Merge pull request #11 from stephengpope/feature/caption-video

Feature/caption video

Dockerfile

@@ -1,11 +1,119 @@
 # Base image
 FROM python:3.9-slim
 
-# Install system dependencies
+# Install system dependencies, build tools, and libraries
 RUN apt-get update && apt-get install -y --no-install-recommends \
-    ffmpeg \
+    ca-certificates \
+    wget \
+    tar \
+    xz-utils \
+    fonts-liberation \
+    fontconfig \
+    build-essential \
+    yasm \
+    cmake \
+    meson \
+    ninja-build \
+    nasm \
+    libssl-dev \
+    libvpx-dev \
+    libx264-dev \
+    libx265-dev \
+    libnuma-dev \
+    libmp3lame-dev \
+    libopus-dev \
+    libvorbis-dev \
+    libtheora-dev \
+    libspeex-dev \
+    libass-dev \
+    libfreetype6-dev \
+    libfontconfig1-dev \
+    libgnutls28-dev \
+    libaom-dev \
+    libdav1d-dev \
+    librav1e-dev \
+    libsvtav1-dev \
+    libzimg-dev \
+    libwebp-dev \
+    git \
+    pkg-config \
+    autoconf \
+    automake \
+    libtool \
     && rm -rf /var/lib/apt/lists/*
 
+# Install SRT from source (latest version using cmake)
+RUN git clone https://github.com/Haivision/srt.git && \
+    cd srt && \
+    mkdir build && cd build && \
+    cmake .. && \
+    make -j$(nproc) && \
+    make install && \
+    cd ../.. && rm -rf srt
+
+# Install SVT-AV1 from source
+RUN git clone https://gitlab.com/AOMediaCodec/SVT-AV1.git && \
+    cd SVT-AV1 && \
+    git checkout v0.9.0 && \
+    cd Build && \
+    cmake .. && \
+    make -j$(nproc) && \
+    make install && \
+    cd ../.. && rm -rf SVT-AV1
+
+# Install libvmaf from source
+RUN git clone https://github.com/Netflix/vmaf.git && \
+    cd vmaf/libvmaf && \
+    meson build --buildtype release && \
+    ninja -C build && \
+    ninja -C build install && \
+    cd ../.. && rm -rf vmaf && \
+    ldconfig  # Update the dynamic linker cache
+
+# Manually build and install fdk-aac (since it is not available via apt-get)
+RUN git clone https://github.com/mstorsjo/fdk-aac && \
+    cd fdk-aac && \
+    autoreconf -fiv && \
+    ./configure && \
+    make -j$(nproc) && \
+    make install && \
+    cd .. && rm -rf fdk-aac
+
+# Build and install FFmpeg with all required features (without macOS-specific options)
+RUN git clone https://git.ffmpeg.org/ffmpeg.git ffmpeg && \
+    cd ffmpeg && \
+    git checkout n7.0.2 && \
+    ./configure --prefix=/usr/local \
+    --enable-gpl \
+    --enable-pthreads \
+    --enable-neon \
+    --enable-libaom \
+    --enable-libdav1d \
+    --enable-librav1e \
+    --enable-libsvtav1 \
+    --enable-libvmaf \
+    --enable-libzimg \
+    --enable-libx264 \
+    --enable-libx265 \
+    --enable-libvpx \
+    --enable-libwebp \
+    --enable-libmp3lame \
+    --enable-libopus \
+    --enable-libvorbis \
+    --enable-libtheora \
+    --enable-libspeex \
+    --enable-libass \
+    --enable-libfreetype \
+    --enable-fontconfig \
+    --enable-libsrt \
+    --enable-gnutls && \
+    make -j$(nproc) && \
+    make install && \
+    cd .. && rm -rf ffmpeg
+
+# Add /usr/local/bin to PATH (if not already included)
+ENV PATH="/usr/local/bin:${PATH}"
+
 # Set work directory
 WORKDIR /app
 
@@ -38,4 +146,4 @@ ENV PYTHONUNBUFFERED=1
 EXPOSE 8080
 
 # Run the application with Gunicorn
-CMD ["gunicorn", "--bind", "0.0.0.0:8080", "--timeout", "300", "app:app"]
+CMD ["gunicorn", "--bind", "0.0.0.0:8080", "--timeout", "300", "app:app"]

app.py

@@ -5,6 +5,7 @@
 from routes.audio_mixing import audio_mixing_bp
 from routes.gdrive_upload import gdrive_upload_bp
 from routes.authentication import auth_bp  # Import the auth_bp blueprint
+from routes.caption_video import caption_bp 
 
 app = Flask(__name__)
 
