gitlab-org--gitlab-foss/lib/gitlab/sql/pattern.rb

82 lines
2.7 KiB
Ruby
Raw Normal View History

# frozen_string_literal: true
module Gitlab
module SQL
2017-08-28 18:14:41 -04:00
module Pattern
extend ActiveSupport::Concern
2017-08-28 18:14:41 -04:00
MIN_CHARS_FOR_PARTIAL_MATCHING = 3
2019-05-05 06:19:14 -04:00
REGEX_QUOTED_WORD = /(?<=\A| )"[^"]+"(?= |\z)/.freeze
2017-08-28 18:14:41 -04:00
class_methods do
def fuzzy_search(query, columns, use_minimum_char_limit: true)
matches = columns.map do |col|
fuzzy_arel_match(col, query, use_minimum_char_limit: use_minimum_char_limit)
end.compact.reduce(:or)
where(matches)
end
def to_pattern(query, use_minimum_char_limit: true)
if partial_matching?(query, use_minimum_char_limit: use_minimum_char_limit)
2017-08-28 18:14:41 -04:00
"%#{sanitize_sql_like(query)}%"
2017-08-29 05:00:03 -04:00
else
sanitize_sql_like(query)
2017-08-28 18:14:41 -04:00
end
end
def min_chars_for_partial_matching
MIN_CHARS_FOR_PARTIAL_MATCHING
end
def partial_matching?(query, use_minimum_char_limit: true)
return true unless use_minimum_char_limit
query.length >= min_chars_for_partial_matching
2017-08-28 18:14:41 -04:00
end
# column - The column name / Arel column to search in.
Optimise searching for users using short queries This optimises searching for users when using queries consisting out of one or two characters such as "ab". We optimise such cases by searching for `LOWER(name)` and `LOWER(username)` instead of using `ILIKE`. Using `LOWER` produces a _much_ better performing query. For example, when searching for all users matching the term "a" we'd produce the following plan: Limit (cost=637.69..637.74 rows=20 width=805) (actual time=41.983..41.995 rows=20 loops=1) Buffers: shared hit=8330 -> Sort (cost=637.69..638.61 rows=368 width=805) (actual time=41.982..41.990 rows=20 loops=1) Sort Key: (CASE WHEN ((name)::text = 'a'::text) THEN 0 WHEN ((username)::text = 'a'::text) THEN 1 WHEN ((email)::text = 'a'::text) THEN 2 ELSE 3 END), name Sort Method: top-N heapsort Memory: 35kB Buffers: shared hit=8330 -> Bitmap Heap Scan on users (cost=75.47..627.89 rows=368 width=805) (actual time=9.452..41.305 rows=277 loops=1) Recheck Cond: (((name)::text ~~* 'a'::text) OR ((username)::text ~~* 'a'::text) OR ((email)::text = 'a'::text)) Rows Removed by Index Recheck: 7601 Heap Blocks: exact=7636 Buffers: shared hit=8327 -> BitmapOr (cost=75.47..75.47 rows=368 width=0) (actual time=8.290..8.290 rows=0 loops=1) Buffers: shared hit=691 -> Bitmap Index Scan on index_users_on_name_trigram (cost=0.00..38.85 rows=180 width=0) (actual time=4.369..4.369 rows=4071 loops=1) Index Cond: ((name)::text ~~* 'a'::text) Buffers: shared hit=360 -> Bitmap Index Scan on index_users_on_username_trigram (cost=0.00..34.41 rows=188 width=0) (actual time=3.896..3.896 rows=4140 loops=1) Index Cond: ((username)::text ~~* 'a'::text) Buffers: shared hit=328 -> Bitmap Index Scan on users_email_key (cost=0.00..1.94 rows=1 width=0) (actual time=0.022..0.022 rows=0 loops=1) Index Cond: ((email)::text = 'a'::text) Buffers: shared hit=3 Planning time: 3.912 ms Execution time: 42.171 ms With the changes in this commit we now