Migrate jsonpull to unique_ptr ownership

Replaces the shared_ptr-based json_object_ptr with a unique_ptr that
has a stateless custom deleter dispatching on json_object::type before
calling the right subclass destructor. Eliminates per-node atomic
reference-counting and the control-block allocation that shared_ptr
required for every node in the tree.

API now distinguishes owning and borrowing pointers explicitly:
- json_read / json_read_separators / json_hash_get return raw
  json_object * (borrowed from the parser-owned tree).
- json_read_tree / json_disconnect return json_object_ptr (caller
  takes ownership; back-pointers are cleared so the subtree can
  outlive the parser).
- json_free / json_context / json_stringify take raw pointers.
- The parser's container_stack holds raw pointers; jp->root keeps
  unique_ptr ownership of the most recent top-level value.

Internally, take_from_owner moves the unique_ptr out of whichever
parent vector / hash entry / parser root owned it, which both
json_free and json_disconnect rely on.

In the streaming parsers (parse_feature, parse_layers, the
geojson-loop callback), we are careful to free `j` only after we
have processed a complete Feature: json_read returns each token
as the tree is being built up, and freeing an intermediate node
would splice it out of the surrounding hash and corrupt the
in-progress feature.

Benchmark (tl_2022_us_county.json, -z0 --extend-zooms-if-still-dropping,
median of 5 runs on macOS arm64): 8.5s, vs 10.6s with shared_ptr
and 8.7s on the pre-refactor C baseline.

