tippecanoe/pool.cpp

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <limits.h>
#include <math.h>
#include "memfile.hpp"
#include "pool.hpp"

int swizzlecmp(const char *a, const char *b) {
	ssize_t a1 = strlen(a) - 1;
	ssize_t b1 = strlen(b) - 1;

	while (a1 >= 0 || b1 >= 0) {
		unsigned char ac = '\0', bc = '\0';
		if (a1 >= 0) {
			ac = a[a1];
		}
		if (b1 >= 0) {
			bc = b[b1];
		}

		int aa = ac;
		int bb = bc;

		int cmp = aa - bb;
		if (cmp != 0) {
			return cmp;
		}

		a1--;
		b1--;
	}

	return 0;
}

long long addpool(struct memfile *poolfile, struct memfile *treefile, const char *s, char type) {
	long long *sp = &treefile->tree;
	size_t depth = 0;

	// In typical data, traversal depth generally stays under 2.5x
	size_t max = 3 * log(treefile->off / sizeof(struct stringpool)) / log(2);
	if (max < 30) {
		max = 30;
	}

	while (*sp != 0) {
		int cmp = swizzlecmp(s, poolfile->map + ((struct stringpool *) (treefile->map + *sp))->off + 1);

		if (cmp == 0) {
			cmp = type - (poolfile->map + ((struct stringpool *) (treefile->map + *sp))->off)[0];
		}

		if (cmp < 0) {
			sp = &(((struct stringpool *) (treefile->map + *sp))->left);
		} else if (cmp > 0) {
			sp = &(((struct stringpool *) (treefile->map + *sp))->right);
		} else {
			return ((struct stringpool *) (treefile->map + *sp))->off;
		}

		depth++;
		if (depth > max) {
			// Search is very deep, so string is probably unique.
			// Add it to the pool without adding it to the search tree.

			long long off = poolfile->off;
			if (memfile_write(poolfile, &type, 1) < 0) {
				perror("memfile write");
				exit(EXIT_FAILURE);
			}
			if (memfile_write(poolfile, (void *) s, strlen(s) + 1) < 0) {
				perror("memfile write");
				exit(EXIT_FAILURE);
			}
			return off;
		}
	}

	// *sp is probably in the memory-mapped file, and will move if the file grows.
	long long ssp;
	if (sp == &treefile->tree) {
		ssp = -1;
	} else {
		ssp = ((char *) sp) - treefile->map;
	}

	long long off = poolfile->off;
	if (memfile_write(poolfile, &type, 1) < 0) {
		perror("memfile write");
		exit(EXIT_FAILURE);
	}
	if (memfile_write(poolfile, (void *) s, strlen(s) + 1) < 0) {
		perror("memfile write");
		exit(EXIT_FAILURE);
	}

	struct stringpool tsp;
	tsp.left = 0;
	tsp.right = 0;
	tsp.off = off;

	long long p = treefile->off;
	if (memfile_write(treefile, &tsp, sizeof(struct stringpool)) < 0) {
		perror("memfile write");
		exit(EXIT_FAILURE);
	}

	if (ssp == -1) {
		treefile->tree = p;
	} else {
		*((long long *) (treefile->map + ssp)) = p;
	}
	return off;
}