123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422 |
- // 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.
- package misspell_test
- import (
- "bytes"
- "fmt"
- "strings"
- "testing"
- . "github.com/client9/misspell"
- )
- var htmlEscaper = NewStringReplacer(
- "&", "&",
- "<", "<",
- ">", ">",
- `"`, """,
- "'", "'",
- )
- var htmlUnescaper = NewStringReplacer(
- "&", "&",
- "<", "<",
- ">", ">",
- """, `"`,
- "'", "'",
- )
- // The http package's old HTML escaping function.
- func oldHTMLEscape(s string) string {
- s = strings.Replace(s, "&", "&", -1)
- s = strings.Replace(s, "<", "<", -1)
- s = strings.Replace(s, ">", ">", -1)
- s = strings.Replace(s, `"`, """, -1)
- s = strings.Replace(s, "'", "'", -1)
- return s
- }
- var capitalLetters = NewStringReplacer("a", "A", "b", "B")
- // TestReplacer tests the replacer implementations.
- func TestReplacer(t *testing.T) {
- type testCase struct {
- r *StringReplacer
- in, out string
- }
- var testCases []testCase
- // str converts 0xff to "\xff". This isn't just string(b) since that converts to UTF-8.
- str := func(b byte) string {
- return string([]byte{b})
- }
- var s []string
- // inc maps "\x00"->"\x01", ..., "a"->"b", "b"->"c", ..., "\xff"->"\x00".
- for i := 0; i < 256; i++ {
- s = append(s, str(byte(i)), str(byte(i+1)))
- }
- inc := NewStringReplacer(s...)
- // Test cases with 1-byte old strings, 1-byte new strings.
- testCases = append(testCases,
- testCase{capitalLetters, "brad", "BrAd"},
- testCase{capitalLetters, strings.Repeat("a", (32<<10)+123), strings.Repeat("A", (32<<10)+123)},
- testCase{capitalLetters, "", ""},
- testCase{inc, "brad", "csbe"},
- testCase{inc, "\x00\xff", "\x01\x00"},
- testCase{inc, "", ""},
- testCase{NewStringReplacer("a", "1", "a", "2"), "brad", "br1d"},
- )
- // repeat maps "a"->"a", "b"->"bb", "c"->"ccc", ...
- s = nil
- for i := 0; i < 256; i++ {
- n := i + 1 - 'a'
- if n < 1 {
- n = 1
- }
- s = append(s, str(byte(i)), strings.Repeat(str(byte(i)), n))
- }
- repeat := NewStringReplacer(s...)
- // Test cases with 1-byte old strings, variable length new strings.
- testCases = append(testCases,
- testCase{htmlEscaper, "No changes", "No changes"},
- testCase{htmlEscaper, "I <3 escaping & stuff", "I <3 escaping & stuff"},
- testCase{htmlEscaper, "&&&", "&&&"},
- testCase{htmlEscaper, "", ""},
- testCase{repeat, "brad", "bbrrrrrrrrrrrrrrrrrradddd"},
- testCase{repeat, "abba", "abbbba"},
- testCase{repeat, "", ""},
- testCase{NewStringReplacer("a", "11", "a", "22"), "brad", "br11d"},
- )
- // The remaining test cases have variable length old strings.
- testCases = append(testCases,
- testCase{htmlUnescaper, "&amp;", "&"},
- testCase{htmlUnescaper, "<b>HTML's neat</b>", "<b>HTML's neat</b>"},
- testCase{htmlUnescaper, "", ""},
- testCase{NewStringReplacer("a", "1", "a", "2", "xxx", "xxx"), "brad", "br1d"},
- testCase{NewStringReplacer("a", "1", "aa", "2", "aaa", "3"), "aaaa", "1111"},
- testCase{NewStringReplacer("aaa", "3", "aa", "2", "a", "1"), "aaaa", "31"},
- )
- // gen1 has multiple old strings of variable length. There is no
- // overall non-empty common prefix, but some pairwise common prefixes.
- gen1 := NewStringReplacer(
- "aaa", "3[aaa]",
- "aa", "2[aa]",
- "a", "1[a]",
- "i", "i",
- "longerst", "most long",
- "longer", "medium",
- "long", "short",
- "xx", "xx",
- "x", "X",
- "X", "Y",
- "Y", "Z",
- )
- testCases = append(testCases,
- testCase{gen1, "fooaaabar", "foo3[aaa]b1[a]r"},
- testCase{gen1, "long, longerst, longer", "short, most long, medium"},
- testCase{gen1, "xxxxx", "xxxxX"},
- testCase{gen1, "XiX", "YiY"},
- testCase{gen1, "", ""},
- )
- // gen2 has multiple old strings with no pairwise common prefix.
- gen2 := NewStringReplacer(
- "roses", "red",
- "violets", "blue",
- "sugar", "sweet",
- )
- testCases = append(testCases,
- testCase{gen2, "roses are red, violets are blue...", "red are red, blue are blue..."},
- testCase{gen2, "", ""},
- )
- // gen3 has multiple old strings with an overall common prefix.
