videopython 0.33.1__tar.gz → 0.33.2__tar.gz

{videopython-0.33.1 → videopython-0.33.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: videopython
-Version: 0.33.1
+Version: 0.33.2
 Summary: Minimal video generation and processing library.
 Project-URL: Homepage, https://videopython.com
 Project-URL: Repository, https://github.com/bartwojtowicz/videopython/

{videopython-0.33.1 → videopython-0.33.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "videopython"
-version = "0.33.1"
+version = "0.33.2"
 description = "Minimal video generation and processing library."
 authors = [
     { name = "Bartosz Wójtowicz", email = "bartoszwojtowicz@outlook.com" },
@@ -137,6 +137,9 @@ Documentation = "https://videopython.com"
 [tool.mypy]
 mypy_path = "src/stubs"
 plugins = ["pydantic.mypy"]
+warn_unused_ignores = true
+warn_redundant_casts = true
+disallow_any_generics = true
 
 [[tool.mypy.overrides]]
 module = [

{videopython-0.33.1 → videopython-0.33.2}/src/videopython/ai/generation/audio.py

@@ -33,7 +33,7 @@ class TextToSpeech:
         self._model: Any = None
 
     def _init_local(self) -> None:
-        from chatterbox.mtl_tts import ChatterboxMultilingualTTS  # type: ignore[import-untyped]
+        from chatterbox.mtl_tts import ChatterboxMultilingualTTS
 
         requested_device = self.device
         device = select_device(self.device, mps_allowed=False)

{videopython-0.33.1 → videopython-0.33.2}/src/videopython/ai/generation/translation.py

@@ -170,7 +170,7 @@ class MarianTranslator:
         return f"Helsinki-NLP/opus-mt-{source_lang}-{target_lang}"
 
     def _init_local(self, source_lang: str, target_lang: str) -> None:
-        from transformers import MarianMTModel, MarianTokenizer  # type: ignore[attr-defined]
+        from transformers import MarianMTModel, MarianTokenizer
 
         model_name = self._get_local_model_name(source_lang, target_lang)
 

{videopython-0.33.1 → videopython-0.33.2}/src/videopython/ai/understanding/audio.py

@@ -188,7 +188,7 @@ class AudioToText:
     def _init_diarization(self) -> None:
         """Initialize pyannote speaker diarization pipeline."""
         import torch
-        from pyannote.audio import Pipeline  # type: ignore[import-untyped]
+        from pyannote.audio import Pipeline
 
         self._diarization_pipeline = Pipeline.from_pretrained(self.PYANNOTE_DIARIZATION_MODEL)
         self._diarization_pipeline.to(torch.device(self.device))
@@ -214,7 +214,7 @@ class AudioToText:
         self._vad_model = None
         release_device_memory(self.device)
 
-    def _process_transcription_result(self, transcription_result: dict) -> Transcription:
+    def _process_transcription_result(self, transcription_result: dict[str, Any]) -> Transcription:
         """Process raw transcription result into a Transcription object."""
         transcription_segments = []
         for segment in transcription_result["segments"]:

{videopython-0.33.1 → videopython-0.33.2}/src/videopython/ai/understanding/faces.py

@@ -237,7 +237,7 @@ class FaceTracker:
 
     def _select_face(
         self,
-        faces: list,
+        faces: list[DetectedFace],
         frame_width: int,
         frame_height: int,
     ) -> tuple[float, float, float, float] | None:
@@ -251,29 +251,24 @@ class FaceTracker:
         Returns:
             Tuple of (center_x, center_y, width, height) in normalized coords, or None.
         """
-        if not faces:
+        faces_with_box = [(f, f.bounding_box) for f in faces if f.bounding_box is not None]
+        if not faces_with_box:
             return None
 
         if self.selection_strategy == "largest":
-            face = faces[0]
+            _, bbox = faces_with_box[0]
         elif self.selection_strategy == "centered":
             frame_center = (0.5, 0.5)
-            face = min(
-                faces,
-                key=lambda f: (
-                    (f.bounding_box.center[0] - frame_center[0]) ** 2
-                    + (f.bounding_box.center[1] - frame_center[1]) ** 2
-                ),
+            _, bbox = min(
+                faces_with_box,
+                key=lambda fb: ((fb[1].center[0] - frame_center[0]) ** 2 + (fb[1].center[1] - frame_center[1]) ** 2),
             )
         elif self.selection_strategy == "index":
-            if self.face_index < len(faces):
-                face = faces[self.face_index]
-            else:
-                face = faces[0]
+            idx = self.face_index if self.face_index < len(faces_with_box) else 0
+            _, bbox = faces_with_box[idx]
         else:
-            face = faces[0]
+            _, bbox = faces_with_box[0]
 
