zhipuzi_pos_windows/opencv-test/.vs/CopilotSnapshots/5DE0B2D02B3A554A9E20C60171EE23C0/98C007A60CF2B74C95830CF0C1A28535/3C134381851B082DA38E7880464684BF


#include "SQLiteVecManager.h"
#include <stdexcept>
#include <iostream>
#include <cmath>
#include <algorithm>

SQLiteVecManager::SQLiteVecManager(const std::string& databaseName) : dbName(databaseName), db(nullptr), useVecExtension(false) {
    int rc = sqlite3_open(dbName.c_str(), &db);
    if (rc) {
        throw std::runtime_error("Can't open database: " + std::string(sqlite3_errmsg(db)));
    }
}

SQLiteVecManager::~SQLiteVecManager() {
    if (db) {
        sqlite3_close(db);
    }
}

bool SQLiteVecManager::initializeDatabase(int vectorDimension) {
    char* errMsg = 0;
    
    // 尝试启用sqlite-vec扩展
    const char* enableVec = "SELECT load_extension('C:/Users/27920/Desktop/test/dll/release/vec0.dll');";
    int rc = sqlite3_exec(db, enableVec, 0, 0, &errMsg);
    if (rc == SQLITE_OK) {
        std::cerr << "success to create vec0 table: " << std::endl;
        useVecExtension = true;
        // 创建vec0虚拟表
        std::string sql = "CREATE VIRTUAL TABLE IF NOT EXISTS image_features USING vec0("
                         "id INTEGER PRIMARY KEY, "
                         "image_path TEXT, "
                         "feature_vector FLOAT[" + std::to_string(vectorDimension) + "]);";
        
        rc = sqlite3_exec(db, sql.c_str(), 0, 0, &errMsg);
        if (rc != SQLITE_OK) {
            std::cerr << "Failed to create vec0 table: " << errMsg << std::endl;
            sqlite3_free(errMsg);
            return false;
        }
    } else {
        // 使用传统表结构
        sqlite3_free(errMsg);
        const char* sql = R"(
            CREATE TABLE IF NOT EXISTS image_features (
                id INTEGER PRIMARY KEY AUTOINCREMENT,
                image_path TEXT UNIQUE NOT NULL,
                feature_vector BLOB NOT NULL
            );
        )";
        rc = sqlite3_exec(db, sql, 0, 0, &errMsg);
        if (rc != SQLITE_OK) {
            std::cerr << "SQL error: " << errMsg << std::endl;
            sqlite3_free(errMsg);
            return false;
        }
    }
    
    return true;
}

bool SQLiteVecManager::addFeatureVector(const std::vector<float>& features, const std::string& imagePath) {
    if (useVecExtension) {
        const char* sql = "INSERT INTO image_features(id, image_path, feature_vector) VALUES (?, ?, vec_f32(?));";
        
        sqlite3_stmt* stmt;
        int rc = sqlite3_prepare_v2(db, sql, -1, &stmt, NULL);
        if (rc != SQLITE_OK) {
            return false;
        }
        
        sqlite3_bind_int(stmt, 1, static_cast<int>(getFeatureCount() + 1));
        sqlite3_bind_text(stmt, 2, imagePath.c_str(), -1, SQLITE_STATIC);
        
        std::string blobData = vectorToBlob(features);
        sqlite3_bind_blob(stmt, 3, blobData.data(), static_cast<int>(blobData.size()), SQLITE_STATIC);
        
        rc = sqlite3_step(stmt);
        sqlite3_finalize(stmt);
        
        return rc == SQLITE_DONE;
    } else {
        const char* sql = "INSERT OR REPLACE INTO image_features (id, image_path, feature_vector) VALUES (?, ?, ?);";
        
        sqlite3_stmt* stmt;
        int rc = sqlite3_prepare_v2(db, sql, -1, &stmt, NULL);
        if (rc != SQLITE_OK) {
            return false;
        }
        
        sqlite3_bind_int(stmt, 1, static_cast<int>(getFeatureCount() + 1));
        sqlite3_bind_text(stmt, 2, imagePath.c_str(), -1, SQLITE_STATIC);
        
        std::string blobData = vectorToBlob(features);
        sqlite3_bind_blob(stmt, 3, blobData.data(), static_cast<int>(blobData.size()), SQLITE_STATIC);
        
        rc = sqlite3_step(stmt);
        sqlite3_finalize(stmt);
        
        return rc == SQLITE_DONE;
    }
}

std::vector<std::pair<std::string, float>> SQLiteVecManager::searchSimilarVectors(const std::vector<float>& queryVector, int k) {
    std::vector<std::pair<std::string, float>> results;
    
    if (useVecExtension) {
        // 使用sqlite-vec的向量搜索功能
        std::string blobData = vectorToBlob(queryVector);
        
        std::string sql = "SELECT image_path, distance FROM image_features "
                         "WHERE feature_vector MATCH vec_f32(?) "
                         "ORDER BY distance "
                         "LIMIT " + std::to_string(k) + ";";
        
        sqlite3_stmt* stmt;
        int rc = sqlite3_prepare_v2(db, sql.c_str(), -1, &stmt, NULL);
        if (rc != SQLITE_OK) {
            return results;
        }
        
