[ { "path": ".clang-format", "content": "BasedOnStyle: Google\n\n# Modifications for Tesseract.\n\n# Only merge empty functions.\nAllowShortFunctionsOnASingleLine: Empty\n# Do not allow short if statements.\nAllowShortIfStatementsOnASingleLine: false\nIndentPPDirectives: AfterHash\n\n# Default style for some settings.\n\nAccessModifierOffset: -2\nAllowShortLoopsOnASingleLine: false\n# Enforce always the same pointer alignment.\nDerivePointerAlignment: false\nIncludeBlocks: Preserve\nPointerAlignment: Right\nSpacesBeforeTrailingComments: 1\n" }, { "path": ".gitattributes", "content": "* text=auto\n" }, { "path": ".github/ISSUE_TEMPLATE/issue-bug.yml", "content": "name: Bug Report\ndescription: File a bug report\nbody:\n - type: markdown\n attributes:\n value: |\n ### Attention\n Before you submit an issue, please review [the guidelines for this repository](https://github.com/tesseract-ocr/tesseract/blob/main/CONTRIBUTING.md).\n\n Have a question? Need help?\n Please use [our forum](https://groups.google.com/g/tesseract-ocr).\n\n Please follow these rules:\n * Check that your Operating Systems is [supported](https://tesseract-ocr.github.io/tessdoc/supported-operating-systems.html).\n * Don't open an issue for [Tesseract version which was released more than a year ago](https://tesseract-ocr.github.io/tessdoc/ReleaseNotes.html).\n * Don't open an issue which involves 3rd party tools that use Tesseract as a library. Only report about an issue with the Tesseract command line tool or the C/C++ API.\n * Please provide the input image.\n * Also provide output files (txt and/or tsv, hocr, pdf). You can make a zip archive that will contain these files, so GitHub will let you upload them.\n * Don't attach a screenshot of the command line and output. Instead, copy the text and paste it in your bug report.\n\n - type: textarea\n attributes:\n label: Current Behavior\n - type: textarea\n attributes:\n label: Expected Behavior\n - type: textarea\n attributes:\n label: Suggested Fix\n - type: textarea\n attributes:\n label: tesseract -v\n description: Version info, compiled libraries, SIMD, OpenMP\n placeholder: \"Please paste the output of the command: tesseract -v\"\n - type: dropdown\n id: os-linux\n attributes:\n label: Operating System\n description: Choose the OS where the bug occurs\n multiple: true\n options:\n - Windows 11\n - Windows 10\n - macOS 26 Tahoe\n - macOS 15 Sequoia\n - macOS 14 Sonoma\n - Ubuntu 24.04 Noble\n - Ubuntu 22.04 Jammy\n - Debian 13 Trixie\n - Debian 12 Bookworm\n - RHEL 10\n - RHEL 9\n - type: textarea\n attributes:\n label: Other Operating System\n placeholder: Enter the name and version of the OS\n - type: textarea\n attributes:\n label: uname -a\n placeholder: \"Paste the output of the command: uname -a (if available in your system).\"\n\n - type: textarea\n attributes:\n label: Compiler\n placeholder: \"Enter compiler name and version (Examples: MSVC 2019 16.11, Clang 13.0.1, GCC 11.2, Xcode 14.1)\"\n - type: textarea\n attributes:\n label: CPU\n placeholder: \"Enter your CPU vendor name and model (Examples: Intel Core i7-11700K, AMD Ryzen 7 5800X, Apple Silicon M1)\"\n - type: textarea\n attributes:\n label: Virtualization / Containers\n placeholder: \"Enter the name and version of the VM / container which you use (Examples: Oracle VM VirtualBox 7.0.4,VMware Workstation 17.0, Hyper-V, Docker 20.10.22)\"\n - type: textarea\n attributes:\n label: Other Information\n placeholder: Add more details here.\n" }, { "path": ".github/ISSUE_TEMPLATE/issue-feature-request.yml", "content": "name: Feature Request\ndescription: File a feature request\nbody:\n - type: textarea\n attributes:\n label: Your Feature Request\n description: Please look first at the [open issues labeled as 'feature request'](https://github.com/tesseract-ocr/tesseract/labels/feature%20request).\n" }, { "path": ".github/copilot-instructions.md", "content": "# Tesseract OCR - GitHub Copilot Instructions\n\n## Repository Overview\n\nTesseract is an open-source **OCR (Optical Character Recognition) engine** that recognizes text from images. This repository contains:\n\n- **libtesseract**: C++ OCR library with C API wrapper\n- **tesseract**: Command-line OCR program\n- **Training tools**: For creating custom language models\n\n**Key Facts:**\n- Primary language: **C++17** (requires C++17-compliant compiler)\n- Size: Large (~100MB+ with submodules)\n- License: Apache 2.0\n- Maintained by: Stefan Weil (lead), Zdenko Podobny (maintainer)\n\n## Build Systems\n\nTesseract supports **two build systems**. Both are actively maintained and tested in CI.\n\n### 1. Autotools (Traditional, POSIX Systems)\n\n**When to use:** Linux, macOS (command-line), MSYS2 on Windows\n\n**Build sequence:**\n```bash\n./autogen.sh # Generate configure script (only needed after git clone)\n./configure # Configure build (creates Makefiles)\nmake # Build library and CLI\nsudo make install # Install to system\nsudo ldconfig # Update library cache (Linux only)\nmake training # Build training tools (optional)\nsudo make training-install # Install training tools\n```\n\n**Important:**\n- ALWAYS run `./autogen.sh` first if building from git clone\n- Use `make -j N` for parallel builds (N = number of CPU cores)\n- Check `configure --help` for build options\n- To clean: `make clean` or `make distclean` (complete cleanup)\n\n### 2. CMake (Modern, Cross-platform)\n\n**When to use:** Windows (MSVC, MinGW), cross-platform, modern development\n\n**Build sequence:**\n```bash\nmkdir build # MUST use out-of-source build\ncd build\ncmake .. # Configure (add options here)\nmake # Or: cmake --build .\nsudo make install # Install to system\n```\n\n**Important CMake options:**\n- `BUILD_TRAINING_TOOLS=ON` - Enable training tools build\n- `CMAKE_BUILD_TYPE=Release` - Release build (default is RelWithDebInfo)\n- `GRAPHICS_DISABLED=ON` - Disable ScrollView (GUI debugger)\n- `ENABLE_NATIVE=OFF` - Disable CPU-specific optimizations (for portability)\n\n**CMake enforces out-of-source builds** - you cannot build in the source directory. If you get an error about this, remove `CMakeCache.txt` and build in a separate directory.\n\n## Dependencies\n\n### Core Required Dependencies\n\n- **Leptonica 1.74.2+** (REQUIRED) - Image I/O library\n - Without this, build will fail\n - Usually installed via package manager: `libleptonica-dev` (Ubuntu) or `leptonica` (Homebrew)\n\n- **C++17 compiler:**\n - GCC 7+, Clang 5+, MSVC 2017+\n - Verified compilers: gcc-11, gcc-12, gcc-14, clang-15, clang++\n\n### Training Tools Dependencies\n\nOnly needed if building training tools (`make training` or `-DBUILD_TRAINING_TOOLS=ON`):\n\n- pango-devel / libpango1.0-dev\n- cairo-devel\n- icu-devel\n\n### Optional Dependencies\n\n- **libarchive-dev**, **libcurl4-openssl-dev** - For advanced features\n- **OpenMP** - For parallel processing (enabled by default if available)\n- **cabextract** - For testing with CAB archives\n\n### Traineddata Files\n\nTesseract requires **traineddata files** to function. Minimum required:\n- `eng.traineddata` (English)\n- `osd.traineddata` (Orientation and Script Detection)\n\n**Installation:**\n```bash\n# Download individual files (to /usr/local/share/tessdata/ or your TESSDATA_PREFIX path)\ncd /usr/local/share/tessdata/ # Or wherever you want to install\nwget https://github.com/tesseract-ocr/tessdata/raw/main/eng.traineddata\nwget https://github.com/tesseract-ocr/tessdata/raw/main/osd.traineddata\n\n# Or clone all languages (WARNING: 1.2+ GB)\ngit clone https://github.com/tesseract-ocr/tessdata.git\n```\n\n**Set environment variable:**\n```bash\nexport TESSDATA_PREFIX=/usr/local/share/tessdata/\n```\n\nVerify with: `tesseract --list-langs`\n\n## Testing\n\n### Running Unit Tests\n\n**With autotools:**\n```bash\n./autogen.sh\n./configure\nmake\nmake check # Runs all unit tests\n```\n\n**With CMake:**\n```bash\nmkdir build && cd build\ncmake ..\nmake\nctest # Or: cmake --build . --target test\n```\n\n**Important:**\n- Tests require `googletest` submodule: `git submodule update --init --recursive`\n- Tests require tessdata files (eng, osd minimum)\n- Test results in `test-suite.log` (autotools) or CTest output (CMake)\n\n### Running Tesseract CLI\n\nBasic test commands:\n```bash\n# After installation:\ntesseract --version\ntesseract --list-langs\ntesseract input.png output # OCR image, creates output.txt\ntesseract input.png output pdf # Create searchable PDF\n```\n\nTest files available in `test/testing/` (requires test submodule):\n- `phototest.tif` - English test image\n- `devatest.png` - Hindi/Devanagari test image (different format intentional)\n\n## Project Structure\n\n### Source Code Layout\n\n```\nsrc/\n├── api/ # Public C/C++ API (baseapi.h, capi.h)\n├── ccmain/ # Main OCR control logic\n├── lstm/ # LSTM neural network engine (Tesseract 4+)\n├── ccutil/, cutil/ # Core utilities, data structures\n├── classify/ # Character classifier\n├── dict/ # Dictionary and language model\n├── textord/ # Text line and word detection\n├── wordrec/ # Word recognition\n├── training/ # Training tools (lstmtraining, text2image, etc.)\n└── tesseract.cpp # CLI main() entry point\n\ninclude/tesseract/ # Public header files\nunittest/ # Unit tests (requires googletest)\ntest/testing/ # Test images and data\ntessdata/ # Default location for traineddata files\ndoc/ # Documentation\n```\n\n### Key Files\n\n- **src/api/baseapi.h** - Main C++ API class (`TessBaseAPI`)\n- **src/api/capi.h** - C wrapper API\n- **src/tesseract.cpp** - Command-line tool\n- **CMakeLists.txt**, **configure.ac**, **Makefile.am** - Build configuration\n- **VERSION** - Current version string\n\n### Configuration Files\n\n- **.clang-format** - Code formatting rules (LLVM style)\n- **tesseract.pc.in** - pkg-config template\n- **.github/workflows/** - CI/CD definitions\n\n## CI/CD Workflows\n\n### Active Workflows\n\n1. **cmake.yml** - CMake builds on Ubuntu/macOS, 6 configurations\n2. **autotools.yml** - Autotools builds, comprehensive testing\n3. **unittest.yml** - Unit tests with sanitizers (ASAN, UBSAN)\n4. **codeql-analysis.yml** - Security static analysis\n5. **vcpkg.yml**, **msys2.yml**, **cmake-win64.yml** - Windows builds\n\n### Validation Requirements\n\nAll PRs trigger:\n- **Build tests** on multiple platforms (Ubuntu 22.04, 24.04, macOS 14, 15)\n- **Compiler tests** (GCC 11-14, Clang 15)\n- **Unit tests** with sanitizers\n- **CodeQL** security scan\n\n**Expect ~10-30 minutes** for full CI validation.\n\n### Common CI Failures\n\n- **Missing dependencies:** Check workflow files for required packages\n- **Test failures:** Often due to missing tessdata files\n- **Sanitizer errors:** Memory leaks, undefined behavior\n- **CodeQL alerts:** Security vulnerabilities in code\n\n## Common Build Issues & Workarounds\n\n### Issue: \"configure: error: Leptonica not found\"\n**Solution:** Install leptonica development package\n```bash\n# Ubuntu/Debian:\nsudo apt-get install libleptonica-dev\n# macOS:\nbrew install leptonica\n```\n\n### Issue: \"CMake Error: cannot build in source directory\"\n**Solution:** CMake requires out-of-source builds\n```bash\nrm -f CMakeCache.txt\nmkdir build && cd build && cmake ..\n```\n\n### Issue: \"make check\" fails with \"cannot find tessdata\"\n**Solution:** Set TESSDATA_PREFIX or download files\n```bash\nexport TESSDATA_PREFIX=/usr/local/share/tessdata/\n# Or copy files to /usr/local/share/tessdata/\n```\n\n### Issue: Submodule errors (googletest, test)\n**Solution:** Initialize submodules\n```bash\ngit submodule update --init --recursive\n```\n\n### Issue: Old Tesseract version conflicts\n**Solution:** Remove previous installation before building\n```bash\n# Find installed files:\nwhich tesseract\npkg-config --modversion tesseract\n# Uninstall old version, then rebuild\n```\n\n### Issue: Training tools not building\n**Solution:** Install pango, cairo, icu dependencies\n```bash\nsudo apt-get install libpango1.0-dev libcairo2-dev libicu-dev\n```\n\n## Validation Steps for Code Changes\n\nWhen making code changes, follow these steps:\n\n1. **Build the project** (choose one):\n ```bash\n # Autotools:\n ./autogen.sh && ./configure && make\n # CMake:\n mkdir build && cd build && cmake .. && make\n ```\n\n2. **Run unit tests**:\n ```bash\n # Autotools:\n make check\n # CMake:\n ctest\n ```\n\n3. **Test CLI manually**:\n ```bash\n tesseract test/testing/phototest.tif output\n cat output.txt # Verify OCR output\n ```\n\n4. **Check for memory issues** (if modifying C++ code):\n ```bash\n # Build with sanitizers:\n CXXFLAGS=\"-g -O2 -fsanitize=address,undefined\" ./configure\n make && make check\n ```\n\n5. **Run CodeQL** (security check):\n - Will run automatically in CI\n - Or use GitHub Code Scanning locally\n\n6. **Verify documentation** (if API changes):\n - Update header comments in `include/tesseract/`\n - Update relevant docs in `doc/`\n\n## Code Style & Conventions\n\n- **Formatting:** Use clang-format with `.clang-format` config (LLVM style)\n- **Naming:** \n - Classes: `CamelCase` (e.g., `TessBaseAPI`)\n - Functions: `CamelCase` (e.g., `ProcessPage`)\n - Variables: `snake_case` or `lower_case`\n- **Headers:** Use include guards, document public APIs\n- **Comments:** Focus on \"why\", not \"what\"\n- **Commits:** Use meaningful messages, reference issue numbers\n\n## Important Notes for AI Coding Agents\n\n1. **Always use out-of-source builds with CMake** - in-source builds are blocked\n2. **Check for Leptonica** before building - it's a hard requirement\n3. **Initialize git submodules** before running tests\n4. **Set TESSDATA_PREFIX** or tests will fail\n5. **Building takes time** - allow 2-5 minutes for full build\n6. **Testing takes time** - `make check` can take 5-10 minutes\n7. **Don't remove existing tests** - they're critical for preventing regressions\n8. **Check CI workflows** for platform-specific requirements\n9. **Sanitizer builds are slower** - 2-3x slower than normal builds\n10. **Training tools are optional** - only build if needed for the task\n\n## Useful Commands Reference\n\n```bash\n# Quick build and test (autotools):\n./autogen.sh && ./configure && make -j8 && make check\n\n# Quick build and test (CMake):\nmkdir build && cd build && cmake .. && make -j8 && ctest\n\n# Format code:\nfind src -name '*.cpp' -o -name '*.h' | xargs clang-format -i\n\n# Check test results:\ncat test-suite.log # autotools\nctest --output-on-failure # CMake\n\n# Install only library (no training):\nmake install # After ./configure && make\n\n# Clean builds:\nmake clean # Partial clean\nmake distclean # Complete clean (autotools)\nrm -rf build # Complete clean (CMake)\n\n# Check installed version:\ntesseract --version\npkg-config --modversion tesseract\n\n# Debug OCR on specific image:\ntesseract input.png output -l eng --psm 6 -c debug_file=/dev/null\n```\n\n---\n\n**Trust these instructions.** Only search for additional information if these instructions are incomplete, outdated, or if you encounter an error not covered here. The workflows and build procedures are tested daily in CI and represent current best practices for this repository.\n" }, { "path": ".github/dependabot.yml", "content": "# To get started with Dependabot version updates, you'll need to specify which\n# package ecosystems to update and where the package manifests are located.\n# Please see the documentation for all configuration options:\n# https://docs.github.com/code-security/dependabot/dependabot-version-updates/configuration-options-for-the-dependabot.yml-file\n\nversion: 2\nupdates:\n - package-ecosystem: \"github-actions\" # See documentation for possible values\n directory: \"/\" # Location of package manifests\n schedule:\n interval: \"weekly\"\n" }, { "path": ".github/workflows/autotools-macos.yml", "content": "name: autotools-macos\n# autotools build of tesseract and training tools on macos homebrew and macports.\n# run command line tests, basicapitest and unittests. '--disable-openmp'\non:\n #push:\n schedule:\n - cron: 0 20 * * *\n workflow_dispatch:\njobs:\n\n brew:\n runs-on: ${{ matrix.config.os }}\n strategy:\n fail-fast: false\n matrix:\n config:\n - { name: macos-latest-clang-autotools, os: macos-latest, cxx: clang++ }\n\n steps:\n - uses: actions/checkout@v6\n with:\n submodules: recursive\n\n - name: Get fonts, tessdata and langdata required for unit tests\n run: |\n git clone https://github.com/egorpugin/tessdata tessdata_unittest\n cp tessdata_unittest/fonts/* test/testing/\n mv tessdata_unittest/* ../\n\n - name: Install dependencies\n run: |\n brew install autoconf automake cabextract libtool\n brew install leptonica libarchive pango\n if ! brew list icu4c &>/dev/null; then\n brew install icu4c\n fi\n if ! brew list curl &>/dev/null; then\n brew install curl\n fi\n\n - name: Setup Tesseract\n run: |\n ./autogen.sh\n\n - name: Configure Tesseract\n run: |\n ./configure '--disable-shared' '--disable-openmp' '--disable-doc' '--with-pic' 'CXX=${{ matrix.config.cxx }}' 'CXXFLAGS=-g -O2'\n\n - name: Make and Install Tesseract\n run: |\n make -j 8\n sudo make install install\n - name: Make and Install Training Tools\n run: |\n make training -j 8\n sudo make install training-install\n\n - name: Make and run Unit Tests (clang)\n if: startsWith(matrix.config.cxx, 'clang')\n run: |\n make check\n\n - name: Make and run Unit Tests (unset LANG needed for g++-8, g++-9, g++-10 on macOS)\n if: startsWith(matrix.config.cxx, 'g')\n shell: bash\n run: |\n unset LANG LC_ALL LC_CTYPE\n locale\n make check\n\n - name: Display Version for tesseract, lstmtraining, text2image\n run: |\n tesseract -v\n lstmtraining -v\n text2image -v\n if: success() || failure()\n\n - name: List languages in different test tessdata-dir\n run: |\n tesseract --list-langs --tessdata-dir ../tessdata\n tesseract --list-langs --tessdata-dir ../tessdata_best\n tesseract --list-langs --tessdata-dir ../tessdata_fast\n\n - name: Run Tesseract on test images in different languages\n run: |\n tesseract test/testing/phototest.tif - --oem 1 --tessdata-dir ../tessdata\n tesseract test/testing/raaj.tif - -l hin --oem 1 --tessdata-dir ../tessdata\n tesseract test/testing/viet.tif - -l vie --oem 1 --tessdata-dir ../tessdata\n tesseract test/testing/hebrew.png - -l heb --oem 1 --tessdata-dir ../tessdata\n tesseract test/testing/eurotext.tif - -l fra --oem 1 --tessdata-dir ../tessdata_best\n tesseract test/testing/arabic.tif - -l ara --oem 1 --psm 6 --tessdata-dir ../tessdata\n\n - name: Run Tesseract basicapitest\n run: |\n export \"PKG_CONFIG_PATH=/usr/local/lib/pkgconfig\"\n cd test\n ${{ matrix.config.cxx }} -o basicapitest testing/basicapitest.cpp $(pkg-config --cflags --libs tesseract lept) -pthread -std=c++17 -framework accelerate\n ./basicapitest\n\n - name: Display Compiler Version\n run: |\n ${{ matrix.config.cxx }} --version\n git log -3 --pretty=format:'%h %ad %s | %an'\n if: always()\n\n - name: Display Unit Tests Report\n run: |\n cat test-suite.log\n if: always()\n\n# ============================================================================================\n\n ports:\n runs-on: ${{ matrix.config.os }}\n strategy:\n fail-fast: false\n matrix:\n config:\n - { name: macos-latest-clang-autotools, os: macos-latest, cxx: clang++ }\n\n steps:\n - uses: actions/checkout@v6\n with:\n submodules: recursive\n\n - name: Get fonts, tessdata and langdata required for tests\n run: |\n git clone https://github.com/egorpugin/tessdata tessdata_unittest\n cp tessdata_unittest/fonts/* test/testing/\n mv tessdata_unittest/* ../\n\n - name: Install Macports\n run: |\n curl -sSLO https://raw.githubusercontent.com/GiovanniBussi/macports-ci/master/macports-ci; source ./macports-ci install\n # --remove-brew does not remove the Homebrew entries in bin,\n # so remove them now.\n rm -v $(brew --prefix)/bin/*\n\n - name: Install Dependencies\n run: |\n sudo port install autoconf automake libtool pkgconfig\n sudo port install leptonica\n sudo port install cairo pango\n sudo port install icu +devel\n sudo port install cabextract libarchive curl\n\n - name: Setup Tesseract\n run: |\n ./autogen.sh\n\n - name: Configure Tesseract\n run: |\n ./configure '--disable-shared' '--disable-openmp' '--disable-doc' '--with-pic' 'CXX=${{ matrix.config.cxx }}' 'CXXFLAGS=-g -O2'\n\n - name: Make and Install Tesseract\n run: |\n make -j 8\n sudo make install install\n\n - name: Make and Install Training Tools\n run: |\n make training -j 8\n sudo make install training-install\n\n - name: Make and run Unit Tests (clang)\n if: startsWith(matrix.config.cxx, 'clang')\n run: |\n make check\n\n - name: Display Version for tesseract, lstmtraining, text2image\n run: |\n tesseract -v\n lstmtraining -v\n text2image -v\n if: success() || failure()\n\n - name: List languages in different test tessdata-dir\n run: |\n tesseract --list-langs --tessdata-dir ../tessdata\n tesseract --list-langs --tessdata-dir ../tessdata_best\n tesseract --list-langs --tessdata-dir ../tessdata_fast\n\n - name: Run Tesseract on test images in different languages\n run: |\n tesseract test/testing/phototest.tif - --oem 1 --tessdata-dir ../tessdata\n tesseract test/testing/raaj.tif - -l hin --oem 1 --tessdata-dir ../tessdata\n tesseract test/testing/viet.tif - -l vie --oem 1 --tessdata-dir ../tessdata\n tesseract test/testing/hebrew.png - -l heb --oem 1 --tessdata-dir ../tessdata\n tesseract test/testing/eurotext.tif - -l fra --oem 1 --tessdata-dir ../tessdata_best\n tesseract test/testing/arabic.tif - -l ara --oem 1 --psm 6 --tessdata-dir ../tessdata\n\n - name: Run Tesseract basicapitest\n run: |\n export \"PKG_CONFIG_PATH=/usr/local/lib/pkgconfig\"\n cd test\n ${{ matrix.config.cxx }} -o basicapitest testing/basicapitest.cpp -I/opt/local/include -L/opt/local/lib $(pkg-config --cflags --libs tesseract lept) -pthread -std=c++17 -framework Accelerate\n ./basicapitest\n\n - name: Display Compiler Version\n run: |\n ${{ matrix.config.cxx }} --version\n git log -3 --pretty=format:'%h %ad %s | %an'\n if: always()\n\n - name: Display Unit Tests Report\n run: |\n cat test-suite.log\n if: always()\n" }, { "path": ".github/workflows/autotools-openmp.yml", "content": "name: autotools-openmp\n# autotools on Ubuntu - run benchmark test. '--enable-openmp' no training tools\non:\n #push:\n #schedule:\n # - cron: 0 20 * * *\n workflow_dispatch:\njobs:\n\n linux:\n runs-on: ${{ matrix.config.os }}\n strategy:\n fail-fast: false\n matrix:\n config:\n - { name: 24.04-openmp, os: ubuntu-24.04 }\n - { name: 22.04-openmp, os: ubuntu-22.04 }\n\n steps:\n - uses: actions/checkout@v6\n with:\n submodules: recursive\n\n - name: Download fonts, tessdata and langdata required for tests\n run: |\n git clone https://github.com/egorpugin/tessdata tessdata_unittest\n cp tessdata_unittest/fonts/* test/testing/\n mv tessdata_unittest/* ../\n\n - name: Install dependencies\n run: |\n sudo apt-get update\n sudo apt-get install autoconf libleptonica-dev -y\n sudo apt-get install libpango1.0-dev -y\n sudo apt-get install cabextract libarchive-dev -y\n sudo apt-get install libcurl4-openssl-dev libcurl4 curl -y\n\n - name: Setup Tesseract\n run: |\n ./autogen.sh\n\n - name: Configure Tesseract\n run: |\n ./configure '--disable-shared' '--enable-openmp' '--disable-doc' 'CXX=g++' 'CXXFLAGS=-g -O2'\n grep -i OpenMP config.log\n\n - name: Make and Install Tesseract\n run: |\n make\n sudo make install\n\n - name: Setup for Tesseract benchmark using image from issue 263 fifteen times in a list file\n run: |\n wget -O i263_speed.jpg https://cloud.githubusercontent.com/assets/9968625/13674495/ac261db4-e6ab-11e5-9b4a-ad91d5b4ff87.jpg\n printf 'i263_speed.jpg\\n%.0s' {1..15} > benchmarks.list\n\n - name: Run Tesseract using image from issue 263 with tessdata_fast\n run: |\n lscpu\n free\n g++ --version\n tesseract -v\n time tesseract benchmarks.list - --tessdata-dir ../tessdata_fast > /dev/null 2>&1\n echo \"tessdata_fast\"\n\n - name: Run Tesseract using image from issue 263 with tessdata_fast and OpenMP Thread Limit\n run: |\n for lmt in {1..3}; do\n time OMP_THREAD_LIMIT=$lmt tesseract benchmarks.list - --tessdata-dir ../tessdata_fast > /dev/null 2>&1 && echo \"OMP_THREAD_LIMIT=\" $lmt \"tessdata_fast\"\n done\n\n - name: Run Tesseract using image from issue 263 with tessdata_best and OpenMP Thread Limit\n run: |\n for lmt in {1..3}; do\n time OMP_THREAD_LIMIT=$lmt tesseract benchmarks.list - --tessdata-dir ../tessdata_best > /dev/null 2>&1 && echo \"OMP_THREAD_LIMIT=\" $lmt \"tessdata_best\"\n done\n\n - name: Run Tesseract using image from issue 263 with tessdata and OpenMP Thread Limit\n run: |\n for lmt in {1..3}; do\n time OMP_THREAD_LIMIT=$lmt tesseract benchmarks.list - --tessdata-dir ../tessdata > /dev/null 2>&1 && echo \"OMP_THREAD_LIMIT=\" $lmt \"tessdata\"\n done\n" }, { "path": ".github/workflows/autotools.yml", "content": "name: autotools\n# autotools build of tesseract and training tools on Ubuntu.\n# run command line tests, basicapitest and unittests. '--disable-openmp'\non:\n #push:\n schedule:\n - cron: 0 20 * * *\njobs:\n\n linux:\n runs-on: ${{ matrix.config.os }}\n strategy:\n fail-fast: false\n matrix:\n config:\n - { name: ubuntu-22.04-clang-15-autotools, os: ubuntu-22.04, cxx: clang++-15 } #installed\n\n - { name: ubuntu-24.04-gcc-14-autotools, os: ubuntu-24.04, cxx: g++-14 } #installed\n - { name: ubuntu-22.04-gcc-12-autotools, os: ubuntu-22.04, cxx: g++-12 } #installed\n - { name: ubuntu-22.04-gcc-11-autotools, os: ubuntu-22.04, cxx: g++-11 } #installed\n\n steps:\n - uses: actions/checkout@v6\n with:\n submodules: recursive\n\n - name: Download fonts, tessdata and langdata required for tests\n run: |\n git clone https://github.com/egorpugin/tessdata tessdata_unittest\n cp tessdata_unittest/fonts/* test/testing/\n mv tessdata_unittest/* ../\n\n - name: Install Compiler\n run: |\n sudo apt-get update\n sudo apt-get install -y ${{ matrix.config.cxx }}\n\n - name: Install dependencies\n run: |\n sudo apt-get install autoconf libleptonica-dev -y\n sudo apt-get install libpango1.0-dev -y\n sudo apt-get install cabextract libarchive-dev -y\n sudo apt-get install libcurl4-openssl-dev libcurl4 curl -y\n\n - name: Setup Tesseract\n run: |\n ./autogen.sh\n\n - name: Configure Tesseract\n run: |\n ./configure '--disable-shared' '--disable-openmp' '--disable-doc' 'CXX=${{ matrix.config.cxx }}' 'CXXFLAGS=-g -O2'\n\n - name: Make and Install Tesseract\n run: |\n make -j 8\n sudo make install install\n\n - name: Make and Install Training Tools\n run: |\n make training -j 8\n sudo make install training-install\n\n - name: Make and run Unit Tests\n run: |\n make check\n\n - name: Display Version for tesseract, lstmtraining, text2image\n run: |\n tesseract -v\n lstmtraining -v\n text2image -v\n if: success() || failure()\n\n - name: List languages in different test tessdata-dir\n run: |\n tesseract --list-langs --tessdata-dir ../tessdata\n tesseract --list-langs --tessdata-dir ../tessdata_best\n tesseract --list-langs --tessdata-dir ../tessdata_fast\n\n - name: Run Tesseract on test images in different languages\n run: |\n tesseract test/testing/phototest.tif - --oem 1 --tessdata-dir ../tessdata\n tesseract test/testing/raaj.tif - -l hin --oem 1 --tessdata-dir ../tessdata\n tesseract test/testing/viet.tif - -l vie --oem 1 --tessdata-dir ../tessdata\n tesseract test/testing/hebrew.png - -l heb --oem 1 --tessdata-dir ../tessdata\n tesseract test/testing/eurotext.tif - -l fra --oem 1 --tessdata-dir ../tessdata_best\n tesseract test/testing/arabic.tif - -l ara --oem 1 --psm 6 --tessdata-dir ../tessdata\n\n - name: Run Tesseract basicapitest\n run: |\n export \"PKG_CONFIG_PATH=/usr/local/lib/pkgconfig\"\n cd test\n ${{ matrix.config.cxx }} -o basicapitest testing/basicapitest.cpp -I/usr/local/include -L/usr/local/lib `pkg-config --cflags --libs tesseract lept ` -pthread -std=c++17\n ./basicapitest\n\n - name: Setup for Tesseract benchmark using image from issue 263 fifteen times in a list file\n run: |\n wget -O i263_speed.jpg https://cloud.githubusercontent.com/assets/9968625/13674495/ac261db4-e6ab-11e5-9b4a-ad91d5b4ff87.jpg\n printf 'i263_speed.jpg\\n%.0s' {1..15} > benchmarks.list\n lscpu\n free\n tesseract -v\n\n - name: Run Tesseract using image from issue 263 with tessdata_fast\n run: |\n time tesseract benchmarks.list - --tessdata-dir ../tessdata_fast > /dev/null 2>&1\n echo \"tessdata_fast - disable-openmp\"\n\n - name: Run Tesseract using image from issue 263 with tessdata_best\n run: |\n time tesseract benchmarks.list - --tessdata-dir ../tessdata_best > /dev/null 2>&1\n echo \"tessdata_best - disable-openmp\"\n\n - name: Run Tesseract using image from issue 263 with tessdata_fast\n run: |\n time tesseract benchmarks.list - --tessdata-dir ../tessdata > /dev/null 2>&1\n echo \"tessdata - disable-openmp\"\n\n - name: Display Compiler Version\n run: |\n ${{ matrix.config.cxx }} --version\n git log -3 --pretty=format:'%h %ad %s | %an'\n if: always()\n\n - name: Display Unit Tests Report\n run: |\n cat test-suite.log\n if: always()\n" }, { "path": ".github/workflows/cifuzz.yml", "content": "name: CIFuzz\n# OSS-Fuzz CI\n# See https://google.github.io/oss-fuzz/getting-started/continuous-integration/\non:\n pull_request:\n branches:\n - main\n paths:\n - '**.cpp'\n - '**.h'\njobs:\n Fuzzing:\n runs-on: ubuntu-latest\n steps:\n - name: Build Fuzzers\n id: build\n uses: google/oss-fuzz/infra/cifuzz/actions/build_fuzzers@master\n with:\n oss-fuzz-project-name: 'tesseract-ocr'\n language: c++\n dry-run: false\n - name: Run Fuzzers\n uses: google/oss-fuzz/infra/cifuzz/actions/run_fuzzers@master\n with:\n oss-fuzz-project-name: 'tesseract-ocr'\n fuzz-seconds: 600\n dry-run: false\n - name: Upload Crash\n uses: actions/upload-artifact@v7\n if: failure() && steps.build.outcome == 'success'\n with:\n name: artifacts\n path: ./out/artifacts\n" }, { "path": ".github/workflows/cmake-win64.yml", "content": "# Based on https://github.com/zdenop/tesserocr/actions/runs/691257659/workflow\n# Build Tesseract on Windows using cmake. No Training Tools.\nname: cmake-win64\non:\n push:\n paths:\n - cmake/**\n - '**/CMakeLists.txt'\n pull_request:\n types: [opened, reopened, synchronize]\n paths:\n - cmake/**\n - '**/CMakeLists.txt'\n schedule:\n - cron: 0 5 * * *\n workflow_dispatch:\n\nenv:\n ILOC: d:/a/local\n png_ver: 1651\n\njobs:\n build:\n name: cmake-win64\n runs-on: windows-latest\n steps:\n - uses: ilammy/setup-nasm@v1\n - uses: microsoft/setup-msbuild@v2\n - name: \"Checkout ${{ github.ref }} ( ${{ github.sha }} )\"\n uses: actions/checkout@v6\n with:\n submodules: recursive\n - run: git fetch --prune --unshallow --tags\n\n - name: Get the version\n id: get_version\n continue-on-error: true\n run: |\n $git_info=$(git describe --tags HEAD)\n $stamp=$(date +'%Y-%m-%d_%H%M%S')\n echo \"version=${git_info}\" >> $env:GITHUB_OUTPUT\n echo \"stamp=${stamp}\" >> $env:GITHUB_OUTPUT\n\n - name: Setup Installation Location\n run: |\n mkdir ${{env.ILOC}}\n\n #- name: Uninstall Perl\n # run: |\n # choco uninstall strawberryperl\n\n - name: Build and Install zlib-ng\n shell: cmd\n run: |\n git clone --depth 1 https://github.com/zlib-ng/zlib-ng.git\n cd zlib-ng\n cmake -Bbuild -DCMAKE_PREFIX_PATH=${{env.ILOC}} -DCMAKE_INSTALL_PREFIX=${{env.ILOC}} -DBUILD_SHARED_LIBS=OFF -DZLIB_COMPAT=ON -DZLIB_ENABLE_TESTS=OFF -DINSTALL_UTILS=OFF\n cmake --build build --target install\n cd ..\n\n - name: Build and Install libpng\n shell: cmd\n run: |\n curl -sSL -o lpng${{env.png_ver}}.zip https://download.sourceforge.net/libpng/lpng${{env.png_ver}}.zip\n unzip.exe -qq lpng${{env.png_ver}}.zip\n cd lpng${{env.png_ver}}\n cmake -Bbuild -DCMAKE_BUILD_TYPE=RelWithDebInfo -DCMAKE_PREFIX_PATH=${{env.ILOC}} -DCMAKE_INSTALL_PREFIX=${{env.ILOC}} -DPNG_TESTS=OFF -DPNG_SHARED=OFF\n cmake --build build --target install\n cd ..\n\n - name: Build and Install libjpeg\n shell: cmd\n run: |\n git clone --depth 1 https://github.com/libjpeg-turbo/libjpeg-turbo.git\n cd libjpeg-turbo\n cmake -Bbuild -DCMAKE_BUILD_TYPE=RelWithDebInfo -DCMAKE_PREFIX_PATH=${{env.ILOC}} -DCMAKE_INSTALL_PREFIX=${{env.ILOC}} -DWITH_TURBOJPEG=OFF -DENABLE_SHARED=OFF\n cmake --build build --target install\n cd ..\n\n - name: Build and Install jbigkit\n shell: cmd\n run: |\n git clone --depth 1 https://github.com/zdenop/jbigkit.git\n cd jbigkit\n cmake -Bbuild -DCMAKE_PREFIX_PATH=${{env.ILOC}} -DCMAKE_INSTALL_PREFIX=${{env.ILOC}} -DBUILD_PROGRAMS=OFF -DBUILD_TOOLS=OFF -DCMAKE_WARN_DEPRECATED=OFF\n cmake --build build --target install\n cd ..\n\n - name: Build and Install libtiff\n shell: cmd\n run: |\n git clone -c advice.detachedHead=false -b \"v4.7.1\" --depth 1 https://gitlab.com/libtiff/libtiff.git\n cd libtiff\n cmake -Bbuild -DCMAKE_BUILD_TYPE=RelWithDebInfo -DCMAKE_PREFIX_PATH=${{env.ILOC}} -DCMAKE_INSTALL_PREFIX=${{env.ILOC}} -Dtiff-tools=OFF -Dtiff-tests=OFF -Dtiff-contrib=OFF -Dtiff-docs=OFF\n cmake --build build --target install\n cd ..\n\n - name: Build and Install leptonica\n shell: cmd\n run: |\n echo \"Building leptonica...\"\n git clone --depth 1 https://github.com/DanBloomberg/leptonica.git\n cd leptonica\n cmake -Bbuild -DCMAKE_BUILD_TYPE=RelWithDebInfo -DCMAKE_PREFIX_PATH=${{env.ILOC}} -DCMAKE_INSTALL_PREFIX=${{env.ILOC}} -DSW_BUILD=OFF -DBUILD_PROG=OFF -DBUILD_SHARED_LIBS=ON\n cmake --build build --target install\n\n - name: Remove not needed tools Before building tesseract\n shell: cmd\n run: >\n rm -Rf ${{env.ILOC}}/bin/*.exe\n\n - name: Build and Install tesseract\n shell: cmd\n run: |\n cmake -Bbuild -G Ninja -DCMAKE_BUILD_TYPE=RelWithDebInfo -DCMAKE_PREFIX_PATH=${{env.ILOC}} -DCMAKE_INSTALL_PREFIX=${{env.ILOC}} -DSW_BUILD=OFF -DBUILD_SHARED_LIBS=ON -DENABLE_LTO=ON -DBUILD_TRAINING_TOOLS=OFF -DFAST_FLOAT=ON -DGRAPHICS_DISABLED=ON -DOPENMP_BUILD=OFF\n cmake --build build --target install\n\n - name: Upload Build Results\n uses: actions/upload-artifact@v7\n with:\n name: tesseract-${{ steps.get_version.outputs.version }}-${{steps.get_version.outputs.stamp}}-VS2019_win64\n path: ${{env.ILOC}}\n retention-days: 5\n\n - name: Display Tesseract Version and Test Command Line Usage\n shell: cmd\n run: |\n curl -sSL https://github.com/tesseract-ocr/tessdata/raw/main/eng.traineddata --output ${{env.ILOC}}/share/tessdata/eng.traineddata\n curl -sSL https://github.com/tesseract-ocr/tessdata/raw/main/osd.traineddata --output ${{env.ILOC}}/share/tessdata/osd.traineddata\n echo \"Setting TESSDATA_PREFIX...\"\n set TESSDATA_PREFIX=${{env.ILOC}}/share/tessdata\n echo \"Setting PATH...\"\n set PATH=${{env.ILOC}}/bin;%PATH%\n echo \"Checking installed tesseract version...\"\n tesseract -v\n echo \"Checking installed langs\"\n tesseract --list-langs\n echo \"Checking OCR process\"\n tesseract test/testing/phototest.tif -\n" }, { "path": ".github/workflows/cmake.yml", "content": "name: cmake\n# cmake build of tesseract and training tools on ubuntu and macOS homebrew using Ninja.\n# test command line version of tesseract. run basicapitest.\non:\n push:\n paths:\n - cmake/**\n - '**/CMakeLists.txt'\n pull_request:\n paths:\n - cmake/**\n - '**/CMakeLists.txt'\n schedule:\n - cron: 0 21 * * *\n workflow_dispatch:\n\njobs:\n basictests:\n name: ${{ matrix.config.name }}\n runs-on: ${{ matrix.config.os }}\n strategy:\n fail-fast: false\n matrix:\n config:\n - { name: macos-14-clang-15-cmake, os: macos-14, cxx: clang++ } # default\n - { name: macos-15-gcc-14-cmake, os: macos-15, cxx: g++ } #installed\n - { name: macos-15-clang-cmake, os: macos-15, cxx: clang++ } # default\n\n - { name: ubuntu-22.04-clang-15-cmake, os: ubuntu-22.04, cxx: clang++-15 } #installed\n - { name: ubuntu-24.04-gcc-12-cmake, os: ubuntu-24.04, cxx: g++-14 } #installed\n - { name: ubuntu-22.04-gcc-12-cmake, os: ubuntu-22.04, cxx: g++-12 } #installed\n\n steps:\n - name: Install compilers on Linux\n run: |\n sudo apt-get update\n sudo apt-get install ${{ matrix.config.cxx }} -y\n if: runner.os == 'Linux'\n\n - name: Install dependencies on Linux\n run: |\n sudo apt-get install autoconf libleptonica-dev -y\n sudo apt-get install libarchive-dev libcurl4-openssl-dev -y\n sudo apt-get install libpango1.0-dev -y\n sudo apt-get install cabextract -y\n sudo apt-get install ninja-build -y\n cmake --version\n if: runner.os == 'Linux'\n\n - name: Install dependencies on macOS\n run: |\n brew install autoconf automake\n brew install leptonica\n # if ! brew list libarchive &>/dev/null; then\n # brew install libarchive\n # fi\n brew install pango\n if ! brew list icu4c &>/dev/null; then\n brew install icu4c\n fi\n if ! brew list curl &>/dev/null; then\n brew install curl\n fi\n brew install cabextract\n ninja --version\n cmake --version\n clang++ --version\n g++ --version\n if: runner.os == 'macOS'\n\n - name: Checkout Source\n uses: actions/checkout@v6\n with:\n submodules: recursive\n\n - name: Configure Tesseract (Linux)\n run: |\n mkdir build\n mkdir inst\n cmake \\\n -S . \\\n -B build \\\n -G Ninja \\\n -DCMAKE_BUILD_TYPE=Release \\\n -DOPENMP_BUILD=OFF \\\n -DCMAKE_CXX_COMPILER=${{ matrix.config.cxx }} \\\n -DCMAKE_INSTALL_PREFIX:PATH=inst\n if: runner.os == 'Linux'\n\n - name: Configure Tesseract (macOS)\n shell: bash\n run: |\n set -e\n mkdir build\n mkdir inst\n cmake \\\n -S . \\\n -B build \\\n -G Ninja \\\n -DCMAKE_BUILD_TYPE=Release \\\n -DOPENMP_BUILD=OFF \\\n -DENABLE_UNITY_BUILD=ON \\\n -DCMAKE_CXX_COMPILER=${{ matrix.config.cxx }} \\\n -DCMAKE_INSTALL_PREFIX:PATH=inst\n if: runner.os == 'macOS'\n\n - name: Build Tesseract\n run: |\n cmake --build build --config Release --target install\n\n - name: Display Tesseract Version\n run: |\n build/inst/bin/tesseract -v\n\n - name: Display Training Tools Version\n run: |\n build/inst/bin/lstmtraining -v\n build/inst/bin/text2image -v\n\n - name: Download fonts, tessdata and langdata required for tests\n run: |\n git clone https://github.com/egorpugin/tessdata tessdata_unittest\n cp tessdata_unittest/fonts/* test/testing/\n mv tessdata_unittest/* ../\n\n - name: List languages in different tessdata-dir\n run: |\n build/inst/bin/tesseract --list-langs --tessdata-dir ../tessdata\n build/inst/bin/tesseract --list-langs --tessdata-dir ../tessdata_best\n build/inst/bin/tesseract --list-langs --tessdata-dir ../tessdata_fast\n\n - name: Run Tesseract on test images in different languages\n run: |\n build/inst/bin/tesseract test/testing/phototest.tif - --oem 1 --tessdata-dir ../tessdata\n build/inst/bin/tesseract test/testing/raaj.tif - -l hin --oem 1 --tessdata-dir ../tessdata\n build/inst/bin/tesseract test/testing/viet.tif - -l vie --oem 1 --tessdata-dir ../tessdata\n build/inst/bin/tesseract test/testing/hebrew.png - -l heb --oem 1 --tessdata-dir ../tessdata\n build/inst/bin/tesseract test/testing/eurotext.tif - -l fra --oem 1 --tessdata-dir ../tessdata_best\n build/inst/bin/tesseract test/testing/arabic.tif - -l ara --oem 1 --psm 6 --tessdata-dir ../tessdata\n\n - name: Build and run basicapitest (Linux)\n run: |\n export \"PKG_CONFIG_PATH=$GITHUB_WORKSPACE/build/inst/lib/pkgconfig/:$PKG_CONFIG_PATH\"\n cd test\n ${{ matrix.config.cxx }} -o basicapitest testing/basicapitest.cpp \"-I$GITHUB_WORKSPACE/build/inst/include\" \"-L$GITHUB_WORKSPACE/build/inst/lib\" $(pkg-config --cflags --libs tesseract lept libarchive libcurl) -pthread -std=c++17\n ./basicapitest\n if: runner.os == 'Linux'\n\n - name: Build and run basicapitest (macOS)\n run: |\n export \"PKG_CONFIG_PATH=$GITHUB_WORKSPACE/build/inst/lib/pkgconfig/:$(brew --prefix)/opt/libarchive/lib/pkgconfig:$(brew --prefix)/Library/Homebrew/os/mac/pkgconfig/11:$PKG_CONFIG_PATH\"\n cd test\n ${{ matrix.config.cxx }} -o basicapitest testing/basicapitest.cpp \"-I$GITHUB_WORKSPACE/build/inst/include\" \"-L$GITHUB_WORKSPACE/build/inst/lib\" $(pkg-config --cflags --libs tesseract lept libcurl) -pthread -std=c++17\n ./basicapitest\n if: runner.os == 'macOS'\n\n - name: Display Compiler Version\n run: |\n ${{ matrix.config.cxx }} --version\n pwd\n ls -la\n # git log -3 --pretty=format:'%h %ad %s | %an'\n if: always()\n" }, { "path": ".github/workflows/codeql-analysis.yml", "content": "# For most projects, this workflow file will not need changing; you simply need\n# to commit it to your repository.\n#\n# You may wish to alter this file to override the set of languages analyzed,\n# or to provide custom queries or build logic.\n#\n# ******** NOTE ********\n# We have attempted to detect the languages in your repository. Please check\n# the `language` matrix defined below to confirm you have the correct set of\n# supported CodeQL languages.\n#\nname: \"CodeQL\"\n\non:\n push:\n branches: [ main ]\n paths:\n - '**.cpp'\n - '**.h'\n - '**/codeql-analysis.yml'\n - 'm4/*.m4'\n - 'Makefile.am'\n - 'autogen.sh'\n - 'configure.ac'\n pull_request:\n # The branches below must be a subset of the branches above\n branches: [ main ]\n paths:\n - '**.cpp'\n - '**.h'\n - '**/codeql-analysis.yml'\n - 'm4/*.m4'\n - 'Makefile.am'\n - 'autogen.sh'\n - 'configure.ac'\n schedule:\n - cron: '34 23 * * 2'\n\njobs:\n analyze:\n name: Analyze\n runs-on: ubuntu-latest\n permissions:\n actions: read\n contents: read\n security-events: write\n\n strategy:\n fail-fast: false\n matrix:\n language: [ 'cpp' ]\n # CodeQL supports [ 'cpp', 'csharp', 'go', 'java', 'javascript', 'python' ]\n # Learn more:\n # https://docs.github.com/en/free-pro-team@latest/github/finding-security-vulnerabilities-and-errors-in-your-code/configuring-code-scanning#changing-the-languages-that-are-analyzed\n\n steps:\n - name: Checkout repository\n uses: actions/checkout@v6\n\n - name: Install dependencies\n run: |\n sudo apt-get update\n sudo apt-get install autoconf libleptonica-dev -y\n sudo apt-get install libpango1.0-dev -y\n sudo apt-get install cabextract libarchive-dev -y\n sudo apt-get install libcurl4-openssl-dev libcurl4 curl -y\n\n # Initializes the CodeQL tools for scanning.