Newer
Older
// Copyright 2009 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.
``,
`.`,
`^.$`,
`a`,
`a*`,
`a+`,
`a?`,
`a|b`,
`a*|b*`,
`(a*|b)(c*|d)`,
`[a-z]`,
`[a-abc-c\-\]\[]`,
`[a-z]+`,
`[abc]`,
`[^1234]`,
{`(abc`, ErrUnmatchedLpar},
{`abc)`, ErrUnmatchedRpar},
{`x[a-z`, ErrUnmatchedLbkt},
{`abc]`, ErrUnmatchedRbkt},
{`[z-a]`, ErrBadRange},
{`abc\`, ErrExtraneousBackslash},
{`a**`, ErrBadClosure},
{`a*+`, ErrBadClosure},
{`a??`, ErrBadClosure},
{`\x`, ErrBadBackslash},
func compileTest(t *testing.T, expr string, error error) *Regexp {
t.Error("compiling `", expr, "`; unexpected error: ", err.Error())
compileTest(t, good_re[i], nil)
compileTest(t, bad_re[i].re, bad_re[i].err)
func matchTest(t *testing.T, test *FindTest) {
re := compileTest(t, test.pat, nil)
Rob Pike
committed
if re == nil {
Rob Pike
committed
}
m := re.MatchString(test.text)
if m != (len(test.matches) > 0) {
t.Errorf("MatchString failure on %s: %t should be %t", test, m, len(test.matches) > 0)
}
// now try bytes
m = re.Match([]byte(test.text))
if m != (len(test.matches) > 0) {
t.Errorf("Match failure on %s: %t should be %t", test, m, len(test.matches) > 0)
Rob Pike
committed
}
}
for _, test := range findTests {
matchTest(t, &test)
Rob Pike
committed
}
}
func matchFunctionTest(t *testing.T, test *FindTest) {
m, err := MatchString(test.pat, test.text)
Rob Pike
committed
if err == nil {
return
Rob Pike
committed
}
if m != (len(test.matches) > 0) {
t.Errorf("Match failure on %s: %t should be %t", test, m, len(test.matches) > 0)
Rob Pike
committed
}
}
for _, test := range findTests {
matchFunctionTest(t, &test)
Rob Pike
committed
}
}
pattern, replacement, input, output string
var replaceTests = []ReplaceTest{
// Test empty input and/or replacement, with pattern that matches the empty string.
{"", "", "", ""},
{"", "x", "", "x"},
{"", "", "abc", "abc"},
{"", "x", "abc", "xaxbxcx"},
// Test empty input and/or replacement, with pattern that does not match the empty string.
{"b", "", "", ""},
{"b", "x", "", ""},
{"b", "", "abc", "ac"},
{"b", "x", "abc", "axc"},
{"y", "", "", ""},
{"y", "x", "", ""},
{"y", "", "abc", "abc"},
{"y", "x", "abc", "abc"},
// Multibyte characters -- verify that we don't try to match in the middle
// of a character.
{"[a-c]*", "x", "\u65e5", "x\u65e5x"},
{"[^\u65e5]", "x", "abc\u65e5def", "xxx\u65e5xxx"},
{"^[a-c]*", "x", "abcdabc", "xdabc"},
{"[a-c]*$", "x", "abcdabc", "abcdx"},
{"^[a-c]*$", "x", "abcdabc", "abcdabc"},
{"^[a-c]*", "x", "abc", "x"},
{"[a-c]*$", "x", "abc", "x"},
{"^[a-c]*$", "x", "abc", "x"},
{"^[a-c]*", "x", "dabce", "xdabce"},
{"[a-c]*$", "x", "dabce", "dabcex"},
{"^[a-c]*$", "x", "dabce", "dabce"},
{"^[a-c]*", "x", "", "x"},
{"[a-c]*$", "x", "", "x"},
{"^[a-c]*$", "x", "", "x"},
{"^[a-c]+", "x", "abcdabc", "xdabc"},
{"[a-c]+$", "x", "abcdabc", "abcdx"},
{"^[a-c]+$", "x", "abcdabc", "abcdabc"},
{"^[a-c]+", "x", "abc", "x"},
{"[a-c]+$", "x", "abc", "x"},
{"^[a-c]+$", "x", "abc", "x"},
{"^[a-c]+", "x", "dabce", "dabce"},
{"[a-c]+$", "x", "dabce", "dabce"},
{"^[a-c]+$", "x", "dabce", "dabce"},
{"^[a-c]+", "x", "", ""},
{"[a-c]+$", "x", "", ""},
{"^[a-c]+$", "x", "", ""},
{"abc", "def", "abcdefg", "defdefg"},
{"bc", "BC", "abcbcdcdedef", "aBCBCdcdedef"},
