Add --cluster-maxzoom option (#75)

* Add `--cluster-maxzoom` option

* Add tests, update changelog

* Update manpage

* Update tests

---------

Co-authored-by: Aurele Nitoref <aurele.nitoref@icloud.com>

CHANGELOG.md

@@ -1,4 +1,7 @@
+* Add --cluster-maxzoom option to limit zoom levels that receive clustering
 * Add `point_count_abbreviated` attribute to clustered features, for consistency with supercluster
+* Makefile changes to support FreeBSD
+* Add -r option to tile-join to provide a file containing a list of input files
 
 ## 2.23.0
 

Makefile

@@ -15,7 +15,7 @@ RELEASE_FLAGS := -O3 -DNDEBUG
 DEBUG_FLAGS := -O0 -DDEBUG -fno-inline-functions -fno-omit-frame-pointer
 
 
-OS := $(shell uname -o)
+OS := $(shell uname -s)
 ifeq ($(OS),FreeBSD)
 ADVSHELL = /usr/local/bin/bash
 else

README.md

@@ -456,6 +456,8 @@ the same layer, enclose them in an `all` expression so they will all be evaluate
  * `-al` or `--drop-lines`: Let "dot" dropping at lower zooms apply to lines too
  * `-ap` or `--drop-polygons`: Let "dot" dropping at lower zooms apply to polygons too
  * `-K` _distance_ or `--cluster-distance=`_distance_: Cluster points (as with `--cluster-densest-as-needed`, but without the experimental discovery process) that are approximately within _distance_ of each other. The units are tile coordinates within a nominally 256-pixel tile, so the maximum value of 255 allows only one feature per tile. Values around 10 are probably appropriate for typical marker sizes. See `--cluster-densest-as-needed` below for behavior.
+ * `-k` _zoom_ or `--cluster-maxzoom=`_zoom_: Max zoom on which to cluster points if clustering is enabled.
+ * `-kg` or `--cluster-maxzoom=g`: Set `--cluster-maxzoom=` to `maxzoom - 1` so that all features are visible at the maximum zoom level.
 
 ### Dropping a fraction of features to keep under tile size limits
 

main.cpp

@@ -82,6 +82,7 @@ size_t max_tile_size = 500000;
 size_t max_tile_features = 200000;
 int cluster_distance = 0;
 int tiny_polygon_size = 2;
+int cluster_maxzoom = MAX_ZOOM;
 long justx = -1, justy = -1;
 std::string attribute_for_id = "";
 size_t limit_tile_feature_count = 0;
@@ -1163,7 +1164,7 @@ void choose_first_zoom(long long *file_bbox, std::vector<struct reader> &readers
 	}
 }
 
-std::pair<int, metadata> read_input(std::vector<source> &sources, char *fname, int maxzoom, int minzoom, int basezoom, double basezoom_marker_width, sqlite3 *outdb, const char *outdir, std::set<std::string> *exclude, std::set<std::string> *include, int exclude_all, json_object *filter, double droprate, int buffer, const char *tmpdir, double gamma, int read_parallel, int forcetable, const char *attribution, bool uses_gamma, long long *file_bbox, const char *prefilter, const char *postfilter, const char *description, bool guess_maxzoom, std::map<std::string, int> const *attribute_types, const char *pgm, std::map<std::string, attribute_op> const *attribute_accum, std::map<std::string, std::string> const &attribute_descriptions, std::string const &commandline, int minimum_maxzoom) {
+std::pair<int, metadata> read_input(std::vector<source> &sources, char *fname, int maxzoom, int minzoom, int basezoom, double basezoom_marker_width, sqlite3 *outdb, const char *outdir, std::set<std::string> *exclude, std::set<std::string> *include, int exclude_all, json_object *filter, double droprate, int buffer, const char *tmpdir, double gamma, int read_parallel, int forcetable, const char *attribution, bool uses_gamma, long long *file_bbox, const char *prefilter, const char *postfilter, const char *description, bool guess_maxzoom, bool guess_cluster_maxzoom, std::map<std::string, int> const *attribute_types, const char *pgm, std::map<std::string, attribute_op> const *attribute_accum, std::map<std::string, std::string> const &attribute_descriptions, std::string const &commandline, int minimum_maxzoom) {
 	int ret = EXIT_SUCCESS;
 
