mirror of
https://github.com/golang/go.git
synced 2025-12-08 06:10:04 +00:00
regexp: speedups
MatchEasy0_1K 500000 4207 ns/op 243.35 MB/s MatchEasy0_1K_Old 500000 4625 ns/op 221.40 MB/s MatchEasy0_1M 500 3948932 ns/op 265.53 MB/s MatchEasy0_1M_Old 500 3943926 ns/op 265.87 MB/s MatchEasy0_32K 10000 122974 ns/op 266.46 MB/s MatchEasy0_32K_Old 10000 123270 ns/op 265.82 MB/s MatchEasy0_32M 10 127265400 ns/op 263.66 MB/s MatchEasy0_32M_Old 10 127123500 ns/op 263.95 MB/s MatchEasy1_1K 500000 5637 ns/op 181.63 MB/s MatchEasy1_1K_Old 10000 100690 ns/op 10.17 MB/s MatchEasy1_1M 200 7683150 ns/op 136.48 MB/s MatchEasy1_1M_Old 10 145774000 ns/op 7.19 MB/s MatchEasy1_32K 10000 239887 ns/op 136.60 MB/s MatchEasy1_32K_Old 500 4508182 ns/op 7.27 MB/s MatchEasy1_32M 10 247103500 ns/op 135.79 MB/s MatchEasy1_32M_Old 1 4660191000 ns/op 7.20 MB/s MatchMedium_1K 10000 160567 ns/op 6.38 MB/s MatchMedium_1K_Old 10000 158367 ns/op 6.47 MB/s MatchMedium_1M 10 162928000 ns/op 6.44 MB/s MatchMedium_1M_Old 10 159699200 ns/op 6.57 MB/s MatchMedium_32K 500 5090758 ns/op 6.44 MB/s MatchMedium_32K_Old 500 5005800 ns/op 6.55 MB/s MatchMedium_32M 1 5233973000 ns/op 6.41 MB/s MatchMedium_32M_Old 1 5109676000 ns/op 6.57 MB/s MatchHard_1K 10000 249087 ns/op 4.11 MB/s MatchHard_1K_Old 5000 364569 ns/op 2.81 MB/s MatchHard_1M 5 256050000 ns/op 4.10 MB/s MatchHard_1M_Old 5 372446400 ns/op 2.82 MB/s MatchHard_32K 200 7944525 ns/op 4.12 MB/s MatchHard_32K_Old 100 11609380 ns/op 2.82 MB/s MatchHard_32M 1 8144503000 ns/op 4.12 MB/s MatchHard_32M_Old 1 11885434000 ns/op 2.82 MB/s R=r, bradfitz CC=golang-dev https://golang.org/cl/5134049
This commit is contained in:
Russ Cox
parent
76ea456e45
commit
8f699a3fb9
6 changed files with 191 additions and 42 deletions
|
|
@ -50,6 +50,13 @@ func progMachine(p *syntax.Prog) *machine {
|
|||
return m
|
||||
}
|
||||
|
||||
func (m *machine) init(ncap int) {
|
||||
for _, t := range m.pool {
|
||||
t.cap = t.cap[:ncap]
|
||||
}
|
||||
m.matchcap = m.matchcap[:ncap]
|
||||
}
|
||||
|
||||
// alloc allocates a new thread with the given instruction.
|
||||
// It uses the free pool if possible.
|
||||
func (m *machine) alloc(i *syntax.Inst) *thread {
|
||||
|
|
@ -59,9 +66,8 @@ func (m *machine) alloc(i *syntax.Inst) *thread {
|
|||
m.pool = m.pool[:n-1]
|
||||
} else {
|
||||
t = new(thread)
|
||||
t.cap = make([]int, cap(m.matchcap))
|
||||
t.cap = make([]int, len(m.matchcap), cap(m.matchcap))
|
||||
}
|
||||
t.cap = t.cap[:len(m.matchcap)]
|
||||
t.inst = i
|
||||
return t
|
||||
}
|
||||
|
|
@ -121,7 +127,7 @@ func (m *machine) match(i input, pos int) bool {
|
|||
if len(m.matchcap) > 0 {
|
||||
m.matchcap[0] = pos
|
||||
}
|
||||
m.add(runq, uint32(m.p.Start), pos, m.matchcap, flag)
|
||||
m.add(runq, uint32(m.p.Start), pos, m.matchcap, flag, nil)
|
||||
}
|
||||
flag = syntax.EmptyOpContext(rune, rune1)
|
||||
m.step(runq, nextq, pos, pos+width, rune, flag)
|
||||
|
|
@ -148,7 +154,8 @@ func (m *machine) match(i input, pos int) bool {
|
|||
func (m *machine) clear(q *queue) {
|
||||
for _, d := range q.dense {
|
||||
if d.t != nil {
|
||||
m.free(d.t)
|
||||
// m.free(d.t)
|
||||
m.pool = append(m.pool, d.t)
|
||||
}
|
||||
}
|
||||
q.dense = q.dense[:0]
|
||||
|
|
@ -168,10 +175,12 @@ func (m *machine) step(runq, nextq *queue, pos, nextPos, c int, nextCond syntax.
|
|||
continue
|
||||
}
|
||||
if longest && m.matched && len(t.cap) > 0 && m.matchcap[0] < t.cap[0] {
|
||||
m.free(t)
|
||||
// m.free(t)
|
||||
m.pool = append(m.pool, t)
|
||||
continue
|
||||
}
|
||||
i := t.inst
|
||||
add := false
|
||||
switch i.Op {
|
||||
default:
|
||||
panic("bad inst")
|
||||
|
|
@ -185,7 +194,8 @@ func (m *machine) step(runq, nextq *queue, pos, nextPos, c int, nextCond syntax.
