Merge branch 'CCExtractor:master' into master

CCExtractor · Aug 9, 2024 · 80d5b92 · 80d5b92
2 parents 4db3260 + 90204d4
commit 80d5b92
Show file tree

Hide file tree

Showing 56 changed files with 3,857 additions and 796 deletions.
diff --git a/.github/workflows/build_linux.yml b/.github/workflows/build_linux.yml
@@ -96,7 +96,7 @@ jobs:
         run: sudo apt update && sudo apt-get install libgpac-dev
       - uses: actions/checkout@v4
       - name: cache 
-        uses: actions/cache@v3
+        uses: actions/cache@v4
         with:
           path: |
             src/rust/.cargo/registry

diff --git a/.github/workflows/build_mac.yml b/.github/workflows/build_mac.yml
@@ -95,7 +95,7 @@ jobs:
     steps:
       - uses: actions/checkout@v4
       - name: cache 
-        uses: actions/cache@v3
+        uses: actions/cache@v4
         with:
           path: |
             src/rust/.cargo/registry

diff --git a/.github/workflows/build_windows.yml b/.github/workflows/build_windows.yml
@@ -3,6 +3,8 @@ name: Build CCExtractor on Windows
 env:
   RUSTFLAGS: -Ctarget-feature=+crt-static
   VCPKG_DEFAULT_TRIPLET: x64-windows-static
+  VCPKG_DEFAULT_BINARY_CACHE: C:\vcpkg\.cache
+  VCPKG_COMMIT: fba75d09065fcc76a25dcf386b1d00d33f5175af
 
 on:
   workflow_dispatch:
@@ -22,36 +24,45 @@ on:
 