        sqlite3_bind_blob(stmt, 1, blobData.data(), static_cast<int>(blobData.size()), SQLITE_STATIC);
        
        while ((rc = sqlite3_step(stmt)) == SQLITE_ROW) {
            const char* imagePath = reinterpret_cast<const char*>(sqlite3_column_text(stmt, 0));
            float distance = static_cast<float>(sqlite3_column_double(stmt, 1));
            results.emplace_back(std::string(imagePath), distance);
        }
        
        sqlite3_finalize(stmt);
    } else {
        // 使用传统方式计算相似度
        const char* sql = "SELECT image_path, feature_vector FROM image_features;";
        sqlite3_stmt* stmt;
        int rc = sqlite3_prepare_v2(db, sql, -1, &stmt, NULL);
        
        if (rc != SQLITE_OK) {
            return results;
        }
        
        // 计算查询向量的模长
        float queryNorm = 0.0f;
        for (float val : queryVector) {
            queryNorm += val * val;
        }
        queryNorm = sqrt(queryNorm);
        
        while ((rc = sqlite3_step(stmt)) == SQLITE_ROW) {
            const char* imagePath = reinterpret_cast<const char*>(sqlite3_column_text(stmt, 0));
            const void* blobData = sqlite3_column_blob(stmt, 1);
            int blobSize = sqlite3_column_bytes(stmt, 1);
            
            std::string blobStr(static_cast<const char*>(blobData), blobSize);
            std::vector<float> storedFeatures = blobToVector(blobStr);
            
            if (storedFeatures.size() == queryVector.size()) {
                // 计算余弦相似度
                float dotProduct = 0.0f;
                float storedNorm = 0.0f;
                
                for (size_t i = 0; i < queryVector.size(); ++i) {
                    dotProduct += queryVector[i] * storedFeatures[i];
                    storedNorm += storedFeatures[i] * storedFeatures[i];
                }
                
                storedNorm = sqrt(storedNorm);
                
                float similarity = 0.0f;
                if (queryNorm > 0.0f && storedNorm > 0.0f) {
                    similarity = dotProduct / (queryNorm * storedNorm);
                }
                
                results.emplace_back(std::string(imagePath), similarity);
            }
        }
        
        sqlite3_finalize(stmt);
        
        // 按相似度降序排列
        std::sort(results.begin(), results.end(), 
                  [](const auto& a, const auto& b) { return a.second > b.second; });
        
        // 返回topK结果
        if (static_cast<int>(results.size()) > k) {
            results.resize(k);
        }
    }
    
    return results;
}

void SQLiteVecManager::saveDatabase() {
    sqlite3_exec(db, "PRAGMA optimize;", 0, 0, 0);
}

bool SQLiteVecManager::loadDatabase() {
    const char* sql = "SELECT name FROM sqlite_master WHERE type='table' AND name='image_features';";
    sqlite3_stmt* stmt;
    int rc = sqlite3_prepare_v2(db, sql, -1, &stmt, NULL);
    
    if (rc == SQLITE_OK && sqlite3_step(stmt) == SQLITE_ROW) {
        sqlite3_finalize(stmt);
        return true;
    }
    
    sqlite3_finalize(stmt);
    return false;
}

int SQLiteVecManager::getFeatureCount() const {
    const char* sql = "SELECT COUNT(*) FROM image_features;";
    sqlite3_stmt* stmt;
    int rc = sqlite3_prepare_v2(db, sql, -1, &stmt, NULL);
    
    if (rc == SQLITE_OK && sqlite3_step(stmt) == SQLITE_ROW) {
        int count = sqlite3_column_int(stmt, 0);
        sqlite3_finalize(stmt);
        return count;
    }
    
    sqlite3_finalize(stmt);
    return 0;
}

bool SQLiteVecManager::isEmpty() const {
    return getFeatureCount() == 0;
}

std::string SQLiteVecManager::vectorToBlob(const std::vector<float>& vec) {
    return std::string(reinterpret_cast<const char*>(vec.data()), vec.size() * sizeof(float));
}

std::vector<float> SQLiteVecManager::blobToVector(const std::string& blob) {
    const float* data = reinterpret_cast<const float*>(blob.data());
    size_t count = blob.size() / sizeof(float);
    return std::vector<float>(data, data + count);
}

float SQLiteVecManager::calculateCosineSimilarity(const std::vector<float>& vec1, const std::vector<float>& vec2) {
    if (vec1.size() != vec2.size() || vec1.empty()) {
        return 0.0f;
    }
    
    float dotProduct = 0.0f;
    float norm1 = 0.0f;
    float norm2 = 0.0f;
    
    for (size_t i = 0; i < vec1.size(); ++i) {
        dotProduct += vec1[i] * vec2[i];
        norm1 += vec1[i] * vec1[i];
        norm2 += vec2[i] * vec2[i];
    }
    
    if (norm1 == 0.0f || norm2 == 0.0f) {
        return 0.0f;
    }
    
    return dotProduct / (std::sqrt(norm1) * std::sqrt(norm2));
}