@@ -15,6 +16,7 @@
 app.register_blueprint(audio_mixing_bp)
 app.register_blueprint(gdrive_upload_bp)
 app.register_blueprint(auth_bp)  # Register the auth_bp blueprint
+app.register_blueprint(caption_bp) 
 
 if __name__ == '__main__':
     app.run(host='0.0.0.0', port=8080)

requirements.txt

@@ -13,4 +13,4 @@ google-auth-oauthlib
 google-auth-httplib2
 google-api-python-client
 google-cloud-storage
-
+psutil

routes/__init__.py

@@ -0,0 +1,10 @@
+from .combine_videos import combine_bp
+from .gdrive_upload import gdrive_upload_bp
+from .media_to_mp3 import convert_bp
+from .caption_video import caption_bp  # Add this line
+
+def register_blueprints(app):
+    app.register_blueprint(combine_bp)
+    app.register_blueprint(gdrive_upload_bp)
+    app.register_blueprint(convert_bp)
+    app.register_blueprint(caption_bp)  # Add this line

routes/caption_video.py

@@ -0,0 +1,87 @@
+from flask import Blueprint, request, jsonify
+import uuid
+import threading
+import logging
+from services.caption_video import process_captioning
+from services.authentication import authenticate
+
+# Configure logging
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+caption_bp = Blueprint('caption', __name__)
+
+def process_job(data, job_id):
+    try:
+        logger.info(f"Job {job_id}: Starting captioning process")
+        file_url = data['video_url']
+        caption_srt = data['srt']
+        options = data.get('options', {})
+
+        output_filename = process_captioning(file_url, caption_srt, options, job_id)
+
+        if 'webhook_url' in data:
+            send_webhook(data['webhook_url'], {
+                "endpoint": "/caption-video",
+                "code": 200,
+                "id": data.get("id"),
+                "job_id": job_id,
+                "response": output_filename,
+                "message": "success"
+            })
+
+        logger.info(f"Job {job_id}: Captioning process completed successfully")
+        return output_filename
+
+    except Exception as e:
+        logger.error(f"Job {job_id}: Error during processing - {e}")
+        if 'webhook_url' in data:
+            send_webhook(data['webhook_url'], {
+                "endpoint": "/caption-video",
+                "code": 500,
+                "id": data.get("id"),
+                "job_id": job_id,
+                "response": None,
+                "message": str(e),
+            })
+        else:
+            raise
+
+@caption_bp.route('/caption-video', methods=['POST'])
+@authenticate
+def caption_video():
+    data = request.json
+
+    if 'X-API-Key' not in request.headers:
+        logger.error("Missing X-API-Key header")
+        return jsonify({"message": "Missing X-API-Key header"}), 400
+
+    if not all(k in data for k in ('video_url', 'srt')):
+        logger.error("video_url and srt are required")
+        return jsonify({"message": "video_url and srt are required"}), 400
+
+    job_id = str(uuid.uuid4())
+    logger.info(f"Processing Job ID: {job_id}")
+
+    if 'webhook_url' in data:
+        threading.Thread(target=process_job, args=(data, job_id)).start()
+        return jsonify({
+            "code": 202,
+            "id": data.get("id"),
+            "job_id": job_id,
+            "message": "processing"
+        }), 202
+    else:
+        try:
+            output_filename = process_job(data, job_id)
+            return jsonify({
+                "code": 200,
+                "response": output_filename,
+                "message": "success"
+            }), 200
+        except Exception as e:
+            logger.error(f"Job {job_id}: Error during synchronous processing - {e}")
+            return jsonify({
+                "code": 500,
+                "message": str(e)
+            }), 500

services/__init__.py

@@ -1,4 +1,7 @@
+from .audio_mixing import process_audio_mixing
 from .authentication import authenticate
 from .ffmpeg_toolkit import process_conversion, process_video_combination
-from .audio_mixing import process_audio_mixing  # Correct import
-from .file_management import delete_old_files
+from .file_management import download_file
+from .gcp_toolkit import upload_to_gcs
+from .transcription import process_transcription
+from .caption_video import process_captioning  # Add this line