
+        ]
+        try:
+            result = subprocess.run(cmd, check=True, capture_output=True, text=True)
+            codec = result.stdout.strip()
+            return codec if codec else None
+        except subprocess.CalledProcessError:
+            return None
+
+    # ------------------------------------------------------------------
+    # Pure-compute probe (uncached)
+    # ------------------------------------------------------------------
+
+    def get_info(self,
+                 file_path: Union[str, Path],  # Path to media file
+                ) -> MediaMetadata:  # Probed metadata
+        """Probe metadata for a media file via ffprobe (UNCACHED pure-query)."""
+        file_path = str(file_path)
+        if not os.path.exists(file_path):
+            raise CapabilityInputError(  # SG-47: missing input file
+                f"File not found: {file_path}", fields_invalid=["file_path"],
+            )
+
+        cmd = [
+            'ffprobe', '-v', 'quiet',
+            '-show_format', '-show_streams', '-of', 'json',
+            file_path
+        ]
+        result = subprocess.run(cmd, check=True, capture_output=True, text=True)
+        probe_data = json.loads(result.stdout)
+
+        format_info = probe_data.get('format', {})
+        duration = float(format_info.get('duration', 0))
+        size_bytes = int(format_info.get('size', 0))
+        container_format = format_info.get('format_name', '')
+
+        video_streams = []
+        audio_streams = []
+        for stream in probe_data.get('streams', []):
+            codec_type = stream.get('codec_type', '')
+            if codec_type == 'video':
+                video_streams.append({
+                    'codec': stream.get('codec_name'),
+                    'width': stream.get('width'),
+                    'height': stream.get('height'),
+                    'fps': stream.get('r_frame_rate'),
+                })
+            elif codec_type == 'audio':
+                stream_duration = float(stream.get('duration', duration))
+                audio_streams.append({
+                    'codec': stream.get('codec_name'),
+                    'sample_rate': int(stream.get('sample_rate', 0)),
+                    'channels': int(stream.get('channels', 0)),
+                    'duration': stream_duration,
+                })
+
+        return MediaMetadata(
+            path=file_path,
+            duration=duration,
+            format=container_format,
+            size_bytes=size_bytes,
+            video_streams=video_streams,
+            audio_streams=audio_streams,
+        )
+
+    # ------------------------------------------------------------------
+    # Pure-compute artifact ops (write into the adapter-supplied output_dir)
+    # ------------------------------------------------------------------
+
+    def convert(self,
+                input_path: Union[str, Path],     # Source (or upstream artifact) media to convert
+                output_dir: str,                  # Adapter-chosen dir to write the artifact into
+                output_format: str,               # Target audio format (e.g. 'wav', 'mp3')
+                sample_rate: Optional[int] = None,  # Target sample rate (e.g. 16000); None = source rate
+                channels: Optional[int] = None,     # Target channel count (e.g. 1 = mono); None = source
+                **kwargs                          # Provenance pass-through (unused by compute)
+               ) -> MediaArtifactResult:  # The produced converted-audio artifact
+        """Convert media to target/model-ready audio — PURE COMPUTE.
+
+        Writes `<output_dir>/<stem>.<output_format>` and returns its pointer. The
+        quality knobs (bitrate, resampler) come from `self.config`; the shape
+        params (format/rate/channels) are the per-call request (the adapter hashes
+        them into the cache key)."""
+        input_path = str(input_path)
+        if not os.path.exists(input_path):
+            raise CapabilityInputError(  # SG-47: missing input file
+                f"File not found: {input_path}", fields_invalid=["input_path"],
+            )
+
+        bitrate = self.config.default_audio_bitrate
+        resampler = self.config.resampler
+
+        os.makedirs(output_dir, exist_ok=True)
+        stem = Path(input_path).stem
+        output_path = os.path.join(output_dir, f"{stem}.{output_format}")
+
+        total_duration = get_media_duration(Path(input_path))
+        codec = get_audio_codec(output_format)
+
+        cmd = ['ffmpeg', '-i', input_path, '-vn', '-acodec', codec]
+        if bitrate:
+            cmd.extend(['-b:a', bitrate])
+        if sample_rate:
+            # Resample with the configured engine (soxr by default — libsoxr at HQ
+            # precision, matching librosa's soxr_hq), standardizing model-ready input.
+            if resampler:
+                cmd.extend(['-af', f'aresample=resampler={resampler}:precision=20'])
+            cmd.extend(['-ar', str(sample_rate)])
+        if channels:
+            cmd.extend(['-ac', str(channels)])
+        cmd.extend(['-progress', 'pipe:2', '-y', output_path])
+
+        self.report_progress(0.0, f"Converting to {output_format}...")
+        run_ffmpeg_with_progress(
+            cmd=cmd, total_duration=total_duration,
+            description=f"Converting to {output_format}"
+        )
+        self.report_progress(1.0, "Complete")
+        self.logger.info(f"Converted {input_path} -> {output_path}")
+
+        return MediaArtifactResult(output_path=output_path, metadata={
+            "output_format": output_format, "sample_rate": sample_rate, "channels": channels,
+            "resampler": resampler, "bitrate": bitrate, "duration": total_duration,
+        })
+
+    def segment_audio(self,
+                      input_path: Union[str, Path],         # Source audio to cut
+                      output_dir: str,                      # Adapter-chosen dir to write the segments into
+                      boundaries: List[Dict[str, float]],   # [{"start", "end"}, ...]
+                      output_format: Optional[str] = None,  # Output format (default: same as input)