{"abc", "", "abcdabc", "d"},
{"x", "xXx", "xxxXxxx", "xXxxXxxXxXxXxxXxxXx"},
{"abc", "d", "", ""},
{"abc", "d", "abc", "d"},
{".+", "x", "abc", "x"},
{"[a-c]*", "x", "def", "xdxexfx"},
{"[a-c]+", "x", "abcbcdcdedef", "xdxdedef"},
{"[a-c]*", "x", "abcbcdcdedef", "xdxdxexdxexfx"},
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
// Substitutions
{"a+", "($0)", "banana", "b(a)n(a)n(a)"},
{"a+", "(${0})", "banana", "b(a)n(a)n(a)"},
{"a+", "(${0})$0", "banana", "b(a)an(a)an(a)a"},
{"a+", "(${0})$0", "banana", "b(a)an(a)an(a)a"},
{"hello, (.+)", "goodbye, ${1}", "hello, world", "goodbye, world"},
{"hello, (.+)", "goodbye, $1x", "hello, world", "goodbye, "},
{"hello, (.+)", "goodbye, ${1}x", "hello, world", "goodbye, worldx"},
{"hello, (.+)", "<$0><$1><$2><$3>", "hello, world", "<hello, world><world><><>"},
{"hello, (?P<noun>.+)", "goodbye, $noun!", "hello, world", "goodbye, world!"},
{"hello, (?P<noun>.+)", "goodbye, ${noun}", "hello, world", "goodbye, world"},
{"(?P<x>hi)|(?P<x>bye)", "$x$x$x", "hi", "hihihi"},
{"(?P<x>hi)|(?P<x>bye)", "$x$x$x", "bye", "byebyebye"},
{"(?P<x>hi)|(?P<x>bye)", "$xyz", "hi", ""},
{"(?P<x>hi)|(?P<x>bye)", "${x}yz", "hi", "hiyz"},
{"(?P<x>hi)|(?P<x>bye)", "hello $$x", "hi", "hello $x"},
{"a+", "${oops", "aaa", "${oops"},
{"a+", "$$", "aaa", "$"},
{"a+", "$", "aaa", "$"},
}
var replaceLiteralTests = []ReplaceTest{
// Substitutions
{"a+", "($0)", "banana", "b($0)n($0)n($0)"},
{"a+", "(${0})", "banana", "b(${0})n(${0})n(${0})"},
{"a+", "(${0})$0", "banana", "b(${0})$0n(${0})$0n(${0})$0"},
{"a+", "(${0})$0", "banana", "b(${0})$0n(${0})$0n(${0})$0"},
{"hello, (.+)", "goodbye, ${1}", "hello, world", "goodbye, ${1}"},
{"hello, (?P<noun>.+)", "goodbye, $noun!", "hello, world", "goodbye, $noun!"},
{"hello, (?P<noun>.+)", "goodbye, ${noun}", "hello, world", "goodbye, ${noun}"},
{"(?P<x>hi)|(?P<x>bye)", "$x$x$x", "hi", "$x$x$x"},
{"(?P<x>hi)|(?P<x>bye)", "$x$x$x", "bye", "$x$x$x"},
{"(?P<x>hi)|(?P<x>bye)", "$xyz", "hi", "$xyz"},
{"(?P<x>hi)|(?P<x>bye)", "${x}yz", "hi", "${x}yz"},
{"(?P<x>hi)|(?P<x>bye)", "hello $$x", "hi", "hello $$x"},
{"a+", "${oops", "aaa", "${oops"},
{"a+", "$$", "aaa", "$$"},
{"a+", "$", "aaa", "$"},
type ReplaceFuncTest struct {
pattern string
replacement func(string) string
input, output string
}
var replaceFuncTests = []ReplaceFuncTest{
{"[a-c]", func(s string) string { return "x" + s + "y" }, "defabcdef", "defxayxbyxcydef"},
{"[a-c]+", func(s string) string { return "x" + s + "y" }, "defabcdef", "defxabcydef"},
{"[a-c]*", func(s string) string { return "x" + s + "y" }, "defabcdef", "xydxyexyfxabcydxyexyfxy"},
re, err := Compile(tc.pattern)
t.Errorf("Unexpected error compiling %q: %v", tc.pattern, err)
continue
actual := re.ReplaceAllString(tc.input, tc.replacement)
if actual != tc.output {
t.Errorf("%q.ReplaceAllString(%q,%q) = %q; want %q",
tc.pattern, tc.input, tc.replacement, actual, tc.output)
}
// now try bytes
actual = string(re.ReplaceAll([]byte(tc.input), []byte(tc.replacement)))
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
t.Errorf("%q.ReplaceAll(%q,%q) = %q; want %q",
tc.pattern, tc.input, tc.replacement, actual, tc.output)
}
}
}
func TestReplaceAllLiteral(t *testing.T) {
// Run ReplaceAll tests that do not have $ expansions.
