Optimization for lower(), upper(), casefold() functions.

Browse Source

Improve performance and reduce table sizes for case mapping.

The main case mapping table stores only 16-bit offsets, which can be
used to look up the mapped code point in any of the case tables (fold,
lower, upper, or title case). Simple case pairs point to the same
offsets.

Generate a function in generate-unicode_case_table.pl that consists of
a nested branches to test for specific codepoint ranges that determine
the offset in the main table.

Other approaches were considered, such as representing these ranges as
another structure (rather than branches in a generated function), or a
different approach such as a radix tree, or perfect hashing. The
author implemented and tested these alternatives and settled on the
generated branches.

Author: Alexander Borisov <lex.borisov@gmail.com>
Reviewed-by: Heikki Linnakangas <hlinnaka@iki.fi>
Discussion: https://postgr.es/m/7cac7e66-9a3b-4e3f-a997-42aa0c401f80%40gmail.com

...

This commit is contained in:

Jeff Davis

2025-03-15 13:00:50 -07:00

parent c3953226a0

commit 27bdec0684

3 changed files with 13674 additions and 3218 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

16418

src/include/common/unicode_case_table.h

File diff suppressed because it is too large Load Diff