+                      filename_template: str = "segment_{index:03d}",  # Per-segment filename pattern
+                      **kwargs                              # Provenance pass-through (unused by compute)
+                     ) -> MediaSegmentationResult:  # The produced batch of segment files
+        """Split an audio file into segments at the given boundaries — PURE COMPUTE.
+
+        Writes one file per boundary into `output_dir` and returns the typed batch
+        result. Batch-level caching is the adapter's concern (one row per
+        (input, boundaries+format config); the per-segment resume-skip the fused
+        tool did is intentionally not reproduced)."""
+        input_path = str(input_path)
+        if not os.path.exists(input_path):
+            raise CapabilityInputError(  # SG-47: missing input file
+                f"File not found: {input_path}", fields_invalid=["input_path"],
+            )
+        if not boundaries:
+            raise CapabilityInputError(  # SG-47: typed input-validation
+                "boundaries list must not be empty", fields_invalid=["boundaries"],
+            )
+        # Validate boundaries are sorted and non-overlapping.
+        for i, b in enumerate(boundaries):
+            if b["end"] <= b["start"]:
+                raise CapabilityInputError(
+                    f"Boundary {i}: end ({b['end']}) must be > start ({b['start']})",
+                    fields_invalid=["boundaries"],
+                )
+            if i > 0 and b["start"] < boundaries[i - 1]["end"]:
+                raise CapabilityInputError(
+                    f"Boundary {i} start ({b['start']}) overlaps boundary {i-1} end ({boundaries[i-1]['end']})",
+                    fields_invalid=["boundaries"],
+                )
+
+        ext = output_format or Path(input_path).suffix.lstrip('.')
+        os.makedirs(output_dir, exist_ok=True)
+        batch_key = str(uuid.uuid4())
+        total = len(boundaries)
+
+        segments: List[MediaSegment] = []
+        for i, boundary in enumerate(boundaries):
+            start = boundary["start"]
+            end = boundary["end"]
+            duration = end - start
+            filename = f"{filename_template.format(index=i)}.{ext}"
+            output_path = os.path.join(output_dir, filename)
+            extract_audio_segment(
+                input_path=Path(input_path),
+                output_path=Path(output_path),
+                start_time=str(start),
+                duration=str(duration),
+            )
+            segments.append(MediaSegment(
+                index=i, output_path=output_path, start=start, end=end, duration=duration,
+            ))
+            self.report_progress((i + 1) / total, f"Segment {i + 1}/{total}")
+
+        total_duration = sum(s.duration for s in segments)
+        self.report_progress(1.0, f"Complete: {total} segments")
+        self.logger.info(f"Segmented {input_path} into {total} segments (batch_key={batch_key})")
+
+        return MediaSegmentationResult(
+            segments=segments, input_path=input_path, segment_count=total,
+            total_duration=total_duration, batch_key=batch_key,
+        )
+
+    def extract_audio(self,
+                      input_path: Union[str, Path],         # Source video container
+                      output_dir: str,                      # Adapter-chosen dir to write the artifact into
+                      output_format: Optional[str] = None,  # Audio format (default: from codec detection)
+                      **kwargs                              # Provenance pass-through (unused by compute)
+                     ) -> MediaArtifactResult:  # The produced extracted-audio artifact
+        """Extract the audio stream from a video container — PURE COMPUTE.
+
+        Stream-copies when the source codec maps cleanly (lossless, fast),
+        otherwise re-encodes to the resolved format. Writes into `output_dir`."""
+        input_path = str(input_path)
+        if not os.path.exists(input_path):
+            raise CapabilityInputError(  # SG-47: missing input file
+                f"File not found: {input_path}", fields_invalid=["input_path"],
+            )
+
+        codec = self._detect_audio_codec(input_path)
+        if not codec:
+            raise CapabilityInputError(  # SG-47: input file has no audio stream
+                f"No audio stream found in: {input_path}", fields_invalid=["input_path"],
+            )
+
+        stream_copy = self.config.prefer_stream_copy
+        if output_format is None:
+            codec_ext_map = {
+                'aac': 'm4a', 'mp3': 'mp3', 'vorbis': 'ogg', 'opus': 'ogg',
+                'flac': 'flac', 'pcm_s16le': 'wav', 'pcm_s24le': 'wav',
+            }
+            output_format = codec_ext_map.get(codec, self.config.default_audio_format)
+            if codec not in codec_ext_map:
+                stream_copy = False
+        else:
+            expected_codec = get_audio_codec(output_format)
+            if expected_codec != 'copy' and expected_codec != codec:
+                stream_copy = False
+
+        os.makedirs(output_dir, exist_ok=True)
+        stem = Path(input_path).stem
+        output_path = os.path.join(output_dir, f"{stem}.{output_format}")
+        total_duration = get_media_duration(Path(input_path))
+
+        cmd = ['ffmpeg', '-i', input_path, '-vn']
+        if stream_copy:
+            cmd.extend(['-acodec', 'copy'])
+        else:
+            cmd.extend(['-acodec', get_audio_codec(output_format)])
+            cmd.extend(['-b:a', self.config.default_audio_bitrate])
+        cmd.extend(['-progress', 'pipe:2', '-y', output_path])
+
+        self.report_progress(0.1, "Extracting audio stream...")
+        run_ffmpeg_with_progress(
+            cmd=cmd, total_duration=total_duration,
+            description="Extracting audio"
+        )
+        self.report_progress(1.0, "Complete")
+        self.logger.info(f"Extracted audio {input_path} -> {output_path} (stream_copy={stream_copy})")
+
+        return MediaArtifactResult(output_path=output_path, metadata={
+            "codec": codec, "duration": total_duration, "output_format": output_format,
+            "stream_copy": stream_copy, "source_video_path": input_path,
+        })