produce the following plan instead: Limit (cost=13257.48..13257.53 rows=20 width=805) (actual time=1.567..1.579 rows=20 loops=1) Buffers: shared hit=287 -> Sort (cost=13257.48..13280.93 rows=9379 width=805) (actual time=1.567..1.572 rows=20 loops=1) Sort Key: (CASE WHEN ((name)::text = 'a'::text) THEN 0 WHEN ((username)::text = 'a'::text) THEN 1 WHEN ((email)::text = 'a'::text) THEN 2 ELSE 3 END), name Sort Method: top-N heapsort Memory: 35kB Buffers: shared hit=287 -> Bitmap Heap Scan on users (cost=135.66..13007.91 rows=9379 width=805) (actual time=0.194..1.107 rows=277 loops=1) Recheck Cond: ((lower((name)::text) = 'a'::text) OR (lower((username)::text) = 'a'::text) OR ((email)::text = 'a'::text)) Heap Blocks: exact=277 Buffers: shared hit=287 -> BitmapOr (cost=135.66..135.66 rows=9379 width=0) (actual time=0.152..0.152 rows=0 loops=1) Buffers: shared hit=10 -> Bitmap Index Scan on yorick_test_users (cost=0.00..124.75 rows=9377 width=0) (actual time=0.101..0.101 rows=277 loops=1) Index Cond: (lower((name)::text) = 'a'::text) Buffers: shared hit=4 -> Bitmap Index Scan on index_on_users_lower_username (cost=0.00..1.94 rows=1 width=0) (actual time=0.035..0.035 rows=1 loops=1) Index Cond: (lower((username)::text) = 'a'::text) Buffers: shared hit=3 -> Bitmap Index Scan on users_email_key (cost=0.00..1.94 rows=1 width=0) (actual time=0.014..0.014 rows=0 loops=1) Index Cond: ((email)::text = 'a'::text) Buffers: shared hit=3 Planning time: 0.303 ms Execution time: 1.687 ms Here we can see the new query is 25 times faster compared to the old query.
2018-02-15 13:34:44 -05:00
# query - The text to search for.
# lower_exact_match - When set to `true` we'll fall back to using
# `LOWER(column) = query` instead of using `ILIKE`.
def fuzzy_arel_match(column, query, lower_exact_match: false, use_minimum_char_limit: true)
query = query.squish
return unless query.present?
arel_column = column.is_a?(Arel::Attributes::Attribute) ? column : arel_table[column]
words = select_fuzzy_words(query, use_minimum_char_limit: use_minimum_char_limit)
if words.any?
words.map { |word| arel_column.matches(to_pattern(word, use_minimum_char_limit: use_minimum_char_limit)) }.reduce(:and)
else
# No words of at least 3 chars, but we can search for an exact
# case insensitive match with the query as a whole
Optimise searching for users using short queries This optimises searching for users when using queries consisting out of one or two characters such as "ab". We optimise such cases by searching for `LOWER(name)` and `LOWER(username)` instead of using `ILIKE`. Using `LOWER` produces a _much_ better performing query. For example, when searching for all users matching the term "a" we'd produce the following plan: Limit (cost=637.69..637.74 rows=20 width=805) (actual time=41.983..41.995 rows=20 loops=1) Buffers: shared hit=8330 -> Sort (cost=637.69..638.61 rows=368 width=805) (actual time=41.982..41.990 rows=20 loops=1) Sort Key: (CASE WHEN ((name)::text = 'a'::text) THEN 0 WHEN ((username)::text = 'a'::text) THEN 1 WHEN ((email)::text = 'a'::text) THEN 2 ELSE 3 END), name Sort Method: top-N heapsort Memory: 35kB Buffers: shared