Merge pull request 'Create version 1.2.1' (#2) from 121 into main

Reviewed-on: #2

.claude/settings.local.json

@@ -0,0 +1,12 @@
+{
+  "permissions": {
+    "allow": [
+      "Bash(find:*)",
+      "Bash(mkdir:*)",
+      "Bash(cmake:*)",
+      "Bash(make:*)",
+      "Bash(cat:*)"
+    ],
+    "deny": []
+  }
+}

.gitignore

@@ -37,4 +37,5 @@ build_*/**
 cmake-build*/**
 .idea
 puml/**
-.vscode/settings.json
+.vscode/settings.json
+CMakeUserPresets.json

ArffFiles.hpp

@@ -10,6 +10,8 @@
 #include <cctype> // std::isdigit
 #include <algorithm> // std::all_of std::transform
 #include <filesystem> // For file size checking
+#include "arffFiles_config.h"
+
 
 // Summary information structure for ARFF files
 struct ArffSummary {
@@ -24,28 +26,28 @@ struct ArffSummary {
 
 /**
  * @brief Header-only C++17 library for parsing ARFF (Attribute-Relation File Format) files
- * 
+ *
  * This class provides functionality to load and parse ARFF files, automatically detecting
  * numeric vs categorical features and performing factorization of categorical attributes.
- * 
+ *
  * @warning THREAD SAFETY: This class is NOT thread-safe!
- * 
+ *
  * Thread Safety Considerations:
  * - Multiple instances can be used safely in different threads (each instance is independent)
  * - A single instance MUST NOT be accessed concurrently from multiple threads
  * - All member functions (including getters) modify or access mutable state
  * - Static methods (summary, trim, split) are thread-safe as they don't access instance state
- * 
+ *
  * Memory Safety:
  * - Built-in protection against resource exhaustion with configurable limits
  * - File size limit: 100 MB (DEFAULT_MAX_FILE_SIZE)
- * - Sample count limit: 1 million samples (DEFAULT_MAX_SAMPLES)  
+ * - Sample count limit: 1 million samples (DEFAULT_MAX_SAMPLES)
  * - Feature count limit: 10,000 features (DEFAULT_MAX_FEATURES)
- * 
+ *
  * Usage Patterns:
  * - Single-threaded: Create one instance, call load(), then access data via getters
  * - Multi-threaded: Create separate instances per thread, or use external synchronization
- * 
+ *
  * @example
  * // Thread-safe usage pattern:
  * void processFile(const std::string& filename) {
@@ -55,24 +57,23 @@ struct ArffSummary {
  *     auto y = arff.getY();
  *     // Process data...
  * }
- * 
- * @example  
+ *
+ * @example
  * // UNSAFE usage pattern:
  * ArffFiles globalArff;  // Global instance
  * // Thread 1: globalArff.load("file1.arff");  // UNSAFE!
  * // Thread 2: globalArff.load("file2.arff");  // UNSAFE!
  */
 class ArffFiles {
-    const std::string VERSION = "1.1.0";
-    
+private:
     // Memory usage limits (configurable via environment variables)
     static constexpr size_t DEFAULT_MAX_FILE_SIZE = 100 * 1024 * 1024; // 100 MB
     static constexpr size_t DEFAULT_MAX_SAMPLES = 1000000; // 1 million samples
     static constexpr size_t DEFAULT_MAX_FEATURES = 10000; // 10k features
-    
+
 public:
     ArffFiles() = default;
-    
+
     // Move constructor
     ArffFiles(ArffFiles&& other) noexcept
         : lines(std::move(other.lines))
@@ -86,7 +87,7 @@ public:
     {
         // Other object is left in a valid but unspecified state
     }
-    
+
     // Move assignment operator
     ArffFiles& operator=(ArffFiles&& other) noexcept
     {
@@ -102,13 +103,13 @@ public:
         }
         return *this;
     }
-    
-    // Copy constructor (explicitly defaulted)
-    ArffFiles(const ArffFiles& other) = default;
-    
-    // Copy assignment operator (explicitly defaulted)
-    ArffFiles& operator=(const ArffFiles& other) = default;
-    
+
+    // Copy constructor (explicitly delete)
+    ArffFiles(const ArffFiles& other) = delete;
+
+    // Copy assignment operator (explicitly deleted)
+    ArffFiles& operator=(const ArffFiles& other) = delete;
+
     // Destructor (explicitly defaulted)
     ~ArffFiles() = default;
     void load(const std::string& fileName, bool classLast = true)
@@ -231,7 +232,7 @@ public:
     const std::vector<int>& getY() const { return y; }
     const std::map<std::string, bool>& getNumericAttributes() const { return numeric_features; }
     const std::vector<std::pair<std::string, std::string>>& getAttributes() const { return attributes; };
-    
+
     // Move-enabled getters for efficient data transfer
     // WARNING: These methods move data OUT of the object, leaving it in an empty but valid state
     // Use these when you want to transfer ownership of large data structures for performance
@@ -241,7 +242,7 @@ public:
     std::map<std::string, std::vector<std::string>> moveStates() noexcept { return std::move(states); }
     std::vector<std::pair<std::string, std::string>> moveAttributes() noexcept { return std::move(attributes); }
     std::map<std::string, bool> moveNumericAttributes() noexcept { return std::move(numeric_features); }
-    
+
     std::vector<std::string> split(const std::string& text, char delimiter)
     {
         std::vector<std::string> result;
@@ -252,26 +253,27 @@ public:
         }
         return result;
     }
-    std::string version() const { return VERSION; }
+    std::string version() const { return ARFFLIB_VERSION; }
 