 	std::vector<struct reader> readers;
@@ -2102,7 +2103,7 @@ std::pair<int, metadata> read_input(std::vector<source> &sources, char *fname, i
 			}
 
 			bool changed = false;
-			while (maxzoom < 32 - full_detail && maxzoom < 33 - low_detail && cluster_distance > 0) {
+			while (maxzoom < 32 - full_detail && maxzoom < 33 - low_detail && maxzoom < cluster_maxzoom && cluster_distance > 0) {
 				unsigned long long zoom_mingap = ((1LL << (32 - maxzoom)) / 256 * cluster_distance) * ((1LL << (32 - maxzoom)) / 256 * cluster_distance);
 				if (avg > zoom_mingap) {
 					break;
@@ -2112,7 +2113,7 @@ std::pair<int, metadata> read_input(std::vector<source> &sources, char *fname, i
 				changed = true;
 			}
 			if (changed) {
-				printf("Choosing a maxzoom of -z%d to keep most features distinct with cluster distance %d\n", maxzoom, cluster_distance);
+				printf("Choosing a maxzoom of -z%d to keep most features distinct with cluster distance %d and cluster maxzoom %d\n", maxzoom, cluster_distance, cluster_maxzoom);
 			}
 
 			if (droprate == -3) {
@@ -2203,6 +2204,11 @@ std::pair<int, metadata> read_input(std::vector<source> &sources, char *fname, i
 		}
 	}
 
+	if (cluster_maxzoom >= maxzoom && guess_cluster_maxzoom) {
+		cluster_maxzoom = maxzoom - 1;
+		fprintf(stderr, "Choosing a cluster maxzoom of -k%d to make all features visible at maximum zoom %d\n", cluster_maxzoom, maxzoom);
+	}
+
 	if (basezoom < 0 || droprate < 0) {
 		struct tile {
 			unsigned x;
@@ -2692,6 +2698,7 @@ int main(int argc, char **argv) {
 	const char *postfilter = NULL;
 	bool guess_maxzoom = false;
 	int minimum_maxzoom = 0;
+	bool guess_cluster_maxzoom = false;
 
 	std::set<std::string> exclude, include;
 	std::map<std::string, int> attribute_types;
@@ -2770,6 +2777,7 @@ int main(int argc, char **argv) {
 		{"drop-lines", no_argument, &additional[A_LINE_DROP], 1},
 		{"drop-polygons", no_argument, &additional[A_POLYGON_DROP], 1},
 		{"cluster-distance", required_argument, 0, 'K'},
+		{"cluster-maxzoom", required_argument, 0, 'k'},
 
 		{"Dropping or merging a fraction of features to keep under tile size limits", 0, 0, 0},
 		{"drop-densest-as-needed", no_argument, &additional[A_DROP_DENSEST_AS_NEEDED], 1},
@@ -3073,6 +3081,15 @@ int main(int argc, char **argv) {
 			}
 			break;
 
+		case 'k':
+			if (strcmp(optarg, "g") == 0) {
+				cluster_maxzoom = MAX_ZOOM - 1;
+				guess_cluster_maxzoom = true;
+			} else {
+				cluster_maxzoom = atoi_require(optarg, "Cluster maxzoom");
+			}
+			break;
+
 		case 'd':
 			full_detail = atoi_require(optarg, "Full detail");
 			if (full_detail > 30) {
@@ -3484,7 +3501,7 @@ int main(int argc, char **argv) {
 
 	auto input_ret = read_input(sources, name ? name : out_mbtiles ? out_mbtiles
 								       : out_dir,
-				    maxzoom, minzoom, basezoom, basezoom_marker_width, outdb, out_dir, &exclude, &include, exclude_all, filter, droprate, buffer, tmpdir, gamma, read_parallel, forcetable, attribution, gamma != 0, file_bbox, prefilter, postfilter, description, guess_maxzoom, &attribute_types, argv[0], &attribute_accum, attribute_descriptions, commandline, minimum_maxzoom);
+				    maxzoom, minzoom, basezoom, basezoom_marker_width, outdb, out_dir, &exclude, &include, exclude_all, filter, droprate, buffer, tmpdir, gamma, read_parallel, forcetable, attribution, gamma != 0, file_bbox, prefilter, postfilter, description, guess_maxzoom, guess_cluster_maxzoom, &attribute_types, argv[0], &attribute_accum, attribute_descriptions, commandline, minimum_maxzoom);
 
 	ret = std::get<0>(input_ret);
 

main.hpp

@@ -53,6 +53,7 @@ extern size_t memsize;
 extern size_t max_tile_size;
 extern size_t max_tile_features;
 extern int cluster_distance;
+extern int cluster_maxzoom;
 extern std::string attribute_for_id;
 extern int tiny_polygon_size;
 extern size_t limit_tile_feature_count;

man/tippecanoe.1

@@ -395,7 +395,7 @@ Parallel processing will also be automatic if the input file is in FlatGeobuf fo
 .IP \(bu 2
 \fB\fC\-zg\fR or \fB\fC\-\-maximum\-zoom=g\fR: Guess what is probably a reasonable maxzoom based on the spacing of features.
 .IP \(bu 2
-\fB\fC\-\-smallest\-maximum\-zoom\-guess=\fR\fIzoom\fP: Guess what is probably a reasonable maxzoom based on the spacing of features, but using the specified \fIzoom\fP if a lower maxzoom is guessed.
+\fB\fC\-\-smallest\-maximum\-zoom\-guess=\fR\fIzoom\fP: Guess what is probably a reasonable maxzoom based on the spacing of features, but using the specified \fIzoom\fP if a lower maxzoom is guessed. If \fB\fC\-Bg\fR is also set, the base zoom will be set to the guessed maxzoom, with all the points carried forward into additional zooms through the one specified.
 .IP \(bu 2
 \fB\fC\-Z\fR \fIzoom\fP or \fB\fC\-\-minimum\-zoom=\fR\fIzoom\fP: Minzoom: the lowest zoom level for which tiles are generated (default 0)
 .IP \(bu 2
@@ -573,6 +573,10 @@ preference to retaining points in sparse areas and dropping points in dense area
 \fB\fC\-ap\fR or \fB\fC\-\-drop\-polygons\fR: Let "dot" dropping at lower zooms apply to polygons too
 .IP \(bu 2
 \fB\fC\-K\fR \fIdistance\fP or \fB\fC\-\-cluster\-distance=\fR\fIdistance\fP: Cluster points (as with \fB\fC\-\-cluster\-densest\-as\-needed\fR, but without the experimental discovery process) that are approximately within \fIdistance\fP of each other. The units are tile coordinates within a nominally 256\-pixel tile, so the maximum value of 255 allows only one feature per tile. Values around 10 are probably appropriate for typical marker sizes. See \fB\fC\-\-cluster\-densest\-as\-needed\fR below for behavior.
+.IP \(bu 2
+\fB\fC\-k\fR \fIzoom\fP or \fB\fC\-\-cluster\-maxzoom=\fR\fIzoom\fP: Max zoom on which to cluster points if clustering is enabled.
+.IP \(bu 2
+\fB\fC\-kg\fR or \fB\fC\-\-cluster\-maxzoom=g\fR: Set \fB\fC\-\-cluster\-maxzoom=\fR to \fB\fCmaxzoom \- 1\fR so that all features are visible at the maximum zoom level.
 .RE
 .SS Dropping a fraction of features to keep under tile size limits
 .RS
@@ -952,6 +956,8 @@ The options are:
 \fB\fC\-e\fR \fIdirectory\fP or \fB\fC\-\-output\-to\-directory=\fR\fIdirectory\fP: Write the new tiles to the specified directory instead of to an mbtiles file.
 .IP \(bu 2
 \fB\fC\-f\fR or \fB\fC\-\-force\fR: Remove \fIout.mbtiles\fP if it already exists.
+.IP \(bu 2
+\fB\fC\-r\fR or \fB\fC\-\-read\-from\fR: list of input mbtiles to read from.
 .RE
 .SS Tileset description and attribution
 .RS

tile.cpp

@@ -2088,7 +2088,7 @@ long long write_tile(decompressor *geoms, std::atomic<long long> *geompos_in, ch
 			// representative of the other features in the tile.
 			const size_t MAX_INDICES = 100000;
 
-			if (additional[A_CLUSTER_DENSEST_AS_NEEDED] || cluster_distance != 0) {
+			if (z <= cluster_maxzoom && (additional[A_CLUSTER_DENSEST_AS_NEEDED] || cluster_distance != 0)) {
 				if (indices.size() < MAX_INDICES) {
 					indices.push_back(sf.index);
 				}