hit=8330 -> Bitmap Heap Scan on users (cost=75.47..627.89 rows=368 width=805) (actual time=9.452..41.305 rows=277 loops=1) Recheck Cond: (((name)::text ~~* 'a'::text) OR ((username)::text ~~* 'a'::text) OR ((email)::text = 'a'::text)) Rows Removed by Index Recheck: 7601 Heap Blocks: exact=7636 Buffers: shared hit=8327 -> BitmapOr (cost=75.47..75.47 rows=368 width=0) (actual time=8.290..8.290 rows=0 loops=1) Buffers: shared hit=691 -> Bitmap Index Scan on index_users_on_name_trigram (cost=0.00..38.85 rows=180 width=0) (actual time=4.369..4.369 rows=4071 loops=1) Index Cond: ((name)::text ~~* 'a'::text) Buffers: shared hit=360 -> Bitmap Index Scan on index_users_on_username_trigram (cost=0.00..34.41 rows=188 width=0) (actual time=3.896..3.896 rows=4140 loops=1) Index Cond: ((username)::text ~~* 'a'::text) Buffers: shared hit=328 -> Bitmap Index Scan on users_email_key (cost=0.00..1.94 rows=1 width=0) (actual time=0.022..0.022 rows=0 loops=1) Index Cond: ((email)::text = 'a'::text) Buffers: shared hit=3 Planning time: 3.912 ms Execution time: 42.171 ms With the changes in this commit we now produce the following plan instead: Limit (cost=13257.48..13257.53 rows=20 width=805) (actual time=1.567..1.579 rows=20 loops=1) Buffers: shared hit=287 -> Sort (cost=13257.48..13280.93 rows=9379 width=805) (actual time=1.567..1.572 rows=20 loops=1) Sort Key: (CASE WHEN ((name)::text = 'a'::text) THEN 0 WHEN ((username)::text = 'a'::text) THEN 1 WHEN ((email)::text = 'a'::text) THEN 2 ELSE 3 END), name Sort Method: top-N heapsort Memory: 35kB Buffers: shared hit=287 -> Bitmap Heap Scan on users (cost=135.66..13007.91 rows=9379 width=805) (actual time=0.194..1.107 rows=277 loops=1) Recheck Cond: ((lower((name)::text) = 'a'::text) OR (lower((username)::text) = 'a'::text) OR ((email)::text = 'a'::text)) Heap Blocks: exact=277 Buffers: shared hit=287 -> BitmapOr (cost=135.66..135.66 rows=9379 width=0) (actual time=0.152..0.152 rows=0 loops=1) Buffers: shared hit=10 -> Bitmap Index Scan on yorick_test_users (cost=0.00..124.75 rows=9377 width=0) (actual time=0.101..0.101 rows=277 loops=1) Index Cond: (lower((name)::text) = 'a'::text) Buffers: shared hit=4 -> Bitmap Index Scan on index_on_users_lower_username (cost=0.00..1.94 rows=1 width=0) (actual time=0.035..0.035 rows=1 loops=1) Index Cond: (lower((username)::text) = 'a'::text) Buffers: shared hit=3 -> Bitmap Index Scan on users_email_key (cost=0.00..1.94 rows=1 width=0) (actual time=0.014..0.014 rows=0 loops=1) Index Cond: ((email)::text = 'a'::text) Buffers: shared hit=3 Planning time: 0.303 ms Execution time: 1.687 ms Here we can see the new query is 25 times faster compared to the old query.
2018-02-15 13:34:44 -05:00
if lower_exact_match
Arel::Nodes::NamedFunction
.new('LOWER', [arel_column])
.eq(query)