 private:
     // Helper function to validate file path for security
-    static void validateFilePath(const std::string& fileName) {
+    static void validateFilePath(const std::string& fileName)
+    {
         if (fileName.empty()) {
             throw std::invalid_argument("File path cannot be empty");
         }
-        
+
         // Check for path traversal attempts
         if (fileName.find("..") != std::string::npos) {
             throw std::invalid_argument("Path traversal detected in file path: " + fileName);
         }
-        
+
         // Check for absolute paths starting with / (Unix) or drive letters (Windows)
         if (fileName[0] == '/' || (fileName.length() >= 3 && fileName[1] == ':')) {
             // Allow absolute paths but log a warning - this is for user awareness
             // In production, you might want to restrict this based on your security requirements
         }
-        
+
         // Check for suspicious characters that could be used in path manipulation
         const std::string suspiciousChars = "\x00\x01\x02\x03\x04\x05\x06\x07\x08\x09\x0b\x0c\x0e\x0f\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f";
         for (char c : suspiciousChars) {
@@ -279,33 +281,35 @@ private:
                 throw std::invalid_argument("Invalid character detected in file path");
             }
         }
-        
+
         // Check for excessively long paths (potential buffer overflow attempts)
         constexpr size_t MAX_PATH_LENGTH = 4096; // Common filesystem limit
         if (fileName.length() > MAX_PATH_LENGTH) {
             throw std::invalid_argument("File path too long (exceeds " + std::to_string(MAX_PATH_LENGTH) + " characters)");
         }
-        
+
         // Additional validation using filesystem operations when available
         try {
             // Check if the file exists and validate its canonical path
             if (std::filesystem::exists(fileName)) {
                 std::filesystem::path normalizedPath = std::filesystem::canonical(fileName);
                 std::string normalizedStr = normalizedPath.string();
-                
+
                 // Check if normalized path still contains traversal attempts
                 if (normalizedStr.find("..") != std::string::npos) {
                     throw std::invalid_argument("Path traversal detected after normalization: " + normalizedStr);
                 }
             }
-        } catch (const std::filesystem::filesystem_error& e) {
+        }
+        catch (const std::filesystem::filesystem_error& e) {
             // If filesystem operations fail, we can still proceed with basic validation
             // This ensures compatibility with systems where filesystem might not be fully available
         }
     }
 