cjm_capability_ffmpeg/utils/availability.py

@@ -0,0 +1,12 @@
+"""Detect whether the ffmpeg binary is installed on this system."""
+
+import logging
+import shutil
+
+# Verify FFmpeg installation. True when the `ffmpeg` binary is on PATH.
+FFMPEG_AVAILABLE = shutil.which("ffmpeg") is not None
+if not FFMPEG_AVAILABLE:
+    logging.warning(
+        "FFmpeg not available - install the system package "
+        "(e.g. apt install ffmpeg, brew install ffmpeg, or https://ffmpeg.org/)"
+    )

cjm_capability_ffmpeg/utils/codec.py

@@ -0,0 +1,15 @@
+"""Map audio container formats to the ffmpeg codec used to encode them."""
+
+
+def get_audio_codec(audio_format: str  # The desired audio format (e.g. 'mp3', 'wav')
+                   ) -> str:  # The ffmpeg audio codec name ('copy' if unknown)
+    """Map an audio container format to the appropriate ffmpeg codec."""
+    codec_map = {
+        'mp3': 'libmp3lame',
+        'wav': 'pcm_s16le',
+        'flac': 'flac',
+        'aac': 'aac',
+        'ogg': 'libvorbis',
+        'm4a': 'aac',
+    }
+    return codec_map.get(audio_format.lower(), 'copy')