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
Erica Fischer
2026-05-30 20:44:25 -07:00
co-authored by Cursor
parent 1a7075e3ab
commit 65beb3f0d7
23 changed files with 408 additions and 289 deletions
+5 -5
View File
@@ -941,7 +941,7 @@ struct write_tile_args {
bool still_dropping = false;
int wrote_zoom = 0;
size_t tiling_seg = 0;
json_object_ptr filter;
json_object *filter = NULL;
std::vector<std::string> const *unidecode_data;
std::atomic<size_t> *dropped_count = NULL;
atomic_strategy *strategy = NULL;
@@ -1102,7 +1102,7 @@ struct next_feature_state {
// This function is called repeatedly from write_tile() to retrieve the next feature
// from the input stream. If the stream is at an end, it returns a feature with the
// geometry type set to -2.
static serial_feature next_feature(decompressor *geoms, std::atomic<long long> *geompos_in, int z, unsigned tx, unsigned ty, unsigned *initial_x, unsigned *initial_y, long long *original_features, long long *unclipped_features, int nextzoom, int maxzoom, int minzoom, int max_zoom_increment, size_t pass, std::atomic<long long> *along, long long alongminus, int buffer, std::atomic<bool> *within, compressor **geomfile, std::atomic<long long> *geompos, long long start_geompos[], std::atomic<double> *oprogress, double todo, const char *fname, int child_shards, json_object_ptr filter, const char *global_stringpool, long long *pool_off, std::vector<std::vector<std::string>> *layer_unmaps, bool first_time, bool compressed, multiplier_state *multiplier_state, std::shared_ptr<std::string> &tile_stringpool, std::vector<std::string> const &unidecode_data, next_feature_state &next_feature_state, double droprate) {
static serial_feature next_feature(decompressor *geoms, std::atomic<long long> *geompos_in, int z, unsigned tx, unsigned ty, unsigned *initial_x, unsigned *initial_y, long long *original_features, long long *unclipped_features, int nextzoom, int maxzoom, int minzoom, int max_zoom_increment, size_t pass, std::atomic<long long> *along, long long alongminus, int buffer, std::atomic<bool> *within, compressor **geomfile, std::atomic<long long> *geompos, long long start_geompos[], std::atomic<double> *oprogress, double todo, const char *fname, int child_shards, json_object *filter, const char *global_stringpool, long long *pool_off, std::vector<std::vector<std::string>> *layer_unmaps, bool first_time, bool compressed, multiplier_state *multiplier_state, std::shared_ptr<std::string> &tile_stringpool, std::vector<std::string> const &unidecode_data, next_feature_state &next_feature_state, double droprate) {
double extra_multiplier_zooms = log(retain_points_multiplier) / log(droprate);
while (1) {
@@ -1350,7 +1350,7 @@ struct run_prefilter_args {
char *global_stringpool = NULL;
long long *pool_off = NULL;
FILE *prefilter_fp = NULL;
json_object_ptr filter;
json_object *filter = NULL;
std::vector<std::string> const *unidecode_data;
bool first_time = false;
bool compressed = false;
@@ -1641,7 +1641,7 @@ void skip_tile(decompressor *geoms, std::atomic<long long> *geompos_in, bool com
}
}
long long write_tile(decompressor *geoms, std::atomic<long long> *geompos_in, char *global_stringpool, int z, const unsigned tx, const unsigned ty, const int detail, int min_detail, sqlite3 *outdb, const char *outdir, int buffer, const char *fname, compressor **geomfile, std::atomic<long long> *geompos, int minzoom, int maxzoom, double todo, std::atomic<long long> *along, long long alongminus, double gamma, int child_shards, long long *pool_off, unsigned *initial_x, unsigned *initial_y, std::atomic<int> *running, double simplification, std::vector<std::map<std::string, layermap_entry>> *layermaps, std::vector<std::vector<std::string>> *layer_unmaps, size_t tiling_seg, size_t pass, unsigned long long mingap, long long minextent, unsigned long long mindrop_sequence, double minattribute, const char *prefilter, const char *postfilter, json_object_ptr filter, write_tile_args *arg, atomic_strategy *strategy_out, bool compressed_input, node *shared_nodes_map, size_t nodepos, std::string const &shared_nodes_bloom, std::vector<std::string> const &unidecode_data, long long estimated_complexity, std::set<zxy> &skip_children_out) {
long long write_tile(decompressor *geoms, std::atomic<long long> *geompos_in, char *global_stringpool, int z, const unsigned tx, const unsigned ty, const int detail, int min_detail, sqlite3 *outdb, const char *outdir, int buffer, const char *fname, compressor **geomfile, std::atomic<long long> *geompos, int minzoom, int maxzoom, double todo, std::atomic<long long> *along, long long alongminus, double gamma, int child_shards, long long *pool_off, unsigned *initial_x, unsigned *initial_y, std::atomic<int> *running, double simplification, std::vector<std::map<std::string, layermap_entry>> *layermaps, std::vector<std::vector<std::string>> *layer_unmaps, size_t tiling_seg, size_t pass, unsigned long long mingap, long long minextent, unsigned long long mindrop_sequence, double minattribute, const char *prefilter, const char *postfilter, json_object *filter, write_tile_args *arg, atomic_strategy *strategy_out, bool compressed_input, node *shared_nodes_map, size_t nodepos, std::string const &shared_nodes_bloom, std::vector<std::string> const &unidecode_data, long long estimated_complexity, std::set<zxy> &skip_children_out) {
double merge_fraction = 1;
double mingap_fraction = 1;
double minextent_fraction = 1;
@@ -3213,7 +3213,7 @@ exit(EXIT_IMPOSSIBLE);
return err_or_null;
}
int traverse_zooms(int *geomfd, off_t *geom_size, char *global_stringpool, std::atomic<unsigned> *midx, std::atomic<unsigned> *midy, int &maxzoom, int minzoom, sqlite3 *outdb, const char *outdir, int buffer, const char *fname, const char *tmpdir, double gamma, int full_detail, int low_detail, int min_detail, long long *pool_off, unsigned *initial_x, unsigned *initial_y, double simplification, double maxzoom_simplification, std::vector<std::map<std::string, layermap_entry>> &layermaps, const char *prefilter, const char *postfilter, std::unordered_map<std::string, attribute_op> const *attribute_accum, json_object_ptr filter, std::vector<strategy> &strategies, int iz, node *shared_nodes_map, size_t nodepos, std::string const &shared_nodes_bloom, int basezoom, double droprate, std::vector<std::string> const &unidecode_data, std::string const *drop_by_attribute_as_needed_attribute, bool drop_by_attribute_descending) {
int traverse_zooms(int *geomfd, off_t *geom_size, char *global_stringpool, std::atomic<unsigned> *midx, std::atomic<unsigned> *midy, int &maxzoom, int minzoom, sqlite3 *outdb, const char *outdir, int buffer, const char *fname, const char *tmpdir, double gamma, int full_detail, int low_detail, int min_detail, long long *pool_off, unsigned *initial_x, unsigned *initial_y, double simplification, double maxzoom_simplification, std::vector<std::map<std::string, layermap_entry>> &layermaps, const char *prefilter, const char *postfilter, std::unordered_map<std::string, attribute_op> const *attribute_accum, json_object *filter, std::vector<strategy> &strategies, int iz, node *shared_nodes_map, size_t nodepos, std::string const &shared_nodes_bloom, int basezoom, double droprate, std::vector<std::string> const &unidecode_data, std::string const *drop_by_attribute_as_needed_attribute, bool drop_by_attribute_descending) {
last_progress = 0;
// The existing layermaps are one table per input thread.