\n - name: Initialize CodeQL\n uses: github/codeql-action/init@v4\n with:\n languages: ${{ matrix.language }}\n # If you wish to specify custom queries, you can do so here or in a config file.\n # By default, queries listed here will override any specified in a config file.\n # Prefix the list here with \"+\" to use these queries and those in the config file.\n # queries: ./path/to/local/query, your-org/your-repo/queries@main\n\n - name: Build\n run: |\n ./autogen.sh\n ./configure\n make all training\n\n - name: Perform CodeQL Analysis\n uses: github/codeql-action/analyze@v4\n" }, { "path": ".github/workflows/installer-for-windows.yml", "content": "# GitHub actions - Create Tesseract installer for Windows\n\nname: Cross build for Windows\n\non:\n # Trigger workflow in GitHub web frontend or from API.\n workflow_dispatch:\n inputs:\n targets:\n description: 'Target operating system'\n required: true\n default: 'Windows (64 bit)'\n type: choice\n options:\n - 'Windows (64 bit)'\n\njobs:\n build64:\n runs-on: [ubuntu-24.04]\n steps:\n - uses: actions/checkout@v6\n - name: Build Tesseract installer (64 bit)\n run: nsis/build.sh x86_64\n - uses: actions/upload-artifact@v7\n with:\n name: Tesseract Installer for Windows (64 bit)\n path: dist\n" }, { "path": ".github/workflows/msys2.yml", "content": "name: msys2\n# msys2 build for tesseract -head from main branch.\non:\n #push:\n schedule:\n - cron: 0 17 * * *\njobs:\n windows:\n runs-on: windows-latest\n strategy:\n fail-fast: false\n matrix:\n include:\n - msystem: MINGW64\n mingw_package_prefix: mingw-w64-x86_64\n defaults:\n run:\n shell: msys2 {0}\n steps:\n - uses: actions/checkout@v6\n with:\n submodules: recursive\n - uses: msys2/setup-msys2@v2\n with:\n msystem: ${{ matrix.msystem }}\n install: autoconf automake automake-wrapper git libtool make\n - run: pacman --noconfirm -S ${{ matrix.mingw_package_prefix }}-gcc\n - run: gcc --version\n\n - name: Install dependencies\n run: |\n pacman --noconfirm -S ${{ matrix.mingw_package_prefix }}-cairo\n pacman --noconfirm -S ${{ matrix.mingw_package_prefix }}-curl\n pacman --noconfirm -S ${{ matrix.mingw_package_prefix }}-gcc-libs\n pacman --noconfirm -S ${{ matrix.mingw_package_prefix }}-icu\n pacman --noconfirm -S ${{ matrix.mingw_package_prefix }}-leptonica\n pacman --noconfirm -S ${{ matrix.mingw_package_prefix }}-libarchive\n pacman --noconfirm -S ${{ matrix.mingw_package_prefix }}-pango\n pacman --noconfirm -S ${{ matrix.mingw_package_prefix }}-pkg-config\n pacman --noconfirm -S ${{ matrix.mingw_package_prefix }}-zlib\n\n - name: Setup Tesseract\n run: |\n ./autogen.sh\n\n - name: Configure Tesseract\n run: |\n ./configure '--disable-shared' '--disable-openmp' '--disable-doc' 'CXX=${{ matrix.config.cxx }}' 'CXXFLAGS=-g -O2'\n\n - name: Build and install Tesseract\n run: |\n make\n make install\n\n - name: Make and install training tools\n run: |\n make training\n make training-install\n\n - name: Display version\n run: |\n tesseract -v\n text2image -v\n lstmtraining -v\n\n - name: Download fonts, tessdata and langdata required for tests\n run: |\n git clone https://github.com/egorpugin/tessdata tessdata_unittest\n cp tessdata_unittest/fonts/* test/testing/\n mv tessdata_unittest/* ../\n\n - name: Run Tesseract on phototest.tif and devatest.png\n run: |\n tesseract test/testing/phototest.tif - --tessdata-dir ../tessdata\n tesseract test/testing/devatest.png - -l hin+eng --tessdata-dir ../tessdata\n" }, { "path": ".github/workflows/sw.yml", "content": "name: sw\n\non:\n schedule:\n # every 3rd day\n - cron: 0 0 */3 * *\n\njobs:\n build:\n runs-on: ${{ matrix.os }}\n container: ${{ matrix.container }}\n strategy:\n fail-fast: false\n matrix:\n os: [windows-2022, macos-latest]\n include:\n - os: ubuntu-22.04\n container: fedora:latest\n\n steps:\n - name: packages\n if: matrix.os == 'ubuntu-22.04'\n run: sudo dnf -y install cmake gcc lld which flex bison clang clang-tools-extra git\n\n - uses: actions/checkout@v6\n with:\n submodules: recursive\n - uses: egorpugin/sw-action@master\n\n - name: build\n if: github.event_name != 'pull_request' && (matrix.os == 'windows-2022')\n run: ./sw -static -shared -platform x86,x64 -config d,r build\n - name: build-pr\n if: github.event_name == 'pull_request' && (matrix.os == 'windows-2022')\n run: ./sw build\n\n - name: build\n if: github.event_name != 'pull_request' && (matrix.os != 'windows-2022')\n run: ./sw -static -shared -config d,r build -Dwith-tests=1\n - name: build-pr\n if: github.event_name == 'pull_request' && (matrix.os != 'windows-2022')\n run: ./sw build -Dwith-tests=1\n\n - name: download test data\n run: git clone https://github.com/egorpugin/tessdata tessdata_unittest\n\n - name: copy fonts\n if: matrix.os != 'windows-2022'\n run: cp tessdata_unittest/fonts/* test/testing/\n - name: copy fonts\n if: matrix.os == 'windows-2022'\n run: Copy-Item -Path \"tessdata_unittest\\fonts\\*\" -Destination \"test\\testing\" -Recurse\n shell: pwsh\n\n - name: test\n if: github.event_name != 'pull_request' && (matrix.os != 'windows-2022' && matrix.os != 'macos-latest')\n run: ./sw -static -shared -config \"d,r\" test -Dwith-tests=1 \"-Dskip-tests=lstm,lstm_recode\"\n continue-on-error: true\n - name: test\n if: github.event_name == 'pull_request' && (matrix.os != 'windows-2022')\n run: ./sw test -Dwith-tests=1 \"-Dskip-tests=lstm,lstm_recode\"\n continue-on-error: true\n\n - name: test-nightly\n if: matrix.os != 'windows-2022' && matrix.os != 'macos-latest' && github.event.schedule=='0 0 * * *'\n run: ./sw -static -shared -config \"d,r\" test -Dwith-tests=1\n continue-on-error: true\n\n # windows and macos-latest tests hang here for some reason, investigate\n #- name: test\n #if: matrix.os == 'windows-2022' || matrix.os == 'macos-latest'\n #run: ./sw test -Dwith-tests=1 \"-Dskip-tests=lstm,lstm_recode\"\n #continue-on-error: true\n\n - name: Upload Unit Test Results\n if: always() && matrix.os != 'windows-2022'\n uses: actions/upload-artifact@v7\n with:\n name: Test Results (${{ matrix.os }})\n path: .sw/test/results.xml\n\n - name: Publish Test Report\n if: always() && matrix.os != 'windows-2022'\n uses: mikepenz/action-junit-report@v6\n with:\n check_name: test (${{ matrix.os }})\n report_paths: .sw/test/results.xml\n github_token: ${{ secrets.GITHUB_TOKEN }}\n" }, { "path": ".github/workflows/unittest-disablelegacy.yml", "content": "name: unittest-disablelegacy\n# autotools build on ubuntu, unittests with disabled legacy engine.\n# currently some unittests are failing with disabled legacy engine.\n\non:\n #push:\n schedule:\n - cron: 0 10 * * *\n\njobs:\n linux:\n runs-on: ${{ matrix.os }}\n timeout-minutes: 150\n strategy:\n fail-fast: false\n matrix:\n compiler: [ g++, clang++-18 ]\n os: [ ubuntu-24.04 ]\n\n steps:\n - uses: actions/checkout@v6\n with:\n submodules: recursive\n\n - name: Install dependencies\n run: |\n sudo apt-get update\n sudo apt-get install autoconf libleptonica-dev libpango1.0-dev -y\n sudo apt-get install cabextract -y\n #sudo apt-get install libc++-7-dev libc++abi-7-dev -y\n\n - name: Setup\n run: |\n ./autogen.sh\n\n - name: Configure\n run: |\n ./configure '--disable-shared' '--disable-legacy' 'CXX=${{ matrix.compiler }}'\n\n - name: Make and Install Tesseract\n run: |\n make\n sudo make install install\n\n - name: Make and Install Training Tools\n run: |\n make training\n sudo make install training-install\n\n - name: Display Version\n run: |\n ${{ matrix.compiler }} --version\n tesseract -v\n lstmtraining -v\n text2image -v\n if: success() || failure()\n\n - name: Download fonts, tessdata and langdata required for tests\n run: |\n git clone https://github.com/egorpugin/tessdata tessdata_unittest\n cp tessdata_unittest/fonts/* test/testing/\n mv tessdata_unittest/* ../\n\n - name: Run Tesseract on phototest.tif and devatest.png\n run: |\n tesseract test/testing/phototest.tif - --tessdata-dir ../tessdata\n tesseract test/testing/devatest.png - -l hin+eng --tessdata-dir ../tessdata\n\n - name: Make and run Unit Tests\n run: |\n make check\n\n - name: Display Unit Tests Report\n run: |\n git log -3\n ${{ matrix.compiler }} --version\n cat test-suite.log\n if: always()\n" }, { "path": ".github/workflows/unittest-macos.yml", "content": "name: unittest-macos\n# autotools build on homebrew. unittests with address sanitizers. with openmp.\non:\n #push:\n schedule:\n - cron: 0 0 * * *\n\njobs:\n sanitizers:\n name: ${{ matrix.config.name }}\n runs-on: ${{ matrix.config.os }}\n strategy:\n fail-fast: false\n matrix:\n config:\n - { name: macos-arm-14-clang-unittest, os: macos-14, cxx: clang++ } # Apple silicon\n - { name: macos-latest-clang-unittest, os: macos-latest, cxx: clang++ }\n - { name: macos-latest-gcc-unittest, os: macos-latest, cxx: g++ }\n\n steps:\n - uses: actions/checkout@v6\n with:\n submodules: recursive\n\n - name: Install dependencies (macOS Homebrew)\n run: |\n brew install autoconf automake cabextract libtool\n brew install leptonica libarchive pango\n if ! brew list icu4c &>/dev/null; then\n brew install icu4c\n fi\n if ! brew list curl &>/dev/null; then\n brew install curl\n fi\n\n - name: Setup\n run: |\n ./autogen.sh\n\n - name: Configure (macOS Homebrew)\n run: |\n ./configure '--disable-shared' '--with-pic' \\\n 'CXX=${{ matrix.config.cxx }}' \\\n 'CXXFLAGS=-g -O2 -fsanitize=address,undefined'\n\n - name: Make and Install Tesseract\n run: |\n make\n sudo make install\n\n - name: Make and Install Training Tools\n run: |\n make training\n sudo make training-install\n\n - name: Display Tesseract and Training Tools Version\n run: |\n tesseract -v\n lstmtraining -v\n text2image -v\n if: success() || failure()\n\n - name: Download fonts, tessdata and langdata required for tests\n run: |\n git clone https://github.com/egorpugin/tessdata tessdata_unittest\n cp tessdata_unittest/fonts/* test/testing/\n mv tessdata_unittest/* ../\n\n - name: Run Tesseract on phototest.tif and devatest.png\n run: |\n tesseract test/testing/phototest.tif - --tessdata-dir ../tessdata\n tesseract test/testing/devatest.png - -l hin+eng --tessdata-dir ../tessdata\n\n - name: Make and run Unit Tests\n run: |\n make check\n\n - name: Display Unit Tests Report and compiler version\n run: |\n cat test-suite.log\n ${{ matrix.config.cxx }} --version\n git log -3 --pretty=format:'%h %ad %s | %an'\n if: always()\n" }, { "path": ".github/workflows/unittest.yml", "content": "name: unittest\n# autotools build on ubuntu. unittests with address sanitizers. with openmp.\n# ubuntu-20.04-gcc-unittest - CI runs out of diskspace.\non:\n #push:\n pull_request:\n paths:\n - '**.cpp'\n - '**.h'\n - '**Makefile.am'\n - '/configure.ac'\n - 'unittest/**.c'\n - 'unittest/**.cc'\n schedule:\n - cron: 0 0 * * *\n workflow_dispatch:\n\njobs:\n sanitizers:\n name: ${{ matrix.config.name }}\n runs-on: ${{ matrix.config.os }}\n strategy:\n fail-fast: false\n matrix:\n config:\n - { name: ubuntu-24.04-gcc-unittest, os: ubuntu-24.04, cxx: g++, cxxflags: '-g -O2 -fsanitize=address,undefined' }\n - { name: ubuntu-22.04-clang-unittest, os: ubuntu-22.04, cxx: clang++, cxxflags: '-g -O2 -fsanitize=address,undefined -stdlib=libc++' }\n steps:\n - uses: actions/checkout@v6\n with:\n submodules: recursive\n\n - name: Remove Homebrew, Android and .NET to provide more disk space\n run: |\n # https://github.com/actions/virtual-environments/issues/2606#issuecomment-772683150\n sudo rm -rf /home/linuxbrew # will release Homebrew\n sudo rm -rf /usr/local/lib/android # will release about 10 GB if you don't need Android\n sudo rm -rf /usr/share/dotnet # will release about 20GB if you don't need .NET\n\n - name: Install dependencies (Linux)\n run: |\n sudo apt-get update\n sudo apt-get install autoconf libleptonica-dev libpango1.0-dev -y\n sudo apt-get install cabextract -y\n\n - name: Setup\n run: |\n ./autogen.sh\n\n - name: Configure (Linux)\n run: |\n ./configure '--disable-shared' 'CXX=${{ matrix.config.cxx }}' \\\n 'CXXFLAGS=${{ matrix.config.cxxflags }}'\n\n - name: Make and Install Tesseract\n run: |\n ${{ matrix.config.cxx }} --version\n make\n sudo make install\n\n - name: Make and Install Training Tools\n run: |\n make training\n sudo make training-install\n\n - name: Display Tesseract and Training Tools Version\n run: |\n tesseract -v\n lstmtraining -v\n text2image -v\n if: success() || failure()\n\n - name: Download fonts, tessdata and langdata required for tests\n run: |\n git clone https://github.com/egorpugin/tessdata tessdata_unittest\n cp tessdata_unittest/fonts/* test/testing/\n mv tessdata_unittest/* ../\n\n - name: Run Tesseract on phototest.tif and devatest.png\n run: |\n tesseract test/testing/phototest.tif - --tessdata-dir ../tessdata\n tesseract test/testing/devatest.png - -l hin+eng --tessdata-dir ../tessdata\n\n - name: Make and run Unit Tests\n run: |\n make check\n\n - name: Display Unit Tests Report and Compiler Version\n run: |\n cat test-suite.log\n ${{ matrix.config.cxx }} --version\n git log -3 --pretty=format:'%h %ad %s | %an'\n if: always()\n" }, { "path": ".github/workflows/vcpkg.yml", "content": "name: vcpkg\n# build and test of tesseract on windows using vcpkg and cmake.\n# vcpkg with -head does not work. https://github.com/microsoft/vcpkg/issues/16019\non:\n #push:\n schedule:\n - cron: 0 23 * * *\n workflow_dispatch:\n\njobs:\n build:\n runs-on: ${{ matrix.os }}\n strategy:\n fail-fast: false\n matrix:\n os: [windows-latest]\n\n steps:\n - name: Checkout Tesseract Source (--head from main branch)\n uses: actions/checkout@v6\n with:\n submodules: recursive\n\n # - name: Visual Studio Setup\n # shell: cmd\n # run: |\n # call \"C:\\Program Files (x86)\\Microsoft Visual Studio\\2019\\Enterprise\\VC\\Auxiliary\\Build\\vcvars64.bat\"\n\n - name: Install vcpkg\n run: |\n git clone https://github.com/microsoft/vcpkg\n vcpkg/bootstrap-vcpkg.bat\n vcpkg/vcpkg integrate install\n\n - name: Build and Install Leptonica and image libraries using vcpkg\n run: |\n vcpkg/vcpkg install leptonica:x64-windows\n\n - name: Configure and Build Tesseract (--head from main branch) with cmake\n run: |\n cmake . -B build -DCMAKE_BUILD_TYPE=Release -DSW_BUILD=OFF -DOPENMP_BUILD=OFF -DBUILD_TRAINING_TOOLS=OFF \"-DCMAKE_TOOLCHAIN_FILE=${env:GITHUB_WORKSPACE}/vcpkg/scripts/buildsystems/vcpkg.cmake\"\n cmake --build build --config Release --target install\n\n - name: Display Tesseract Version\n run: |\n D:\\a\\tesseract\\tesseract\\build\\bin\\Release\\tesseract.exe --version\n\n - name: Create CMakeLists.txt file for basicapitest\n shell: bash\n run: |\n cd test\n cat << \"EOF\" > CMakeLists.txt\n cmake_minimum_required(VERSION 3.19)\n project( basicapitest )\n find_package( Tesseract REQUIRED )\n find_package( Leptonica REQUIRED )\n include_directories(${Tesseract_INCLUDE_DIRS})\n include_directories(${Leptonica_INCLUDE_DIRS})\n add_executable( basicapitest testing/basicapitest.cpp )\n target_link_libraries(basicapitest ${Leptonica_LIBRARIES})\n target_link_libraries(basicapitest Tesseract::libtesseract)\n add_library(libtesseract UNKNOWN IMPORTED)\n set_property(TARGET libtesseract PROPERTY IMPORTED_LOCATION D:/a/tesseract/tesseract/build/Release/tesseract50.lib)\n target_link_libraries(basicapitest Tesseract::libtesseract)\n EOF\n cat CMakeLists.txt\n\n - name: Configure basicapitest\n run: |\n cd test\n cmake . \"-DCMAKE_TOOLCHAIN_FILE=${env:GITHUB_WORKSPACE}/vcpkg/scripts/buildsystems/vcpkg.cmake\"\n\n - name: Build basicapitest\n run: |\n cd test\n cmake --build . --config Release\n\n - name: Download tessdata and image files used for tests\n run: |\n git clone https://github.com/egorpugin/tessdata tessdata_unittest\n mv tessdata_unittest/* ../\n\n - name: Run basicapitest\n run: |\n cd test\n D:\\a\\tesseract\\tesseract\\test\\Release\\basicapitest.exe\n\n - name: Run Tesseract CLI on test images in different languages\n run: |\n D:\\a\\tesseract\\tesseract\\build\\bin\\Release\\tesseract.exe test\\testing\\phototest.tif - --oem 1 --tessdata-dir ..\\tessdata\n D:\\a\\tesseract\\tesseract\\build\\bin\\Release\\tesseract.exe test\\testing\\raaj.tif - -l hin --oem 1 --tessdata-dir ..\\tessdata\n D:\\a\\tesseract\\tesseract\\build\\bin\\Release\\tesseract.exe test\\testing\\viet.tif - -l vie --oem 1 --tessdata-dir ..\\tessdata\n D:\\a\\tesseract\\tesseract\\build\\bin\\Release\\tesseract.exe test\\testing\\hebrew.png - -l heb --oem 1 --tessdata-dir ..\\tessdata\n D:\\a\\tesseract\\tesseract\\build\\bin\\Release\\tesseract.exe test\\testing\\eurotext.tif - -l fra --oem 1 --tessdata-dir ..\\tessdata_best\n D:\\a\\tesseract\\tesseract\\build\\bin\\Release\\tesseract.exe test\\testing\\arabic.tif - -l ara --oem 1 --psm 6 --tessdata-dir ..\\tessdata\n\n - name: List languages in different test tessdata-dir\n run: |\n D:\\a\\tesseract\\tesseract\\build\\bin\\Release\\tesseract.exe --list-langs --tessdata-dir ..\\tessdata\n D:\\a\\tesseract\\tesseract\\build\\bin\\Release\\tesseract.exe --list-langs --tessdata-dir ..\\tessdata_best\n D:\\a\\tesseract\\tesseract\\build\\bin\\Release\\tesseract.exe --list-langs --tessdata-dir ..\\tessdata_fast\n" }, { "path": ".gitignore", "content": "*~\n# Windows\n*.user.*\n*.idea*\n*.log\n*.tlog\n*.cache\n*.obj\n*.sdf\n*.opensdf\n*.lastbuildstate\n*.unsuccessfulbuild\n*.suo\n*.res\n*.ipch\n*.manifest\n\n# Linux\n# ignore local configuration\nconfig.*\nconfig/*\nMakefile\nMakefile.in\n*.m4\n\n# ignore help scripts/files\nconfigure\nlibtool\nstamp-h1\ntesseract.pc\nconfig_auto.h\n/doc/html/*\n/doc/*.1\n/doc/*.5\n/doc/*.html\n/doc/*.xml\n\n# generated version file\n/include/tesseract/version.h\n\n# executables\n/tesseract\n/src/training/ambiguous_words\n/src/training/classifier_tester\n/src/training/cntraining\n/src/training/combine_tessdata\n/src/training/dawg2wordlist\n/src/training/merge_unicharsets\n/src/training/mftraining\n/src/training/set_unicharset_properties\n/src/training/shapeclustering\n/src/training/text2image\n/src/training/unicharset_extractor\n/src/training/wordlist2dawg\n\n*.patch\n\n# files generated by libtool\n/src/training/combine_lang_model\n/src/training/lstmeval\n/src/training/lstmtraining\n\n# ignore compilation files\nbuild/*\n/bin\n/cmake-*\n.deps\n.dirstamp\n/.libs\n*/.libs/*\n*/*/.deps/*\n*/*/.libs/*\n*.lo\n*.la\n*.o\n*.Plo\n*.a\n*.class\n*.jar\n__pycache__\n\n# tessdata\n*.traineddata\ntessdata_*\n\n# build dirs\n/build*\n/*.dll\n/*.lib\n/*.exe\n/*.lnk\n/win*\n.vs*\n.s*\n\n# files generated by \"make check\"\n/tests/.dirstamp\n/unittest/*.trs\n/unittest/tmp/*\n\n# test programs\n/unittest/*_test\n/unittest/primesbitvector\n/unittest/primesmap\n\n# generated files from unlvtests\ntimes.txt\n/unlvtests/results*\n\n# snap packaging specific rules\n/parts/\n/stage/\n/prime/\n/snap/.snapcraft/\n\n/*.snap\n/*_source.tar.bz2\n\n# CodeQL and build artifacts\n_codeql_detected_source_root\ninstall-sh\n" }, { "path": ".gitmodules", "content": "[submodule \"googletest\"]\n\tpath = unittest/third_party/googletest\n\turl = https://github.com/google/googletest.git\n[submodule \"test\"]\n\tpath = test\n\turl = https://github.com/tesseract-ocr/test.git\n" }, { "path": ".mailmap", "content": "Amit Dovev \n\nEgor Pugin \n\nJeff Breidenbach \n\nJim O'Regan \nJim O'Regan \n\nRay Smith \nRay Smith \nRay Smith \nRay Smith \nRay Smith \n\nShree Devi Kumar <5095331+Shreeshrii@users.noreply.github.com>\n\nStefan Weil \nStefan Weil \nStefan Weil \nStefan Weil \nStefan Weil \n\nZdenko Podobný \nZdenko Podobný \nZdenko Podobný \n" }, { "path": "AUTHORS", "content": "Ray Smith (lead developer) \nAhmad Abdulkader\nRika Antonova\nNicholas Beato\nJeff Breidenbach\nSamuel Charron\nPhil Cheatle\nSimon Crouch\nDavid Eger\nSheelagh Huddleston\nDan Johnson\nRajesh Katikam\nThomas Kielbus\nDar-Shyang Lee\nZongyi (Joe) Liu\nRobert Moss\nChris Newton\nMichael Reimer\nMarius Renn\nRaquel Romano\nChristy Russon\nShobhit Saxena\nMark Seaman\nFaisal Shafait\nHiroshi Takenaka\nRanjith Unnikrishnan\nJoern Wanke\nPing Ping Xiu\nAndrew Ziem\nOscar Zuniga\n\nCommunity Contributors:\nZdenko Podobný (Maintainer)\nJim Regan (Maintainer)\nJames R Barlow\nStefan Brechtken\nThomas Breuel\nAmit Dovev\nMartin Ettl\nShree Devi Kumar\nNoah Metzger\nTom Morris\nTobias Müller\nEgor Pugin\nRobert Sachunsky\nRaf Schietekat\nSundar M. Vaidya\nRobin Watts\nStefan Weil\nNick White\nAlexander Zaitsev\n" }, { "path": "CITATIONS.bib", "content": "@inproceedings{TableDetect,\n author = {Faisal Shafait and Ray Smith},\n booktitle = {Document Analysis Systems},\n editor = {David S. Doermann and Venu Govindaraju and Daniel P. Lopresti and Premkumar Natarajan},\n pages = {65--72},\n publisher = {ACM},\n series = {ACM International Conference Proceeding Series},\n title = {Table detection in heterogeneous documents.},\n url = {http://dblp.uni-trier.de/db/conf/das/das2010.html#ShafaitS10},\n year = 2010,\n isbn = {978-1-60558-773-8},\n date = {2010-07-07}\n}\n\n@inproceedings{Multilingual,\n author = {Ray Smith and Daria Antonova and Dar-Shyang Lee},\n booktitle = {MOCR '09: Proceedings of the International Workshop on Multilingual OCR},\n editor = {Venu Govindaraju and Premkumar Natarajan and Santanu Chaudhury and Daniel P. Lopresti},\n pages = {1--8},\n publisher = {ACM},\n series = {ACM International Conference Proceeding Series},\n title = {Adapting the Tesseract Open Source OCR Engine for Multilingual OCR.},\n url = {https://storage.googleapis.com/pub-tools-public-publication-data/pdf/35248.pdf},\n year = 2009,\n isbn = {978-1-60558-698-4},\n date = {2009-07-25},\n doi = {http://doi.acm.org/10/1145/1577802.1577804},\n location = {Barcelona, Spain},\n}\n\n@inproceedings{ScriptDetect,\n author = {Ranjith Unnikrishnan and Ray Smith},\n title = {Combined Orientation and Script Detection using the Tesseract OCR Engine},\n booktitle = {MOCR '09: Proceedings of the International Workshop on Multilingual OCR},\n editor = {Venu Govindaraju and Premkumar Natarajan and Santanu Chaudhury and Daniel P. Lopresti},\n url = {https://storage.googleapis.com/pub-tools-public-publication-data/pdf/35506.pdf},\n year = {2009},\n isbn = {978-1-60558-698-4},\n pages = {1--7},\n location = {Barcelona, Spain},\n doi = {http://doi.acm.org/10.1145/1577802.1577809},\n publisher = {ACM},\n address = {New York, NY, USA},\n}\n\n@inproceedings{PageLayout,\n author = {Ray Smith},\n title = {Hybrid Page Layout Analysis via Tab-Stop Detection},\n booktitle = {ICDAR '09: Proceedings of the 2009 10th International Conference on Document Analysis and Recognition},\n url = {https://storage.googleapis.com/pub-tools-public-publication-data/pdf/35094.pdf},\n year = {2009},\n isbn = {978-0-7695-3725-2},\n pages = {241--245},\n doi = {http://dx.doi.org/10.1109/ICDAR.2009.257},\n publisher = {IEEE Computer Society},\n address = {Washington, DC, USA},\n}\n\n@inproceedings{TessOverview,\n author = {Ray Smith},\n title = {An Overview of the Tesseract OCR Engine},\n booktitle = {ICDAR '07: Proceedings of the Ninth International Conference on Document Analysis and Recognition},\n url = {https://storage.googleapis.com/pub-tools-public-publication-data/pdf/33418.pdf},\n year = {2007},\n isbn = {0-7695-2822-8},\n pages = {629--633},\n publisher = {IEEE Computer Society},\n address = {Washington, DC, USA},\n}\n\n" }, { "path": "CMakeLists.txt", "content": "#\n# tesseract\n#\n\n# ##############################################################################\n#\n# cmake settings\n#\n# ##############################################################################\n\n# Require CMake 3.18 for modern features like precompiled headers, unity builds, and better target management\ncmake_minimum_required(VERSION 3.18 FATAL_ERROR)\n\n# In-source builds are disabled.\nif(\"${CMAKE_CURRENT_SOURCE_DIR}\" STREQUAL \"${CMAKE_CURRENT_BINARY_DIR}\")\n message(\n FATAL_ERROR\n \"CMake generation is not possible within the source directory!\"\n \"\\n Remove the CMakeCache.txt file and try again from another folder, \"\n \"e.g.:\\n \"\n \"\\n rm CMakeCache.txt\"\n \"\\n mkdir build\"\n \"\\n cd build\"\n \"\\n cmake ..\")\nendif()\n\nset(CMAKE_MODULE_PATH \"${CMAKE_MODULE_PATH};${CMAKE_CURRENT_SOURCE_DIR}/cmake\")\n\nset(EXECUTABLE_OUTPUT_PATH \"${CMAKE_BINARY_DIR}/bin\")\nset(CMAKE_RUNTIME_OUTPUT_DIRECTORY \"${EXECUTABLE_OUTPUT_PATH}\")\n\n# Use solution folders.\nset_property(GLOBAL PROPERTY USE_FOLDERS ON)\nset_property(GLOBAL PROPERTY PREDEFINED_TARGETS_FOLDER \"CMake Targets\")\n\nif(NOT ${CMAKE_VERSION} VERSION_LESS \"3.15.0\")\n if(WIN32)\n cmake_policy(SET CMP0091 NEW)\n message(STATUS \"Setting policy CMP0091 to NEW\")\n endif()\nendif()\n\n# ##############################################################################\n#\n# project settings\n#\n# ##############################################################################\n\nproject(tesseract C CXX)\n\n# Get version with components from VERSION file.\nfile(STRINGS \"VERSION\" VERSION_PLAIN)\nstring(REGEX REPLACE \"^([^.]*)\\\\..*\" \"\\\\1\" VERSION_MAJOR ${VERSION_PLAIN})\nstring(REGEX REPLACE \"^[^.]*\\\\.([^.]*)\\\\..*\" \"\\\\1\" VERSION_MINOR\n ${VERSION_PLAIN})\nstring(REGEX REPLACE \"^[^.]*\\\\.[^.]*\\\\.([0-9]*).*\" \"\\\\1\" VERSION_PATCH\n ${VERSION_PLAIN})\nif(EXISTS ${CMAKE_CURRENT_SOURCE_DIR}/.git)\n execute_process(COMMAND git --git-dir ${CMAKE_CURRENT_SOURCE_DIR}/.git\n describe --abbrev=4 OUTPUT_VARIABLE GIT_REV)\n string(REGEX REPLACE \"\\n$\" \"\" PACKAGE_VERSION \"${GIT_REV}\")\nendif()\nif(NOT PACKAGE_VERSION)\n set(PACKAGE_VERSION ${VERSION_PLAIN})\nendif()\n\n# Provide also same macro names as autoconf (see configure.ac).\nset(GENERIC_MAJOR_VERSION ${VERSION_MAJOR})\nset(GENERIC_MINOR_VERSION ${VERSION_MINOR})\nset(GENERIC_MICRO_VERSION ${VERSION_PATCH})\n\nset(MINIMUM_LEPTONICA_VERSION 1.74)\n\n# ##############################################################################\n#\n# options\n#\n# ##############################################################################\n\nmessage(STATUS \"Configuring tesseract version ${PACKAGE_VERSION}...\")\n\nif(WIN32)\n option(SW_BUILD \"Build with sw\" ON)\nelse()\n option(SW_BUILD \"Build with sw\" OFF)\nendif()\n\n# Apple's toolchains dont populate CMAKE_SYSTEM_PROCESSOR when crosscompiling\n# instead it uses CMAKE_OSX_ARCHITECTURES which can contain multiple architectures\nif(APPLE AND NOT CMAKE_SYSTEM_PROCESSOR AND CMAKE_OSX_ARCHITECTURES)\n list(LENGTH CMAKE_OSX_ARCHITECTURES NO_OF_ARCH)\n if(NO_OF_ARCH GREATER 1)\n message(FATAL_ERROR \"Apple's universal build for ${NO_OF_ARCH} architectures not supported. CMAKE_OSX_ARCHITECTURES: ${CMAKE_OSX_ARCHITECTURES}\")\n endif()\n set(CMAKE_SYSTEM_PROCESSOR \"${CMAKE_OSX_ARCHITECTURES}\" CACHE STRING \"Target processor\" FORCE)\n message(STATUS \"CMAKE_SYSTEM_PROCESSOR set to '${CMAKE_SYSTEM_PROCESSOR}' from CMAKE_OSX_ARCHITECTURES\")\nendif()\n\noption(OPENMP_BUILD \"Build with openmp support\" OFF) # see issue #1662\noption(GRAPHICS_DISABLED \"Disable disable graphics (ScrollView)\" OFF)\noption(DISABLED_LEGACY_ENGINE \"Disable the legacy OCR engine\" OFF)\noption(ENABLE_LTO \"Enable link-time optimization\" OFF)\noption(FAST_FLOAT \"Enable float for LSTM\" ON)\noption(ENABLE_NATIVE\n \"Enable optimization for host CPU (could break HW compatibility)\" OFF)\n# see\n# https://stackoverflow.com/questions/52653025/why-is-march-native-used-so-rarely\noption(BUILD_TRAINING_TOOLS \"Build training tools\" ON)\noption(BUILD_TESTS \"Build tests\" OFF)\noption(USE_SYSTEM_ICU \"Use system ICU\" OFF)\noption(DISABLE_TIFF \"Disable build with libtiff (if available)\" OFF)\noption(DISABLE_ARCHIVE \"Disable build with libarchive (if available)\" OFF)\noption(DISABLE_CURL \"Disable build with libcurl (if available)\" OFF)\noption(INSTALL_CONFIGS \"Install tesseract configs\" ON)\n\n# Build optimization options\noption(ENABLE_UNITY_BUILD \"Enable Unity/Jumbo builds for faster compilation\" OFF)\noption(ENABLE_PRECOMPILED_HEADERS \"Enable precompiled headers for faster compilation\" ON)\noption(ENABLE_CCACHE \"Enable ccache for faster incremental builds\" ON)\noption(ENABLE_NINJA_POOL \"Enable Ninja job pools to manage parallelism\" ON)\n\n\n# ##############################################################################\n#\n# compiler and linker\n#\n# ##############################################################################\n\nif(CMAKE_CXX_COMPILER_ID MATCHES \"Clang\")\n set(CLANG 1)\nendif()\n\nif(NOT CMAKE_BUILD_TYPE)\n message(STATUS \"Setting build type to 'Release' as none was specified.\")\n set(CMAKE_BUILD_TYPE\n Release\n CACHE STRING \"Choose the type of build.\" FORCE)\n set_property(CACHE CMAKE_BUILD_TYPE PROPERTY STRINGS \"Debug\" \"Release\")\nendif()\n\ninclude(CheckCXXCompilerFlag)\n\nset(CMAKE_CXX_STANDARD 17)\nif(\"cxx_std_20\" IN_LIST CMAKE_CXX_COMPILE_FEATURES)\n set(CMAKE_CXX_STANDARD 20)\nendif()\nset(CMAKE_CXX_STANDARD_REQUIRED ON)\nif(NOT CMAKE_CXX_COMPILER_ID STREQUAL \"GNU\")\n # cygwin gnu c++ needs to use -std=gnu++17 instead of -std=c++17\n set(CMAKE_CXX_EXTENSIONS OFF)\nendif()\n\nif(BUILD_SHARED_LIBS)\n set(CMAKE_CXX_VISIBILITY_PRESET hidden)\nendif()\n\n# LTO\ncmake_policy(SET CMP0069 NEW)\ninclude(CheckIPOSupported)\ncheck_ipo_supported(RESULT LTO_SUPPORTED OUTPUT error)\nif(LTO_SUPPORTED)\n message(STATUS \"IPO / LTO supported\")\nelse()\n message(STATUS \"IPO / LTO not supported: <${error}>\")\nendif()\n\nset(MARCH_NATIVE_OPT OFF)\nif(ENABLE_NATIVE)\n check_cxx_compiler_flag(\"-march=native\" COMPILER_SUPPORTS_MARCH_NATIVE)\n if(COMPILER_SUPPORTS_MARCH_NATIVE)\n set(DOTPRODUCT_FLAGS \"${DOTPRODUCT_FLAGS} -march=native\")\n if(NOT CLANG AND MSVC)\n # clang-cl does not know this argument\n set(DOTPRODUCT_FLAGS \"${DOTPRODUCT_FLAGS} -mtune=native\")\n endif()\n set(MARCH_NATIVE_OPT ON)\n endif(COMPILER_SUPPORTS_MARCH_NATIVE)\nendif(ENABLE_NATIVE)\n\nmessage(STATUS \"CMAKE_SYSTEM_PROCESSOR=<${CMAKE_SYSTEM_PROCESSOR}>\")\n\nif(CMAKE_SYSTEM_PROCESSOR MATCHES \"x86|x86_64|AMD64|amd64|i386|i686\")\n\n set(HAVE_NEON FALSE)\n if(MSVC)\n set(HAVE_AVX ON)\n set(AVX_COMPILE_FLAGS \"/arch:AVX\")\n add_definitions(\"-DHAVE_AVX\")\n\n set(HAVE_AVX2 ON)\n set(AVX2_COMPILE_FLAGS \"/arch:AVX2\")\n add_definitions(\"-DHAVE_AVX2\")\n\n set(HAVE_AVX512F ON)\n set(AVX512F_COMPILE_FLAGS \"/arch:AVX512\")\n add_definitions(\"-DHAVE_AVX512F\")\n\n set(HAVE_FMA ON)\n set(FMA_COMPILE_FLAGS \"-D__FMA__\")\n add_definitions(\"-DHAVE_FMA\")\n\n set(HAVE_SSE4_1 ON)\n set(SSE4_1_COMPILE_FLAGS \"-D__SSE4_1__\")\n add_definitions(\"-DHAVE_SSE4_1\")\n\n set(DOTPRODUCT_FLAGS \"${DOTPRODUCT_FLAGS} -openmp:experimental\")\n add_definitions(\"-DOPENMP_SIMD\")\n\n # clang with MSVC compatibility\n if(CLANG)\n set(CMAKE_CXX_FLAGS\n \"${CMAKE_CXX_FLAGS} -Wno-microsoft-unqualified-friend\")\n if(HAVE_FMA)\n set(FMA_COMPILE_FLAGS \"-mfma ${FMA_COMPILE_FLAGS}\")\n endif(HAVE_FMA)\n if(HAVE_SSE4_1)\n set(SSE4_1_COMPILE_FLAGS \"-msse4.1 ${SSE4_1_COMPILE_FLAGS}\")\n endif(HAVE_SSE4_1)\n endif(CLANG)\n else() # if not MSVC\n check_cxx_compiler_flag(\"-mavx\" HAVE_AVX)\n if(HAVE_AVX)\n set(AVX_COMPILE_FLAGS \"-mavx\")\n add_definitions(\"-DHAVE_AVX\")\n endif(HAVE_AVX)\n\n check_cxx_compiler_flag(\"-mavx2\" HAVE_AVX2)\n if(HAVE_AVX2)\n set(AVX2_COMPILE_FLAGS \"-mavx2\")\n add_definitions(\"-DHAVE_AVX2\")\n endif()\n\n check_cxx_compiler_flag(\"-mavx512f\" HAVE_AVX512F)\n if(HAVE_AVX512F)\n set(AVX512F_COMPILE_FLAGS \"-mavx512f\")\n add_definitions(\"-DHAVE_AVX512F\")\n endif()\n\n check_cxx_compiler_flag(\"-mfma\" HAVE_FMA)\n if(HAVE_FMA)\n set(FMA_COMPILE_FLAGS \"-mfma\")\n add_definitions(\"-DHAVE_FMA\")\n endif()\n\n check_cxx_compiler_flag(\"-msse4.1\" HAVE_SSE4_1)\n if(HAVE_SSE4_1)\n set(SSE4_1_COMPILE_FLAGS \"-msse4.1\")\n add_definitions(\"-DHAVE_SSE4_1\")\n endif()\n\n check_cxx_compiler_flag(\"-fopenmp-simd\" OPENMP_SIMD)\n if(OPENMP_SIMD)\n set(DOTPRODUCT_FLAGS \"${DOTPRODUCT_FLAGS} -fopenmp-simd\")\n add_definitions(\"-DOPENMP_SIMD\")\n endif(OPENMP_SIMD)\n endif(MSVC)\n\nelseif(CMAKE_SYSTEM_PROCESSOR MATCHES \"arm64|aarch64.*|AARCH64.*\")\n\n set(HAVE_AVX FALSE)\n set(HAVE_AVX2 FALSE)\n set(HAVE_AVX512F FALSE)\n set(HAVE_FMA FALSE)\n set(HAVE_SSE4_1 FALSE)\n set(HAVE_NEON TRUE)\n\nelseif(CMAKE_SYSTEM_PROCESSOR MATCHES \"arm.*\")\n\n set(HAVE_AVX FALSE)\n set(HAVE_AVX2 FALSE)\n set(HAVE_AVX512F FALSE)\n set(HAVE_FMA FALSE)\n set(HAVE_SSE4_1 FALSE)\n\n check_cxx_compiler_flag(\"-mfpu=neon\" HAVE_NEON)\n if(HAVE_NEON)\n set(NEON_COMPILE_FLAGS \"-mfpu=neon\")\n endif(HAVE_NEON)\n\nelse()\n\n set(HAVE_AVX FALSE)\n set(HAVE_AVX2 FALSE)\n set(HAVE_AVX512F FALSE)\n set(HAVE_FMA FALSE)\n set(HAVE_NEON FALSE)\n set(HAVE_SSE4_1 FALSE)\n\nendif(CMAKE_SYSTEM_PROCESSOR MATCHES \"x86|x86_64|AMD64|amd64|i386|i686\")\n\nif(HAVE_NEON)\n message(STATUS \"LTO build is not supported on arm/RBPi.\")\n set(ENABLE_LTO FALSE) # enable LTO cause fatal error on arm/RBPi\nendif()\n\n# Compiler specific environment\nif(CMAKE_COMPILER_IS_GNUCXX OR MINGW)\n set(CMAKE_CXX_FLAGS_DEBUG\n \"${CMAKE_CXX_FLAGS_DEBUG} -Wall -DDEBUG -pedantic -Og -Wno-unknown-pragmas\")\nelseif(MSVC)\n add_definitions(-D_CRT_SECURE_NO_WARNINGS)\n add_definitions(-D_CRT_NONSTDC_NO_DEPRECATE) # strdup\n add_definitions(-D_USE_MATH_DEFINES) # Enable M_PI and other math constants\n add_definitions(-DNOMINMAX) # Prevent min/max macro conflicts\n set(CMAKE_CXX_FLAGS \"${CMAKE_CXX_FLAGS} /utf-8\")\n if(NOT CLANG)\n set(CMAKE_CXX_FLAGS \"${CMAKE_CXX_FLAGS} /MP\")\n endif()\n # Hide some warnings for release target wd4244 'argument': conversion from\n # 'uint64_t' to 'unsigned int', possible loss of data wd4251 needs to have\n # dll-interface wd4267 return': conversion from 'size_t' to 'int', possible\n # loss of data wd4275 non dll-interface class wd4305 ...truncation from\n # 'double' to 'float'\n set(CMAKE_CXX_FLAGS_RELEASE\n \"${CMAKE_CXX_FLAGS_RELEASE} /wd4244 /wd4305 /wd4267 /wd4251 /wd4275 /wd4005\"\n )\n set(CMAKE_CXX_FLAGS_RELEASE \"${CMAKE_CXX_FLAGS_RELEASE} /wd4068\")\n # Don't use /Wall because it generates too many warnings.\n set(CMAKE_CXX_FLAGS_DEBUG \"${CMAKE_CXX_FLAGS_DEBUG} /W0 /bigobj\")\n # MT flag\n if(WIN32_MT_BUILD)\n set(CMAKE_MSVC_RUNTIME_LIBRARY \"MultiThreaded$<$:Debug>\")\n message(STATUS \"Building with static CRT.\")\n endif()\n # Workaround: When building on VS 2022 17.10 or newer, but using an older runtime,\n # mutexes can crash\n # https://stackoverflow.com/questions/78598141/first-stdmutexlock-crashes-in-application-built-with-latest-visual-studio\n add_definitions(-D_DISABLE_CONSTEXPR_MUTEX_CONSTRUCTOR)\nendif()\nif(CLANG) # clang all platforms\n set(CMAKE_CXX_FLAGS_RELEASE\n \"${CMAKE_CXX_FLAGS_RELEASE} -Wno-unused-command-line-argument\")\n set(CMAKE_CXX_FLAGS_DEBUG\n \"${CMAKE_CXX_FLAGS_DEBUG} -Wall -DDEBUG -pedantic -O0\")\nendif()\n\nif(OPENMP_BUILD\n AND MSVC\n AND \"${MSVC_VERSION}\" LESS 1929)\n set(OPENMP_BUILD OFF)\nendif()\nif(OPENMP_BUILD)\n if(MSVC) # supported from cmake 3.30\n set(OpenMP_RUNTIME_MSVC \"llvm\")\n endif(MSVC)\n find_package(OpenMP)\n # https://stackoverflow.com/questions/12399422\n # how-to-set-linker-flags-for-openmp-in-cmakes-try-compile-function\n if(NOT OpenMP_FOUND\n AND CLANG\n AND WIN32)\n # workaround because find_package(OpenMP) does not work for clang-cl\n # https://gitlab.kitware.com/cmake/cmake/issues/19404\n check_include_file_cxx(omp.h HAVE_OMP_H_INCLUDE)\n find_library(OpenMP_LIBRARY NAMES omp libomp.lib)\n message(\">> OpenMP_LIBRARY: ${OpenMP_LIBRARY}\")\n if(MSVC)\n set(CMAKE_CXX_FLAGS \"${CMAKE_CXX_FLAGS} /openmp\")\n else()\n set(CMAKE_CXX_FLAGS \"${CMAKE_CXX_FLAGS} -fopenmp\")\n endif()\n set(OpenMP_FOUND 1)\n # OpenMP 3.1 is fully supported from Clang 3.8.0\n add_definitions(-D_OPENMP=201107)\n endif()\n if(MSVC)\n # Note: -openmp:llvm is available for X64 from MSVC 16.9 from MSVC 16.10\n # Preview 2 there is support also for x86 and arm64\n # https://devblogs.microsoft.com/cppblog/openmp-updates-and-fixes-for-cpp-in-visual-studio-2019-16-10/\n if(\"${OpenMP_CXX_FLAGS}\" STREQUAL \"-openmp\")\n set(OpenMP_CXX_FLAGS \"-openmp:llvm\")\n endif()\n endif()\n if(OpenMP_FOUND)\n message(\">> OpenMP_FOUND ${OpenMP_FOUND} version: ${OpenMP_CXX_VERSION}\")\n set(CMAKE_CXX_FLAGS \"${CMAKE_CXX_FLAGS} ${OpenMP_CXX_FLAGS}\")\n if(NOT TARGET OpenMP::OpenMP_CXX)\n add_library(OpenMP::OpenMP_CXX IMPORTED INTERFACE)\n endif()\n endif()\nendif()\n\nif(CYGWIN)\n add_definitions(-D__CYGWIN__)\nelseif(UNIX)\n if(NOT ANDROID)\n set(LIB_pthread pthread)\n endif()\nelseif(WIN32)\n set(LIB_Ws2_32 Ws2_32)\nendif()\n\nadd_definitions(\"-DCMAKE_BUILD\")\n\n# ##############################################################################\n#\n# Build optimizations\n#\n# ##############################################################################\n\n# Setup ccache if available and enabled\nif(ENABLE_CCACHE)\n find_program(CCACHE_PROGRAM ccache)\n if(CCACHE_PROGRAM)\n message(STATUS \"Found ccache: ${CCACHE_PROGRAM}\")\n set(CMAKE_CXX_COMPILER_LAUNCHER \"${CCACHE_PROGRAM}\")\n set(CMAKE_C_COMPILER_LAUNCHER \"${CCACHE_PROGRAM}\")\n # Configure ccache for better performance\n set(ENV{CCACHE_SLOPPINESS} \"pch_defines,time_macros\")\n set(ENV{CCACHE_CPP2} \"true\")\n else()\n message(STATUS \"ccache not found, disabling ccache support\")\n set(ENABLE_CCACHE OFF)\n endif()\nendif()\n\n# Setup Ninja job pools for better resource management\nif(ENABLE_NINJA_POOL AND CMAKE_GENERATOR STREQUAL \"Ninja\")\n include(ProcessorCount)\n ProcessorCount(N)\n if(N GREATER 1)\n # Use 75% of available cores for compilation, rest for linking\n math(EXPR COMPILE_JOBS \"${N} * 3 / 4\")\n math(EXPR LINK_JOBS \"${N} - ${COMPILE_JOBS}\")\n if(LINK_JOBS LESS 1)\n set(LINK_JOBS 1)\n endif()\n\n set_property(GLOBAL PROPERTY JOB_POOLS \"compile=${COMPILE_JOBS};link=${LINK_JOBS}\")\n set(CMAKE_JOB_POOL_COMPILE compile)\n set(CMAKE_JOB_POOL_LINK link)\n message(STATUS \"Ninja job pools: compile=${COMPILE_JOBS}, link=${LINK_JOBS}\")\n endif()\nendif()\n\n# ##############################################################################\n#\n# packages\n#\n# ##############################################################################\ninclude(CheckFunctions)\n\nif(SW_BUILD)\n find_package(SW REQUIRED)\n if(BUILD_SHARED_LIBS)\n set(SW_BUILD_SHARED_LIBS 1)\n else()\n set(SW_BUILD_SHARED_LIBS 0)\n endif()\n sw_add_package(org.sw.demo.danbloomberg.leptonica\n org.sw.demo.libarchive.libarchive)\n if(BUILD_TRAINING_TOOLS)\n sw_add_package(org.sw.demo.gnome.pango.pangocairo\n org.sw.demo.unicode.icu.i18n)\n endif()\n sw_execute()\nelse()\n find_package(PkgConfig)\n if(APPLE)\n if(DEFINED ENV{HOMEBREW_PREFIX})\n set(HOMEBREW_PREFIX $ENV{HOMEBREW_PREFIX})\n set(PKG_CONFIG_PATH \"${HOMEBREW_PREFIX}/opt/icu4c/lib/pkgconfig:${HOMEBREW_PREFIX}/opt/libarchive/lib/pkgconfig\")\n set(ENV{PKG_CONFIG_PATH} \"${PKG_CONFIG_PATH}\")\n endif()\n endif()\n # Check for required library. option -DLeptonica_DIR=path => cmake hint where\n # to find leptonica\n find_package(Leptonica ${MINIMUM_LEPTONICA_VERSION} CONFIG)\n if(NOT Leptonica_FOUND AND PKG_CONFIG_EXECUTABLE)\n pkg_check_modules(Leptonica lept>=${MINIMUM_LEPTONICA_VERSION})\n link_directories(${Leptonica_LIBRARY_DIRS})\n endif()\n if(NOT Leptonica_FOUND)\n message(FATAL_ERROR \"Cannot find required library Leptonica. Quitting!\")\n else()\n message(STATUS \"Found leptonica version: ${Leptonica_VERSION}\")\n endif(NOT Leptonica_FOUND)\n include_directories(${Leptonica_INCLUDE_DIRS})\n\n check_leptonica_tiff_support()\n if ((NOT LEPT_TIFF_RESULT EQUAL 0) AND LEPT_TIFF_COMPILE_SUCCESS)\n message(NOTICE \"Leptonica was build without TIFF support! Disabling TIFF support...\")\n set(DISABLE_TIFF ON)\n elseif(NOT ${CMAKE_VERSION} VERSION_LESS \"3.25\")\n message(STATUS \"Leptonica was build with TIFF support.\")\n endif()\n\n # Check for optional libraries.\n if(DISABLE_TIFF)\n set(HAVE_TIFFIO_H OFF)\n message(STATUS \"TIFF support disabled.\")\n else(DISABLE_TIFF)\n find_package(TIFF) # for tesseract\n if(NOT TIFF_FOUND AND PKG_CONFIG_EXECUTABLE)\n # try PKG_CONFIG to find libtiff if cmake failed\n pkg_check_modules(TIFF libtiff-4)\n endif()\n if(TIFF_FOUND)\n set(HAVE_TIFFIO_H ON)\n include_directories(${TIFF_INCLUDE_DIRS})\n endif(TIFF_FOUND)\n endif(DISABLE_TIFF)\n if(DISABLE_ARCHIVE)\n set(HAVE_LIBARCHIVE OFF)\n message(STATUS \"LibArchive support disabled.\")\n else(DISABLE_ARCHIVE)\n find_package(LibArchive)\n if(NOT LibArchive_FOUND AND PKG_CONFIG_EXECUTABLE)\n # try PKG_CONFIG to find libarchive if cmake failed\n pkg_check_modules(LibArchive libarchive)\n endif()\n if(LibArchive_FOUND)\n set(HAVE_LIBARCHIVE ON)\n include_directories(${LibArchive_INCLUDE_DIRS})\n endif(LibArchive_FOUND)\n endif(DISABLE_ARCHIVE)\n if(DISABLE_CURL)\n set(HAVE_LIBCURL OFF)\n message(STATUS \"CURL support disabled.\")\n else(DISABLE_CURL)\n find_package(CURL)\n if(NOT CURL_FOUND AND PKG_CONFIG_EXECUTABLE)\n # try PKG_CONFIG to find libcurl if cmake failed\n pkg_check_modules(CURL libcurl)\n endif()\n if(CURL_FOUND)\n set(HAVE_LIBCURL ON)\n include_directories(${CURL_INCLUDE_DIRS})\n endif(CURL_FOUND)\n endif(DISABLE_CURL)\nendif()\n\n# ##############################################################################\n#\n# configure\n#\n# ##############################################################################\n\nif(MSVC)\n set(DOTPRODUCT_FLAGS \"${DOTPRODUCT_FLAGS} /fp:fast\")\nelse()\n set(DOTPRODUCT_FLAGS \"${DOTPRODUCT_FLAGS} -O3 -ffast-math\")\nendif()\n\ninclude (GNUInstallDirs)\n\nset(AUTOCONFIG_SRC ${CMAKE_CURRENT_BINARY_DIR}/config_auto.h.in)\nset(AUTOCONFIG ${CMAKE_CURRENT_BINARY_DIR}/config_auto.h)\nadd_definitions(-DHAVE_CONFIG_H)\n\nif(GRAPHICS_DISABLED)\n message(\"ScrollView debugging disabled.\")\nendif()\nset(CMAKE_REQUIRED_INCLUDES\n ${CMAKE_REQUIRED_INCLUDES} \"${CMAKE_PREFIX_PATH}/include\"\n ${CMAKE_INSTALL_INCLUDEDIR})\ninclude(Configure)\n\nconfigure_file(${AUTOCONFIG_SRC} ${AUTOCONFIG} @ONLY)\n\nset(INCLUDE_DIR ${CMAKE_INSTALL_INCLUDEDIR})\nset(LIBRARY_DIRS ${CMAKE_INSTALL_LIBDIR})\n\nconfigure_file(${CMAKE_CURRENT_SOURCE_DIR}/include/tesseract/version.h.in\n ${CMAKE_CURRENT_BINARY_DIR}/include/tesseract/version.h @ONLY)\n\ninclude(CMakePackageConfigHelpers)\ninclude(GenerateExportHeader)\n\n# show summary of configuration\nif(${CMAKE_BUILD_TYPE} MATCHES Debug)\n set(COMPILER_FLAGS \"${CMAKE_CXX_FLAGS} ${CMAKE_CXX_FLAGS_DEBUG}\")\nelseif(${CMAKE_BUILD_TYPE} MATCHES Release)\n set(COMPILER_FLAGS \"${CMAKE_CXX_FLAGS} ${CMAKE_CXX_FLAGS_RELEASE}\")\n if(LTO_SUPPORTED AND ENABLE_LTO)\n set(CMAKE_INTERPROCEDURAL_OPTIMIZATION TRUE)\n else()\n set(CMAKE_INTERPROCEDURAL_OPTIMIZATION FALSE)\n endif() # LTO_SUPPORTED\nendif()\n\nif(CMAKE_SIZEOF_VOID_P EQUAL 8)\n set(BUILD_ARCH \"64 bits\")\nelseif(CMAKE_SIZEOF_VOID_P EQUAL 4)\n set(BUILD_ARCH \"32 bits\")\nendif()\n\nmessage(STATUS)\nmessage(STATUS \"General configuration for Tesseract ${PACKAGE_VERSION}\")\nmessage(STATUS \"--------------------------------------------------------\")\nmessage(STATUS \"Build type: ${CMAKE_BUILD_TYPE} ${BUILD_ARCH}\")\nmessage(STATUS \"Compiler: ${CMAKE_CXX_COMPILER_ID}\")\nmessage(STATUS \"Compiler version: ${CMAKE_CXX_COMPILER_VERSION}\")\nmessage(STATUS \"Used standard: C++${CMAKE_CXX_STANDARD}\")\nmessage(STATUS \"CXX compiler options: ${COMPILER_FLAGS}\")\nget_directory_property(DirCompDefs COMPILE_DEFINITIONS)\nmessage(STATUS \"Compile definitions = ${DirCompDefs}\")\nmessage(STATUS \"Linker options: ${CMAKE_EXE_LINKER_FLAGS} \"\n \"${CMAKE_EXE_LINKER_FLAGS_${CMAKE_BUILD_TYPE_UP}}\")\nmessage(STATUS \"Install directory: ${CMAKE_INSTALL_PREFIX}\")\nmessage(STATUS \"HAVE_AVX: ${HAVE_AVX}\")\nmessage(STATUS \"HAVE_AVX2: ${HAVE_AVX2}\")\nmessage(STATUS \"HAVE_AVX512F: ${HAVE_AVX512F}\")\nmessage(STATUS \"HAVE_FMA: ${HAVE_FMA}\")\nmessage(STATUS \"HAVE_SSE4_1: ${HAVE_SSE4_1}\")\nmessage(STATUS \"MARCH_NATIVE_OPT: ${MARCH_NATIVE_OPT}\")\nmessage(STATUS \"HAVE_NEON: ${HAVE_NEON}\")\nmessage(STATUS \"Link-time optimization: ${CMAKE_INTERPROCEDURAL_OPTIMIZATION}\")\nmessage(STATUS \"--------------------------------------------------------\")\nmessage(STATUS \"Build with sw [SW_BUILD]: ${SW_BUILD}\")\nmessage(STATUS \"Build with openmp support [OPENMP_BUILD]: ${OPENMP_BUILD}\")\nmessage(STATUS \"Build with libarchive support [HAVE_LIBARCHIVE]: \"\n \"${HAVE_LIBARCHIVE}\")\nmessage(STATUS \"Build with libcurl support [HAVE_LIBCURL]: ${HAVE_LIBCURL}\")\nmessage(STATUS \"Enable float for LSTM [FAST_FLOAT]: ${FAST_FLOAT}\")\nmessage(STATUS \"Enable optimization for host CPU (could break HW compatibility)\"\n \" [ENABLE_NATIVE]: ${ENABLE_NATIVE}\")\nmessage(STATUS \"Disable disable graphics (ScrollView) [GRAPHICS_DISABLED]: \"\n \"${GRAPHICS_DISABLED}\")\nmessage(STATUS \"Disable the legacy OCR engine [DISABLED_LEGACY_ENGINE]: \"\n \"${DISABLED_LEGACY_ENGINE}\")\nmessage(STATUS \"Build training tools [BUILD_TRAINING_TOOLS]: \"\n \"${BUILD_TRAINING_TOOLS}\")\nmessage(STATUS \"Build tests [BUILD_TESTS]: ${BUILD_TESTS}\")\nmessage(STATUS \"Use system ICU Library [USE_SYSTEM_ICU]: ${USE_SYSTEM_ICU}\")\nmessage(\n STATUS \"Install tesseract configs [INSTALL_CONFIGS]: ${INSTALL_CONFIGS}\")\nmessage(STATUS \"--------------------------------------------------------\")\nmessage(STATUS \"Modern build optimizations:\")\nmessage(STATUS \"Unity build [ENABLE_UNITY_BUILD]: ${ENABLE_UNITY_BUILD}\")\nmessage(STATUS \"Precompiled headers [ENABLE_PRECOMPILED_HEADERS]: ${ENABLE_PRECOMPILED_HEADERS}\")\nmessage(STATUS \"ccache [ENABLE_CCACHE]: ${ENABLE_CCACHE}\")\nif(CMAKE_GENERATOR STREQUAL \"Ninja\")\n message(STATUS \"Ninja job pools [ENABLE_NINJA_POOL]: ${ENABLE_NINJA_POOL}\")\nelse()\n message(STATUS \"Ninja job pools [ENABLE_NINJA_POOL]: Disabled (not using Ninja)\")\nendif()\nmessage(STATUS \"--------------------------------------------------------\")\nmessage(STATUS)\n\n# ##############################################################################\n#\n# build\n#\n# ##############################################################################\n\ninclude(BuildFunctions)\ninclude(SourceGroups)\n\nadd_definitions(-D_SILENCE_STDEXT_HASH_DEPRECATION_WARNINGS=1)\n\ninclude_directories(${CMAKE_CURRENT_BINARY_DIR})\ninclude_directories(${CMAKE_CURRENT_BINARY_DIR}/include)\nif(ANDROID_TOOLCHAIN)\n include_directories(${ANDROID_TOOLCHAIN}/sysroot/usr/include)\n add_compile_definitions(__ANDROID_API_FUTURE__)\nendif()\n\n# ##############################################################################\n# LIBRARY tesseract\n# ##############################################################################\n\n# Include source file lists\ninclude(cmake/SourceLists.cmake)\n\n# Build the core source file list\nset(TESSERACT_SRC ${TESSERACT_SRC_CORE})\n\nif(DISABLED_LEGACY_ENGINE)\n # prepend path to list of source files\n function(prepend_path srcs path)\n set(tmp, \"\")\n foreach(src IN LISTS ${srcs})\n list(APPEND tmp ${path}/${src})\n endforeach(src ${srcs})\n set(${srcs}\n ${tmp}\n PARENT_SCOPE)\n endfunction()\n\n set(TESSERACT_SRC_LEGACY\n src/ccmain/adaptions.cpp\n src/ccmain/docqual.cpp\n src/ccmain/equationdetect.cpp\n src/ccmain/fixspace.cpp\n src/ccmain/fixxht.cpp\n src/ccmain/osdetect.cpp\n src/ccmain/par_control.cpp\n src/ccmain/recogtraining.cpp\n src/ccmain/superscript.cpp\n src/ccmain/tessbox.cpp\n src/ccmain/tfacepp.cpp\n src/ccstruct/fontinfo.cpp\n src/ccstruct/params_training_featdef.cpp\n src/ccutil/ambigs.cpp\n src/ccutil/bitvector.cpp\n src/ccutil/indexmapbidi.cpp\n src/classify/adaptive.cpp\n src/classify/adaptmatch.cpp\n src/classify/blobclass.cpp\n src/classify/cluster.cpp\n src/classify/clusttool.cpp\n src/classify/cutoffs.cpp\n src/classify/featdefs.cpp\n src/classify/float2int.cpp\n src/classify/fpoint.cpp\n src/classify/intfeaturespace.cpp\n src/classify/intfx.cpp\n src/classify/intmatcher.cpp\n src/classify/intproto.cpp\n src/classify/kdtree.cpp\n src/classify/mf.cpp\n src/classify/mfoutline.cpp\n src/classify/mfx.cpp\n src/classify/normfeat.cpp\n src/classify/normmatch.cpp\n src/classify/ocrfeatures.cpp\n src/classify/outfeat.cpp\n src/classify/picofeat.cpp\n src/classify/protos.cpp\n src/classify/shapeclassifier.cpp\n src/classify/shapetable.cpp\n src/classify/tessclassifier.cpp\n src/classify/trainingsample.cpp\n src/dict/permdawg.cpp\n src/dict/hyphen.cpp\n src/wordrec/associate.cpp\n src/wordrec/chop.cpp\n src/wordrec/chopper.cpp\n src/wordrec/drawfx.cpp\n src/wordrec/findseam.cpp\n src/wordrec/gradechop.cpp\n src/wordrec/language_model.cpp\n src/wordrec/lm_consistency.cpp\n src/wordrec/lm_pain_points.cpp\n src/wordrec/lm_state.cpp\n src/wordrec/outlines.cpp\n src/wordrec/params_model.cpp\n src/wordrec/pieces.cpp\n src/wordrec/plotedges.cpp\n src/wordrec/render.cpp\n src/wordrec/segsearch.cpp\n src/wordrec/wordclass.cpp)\n prepend_path(TESSERACT_SRC_LEGACY \"${CMAKE_CURRENT_SOURCE_DIR}\")\n list(REMOVE_ITEM TESSERACT_SRC ${TESSERACT_SRC_LEGACY})\nendif(DISABLED_LEGACY_ENGINE)\n\n# Use architecture files from SourceLists.cmake\nset(arch_files ${TESSERACT_SRC_ARCH})\n\nif(DOTPRODUCT_FLAGS)\n set_source_files_properties(src/arch/dotproduct.cpp\n PROPERTIES COMPILE_FLAGS ${DOTPRODUCT_FLAGS})\nendif(DOTPRODUCT_FLAGS)\nif(HAVE_AVX)\n list(APPEND arch_files_opt src/arch/dotproductavx.cpp)\n set_source_files_properties(src/arch/dotproductavx.cpp\n PROPERTIES COMPILE_FLAGS ${AVX_COMPILE_FLAGS})\nendif(HAVE_AVX)\nif(HAVE_AVX2)\n list(APPEND arch_files_opt src/arch/intsimdmatrixavx2.cpp\n src/arch/dotproductavx.cpp)\n set_source_files_properties(src/arch/intsimdmatrixavx2.cpp\n PROPERTIES COMPILE_FLAGS ${AVX2_COMPILE_FLAGS})\nendif(HAVE_AVX2)\nif(HAVE_AVX512F)\n list(APPEND arch_files_opt src/arch/dotproductavx512.cpp)\n set_source_files_properties(src/arch/dotproductavx512.cpp\n PROPERTIES COMPILE_FLAGS ${AVX512F_COMPILE_FLAGS})\nendif(HAVE_AVX512F)\nif(HAVE_FMA)\n list(APPEND arch_files_opt src/arch/dotproductfma.cpp)\n set_source_files_properties(src/arch/dotproductfma.cpp\n PROPERTIES COMPILE_FLAGS ${FMA_COMPILE_FLAGS})\nendif(HAVE_FMA)\nif(HAVE_SSE4_1)\n list(APPEND arch_files_opt src/arch/dotproductsse.cpp\n src/arch/intsimdmatrixsse.cpp)\n set_source_files_properties(\n src/arch/dotproductsse.cpp src/arch/intsimdmatrixsse.cpp\n PROPERTIES COMPILE_FLAGS ${SSE4_1_COMPILE_FLAGS})\nendif(HAVE_SSE4_1)\nif(HAVE_NEON)\n list(APPEND arch_files_opt src/arch/dotproductneon.cpp\n src/arch/intsimdmatrixneon.cpp)\n if(NEON_COMPILE_FLAGS)\n set_source_files_properties(\n src/arch/dotproductneon.cpp src/arch/intsimdmatrixneon.cpp\n PROPERTIES COMPILE_FLAGS ${NEON_COMPILE_FLAGS})\n endif()\nendif(HAVE_NEON)\n\n# Use explicit header file lists from SourceLists.cmake\nset(TESSERACT_HDR ${TESSERACT_HDR_INCLUDE} ${TESSERACT_HDR_INTERNAL})\n\nset(TESSERACT_SRC\n ${TESSERACT_SRC}\n src/api/baseapi.cpp\n src/api/capi.cpp\n src/api/renderer.cpp\n src/api/altorenderer.cpp\n src/api/pagerenderer.cpp\n src/api/hocrrenderer.cpp\n src/api/lstmboxrenderer.cpp\n src/api/pdfrenderer.cpp\n src/api/wordstrboxrenderer.cpp)\n\nset(TESSERACT_CONFIGS\n tessdata/configs/alto\n tessdata/configs/ambigs.train\n tessdata/configs/api_config\n tessdata/configs/bazaar\n tessdata/configs/bigram\n tessdata/configs/box.train\n tessdata/configs/box.train.stderr\n tessdata/configs/digits\n tessdata/configs/get.images\n tessdata/configs/hocr\n tessdata/configs/inter\n tessdata/configs/kannada\n tessdata/configs/linebox\n tessdata/configs/logfile\n tessdata/configs/lstm.train\n tessdata/configs/lstmbox\n tessdata/configs/lstmdebug\n tessdata/configs/makebox\n tessdata/configs/page\n tessdata/configs/pdf\n tessdata/configs/quiet\n tessdata/configs/rebox\n tessdata/configs/strokewidth\n tessdata/configs/tsv\n tessdata/configs/txt\n tessdata/configs/unlv\n tessdata/configs/wordstrbox)\n\nset(TESSERACT_TESSCONFIGS\n tessdata/tessconfigs/batch tessdata/tessconfigs/batch.nochop\n tessdata/tessconfigs/matdemo tessdata/tessconfigs/msdemo\n tessdata/tessconfigs/nobatch tessdata/tessconfigs/segdemo)\n\nset(LIBTESSFILES ${TESSERACT_SRC} ${arch_files} ${arch_files_opt}\n ${TESSERACT_HDR})\n\nsource_group(TREE ${CMAKE_CURRENT_SOURCE_DIR} FILES ${LIBTESSFILES})\n\nadd_library(libtesseract ${LIBTESSFILES})\n\n# Apply modern optimizations to the main library\nif(ENABLE_UNITY_BUILD)\n set_target_properties(libtesseract PROPERTIES UNITY_BUILD ON)\n set_target_properties(libtesseract PROPERTIES UNITY_BUILD_BATCH_SIZE 16)\n message(STATUS \"Unity build enabled for libtesseract with batch size 16\")\nendif()\n\n# Apply precompiled headers to reduce compilation time\nif(ENABLE_PRECOMPILED_HEADERS)\n target_precompile_headers(libtesseract PRIVATE\n \n \n \n \n \n \n \n \n )\n\n # Exclude architecture-specific files from PCH due to custom compiler flags\n set(ARCH_FILES_NO_PCH\n src/arch/dotproduct.cpp\n src/arch/dotproductavx.cpp\n src/arch/dotproductavx512.cpp\n src/arch/dotproductfma.cpp\n src/arch/dotproductsse.cpp\n src/arch/dotproductneon.cpp\n src/arch/intsimdmatrixavx2.cpp\n src/arch/intsimdmatrixsse.cpp\n src/arch/intsimdmatrixneon.cpp\n )\n\n foreach(file ${ARCH_FILES_NO_PCH})\n if(EXISTS \"${CMAKE_CURRENT_SOURCE_DIR}/${file}\")\n set_source_files_properties(\"${file}\" PROPERTIES SKIP_PRECOMPILE_HEADERS ON)\n endif()\n endforeach()\n\n message(STATUS \"Precompiled headers enabled for libtesseract (excluding architecture-specific files)\")\nendif()\n\n# Configure build pools for Ninja\nif(ENABLE_NINJA_POOL AND CMAKE_GENERATOR STREQUAL \"Ninja\")\n set_target_properties(libtesseract PROPERTIES JOB_POOL_COMPILE compile)\n set_target_properties(libtesseract PROPERTIES JOB_POOL_LINK link)\nendif()\n\ntarget_include_directories(\n libtesseract BEFORE\n PRIVATE src\n PUBLIC $\n $\n $\n $\n $\n $\n $\n $\n $\n $\n $\n $\n $)\nif(BUILD_SHARED_LIBS)\n target_compile_definitions(\n libtesseract\n PRIVATE -DTESS_EXPORTS\n INTERFACE -DTESS_IMPORTS)\n # generate_export_header (libtesseract EXPORT_MACRO_NAME TESS_API)\nendif()\ntarget_link_libraries(libtesseract PRIVATE ${LIB_Ws2_32} ${LIB_pthread})\nif(OpenMP_CXX_FOUND)\n target_link_libraries(libtesseract PUBLIC OpenMP::OpenMP_CXX)\nendif()\nif(LibArchive_FOUND)\n target_link_libraries(libtesseract PUBLIC ${LibArchive_LIBRARIES})\nendif(LibArchive_FOUND)\nif(CURL_FOUND)\n if(NOT CURL_LIBRARIES)\n target_link_libraries(libtesseract PUBLIC CURL::libcurl)\n else()\n target_link_libraries(libtesseract PUBLIC ${CURL_LIBRARIES})\n endif()\nendif(CURL_FOUND)\n\nset_target_properties(\n libtesseract PROPERTIES VERSION\n ${VERSION_MAJOR}.${VERSION_MINOR}.${VERSION_PATCH})\nset_target_properties(\n libtesseract PROPERTIES SOVERSION\n ${VERSION_MAJOR}.${VERSION_MINOR})\n\nset_target_properties(\n libtesseract\n PROPERTIES\n OUTPUT_NAME\n tesseract$<$:${VERSION_MAJOR}${VERSION_MINOR}$<$:d>>\n)\n\nif(SW_BUILD)\n target_link_libraries(libtesseract PUBLIC org.sw.demo.danbloomberg.leptonica\n org.sw.demo.libarchive.libarchive)\n file(WRITE ${CMAKE_CURRENT_BINARY_DIR}/TesseractTargets.cmake\n \"include(${CMAKE_CURRENT_BINARY_DIR}/cppan.cmake)\\n\")\n export(\n TARGETS libtesseract\n APPEND\n FILE ${CMAKE_CURRENT_BINARY_DIR}/TesseractTargets.cmake\n NAMESPACE Tesseract::)\nelse()\n target_link_libraries(libtesseract PUBLIC ${Leptonica_LIBRARIES})\n export(\n TARGETS libtesseract\n FILE ${CMAKE_CURRENT_BINARY_DIR}/TesseractTargets.cmake\n NAMESPACE Tesseract::)\nendif()\n\nif(WIN32\n AND CLANG\n AND OPENMP_BUILD)\n # Workaround for \"libomp.lib is not automatically added on Windows\" see:\n # http://lists.llvm.org/pipermail/openmp-dev/2015-August/000857.html\n target_link_libraries(libtesseract PRIVATE ${OpenMP_LIBRARY})\nendif()\n\nif(ANDROID)\n add_definitions(-DANDROID)\n find_package(CpuFeaturesNdkCompat REQUIRED)\n target_include_directories(\n libtesseract\n PRIVATE \"${CpuFeaturesNdkCompat_DIR}/../../../include/ndk_compat\")\n target_link_libraries(libtesseract PRIVATE CpuFeatures::ndk_compat)\nendif()\n\n# ##############################################################################\n# EXECUTABLE tesseract\n# ##############################################################################\n\nadd_executable(tesseract src/tesseract.cpp)\ntarget_link_libraries(tesseract libtesseract)\nif(HAVE_TIFFIO_H AND WIN32)\n target_link_libraries(tesseract ${TIFF_LIBRARIES})\nendif()\n\nif(OPENMP_BUILD AND UNIX)\n target_link_libraries(tesseract pthread)\nendif()\n\n# ##############################################################################\n\nif(BUILD_TESTS\n AND EXISTS\n ${CMAKE_CURRENT_SOURCE_DIR}/unittest/third_party/googletest/CMakeLists.txt\n)\n enable_testing()\n add_subdirectory(unittest/third_party/googletest)\n add_subdirectory(unittest)\nendif()\n\nif(BUILD_TRAINING_TOOLS)\n add_subdirectory(src/training)\nendif()\n\nget_target_property(tesseract_NAME libtesseract NAME)\nget_target_property(tesseract_VERSION libtesseract VERSION)\nget_target_property(tesseract_OUTPUT_NAME libtesseract OUTPUT_NAME)\n\nconfigure_file(tesseract.pc.cmake ${CMAKE_CURRENT_BINARY_DIR}/tesseract.pc.in\n @ONLY)\n# to resolve generator expression in OUTPUT_NAME\nfile(\n GENERATE\n OUTPUT ${CMAKE_CURRENT_BINARY_DIR}/tesseract_$.pc\n INPUT ${CMAKE_CURRENT_BINARY_DIR}/tesseract.pc.in)\n\nconfigure_package_config_file(\n cmake/templates/TesseractConfig.cmake.in\n ${CMAKE_CURRENT_BINARY_DIR}/cmake/tesseract/TesseractConfig.cmake\n INSTALL_DESTINATION ${CMAKE_INSTALL_LIBDIR}/cmake/tesseract\n PATH_VARS INCLUDE_DIR LIBRARY_DIRS)\nwrite_basic_package_version_file(\n ${CMAKE_CURRENT_BINARY_DIR}/cmake/tesseract/TesseractConfigVersion.cmake\n VERSION ${PACKAGE_VERSION}\n COMPATIBILITY SameMajorVersion)\n\ninstall(\n FILES ${CMAKE_CURRENT_BINARY_DIR}/tesseract_$.pc\n DESTINATION ${CMAKE_INSTALL_LIBDIR}/pkgconfig\n RENAME tesseract.pc)\ninstall(TARGETS tesseract DESTINATION bin)\nif (MSVC)\n install(FILES $ DESTINATION bin OPTIONAL)\nendif()\ninstall(\n TARGETS libtesseract\n EXPORT TesseractTargets\n RUNTIME DESTINATION bin\n RUNTIME DESTINATION bin\n LIBRARY DESTINATION ${CMAKE_INSTALL_LIBDIR}\n ARCHIVE DESTINATION ${CMAKE_INSTALL_LIBDIR})\nif (MSVC AND BUILD_SHARED_LIBS)\n install(FILES $ DESTINATION bin OPTIONAL)\nendif()\ninstall(\n EXPORT TesseractTargets\n NAMESPACE Tesseract::\n DESTINATION ${CMAKE_INSTALL_LIBDIR}/cmake/tesseract)\ninstall(DIRECTORY ${CMAKE_CURRENT_BINARY_DIR}/cmake\n DESTINATION ${CMAKE_INSTALL_LIBDIR})\n\ninstall(\n FILES include/tesseract/baseapi.h\n include/tesseract/capi.h\n include/tesseract/renderer.h\n ${CMAKE_CURRENT_BINARY_DIR}/include/tesseract/version.h\n include/tesseract/ltrresultiterator.h\n include/tesseract/pageiterator.h\n include/tesseract/resultiterator.h\n include/tesseract/osdetect.h\n include/tesseract/publictypes.h\n include/tesseract/ocrclass.h\n include/tesseract/export.h\n include/tesseract/unichar.h\n # ${CMAKE_CURRENT_BINARY_DIR}/src/endianness.h\n DESTINATION include/tesseract)\n\nif(INSTALL_CONFIGS)\n install(FILES ${TESSERACT_CONFIGS}\n DESTINATION ${CMAKE_INSTALL_DATAROOTDIR}/tessdata/configs)\n install(FILES ${TESSERACT_TESSCONFIGS}\n DESTINATION ${CMAKE_INSTALL_DATAROOTDIR}/tessdata/tessconfigs)\nendif()\n\n# ##############################################################################\n# uninstall target\n# ##############################################################################\nif(NOT TARGET uninstall)\n configure_file(\n \"${CMAKE_CURRENT_SOURCE_DIR}/cmake/templates/cmake_uninstall.cmake.in\"\n \"${CMAKE_CURRENT_BINARY_DIR}/cmake_uninstall.cmake\" IMMEDIATE @ONLY)\n\n add_custom_target(\n uninstall\n COMMENT \"Uninstall installed files\"\n COMMAND ${CMAKE_COMMAND} -P\n ${CMAKE_CURRENT_BINARY_DIR}/cmake_uninstall.cmake)\nendif()\n\n# ##############################################################################\n" }, { "path": "CONTRIBUTING.md", "content": "# Contributing\n\n**Please follow these rules and advice**.\n\n## Creating an Issue or Using the Forum\n\nIf you think you found a bug in Tesseract, please create an issue.\n\nUse the [user forum](https://groups.google.com/g/tesseract-ocr) instead of creating an issue if ...\n\n* You have problems using Tesseract and need some help.\n* You have problems installing the software.\n* You are not satisfied with the accuracy of the OCR, and want to ask how you can improve it. Note: You should first read the [ImproveQuality](https://tesseract-ocr.github.io/tessdoc/ImproveQuality.html) documentation.\n* You are trying to train Tesseract and you have a problem and/or want to ask a question about the training process. Note: You should first read the **official** guides [[1]](https://tesseract-ocr.github.io/tessdoc/) or [[2]](https://tesseract-ocr.github.io/tessdoc/tess5/TrainingTesseract-5.html) found in the project documentation.\n* You have a general question.\n\nAn issue should only be reported if the platform you are using is one of these:\n\n* Linux (but not a version that is more than 4 years old)\n* Windows (Windows 7 or newer version)\n* macOS (last 3 releases)\n\nFor older versions or other operating systems, use the Tesseract forum.\n\nWhen creating an issue, please report your operating system, including its specific version: \"Ubuntu 16.04\", \"Windows 10\", \"Mac OS X 10.11\" etc.\n\nSearch through open and closed issues to see if similar issue has been reported already (and sometimes also has been solved).\n\nSimilarly, before you post your question in the forum, search through past threads to see if similar question has been asked already.\n\nRead the [documentation](https://tesseract-ocr.github.io/tessdoc/) before you report your issue or ask a question in the forum.\n\nOnly report an issue in the latest official release. Optionally, try to check if the issue is not already solved in the latest snapshot in the git repository.\n\nMake sure you are able to replicate the problem with Tesseract command line program. For external programs that use Tesseract (including wrappers and your own program, if you are developer), report the issue to the developers of that software if it's possible. You can also try to find help in the Tesseract forum.\n\nEach version of Tesseract has its own language data you need to obtain. You **must** obtain and install trained data for English (eng) and osd. Verify that Tesseract knows about these two files (and other trained data you installed) with this command:\n`tesseract --list-langs`.\n\nPost example files to demonstrate the problem.\nBUT don't post files with private info (about yourself or others).\n\nWhen attaching a file to the issue report / forum ...\n\n* Do not post a file larger than 20 MB.\n* GitHub supports only few file name extensions like `.png` or `.txt`. If GitHub rejects your files, you can compress them using a program that can produce a zip archive and then load this zip file to GitHub.\n\nDo not attach programs or libraries to your issues/posts.\n\nFor large files or for programs, add a link to a location where they can be downloaded (your site, Git repo, Google Drive, Dropbox etc.)\n\nAttaching a multi-page TIFF image is useful only if you have problem with multi-page functionality, otherwise attach only one or a few single page images.\n\nCopy the error message from the console instead of sending a screenshot of it.\n\nUse the toolbar above the comment edit area to format your comment.\n\nAdd three backticks before and after a code sample or output of a command to format it (The `Insert code` button can help you doing it).\n\nIf your comment includes a code sample or output of a command that exceeds ~25 lines, post it as attached text file (`filename.txt`).\n\nUse `Preview` before you send your issue. Read it again before sending.\n\nNote that most of the people that respond to issues and answer questions are either other 'regular' users or **volunteers** developers. Please be nice to them :-)\n\nThe [tesseract developers](https://groups.google.com/g/tesseract-dev) forum should be used to discuss Tesseract development: bug fixes, enhancements, add-ons for Tesseract.\n\nSometimes you will not get a respond to your issue or question. We apologize in advance! Please don't take it personally. There can be many reasons for this, including: time limits, no one knows the answer (at least not the ones that are available at that time) or just that\nyour question has been asked (and has been answered) many times before...\n\n## For Developers: Creating a Pull Request\n\nYou should always make sure your changes build and run successfully.\n\nFor that, your clone needs to have all submodules (`googletest`, `test`) included. To do so, either specify `--recurse-submodules` during the initial clone, or run `git submodule update --init --recursive NAME` for each `NAME` later. If `configure` already created those directories (blocking the clone), remove them first (or `make distclean`), then clone and reconfigure.\n\nHave a look at [the README](./README.md) and [testing README](https://github.com/tesseract-ocr/test/blob/main/README.md) and the [documentation](https://tesseract-ocr.github.io/tessdoc/Compiling-%E2%80%93-GitInstallation.html#unit-test-builds) on installation.\n\nIn short, after running `configure` from the build directory of your choice, to build the library and CLI, run `make`. To test it, run `make check`. To build the training tools, run `make training`.\n\nAs soon as your changes are building and tests are succeeding, you can publish them. If you have not already, please [fork](https://docs.github.com/en/get-started/quickstart/contributing-to-projects) tesseract (somewhere) on GitHub, and push your changes to that fork (in a new branch). Then [submit as PR](https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/proposing-changes-to-your-work-with-pull-requests/creating-a-pull-request-from-a-fork).\n\nPlease also keep track of reports from CI (automated build status) and Coverity/CodeQL (quality scan). When the indicators show deterioration after your changes, further action may be required to improve them.\n" }, { "path": "ChangeLog", "content": "The ChangeLog for all releases from 1.0 (2006-06-16) up to 5.0.0 (2024-11-10)\nis available here:\n\nhttps://github.com/tesseract-ocr/tesseract/blob/64eab6c457b2337dd690746a5fde5c222b40d5f8/ChangeLog\n\nSee https://github.com/tesseract-ocr/tesseract/releases for the latest release notes.\n\n" }, { "path": "INSTALL", "content": "Copyright 1994, 1995, 1996, 1999, 2000, 2001, 2002 Free Software\nFoundation, Inc.\n\n This file is free documentation; the Free Software Foundation gives\nunlimited permission to copy, distribute and modify it.\n\nBasic Installation\n==================\n\n These are generic installation instructions. First you need to run\n`./autogen.sh', that creates `configure' script.\n\n The `configure' shell script attempts to guess correct values for\nvarious system-dependent variables used during compilation. It uses\nthose values to create a `Makefile' in each directory of the package.\nIt may also create one or more `.h' files containing system-dependent\ndefinitions. Finally, it creates a shell script `config.status' that\nyou can run in the future to recreate the current configuration, and a\nfile `config.log' containing compiler output (useful mainly for\ndebugging `configure').\n\n It can also use an optional file (typically called `config.cache'\nand enabled with `--cache-file=config.cache' or simply `-C') that saves\nthe results of its tests to speed up reconfiguring. (Caching is\ndisabled by default to prevent problems with accidental use of stale\ncache files.)\n\n If you need to do unusual things to compile the package, please try\nto figure out how `configure' could check whether to do them, and mail\ndiffs or instructions to the address given in the `README' so they can\nbe considered for the next release. If you are using the cache, and at\nsome point `config.cache' contains results you don't want to keep, you\nmay remove or edit it.\n\n The file `configure.ac' (or `configure.in') is used to create\n`configure' by a program called `autoconf'. You only need\n`configure.ac' if you want to change it or regenerate `configure' using\na newer version of `autoconf'.\n\nThe simplest way to compile this package is:\n\n 1. `cd' to the directory containing the package's source code and type\n `./configure' to configure the package for your system. If you're\n using `csh' on an old version of System V, you might need to type\n `sh ./configure' instead to prevent `csh' from trying to execute\n `configure' itself.\n\n Running `configure' takes a while. While running, it prints some\n messages telling which features it is checking for.\n\n 2. Type `make' to compile the package.\n\n 3. Optionally, type `make check' to run any self-tests that come with\n the package.\n\n 4. Type `make install' to install the programs and any data files and\n documentation.\n\n 5. You can remove the program binaries and object files from the\n source code directory by typing `make clean'. To also remove the\n files that `configure' created (so you can compile the package for\n a different kind of computer), type `make distclean'. There is\n also a `make maintainer-clean' target, but that is intended mainly\n for the package's developers. If you use it, you may have to get\n all sorts of other programs in order to regenerate files that came\n with the distribution.\n\nCompilers and Options\n=====================\n\n Some systems require unusual options for compilation or linking that\nthe `configure' script does not know about. Run `./configure --help'\nfor details on some of the pertinent environment variables.\n\n You can give `configure' initial values for configuration parameters\nby setting variables in the command line or in the environment. Here\nis an example:\n\n ./configure CC=c89 CFLAGS=-O2 LIBS=-lposix\n\n *Note Defining Variables::, for more details.\n\nCompiling For Multiple Architectures\n====================================\n\n You can compile the package for more than one kind of computer at the\nsame time, by placing the object files for each architecture in their\nown directory. To do this, you must use a version of `make' that\nsupports the `VPATH' variable, such as GNU `make'. `cd' to the\ndirectory where you want the object files and executables to go and run\nthe `configure' script. `configure' automatically checks for the\nsource code in the directory that `configure' is in and in `..'.\n\n If you have to use a `make' that does not support the `VPATH'\nvariable, you have to compile the package for one architecture at a\ntime in the source code directory. After you have installed the\npackage for one architecture, use `make distclean' before reconfiguring\nfor another architecture.\n\nInstallation Names\n==================\n\n By default, `make install' will install the package's files in\n`/usr/local/bin', `/usr/local/man', etc. You can specify an\ninstallation prefix other than `/usr/local' by giving `configure' the\noption `--prefix=PATH'.\n\n You can specify separate installation prefixes for\narchitecture-specific files and architecture-independent files. If you\ngive `configure' the option `--exec-prefix=PATH', the package will use\nPATH as the prefix for installing programs and libraries.\nDocumentation and other data files will still use the regular prefix.\n\n In addition, if you use an unusual directory layout you can give\noptions like `--bindir=PATH' to specify different values for particular\nkinds of files. Run `configure --help' for a list of the directories\nyou can set and what kinds of files go in them.\n\n If the package supports it, you can cause programs to be installed\nwith an extra prefix or suffix on their names by giving `configure' the\noption `--program-prefix=PREFIX' or `--program-suffix=SUFFIX'.\n\nOptional Features\n=================\n\n Some packages pay attention to `--enable-FEATURE' options to\n`configure', where FEATURE indicates an optional part of the package.\nThey may also pay attention to `--with-PACKAGE' options, where PACKAGE\nis something like `gnu-as' or `x' (for the X Window System). The\n`README' should mention any `--enable-' and `--with-' options that the\npackage recognizes.\n\n For packages that use the X Window System, `configure' can usually\nfind the X include and library files automatically, but if it doesn't,\nyou can use the `configure' options `--x-includes=DIR' and\n`--x-libraries=DIR' to specify their locations.\n\nSpecifying the System Type\n==========================\n\n There may be some features `configure' cannot figure out\nautomatically, but needs to determine by the type of machine the package\nwill run on. Usually, assuming the package is built to be run on the\n_same_ architectures, `configure' can figure that out, but if it prints\na message saying it cannot guess the machine type, give it the\n`--build=TYPE' option. TYPE can either be a short name for the system\ntype, such as `sun4', or a canonical name which has the form:\n\n CPU-COMPANY-SYSTEM\n\nwhere SYSTEM can have one of these forms:\n\n OS KERNEL-OS\n\n See the file `config.sub' for the possible values of each field. If\n`config.sub' isn't included in this package, then this package doesn't\nneed to know the machine type.\n\n If you are _building_ compiler tools for cross-compiling, you should\nuse the `--target=TYPE' option to select the type of system they will\nproduce code for.\n\n If you want to _use_ a cross compiler, that generates code for a\nplatform different from the build platform, you should specify the\n\"host\" platform (i.e., that on which the generated programs will\neventually be run) with `--host=TYPE'.\n\nSharing Defaults\n================\n\n If you want to set default values for `configure' scripts to share,\nyou can create a site shell script called `config.site' that gives\ndefault values for variables like `CC', `cache_file', and `prefix'.\n`configure' looks for `PREFIX/share/config.site' if it exists, then\n`PREFIX/etc/config.site' if it exists. Or, you can set the\n`CONFIG_SITE' environment variable to the location of the site script.\nA warning: not all `configure' scripts look for a site script.\n\nDefining Variables\n==================\n\n Variables not defined in a site shell script can be set in the\nenvironment passed to `configure'. However, some packages may run\nconfigure again during the build, and the customized values of these\nvariables may be lost. In order to avoid this problem, you should set\nthem in the `configure' command line, using `VAR=value'. For example:\n\n ./configure CC=/usr/local2/bin/gcc\n\nwill cause the specified gcc to be used as the C compiler (unless it is\noverridden in the site shell script).\n\n`configure' Invocation\n======================\n\n `configure' recognizes the following options to control how it\noperates.\n\n`--help'\n`-h'\n Print a summary of the options to `configure', and exit.\n\n`--version'\n`-V'\n Print the version of Autoconf used to generate the `configure'\n script, and exit.\n\n`--cache-file=FILE'\n Enable the cache: use and save the results of the tests in FILE,\n traditionally `config.cache'. FILE defaults to `/dev/null' to\n disable caching.\n\n`--config-cache'\n`-C'\n Alias for `--cache-file=config.cache'.\n\n`--quiet'\n`--silent'\n`-q'\n Do not print messages saying which checks are being made. To\n suppress all normal output, redirect it to `/dev/null' (any error\n messages will still be shown).\n\n`--srcdir=DIR'\n Look for the package's source code in directory DIR. Usually\n `configure' can determine that directory automatically.\n\n`configure' also accepts some other, not widely useful, options. Run\n`configure --help' for more details.\n" }, { "path": "INSTALL.GIT.md", "content": "## autotools (LINUX/UNIX , msys...)\n\nIf you have cloned Tesseract from GitHub, you must generate\nthe configure script.\n\nIf you have tesseract 4.0x installation in your system, please remove it\nbefore new build.\n\nYou need Leptonica 1.74.2 (minimum) for Tesseract 4.0x.\n\nKnown dependencies for training tools (excluding leptonica):\n\n* compiler with c++17 support\n* automake\n* pkg-config\n* pango-devel\n* cairo-devel\n* icu-devel\n\nSo, the steps for making Tesseract are:\n\n ./autogen.sh\n ./configure\n make\n sudo make install\n sudo ldconfig\n make training\n sudo make training-install\n\nYou need to install at least English language and OSD traineddata files to\n`TESSDATA_PREFIX` directory.\n\nYou can retrieve single file with tools like [wget](https://www.gnu.org/software/wget/), [curl](https://curl.haxx.se/), [GithubDownloader](https://github.com/intezer/GithubDownloader) or browser.\n\nAll language data files can be retrieved from git repository (useful only for packagers!).\n(Repository is huge - more that 1.2 GB. You do NOT need to download traineddata files for\nall languages).\n\n git clone https://github.com/tesseract-ocr/tessdata.git tesseract-ocr.tessdata\n\nYou need an Internet connection and [curl](https://curl.haxx.se/) to compile `ScrollView.jar`\nbecause the build will automatically download\n[piccolo2d-core-3.0.1.jar](https://search.maven.org/remotecontent?filepath=org/piccolo2d/piccolo2d-core/3.0.1/piccolo2d-core-3.0.1.jar) and\n[piccolo2d-extras-3.0.1.jar](https://search.maven.org/remotecontent?filepath=org/piccolo2d/piccolo2d-extras/3.0.1/piccolo2d-extras-3.0.1.jar) and\n[jaxb-api-2.3.1.jar](http://search.maven.org/remotecontent?filepath=javax/xml/bind/jaxb-api/2.3.1/jaxb-api-2.3.1.jar) and place them to `tesseract/java`.\n\nJust run:\n\n make ScrollView.jar\n\nand follow the instruction on [Viewer Debugging](https://tesseract-ocr.github.io/tessdoc/ViewerDebugging.html).\n\n## cmake\n\nThere is alternative build system based on multiplatform [cmake](https://cmake.org/)\n\n### LINUX\n\n mkdir build\n cd build && cmake .. && make\n sudo make install\n\n### WINDOWS\n\nSee the [documentation](https://tesseract-ocr.github.io/tessdoc/) for more information on this.\n" }, { "path": "LICENSE", "content": "\n Apache License\n Version 2.0, January 2004\n http://www.apache.org/licenses/\n\n TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION\n\n 1. Definitions.\n\n \"License\" shall mean the terms and conditions for use, reproduction,\n and distribution as defined by Sections 1 through 9 of this document.\n\n \"Licensor\" shall mean the copyright owner or entity authorized by\n the copyright owner that is granting the License.\n\n \"Legal Entity\" shall mean the union of the acting entity and all\n other entities that control, are controlled by, or are under common\n control with that entity. For the purposes of this definition,\n \"control\" means (i) the power, direct or indirect, to cause the\n direction or management of such entity, whether by contract or\n otherwise, or (ii) ownership of fifty percent (50%) or more of the\n outstanding shares, or (iii) beneficial ownership of such entity.\n\n \"You\" (or \"Your\") shall mean an individual or Legal Entity\n exercising permissions granted by this License.\n\n \"Source\" form shall mean the preferred form for making modifications,\n including but not limited to software source code, documentation\n source, and configuration files.\n\n \"Object\" form shall mean any form resulting from mechanical\n transformation or translation of a Source form, including but\n not limited to compiled object code, generated documentation,\n and conversions to other media types.\n\n \"Work\" shall mean the work of authorship, whether in Source or\n Object form, made available under the License, as indicated by a\n copyright notice that is included in or attached to the work\n (an example is provided in the Appendix below).\n\n \"Derivative Works\" shall mean any work, whether in Source or Object\n form, that is based on (or derived from) the Work and for which the\n editorial revisions, annotations, elaborations, or other modifications\n represent, as a whole, an original work of authorship. For the purposes\n of this License, Derivative Works shall not include works that remain\n separable from, or merely link (or bind by name) to the interfaces of,\n the Work and Derivative Works thereof.\n\n \"Contribution\" shall mean any work of authorship, including\n the original version of the Work and any modifications or additions\n to that Work or Derivative Works thereof, that is intentionally\n submitted to Licensor for inclusion in the Work by the copyright owner\n or by an individual or Legal Entity authorized to submit on behalf of\n the copyright owner. For the purposes of this definition, \"submitted\"\n means any form of electronic, verbal, or written communication sent\n to the Licensor or its representatives, including but not limited to\n communication on electronic mailing lists, source code control systems,\n and issue tracking systems that are managed by, or on behalf of, the\n Licensor for the purpose of discussing and improving the Work, but\n excluding communication that is conspicuously marked or otherwise\n designated in writing by the copyright owner as \"Not a Contribution.\"\n\n \"Contributor\" shall mean Licensor and any individual or Legal Entity\n on behalf of whom a Contribution has been received by Licensor and\n subsequently incorporated within the Work.\n\n 2. Grant of Copyright License. Subject to the terms and conditions of\n this License, each Contributor hereby grants to You a perpetual,\n worldwide, non-exclusive, no-charge, royalty-free, irrevocable\n copyright license to reproduce, prepare Derivative Works of,\n publicly display, publicly perform, sublicense, and distribute the\n Work and such Derivative Works in Source or Object form.