cjm_capability_ffmpeg/utils/probe.py

@@ -0,0 +1,24 @@
+"""Probe media files for metadata (duration, ...) via ffprobe."""
+
+import subprocess
+from pathlib import Path
+from typing import Optional
+
+
+def get_media_duration(file_path: Path  # Path to the media file
+                      ) -> Optional[float]:  # Duration in seconds, or None if it cannot be determined
+    """Get the duration of a media file (seconds) via ffprobe."""
+    duration_cmd = [
+        'ffprobe',
+        '-v', 'quiet',
+        '-show_entries', 'format=duration',
+        '-of', 'csv=p=0',
+        str(file_path),
+    ]
+    try:
+        duration_result = subprocess.run(
+            duration_cmd, check=True, capture_output=True, text=True,
+        )
+        return float(duration_result.stdout.strip())
+    except (subprocess.CalledProcessError, ValueError, FileNotFoundError):
+        return None

cjm_capability_ffmpeg/utils/progress.py

@@ -0,0 +1,97 @@
+"""Run ffmpeg subprocess commands with a progress bar and optional callback."""
+
+import subprocess
+from typing import Callable, List, Optional
+
+from tqdm.auto import tqdm
+
+
+def parse_progress_line(line: str  # A line of stderr output from ffmpeg
+                        ) -> Optional[float]:  # Current time in seconds, or None if the line has no progress info
+    """Parse a progress line from ffmpeg stderr output."""
+    # Look for time progress in the format "out_time_ms=123456789"
+    if line.startswith('out_time_ms='):
+        try:
+            time_ms = int(line.strip().split('=')[1])
+            return time_ms / 1000000.0  # microseconds -> seconds
+        except (ValueError, IndexError):
+            pass
+    # Alternative: look for time in the format "time=00:01:23.45"
+    elif line.startswith('time='):
+        try:
+            time_str = line.strip().split('=')[1]
+            time_parts = time_str.split(':')
+            if len(time_parts) == 3:
+                hours = float(time_parts[0])
+                minutes = float(time_parts[1])
+                seconds = float(time_parts[2])
+                return hours * 3600 + minutes * 60 + seconds
+        except (ValueError, IndexError):
+            pass
+    return None
+
+
+def run_ffmpeg_with_progress(
+    cmd: List[str],  # The ffmpeg command and arguments
+    total_duration: Optional[float] = None,  # Total duration in seconds for a determinate bar, else indeterminate
+    description: str = "Processing",  # Description text for the progress bar
+    verbose: bool = False,  # If True, prints detailed ffmpeg output
+    progress_callback: Optional[Callable[[float], None]] = None  # Optional callback receiving current progress in seconds
+) -> None:  # Raises FileNotFoundError or subprocess.CalledProcessError on failure
+    """Run an ffmpeg command with a progress bar."""
+    try:
+        if total_duration:
+            pbar = tqdm(
+                total=total_duration, unit='s', desc=description,
+                bar_format='{l_bar}{bar}| {n:.1f}/{total:.1f}s [{elapsed}<{remaining}]',
+            )
+        else:
+            pbar = tqdm(desc=description, unit='frames')
+
+        process = subprocess.Popen(
+            cmd, stderr=subprocess.PIPE, stdout=subprocess.PIPE,
+            text=True, bufsize=1, universal_newlines=True,
+        )
+
+        while process.poll() is None:  # while the process is running
+            line = process.stderr.readline()
+            if not line:
+                continue
+            if verbose:
+                print(line.strip())
+            current_time = parse_progress_line(line)
+            if current_time is not None:
+                if total_duration:
+                    pbar.n = min(current_time, total_duration)
+                    pbar.refresh()
+                else:
+                    pbar.update(1)
+                if progress_callback:
+                    progress_callback(current_time)
+
+        remaining_stderr = process.stderr.read()
+        if verbose and remaining_stderr:
+            print(remaining_stderr)
+
+        return_code = process.returncode
+        if total_duration:
+            pbar.n = total_duration
+            pbar.refresh()
+        pbar.close()
+
+        if return_code != 0:
+            stderr_output = remaining_stderr or ""
+            error_msg = f"FFmpeg failed with return code {return_code}"
+            if stderr_output:
+                error_msg += f"\nError output: {stderr_output}"
+            raise subprocess.CalledProcessError(return_code, cmd, error_msg)
+    except FileNotFoundError:
+        if 'pbar' in locals():
+            pbar.close()
+        raise FileNotFoundError(
+            "ffmpeg not found. Please install ffmpeg and ensure it's in your PATH."
+        )
+    except Exception:
+        if 'pbar' in locals():
+            pbar.close()
+        raise