for _, tc := range replaceTests {
if strings.Contains(tc.replacement, "$") {
continue
}
re, err := Compile(tc.pattern)
if err != nil {
t.Errorf("Unexpected error compiling %q: %v", tc.pattern, err)
continue
}
actual := re.ReplaceAllLiteralString(tc.input, tc.replacement)
if actual != tc.output {
t.Errorf("%q.ReplaceAllLiteralString(%q,%q) = %q; want %q",
tc.pattern, tc.input, tc.replacement, actual, tc.output)
}
// now try bytes
actual = string(re.ReplaceAllLiteral([]byte(tc.input), []byte(tc.replacement)))
if actual != tc.output {
t.Errorf("%q.ReplaceAllLiteral(%q,%q) = %q; want %q",
tc.pattern, tc.input, tc.replacement, actual, tc.output)
}
}
// Run literal-specific tests.
for _, tc := range replaceLiteralTests {
re, err := Compile(tc.pattern)
if err != nil {
t.Errorf("Unexpected error compiling %q: %v", tc.pattern, err)
continue
}
actual := re.ReplaceAllLiteralString(tc.input, tc.replacement)
if actual != tc.output {
t.Errorf("%q.ReplaceAllLiteralString(%q,%q) = %q; want %q",
tc.pattern, tc.input, tc.replacement, actual, tc.output)
}
// now try bytes
actual = string(re.ReplaceAllLiteral([]byte(tc.input), []byte(tc.replacement)))
if actual != tc.output {
t.Errorf("%q.ReplaceAllLiteral(%q,%q) = %q; want %q",
tc.pattern, tc.input, tc.replacement, actual, tc.output)
func TestReplaceAllFunc(t *testing.T) {
for _, tc := range replaceFuncTests {
re, err := Compile(tc.pattern)
if err != nil {
t.Errorf("Unexpected error compiling %q: %v", tc.pattern, err)
continue
}
actual := re.ReplaceAllStringFunc(tc.input, tc.replacement)
if actual != tc.output {
t.Errorf("%q.ReplaceFunc(%q,%q) = %q; want %q",
tc.pattern, tc.input, tc.replacement, actual, tc.output)
}
// now try bytes
actual = string(re.ReplaceAllFunc([]byte(tc.input), func(s []byte) []byte { return []byte(tc.replacement(string(s))) }))
if actual != tc.output {
t.Errorf("%q.ReplaceFunc(%q,%q) = %q; want %q",
tc.pattern, tc.input, tc.replacement, actual, tc.output)
}
}
}
type MetaTest struct {
pattern, output, literal string
isLiteral bool
var metaTests = []MetaTest{
{``, ``, ``, true},
{`foo`, `foo`, `foo`, true},
{`foo\.\$`, `foo\\\.\\\$`, `foo.$`, true}, // has meta but no operator
{`foo.\$`, `foo\.\\\$`, `foo`, false}, // has escaped operators and real operators
{`!@#$%^&*()_+-=[{]}\|,<.>/?~`, `!@#\$%\^&\*\(\)_\+-=\[\{\]\}\\\|,<\.>/\?~`, `!@#`, false},
}
func TestQuoteMeta(t *testing.T) {
for _, tc := range metaTests {
// Verify that QuoteMeta returns the expected string.
quoted := QuoteMeta(tc.pattern)
if quoted != tc.output {
t.Errorf("QuoteMeta(`%s`) = `%s`; want `%s`",
tc.pattern, quoted, tc.output)
continue
}
// Verify that the quoted string is in fact treated as expected
// by Compile -- i.e. that it matches the original, unquoted string.
if tc.pattern != "" {
re, err := Compile(quoted)
t.Errorf("Unexpected error compiling QuoteMeta(`%s`): %v", tc.pattern, err)
continue
src := "abc" + tc.pattern + "def"
repl := "xyz"
replaced := re.ReplaceAllString(src, repl)
expected := "abcxyzdef"
if replaced != expected {
t.Errorf("QuoteMeta(`%s`).Replace(`%s`,`%s`) = `%s`; want `%s`",
tc.pattern, src, repl, replaced, expected)
func TestLiteralPrefix(t *testing.T) {
for _, tc := range metaTests {
// Literal method needs to scan the pattern.