\n\n 3. Grant of Patent License. Subject to the terms and conditions of\n this License, each Contributor hereby grants to You a perpetual,\n worldwide, non-exclusive, no-charge, royalty-free, irrevocable\n (except as stated in this section) patent license to make, have made,\n use, offer to sell, sell, import, and otherwise transfer the Work,\n where such license applies only to those patent claims licensable\n by such Contributor that are necessarily infringed by their\n Contribution(s) alone or by combination of their Contribution(s)\n with the Work to which such Contribution(s) was submitted. If You\n institute patent litigation against any entity (including a\n cross-claim or counterclaim in a lawsuit) alleging that the Work\n or a Contribution incorporated within the Work constitutes direct\n or contributory patent infringement, then any patent licenses\n granted to You under this License for that Work shall terminate\n as of the date such litigation is filed.\n\n 4. Redistribution. You may reproduce and distribute copies of the\n Work or Derivative Works thereof in any medium, with or without\n modifications, and in Source or Object form, provided that You\n meet the following conditions:\n\n (a) You must give any other recipients of the Work or\n Derivative Works a copy of this License; and\n\n (b) You must cause any modified files to carry prominent notices\n stating that You changed the files; and\n\n (c) You must retain, in the Source form of any Derivative Works\n that You distribute, all copyright, patent, trademark, and\n attribution notices from the Source form of the Work,\n excluding those notices that do not pertain to any part of\n the Derivative Works; and\n\n (d) If the Work includes a \"NOTICE\" text file as part of its\n distribution, then any Derivative Works that You distribute must\n include a readable copy of the attribution notices contained\n within such NOTICE file, excluding those notices that do not\n pertain to any part of the Derivative Works, in at least one\n of the following places: within a NOTICE text file distributed\n as part of the Derivative Works; within the Source form or\n documentation, if provided along with the Derivative Works; or,\n within a display generated by the Derivative Works, if and\n wherever such third-party notices normally appear. The contents\n of the NOTICE file are for informational purposes only and\n do not modify the License. You may add Your own attribution\n notices within Derivative Works that You distribute, alongside\n or as an addendum to the NOTICE text from the Work, provided\n that such additional attribution notices cannot be construed\n as modifying the License.\n\n You may add Your own copyright statement to Your modifications and\n may provide additional or different license terms and conditions\n for use, reproduction, or distribution of Your modifications, or\n for any such Derivative Works as a whole, provided Your use,\n reproduction, and distribution of the Work otherwise complies with\n the conditions stated in this License.\n\n 5. Submission of Contributions. Unless You explicitly state otherwise,\n any Contribution intentionally submitted for inclusion in the Work\n by You to the Licensor shall be under the terms and conditions of\n this License, without any additional terms or conditions.\n Notwithstanding the above, nothing herein shall supersede or modify\n the terms of any separate license agreement you may have executed\n with Licensor regarding such Contributions.\n\n 6. Trademarks. This License does not grant permission to use the trade\n names, trademarks, service marks, or product names of the Licensor,\n except as required for reasonable and customary use in describing the\n origin of the Work and reproducing the content of the NOTICE file.\n\n 7. Disclaimer of Warranty. Unless required by applicable law or\n agreed to in writing, Licensor provides the Work (and each\n Contributor provides its Contributions) on an \"AS IS\" BASIS,\n WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or\n implied, including, without limitation, any warranties or conditions\n of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A\n PARTICULAR PURPOSE. You are solely responsible for determining the\n appropriateness of using or redistributing the Work and assume any\n risks associated with Your exercise of permissions under this License.\n\n 8. Limitation of Liability. In no event and under no legal theory,\n whether in tort (including negligence), contract, or otherwise,\n unless required by applicable law (such as deliberate and grossly\n negligent acts) or agreed to in writing, shall any Contributor be\n liable to You for damages, including any direct, indirect, special,\n incidental, or consequential damages of any character arising as a\n result of this License or out of the use or inability to use the\n Work (including but not limited to damages for loss of goodwill,\n work stoppage, computer failure or malfunction, or any and all\n other commercial damages or losses), even if such Contributor\n has been advised of the possibility of such damages.\n\n 9. Accepting Warranty or Additional Liability. While redistributing\n the Work or Derivative Works thereof, You may choose to offer,\n and charge a fee for, acceptance of support, warranty, indemnity,\n or other liability obligations and/or rights consistent with this\n License. However, in accepting such obligations, You may act only\n on Your own behalf and on Your sole responsibility, not on behalf\n of any other Contributor, and only if You agree to indemnify,\n defend, and hold each Contributor harmless for any liability\n incurred by, or claims asserted against, such Contributor by reason\n of your accepting any such warranty or additional liability.\n\n END OF TERMS AND CONDITIONS\n\n APPENDIX: How to apply the Apache License to your work.\n\n To apply the Apache License to your work, attach the following\n boilerplate notice, with the fields enclosed by brackets \"[]\"\n replaced with your own identifying information. (Don't include\n the brackets!) The text should be enclosed in the appropriate\n comment syntax for the file format. We also recommend that a\n file or class name and description of purpose be included on the\n same \"printed page\" as the copyright notice for easier\n identification within third-party archives.\n\n Copyright [yyyy] [name of copyright owner]\n\n Licensed under the Apache License, Version 2.0 (the \"License\");\n you may not use this file except in compliance with the License.\n You may obtain a copy of the License at\n\n http://www.apache.org/licenses/LICENSE-2.0\n\n Unless required by applicable law or agreed to in writing, software\n distributed under the License is distributed on an \"AS IS\" BASIS,\n WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n See the License for the specific language governing permissions and\n limitations under the License.\n" }, { "path": "Makefile.am", "content": "## run autogen.sh to create Makefile.in from this file\nACLOCAL_AMFLAGS = -I m4\n\n.PHONY: doc html install-langs ScrollView.jar install-jars pdf training\n\nCLEANFILES =\n\nSUBDIRS = . tessdata\nif MINGW\nSUBDIRS += nsis\nendif\n\nEXTRA_DIST = README.md LICENSE\nEXTRA_DIST += aclocal.m4 config configure.ac autogen.sh\nEXTRA_DIST += tesseract.pc.in doc\nif !GRAPHICS_DISABLED\nEXTRA_DIST += java\nendif\nEXTRA_DIST += CMakeLists.txt tesseract.pc.cmake cmake VERSION\n\nDIST_SUBDIRS = $(SUBDIRS)\n\nEXTRA_PROGRAMS =\n\nuninstall-hook:\n\trm -rf $(DESTDIR)$(pkgincludedir)\n\ndist-hook:\n# added using EXTRA_DIST. $(distdir)/tessdata would in\n# theory suffice.\n\trm -rf `find $(distdir) -name .deps -type d`\n\t-rm -f $(distdir)/*/Makefile $(distdir)/*/*/Makefile\n\trm -f `find $(distdir) -name '*~'`\n\trm -rf $(distdir)/doc/html/* $(distdir)/doc/*.log\n\nif !GRAPHICS_DISABLED\nScrollView.jar:\n\t@cd \"$(top_builddir)/java\" && $(MAKE) $@\n\ninstall-jars:\n\t@cd \"$(top_builddir)/java\" && $(MAKE) $@\nendif\n\ndoc:\n\t-srcdir=\"$(top_srcdir)\" builddir=\"$(top_builddir)\" \\\n\tversion=\"@PACKAGE_VERSION@\" name=\"@PACKAGE_NAME@\" \\\n\tdoxygen $(top_srcdir)/doc/Doxyfile\n\ndoc-pack: doc\n\t-chmod a+r $(top_builddir)/doc/html/*\n\t @tar --create --directory=$(top_builddir)/doc/html --verbose --file=- . | gzip -c -9 > $(top_builddir)/@PACKAGE_NAME@-@PACKAGE_VERSION@-doc-html.tar.gz;\n\ndoc-clean:\n\trm -rf $(top_builddir)/doc/html/*\n\nif MINGW\nwinsetup: training ScrollView.jar\n\t@cd \"$(top_builddir)/nsis\" && $(MAKE) winsetup\nendif\n\npkgconfigdir = $(libdir)/pkgconfig\npkgconfig_DATA = tesseract.pc\n\npkginclude_HEADERS = $(top_builddir)/include/tesseract/version.h\npkginclude_HEADERS += include/tesseract/baseapi.h\npkginclude_HEADERS += include/tesseract/capi.h\npkginclude_HEADERS += include/tesseract/export.h\npkginclude_HEADERS += include/tesseract/ltrresultiterator.h\npkginclude_HEADERS += include/tesseract/ocrclass.h\npkginclude_HEADERS += include/tesseract/osdetect.h\npkginclude_HEADERS += include/tesseract/pageiterator.h\npkginclude_HEADERS += include/tesseract/publictypes.h\npkginclude_HEADERS += include/tesseract/renderer.h\npkginclude_HEADERS += include/tesseract/resultiterator.h\npkginclude_HEADERS += include/tesseract/unichar.h\n\n# Rules for all subdirectories.\n\nnoinst_HEADERS =\nnoinst_LTLIBRARIES =\n\nAM_CPPFLAGS += -I$(top_srcdir)/include\nAM_CPPFLAGS += -I$(top_builddir)/include\nif VISIBILITY\nAM_CPPFLAGS += -DTESS_EXPORTS\nAM_CPPFLAGS += -fvisibility=hidden -fvisibility-inlines-hidden -fPIC\nendif\n\nAM_CXXFLAGS = $(OPENMP_CXXFLAGS)\n\n# Rules for src/api.\n\nlibtesseract_la_CPPFLAGS = $(AM_CPPFLAGS)\nlibtesseract_la_CPPFLAGS += -DTESS_COMMON_TRAINING_API=\nlibtesseract_la_CPPFLAGS += -I$(top_srcdir)/src/arch\nlibtesseract_la_CPPFLAGS += -I$(top_srcdir)/src/ccmain\nlibtesseract_la_CPPFLAGS += -I$(top_srcdir)/src/ccstruct\nlibtesseract_la_CPPFLAGS += -I$(top_srcdir)/src/ccutil\nlibtesseract_la_CPPFLAGS += -I$(top_srcdir)/src/classify\nlibtesseract_la_CPPFLAGS += -I$(top_srcdir)/src/cutil\nlibtesseract_la_CPPFLAGS += -I$(top_srcdir)/src/dict\nlibtesseract_la_CPPFLAGS += -I$(top_srcdir)/src/lstm\nlibtesseract_la_CPPFLAGS += -I$(top_srcdir)/src/textord\nlibtesseract_la_CPPFLAGS += -I$(top_srcdir)/src/training/common\nlibtesseract_la_CPPFLAGS += -I$(top_srcdir)/src/viewer\nlibtesseract_la_CPPFLAGS += -I$(top_srcdir)/src/wordrec\nlibtesseract_la_CPPFLAGS += $(libcurl_CFLAGS)\n\nlib_LTLIBRARIES = libtesseract.la\nlibtesseract_la_LDFLAGS = $(LEPTONICA_LIBS)\nlibtesseract_la_LDFLAGS += $(libarchive_LIBS)\nlibtesseract_la_LDFLAGS += $(libcurl_LIBS)\nif T_WIN\nlibtesseract_la_LDFLAGS += -no-undefined -lws2_32\nelse\nlibtesseract_la_LDFLAGS += $(NOUNDEFINED)\nendif\nlibtesseract_la_LDFLAGS += -version-info $(GENERIC_LIBRARY_VERSION)\n\nlibtesseract_la_SOURCES = src/api/baseapi.cpp\nlibtesseract_la_SOURCES += src/api/altorenderer.cpp\nlibtesseract_la_SOURCES += src/api/pagerenderer.cpp\nlibtesseract_la_SOURCES += src/api/capi.cpp\nlibtesseract_la_SOURCES += src/api/hocrrenderer.cpp\nlibtesseract_la_SOURCES += src/api/lstmboxrenderer.cpp\nlibtesseract_la_SOURCES += src/api/pdfrenderer.cpp\nlibtesseract_la_SOURCES += src/api/renderer.cpp\nlibtesseract_la_SOURCES += src/api/wordstrboxrenderer.cpp\n\nlibtesseract_la_LIBADD = libtesseract_ccutil.la\nlibtesseract_la_LIBADD += libtesseract_lstm.la\nlibtesseract_la_LIBADD += libtesseract_native.la\n\n# Rules for src/arch.\n\nnoinst_HEADERS += src/arch/dotproduct.h\nnoinst_HEADERS += src/arch/intsimdmatrix.h\nnoinst_HEADERS += src/arch/simddetect.h\n\nnoinst_LTLIBRARIES += libtesseract_native.la\n\nlibtesseract_native_la_CXXFLAGS = -O3 -ffast-math\nif OPENMP_SIMD\nlibtesseract_native_la_CXXFLAGS += -fopenmp-simd -DOPENMP_SIMD\nendif\nlibtesseract_native_la_CXXFLAGS += -I$(top_srcdir)/src/ccutil\nlibtesseract_native_la_SOURCES = src/arch/dotproduct.cpp\n\nif HAVE_AVX\nlibtesseract_avx_la_CXXFLAGS = -mavx\nlibtesseract_avx_la_CXXFLAGS += -I$(top_srcdir)/src/ccutil\nlibtesseract_avx_la_SOURCES = src/arch/dotproductavx.cpp\nlibtesseract_la_LIBADD += libtesseract_avx.la\nnoinst_LTLIBRARIES += libtesseract_avx.la\nendif\n\nif HAVE_AVX2\nlibtesseract_avx2_la_CXXFLAGS = -mavx2\nlibtesseract_avx2_la_CXXFLAGS += -I$(top_srcdir)/src/ccutil\nlibtesseract_avx2_la_SOURCES = src/arch/intsimdmatrixavx2.cpp\nlibtesseract_la_LIBADD += libtesseract_avx2.la\nnoinst_LTLIBRARIES += libtesseract_avx2.la\nendif\n\nif HAVE_AVX512F\nlibtesseract_avx512_la_CXXFLAGS = -mavx512f\nlibtesseract_avx512_la_CXXFLAGS += -I$(top_srcdir)/src/ccutil\nlibtesseract_avx512_la_SOURCES = src/arch/dotproductavx512.cpp\nlibtesseract_la_LIBADD += libtesseract_avx512.la\nnoinst_LTLIBRARIES += libtesseract_avx512.la\nendif\n\nif HAVE_FMA\nlibtesseract_fma_la_CXXFLAGS = -mfma\nlibtesseract_fma_la_CXXFLAGS += -I$(top_srcdir)/src/ccutil\nlibtesseract_fma_la_SOURCES = src/arch/dotproductfma.cpp\nlibtesseract_la_LIBADD += libtesseract_fma.la\nnoinst_LTLIBRARIES += libtesseract_fma.la\nendif\n\nif HAVE_SSE4_1\nlibtesseract_sse_la_CXXFLAGS = -msse4.1\nlibtesseract_sse_la_CXXFLAGS += -I$(top_srcdir)/src/ccutil\nlibtesseract_sse_la_SOURCES = src/arch/dotproductsse.cpp src/arch/intsimdmatrixsse.cpp\nlibtesseract_la_LIBADD += libtesseract_sse.la\nnoinst_LTLIBRARIES += libtesseract_sse.la\nendif\n\nif HAVE_NEON\nlibtesseract_neon_la_CXXFLAGS = $(NEON_CXXFLAGS)\nlibtesseract_neon_la_CXXFLAGS += -O3\nif OPENMP_SIMD\nlibtesseract_neon_la_CXXFLAGS += -fopenmp-simd -DOPENMP_SIMD\nendif\nlibtesseract_neon_la_CXXFLAGS += -I$(top_srcdir)/src/ccutil\nlibtesseract_neon_la_SOURCES = src/arch/intsimdmatrixneon.cpp\nlibtesseract_neon_la_SOURCES += src/arch/dotproductneon.cpp\nlibtesseract_la_LIBADD += libtesseract_neon.la\nnoinst_LTLIBRARIES += libtesseract_neon.la\nendif\n\nif HAVE_RVV\nlibtesseract_rvv_la_CXXFLAGS = $(RVV_CXXFLAGS)\nlibtesseract_rvv_la_CXXFLAGS += -O3\nlibtesseract_rvv_la_CXXFLAGS += -I$(top_srcdir)/src/ccutil\nlibtesseract_rvv_la_SOURCES = src/arch/intsimdmatrixrvv.cpp\nlibtesseract_la_LIBADD += libtesseract_rvv.la\nnoinst_LTLIBRARIES += libtesseract_rvv.la\nendif\n\nlibtesseract_la_SOURCES += src/arch/intsimdmatrix.cpp\nlibtesseract_la_SOURCES += src/arch/simddetect.cpp\n\n# Rules for src/ccmain.\n\nnoinst_HEADERS += src/ccmain/control.h\nnoinst_HEADERS += src/ccmain/mutableiterator.h\nnoinst_HEADERS += src/ccmain/output.h\nnoinst_HEADERS += src/ccmain/paragraphs.h\nnoinst_HEADERS += src/ccmain/paragraphs_internal.h\nnoinst_HEADERS += src/ccmain/paramsd.h\nnoinst_HEADERS += src/ccmain/pgedit.h\nnoinst_HEADERS += src/ccmain/tesseractclass.h\nnoinst_HEADERS += src/ccmain/tessvars.h\nnoinst_HEADERS += src/ccmain/thresholder.h\nnoinst_HEADERS += src/ccmain/werdit.h\nif !DISABLED_LEGACY_ENGINE\nnoinst_HEADERS += src/ccmain/docqual.h\nnoinst_HEADERS += src/ccmain/equationdetect.h\nnoinst_HEADERS += src/ccmain/fixspace.h\nnoinst_HEADERS += src/ccmain/reject.h\nendif\n\nlibtesseract_la_SOURCES += src/ccmain/applybox.cpp\nlibtesseract_la_SOURCES += src/ccmain/control.cpp\nlibtesseract_la_SOURCES += src/ccmain/linerec.cpp\nlibtesseract_la_SOURCES += src/ccmain/ltrresultiterator.cpp\nlibtesseract_la_SOURCES += src/ccmain/mutableiterator.cpp\nlibtesseract_la_SOURCES += src/ccmain/output.cpp\nlibtesseract_la_SOURCES += src/ccmain/pageiterator.cpp\nlibtesseract_la_SOURCES += src/ccmain/pagesegmain.cpp\nlibtesseract_la_SOURCES += src/ccmain/pagewalk.cpp\nlibtesseract_la_SOURCES += src/ccmain/paragraphs.cpp\nif !GRAPHICS_DISABLED\nlibtesseract_la_SOURCES += src/ccmain/paramsd.cpp\nlibtesseract_la_SOURCES += src/ccmain/pgedit.cpp\nendif\nlibtesseract_la_SOURCES += src/ccmain/reject.cpp\nlibtesseract_la_SOURCES += src/ccmain/resultiterator.cpp\nlibtesseract_la_SOURCES += src/ccmain/tessedit.cpp\nlibtesseract_la_SOURCES += src/ccmain/tesseractclass.cpp\nlibtesseract_la_SOURCES += src/ccmain/tessvars.cpp\nlibtesseract_la_SOURCES += src/ccmain/thresholder.cpp\nlibtesseract_la_SOURCES += src/ccmain/werdit.cpp\nif !DISABLED_LEGACY_ENGINE\nlibtesseract_la_SOURCES += src/ccmain/adaptions.cpp\nlibtesseract_la_SOURCES += src/ccmain/docqual.cpp\nlibtesseract_la_SOURCES += src/ccmain/equationdetect.cpp\nlibtesseract_la_SOURCES += src/ccmain/fixspace.cpp\nlibtesseract_la_SOURCES += src/ccmain/fixxht.cpp\nlibtesseract_la_SOURCES += src/ccmain/osdetect.cpp\nlibtesseract_la_SOURCES += src/ccmain/par_control.cpp\nlibtesseract_la_SOURCES += src/ccmain/recogtraining.cpp\nlibtesseract_la_SOURCES += src/ccmain/superscript.cpp\nlibtesseract_la_SOURCES += src/ccmain/tessbox.cpp\nlibtesseract_la_SOURCES += src/ccmain/tfacepp.cpp\nendif\n\n# Rules for src/ccstruct.\n\nnoinst_HEADERS += src/ccstruct/blamer.h\nnoinst_HEADERS += src/ccstruct/blobbox.h\nnoinst_HEADERS += src/ccstruct/blobs.h\nnoinst_HEADERS += src/ccstruct/blread.h\nnoinst_HEADERS += src/ccstruct/boxread.h\nnoinst_HEADERS += src/ccstruct/boxword.h\nnoinst_HEADERS += src/ccstruct/ccstruct.h\nnoinst_HEADERS += src/ccstruct/coutln.h\nnoinst_HEADERS += src/ccstruct/crakedge.h\nnoinst_HEADERS += src/ccstruct/debugpixa.h\nnoinst_HEADERS += src/ccstruct/detlinefit.h\nnoinst_HEADERS += src/ccstruct/dppoint.h\nnoinst_HEADERS += src/ccstruct/image.h\nnoinst_HEADERS += src/ccstruct/imagedata.h\nnoinst_HEADERS += src/ccstruct/linlsq.h\nnoinst_HEADERS += src/ccstruct/matrix.h\nnoinst_HEADERS += src/ccstruct/mod128.h\nnoinst_HEADERS += src/ccstruct/normalis.h\nnoinst_HEADERS += src/ccstruct/ocrblock.h\nnoinst_HEADERS += src/ccstruct/ocrpara.h\nnoinst_HEADERS += src/ccstruct/ocrrow.h\nnoinst_HEADERS += src/ccstruct/otsuthr.h\nnoinst_HEADERS += src/ccstruct/pageres.h\nnoinst_HEADERS += src/ccstruct/pdblock.h\nnoinst_HEADERS += src/ccstruct/points.h\nnoinst_HEADERS += src/ccstruct/polyaprx.h\nnoinst_HEADERS += src/ccstruct/polyblk.h\nnoinst_HEADERS += src/ccstruct/quadlsq.h\nnoinst_HEADERS += src/ccstruct/quadratc.h\nnoinst_HEADERS += src/ccstruct/quspline.h\nnoinst_HEADERS += src/ccstruct/ratngs.h\nnoinst_HEADERS += src/ccstruct/rect.h\nnoinst_HEADERS += src/ccstruct/rejctmap.h\nnoinst_HEADERS += src/ccstruct/seam.h\nnoinst_HEADERS += src/ccstruct/split.h\nnoinst_HEADERS += src/ccstruct/statistc.h\nnoinst_HEADERS += src/ccstruct/stepblob.h\nnoinst_HEADERS += src/ccstruct/werd.h\nif !DISABLED_LEGACY_ENGINE\nnoinst_HEADERS += src/ccstruct/fontinfo.h\nnoinst_HEADERS += src/ccstruct/params_training_featdef.h\nendif\n\nlibtesseract_la_SOURCES += src/ccstruct/blamer.cpp\nlibtesseract_la_SOURCES += src/ccstruct/blobbox.cpp\nlibtesseract_la_SOURCES += src/ccstruct/blobs.cpp\nlibtesseract_la_SOURCES += src/ccstruct/blread.cpp\nlibtesseract_la_SOURCES += src/ccstruct/boxread.cpp\nlibtesseract_la_SOURCES += src/ccstruct/boxword.cpp\nlibtesseract_la_SOURCES += src/ccstruct/ccstruct.cpp\nlibtesseract_la_SOURCES += src/ccstruct/coutln.cpp\nlibtesseract_la_SOURCES += src/ccstruct/detlinefit.cpp\nlibtesseract_la_SOURCES += src/ccstruct/dppoint.cpp\nlibtesseract_la_SOURCES += src/ccstruct/image.cpp\nlibtesseract_la_SOURCES += src/ccstruct/imagedata.cpp\nlibtesseract_la_SOURCES += src/ccstruct/linlsq.cpp\nlibtesseract_la_SOURCES += src/ccstruct/matrix.cpp\nlibtesseract_la_SOURCES += src/ccstruct/mod128.cpp\nlibtesseract_la_SOURCES += src/ccstruct/normalis.cpp\nlibtesseract_la_SOURCES += src/ccstruct/ocrblock.cpp\nlibtesseract_la_SOURCES += src/ccstruct/ocrpara.cpp\nlibtesseract_la_SOURCES += src/ccstruct/ocrrow.cpp\nlibtesseract_la_SOURCES += src/ccstruct/otsuthr.cpp\nlibtesseract_la_SOURCES += src/ccstruct/pageres.cpp\nlibtesseract_la_SOURCES += src/ccstruct/pdblock.cpp\nlibtesseract_la_SOURCES += src/ccstruct/points.cpp\nlibtesseract_la_SOURCES += src/ccstruct/polyaprx.cpp\nlibtesseract_la_SOURCES += src/ccstruct/polyblk.cpp\nlibtesseract_la_SOURCES += src/ccstruct/quadlsq.cpp\nlibtesseract_la_SOURCES += src/ccstruct/quspline.cpp\nlibtesseract_la_SOURCES += src/ccstruct/ratngs.cpp\nlibtesseract_la_SOURCES += src/ccstruct/rect.cpp\nlibtesseract_la_SOURCES += src/ccstruct/rejctmap.cpp\nlibtesseract_la_SOURCES += src/ccstruct/seam.cpp\nlibtesseract_la_SOURCES += src/ccstruct/split.cpp\nlibtesseract_la_SOURCES += src/ccstruct/statistc.cpp\nlibtesseract_la_SOURCES += src/ccstruct/stepblob.cpp\nlibtesseract_la_SOURCES += src/ccstruct/werd.cpp\n\nif !DISABLED_LEGACY_ENGINE\nlibtesseract_la_SOURCES += src/ccstruct/fontinfo.cpp\nlibtesseract_la_SOURCES += src/ccstruct/params_training_featdef.cpp\nendif\n\n# Rules for src/ccutil\n\nlibtesseract_ccutil_la_CPPFLAGS = $(AM_CPPFLAGS)\nlibtesseract_ccutil_la_CPPFLAGS += $(libarchive_CFLAGS)\nif !NO_TESSDATA_PREFIX\nlibtesseract_ccutil_la_CPPFLAGS += -DTESSDATA_PREFIX='\"@datadir@\"'\nendif\n\nnoinst_HEADERS += src/ccutil/ccutil.h\nnoinst_HEADERS += src/ccutil/clst.h\nnoinst_HEADERS += src/ccutil/elst2.h\nnoinst_HEADERS += src/ccutil/elst.h\nnoinst_HEADERS += src/ccutil/errcode.h\nnoinst_HEADERS += src/ccutil/fileerr.h\nnoinst_HEADERS += src/ccutil/genericheap.h\nnoinst_HEADERS += src/ccutil/genericvector.h\nnoinst_HEADERS += src/ccutil/helpers.h\nnoinst_HEADERS += src/ccutil/host.h\nnoinst_HEADERS += src/ccutil/kdpair.h\nnoinst_HEADERS += src/ccutil/lsterr.h\nnoinst_HEADERS += src/ccutil/object_cache.h\nnoinst_HEADERS += src/ccutil/params.h\nnoinst_HEADERS += src/ccutil/qrsequence.h\nnoinst_HEADERS += src/ccutil/sorthelper.h\nnoinst_HEADERS += src/ccutil/scanutils.h\nnoinst_HEADERS += src/ccutil/serialis.h\nnoinst_HEADERS += src/ccutil/tessdatamanager.h\nnoinst_HEADERS += src/ccutil/tprintf.h\nnoinst_HEADERS += src/ccutil/unicharcompress.h\nnoinst_HEADERS += src/ccutil/unicharmap.h\nnoinst_HEADERS += src/ccutil/unicharset.h\nnoinst_HEADERS += src/ccutil/unicity_table.h\nif !DISABLED_LEGACY_ENGINE\nnoinst_HEADERS += src/ccutil/ambigs.h\nnoinst_HEADERS += src/ccutil/bitvector.h\nnoinst_HEADERS += src/ccutil/indexmapbidi.h\nnoinst_HEADERS += src/ccutil/universalambigs.h\nendif\n\nnoinst_LTLIBRARIES += libtesseract_ccutil.la\n\nlibtesseract_ccutil_la_SOURCES = src/ccutil/ccutil.cpp\nlibtesseract_ccutil_la_SOURCES += src/ccutil/errcode.cpp\nlibtesseract_ccutil_la_SOURCES += src/ccutil/serialis.cpp\nlibtesseract_ccutil_la_SOURCES += src/ccutil/scanutils.cpp\nlibtesseract_ccutil_la_SOURCES += src/ccutil/tessdatamanager.cpp\nlibtesseract_ccutil_la_SOURCES += src/ccutil/tprintf.cpp\nlibtesseract_ccutil_la_SOURCES += src/ccutil/unichar.cpp\nlibtesseract_ccutil_la_SOURCES += src/ccutil/unicharcompress.cpp\nlibtesseract_ccutil_la_SOURCES += src/ccutil/unicharmap.cpp\nlibtesseract_ccutil_la_SOURCES += src/ccutil/unicharset.cpp\nlibtesseract_ccutil_la_SOURCES += src/ccutil/params.cpp\nif !DISABLED_LEGACY_ENGINE\nlibtesseract_ccutil_la_SOURCES += src/ccutil/ambigs.cpp\nlibtesseract_ccutil_la_SOURCES += src/ccutil/bitvector.cpp\nlibtesseract_ccutil_la_SOURCES += src/ccutil/indexmapbidi.cpp\nendif\n\n# Rules for src/classify.\n\nnoinst_HEADERS += src/classify/classify.h\nif !DISABLED_LEGACY_ENGINE\nnoinst_HEADERS += src/classify/adaptive.h\nnoinst_HEADERS += src/classify/cluster.h\nnoinst_HEADERS += src/classify/clusttool.h\nnoinst_HEADERS += src/classify/featdefs.h\nnoinst_HEADERS += src/classify/float2int.h\nnoinst_HEADERS += src/classify/fpoint.h\nnoinst_HEADERS += src/classify/intfeaturespace.h\nnoinst_HEADERS += src/classify/intfx.h\nnoinst_HEADERS += src/classify/intmatcher.h\nnoinst_HEADERS += src/classify/intproto.h\nnoinst_HEADERS += src/classify/kdtree.h\nnoinst_HEADERS += src/classify/mf.h\nnoinst_HEADERS += src/classify/mfdefs.h\nnoinst_HEADERS += src/classify/mfoutline.h\nnoinst_HEADERS += src/classify/mfx.h\nnoinst_HEADERS += src/classify/normfeat.h\nnoinst_HEADERS += src/classify/normmatch.h\nnoinst_HEADERS += src/classify/ocrfeatures.h\nnoinst_HEADERS += src/classify/outfeat.h\nnoinst_HEADERS += src/classify/picofeat.h\nnoinst_HEADERS += src/classify/protos.h\nnoinst_HEADERS += src/classify/shapeclassifier.h\nnoinst_HEADERS += src/classify/shapetable.h\nnoinst_HEADERS += src/classify/tessclassifier.h\nnoinst_HEADERS += src/classify/trainingsample.h\nendif\n\nlibtesseract_la_SOURCES += src/classify/classify.cpp\nif !DISABLED_LEGACY_ENGINE\nlibtesseract_la_SOURCES += src/classify/adaptive.cpp\nlibtesseract_la_SOURCES += src/classify/adaptmatch.cpp\nlibtesseract_la_SOURCES += src/classify/blobclass.cpp\nlibtesseract_la_SOURCES += src/classify/cluster.cpp\nlibtesseract_la_SOURCES += src/classify/clusttool.cpp\nlibtesseract_la_SOURCES += src/classify/cutoffs.cpp\nlibtesseract_la_SOURCES += src/classify/featdefs.cpp\nlibtesseract_la_SOURCES += src/classify/float2int.cpp\nlibtesseract_la_SOURCES += src/classify/fpoint.cpp\nlibtesseract_la_SOURCES += src/classify/intfeaturespace.cpp\nlibtesseract_la_SOURCES += src/classify/intfx.cpp\nlibtesseract_la_SOURCES += src/classify/intmatcher.cpp\nlibtesseract_la_SOURCES += src/classify/intproto.cpp\nlibtesseract_la_SOURCES += src/classify/kdtree.cpp\nlibtesseract_la_SOURCES += src/classify/mf.cpp\nlibtesseract_la_SOURCES += src/classify/mfoutline.cpp\nlibtesseract_la_SOURCES += src/classify/mfx.cpp\nlibtesseract_la_SOURCES += src/classify/normfeat.cpp\nlibtesseract_la_SOURCES += src/classify/normmatch.cpp\nlibtesseract_la_SOURCES += src/classify/ocrfeatures.cpp\nlibtesseract_la_SOURCES += src/classify/outfeat.cpp\nlibtesseract_la_SOURCES += src/classify/picofeat.cpp\nlibtesseract_la_SOURCES += src/classify/protos.cpp\nlibtesseract_la_SOURCES += src/classify/shapeclassifier.cpp\nlibtesseract_la_SOURCES += src/classify/shapetable.cpp\nlibtesseract_la_SOURCES += src/classify/tessclassifier.cpp\nlibtesseract_la_SOURCES += src/classify/trainingsample.cpp\nendif\n\n# Rules for src/cutil.\n\nif !DISABLED_LEGACY_ENGINE\nnoinst_HEADERS += src/cutil/bitvec.h\nnoinst_HEADERS += src/cutil/oldlist.h\nendif\n\nif !DISABLED_LEGACY_ENGINE\nlibtesseract_la_SOURCES += src/cutil/oldlist.cpp\nendif\n\n# Rules for src/dict.\n\nnoinst_HEADERS += src/dict/dawg.h\nnoinst_HEADERS += src/dict/dawg_cache.h\nnoinst_HEADERS += src/dict/dict.h\nnoinst_HEADERS += src/dict/matchdefs.h\nnoinst_HEADERS += src/dict/stopper.h\nnoinst_HEADERS += src/dict/trie.h\n\nlibtesseract_la_SOURCES += src/dict/context.cpp\nlibtesseract_la_SOURCES += src/dict/dawg.cpp\nlibtesseract_la_SOURCES += src/dict/dawg_cache.cpp\nlibtesseract_la_SOURCES += src/dict/dict.cpp\nlibtesseract_la_SOURCES += src/dict/stopper.cpp\nlibtesseract_la_SOURCES += src/dict/trie.cpp\nif !DISABLED_LEGACY_ENGINE\nlibtesseract_la_SOURCES += src/dict/hyphen.cpp\nlibtesseract_la_SOURCES += src/dict/permdawg.cpp\nendif\n\n# Rules for src/lstm.\n\nlibtesseract_lstm_la_CPPFLAGS = $(AM_CPPFLAGS)\nlibtesseract_lstm_la_CPPFLAGS += -I$(top_srcdir)/src/arch\nlibtesseract_lstm_la_CPPFLAGS += -I$(top_srcdir)/src/ccstruct\nlibtesseract_lstm_la_CPPFLAGS += -I$(top_srcdir)/src/ccutil\nlibtesseract_lstm_la_CPPFLAGS += -I$(top_srcdir)/src/classify\nlibtesseract_lstm_la_CPPFLAGS += -I$(top_srcdir)/src/cutil\nlibtesseract_lstm_la_CPPFLAGS += -I$(top_srcdir)/src/dict\nlibtesseract_lstm_la_CPPFLAGS += -I$(top_srcdir)/src/lstm\nlibtesseract_lstm_la_CPPFLAGS += -I$(top_srcdir)/src/viewer\nif !NO_TESSDATA_PREFIX\nlibtesseract_lstm_la_CPPFLAGS += -DTESSDATA_PREFIX='\"@datadir@\"'\nendif\n\nnoinst_HEADERS += src/lstm/convolve.h\nnoinst_HEADERS += src/lstm/fullyconnected.h\nnoinst_HEADERS += src/lstm/functions.h\nnoinst_HEADERS += src/lstm/input.h\nnoinst_HEADERS += src/lstm/lstm.h\nnoinst_HEADERS += src/lstm/lstmrecognizer.h\nnoinst_HEADERS += src/lstm/maxpool.h\nnoinst_HEADERS += src/lstm/network.h\nnoinst_HEADERS += src/lstm/networkio.h\nnoinst_HEADERS += src/lstm/networkscratch.h\nnoinst_HEADERS += src/lstm/parallel.h\nnoinst_HEADERS += src/lstm/plumbing.h\nnoinst_HEADERS += src/lstm/recodebeam.h\nnoinst_HEADERS += src/lstm/reconfig.h\nnoinst_HEADERS += src/lstm/reversed.h\nnoinst_HEADERS += src/lstm/series.h\nnoinst_HEADERS += src/lstm/static_shape.h\nnoinst_HEADERS += src/lstm/stridemap.h\nnoinst_HEADERS += src/lstm/weightmatrix.h\n\nnoinst_LTLIBRARIES += libtesseract_lstm.la\n\nlibtesseract_lstm_la_SOURCES = src/lstm/convolve.cpp\nlibtesseract_lstm_la_SOURCES += src/lstm/fullyconnected.cpp\nlibtesseract_lstm_la_SOURCES += src/lstm/functions.cpp\nlibtesseract_lstm_la_SOURCES += src/lstm/input.cpp\nlibtesseract_lstm_la_SOURCES += src/lstm/lstm.cpp\nlibtesseract_lstm_la_SOURCES += src/lstm/lstmrecognizer.cpp\nlibtesseract_lstm_la_SOURCES += src/lstm/maxpool.cpp\nlibtesseract_lstm_la_SOURCES += src/lstm/network.cpp\nlibtesseract_lstm_la_SOURCES += src/lstm/networkio.cpp\nlibtesseract_lstm_la_SOURCES += src/lstm/parallel.cpp\nlibtesseract_lstm_la_SOURCES += src/lstm/plumbing.cpp\nlibtesseract_lstm_la_SOURCES += src/lstm/recodebeam.cpp\nlibtesseract_lstm_la_SOURCES += src/lstm/reconfig.cpp\nlibtesseract_lstm_la_SOURCES += src/lstm/reversed.cpp\nlibtesseract_lstm_la_SOURCES += src/lstm/series.cpp\nlibtesseract_lstm_la_SOURCES += src/lstm/stridemap.cpp\nlibtesseract_lstm_la_SOURCES += src/lstm/weightmatrix.cpp\n\n# Rules for src/textord.\n\nnoinst_HEADERS += src/textord/alignedblob.h\nnoinst_HEADERS += src/textord/baselinedetect.h\nnoinst_HEADERS += src/textord/bbgrid.h\nnoinst_HEADERS += src/textord/blkocc.h\nnoinst_HEADERS += src/textord/blobgrid.h\nnoinst_HEADERS += src/textord/ccnontextdetect.h\nnoinst_HEADERS += src/textord/cjkpitch.h\nnoinst_HEADERS += src/textord/colfind.h\nnoinst_HEADERS += src/textord/colpartition.h\nnoinst_HEADERS += src/textord/colpartitionset.h\nnoinst_HEADERS += src/textord/colpartitiongrid.h\nnoinst_HEADERS += src/textord/devanagari_processing.h\nnoinst_HEADERS += src/textord/drawtord.h\nnoinst_HEADERS += src/textord/edgblob.h\nnoinst_HEADERS += src/textord/edgloop.h\nnoinst_HEADERS += src/textord/fpchop.h\nnoinst_HEADERS += src/textord/gap_map.h\nnoinst_HEADERS += src/textord/imagefind.h\nnoinst_HEADERS += src/textord/linefind.h\nnoinst_HEADERS += src/textord/makerow.h\nnoinst_HEADERS += src/textord/oldbasel.h\nnoinst_HEADERS += src/textord/pithsync.h\nnoinst_HEADERS += src/textord/pitsync1.h\nnoinst_HEADERS += src/textord/scanedg.h\nnoinst_HEADERS += src/textord/sortflts.h\nnoinst_HEADERS += src/textord/strokewidth.h\nnoinst_HEADERS += src/textord/tabfind.h\nnoinst_HEADERS += src/textord/tablefind.h\nnoinst_HEADERS += src/textord/tabvector.h\nnoinst_HEADERS += src/textord/tablerecog.h\nnoinst_HEADERS += src/textord/textlineprojection.h\nnoinst_HEADERS += src/textord/textord.h\nnoinst_HEADERS += src/textord/topitch.h\nnoinst_HEADERS += src/textord/tordmain.h\nnoinst_HEADERS += src/textord/tovars.h\nnoinst_HEADERS += src/textord/underlin.h\nnoinst_HEADERS += src/textord/wordseg.h\nnoinst_HEADERS += src/textord/workingpartset.h\nif !DISABLED_LEGACY_ENGINE\nnoinst_HEADERS += src/textord/equationdetectbase.h\nendif\n\nlibtesseract_la_SOURCES += src/textord/alignedblob.cpp\nlibtesseract_la_SOURCES += src/textord/baselinedetect.cpp\nlibtesseract_la_SOURCES += src/textord/bbgrid.cpp\nlibtesseract_la_SOURCES += src/textord/blkocc.cpp\nlibtesseract_la_SOURCES += src/textord/blobgrid.cpp\nlibtesseract_la_SOURCES += src/textord/ccnontextdetect.cpp\nlibtesseract_la_SOURCES += src/textord/cjkpitch.cpp\nlibtesseract_la_SOURCES += src/textord/colfind.cpp\nlibtesseract_la_SOURCES += src/textord/colpartition.cpp\nlibtesseract_la_SOURCES += src/textord/colpartitionset.cpp\nlibtesseract_la_SOURCES += src/textord/colpartitiongrid.cpp\nlibtesseract_la_SOURCES += src/textord/devanagari_processing.cpp\nlibtesseract_la_SOURCES += src/textord/drawtord.cpp\nlibtesseract_la_SOURCES += src/textord/edgblob.cpp\nlibtesseract_la_SOURCES += src/textord/edgloop.cpp\nlibtesseract_la_SOURCES += src/textord/fpchop.cpp\nlibtesseract_la_SOURCES += src/textord/gap_map.cpp\nlibtesseract_la_SOURCES += src/textord/imagefind.cpp\nlibtesseract_la_SOURCES += src/textord/linefind.cpp\nlibtesseract_la_SOURCES += src/textord/makerow.cpp\nlibtesseract_la_SOURCES += src/textord/oldbasel.cpp\nlibtesseract_la_SOURCES += src/textord/pithsync.cpp\nlibtesseract_la_SOURCES += src/textord/pitsync1.cpp\nlibtesseract_la_SOURCES += src/textord/scanedg.cpp\nlibtesseract_la_SOURCES += src/textord/sortflts.cpp\nlibtesseract_la_SOURCES += src/textord/strokewidth.cpp\nlibtesseract_la_SOURCES += src/textord/tabfind.cpp\nlibtesseract_la_SOURCES += src/textord/tablefind.cpp\nlibtesseract_la_SOURCES += src/textord/tabvector.cpp\nlibtesseract_la_SOURCES += src/textord/tablerecog.cpp\nlibtesseract_la_SOURCES += src/textord/textlineprojection.cpp\nlibtesseract_la_SOURCES += src/textord/textord.cpp\nlibtesseract_la_SOURCES += src/textord/topitch.cpp\nlibtesseract_la_SOURCES += src/textord/tordmain.cpp\nlibtesseract_la_SOURCES += src/textord/tospace.cpp\nlibtesseract_la_SOURCES += src/textord/tovars.cpp\nlibtesseract_la_SOURCES += src/textord/underlin.cpp\nlibtesseract_la_SOURCES += src/textord/wordseg.cpp\nlibtesseract_la_SOURCES += src/textord/workingpartset.cpp\nif !DISABLED_LEGACY_ENGINE\nlibtesseract_la_SOURCES += src/textord/equationdetectbase.cpp\nendif\n\n# Rules for src/viewer.\n\nif !GRAPHICS_DISABLED\nnoinst_HEADERS += src/viewer/scrollview.h\nnoinst_HEADERS += src/viewer/svmnode.h\nnoinst_HEADERS += src/viewer/svutil.h\n\nlibtesseract_la_SOURCES += src/viewer/scrollview.cpp\nlibtesseract_la_SOURCES += src/viewer/svmnode.cpp\nlibtesseract_la_SOURCES += src/viewer/svutil.cpp\n\nEXTRA_PROGRAMS += svpaint\nsvpaint_CPPFLAGS = $(AM_CPPFLAGS)\nsvpaint_CPPFLAGS += -I$(top_srcdir)/src/ccstruct\nsvpaint_CPPFLAGS += -I$(top_srcdir)/src/viewer\nsvpaint_SOURCES = src/svpaint.cpp\nsvpaint_LDADD = libtesseract.la\nendif\n\n# Rules for src/wordrec.\n\nnoinst_HEADERS += src/wordrec/wordrec.h\nif !DISABLED_LEGACY_ENGINE\nnoinst_HEADERS += src/wordrec/associate.h\nnoinst_HEADERS += src/wordrec/chop.h\nnoinst_HEADERS += src/wordrec/drawfx.h\nnoinst_HEADERS += src/wordrec/findseam.h\nnoinst_HEADERS += src/wordrec/language_model.h\nnoinst_HEADERS += src/wordrec/lm_consistency.h\nnoinst_HEADERS += src/wordrec/lm_pain_points.h\nnoinst_HEADERS += src/wordrec/lm_state.h\nnoinst_HEADERS += src/wordrec/outlines.h\nnoinst_HEADERS += src/wordrec/params_model.h\nnoinst_HEADERS += src/wordrec/plotedges.h\nnoinst_HEADERS += src/wordrec/render.h\nendif\n\nlibtesseract_la_SOURCES += src/wordrec/tface.cpp\nlibtesseract_la_SOURCES += src/wordrec/wordrec.cpp\nif !DISABLED_LEGACY_ENGINE\nlibtesseract_la_SOURCES += src/wordrec/associate.cpp\nlibtesseract_la_SOURCES += src/wordrec/chop.cpp\nlibtesseract_la_SOURCES += src/wordrec/chopper.cpp\nlibtesseract_la_SOURCES += src/wordrec/drawfx.cpp\nlibtesseract_la_SOURCES += src/wordrec/findseam.cpp\nlibtesseract_la_SOURCES += src/wordrec/gradechop.cpp\nlibtesseract_la_SOURCES += src/wordrec/language_model.cpp\nlibtesseract_la_SOURCES += src/wordrec/lm_consistency.cpp\nlibtesseract_la_SOURCES += src/wordrec/lm_pain_points.cpp\nlibtesseract_la_SOURCES += src/wordrec/lm_state.cpp\nlibtesseract_la_SOURCES += src/wordrec/outlines.cpp\nlibtesseract_la_SOURCES += src/wordrec/params_model.cpp\nlibtesseract_la_SOURCES += src/wordrec/pieces.cpp\nif !GRAPHICS_DISABLED\nlibtesseract_la_SOURCES += src/wordrec/plotedges.cpp\nendif\nlibtesseract_la_SOURCES += src/wordrec/render.cpp\nlibtesseract_la_SOURCES += src/wordrec/segsearch.cpp\nlibtesseract_la_SOURCES += src/wordrec/wordclass.cpp\nendif\n\n# Rules for tesseract executable.\n\nbin_PROGRAMS = tesseract\ntesseract_SOURCES = src/tesseract.cpp\ntesseract_CPPFLAGS = $(AM_CPPFLAGS)\ntesseract_CPPFLAGS += -I$(top_srcdir)/src/arch\ntesseract_CPPFLAGS += -I$(top_srcdir)/src/ccmain\ntesseract_CPPFLAGS += -I$(top_srcdir)/src/ccstruct\ntesseract_CPPFLAGS += -I$(top_srcdir)/src/ccutil\ntesseract_CPPFLAGS += -I$(top_srcdir)/src/classify\ntesseract_CPPFLAGS += -I$(top_srcdir)/src/cutil\ntesseract_CPPFLAGS += -I$(top_srcdir)/src/dict\ntesseract_CPPFLAGS += -I$(top_srcdir)/src/textord\ntesseract_CPPFLAGS += -I$(top_srcdir)/src/viewer\ntesseract_CPPFLAGS += -I$(top_srcdir)/src/wordrec\n\ntesseract_LDFLAGS = $(OPENMP_CXXFLAGS)\n\ntesseract_LDADD = libtesseract.la\ntesseract_LDADD += $(LEPTONICA_LIBS)\ntesseract_LDADD += $(libarchive_LIBS)\ntesseract_LDADD += $(libcurl_LIBS)\n\nif T_WIN\ntesseract_LDADD += -ltiff\ntesseract_LDADD += -lws2_32\nendif\nif ADD_RT\ntesseract_LDADD += -lrt\nendif\n\n# Rules for training tools.\n\nif ENABLE_TRAINING\n\ntraining: $(trainingtools) | $(PROGRAMS)\n\ntraining-install: $(trainingtools)\n\tmkdir -p $(DESTDIR)$(bindir)\n\t$(LIBTOOL) $(AM_LIBTOOLFLAGS) $(LIBTOOLFLAGS) --mode=install \\\n\t$(INSTALL) $(INSTALL_STRIP_FLAG) $(trainingtools) $(DESTDIR)$(bindir)\n\ntraining-uninstall:\n\n# Some unit tests use code from training.\ncheck: libtesseract_training.la\n\n# dawg_test runs dawg2wordlist and wordlist2dawg.\ncheck: dawg2wordlist wordlist2dawg\n\nelse\n\ntraining:\n\t@echo \"Need to reconfigure project, so there are no errors\"\n\nendif\n\nCLEANFILES += $(EXTRA_PROGRAMS)\n\ntraining_CPPFLAGS = $(AM_CPPFLAGS)\ntraining_CPPFLAGS += -DPANGO_ENABLE_ENGINE\ntraining_CPPFLAGS += -DTESS_COMMON_TRAINING_API=\ntraining_CPPFLAGS += -DTESS_PANGO_TRAINING_API=\ntraining_CPPFLAGS += -DTESS_UNICHARSET_TRAINING_API=\ntraining_CPPFLAGS += -I$(top_srcdir)/src/training\ntraining_CPPFLAGS += -I$(top_srcdir)/src/training/common\ntraining_CPPFLAGS += -I$(top_srcdir)/src/training/pango\ntraining_CPPFLAGS += -I$(top_srcdir)/src/training/unicharset\ntraining_CPPFLAGS += -I$(top_srcdir)/src/api\ntraining_CPPFLAGS += -I$(top_srcdir)/src/ccmain\ntraining_CPPFLAGS += -I$(top_srcdir)/src/ccutil\ntraining_CPPFLAGS += -I$(top_srcdir)/src/ccstruct\ntraining_CPPFLAGS += -I$(top_srcdir)/src/lstm\ntraining_CPPFLAGS += -I$(top_srcdir)/src/arch\ntraining_CPPFLAGS += -I$(top_srcdir)/src/viewer\ntraining_CPPFLAGS += -I$(top_srcdir)/src/textord\ntraining_CPPFLAGS += -I$(top_srcdir)/src/dict\ntraining_CPPFLAGS += -I$(top_srcdir)/src/classify\ntraining_CPPFLAGS += -I$(top_srcdir)/src/wordrec\ntraining_CPPFLAGS += -I$(top_srcdir)/src/cutil\ntraining_CPPFLAGS += $(ICU_UC_CFLAGS) $(ICU_I18N_CFLAGS)\ntraining_CPPFLAGS += $(pango_CFLAGS)\ntraining_CPPFLAGS += $(cairo_CFLAGS)\n\nif DISABLED_LEGACY_ENGINE\ntraining_CPPFLAGS += -DDISABLED_LEGACY_ENGINE\nendif\n\n# TODO: training programs cannot be linked to shared library created\n# with -fvisibility\nif VISIBILITY\nAM_LDFLAGS += -all-static\nendif\n\nnoinst_HEADERS += src/training/pango/boxchar.h\nnoinst_HEADERS += src/training/common/commandlineflags.h\nnoinst_HEADERS += src/training/common/commontraining.h\nnoinst_HEADERS += src/training/common/ctc.h\nnoinst_HEADERS += src/training/common/networkbuilder.h\nnoinst_HEADERS += src/training/degradeimage.h\nnoinst_HEADERS += src/training/pango/ligature_table.h\nnoinst_HEADERS += src/training/pango/pango_font_info.h\nnoinst_HEADERS += src/training/pango/stringrenderer.h\nnoinst_HEADERS += src/training/pango/tlog.h\nnoinst_HEADERS += src/training/unicharset/icuerrorcode.h\nnoinst_HEADERS += src/training/unicharset/fileio.h\nnoinst_HEADERS += src/training/unicharset/lang_model_helpers.h\nnoinst_HEADERS += src/training/unicharset/lstmtester.h\nnoinst_HEADERS += src/training/unicharset/lstmtrainer.h\nnoinst_HEADERS += src/training/unicharset/normstrngs.h\nnoinst_HEADERS += src/training/unicharset/unicharset_training_utils.h\nnoinst_HEADERS += src/training/unicharset/validate_grapheme.h\nnoinst_HEADERS += src/training/unicharset/validate_indic.h\nnoinst_HEADERS += src/training/unicharset/validate_javanese.h\nnoinst_HEADERS += src/training/unicharset/validate_khmer.h\nnoinst_HEADERS += src/training/unicharset/validate_myanmar.h\nnoinst_HEADERS += src/training/unicharset/validator.h\nif !DISABLED_LEGACY_ENGINE\nnoinst_HEADERS += src/training/common/errorcounter.h\nnoinst_HEADERS += src/training/common/intfeaturedist.h\nnoinst_HEADERS += src/training/common/intfeaturemap.h\nnoinst_HEADERS += src/training/common/mastertrainer.h\nnoinst_HEADERS += src/training/common/sampleiterator.h\nnoinst_HEADERS += src/training/common/trainingsampleset.h\nnoinst_HEADERS += src/training/mergenf.h\nendif\n\nCLEANFILES += libtesseract_training.la\n\nEXTRA_LTLIBRARIES = libtesseract_training.la\n\nlibtesseract_training_la_CPPFLAGS = $(training_CPPFLAGS)\nlibtesseract_training_la_SOURCES = src/training/pango/boxchar.cpp\nlibtesseract_training_la_SOURCES += src/training/common/commandlineflags.cpp\nlibtesseract_training_la_SOURCES += src/training/common/commontraining.cpp\nlibtesseract_training_la_SOURCES += src/training/common/ctc.cpp\nlibtesseract_training_la_SOURCES += src/training/common/networkbuilder.cpp\nlibtesseract_training_la_SOURCES += src/training/degradeimage.cpp\nlibtesseract_training_la_SOURCES += src/training/pango/ligature_table.cpp\nlibtesseract_training_la_SOURCES += src/training/pango/pango_font_info.cpp\nlibtesseract_training_la_SOURCES += src/training/pango/stringrenderer.cpp\nlibtesseract_training_la_SOURCES += src/training/pango/tlog.cpp\nlibtesseract_training_la_SOURCES += src/training/unicharset/icuerrorcode.cpp\nlibtesseract_training_la_SOURCES += src/training/unicharset/fileio.cpp\nlibtesseract_training_la_SOURCES += src/training/unicharset/lang_model_helpers.cpp\nlibtesseract_training_la_SOURCES += src/training/unicharset/lstmtester.cpp\nlibtesseract_training_la_SOURCES += src/training/unicharset/lstmtrainer.cpp\nlibtesseract_training_la_SOURCES += src/training/unicharset/normstrngs.cpp\nlibtesseract_training_la_SOURCES += src/training/unicharset/unicharset_training_utils.cpp\nlibtesseract_training_la_SOURCES += src/training/unicharset/validate_grapheme.cpp\nlibtesseract_training_la_SOURCES += src/training/unicharset/validate_indic.cpp\nlibtesseract_training_la_SOURCES += src/training/unicharset/validate_javanese.cpp\nlibtesseract_training_la_SOURCES += src/training/unicharset/validate_khmer.cpp\nlibtesseract_training_la_SOURCES += src/training/unicharset/validate_myanmar.cpp\nlibtesseract_training_la_SOURCES += src/training/unicharset/validator.cpp\nif !DISABLED_LEGACY_ENGINE\nlibtesseract_training_la_SOURCES += src/training/common/errorcounter.cpp\nlibtesseract_training_la_SOURCES += src/training/common/intfeaturedist.cpp\nlibtesseract_training_la_SOURCES += src/training/common/intfeaturemap.cpp\nlibtesseract_training_la_SOURCES += src/training/common/mastertrainer.cpp\nlibtesseract_training_la_SOURCES += src/training/common/sampleiterator.cpp\nlibtesseract_training_la_SOURCES += src/training/common/trainingsampleset.cpp\nendif\n\ntrainingtools = combine_lang_model$(EXEEXT)\ntrainingtools += combine_tessdata$(EXEEXT)\ntrainingtools += dawg2wordlist$(EXEEXT)\ntrainingtools += lstmeval$(EXEEXT)\ntrainingtools += lstmtraining$(EXEEXT)\ntrainingtools += merge_unicharsets$(EXEEXT)\ntrainingtools += set_unicharset_properties$(EXEEXT)\ntrainingtools += text2image$(EXEEXT)\ntrainingtools += unicharset_extractor$(EXEEXT)\ntrainingtools += wordlist2dawg$(EXEEXT)\nif !DISABLED_LEGACY_ENGINE\ntrainingtools += ambiguous_words$(EXEEXT)\ntrainingtools += classifier_tester$(EXEEXT)\ntrainingtools += cntraining$(EXEEXT)\ntrainingtools += mftraining$(EXEEXT)\ntrainingtools += shapeclustering$(EXEEXT)\nendif\n\n$(trainingtools): libtesseract.la\n\nEXTRA_PROGRAMS += $(trainingtools)\n\nextralib = libtesseract.la\nextralib += $(libarchive_LIBS)\nextralib += $(LEPTONICA_LIBS)\nif T_WIN\nextralib += -lws2_32\nendif\n\nif !DISABLED_LEGACY_ENGINE\nambiguous_words_CPPFLAGS = $(training_CPPFLAGS)\nambiguous_words_SOURCES = src/training/ambiguous_words.cpp\nambiguous_words_LDADD = libtesseract_training.la\nambiguous_words_LDADD += $(extralib)\n\nclassifier_tester_CPPFLAGS = $(training_CPPFLAGS)\nclassifier_tester_SOURCES = src/training/classifier_tester.cpp\nclassifier_tester_LDADD = libtesseract_training.la\nclassifier_tester_LDADD += $(extralib)\n\ncntraining_CPPFLAGS = $(training_CPPFLAGS)\ncntraining_SOURCES = src/training/cntraining.cpp\ncntraining_LDADD = libtesseract_training.la\ncntraining_LDADD += $(extralib)\n\nmftraining_CPPFLAGS = $(training_CPPFLAGS)\nmftraining_SOURCES = src/training/mftraining.cpp src/training/mergenf.cpp\nmftraining_LDADD = libtesseract_training.la\nmftraining_LDADD += $(ICU_UC_LIBS)\nmftraining_LDADD += $(extralib)\n\nshapeclustering_CPPFLAGS = $(training_CPPFLAGS)\nshapeclustering_SOURCES = src/training/shapeclustering.cpp\nshapeclustering_LDADD = libtesseract_training.la\nshapeclustering_LDADD += $(extralib)\nendif\n\ncombine_lang_model_CPPFLAGS = $(training_CPPFLAGS)\ncombine_lang_model_SOURCES = src/training/combine_lang_model.cpp\ncombine_lang_model_LDADD = libtesseract_training.la\ncombine_lang_model_LDADD += $(ICU_I18N_LIBS) $(ICU_UC_LIBS)\ncombine_lang_model_LDADD += $(extralib)\n\ncombine_tessdata_CPPFLAGS = $(training_CPPFLAGS)\ncombine_tessdata_SOURCES = src/training/combine_tessdata.cpp\ncombine_tessdata_LDADD = $(extralib)\n\ndawg2wordlist_CPPFLAGS = $(training_CPPFLAGS)\ndawg2wordlist_SOURCES = src/training/dawg2wordlist.cpp\ndawg2wordlist_LDADD = $(extralib)\n\nlstmeval_CPPFLAGS = $(training_CPPFLAGS)\nlstmeval_SOURCES = src/training/lstmeval.cpp\nlstmeval_LDADD = libtesseract_training.la\nlstmeval_LDADD += $(ICU_UC_LIBS)\nlstmeval_LDADD += $(extralib)\n\nlstmtraining_CPPFLAGS = $(training_CPPFLAGS)\nlstmtraining_SOURCES = src/training/lstmtraining.cpp\nlstmtraining_LDADD = libtesseract_training.la\nlstmtraining_LDADD += $(ICU_I18N_LIBS) $(ICU_UC_LIBS)\nlstmtraining_LDADD += $(extralib)\n\nmerge_unicharsets_CPPFLAGS = $(training_CPPFLAGS)\nmerge_unicharsets_SOURCES = src/training/merge_unicharsets.cpp\nmerge_unicharsets_LDADD = $(extralib)\n\nset_unicharset_properties_CPPFLAGS = $(training_CPPFLAGS)\nset_unicharset_properties_SOURCES = src/training/set_unicharset_properties.cpp\nset_unicharset_properties_LDADD = libtesseract_training.la\nset_unicharset_properties_LDADD += $(ICU_I18N_LIBS) $(ICU_UC_LIBS)\nset_unicharset_properties_LDADD += $(extralib)\n\ntext2image_CPPFLAGS = $(training_CPPFLAGS)\ntext2image_SOURCES = src/training/text2image.cpp\ntext2image_LDADD = libtesseract_training.la\ntext2image_LDADD += $(ICU_I18N_LIBS) $(ICU_UC_LIBS)\ntext2image_LDADD += $(extralib)\ntext2image_LDADD += $(ICU_UC_LIBS) $(cairo_LIBS)\ntext2image_LDADD += $(pango_LIBS) $(pangocairo_LIBS) $(pangoft2_LIBS)\n\nunicharset_extractor_CPPFLAGS = $(training_CPPFLAGS)\nunicharset_extractor_SOURCES = src/training/unicharset_extractor.cpp\nunicharset_extractor_LDADD = libtesseract_training.la\nunicharset_extractor_LDADD += $(ICU_I18N_LIBS) $(ICU_UC_LIBS)\nunicharset_extractor_LDADD += $(extralib)\n\nwordlist2dawg_CPPFLAGS = $(training_CPPFLAGS)\nwordlist2dawg_SOURCES = src/training/wordlist2dawg.cpp\nwordlist2dawg_LDADD = $(extralib)\n\n# fuzzer-api is used for fuzzing tests.