cjm_capability_ffmpeg/utils/segments.py

@@ -0,0 +1,52 @@
+"""Extract temporal segments from audio files via ffmpeg stream-copy."""
+
+import subprocess
+from pathlib import Path
+
+from cjm_capability_ffmpeg.utils.progress import run_ffmpeg_with_progress
+
+
+def extract_audio_segment(input_path: Path,  # Path to the input audio file
+                          output_path: Path,  # Path where the extracted segment is saved
+                          start_time: str,  # Start time as "HH:MM:SS" or seconds
+                          duration: str,  # Duration as "HH:MM:SS" or seconds
+                          verbose: bool = False,  # If True, shows verbose ffmpeg output
+                          pbar: bool = False,  # If True, shows a progress bar
+                          copy_codec: bool = True,  # Stream-copy without re-encoding (fast)
+                        ) -> None:  # Raises subprocess.CalledProcessError if extraction fails
+    """Extract a temporal segment from an audio file."""
+    # Compute the expected segment duration for the progress bar.
+    try:
+        segment_duration = float(duration)
+    except ValueError:
+        time_parts = duration.split(':')
+        if len(time_parts) == 3:
+            hours = float(time_parts[0])
+            minutes = float(time_parts[1])
+            seconds = float(time_parts[2])
+            segment_duration = hours * 3600 + minutes * 60 + seconds
+        else:
+            segment_duration = None
+
+    # Place -ss before -i for fast input seeking (seeks to the nearest keyframe).
+    cmd = [
+        'ffmpeg',
+        '-ss', start_time,
+        '-i', str(input_path),
+        '-t', duration,
+    ]
+    if copy_codec:
+        cmd.extend(['-acodec', 'copy'])
+    cmd.extend(['-progress', 'pipe:2', '-y', str(output_path)])
+
+    if pbar:
+        run_ffmpeg_with_progress(
+            cmd=cmd, total_duration=segment_duration,
+            description="Extracting segment", verbose=verbose,
+        )
+    else:
+        result = subprocess.run(
+            cmd, stdout=subprocess.DEVNULL, stderr=subprocess.PIPE, text=True,
+        )
+        if result.returncode != 0:
+            raise subprocess.CalledProcessError(result.returncode, cmd)

