cjm-media-processing-adapter-interface 0.0.2__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -0,0 +1 @@
1
+ __version__ = "0.0.2"
@@ -0,0 +1,65 @@
1
+ # Autogenerated by nbdev
2
+
3
+ d = { 'settings': { 'branch': 'main',
4
+ 'doc_baseurl': '/cjm-media-processing-adapter-interface',
5
+ 'doc_host': 'https://cj-mills.github.io',
6
+ 'git_url': 'https://github.com/cj-mills/cjm-media-processing-adapter-interface',
7
+ 'lib_path': 'cjm_media_processing_adapter_interface'},
8
+ 'syms': { 'cjm_media_processing_adapter_interface.adapter': { 'cjm_media_processing_adapter_interface.adapter.MediaProcessingAdapter': ( 'adapter.html#mediaprocessingadapter',
9
+ 'cjm_media_processing_adapter_interface/adapter.py'),
10
+ 'cjm_media_processing_adapter_interface.adapter.MediaProcessingAdapter.__init__': ( 'adapter.html#mediaprocessingadapter.__init__',
11
+ 'cjm_media_processing_adapter_interface/adapter.py'),
12
+ 'cjm_media_processing_adapter_interface.adapter.MediaProcessingAdapter.convert': ( 'adapter.html#mediaprocessingadapter.convert',
13
+ 'cjm_media_processing_adapter_interface/adapter.py'),
14
+ 'cjm_media_processing_adapter_interface.adapter.MediaProcessingAdapter.extract_audio': ( 'adapter.html#mediaprocessingadapter.extract_audio',
15
+ 'cjm_media_processing_adapter_interface/adapter.py'),
16
+ 'cjm_media_processing_adapter_interface.adapter.MediaProcessingAdapter.get_info': ( 'adapter.html#mediaprocessingadapter.get_info',
17
+ 'cjm_media_processing_adapter_interface/adapter.py'),
18
+ 'cjm_media_processing_adapter_interface.adapter.MediaProcessingAdapter.segment_audio': ( 'adapter.html#mediaprocessingadapter.segment_audio',
19
+ 'cjm_media_processing_adapter_interface/adapter.py'),
20
+ 'cjm_media_processing_adapter_interface.adapter.MediaProcessingToolProtocol': ( 'adapter.html#mediaprocessingtoolprotocol',
21
+ 'cjm_media_processing_adapter_interface/adapter.py'),
22
+ 'cjm_media_processing_adapter_interface.adapter.MediaProcessingToolProtocol.convert': ( 'adapter.html#mediaprocessingtoolprotocol.convert',
23
+ 'cjm_media_processing_adapter_interface/adapter.py'),
24
+ 'cjm_media_processing_adapter_interface.adapter.MediaProcessingToolProtocol.extract_audio': ( 'adapter.html#mediaprocessingtoolprotocol.extract_audio',
25
+ 'cjm_media_processing_adapter_interface/adapter.py'),
26
+ 'cjm_media_processing_adapter_interface.adapter.MediaProcessingToolProtocol.get_current_config': ( 'adapter.html#mediaprocessingtoolprotocol.get_current_config',
27
+ 'cjm_media_processing_adapter_interface/adapter.py'),
28
+ 'cjm_media_processing_adapter_interface.adapter.MediaProcessingToolProtocol.get_info': ( 'adapter.html#mediaprocessingtoolprotocol.get_info',
29
+ 'cjm_media_processing_adapter_interface/adapter.py'),
30
+ 'cjm_media_processing_adapter_interface.adapter.MediaProcessingToolProtocol.segment_audio': ( 'adapter.html#mediaprocessingtoolprotocol.segment_audio',
31
+ 'cjm_media_processing_adapter_interface/adapter.py')},
32
+ 'cjm_media_processing_adapter_interface.generic': { 'cjm_media_processing_adapter_interface.generic.GenericMediaProcessingAdapter': ( 'generic.html#genericmediaprocessingadapter',
33
+ 'cjm_media_processing_adapter_interface/generic.py'),
34
+ 'cjm_media_processing_adapter_interface.generic.GenericMediaProcessingAdapter._artifact_op': ( 'generic.html#genericmediaprocessingadapter._artifact_op',
35
+ 'cjm_media_processing_adapter_interface/generic.py'),
36
+ 'cjm_media_processing_adapter_interface.generic.GenericMediaProcessingAdapter._cache_inputs': ( 'generic.html#genericmediaprocessingadapter._cache_inputs',
37
+ 'cjm_media_processing_adapter_interface/generic.py'),
38
+ 'cjm_media_processing_adapter_interface.generic.GenericMediaProcessingAdapter._force': ( 'generic.html#genericmediaprocessingadapter._force',
39
+ 'cjm_media_processing_adapter_interface/generic.py'),
40
+ 'cjm_media_processing_adapter_interface.generic.GenericMediaProcessingAdapter._get_storage': ( 'generic.html#genericmediaprocessingadapter._get_storage',
41
+ 'cjm_media_processing_adapter_interface/generic.py'),
42
+ 'cjm_media_processing_adapter_interface.generic.GenericMediaProcessingAdapter.convert': ( 'generic.html#genericmediaprocessingadapter.convert',
43
+ 'cjm_media_processing_adapter_interface/generic.py'),
44
+ 'cjm_media_processing_adapter_interface.generic.GenericMediaProcessingAdapter.extract_audio': ( 'generic.html#genericmediaprocessingadapter.extract_audio',
45
+ 'cjm_media_processing_adapter_interface/generic.py'),
46
+ 'cjm_media_processing_adapter_interface.generic.GenericMediaProcessingAdapter.get_info': ( 'generic.html#genericmediaprocessingadapter.get_info',
47
+ 'cjm_media_processing_adapter_interface/generic.py'),
48
+ 'cjm_media_processing_adapter_interface.generic.GenericMediaProcessingAdapter.segment_audio': ( 'generic.html#genericmediaprocessingadapter.segment_audio',
49
+ 'cjm_media_processing_adapter_interface/generic.py')},
50
+ 'cjm_media_processing_adapter_interface.storage': { 'cjm_media_processing_adapter_interface.storage.MediaProcessingRow': ( 'storage.html#mediaprocessingrow',
51
+ 'cjm_media_processing_adapter_interface/storage.py'),
52
+ 'cjm_media_processing_adapter_interface.storage.MediaProcessingStorage': ( 'storage.html#mediaprocessingstorage',
53
+ 'cjm_media_processing_adapter_interface/storage.py'),
54
+ 'cjm_media_processing_adapter_interface.storage.MediaProcessingStorage.__init__': ( 'storage.html#mediaprocessingstorage.__init__',
55
+ 'cjm_media_processing_adapter_interface/storage.py'),
56
+ 'cjm_media_processing_adapter_interface.storage.MediaProcessingStorage.get_cached': ( 'storage.html#mediaprocessingstorage.get_cached',
57
+ 'cjm_media_processing_adapter_interface/storage.py'),
58
+ 'cjm_media_processing_adapter_interface.storage.MediaProcessingStorage.list_jobs': ( 'storage.html#mediaprocessingstorage.list_jobs',
59
+ 'cjm_media_processing_adapter_interface/storage.py'),
60
+ 'cjm_media_processing_adapter_interface.storage.MediaProcessingStorage.save': ( 'storage.html#mediaprocessingstorage.save',
61
+ 'cjm_media_processing_adapter_interface/storage.py'),
62
+ 'cjm_media_processing_adapter_interface.storage.MediaProcessingStorage.save_with_logging': ( 'storage.html#mediaprocessingstorage.save_with_logging',
63
+ 'cjm_media_processing_adapter_interface/storage.py'),
64
+ 'cjm_media_processing_adapter_interface.storage.MediaProcessingStorage.verify_input': ( 'storage.html#mediaprocessingstorage.verify_input',
65
+ 'cjm_media_processing_adapter_interface/storage.py')}}}
@@ -0,0 +1,130 @@
1
+ """The typed media-processing task contract — the multi-method `MediaProcessingAdapter` ABC + the `MediaProcessingToolProtocol` structural contract (capability-unit Option C, pass-2 Thread 3). ONE multi-method adapter for the media-processing tool's whole repertoire (the graph-storage precedent), NOT per-action adapters.
