Merge pull request #449 from classtranscribe/staging

Push to production

API.Dockerfile

@@ -1,14 +1,34 @@
-FROM mcr.microsoft.com/dotnet/sdk:8.0.100-1-bookworm-slim as build
+# Also remove platform from docker-compose.override.yml for api and taskengine
+# Uncomment build context in docker-compose.override.yml for api and taskengine
+
+# e.g.,
+#   taskengine:
+#    image: classtranscribe/taskengine:staging
+#    #xx platform: linux/amd64 # Nope - Causes SDK "dotnet restore" to hang on M1 Mac
+#    build:
+#      context: ../../WebAPI
+#      target: publish
+#      dockerfile: ./TaskEngine.Dockerfile
+#
+
+
+#FROM mcr.microsoft.com/dotnet/sdk:8.0-bookworm-slim-amd64 as build
+FROM mcr.microsoft.com/dotnet/sdk:8.0-bookworm-slim as build
 # See https://mcr.microsoft.com/en-us/product/dotnet/sdk/tags
 
-# FROM mcr.microsoft.com/dotnet/core/sdk:3.1.201-bionic as build
+# Running the AMD64 version is of the SDK is broken
+# https://github.com/dotnet/dotnet-docker/discussions/4285
+# https://github.com/NuGet/Home/issues/13062
+
 RUN apt-get -q update && apt-get -qy install git
 WORKDIR /
 RUN git clone https://github.com/eficode/wait-for.git
 
 WORKDIR /src
 COPY ./ClassTranscribeDatabase/ClassTranscribeDatabase.csproj ./ClassTranscribeDatabase/ClassTranscribeDatabase.csproj
-RUN dotnet restore ./ClassTranscribeDatabase/ClassTranscribeDatabase.csproj
+# Did not help ENV DOTNET_NUGET_SIGNATURE_VERIFICATION=false
+# Add --verbosity normal|diagnostic
+RUN dotnet restore --verbosity diagnostic  ./ClassTranscribeDatabase/ClassTranscribeDatabase.csproj
 
 COPY ./ClassTranscribeServer/ClassTranscribeServer.csproj ./ClassTranscribeServer/ClassTranscribeServer.csproj
 RUN dotnet restore ./ClassTranscribeServer/ClassTranscribeServer.csproj

ClassTranscribeDatabase/ClassTranscribeDatabase.csproj

@@ -39,7 +39,7 @@
     <PackageReference Include="Microsoft.AspNet.WebApi.Client" Version="6.0.0" />
     <PackageReference Include="Microsoft.AspNetCore.Http.Abstractions" Version="2.2.0" />
     <PackageReference Include="Microsoft.AspNetCore.Identity.EntityFrameworkCore" Version="8.0.0" />
-    <PackageReference Include="Microsoft.CognitiveServices.Speech" Version="1.34.0" />
+    <PackageReference Include="Microsoft.CognitiveServices.Speech" Version="1.34.1" />
     <PackageReference Include="Microsoft.EntityFrameworkCore" Version="8.0.0" />
     <PackageReference Include="Microsoft.EntityFrameworkCore.Design" Version="8.0.0">
       <IncludeAssets>runtime; build; native; contentfiles; analyzers; buildtransitive</IncludeAssets>

ClassTranscribeServer/Controllers/MediaController.cs

@@ -40,7 +40,9 @@ public MediaController(IAuthorizationService authorizationService,
         [HttpGet("{id}")]
         public async Task<ActionResult<MediaDTO>> GetMedia(string id)
         {
-            var media = await _context.Medias.FindAsync(id);
+            var media = await _context.Medias.
+                Include(m => m.Video).ThenInclude(v => v.Transcriptions).
+                Where(m => m.Id == id).FirstOrDefaultAsync();
 
             if (media == null)
             {

ClassTranscribeServer/Controllers/PlaylistsController.cs

@@ -133,6 +133,13 @@ public async Task<ActionResult<IEnumerable<PlaylistDTO>>> GetPlaylists2(string o
             }
 