cjm_capability_ffmpeg-0.0.25.dist-info/METADATA

@@ -0,0 +1,59 @@
+Metadata-Version: 2.4
+Name: cjm-capability-ffmpeg
+Version: 0.0.25
+Summary: An FFmpeg-based media-processing capability for the cjm-substrate runtime that provides audio extraction, segmentation, and format conversion.
+Author-email: "Christian J. Mills" <9126128+cj-mills@users.noreply.github.com>
+License: Apache-2.0
+Project-URL: Repository, https://github.com/cj-mills/cjm-capability-ffmpeg
+Keywords: python
+Classifier: Natural Language :: English
+Classifier: Intended Audience :: Developers
+Classifier: Development Status :: 3 - Alpha
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Requires-Python: >=3.12
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: cjm-substrate>=0.0.51
+Requires-Dist: cjm-capability-primitives>=0.0.10
+Requires-Dist: tqdm
+Dynamic: license-file
+
+# cjm-capability-ffmpeg
+
+<!-- generated from the context graph by `cjm-context-graph readme` — do not edit by hand; edit the graph (the urge to hand-edit = move it on-graph) -->
+
+An FFmpeg-based media-processing capability for the cjm-substrate runtime that provides audio extraction, segmentation, and format conversion.
+
+## Modules
+
+- **`cjm_capability_ffmpeg.capability`** — FFmpeg-based media processing capability implementing the MediaProcessingCapability interface.
+- **`cjm_capability_ffmpeg.utils.availability`** — Detect whether the ffmpeg binary is installed on this system.
+- **`cjm_capability_ffmpeg.utils.codec`** — Map audio container formats to the ffmpeg codec used to encode them.
+- **`cjm_capability_ffmpeg.utils.probe`** — Probe media files for metadata (duration, ...) via ffprobe.
+- **`cjm_capability_ffmpeg.utils.progress`** — Run ffmpeg subprocess commands with a progress bar and optional callback.
+- **`cjm_capability_ffmpeg.utils.segments`** — Extract temporal segments from audio files via ffmpeg stream-copy.
+
+## API
+
+### `cjm_capability_ffmpeg.capability`
+
+- `FFmpegCapabilityConfig` _class_ — Configuration for the FFmpeg processing tool (the HOW knobs only).
+- `FFmpegProcessingCapability` _class_ — FFmpeg-based media-processing tool capability (stage 8: pure compute).
+
+### `cjm_capability_ffmpeg.utils.codec`
+
+- `get_audio_codec` _function_ — Map an audio container format to the appropriate ffmpeg codec.
+
+### `cjm_capability_ffmpeg.utils.probe`
+
+- `get_media_duration` _function_ — Get the duration of a media file (seconds) via ffprobe.
+
+### `cjm_capability_ffmpeg.utils.progress`
+
+- `parse_progress_line` _function_ — Parse a progress line from ffmpeg stderr output.
+- `run_ffmpeg_with_progress` _function_ — Run an ffmpeg command with a progress bar.
+
+### `cjm_capability_ffmpeg.utils.segments`
+
+- `extract_audio_segment` _function_ — Extract a temporal segment from an audio file.

cjm_capability_ffmpeg-0.0.25.dist-info/RECORD

@@ -0,0 +1,13 @@
+cjm_capability_ffmpeg/__init__.py,sha256=ognSasPrsQjE8uJUk5Fcsl4caTERui00vZnmFlQnMoU,23
+cjm_capability_ffmpeg/capability.py,sha256=JMOgFQIKTANvNzMe8qONcSN5xuDx8IMfqUafJqjQuso,19062
+cjm_capability_ffmpeg/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+cjm_capability_ffmpeg/utils/availability.py,sha256=t3yfTOkYiAwcHzRW1UbOB7oz3vheAWzHewyQtG0zz8c,419
+cjm_capability_ffmpeg/utils/codec.py,sha256=X-B2jw3BbXLUKj1FGV4eUp6c6adyXH6FuXujyF8Plko,548
+cjm_capability_ffmpeg/utils/probe.py,sha256=hNDVXNHQVz2uujVe7OeNj8PtMMtOSqPZ7kJdao8-I80,816
+cjm_capability_ffmpeg/utils/progress.py,sha256=AwmgdNt5kL3wZzpNAH7dEfulHLYclS0kLjcxlJO08KU,3828
+cjm_capability_ffmpeg/utils/segments.py,sha256=Ruz0fsGfX4uyd9x83KFBTRURWzoEy6m2oj5szzATh4I,2132
+cjm_capability_ffmpeg-0.0.25.dist-info/licenses/LICENSE,sha256=xV8xoN4VOL0uw9X8RSs2IMuD_Ss_a9yAbtGNeBWZwnw,11337
+cjm_capability_ffmpeg-0.0.25.dist-info/METADATA,sha256=06TfKe6GcdyMX7w4aBt6Zawo3nT67DRIWDfuC5fOHpE,2806
+cjm_capability_ffmpeg-0.0.25.dist-info/WHEEL,sha256=K260EYznzXsJYBQGqmI8VTxEdiZYNvDZwW9cBh9-_MA,91
+cjm_capability_ffmpeg-0.0.25.dist-info/top_level.txt,sha256=S6sh1sdHi7wMuCAncf9Z-fPbxJJQzCE7SBfmUnwAApo,22
+cjm_capability_ffmpeg-0.0.25.dist-info/RECORD,,

cjm_capability_ffmpeg-0.0.25.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (83.0.0)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

cjm_capability_ffmpeg-0.0.25.dist-info/licenses/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2022, fastai
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

cjm_capability_ffmpeg-0.0.25.dist-info/top_level.txt

@@ -0,0 +1 @@
+cjm_capability_ffmpeg