Files
tippecanoe/attribute.cpp
T
Erica Fischer e2a7a409c7 Improve tiling speed (#195)
* Add a way to run tippecanoe single-threaded for profiling

* Do less work when the tilestats sample values list is already full

* Save a copy when retrieving the attribute key

* Fewer atomic operations

* Move string hashing from mbtiles to text

* Only do approximate attribute deduplication when writing tiles

* Feature dropping tests are sensitive to exact tile size

* All tile creators now create a string pool for the tile

* Features clipped away to nothing should not participate in that tile

* Revert "Only do approximate attribute deduplication when writing tiles"

This reverts commit c42b34b498.

* Also revert the related test changes

* Revert "Revert "Only do approximate attribute deduplication when writing tiles""

This reverts commit 18509876c3.

* Be more specific about the string hash function

* Use fnv1a instead of std::hash for everything

* Reduce the chance of hash collisions

* Stick a hash search on the front of the tree search in addpool

* Eliminate repeated hashing of the same string

* Switch instead of ifs in json parsing

* A few more cases to populate the hash in addpool

* Store the hash in the tree instead of recalculating

* Add explanatory comment for mysterious argument

* Fewer copies in attribute stringification

* Clean up ancient weirdness in JSON attribute stringification

* More serial_val cleanup

* Pass a serial_feature to rewrite instead of many broken-down arguments

* Get rid of the multiple geometries within `partial`

* Revert "Pass a serial_feature to rewrite instead of many broken-down arguments"

This reverts commit 6f4ab9b725.

* Goodbye, struct coalesce

* Revert "Features clipped away to nothing should not participate in that tile"

This reverts commit 124462fbdc.

* Migrating fields from partial to serial_feature

* Name reconciliation between serial_feature and partial

* Replace struct partial with an augmented serial_feature

* Fix some overzealous search-and-replace renaming

* Don't say struct so often

* Remove more of the former partial construction

* Commenting and cleaning up

* Trying again to avoid all these arguments to rewrite

* I swear I did this same thing before and it didn't work.

* More rewrite cleanup

* Exile --detect-shared-borders to its own file

* Add missing headers

* More commenting and cleanup

* More comments

* Sprinkle consts around

* Emplacing and std::moving

* More cleanup

* That shouldn't have worked after a std::move

* Don't need to allocate memory to compare keys

* Reduce use of the global string pool in tiling

* Another avoidable mvt_value construction

* Further reduction to explicit string pool passing

* These reverses are no longer optimizations

* These layernames can all be references

* Don't drag an unused layername string around with every feature

* Heed a compiler warning about potential buffer overflow

* Fix my confusion about which feature's string pool is relevant

* Avoid some unnecessary allocations in attribute accumulation

* Maybe faster serialization?