\n# They are run by OSS-Fuzz https://oss-fuzz.com/, but can also be run locally.\n# Note: -fsanitize=fuzzer currently requires the clang++ compiler.\n\n# LIB_FUZZING_ENGINE can be overridden by the caller.\n# This is used by OSS-Fuzz.\nLIB_FUZZING_ENGINE ?= -fsanitize=fuzzer\n\nfuzzer-api: libtesseract.la\nfuzzer-api: unittest/fuzzers/fuzzer-api.cpp\n\t$(CXX) $(CXXFLAGS) -g $(LIB_FUZZING_ENGINE) \\\n -I $(top_srcdir)/include \\\n -I $(builddir)/include \\\n -I $(top_srcdir)/src/ccmain \\\n -I $(top_srcdir)/src/ccstruct \\\n -I $(top_srcdir)/src/ccutil \\\n $(LEPTONICA_CFLAGS) \\\n $(OPENMP_CXXFLAGS) \\\n $< \\\n $(builddir)/.libs/libtesseract.a \\\n $(LEPTONICA_LIBS) \\\n $(libarchive_LIBS) \\\n $(libcurl_LIBS) \\\n -o $@\n\nfuzzer-api-512x256: libtesseract.la\nfuzzer-api-512x256: unittest/fuzzers/fuzzer-api.cpp\n\t$(CXX) $(CXXFLAGS) -g $(LIB_FUZZING_ENGINE) \\\n -DTESSERACT_FUZZER_WIDTH=512 \\\n -DTESSERACT_FUZZER_HEIGHT=256 \\\n -I $(top_srcdir)/include \\\n -I $(builddir)/include \\\n -I $(top_srcdir)/src/ccmain \\\n -I $(top_srcdir)/src/ccstruct \\\n -I $(top_srcdir)/src/ccutil \\\n $(LEPTONICA_CFLAGS) \\\n $(OPENMP_CXXFLAGS) \\\n $< \\\n $(builddir)/.libs/libtesseract.a \\\n $(LEPTONICA_LIBS) \\\n $(libarchive_LIBS) \\\n $(libcurl_LIBS) \\\n -o $@\n\nCLEANFILES += fuzzer-api fuzzer-api-512x256\n\nif ASCIIDOC\n\nman_MANS = doc/combine_lang_model.1\nman_MANS += doc/combine_tessdata.1\nman_MANS += doc/dawg2wordlist.1\nman_MANS += doc/lstmeval.1\nman_MANS += doc/lstmtraining.1\nman_MANS += doc/merge_unicharsets.1\nman_MANS += doc/set_unicharset_properties.1\nman_MANS += doc/tesseract.1\nman_MANS += doc/text2image.1\nman_MANS += doc/unicharset.5\nman_MANS += doc/unicharset_extractor.1\nman_MANS += doc/wordlist2dawg.1\n\nif !DISABLED_LEGACY_ENGINE\nman_MANS += doc/ambiguous_words.1\nman_MANS += doc/classifier_tester.1\nman_MANS += doc/cntraining.1\nman_MANS += doc/mftraining.1\nman_MANS += doc/shapeclustering.1\nman_MANS += doc/unicharambigs.5\nendif\n\nman_xslt = http://docbook.sourceforge.net/release/xsl/current/manpages/docbook.xsl\n\nEXTRA_DIST += $(man_MANS) doc/Doxyfile\n\nhtml: ${man_MANS:%=%.html}\npdf: ${man_MANS:%=%.pdf}\n\nSUFFIXES = .asc .html .pdf\n\n.asc:\nif HAVE_XML_CATALOG_FILES\n\tasciidoc -b docbook -d manpage -o - $< | \\\n\tXML_CATALOG_FILES=$(XML_CATALOG_FILES) xsltproc --nonet -o $@ $(man_xslt) -\nelse\n\tasciidoc -b docbook -d manpage -o - $< | \\\n\txsltproc --nonet -o $@ $(man_xslt) -\nendif\n\n.asc.html:\n\tasciidoc -b html5 -o $@ $<\n\n.asc.pdf:\n\tasciidoc -b docbook -d manpage -o $*.dbk $<\n\tdocbook2pdf -o doc $*.dbk\n\nMAINTAINERCLEANFILES = $(man_MANS) Doxyfile\n\nendif\n\n# Absolute path of directory 'langdata'.\nLANGDATA_DIR=$(shell cd $(top_srcdir) && cd .. && pwd)/langdata_lstm\n\n# Absolute path of directory 'tessdata' with traineddata files\n# (must be on same level as top source directory).\nTESSDATA_DIR=$(shell cd $(top_srcdir) && cd .. && pwd)/tessdata\n\n# Absolute path of directory 'testing' with test images and ground truth texts\n# (using submodule test).\nTESTING_DIR=$(shell cd $(top_srcdir) && pwd)/test/testing\n# Absolute path of directory 'testdata' with test unicharset etc.\n# (using submodule test).\nTESTDATA_DIR=$(shell cd $(top_srcdir) && pwd)/test/testdata\n\n# Suppress some memory leaks reported by LeakSanitizer.\nexport LSAN_OPTIONS=suppressions=$(top_srcdir)/unittest/tesseract_leaksanitizer.supp\n\nunittest_CPPFLAGS = $(AM_CPPFLAGS)\nunittest_CPPFLAGS += -DTESSBIN_DIR=\"\\\"$(abs_top_builddir)\\\"\"\nunittest_CPPFLAGS += -DLANGDATA_DIR=\"\\\"$(LANGDATA_DIR)\\\"\"\nunittest_CPPFLAGS += -DTESSDATA_DIR=\"\\\"$(TESSDATA_DIR)\\\"\"\nunittest_CPPFLAGS += -DTESTING_DIR=\"\\\"$(TESTING_DIR)\\\"\"\nunittest_CPPFLAGS += -DTESTDATA_DIR=\"\\\"$(TESTDATA_DIR)\\\"\"\nunittest_CPPFLAGS += -DPANGO_ENABLE_ENGINE\nif DISABLED_LEGACY_ENGINE\nunittest_CPPFLAGS += -DDISABLED_LEGACY_ENGINE\nendif # DISABLED_LEGACY_ENGINE\nunittest_CPPFLAGS += -DTESS_COMMON_TRAINING_API=\nunittest_CPPFLAGS += -DTESS_PANGO_TRAINING_API=\nunittest_CPPFLAGS += -DTESS_UNICHARSET_TRAINING_API=\nunittest_CPPFLAGS += -I$(top_srcdir)/src/arch\nunittest_CPPFLAGS += -I$(top_srcdir)/src/ccmain\nunittest_CPPFLAGS += -I$(top_srcdir)/src/ccstruct\nunittest_CPPFLAGS += -I$(top_srcdir)/src/ccutil\nunittest_CPPFLAGS += -I$(top_srcdir)/src/classify\nunittest_CPPFLAGS += -I$(top_srcdir)/src/cutil\nunittest_CPPFLAGS += -I$(top_srcdir)/src/dict\nunittest_CPPFLAGS += -I$(top_srcdir)/src/display\nunittest_CPPFLAGS += -I$(top_srcdir)/src/lstm\nunittest_CPPFLAGS += -I$(top_srcdir)/src/textord\nunittest_CPPFLAGS += -I$(top_srcdir)/unittest/base\nunittest_CPPFLAGS += -I$(top_srcdir)/unittest/util\nunittest_CPPFLAGS += $(LEPTONICA_CFLAGS)\nif ENABLE_TRAINING\nunittest_CPPFLAGS += -I$(top_srcdir)/src/training\nunittest_CPPFLAGS += -I$(top_srcdir)/src/training/common\nunittest_CPPFLAGS += -I$(top_srcdir)/src/training/pango\nunittest_CPPFLAGS += -I$(top_srcdir)/src/training/unicharset\nunittest_CPPFLAGS += $(pangocairo_CFLAGS)\nendif # ENABLE_TRAINING\nunittest_CPPFLAGS += -I$(top_srcdir)/src/viewer\nunittest_CPPFLAGS += -I$(top_srcdir)/src/wordrec\nunittest_CPPFLAGS += -I$(top_srcdir)/unittest\n\n# Build googletest:\ncheck_LTLIBRARIES = libgtest.la libgtest_main.la libgmock.la libgmock_main.la\nlibgtest_la_SOURCES = unittest/third_party/googletest/googletest/src/gtest-all.cc\nlibgtest_la_CPPFLAGS = -I$(top_srcdir)/unittest/third_party/googletest/googletest/include\nlibgtest_la_CPPFLAGS += -I$(top_srcdir)/unittest/third_party/googletest/googletest\nlibgtest_la_CPPFLAGS += -pthread\nlibgtest_main_la_SOURCES = unittest/third_party/googletest/googletest/src/gtest_main.cc\nlibgtest_main_la_CPPFLAGS = $(libgtest_la_CPPFLAGS)\n\nGMOCK_INCLUDES = -I$(top_srcdir)/unittest/third_party/googletest/googlemock/include \\\n -I$(top_srcdir)/unittest/third_party/googletest/googlemock \\\n -I$(top_srcdir)/unittest/third_party/googletest/googletest/include \\\n -I$(top_srcdir)/unittest/third_party/googletest/googletest\n\nlibgmock_la_SOURCES = unittest/third_party/googletest/googlemock/src/gmock-all.cc\nlibgmock_la_CPPFLAGS = $(GMOCK_INCLUDES) \\\n -pthread\nlibgmock_main_la_SOURCES = unittest/third_party/googletest/googlemock/src/gmock_main.cc\nlibgmock_main_la_CPPFLAGS = $(GMOCK_INCLUDES) \\\n -pthread\n\n# Build unittests\nGTEST_LIBS = libgtest.la libgtest_main.la -lpthread\nGMOCK_LIBS = libgmock.la libgmock_main.la\nTESS_LIBS = $(GTEST_LIBS)\nTESS_LIBS += libtesseract.la $(libarchive_LIBS)\nTRAINING_LIBS = libtesseract_training.la\nTRAINING_LIBS += $(TESS_LIBS)\nunittest_CPPFLAGS += -isystem $(top_srcdir)/unittest/third_party/googletest/googletest/include\nunittest_CPPFLAGS += -isystem $(top_srcdir)/unittest/third_party/googletest/googlemock/include\n\ncheck_PROGRAMS = apiexample_test\nif ENABLE_TRAINING\nif !DISABLED_LEGACY_ENGINE\ncheck_PROGRAMS += applybox_test\nendif # !DISABLED_LEGACY_ENGINE\ncheck_PROGRAMS += baseapi_test\ncheck_PROGRAMS += baseapi_thread_test\nif !DISABLED_LEGACY_ENGINE\ncheck_PROGRAMS += bitvector_test\nendif # !DISABLED_LEGACY_ENGINE\nendif # ENABLE_TRAINING\ncheck_PROGRAMS += cleanapi_test\ncheck_PROGRAMS += colpartition_test\nif ENABLE_TRAINING\ncheck_PROGRAMS += commandlineflags_test\ncheck_PROGRAMS += dawg_test\nendif # ENABLE_TRAINING\ncheck_PROGRAMS += denorm_test\nif !DISABLED_LEGACY_ENGINE\ncheck_PROGRAMS += equationdetect_test\nendif # !DISABLED_LEGACY_ENGINE\ncheck_PROGRAMS += fileio_test\ncheck_PROGRAMS += heap_test\ncheck_PROGRAMS += imagedata_test\nif !DISABLED_LEGACY_ENGINE\ncheck_PROGRAMS += indexmapbidi_test\ncheck_PROGRAMS += intfeaturemap_test\nendif # !DISABLED_LEGACY_ENGINE\ncheck_PROGRAMS += intsimdmatrix_test\ncheck_PROGRAMS += lang_model_test\ncheck_PROGRAMS += layout_test\ncheck_PROGRAMS += ligature_table_test\ncheck_PROGRAMS += linlsq_test\ncheck_PROGRAMS += list_test\nif ENABLE_TRAINING\ncheck_PROGRAMS += lstm_recode_test\ncheck_PROGRAMS += lstm_squashed_test\ncheck_PROGRAMS += lstm_test\ncheck_PROGRAMS += lstmtrainer_test\nendif # ENABLE_TRAINING\ncheck_PROGRAMS += loadlang_test\nif !DISABLED_LEGACY_ENGINE\ncheck_PROGRAMS += mastertrainer_test\nendif # !DISABLED_LEGACY_ENGINE\ncheck_PROGRAMS += matrix_test\ncheck_PROGRAMS += networkio_test\nif ENABLE_TRAINING\ncheck_PROGRAMS += normstrngs_test\nendif # ENABLE_TRAINING\ncheck_PROGRAMS += nthitem_test\nif !DISABLED_LEGACY_ENGINE\ncheck_PROGRAMS += osd_test\nendif # !DISABLED_LEGACY_ENGINE\ncheck_PROGRAMS += pagesegmode_test\nif ENABLE_TRAINING\ncheck_PROGRAMS += pango_font_info_test\nendif # ENABLE_TRAINING\ncheck_PROGRAMS += paragraphs_test\nif !DISABLED_LEGACY_ENGINE\ncheck_PROGRAMS += params_model_test\nendif # !DISABLED_LEGACY_ENGINE\ncheck_PROGRAMS += progress_test\ncheck_PROGRAMS += qrsequence_test\ncheck_PROGRAMS += recodebeam_test\ncheck_PROGRAMS += rect_test\ncheck_PROGRAMS += resultiterator_test\ncheck_PROGRAMS += scanutils_test\nif !DISABLED_LEGACY_ENGINE\ncheck_PROGRAMS += shapetable_test\nendif # !DISABLED_LEGACY_ENGINE\ncheck_PROGRAMS += stats_test\ncheck_PROGRAMS += stridemap_test\ncheck_PROGRAMS += stringrenderer_test\ncheck_PROGRAMS += tablefind_test\ncheck_PROGRAMS += tablerecog_test\ncheck_PROGRAMS += tabvector_test\ncheck_PROGRAMS += tatweel_test\nif !DISABLED_LEGACY_ENGINE\ncheck_PROGRAMS += textlineprojection_test\nendif # !DISABLED_LEGACY_ENGINE\ncheck_PROGRAMS += tfile_test\nif ENABLE_TRAINING\ncheck_PROGRAMS += unichar_test\ncheck_PROGRAMS += unicharcompress_test\ncheck_PROGRAMS += unicharset_test\ncheck_PROGRAMS += validate_grapheme_test\ncheck_PROGRAMS += validate_indic_test\ncheck_PROGRAMS += validate_khmer_test\ncheck_PROGRAMS += validate_myanmar_test\ncheck_PROGRAMS += validator_test\nendif # ENABLE_TRAINING\n\ncheck_PROGRAMS: libtesseract.la libtesseract_training.la\n\nTESTS = $(check_PROGRAMS)\n\n# List of source files needed to build the executable:\n\napiexample_test_SOURCES = unittest/apiexample_test.cc\napiexample_test_CPPFLAGS = $(unittest_CPPFLAGS)\napiexample_test_LDFLAGS = $(LEPTONICA_LIBS)\napiexample_test_LDADD = $(TESS_LIBS) $(LEPTONICA_LIBS)\n\nif !DISABLED_LEGACY_ENGINE\napplybox_test_SOURCES = unittest/applybox_test.cc\napplybox_test_CPPFLAGS = $(unittest_CPPFLAGS)\napplybox_test_LDADD = $(TRAINING_LIBS) $(LEPTONICA_LIBS)\nendif # !DISABLED_LEGACY_ENGINE\n\nbaseapi_test_SOURCES = unittest/baseapi_test.cc\nbaseapi_test_CPPFLAGS = $(unittest_CPPFLAGS)\nbaseapi_test_LDADD = $(TRAINING_LIBS) $(LEPTONICA_LIBS)\n\nbaseapi_thread_test_SOURCES = unittest/baseapi_thread_test.cc\nbaseapi_thread_test_CPPFLAGS = $(unittest_CPPFLAGS)\nbaseapi_thread_test_LDADD = $(TESS_LIBS) $(LEPTONICA_LIBS)\n\nif !DISABLED_LEGACY_ENGINE\nbitvector_test_SOURCES = unittest/bitvector_test.cc\nbitvector_test_CPPFLAGS = $(unittest_CPPFLAGS)\nbitvector_test_LDADD = $(TRAINING_LIBS)\nendif # !DISABLED_LEGACY_ENGINE\n\ncleanapi_test_SOURCES = unittest/cleanapi_test.cc\ncleanapi_test_CPPFLAGS = $(unittest_CPPFLAGS)\ncleanapi_test_LDADD = $(TESS_LIBS)\n\ncolpartition_test_SOURCES = unittest/colpartition_test.cc\ncolpartition_test_CPPFLAGS = $(unittest_CPPFLAGS)\ncolpartition_test_LDADD = $(TESS_LIBS)\n\ncommandlineflags_test_SOURCES = unittest/commandlineflags_test.cc\ncommandlineflags_test_CPPFLAGS = $(unittest_CPPFLAGS)\ncommandlineflags_test_LDADD = $(TRAINING_LIBS) $(ICU_UC_LIBS)\n\ndawg_test_SOURCES = unittest/dawg_test.cc\ndawg_test_CPPFLAGS = $(unittest_CPPFLAGS)\ndawg_test_LDADD = $(TRAINING_LIBS)\n\ndenorm_test_SOURCES = unittest/denorm_test.cc\ndenorm_test_CPPFLAGS = $(unittest_CPPFLAGS)\ndenorm_test_LDADD = $(TESS_LIBS)\n\nif !DISABLED_LEGACY_ENGINE\nequationdetect_test_SOURCES = unittest/equationdetect_test.cc\nequationdetect_test_CPPFLAGS = $(unittest_CPPFLAGS)\nequationdetect_test_LDADD = $(TESS_LIBS) $(LEPTONICA_LIBS)\nendif # !DISABLED_LEGACY_ENGINE\n\nfileio_test_SOURCES = unittest/fileio_test.cc\nfileio_test_CPPFLAGS = $(unittest_CPPFLAGS)\nfileio_test_LDADD = $(TRAINING_LIBS)\n\nheap_test_SOURCES = unittest/heap_test.cc\nheap_test_CPPFLAGS = $(unittest_CPPFLAGS)\nheap_test_LDADD = $(TESS_LIBS)\n\nimagedata_test_SOURCES = unittest/imagedata_test.cc\nimagedata_test_CPPFLAGS = $(unittest_CPPFLAGS)\nimagedata_test_LDADD = $(TRAINING_LIBS)\n\nif !DISABLED_LEGACY_ENGINE\nindexmapbidi_test_SOURCES = unittest/indexmapbidi_test.cc\nindexmapbidi_test_CPPFLAGS = $(unittest_CPPFLAGS)\nindexmapbidi_test_LDADD = $(TRAINING_LIBS)\nendif # !DISABLED_LEGACY_ENGINE\n\nif !DISABLED_LEGACY_ENGINE\nintfeaturemap_test_SOURCES = unittest/intfeaturemap_test.cc\nintfeaturemap_test_CPPFLAGS = $(unittest_CPPFLAGS)\nintfeaturemap_test_LDADD = $(TRAINING_LIBS)\nendif # !DISABLED_LEGACY_ENGINE\n\nintsimdmatrix_test_SOURCES = unittest/intsimdmatrix_test.cc\nintsimdmatrix_test_CPPFLAGS = $(unittest_CPPFLAGS)\nif HAVE_AVX2\nintsimdmatrix_test_CPPFLAGS += -DHAVE_AVX2\nendif\nif HAVE_SSE4_1\nintsimdmatrix_test_CPPFLAGS += -DHAVE_SSE4_1\nendif\nintsimdmatrix_test_LDADD = $(TESS_LIBS)\n\nlang_model_test_SOURCES = unittest/lang_model_test.cc\nlang_model_test_CPPFLAGS = $(unittest_CPPFLAGS)\nlang_model_test_LDADD = $(TRAINING_LIBS) $(ICU_I18N_LIBS) $(ICU_UC_LIBS)\n\nlayout_test_SOURCES = unittest/layout_test.cc\nlayout_test_CPPFLAGS = $(unittest_CPPFLAGS)\nlayout_test_LDADD = $(TRAINING_LIBS) $(LEPTONICA_LIBS)\n\nligature_table_test_SOURCES = unittest/ligature_table_test.cc\nligature_table_test_CPPFLAGS = $(unittest_CPPFLAGS)\nligature_table_test_LDADD = $(TRAINING_LIBS) $(LEPTONICA_LIBS)\nligature_table_test_LDADD += $(ICU_I18N_LIBS) $(ICU_UC_LIBS)\nligature_table_test_LDADD += $(pangocairo_LIBS) $(pangoft2_LIBS)\nligature_table_test_LDADD += $(cairo_LIBS) $(pango_LIBS)\n\nlinlsq_test_SOURCES = unittest/linlsq_test.cc\nlinlsq_test_CPPFLAGS = $(unittest_CPPFLAGS)\nlinlsq_test_LDADD = $(TESS_LIBS)\n\nlist_test_SOURCES = unittest/list_test.cc\nlist_test_CPPFLAGS = $(unittest_CPPFLAGS)\nlist_test_LDADD = $(TESS_LIBS)\n\nloadlang_test_SOURCES = unittest/loadlang_test.cc\nloadlang_test_CPPFLAGS = $(unittest_CPPFLAGS)\nloadlang_test_LDADD = $(TESS_LIBS) $(LEPTONICA_LIBS)\n\nlstm_recode_test_SOURCES = unittest/lstm_recode_test.cc\nlstm_recode_test_CPPFLAGS = $(unittest_CPPFLAGS)\nlstm_recode_test_LDADD = $(TRAINING_LIBS)\n\nlstm_squashed_test_SOURCES = unittest/lstm_squashed_test.cc\nlstm_squashed_test_CPPFLAGS = $(unittest_CPPFLAGS)\nlstm_squashed_test_LDADD = $(TRAINING_LIBS)\n\nlstm_test_SOURCES = unittest/lstm_test.cc\nlstm_test_CPPFLAGS = $(unittest_CPPFLAGS)\nlstm_test_LDADD = $(TRAINING_LIBS)\n\nlstmtrainer_test_SOURCES = unittest/lstmtrainer_test.cc\nlstmtrainer_test_CPPFLAGS = $(unittest_CPPFLAGS)\nlstmtrainer_test_LDADD = $(TRAINING_LIBS) $(LEPTONICA_LIBS)\n\nif !DISABLED_LEGACY_ENGINE\nmastertrainer_test_SOURCES = unittest/mastertrainer_test.cc\nmastertrainer_test_CPPFLAGS = $(unittest_CPPFLAGS)\nmastertrainer_test_LDADD = $(TRAINING_LIBS) $(LEPTONICA_LIBS)\nendif # !DISABLED_LEGACY_ENGINE\n\nmatrix_test_SOURCES = unittest/matrix_test.cc\nmatrix_test_CPPFLAGS = $(unittest_CPPFLAGS)\nmatrix_test_LDADD = $(TESS_LIBS)\n\nnetworkio_test_SOURCES = unittest/networkio_test.cc\nnetworkio_test_CPPFLAGS = $(unittest_CPPFLAGS)\nnetworkio_test_LDADD = $(TESS_LIBS)\n\nnormstrngs_test_SOURCES = unittest/normstrngs_test.cc\nnormstrngs_test_CPPFLAGS = $(unittest_CPPFLAGS)\nnormstrngs_test_LDADD = $(TRAINING_LIBS) $(ICU_I18N_LIBS) $(ICU_UC_LIBS)\n\nnthitem_test_SOURCES = unittest/nthitem_test.cc\nnthitem_test_CPPFLAGS = $(unittest_CPPFLAGS)\nnthitem_test_LDADD = $(TESS_LIBS)\n\nif !DISABLED_LEGACY_ENGINE\nosd_test_SOURCES = unittest/osd_test.cc\nosd_test_CPPFLAGS = $(unittest_CPPFLAGS)\nosd_test_LDADD = $(TESS_LIBS) $(LEPTONICA_LIBS)\nendif # !DISABLED_LEGACY_ENGINE\n\npagesegmode_test_SOURCES = unittest/pagesegmode_test.cc\npagesegmode_test_CPPFLAGS = $(unittest_CPPFLAGS)\npagesegmode_test_LDADD = $(TRAINING_LIBS) $(LEPTONICA_LIBS)\n\npango_font_info_test_SOURCES = unittest/pango_font_info_test.cc\npango_font_info_test_CPPFLAGS = $(unittest_CPPFLAGS)\npango_font_info_test_LDADD = $(TRAINING_LIBS) $(LEPTONICA_LIBS)\npango_font_info_test_LDADD += $(ICU_I18N_LIBS) $(ICU_UC_LIBS)\npango_font_info_test_LDADD += $(pangocairo_LIBS)\npango_font_info_test_LDADD += $(pangoft2_LIBS)\n\nparagraphs_test_SOURCES = unittest/paragraphs_test.cc\nparagraphs_test_CPPFLAGS = $(unittest_CPPFLAGS)\nparagraphs_test_LDADD = $(TESS_LIBS)\n\nif !DISABLED_LEGACY_ENGINE\nparams_model_test_SOURCES = unittest/params_model_test.cc\nparams_model_test_CPPFLAGS = $(unittest_CPPFLAGS)\nparams_model_test_LDADD = $(TRAINING_LIBS)\nendif # !DISABLED_LEGACY_ENGINE\n\nprogress_test_SOURCES = unittest/progress_test.cc\nprogress_test_CPPFLAGS = $(unittest_CPPFLAGS)\nprogress_test_LDFLAGS = $(LEPTONICA_LIBS)\nprogress_test_LDADD = $(GTEST_LIBS) $(GMOCK_LIBS) $(TESS_LIBS) $(LEPTONICA_LIBS)\n\nqrsequence_test_SOURCES = unittest/qrsequence_test.cc\nqrsequence_test_CPPFLAGS = $(unittest_CPPFLAGS)\nqrsequence_test_LDADD = $(TESS_LIBS)\n\nrecodebeam_test_SOURCES = unittest/recodebeam_test.cc\nrecodebeam_test_CPPFLAGS = $(unittest_CPPFLAGS)\nrecodebeam_test_LDADD = $(TRAINING_LIBS) $(ICU_I18N_LIBS) $(ICU_UC_LIBS)\n\nrect_test_SOURCES = unittest/rect_test.cc\nrect_test_CPPFLAGS = $(unittest_CPPFLAGS)\nrect_test_LDADD = $(TESS_LIBS)\n\nresultiterator_test_SOURCES = unittest/resultiterator_test.cc\nresultiterator_test_CPPFLAGS = $(unittest_CPPFLAGS)\nresultiterator_test_LDADD = $(TRAINING_LIBS)\nresultiterator_test_LDADD += $(LEPTONICA_LIBS) $(ICU_I18N_LIBS) $(ICU_UC_LIBS)\n\nscanutils_test_SOURCES = unittest/scanutils_test.cc\nscanutils_test_CPPFLAGS = $(unittest_CPPFLAGS)\nscanutils_test_LDADD = $(TRAINING_LIBS)\n\nif !DISABLED_LEGACY_ENGINE\nshapetable_test_SOURCES = unittest/shapetable_test.cc\nshapetable_test_CPPFLAGS = $(unittest_CPPFLAGS)\nshapetable_test_LDADD = $(TRAINING_LIBS)\nendif # !DISABLED_LEGACY_ENGINE\n\nstats_test_SOURCES = unittest/stats_test.cc\nstats_test_CPPFLAGS = $(unittest_CPPFLAGS)\nstats_test_LDADD = $(TESS_LIBS)\n\nstridemap_test_SOURCES = unittest/stridemap_test.cc\nstridemap_test_CPPFLAGS = $(unittest_CPPFLAGS)\nstridemap_test_LDADD = $(TESS_LIBS)\n\nstringrenderer_test_SOURCES = unittest/stringrenderer_test.cc\nstringrenderer_test_CPPFLAGS = $(unittest_CPPFLAGS)\nstringrenderer_test_LDADD = $(TRAINING_LIBS) $(LEPTONICA_LIBS)\nstringrenderer_test_LDADD += $(ICU_I18N_LIBS) $(ICU_UC_LIBS)\nstringrenderer_test_LDADD += $(pangocairo_LIBS) $(pangoft2_LIBS)\nstringrenderer_test_LDADD += $(cairo_LIBS) $(pango_LIBS)\n\ntablefind_test_SOURCES = unittest/tablefind_test.cc\ntablefind_test_CPPFLAGS = $(unittest_CPPFLAGS)\ntablefind_test_LDADD = $(TESS_LIBS)\n\ntablerecog_test_SOURCES = unittest/tablerecog_test.cc\ntablerecog_test_CPPFLAGS = $(unittest_CPPFLAGS)\ntablerecog_test_LDADD = $(TESS_LIBS)\n\ntabvector_test_SOURCES = unittest/tabvector_test.cc\ntabvector_test_CPPFLAGS = $(unittest_CPPFLAGS)\ntabvector_test_LDADD = $(TESS_LIBS)\n\ntatweel_test_SOURCES = unittest/tatweel_test.cc\ntatweel_test_SOURCES += unittest/third_party/utf/rune.c\ntatweel_test_SOURCES += unittest/util/utf8/unicodetext.cc\ntatweel_test_SOURCES += unittest/util/utf8/unilib.cc\ntatweel_test_CPPFLAGS = $(unittest_CPPFLAGS)\ntatweel_test_LDADD = $(TRAINING_LIBS)\n\ntextlineprojection_test_SOURCES = unittest/textlineprojection_test.cc\ntextlineprojection_test_CPPFLAGS = $(unittest_CPPFLAGS)\ntextlineprojection_test_LDADD = $(TRAINING_LIBS) $(LEPTONICA_LIBS)\n\ntfile_test_SOURCES = unittest/tfile_test.cc\ntfile_test_CPPFLAGS = $(unittest_CPPFLAGS)\ntfile_test_LDADD = $(TESS_LIBS)\n\nunichar_test_SOURCES = unittest/unichar_test.cc\nunichar_test_CPPFLAGS = $(unittest_CPPFLAGS)\nunichar_test_LDADD = $(TRAINING_LIBS) $(ICU_UC_LIBS)\n\nunicharcompress_test_SOURCES = unittest/unicharcompress_test.cc\nunicharcompress_test_CPPFLAGS = $(unittest_CPPFLAGS)\nunicharcompress_test_LDADD = $(TRAINING_LIBS) $(ICU_UC_LIBS)\n\nunicharset_test_SOURCES = unittest/unicharset_test.cc\nunicharset_test_CPPFLAGS = $(unittest_CPPFLAGS)\nunicharset_test_LDADD = $(TRAINING_LIBS) $(ICU_UC_LIBS)\n\nvalidate_grapheme_test_SOURCES = unittest/validate_grapheme_test.cc\nvalidate_grapheme_test_CPPFLAGS = $(unittest_CPPFLAGS)\nvalidate_grapheme_test_LDADD = $(TRAINING_LIBS) $(ICU_I18N_LIBS) $(ICU_UC_LIBS)\n\nvalidate_indic_test_SOURCES = unittest/validate_indic_test.cc\nvalidate_indic_test_CPPFLAGS = $(unittest_CPPFLAGS)\nvalidate_indic_test_LDADD = $(TRAINING_LIBS) $(ICU_I18N_LIBS) $(ICU_UC_LIBS)\n\nvalidate_khmer_test_SOURCES = unittest/validate_khmer_test.cc\nvalidate_khmer_test_CPPFLAGS = $(unittest_CPPFLAGS)\nvalidate_khmer_test_LDADD = $(TRAINING_LIBS) $(ICU_I18N_LIBS) $(ICU_UC_LIBS)\n\nvalidate_myanmar_test_SOURCES = unittest/validate_myanmar_test.cc\nvalidate_myanmar_test_CPPFLAGS = $(unittest_CPPFLAGS)\nvalidate_myanmar_test_LDADD = $(TRAINING_LIBS) $(ICU_I18N_LIBS) $(ICU_UC_LIBS)\n\nvalidator_test_SOURCES = unittest/validator_test.cc\nvalidator_test_CPPFLAGS = $(unittest_CPPFLAGS)\nvalidator_test_LDADD = $(TRAINING_LIBS) $(ICU_UC_LIBS)\n\n# for windows\nif T_WIN\napiexample_test_LDADD += -lws2_32\nintsimdmatrix_test_LDADD += -lws2_32\nmatrix_test_LDADD += -lws2_32\nif !DISABLED_LEGACY_ENGINE\nosd_test_LDADD += -lws2_32\nendif # !DISABLED_LEGACY_ENGINE\nloadlang_test_LDADD += -lws2_32\nendif\n\nEXTRA_apiexample_test_DEPENDENCIES = $(abs_top_builddir)/test/testing/phototest.tif\nEXTRA_apiexample_test_DEPENDENCIES += $(abs_top_builddir)/test/testing/phototest.txt\n\n$(abs_top_builddir)/test/testing/phototest.tif:\n\tmkdir -p $(top_builddir)/test/testing\n\tln -s $(TESTING_DIR)/phototest.tif $(top_builddir)/test/testing/phototest.tif\n\n$(abs_top_builddir)/test/testing/phototest.txt:\n\tmkdir -p $(top_builddir)/test/testing\n\tln -s $(TESTING_DIR)/phototest.txt $(top_builddir)/test/testing/phototest.txt\n\n# Some tests require a local tmp directory.\n\n$(check_PROGRAMS): | tmp\n\ntmp:\n\tmkdir -p tmp\n\n# Some tests require a well defined set of the following font files.\n\nfonts = ae_Arab.ttf\nfonts += Arial_Bold_Italic.ttf\nfonts += DejaVuSans-ExtraLight.ttf\nfonts += Lohit-Hindi.ttf\nfonts += Times_New_Roman.ttf\nfonts += UnBatang.ttf\nfonts += Verdana.ttf\n\n# These tests depend on installed model files and fonts:\n#\n# apiexample_test baseapi_test lang_model_test layout_test\n# ligature_table_test loadlang_test lstm_recode_test lstm_squashed_test\n# lstm_test lstmtrainer_test mastertrainer_test osd_test\n# pagesegmode_test pango_font_info_test progress_test\n# recodebeam_test resultiterator_test stringrenderer_test\n# textlineprojection_test unicharcompress_test\n#\n# Instead of fine-tuned dependencies the following lines\n# simply require those dependencies for all tests.\n# That can be improved if necessary.\n\n$(check_PROGRAMS): | $(LANGDATA_DIR)\n$(check_PROGRAMS): | $(TESSDATA_DIR)\n$(check_PROGRAMS): | $(TESSDATA_BEST_DIR)\n$(check_PROGRAMS): | $(TESSDATA_FAST_DIR)\n$(check_PROGRAMS): | $(fonts:%=$(TESTING_DIR)/%)\n\n$(LANGDATA_DIR) $(TESSDATA_DIR) $(TESSDATA_BEST_DIR) $(TESSDATA_FAST_DIR):\n\t@echo \"Some unit tests require $@.\"\n\t@echo \"It can be installed manually by running this command:\"\n\t@echo \" git clone https://github.com/tesseract-ocr/$$(basename $@).git $@\"\n\t@exit 1\n\n$(TESTING_DIR)/Arial_Bold_Italic.ttf:\n\tcurl -sSL -o Arial.exe https://sourceforge.net/projects/corefonts/files/the%20fonts/final/arial32.exe/download\n\tcabextract -F Arialbi.TTF -q Arial.exe\n\trm Arial.exe\n\tmv Arialbi.TTF $@\n\n$(TESTING_DIR)/DejaVuSans-ExtraLight.ttf:\n\tcurl -sSL http://sourceforge.net/projects/dejavu/files/dejavu/2.37/dejavu-fonts-ttf-2.37.tar.bz2 | \\\n\ttar -xjO dejavu-fonts-ttf-2.37/ttf/DejaVuSans-ExtraLight.ttf >$@\n\n$(TESTING_DIR)/Lohit-Hindi.ttf:\n\tcurl -sSL https://releases.pagure.org/lohit/lohit-hindi-ttf-2.4.3.tar.gz | \\\n\ttar -xzO lohit-hindi-ttf-2.4.3/Lohit-Hindi.ttf >$@\n\n$(TESTING_DIR)/Times_New_Roman.ttf:\n\tcurl -sSL -o Times.exe https://sourceforge.net/projects/corefonts/files/the%20fonts/final/times32.exe/download\n\tcabextract -F Times.TTF -q Times.exe\n\trm Times.exe\n\tmv Times.TTF $@\n\n$(TESTING_DIR)/UnBatang.ttf:\n\tcurl -sSL -o $@ https://salsa.debian.org/fonts-team/fonts-unfonts-core/-/raw/master/UnBatang.ttf\n\n$(TESTING_DIR)/Verdana.ttf:\n\tcurl -sSL -o Verdana.exe https://sourceforge.net/projects/corefonts/files/the%20fonts/final/verdan32.exe/download\n\tcabextract -F Verdana.TTF -q Verdana.exe\n\trm Verdana.exe\n\tmv Verdana.TTF $@\n\n$(TESTING_DIR)/ae_Arab.ttf:\n\tcurl -sSL -o $@ https://salsa.debian.org/fonts-team/fonts-arabeyes/-/raw/master/ae_Arab.ttf\n" }, { "path": "README.md", "content": "# Tesseract OCR\n\n[![Coverity Scan Build Status](https://scan.coverity.com/projects/tesseract-ocr/badge.svg)](https://scan.coverity.com/projects/tesseract-ocr)\n[![CodeQL](https://github.com/tesseract-ocr/tesseract/workflows/CodeQL/badge.svg)](https://github.com/tesseract-ocr/tesseract/security/code-scanning)\n[![OSS-Fuzz](https://img.shields.io/badge/oss--fuzz-fuzzing-brightgreen)](https://issues.oss-fuzz.com/issues?q=is:open%20title:tesseract-ocr)\n\\\n[![GitHub license](https://img.shields.io/badge/license-Apache--2.0-blue.svg)](https://raw.githubusercontent.com/tesseract-ocr/tesseract/main/LICENSE)\n[![Downloads](https://img.shields.io/badge/download-all%20releases-brightgreen.svg)](https://github.com/tesseract-ocr/tesseract/releases/)\n\n## Table of Contents\n\n* [Tesseract OCR](#tesseract-ocr)\n * [About](#about)\n * [Brief history](#brief-history)\n * [Installing Tesseract](#installing-tesseract)\n * [Running Tesseract](#running-tesseract)\n * [For developers](#for-developers)\n * [Support](#support)\n * [License](#license)\n * [Dependencies](#dependencies)\n * [Latest Version of README](#latest-version-of-readme)\n\n## About\n\nThis package contains an **OCR engine** - `libtesseract` and a **command line program** - `tesseract`.\n\nTesseract 4 adds a new neural net (LSTM) based [OCR engine](https://en.wikipedia.org/wiki/Optical_character_recognition) which is focused on line recognition, but also still supports the legacy Tesseract OCR engine of Tesseract 3 which works by recognizing character patterns. Compatibility with Tesseract 3 is enabled by using the Legacy OCR Engine mode (--oem 0).\nIt also needs [traineddata](https://tesseract-ocr.github.io/tessdoc/Data-Files.html) files which support the legacy engine, for example those from the [tessdata](https://github.com/tesseract-ocr/tessdata) repository.\n\nStefan Weil is the current lead developer. Ray Smith was the lead developer until 2017. The maintainer is Zdenko Podobny. For a list of contributors see [AUTHORS](https://github.com/tesseract-ocr/tesseract/blob/main/AUTHORS)\nand GitHub's log of [contributors](https://github.com/tesseract-ocr/tesseract/graphs/contributors).\n\nTesseract has **unicode (UTF-8) support**, and can **recognize [more than 100 languages](https://tesseract-ocr.github.io/tessdoc/Data-Files-in-different-versions.html)** \"out of the box\".\n\nTesseract supports **[various image formats](https://tesseract-ocr.github.io/tessdoc/InputFormats)** including PNG, JPEG and TIFF.\n\nTesseract supports **various output formats**: plain text, hOCR (HTML), PDF, invisible-text-only PDF, TSV, ALTO and PAGE.\n\nYou should note that in many cases, in order to get better OCR results, you'll need to **[improve the quality](https://tesseract-ocr.github.io/tessdoc/ImproveQuality.html) of the image** you are giving Tesseract.\n\nThis project **does not include a GUI application**. If you need one, please see the [3rdParty](https://tesseract-ocr.github.io/tessdoc/User-Projects-%E2%80%93-3rdParty.html) documentation.\n\nTesseract **can be trained to recognize other languages**.\nSee [Tesseract Training](https://tesseract-ocr.github.io/tessdoc/Training-Tesseract.html) for more information.\n\n## Brief history\n\nTesseract was originally developed at Hewlett-Packard Laboratories Bristol UK and at Hewlett-Packard Co, Greeley Colorado USA between 1985 and 1994, with some more changes made in 1996 to port to Windows, and some C++izing in 1998. In 2005 Tesseract was open sourced by HP. From 2006 until August 2017 it was developed by Google.\n\nMajor version 5 is the current stable version and started with release\n[5.0.0](https://github.com/tesseract-ocr/tesseract/releases/tag/5.0.0) on November 30, 2021. Newer minor versions and bugfix versions are available from\n[GitHub](https://github.com/tesseract-ocr/tesseract/releases/).\n\nLatest source code is available from [main branch on GitHub](https://github.com/tesseract-ocr/tesseract/tree/main).\nOpen issues can be found in [issue tracker](https://github.com/tesseract-ocr/tesseract/issues),\nand [planning documentation](https://tesseract-ocr.github.io/tessdoc/Planning.html).\n\nSee **[Release Notes](https://tesseract-ocr.github.io/tessdoc/ReleaseNotes.html)**\nand **[Change Log](https://github.com/tesseract-ocr/tesseract/blob/main/ChangeLog)** for more details of the releases.\n\n## Installing Tesseract\n\nYou can either [Install Tesseract via pre-built binary package](https://tesseract-ocr.github.io/tessdoc/Installation.html)\nor [build it from source](https://tesseract-ocr.github.io/tessdoc/Compiling.html).\n\nBefore building Tesseract from source, please check that your system has a compiler which is one of the [supported compilers](https://tesseract-ocr.github.io/tessdoc/supported-compilers.html).\n\n## Running Tesseract\n\nBasic **[command line usage](https://tesseract-ocr.github.io/tessdoc/Command-Line-Usage.html)**:\n\n tesseract imagename outputbase [-l lang] [--oem ocrenginemode] [--psm pagesegmode] [configfiles...]\n\nFor more information about the various command line options use `tesseract --help` or `man tesseract`.\n\nExamples can be found in the [documentation](https://tesseract-ocr.github.io/tessdoc/Command-Line-Usage.html#simplest-invocation-to-ocr-an-image).\n\n## For developers\n\nDevelopers can use `libtesseract` [C](https://github.com/tesseract-ocr/tesseract/blob/main/include/tesseract/capi.h) or\n[C++](https://github.com/tesseract-ocr/tesseract/blob/main/include/tesseract/baseapi.h) API to build their own application. If you need bindings to `libtesseract` for other programming languages, please see the\n[wrapper](https://tesseract-ocr.github.io/tessdoc/AddOns.html#tesseract-wrappers) section in the AddOns documentation.\n\nDocumentation of Tesseract generated from source code by doxygen can be found on [tesseract-ocr.github.io](https://tesseract-ocr.github.io/).\n\n## Support\n\nBefore you submit an issue, please review **[the guidelines for this repository](https://github.com/tesseract-ocr/tesseract/blob/main/CONTRIBUTING.md)**.\n\nFor support, first read the [documentation](https://tesseract-ocr.github.io/tessdoc/),\nparticularly the [FAQ](https://tesseract-ocr.github.io/tessdoc/FAQ.html) to see if your problem is addressed there.\nIf not, search the [Tesseract user forum](https://groups.google.com/g/tesseract-ocr), the [Tesseract developer forum](https://groups.google.com/g/tesseract-dev) and [past issues](https://github.com/tesseract-ocr/tesseract/issues), and if you still can't find what you need, ask for support in the mailing-lists.\n\nMailing-lists:\n\n* [tesseract-ocr](https://groups.google.com/g/tesseract-ocr) - For tesseract users.\n* [tesseract-dev](https://groups.google.com/g/tesseract-dev) - For tesseract developers.\n\nPlease report an issue only for a **bug**, not for asking questions.\n\n## License\n\n The code in this repository is licensed under the Apache License, Version 2.0 (the \"License\");\n you may not use this file except in compliance with the License.\n You may obtain a copy of the License at\n\n http://www.apache.org/licenses/LICENSE-2.0\n\n Unless required by applicable law or agreed to in writing, software\n distributed under the License is distributed on an \"AS IS\" BASIS,\n WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n See the License for the specific language governing permissions and\n limitations under the License.\n\n**NOTE**: This software depends on other packages that may be licensed under different open source licenses.\n\nTesseract uses [Leptonica library](http://leptonica.com/) which essentially\nuses a [BSD 2-clause license](http://leptonica.com/about-the-license.html).\n\n## Dependencies\n\nTesseract uses [Leptonica library](https://github.com/DanBloomberg/leptonica)\nfor opening input images (e.g. not documents like pdf).\nIt is suggested to use leptonica with built-in support for [zlib](https://zlib.net),\n[png](https://sourceforge.net/projects/libpng) and\n[tiff](http://www.simplesystems.org/libtiff) (for multipage tiff).\n\n## Latest Version of README\n\nFor the latest online version of the README.md see:\n\n\n" }, { "path": "VERSION", "content": "5.5.2\n" }, { "path": "appveyor.yml", "content": "environment:\n matrix:\n - APPVEYOR_BUILD_WORKER_IMAGE: Visual Studio 2022\n platform: Win64\n\nconfiguration:\n - Release\n\ncache:\n - c:/Users/appveyor/.sw -> appveyor.yml\n\nonly_commits:\n files:\n - appveyor.yml\n - '**.cpp'\n - '**.h'\n - 'unittest/**.c'\n - 'unittest/**.cc'\n\nbefore_build:\n - git submodule update --init --recursive\n - curl -fsS -L -o dl.zip https://software-network.org/client/sw-master-windows_x86_64-client.zip\n - 7z x dl.zip\n - set PATH=%PATH%;%cd%\n\nbuild_script:\n - sw -version\n # -show-output - show command output\n # debug build causes long builds (> 1h), appveyor drops them\n - sw -platform %platform% -config r build -Dwith-tests=1\n # test\n - git clone https://github.com/egorpugin/tessdata tessdata_unittest\n - ps: Copy-Item -Path \"tessdata_unittest\\fonts\\*\" -Destination \"test\\testing\" -Recurse\n - sw -platform %platform% -config r test -Dwith-tests=1 -Dskip-tests=lstm,lstm_recode\n\nafter_build:\n - 7z a tesseract.zip %APPVEYOR_BUILD_FOLDER%\\.sw\\out\\**\\*.exe %APPVEYOR_BUILD_FOLDER%\\.sw\\out\\**\\*.dll\n #- 7z a tesseract.zip %APPVEYOR_BUILD_FOLDER%\\.sw\\Windows_*_Shared_Release_MSVC_*\\*.exe %APPVEYOR_BUILD_FOLDER%\\.sw\\Windows_*_Shared_Release_MSVC_*\\*.dll\n\non_finish:\n # gather tests\n - ps: $wc = New-Object 'System.Net.WebClient'\n - ps: $wc.UploadFile(\"https://ci.appveyor.com/api/testresults/junit/$($env:APPVEYOR_JOB_ID)\", (Resolve-Path .\\.sw\\test\\results.xml))\n\nartifacts:\n - path: tesseract.zip\n name: tesseract-$(APPVEYOR_BUILD_VERSION)\n\n" }, { "path": "autogen.sh", "content": "#!/bin/sh\n# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n# http://www.apache.org/licenses/LICENSE-2.0\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\n\n# This is a simple script which is meant to help developers\n# better deal with the GNU autotools, specifically:\n#\n# aclocal\n# libtoolize\n# autoconf\n# autoheader\n# automake\n#\n# The whole thing is quite complex...\n#\n# The idea is to run this collection of tools on a single platform,\n# typically the main development platform, running a recent version of\n# autoconf. In theory, if we had these tools on each platform where we\n# ever expected to port the software, we would never need to checkin\n# more than a few autotools configuration files. However, the whole\n# idea is to generate a configure script and associated files in a way\n# that is portable across platforms, so we *have* to check in a whole\n# bunch of files generated by all these tools.\n\n# The real source files are:\n#\n# acinclude.m4 (used by aclocal)\n# configure.ac (main autoconf file)\n# Makefile.am, */Makefile.am (automake config files)\n#\n# All the rest is auto-generated.\n\nif [ \"$1\" = \"clean\" ]; then\n echo \"Cleaning...\"\n rm configure aclocal.m4\n rm m4/l*\n rm config/*\n rmdir config\n find . -iname \"Makefile.in\" -type f -exec rm '{}' +\nfi\n\nbail_out()\n{\n echo\n echo \" Something went wrong, bailing out!\"\n echo\n exit 1\n}\n\n# Prevent any errors that might result from failing to properly invoke\n# `libtoolize` or `glibtoolize,` whichever is present on your system,\n# from occurring by testing for its existence and capturing the absolute path to\n# its location for caching purposes prior to using it later on in 'Step 2:'\nif command -v libtoolize >/dev/null 2>&1; then\n LIBTOOLIZE=\"$(command -v libtoolize)\"\nelif command -v glibtoolize >/dev/null 2>&1; then\n LIBTOOLIZE=\"$(command -v glibtoolize)\"\nelse\n echo \"Unable to find a valid copy of libtoolize or glibtoolize in your PATH!\"\n bail_out\nfi\n\n# --- Step 1: Generate aclocal.m4 from:\n# . acinclude.m4\n# . config/*.m4 (these files are referenced in acinclude.m4)\n\nmkdir -p config\n\necho \"Running aclocal\"\naclocal -I config || bail_out\n\n# --- Step 2:\n\necho \"Running $LIBTOOLIZE\"\n$LIBTOOLIZE -f -c || bail_out\n$LIBTOOLIZE --automake || bail_out\n\n# Run aclocal a 2nd time because glibtoolize created additional m4 files.\necho \"Running aclocal\"\naclocal -I config || bail_out\n\n# --- Step 3: Generate configure and include/miaconfig.h from:\n# . configure.ac\n#\n\necho \"Running autoconf\"\nautoconf || bail_out\n\nif grep -q PKG_CHECK_MODULES configure; then\n # The generated configure is invalid because pkg-config is unavailable.\n rm configure\n echo \"Missing pkg-config. Check the build requirements.\"\n bail_out\nfi\n\n# --- Step 4: Generate config.h.in from:\n# . configure.ac (look for AM_CONFIG_HEADER tag or AC_CONFIG_HEADER tag)\n\necho \"Running autoheader\"\nautoheader -f || bail_out\n\n# --- Step 5: Generate Makefile.in, src/Makefile.in, and a whole bunch of\n# files in config (config.guess, config.sub, depcomp,\n# install-sh, missing, mkinstalldirs) plus COPYING and\n# INSTALL from:\n# . Makefile.am\n# . src/Makefile.am\n#\n# Using --add-missing --copy makes sure that, if these files are missing,\n# they are copied from the system so they can be used in a distribution.\n\necho \"Running automake --add-missing --copy\"\nautomake --add-missing --copy --warnings=all || bail_out\n\necho \"\"\necho \"All done.\"\necho \"To build the software now, do something like:\"\necho \"\"\necho \"$ ./configure [--enable-debug] [...other options]\"\n" }, { "path": "cmake/BuildFunctions.cmake", "content": "# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n# http://www.apache.org/licenses/LICENSE-2.0\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\n################################################################################\n#\n# macros and functions\n#\n################################################################################\n\n########################################\n# FUNCTION project_group\n########################################\nfunction(project_group target name)\n set_target_properties(${target} PROPERTIES FOLDER ${name})\nendfunction(project_group)\n\n################################################################################\n" }, { "path": "cmake/BuildOptimizations.cmake", "content": "# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n# http://www.apache.org/licenses/LICENSE-2.0\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\n\n################################################################################\n#\n# Build Optimizations Module\n#\n# This module provides functions to apply modern CMake build optimizations\n# to targets for faster and incremental builds.\n#\n################################################################################\n\n#\n# Function: apply_modern_optimizations\n# Apply build optimizations to a target\n#\n# Parameters:\n# target_name - Name of the target to optimize\n# PCH_HEADERS - Optional list of headers for precompiled headers\n#\nfunction(apply_modern_optimizations target_name)\n # Parse arguments\n set(oneValueArgs )\n set(multiValueArgs PCH_HEADERS)\n cmake_parse_arguments(ARG \"\" \"${oneValueArgs}\" \"${multiValueArgs}\" ${ARGN})\n\n # Apply Unity Build if enabled\n if(ENABLE_UNITY_BUILD)\n set_target_properties(${target_name} PROPERTIES UNITY_BUILD ON)\n # Use smaller batch sizes for libraries with many files\n get_target_property(target_type ${target_name} TYPE)\n if(target_type STREQUAL \"STATIC_LIBRARY\" OR target_type STREQUAL \"SHARED_LIBRARY\")\n set_target_properties(${target_name} PROPERTIES UNITY_BUILD_BATCH_SIZE 16)\n else()\n set_target_properties(${target_name} PROPERTIES UNITY_BUILD_BATCH_SIZE 8)\n endif()\n message(STATUS \"Unity build enabled for ${target_name}\")\n endif()\n\n # Apply Precompiled Headers if enabled and headers provided\n if(ENABLE_PRECOMPILED_HEADERS)\n if(ARG_PCH_HEADERS)\n target_precompile_headers(${target_name} PRIVATE ${ARG_PCH_HEADERS})\n message(STATUS \"Precompiled headers enabled for ${target_name}\")\n else()\n # Use common standard library headers as default\n target_precompile_headers(${target_name} PRIVATE\n \n \n \n \n \n \n \n \n )\n message(STATUS \"Default precompiled headers enabled for ${target_name}\")\n endif()\n endif()\n\n # Configure build pools for Ninja\n if(ENABLE_NINJA_POOL AND CMAKE_GENERATOR STREQUAL \"Ninja\")\n set_target_properties(${target_name} PROPERTIES JOB_POOL_COMPILE compile)\n set_target_properties(${target_name} PROPERTIES JOB_POOL_LINK link)\n endif()\n\n # Apply compiler-specific optimizations\n if(MSVC)\n # Enable parallel compilation for MSVC if not already enabled\n get_target_property(target_compile_options ${target_name} COMPILE_OPTIONS)\n if(NOT target_compile_options MATCHES \"/MP\")\n target_compile_options(${target_name} PRIVATE \"/MP\")\n endif()\n\n # Enable function-level linking for better optimization\n target_compile_options(${target_name} PRIVATE \"/Gy\")\n\n # Enable intrinsic functions for better performance\n target_compile_options(${target_name} PRIVATE \"/Oi\")\n elseif(CMAKE_CXX_COMPILER_ID MATCHES \"GNU|Clang\")\n # Enable split debug info for faster incremental builds\n if(CMAKE_BUILD_TYPE MATCHES Debug)\n target_compile_options(${target_name} PRIVATE \"-gsplit-dwarf\")\n endif()\n\n # Enable function sections for better dead code elimination\n target_compile_options(${target_name} PRIVATE \"-ffunction-sections\" \"-fdata-sections\")\n endif()\nendfunction()\n\n#\n# Function: apply_training_optimizations\n# Apply optimizations specific to training tools\n#\nfunction(apply_training_optimizations target_name)\n apply_modern_optimizations(${target_name}\n PCH_HEADERS\n \n \n \n \n \n \n \n )\n\n # Training tools usually build faster, so smaller unity batches are fine\n if(ENABLE_UNITY_BUILD)\n set_target_properties(${target_name} PROPERTIES UNITY_BUILD_BATCH_SIZE 4)\n endif()\nendfunction()\n\n#\n# Function: apply_test_optimizations\n# Apply optimizations specific to test targets\n#\nfunction(apply_test_optimizations target_name)\n # Tests often have different compilation patterns\n if(ENABLE_PRECOMPILED_HEADERS)\n target_precompile_headers(${target_name} PRIVATE\n \n \n \n \n \n )\n message(STATUS \"Test precompiled headers enabled for ${target_name}\")\n endif()\n\n # Tests benefit from unity builds but smaller batches\n if(ENABLE_UNITY_BUILD)\n set_target_properties(${target_name} PROPERTIES UNITY_BUILD ON)\n set_target_properties(${target_name} PROPERTIES UNITY_BUILD_BATCH_SIZE 8)\n message(STATUS \"Unity build enabled for test ${target_name}\")\n endif()\n\n # Configure Ninja pools\n if(ENABLE_NINJA_POOL AND CMAKE_GENERATOR STREQUAL \"Ninja\")\n set_target_properties(${target_name} PROPERTIES JOB_POOL_COMPILE compile)\n set_target_properties(${target_name} PROPERTIES JOB_POOL_LINK link)\n endif()\nendfunction()\n" }, { "path": "cmake/CheckFunctions.cmake", "content": "# Licensed under the Apache License, Version 2.0 (the \"License\"); you may not\n# use this file except in compliance with the License. You may obtain a copy of\n# the License at http://www.apache.org/licenses/LICENSE-2.0 Unless required by\n# applicable law or agreed to in writing, software distributed under the License\n# is distributed on an \"AS IS\" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY\n# KIND, either express or implied. See the License for the specific language\n# governing permissions and limitations under the License.\n# ##############################################################################\n#\n# macros and functions\n#\n# ##############################################################################\n\n# ##############################################################################\n# FUNCTION check_leptonica_tiff_support\n# ##############################################################################\nfunction(check_leptonica_tiff_support)\n # check if leptonica was build with tiff support set result to\n # LEPT_TIFF_RESULT\n set(TIFF_TEST\n \"#include \\\"allheaders.h\\\"\\n\"\n \"int main() {\\n\"\n \" l_uint8 *data = NULL;\\n\"\n \" size_t size = 0;\\n\"\n \" PIX* pix = pixCreate(3, 3, 4);\\n\"\n \" l_int32 ret_val = pixWriteMemTiff(&data, &size, pix, IFF_TIFF_G3);\\n\"\n \" pixDestroy(&pix);\\n\"\n \" lept_free(data);\\n\"\n \" return ret_val;}\\n\")\n if(${CMAKE_VERSION} VERSION_LESS \"3.25\")\n message(STATUS \"Testing TIFF support in Leptonica is available with CMake >= 3.25 (you have ${CMAKE_VERSION}))\")\n else()\n set(CMAKE_TRY_COMPILE_CONFIGURATION ${CMAKE_BUILD_TYPE})\n try_run(\n LEPT_TIFF_RESULT\n LEPT_TIFF_COMPILE_SUCCESS\n SOURCE_FROM_CONTENT tiff_test.cpp \"${TIFF_TEST}\"\n CMAKE_FLAGS \"-DINCLUDE_DIRECTORIES=${Leptonica_INCLUDE_DIRS}\"\n LINK_LIBRARIES ${Leptonica_LIBRARIES}\n COMPILE_OUTPUT_VARIABLE\n COMPILE_OUTPUT)\n if(NOT LEPT_TIFF_COMPILE_SUCCESS)\n message(STATUS \"COMPILE_OUTPUT: ${COMPILE_OUTPUT}\")\n message(STATUS \"Leptonica_INCLUDE_DIRS: ${Leptonica_INCLUDE_DIRS}\")\n message(STATUS \"Leptonica_LIBRARIES: ${Leptonica_LIBRARIES}\")\n message(STATUS \"LEPT_TIFF_RESULT: ${LEPT_TIFF_RESULT}\")\n message(STATUS \"LEPT_TIFF_COMPILE: ${LEPT_TIFF_COMPILE}\")\n message(WARNING \"Failed to compile test\")\n endif()\n endif()\nendfunction(check_leptonica_tiff_support)\n\n# ##############################################################################\n" }, { "path": "cmake/Configure.cmake", "content": "# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n# http://www.apache.org/licenses/LICENSE-2.0\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\n################################################################################\n#\n# configure\n#\n################################################################################\n\n########################################\n# FUNCTION check_includes\n########################################\nfunction(check_includes files)\n foreach(F ${${files}})\n set(name ${F})\n string(REPLACE \"-\" \"_\" name ${name})\n string(REPLACE \".\" \"_\" name ${name})\n string(REPLACE \"/\" \"_\" name ${name})\n string(TOUPPER ${name} name)\n check_include_files(${F} HAVE_${name})\n file(APPEND ${AUTOCONFIG_SRC} \"/* Define to 1 if you have the <${F}> header file. */\\n\")\n file(APPEND ${AUTOCONFIG_SRC} \"#cmakedefine HAVE_${name} 1\\n\")\n file(APPEND ${AUTOCONFIG_SRC} \"\\n\")\n endforeach()\nendfunction(check_includes)\n\n########################################\n# FUNCTION check_functions\n########################################\nfunction(check_functions functions)\n foreach(F ${${functions}})\n set(name ${F})\n string(TOUPPER ${name} name)\n check_function_exists(${F} HAVE_${name})\n file(APPEND ${AUTOCONFIG_SRC} \"/* Define to 1 if you have the `${F}' function. */\\n\")\n file(APPEND ${AUTOCONFIG_SRC} \"#cmakedefine HAVE_${name} 1\\n\")\n file(APPEND ${AUTOCONFIG_SRC} \"\\n\")\n endforeach()\nendfunction(check_functions)\n\n########################################\n# FUNCTION check_types\n########################################\nfunction(check_types types)\n foreach(T ${${types}})\n set(name ${T})\n string(REPLACE \" \" \"_\" name ${name})\n string(REPLACE \"-\" \"_\" name ${name})\n string(REPLACE \".\" \"_\" name ${name})\n string(REPLACE \"/\" \"_\" name ${name})\n string(TOUPPER ${name} name)\n check_type_size(${T} HAVE_${name})\n file(APPEND ${AUTOCONFIG_SRC} \"/* Define to 1 if the system has the type `${T}'. */\\n\")\n file(APPEND ${AUTOCONFIG_SRC} \"#cmakedefine HAVE_${name} 1\\n\")\n file(APPEND ${AUTOCONFIG_SRC} \"\\n\")\n endforeach()\nendfunction(check_types)\n\n########################################\n\nfile(WRITE ${AUTOCONFIG_SRC})\n\ninclude(CheckCSourceCompiles)\ninclude(CheckCSourceRuns)\ninclude(CheckCXXSourceCompiles)\ninclude(CheckCXXSourceRuns)\ninclude(CheckFunctionExists)\ninclude(CheckIncludeFiles)\ninclude(CheckLibraryExists)\ninclude(CheckPrototypeDefinition)\ninclude(CheckStructHasMember)\ninclude(CheckSymbolExists)\ninclude(CheckTypeSize)\ninclude(TestBigEndian)\n\nset(include_files_list\n dlfcn.h\n inttypes.h\n memory.h\n stdint.h\n stdlib.h\n string.h\n sys/stat.h\n sys/types.h\n unistd.h\n\n cairo/cairo-version.h\n pango-1.0/pango/pango-features.h\n unicode/uchar.h\n)\n# check_includes(include_files_list)\n\nset(types_list\n \"long long int\"\n wchar_t\n)\n# check_types(types_list)\n\nlist(APPEND CMAKE_REQUIRED_DEFINITIONS -D_GNU_SOURCE)\nlist(APPEND CMAKE_REQUIRED_LIBRARIES -lm)\nset(functions_list\n feenableexcept\n)\ncheck_functions(functions_list)\n\nfile(APPEND ${AUTOCONFIG_SRC} \"\n/* Version number */\n#cmakedefine PACKAGE_VERSION \\\"${PACKAGE_VERSION}\\\"\n#cmakedefine GRAPHICS_DISABLED ${GRAPHICS_DISABLED}\n#cmakedefine FAST_FLOAT ${FAST_FLOAT}\n#cmakedefine DISABLED_LEGACY_ENGINE ${DISABLED_LEGACY_ENGINE}\n#cmakedefine HAVE_TIFFIO_H ${HAVE_TIFFIO_H}\n#cmakedefine HAVE_NEON ${HAVE_NEON}\n#cmakedefine HAVE_LIBARCHIVE ${HAVE_LIBARCHIVE}\n#cmakedefine HAVE_LIBCURL ${HAVE_LIBCURL}\n\")\n\nif(TESSDATA_PREFIX)\n file(APPEND ${AUTOCONFIG_SRC} \"\n#cmakedefine TESSDATA_PREFIX \\\"${TESSDATA_PREFIX}\\\"\n\")\nendif()\n\n########################################\n\n################################################################################\n" }, { "path": "cmake/SourceGroups.cmake", "content": "# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n# http://www.apache.org/licenses/LICENSE-2.0\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\n#include(SourceGroups)\n\nset(SSRC ${CMAKE_SOURCE_DIR})\nset(BSRC ${CMAKE_BINARY_DIR})\n\nset(_CPP \".*\\\\.cpp\")\nset(CPP \"${_CPP}$\")\n\nset(_H \".*\\\\.h\")\nset(H \"${_H}$\")\n\nset(H_CPP \"(${H}|${CPP})\")\n\nsource_group(\"Resource files\" \".*\\\\.(rc|ico)\")\n\nsource_group(\"api\" \"${SSRC}/api/${H_CPP}\")\nsource_group(\"arch\" \"${SSRC}/arch/${H_CPP}\")\nsource_group(\"ccmain\" \"${SSRC}/ccmain/${H_CPP}\")\nsource_group(\"ccstruct\" \"${SSRC}/ccstruct/${H_CPP}\")\nsource_group(\"ccutil\" \"${SSRC}/ccutil/${H_CPP}\")\nsource_group(\"classify\" \"${SSRC}/classify/${H_CPP}\")\nsource_group(\"cutil\" \"${SSRC}/cutil/${H_CPP}\")\nsource_group(\"dict\" \"${SSRC}/dict/${H_CPP}\")\nsource_group(\"lstm\" \"${SSRC}/lstm/${H_CPP}\")\nsource_group(\"textord\" \"${SSRC}/textord/${H_CPP}\")\nsource_group(\"viewer\" \"${SSRC}/viewer/${H_CPP}\")\nsource_group(\"wordrec\" \"${SSRC}/wordrec/${H_CPP}\")\n" }, { "path": "cmake/SourceLists.cmake", "content": "# Source file lists for tesseract\n# This file contains all source files organized by module\n\n# API module sources\nset(TESSERACT_SRC_API\n src/api/altorenderer.cpp\n src/api/baseapi.cpp\n src/api/capi.cpp\n src/api/hocrrenderer.cpp\n src/api/lstmboxrenderer.cpp\n src/api/pagerenderer.cpp\n src/api/pdfrenderer.cpp\n src/api/renderer.cpp\n src/api/wordstrboxrenderer.cpp\n)\n\n# Architecture-specific sources\nset(TESSERACT_SRC_ARCH\n src/arch/dotproduct.cpp\n src/arch/simddetect.cpp\n src/arch/intsimdmatrix.cpp\n)\n\n# Optional architecture-specific sources (conditionally added)\nset(TESSERACT_SRC_ARCH_AVX\n src/arch/dotproductavx.cpp\n)\n\nset(TESSERACT_SRC_ARCH_AVX2\n src/arch/intsimdmatrixavx2.cpp\n src/arch/dotproductavx.cpp\n)\n\nset(TESSERACT_SRC_ARCH_AVX512F\n src/arch/dotproductavx512.cpp\n)\n\nset(TESSERACT_SRC_ARCH_FMA\n src/arch/dotproductfma.cpp\n)\n\nset(TESSERACT_SRC_ARCH_SSE41\n src/arch/dotproductsse.cpp\n src/arch/intsimdmatrixsse.cpp\n)\n\nset(TESSERACT_SRC_ARCH_NEON\n src/arch/dotproductneon.cpp\n src/arch/intsimdmatrixneon.cpp\n)\n\n# CCMain module sources\nset(TESSERACT_SRC_CCMAIN\n src/ccmain/adaptions.cpp\n src/ccmain/applybox.cpp\n src/ccmain/control.cpp\n src/ccmain/docqual.cpp\n src/ccmain/equationdetect.cpp\n src/ccmain/fixspace.cpp\n src/ccmain/fixxht.cpp\n src/ccmain/linerec.cpp\n src/ccmain/ltrresultiterator.cpp\n src/ccmain/mutableiterator.cpp\n src/ccmain/osdetect.cpp\n src/ccmain/output.cpp\n src/ccmain/pageiterator.cpp\n src/ccmain/pagesegmain.cpp\n src/ccmain/pagewalk.cpp\n src/ccmain/par_control.cpp\n src/ccmain/paragraphs.cpp\n src/ccmain/paramsd.cpp\n src/ccmain/pgedit.cpp\n src/ccmain/recogtraining.cpp\n src/ccmain/reject.cpp\n src/ccmain/resultiterator.cpp\n src/ccmain/superscript.cpp\n src/ccmain/tessbox.cpp\n src/ccmain/tessedit.cpp\n src/ccmain/tesseractclass.cpp\n src/ccmain/tessvars.cpp\n src/ccmain/tfacepp.cpp\n src/ccmain/thresholder.cpp\n src/ccmain/werdit.cpp\n)\n\n# CCStruct module sources\nset(TESSERACT_SRC_CCSTRUCT\n src/ccstruct/blamer.cpp\n src/ccstruct/blobbox.cpp\n src/ccstruct/blobs.cpp\n src/ccstruct/blread.cpp\n src/ccstruct/boxread.cpp\n src/ccstruct/boxword.cpp\n src/ccstruct/ccstruct.cpp\n src/ccstruct/coutln.cpp\n src/ccstruct/detlinefit.cpp\n src/ccstruct/dppoint.cpp\n src/ccstruct/fontinfo.cpp\n src/ccstruct/image.cpp\n src/ccstruct/imagedata.cpp\n src/ccstruct/linlsq.cpp\n src/ccstruct/matrix.cpp\n src/ccstruct/mod128.cpp\n src/ccstruct/normalis.cpp\n src/ccstruct/ocrblock.cpp\n src/ccstruct/ocrpara.cpp\n src/ccstruct/ocrrow.cpp\n src/ccstruct/otsuthr.cpp\n src/ccstruct/pageres.cpp\n src/ccstruct/params_training_featdef.cpp\n src/ccstruct/pdblock.cpp\n src/ccstruct/points.cpp\n src/ccstruct/polyaprx.cpp\n src/ccstruct/polyblk.cpp\n src/ccstruct/quadlsq.cpp\n src/ccstruct/quspline.cpp\n src/ccstruct/ratngs.cpp\n src/ccstruct/rect.cpp\n src/ccstruct/rejctmap.cpp\n src/ccstruct/seam.cpp\n src/ccstruct/split.cpp\n src/ccstruct/statistc.cpp\n src/ccstruct/stepblob.cpp\n src/ccstruct/werd.cpp\n)\n\n# CCUtil module sources\nset(TESSERACT_SRC_CCUTIL\n src/ccutil/ambigs.cpp\n src/ccutil/bitvector.cpp\n src/ccutil/ccutil.cpp\n src/ccutil/errcode.cpp\n src/ccutil/indexmapbidi.cpp\n src/ccutil/params.cpp\n src/ccutil/scanutils.cpp\n src/ccutil/serialis.cpp\n src/ccutil/tessdatamanager.cpp\n src/ccutil/tprintf.cpp\n src/ccutil/unichar.cpp\n src/ccutil/unicharcompress.cpp\n src/ccutil/unicharmap.cpp\n src/ccutil/unicharset.cpp\n)\n\n# Classify module sources\nset(TESSERACT_SRC_CLASSIFY\n src/classify/adaptive.cpp\n src/classify/adaptmatch.cpp\n src/classify/blobclass.cpp\n src/classify/classify.cpp\n src/classify/cluster.cpp\n src/classify/clusttool.cpp\n src/classify/cutoffs.cpp\n src/classify/featdefs.cpp\n src/classify/float2int.cpp\n src/classify/fpoint.cpp\n src/classify/intfeaturespace.cpp\n src/classify/intfx.cpp\n src/classify/intmatcher.cpp\n src/classify/intproto.cpp\n src/classify/kdtree.cpp\n src/classify/mf.cpp\n src/classify/mfoutline.cpp\n src/classify/mfx.cpp\n src/classify/normfeat.cpp\n src/classify/normmatch.cpp\n src/classify/ocrfeatures.cpp\n src/classify/outfeat.cpp\n src/classify/picofeat.cpp\n src/classify/protos.cpp\n src/classify/shapeclassifier.cpp\n src/classify/shapetable.cpp\n src/classify/tessclassifier.cpp\n src/classify/trainingsample.cpp\n)\n\n# CUtil module sources\nset(TESSERACT_SRC_CUTIL\n src/cutil/oldlist.cpp\n)\n\n# Dict module sources\nset(TESSERACT_SRC_DICT\n src/dict/context.cpp\n src/dict/dawg.cpp\n src/dict/dawg_cache.cpp\n src/dict/dict.cpp\n src/dict/hyphen.cpp\n src/dict/permdawg.cpp\n src/dict/stopper.cpp\n src/dict/trie.cpp\n)\n\n# LSTM module sources\nset(TESSERACT_SRC_LSTM\n src/lstm/convolve.cpp\n src/lstm/fullyconnected.cpp\n src/lstm/functions.cpp\n src/lstm/input.cpp\n src/lstm/lstm.cpp\n src/lstm/lstmrecognizer.cpp\n src/lstm/maxpool.cpp\n src/lstm/network.cpp\n src/lstm/networkio.cpp\n src/lstm/parallel.cpp\n src/lstm/plumbing.cpp\n src/lstm/recodebeam.cpp\n src/lstm/reconfig.cpp\n src/lstm/reversed.cpp\n src/lstm/series.cpp\n src/lstm/stridemap.cpp\n src/lstm/weightmatrix.cpp\n)\n\n# TextOrd module sources\nset(TESSERACT_SRC_TEXTORD\n src/textord/alignedblob.cpp\n src/textord/baselinedetect.cpp\n src/textord/bbgrid.cpp\n src/textord/blkocc.cpp\n src/textord/blobgrid.cpp\n src/textord/ccnontextdetect.cpp\n src/textord/cjkpitch.cpp\n src/textord/colfind.cpp\n src/textord/colpartition.cpp\n src/textord/colpartitiongrid.cpp\n src/textord/colpartitionset.cpp\n src/textord/devanagari_processing.cpp\n src/textord/drawtord.cpp\n src/textord/edgblob.cpp\n src/textord/edgloop.cpp\n src/textord/equationdetectbase.cpp\n src/textord/fpchop.cpp\n src/textord/gap_map.cpp\n src/textord/imagefind.cpp\n src/textord/linefind.cpp\n src/textord/makerow.cpp\n src/textord/oldbasel.cpp\n src/textord/pithsync.cpp\n src/textord/pitsync1.cpp\n src/textord/scanedg.cpp\n src/textord/sortflts.cpp\n src/textord/strokewidth.cpp\n src/textord/tabfind.cpp\n src/textord/tablefind.cpp\n src/textord/tablerecog.cpp\n src/textord/tabvector.cpp\n src/textord/textlineprojection.cpp\n src/textord/textord.cpp\n src/textord/topitch.cpp\n src/textord/tordmain.cpp\n src/textord/tospace.cpp\n src/textord/tovars.cpp\n src/textord/underlin.cpp\n src/textord/wordseg.cpp\n src/textord/workingpartset.cpp\n)\n\n# Viewer module sources\nset(TESSERACT_SRC_VIEWER\n src/viewer/scrollview.cpp\n src/viewer/svmnode.cpp\n src/viewer/svutil.cpp\n)\n\n# WordRec module sources\nset(TESSERACT_SRC_WORDREC\n src/wordrec/associate.cpp\n src/wordrec/chop.cpp\n src/wordrec/chopper.cpp\n src/wordrec/drawfx.cpp\n src/wordrec/findseam.cpp\n src/wordrec/gradechop.cpp\n src/wordrec/language_model.cpp\n src/wordrec/lm_consistency.cpp\n src/wordrec/lm_pain_points.cpp\n src/wordrec/lm_state.cpp\n src/wordrec/outlines.cpp\n src/wordrec/params_model.cpp\n src/wordrec/pieces.cpp\n src/wordrec/plotedges.cpp\n src/wordrec/render.cpp\n src/wordrec/segsearch.cpp\n src/wordrec/tface.cpp\n src/wordrec/wordclass.cpp\n src/wordrec/wordrec.cpp\n)\n\n# Legacy engine sources (excluded when DISABLED_LEGACY_ENGINE is ON)\nset(TESSERACT_SRC_LEGACY\n src/ccmain/adaptions.cpp\n src/ccmain/docqual.cpp\n src/ccmain/equationdetect.cpp\n src/ccmain/fixspace.cpp\n src/ccmain/fixxht.cpp\n src/ccmain/osdetect.cpp\n src/ccmain/par_control.cpp\n src/ccmain/recogtraining.cpp\n src/ccmain/superscript.cpp\n src/ccmain/tessbox.cpp\n src/ccmain/tfacepp.cpp\n src/ccstruct/fontinfo.cpp\n src/ccstruct/params_training_featdef.cpp\n src/ccutil/ambigs.cpp\n src/ccutil/bitvector.cpp\n src/ccutil/indexmapbidi.cpp\n src/classify/adaptive.cpp\n src/classify/adaptmatch.cpp\n src/classify/blobclass.cpp\n src/classify/cluster.cpp\n src/classify/clusttool.cpp\n src/classify/cutoffs.cpp\n src/classify/featdefs.cpp\n src/classify/float2int.cpp\n src/classify/fpoint.cpp\n src/classify/intfeaturespace.cpp\n src/classify/intfx.cpp\n src/classify/intmatcher.cpp\n src/classify/intproto.cpp\n src/classify/kdtree.cpp\n src/classify/mf.cpp\n src/classify/mfoutline.cpp\n src/classify/mfx.cpp\n src/classify/normfeat.cpp\n src/classify/normmatch.cpp\n src/classify/ocrfeatures.cpp\n src/classify/outfeat.cpp\n src/classify/picofeat.cpp\n src/classify/protos.cpp\n src/classify/shapeclassifier.cpp\n src/classify/shapetable.cpp\n src/classify/tessclassifier.cpp\n src/classify/trainingsample.cpp\n src/dict/permdawg.cpp\n src/dict/hyphen.cpp\n src/wordrec/associate.cpp\n src/wordrec/chop.cpp\n src/wordrec/chopper.cpp\n src/wordrec/drawfx.cpp\n src/wordrec/findseam.cpp\n src/wordrec/gradechop.cpp\n src/wordrec/language_model.cpp\n src/wordrec/lm_consistency.cpp\n src/wordrec/lm_pain_points.cpp\n src/wordrec/lm_state.cpp\n src/wordrec/outlines.cpp\n src/wordrec/params_model.cpp\n src/wordrec/pieces.cpp\n src/wordrec/plotedges.cpp\n src/wordrec/render.cpp\n src/wordrec/segsearch.cpp\n src/wordrec/wordclass.cpp\n)\n\n# Header files\nset(TESSERACT_HDR_INCLUDE\n include/tesseract/baseapi.h\n include/tesseract/capi.h\n include/tesseract/export.h\n include/tesseract/ltrresultiterator.h\n include/tesseract/ocrclass.h\n include/tesseract/osdetect.h\n include/tesseract/pageiterator.h\n include/tesseract/publictypes.h\n include/tesseract/renderer.h\n include/tesseract/resultiterator.h\n include/tesseract/unichar.h\n)\n\n# Internal header files\nset(TESSERACT_HDR_INTERNAL\n src/api/pdf_ttf.h\n src/arch/dotproduct.h\n src/arch/intsimdmatrix.h\n src/arch/simddetect.h\n src/ccmain/control.h\n src/ccmain/docqual.h\n src/ccmain/equationdetect.h\n src/ccmain/fixspace.h\n src/ccmain/mutableiterator.h\n src/ccmain/output.h\n src/ccmain/paragraphs.h\n src/ccmain/paragraphs_internal.h\n src/ccmain/paramsd.h\n src/ccmain/pgedit.h\n src/ccmain/reject.h\n src/ccmain/tesseractclass.h\n src/ccmain/tessvars.h\n src/ccmain/thresholder.h\n src/ccmain/werdit.h\n src/ccstruct/blamer.h\n src/ccstruct/blobbox.h\n src/ccstruct/blobs.h\n src/ccstruct/blread.h\n src/ccstruct/boxread.h\n src/ccstruct/boxword.h\n src/ccstruct/ccstruct.h\n src/ccstruct/coutln.h\n src/ccstruct/crakedge.h\n src/ccstruct/debugpixa.h\n src/ccstruct/detlinefit.h\n src/ccstruct/dppoint.h\n src/ccstruct/fontinfo.h\n src/ccstruct/image.h\n src/ccstruct/imagedata.h\n src/ccstruct/linlsq.h\n src/ccstruct/matrix.h\n src/ccstruct/mod128.h\n src/ccstruct/normalis.h\n src/ccstruct/ocrblock.h\n src/ccstruct/ocrpara.h\n src/ccstruct/ocrrow.h\n src/ccstruct/otsuthr.h\n src/ccstruct/pageres.h\n src/ccstruct/params_training_featdef.h\n src/ccstruct/pdblock.h\n src/ccstruct/points.h\n src/ccstruct/polyaprx.h\n src/ccstruct/polyblk.h\n src/ccstruct/quadlsq.h\n src/ccstruct/quadratc.h\n src/ccstruct/quspline.h\n src/ccstruct/ratngs.h\n src/ccstruct/rect.h\n src/ccstruct/rejctmap.h\n src/ccstruct/seam.h\n src/ccstruct/split.h\n src/ccstruct/statistc.h\n src/ccstruct/stepblob.h\n src/ccstruct/werd.h\n src/ccutil/ambigs.h\n src/ccutil/bitvector.h\n src/ccutil/ccutil.h\n src/ccutil/clst.h\n src/ccutil/elst.h\n src/ccutil/elst2.h\n src/ccutil/errcode.h\n src/ccutil/fileerr.h\n src/ccutil/genericvector.h\n src/ccutil/genericheap.h\n src/ccutil/helpers.h\n src/ccutil/host.h\n src/ccutil/indexmapbidi.h\n src/ccutil/kdpair.h\n src/ccutil/lsterr.h\n src/ccutil/object_cache.h\n src/ccutil/params.h\n src/ccutil/qrsequence.h\n src/ccutil/scanutils.h\n src/ccutil/serialis.h\n src/ccutil/sorthelper.h\n src/ccutil/tessdatamanager.h\n src/ccutil/tesserrstream.h\n src/ccutil/tesstypes.h\n src/ccutil/tprintf.h\n src/ccutil/unicity_table.h\n src/ccutil/unicharcompress.h\n src/ccutil/unicharmap.h\n src/ccutil/unicharset.h\n src/ccutil/universalambigs.h\n src/classify/adaptive.h\n src/classify/classify.h\n src/classify/cluster.h\n src/classify/clusttool.h\n src/classify/featdefs.h\n src/classify/float2int.h\n src/classify/fpoint.h\n src/classify/intfeaturespace.h\n src/classify/intfx.h\n src/classify/intmatcher.h\n src/classify/intproto.h\n src/classify/kdtree.h\n src/classify/mf.h\n src/classify/mfdefs.h\n src/classify/mfoutline.h\n src/classify/mfx.h\n src/classify/normfeat.h\n src/classify/normmatch.h\n src/classify/ocrfeatures.h\n src/classify/outfeat.h\n src/classify/picofeat.h\n src/classify/protos.h\n src/classify/shapeclassifier.h\n src/classify/shapetable.h\n src/classify/tessclassifier.h\n src/classify/trainingsample.h\n src/cutil/bitvec.h\n src/cutil/oldlist.h\n src/dict/dawg.h\n src/dict/dawg_cache.h\n src/dict/dict.h\n src/dict/matchdefs.h\n src/dict/stopper.h\n src/dict/trie.h\n src/lstm/convolve.h\n src/lstm/fullyconnected.h\n src/lstm/functions.h\n src/lstm/input.h\n src/lstm/lstm.h\n src/lstm/lstmrecognizer.h\n src/lstm/maxpool.h\n src/lstm/network.h\n src/lstm/networkio.h\n src/lstm/networkscratch.h\n src/lstm/parallel.h\n src/lstm/plumbing.h\n src/lstm/recodebeam.h\n src/lstm/reconfig.h\n src/lstm/reversed.h\n src/lstm/series.h\n src/lstm/static_shape.h\n src/lstm/stridemap.h\n src/lstm/weightmatrix.h\n src/textord/alignedblob.h\n src/textord/baselinedetect.h\n src/textord/bbgrid.h\n src/textord/blkocc.h\n src/textord/blobgrid.h\n src/textord/ccnontextdetect.h\n src/textord/cjkpitch.h\n src/textord/colfind.h\n src/textord/colpartition.h\n src/textord/colpartitiongrid.h\n src/textord/colpartitionset.h\n src/textord/devanagari_processing.h\n src/textord/drawtord.h\n src/textord/edgblob.h\n src/textord/edgloop.h\n src/textord/equationdetectbase.h\n src/textord/fpchop.h\n src/textord/gap_map.h\n src/textord/imagefind.h\n src/textord/linefind.h\n src/textord/makerow.h\n src/textord/oldbasel.h\n src/textord/pithsync.h\n src/textord/pitsync1.h\n src/textord/scanedg.h\n src/textord/sortflts.h\n src/textord/strokewidth.h\n src/textord/tabfind.h\n src/textord/tablefind.h\n src/textord/tablerecog.h\n src/textord/tabvector.h\n src/textord/textlineprojection.h\n src/textord/textord.h\n src/textord/topitch.h\n src/textord/tordmain.h\n src/textord/tovars.h\n src/textord/underlin.h\n src/textord/wordseg.h\n src/textord/workingpartset.h\n src/viewer/scrollview.h\n src/viewer/svmnode.h\n src/viewer/svutil.h\n src/wordrec/associate.h\n src/wordrec/chop.h\n src/wordrec/drawfx.h\n src/wordrec/findseam.h\n src/wordrec/language_model.h\n src/wordrec/lm_consistency.h\n src/wordrec/lm_pain_points.h\n src/wordrec/lm_state.h\n src/wordrec/outlines.h\n src/wordrec/params_model.h\n src/wordrec/plotedges.h\n src/wordrec/render.h\n src/wordrec/wordrec.h\n)\n\n# Combine all core source files\nset(TESSERACT_SRC_CORE\n ${TESSERACT_SRC_API}\n ${TESSERACT_SRC_CCMAIN}\n ${TESSERACT_SRC_CCSTRUCT}\n ${TESSERACT_SRC_CCUTIL}\n ${TESSERACT_SRC_CLASSIFY}\n ${TESSERACT_SRC_CUTIL}\n ${TESSERACT_SRC_DICT}\n ${TESSERACT_SRC_LSTM}\n ${TESSERACT_SRC_TEXTORD}\n ${TESSERACT_SRC_VIEWER}\n ${TESSERACT_SRC_WORDREC}\n)\n" }, { "path": "cmake/templates/TesseractConfig.cmake.in", "content": "# ===================================================================================\n# The Tesseract CMake configuration file\n#\n# ** File generated automatically, do not modify **\n#\n# Usage from an external project:\n# In your CMakeLists.txt, add these lines:\n#\n# find_package(Tesseract REQUIRED)\n# target_link_libraries(MY_TARGET_NAME Tesseract::libtesseract)\n#\n# This file will define the following variables:\n# - Tesseract_LIBRARIES : The list of all imported targets.\n# - Tesseract_INCLUDE_DIRS : The Tesseract include directories.\n# - Tesseract_LIBRARY_DIRS : The Tesseract library directories.\n# - Tesseract_VERSION : The version of this Tesseract build: \"@VERSION_PLAIN@\"\n# - Tesseract_VERSION_MAJOR : Major version part of Tesseract_VERSION: \"@VERSION_MAJOR@\"\n# - Tesseract_VERSION_MINOR : Minor version part of Tesseract_VERSION: \"@VERSION_MINOR@\"\n# - Tesseract_VERSION_PATCH : Patch version part of Tesseract_VERSION: \"@VERSION_PATCH@\"\n#\n# ===================================================================================\n\ninclude(CMakeFindDependencyMacro)\nfind_dependency(Leptonica)\n\ninclude(${CMAKE_CURRENT_LIST_DIR}/TesseractTargets.cmake)\n\n@PACKAGE_INIT@\n\nSET(Tesseract_VERSION @VERSION_PLAIN@)\nSET(Tesseract_VERSION_MAJOR @VERSION_MAJOR@)\nSET(Tesseract_VERSION_MINOR @VERSION_MINOR@)\nSET(Tesseract_VERSION_PATCH @VERSION_PATCH@)\n\nset_and_check(Tesseract_INCLUDE_DIRS \"@PACKAGE_INCLUDE_DIR@\")\nset_and_check(Tesseract_LIBRARY_DIRS \"@PACKAGE_LIBRARY_DIRS@\")\nset(Tesseract_LIBRARIES @tesseract_OUTPUT_NAME@)\n\ncheck_required_components(Tesseract)\n" }, { "path": "cmake/templates/cmake_uninstall.cmake.in", "content": "# https://gitlab.kitware.com/cmake/community/wikis/FAQ#can-i-do-make-uninstall-with-cmake\nif(NOT EXISTS \"@CMAKE_BINARY_DIR@/install_manifest.txt\")\n message(FATAL_ERROR \"Cannot find install manifest: @CMAKE_BINARY_DIR@/install_manifest.txt\")\nendif(NOT EXISTS \"@CMAKE_BINARY_DIR@/install_manifest.txt\")\n\nfile(READ \"@CMAKE_BINARY_DIR@/install_manifest.txt\" files)\nstring(REGEX REPLACE \"\\n\" \";\" files \"${files}\")\nforeach(file ${files})\n message(STATUS \"Uninstalling $ENV{DESTDIR}${file}\")\n if(IS_SYMLINK \"$ENV{DESTDIR}${file}\" OR EXISTS \"$ENV{DESTDIR}${file}\")\n exec_program(\n \"@CMAKE_COMMAND@\" ARGS \"-E remove \\\"$ENV{DESTDIR}${file}\\\"\"\n OUTPUT_VARIABLE rm_out\n RETURN_VALUE rm_retval\n )\n if(NOT \"${rm_retval}\" STREQUAL 0)\n message(FATAL_ERROR \"Problem when removing $ENV{DESTDIR}${file}\")\n endif(NOT \"${rm_retval}\" STREQUAL 0)\n else(IS_SYMLINK \"$ENV{DESTDIR}${file}\" OR EXISTS \"$ENV{DESTDIR}${file}\")\n message(STATUS \"File $ENV{DESTDIR}${file} does not exist.\")\n endif(IS_SYMLINK \"$ENV{DESTDIR}${file}\" OR EXISTS \"$ENV{DESTDIR}${file}\")\nendforeach(file)\n" }, { "path": "configure.ac", "content": "# -*-Shell-script-*-\n#\n# Copyright (c) Luc Vincent\n\n# ----------------------------------------\n# Initialization\n# ----------------------------------------\nAC_PREREQ([2.69])\nAC_INIT([tesseract],\n [m4_esyscmd_s([test -d .git && git describe --abbrev=4 2>/dev/null || cat VERSION])],\n [https://github.com/tesseract-ocr/tesseract/issues],,\n [https://github.com/tesseract-ocr/tesseract/])\n\n# Store command like options for CXXFLAGS\nOLD_CXXFLAGS=$CXXFLAGS\nAC_PROG_CXX([g++ clang++])\n# reset compiler flags to initial flags\nAC_LANG([C++])\nAC_LANG_COMPILER_REQUIRE\nCXXFLAGS=${CXXFLAGS:-\"\"}\nAC_CONFIG_MACRO_DIR([m4])\nAC_CONFIG_AUX_DIR([config])\nAC_CONFIG_SRCDIR([src/tesseract.cpp])\nAC_PREFIX_DEFAULT([/usr/local])\n\n# Automake configuration. Do not require README file (we use README.md).\nAM_INIT_AUTOMAKE([foreign subdir-objects nostdinc])\n\n# Define date of package, etc. Could be useful in auto-generated\n# documentation.\nPACKAGE_YEAR=2025\nPACKAGE_DATE=\"12/26\"\n\nabs_top_srcdir=`AS_DIRNAME([$0])`\n\nAC_DEFINE_UNQUOTED([PACKAGE_NAME], [\"${PACKAGE_NAME}\"], [Name of package])\nAC_DEFINE_UNQUOTED([PACKAGE_VERSION], [\"${PACKAGE_VERSION}\"], [Version number])\nAC_DEFINE_UNQUOTED([PACKAGE_YEAR], [\"$PACKAGE_YEAR\"], [Official year for this release])\nAC_DEFINE_UNQUOTED([PACKAGE_DATE], [\"$PACKAGE_DATE\"], [Official date of release])\n\nAC_SUBST([PACKAGE_NAME])\nAC_SUBST([PACKAGE_VERSION])\nAC_SUBST([PACKAGE_YEAR])\nAC_SUBST([PACKAGE_DATE])\n\nGENERIC_LIBRARY_NAME=tesseract\n\n# Release versioning. Get versions from PACKAGE_VERSION.\nAX_SPLIT_VERSION\nGENERIC_MAJOR_VERSION=$(echo \"$AX_MAJOR_VERSION\" | $SED 's/^[[^0-9]]*//')\nGENERIC_MINOR_VERSION=$AX_MINOR_VERSION\nGENERIC_MICRO_VERSION=`echo \"$AX_POINT_VERSION\" | $SED 's/^\\([[0-9]][[0-9]]*\\).*/\\1/'`\n\n# API version (often = GENERIC_MAJOR_VERSION.GENERIC_MINOR_VERSION)\nGENERIC_API_VERSION=$GENERIC_MAJOR_VERSION.$GENERIC_MINOR_VERSION\nGENERIC_LIBRARY_VERSION=$GENERIC_MAJOR_VERSION:$GENERIC_MINOR_VERSION\nAC_SUBST([GENERIC_API_VERSION])\nAC_SUBST([GENERIC_MAJOR_VERSION])\nAC_SUBST([GENERIC_MINOR_VERSION])\nAC_SUBST([GENERIC_MICRO_VERSION])\n\nAC_SUBST([GENERIC_LIBRARY_VERSION])\nPACKAGE=$GENERIC_LIBRARY_NAME\nAC_SUBST([GENERIC_LIBRARY_NAME])\n\nGENERIC_VERSION=$GENERIC_MAJOR_VERSION.$GENERIC_MINOR_VERSION.$GENERIC_MICRO_VERSION\nGENERIC_RELEASE=$GENERIC_MAJOR_VERSION.$GENERIC_MINOR_VERSION\nAC_SUBST([GENERIC_RELEASE])\nAC_SUBST([GENERIC_VERSION])\n\nAC_CONFIG_HEADERS([include/config_auto.h:config/config.h.in])\n\n# default conditional\nAM_CONDITIONAL([T_WIN], false)\nAM_CONDITIONAL([MINGW], false)\nAM_CONDITIONAL([GRAPHICS_DISABLED], false)\nAC_SUBST([AM_CPPFLAGS])\n\n# Be less noisy by default.\n# Can be overridden with `configure --disable-silent-rules` or with `make V=1`.\nAM_SILENT_RULES([yes])\n\n#############################\n#\n# Platform specific setup\n#\n#############################\nAC_CANONICAL_HOST\ncase \"${host_os}\" in\n mingw*)\n AC_DEFINE_UNQUOTED([MINGW], 1, [This is a MinGW system])\n AM_CONDITIONAL([T_WIN], true)\n AM_CONDITIONAL([MINGW], true)\n AM_CONDITIONAL([ADD_RT], false)\n AC_SUBST([AM_LDFLAGS], ['-no-undefined'])\n ;;\n cygwin*)\n AM_CONDITIONAL([ADD_RT], false)\n AC_SUBST([NOUNDEFINED], ['-no-undefined'])\n ;;\n solaris*)\n LIBS=\"$LIBS -lsocket -lnsl -lrt -lxnet\"\n AM_CONDITIONAL([ADD_RT], true)\n ;;\n *darwin*)\n AM_CONDITIONAL([ADD_RT], false)\n ;;\n *android*|openbsd*)\n AM_CONDITIONAL([ADD_RT], false)\n ;;\n powerpc-*-darwin*)\n ;;\n *)\n # default\n AM_CONDITIONAL([ADD_RT], true)\n ;;\nesac\n\nWERROR=-Werror\n# The test code used by AX_CHECK_COMPILE_FLAG uses an empty statement\n# and unused macros which must not raise a compiler error, but it must\n# be an error if flags like -avx are ignored on ARM and other\n# architectures because they are unsupported.\nAX_CHECK_COMPILE_FLAG([-Werror=unused-command-line-argument], [WERROR=-Werror=unused-command-line-argument])\n\n## Checks for supported compiler options.\n\nAM_CONDITIONAL([HAVE_AVX], false)\nAM_CONDITIONAL([HAVE_AVX2], false)\nAM_CONDITIONAL([HAVE_AVX512F], false)\nAM_CONDITIONAL([HAVE_FMA], false)\nAM_CONDITIONAL([HAVE_SSE4_1], false)\nAM_CONDITIONAL([HAVE_NEON], false)\nAM_CONDITIONAL([HAVE_RVV], false)\n\ncase \"${host_cpu}\" in\n\n amd64|*86*)\n\n AX_CHECK_COMPILE_FLAG([-mavx], [avx=true], [avx=false], [$WERROR])\n AM_CONDITIONAL([HAVE_AVX], ${avx})\n if $avx; then\n AC_DEFINE([HAVE_AVX], [1], [Enable AVX instructions])\n fi\n\n AX_CHECK_COMPILE_FLAG([-mavx2], [avx2=true], [avx2=false], [$WERROR])\n AM_CONDITIONAL([HAVE_AVX2], $avx2)\n if $avx2; then\n AC_DEFINE([HAVE_AVX2], [1], [Enable AVX2 instructions])\n fi\n\n AX_CHECK_COMPILE_FLAG([-mavx512f], [avx512f=true], [avx512f=false], [$WERROR])\n AM_CONDITIONAL([HAVE_AVX512F], $avx512f)\n if $avx512f; then\n AC_DEFINE([HAVE_AVX512F], [1], [Enable AVX512F instructions])\n fi\n\n AX_CHECK_COMPILE_FLAG([-mfma], [fma=true], [fma=false], [$WERROR])\n AM_CONDITIONAL([HAVE_FMA], $fma)\n if $fma; then\n AC_DEFINE([HAVE_FMA], [1], [Enable FMA instructions])\n fi\n\n AX_CHECK_COMPILE_FLAG([-msse4.1], [sse41=true], [sse41=false], [$WERROR])\n AM_CONDITIONAL([HAVE_SSE4_1], $sse41)\n if $sse41; then\n AC_DEFINE([HAVE_SSE4_1], [1], [Enable SSE 4.1 instructions])\n fi\n\n ;;\n\n aarch64*|arm64)\n\n # ARMv8 always has NEON and does not need special compiler flags.\n AM_CONDITIONAL([HAVE_NEON], true)\n AC_DEFINE([HAVE_NEON], [1], [Enable NEON instructions])\n ;;\n\n arm*)\n\n AX_CHECK_COMPILE_FLAG([-mfpu=neon], [neon=true], [neon=false], [$WERROR])\n AM_CONDITIONAL([HAVE_NEON], $neon)\n if $neon; then\n AC_DEFINE([HAVE_NEON], [1], [Enable NEON instructions])\n NEON_CXXFLAGS=\"-mfpu=neon\"\n AC_SUBST([NEON_CXXFLAGS])\n check_for_neon=1\n fi\n\n ;;\n\n riscv*)\n\n AX_CHECK_COMPILE_FLAG([-march=rv64gcv], [rvv=true], [rvv=false], [$WERROR])\n AM_CONDITIONAL([HAVE_RVV], [$rvv])\n if $rvv; then\n AC_DEFINE([HAVE_RVV], [1], [Enable RVV instructions])\n check_for_rvv=1\n fi\n ;;\n\n *)\n\n AC_MSG_WARN([No compiler options for $host_cpu])\n\nesac\n\n# check whether feenableexcept is supported. some C libraries (e.g. uclibc) don't.\nAC_CHECK_FUNCS([feenableexcept])\n\n# additional checks for NEON targets\nif test x$check_for_neon = x1; then\n AC_MSG_NOTICE([checking how to detect NEON availability])\n AC_CHECK_FUNCS([getauxval elf_aux_info android_getCpuFamily])\n\n if test $ac_cv_func_getauxval = no && test $ac_cv_func_elf_aux_info = no && test $ac_cv_func_android_getCpuFamily = no; then\n AC_MSG_WARN([NEON is available, but we don't know how to check for it. Will not be able to use NEON.])\n fi\nfi\n\n# additional checks for RVV targets\nif test x$check_for_rvv = x1; then\n AC_MSG_NOTICE([checking how to detect RVV availability])\n AC_CHECK_FUNCS([getauxval elf_aux_info])\n\n if test $ac_cv_func_getauxval = no && test $ac_cv_func_elf_aux_info = no; then\n AC_MSG_WARN([RVV is available, but we don't know how to check for it. Will not be able to use RVV.])\n fi\nfi\n\nAX_CHECK_COMPILE_FLAG([-fopenmp-simd], [openmp_simd=true], [openmp_simd=false], [$WERROR])\nAM_CONDITIONAL([OPENMP_SIMD], $openmp_simd)\n\nAC_ARG_WITH([extra-includes],\n [AS_HELP_STRING([--with-extra-includes=DIR],\n [Define an additional directory for include files])],\n [if test -d \"$withval\" ; then\n CFLAGS=\"$CFLAGS -I$withval\"\n else\n AC_MSG_ERROR([Cannot stat directory $withval])\n fi])\n\nAC_ARG_WITH([extra-libraries],\n [AS_HELP_STRING([--with-extra-libraries=DIR],\n [Define an additional directory for library files])],\n [if test -d \"$withval\" ; then\n LDFLAGS=\"$LDFLAGS -L$withval\"\n else\n AC_MSG_ERROR([Cannot stat directory $withval])\n fi])\n\nAC_MSG_CHECKING([--enable-float32 argument])\nAC_ARG_ENABLE([float32],\n\t AS_HELP_STRING([--disable-float32], [disable float and enable double for LSTM]))\nAC_MSG_RESULT([$enable_float32])\nif test \"$enable_float32\" != \"no\"; then\n AC_DEFINE([FAST_FLOAT], [1], [Enable float for LSTM])\nfi\n\nAC_MSG_CHECKING([--enable-graphics argument])\nAC_ARG_ENABLE([graphics],\n AS_HELP_STRING([--disable-graphics], [disable graphics (ScrollView)]))\nAC_MSG_RESULT([$enable_graphics])\nif test \"$enable_graphics\" = \"no\"; then\n AC_DEFINE([GRAPHICS_DISABLED], [], [Disable graphics])\n AM_CONDITIONAL([GRAPHICS_DISABLED], true)\nfi\n\nAC_MSG_CHECKING([--enable-legacy argument])\nAC_ARG_ENABLE([legacy],\n AS_HELP_STRING([--disable-legacy], [disable the legacy OCR engine]))\nAC_MSG_RESULT([$enable_legacy])\nAM_CONDITIONAL([DISABLED_LEGACY_ENGINE], test \"$enable_legacy\" = \"no\")\nif test \"$enable_legacy\" = \"no\"; then\n AC_DEFINE([DISABLED_LEGACY_ENGINE], [1], [Disable legacy OCR engine])\nfi\n\n# check whether to build OpenMP support\nAC_OPENMP\n\nhave_tiff=false\n# Note that the first usage of AC_CHECK_HEADERS must be unconditional.\nAC_CHECK_HEADERS([tiffio.h], [have_tiff=true], [have_tiff=false])\n\n# Configure arguments which allow disabling some optional libraries.