- gen3 := NewStringReplacer(
- "abracadabra", "poof",
- "abracadabrakazam", "splat",
- "abraham", "lincoln",
- "abrasion", "scrape",
- "abraham", "isaac",
- )
- testCases = append(testCases,
- testCase{gen3, "abracadabrakazam abraham", "poofkazam lincoln"},
- testCase{gen3, "abrasion abracad", "scrape abracad"},
- testCase{gen3, "abba abram abrasive", "abba abram abrasive"},
- testCase{gen3, "", ""},
- )
- // foo{1,2,3,4} have multiple old strings with an overall common prefix
- // and 1- or 2- byte extensions from the common prefix.
- foo1 := NewStringReplacer(
- "foo1", "A",
- "foo2", "B",
- "foo3", "C",
- )
- foo2 := NewStringReplacer(
- "foo1", "A",
- "foo2", "B",
- "foo31", "C",
- "foo32", "D",
- )
- foo3 := NewStringReplacer(
- "foo11", "A",
- "foo12", "B",
- "foo31", "C",
- "foo32", "D",
- )
- foo4 := NewStringReplacer(
- "foo12", "B",
- "foo32", "D",
- )
- testCases = append(testCases,
- testCase{foo1, "fofoofoo12foo32oo", "fofooA2C2oo"},
- testCase{foo1, "", ""},
- testCase{foo2, "fofoofoo12foo32oo", "fofooA2Doo"},
- testCase{foo2, "", ""},
- testCase{foo3, "fofoofoo12foo32oo", "fofooBDoo"},
- testCase{foo3, "", ""},
- testCase{foo4, "fofoofoo12foo32oo", "fofooBDoo"},
- testCase{foo4, "", ""},
- )
- // genAll maps "\x00\x01\x02...\xfe\xff" to "[all]", amongst other things.
- allBytes := make([]byte, 256)
- for i := range allBytes {
- allBytes[i] = byte(i)
- }
- allString := string(allBytes)
- genAll := NewStringReplacer(
- allString, "[all]",
- "\xff", "[ff]",
- "\x00", "[00]",
- )
- testCases = append(testCases,
- testCase{genAll, allString, "[all]"},
- testCase{genAll, "a\xff" + allString + "\x00", "a[ff][all][00]"},
- testCase{genAll, "", ""},
- )
- // Test cases with empty old strings.
- blankToX1 := NewStringReplacer("", "X")
- blankToX2 := NewStringReplacer("", "X", "", "")
- blankHighPriority := NewStringReplacer("", "X", "o", "O")
- blankLowPriority := NewStringReplacer("o", "O", "", "X")
- blankNoOp1 := NewStringReplacer("", "")
- blankNoOp2 := NewStringReplacer("", "", "", "A")
- blankFoo := NewStringReplacer("", "X", "foobar", "R", "foobaz", "Z")
- testCases = append(testCases,
- testCase{blankToX1, "foo", "XfXoXoX"},
- testCase{blankToX1, "", "X"},
- testCase{blankToX2, "foo", "XfXoXoX"},
- testCase{blankToX2, "", "X"},
- testCase{blankHighPriority, "oo", "XOXOX"},
- testCase{blankHighPriority, "ii", "XiXiX"},
- testCase{blankHighPriority, "oiio", "XOXiXiXOX"},
- testCase{blankHighPriority, "iooi", "XiXOXOXiX"},
- testCase{blankHighPriority, "", "X"},
- testCase{blankLowPriority, "oo", "OOX"},
- testCase{blankLowPriority, "ii", "XiXiX"},
- testCase{blankLowPriority, "oiio", "OXiXiOX"},
- testCase{blankLowPriority, "iooi", "XiOOXiX"},
- testCase{blankLowPriority, "", "X"},
- testCase{blankNoOp1, "foo", "foo"},
- testCase{blankNoOp1, "", ""},
- testCase{blankNoOp2, "foo", "foo"},
- testCase{blankNoOp2, "", ""},
- testCase{blankFoo, "foobarfoobaz", "XRXZX"},
- testCase{blankFoo, "foobar-foobaz", "XRX-XZX"},
- testCase{blankFoo, "", "X"},
- )
- // single string replacer
- abcMatcher := NewStringReplacer("abc", "[match]")
- testCases = append(testCases,
- testCase{abcMatcher, "", ""},
- testCase{abcMatcher, "ab", "ab"},
- testCase{abcMatcher, "abc", "[match]"},
- testCase{abcMatcher, "abcd", "[match]d"},
- testCase{abcMatcher, "cabcabcdabca", "c[match][match]d[match]a"},
- )
- // Issue 6659 cases (more single string replacer)
- noHello := NewStringReplacer("Hello", "")
- testCases = append(testCases,
- testCase{noHello, "Hello", ""},
- testCase{noHello, "Hellox", "x"},
- testCase{noHello, "xHello", "x"},
- testCase{noHello, "xHellox", "xx"},
- )
- // No-arg test cases.