             var playLists = await _context.Playlists
+                .Include(p=>p.Medias).ThenInclude(m=>m.Video).ThenInclude(v=>v.Transcriptions)
+                .Include(p=>p.Medias).ThenInclude(m=>m.Video).ThenInclude(v=>v.ProcessedVideo1)
+                .Include(p=>p.Medias).ThenInclude(m=>m.Video).ThenInclude(v=>v.ProcessedVideo2)
+                .Include(p=>p.Medias).ThenInclude(m=>m.Video).ThenInclude(v=>v.Video1)
+                .Include(p=>p.Medias).ThenInclude(m=>m.Video).ThenInclude(v=>v.Video2)
+                .Include(p=>p.Medias).ThenInclude(m=>m.Video).ThenInclude(v=>v.ASLVideo)
+
                 .Where(p => p.OfferingId == offeringId)
                 .OrderBy(p => p.Index)
                 .ThenBy(p => p.CreatedAt).ToListAsync();
@@ -216,6 +223,8 @@ public async Task<ActionResult<IEnumerable<MediaSearchDTO>>> SearchForMedia(stri
         public async Task<ActionResult<PlaylistDTO>> GetPlaylist(string id)
         {
             var p = await _context.Playlists.FindAsync(id);
+            // Media are explicitly loaded below, so LoadAsync is not needed
+
             var user = await _userUtils.GetUser(User);
             if (p == null)
             {

ClassTranscribeServer/Utils/Authorization.cs

@@ -84,7 +84,9 @@ protected override async Task HandleRequirementAsync(AuthorizationHandlerContext
             }
             else if (offering != null && offering.AccessType == AccessTypes.UniversityOnly && user != null)
             {
-                var universityId = await _ctDbContext.CourseOfferings.Where(co => co.OfferingId == offering.Id)
+                var universityId = await _ctDbContext.CourseOfferings
+                    .Include(co=>co.Course).ThenInclude(c=>c.Department)
+                    .Where(co => co.OfferingId == offering.Id)
                     .Select(c => c.Course.Department.UniversityId).FirstAsync();
                 if (user.UniversityId == universityId)
                 {

PythonRpcServer/requirements.txt

@@ -1,49 +1,58 @@
-backcall==0.1.0
-certifi==2023.7.22
-chardet==3.0.4
-click==7.1.1
-decorator==4.4.2
-ffmpy==0.2.2
-grpcio==1.28.1
-grpcio-tools==1.28.1
-idna==2.9
-ipython==7.16.3
-ipython-genutils==0.2.0
-jedi==0.17.0
-KalturaApiClient==18.11.0
-lxml==4.9.1
-
-#numpy==1.21.6
-numpy
-#Dependabot suggested 1.22 ; but that's not generally available yet
+# 2024-1-17 Removed Pygments,python-genutils and ipython 
+# Also removed jedi. why autocomplete?? jedi==0.19.1
+#Why? prompt-toolkit==3.0.43
+
+#Did not try updating (maybe nexttime)
+#protobuf==3.15.0 #4.25.2 
+protobuf==4.25.2 
 
-#opencv-python==4.2.0.34
-# replaced by opencv-contrib-python
-parso==0.7.0
-pexpect==4.8.0
+#Floowing Updated to latest 2024-1-17:
+certifi==2023.11.17
+backcall==0.2.0
+chardet==5.2.0
+click==8.1.7
+decorator==5.1.1
+ffmpy==0.3.1
+grpcio==1.60.0
+grpcio-tools==1.60.0
+idna==3.6
+KalturaApiClient==19.3.0
+lxml==5.1.0
+parso==0.8.3
+pexpect==4.9.0
 pickleshare==0.7.5
-prompt-toolkit==3.0.5
-protobuf==3.15.0
+ptyprocess==0.7.0
+requests==2.31.0
+requests-toolbelt==1.0.0
+six==1.16.0
+tqdm==4.66.1
+traitlets==4.3.3
+urllib3==2.1.0
+wcwidth==0.2.13
+
+# Not versioned
+numpy
+pytube     # if not available, use the tar.gz package (see Dockerfile)
+
+
 # protobuf version 3.18.3 causes  NotImplementedError("To be implemented") in PythonRpcServer/mediaprovider.py
 # Likely need to coordinate updating the C# version too
 