     // Helper function to validate resource usage limits
-    static void validateResourceLimits(const std::string& fileName, size_t sampleCount = 0, size_t featureCount = 0) {
+    static void validateResourceLimits(const std::string& fileName, size_t sampleCount = 0, size_t featureCount = 0)
+    {
         // Check file size limit
         try {
             if (std::filesystem::exists(fileName)) {
@@ -314,16 +318,17 @@ private:
                     throw std::invalid_argument("File size (" + std::to_string(fileSize) + " bytes) exceeds maximum allowed size (" + std::to_string(DEFAULT_MAX_FILE_SIZE) + " bytes)");
                 }
             }
-        } catch (const std::filesystem::filesystem_error&) {
+        }
+        catch (const std::filesystem::filesystem_error&) {
             // If filesystem operations fail, continue without size checking
             // This ensures compatibility with systems where filesystem might not be available
         }
-        
+
         // Check sample count limit
         if (sampleCount > DEFAULT_MAX_SAMPLES) {
             throw std::invalid_argument("Number of samples (" + std::to_string(sampleCount) + ") exceeds maximum allowed (" + std::to_string(DEFAULT_MAX_SAMPLES) + ")");
         }
-        
+
         // Check feature count limit
         if (featureCount > DEFAULT_MAX_FEATURES) {
             throw std::invalid_argument("Number of features (" + std::to_string(featureCount) + ") exceeds maximum allowed (" + std::to_string(DEFAULT_MAX_FEATURES) + ")");
@@ -352,12 +357,12 @@ private:
                 continue;
             auto values = attribute.second;
             std::transform(values.begin(), values.end(), values.begin(), ::toupper);
-            
+
             // Enhanced attribute type detection
             bool isNumeric = values == "REAL" || values == "INTEGER" || values == "NUMERIC";
             bool isDate = values.find("DATE") != std::string::npos;
             bool isString = values == "STRING";
-            
+
             // For now, treat DATE and STRING as categorical (non-numeric)
             // This provides basic compatibility while maintaining existing functionality
             numeric_features[feature] = isNumeric;
@@ -490,7 +495,7 @@ private:
 
         // Validate file path for security
         validateFilePath(fileName);
-        
+
         // Validate file size before processing
         validateResourceLimits(fileName);
 
@@ -507,13 +512,13 @@ private:
             if (line.empty() || line[0] == '%' || line == "\r" || line == " ") {
                 continue;
             }
-            
+
             // Skip sparse data format for now (lines starting with '{')
             // Future enhancement: implement full sparse data support
             if (!line.empty() && line[0] == '{') {
                 continue;
             }
-            
+
             if (line.find("@attribute") != std::string::npos || line.find("@ATTRIBUTE") != std::string::npos) {
                 std::stringstream ss(line);
                 ss >> keyword >> attribute;
@@ -564,7 +569,7 @@ private:
         if (lines.empty()) {
             throw std::invalid_argument("No data samples found in file");
         }
-        
+
         // Validate loaded data dimensions against limits
         validateResourceLimits(fileName, lines.size(), attributes.size());
 
@@ -621,15 +626,16 @@ private:
     }
 
     // Common helper function to parse ARFF file attributes and count samples
-    static int parseArffFile(const std::string& fileName, 
-                            std::vector<std::pair<std::string, std::string>>& attributes,
-                            std::set<std::string>& uniqueClasses,
-                            size_t& sampleCount,
-                            int classIndex = -1,
-                            const std::string& classNameToFind = "") {
+    static int parseArffFile(const std::string& fileName,
+        std::vector<std::pair<std::string, std::string>>& attributes,
+        std::set<std::string>& uniqueClasses,
+        size_t& sampleCount,
+        int classIndex = -1,
+        const std::string& classNameToFind = "")
+    {
         // Validate file path for security
         validateFilePath(fileName);
-        
+
         std::ifstream file(fileName);
         if (!file.is_open()) {
             throw std::invalid_argument("Unable to open file: " + fileName);
@@ -645,12 +651,12 @@ private:
             if (line.empty() || line[0] == '%' || line == "\r" || line == " ") {
                 continue;
             }
-            
+
             // Skip sparse data format for now (lines starting with '{')
             if (!line.empty() && line[0] == '{') {
                 continue;
             }
-            
+
             if (line.find("@attribute") != std::string::npos || line.find("@ATTRIBUTE") != std::string::npos) {
                 std::stringstream ss(line);
                 std::string keyword, attribute, type_w;
@@ -717,7 +723,7 @@ private:
                         // Use specific index
                         classValue = trim(tokens[actualClassIndex]);
                     }
-                    
+
                     if (!classValue.empty()) {
                         uniqueClasses.insert(classValue);
                         sampleCount++;
@@ -726,7 +732,7 @@ private:
             }
         }
         while (getline(file, line));
-        
+
         return actualClassIndex;
     }
 

