Created
August 2, 2020 06:08
-
-
Save nitely/3063868bede57b0c9fb5305242a6a6e7 to your computer and use it in GitHub Desktop.
Fast find for Rune / Unicode / utf-8 in Nim
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from strutils import find | |
from unicode import Rune | |
# XXX do a simpler find when vm (or no memchr available), | |
# since this is only fast due to memchr | |
# untested | |
func find*(s: string, r: Rune, start: Natural = 0): int = | |
if r.ord < 0xff: | |
return find(s, r.char, start) | |
let c = (r.ord and 0xff).char | |
let rsize = r.size() | |
var i = start+rsize-1 | |
var r2 = 0'u32 | |
doAssert rsize >= 1 and rsize <= 4 | |
while i < len(s): | |
i = find(s, c, i) | |
if i == -1: | |
return -1 | |
for j in i-rsize-1 .. i: | |
r2 = (r2 shl 8) or s[j].uint32 | |
if r.uint32 == r2: | |
return i-rsize-1 | |
r2 = 0 | |
inc i | |
return -1 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment