bytes, strings: add Lines, SplitSeq, SplitAfterSeq, FieldsSeq, FieldsFuncSeq

Fixes #61901.

Change-Id: I4db21c91fd21079f2aa3bc81fb03dd6f40423a38
GitHub-Last-Rev: ed3df56
GitHub-Pull-Request: #67543
Reviewed-on: https://go-review.googlesource.com/c/go/+/587095
Auto-Submit: Ian Lance Taylor <[email protected]>
LUCI-TryBot-Result: Go LUCI <[email protected]>
Reviewed-by: Carlos Amedee <[email protected]>
Reviewed-by: Ian Lance Taylor <[email protected]>

Author: aimuz

api/next/61901.txt

@@ -0,0 +1,10 @@
+pkg bytes, func FieldsFuncSeq([]uint8, func(int32) bool) iter.Seq[[]uint8] #61901
+pkg bytes, func FieldsSeq([]uint8) iter.Seq[[]uint8] #61901
+pkg bytes, func Lines([]uint8) iter.Seq[[]uint8] #61901
+pkg bytes, func SplitAfterSeq([]uint8, []uint8) iter.Seq[[]uint8] #61901
+pkg bytes, func SplitSeq([]uint8, []uint8) iter.Seq[[]uint8] #61901
+pkg strings, func FieldsFuncSeq(string, func(int32) bool) iter.Seq[string] #61901
+pkg strings, func FieldsSeq(string) iter.Seq[string] #61901
+pkg strings, func Lines(string) iter.Seq[string] #61901
+pkg strings, func SplitAfterSeq(string, string) iter.Seq[string] #61901
+pkg strings, func SplitSeq(string, string) iter.Seq[string] #61901

doc/next/6-stdlib/99-minor/bytes/61901.md

@@ -0,0 +1,12 @@
+The [bytes] package adds several functions that work with iterators:
+- [Lines] returns an iterator over the
+  newline-terminated lines in the byte slice s.
+- [SplitSeq] returns an iterator over
+  all substrings of s separated by sep.
+- [SplitAfterSeq] returns an iterator
+  over substrings of s split after each instance of sep.
+- [FieldsSeq] returns an iterator over
+  substrings of s split around runs of whitespace characters,
+  as defined by unicode.IsSpace.
+- [FieldsFuncSeq] returns an iterator
+  over substrings of s split around runs of Unicode code points satisfying f(c).

doc/next/6-stdlib/99-minor/strings/61901.md

@@ -0,0 +1,12 @@
+The [strings] package adds several functions that work with iterators:
+- [Lines] returns an iterator over
+  the newline-terminated lines in the string s.
+- [SplitSeq] returns an iterator over
+  all substrings of s separated by sep.
+- [SplitAfterSeq] returns an iterator
+  over substrings of s split after each instance of sep.
+- [FieldsSeq] returns an iterator over
+  substrings of s split around runs of whitespace characters,
+  as defined by unicode.IsSpace.
+- [FieldsFuncSeq] returns an iterator
+  over substrings of s split around runs of Unicode code points satisfying f(c).

src/bytes/bytes_test.go

@@ -8,6 +8,7 @@ import (
 	. "bytes"
 	"fmt"
 	"internal/testenv"
+	"iter"
 	"math"
 	"math/rand"
 	"slices"
@@ -26,6 +27,37 @@ func sliceOfString(s [][]byte) []string {
 	return result
 }
 