CHANGELOG.md

@@ -5,6 +5,14 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [1.2.1] 2025-07-15 Bug Fixes and Improvements
+
+### Added
+
+- Library version from CMake projecto to `ArffFiles.hpp`
+- Library `catch2` as a conan test requirement
+- Install target for CMake
+
 ## [1.2.0] 2025-06-27 Refactoring and Improvements
 
 ### Added

CMakeLists.txt

@@ -1,7 +1,7 @@
 cmake_minimum_required(VERSION 3.20)
 
 project(ArffFiles
-  VERSION 1.2.0
+  VERSION 1.2.1
   DESCRIPTION "Library to read Arff Files and return STL vectors with the data read."
   HOMEPAGE_URL "https://github.com/rmontanana/ArffFiles"
   LANGUAGES CXX
@@ -41,14 +41,60 @@ add_subdirectory(config)
 # -------
 if (ENABLE_TESTING)
   MESSAGE("Testing enabled")
-  Include(FetchContent)
-    FetchContent_Declare(Catch2
-        GIT_REPOSITORY https://github.com/catchorg/Catch2.git
-        GIT_TAG        v3.3.2
-    )
-    FetchContent_MakeAvailable(Catch2)
+  find_package(Catch2 REQUIRED)
   include(CTest)
   add_subdirectory(tests)
 endif (ENABLE_TESTING)
 
 add_library(ArffFiles INTERFACE ArffFiles.hpp)
+
+target_include_directories(ArffFiles INTERFACE
+    $<BUILD_INTERFACE:${CMAKE_CURRENT_SOURCE_DIR}>
+    $<BUILD_INTERFACE:${CMAKE_CURRENT_BINARY_DIR}/configured_files/include>
+    $<INSTALL_INTERFACE:include>
+)
+# Install
+# -------
+install(TARGETS ArffFiles EXPORT ArffFilesTargets
+  INCLUDES DESTINATION include
+)
+install(EXPORT ArffFilesTargets
+  FILE ArffFilesTargets.cmake
+  NAMESPACE ArffFiles::
+  DESTINATION lib/cmake/ArffFiles
+)
+
+# Install the main header file
+install(FILES ArffFiles.hpp
+  DESTINATION include
+)
+
+# Install the generated configuration header
+install(FILES "${CMAKE_CURRENT_BINARY_DIR}/configured_files/include/arffFiles_config.h"
+  DESTINATION include
+)
+
+# Install documentation files
+install(FILES LICENSE README.md
+  DESTINATION share/doc/ArffFiles
+)
+
+# Create and install package configuration files
+include(CMakePackageConfigHelpers)
+write_basic_package_version_file(
+  "${CMAKE_CURRENT_BINARY_DIR}/ArffFilesConfigVersion.cmake"
+  VERSION ${PROJECT_VERSION}
+  COMPATIBILITY AnyNewerVersion
+)
+
+configure_package_config_file(
+  "${CMAKE_CURRENT_SOURCE_DIR}/cmake/ArffFilesConfig.cmake.in"
+  "${CMAKE_CURRENT_BINARY_DIR}/ArffFilesConfig.cmake"
+  INSTALL_DESTINATION lib/cmake/ArffFiles
+)
+
+install(FILES
+  "${CMAKE_CURRENT_BINARY_DIR}/ArffFilesConfig.cmake"
+  "${CMAKE_CURRENT_BINARY_DIR}/ArffFilesConfigVersion.cmake"
+  DESTINATION lib/cmake/ArffFiles
+)