* Eliminate a comparison

* Do the same here

* Save a couple of allocations when parsing numbers in JSON

* Immediately assign features to layers instead of subdividing later

* Maintain tilestats for tippecanoe:retain_points_multiplier_sequence

* Crunch out more duplicate attribute values when writing out the tile

* Do tilestats for tippecanoe:retain_points_multiplier_first too

* Shell filters need to be real threads, even if nothing else does

* Simplify tippecanoe_minzoom/maxzoom representation

* Update version and changelog
2024-02-07 17:50:35 -08:00

147 lines
4.0 KiB
C++

#include <string>
#include <unordered_map>
#include "attribute.hpp"
#include "errors.hpp"
#include "serial.hpp"
#include "jsonpull/jsonpull.h"
#include "milo/dtoa_milo.h"
void set_attribute_accum(std::unordered_map<std::string, attribute_op> &attribute_accum, std::string name, std::string type) {
attribute_op t;
if (type == "sum") {
t = op_sum;
} else if (type == "product") {
t = op_product;
} else if (type == "mean") {
t = op_mean;
} else if (type == "max") {
t = op_max;
} else if (type == "min") {
t = op_min;
} else if (type == "concat") {
t = op_concat;
} else if (type == "comma") {
t = op_comma;
} else {
fprintf(stderr, "Attribute method (%s) must be sum, product, mean, max, min, concat, or comma\n", type.c_str());
exit(EXIT_ARGS);
}
attribute_accum.insert(std::pair<std::string, attribute_op>(name, t));
}
void set_attribute_accum(std::unordered_map<std::string, attribute_op> &attribute_accum, const char *arg, char **argv) {
if (*arg == '{') {
json_pull *jp = json_begin_string(arg);
json_object *o = json_read_tree(jp);
if (o == NULL) {
fprintf(stderr, "%s: -E%s: %s\n", *argv, arg, jp->error);
exit(EXIT_JSON);
}
if (o->type != JSON_HASH) {
fprintf(stderr, "%s: -E%s: not a JSON object\n", *argv, arg);
exit(EXIT_JSON);
}
for (size_t i = 0; i < o->value.object.length; i++) {
json_object *k = o->value.object.keys[i];
json_object *v = o->value.object.values[i];
if (k->type != JSON_STRING) {
fprintf(stderr, "%s: -E%s: key %zu not a string\n", *argv, arg, i);
exit(EXIT_JSON);
}
if (v->type != JSON_STRING) {
fprintf(stderr, "%s: -E%s: value %zu not a string\n", *argv, arg, i);
exit(EXIT_JSON);
}
set_attribute_accum(attribute_accum, k->value.string.string, v->value.string.string);
}
json_free(o);
json_end(jp);
return;
}
const char *s = strchr(arg, ':');
if (s == NULL) {
fprintf(stderr, "-E%s option must be in the form -Ename:method\n", arg);
exit(EXIT_ARGS);
}
std::string name = std::string(arg, s - arg);
std::string type = std::string(s + 1);
set_attribute_accum(attribute_accum, name, type);
}
void preserve_attribute(attribute_op const &op, std::string const &key, serial_val const &val, std::vector<std::string> &full_keys, std::vector<serial_val> &full_values, std::unordered_map<std::string, accum_state> &attribute_accum_state) {
for (size_t i = 0; i < full_keys.size(); i++) {
if (key == full_keys[i]) {
switch (op) {
case op_sum:
full_values[i].s = milo::dtoa_milo(atof(full_values[i].s.c_str()) + atof(val.s.c_str()));
full_values[i].type = mvt_double;
break;
case op_product:
full_values[i].s = milo::dtoa_milo(atof(full_values[i].s.c_str()) * atof(val.s.c_str()));
full_values[i].type = mvt_double;
break;
case op_max: {
double existing = atof(full_values[i].s.c_str());
double maybe = atof(val.s.c_str());
if (maybe > existing) {
full_values[i].s = val.s.c_str();
full_values[i].type = mvt_double;
}
break;
}
case op_min: {
double existing = atof(full_values[i].s.c_str());
double maybe = atof(val.s.c_str());
if (maybe < existing) {
full_values[i].s = val.s.c_str();
full_values[i].type = mvt_double;
}
break;
}
case op_mean: {
auto state = attribute_accum_state.find(key);
if (state == attribute_accum_state.end()) {
accum_state s;
s.sum = atof(full_values[i].s.c_str()) + atof(val.s.c_str());
s.count = 2;
attribute_accum_state.insert(std::pair<std::string, accum_state>(key, s));
full_values[i].s = milo::dtoa_milo(s.sum / s.count);
} else {
state->second.sum += atof(val.s.c_str());
state->second.count += 1;
full_values[i].s = milo::dtoa_milo(state->second.sum / state->second.count);
}
break;
}
case op_concat:
full_values[i].s += val.s;
full_values[i].type = mvt_string;
break;
case op_comma:
full_values[i].s += std::string(",") + val.s;
full_values[i].type = mvt_string;
break;
}
}
}
}