2
+
3
+ Docs: https://cj-mills.github.io/cjm-media-processing-adapter-interfaceadapter.html.md"""
4
+
5
+ # AUTOGENERATED! DO NOT EDIT! File to edit: ../nbs/adapter.ipynb.
6
+
7
+ # %% auto #0
8
+ __all__ = ['MediaProcessingToolProtocol', 'MediaProcessingAdapter']
9
+
10
+ # %% ../nbs/adapter.ipynb #a7b39b97
11
+ from abc import abstractmethod
12
+ from pathlib import Path
13
+ from typing import Any, ClassVar, Dict, List, Optional, Protocol, Union, runtime_checkable
14
+
15
+ from cjm_plugin_system.core.adapter import TaskAdapter
16
+
17
+ # Canonical home (stage 8 / PILLAR 1c): the data nouns live in
18
+ # cjm-capability-primitives, so the pure-compute tool depends on them, never on
19
+ # this adapter machinery.
20
+ from cjm_capability_primitives.media_processing import (
21
+ MediaArtifactResult, MediaSegmentationResult, MediaMetadata,
22
+ )
23
+
24
+ # %% ../nbs/adapter.ipynb #edacb217
25
+ @runtime_checkable
26
+ class MediaProcessingToolProtocol(Protocol):
27
+ """Structural contract for media-processing tool capabilities (ffmpeg today;
28
+ born-final at stage 8 — derived from the native tool surface).
29
+
30
+ Artifact-producing ops (`convert`, `segment_audio`, `extract_audio`) are pure
31
+ compute that WRITE audio file(s) into the adapter-chosen `output_dir` (the
32
+ artifact-write seam) and return a typed pointer. `get_info` is a pure-query
33
+ probe returning inline `MediaMetadata` (no artifact). `get_current_config`
34
+ supplies the effective config the generic adapter hashes (together with the
35
+ per-call request params) for its cache key.
36
+
37
+ The `output_dir` parameter on the artifact ops is the adapter telling the
38
+ tool WHERE to persist (the `db_path`-off-the-tool rule); encoding the audio
39
+ stays tool-side compute. Per-call request params (`output_format`,
40
+ `sample_rate`, `channels`, `boundaries`, `filename_template`) define WHAT
41
+ artifact to produce and are hashed into the cache key."""
42
+ def convert(self, input_path: Union[str, Path], output_dir: str,
43
+ output_format: str, sample_rate: Optional[int] = None,
44
+ channels: Optional[int] = None, **kwargs) -> MediaArtifactResult: ...
45
+ def segment_audio(self, input_path: Union[str, Path], output_dir: str,
46
+ boundaries: List[Dict[str, float]], output_format: Optional[str] = None,
47
+ filename_template: str = "segment_{index:03d}", **kwargs) -> MediaSegmentationResult: ...
48
+ def extract_audio(self, input_path: Union[str, Path], output_dir: str,
49
+ output_format: Optional[str] = None, **kwargs) -> MediaArtifactResult: ...
50
+ def get_info(self, file_path: Union[str, Path]) -> MediaMetadata: ...
51
+ def get_current_config(self) -> Dict[str, Any]: ...
52
+
53
+ # %% ../nbs/adapter.ipynb #9c358302
54
+ class MediaProcessingAdapter(TaskAdapter):
55
+ """Typed media-processing task adapter — ONE multi-method adapter for the
56
+ media-processing tool's whole repertoire (the graph-storage multi-method
57
+ precedent, NOT per-action adapters: the `task_name` key answers "which tools
58
+ do media-processing", and there is one such tool — ffmpeg — that will gain
59
+ MORE ops over time, e.g. building video from images + audio, so per-action
60
+ would only multiply task families + libs without aiding discovery).
61
+
62
+ Native-surface model (stage 8 / PILLAR 1c): the TOOL is pure compute; the
63
+ ADAPTER owns the cache + persistence bookends (see
64
+ `GenericMediaProcessingAdapter`) + the per-call `force` control. The
65
+ artifact ops write audio file(s) under the substrate-injected
66
+ `PLUGIN_DATA_DIR`; the cache row maps (action, input, config) -> output(s).
67
+ The adapter chooses the output location and passes it to the tool; `db_path`
68
+ is not on the tool protocol. `get_info` is an UNCACHED pure-query
69
+ pass-through (a probe; no artifact).
70
+
71
+ Input contract: `convert`/`segment_audio` receive a source (or an upstream
72
+ artifact, e.g. a vocals stem) path; the produced WAVs ARE the model-ready
73
+ audio downstream consumers (VAD/transcription) use. `extract_audio` pulls an
74
+ audio stream from a video container (the non-minimal video-input path).
75
+ Implementations run in-worker beside their tool, constructed
76
+ `AdapterClass(tool)` (mirrors `GraphStorageAdapter`). Result DTOs are
77
+ wire-registered (`media_processing.{artifact,segmentation,metadata}`) so
78
+ returned values cross the worker boundary typed.
79
+ """
80
+
81
+ task_name: ClassVar[str] = "media_processing"
82
+ required_tool_protocol: ClassVar[type] = MediaProcessingToolProtocol
83
+
84
+ def __init__(
85
+ self,
86
+ tool: MediaProcessingToolProtocol, # The bound tool capability instance (worker-side binding)
87
+ ):
88
+ self.tool = tool
89
+
90
+ @abstractmethod
91
+ def convert(
92
+ self,
93
+ input_path: Union[str, Path], # Source (or upstream artifact) audio/video to convert
94
+ output_format: str, # Target audio format (e.g. 'wav', 'mp3')
95
+ sample_rate: Optional[int] = None, # Target sample rate (e.g. 16000 for model input); None = source rate
96
+ channels: Optional[int] = None, # Target channel count (e.g. 1 = mono); None = source channels
97
+ **kwargs, # Provenance + tool options
98
+ ) -> MediaArtifactResult: # The produced converted-audio artifact (cached)
99
+ """Convert media to target/model-ready audio (cached artifact)."""
100
+ ...
101
+
102
+ @abstractmethod
103
+ def segment_audio(
104
+ self,
105
+ input_path: Union[str, Path], # Source audio to cut
106
+ boundaries: List[Dict[str, float]], # [{start, end}, ...] cut points (seconds)
107
+ output_format: Optional[str] = None, # Output format; None = same as input
108
+ filename_template: str = "segment_{index:03d}", # Per-segment filename pattern
109
+ **kwargs, # Provenance + tool options
110
+ ) -> MediaSegmentationResult: # The produced batch of segment files (cached at batch level)
111
+ """Cut a source into a batch of segment files at the given boundaries (cached batch)."""
112
+ ...
113
+
114
+ @abstractmethod
115
+ def extract_audio(
116
+ self,
117
+ input_path: Union[str, Path], # Source video container
118
+ output_format: Optional[str] = None, # Audio format; None = codec-derived
119
+ **kwargs, # Provenance + tool options
120
+ ) -> MediaArtifactResult: # The produced extracted-audio artifact (cached)
121
+ """Extract the audio stream from a video container (cached artifact)."""
122
+ ...
123
+
124
+ @abstractmethod
125
+ def get_info(
126
+ self,
127
+ file_path: Union[str, Path], # Media file to probe
128
+ ) -> MediaMetadata: # Probed metadata (uncached)
129
+ """Probe media metadata (uncached pure-query)."""
130
+ ...
@@ -0,0 +1,144 @@
1
+ """The generic (tool-agnostic) multi-method media-processing adapter — cache-bookended artifact ops (`convert` / `segment_audio` / `extract_audio`) + an uncached `get_info` probe. Reused across every tool capability satisfying `MediaProcessingToolProtocol` (ffmpeg today).
2
+
3
+ Docs: https://cj-mills.github.io/cjm-media-processing-adapter-interfacegeneric.html.md"""
4
+
5
+ # AUTOGENERATED! DO NOT EDIT! File to edit: ../nbs/generic.ipynb.
