From: Jes Cok Date: Tue, 31 Oct 2023 18:34:07 +0000 (+0000) Subject: bytes,internal/bytealg: add func bytealg.LastIndexRabinKarp X-Git-Tag: go1.22rc1~462 X-Git-Url: http://www.git.cypherpunks.su/?a=commitdiff_plain;h=a05a25cb19d1ea222e37e7172fe489d972c0ec67;p=gostls13.git bytes,internal/bytealg: add func bytealg.LastIndexRabinKarp Also rename 'substr' to 'sep' in IndexRabinKarp for consistency. Change-Id: Icc2ad1116aecaf002c8264daa2fa608306c9a88a GitHub-Last-Rev: 1784b93f53d569991f86585f9011120ea26f193f GitHub-Pull-Request: golang/go#63854 Reviewed-on: https://go-review.googlesource.com/c/go/+/538716 Reviewed-by: Keith Randall Auto-Submit: Keith Randall LUCI-TryBot-Result: Go LUCI Reviewed-by: David Chase Reviewed-by: Keith Randall --- diff --git a/src/bytes/bytes.go b/src/bytes/bytes.go index c84accd8f5..0679b43a20 100644 --- a/src/bytes/bytes.go +++ b/src/bytes/bytes.go @@ -121,25 +121,7 @@ func LastIndex(s, sep []byte) int { case n > len(s): return -1 } - // Rabin-Karp search from the end of the string - hashss, pow := bytealg.HashStrRev(sep) - last := len(s) - n - var h uint32 - for i := len(s) - 1; i >= last; i-- { - h = h*bytealg.PrimeRK + uint32(s[i]) - } - if h == hashss && Equal(s[last:], sep) { - return last - } - for i := last - 1; i >= 0; i-- { - h *= bytealg.PrimeRK - h += uint32(s[i]) - h -= pow * uint32(s[i+n]) - if h == hashss && Equal(s[i:i+n], sep) { - return i - } - } - return -1 + return bytealg.LastIndexRabinKarp(s, sep) } // LastIndexByte returns the index of the last instance of c in s, or -1 if c is not present in s. diff --git a/src/internal/bytealg/bytealg.go b/src/internal/bytealg/bytealg.go index 92be8ea79b..1103891eee 100644 --- a/src/internal/bytealg/bytealg.go +++ b/src/internal/bytealg/bytealg.go @@ -62,16 +62,16 @@ func HashStrRev[T string | []byte](sep T) (uint32, uint32) { } // IndexRabinKarp uses the Rabin-Karp search algorithm to return the index of the -// first occurrence of substr in s, or -1 if not present. -func IndexRabinKarp[T string | []byte](s, substr T) int { +// first occurrence of sep in s, or -1 if not present. +func IndexRabinKarp[T string | []byte](s, sep T) int { // Rabin-Karp search - hashss, pow := HashStr(substr) - n := len(substr) + hashss, pow := HashStr(sep) + n := len(sep) var h uint32 for i := 0; i < n; i++ { h = h*PrimeRK + uint32(s[i]) } - if h == hashss && string(s[:n]) == string(substr) { + if h == hashss && string(s[:n]) == string(sep) { return 0 } for i := n; i < len(s); { @@ -79,13 +79,38 @@ func IndexRabinKarp[T string | []byte](s, substr T) int { h += uint32(s[i]) h -= pow * uint32(s[i-n]) i++ - if h == hashss && string(s[i-n:i]) == string(substr) { + if h == hashss && string(s[i-n:i]) == string(sep) { return i - n } } return -1 } +// LastIndexRabinKarp uses the Rabin-Karp search algorithm to return the last index of the +// occurrence of sep in s, or -1 if not present. +func LastIndexRabinKarp[T string | []byte](s, sep T) int { + // Rabin-Karp search from the end of the string + hashss, pow := HashStrRev(sep) + n := len(sep) + last := len(s) - n + var h uint32 + for i := len(s) - 1; i >= last; i-- { + h = h*PrimeRK + uint32(s[i]) + } + if h == hashss && string(s[last:]) == string(sep) { + return last + } + for i := last - 1; i >= 0; i-- { + h *= PrimeRK + h += uint32(s[i]) + h -= pow * uint32(s[i+n]) + if h == hashss && string(s[i:i+n]) == string(sep) { + return i + } + } + return -1 +} + // MakeNoZero makes a slice of length and capacity n without zeroing the bytes. // It is the caller's responsibility to ensure uninitialized bytes // do not leak to the end user.