Optimise searching for users using short queries This optimises searching for users when using queries consisting out of one or two characters such as "ab". We optimise such cases by searching for `LOWER(name)` and `LOWER(username)` instead of using `ILIKE`. Using `LOWER` produces a _much_ better performing query. For example, when searching for all users matching the term "a" we'd produce the following plan: Limit (cost=637.69..637.74 rows=20 width=805) (actual time=41.983..41.995 rows=20 loops=1) Buffers: shared hit=8330 -> Sort (cost=637.69..638.61 rows=368 width=805) (actual time=41.982..41.990 rows=20 loops=1) Sort Key: (CASE WHEN ((name)::text = 'a'::text) THEN 0 WHEN ((username)::text = 'a'::text) THEN 1 WHEN ((email)::text = 'a'::text) THEN 2 ELSE 3 END), name Sort Method: top-N heapsort Memory: 35kB Buffers: shared hit=8330 -> Bitmap Heap Scan on users (cost=75.47..627.89 rows=368 width=805) (actual time=9.452..41.305 rows=277 loops=1) Recheck Cond: (((name)::text ~~* 'a'::text) OR ((username)::text ~~* 'a'::text) OR ((email)::text = 'a'::text)) Rows Removed by Index Recheck: 7601 Heap Blocks: exact=7636 Buffers: shared hit=8327 -> BitmapOr (cost=75.47..75.47 rows=368 width=0) (actual time=8.290..8.290 rows=0 loops=1) Buffers: shared hit=691 -> Bitmap Index Scan on index_users_on_name_trigram (cost=0.00..38.85 rows=180 width=0) (actual time=4.369..4.369 rows=4071 loops=1) Index Cond: ((name)::text ~~* 'a'::text) Buffers: shared hit=360 -> Bitmap Index Scan on index_users_on_username_trigram (cost=0.00..34.41 rows=188 width=0) (actual time=3.896..3.896 rows=4140 loops=1) Index Cond: ((username)::text ~~* 'a'::text) Buffers: shared hit=328 -> Bitmap Index Scan on users_email_key (cost=0.00..1.94 rows=1 width=0) (actual time=0.022..0.022 rows=0 loops=1) Index Cond: ((email)::text = 'a'::text) Buffers: shared hit=3 Planning time: 3.912 ms Execution time: 42.171 ms With the changes in this commit we now produce the following plan instead: Limit (cost=13257.48..13257.53 rows=20 width=805) (actual time=1.567..1.579 rows=20 loops=1) Buffers: shared hit=287 -> Sort (cost=13257.48..13280.93 rows=9379 width=805) (actual time=1.567..1.572 rows=20 loops=1) Sort Key: (CASE WHEN ((name)::text = 'a'::text) THEN 0 WHEN ((username)::text = 'a'::text) THEN 1 WHEN ((email)::text = 'a'::text) THEN 2 ELSE 3 END), name Sort Method: top-N heapsort Memory: 35kB Buffers: shared hit=287 -> Bitmap Heap Scan on users (cost=135.66..13007.91 rows=9379 width=805) (actual time=0.194..1.107 rows=277 loops=1) Recheck Cond: ((lower((name)::text) = 'a'::text) OR (lower((username)::text) = 'a'::text) OR ((email)::text = 'a'::text)) Heap Blocks: exact=277 Buffers: shared hit=287 -> BitmapOr (cost=135.66..135.66 rows=9379 width=0) (actual time=0.152..0.152 rows=0 loops=1) Buffers: shared hit=10 -> Bitmap Index Scan on yorick_test_users (cost=0.00..124.75 rows=9377 width=0) (actual time=0.101..0.101 rows=277 loops=1) Index Cond: (lower((name)::text) = 'a'::text) Buffers: shared hit=4 -> Bitmap Index Scan on index_on_users_lower_username (cost=0.00..1.94 rows=1 width=0) (actual time=0.035..0.035 rows=1 loops=1) Index Cond: (lower((username)::text) = 'a'::text) Buffers: shared hit=3 -> Bitmap Index Scan on users_email_key (cost=0.00..1.94 rows=1 width=0) (actual time=0.014..0.014 rows=0 loops=1) Index Cond: ((email)::text = 'a'::text) Buffers: shared hit=3 Planning time: 0.303 ms Execution time: 1.687 ms Here we can see the new query is 25 times faster compared to the old query.
2018-02-15 13:34:44 -05:00
else
arel_column.matches(sanitize_sql_like(query))
Optimise searching for users using short queries This optimises searching for users when using queries consisting out of one or two characters such as "ab". We optimise such cases by searching for `LOWER(name)` and `LOWER(username)` instead of using `ILIKE`. Using `LOWER` produces a _much_ better performing query. For example, when searching for all users matching the term "a" we'd produce the following plan: Limit (cost=637.69..637.74 rows=20 width=805) (actual time=41.983..41.995 rows=20 loops=1) Buffers: shared hit=8330 -> Sort (cost=637.69..638.61 rows=368 width=805) (actual time=41.982..41.990 rows=20 loops=1) Sort Key: (CASE WHEN ((name)::text = 'a'::text) THEN 0 WHEN ((username)::text = 'a'::text) THEN 1 WHEN ((email)::text = 'a'::text) THEN 2 ELSE 3 END), name Sort Method: top-N heapsort Memory: 35kB Buffers: shared hit=8330 -> Bitmap Heap Scan on users (cost=75.47..627.89 rows=368 width=805) (actual time=9.452..41.305 rows=277 loops=1) Recheck Cond: (((name)::text ~~* 'a'::text) OR ((username)::text ~~* 'a'::text) OR ((email)::text = 'a'::text)) Rows Removed by Index Recheck: 7601 Heap Blocks: exact=7636 Buffers: shared hit=8327 -> BitmapOr (cost=75.47..75.47 rows=368 width=0) (actual time=8.290..8.290 rows=0 loops=1) Buffers: shared hit=691 -> Bitmap Index Scan on index_users_on_name_trigram (cost=0.00..38.85 rows=180 width=0) (actual time=4.369..4.369 rows=4071 loops=1) Index Cond: ((name)::text ~~* 'a'::text) Buffers: shared hit=360 -> Bitmap Index Scan on index_users_on_username_trigram (cost=0.00..34.41 rows=188 width=0) (actual time=3.896..3.896 rows=4140 loops=1) Index Cond: ((username)::text ~~* 'a'::text) Buffers: shared hit=328 -> Bitmap Index Scan on users_email_key (cost=0.00..1.94 rows=1 width=0) (actual time=0.022..0.022 rows=0 loops=1) Index Cond: ((email)::text = 'a'::text) Buffers: shared hit=3 Planning time: 3.912 ms Execution time: 42.171 ms With the changes in this commit we now produce the following plan instead: Limit (cost=13257.48..13257.53 rows=20 width=805) (actual time=1.567..1.579 rows=20 loops=1) Buffers: shared hit=287 -> Sort (cost=13257.48..13280.93 rows=9379 width=805) (actual time=1.567..1.572 rows=20 loops=1) Sort Key: (CASE WHEN ((name)::text = 'a'::text) THEN 0 WHEN ((username)::text = 'a'::text) THEN 1 WHEN ((email)::text = 'a'::text) THEN 2 ELSE 3 END), name Sort Method: top-N heapsort Memory: 35kB Buffers: shared hit=287 -> Bitmap Heap Scan on users (cost=135.66..13007.91 rows=9379 width=805) (actual time=0.194..1.107 rows=277 loops=1) Recheck Cond: ((lower((name)::text) = 'a'::text) OR (lower((username)::text) = 'a'::text) OR ((email)::text = 'a'::text)) Heap Blocks: exact=277 Buffers: shared hit=287 -> BitmapOr (cost=135.66..135.66 rows=9379 width=0) (actual time=0.152..0.152 rows=0 loops=1) Buffers: shared hit=10 -> Bitmap Index Scan on yorick_test_users (cost=0.00..124.75 rows=9377 width=0) (actual time=0.101..0.101 rows=277 loops=1) Index Cond: (lower((name)::text) = 'a'::text) Buffers: shared hit=4 -> Bitmap Index Scan on index_on_users_lower_username (cost=0.00..1.94 rows=1 width=0) (actual time=0.035..0.035 rows=1 loops=1) Index Cond: (lower((username)::text) = 'a'::text) Buffers: shared hit=3 -> Bitmap Index Scan on users_email_key (cost=0.00..1.94 rows=1 width=0) (actual time=0.014..0.014 rows=0 loops=1) Index Cond: ((email)::text = 'a'::text) Buffers: shared hit=3 Planning time: 0.303 ms Execution time: 1.687 ms Here we can see the new query is 25 times faster compared to the old query.
2018-02-15 13:34:44 -05:00
end
end
end
def select_fuzzy_words(query, use_minimum_char_limit: true)
quoted_words = query.scan(REGEX_QUOTED_WORD)
query = quoted_words.reduce(query) { |q, quoted_word| q.sub(quoted_word, '') }
words = query.split
quoted_words.map! { |quoted_word| quoted_word[1..-2] }
words.concat(quoted_words)
words.select { |word| partial_matching?(word, use_minimum_char_limit: use_minimum_char_limit) }
end
end
end
end
end