re := MustCompile(tc.pattern)
str, complete := re.LiteralPrefix()
if complete != tc.isLiteral {
t.Errorf("LiteralPrefix(`%s`) = %t; want %t", tc.pattern, complete, tc.isLiteral)
}
if str != tc.literal {
t.Errorf("LiteralPrefix(`%s`) = `%s`; want `%s`", tc.pattern, str, tc.literal)
type subexpCase struct {
input string
num int
names []string
var subexpCases = []subexpCase{
{``, 0, nil},
{`.*`, 0, nil},
{`abba`, 0, nil},
{`ab(b)a`, 1, []string{"", ""}},
{`ab(.*)a`, 1, []string{"", ""}},
{`(.*)ab(.*)a`, 2, []string{"", "", ""}},
{`(.*)(ab)(.*)a`, 3, []string{"", "", "", ""}},
{`(.*)((a)b)(.*)a`, 4, []string{"", "", "", "", ""}},
{`(.*)(\(ab)(.*)a`, 3, []string{"", "", "", ""}},
{`(.*)(\(a\)b)(.*)a`, 3, []string{"", "", "", ""}},
{`(?P<foo>.*)(?P<bar>(a)b)(?P<foo>.*)a`, 4, []string{"", "foo", "bar", "", "foo"}},
func TestSubexp(t *testing.T) {
for _, c := range subexpCases {
re := MustCompile(c.input)
if n != c.num {
t.Errorf("%q: NumSubexp = %d, want %d", c.input, n, c.num)
continue
}
names := re.SubexpNames()
if len(names) != 1+n {
t.Errorf("%q: len(SubexpNames) = %d, want %d", c.input, len(names), n)
continue
}
if c.names != nil {
for i := 0; i < 1+n; i++ {
if names[i] != c.names[i] {
t.Errorf("%q: SubexpNames[%d] = %q, want %q", c.input, i, names[i], c.names[i])
}
}
func BenchmarkLiteral(b *testing.B) {
x := strings.Repeat("x", 50) + "y"
for i := 0; i < b.N; i++ {
if !re.MatchString(x) {
}
}
}
func BenchmarkNotLiteral(b *testing.B) {
x := strings.Repeat("x", 50) + "y"
b.StartTimer()
for i := 0; i < b.N; i++ {
if !re.MatchString(x) {
}
}
}
func BenchmarkMatchClass(b *testing.B) {
b.StopTimer()
x := strings.Repeat("xxxx", 20) + "w"
re := MustCompile("[abcdw]")
b.StartTimer()
for i := 0; i < b.N; i++ {
if !re.MatchString(x) {
}
}
}
func BenchmarkMatchClass_InRange(b *testing.B) {
b.StopTimer()
// 'b' is between 'a' and 'c', so the charclass
// range checking is no help here.
x := strings.Repeat("bbbb", 20) + "c"
re := MustCompile("[ac]")
for i := 0; i < b.N; i++ {
if !re.MatchString(x) {
func BenchmarkReplaceAll(b *testing.B) {
x := "abcdefghijklmnopqrstuvwxyz"
b.StopTimer()
re := MustCompile("[cjrw]")
b.StartTimer()
for i := 0; i < b.N; i++ {
re.ReplaceAllString(x, "")
}
}
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
func BenchmarkAnchoredLiteralShortNonMatch(b *testing.B) {
b.StopTimer()
x := []byte("abcdefghijklmnopqrstuvwxyz")
re := MustCompile("^zbc(d|e)")
b.StartTimer()
for i := 0; i < b.N; i++ {
re.Match(x)
}
}
func BenchmarkAnchoredLiteralLongNonMatch(b *testing.B) {
b.StopTimer()
x := []byte("abcdefghijklmnopqrstuvwxyz")
for i := 0; i < 15; i++ {
x = append(x, x...)
}
re := MustCompile("^zbc(d|e)")
b.StartTimer()
for i := 0; i < b.N; i++ {
re.Match(x)
}
}
func BenchmarkAnchoredShortMatch(b *testing.B) {
b.StopTimer()
x := []byte("abcdefghijklmnopqrstuvwxyz")
re := MustCompile("^.bc(d|e)")
b.StartTimer()
for i := 0; i < b.N; i++ {
re.Match(x)
}
}
func BenchmarkAnchoredLongMatch(b *testing.B) {
b.StopTimer()
x := []byte("abcdefghijklmnopqrstuvwxyz")
for i := 0; i < 15; i++ {
x = append(x, x...)
}
re := MustCompile("^.bc(d|e)")
b.StartTimer()
for i := 0; i < b.N; i++ {
re.Match(x)
}
}