From 9575fe628f302a4f89efd99cfeadb0b66db80555 Mon Sep 17 00:00:00 2001 From: deadprogram Date: Fri, 14 Aug 2020 22:21:04 +0200 Subject: [PATCH] internal/bytealg: naive attempt to copy the main Go 1.15 implementatation Signed-off-by: deadprogram --- src/internal/bytealg/bytealg.go | 127 ++++++++++++++++++++++++++++++++ 1 file changed, 127 insertions(+) diff --git a/src/internal/bytealg/bytealg.go b/src/internal/bytealg/bytealg.go index f52b507b..0169fbbc 100644 --- a/src/internal/bytealg/bytealg.go +++ b/src/internal/bytealg/bytealg.go @@ -124,3 +124,130 @@ func IndexString(str, sub string) int { } return -1 } + +// Copyright 2020 The Go Authors. All rights reserved. +// Use of this source code is governed by a BSD-style +// license that can be found in the LICENSE file. + +// The following code has been copied from the Go 1.15 release tree. + +// PrimeRK is the prime base used in Rabin-Karp algorithm. +const PrimeRK = 16777619 + +// HashStrBytes returns the hash and the appropriate multiplicative +// factor for use in Rabin-Karp algorithm. +func HashStrBytes(sep []byte) (uint32, uint32) { + hash := uint32(0) + for i := 0; i < len(sep); i++ { + hash = hash*PrimeRK + uint32(sep[i]) + } + var pow, sq uint32 = 1, PrimeRK + for i := len(sep); i > 0; i >>= 1 { + if i&1 != 0 { + pow *= sq + } + sq *= sq + } + return hash, pow +} + +// HashStr returns the hash and the appropriate multiplicative +// factor for use in Rabin-Karp algorithm. +func HashStr(sep string) (uint32, uint32) { + hash := uint32(0) + for i := 0; i < len(sep); i++ { + hash = hash*PrimeRK + uint32(sep[i]) + } + var pow, sq uint32 = 1, PrimeRK + for i := len(sep); i > 0; i >>= 1 { + if i&1 != 0 { + pow *= sq + } + sq *= sq + } + return hash, pow +} + +// HashStrRevBytes returns the hash of the reverse of sep and the +// appropriate multiplicative factor for use in Rabin-Karp algorithm. +func HashStrRevBytes(sep []byte) (uint32, uint32) { + hash := uint32(0) + for i := len(sep) - 1; i >= 0; i-- { + hash = hash*PrimeRK + uint32(sep[i]) + } + var pow, sq uint32 = 1, PrimeRK + for i := len(sep); i > 0; i >>= 1 { + if i&1 != 0 { + pow *= sq + } + sq *= sq + } + return hash, pow +} + +// HashStrRev returns the hash of the reverse of sep and the +// appropriate multiplicative factor for use in Rabin-Karp algorithm. +func HashStrRev(sep string) (uint32, uint32) { + hash := uint32(0) + for i := len(sep) - 1; i >= 0; i-- { + hash = hash*PrimeRK + uint32(sep[i]) + } + var pow, sq uint32 = 1, PrimeRK + for i := len(sep); i > 0; i >>= 1 { + if i&1 != 0 { + pow *= sq + } + sq *= sq + } + return hash, pow +} + +// IndexRabinKarpBytes uses the Rabin-Karp search algorithm to return the index of the +// first occurence of substr in s, or -1 if not present. +func IndexRabinKarpBytes(s, sep []byte) int { + // Rabin-Karp search + hashsep, pow := HashStrBytes(sep) + n := len(sep) + var h uint32 + for i := 0; i < n; i++ { + h = h*PrimeRK + uint32(s[i]) + } + if h == hashsep && Equal(s[:n], sep) { + return 0 + } + for i := n; i < len(s); { + h *= PrimeRK + h += uint32(s[i]) + h -= pow * uint32(s[i-n]) + i++ + if h == hashsep && Equal(s[i-n:i], sep) { + return i - n + } + } + return -1 +} + +// IndexRabinKarp uses the Rabin-Karp search algorithm to return the index of the +// first occurence of substr in s, or -1 if not present. +func IndexRabinKarp(s, substr string) int { + // Rabin-Karp search + hashss, pow := HashStr(substr) + n := len(substr) + var h uint32 + for i := 0; i < n; i++ { + h = h*PrimeRK + uint32(s[i]) + } + if h == hashss && s[:n] == substr { + return 0 + } + for i := n; i < len(s); { + h *= PrimeRK + h += uint32(s[i]) + h -= pow * uint32(s[i-n]) + i++ + if h == hashss && s[i-n:i] == substr { + return i - n + } + } + return -1 +}