\nAC_ARG_WITH([archive],\n AS_HELP_STRING([--with-archive],\n [Build with libarchive which supports compressed model files @<:@default=check@:>@]),\n [], [with_archive=check])\nAC_ARG_WITH([curl],\n AS_HELP_STRING([--with-curl],\n [Build with libcurl which supports processing an image URL @<:@default=check@:>@]),\n [], [with_curl=check])\n\n# https://lists.apple.com/archives/unix-porting/2009/Jan/msg00026.html\nm4_define([MY_CHECK_FRAMEWORK],\n [AC_CACHE_CHECK([if -framework $1 works],[my_cv_framework_$1],\n [save_LIBS=\"$LIBS\"\n LIBS=\"$LIBS -framework $1\"\n AC_LINK_IFELSE([AC_LANG_PROGRAM([],[])],\n [my_cv_framework_$1=yes],\n [my_cv_framework_$1=no])\n LIBS=\"$save_LIBS\"\n ])\n if test \"$my_cv_framework_$1\"=\"yes\"; then\n AC_DEFINE(AS_TR_CPP([HAVE_FRAMEWORK_$1]), 1,\n [Define if you have the $1 framework])\n AS_TR_CPP([FRAMEWORK_$1])=\"-framework $1\"\n AC_SUBST(AS_TR_CPP([FRAMEWORK_$1]))\n fi]\n)\n\ncase \"${host_os}\" in\n *darwin* | *-macos10*)\n MY_CHECK_FRAMEWORK([Accelerate])\n if test $my_cv_framework_Accelerate = yes; then\n AM_CPPFLAGS=\"-DHAVE_FRAMEWORK_ACCELERATE $AM_CPPFLAGS\"\n AM_LDFLAGS=\"$AM_LDFLAGS -framework Accelerate\"\n fi\n ;;\n *)\n # default\n ;;\nesac\n\n# check whether to build tesseract with -fvisibility=hidden -fvisibility-inlines-hidden\n# http://gcc.gnu.org/wiki/Visibility\n# https://groups.google.com/g/tesseract-dev/c/l2ZFrpgYkSc/m/_cdYSRDSXuUJ\nAC_MSG_CHECKING([--enable-visibility argument])\nAC_ARG_ENABLE([visibility],\n AS_HELP_STRING([--enable-visibility],\n [enable experimental build with -fvisibility [default=no]]))\nAC_MSG_RESULT([$enable_visibility])\nAM_CONDITIONAL([VISIBILITY], [test \"$enable_visibility\" = \"yes\"])\n\n# Check if tessdata-prefix is disabled\nAC_MSG_CHECKING([whether to use tessdata-prefix])\nAC_ARG_ENABLE([tessdata-prefix],\n [AS_HELP_STRING([--disable-tessdata-prefix],\n [don't set TESSDATA-PREFIX during compile])],\n [tessdata_prefix=\"no\"], [tessdata_prefix=\"yes\"])\nAC_MSG_RESULT([$tessdata_prefix])\nAM_CONDITIONAL([NO_TESSDATA_PREFIX], [test \"$tessdata_prefix\" = \"no\"])\n\n\n# Detect Clang compiler\nAC_MSG_CHECKING([if compiling with clang])\nAC_COMPILE_IFELSE(\n[AC_LANG_PROGRAM([], [[\n#ifndef __clang__\n not clang\n#endif\n]])],\n[CLANG=yes], [CLANG=no])\nAC_MSG_RESULT([$CLANG])\n\n# Check whether to enable debugging\nAC_MSG_CHECKING([whether to enable debugging])\nAC_ARG_ENABLE([debug],\n AS_HELP_STRING([--enable-debug], [turn on debugging [default=no]]))\nAC_MSG_RESULT([$enable_debug])\nif test x\"$enable_debug\" = x\"yes\"; then\n CXXFLAGS=${CXXFLAGS:-\"-O2\"}\n AM_CPPFLAGS=\"$AM_CPPFLAGS -g -Wall -DDEBUG -pedantic\"\n AM_CXXFLAGS=\"$AM_CXXFLAGS -g -Wall -DDEBUG -pedantic\"\n if test \"x$CLANG\" = \"xyes\"; then\n # https://clang.llvm.org/docs/CommandGuide/clang.html\n # clang treats -Og as -O1\n AM_CPPFLAGS=\"$AM_CPPFLAGS -O0\"\n AM_CXXFLAGS=\"$AM_CXXFLAGS -O0\"\n else\n AM_CPPFLAGS=\"$AM_CPPFLAGS -Og\"\n AM_CXXFLAGS=\"$AM_CXXFLAGS -Og\"\n fi\nelse\n AM_CXXFLAGS=\"$AM_CXXFLAGS -O2 -DNDEBUG\"\n AM_CPPFLAGS=\"$AM_CPPFLAGS -O2 -DNDEBUG\"\nfi\n\n# ----------------------------------------\n# Init libtool\n# ----------------------------------------\n\nLT_INIT\n\n\n# ----------------------------------------\n# C++ related options\n# ----------------------------------------\ndnl **********************\ndnl Turn on C++17 or newer\ndnl **********************\n\nCPLUSPLUS=\nAX_CHECK_COMPILE_FLAG([-std=c++17], [CPLUSPLUS=17], [], [$WERROR])\nAX_CHECK_COMPILE_FLAG([-std=c++20], [CPLUSPLUS=20], [], [$WERROR])\n\nif test -z \"$CPLUSPLUS\"; then\n AC_MSG_ERROR([Your compiler does not have the necessary C++17 support! Cannot proceed.])\nfi\n\n# Set C++17 or newer support based on platform/compiler\ncase \"${host_os}\" in\n cygwin*)\n CXXFLAGS=\"$CXXFLAGS -std=gnu++$CPLUSPLUS\"\n ;;\n *-darwin* | *-macos10*)\n CXXFLAGS=\"$CXXFLAGS -std=c++$CPLUSPLUS\"\n if test \"x$CLANG\" = \"xyes\"; then\n LDFLAGS=\"$LDFLAGS -stdlib=libc++\"\n fi\n ;;\n *)\n # default\n CXXFLAGS=\"$CXXFLAGS -std=c++$CPLUSPLUS\"\n ;;\nesac\n\n\n# ----------------------------------------\n# Check for libraries\n# ----------------------------------------\n\nAC_SEARCH_LIBS([pthread_create], [pthread])\n\n# Set PKG_CONFIG_PATH for macOS with Homebrew unless it is already set.\nAC_CHECK_PROG([have_brew], brew, true, false)\nif $have_brew; then\n brew_prefix=$(brew --prefix)\n if test -z \"$PKG_CONFIG_PATH\"; then\n PKG_CONFIG_PATH=$brew_prefix/opt/icu4c/lib/pkgconfig:$brew_prefix/opt/libarchive/lib/pkgconfig\n export PKG_CONFIG_PATH\n fi\nfi\n\n# ----------------------------------------\n# Check for programs needed to build documentation.\n# ----------------------------------------\n\nAM_CONDITIONAL([ASCIIDOC], false)\nAM_CONDITIONAL([HAVE_XML_CATALOG_FILES], false)\nAC_ARG_ENABLE([doc],\n AS_HELP_STRING([--disable-doc], [disable build of documentation])\n [],\n [: m4_divert_text([DEFAULTS], [enable_doc=check])])\nAS_IF([test \"$enable_doc\" != \"no\"], [\n AC_CHECK_PROG([have_asciidoc], asciidoc, true, false)\n AC_CHECK_PROG([have_xsltproc], xsltproc, true, false)\n # macOS with Homebrew requires the environment variable\n # XML_CATALOG_FILES for xsltproc.\n if $have_asciidoc && $have_xsltproc; then\n AM_CONDITIONAL([ASCIIDOC], true)\n XML_CATALOG_FILES=\n if $have_brew; then\n catalog_file=$brew_prefix/etc/xml/catalog\n if test -f $catalog_file; then\n AM_CONDITIONAL([HAVE_XML_CATALOG_FILES], true)\n XML_CATALOG_FILES=file:$catalog_file\n else\n AC_MSG_WARN([Missing file $catalog_file.])\n fi\n fi\n AC_SUBST([XML_CATALOG_FILES])\n else\n AS_IF([test \"x$enable_doc\" != xcheck], [\n AC_MSG_FAILURE(\n [--enable-doc was given, but test for asciidoc and xsltproc failed])\n ])\n fi\n])\n\n# ----------------------------------------\n# Checks for typedefs, structures, and compiler characteristics.\n# ----------------------------------------\n\nAC_CHECK_TYPES([wchar_t],,, [#include \"wchar.h\"])\nAC_CHECK_TYPES([long long int])\n\n# ----------------------------------------\n# Test auxiliary packages\n# ----------------------------------------\n\nAM_CONDITIONAL([HAVE_LIBCURL], false)\nAS_IF([test \"x$with_curl\" != xno], [\n PKG_CHECK_MODULES([libcurl], [libcurl], [have_libcurl=true], [have_libcurl=false])\n AM_CONDITIONAL([HAVE_LIBCURL], $have_libcurl)\n if $have_libcurl; then\n AC_DEFINE([HAVE_LIBCURL], [1], [Enable libcurl])\n else\n AS_IF([test \"x$with_curl\" != xcheck], [\n AC_MSG_FAILURE(\n [--with-curl was given, but test for libcurl failed])\n ])\n fi\n])\n\nPKG_CHECK_MODULES([LEPTONICA], [lept >= 1.74], [have_lept=true], [have_lept=false])\nif $have_lept; then\n CPPFLAGS=\"$CPPFLAGS $LEPTONICA_CFLAGS\"\nelse\n AC_MSG_ERROR([Leptonica 1.74 or higher is required. Try to install libleptonica-dev package.])\nfi\n\nAM_CONDITIONAL([HAVE_LIBARCHIVE], false)\nAS_IF([test \"x$with_archive\" != xno], [\n PKG_CHECK_MODULES([libarchive], [libarchive], [have_libarchive=true], [have_libarchive=false])\n AM_CONDITIONAL([HAVE_LIBARCHIVE], [$have_libarchive])\n if $have_libarchive; then\n AC_DEFINE([HAVE_LIBARCHIVE], [1], [Enable libarchive])\n CPPFLAGS=\"$CPPFLAGS $libarchive_CFLAGS\"\n else\n AS_IF([test \"x$with_archive\" != xcheck], [\n AC_MSG_FAILURE(\n [--with-archive was given, but test for libarchive failed])\n ])\n fi\n])\n\nAM_CONDITIONAL([ENABLE_TRAINING], true)\n\n# Check availability of ICU packages.\nPKG_CHECK_MODULES([ICU_UC], [icu-uc >= 52.1], [have_icu_uc=true], [have_icu_uc=false])\nPKG_CHECK_MODULES([ICU_I18N], [icu-i18n >= 52.1], [have_icu_i18n=true], [have_icu_i18n=false])\nif !($have_icu_uc && $have_icu_i18n); then\n AC_MSG_WARN([icu 52.1 or higher is required, but was not found.])\n AC_MSG_WARN([Training tools WILL NOT be built.])\n AC_MSG_WARN([Try to install libicu-dev package.])\n AM_CONDITIONAL([ENABLE_TRAINING], false)\nfi\n\n# Check location of pango headers\nPKG_CHECK_MODULES([pango], [pango >= 1.38.0], [have_pango=true], [have_pango=false])\nif !($have_pango); then\n AC_MSG_WARN([pango 1.38.0 or higher is required, but was not found.])\n AC_MSG_WARN([Training tools WILL NOT be built.])\n AC_MSG_WARN([Try to install libpango1.0-dev package.])\n AM_CONDITIONAL([ENABLE_TRAINING], false)\nfi\n\n# Check location of cairo headers\nPKG_CHECK_MODULES([cairo], [cairo], [have_cairo=true], [have_cairo=false])\nif !($have_cairo); then\n AC_MSG_WARN([Training tools WILL NOT be built because of missing cairo library.])\n AC_MSG_WARN([Try to install libcairo-dev?? package.])\n AM_CONDITIONAL([ENABLE_TRAINING], false)\nfi\n\nPKG_CHECK_MODULES([pangocairo], [pangocairo], [], [false])\nPKG_CHECK_MODULES([pangoft2], [pangoft2], [], [false])\n\n# ----------------------------------------\n# Final Tasks and Output\n# ----------------------------------------\n\n# Output files\nAC_CONFIG_FILES([include/tesseract/version.h])\nAC_CONFIG_FILES([Makefile tesseract.pc])\nAC_CONFIG_FILES([tessdata/Makefile])\nAC_CONFIG_FILES([tessdata/configs/Makefile])\nAC_CONFIG_FILES([tessdata/tessconfigs/Makefile])\nAC_CONFIG_FILES([java/Makefile])\nAC_CONFIG_FILES([java/com/Makefile])\nAC_CONFIG_FILES([java/com/google/Makefile])\nAC_CONFIG_FILES([java/com/google/scrollview/Makefile])\nAC_CONFIG_FILES([java/com/google/scrollview/events/Makefile])\nAC_CONFIG_FILES([java/com/google/scrollview/ui/Makefile])\nAC_CONFIG_FILES([nsis/Makefile])\nAC_OUTPUT\n\n# Final message\necho \"\"\necho \"Configuration is done.\"\necho \"You can now build and install $PACKAGE_NAME by running:\"\necho \"\"\necho \"$ make\"\necho \"$ sudo make install\"\necho \"$ sudo ldconfig\"\necho \"\"\n\nAM_COND_IF([ASCIIDOC], [\n echo \"This will also build the documentation.\"\n], [\n AS_IF([test \"$enable_doc\" = \"no\"], [\n echo \"Documentation will not be built because it was disabled.\"\n ], [\n echo \"Documentation will not be built because asciidoc or xsltproc is missing.\"\n ])\n])\n\n# echo \"$ sudo make install LANGS=\\\"eng ara deu\\\"\"\n# echo \" Or:\"\n# echo \"$ sudo make install-langs\"\necho \"\"\n\nAM_COND_IF([ENABLE_TRAINING],\n [\n echo \"Training tools can be built and installed with:\"\n echo \"\"\n echo \"$ make training\"\n echo \"$ sudo make training-install\"\n echo \"\"],\n [\n echo \"You cannot build training tools because of missing dependency.\"\n echo \"Check configure output for details.\"\n echo \"\"]\n)\n\n# ----------------------------------------\n# CONFIG Template\n# ----------------------------------------\n\n# Fence added in configuration file\nAH_TOP([\n#ifndef CONFIG_AUTO_H\n#define CONFIG_AUTO_H\n/* config_auto.h: begin */\n])\n\n# Stuff added at bottom of file\nAH_BOTTOM([\n\n/* Miscellaneous defines */\n#define AUTOCONF 1\n\n/* Not used yet\n#ifndef NO_GETTEXT\n#define USING_GETTEXT\n#endif\n*/\n\n/* config_auto.h: end */\n#endif\n])\n" }, { "path": "doc/Doxyfile", "content": "# Doxyfile 1.8.16\n\n# This file describes the settings to be used by the documentation system\n# doxygen (www.doxygen.org) for a project.\n#\n# All text after a double hash (##) is considered a comment and is placed in\n# front of the TAG it is preceding.\n#\n# All text after a single hash (#) is considered a comment and will be ignored.\n# The format is:\n# TAG = value [value, ...]\n# For lists, items can also be appended using:\n# TAG += value [value, ...]\n# Values that contain spaces should be placed between quotes (\\\" \\\").\n\n#---------------------------------------------------------------------------\n# Project related configuration options\n#---------------------------------------------------------------------------\n\n# This tag specifies the encoding used for all characters in the configuration\n# file that follow. The default is UTF-8 which is also the encoding used for all\n# text before the first occurrence of this tag. Doxygen uses libiconv (or the\n# iconv built into libc) for the transcoding. See\n# https://www.gnu.org/software/libiconv/ for the list of possible encodings.\n# The default value is: UTF-8.\n\nDOXYFILE_ENCODING = UTF-8\n\n# The PROJECT_NAME tag is a single word (or a sequence of words surrounded by\n# double-quotes, unless you are using Doxywizard) that should identify the\n# project for which the documentation is generated. This name is used in the\n# title of most generated pages and in a few other places.\n# The default value is: My Project.\n\nPROJECT_NAME = $(name)\n\n# The PROJECT_NUMBER tag can be used to enter a project or revision number. This\n# could be handy for archiving the generated documentation or if some version\n# control system is used.\n\nPROJECT_NUMBER = $(version)\n\n# Using the PROJECT_BRIEF tag one can provide an optional one line description\n# for a project that appears at the top of each page and should give viewer a\n# quick idea about the purpose of the project. Keep the description short.\n\nPROJECT_BRIEF =\n\n# With the PROJECT_LOGO tag one can specify a logo or an icon that is included\n# in the documentation. The maximum height of the logo should not exceed 55\n# pixels and the maximum width should not exceed 200 pixels. Doxygen will copy\n# the logo to the output directory.\n\nPROJECT_LOGO =\n\n# The OUTPUT_DIRECTORY tag is used to specify the (relative or absolute) path\n# into which the generated documentation will be written. If a relative path is\n# entered, it will be relative to the location where doxygen was started. If\n# left blank the current directory will be used.\n\nOUTPUT_DIRECTORY = doc/\n\n# If the CREATE_SUBDIRS tag is set to YES then doxygen will create 4096 sub-\n# directories (in 2 levels) under the output directory of each output format and\n# will distribute the generated files over these directories. Enabling this\n# option can be useful when feeding doxygen a huge amount of source files, where\n# putting all generated files in the same directory would otherwise causes\n# performance problems for the file system.\n# The default value is: NO.\n\nCREATE_SUBDIRS = NO\n\n# If the ALLOW_UNICODE_NAMES tag is set to YES, doxygen will allow non-ASCII\n# characters to appear in the names of generated files. If set to NO, non-ASCII\n# characters will be escaped, for example _xE3_x81_x84 will be used for Unicode\n# U+3044.\n# The default value is: NO.\n\nALLOW_UNICODE_NAMES = NO\n\n# The OUTPUT_LANGUAGE tag is used to specify the language in which all\n# documentation generated by doxygen is written. Doxygen will use this\n# information to generate all constant output in the proper language.\n# Possible values are: Afrikaans, Arabic, Armenian, Brazilian, Catalan, Chinese,\n# Chinese-Traditional, Croatian, Czech, Danish, Dutch, English (United States),\n# Esperanto, Farsi (Persian), Finnish, French, German, Greek, Hungarian,\n# Indonesian, Italian, Japanese, Japanese-en (Japanese with English messages),\n# Korean, Korean-en (Korean with English messages), Latvian, Lithuanian,\n# Macedonian, Norwegian, Persian (Farsi), Polish, Portuguese, Romanian, Russian,\n# Serbian, Serbian-Cyrillic, Slovak, Slovene, Spanish, Swedish, Turkish,\n# Ukrainian and Vietnamese.\n# The default value is: English.\n\nOUTPUT_LANGUAGE = English\n\n# The OUTPUT_TEXT_DIRECTION tag is used to specify the direction in which all\n# documentation generated by doxygen is written. Doxygen will use this\n# information to generate all generated output in the proper direction.\n# Possible values are: None, LTR, RTL and Context.\n# The default value is: None.\n\nOUTPUT_TEXT_DIRECTION = None\n\n# If the BRIEF_MEMBER_DESC tag is set to YES, doxygen will include brief member\n# descriptions after the members that are listed in the file and class\n# documentation (similar to Javadoc). Set to NO to disable this.\n# The default value is: YES.\n\nBRIEF_MEMBER_DESC = YES\n\n# If the REPEAT_BRIEF tag is set to YES, doxygen will prepend the brief\n# description of a member or function before the detailed description\n#\n# Note: If both HIDE_UNDOC_MEMBERS and BRIEF_MEMBER_DESC are set to NO, the\n# brief descriptions will be completely suppressed.\n# The default value is: YES.\n\nREPEAT_BRIEF = YES\n\n# This tag implements a quasi-intelligent brief description abbreviator that is\n# used to form the text in various listings. Each string in this list, if found\n# as the leading text of the brief description, will be stripped from the text\n# and the result, after processing the whole list, is used as the annotated\n# text. Otherwise, the brief description is used as-is. If left blank, the\n# following values are used ($name is automatically replaced with the name of\n# the entity):The $name class, The $name widget, The $name file, is, provides,\n# specifies, contains, represents, a, an and the.\n\nABBREVIATE_BRIEF = \"The $name class\" \\\n \"The $name widget\" \\\n \"The $name file\" \\\n is \\\n provides \\\n specifies \\\n contains \\\n represents \\\n a \\\n an \\\n the\n\n# If the ALWAYS_DETAILED_SEC and REPEAT_BRIEF tags are both set to YES then\n# doxygen will generate a detailed section even if there is only a brief\n# description.\n# The default value is: NO.\n\nALWAYS_DETAILED_SEC = NO\n\n# If the INLINE_INHERITED_MEMB tag is set to YES, doxygen will show all\n# inherited members of a class in the documentation of that class as if those\n# members were ordinary class members. Constructors, destructors and assignment\n# operators of the base classes will not be shown.\n# The default value is: NO.\n\nINLINE_INHERITED_MEMB = NO\n\n# If the FULL_PATH_NAMES tag is set to YES, doxygen will prepend the full path\n# before files name in the file list and in the header files. If set to NO the\n# shortest path that makes the file name unique will be used\n# The default value is: YES.\n\nFULL_PATH_NAMES = YES\n\n# The STRIP_FROM_PATH tag can be used to strip a user-defined part of the path.\n# Stripping is only done if one of the specified strings matches the left-hand\n# part of the path. The tag can be used to show relative paths in the file list.\n# If left blank the directory from which doxygen is run is used as the path to\n# strip.\n#\n# Note that you can specify absolute paths here, but also relative paths, which\n# will be relative from the directory where doxygen is started.\n# This tag requires that the tag FULL_PATH_NAMES is set to YES.\n\nSTRIP_FROM_PATH = $(builddir)\n\n# The STRIP_FROM_INC_PATH tag can be used to strip a user-defined part of the\n# path mentioned in the documentation of a class, which tells the reader which\n# header file to include in order to use a class. If left blank only the name of\n# the header file containing the class definition is used. Otherwise one should\n# specify the list of include paths that are normally passed to the compiler\n# using the -I flag.\n\nSTRIP_FROM_INC_PATH =\n\n# If the SHORT_NAMES tag is set to YES, doxygen will generate much shorter (but\n# less readable) file names. This can be useful is your file systems doesn't\n# support long names like on DOS, Mac, or CD-ROM.\n# The default value is: NO.\n\nSHORT_NAMES = YES\n\n# If the JAVADOC_AUTOBRIEF tag is set to YES then doxygen will interpret the\n# first line (until the first dot) of a Javadoc-style comment as the brief\n# description. If set to NO, the Javadoc-style will behave just like regular Qt-\n# style comments (thus requiring an explicit @brief command for a brief\n# description.)\n# The default value is: NO.\n\nJAVADOC_AUTOBRIEF = NO\n\n# If the JAVADOC_BANNER tag is set to YES then doxygen will interpret a line\n# such as\n# /***************\n# as being the beginning of a Javadoc-style comment \"banner\". If set to NO, the\n# Javadoc-style will behave just like regular comments and it will not be\n# interpreted by doxygen.\n# The default value is: NO.\n\nJAVADOC_BANNER = NO\n\n# If the QT_AUTOBRIEF tag is set to YES then doxygen will interpret the first\n# line (until the first dot) of a Qt-style comment as the brief description. If\n# set to NO, the Qt-style will behave just like regular Qt-style comments (thus\n# requiring an explicit \\brief command for a brief description.)\n# The default value is: NO.\n\nQT_AUTOBRIEF = NO\n\n# The MULTILINE_CPP_IS_BRIEF tag can be set to YES to make doxygen treat a\n# multi-line C++ special comment block (i.e. a block of //! or /// comments) as\n# a brief description. This used to be the default behavior. The new default is\n# to treat a multi-line C++ comment block as a detailed description. Set this\n# tag to YES if you prefer the old behavior instead.\n#\n# Note that setting this tag to YES also means that rational rose comments are\n# not recognized any more.\n# The default value is: NO.\n\nMULTILINE_CPP_IS_BRIEF = NO\n\n# If the INHERIT_DOCS tag is set to YES then an undocumented member inherits the\n# documentation from any documented member that it re-implements.\n# The default value is: YES.\n\nINHERIT_DOCS = YES\n\n# If the SEPARATE_MEMBER_PAGES tag is set to YES then doxygen will produce a new\n# page for each member. If set to NO, the documentation of a member will be part\n# of the file/class/namespace that contains it.\n# The default value is: NO.\n\nSEPARATE_MEMBER_PAGES = NO\n\n# The TAB_SIZE tag can be used to set the number of spaces in a tab. Doxygen\n# uses this value to replace tabs by spaces in code fragments.\n# Minimum value: 1, maximum value: 16, default value: 4.\n\nTAB_SIZE = 8\n\n# This tag can be used to specify a number of aliases that act as commands in\n# the documentation. An alias has the form:\n# name=value\n# For example adding\n# \"sideeffect=@par Side Effects:\\n\"\n# will allow you to put the command \\sideeffect (or @sideeffect) in the\n# documentation, which will result in a user-defined paragraph with heading\n# \"Side Effects:\". You can put \\n's in the value part of an alias to insert\n# newlines (in the resulting output). You can put ^^ in the value part of an\n# alias to insert a newline as if a physical newline was in the original file.\n# When you need a literal { or } or , in the value part of an alias you have to\n# escape them by means of a backslash (\\), this can lead to conflicts with the\n# commands \\{ and \\} for these it is advised to use the version @{ and @} or use\n# a double escape (\\\\{ and \\\\})\n\nALIASES =\n\n# This tag can be used to specify a number of word-keyword mappings (TCL only).\n# A mapping has the form \"name=value\". For example adding \"class=itcl::class\"\n# will allow you to use the command class in the itcl::class meaning.\n\nTCL_SUBST =\n\n# Set the OPTIMIZE_OUTPUT_FOR_C tag to YES if your project consists of C sources\n# only. Doxygen will then generate output that is more tailored for C. For\n# instance, some of the names that are used will be different. The list of all\n# members will be omitted, etc.\n# The default value is: NO.\n\nOPTIMIZE_OUTPUT_FOR_C = NO\n\n# Set the OPTIMIZE_OUTPUT_JAVA tag to YES if your project consists of Java or\n# Python sources only. Doxygen will then generate output that is more tailored\n# for that language. For instance, namespaces will be presented as packages,\n# qualified scopes will look different, etc.\n# The default value is: NO.\n\nOPTIMIZE_OUTPUT_JAVA = NO\n\n# Set the OPTIMIZE_FOR_FORTRAN tag to YES if your project consists of Fortran\n# sources. Doxygen will then generate output that is tailored for Fortran.\n# The default value is: NO.\n\nOPTIMIZE_FOR_FORTRAN = NO\n\n# Set the OPTIMIZE_OUTPUT_VHDL tag to YES if your project consists of VHDL\n# sources. Doxygen will then generate output that is tailored for VHDL.\n# The default value is: NO.\n\nOPTIMIZE_OUTPUT_VHDL = NO\n\n# Set the OPTIMIZE_OUTPUT_SLICE tag to YES if your project consists of Slice\n# sources only. Doxygen will then generate output that is more tailored for that\n# language. For instance, namespaces will be presented as modules, types will be\n# separated into more groups, etc.\n# The default value is: NO.\n\nOPTIMIZE_OUTPUT_SLICE = NO\n\n# Doxygen selects the parser to use depending on the extension of the files it\n# parses. With this tag you can assign which parser to use for a given\n# extension. Doxygen has a built-in mapping, but you can override or extend it\n# using this tag. The format is ext=language, where ext is a file extension, and\n# language is one of the parsers supported by doxygen: IDL, Java, Javascript,\n# Csharp (C#), C, C++, D, PHP, md (Markdown), Objective-C, Python, Slice,\n# Fortran (fixed format Fortran: FortranFixed, free formatted Fortran:\n# FortranFree, unknown formatted Fortran: Fortran. In the later case the parser\n# tries to guess whether the code is fixed or free formatted code, this is the\n# default for Fortran type files), VHDL, tcl. For instance to make doxygen treat\n# .inc files as Fortran files (default is PHP), and .f files as C (default is\n# Fortran), use: inc=Fortran f=C.\n#\n# Note: For files without extension you can use no_extension as a placeholder.\n#\n# Note that for custom extensions you also need to set FILE_PATTERNS otherwise\n# the files are not read by doxygen.\n\nEXTENSION_MAPPING =\n\n# If the MARKDOWN_SUPPORT tag is enabled then doxygen pre-processes all comments\n# according to the Markdown format, which allows for more readable\n# documentation. See https://daringfireball.net/projects/markdown/ for details.\n# The output of markdown processing is further processed by doxygen, so you can\n# mix doxygen, HTML, and XML commands with Markdown formatting. Disable only in\n# case of backward compatibilities issues.\n# The default value is: YES.\n\nMARKDOWN_SUPPORT = YES\n\n# When the TOC_INCLUDE_HEADINGS tag is set to a non-zero value, all headings up\n# to that level are automatically included in the table of contents, even if\n# they do not have an id attribute.\n# Note: This feature currently applies only to Markdown headings.\n# Minimum value: 0, maximum value: 99, default value: 5.\n# This tag requires that the tag MARKDOWN_SUPPORT is set to YES.\n\nTOC_INCLUDE_HEADINGS = 5\n\n# When enabled doxygen tries to link words that correspond to documented\n# classes, or namespaces to their corresponding documentation. Such a link can\n# be prevented in individual cases by putting a % sign in front of the word or\n# globally by setting AUTOLINK_SUPPORT to NO.\n# The default value is: YES.\n\nAUTOLINK_SUPPORT = YES\n\n# If you use STL classes (i.e. std::string, std::vector, etc.) but do not want\n# to include (a tag file for) the STL sources as input, then you should set this\n# tag to YES in order to let doxygen match functions declarations and\n# definitions whose arguments contain STL classes (e.g. func(std::string);\n# versus func(std::string) {}). This also make the inheritance and collaboration\n# diagrams that involve STL classes more complete and accurate.\n# The default value is: NO.\n\nBUILTIN_STL_SUPPORT = YES\n\n# If you use Microsoft's C++/CLI language, you should set this option to YES to\n# enable parsing support.\n# The default value is: NO.\n\nCPP_CLI_SUPPORT = NO\n\n# Set the SIP_SUPPORT tag to YES if your project consists of sip (see:\n# https://www.riverbankcomputing.com/software/sip/intro) sources only. Doxygen\n# will parse them like normal C++ but will assume all classes use public instead\n# of private inheritance when no explicit protection keyword is present.\n# The default value is: NO.\n\nSIP_SUPPORT = NO\n\n# For Microsoft's IDL there are propget and propput attributes to indicate\n# getter and setter methods for a property. Setting this option to YES will make\n# doxygen to replace the get and set methods by a property in the documentation.\n# This will only work if the methods are indeed getting or setting a simple\n# type. If this is not the case, or you want to show the methods anyway, you\n# should set this option to NO.\n# The default value is: YES.\n\nIDL_PROPERTY_SUPPORT = YES\n\n# If member grouping is used in the documentation and the DISTRIBUTE_GROUP_DOC\n# tag is set to YES then doxygen will reuse the documentation of the first\n# member in the group (if any) for the other members of the group. By default\n# all members of a group must be documented explicitly.\n# The default value is: NO.\n\nDISTRIBUTE_GROUP_DOC = NO\n\n# If one adds a struct or class to a group and this option is enabled, then also\n# any nested class or struct is added to the same group. By default this option\n# is disabled and one has to add nested compounds explicitly via \\ingroup.\n# The default value is: NO.\n\nGROUP_NESTED_COMPOUNDS = NO\n\n# Set the SUBGROUPING tag to YES to allow class member groups of the same type\n# (for instance a group of public functions) to be put as a subgroup of that\n# type (e.g. under the Public Functions section). Set it to NO to prevent\n# subgrouping. Alternatively, this can be done per class using the\n# \\nosubgrouping command.\n# The default value is: YES.\n\nSUBGROUPING = YES\n\n# When the INLINE_GROUPED_CLASSES tag is set to YES, classes, structs and unions\n# are shown inside the group in which they are included (e.g. using \\ingroup)\n# instead of on a separate page (for HTML and Man pages) or section (for LaTeX\n# and RTF).\n#\n# Note that this feature does not work in combination with\n# SEPARATE_MEMBER_PAGES.\n# The default value is: NO.\n\nINLINE_GROUPED_CLASSES = NO\n\n# When the INLINE_SIMPLE_STRUCTS tag is set to YES, structs, classes, and unions\n# with only public data fields or simple typedef fields will be shown inline in\n# the documentation of the scope in which they are defined (i.e. file,\n# namespace, or group documentation), provided this scope is documented. If set\n# to NO, structs, classes, and unions are shown on a separate page (for HTML and\n# Man pages) or section (for LaTeX and RTF).\n# The default value is: NO.\n\nINLINE_SIMPLE_STRUCTS = NO\n\n# When TYPEDEF_HIDES_STRUCT tag is enabled, a typedef of a struct, union, or\n# enum is documented as struct, union, or enum with the name of the typedef. So\n# typedef struct TypeS {} TypeT, will appear in the documentation as a struct\n# with name TypeT. When disabled the typedef will appear as a member of a file,\n# namespace, or class. And the struct will be named TypeS. This can typically be\n# useful for C code in case the coding convention dictates that all compound\n# types are typedef'ed and only the typedef is referenced, never the tag name.\n# The default value is: NO.\n\nTYPEDEF_HIDES_STRUCT = NO\n\n# The size of the symbol lookup cache can be set using LOOKUP_CACHE_SIZE. This\n# cache is used to resolve symbols given their name and scope. Since this can be\n# an expensive process and often the same symbol appears multiple times in the\n# code, doxygen keeps a cache of pre-resolved symbols. If the cache is too small\n# doxygen will become slower. If the cache is too large, memory is wasted. The\n# cache size is given by this formula: 2^(16+LOOKUP_CACHE_SIZE). The valid range\n# is 0..9, the default is 0, corresponding to a cache size of 2^16=65536\n# symbols. At the end of a run doxygen will report the cache usage and suggest\n# the optimal cache size from a speed point of view.\n# Minimum value: 0, maximum value: 9, default value: 0.\n\nLOOKUP_CACHE_SIZE = 0\n\n#---------------------------------------------------------------------------\n# Build related configuration options\n#---------------------------------------------------------------------------\n\n# If the EXTRACT_ALL tag is set to YES, doxygen will assume all entities in\n# documentation are documented, even if no documentation was available. Private\n# class members and static file members will be hidden unless the\n# EXTRACT_PRIVATE respectively EXTRACT_STATIC tags are set to YES.\n# Note: This will also disable the warnings about undocumented members that are\n# normally produced when WARNINGS is set to YES.\n# The default value is: NO.\n\nEXTRACT_ALL = YES\n\n# If the EXTRACT_PRIVATE tag is set to YES, all private members of a class will\n# be included in the documentation.\n# The default value is: NO.\n\nEXTRACT_PRIVATE = NO\n\n# If the EXTRACT_PRIV_VIRTUAL tag is set to YES, documented private virtual\n# methods of a class will be included in the documentation.\n# The default value is: NO.\n\nEXTRACT_PRIV_VIRTUAL = NO\n\n# If the EXTRACT_PACKAGE tag is set to YES, all members with package or internal\n# scope will be included in the documentation.\n# The default value is: NO.\n\nEXTRACT_PACKAGE = NO\n\n# If the EXTRACT_STATIC tag is set to YES, all static members of a file will be\n# included in the documentation.\n# The default value is: NO.\n\nEXTRACT_STATIC = NO\n\n# If the EXTRACT_LOCAL_CLASSES tag is set to YES, classes (and structs) defined\n# locally in source files will be included in the documentation. If set to NO,\n# only classes defined in header files are included. Does not have any effect\n# for Java sources.\n# The default value is: YES.\n\nEXTRACT_LOCAL_CLASSES = YES\n\n# This flag is only useful for Objective-C code. If set to YES, local methods,\n# which are defined in the implementation section but not in the interface are\n# included in the documentation. If set to NO, only methods in the interface are\n# included.\n# The default value is: NO.\n\nEXTRACT_LOCAL_METHODS = NO\n\n# If this flag is set to YES, the members of anonymous namespaces will be\n# extracted and appear in the documentation as a namespace called\n# 'anonymous_namespace{file}', where file will be replaced with the base name of\n# the file that contains the anonymous namespace. By default anonymous namespace\n# are hidden.\n# The default value is: NO.\n\nEXTRACT_ANON_NSPACES = NO\n\n# If the HIDE_UNDOC_MEMBERS tag is set to YES, doxygen will hide all\n# undocumented members inside documented classes or files. If set to NO these\n# members will be included in the various overviews, but no documentation\n# section is generated. This option has no effect if EXTRACT_ALL is enabled.\n# The default value is: NO.\n\nHIDE_UNDOC_MEMBERS = NO\n\n# If the HIDE_UNDOC_CLASSES tag is set to YES, doxygen will hide all\n# undocumented classes that are normally visible in the class hierarchy. If set\n# to NO, these classes will be included in the various overviews. This option\n# has no effect if EXTRACT_ALL is enabled.\n# The default value is: NO.\n\nHIDE_UNDOC_CLASSES = NO\n\n# If the HIDE_FRIEND_COMPOUNDS tag is set to YES, doxygen will hide all friend\n# (class|struct|union) declarations. If set to NO, these declarations will be\n# included in the documentation.\n# The default value is: NO.\n\nHIDE_FRIEND_COMPOUNDS = NO\n\n# If the HIDE_IN_BODY_DOCS tag is set to YES, doxygen will hide any\n# documentation blocks found inside the body of a function. If set to NO, these\n# blocks will be appended to the function's detailed documentation block.\n# The default value is: NO.\n\nHIDE_IN_BODY_DOCS = NO\n\n# The INTERNAL_DOCS tag determines if documentation that is typed after a\n# \\internal command is included. If the tag is set to NO then the documentation\n# will be excluded. Set it to YES to include the internal documentation.\n# The default value is: NO.\n\nINTERNAL_DOCS = NO\n\n# If the CASE_SENSE_NAMES tag is set to NO then doxygen will only generate file\n# names in lower-case letters. If set to YES, upper-case letters are also\n# allowed. This is useful if you have classes or files whose names only differ\n# in case and if your file system supports case sensitive file names. Windows\n# (including Cygwin) ands Mac users are advised to set this option to NO.\n# The default value is: system dependent.\n\nCASE_SENSE_NAMES = NO\n\n# If the HIDE_SCOPE_NAMES tag is set to NO then doxygen will show members with\n# their full class and namespace scopes in the documentation. If set to YES, the\n# scope will be hidden.\n# The default value is: NO.\n\nHIDE_SCOPE_NAMES = NO\n\n# If the HIDE_COMPOUND_REFERENCE tag is set to NO (default) then doxygen will\n# append additional text to a page's title, such as Class Reference. If set to\n# YES the compound reference will be hidden.\n# The default value is: NO.\n\nHIDE_COMPOUND_REFERENCE= NO\n\n# If the SHOW_INCLUDE_FILES tag is set to YES then doxygen will put a list of\n# the files that are included by a file in the documentation of that file.\n# The default value is: YES.\n\nSHOW_INCLUDE_FILES = YES\n\n# If the SHOW_GROUPED_MEMB_INC tag is set to YES then Doxygen will add for each\n# grouped member an include statement to the documentation, telling the reader\n# which file to include in order to use the member.\n# The default value is: NO.\n\nSHOW_GROUPED_MEMB_INC = NO\n\n# If the FORCE_LOCAL_INCLUDES tag is set to YES then doxygen will list include\n# files with double quotes in the documentation rather than with sharp brackets.\n# The default value is: NO.\n\nFORCE_LOCAL_INCLUDES = NO\n\n# If the INLINE_INFO tag is set to YES then a tag [inline] is inserted in the\n# documentation for inline members.\n# The default value is: YES.\n\nINLINE_INFO = YES\n\n# If the SORT_MEMBER_DOCS tag is set to YES then doxygen will sort the\n# (detailed) documentation of file and class members alphabetically by member\n# name. If set to NO, the members will appear in declaration order.\n# The default value is: YES.\n\nSORT_MEMBER_DOCS = YES\n\n# If the SORT_BRIEF_DOCS tag is set to YES then doxygen will sort the brief\n# descriptions of file, namespace and class members alphabetically by member\n# name. If set to NO, the members will appear in declaration order. Note that\n# this will also influence the order of the classes in the class list.\n# The default value is: NO.\n\nSORT_BRIEF_DOCS = NO\n\n# If the SORT_MEMBERS_CTORS_1ST tag is set to YES then doxygen will sort the\n# (brief and detailed) documentation of class members so that constructors and\n# destructors are listed first. If set to NO the constructors will appear in the\n# respective orders defined by SORT_BRIEF_DOCS and SORT_MEMBER_DOCS.\n# Note: If SORT_BRIEF_DOCS is set to NO this option is ignored for sorting brief\n# member documentation.\n# Note: If SORT_MEMBER_DOCS is set to NO this option is ignored for sorting\n# detailed member documentation.\n# The default value is: NO.\n\nSORT_MEMBERS_CTORS_1ST = NO\n\n# If the SORT_GROUP_NAMES tag is set to YES then doxygen will sort the hierarchy\n# of group names into alphabetical order. If set to NO the group names will\n# appear in their defined order.\n# The default value is: NO.\n\nSORT_GROUP_NAMES = NO\n\n# If the SORT_BY_SCOPE_NAME tag is set to YES, the class list will be sorted by\n# fully-qualified names, including namespaces. If set to NO, the class list will\n# be sorted only by class name, not including the namespace part.\n# Note: This option is not very useful if HIDE_SCOPE_NAMES is set to YES.\n# Note: This option applies only to the class list, not to the alphabetical\n# list.\n# The default value is: NO.\n\nSORT_BY_SCOPE_NAME = NO\n\n# If the STRICT_PROTO_MATCHING option is enabled and doxygen fails to do proper\n# type resolution of all parameters of a function it will reject a match between\n# the prototype and the implementation of a member function even if there is\n# only one candidate or it is obvious which candidate to choose by doing a\n# simple string match. By disabling STRICT_PROTO_MATCHING doxygen will still\n# accept a match between prototype and implementation in such cases.\n# The default value is: NO.\n\nSTRICT_PROTO_MATCHING = NO\n\n# The GENERATE_TODOLIST tag can be used to enable (YES) or disable (NO) the todo\n# list. This list is created by putting \\todo commands in the documentation.\n# The default value is: YES.\n\nGENERATE_TODOLIST = YES\n\n# The GENERATE_TESTLIST tag can be used to enable (YES) or disable (NO) the test\n# list. This list is created by putting \\test commands in the documentation.\n# The default value is: YES.\n\nGENERATE_TESTLIST = YES\n\n# The GENERATE_BUGLIST tag can be used to enable (YES) or disable (NO) the bug\n# list. This list is created by putting \\bug commands in the documentation.\n# The default value is: YES.\n\nGENERATE_BUGLIST = YES\n\n# The GENERATE_DEPRECATEDLIST tag can be used to enable (YES) or disable (NO)\n# the deprecated list. This list is created by putting \\deprecated commands in\n# the documentation.\n# The default value is: YES.\n\nGENERATE_DEPRECATEDLIST= YES\n\n# The ENABLED_SECTIONS tag can be used to enable conditional documentation\n# sections, marked by \\if ... \\endif and \\cond \n# ... \\endcond blocks.\n\nENABLED_SECTIONS =\n\n# The MAX_INITIALIZER_LINES tag determines the maximum number of lines that the\n# initial value of a variable or macro / define can have for it to appear in the\n# documentation. If the initializer consists of more lines than specified here\n# it will be hidden. Use a value of 0 to hide initializers completely. The\n# appearance of the value of individual variables and macros / defines can be\n# controlled using \\showinitializer or \\hideinitializer command in the\n# documentation regardless of this setting.\n# Minimum value: 0, maximum value: 10000, default value: 30.\n\nMAX_INITIALIZER_LINES = 30\n\n# Set the SHOW_USED_FILES tag to NO to disable the list of files generated at\n# the bottom of the documentation of classes and structs. If set to YES, the\n# list will mention the files that were used to generate the documentation.\n# The default value is: YES.