From f189e5dc1020db9b41e77488d6290d6e7f032b13 Mon Sep 17 00:00:00 2001
From: =?utf8?q?Mattias=20Engdeg=C3=A5rd?= <mattiase@acm.org>
Date: Tue, 17 Mar 2020 13:18:14 +0100
Subject: [PATCH] Don't generate useless range table entries for ASCII chars
In multibyte regexps, each ASCII char or range in a character
alternative produces a nonsense range table entry in addition to the
correct bits in the ASCII bitmap. Those entries do not match anything
but waste space and time.
* src/regex-emacs.c (regex_compile): Don't generate reversed intervals.
---
src/regex-emacs.c | 25 ++++++++++++++-----------
1 file changed, 14 insertions(+), 11 deletions(-)
diff --git a/src/regex-emacs.c b/src/regex-emacs.c
index 694431c95e2..0ae004e4636 100644
--- a/src/regex-emacs.c
+++ b/src/regex-emacs.c
@@ -2113,17 +2113,20 @@ regex_compile (re_char *pattern, ptrdiff_t size,
if (CHAR_BYTE8_P (c1))
c = BYTE8_TO_CHAR (128);
}
- if (CHAR_BYTE8_P (c))
- {
- c = CHAR_TO_BYTE8 (c);
- c1 = CHAR_TO_BYTE8 (c1);
- for (; c <= c1; c++)
- SET_LIST_BIT (c);
- }
- else if (multibyte)
- SETUP_MULTIBYTE_RANGE (range_table_work, c, c1);
- else
- SETUP_UNIBYTE_RANGE (range_table_work, c, c1);
+ if (c <= c1)
+ {
+ if (CHAR_BYTE8_P (c))
+ {
+ c = CHAR_TO_BYTE8 (c);
+ c1 = CHAR_TO_BYTE8 (c1);
+ for (; c <= c1; c++)
+ SET_LIST_BIT (c);
+ }
+ else if (multibyte)
+ SETUP_MULTIBYTE_RANGE (range_table_work, c, c1);
+ else
+ SETUP_UNIBYTE_RANGE (range_table_work, c, c1);
+ }
}
}
--
2.39.5