collate: make Collator.Compare and CompareString goroutine-safe

collate/collate.go

@@ -20,17 +20,13 @@ import (
 
 // Collator provides functionality for comparing strings for a given
 // collation order.
+//
+// A Collator is safe for concurrent use by multiple goroutines after
+// construction. Compare and CompareString use goroutine-local state only.
 type Collator struct {
 	options
 
 	sorter sorter
-
-	_iter [2]iter
-}
-
-func (c *Collator) iter(i int) *iter {
-	// TODO: evaluate performance for making the second iterator optional.
-	return &c._iter[i]
 }
 
 // Supported returns the list of languages for which collating differs from its parent.
@@ -79,8 +75,6 @@ func (c *Collator) init() {
 	if c.numeric {
 		c.t = colltab.NewNumericWeighter(c.t)
 	}
-	c._iter[0].init(c)
-	c._iter[1].init(c)
 }
 
 // Buffer holds keys generated by Key and KeyString.
@@ -102,12 +96,16 @@ func (b *Buffer) Reset() {
 
 // Compare returns an integer comparing the two byte slices.
 // The result will be 0 if a==b, -1 if a < b, and +1 if a > b.
+// Compare is safe for concurrent use by multiple goroutines.
 func (c *Collator) Compare(a, b []byte) int {
 	// TODO: skip identical prefixes once we have a fast way to detect if a rune is
 	// part of a contraction. This would lead to roughly a 10% speedup for the colcmp regtest.
-	c.iter(0).SetInput(a)
-	c.iter(1).SetInput(b)
-	if res := c.compare(); res != 0 {
+	var ia, ib iter
+	ia.init(c)
+	ib.init(c)
+	ia.SetInput(a)
+	ib.SetInput(b)
+	if res := c.compareIters(&ia, &ib); res != 0 {
 		return res
 	}
 	if !c.ignore[colltab.Identity] {
@@ -118,12 +116,16 @@ func (c *Collator) Compare(a, b []byte) int {
 
 // CompareString returns an integer comparing the two strings.
 // The result will be 0 if a==b, -1 if a < b, and +1 if a > b.
+// CompareString is safe for concurrent use by multiple goroutines.
 func (c *Collator) CompareString(a, b string) int {
 	// TODO: skip identical prefixes once we have a fast way to detect if a rune is
 	// part of a contraction. This would lead to roughly a 10% speedup for the colcmp regtest.
-	c.iter(0).SetInputString(a)
-	c.iter(1).SetInputString(b)
-	if res := c.compare(); res != 0 {
+	var ia, ib iter
+	ia.init(c)
+	ib.init(c)
+	ia.SetInputString(a)
+	ib.SetInputString(b)
+	if res := c.compareIters(&ia, &ib); res != 0 {
 		return res
 	}
 	if !c.ignore[colltab.Identity] {
@@ -154,8 +156,7 @@ func compareLevel(f func(i *iter) int, a, b *iter) int {
 	return 0
 }
 
-func (c *Collator) compare() int {
-	ia, ib := c.iter(0), c.iter(1)
+func (c *Collator) compareIters(ia, ib *iter) int {
 	// Process primary level
 	if c.alternate != altShifted {
 		// TODO: implement script reordering
@@ -216,22 +217,27 @@ func (c *Collator) key(buf *Buffer, w []colltab.Elem) []byte {
 }
 
 func (c *Collator) getColElems(str []byte) []colltab.Elem {
-	i := c.iter(0)
+	var i iter
+	i.init(c)
 	i.SetInput(str)
 	for i.Next() {
 	}
 	return i.Elems
 }
 
 func (c *Collator) getColElemsString(str string) []colltab.Elem {
-	i := c.iter(0)
+	var i iter
+	i.init(c)
 	i.SetInputString(str)
 	for i.Next() {
 	}
 	return i.Elems
 }
 
 type iter struct {
+	// wa is the goroutine-local scratch buffer for collation elements.
+	// 512 slots avoid heap fallback for virtually all real-world strings;
+	// the CPU only touches as many cache lines as the comparison actually needs.
 	wa [512]colltab.Elem
 
 	colltab.Iter

go.mod

@@ -1,6 +1,6 @@
 module golang.org/x/text
 
-go 1.25.0
+go 1.24.0
 
 require golang.org/x/tools v0.41.0 // tagx:ignore