From: Rob Pike <r@golang.org>
Date: Sun, 15 May 2022 03:14:49 +0000 (+1000)
Subject: text/template/parse: make atTerminator more efficient
X-Git-Tag: go1.19beta1~224
X-Git-Url: http://www.git.cypherpunks.su/?a=commitdiff_plain;h=053b63cfb56f574fd216166020066f3b48d5d878;p=gostls13.git

text/template/parse: make atTerminator more efficient

The change https://go.dev/cl/398475 was too complicated and expensive.
Since the whole string is always available, all that's needed
is a call to strings.HasPrefix.

While we're here, change the way lexer.backup works
so it can be called repeatedly to back up more than one
rune, in case that becomes necessary. This change also
requires less state to maintain, as lexer.width was only
there for backup, and prevented multiple steps.

Fixes #52191

Change-Id: I43b64fc66edeb8ba73ba5aa72f3b727c377dc067
Reviewed-on: https://go-review.googlesource.com/c/go/+/406476
Reviewed-by: Daniel Martí <mvdan@mvdan.cc>
Reviewed-by: Dmitri Shuralyov <dmitshur@google.com>
Run-TryBot: Rob Pike <r@golang.org>
TryBot-Result: Gopher Robot <gobot@golang.org>
Reviewed-by: Ian Lance Taylor <iant@google.com>
---

diff --git a/src/text/template/parse/lex.go b/src/text/template/parse/lex.go
index 078f714ccf..4c32d261f2 100644
--- a/src/text/template/parse/lex.go
+++ b/src/text/template/parse/lex.go
@@ -118,7 +118,7 @@ type lexer struct {
 	emitComment bool      // emit itemComment tokens.
 	pos         Pos       // current position in the input
 	start       Pos       // start position of this item
-	width       Pos       // width of last rune read from input
+	atEOF       bool      // we have hit the end of input and returned eof
 	items       chan item // channel of scanned items
 	parenDepth  int       // nesting depth of ( ) exprs
 	line        int       // 1+number of newlines seen
@@ -130,12 +130,11 @@ type lexer struct {
 // next returns the next rune in the input.
 func (l *lexer) next() rune {
 	if int(l.pos) >= len(l.input) {
-		l.width = 0
+		l.atEOF = true
 		return eof
 	}
 	r, w := utf8.DecodeRuneInString(l.input[l.pos:])
-	l.width = Pos(w)
-	l.pos += l.width
+	l.pos += Pos(w)
 	if r == '\n' {
 		l.line++
 	}
@@ -149,12 +148,15 @@ func (l *lexer) peek() rune {
 	return r
 }
 
-// backup steps back one rune. Can only be called once per call of next.
+// backup steps back one rune.
 func (l *lexer) backup() {
-	l.pos -= l.width
-	// Correct newline count.
-	if l.width == 1 && l.input[l.pos] == '\n' {
-		l.line--
+	if !l.atEOF && l.pos > 0 {
+		r, w := utf8.DecodeLastRuneInString(l.input[:l.pos])
+		l.pos -= Pos(w)
+		// Correct newline count.
+		if r == '\n' {
+			l.line--
+		}
 	}
 }
 
@@ -249,7 +251,6 @@ const (
 
 // lexText scans until an opening action delimiter, "{{".
 func lexText(l *lexer) stateFn {
-	l.width = 0
 	if x := strings.Index(l.input[l.pos:], l.leftDelim); x >= 0 {
 		ldn := Pos(len(l.leftDelim))
 		l.pos += Pos(x)
@@ -541,25 +542,7 @@ func (l *lexer) atTerminator() bool {
 	case eof, '.', ',', '|', ':', ')', '(':
 		return true
 	}
-	// Are we at a right delimiter? TODO: This is harder than it should be
-	// because lookahead is only one rune.
-	rightDelim := l.rightDelim
-	defer func(pos Pos, line int) {
-		l.pos = pos
-		l.line = line
-	}(l.pos, l.line)
-	for len(rightDelim) > 0 {
-		rNext := l.next()
-		if rNext == eof {
-			return false
-		}
-		rDelim, size := utf8.DecodeRuneInString(rightDelim)
-		if rNext != rDelim {
-			return false
-		}
-		rightDelim = rightDelim[size:]
-	}
-	return true
+	return strings.HasPrefix(l.input[l.pos:], l.rightDelim)
 }
 
 // lexChar scans a character constant. The initial quote is already