Mercurial > vim
view src/memfile_test.c @ 34854:97b5457962ed v9.1.0296
patch 9.1.0296: regexp: engines do not handle case-folding well
Commit: https://github.com/vim/vim/commit/7a27c108e0509f3255ebdcb6558e896c223e4d23
Author: Christian Brabandt <cb@256bit.org>
Date: Tue Apr 9 22:53:19 2024 +0200
patch 9.1.0296: regexp: engines do not handle case-folding well
Problem: Regex engines do not handle case-folding well
Solution: Correctly calculate byte length of characters to skip
When the regexp engine compares two utf-8 codepoints case insensitively
it may match an adjacent character, because it assumes it can step over
as many bytes as the pattern contains.
This however is not necessarily true because of case-folding, a
multi-byte UTF-8 character can be considered equal to some single-byte
value.
Let's consider the pattern '?' and the string 's'. When comparing and
ignoring case, the single character 's' matches, and since it matches
Vim will try to step over the match (by the amount of bytes of the
pattern), assuming that since it matches, the length of both strings is
the same.
However in that case, it should only step over the single byte
value 's' so by 1 byte and try to start matching after it again. So for the
backtracking engine we need to ensure:
- we try to match the correct length for the pattern and the text
- in case of a match, we step over it correctly
The same thing can happen for the NFA engine, when skipping to the next
character to test for a match. We are skipping over the regstart
pointer, however we do not consider the case that because of
case-folding we may need to adjust the number of bytes to skip over. So
this needs to be adjusted in find_match_text() as well.
A related issue turned out, when prog->match_text is actually empty. In
that case we should try to find the next match and skip this condition.
fixes: #14294
closes: #14433
Signed-off-by: Christian Brabandt <cb@256bit.org>
author | Christian Brabandt <cb@256bit.org> |
---|---|
date | Tue, 09 Apr 2024 23:00:08 +0200 |
parents | f41b55f9357c |
children |
line wrap: on
line source
/* vi:set ts=8 sts=4 sw=4 noet: * * VIM - Vi IMproved by Bram Moolenaar * * Do ":help uganda" in Vim to read copying and usage conditions. * Do ":help credits" in Vim to see a list of people who contributed. * See README.txt for an overview of the Vim source code. */ /* * memfile_test.c: Unittests for memfile.c * Mostly by Ivan Krasilnikov. */ #undef NDEBUG #include <assert.h> // Must include main.c because it contains much more than just main() #define NO_VIM_MAIN #include "main.c" // This file has to be included because the tested functions are static #include "memfile.c" #define index_to_key(i) ((i) ^ 15167) #define TEST_COUNT 50000 /* * Test mf_hash_*() functions. */ static void test_mf_hash(void) { mf_hashtab_T ht; mf_hashitem_T *item; blocknr_T key; long_u i; long_u num_buckets; mf_hash_init(&ht); // insert some items and check invariants for (i = 0; i < TEST_COUNT; i++) { assert(ht.mht_count == i); // check that number of buckets is a power of 2 num_buckets = ht.mht_mask + 1; assert(num_buckets > 0 && (num_buckets & (num_buckets - 1)) == 0); // check load factor assert(ht.mht_count <= (num_buckets << MHT_LOG_LOAD_FACTOR)); if (i < (MHT_INIT_SIZE << MHT_LOG_LOAD_FACTOR)) { // first expansion shouldn't have occurred yet assert(num_buckets == MHT_INIT_SIZE); assert(ht.mht_buckets == ht.mht_small_buckets); } else { assert(num_buckets > MHT_INIT_SIZE); assert(ht.mht_buckets != ht.mht_small_buckets); } key = index_to_key(i); assert(mf_hash_find(&ht, key) == NULL); // allocate and add new item item = LALLOC_CLEAR_ONE(mf_hashitem_T); assert(item != NULL); item->mhi_key = key; mf_hash_add_item(&ht, item); assert(mf_hash_find(&ht, key) == item); if (ht.mht_mask + 1 != num_buckets) { // hash table was expanded assert(ht.mht_mask + 1 == num_buckets * MHT_GROWTH_FACTOR); assert(i + 1 == (num_buckets << MHT_LOG_LOAD_FACTOR)); } } // check presence of inserted items for (i = 0; i < TEST_COUNT; i++) { key = index_to_key(i); item = mf_hash_find(&ht, key); assert(item != NULL); assert(item->mhi_key == key); } // delete some items for (i = 0; i < TEST_COUNT; i++) { if (i % 100 < 70) { key = index_to_key(i); item = mf_hash_find(&ht, key); assert(item != NULL); assert(item->mhi_key == key); mf_hash_rem_item(&ht, item); assert(mf_hash_find(&ht, key) == NULL); mf_hash_add_item(&ht, item); assert(mf_hash_find(&ht, key) == item); mf_hash_rem_item(&ht, item); assert(mf_hash_find(&ht, key) == NULL); vim_free(item); } } // check again for (i = 0; i < TEST_COUNT; i++) { key = index_to_key(i); item = mf_hash_find(&ht, key); if (i % 100 < 70) { assert(item == NULL); } else { assert(item != NULL); assert(item->mhi_key == key); } } // free hash table and all remaining items mf_hash_free_all(&ht); } int main(void) { test_mf_hash(); return 0; }