-        bbox = face.bounding_box
         return (bbox.center[0], bbox.center[1], bbox.width, bbox.height)
 
     def detect_and_track(
@@ -407,7 +402,7 @@ class FaceTracker:
 
         sampled_frames = [frames[i] for i in sample_indices]
 
-        sampled_detections: list[list] = []
+        sampled_detections: list[list[DetectedFace]] = []
         for batch_start in range(0, len(sampled_frames), self.batch_size):
             batch_end = min(batch_start + self.batch_size, len(sampled_frames))
             batch = sampled_frames[batch_start:batch_end]

{videopython-0.33.1 → videopython-0.33.2}/src/videopython/ai/understanding/image.py

@@ -151,7 +151,7 @@ class SceneVLM:
     def _init_local(self) -> None:
         """Initialize local Qwen3.5 model."""
         import torch
-        from transformers import AutoModelForImageTextToText, AutoProcessor  # type: ignore[attr-defined]
+        from transformers import AutoModelForImageTextToText, AutoProcessor
 
         t0 = time.perf_counter()
         requested_device = self.device
@@ -275,7 +275,7 @@ class SceneVLM:
     def _generate_from_message_batch(self, messages_batch: list[list[dict[str, Any]]]) -> list[str]:
         """Run batch generation for one or more multimodal chat messages."""
         import torch
-        from qwen_vl_utils import process_vision_info  # type: ignore
+        from qwen_vl_utils import process_vision_info
 
         if self._model is None:
             self._init_local()

{videopython-0.33.1 → videopython-0.33.2}/src/videopython/audio/audio.py

@@ -5,7 +5,7 @@ import subprocess
 import wave
 from dataclasses import dataclass
 from pathlib import Path
-from typing import TYPE_CHECKING
+from typing import TYPE_CHECKING, Any
 
 import numpy as np
 
@@ -69,7 +69,7 @@ class Audio:
         return bool(np.all(np.abs(self.data) < 1e-7))
 
     @staticmethod
-    def _get_ffmpeg_info(file_path: Path) -> dict:
+    def _get_ffmpeg_info(file_path: Path) -> dict[str, Any]:
         """Get audio metadata using ffprobe"""
         try:
             info = _ffmpeg.probe(file_path)
@@ -483,7 +483,7 @@ class Audio:
         if first.metadata.channels == 1:
             output = np.zeros(total_samples, dtype=np.float32)
         else:
-            output = np.zeros((total_samples, 2), dtype=np.float32)  # type: ignore
+            output = np.zeros((total_samples, 2), dtype=np.float32)
 
         # Copy non-crossfaded portions
         crossfade_start = len(first.data) - crossfade_samples
@@ -761,7 +761,7 @@ class Audio:
         if base.metadata.channels == 1:
             output = np.zeros(total_length, dtype=np.float32)
         else:
-            output = np.zeros((total_length, 2), dtype=np.float32)  # type: ignore
+            output = np.zeros((total_length, 2), dtype=np.float32)
 
         # Copy base audio
         output[: len(base.data)] = base.data

{videopython-0.33.1 → videopython-0.33.2}/src/videopython/base/_ffmpeg.py

@@ -13,7 +13,7 @@ import json
 import subprocess
 from contextlib import contextmanager
 from pathlib import Path
-from typing import Iterator, Sequence
+from typing import Any, Iterator, Sequence
 
 from videopython.base.exceptions import FFmpegProbeError, FFmpegRunError
 
@@ -44,7 +44,7 @@ def run(cmd: Sequence[str], *, stdin: bytes | None = None) -> bytes:
     return result.stdout
 
 
-def probe(path: str | Path, *, extra_args: Sequence[str] | None = None) -> dict:
+def probe(path: str | Path, *, extra_args: Sequence[str] | None = None) -> dict[str, Any]:
     """Run ffprobe and return the parsed JSON payload.
 
