From 991008dc460854b5f2f978a87946f9d90e3e5ee5 Mon Sep 17 00:00:00 2001 From: Hiltjo Posthuma Date: Mon, 9 Mar 2020 19:16:52 +0100 Subject: sfeed_plain: optimize utf8-decoding and column position calculation Optimize for the common-case: assuming ASCII. The input is assumed to be valid UTF-8 input (output of sfeed). This saves 2 function calls for determining the width of a single ASCII character, which of course is 1. Ranges: < 32 are control-characters and are skipped. < 127 is typical ASCII and is 1 column wide. >= 127 is the normal path (control-character and multi-byte UTF-8). Tested on OpenBSD and Linux with various compilers (clang, gcc, pcc and tcc). On OpenBSD and Linux glibc much improvement. On Linux musl (almost) no change. In a common-case upto 40% performance improvement. In the worst-case negligible performance degration (<1%). --- util.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/util.c b/util.c index 6b155dc..51f7bd8 100644 --- a/util.c +++ b/util.c @@ -247,10 +247,15 @@ printutf8pad(FILE *fp, const char *s, size_t len, int pad) slen = strlen(s); for (i = 0; i < slen; i += rl) { - if ((rl = mbtowc(&wc, s + i, slen - i < 4 ? slen - i : 4)) <= 0) - break; - if ((w = wcwidth(wc)) == -1) + rl = w = 1; + if ((unsigned char)s[i] < 32) continue; + if ((unsigned char)s[i] >= 127) { + if ((rl = mbtowc(&wc, s + i, slen - i < 4 ? slen - i : 4)) <= 0) + break; + if ((w = wcwidth(wc)) == -1) + continue; + } if (col + w > len || (col + w == len && s[i + rl])) { fputs("\xe2\x80\xa6", fp); col++; -- cgit v1.2.3