6
+
7
+ # %% auto #0
8
+ __all__ = ['GenericMediaProcessingAdapter']
9
+
10
+ # %% ../nbs/generic.ipynb #81d6c059
11
+ import os
12
+ from pathlib import Path
13
+ from typing import Any, Callable, Dict, List, Optional, Union
14
+
15
+ from cjm_plugin_system.core.wire import get_call_envelope
16
+ from cjm_plugin_system.utils.hashing import hash_file, hash_dict_canonical
17
+ from cjm_plugin_system.utils.cache_paths import cache_dir_for_config
18
+
19
+ from cjm_capability_primitives.media_processing import (
20
+ MediaArtifactResult, MediaSegmentationResult, MediaMetadata,
21
+ )
22
+ from .adapter import MediaProcessingAdapter
23
+ from .storage import MediaProcessingStorage
24
+
25
+ # %% ../nbs/generic.ipynb #a11b0d2b
26
+ class GenericMediaProcessingAdapter(MediaProcessingAdapter):
27
+ """Generic multi-method media-processing adapter, reused across any tool
28
+ satisfying `MediaProcessingToolProtocol`.
29
+
30
+ Artifact ops (`convert`/`extract_audio`/`segment_audio`) share the
31
+ source-separation bookend (cache-check + artifact-existence recheck ->
32
+ adapter-chosen `output_dir` -> tool -> persist). `get_info` is an uncached
33
+ pass-through. The cache key hashes `get_current_config()` together with the
34
+ per-call request params, and `force` rides `CallEnvelope.control` (keeping
35
+ the task methods pure). Storage + artifacts live under the substrate-injected
36
+ `PLUGIN_DATA_DIR` (`media_processing.db` + `cache_dir_for_config` dirs)."""
37
+
38
+ def _get_storage(self) -> MediaProcessingStorage:
39
+ """Lazily open the per-capability cache DB under the substrate-injected
40
+ PLUGIN_DATA_DIR (created at worker spawn)."""
41
+ if getattr(self, "_storage", None) is None:
42
+ db_path = os.path.join(os.environ["PLUGIN_DATA_DIR"], "media_processing.db")
43
+ self._storage = MediaProcessingStorage(db_path)
44
+ return self._storage
45
+
46
+ def _force(self) -> bool:
47
+ """Per-call cache-bypass flag off the CallEnvelope control channel."""
48
+ env = get_call_envelope()
49
+ return bool(env.control.get("force")) if env is not None else False
50
+
51
+ def _cache_inputs(
52
+ self,
53
+ request_params: Dict[str, Any], # The op's per-call WHAT params (format/rate/channels/boundaries/...)
54
+ ) -> Dict[str, Any]: # The dict hashed for config_hash AND used to address the output dir
55
+ """Tool CONFIG (HOW knobs) + per-call REQUEST params (WHAT artifact) — both
56
+ determine the output, so both go in the cache key. The request params are
57
+ HASHED (not silently bypassed — the FA `language` lesson)."""
58
+ return {**self.tool.get_current_config(), **request_params}
59
+
60
+ def _artifact_op(
61
+ self,
62
+ action: str, # 'convert' | 'extract_audio'
63
+ input_path: str, # Source media path
64
+ request_params: Dict[str, Any], # Per-call WHAT params (hashed + dir-addressing)
65
+ compute: Callable[[str], MediaArtifactResult], # out_dir -> tool call returning the artifact
66
+ ) -> MediaArtifactResult: # The produced (or cache-served) artifact
67
+ """Shared single-artifact bookend for `convert` / `extract_audio`."""
68
+ input_hash = hash_file(input_path)
69
+ cache_inputs = self._cache_inputs(request_params)
70
+ config_hash = hash_dict_canonical(cache_inputs)
71
+ storage = self._get_storage()
72
+ if not self._force():
73
+ cached = storage.get_cached(action, input_path, input_hash, config_hash)
74
+ # A row hit is only a cache hit if the produced artifact still exists.
75
+ if cached is not None and Path(cached.output_path).exists():
76
+ return MediaArtifactResult(output_path=cached.output_path, metadata=cached.metadata or {})
77
+ out_dir = str(cache_dir_for_config(os.environ["PLUGIN_DATA_DIR"], input_path, action, cache_inputs))
78
+ result = compute(out_dir)
79
+ output_hash = hash_file(result.output_path) if result.output_path else None
80
+ storage.save_with_logging(
81
+ action=action, input_path=input_path, input_hash=input_hash, config_hash=config_hash,
82
+ output_path=result.output_path, output_hash=output_hash, metadata=result.metadata,
83
+ )
84
+ return result
85
+
86
+ def convert(self, input_path, output_format, sample_rate=None, channels=None, **kwargs) -> MediaArtifactResult:
87
+ """Convert media to target/model-ready audio (cached artifact)."""
88
+ request_params = {"output_format": output_format, "sample_rate": sample_rate, "channels": channels}
89
+ return self._artifact_op(
90
+ "convert", str(input_path), request_params,
91
+ lambda out_dir: self.tool.convert(
92
+ input_path, output_dir=out_dir, output_format=output_format,
93
+ sample_rate=sample_rate, channels=channels, **kwargs),
94
+ )
95
+
96
+ def extract_audio(self, input_path, output_format=None, **kwargs) -> MediaArtifactResult:
97
+ """Extract the audio stream from a video container (cached artifact)."""
98
+ request_params = {"output_format": output_format}
99
+ return self._artifact_op(
100
+ "extract_audio", str(input_path), request_params,
101
+ lambda out_dir: self.tool.extract_audio(
102
+ input_path, output_dir=out_dir, output_format=output_format, **kwargs),
103
+ )
104
+
105
+ def segment_audio(self, input_path, boundaries, output_format=None,
106
+ filename_template="segment_{index:03d}", **kwargs) -> MediaSegmentationResult:
107
+ """Cut a source into a batch of segment files (cached at BATCH level).
108
+
109
+ One cache row per (segment_audio, input, config): output_path = the batch
110
+ dir, metadata = the whole typed result (segments + batch_key + counts), so
111
+ a hit reconstructs the `MediaSegmentationResult` — but only if EVERY
112
+ produced segment file still exists (the batch analog of the single-artifact
113
+ existence recheck). The per-segment resume-skip the fused tool did is
114
+ intentionally NOT ported (born-final simplicity); watch the journal for
115
+ batch re-compute cost before reinstating it."""
116
+ input_path = str(input_path)
117
+ request_params = {"boundaries": boundaries, "output_format": output_format,
118
+ "filename_template": filename_template}
119
+ input_hash = hash_file(input_path)
120
+ cache_inputs = self._cache_inputs(request_params)
121
+ config_hash = hash_dict_canonical(cache_inputs)
122
+ storage = self._get_storage()
123
+ if not self._force():
124
+ cached = storage.get_cached("segment_audio", input_path, input_hash, config_hash)
125
+ if cached is not None and cached.metadata:
126
+ batch = MediaSegmentationResult.from_dict(cached.metadata)
127
+ if batch.segments and all(Path(s.output_path).exists() for s in batch.segments):
128
+ return batch
129
+ out_dir = str(cache_dir_for_config(os.environ["PLUGIN_DATA_DIR"], input_path, "segment_audio", cache_inputs))
130
+ result = self.tool.segment_audio(
131
+ input_path, output_dir=out_dir, boundaries=boundaries,
132
+ output_format=output_format, filename_template=filename_template, **kwargs)
133
+ storage.save_with_logging(
134
+ action="segment_audio", input_path=input_path, input_hash=input_hash, config_hash=config_hash,
135
+ output_path=out_dir, output_hash=None,
136
+ metadata={"segments": [s.to_dict() for s in result.segments],
137
+ "input_path": result.input_path, "segment_count": result.segment_count,
138
+ "total_duration": result.total_duration, "batch_key": result.batch_key},
139
+ )
140
+ return result
141
+
142
+ def get_info(self, file_path) -> MediaMetadata:
143
+ """Probe media metadata — UNCACHED pure-query pass-through (no artifact)."""
144
+ return self.tool.get_info(file_path)
@@ -0,0 +1,223 @@
1
+ """Standardized SQLite storage for media-processing results (produced-artifact pointers) with content hashing — born-final, action-aware, no `job_id`.
2
+
3
+ Docs: https://cj-mills.github.io/cjm-media-processing-adapter-interfacestorage.html.md"""
4
+
5
+ # AUTOGENERATED! DO NOT EDIT! File to edit: ../nbs/storage.ipynb.
6
+
7
+ # %% auto #0
8
+ __all__ = ['MediaProcessingRow', 'MediaProcessingStorage']
9
+
10
+ # %% ../nbs/storage.ipynb #80a9ba21
11
+ import json
12
+ import logging
13
+ import sqlite3
14
+ import time
15
+ from dataclasses import dataclass
16
+ from typing import Any, Dict, List, Optional
17
+
18
+ from cjm_plugin_system.utils.hashing import hash_file
19
+ # CR-14 follow-up: storage events are substrate-family accounts. The helpers
20
+ # below RECORD them (no-op outside a worker call span); the host journals
21
+ # them off the response header with worker_reported=True.
22
+ from cjm_plugin_system.core.journal_store import SubstrateEventType
23
+ from cjm_plugin_system.core.wire import record_account
24
+
25
+ # %% ../nbs/storage.ipynb #f4d22588
26
+ @dataclass
27
+ class MediaProcessingRow:
28
+ """A single row from the media_processing_results table."""
29
+ action: str # The media-processing op: 'convert', 'segment_audio', 'extract_audio'
30
+ input_path: str # Path to the source media file
31
+ input_hash: str # Hash of the input file in "algo:hexdigest" format
32
+ config_hash: str # Hash of the effective config + per-call request params
33
+ output_path: str # Produced artifact path (a file for convert/extract_audio; the batch dir for segment_audio)
34
+ output_hash: Optional[str] = None # Hash of the produced artifact (None for a batch)
35
+ metadata: Optional[Dict[str, Any]] = None # Processing metadata (for segment_audio: the full typed batch result)
36
+ created_at: Optional[float] = None # Unix timestamp
37
+
38
+ # %% ../nbs/storage.ipynb #b11a2421
39
+ class MediaProcessingStorage:
40
+ """Standardized SQLite storage for media-processing results (artifact pointers), born-final."""
41
+
42
+ SCHEMA = """
43
+ CREATE TABLE IF NOT EXISTS media_processing_results (
44
+ id INTEGER PRIMARY KEY AUTOINCREMENT,
45
+ action TEXT NOT NULL,
46
+ input_path TEXT NOT NULL,
47
+ input_hash TEXT NOT NULL,
48
+ config_hash TEXT NOT NULL,
49
+ output_path TEXT NOT NULL,
50
+ output_hash TEXT,
51
+ metadata JSON,
52
+ created_at REAL NOT NULL,
53
+ UNIQUE(action, input_path, config_hash)
54
+ )
55
+ """
56
+
57
+ INDEX = "CREATE INDEX IF NOT EXISTS idx_mp_input_path ON media_processing_results(input_path);"
58
+
59
+ def __init__(
60
+ self,
61
+ db_path: str # Absolute path to the SQLite database file
62
+ ):
63
+ """Initialize storage and create table if needed."""
64
+ self.db_path = db_path
65
+ with sqlite3.connect(self.db_path) as con:
66
+ con.execute(self.SCHEMA)
67
+ con.execute(self.INDEX)
68
+
69
+ def save(
70
+ self,
71
+ action: str, # Media-processing op: 'convert', 'segment_audio', 'extract_audio'
72
+ input_path: str, # Path to the source media file
73
+ input_hash: str, # Hash of the input file in "algo:hexdigest" format
74
+ config_hash: str, # Hash of the effective config + per-call request params
75
+ output_path: str, # Produced artifact path (file, or batch dir for segment_audio)
76
+ output_hash: Optional[str] = None, # Hash of the produced artifact (None for a batch)
77
+ metadata: Optional[Dict[str, Any]] = None # Processing metadata (batch result for segment_audio)
78
+ ) -> None:
79
+ """Save or replace a media-processing result (upsert by action + input_path + config_hash)."""
80
+ with sqlite3.connect(self.db_path) as con:
81
+ con.execute(
82
+ """INSERT OR REPLACE INTO media_processing_results
83
+ (action, input_path, input_hash, config_hash, output_path, output_hash, metadata, created_at)
84
+ VALUES (?, ?, ?, ?, ?, ?, ?, ?)""",
85
+ (
86
+ action,
87
+ input_path,
88
+ input_hash,
89
+ config_hash,
90
+ output_path,
91
+ output_hash,
92
+ json.dumps(metadata) if metadata else None,
93
+ time.time()
94
+ )
95
+ )
96
+
97
+ def save_with_logging(
98
+ self,
99
+ *,
100
+ action: str, # Media-processing op
101
+ input_path: str, # Path to the source media file
102
+ input_hash: str, # Hash of the input file in "algo:hexdigest" format
103
+ config_hash: str, # Hash of the effective config + per-call request params
104
+ output_path: str, # Produced artifact path
105
+ output_hash: Optional[str] = None, # Hash of the produced artifact
106
+ metadata: Optional[Dict[str, Any]] = None, # Processing metadata
107
+ logger: Optional[logging.Logger] = None # Optional logger for success/failure messages
108
+ ) -> bool: # True if saved; False if the save failed (error logged, not raised)
109
+ """Save a result, logging success/failure. Failures are logged and swallowed (returns False).
110
+
111
+ CR-14 follow-up: records a RESULT_SAVED account either way (ok flag +
112
+ action/input/output/config references — the journal never carries
113
+ content) so saves AND swallowed save-failures become auditable journal rows."""
114
+ try:
115
+ self.save(
116
+ action=action,
117
+ input_path=input_path,
118
+ input_hash=input_hash,
119
+ config_hash=config_hash,
120
+ output_path=output_path,
121
+ output_hash=output_hash,
122
+ metadata=metadata,
123
+ )
124
+ record_account(SubstrateEventType.RESULT_SAVED.value, {
125
+ "ok": True, "action": action, "input_path": input_path,
126
+ "input_hash": input_hash, "config_hash": config_hash, "output_path": output_path,
127
+ })
128
+ if logger:
129
+ logger.info(f"Saved media-processing result to DB ({action}: {input_path} -> {output_path})")
130
+ return True
131
+ except Exception as e:
132
+ record_account(SubstrateEventType.RESULT_SAVED.value, {
133
+ "ok": False, "action": action, "input_path": input_path,
134
+ "input_hash": input_hash, "config_hash": config_hash, "error": str(e),
135
+ })
136
+ if logger:
137
+ logger.error(f"Failed to save to DB: {e}")
138
+ return False
139
+
140
+ def get_cached(
141
+ self,
142
+ action: str, # Media-processing op
143
+ input_path: str, # Path to the source media file
144
+ input_hash: str, # Content hash of the input (cache miss if the file changed)
145
+ config_hash: str # Config hash to match
146
+ ) -> Optional[MediaProcessingRow]: # Cached row or None
147
+ """Retrieve a content-correct cached media-processing result.
148
+
149
+ Matches on action + input_path + input_hash + config_hash, so a changed
150
+ input (new input_hash) misses even though a stale row may still exist at
151
+ the same (action, input_path, config_hash) — the next save() replaces it.
152
+ The CALLER must still confirm the artifact(s) at `output_path` exist
153
+ before serving them (they live outside the DB).
154
+
155
+ CR-14 follow-up: a hit records a CACHE_HIT account (the cache-serving
156
+ decision is an account-of-action)."""
157
+ with sqlite3.connect(self.db_path) as con:
158
+ cur = con.execute(
159
+ """SELECT action, input_path, input_hash, config_hash, output_path, output_hash, metadata, created_at
160
+ FROM media_processing_results
161
+ WHERE action = ? AND input_path = ? AND input_hash = ? AND config_hash = ?""",
162
+ (action, input_path, input_hash, config_hash)
163
+ )
164
+ row = cur.fetchone()
165
+ if not row:
166
+ return None
167
+ record_account(SubstrateEventType.CACHE_HIT.value, {
168
+ "action": action, "input_path": input_path,
169
+ "input_hash": input_hash, "config_hash": config_hash,
170
+ })
171
+ return MediaProcessingRow(
172
+ action=row[0],
173
+ input_path=row[1],
174
+ input_hash=row[2],
175
+ config_hash=row[3],
176
+ output_path=row[4],
177
+ output_hash=row[5],
178
+ metadata=json.loads(row[6]) if row[6] else None,
179
+ created_at=row[7]
180
+ )
181
+
182
+ def list_jobs(
183
+ self,
184
+ limit: int = 100 # Maximum number of rows to return
185
+ ) -> List[MediaProcessingRow]: # List of media-processing rows
186
+ """List media-processing results ordered by creation time (newest first)."""
187
+ results = []
188
+ with sqlite3.connect(self.db_path) as con:
189
+ cur = con.execute(
190
+ """SELECT action, input_path, input_hash, config_hash, output_path, output_hash, metadata, created_at
191
+ FROM media_processing_results ORDER BY created_at DESC LIMIT ?""",
192
+ (limit,)
193
+ )
194
+ for row in cur:
195
+ results.append(MediaProcessingRow(
196
+ action=row[0],
197
+ input_path=row[1],
198
+ input_hash=row[2],
199
+ config_hash=row[3],
200
+ output_path=row[4],
201
+ output_hash=row[5],
202
+ metadata=json.loads(row[6]) if row[6] else None,
203
+ created_at=row[7]
204
+ ))
205
+ return results
206
+
207
+ def verify_input(
208
+ self,
209
+ action: str, # Media-processing op
210
+ input_path: str, # Path to the source media file
211
+ config_hash: str # Config hash to look up
212
+ ) -> Optional[bool]: # True if input matches, False if changed, None if not found
213
+ """Verify the source file still matches the hash stored for (action, input_path, config_hash)."""
214
+ with sqlite3.connect(self.db_path) as con:
215
+ cur = con.execute(
216
+ """SELECT input_hash FROM media_processing_results
217
+ WHERE action = ? AND input_path = ? AND config_hash = ?""",
218
+ (action, input_path, config_hash)
219
+ )
220
+ row = cur.fetchone()
221
+ if not row:
222
+ return None
223
+ return hash_file(input_path) == row[0]
@@ -0,0 +1,357 @@
1
+ Metadata-Version: 2.4
2
+ Name: cjm-media-processing-adapter-interface
3
+ Version: 0.0.2
4
+ Summary: Typed media-processing task-adapter interface — the multi-method MediaProcessingAdapter ABC + GenericMediaProcessingAdapter (cache/persist bookends around a pure-compute tool: convert, segment_audio, extract_audio, plus an uncached get_info probe) + the MediaProcessingToolProtocol. Result DTOs live in cjm-capability-primitives.
5
+ Author-email: "Christian J. Mills" <9126128+cj-mills@users.noreply.github.com>
6
+ License: Apache-2.0
7
+ Project-URL: Repository, https://github.com/cj-mills/cjm-media-processing-adapter-interface
8
+ Project-URL: Documentation, https://cj-mills.github.io/cjm-media-processing-adapter-interface/
9
+ Keywords: nbdev
10
+ Classifier: Programming Language :: Python :: 3
11
+ Classifier: Programming Language :: Python :: 3 :: Only
12
+ Requires-Python: >=3.12
13
+ Description-Content-Type: text/markdown
14
+ License-File: LICENSE
15
+ Requires-Dist: cjm_plugin_system>=0.0.46
16
+ Requires-Dist: cjm_capability_primitives>=0.0.6
17
+ Dynamic: license-file
18
+
19
+ # cjm-media-processing-adapter-interface
20
+
21
+
22
+ <!-- WARNING: THIS FILE WAS AUTOGENERATED! DO NOT EDIT! -->
23
+
24
+ ## Install
25
+
26
+ ``` bash
27
+ pip install cjm_media_processing_adapter_interface
28
+ ```
29
+
30
+ ## Project Structure
31
+
32
+ nbs/
33
+ ├── adapter.ipynb # The typed media-processing task contract — the multi-method `MediaProcessingAdapter` ABC + the `MediaProcessingToolProtocol` structural contract (capability-unit Option C, pass-2 Thread 3). ONE multi-method adapter for the media-processing tool's whole repertoire (the graph-storage precedent), NOT per-action adapters.
34
+ ├── generic.ipynb # The generic (tool-agnostic) multi-method media-processing adapter — cache-bookended artifact ops (`convert` / `segment_audio` / `extract_audio`) + an uncached `get_info` probe. Reused across every tool capability satisfying `MediaProcessingToolProtocol` (ffmpeg today).
35
+ └── storage.ipynb # Standardized SQLite storage for media-processing results (produced-artifact pointers) with content hashing — born-final, action-aware, no `job_id`.
36
+
37
+ Total: 3 notebooks
38
+
39
+ ## Module Dependencies
40
+
41
+ ``` mermaid
42
+ graph LR
43
+ adapter["adapter<br/>Media Processing Adapter"]
44
+ generic["generic<br/>Generic Media Processing Adapter"]
45
+ storage["storage<br/>Media Processing Storage"]
46
+
47
+ generic --> adapter
48
+ generic --> storage
49
+ ```
50
+
51
+ *2 cross-module dependencies detected*
52
+
53
+ ## CLI Reference
54
+
55
+ No CLI commands found in this project.
56
+
57
+ ## Module Overview
58
+
59
+ Detailed documentation for each module in the project:
60
+
61
+ ### Media Processing Adapter (`adapter.ipynb`)
62
+
63
+ > The typed media-processing task contract — the multi-method
64
+ > `MediaProcessingAdapter` ABC + the `MediaProcessingToolProtocol`
65
+ > structural contract (capability-unit Option C, pass-2 Thread 3). ONE
66
+ > multi-method adapter for the media-processing tool’s whole repertoire
67
+ > (the graph-storage precedent), NOT per-action adapters.
68
+
69
+ #### Import
70
+
71
+ ``` python
72
+ from cjm_media_processing_adapter_interface.adapter import (
73
+ MediaProcessingToolProtocol,
74
+ MediaProcessingAdapter
75
+ )
76
+ ```
77
+
78
+ #### Classes
79
+
80
+ ``` python
81
+ @runtime_checkable
82
+ class MediaProcessingToolProtocol(Protocol):
83
+ """
84
+ Structural contract for media-processing tool capabilities (ffmpeg today;
85
+ born-final at stage 8 — derived from the native tool surface).
86
+
87
+ Artifact-producing ops (`convert`, `segment_audio`, `extract_audio`) are pure
88
+ compute that WRITE audio file(s) into the adapter-chosen `output_dir` (the
89
+ artifact-write seam) and return a typed pointer. `get_info` is a pure-query
90
+ probe returning inline `MediaMetadata` (no artifact). `get_current_config`
91
+ supplies the effective config the generic adapter hashes (together with the
92
+ per-call request params) for its cache key.
93
+
94
+ The `output_dir` parameter on the artifact ops is the adapter telling the
95
+ tool WHERE to persist (the `db_path`-off-the-tool rule); encoding the audio
96
+ stays tool-side compute. Per-call request params (`output_format`,
97
+ `sample_rate`, `channels`, `boundaries`, `filename_template`) define WHAT
98
+ artifact to produce and are hashed into the cache key.
99
+ """
100
+
101
+ def convert(self, input_path: Union[str, Path], output_dir: str,
102
+ output_format: str, sample_rate: Optional[int] = None,
103
+ channels: Optional[int] = None, **kwargs) -> MediaArtifactResult: ...
104
+
105
+ def segment_audio(self, input_path: Union[str, Path], output_dir: str,
106
+ boundaries: List[Dict[str, float]], output_format: Optional[str] = None,
107
+ filename_template: str = "segment_{index:03d}", **kwargs) -> MediaSegmentationResult: ...
108
+
109
+ def extract_audio(self, input_path: Union[str, Path], output_dir: str,
110
+ output_format: Optional[str] = None, **kwargs) -> MediaArtifactResult: ...
111
+
112
+ def get_info(self, file_path: Union[str, Path]) -> MediaMetadata: ...
113
+ def get_current_config(self) -> Dict[str, Any]: ...
114
+
115
+ def get_current_config(self) -> Dict[str, Any]: ...
116
+ ```
117
+
118
+ ``` python
119
+ class MediaProcessingAdapter:
120
+ def __init__(
121
+ self,
122
+ tool: MediaProcessingToolProtocol, # The bound tool capability instance (worker-side binding)
123
+ )
124
+ """
125
+ Typed media-processing task adapter — ONE multi-method adapter for the
126
+ media-processing tool's whole repertoire (the graph-storage multi-method
127
+ precedent, NOT per-action adapters: the `task_name` key answers "which tools
128
+ do media-processing", and there is one such tool — ffmpeg — that will gain
129
+ MORE ops over time, e.g. building video from images + audio, so per-action
130
+ would only multiply task families + libs without aiding discovery).
131
+
132
+ Native-surface model (stage 8 / PILLAR 1c): the TOOL is pure compute; the
133
+ ADAPTER owns the cache + persistence bookends (see
134
+ `GenericMediaProcessingAdapter`) + the per-call `force` control. The
135
+ artifact ops write audio file(s) under the substrate-injected
136
+ `PLUGIN_DATA_DIR`; the cache row maps (action, input, config) -> output(s).
137
+ The adapter chooses the output location and passes it to the tool; `db_path`
138
+ is not on the tool protocol. `get_info` is an UNCACHED pure-query
139
+ pass-through (a probe; no artifact).
140
+
141
+ Input contract: `convert`/`segment_audio` receive a source (or an upstream
142
+ artifact, e.g. a vocals stem) path; the produced WAVs ARE the model-ready
143
+ audio downstream consumers (VAD/transcription) use. `extract_audio` pulls an
144
+ audio stream from a video container (the non-minimal video-input path).
145
+ Implementations run in-worker beside their tool, constructed
146
+ `AdapterClass(tool)` (mirrors `GraphStorageAdapter`). Result DTOs are
147
+ wire-registered (`media_processing.{artifact,segmentation,metadata}`) so
148
+ returned values cross the worker boundary typed.
149
+ """
150
+
151
+ def __init__(
152
+ self,
153
+ tool: MediaProcessingToolProtocol, # The bound tool capability instance (worker-side binding)
154
+ )
155
+
156
+ def convert(
157
+ self,
158
+ input_path: Union[str, Path], # Source (or upstream artifact) audio/video to convert
159
+ output_format: str, # Target audio format (e.g. 'wav', 'mp3')
160
+ sample_rate: Optional[int] = None, # Target sample rate (e.g. 16000 for model input); None = source rate
161
+ channels: Optional[int] = None, # Target channel count (e.g. 1 = mono); None = source channels
162
+ **kwargs, # Provenance + tool options
163
+ ) -> MediaArtifactResult: # The produced converted-audio artifact (cached)
164
+ "Convert media to target/model-ready audio (cached artifact)."
165
+
166
+ def segment_audio(
167
+ self,
168
+ input_path: Union[str, Path], # Source audio to cut
169
+ boundaries: List[Dict[str, float]], # [{start, end}, ...] cut points (seconds)
170
+ output_format: Optional[str] = None, # Output format; None = same as input
171
+ filename_template: str = "segment_{index:03d}", # Per-segment filename pattern
172
+ **kwargs, # Provenance + tool options
173
+ ) -> MediaSegmentationResult: # The produced batch of segment files (cached at batch level)
174
+ "Cut a source into a batch of segment files at the given boundaries (cached batch)."
175
+
176
+ def extract_audio(
177
+ self,
178
+ input_path: Union[str, Path], # Source video container
179
+ output_format: Optional[str] = None, # Audio format; None = codec-derived
180
+ **kwargs, # Provenance + tool options
181
+ ) -> MediaArtifactResult: # The produced extracted-audio artifact (cached)
182
+ "Extract the audio stream from a video container (cached artifact)."
183
+
184
+ def get_info(
185
+ self,
186
+ file_path: Union[str, Path], # Media file to probe
187
+ ) -> MediaMetadata: # Probed metadata (uncached)
188
+ "Probe media metadata (uncached pure-query)."
189
+ ```
190
+
191
+ ### Generic Media Processing Adapter (`generic.ipynb`)
192
+
193
+ > The generic (tool-agnostic) multi-method media-processing adapter —
194
+ > cache-bookended artifact ops (`convert` / `segment_audio` /
195
+ > `extract_audio`) + an uncached `get_info` probe. Reused across every
196
+ > tool capability satisfying `MediaProcessingToolProtocol` (ffmpeg
197
+ > today).
198
+
199
+ #### Import
200
+
201
+ ``` python
202
+ from cjm_media_processing_adapter_interface.generic import (
203
+ GenericMediaProcessingAdapter
204
+ )
205
+ ```
206
+
207
+ #### Classes
208
+
209
+ ``` python
210
+ class GenericMediaProcessingAdapter(MediaProcessingAdapter):
211
+ """
212
+ Generic multi-method media-processing adapter, reused across any tool
213
+ satisfying `MediaProcessingToolProtocol`.
214
+
215
+ Artifact ops (`convert`/`extract_audio`/`segment_audio`) share the
216
+ source-separation bookend (cache-check + artifact-existence recheck ->
217
+ adapter-chosen `output_dir` -> tool -> persist). `get_info` is an uncached
218
+ pass-through. The cache key hashes `get_current_config()` together with the
219
+ per-call request params, and `force` rides `CallEnvelope.control` (keeping
220
+ the task methods pure). Storage + artifacts live under the substrate-injected
221
+ `PLUGIN_DATA_DIR` (`media_processing.db` + `cache_dir_for_config` dirs).
222
+ """
223
+
224
+ def convert(self, input_path, output_format, sample_rate=None, channels=None, **kwargs) -> MediaArtifactResult:
225
+ """Convert media to target/model-ready audio (cached artifact)."""
226
+ request_params = {"output_format": output_format, "sample_rate": sample_rate, "channels": channels}
227
+ "Convert media to target/model-ready audio (cached artifact)."
228
+
229
+ def extract_audio(self, input_path, output_format=None, **kwargs) -> MediaArtifactResult:
230
+ """Extract the audio stream from a video container (cached artifact)."""
231
+ request_params = {"output_format": output_format}
232
+ "Extract the audio stream from a video container (cached artifact)."
233
+
234
+ def segment_audio(self, input_path, boundaries, output_format=None,
235
+ filename_template="segment_{index:03d}", **kwargs) -> MediaSegmentationResult
236
+ "Cut a source into a batch of segment files (cached at BATCH level).
237
+
238
+ One cache row per (segment_audio, input, config): output_path = the batch
239
+ dir, metadata = the whole typed result (segments + batch_key + counts), so
240
+ a hit reconstructs the `MediaSegmentationResult` — but only if EVERY
241
+ produced segment file still exists (the batch analog of the single-artifact
242
+ existence recheck). The per-segment resume-skip the fused tool did is
243
+ intentionally NOT ported (born-final simplicity); watch the journal for
244
+ batch re-compute cost before reinstating it."
245
+
246
+ def get_info(self, file_path) -> MediaMetadata
247
+ "Probe media metadata — UNCACHED pure-query pass-through (no artifact)."
248
+ ```
249
+
250
+ ### Media Processing Storage (`storage.ipynb`)
251
+
252
+ > Standardized SQLite storage for media-processing results
253
+ > (produced-artifact pointers) with content hashing — born-final,
254
+ > action-aware, no `job_id`.
255
+
256
+ #### Import
257
+
258
+ ``` python
259
+ from cjm_media_processing_adapter_interface.storage import (
260
+ MediaProcessingRow,
261
+ MediaProcessingStorage
262
+ )
263
+ ```
264
+
265
+ #### Classes
266
+
267
+ ``` python
268
+ @dataclass
269
+ class MediaProcessingRow:
270
+ "A single row from the media_processing_results table."