     Args:
@@ -76,7 +76,7 @@ def probe(path: str | Path, *, extra_args: Sequence[str] | None = None) -> dict:
         raise FFmpegProbeError(f"Error parsing ffprobe output: {e}") from e
 
 
-def _terminate(proc: subprocess.Popen, *, timeout: float = 5) -> None:
+def _terminate(proc: subprocess.Popen[bytes], *, timeout: float = 5) -> None:
     """Terminate a still-running process, escalating to kill after ``timeout``."""
     if proc.poll() is None:
         proc.terminate()
@@ -88,7 +88,7 @@ def _terminate(proc: subprocess.Popen, *, timeout: float = 5) -> None:
 
 
 @contextmanager
-def popen_decode(cmd: Sequence[str], *, bufsize: int = -1) -> Iterator[subprocess.Popen]:
+def popen_decode(cmd: Sequence[str], *, bufsize: int = -1) -> Iterator[subprocess.Popen[bytes]]:
     """Context manager wrapping an ffmpeg decode process.
 
     Yields a Popen with ``stdout=PIPE`` and ``stderr=DEVNULL``. Callers
@@ -116,7 +116,7 @@ def popen_decode(cmd: Sequence[str], *, bufsize: int = -1) -> Iterator[subproces
 
 
 @contextmanager
-def popen_encode(cmd: Sequence[str]) -> Iterator[subprocess.Popen]:
+def popen_encode(cmd: Sequence[str]) -> Iterator[subprocess.Popen[bytes]]:
     """Context manager wrapping an ffmpeg encode process via stdin pipe.
 
     Yields a Popen with ``stdin=PIPE``, ``stdout=DEVNULL``, and

{videopython-0.33.1 → videopython-0.33.2}/src/videopython/base/_video_io.py

@@ -173,7 +173,7 @@ def decode_video(
         if frames_read == 0:
             raise ValueError("No frames were read from the video")
 
-        frames = frames[:frames_read]  # type: ignore
+        frames = frames[:frames_read]
 
         try:
             audio = Audio.from_path(path)

{videopython-0.33.1 → videopython-0.33.2}/src/videopython/base/description.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
 from dataclasses import dataclass, field
+from typing import Any
 
 from pydantic import BaseModel, ConfigDict, Field
 
@@ -49,7 +50,7 @@ class SceneBoundary:
         """Number of frames in this scene."""
         return self.end_frame - self.start_frame
 
-    def to_dict(self) -> dict:
+    def to_dict(self) -> dict[str, Any]:
         """Convert to dictionary for JSON serialization."""
         return {
             "start": self.start,
@@ -59,7 +60,7 @@ class SceneBoundary:
         }
 
     @classmethod
-    def from_dict(cls, data: dict) -> "SceneBoundary":
+    def from_dict(cls, data: dict[str, Any]) -> "SceneBoundary":
         """Create SceneBoundary from dictionary."""
         return cls(
             start=data["start"],
@@ -95,12 +96,12 @@ class BoundingBox(BaseModel):
         """Area of the bounding box (normalized)."""
         return self.width * self.height
 
-    def to_dict(self) -> dict:
+    def to_dict(self) -> dict[str, Any]:
         """Backwards-compat alias for ``model_dump()``."""
         return self.model_dump()
 
     @classmethod
-    def from_dict(cls, data: dict) -> BoundingBox:
+    def from_dict(cls, data: dict[str, Any]) -> BoundingBox:
         """Backwards-compat alias for ``model_validate(data)``."""
         return cls.model_validate(data)
 
@@ -119,7 +120,7 @@ class DetectedObject:
     confidence: float
     bounding_box: BoundingBox | None = None
 
-    def to_dict(self) -> dict:
+    def to_dict(self) -> dict[str, Any]:
         """Convert to dictionary for JSON serialization."""
         return {
             "label": self.label,
@@ -128,7 +129,7 @@ class DetectedObject:
         }
 
     @classmethod
-    def from_dict(cls, data: dict) -> DetectedObject:
+    def from_dict(cls, data: dict[str, Any]) -> DetectedObject:
         """Create DetectedObject from dictionary."""
         return cls(
             label=data["label"],
@@ -160,7 +161,7 @@ class DetectedFace:
         """Area of the face bounding box (normalized), or None if no bounding box."""
         return self.bounding_box.area if self.bounding_box else None
 
-    def to_dict(self) -> dict:
+    def to_dict(self) -> dict[str, Any]:
         """Convert to dictionary for JSON serialization."""
         return {
             "bounding_box": self.bounding_box.to_dict() if self.bounding_box else None,
@@ -168,7 +169,7 @@ class DetectedFace:
         }
 
     @classmethod
-    def from_dict(cls, data: dict) -> DetectedFace:
+    def from_dict(cls, data: dict[str, Any]) -> DetectedFace:
         """Create DetectedFace from dictionary."""
         return cls(
             bounding_box=BoundingBox.from_dict(data["bounding_box"]) if data.get("bounding_box") else None,
@@ -190,7 +191,7 @@ class DetectedText:
     confidence: float
     bounding_box: BoundingBox | None = None
 
-    def to_dict(self) -> dict:
+    def to_dict(self) -> dict[str, Any]:
         """Convert to dictionary for JSON serialization."""
         return {
             "text": self.text,
@@ -199,7 +200,7 @@ class DetectedText:
         }
 
     @classmethod
-    def from_dict(cls, data: dict) -> "DetectedText":
+    def from_dict(cls, data: dict[str, Any]) -> "DetectedText":
         """Create DetectedText from dictionary."""
         return cls(
             text=data["text"],
@@ -229,7 +230,7 @@ class AudioEvent:
         """Duration of the audio event in seconds."""
         return self.end - self.start
 
-    def to_dict(self) -> dict:
+    def to_dict(self) -> dict[str, Any]:
         """Convert to dictionary for JSON serialization."""
         return {
             "start": self.start,
@@ -239,7 +240,7 @@ class AudioEvent:
         }
 
     @classmethod
-    def from_dict(cls, data: dict) -> AudioEvent:
+    def from_dict(cls, data: dict[str, Any]) -> AudioEvent:
         """Create AudioEvent from dictionary."""
         return cls(
             start=data["start"],
@@ -261,7 +262,7 @@ class AudioClassification:
     events: list[AudioEvent]
     clip_predictions: dict[str, float] = field(default_factory=dict)
 
-    def to_dict(self) -> dict:
+    def to_dict(self) -> dict[str, Any]:
         """Convert to dictionary for JSON serialization."""
         return {
             "events": [event.to_dict() for event in self.events],
@@ -269,7 +270,7 @@ class AudioClassification:
         }
 
     @classmethod
-    def from_dict(cls, data: dict) -> "AudioClassification":
+    def from_dict(cls, data: dict[str, Any]) -> "AudioClassification":
         """Create AudioClassification from dictionary."""
         return cls(
             events=[AudioEvent.from_dict(event) for event in data.get("events", [])],
@@ -306,7 +307,7 @@ class MotionInfo:
         """Check if this frame has significant motion."""
         return self.motion_type != "static"
 
-    def to_dict(self) -> dict:
+    def to_dict(self) -> dict[str, Any]:
         """Convert to dictionary for JSON serialization."""
         return {
             "motion_type": self.motion_type,
@@ -315,7 +316,7 @@ class MotionInfo:
         }
 
     @classmethod
-    def from_dict(cls, data: dict) -> MotionInfo:
+    def from_dict(cls, data: dict[str, Any]) -> MotionInfo:
         """Create MotionInfo from dictionary."""
         return cls(
             motion_type=data["motion_type"],
@@ -344,7 +345,7 @@ class SceneDescription:
     subjects: list[str] = field(default_factory=list)
     shot_type: str | None = None
 
-    def to_dict(self) -> dict:
+    def to_dict(self) -> dict[str, Any]:
         return {
             "caption": self.caption,
             "subjects": list(self.subjects),
@@ -352,7 +353,7 @@ class SceneDescription:
         }
 
     @classmethod
-    def from_dict(cls, data: dict) -> "SceneDescription":
+    def from_dict(cls, data: dict[str, Any]) -> "SceneDescription":
         return cls(
             caption=str(data["caption"]),
             subjects=[str(s) for s in data.get("subjects", [])],
@@ -386,7 +387,7 @@ class FaceTrack:
         """Number of frames in this track."""
         return len(self.frame_indices)
 
-    def to_dict(self) -> dict:
+    def to_dict(self) -> dict[str, Any]:
         return {
             "track_id": self.track_id,
             "frame_indices": list(self.frame_indices),
@@ -395,7 +396,7 @@ class FaceTrack:
         }
 
     @classmethod
-    def from_dict(cls, data: dict) -> "FaceTrack":
+    def from_dict(cls, data: dict[str, Any]) -> "FaceTrack":
         return cls(
             track_id=int(data["track_id"]),
             frame_indices=[int(i) for i in data.get("frame_indices", [])],

{videopython-0.33.1 → videopython-0.33.2}/src/videopython/base/transcription.py

@@ -2,6 +2,7 @@ from __future__ import annotations
 
 from dataclasses import dataclass
 from pathlib import Path
+from typing import Any
 