CMakeLists_conan.txt

@@ -0,0 +1,11 @@
+cmake_minimum_required(VERSION 3.20)
+
+project(ArffFiles
+  VERSION 1.2.1
+  DESCRIPTION "Library to read Arff Files and return STL vectors with the data read."
+  HOMEPAGE_URL "https://github.com/rmontanana/ArffFiles"
+  LANGUAGES CXX
+)
+
+# Subdirectories
+add_subdirectory(config)

Makefile

@@ -25,10 +25,12 @@ clean: ## Clean the tests info
 	@echo ">>> Done";
 
 build: ## Build a debug version of the project
-	@echo ">>> Building Debug ArffFiles...";
-	@if [ -d ./$(f_debug) ]; then rm -rf ./$(f_debug); fi
+	@echo ">>> Building Debug Folding...";
+	@if [ -d $(f_debug) ]; then rm -rf $(f_debug); fi
 	@mkdir $(f_debug); 
-	@cmake -S . -B $(f_debug) -D CMAKE_BUILD_TYPE=Debug -D ENABLE_TESTING=ON -D CODE_COVERAGE=ON
+	conan install . -of $(f_debug) -s build_type=Debug -b missing 
+	cmake -B $(f_debug) -S . -DCMAKE_BUILD_TYPE=Debug -DCMAKE_TOOLCHAIN_FILE=$(f_debug)/conan_toolchain.cmake -DENABLE_TESTING=ON
+	cmake --build $(f_debug) -t $(test_targets) $(n_procs)
 	@echo ">>> Done";
 
 opt = ""

README.md

@@ -29,10 +29,10 @@ A modern C++17 header-only library to read **ARFF (Attribute-Relation File Forma
 ```bash
 # Add the package to your conanfile.txt
 [requires]
-arff-files/1.0.1
+arff-files/1.2.1
 
 # Or install directly
-conan install arff-files/1.0.1@
+conan install arff-files/1.2.1@
 ```
 
 ### Manual Installation

cmake/ArffFilesConfig.cmake.in

@@ -0,0 +1,5 @@
+@PACKAGE_INIT@
+
+include("${CMAKE_CURRENT_LIST_DIR}/ArffFilesTargets.cmake")
+
+check_required_components(ArffFiles)

conanfile.py

@@ -1,21 +1,29 @@
 import re
 from conan import ConanFile
 from conan.tools.files import copy
+from conan.tools.cmake import CMakeToolchain, CMakeDeps
 
 
 class ArffFilesConan(ConanFile):
     name = "arff-files"
     version = "X.X.X"
-    description = (
-        "Header-only library to read ARFF (Attribute-Relation File Format) files and return STL vectors with the data read."
-    )
+    description = "Header-only library to read ARFF (Attribute-Relation \
+        File Format) files and return STL vectors with the data read."
     url = "https://github.com/rmontanana/ArffFiles"
     license = "MIT"
     homepage = "https://github.com/rmontanana/ArffFiles"
     topics = ("arff", "data-processing", "file-parsing", "header-only", "cpp17")
     no_copy_source = True
-    exports_sources = "ArffFiles.hpp", "LICENSE", "README.md"
+    exports_sources = (
+        "ArffFiles.hpp",
+        "LICENSE",
+        "README.md",
+        "CMakeLists.txt",
+        "config/*",
+        "cmake/*",
+    )
     package_type = "header-library"
+    settings = "build_type", "compiler", "arch", "os"
 
     def init(self):
         # Read the CMakeLists.txt file to get the version
@@ -28,12 +36,76 @@ class ArffFilesConan(ConanFile):
                 if match:
                     self.version = match.group(1)
 