271
+
272
+ action: str # The media-processing op: 'convert', 'segment_audio', 'extract_audio'
273
+ input_path: str # Path to the source media file
274
+ input_hash: str # Hash of the input file in "algo:hexdigest" format
275
+ config_hash: str # Hash of the effective config + per-call request params
276
+ output_path: str # Produced artifact path (a file for convert/extract_audio; the batch dir for segment_audio)
277
+ output_hash: Optional[str] # Hash of the produced artifact (None for a batch)
278
+ metadata: Optional[Dict[str, Any]] # Processing metadata (for segment_audio: the full typed batch result)
279
+ created_at: Optional[float] # Unix timestamp
280
+ ```
281
+
282
+ ``` python
283
+ class MediaProcessingStorage:
284
+ def __init__(
285
+ self,
286
+ db_path: str # Absolute path to the SQLite database file
287
+ )
288
+ "Standardized SQLite storage for media-processing results (artifact pointers), born-final."
289
+
290
+ def __init__(
291
+ self,
292
+ db_path: str # Absolute path to the SQLite database file
293
+ )
294
+ "Initialize storage and create table if needed."
295
+
296
+ def save(
297
+ self,
298
+ action: str, # Media-processing op: 'convert', 'segment_audio', 'extract_audio'
299
+ input_path: str, # Path to the source media file
300
+ input_hash: str, # Hash of the input file in "algo:hexdigest" format
301
+ config_hash: str, # Hash of the effective config + per-call request params
302
+ output_path: str, # Produced artifact path (file, or batch dir for segment_audio)
303
+ output_hash: Optional[str] = None, # Hash of the produced artifact (None for a batch)
304
+ metadata: Optional[Dict[str, Any]] = None # Processing metadata (batch result for segment_audio)
305
+ ) -> None
306
+ "Save or replace a media-processing result (upsert by action + input_path + config_hash)."
307
+
308
+ def save_with_logging(
309
+ self,
310
+ *,
311
+ action: str, # Media-processing op
312
+ input_path: str, # Path to the source media file
313
+ input_hash: str, # Hash of the input file in "algo:hexdigest" format
314
+ config_hash: str, # Hash of the effective config + per-call request params
315
+ output_path: str, # Produced artifact path
316
+ output_hash: Optional[str] = None, # Hash of the produced artifact
317
+ metadata: Optional[Dict[str, Any]] = None, # Processing metadata
318
+ logger: Optional[logging.Logger] = None # Optional logger for success/failure messages
319
+ ) -> bool: # True if saved; False if the save failed (error logged, not raised)
320
+ "Save a result, logging success/failure. Failures are logged and swallowed (returns False).
321
+
322
+ CR-14 follow-up: records a RESULT_SAVED account either way (ok flag +
323
+ action/input/output/config references — the journal never carries
324
+ content) so saves AND swallowed save-failures become auditable journal rows."
325
+
326
+ def get_cached(
327
+ self,
328
+ action: str, # Media-processing op
329
+ input_path: str, # Path to the source media file
330
+ input_hash: str, # Content hash of the input (cache miss if the file changed)
331
+ config_hash: str # Config hash to match
332
+ ) -> Optional[MediaProcessingRow]: # Cached row or None
333
+ "Retrieve a content-correct cached media-processing result.
334
+
335
+ Matches on action + input_path + input_hash + config_hash, so a changed
336
+ input (new input_hash) misses even though a stale row may still exist at
337
+ the same (action, input_path, config_hash) — the next save() replaces it.
338
+ The CALLER must still confirm the artifact(s) at `output_path` exist
339
+ before serving them (they live outside the DB).
340
+
341
+ CR-14 follow-up: a hit records a CACHE_HIT account (the cache-serving
342
+ decision is an account-of-action)."
343
+
344
+ def list_jobs(
345
+ self,
346
+ limit: int = 100 # Maximum number of rows to return
347
+ ) -> List[MediaProcessingRow]: # List of media-processing rows
348
+ "List media-processing results ordered by creation time (newest first)."
349
+
350
+ def verify_input(
351
+ self,
352
+ action: str, # Media-processing op
353
+ input_path: str, # Path to the source media file
354
+ config_hash: str # Config hash to look up
355
+ ) -> Optional[bool]: # True if input matches, False if changed, None if not found
356
+ "Verify the source file still matches the hash stored for (action, input_path, config_hash)."
357
+ ```
@@ -0,0 +1,11 @@
1
+ cjm_media_processing_adapter_interface/__init__.py,sha256=QvlVh4JTl3JL7jQAja76yKtT-IvF4631ASjWY1wS6AQ,22
2
+ cjm_media_processing_adapter_interface/_modidx.py,sha256=Ve27HutPOi1Ds6IZ4iTa8aleDbNy7UgEmB3YEW1d9ew,12222
3
+ cjm_media_processing_adapter_interface/adapter.py,sha256=GOGT303rlcmzK-6e5pfjZBXGKgvCXZXMAJsKTHMx7Io,7014
4
+ cjm_media_processing_adapter_interface/generic.py,sha256=j4lRHrMoXRIwQ7lx5_YrfXQjvsnr-9LQsm7BqVvi-Fw,8204
5
+ cjm_media_processing_adapter_interface/storage.py,sha256=i7YHuVfc5LRtNjxoS-p-JQdEA2QQ65uudSH5xE5YvkQ,10314
6
+ cjm_media_processing_adapter_interface-0.0.2.dist-info/licenses/LICENSE,sha256=xV8xoN4VOL0uw9X8RSs2IMuD_Ss_a9yAbtGNeBWZwnw,11337
7
+ cjm_media_processing_adapter_interface-0.0.2.dist-info/METADATA,sha256=02iaHg0d1xGeVakUXhGp2eE_yUWJ9fwyzgZwPbCMxKk,16866
8
+ cjm_media_processing_adapter_interface-0.0.2.dist-info/WHEEL,sha256=aeYiig01lYGDzBgS8HxWXOg3uV61G9ijOsup-k9o1sk,91
9
+ cjm_media_processing_adapter_interface-0.0.2.dist-info/entry_points.txt,sha256=0SO5NsNtHkFrBNOWXI0BIQBh8EPYgTguiJGKL6yE_bY,98
10
+ cjm_media_processing_adapter_interface-0.0.2.dist-info/top_level.txt,sha256=Oklij0ZAwWAYYN_Pw9gmdqVdopjgcbM-f5blid-Ww4A,39
11
+ cjm_media_processing_adapter_interface-0.0.2.dist-info/RECORD,,
@@ -0,0 +1,5 @@
1
+ Wheel-Version: 1.0
2
+ Generator: setuptools (82.0.1)
3
+ Root-Is-Purelib: true
4
+ Tag: py3-none-any
5
+
@@ -0,0 +1,2 @@
1
+ [nbdev]
2
+ cjm_media_processing_adapter_interface = cjm_media_processing_adapter_interface._modidx:d
@@ -0,0 +1,201 @@
1
+ Apache License
2
+ Version 2.0, January 2004
3
+ http://www.apache.org/licenses/
4
+
5
+ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
6
+
7
+ 1. Definitions.
8
+
9
+ "License" shall mean the terms and conditions for use, reproduction,
10
+ and distribution as defined by Sections 1 through 9 of this document.
11
+
12
+ "Licensor" shall mean the copyright owner or entity authorized by
13
+ the copyright owner that is granting the License.
14
+
15
+ "Legal Entity" shall mean the union of the acting entity and all
16
+ other entities that control, are controlled by, or are under common
17
+ control with that entity. For the purposes of this definition,
18
+ "control" means (i) the power, direct or indirect, to cause the
19
+ direction or management of such entity, whether by contract or
20
+ otherwise, or (ii) ownership of fifty percent (50%) or more of the
21
+ outstanding shares, or (iii) beneficial ownership of such entity.
22
+
23
+ "You" (or "Your") shall mean an individual or Legal Entity
24
+ exercising permissions granted by this License.
25
+
26
+ "Source" form shall mean the preferred form for making modifications,
27
+ including but not limited to software source code, documentation
28
+ source, and configuration files.
29
+
30
+ "Object" form shall mean any form resulting from mechanical
31
+ transformation or translation of a Source form, including but
32
+ not limited to compiled object code, generated documentation,
33
+ and conversions to other media types.
34
+
35
+ "Work" shall mean the work of authorship, whether in Source or
36
+ Object form, made available under the License, as indicated by a
37
+ copyright notice that is included in or attached to the work
38
+ (an example is provided in the Appendix below).