- nop := NewStringReplacer()
- testCases = append(testCases,
- testCase{nop, "abc", "abc"},
- testCase{nop, "", ""},
- )
- // Run the test cases.
- for i, tc := range testCases {
- if s := tc.r.Replace(tc.in); s != tc.out {
- t.Errorf("%d. strings.Replace(%q) = %q, want %q", i, tc.in, s, tc.out)
- }
- var buf bytes.Buffer
- n, err := tc.r.WriteString(&buf, tc.in)
- if err != nil {
- t.Errorf("%d. WriteString: %v", i, err)
- continue
- }
- got := buf.String()
- if got != tc.out {
- t.Errorf("%d. WriteString(%q) wrote %q, want %q", i, tc.in, got, tc.out)
- continue
- }
- if n != len(tc.out) {
- t.Errorf("%d. WriteString(%q) wrote correct string but reported %d bytes; want %d (%q)",
- i, tc.in, n, len(tc.out), tc.out)
- }
- }
- }
- type errWriter struct{}
- func (errWriter) Write(p []byte) (n int, err error) {
- return 0, fmt.Errorf("unwritable")
- }
- func BenchmarkGenericNoMatch(b *testing.B) {
- str := strings.Repeat("A", 100) + strings.Repeat("B", 100)
- generic := NewStringReplacer("a", "A", "b", "B", "12", "123") // varying lengths forces generic
- for i := 0; i < b.N; i++ {
- generic.Replace(str)
- }
- }
- func BenchmarkGenericMatch1(b *testing.B) {
- str := strings.Repeat("a", 100) + strings.Repeat("b", 100)
- generic := NewStringReplacer("a", "A", "b", "B", "12", "123")
- for i := 0; i < b.N; i++ {
- generic.Replace(str)
- }
- }
- func BenchmarkGenericMatch2(b *testing.B) {
- str := strings.Repeat("It's <b>HTML</b>!", 100)
- for i := 0; i < b.N; i++ {
- htmlUnescaper.Replace(str)
- }
- }
- func benchmarkSingleString(b *testing.B, pattern, text string) {
- r := NewStringReplacer(pattern, "[match]")
- b.SetBytes(int64(len(text)))
- b.ResetTimer()
- for i := 0; i < b.N; i++ {
- r.Replace(text)
- }
- }
- func BenchmarkSingleMaxSkipping(b *testing.B) {
- benchmarkSingleString(b, strings.Repeat("b", 25), strings.Repeat("a", 10000))
- }
- func BenchmarkSingleLongSuffixFail(b *testing.B) {
- benchmarkSingleString(b, "b"+strings.Repeat("a", 500), strings.Repeat("a", 1002))
- }
- func BenchmarkSingleMatch(b *testing.B) {
- benchmarkSingleString(b, "abcdef", strings.Repeat("abcdefghijklmno", 1000))
- }
- func BenchmarkByteByteNoMatch(b *testing.B) {
- str := strings.Repeat("A", 100) + strings.Repeat("B", 100)
- for i := 0; i < b.N; i++ {
- capitalLetters.Replace(str)
- }
- }
- func BenchmarkByteByteMatch(b *testing.B) {
- str := strings.Repeat("a", 100) + strings.Repeat("b", 100)
- for i := 0; i < b.N; i++ {
- capitalLetters.Replace(str)
- }
- }
- func BenchmarkByteStringMatch(b *testing.B) {
- str := "<" + strings.Repeat("a", 99) + strings.Repeat("b", 99) + ">"
- for i := 0; i < b.N; i++ {
- htmlEscaper.Replace(str)
- }
- }
- func BenchmarkHTMLEscapeNew(b *testing.B) {
- str := "I <3 to escape HTML & other text too."
- for i := 0; i < b.N; i++ {
- htmlEscaper.Replace(str)
- }
- }
- func BenchmarkHTMLEscapeOld(b *testing.B) {
- str := "I <3 to escape HTML & other text too."
- for i := 0; i < b.N; i++ {
- oldHTMLEscape(str)
- }
- }
- func BenchmarkByteStringReplacerWriteString(b *testing.B) {
- str := strings.Repeat("I <3 to escape HTML & other text too.", 100)
- buf := new(bytes.Buffer)
- for i := 0; i < b.N; i++ {
- htmlEscaper.WriteString(buf, str)
- buf.Reset()
- }
- }
- func BenchmarkByteReplacerWriteString(b *testing.B) {
- str := strings.Repeat("abcdefghijklmnopqrstuvwxyz", 100)
- buf := new(bytes.Buffer)
- for i := 0; i < b.N; i++ {
- capitalLetters.WriteString(buf, str)
- buf.Reset()
- }
- }
- // BenchmarkByteByteReplaces compares byteByteImpl against multiple Replaces.
- func BenchmarkByteByteReplaces(b *testing.B) {
- str := strings.Repeat("a", 100) + strings.Repeat("b", 100)
- for i := 0; i < b.N; i++ {
- strings.Replace(strings.Replace(str, "a", "A", -1), "b", "B", -1)
- }
- }
|