zektyc/data/maxspeed/build_global.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

245 lines
7.2 KiB
C++

#include <osmium/io/any_input.hpp>
#include <osmium/visitor.hpp>
#include <osmium/handler/node_locations_for_ways.hpp>
#include <osmium/index/map/sparse_file_array.hpp>
#include <osmium/osm/way.hpp>
#include <cstdio>
#include <cstdint>
#include <cstring>
#include <cmath>
#include <string>
#include <vector>
#include <algorithm>
#include <filesystem>
#include <fcntl.h>
#include <unistd.h>
namespace fs = std::filesystem;
using index_type = osmium::index::map::SparseFileArray<osmium::unsigned_object_id_type, osmium::Location>;
using location_handler_type = osmium::handler::NodeLocationsForWays<index_type>;
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;
}; // 11 bytes
static inline uint16_t quantize_lon(double lon) {
return static_cast<uint16_t>((lon - LON_MIN) / (LON_MAX - LON_MIN) * 65535.0);
}
static inline uint16_t quantize_lat(double lat) {
return static_cast<uint16_t>((lat - LAT_MIN) / (LAT_MAX - LAT_MIN) * 65535.0);
}
static inline uint8_t parse_speed_val(const char* s) {
if (!s || !*s) return 0;
char* end = nullptr;
double v = strtod(s, &end);
if (end != s && v > 0 && v <= 255) return static_cast<uint8_t>(v);
if (strstr(s, "mph")) {
v = strtod(s, &end);
if (end != s) {
v *= 1.609;
if (v > 0 && v <= 255) return static_cast<uint8_t>(v);
}
}
return 0;
}
struct Point64 {
uint16_t lonq;
uint16_t latq;
uint8_t speed;
};
class SpeedHandler : public osmium::handler::Handler {
public:
FILE* tmpfile;
uint64_t way_count = 0;
uint64_t point_count = 0;
explicit SpeedHandler(FILE* f) : tmpfile(f) {}
void way(const osmium::Way& way) {
const char* highway = way.tags().get_value_by_key("highway");
if (!highway) return;
const char* ms = way.tags().get_value_by_key("maxspeed");
uint8_t speed = ms ? parse_speed_val(ms) : 0;
if (speed == 0) return;
way_count++;
for (const auto& wn : way.nodes()) {
if (!wn.location().valid()) continue;
double lon = wn.location().lon();
double lat = wn.location().lat();
if (lon < LON_MIN || lon >= LON_MAX || lat < LAT_MIN || lat >= LAT_MAX) continue;
int32_t col = static_cast<int32_t>((lon - LON_MIN) / CELL);
int32_t row = static_cast<int32_t>((lat - LAT_MIN) / CELL);
RawPoint rp;
rp.col = col;
rp.row = row;
rp.lonq = quantize_lon(lon);
rp.latq = quantize_lat(lat);
rp.speed = speed;
fwrite(&rp, sizeof(RawPoint), 1, tmpfile);
point_count++;
if (point_count % 10000000 == 0) {
fprintf(stderr, " %lu points (%lu ways)...\n", point_count, way_count);
}
}
}
};
static bool compare_by_cell(const RawPoint& a, const RawPoint& b) {
if (a.col != b.col) return a.col < b.col;
return a.row < b.row;
}
static void split_and_write(const char* tmppath, const std::string& outdir) {
fprintf(stderr, "Reading temp file into memory for sort...\n");
FILE* f = fopen(tmppath, "rb");
fseek(f, 0, SEEK_END);
long fsize = ftell(f);
fseek(f, 0, SEEK_SET);
uint64_t npoints = fsize / sizeof(RawPoint);
fprintf(stderr, "Sorting %lu points (%.1f MB)...\n", npoints, fsize / 1048576.0);
std::vector<RawPoint> points(npoints);
fread(points.data(), sizeof(RawPoint), npoints, f);
fclose(f);
std::sort(points.begin(), points.end(), compare_by_cell);
fprintf(stderr, "Sort done. Writing cells...\n");
fs::create_directories(outdir);
std::string index_path = outdir + "/index.bin";
FILE* index = fopen(index_path.c_str(), "wb");
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 <= npoints; i++) {
bool new_cell = (i == npoints || points[i].col != cur_col || 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 % 1000 == 0) {
fprintf(stderr, " %u cells written...\n", num_cells);
}
}
if (i == npoints) break;
if (new_cell) {
cur_col = points[i].col;
cur_row = points[i].row;
cur_key = std::to_string(cur_col) + "_" + std::to_string(cur_row);
std::string cellfile = outdir + "/cell_" + cur_key + ".bin";
cur_file = fopen(cellfile.c_str(), "wb");
cell_points = 0;
}
Point64 p;
p.lonq = points[i].lonq;
p.latq = points[i].latq;
p.speed = 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);
}
int main(int argc, char* argv[]) {
if (argc < 3) {
fprintf(stderr, "Usage: %s <input.pbf> <output_dir>\n", argv[0]);
return 1;
}
const char* input = argv[1];
const char* outdir = argv[2];
std::string tmppath = std::string(outdir) + "/_points.tmp";
fs::create_directories(outdir);
fprintf(stderr, "Step 1: Reading PBF, writing raw points to temp file...\n");
FILE* tmpf = fopen(tmppath.c_str(), "w+b");
if (!tmpf) { fprintf(stderr, "Cannot create temp file\n"); return 1; }
std::string idx_path = std::string(outdir) + "/_node_index.tmp";
int idx_fd = ::open(idx_path.c_str(), O_CREAT | O_RDWR | O_TRUNC, 0644);
if (idx_fd == -1) { fprintf(stderr, "Cannot create index temp file\n"); return 1; }
index_type index(idx_fd);
location_handler_type location_handler(index);
SpeedHandler handler(tmpf);
osmium::io::Reader reader(input);
osmium::apply(reader, location_handler, handler);
reader.close();
fclose(tmpf);
fprintf(stderr, "\nWays with maxspeed: %lu\n", handler.way_count);
fprintf(stderr, "Total points: %lu\n", handler.point_count);
fprintf(stderr, "Step 2: Sort + write grid cells...\n");
split_and_write(tmppath.c_str(), outdir);
::close(idx_fd);
unlink(idx_path.c_str());
unlink(tmppath.c_str());
fprintf(stderr, "Done! Grid written to %s\n", outdir);
return 0;
}