39
+
40
+ "Derivative Works" shall mean any work, whether in Source or Object
41
+ form, that is based on (or derived from) the Work and for which the
42
+ editorial revisions, annotations, elaborations, or other modifications
43
+ represent, as a whole, an original work of authorship. For the purposes
44
+ of this License, Derivative Works shall not include works that remain
45
+ separable from, or merely link (or bind by name) to the interfaces of,
46
+ the Work and Derivative Works thereof.
47
+
48
+ "Contribution" shall mean any work of authorship, including
49
+ the original version of the Work and any modifications or additions
50
+ to that Work or Derivative Works thereof, that is intentionally
51
+ submitted to Licensor for inclusion in the Work by the copyright owner
52
+ or by an individual or Legal Entity authorized to submit on behalf of
53
+ the copyright owner. For the purposes of this definition, "submitted"
54
+ means any form of electronic, verbal, or written communication sent
55
+ to the Licensor or its representatives, including but not limited to
56
+ communication on electronic mailing lists, source code control systems,
57
+ and issue tracking systems that are managed by, or on behalf of, the
58
+ Licensor for the purpose of discussing and improving the Work, but
59
+ excluding communication that is conspicuously marked or otherwise
60
+ designated in writing by the copyright owner as "Not a Contribution."
61
+
62
+ "Contributor" shall mean Licensor and any individual or Legal Entity
63
+ on behalf of whom a Contribution has been received by Licensor and
64
+ subsequently incorporated within the Work.
65
+
66
+ 2. Grant of Copyright License. Subject to the terms and conditions of
67
+ this License, each Contributor hereby grants to You a perpetual,
68
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
69
+ copyright license to reproduce, prepare Derivative Works of,
70
+ publicly display, publicly perform, sublicense, and distribute the
71
+ Work and such Derivative Works in Source or Object form.
72
+
73
+ 3. Grant of Patent License. Subject to the terms and conditions of
74
+ this License, each Contributor hereby grants to You a perpetual,
75
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
76
+ (except as stated in this section) patent license to make, have made,
77
+ use, offer to sell, sell, import, and otherwise transfer the Work,
78
+ where such license applies only to those patent claims licensable
79
+ by such Contributor that are necessarily infringed by their
80
+ Contribution(s) alone or by combination of their Contribution(s)
81
+ with the Work to which such Contribution(s) was submitted. If You
82
+ institute patent litigation against any entity (including a
83
+ cross-claim or counterclaim in a lawsuit) alleging that the Work
84
+ or a Contribution incorporated within the Work constitutes direct
85
+ or contributory patent infringement, then any patent licenses
86
+ granted to You under this License for that Work shall terminate
87
+ as of the date such litigation is filed.
88
+
89
+ 4. Redistribution. You may reproduce and distribute copies of the
90
+ Work or Derivative Works thereof in any medium, with or without
91
+ modifications, and in Source or Object form, provided that You
92
+ meet the following conditions:
93
+
94
+ (a) You must give any other recipients of the Work or
95
+ Derivative Works a copy of this License; and
96
+
97
+ (b) You must cause any modified files to carry prominent notices
98
+ stating that You changed the files; and
99
+
100
+ (c) You must retain, in the Source form of any Derivative Works
101
+ that You distribute, all copyright, patent, trademark, and
102
+ attribution notices from the Source form of the Work,
103
+ excluding those notices that do not pertain to any part of
104
+ the Derivative Works; and
105
+
106
+ (d) If the Work includes a "NOTICE" text file as part of its
107
+ distribution, then any Derivative Works that You distribute must
108
+ include a readable copy of the attribution notices contained
109
+ within such NOTICE file, excluding those notices that do not
110
+ pertain to any part of the Derivative Works, in at least one
111
+ of the following places: within a NOTICE text file distributed
112
+ as part of the Derivative Works; within the Source form or
113
+ documentation, if provided along with the Derivative Works; or,
114
+ within a display generated by the Derivative Works, if and
115
+ wherever such third-party notices normally appear. The contents
116
+ of the NOTICE file are for informational purposes only and
117
+ do not modify the License. You may add Your own attribution
118
+ notices within Derivative Works that You distribute, alongside
119
+ or as an addendum to the NOTICE text from the Work, provided
120
+ that such additional attribution notices cannot be construed
121
+ as modifying the License.
122
+
123
+ You may add Your own copyright statement to Your modifications and
124
+ may provide additional or different license terms and conditions
125
+ for use, reproduction, or distribution of Your modifications, or
126
+ for any such Derivative Works as a whole, provided Your use,
127
+ reproduction, and distribution of the Work otherwise complies with
128
+ the conditions stated in this License.
129
+
130
+ 5. Submission of Contributions. Unless You explicitly state otherwise,
131
+ any Contribution intentionally submitted for inclusion in the Work
132
+ by You to the Licensor shall be under the terms and conditions of
133
+ this License, without any additional terms or conditions.
134
+ Notwithstanding the above, nothing herein shall supersede or modify
135
+ the terms of any separate license agreement you may have executed
136
+ with Licensor regarding such Contributions.
137
+
138
+ 6. Trademarks. This License does not grant permission to use the trade
139
+ names, trademarks, service marks, or product names of the Licensor,
140
+ except as required for reasonable and customary use in describing the
141
+ origin of the Work and reproducing the content of the NOTICE file.
142
+
143
+ 7. Disclaimer of Warranty. Unless required by applicable law or
144
+ agreed to in writing, Licensor provides the Work (and each
145
+ Contributor provides its Contributions) on an "AS IS" BASIS,
146
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
147
+ implied, including, without limitation, any warranties or conditions
148
+ of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
149
+ PARTICULAR PURPOSE. You are solely responsible for determining the
150
+ appropriateness of using or redistributing the Work and assume any
151
+ risks associated with Your exercise of permissions under this License.
152
+
153
+ 8. Limitation of Liability. In no event and under no legal theory,
154
+ whether in tort (including negligence), contract, or otherwise,
155
+ unless required by applicable law (such as deliberate and grossly
156
+ negligent acts) or agreed to in writing, shall any Contributor be
157
+ liable to You for damages, including any direct, indirect, special,
158
+ incidental, or consequential damages of any character arising as a
159
+ result of this License or out of the use or inability to use the
160
+ Work (including but not limited to damages for loss of goodwill,
161
+ work stoppage, computer failure or malfunction, or any and all
162
+ other commercial damages or losses), even if such Contributor
163
+ has been advised of the possibility of such damages.
164
+
165
+ 9. Accepting Warranty or Additional Liability. While redistributing
166
+ the Work or Derivative Works thereof, You may choose to offer,
167
+ and charge a fee for, acceptance of support, warranty, indemnity,
168
+ or other liability obligations and/or rights consistent with this
169
+ License. However, in accepting such obligations, You may act only
170
+ on Your own behalf and on Your sole responsibility, not on behalf
171
+ of any other Contributor, and only if You agree to indemnify,
172
+ defend, and hold each Contributor harmless for any liability
173
+ incurred by, or claims asserted against, such Contributor by reason
174
+ of your accepting any such warranty or additional liability.
175
+
176
+ END OF TERMS AND CONDITIONS
177
+
178
+ APPENDIX: How to apply the Apache License to your work.
179
+
180
+ To apply the Apache License to your work, attach the following
181
+ boilerplate notice, with the fields enclosed by brackets "[]"
182
+ replaced with your own identifying information. (Don't include
183
+ the brackets!) The text should be enclosed in the appropriate
184
+ comment syntax for the file format. We also recommend that a
185
+ file or class name and description of purpose be included on the
186
+ same "printed page" as the copyright notice for easier
187
+ identification within third-party archives.
188
+
189
+ Copyright 2022, fastai
190
+
191
+ Licensed under the Apache License, Version 2.0 (the "License");
192
+ you may not use this file except in compliance with the License.
193
+ You may obtain a copy of the License at
194
+
195
+ http://www.apache.org/licenses/LICENSE-2.0
196
+
197
+ Unless required by applicable law or agreed to in writing, software
198
+ distributed under the License is distributed on an "AS IS" BASIS,
199
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
200
+ See the License for the specific language governing permissions and
201
+ limitations under the License.
@@ -0,0 +1 @@
1
+ cjm_media_processing_adapter_interface