 jobs:
   build_release:
-    runs-on: windows-2019
+    runs-on: windows-2022
     steps:
       - name: Check out repository
         uses: actions/checkout@v4
       - name: Setup MSBuild.exe
         uses: microsoft/[email protected]
-      - name: Install llvm and clang
-        run: choco install llvm gpac
+        with:
+          msbuild-architecture: x64
+      - name: Install gpac
+        run: choco install gpac --version 2.4.0
+      - name: Setup vcpkg
+        run: mkdir C:\vcpkg\.cache
+      - name: Cache vcpkg
+        id: cache
+        uses: actions/cache@v3
+        with:
+          path: |
+            C:\vcpkg\.cache
+          key: vcpkg-${{ runner.os }}-${{ env.VCPKG_COMMIT }}
+      - name: Build vcpkg
+        run: |
+          git clone https://github.com/microsoft/vcpkg
+          ./vcpkg/bootstrap-vcpkg.bat
+      - name: Install dependencies
+        run: ${{ github.workspace }}/vcpkg/vcpkg.exe install --x-install-root ${{ github.workspace }}/vcpkg/installed/
+        working-directory: windows
       - uses: actions-rs/toolchain@v1
         with:
           toolchain: stable
           override: true
       - name: Install Win 10 SDK
         uses: ilammy/msvc-dev-cmd@v1
-      - name: Setup Vcpkg
-        id: vcpkg
-        uses: friendlyanon/setup-vcpkg@v1
-        with:
-          committish: "2023.08.09"
-          cache-version: "3"
-          ignore-reserve-cache-error: true
-      - name: Install dependencies
-        run: cd vcpkg && vcpkg integrate install && vcpkg install leptonica tesseract ffmpeg --triplet x64-windows-static
       - name: build Release-Full
         env:
           LIBCLANG_PATH: "C:\\Program Files\\LLVM\\lib"
           LLVM_CONFIG_PATH: "C:\\Program Files\\LLVM\\bin\\llvm-config"
           CARGO_TARGET_DIR: "..\\..\\windows"
           BINDGEN_EXTRA_CLANG_ARGS: -fmsc-version=0
-          VCPKG_ROOT: ${{ github.workspace }}\vcpkg
+          VCPKG_ROOT: ${{ github.workspace }}/vcpkg
         run: msbuild ccextractor.sln /p:Configuration=Release-Full /p:Platform=x64
         working-directory: ./windows
       - name: Display version information
@@ -64,23 +75,32 @@ jobs:
             ./windows/x64/Release-Full/ccextractorwinfull.exe
             ./windows/x64/Release-Full/*.dll
   build_debug:
-    runs-on: windows-2019
+    runs-on: windows-2022
     steps:
       - name: Check out repository
         uses: actions/checkout@v4
       - name: Setup MSBuild.exe
         uses: microsoft/[email protected]
-      - name: Install llvm and clang
-        run: choco install llvm gpac
-      - name: Setup Vcpkg
-        id: vcpkg
-        uses: friendlyanon/setup-vcpkg@v1
         with:
-          committish: "2023.08.09"
-          cache-version: "3"
-          ignore-reserve-cache-error: true
+          msbuild-architecture: x64
+      - name: Install gpac
+        run: choco install gpac --version 2.4.0
+      - name: Setup vcpkg
+        run: mkdir C:\vcpkg\.cache
+      - name: Cache vcpkg
+        id: cache
+        uses: actions/cache@v3
+        with:
+          path: |
+            C:\vcpkg\.cache
+          key: vcpkg-${{ runner.os }}-${{ env.VCPKG_COMMIT }}
+      - name: Build vcpkg
+        run: |
+          git clone https://github.com/microsoft/vcpkg
+          ./vcpkg/bootstrap-vcpkg.bat
       - name: Install dependencies
-        run: cd vcpkg && vcpkg integrate install && vcpkg install leptonica tesseract ffmpeg --triplet x64-windows-static
+        run: ${{ github.workspace }}/vcpkg/vcpkg.exe install --x-install-root ${{ github.workspace }}/vcpkg/installed/
+        working-directory: windows
       - uses: actions-rs/toolchain@v1
         with:
           toolchain: stable
@@ -93,10 +113,11 @@ jobs:
           LLVM_CONFIG_PATH: "C:\\Program Files\\LLVM\\bin\\llvm-config"
           CARGO_TARGET_DIR: "..\\..\\windows"
           BINDGEN_EXTRA_CLANG_ARGS: -fmsc-version=0
-          VCPKG_ROOT: ${{ github.workspace }}\vcpkg
+          VCPKG_ROOT: ${{ github.workspace }}/vcpkg
         run: msbuild ccextractor.sln /p:Configuration=Debug-Full /p:Platform=x64
         working-directory: ./windows
       - name: Display version information
+        continue-on-error: true
         run: ./ccextractorwinfull.exe --version
         working-directory: ./windows/x64/Debug-Full
       - uses: actions/upload-artifact@v4

diff --git a/.github/workflows/format.yml b/.github/workflows/format.yml
@@ -32,7 +32,7 @@ jobs:
     steps:
       - uses: actions/checkout@v4
       - name: cache 
-        uses: actions/cache@v3
+        uses: actions/cache@v4
         with:
           path: |
             src/rust/.cargo/registry

diff --git a/.github/workflows/release.yml b/.github/workflows/release.yml
@@ -16,7 +16,7 @@ jobs:
       run: echo ::set-output name=VERSION::${GITHUB_REF/refs\/tags\/v/}
       shell: bash
     - name: Setup MSBuild.exe
-      uses: microsoft/setup-msbuild@v1.3.1
+      uses: microsoft/setup-msbuild@v2.0.0
     - name: Install llvm and clang
       uses: egor-tensin/setup-clang@v1
       with:

diff --git a/.gitignore b/.gitignore
@@ -149,7 +149,8 @@ src/rust/CMakeCache.txt
 src/rust/Makefile
 src/rust/cmake_install.cmake
 src/rust/target/
+src/rust/lib_ccxr/target/
 windows/ccx_rust.lib
 windows/*/debug/*
 windows/*/CACHEDIR.TAG
-windows/.rustc_info.json
+windows/.rustc_info.json
diff --git a/docker/README.md b/docker/README.md
@@ -0,0 +1,61 @@
+# CCExtractor Docker image
+
+This dockerfile prepares a minimalist Docker image with CCExtractor. It compiles CCExtractor from sources following instructions from the [Compilation Guide](https://github.com/CCExtractor/ccextractor/blob/master/docs/COMPILATION.MD).
+
+You can install the latest build of this image by running `docker pull CCExtractor/ccextractor`
+
+## Build
+
+You can build the Docker image directly from the Dockerfile provided in [docker](https://github.com/CCExtractor/ccextractor/tree/master/docker) directory of CCExtractor source
+
+```bash
+$ git clone https://github.com/CCExtractor/ccextractor.git && cd ccextractor
+$ cd docker/
+$ docker build -t ccextractor .
+```
+
+## Usage
+
+The CCExtractor Docker image can be used in several ways, depending on your needs.
+
+```bash
+# General usage
+$ docker run ccextractor:latest <features>
+```
+
+1. Process a local file & use `-o` flag
+
+To process a local video file, mount a directory containing the input file inside the container:
+
+```bash
+# Use `-o` to specifying output file
+$ docker run --rm -v $(pwd):$(pwd) -w $(pwd) ccextractor:latest input.mp4 -o output.srt
+
+# Alternatively use `--stdout` feature
+$ docker run --rm -v $(pwd):$(pwd) -w $(pwd) ccextractor:latest input.mp4 --stdout > output.srt
+```
+
+Run this command from where your input video file is present, and change `input.mp4` & `output.srt` with the actual name of files.
+
+2. Enter an interactive environment
+
+If you need to run CCExtractor with additional options or perform other tasks within the container, you can enter an interactive environment:
+bash
+
+```bash
+$ docker run --rm -it --entrypoint='sh' ccextractor:latest
+```
+
+This will start a Bash shell inside the container, allowing you to run CCExtractor commands manually or perform other operations.
+
+### Example
+
+I run help command in image built from `dockerfile`
+
+```bash
+$ docker build -t ccextractor .
+$ docker run --rm ccextractor:latest --help
+```
+
+This will show the `--help` message of CCExtractor tool
+From there you can see all the features and flags which can be used.
diff --git a/docker/dockerfile b/docker/dockerfile
@@ -0,0 +1,48 @@
+FROM alpine:latest as base
+
+FROM base as builder
+
+RUN apk add --no-cache --update git curl gcc cmake glew glfw \
+  tesseract-ocr-dev leptonica-dev clang-dev llvm-dev make pkgconfig \
+  zlib-dev libpng-dev libjpeg-turbo-dev openssl-dev freetype-dev libxml2-dev
+
+RUN cd && git clone https://github.com/gpac/gpac 
+WORKDIR root/gpac/
+RUN ./configure && make && make install-lib  && cd && rm -rf /root/gpac
+
+WORKDIR /root
+RUN git clone https://github.com/CCExtractor/ccextractor.git 
+RUN apk add bash cargo
+RUN export LIB_CLANG_PATH=$(find / -name 'libclang*.so*' 2>/dev/null | grep -v 'No such file' | head -n 1 | xargs dirname)
+RUN cd /root/ccextractor/linux && ./pre-build.sh && ./build
+
+RUN cp /root/ccextractor/linux/ccextractor /ccextractor && rm -rf ~/ccextractor
+
+FROM base as final
+
+COPY --from=builder /lib/ld-musl-x86_64.so.1 /lib/
+COPY --from=builder /usr/lib/libtesseract.so.5 /usr/lib/
+COPY --from=builder /usr/lib/libleptonica.so.6 /usr/lib/
+COPY --from=builder /usr/local/lib/libgpac.so.12 /usr/local/lib/
+COPY --from=builder /usr/lib/libstdc++.so.6 /usr/lib/
+COPY --from=builder /usr/lib/libgcc_s.so.1 /usr/lib/
+COPY --from=builder /usr/lib/libgomp.so.1 /usr/lib/
+COPY --from=builder /usr/lib/libpng16.so.16 /usr/lib/
+COPY --from=builder /usr/lib/libjpeg.so.8 /usr/lib/
+COPY --from=builder /usr/lib/libgif.so.7 /usr/lib/
+COPY --from=builder /usr/lib/libtiff.so.6 /usr/lib/
+COPY --from=builder /usr/lib/libwebp.so.7 /usr/lib/
+COPY --from=builder /usr/lib/libwebpmux.so.3 /usr/lib/
+COPY --from=builder /lib/libz.so.1 /lib/
+COPY --from=builder /lib/libssl.so.3 /lib/
+COPY --from=builder /lib/libcrypto.so.3 /lib/
+COPY --from=builder /usr/lib/liblzma.so.5 /usr/lib/
+COPY --from=builder /usr/lib/libzstd.so.1 /usr/lib/
+COPY --from=builder /usr/lib/libsharpyuv.so.0 /usr/lib/
+
+COPY --from=builder /ccextractor /
+
+ENTRYPOINT [ "/ccextractor" ]
+
+CMD [ "/ccextractor" ]
+
diff --git a/docs/CHANGES.TXT b/docs/CHANGES.TXT
@@ -1,5 +1,14 @@
 0.95 (to be released)
 -----------------
+- New: Create a Docker image to simplify the CCExtractor usage without any environmental hustle (#1611)
+- New: Add time units module in lib_ccxr (#1623)
+- New: Add bits and levenshtein module in lib_ccxr (#1627)
+- New: Add constants module in lib_ccxr (#1624) 
+- New: Add log module in lib_ccxr (#1622)
+- New: Create `lib_ccxr` and `libccxr_exports` (#1621)
+- Fix: Unexpected behavior of get_write_interval (#1609)
+- Update: Bump rsmpeg to latest version for ffmpeg bindings (#1600)
+- New: Add SCC support for CEA-708 decoder (#1595)
 - Fix: respect `-stdout` even if multiple CC tracks are present in a Matroska input file (#1453)
 - Fix: crash in Rust decoder on ATSC1.0 TS Files (#1407)
 - Removed the --with-gui flag for linux/configure and mac/configure (use the Flutter GUI instead)

diff --git a/docs/COMPILATION.MD b/docs/COMPILATION.MD
@@ -10,6 +10,9 @@ Clone the latest repository from Github
 git clone https://github.com/CCExtractor/ccextractor.git
 ```
 
+## Docker
+You can now use docker image to build latest source of CCExtractor without any environmental hustle. Follow these [instructions](https://github.com/CCExtractor/ccextractor/tree/master/docker/README.md) for building docker image & usage of it.
+
 ## Linux
 
 1. Make sure all the dependencies are met.
@@ -20,15 +23,15 @@ Debian:
 sudo apt-get install -y libgpac-dev libglew-dev libglfw3-dev cmake gcc libcurl4-gnutls-dev tesseract-ocr libtesseract-dev libleptonica-dev clang libclang-dev
 ```
 
-RHEL:
+RHEL/Fedora:
 
 ```bash
-yum install -y glew-devel glfw-devel cmake gcc libcurl-devel tesseract-devel leptonica-devel clang
+yum install -y glew-devel glfw-devel cmake gcc libcurl-devel tesseract-devel leptonica-devel clang gpac-devel
 ```
 
 Arch:
 ```bash
-sudo paru -S glew glfw curl tesseract leptonica cmake gcc clang
+sudo paru -S glew glfw curl tesseract leptonica cmake gcc clang gpac
 ```
 
 Rust 1.54 or above is also required. [Install Rust](https://www.rust-lang.org/tools/install). Check specific compilation methods below, on how to compile without rust.
@@ -57,7 +60,7 @@ cd ccextractor/linux
 ./build -without-rust
 
 # compile with debug info
-./build -debug            # same as ./build_debug
+./build -debug            # same as ./builddebug
 
 # compile with hardsubx
 [Optional] You need to set these environment variables correctly according to your machine,