+    def build_requirements(self):
+        self.tool_requires("cmake/[>=3.15]")
+        self.test_requires("catch2/3.8.1")
+
+    def layout(self):
+        # Only use cmake_layout for conan packaging, not for development builds
+        # This can be detected by checking if we're in a conan cache folder
+        if (
+            hasattr(self, "folders")
+            and hasattr(self.folders, "base_build")
+            and self.folders.base_build
+            and ".conan2" in self.folders.base_build
+        ):
+            from conan.tools.cmake import cmake_layout
+
+            cmake_layout(self)
+
+    def generate(self):
+        # Generate CMake toolchain file
+        tc = CMakeToolchain(self)
+        tc.generate()
+
+        # Generate CMake dependencies file (needed for test requirements like catch2)
+        deps = CMakeDeps(self)
+        deps.generate()
+
+    def build(self):
+        # Use CMake to generate the config file through existing config system
+        from conan.tools.cmake import CMake
+
+        cmake = CMake(self)
+        # Configure with minimal options - just enough to generate the config file
+        cmake.configure(
+            build_script_folder=None,
+            cli_args=["-DENABLE_TESTING=OFF", "-DCODE_COVERAGE=OFF"],
+        )
+        # No need to build anything, just configure to generate the config file
+
     def package(self):
-        # Copy header file to include directory
-        copy(self, "*.hpp", src=self.source_folder, dst=self.package_folder, keep_path=False)
+        # Copy header file
+        copy(
+            self,
+            "ArffFiles.hpp",
+            src=self.source_folder,
+            dst=self.package_folder,
+            keep_path=False,
+        )
+        # Copy the generated config file from CMake build folder
+        copy(
+            self,
+            "arffFiles_config.h",
+            src=f"{self.build_folder}/configured_files/include",
+            dst=self.package_folder,
+            keep_path=False,
+        )
         # Copy license and readme for package documentation
-        copy(self, "LICENSE", src=self.source_folder, dst=self.package_folder, keep_path=False)
-        copy(self, "README.md", src=self.source_folder, dst=self.package_folder, keep_path=False)
+        copy(
+            self,
+            "LICENSE",
+            src=self.source_folder,
+            dst=self.package_folder,
+            keep_path=False,
+        )
+        copy(
+            self,
+            "README.md",
+            src=self.source_folder,
+            dst=self.package_folder,
+            keep_path=False,
+        )
 
     def package_info(self):
         # Header-only library configuration

config/config.h.in

@@ -1,11 +1,10 @@
 #pragma once
 
-#include <string>
-#include <string_view>
+#define ARFFLIB_VERSION_MAJOR @PROJECT_VERSION_MAJOR@
+#define ARFFLIB_VERSION_MINOR @PROJECT_VERSION_MINOR@
+#define ARFFLIB_VERSION_PATCH @PROJECT_VERSION_PATCH@
 
-#define PROJECT_VERSION_MAJOR @PROJECT_VERSION_MAJOR @
-#define PROJECT_VERSION_MINOR @PROJECT_VERSION_MINOR @
-#define PROJECT_VERSION_PATCH @PROJECT_VERSION_PATCH @
+#define ARFFLIB_VERSION "@PROJECT_VERSION@"
 
 static constexpr std::string_view arffFiles_project_name = "@PROJECT_NAME@";
 static constexpr std::string_view arffFiles_project_version = "@PROJECT_VERSION@";

tests/TestArffFiles.cc

@@ -3,7 +3,6 @@
 #include <catch2/generators/catch_generators.hpp>
 #include <catch2/matchers/catch_matchers_string.hpp>
 #include "ArffFiles.hpp"
-#include "arffFiles_config.h"
 #include <iostream>
 
 class Paths {
@@ -28,7 +27,7 @@ public:
 TEST_CASE("Version Test", "[ArffFiles]")
 {
     ArffFiles arff;
-    REQUIRE(arff.version() == "1.1.0");
+    REQUIRE(arff.version() == "1.2.1");
 }
 TEST_CASE("Load Test", "[ArffFiles]")
 {