+func collect(t *testing.T, seq iter.Seq[[]byte]) [][]byte {
+	out := slices.Collect(seq)
+	out1 := slices.Collect(seq)
+	if !slices.Equal(sliceOfString(out), sliceOfString(out1)) {
+		t.Fatalf("inconsistent seq:\n%s\n%s", out, out1)
+	}
+	return out
+}
+
+type LinesTest struct {
+	a string
+	b []string
+}
+
+var linesTests = []LinesTest{
+	{a: "abc\nabc\n", b: []string{"abc\n", "abc\n"}},
+	{a: "abc\r\nabc", b: []string{"abc\r\n", "abc"}},
+	{a: "abc\r\n", b: []string{"abc\r\n"}},
+	{a: "\nabc", b: []string{"\n", "abc"}},
+	{a: "\nabc\n\n", b: []string{"\n", "abc\n", "\n"}},
+}
+
+func TestLines(t *testing.T) {
+	for _, s := range linesTests {
+		result := sliceOfString(slices.Collect(Lines([]byte(s.a))))
+		if !slices.Equal(result, s.b) {
+			t.Errorf(`slices.Collect(Lines(%q)) = %q; want %q`, s.a, result, s.b)
+		}
+	}
+}
+
 // For ease of reading, the test cases use strings that are converted to byte
 // slices before invoking the functions.
 
@@ -800,6 +832,14 @@ func TestSplit(t *testing.T) {
 			t.Errorf(`Split(%q, %q, %d) = %v; want %v`, tt.s, tt.sep, tt.n, result, tt.a)
 			continue
 		}
+
+		if tt.n < 0 {
+			b := sliceOfString(slices.Collect(SplitSeq([]byte(tt.s), []byte(tt.sep))))
+			if !slices.Equal(b, tt.a) {
+				t.Errorf(`collect(SplitSeq(%q, %q)) = %v; want %v`, tt.s, tt.sep, b, tt.a)
+			}
+		}
+
 		if tt.n == 0 || len(a) == 0 {
 			continue
 		}
@@ -859,6 +899,13 @@ func TestSplitAfter(t *testing.T) {
 			continue
 		}
 
+		if tt.n < 0 {
+			b := sliceOfString(slices.Collect(SplitAfterSeq([]byte(tt.s), []byte(tt.sep))))
+			if !slices.Equal(b, tt.a) {
+				t.Errorf(`collect(SplitAfterSeq(%q, %q)) = %v; want %v`, tt.s, tt.sep, b, tt.a)
+			}
+		}
+
 		if want := tt.a[len(tt.a)-1] + "z"; string(x) != want {
 			t.Errorf("last appended result was %s; want %s", x, want)
 		}
@@ -912,6 +959,11 @@ func TestFields(t *testing.T) {
 			continue
 		}
 
+		result2 := sliceOfString(collect(t, FieldsSeq([]byte(tt.s))))
+		if !slices.Equal(result2, tt.a) {
+			t.Errorf(`collect(FieldsSeq(%q)) = %v; want %v`, tt.s, result2, tt.a)
+		}
+
 		if string(b) != tt.s {
 			t.Errorf("slice changed to %s; want %s", string(b), tt.s)
 		}
@@ -954,6 +1006,11 @@ func TestFieldsFunc(t *testing.T) {
 			t.Errorf("FieldsFunc(%q) = %v, want %v", tt.s, a, tt.a)
 		}
 
+		result2 := sliceOfString(collect(t, FieldsFuncSeq([]byte(tt.s), pred)))
+		if !slices.Equal(result2, tt.a) {
+			t.Errorf(`collect(FieldsFuncSeq(%q)) = %v; want %v`, tt.s, result2, tt.a)
+		}
+
 		if string(b) != tt.s {
 			t.Errorf("slice changed to %s; want %s", b, tt.s)
 		}