\n\nSHOW_USED_FILES = YES\n\n# Set the SHOW_FILES tag to NO to disable the generation of the Files page. This\n# will remove the Files entry from the Quick Index and from the Folder Tree View\n# (if specified).\n# The default value is: YES.\n\nSHOW_FILES = YES\n\n# Set the SHOW_NAMESPACES tag to NO to disable the generation of the Namespaces\n# page. This will remove the Namespaces entry from the Quick Index and from the\n# Folder Tree View (if specified).\n# The default value is: YES.\n\nSHOW_NAMESPACES = YES\n\n# The FILE_VERSION_FILTER tag can be used to specify a program or script that\n# doxygen should invoke to get the current version for each file (typically from\n# the version control system). Doxygen will invoke the program by executing (via\n# popen()) the command command input-file, where command is the value of the\n# FILE_VERSION_FILTER tag, and input-file is the name of an input file provided\n# by doxygen. Whatever the program writes to standard output is used as the file\n# version. For an example see the documentation.\n\nFILE_VERSION_FILTER =\n\n# The LAYOUT_FILE tag can be used to specify a layout file which will be parsed\n# by doxygen. The layout file controls the global structure of the generated\n# output files in an output format independent way. To create the layout file\n# that represents doxygen's defaults, run doxygen with the -l option. You can\n# optionally specify a file name after the option, if omitted DoxygenLayout.xml\n# will be used as the name of the layout file.\n#\n# Note that if you run doxygen from a directory containing a file called\n# DoxygenLayout.xml, doxygen will parse it automatically even if the LAYOUT_FILE\n# tag is left empty.\n\nLAYOUT_FILE =\n\n# The CITE_BIB_FILES tag can be used to specify one or more bib files containing\n# the reference definitions. This must be a list of .bib files. The .bib\n# extension is automatically appended if omitted. This requires the bibtex tool\n# to be installed. See also https://en.wikipedia.org/wiki/BibTeX for more info.\n# For LaTeX the style of the bibliography can be controlled using\n# LATEX_BIB_STYLE. To use this feature you need bibtex and perl available in the\n# search path. See also \\cite for info how to create references.\n\nCITE_BIB_FILES =\n\n#---------------------------------------------------------------------------\n# Configuration options related to warning and progress messages\n#---------------------------------------------------------------------------\n\n# The QUIET tag can be used to turn on/off the messages that are generated to\n# standard output by doxygen. If QUIET is set to YES this implies that the\n# messages are off.\n# The default value is: NO.\n\nQUIET = NO\n\n# The WARNINGS tag can be used to turn on/off the warning messages that are\n# generated to standard error (stderr) by doxygen. If WARNINGS is set to YES\n# this implies that the warnings are on.\n#\n# Tip: Turn warnings on while writing the documentation.\n# The default value is: YES.\n\nWARNINGS = YES\n\n# If the WARN_IF_UNDOCUMENTED tag is set to YES then doxygen will generate\n# warnings for undocumented members. If EXTRACT_ALL is set to YES then this flag\n# will automatically be disabled.\n# The default value is: YES.\n\nWARN_IF_UNDOCUMENTED = YES\n\n# If the WARN_IF_DOC_ERROR tag is set to YES, doxygen will generate warnings for\n# potential errors in the documentation, such as not documenting some parameters\n# in a documented function, or documenting parameters that don't exist or using\n# markup commands wrongly.\n# The default value is: YES.\n\nWARN_IF_DOC_ERROR = YES\n\n# This WARN_NO_PARAMDOC option can be enabled to get warnings for functions that\n# are documented, but have no documentation for their parameters or return\n# value. If set to NO, doxygen will only warn about wrong or incomplete\n# parameter documentation, but not about the absence of documentation. If\n# EXTRACT_ALL is set to YES then this flag will automatically be disabled.\n# The default value is: NO.\n\nWARN_NO_PARAMDOC = YES\n\n# If the WARN_AS_ERROR tag is set to YES then doxygen will immediately stop when\n# a warning is encountered.\n# The default value is: NO.\n\nWARN_AS_ERROR = NO\n\n# The WARN_FORMAT tag determines the format of the warning messages that doxygen\n# can produce. The string should contain the $file, $line, and $text tags, which\n# will be replaced by the file and line number from which the warning originated\n# and the warning text. Optionally the format may contain $version, which will\n# be replaced by the version of the file (if it could be obtained via\n# FILE_VERSION_FILTER)\n# The default value is: $file:$line: $text.\n\nWARN_FORMAT = \"$file:$line: $text\"\n\n# The WARN_LOGFILE tag can be used to specify a file to which warning and error\n# messages should be written. If left blank the output is written to standard\n# error (stderr).\n\nWARN_LOGFILE = $(builddir)/doc/DoxyWarn.log\n\n#---------------------------------------------------------------------------\n# Configuration options related to the input files\n#---------------------------------------------------------------------------\n\n# The INPUT tag is used to specify the files and/or directories that contain\n# documented source files. You may enter file names like myfile.cpp or\n# directories like /usr/src/myproject. Separate the files or directories with\n# spaces. See also FILE_PATTERNS and EXTENSION_MAPPING\n# Note: If this tag is empty the current directory is searched.\n\nINPUT = $(srcdir)/include $(srcdir)/src $(srcdir)/unittest\n\n# This tag can be used to specify the character encoding of the source files\n# that doxygen parses. Internally doxygen uses the UTF-8 encoding. Doxygen uses\n# libiconv (or the iconv built into libc) for the transcoding. See the libiconv\n# documentation (see: https://www.gnu.org/software/libiconv/) for the list of\n# possible encodings.\n# The default value is: UTF-8.\n\nINPUT_ENCODING = UTF-8\n\n# If the value of the INPUT tag contains directories, you can use the\n# FILE_PATTERNS tag to specify one or more wildcard patterns (like *.cpp and\n# *.h) to filter out the source-files in the directories.\n#\n# Note that for custom extensions or not directly supported extensions you also\n# need to set EXTENSION_MAPPING for the extension otherwise the files are not\n# read by doxygen.\n#\n# If left blank the following patterns are tested:*.c, *.cc, *.cxx, *.cpp,\n# *.c++, *.java, *.ii, *.ixx, *.ipp, *.i++, *.inl, *.idl, *.ddl, *.odl, *.h,\n# *.hh, *.hxx, *.hpp, *.h++, *.cs, *.d, *.php, *.php4, *.php5, *.phtml, *.inc,\n# *.m, *.markdown, *.md, *.mm, *.dox, *.py, *.pyw, *.f90, *.f95, *.f03, *.f08,\n# *.f, *.for, *.tcl, *.vhd, *.vhdl, *.ucf, *.qsf and *.ice.\n\nFILE_PATTERNS = *.c \\\n *.cc \\\n *.cxx \\\n *.cpp \\\n *.c++ \\\n *.d \\\n *.java \\\n *.ii \\\n *.ixx \\\n *.ipp \\\n *.i++ \\\n *.inl \\\n *.h \\\n *.hh \\\n *.hxx \\\n *.hpp \\\n *.h++ \\\n *.idl \\\n *.odl \\\n *.cs \\\n *.php \\\n *.php3 \\\n *.inc \\\n *.m \\\n *.mm \\\n *.dox \\\n *.py \\\n *.f90 \\\n *.f \\\n *.vhd \\\n *.vhdl\n\n# The RECURSIVE tag can be used to specify whether or not subdirectories should\n# be searched for input files as well.\n# The default value is: NO.\n\nRECURSIVE = YES\n\n# The EXCLUDE tag can be used to specify files and/or directories that should be\n# excluded from the INPUT source files. This way you can easily exclude a\n# subdirectory from a directory tree whose root is specified with the INPUT tag.\n#\n# Note that relative paths are relative to the directory from which doxygen is\n# run.\n\nEXCLUDE =\n\n# The EXCLUDE_SYMLINKS tag can be used to select whether or not files or\n# directories that are symbolic links (a Unix file system feature) are excluded\n# from the input.\n# The default value is: NO.\n\nEXCLUDE_SYMLINKS = NO\n\n# If the value of the INPUT tag contains directories, you can use the\n# EXCLUDE_PATTERNS tag to specify one or more wildcard patterns to exclude\n# certain files from those directories.\n#\n# Note that the wildcards are matched against the file with absolute path, so to\n# exclude all test directories for example use the pattern */test/*\n\nEXCLUDE_PATTERNS = */.svn/*\n\n# The EXCLUDE_SYMBOLS tag can be used to specify one or more symbol names\n# (namespaces, classes, functions, etc.) that should be excluded from the\n# output. The symbol name can be a fully qualified name, a word, or if the\n# wildcard * is used, a substring. Examples: ANamespace, AClass,\n# AClass::ANamespace, ANamespace::*Test\n#\n# Note that the wildcards are matched against the file with absolute path, so to\n# exclude all test directories use the pattern */test/*\n\nEXCLUDE_SYMBOLS =\n\n# The EXAMPLE_PATH tag can be used to specify one or more files or directories\n# that contain example code fragments that are included (see the \\include\n# command).\n\nEXAMPLE_PATH =\n\n# If the value of the EXAMPLE_PATH tag contains directories, you can use the\n# EXAMPLE_PATTERNS tag to specify one or more wildcard pattern (like *.cpp and\n# *.h) to filter out the source-files in the directories. If left blank all\n# files are included.\n\nEXAMPLE_PATTERNS = *\n\n# If the EXAMPLE_RECURSIVE tag is set to YES then subdirectories will be\n# searched for input files to be used with the \\include or \\dontinclude commands\n# irrespective of the value of the RECURSIVE tag.\n# The default value is: NO.\n\nEXAMPLE_RECURSIVE = NO\n\n# The IMAGE_PATH tag can be used to specify one or more files or directories\n# that contain images that are to be included in the documentation (see the\n# \\image command).\n\nIMAGE_PATH =\n\n# The INPUT_FILTER tag can be used to specify a program that doxygen should\n# invoke to filter for each input file. Doxygen will invoke the filter program\n# by executing (via popen()) the command:\n#\n# \n#\n# where is the value of the INPUT_FILTER tag, and is the\n# name of an input file. Doxygen will then use the output that the filter\n# program writes to standard output. If FILTER_PATTERNS is specified, this tag\n# will be ignored.\n#\n# Note that the filter must not add or remove lines; it is applied before the\n# code is scanned, but not when the output code is generated. If lines are added\n# or removed, the anchors will not be placed correctly.\n#\n# Note that for custom extensions or not directly supported extensions you also\n# need to set EXTENSION_MAPPING for the extension otherwise the files are not\n# properly processed by doxygen.\n\nINPUT_FILTER =\n\n# The FILTER_PATTERNS tag can be used to specify filters on a per file pattern\n# basis. Doxygen will compare the file name with each pattern and apply the\n# filter if there is a match. The filters are a list of the form: pattern=filter\n# (like *.cpp=my_cpp_filter). See INPUT_FILTER for further information on how\n# filters are used. If the FILTER_PATTERNS tag is empty or if none of the\n# patterns match the file name, INPUT_FILTER is applied.\n#\n# Note that for custom extensions or not directly supported extensions you also\n# need to set EXTENSION_MAPPING for the extension otherwise the files are not\n# properly processed by doxygen.\n\nFILTER_PATTERNS =\n\n# If the FILTER_SOURCE_FILES tag is set to YES, the input filter (if set using\n# INPUT_FILTER) will also be used to filter the input files that are used for\n# producing the source files to browse (i.e. when SOURCE_BROWSER is set to YES).\n# The default value is: NO.\n\nFILTER_SOURCE_FILES = NO\n\n# The FILTER_SOURCE_PATTERNS tag can be used to specify source filters per file\n# pattern. A pattern will override the setting for FILTER_PATTERN (if any) and\n# it is also possible to disable source filtering for a specific pattern using\n# *.ext= (so without naming a filter).\n# This tag requires that the tag FILTER_SOURCE_FILES is set to YES.\n\nFILTER_SOURCE_PATTERNS =\n\n# If the USE_MDFILE_AS_MAINPAGE tag refers to the name of a markdown file that\n# is part of the input, its contents will be placed on the main page\n# (index.html). This can be useful if you have a project on for instance GitHub\n# and want to reuse the introduction page also for the doxygen output.\n\nUSE_MDFILE_AS_MAINPAGE =\n\n#---------------------------------------------------------------------------\n# Configuration options related to source browsing\n#---------------------------------------------------------------------------\n\n# If the SOURCE_BROWSER tag is set to YES then a list of source files will be\n# generated. Documented entities will be cross-referenced with these sources.\n#\n# Note: To get rid of all source code in the generated output, make sure that\n# also VERBATIM_HEADERS is set to NO.\n# The default value is: NO.\n\nSOURCE_BROWSER = YES\n\n# Setting the INLINE_SOURCES tag to YES will include the body of functions,\n# classes and enums directly into the documentation.\n# The default value is: NO.\n\nINLINE_SOURCES = YES\n\n# Setting the STRIP_CODE_COMMENTS tag to YES will instruct doxygen to hide any\n# special comment blocks from generated source code fragments. Normal C, C++ and\n# Fortran comments will always remain visible.\n# The default value is: YES.\n\nSTRIP_CODE_COMMENTS = YES\n\n# If the REFERENCED_BY_RELATION tag is set to YES then for each documented\n# entity all documented functions referencing it will be listed.\n# The default value is: NO.\n\nREFERENCED_BY_RELATION = NO\n\n# If the REFERENCES_RELATION tag is set to YES then for each documented function\n# all documented entities called/used by that function will be listed.\n# The default value is: NO.\n\nREFERENCES_RELATION = NO\n\n# If the REFERENCES_LINK_SOURCE tag is set to YES and SOURCE_BROWSER tag is set\n# to YES then the hyperlinks from functions in REFERENCES_RELATION and\n# REFERENCED_BY_RELATION lists will link to the source code. Otherwise they will\n# link to the documentation.\n# The default value is: YES.\n\nREFERENCES_LINK_SOURCE = YES\n\n# If SOURCE_TOOLTIPS is enabled (the default) then hovering a hyperlink in the\n# source code will show a tooltip with additional information such as prototype,\n# brief description and links to the definition and documentation. Since this\n# will make the HTML file larger and loading of large files a bit slower, you\n# can opt to disable this feature.\n# The default value is: YES.\n# This tag requires that the tag SOURCE_BROWSER is set to YES.\n\nSOURCE_TOOLTIPS = YES\n\n# If the USE_HTAGS tag is set to YES then the references to source code will\n# point to the HTML generated by the htags(1) tool instead of doxygen built-in\n# source browser. The htags tool is part of GNU's global source tagging system\n# (see https://www.gnu.org/software/global/global.html). You will need version\n# 4.8.6 or higher.\n#\n# To use it do the following:\n# - Install the latest version of global\n# - Enable SOURCE_BROWSER and USE_HTAGS in the configuration file\n# - Make sure the INPUT points to the root of the source tree\n# - Run doxygen as normal\n#\n# Doxygen will invoke htags (and that will in turn invoke gtags), so these\n# tools must be available from the command line (i.e. in the search path).\n#\n# The result: instead of the source browser generated by doxygen, the links to\n# source code will now point to the output of htags.\n# The default value is: NO.\n# This tag requires that the tag SOURCE_BROWSER is set to YES.\n\nUSE_HTAGS = NO\n\n# If the VERBATIM_HEADERS tag is set the YES then doxygen will generate a\n# verbatim copy of the header file for each class for which an include is\n# specified. Set to NO to disable this.\n# See also: Section \\class.\n# The default value is: YES.\n\nVERBATIM_HEADERS = YES\n\n# If the CLANG_ASSISTED_PARSING tag is set to YES then doxygen will use the\n# clang parser (see: http://clang.llvm.org/) for more accurate parsing at the\n# cost of reduced performance. This can be particularly helpful with template\n# rich C++ code for which doxygen's built-in parser lacks the necessary type\n# information.\n# Note: The availability of this option depends on whether or not doxygen was\n# generated with the -Duse_libclang=ON option for CMake.\n# The default value is: NO.\n\nCLANG_ASSISTED_PARSING = NO\n\n# If clang assisted parsing is enabled you can provide the compiler with command\n# line options that you would normally use when invoking the compiler. Note that\n# the include paths will already be set by doxygen for the files and directories\n# specified with INPUT and INCLUDE_PATH.\n# This tag requires that the tag CLANG_ASSISTED_PARSING is set to YES.\n\nCLANG_OPTIONS =\n\n# If clang assisted parsing is enabled you can provide the clang parser with the\n# path to the compilation database (see:\n# http://clang.llvm.org/docs/HowToSetupToolingForLLVM.html) used when the files\n# were built. This is equivalent to specifying the \"-p\" option to a clang tool,\n# such as clang-check. These options will then be passed to the parser.\n# Note: The availability of this option depends on whether or not doxygen was\n# generated with the -Duse_libclang=ON option for CMake.\n\nCLANG_DATABASE_PATH =\n\n#---------------------------------------------------------------------------\n# Configuration options related to the alphabetical class index\n#---------------------------------------------------------------------------\n\n# If the ALPHABETICAL_INDEX tag is set to YES, an alphabetical index of all\n# compounds will be generated. Enable this if the project contains a lot of\n# classes, structs, unions or interfaces.\n# The default value is: YES.\n\nALPHABETICAL_INDEX = NO\n\n# The COLS_IN_ALPHA_INDEX tag can be used to specify the number of columns in\n# which the alphabetical index list will be split.\n# Minimum value: 1, maximum value: 20, default value: 5.\n# This tag requires that the tag ALPHABETICAL_INDEX is set to YES.\n\nCOLS_IN_ALPHA_INDEX = 5\n\n# In case all classes in a project start with a common prefix, all classes will\n# be put under the same header in the alphabetical index. The IGNORE_PREFIX tag\n# can be used to specify a prefix (or a list of prefixes) that should be ignored\n# while generating the index headers.\n# This tag requires that the tag ALPHABETICAL_INDEX is set to YES.\n\nIGNORE_PREFIX =\n\n#---------------------------------------------------------------------------\n# Configuration options related to the HTML output\n#---------------------------------------------------------------------------\n\n# If the GENERATE_HTML tag is set to YES, doxygen will generate HTML output\n# The default value is: YES.\n\nGENERATE_HTML = YES\n\n# The HTML_OUTPUT tag is used to specify where the HTML docs will be put. If a\n# relative path is entered the value of OUTPUT_DIRECTORY will be put in front of\n# it.\n# The default directory is: html.\n# This tag requires that the tag GENERATE_HTML is set to YES.\n\nHTML_OUTPUT = html\n\n# The HTML_FILE_EXTENSION tag can be used to specify the file extension for each\n# generated HTML page (for example: .htm, .php, .asp).\n# The default value is: .html.\n# This tag requires that the tag GENERATE_HTML is set to YES.\n\nHTML_FILE_EXTENSION = .html\n\n# The HTML_HEADER tag can be used to specify a user-defined HTML header file for\n# each generated HTML page. If the tag is left blank doxygen will generate a\n# standard header.\n#\n# To get valid HTML the header file that includes any scripts and style sheets\n# that doxygen needs, which is dependent on the configuration options used (e.g.\n# the setting GENERATE_TREEVIEW). It is highly recommended to start with a\n# default header using\n# doxygen -w html new_header.html new_footer.html new_stylesheet.css\n# YourConfigFile\n# and then modify the file new_header.html. See also section \"Doxygen usage\"\n# for information on how to generate the default header that doxygen normally\n# uses.\n# Note: The header is subject to change so you typically have to regenerate the\n# default header when upgrading to a newer version of doxygen. For a description\n# of the possible markers and block names see the documentation.\n# This tag requires that the tag GENERATE_HTML is set to YES.\n\nHTML_HEADER =\n\n# The HTML_FOOTER tag can be used to specify a user-defined HTML footer for each\n# generated HTML page. If the tag is left blank doxygen will generate a standard\n# footer. See HTML_HEADER for more information on how to generate a default\n# footer and what special commands can be used inside the footer. See also\n# section \"Doxygen usage\" for information on how to generate the default footer\n# that doxygen normally uses.\n# This tag requires that the tag GENERATE_HTML is set to YES.\n\nHTML_FOOTER =\n\n# The HTML_STYLESHEET tag can be used to specify a user-defined cascading style\n# sheet that is used by each HTML page. It can be used to fine-tune the look of\n# the HTML output. If left blank doxygen will generate a default style sheet.\n# See also section \"Doxygen usage\" for information on how to generate the style\n# sheet that doxygen normally uses.\n# Note: It is recommended to use HTML_EXTRA_STYLESHEET instead of this tag, as\n# it is more robust and this tag (HTML_STYLESHEET) will in the future become\n# obsolete.\n# This tag requires that the tag GENERATE_HTML is set to YES.\n\nHTML_STYLESHEET =\n\n# The HTML_EXTRA_STYLESHEET tag can be used to specify additional user-defined\n# cascading style sheets that are included after the standard style sheets\n# created by doxygen. Using this option one can overrule certain style aspects.\n# This is preferred over using HTML_STYLESHEET since it does not replace the\n# standard style sheet and is therefore more robust against future updates.\n# Doxygen will copy the style sheet files to the output directory.\n# Note: The order of the extra style sheet files is of importance (e.g. the last\n# style sheet in the list overrules the setting of the previous ones in the\n# list). For an example see the documentation.\n# This tag requires that the tag GENERATE_HTML is set to YES.\n\nHTML_EXTRA_STYLESHEET =\n\n# The HTML_EXTRA_FILES tag can be used to specify one or more extra images or\n# other source files which should be copied to the HTML output directory. Note\n# that these files will be copied to the base HTML output directory. Use the\n# $relpath^ marker in the HTML_HEADER and/or HTML_FOOTER files to load these\n# files. In the HTML_STYLESHEET file, use the file name only. Also note that the\n# files will be copied as-is; there are no commands or markers available.\n# This tag requires that the tag GENERATE_HTML is set to YES.\n\nHTML_EXTRA_FILES =\n\n# The HTML_COLORSTYLE_HUE tag controls the color of the HTML output. Doxygen\n# will adjust the colors in the style sheet and background images according to\n# this color. Hue is specified as an angle on a colorwheel, see\n# https://en.wikipedia.org/wiki/Hue for more information. For instance the value\n# 0 represents red, 60 is yellow, 120 is green, 180 is cyan, 240 is blue, 300\n# purple, and 360 is red again.\n# Minimum value: 0, maximum value: 359, default value: 220.\n# This tag requires that the tag GENERATE_HTML is set to YES.\n\nHTML_COLORSTYLE_HUE = 220\n\n# The HTML_COLORSTYLE_SAT tag controls the purity (or saturation) of the colors\n# in the HTML output. For a value of 0 the output will use grayscales only. A\n# value of 255 will produce the most vivid colors.\n# Minimum value: 0, maximum value: 255, default value: 100.\n# This tag requires that the tag GENERATE_HTML is set to YES.\n\nHTML_COLORSTYLE_SAT = 100\n\n# The HTML_COLORSTYLE_GAMMA tag controls the gamma correction applied to the\n# luminance component of the colors in the HTML output. Values below 100\n# gradually make the output lighter, whereas values above 100 make the output\n# darker. The value divided by 100 is the actual gamma applied, so 80 represents\n# a gamma of 0.8, The value 220 represents a gamma of 2.2, and 100 does not\n# change the gamma.\n# Minimum value: 40, maximum value: 240, default value: 80.\n# This tag requires that the tag GENERATE_HTML is set to YES.\n\nHTML_COLORSTYLE_GAMMA = 80\n\n# If the HTML_TIMESTAMP tag is set to YES then the footer of each generated HTML\n# page will contain the date and time when the page was generated. Setting this\n# to YES can help to show when doxygen was last run and thus if the\n# documentation is up to date.\n# The default value is: NO.\n# This tag requires that the tag GENERATE_HTML is set to YES.\n\nHTML_TIMESTAMP = YES\n\n# If the HTML_DYNAMIC_MENUS tag is set to YES then the generated HTML\n# documentation will contain a main index with vertical navigation menus that\n# are dynamically created via Javascript. If disabled, the navigation index will\n# consists of multiple levels of tabs that are statically embedded in every HTML\n# page. Disable this option to support browsers that do not have Javascript,\n# like the Qt help browser.\n# The default value is: YES.\n# This tag requires that the tag GENERATE_HTML is set to YES.\n\nHTML_DYNAMIC_MENUS = YES\n\n# If the HTML_DYNAMIC_SECTIONS tag is set to YES then the generated HTML\n# documentation will contain sections that can be hidden and shown after the\n# page has loaded.\n# The default value is: NO.\n# This tag requires that the tag GENERATE_HTML is set to YES.\n\nHTML_DYNAMIC_SECTIONS = NO\n\n# With HTML_INDEX_NUM_ENTRIES one can control the preferred number of entries\n# shown in the various tree structured indices initially; the user can expand\n# and collapse entries dynamically later on. Doxygen will expand the tree to\n# such a level that at most the specified number of entries are visible (unless\n# a fully collapsed tree already exceeds this amount). So setting the number of\n# entries 1 will produce a full collapsed tree by default. 0 is a special value\n# representing an infinite number of entries and will result in a full expanded\n# tree by default.\n# Minimum value: 0, maximum value: 9999, default value: 100.\n# This tag requires that the tag GENERATE_HTML is set to YES.\n\nHTML_INDEX_NUM_ENTRIES = 100\n\n# If the GENERATE_DOCSET tag is set to YES, additional index files will be\n# generated that can be used as input for Apple's Xcode 3 integrated development\n# environment (see: https://developer.apple.com/xcode/), introduced with OSX\n# 10.5 (Leopard). To create a documentation set, doxygen will generate a\n# Makefile in the HTML output directory. Running make will produce the docset in\n# that directory and running make install will install the docset in\n# ~/Library/Developer/Shared/Documentation/DocSets so that Xcode will find it at\n# startup. See https://developer.apple.com/library/archive/featuredarticles/Doxy\n# genXcode/_index.html for more information.\n# The default value is: NO.\n# This tag requires that the tag GENERATE_HTML is set to YES.\n\nGENERATE_DOCSET = NO\n\n# This tag determines the name of the docset feed. A documentation feed provides\n# an umbrella under which multiple documentation sets from a single provider\n# (such as a company or product suite) can be grouped.\n# The default value is: Doxygen generated docs.\n# This tag requires that the tag GENERATE_DOCSET is set to YES.\n\nDOCSET_FEEDNAME = \"Doxygen generated docs\"\n\n# This tag specifies a string that should uniquely identify the documentation\n# set bundle. This should be a reverse domain-name style string, e.g.\n# com.mycompany.MyDocSet. Doxygen will append .docset to the name.\n# The default value is: org.doxygen.Project.\n# This tag requires that the tag GENERATE_DOCSET is set to YES.\n\nDOCSET_BUNDLE_ID = org.doxygen.Project\n\n# The DOCSET_PUBLISHER_ID tag specifies a string that should uniquely identify\n# the documentation publisher. This should be a reverse domain-name style\n# string, e.g. com.mycompany.MyDocSet.documentation.\n# The default value is: org.doxygen.Publisher.\n# This tag requires that the tag GENERATE_DOCSET is set to YES.\n\nDOCSET_PUBLISHER_ID = org.doxygen.Publisher\n\n# The DOCSET_PUBLISHER_NAME tag identifies the documentation publisher.\n# The default value is: Publisher.\n# This tag requires that the tag GENERATE_DOCSET is set to YES.\n\nDOCSET_PUBLISHER_NAME = Publisher\n\n# If the GENERATE_HTMLHELP tag is set to YES then doxygen generates three\n# additional HTML index files: index.hhp, index.hhc, and index.hhk. The\n# index.hhp is a project file that can be read by Microsoft's HTML Help Workshop\n# (see: https://www.microsoft.com/en-us/download/details.aspx?id=21138) on\n# Windows.\n#\n# The HTML Help Workshop contains a compiler that can convert all HTML output\n# generated by doxygen into a single compiled HTML file (.chm). Compiled HTML\n# files are now used as the Windows 98 help format, and will replace the old\n# Windows help format (.hlp) on all Windows platforms in the future. Compressed\n# HTML files also contain an index, a table of contents, and you can search for\n# words in the documentation. The HTML workshop also contains a viewer for\n# compressed HTML files.\n# The default value is: NO.\n# This tag requires that the tag GENERATE_HTML is set to YES.\n\nGENERATE_HTMLHELP = NO\n\n# The CHM_FILE tag can be used to specify the file name of the resulting .chm\n# file. You can add a path in front of the file if the result should not be\n# written to the html output directory.\n# This tag requires that the tag GENERATE_HTMLHELP is set to YES.\n\nCHM_FILE =\n\n# The HHC_LOCATION tag can be used to specify the location (absolute path\n# including file name) of the HTML help compiler (hhc.exe). If non-empty,\n# doxygen will try to run the HTML help compiler on the generated index.hhp.\n# The file has to be specified with full path.\n# This tag requires that the tag GENERATE_HTMLHELP is set to YES.\n\nHHC_LOCATION =\n\n# The GENERATE_CHI flag controls if a separate .chi index file is generated\n# (YES) or that it should be included in the master .chm file (NO).\n# The default value is: NO.\n# This tag requires that the tag GENERATE_HTMLHELP is set to YES.\n\nGENERATE_CHI = NO\n\n# The CHM_INDEX_ENCODING is used to encode HtmlHelp index (hhk), content (hhc)\n# and project file content.\n# This tag requires that the tag GENERATE_HTMLHELP is set to YES.\n\nCHM_INDEX_ENCODING =\n\n# The BINARY_TOC flag controls whether a binary table of contents is generated\n# (YES) or a normal table of contents (NO) in the .chm file. Furthermore it\n# enables the Previous and Next buttons.\n# The default value is: NO.\n# This tag requires that the tag GENERATE_HTMLHELP is set to YES.\n\nBINARY_TOC = NO\n\n# The TOC_EXPAND flag can be set to YES to add extra items for group members to\n# the table of contents of the HTML help documentation and to the tree view.\n# The default value is: NO.\n# This tag requires that the tag GENERATE_HTMLHELP is set to YES.\n\nTOC_EXPAND = NO\n\n# If the GENERATE_QHP tag is set to YES and both QHP_NAMESPACE and\n# QHP_VIRTUAL_FOLDER are set, an additional index file will be generated that\n# can be used as input for Qt's qhelpgenerator to generate a Qt Compressed Help\n# (.qch) of the generated HTML documentation.\n# The default value is: NO.\n# This tag requires that the tag GENERATE_HTML is set to YES.\n\nGENERATE_QHP = NO\n\n# If the QHG_LOCATION tag is specified, the QCH_FILE tag can be used to specify\n# the file name of the resulting .qch file. The path specified is relative to\n# the HTML output folder.\n# This tag requires that the tag GENERATE_QHP is set to YES.\n\nQCH_FILE =\n\n# The QHP_NAMESPACE tag specifies the namespace to use when generating Qt Help\n# Project output. For more information please see Qt Help Project / Namespace\n# (see: https://doc.qt.io/archives/qt-4.8/qthelpproject.html#namespace).\n# The default value is: org.doxygen.Project.\n# This tag requires that the tag GENERATE_QHP is set to YES.\n\nQHP_NAMESPACE = org.doxygen.Project\n\n# The QHP_VIRTUAL_FOLDER tag specifies the namespace to use when generating Qt\n# Help Project output. For more information please see Qt Help Project / Virtual\n# Folders (see: https://doc.qt.io/archives/qt-4.8/qthelpproject.html#virtual-\n# folders).\n# The default value is: doc.\n# This tag requires that the tag GENERATE_QHP is set to YES.\n\nQHP_VIRTUAL_FOLDER = doc\n\n# If the QHP_CUST_FILTER_NAME tag is set, it specifies the name of a custom\n# filter to add. For more information please see Qt Help Project / Custom\n# Filters (see: https://doc.qt.io/archives/qt-4.8/qthelpproject.html#custom-\n# filters).\n# This tag requires that the tag GENERATE_QHP is set to YES.\n\nQHP_CUST_FILTER_NAME =\n\n# The QHP_CUST_FILTER_ATTRS tag specifies the list of the attributes of the\n# custom filter to add. For more information please see Qt Help Project / Custom\n# Filters (see: https://doc.qt.io/archives/qt-4.8/qthelpproject.html#custom-\n# filters).\n# This tag requires that the tag GENERATE_QHP is set to YES.\n\nQHP_CUST_FILTER_ATTRS =\n\n# The QHP_SECT_FILTER_ATTRS tag specifies the list of the attributes this\n# project's filter section matches. Qt Help Project / Filter Attributes (see:\n# https://doc.qt.io/archives/qt-4.8/qthelpproject.html#filter-attributes).\n# This tag requires that the tag GENERATE_QHP is set to YES.\n\nQHP_SECT_FILTER_ATTRS =\n\n# The QHG_LOCATION tag can be used to specify the location of Qt's\n# qhelpgenerator. If non-empty doxygen will try to run qhelpgenerator on the\n# generated .qhp file.\n# This tag requires that the tag GENERATE_QHP is set to YES.\n\nQHG_LOCATION =\n\n# If the GENERATE_ECLIPSEHELP tag is set to YES, additional index files will be\n# generated, together with the HTML files, they form an Eclipse help plugin. To\n# install this plugin and make it available under the help contents menu in\n# Eclipse, the contents of the directory containing the HTML and XML files needs\n# to be copied into the plugins directory of eclipse. The name of the directory\n# within the plugins directory should be the same as the ECLIPSE_DOC_ID value.\n# After copying Eclipse needs to be restarted before the help appears.\n# The default value is: NO.\n# This tag requires that the tag GENERATE_HTML is set to YES.\n\nGENERATE_ECLIPSEHELP = NO\n\n# A unique identifier for the Eclipse help plugin. When installing the plugin\n# the directory name containing the HTML and XML files should also have this\n# name. Each documentation set should have its own identifier.\n# The default value is: org.doxygen.Project.\n# This tag requires that the tag GENERATE_ECLIPSEHELP is set to YES.\n\nECLIPSE_DOC_ID = org.doxygen.Project\n\n# If you want full control over the layout of the generated HTML pages it might\n# be necessary to disable the index and replace it with your own. The\n# DISABLE_INDEX tag can be used to turn on/off the condensed index (tabs) at top\n# of each HTML page. A value of NO enables the index and the value YES disables\n# it. Since the tabs in the index contain the same information as the navigation\n# tree, you can set this option to YES if you also set GENERATE_TREEVIEW to YES.\n# The default value is: NO.\n# This tag requires that the tag GENERATE_HTML is set to YES.\n\nDISABLE_INDEX = NO\n\n# The GENERATE_TREEVIEW tag is used to specify whether a tree-like index\n# structure should be generated to display hierarchical information. If the tag\n# value is set to YES, a side panel will be generated containing a tree-like\n# index structure (just like the one that is generated for HTML Help). For this\n# to work a browser that supports JavaScript, DHTML, CSS and frames is required\n# (i.e. any modern browser). Windows users are probably better off using the\n# HTML help feature. Via custom style sheets (see HTML_EXTRA_STYLESHEET) one can\n# further fine-tune the look of the index. As an example, the default style\n# sheet generated by doxygen has an example that shows how to put an image at\n# the root of the tree instead of the PROJECT_NAME. Since the tree basically has\n# the same information as the tab index, you could consider setting\n# DISABLE_INDEX to YES when enabling this option.\n# The default value is: NO.\n# This tag requires that the tag GENERATE_HTML is set to YES.\n\nGENERATE_TREEVIEW = YES\n\n# The ENUM_VALUES_PER_LINE tag can be used to set the number of enum values that\n# doxygen will group on one line in the generated HTML documentation.\n#\n# Note that a value of 0 will completely suppress the enum values from appearing\n# in the overview section.\n# Minimum value: 0, maximum value: 20, default value: 4.\n# This tag requires that the tag GENERATE_HTML is set to YES.\n\nENUM_VALUES_PER_LINE = 4\n\n# If the treeview is enabled (see GENERATE_TREEVIEW) then this tag can be used\n# to set the initial width (in pixels) of the frame in which the tree is shown.\n# Minimum value: 0, maximum value: 1500, default value: 250.\n# This tag requires that the tag GENERATE_HTML is set to YES.\n\nTREEVIEW_WIDTH = 250\n\n# If the EXT_LINKS_IN_WINDOW option is set to YES, doxygen will open links to\n# external symbols imported via tag files in a separate window.\n# The default value is: NO.\n# This tag requires that the tag GENERATE_HTML is set to YES.\n\nEXT_LINKS_IN_WINDOW = NO\n\n# Use this tag to change the font size of LaTeX formulas included as images in\n# the HTML documentation. When you change the font size after a successful\n# doxygen run you need to manually remove any form_*.png images from the HTML\n# output directory to force them to be regenerated.\n# Minimum value: 8, maximum value: 50, default value: 10.\n# This tag requires that the tag GENERATE_HTML is set to YES.\n\nFORMULA_FONTSIZE = 10\n\n# Use the FORMULA_TRANSPARENT tag to determine whether or not the images\n# generated for formulas are transparent PNGs. Transparent PNGs are not\n# supported properly for IE 6.0, but are supported on all modern browsers.\n#\n# Note that when changing this option you need to delete any form_*.png files in\n# the HTML output directory before the changes have effect.\n# The default value is: YES.\n# This tag requires that the tag GENERATE_HTML is set to YES.\n\nFORMULA_TRANSPARENT = YES\n\n# Enable the USE_MATHJAX option to render LaTeX formulas using MathJax (see\n# https://www.mathjax.org) which uses client side Javascript for the rendering\n# instead of using pre-rendered bitmaps. Use this if you do not have LaTeX\n# installed or if you want to formulas look prettier in the HTML output. When\n# enabled you may also need to install MathJax separately and configure the path\n# to it using the MATHJAX_RELPATH option.\n# The default value is: NO.\n# This tag requires that the tag GENERATE_HTML is set to YES.\n\nUSE_MATHJAX = NO\n\n# When MathJax is enabled you can set the default output format to be used for\n# the MathJax output. See the MathJax site (see:\n# http://docs.mathjax.org/en/latest/output.html) for more details.\n# Possible values are: HTML-CSS (which is slower, but has the best\n# compatibility), NativeMML (i.e. MathML) and SVG.\n# The default value is: HTML-CSS.\n# This tag requires that the tag USE_MATHJAX is set to YES.\n\nMATHJAX_FORMAT = HTML-CSS\n\n# When MathJax is enabled you need to specify the location relative to the HTML\n# output directory using the MATHJAX_RELPATH option. The destination directory\n# should contain the MathJax.js script. For instance, if the mathjax directory\n# is located at the same level as the HTML output directory, then\n# MATHJAX_RELPATH should be ../mathjax. The default value points to the MathJax\n# Content Delivery Network so you can quickly see the result without installing\n# MathJax. However, it is strongly recommended to install a local copy of\n# MathJax from https://www.mathjax.org before deployment.\n# The default value is: https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/.\n# This tag requires that the tag USE_MATHJAX is set to YES.\n\nMATHJAX_RELPATH = http://www.mathjax.org/mathjax\n\n# The MATHJAX_EXTENSIONS tag can be used to specify one or more MathJax\n# extension names that should be enabled during MathJax rendering. For example\n# MATHJAX_EXTENSIONS = TeX/AMSmath TeX/AMSsymbols\n# This tag requires that the tag USE_MATHJAX is set to YES.\n\nMATHJAX_EXTENSIONS =\n\n# The MATHJAX_CODEFILE tag can be used to specify a file with javascript pieces\n# of code that will be used on startup of the MathJax code. See the MathJax site\n# (see: http://docs.mathjax.org/en/latest/output.html) for more details. For an\n# example see the documentation.\n# This tag requires that the tag USE_MATHJAX is set to YES.\n\nMATHJAX_CODEFILE =\n\n# When the SEARCHENGINE tag is enabled doxygen will generate a search box for\n# the HTML output. The underlying search engine uses javascript and DHTML and\n# should work on any modern browser. Note that when using HTML help\n# (GENERATE_HTMLHELP), Qt help (GENERATE_QHP), or docsets (GENERATE_DOCSET)\n# there is already a search function so this one should typically be disabled.\n# For large projects the javascript based search engine can be slow, then\n# enabling SERVER_BASED_SEARCH may provide a better solution. It is possible to\n# search using the keyboard; to jump to the search box use + S\n# (what the is depends on the OS and browser, but it is typically\n# , /