Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

ARROW-9460: [C++] Fix BinaryContainsExact for pattern with repeated characters #7750

Closed
wants to merge 1 commit into from
Closed

ARROW-9460: [C++] Fix BinaryContainsExact for pattern with repeated characters #7750

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 8 additions & 9 deletions cpp/src/arrow/compute/kernels/scalar_string.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -356,7 +356,7 @@ void TransformBinaryContainsExact(const uint8_t* pattern, int64_t pattern_length
prefix_table[0] = -1;
for (offset_type pos = 0; pos < pattern_length; ++pos) {
// The prefix cannot be expanded, reset.
if (prefix_length >= 0 && pattern[pos] != pattern[prefix_length]) {
while (prefix_length >= 0 && pattern[pos] != pattern[prefix_length]) {
prefix_length = prefix_table[prefix_length];
}
prefix_length++;
Expand All @@ -371,14 +371,13 @@ void TransformBinaryContainsExact(const uint8_t* pattern, int64_t pattern_length

int64_t pattern_pos = 0;
for (int64_t k = 0; k < current_length; k++) {
if (pattern[pattern_pos] == current_data[k]) {
pattern_pos++;
if (pattern_pos == pattern_length) {
bitmap_writer.Set();
break;
}
} else {
pattern_pos = std::max<offset_type>(0, prefix_table[pattern_pos]);
while ((pattern_pos >= 0) && (pattern[pattern_pos] != current_data[k])) {
pattern_pos = prefix_table[pattern_pos];
}
pattern_pos++;
if (pattern_pos == pattern_length) {
bitmap_writer.Set();
break;
}
}
bitmap_writer.Next();
Expand Down
8 changes: 8 additions & 0 deletions cpp/src/arrow/compute/kernels/scalar_string_test.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -320,6 +320,14 @@ TYPED_TEST(TestStringKernels, BinaryContainsExact) {
BinaryContainsExactOptions options_repeated{"abab"};
this->CheckUnary("binary_contains_exact", R"(["abab", "ab", "cababc", null, "bac"])",
boolean(), "[true, false, true, null, false]", &options_repeated);

// ARROW-9460
BinaryContainsExactOptions options_double_char{"aab"};
this->CheckUnary("binary_contains_exact", R"(["aacb", "aab", "ab", "aaab"])", boolean(),
"[false, true, false, true]", &options_double_char);
BinaryContainsExactOptions options_double_char_2{"bbcaa"};
this->CheckUnary("binary_contains_exact", R"(["abcbaabbbcaabccabaab"])", boolean(),
"[true]", &options_double_char_2);
}

TYPED_TEST(TestStringKernels, Strptime) {
Expand Down