 __all__ = ["Transcription", "TranscriptionSegment", "TranscriptionWord"]
 
@@ -13,7 +14,7 @@ class TranscriptionWord:
     word: str
     speaker: str | None = None
 
-    def to_dict(self) -> dict:
+    def to_dict(self) -> dict[str, Any]:
         """Convert to dictionary for JSON serialization."""
         return {
             "start": self.start,
@@ -23,7 +24,7 @@ class TranscriptionWord:
         }
 
     @classmethod
-    def from_dict(cls, data: dict) -> TranscriptionWord:
+    def from_dict(cls, data: dict[str, Any]) -> TranscriptionWord:
         """Create TranscriptionWord from dictionary."""
         return cls(
             start=data["start"],
@@ -44,7 +45,7 @@ class TranscriptionSegment:
     no_speech_prob: float | None = None
     compression_ratio: float | None = None
 
-    def to_dict(self) -> dict:
+    def to_dict(self) -> dict[str, Any]:
         """Convert to dictionary for JSON serialization."""
         return {
             "start": self.start,
@@ -58,7 +59,7 @@ class TranscriptionSegment:
         }
 
     @classmethod
-    def from_dict(cls, data: dict) -> TranscriptionSegment:
+    def from_dict(cls, data: dict[str, Any]) -> TranscriptionSegment:
         """Create TranscriptionSegment from dictionary."""
         return cls(
             start=data["start"],
@@ -98,8 +99,9 @@ class Transcription:
             self.segments = segments
             self.speakers = {s.speaker for s in segments if s.speaker is not None}
         else:
-            self.segments = self._words_to_segments(words)  # type: ignore
-            self.speakers = {w.speaker for w in words if w.speaker is not None}  # type: ignore
+            assert words is not None
+            self.segments = self._words_to_segments(words)
+            self.speakers = {w.speaker for w in words if w.speaker is not None}
 
     @property
     def words(self) -> list[TranscriptionWord]:
@@ -410,7 +412,7 @@ class Transcription:
         """
         Path(path).write_text(self.to_srt(), encoding="utf-8")
 
-    def to_dict(self) -> dict:
+    def to_dict(self) -> dict[str, Any]:
         """Convert to dictionary for JSON serialization."""
         return {
             "segments": [s.to_dict() for s in self.segments],
@@ -418,7 +420,7 @@ class Transcription:
         }
 
     @classmethod
-    def from_dict(cls, data: dict) -> Transcription:
+    def from_dict(cls, data: dict[str, Any]) -> Transcription:
         """Create Transcription from dictionary."""
         return cls(
             segments=[TranscriptionSegment.from_dict(s) for s in data["segments"]],

{videopython-0.33.1 → videopython-0.33.2}/src/videopython/base/video.py

@@ -3,7 +3,7 @@ from __future__ import annotations
 from dataclasses import dataclass
 from fractions import Fraction
 from pathlib import Path
-from typing import Generator
+from typing import Any, Generator
 
 import numpy as np
 
@@ -48,7 +48,7 @@ class VideoMetadata:
         return np.array((self.frame_count, self.height, self.width, 3))
 
     @staticmethod
-    def _run_ffprobe(video_path: str | Path) -> dict:
+    def _run_ffprobe(video_path: str | Path) -> dict[str, Any]:
         """Run ffprobe and return parsed JSON output."""
         try:
             return _ffmpeg.probe(

{videopython-0.33.1 → videopython-0.33.2}/src/videopython/editing/__init__.py

@@ -1,10 +1,20 @@
 from .effects import (
     Blur,
+    ChromaticAberration,
     ColorGrading,
     Effect,
     Fade,
+    FilmGrain,
+    Flash,
     FullImageOverlay,
+    Glitch,
+    Kaleidoscope,
     KenBurns,
+    MirrorFlip,
+    Pixelate,
+    PunchIn,
+    Shake,
+    Sharpen,
     TextOverlay,
     Vignette,
     VolumeAdjust,
@@ -55,6 +65,16 @@ __all__ = [
     "VolumeAdjust",
     "TextOverlay",
     "TranscriptionOverlay",
+    "Shake",
+    "PunchIn",
+    "Flash",
+    "ChromaticAberration",
+    "Glitch",
+    "FilmGrain",
+    "Sharpen",
+    "Pixelate",
+    "MirrorFlip",
+    "Kaleidoscope",
     # Plan runner
     "VideoEdit",
     "SegmentConfig",