-ptyprocess==0.6.0
-Pygments==2.7.4
-requests==2.23.0
-requests-toolbelt==0.9.1
+
+#############
+# Gone
+#ipython==7.16.3
+#ipython-genutils==0.2.0
+# Pygments==2.7.4
+
+# No longer needed for remaning pythonrpcserver tasks
 #scenedetect==0.5.2
-six==1.14.0
-tqdm==4.45.0
-traitlets==4.3.3
-urllib3==1.25.8
-wcwidth==0.1.9
 #scikit-image==0.17.2
 #nltk==3.6.6
 #pytesseract==0.3.7
 #prefixspan==0.5.2
 #opencv-contrib-python==4.5.3.56
 #mtcnn-opencv==1.0.2
 #decord==0.6.0
-
-# Use latest version
-pytube     # if not available, use the tar.gz package (see Dockerfile)
+#opencv-python==4.2.0.34; replaced by opencv-contrib-python
+#

TaskEngine.Dockerfile

@@ -1,14 +1,14 @@
-FROM mcr.microsoft.com/dotnet/sdk:8.0.100-1-bookworm-slim as build
+FROM mcr.microsoft.com/dotnet/sdk:8.0-bookworm-slim as build
 # See https://mcr.microsoft.com/en-us/product/dotnet/sdk/tags
-# 7.0.404-1 as build
-# FROM mcr.microsoft.com/dotnet/core/sdk:3.1.201-bionic as build
+#See more comments in API.Dockerfile
 
 WORKDIR /
 RUN git clone https://github.com/eficode/wait-for.git
 
 WORKDIR /src
 COPY ./ClassTranscribeDatabase/ClassTranscribeDatabase.csproj ./ClassTranscribeDatabase/ClassTranscribeDatabase.csproj
-RUN dotnet restore ./ClassTranscribeDatabase/ClassTranscribeDatabase.csproj
+# --verbosity normal|diagnostic
+RUN dotnet restore --verbosity diagnostic ./ClassTranscribeDatabase/ClassTranscribeDatabase.csproj
 
 COPY ./TaskEngine/TaskEngine.csproj ./TaskEngine/TaskEngine.csproj
 RUN dotnet restore ./TaskEngine/TaskEngine.csproj
@@ -20,8 +20,11 @@ COPY ./TaskEngine ./TaskEngine
 WORKDIR /src/TaskEngine
 RUN dotnet publish TaskEngine.csproj -c Release -o /app --no-restore
 
-FROM mcr.microsoft.com/dotnet/aspnet:8.0-bookworm-slim as publish_base
-# FROM mcr.microsoft.com/dotnet/core/runtime:3.1.3-bionic as publish_base
+#FROM mcr.microsoft.com/dotnet/aspnet:8.0-bookworm-slim as publish_base
+FROM mcr.microsoft.com/dotnet/aspnet:8.0 as publish_base
+# https://hub.docker.com/_/microsoft-dotnet-aspnet/
+
+# force AMD64 build here: the ssl1.1.1 workaround below assumes amd64
 # Install prerequisites for Azure Speech Services: build-essential libssl-dev ca-certificates libasound2 wget
 # See https://docs.microsoft.com/en-us/azure/cognitive-services/speech-service/quickstarts/setup-platform
 
@@ -30,12 +33,9 @@ apt-get install -y netcat-traditional && apt-get -q update
 
 # Microsoft 8.0 issue: https://github.com/Azure-Samples/cognitive-services-speech-sdk/issues/2204
 # This  will install OpenSSL 1.1.1 because it is needed by the Speech SDK.
-RUN \
-wget http://security.ubuntu.com/ubuntu/pool/main/o/openssl/libssl1.1_1.1.1f-1ubuntu2.20_amd64.deb && \
-wget http://security.ubuntu.com/ubuntu/pool/main/o/openssl/libssl-dev_1.1.1f-1ubuntu2.20_amd64.deb && \
-dpkg -i libssl1.1_1.1.1f-1ubuntu2.20_amd64.deb && \
-dpkg -i libssl-dev_1.1.1f-1ubuntu2.20_amd64.deb && \
-rm libssl1.1_1.1.1f-1ubuntu2.20_amd64.deb libssl-dev_1.1.1f-1ubuntu2.20_amd64.deb
+# RUN ARCH=$(dpkg --print-architecture)
+COPY ./install-speech-hack-libssl1.sh /
+RUN /install-speech-hack-libssl1.sh
 
