Issue #7, #16, #17 | Small enhancements (#18)

* Issue #7 | Fix state insolvency, add more debug code, add YO_ prefix to internal macros

* Issue #7 | Try to fix the GitHub Action pipeline

* Committing clang-format changes

* Issue #7 | Trigger clang-format and fix logo and name

* Issue #0 | General readability enhancements

* Committing clang-format changes

* Issue #17 | Add examples of library optimisation to README.md

---------

Co-authored-by: Clang Robot <robot@example.com>
Co-authored-by: GitHub Actions <actions@github.com>

.github/workflows/cmake.yml

@@ -21,17 +21,20 @@ jobs:
     - uses: actions/checkout@v3
       with:
         submodules: recursive
+        repository: ${{ github.event.pull_request.head.repo.full_name }}
+        ref: ${{ github.event.pull_request.head.ref }}
 
     - uses: DoozyX/clang-format-lint-action@v0.16.2
       with:
         source: '.'
         clangFormatVersion: 16
         style: file
         inplace: True
+
     - uses: EndBug/add-and-commit@v9
       with:
-        author_name: Clang Robot
-        author_email: robot@example.com
+        author_name: GitHub Actions
+        author_email: actions@github.com
         message: 'Committing clang-format changes'
       env:
         GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
@@ -61,4 +64,3 @@ jobs:
       # Execute tests defined by the CMake configuration.
       # See https://cmake.org/cmake/help/latest/manual/ctest.1.html for more detail
       run: ctest -C ${{env.BUILD_TYPE}}
-

CMakeLists.txt

@@ -14,7 +14,7 @@ add_subdirectory(deps/rapidyaml)
 set(LIB_NAME yaml-optimizer-lib)
 
 # Add optimization library as a dependency
-add_subdirectory(src)
+add_subdirectory(optimizer)
 
 if (YO_BUILD_TESTS)
     add_subdirectory(test)

README.md

@@ -10,6 +10,72 @@ The project aims to provide a fast and convenient way to optimise large YAML con
 - [Lyra](https://github.com/bfgroup/Lyra.git): A simple-to-use, composing, header-only, command line arguments parser for C++ 11 and beyond.
 - [fmt](https://github.com/fmtlib/fmt): A formatting library providing a fast and safe alternative to C stdio and C++ iostreams.
 
+## Examples
+
+Currently library only supports optimizing fully identical nodes:
+
+```yaml
+# YAML example with references and anchors
+
+# Define an anchor for a nested sequence
+- top_level:
+    - nested:
+        - - Apple
+          - Orange
+          - Banana
+
+# Define an anchor for a nested mapping
+- another_level:
+    - even_deeper:
+        - further:
+            - key1: value1
+              key2: value2
+
+# Use the anchors in different parts of the YAML
+- other_level:
+    - some_key:
+        - Apple
+        - Orange
+        - Banana
+    - additional_key:
+        key1: value1
+        key2: value2
+
+# Additional data
+- SomeList:
+    - 1
+    - 2
+    - 3
+    - 4
+- SomeValue: true
+```
+
+So the result would be (note that indentations and comments are currently removed):
+
+```yaml
+- top_level:
+    - nested:
+        - &anchor_0
+          - Apple
+          - Orange
+          - Banana
+- another_level:
+    - even_deeper:
+        - further:
+            - &anchor_1
+              key1: value1
+              key2: value2
+- other_level:
+    - some_key: *anchor_0
+    - additional_key: *anchor_1
+- SomeList:
+    - 1
+    - 2
+    - 3
+    - 4
+- SomeValue: true
+```
+
 ## Roadmap
 
 - [x] Replace identical blocks with anchors to the first one

src/CMakeLists.txt → optimizer/CMakeLists.txt

@@ -1,4 +1,5 @@
-add_library(${LIB_NAME} STATIC optimizer.cpp)
+file(GLOB LIB_OPTIMIZER_SOURCES "src/**/*.cpp")
+add_library(${LIB_NAME} STATIC ${LIB_OPTIMIZER_SOURCES})
 
 target_include_directories(${LIB_NAME} PUBLIC inc)
 

optimizer/inc/debug/assert.h

@@ -0,0 +1,19 @@
+#pragma once
+
+#include "debug/exception.h"
+#include "debug/throw.h"
+
+#include <sstream>
+
+#define YO_DEBUG_ASSERT(condition) YO_DEBUG_ASSERT_WITH_MSG(condition, "");
+
+#define YO_DEBUG_ASSERT_WITH_MSG(condition, description, ...)                  \
+    do                                                                         \
+    {                                                                          \
+        if (!(condition))                                                      \
+        {                                                                      \
+            YO_THROW(YamlOptimizerError,                                       \
+                     "Assertion failed: {} in file " __FILE__ " at line {}",   \
+                     fmt::format(description, ##__VA_ARGS__), __LINE__)        \
+        }                                                                      \
+    } while (false);

src/inc/debug/exception.hpp → optimizer/inc/debug/exception.h

@@ -5,5 +5,5 @@
 class YamlOptimizerError : public std::runtime_error
 {
 public:
-    YamlOptimizerError(std::string const& what) : std::runtime_error(what) {}
+    YamlOptimizerError(std::string const& what);
 };

src/inc/debug/print.hpp → optimizer/inc/debug/print.h

@@ -2,13 +2,13 @@
 
 #ifndef YO_DEBUG
 
-#define DEBUG_PRINT(...)
+#define YO_DEBUG_PRINT(...)
 