|
|||
// First-match mode: cut off all lower-priority threads.
|
||||
for _, d := range runq.dense[j+1:] {
|
||||
if d.t != nil {
|
||||
m.free(d.t)
|
||||
// m.free(d.t)
|
||||
m.pool = append(m.pool, d.t)
|
||||
}
|
||||
}
|
||||
runq.dense = runq.dense[:0]
|
||||
|
|
@ -193,11 +203,21 @@ func (m *machine) step(runq, nextq *queue, pos, nextPos, c int, nextCond syntax.
|
|||
m.matched = true
|
||||
|
||||
case syntax.InstRune:
|
||||
if i.MatchRune(c) {
|
||||
m.add(nextq, i.Out, nextPos, t.cap, nextCond)
|
||||
}
|
||||
add = i.MatchRune(c)
|
||||
case syntax.InstRune1:
|
||||
add = c == i.Rune[0]
|
||||
case syntax.InstRuneAny:
|
||||
add = true
|
||||
case syntax.InstRuneAnyNotNL:
|
||||
add = c != '\n'
|
||||
}
|
||||
if add {
|
||||
t = m.add(nextq, i.Out, nextPos, t.cap, nextCond, t)
|
||||
}
|
||||
if t != nil {
|
||||
// m.free(t)
|
||||
m.pool = append(m.pool, t)
|
||||
}
|
||||
m.free(t)
|
||||
}
|
||||
runq.dense = runq.dense[:0]
|
||||
}
|
||||
|
|
@ -206,12 +226,12 @@ func (m *machine) step(runq, nextq *queue, pos, nextPos, c int, nextCond syntax.
|
|||
// It also recursively adds an entry for all instructions reachable from pc by following
|
||||
// empty-width conditions satisfied by cond. pos gives the current position
|
||||
// in the input.
|
||||
func (m *machine) add(q *queue, pc uint32, pos int, cap []int, cond syntax.EmptyOp) {
|
||||
func (m *machine) add(q *queue, pc uint32, pos int, cap []int, cond syntax.EmptyOp, t *thread) *thread {
|
||||
if pc == 0 {
|
||||
return
|
||||
return t
|
||||
}
|
||||
if j := q.sparse[pc]; j < uint32(len(q.dense)) && q.dense[j].pc == pc {
|
||||
return
|
||||
return t
|
||||
}
|
||||
|
||||
j := len(q.dense)
|
||||
|
|
@ -228,30 +248,36 @@ func (m *machine) add(q *queue, pc uint32, pos int, cap []int, cond syntax.Empty
|
|||
case syntax.InstFail:
|
||||
// nothing
|
||||
case syntax.InstAlt, syntax.InstAltMatch:
|
||||
m.add(q, i.Out, pos, cap, cond)
|
||||
m.add(q, i.Arg, pos, cap, cond)
|
||||
t = m.add(q, i.Out, pos, cap, cond, t)
|
||||
t = m.add(q, i.Arg, pos, cap, cond, t)
|
||||
case syntax.InstEmptyWidth:
|
||||
if syntax.EmptyOp(i.Arg)&^cond == 0 {
|
||||
m.add(q, i.Out, pos, cap, cond)
|
||||
t = m.add(q, i.Out, pos, cap, cond, t)
|
||||
}
|
||||
case syntax.InstNop:
|
||||
m.add(q, i.Out, pos, cap, cond)
|
||||
t = m.add(q, i.Out, pos, cap, cond, t)
|
||||
case syntax.InstCapture:
|
||||
if int(i.Arg) < len(cap) {
|
||||
opos := cap[i.Arg]
|
||||
cap[i.Arg] = pos
|
||||
m.add(q, i.Out, pos, cap, cond)
|
||||
m.add(q, i.Out, pos, cap, cond, nil)
|
||||
cap[i.Arg] = opos
|
||||
} else {
|
||||
m.add(q, i.Out, pos, cap, cond)
|
||||
t = m.add(q, i.Out, pos, cap, cond, t)
|
||||
}
|
||||
case syntax.InstMatch, syntax.InstRune:
|
||||
t := m.alloc(i)
|
||||
if len(t.cap) > 0 {
|
||||
case syntax.InstMatch, syntax.InstRune, syntax.InstRune1, syntax.InstRuneAny, syntax.InstRuneAnyNotNL:
|
||||
if t == nil {
|
||||
t = m.alloc(i)
|
||||
} else {
|
||||
t.inst = i
|
||||
}
|
||||
if len(cap) > 0 && &t.cap[0] != &cap[0] {
|
||||
copy(t.cap, cap)
|
||||
}
|
||||
d.t = t
|
||||
t = nil
|
||||
}
|
||||
return t
|
||||
}
|
||||
|
||||
// empty is a non-nil 0-element slice,
|
||||
|
|
@ -263,7 +289,7 @@ var empty = make([]int, 0)
|
|||
// the position of its subexpressions.
|
||||
func (re *Regexp) doExecute(i input, pos int, ncap int) []int {
|
||||
m := re.get()
|
||||
m.matchcap = m.matchcap[:ncap]
|
||||
m.init(ncap)
|
||||
if !m.match(i, pos) {
|
||||
re.put(m)
|
||||
return nil
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue