From 4a6e0875ae9b71530bc8a43ce5c25ef96d08b857 Mon Sep 17 00:00:00 2001 From: David Geier Date: Tue, 11 Nov 2025 13:18:59 +0100 Subject: [PATCH v11 2/3] Use radix sort to extract trigrams Replace the comparison-based sort used by generate_trgm() and generate_wildcard_trgm() with a three-pass radix sort. Trigrams consist of three bytes, so their keys have a fixed and very small width. A radix sort can therefore order them in linear time with respect to the number of trigrams, avoiding the repeated comparator calls and recursive partitioning performed by qsort. The implementation preserves the existing behavior on platforms where char is signed by flipping the most significant bit before sorting. The radix sort requires a temporary buffer, increasing the memory footprint while trigrams are being extracted from an input string. However, the sort is performed separately for each string and is never applied across multiple strings at once. Consequently, the additional memory is limited to the processing of the current string and should have a negligible effect on the overall memory footprint of a GIN index build. The resulting order remains compatible with trigram deduplication and does not change the generated trigram sets. --- contrib/pg_trgm/trgm_op.c | 99 ++++++++++++++++++++++++--------------- 1 file changed, 61 insertions(+), 38 deletions(-) diff --git a/contrib/pg_trgm/trgm_op.c b/contrib/pg_trgm/trgm_op.c index 22bcc3c3361..57eaba43f14 100644 --- a/contrib/pg_trgm/trgm_op.c +++ b/contrib/pg_trgm/trgm_op.c @@ -226,33 +226,6 @@ CMPTRGM_CHOOSE(const void *a, const void *b) return CMPTRGM(a, b); } -#define ST_SORT trigram_qsort_signed -#define ST_ELEMENT_TYPE_VOID -#define ST_COMPARE(a, b) CMPTRGM_SIGNED(a, b) -#define ST_SCOPE static -#define ST_DEFINE -#define ST_DECLARE -#include "lib/sort_template.h" - -#define ST_SORT trigram_qsort_unsigned -#define ST_ELEMENT_TYPE_VOID -#define ST_COMPARE(a, b) CMPTRGM_UNSIGNED(a, b) -#define ST_SCOPE static -#define ST_DEFINE -#define ST_DECLARE -#include "lib/sort_template.h" - -/* Sort an array of trigrams, handling signedness correctly */ -static void -trigram_qsort(trgm *array, size_t n) -{ - if (GetDefaultCharSignedness()) - trigram_qsort_signed(array, n, sizeof(trgm)); - else - trigram_qsort_unsigned(array, n, sizeof(trgm)); -} - - /* * Compare two trigrams for equality. This has the same signature as * comparison functions used for sorting, so that this can be used with @@ -268,11 +241,67 @@ CMPTRGM_EQ(const void *a, const void *b) return aa[0] != bb[0] || aa[1] != bb[1] || aa[2] != bb[2] ? 1 : 0; } -/* Deduplicate an array of trigrams */ +/* + * Needed to properly handle negative numbers in case char is signed. + */ +static inline unsigned char +radix_key(char x, bool char_is_signed) +{ + return char_is_signed ? x ^ 0x80 : x; +} + +static inline size_t +trigram_radix_sort_and_unique(trgm *trg, size_t count, bool char_is_signed) +{ + trgm *buffer = palloc_array(trgm, count); + trgm *starts[256]; + trgm *from = trg; + trgm *to = buffer; + size_t freqs[256]; + + /* + * Do the sorting. Start with last character because that's the "LSB" + * in a trigram. Avoid unnecessary copies by ping-ponging between the buffers. + */ + for (int i = 2; i >= 0; i--) + { + trgm *old_from = from; + trgm *next = to; + + /* + * Compute frequencies to partition the buffer. + */ + memset(freqs, 0, sizeof(freqs)); + + for (size_t j = 0; j < count; j++) + freqs[radix_key(trg[j][i], char_is_signed)]++; + + for (size_t j = 0; j < 256; j++) + { + starts[j] = next; + next += freqs[j]; + } + + for (size_t j = 0; j < count; j++) + memcpy(starts[radix_key(from[j][i], char_is_signed)]++, from[j], sizeof(trgm)); + + from = to; + to = old_from; + } + + count = qunique(buffer, count, sizeof(trgm), CMPTRGM_EQ); + memcpy(trg, buffer, sizeof(trgm) * count); + pfree(buffer); + return count; +} + static size_t -trigram_qunique(trgm *array, size_t n) +trigram_sort_and_unique(trgm *array, size_t n) { - return qunique(array, n, sizeof(trgm), CMPTRGM_EQ); + if (GetDefaultCharSignedness()) + return trigram_radix_sort_and_unique(array, n, true); + else + return trigram_radix_sort_and_unique(array, n, false); } /* @@ -611,10 +640,7 @@ generate_trgm(char *str, int slen) * Make trigrams unique. */ if (len > 1) - { - trigram_qsort(GETARR(trg), len); - len = trigram_qunique(GETARR(trg), len); - } + len = trigram_sort_and_unique(GETARR(trg), len); SET_VARSIZE(trg, CALCGTSIZE(ARRKEY, len)); @@ -1142,10 +1168,7 @@ generate_wildcard_trgm(const char *str, int slen) trg = arr.datum; len = arr.length; if (len > 1) - { - trigram_qsort(GETARR(trg), len); - len = trigram_qunique(GETARR(trg), len); - } + len = trigram_sort_and_unique(GETARR(trg), len); trg->flag = ARRKEY; SET_VARSIZE(trg, CALCGTSIZE(ARRKEY, len)); -- 2.53.0