 #else
 
 #include <fmt/format.h>
 
-#define DEBUG_PRINT(message, ...)                                              \
+#define YO_DEBUG_PRINT(message, ...)                                           \
     fmt::print("[DEBUG] " message "\n", ##__VA_ARGS__)
 
 #endif // YO_DEBUG

src/inc/optimizer/optimizer.h → optimizer/inc/optimizer/optimizer.h

@@ -59,7 +59,9 @@ class YamlOptimizer
      */
     void dump(std::string const& filename);
 
-    NAMED_PRIVATE_SECTION(Input data)
+private:
+    /* clang-format off */
+NAMED_PRIVATE_SECTION(Input data)
 
     const OptimizationSettings settings_;
 
@@ -68,7 +70,7 @@ class YamlOptimizer
     static constexpr std::string_view BOM{"\xEF\xBB\xBF"};
     bool is_utf8 = false;
 
-    NAMED_PRIVATE_SECTION(Processed data)
+NAMED_PRIVATE_SECTION(Processed data)
 
     struct NodeInfo
     {
@@ -79,27 +81,28 @@ class YamlOptimizer
     ryml::Tree tree_;
     std::size_t anchor_count_ = 0;
 
-    NAMED_PRIVATE_SECTION(Tree pre - processing utils)
+NAMED_PRIVATE_SECTION(Tree pre-processing utils)
 
     void get_info();
     std::size_t get_info_impl(ryml::ConstNodeRef const& node);
 
-    NAMED_PRIVATE_SECTION(Node utils)
+NAMED_PRIVATE_SECTION(Node utils)
 
     bool nodes_equal(ryml::ConstNodeRef const& a,
                      ryml::ConstNodeRef const& b) const;
     bool long_types_equal(ryml::ConstNodeRef const& a,
                           ryml::ConstNodeRef const& b) const;
 
-    NAMED_PRIVATE_SECTION(IO utils)
+NAMED_PRIVATE_SECTION(IO utils)
 
     void write_to_ostream(std::ostream& os) const;
     ryml::substr get_clean_content(std::string& content);
 
 #ifdef YO_DEBUG
-    NAMED_PRIVATE_SECTION(Debug utils)
+NAMED_PRIVATE_SECTION(Debug utils)
 
     void debug_print_data() const;
 
 #endif // YO_DEBUG
-};
+    /* clang-format on */
+}; // class YamlOptimizer

optimizer/inc/utils/io.h

@@ -0,0 +1,11 @@
+#pragma once
+
+#include <istream>
+#include <string>
+
+namespace io_utils
+{
+
+std::string get_file_content(std::istream& is);
+
+} // namespace io_utils

optimizer/inc/utils/node.h

@@ -0,0 +1,29 @@
+#pragma once
+
+#include "ryml.hpp"
+
+namespace node_utils
+{
+
+void set_reference(ryml::NodeRef& node, ryml::csubstr anchor);
+
+std::size_t
+get_next_valid_id_after_content_removal(ryml::NodeRef node,
+                                        std::size_t max_possible_id);
+
+std::string to_string(const ryml::ConstNodeRef& node);
+
+class NodeDiff
+{
+    ryml::ConstNodeRef lhs_;
+    ryml::ConstNodeRef rhs_;
+
+public:
+    NodeDiff(const ryml::ConstNodeRef& lhs, const ryml::ConstNodeRef& rhs);
+
+    std::string str() const;
+
+    friend std::ostream& operator<<(std::ostream& os, NodeDiff const& diff);
+};
+
+} // namespace node_utils

optimizer/inc/utils/platform.h

@@ -0,0 +1,55 @@
+#pragma once
+
+/* clang-format off */
+#if defined(__APPLE__) && defined(__MACH__)
+    // Apple platforms
+    #define YO_APPLE
+
+    #include <TargetConditionals.h>
+    #if TARGET_OS_MAC
+        // macOS
+        #define YO_MACOS
+    #endif
+
+    #if TARGET_OS_IOS
+        // iOS
+        #define YO_IOS
+    #endif
+
+    #if TARGET_OS_TV
+        // tvOS
+        #define YO_TVOS
+    #endif
+
+    #if TARGET_OS_WATCH
+        // watchOS
+        #define YO_WATCHOS
+    #endif
+#elif defined(_WIN32) || defined(_WIN64)
+    // Windows platforms
+    #define YO_WINDOWS
+
+    #ifdef _WIN32
+        #define YO_WINDOWS32
+    #endif
+
+    #ifdef _WIN64
+        #define YO_WINDOWS64
+    #endif
+#elif defined(__linux__)
+    // Linux platform
+    #define YO_LINUX
+#elif defined(__ANDROID__)
+    // Android platform
+    #define YO_ANDROID
+#elif defined(__FreeBSD__)
+    // FreeBSD platform
+    #define YO_FREEBSD
+#elif defined(__unix__) || defined(__unix)
+    // Generic Unix platform
+    #define YO_UNIX
+#else
+    // Unsupported platform
+    #error Unsupported platform
+#endif
+/* clang-format off */

optimizer/inc/utils/string.h

@@ -0,0 +1,27 @@
+#pragma once
+
+#include <string>
+
+namespace string_utils
+{
+
+// Function to check if a string starts with a given substring
+bool starts_with(std::string_view str, std::string_view start);
+
+// Function to check if a string ends with a given substring
+bool ends_with(std::string_view str, std::string_view end);
+
+class StringDiff
+{
+    std::string lhs_;
+    std::string rhs_;
+
+public:
+    StringDiff(const std::string& lhs, const std::string& rhs);
+
+    std::string str() const;
+
+    friend std::ostream& operator<<(std::ostream& os, StringDiff const& diff);
+}; // class StringDiff
+
+} // namespace string_utils

optimizer/src/debug/exception.cpp

@@ -0,0 +1,6 @@
+#include "debug/exception.h"
+
+YamlOptimizerError::YamlOptimizerError(std::string const& what)
+    : std::runtime_error(what)
+{
+}