src/bytes/iter.go

@@ -0,0 +1,148 @@
+// Copyright 2024 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.
+
+package bytes
+
+import (
+	"iter"
+	"unicode"
+	"unicode/utf8"
+)
+
+// Lines returns an iterator over the newline-terminated lines in the byte slice s.
+// The lines yielded by the iterator include their terminating newlines.
+// If s is empty, the iterator yields no lines at all.
+// If s does not end in a newline, the final yielded line will not end in a newline.
+// It returns a single-use iterator.
+func Lines(s []byte) iter.Seq[[]byte] {
+	return func(yield func([]byte) bool) {
+		for len(s) > 0 {
+			var line []byte
+			if i := IndexByte(s, '\n'); i >= 0 {
+				line, s = s[:i+1], s[i+1:]
+			} else {
+				line, s = s, nil
+			}
+			if !yield(line[:len(line):len(line)]) {
+				return
+			}
+		}
+		return
+	}
+}
+
+// explodeSeq returns an iterator over the runes in s.
+func explodeSeq(s []byte) iter.Seq[[]byte] {
+	return func(yield func([]byte) bool) {
+		for len(s) > 0 {
+			_, size := utf8.DecodeRune(s)
+			if !yield(s[:size:size]) {
+				return
+			}
+			s = s[size:]
+		}
+	}
+}
+
+// splitSeq is SplitSeq or SplitAfterSeq, configured by how many
+// bytes of sep to include in the results (none or all).
+func splitSeq(s, sep []byte, sepSave int) iter.Seq[[]byte] {
+	if len(sep) == 0 {
+		return explodeSeq(s)
+	}
+	return func(yield func([]byte) bool) {
+		for {
+			i := Index(s, sep)
+			if i < 0 {
+				break
+			}
+			frag := s[:i+sepSave]
+			if !yield(frag[:len(frag):len(frag)]) {
+				return
+			}
+			s = s[i+len(sep):]
+		}
+		yield(s[:len(s):len(s)])
+	}
+}
+
+// SplitSeq returns an iterator over all substrings of s separated by sep.
+// The iterator yields the same strings that would be returned by Split(s, sep),
+// but without constructing the slice.
+// It returns a single-use iterator.
+func SplitSeq(s, sep []byte) iter.Seq[[]byte] {
+	return splitSeq(s, sep, 0)
+}
+
+// SplitAfterSeq returns an iterator over substrings of s split after each instance of sep.
+// The iterator yields the same strings that would be returned by SplitAfter(s, sep),
+// but without constructing the slice.
+// It returns a single-use iterator.
+func SplitAfterSeq(s, sep []byte) iter.Seq[[]byte] {
+	return splitSeq(s, sep, len(sep))
+}
+
+// FieldsSeq returns an iterator over substrings of s split around runs of
+// whitespace characters, as defined by unicode.IsSpace.
+// The iterator yields the same strings that would be returned by Fields(s),
+// but without constructing the slice.
+func FieldsSeq(s []byte) iter.Seq[[]byte] {
+	return func(yield func([]byte) bool) {
+		start := -1
+		for i := 0; i < len(s); {
+			size := 1
+			r := rune(s[i])
+			isSpace := asciiSpace[s[i]] != 0
+			if r >= utf8.RuneSelf {
+				r, size = utf8.DecodeRune(s[i:])
+				isSpace = unicode.IsSpace(r)
+			}
+			if isSpace {
+				if start >= 0 {
+					if !yield(s[start:i:i]) {
+						return
+					}
+					start = -1
+				}
+			} else if start < 0 {
+				start = i
+			}
+			i += size
+		}
+		if start >= 0 {
+			yield(s[start:len(s):len(s)])
+		}
+	}
+}
+
+// FieldsFuncSeq returns an iterator over substrings of s split around runs of
+// Unicode code points satisfying f(c).
+// The iterator yields the same strings that would be returned by FieldsFunc(s),
+// but without constructing the slice.
+func FieldsFuncSeq(s []byte, f func(rune) bool) iter.Seq[[]byte] {
+	return func(yield func([]byte) bool) {
+		start := -1
+		for i := 0; i < len(s); {
+			size := 1
+			r := rune(s[i])
+			if r >= utf8.RuneSelf {
+				r, size = utf8.DecodeRune(s[i:])
+			}
+			if f(r) {
+				if start >= 0 {
+					if !yield(s[start:i:i]) {
+						return
+					}
+					start = -1
+				}
+			} else if start < 0 {
+				start = i
+			}
+			i += size
+		}
+		if start >= 0 {
+			yield(s[start:len(s):len(s)])
+		}
+	}
+}