cut: optimize UTF-8 input with 0xF5-0xFF delimiters

* src/cut.c (bytesearch_field_delim_ok): Expand the range
of bytes that can be simply searched for. 0xF5-0xFF can't
appear in valid UTF-8 characters, and so may be used as
delimiters in UTF-8 input, so it's worth optimizing for.
* tests/cut/cut.pl: Add a test case (mainly as documentation).
This commit is contained in:
Pádraig Brady committed 2026-04-05 13:15:56 +01:00
1 parent 03a686a456
commit 24571c41f3
2 files changed
+8 -1

No files matched your search

+5 -1
View File
@@ -311,6 +311,9 @@ mcel_isblank (mcel_t g)
return (g.len == 1 && c_isblank (g.ch)) || (g.len > 1 && c32issep (g.ch));
}
/* Return TRUE if it's valid to do a simple byte search
for the delimiter bytes. */
static inline bool
bytesearch_field_delim_ok (void)
{
@@ -318,7 +321,8 @@ bytesearch_field_delim_ok (void)
return (delim_length == 1
? (MB_CUR_MAX <= 1
|| (is_utf8_charset () ? delim_0 < 0x80 : delim_0 < 0x30))
|| (is_utf8_charset ()
? (delim_0 < 0x80 || delim_0 > 0xF4) : delim_0 < 0x30))
: utf8_field_delim_ok ());
}
+3
View File
@@ -337,6 +337,9 @@ if ($mb_locale ne 'C')
['mb-delim-7', '-d', "\xc3\xa9", '-f2',
{IN=>"a\0b\xc3\xa9c\n"}, {OUT=>"c\n"},
{ENV => "LC_ALL=$mb_locale"}],
['mb-delim-8', '-d', "\xff", '-f2', # Note 0xF5-0xFF is efficient
{IN=>"a\xffb\n"}, {OUT=>"b\n"},
{ENV => "LC_ALL=$mb_locale"}],
['mb-w-delim-1', '-w', '-f2', {IN=>"a\xe2\x80\x83b\n"}, {OUT=>"b\n"},
{ENV => "LC_ALL=$mb_locale"}],
['mb-w-delim-2', '-sw', '-f2', {IN=>"a\xc2\xa0b\n"}, {OUT=>""},