 
 FROM publish_base as publish

TaskEngine/Tasks/DescribeVideoTask.cs

@@ -1,12 +1,14 @@
-using ClassTranscribeDatabase;
-using ClassTranscribeDatabase.Models;
-using ClassTranscribeDatabase.Services;using Microsoft.Extensions.Logging;
-using Newtonsoft.Json.Linq;
-using System.Collections.Generic;
+using System.Collections.Generic;
 using System.Diagnostics.CodeAnalysis;
 using System;
 using System.Linq;
 using System.Threading.Tasks;
+using Microsoft.Extensions.Logging;
+using Microsoft.EntityFrameworkCore;
+using Newtonsoft.Json.Linq;
+using ClassTranscribeDatabase;
+using ClassTranscribeDatabase.Models;
+using ClassTranscribeDatabase.Services;
 using static ClassTranscribeDatabase.CommonUtils;
 
 
@@ -35,13 +37,14 @@ protected async override Task OnConsume(string videoId, TaskParameters taskParam
 
             using var _context = CTDbContext.CreateDbContext();
             Video video = await _context.Videos.FindAsync(videoId);
-
+            
             if (!video.HasSceneObjectData())
             {
                 GetLogger().LogInformation($"Describe Video {videoId}: Early return - no scene data to process");
                 return;
             }
             TextData td = await _context.TextData.FindAsync(video.SceneObjectDataId);
+            await _context.Transcriptions.Where(t => t.VideoId == videoId).LoadAsync();            
 
             JObject sceneData = td.GetAsJSON() as JObject;
             JArray scenes = sceneData["Scenes"] as JArray;

TaskEngine/Tasks/DownloadMediaTask.cs

@@ -52,7 +52,7 @@ protected override async Task OnConsume(string mediaId, TaskParameters taskParam
                 media = await _context.Medias.Where(m => m.Id == mediaId)
                     .Include(m => m.Playlist).FirstAsync();
                 GetLogger().LogInformation($"Downloading media id=({media.Id}), UniqueMediaIdentifier={media.UniqueMediaIdentifier}");
-                subdir = ToCourseOfferingSubDirectory(_context, media); // e.g. "/data/2203-abcd"
+                subdir = ToCourseOfferingSubDirectory(_context, media.Playlist); // e.g. "/data/2203-abcd"
             }
             Video video = new Video();
             switch (media.SourceType)
@@ -72,7 +72,14 @@ protected override async Task OnConsume(string mediaId, TaskParameters taskParam
 
             using (var _context = CTDbContext.CreateDbContext())
             {
-                var latestMedia = await _context.Medias.FindAsync(media.Id);
+                var latestMedia = await _context.Medias
+                    .Include(m=>m.Video).ThenInclude(v=>v.Video2)
+                    .Include(m=>m.Video).ThenInclude(v=>v.Video1)
+                    .FirstOrDefaultAsync(m => m.Id==media.Id); // Find does not support Include
+                if(latestMedia == null) { // should never happen...
+                    GetLogger().LogInformation($"Media ({media.Id}): latestMedia == null !?");
+                    return;
+                }
                 GetLogger().LogInformation($"Media ({media.Id}): latestMedia.Video == null is {latestMedia.Video == null}");
 
                 // Don't add video if there are already videos for the given media.

TaskEngine/Tasks/TranscriptionTask.cs

@@ -38,7 +38,7 @@ public TranscriptionTask(RabbitMQConnection rabbitMQ, MSTranscriptionService msT
             _captionQueries = captionQueries;
 
         }
-        private async void buildMockCaptions(string videoId)
+        private async Task buildMockCaptions(string videoId)
         {
             GetLogger().LogInformation($"Building Mock Captions for video {videoId}");
 

TestAzureCognitiveServices/.dockerignore

@@ -7,4 +7,6 @@
 **/*.*proj.user
 **/charts
 **/bin
-**/obj
+**/obj
+*Dockerfile
+*cproj

