zektyc/data/maxspeed/merge_grid.cpp
riricdev 8e7ec41f18 chore: checkpoint initial — Zektyc dataset, avant humanisation
- site vitrine + fingerprint test + zmap + z-panel
- remplacement duckdns -> riricdev.tail5ea5cd.ts.net (canonical/og/alternates/docs)
- suppression du token DuckDNS (plus utilisé)
2026-09-06 13:03:25 +02:00

140 lines
4 KiB
C++

#include <cstdio>
#include <cstdint>
#include <cstring>
#include <string>
#include <vector>
#include <algorithm>
#include <filesystem>
#include <glob.h>
namespace fs = std::filesystem;
static constexpr double CELL = 0.5;
static constexpr int SUB = 32;
static constexpr double LON_MIN = -180.0;
static constexpr double LAT_MIN = -60.0;
static constexpr double LON_MAX = 180.0;
static constexpr double LAT_MAX = 85.0;
struct RawPoint {
int32_t col;
int32_t row;
uint16_t lonq;
uint16_t latq;
uint8_t speed;
};
struct Point64 {
uint16_t lonq;
uint16_t latq;
uint8_t speed;
};
static bool cmp_cell(const RawPoint& a, const RawPoint& b) {
if (a.col != b.col) return a.col < b.col;
if (a.row != b.row) return a.row < b.row;
return false;
}
int main(int argc, char* argv[]) {
if (argc < 3) {
fprintf(stderr, "Usage: %s <output_dir> <raw_file1> [raw_file2] ...\n", argv[0]);
return 1;
}
const char* outdir = argv[1];
fs::create_directories(outdir);
std::vector<RawPoint> all_points;
for (int i = 2; i < argc; i++) {
FILE* f = fopen(argv[i], "rb");
if (!f) { fprintf(stderr, "Cannot open %s\n", argv[i]); continue; }
fseek(f, 0, SEEK_END);
long fsize = ftell(f);
fseek(f, 0, SEEK_SET);
uint64_t before = all_points.size();
uint64_t npoints = fsize / sizeof(RawPoint);
all_points.resize(before + npoints);
fread(all_points.data() + before, sizeof(RawPoint), npoints, f);
fclose(f);
fprintf(stderr, "Loaded %s: %lu points (total: %lu)\n", argv[i], npoints, all_points.size());
}
fprintf(stderr, "Sorting %lu points...\n", all_points.size());
std::sort(all_points.begin(), all_points.end(), cmp_cell);
fprintf(stderr, "Sort done. Writing cells...\n");
std::string index_path = std::string(outdir) + "/index.bin";
FILE* index = fopen(index_path.c_str(), "wb");
if (!index) { fprintf(stderr, "Cannot write index\n"); return 1; }
uint32_t magic = 0x5A4D4150;
fwrite(&magic, 4, 1, index);
uint16_t version = 2;
fwrite(&version, 2, 1, index);
uint16_t sub = SUB;
fwrite(&sub, 2, 1, index);
fwrite(&CELL, 8, 1, index);
fwrite(&LON_MIN, 8, 1, index);
fwrite(&LAT_MIN, 8, 1, index);
fwrite(&LON_MAX, 8, 1, index);
fwrite(&LAT_MAX, 8, 1, index);
uint32_t num_cells = 0;
fseek(index, 36, SEEK_SET);
fwrite(&num_cells, 4, 1, index);
fseek(index, 0, SEEK_END);
int32_t cur_col = -1, cur_row = -1;
FILE* cur_file = nullptr;
uint32_t cell_points = 0;
std::string cur_key;
for (uint64_t i = 0; i <= all_points.size(); i++) {
bool new_cell = (i == all_points.size() ||
all_points[i].col != cur_col ||
all_points[i].row != cur_row);
if (new_cell && cur_file) {
fclose(cur_file);
uint32_t klen = static_cast<uint32_t>(cur_key.size());
fwrite(&klen, 4, 1, index);
fwrite(cur_key.data(), 1, klen, index);
fwrite(&cell_points, 4, 1, index);
num_cells++;
if (num_cells % 500 == 0) {
fprintf(stderr, " %u cells written...\n", num_cells);
}
}
if (i == all_points.size()) break;
if (new_cell) {
cur_col = all_points[i].col;
cur_row = all_points[i].row;
cur_key = std::to_string(cur_col) + "_" + std::to_string(cur_row);
std::string cellfile = std::string(outdir) + "/cell_" + cur_key + ".bin";
cur_file = fopen(cellfile.c_str(), "wb");
cell_points = 0;
}
Point64 p;
p.lonq = all_points[i].lonq;
p.latq = all_points[i].latq;
p.speed = all_points[i].speed;
fwrite(&p, sizeof(Point64), 1, cur_file);
cell_points++;
}
fseek(index, 36, SEEK_SET);
fwrite(&num_cells, 4, 1, index);
fclose(index);
fprintf(stderr, "Total cells: %u\n", num_cells);
fprintf(stderr, "Grid written to %s\n", outdir);
return 0;
}