Merge branch 'master' of https://github.com/CCExtractor/ccextractor i…

…nto qualip-ocr_bitmap-last_font_tag

.github/workflows/build_mac.yml

@@ -74,22 +74,6 @@ jobs:
       working-directory: build
     - name: Display version information
       run: ./build/ccextractor --version
-  cmake_ocr_hardsubx:
-    runs-on: macos-latest
-    steps:
-    - uses: actions/checkout@v4
-    - name: Install dependencies
-      run: brew install pkg-config autoconf automake libtool tesseract leptonica gpac ffmpeg
-    - name: cmake
-      run: |
-        mkdir build && cd build
-        cmake -DWITH_OCR=ON -DWITH_HARDSUBX=ON ../src
-    - name: build
-      run: |
-        make -j$(nproc)
-      working-directory: build
-    - name: Display version information
-      run: ./build/ccextractor --version
   build_rust:
     runs-on: macos-latest
     steps:

.github/workflows/build_windows.yml

@@ -29,7 +29,7 @@ jobs:
       - name: Check out repository
         uses: actions/checkout@v4
       - name: Setup MSBuild.exe
-        uses: microsoft/setup-msbuild@v1.3.1
+        uses: microsoft/setup-msbuild@v2.0.0
         with:
           msbuild-architecture: x64
       - name: Install gpac
@@ -38,7 +38,7 @@ jobs:
         run: mkdir C:\vcpkg\.cache
       - name: Cache vcpkg
         id: cache
-        uses: actions/cache@v3
+        uses: actions/cache@v4
         with:
           path: |
             C:\vcpkg\.cache
@@ -80,7 +80,7 @@ jobs:
       - name: Check out repository
         uses: actions/checkout@v4
       - name: Setup MSBuild.exe
-        uses: microsoft/setup-msbuild@v1.3.1
+        uses: microsoft/setup-msbuild@v2.0.0
         with:
           msbuild-architecture: x64
       - name: Install gpac
@@ -89,7 +89,7 @@ jobs:
         run: mkdir C:\vcpkg\.cache
       - name: Cache vcpkg
         id: cache
-        uses: actions/cache@v3
+        uses: actions/cache@v4
         with:
           path: |
             C:\vcpkg\.cache

.github/workflows/format.yml

@@ -26,19 +26,22 @@ jobs:
           git diff-index --quiet HEAD -- || (git diff && exit 1)
   format_rust:
     runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        workdir: ['./src/rust', './src/rust/lib_ccxr']
     defaults:
       run:
-        working-directory: ./src/rust
+        working-directory: ${{ matrix.workdir }}
     steps:
       - uses: actions/checkout@v4
       - name: cache 
         uses: actions/cache@v4
         with:
           path: |
-            src/rust/.cargo/registry
-            src/rust/.cargo/git
-            src/rust/target
-          key: ${{ runner.os }}-cargo-${{ hashFiles('**/Cargo.lock') }}
+            ${{ matrix.workdir }}/.cargo/registry
+            ${{ matrix.workdir }}/.cargo/git
+            ${{ matrix.workdir }}/target
+          key: ${{ runner.os }}-cargo-${{ hashFiles('${{ matrix.workdir }}/Cargo.lock') }}
           restore-keys: ${{ runner.os }}-cargo-
       - uses: actions-rs/toolchain@v1
         with:
@@ -51,4 +54,4 @@ jobs:
         run: cargo fmt --all -- --check
       - name: clippy
         run: |
-          cargo clippy --all-features -- -D warnings
+          cargo clippy -- -D warnings

.github/workflows/test_rust.yml

@@ -0,0 +1,41 @@
+name: Unit Test Rust
+on:
+  push:
+    paths:
+      - ".github/workflows/test.yml"
+      - "src/rust/**"
+    tags-ignore:
+      - "*.*"
+  pull_request:
+    types: [opened, synchronize, reopened]
+    paths:
+      - ".github/workflows/test.yml"
+      - "src/rust/**"
+jobs:
+  test_rust:
+    runs-on: ubuntu-latest
+    defaults:
+      run:
+        working-directory: ./src/rust
+    steps:
+      - uses: actions/checkout@v4
+      - name: cache
+        uses: actions/cache@v4
+        with:
+          path: |
+            src/rust/.cargo/registry
+            src/rust/.cargo/git
+            src/rust/target
+            src/rust/lib_ccxr/target
+          key: ${{ runner.os }}-cargo-${{ hashFiles('**/Cargo.lock') }}
+          restore-keys: ${{ runner.os }}-cargo-
+      - uses: actions-rs/toolchain@v1
+        with:
+          toolchain: stable
+          override: true
+      - name: Test main module
+        run: cargo test
+        working-directory: ./src/rust
+      - name: Test lib_ccxr module
+        run: cargo test
+        working-directory: ./src/rust/lib_ccxr

.gitignore

@@ -17,8 +17,10 @@ CVS
 mac/ccextractor
 linux/ccextractor
 linux/depend
+windows/x86_64-pc-windows-msvc/**
 windows/Debug/**
 windows/Debug-OCR/**
+windows/release-with-debug/**
 windows/Release/**
 windows/Release-Full/**
 windows/Release-OCR/**
@@ -154,3 +156,4 @@ windows/ccx_rust.lib
 windows/*/debug/*
 windows/*/CACHEDIR.TAG
 windows/.rustc_info.json
+linux/configure~

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.

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" ]
+

docs/CHANGES.TXT

@@ -1,5 +1,12 @@
-0.95 (to be released)
------------------
+1.0 (to be released)
+-----------------
+- New: Create unit test for rust code (#1615)
+- Breaking: Major argument flags revamp for CCExtractor (#1564 & #1619)
+- 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)
@@ -26,6 +33,10 @@
 - Cleanup: Remove the (unmaintained) Nuklear GUI code
 - Cleanup: Reduce the amount of Windows build options in the project file
 - Fix: infinite loop in MP4 file type detector.
+- Improvement: Use Corrosion to build Rust code
+- Improvement: Ignore MXF Caption Essence Container version byte to enhance SRT subtitle extraction compatibility
+- New: Add tesseract page segmentation modes control with `--psm` flag
+- Fix: Resolve compile-time error about implicit declarations (#1646)
 - Fix: fatal out of memory error extracting from a VOB PS
 
 0.94 (2021-12-14)

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.

docs/FFMPEG.md

@@ -42,7 +42,7 @@ Note:If you installed ffmpeg on non-standard location, please change/update your
 
 ### On Windows:
 #### Set preprocessor flag `ENABLE_FFMPEG=1`
-1. In visual studio 2013 right click <Project> and select property.
+1. In visual studio 2022 right click <Project> and select property.
 2. In the left panel, select Configuration Properties, C/C++, Preprocessor.
 3. In the right panel, in the right-hand column of the Preprocessor Definitions property, open the drop-down menu and choose Edit.
 4. In the Preprocessor Definitions dialog box, add `ENABLE_FFMPEG=1`. Choose OK to save your changes.

docs/OCR.md

@@ -93,15 +93,15 @@ Download prebuild library of leptonica and tesseract from following link
 https://drive.google.com/file/d/0B2ou7ZfB-2nZOTRtc3hJMHBtUFk/view?usp=sharing  
 
 put the path of libs/include of leptonica and tesseract in library paths.  
-1. In visual studio 2013 right click <Project> and select property.
+1. In visual studio 2022 right click <Project> and select property.
 2. Select Configuration properties in left panel(column) of property.
 3. Select VC++ Directory.
 4. In the right pane, in the right-hand column of the VC++ Directory property, open the drop-down menu and choose Edit.
 5. Add path of Directory where you have kept uncompressed library of leptonica and tesseract.
 
 
 Set preprocessor flag ENABLE_OCR=1  
-1. In visual studio 2013 right click <Project> and select property.
+1. In visual studio 2022 right click <Project> and select property.
 2. In the left panel, select Configuration Properties, C/C++, Preprocessor.
 3. In the right panel, in the right-hand column of the Preprocessor Definitions property, open the drop-down menu and choose Edit.
 4. In the Preprocessor Definitions dialog box, add ENABLE_OCR=1. Choose OK to save your changes.

docs/Rust_migration_guide.md

@@ -0,0 +1,71 @@
+# C to Rust Migration Guide
+
+## Porting C Functions to Rust
+
+This guide outlines the process of migrating C functions to Rust while maintaining compatibility with existing C code.
+
+### Step 1: Identify the C Function
+
+First, identify the C function you want to port. For example, let's consider a function named `net_send_cc()` in a file called `networking.c`:
+
+```c
+void net_send_cc() {
+    // Some C code
+}
+```
+
+### Step 2: Create a Pure Rust Equivalent
+
+Write an equivalent function in pure Rust within the `lib_ccxr` module:
+
+```rust
+fn net_send_cc() {
+    // Rust equivalent code to `net_send_cc` function in `networking.c`
+}
+```
+
+### Step 3: Create a C-Compatible Rust Function
+
+In the `libccxr_exports` module, create a new function that will be callable from C:
+
+```rust
+#[no_mangle]
+pub extern "C" fn ccxr_net_send_cc() {
+    net_send_cc() // Call the pure Rust function
+}
+```
+
+### Step 4: Declare the Rust Function in C
+
+In the original C file (`networking.c`), declare the Rust function as an external function:
+
+```rust
+extern void ccxr_net_send_cc();
+```
+
+### Step 5: Modify the Original C Function
+
+Update the original C function to use the Rust implementation when available:
+
+```c
+void net_send_cc() {
+    #ifndef DISABLE_RUST
+        return ccxr_net_send_cc(); // Use the Rust implementation
+    #else
+        // Original C code
+    #endif
+}
+```
+
+## Rust module system
+
+- `lib_ccxr` crate -> **The Idiomatic Rust layer**
+
+  - Path: `src/rust/lib_ccxr`
+  - This layer will contain the migrated idiomatic Rust. It will have complete documentation and tests.
+
+- `libccxr_exports` module -> **The C-like Rust layer**
+
+  - Path: `src/rust/src/libccxr_exports`
+  - This layer will have function names the same as defined in C but with the prefix `ccxr_`. These are the functions defined in the `lib_ccx` crate under appropriate modules. And these functions will be provided to the C library.
+  - Ex: `extern "C" fn ccxr_<function_name>(<args>) {}`