TestAzureCognitiveServices/Program.cs

@@ -143,7 +143,7 @@ static void Main(string[] args)
         }
 
         async static Task<string> useAzureTranslationAsync() {
-            var defaultKeys = "996885bc424b4fda9df983c404e7309c,westus";
+            var defaultKeys = "123,westus";
             Console.WriteLine($"Environment variable AZURE_SUBSCRIPTION_KEYS=key,region;...");
             var keys = System.Environment.GetEnvironmentVariable("AZURE_SUBSCRIPTION_KEYS") ?? defaultKeys;
 

TestAzureCognitiveServices/TestAzure.Dockerfile

@@ -6,7 +6,11 @@ COPY . .
 RUN dotnet restore ./TestAzureCognitiveServices.csproj
 RUN dotnet publish ./TestAzureCognitiveServices.csproj -c Release -o /app --no-restore
 
-FROM mcr.microsoft.com/dotnet/aspnet:8.0-bookworm-slim as publish_base1
+#FROM mcr.microsoft.com/dotnet/aspnet:8.0-bookworm-slim as publish_base1
+# FROM mcr.microsoft.com/dotnet/aspnet:8.0-bookworm-slim-arm64v8 as publish_base1
+FROM mcr.microsoft.com/dotnet/aspnet:8.0 as publish_base1
+
+#COPY ./Program.cs /
 
 # Grrr AzureServices does not work on dotnet8 on Debian 12 because it wont link to libssl3 - fix below is needed for short-term
 
@@ -17,16 +21,9 @@ RUN apt-get -y install build-essential libssl-dev libasound2 wget
 
 # Microsoft 8.0 issue: https://github.com/Azure-Samples/cognitive-services-speech-sdk/issues/2204
 # This  will install OpenSSL 1.1.1 because it is needed by the Speech SDK.
-RUN \
-wget http://security.ubuntu.com/ubuntu/pool/main/o/openssl/libssl1.1_1.1.1f-1ubuntu2.20_amd64.deb && \
-wget http://security.ubuntu.com/ubuntu/pool/main/o/openssl/libssl-dev_1.1.1f-1ubuntu2.20_amd64.deb && \
-dpkg -i libssl1.1_1.1.1f-1ubuntu2.20_amd64.deb && \
-dpkg -i libssl-dev_1.1.1f-1ubuntu2.20_amd64.deb && \
-rm libssl1.1_1.1.1f-1ubuntu2.20_amd64.deb libssl-dev_1.1.1f-1ubuntu2.20_amd64.deb
-
-
-
-
+#RUN ARCH=$(dpkg --print-architecture)
+COPY ./install-libssl1.sh /
+RUN /install-libssl1.sh
 
 FROM publish_base1 as publish1
 WORKDIR /app

TestAzureCognitiveServices/TestAzureCognitiveServices.csproj

@@ -6,7 +6,7 @@
   </PropertyGroup>
 
   <ItemGroup>
-    <PackageReference Include="Microsoft.CognitiveServices.Speech" Version="1.34.0" />
+    <PackageReference Include="Microsoft.CognitiveServices.Speech" Version="1.34.1" />
   </ItemGroup>
 
 </Project>

TestAzureCognitiveServices/install-libssl1.sh

@@ -0,0 +1,17 @@
+#!/bin/sh
+# Temporary 2024 Hack for MS SpeechSDK to run on dotnet8
+ARCH=$(dpkg --print-architecture)
+
+if [ "$ARCH" = "arm64" ] ; then
+    BASE="http://ports.ubuntu.com/ubuntu-ports/pool/main/o/openssl/"
+else
+    BASE="http://security.ubuntu.com/ubuntu/pool/main/o/openssl/"
+fi
+
+wget $BASE/libssl1.1_1.1.1f-1ubuntu2.20_${ARCH}.deb
+wget $BASE/libssl-dev_1.1.1f-1ubuntu2.20_${ARCH}.deb 
+dpkg -i libssl1.1_1.1.1f-1ubuntu2.20_${ARCH}.deb 
+dpkg -i libssl-dev_1.1.1f-1ubuntu2.20_${ARCH}.deb
+rm libssl1.1_1.1.1f-1ubuntu2.20_${ARCH}.deb libssl-dev_1.1.1f-1ubuntu2.20_${ARCH}.deb
+
+