diff options
author | Ondřej Surý <ondrej@sury.org> | 2011-01-17 12:40:45 +0100 |
---|---|---|
committer | Ondřej Surý <ondrej@sury.org> | 2011-01-17 12:40:45 +0100 |
commit | 3e45412327a2654a77944249962b3652e6142299 (patch) | |
tree | bc3bf69452afa055423cbe0c5cfa8ca357df6ccf /src/pkg/strings | |
parent | c533680039762cacbc37db8dc7eed074c3e497be (diff) | |
download | golang-upstream/2011.01.12.tar.gz |
Imported Upstream version 2011.01.12upstream/2011.01.12
Diffstat (limited to 'src/pkg/strings')
-rw-r--r-- | src/pkg/strings/Makefile | 2 | ||||
-rw-r--r-- | src/pkg/strings/strings.go | 158 | ||||
-rw-r--r-- | src/pkg/strings/strings_test.go | 481 |
3 files changed, 358 insertions, 283 deletions
diff --git a/src/pkg/strings/Makefile b/src/pkg/strings/Makefile index 9bae470e9..c1be58243 100644 --- a/src/pkg/strings/Makefile +++ b/src/pkg/strings/Makefile @@ -2,7 +2,7 @@ # Use of this source code is governed by a BSD-style # license that can be found in the LICENSE file. -include ../../Make.$(GOARCH) +include ../../Make.inc TARG=strings GOFILES=\ diff --git a/src/pkg/strings/strings.go b/src/pkg/strings/strings.go index 5d3d61e19..98a0d5731 100644 --- a/src/pkg/strings/strings.go +++ b/src/pkg/strings/strings.go @@ -28,8 +28,10 @@ func explode(s string, n int) []string { a[i] = string(rune) cur += size } - // add the rest - a[i] = s[cur:] + // add the rest, if there is any + if cur < len(s) { + a[i] = s[cur:] + } return a } @@ -59,6 +61,11 @@ func Count(s, sep string) int { return n } +// Contains returns true if substr is within s. +func Contains(s, substr string) bool { + return Index(s, substr) != -1 +} + // Index returns the index of the first instance of sep in s, or -1 if sep is not present in s. func Index(s, sep string) int { n := len(sep) @@ -135,6 +142,24 @@ func IndexAny(s, chars string) int { return -1 } +// LastIndexAny returns the index of the last instance of any Unicode code +// point from chars in s, or -1 if no Unicode code point from chars is +// present in s. +func LastIndexAny(s, chars string) int { + if len(chars) > 0 { + for i := len(s); i > 0; { + rune, size := utf8.DecodeLastRuneInString(s[0:i]) + i -= size + for _, m := range chars { + if rune == m { + return i + } + } + } + } + return -1 +} + // Generic split: splits after each instance of sep, // including sepSave bytes of sep in the subarrays. func genSplit(s, sep string, sepSave, n int) []string { @@ -163,16 +188,22 @@ func genSplit(s, sep string, sepSave, n int) []string { return a[0 : na+1] } -// Split splits the string s around each instance of sep, returning an array of substrings of s. -// If sep is empty, Split splits s after each UTF-8 sequence. -// If n >= 0, Split splits s into at most n substrings; the last substring will be the unsplit remainder. -// Thus if n == 0, the result will be nil. +// Split slices s into substrings separated by sep and returns a slice of +// the substrings between those separators. +// If sep is empty, Split splits after each UTF-8 sequence. +// The count determines the number of substrings to return: +// n > 0: at most n substrings; the last substring will be the unsplit remainder. +// n == 0: the result is nil (zero substrings) +// n < 0: all substrings func Split(s, sep string, n int) []string { return genSplit(s, sep, 0, n) } -// SplitAfter splits the string s after each instance of sep, returning an array of substrings of s. -// If sep is empty, SplitAfter splits s after each UTF-8 sequence. -// If n >= 0, SplitAfter splits s into at most n substrings; the last substring will be the unsplit remainder. -// Thus if n == 0, the result will be nil. +// SplitAfter slices s into substrings after each instance of sep and +// returns a slice of those substrings. +// If sep is empty, Split splits after each UTF-8 sequence. +// The count determines the number of substrings to return: +// n > 0: at most n substrings; the last substring will be the unsplit remainder. +// n == 0: the result is nil (zero substrings) +// n < 0: all substrings func SplitAfter(s, sep string, n int) []string { return genSplit(s, sep, len(sep), n) } @@ -183,9 +214,9 @@ func Fields(s string) []string { return FieldsFunc(s, unicode.IsSpace) } -// FieldsFunc splits the string s at each run of Unicode code points c satifying f(c) -// and returns an array of slices of s. If no code points in s satisfy f(c), an empty slice -// is returned. +// FieldsFunc splits the string s at each run of Unicode code points c satisfying f(c) +// and returns an array of slices of s. If all code points in s satisfy f(c) or the +// string is empty, an empty slice is returned. func FieldsFunc(s string, f func(int) bool) []string { // First count the fields. n := 0 @@ -286,7 +317,7 @@ func Map(mapping func(rune int) int, s string) string { copy(nb, b[0:nbytes]) b = nb } - nbytes += utf8.EncodeRune(rune, b[nbytes:maxbytes]) + nbytes += utf8.EncodeRune(b[nbytes:maxbytes], rune) } } return string(b[0:nbytes]) @@ -333,6 +364,52 @@ func ToTitleSpecial(_case unicode.SpecialCase, s string) string { return Map(func(r int) int { return _case.ToTitle(r) }, s) } +// isSeparator reports whether the rune could mark a word boundary. +// TODO: update when package unicode captures more of the properties. +func isSeparator(rune int) bool { + // ASCII alphanumerics and underscore are not separators + if rune <= 0x7F { + switch { + case '0' <= rune && rune <= '9': + return false + case 'a' <= rune && rune <= 'z': + return false + case 'A' <= rune && rune <= 'Z': + return false + case rune == '_': + return false + } + return true + } + // Letters and digits are not separators + if unicode.IsLetter(rune) || unicode.IsDigit(rune) { + return false + } + // Otherwise, all we can do for now is treat spaces as separators. + return unicode.IsSpace(rune) +} + +// BUG(r): The rule Title uses for word boundaries does not handle Unicode punctuation properly. + +// Title returns a copy of the string s with all Unicode letters that begin words +// mapped to their title case. +func Title(s string) string { + // Use a closure here to remember state. + // Hackish but effective. Depends on Map scanning in order and calling + // the closure once per rune. + prev := ' ' + return Map( + func(r int) int { + if isSeparator(prev) { + prev = r + return unicode.ToTitle(r) + } + prev = r + return r + }, + s) +} + // TrimLeftFunc returns a slice of the string s with all leading // Unicode code points c satisfying f(c) removed. func TrimLeftFunc(s string, f func(r int) bool) string { @@ -376,8 +453,7 @@ func LastIndexFunc(s string, f func(r int) bool) int { // indexFunc is the same as IndexFunc except that if // truth==false, the sense of the predicate function is -// inverted. We could use IndexFunc directly, but this -// way saves a closure allocation. +// inverted. func indexFunc(s string, f func(r int) bool, truth bool) int { start := 0 for start < len(s) { @@ -396,37 +472,14 @@ func indexFunc(s string, f func(r int) bool, truth bool) int { // lastIndexFunc is the same as LastIndexFunc except that if // truth==false, the sense of the predicate function is -// inverted. We could use IndexFunc directly, but this -// way saves a closure allocation. +// inverted. func lastIndexFunc(s string, f func(r int) bool, truth bool) int { - end := len(s) - for end > 0 { - start := end - 1 - rune := int(s[start]) - if rune >= utf8.RuneSelf { - // Back up & look for beginning of rune. Mustn't pass start. - for start--; start >= 0; start-- { - if utf8.RuneStart(s[start]) { - break - } - } - if start < 0 { - return -1 - } - var wid int - rune, wid = utf8.DecodeRuneInString(s[start:end]) - - // If we've decoded fewer bytes than we expected, - // we've got some invalid UTF-8, so make sure we return - // the last possible index in s. - if start+wid < end && f(utf8.RuneError) == truth { - return end - 1 - } - } + for i := len(s); i > 0; { + rune, size := utf8.DecodeLastRuneInString(s[0:i]) + i -= size if f(rune) == truth { - return start + return i } - end = start } return -1 } @@ -497,21 +550,10 @@ func Replace(s, old, new string, n int) string { } else { j += Index(s[start:], old) } - w += copyString(t[w:], s[start:j]) - w += copyString(t[w:], new) + w += copy(t[w:], s[start:j]) + w += copy(t[w:], new) start = j + len(old) } - w += copyString(t[w:], s[start:]) + w += copy(t[w:], s[start:]) return string(t[0:w]) } - -func copyString(dst []byte, src string) int { - n := len(dst) - if n > len(src) { - n = len(src) - } - for i := 0; i < n; i++ { - dst[i] = src[i] - } - return n -} diff --git a/src/pkg/strings/strings_test.go b/src/pkg/strings/strings_test.go index 06f1f1de1..734fdd33d 100644 --- a/src/pkg/strings/strings_test.go +++ b/src/pkg/strings/strings_test.go @@ -36,55 +36,68 @@ type IndexTest struct { } var indexTests = []IndexTest{ - IndexTest{"", "", 0}, - IndexTest{"", "a", -1}, - IndexTest{"", "foo", -1}, - IndexTest{"fo", "foo", -1}, - IndexTest{"foo", "foo", 0}, - IndexTest{"oofofoofooo", "f", 2}, - IndexTest{"oofofoofooo", "foo", 4}, - IndexTest{"barfoobarfoo", "foo", 3}, - IndexTest{"foo", "", 0}, - IndexTest{"foo", "o", 1}, - IndexTest{"abcABCabc", "A", 3}, + {"", "", 0}, + {"", "a", -1}, + {"", "foo", -1}, + {"fo", "foo", -1}, + {"foo", "foo", 0}, + {"oofofoofooo", "f", 2}, + {"oofofoofooo", "foo", 4}, + {"barfoobarfoo", "foo", 3}, + {"foo", "", 0}, + {"foo", "o", 1}, + {"abcABCabc", "A", 3}, // cases with one byte strings - test special case in Index() - IndexTest{"", "a", -1}, - IndexTest{"x", "a", -1}, - IndexTest{"x", "x", 0}, - IndexTest{"abc", "a", 0}, - IndexTest{"abc", "b", 1}, - IndexTest{"abc", "c", 2}, - IndexTest{"abc", "x", -1}, + {"", "a", -1}, + {"x", "a", -1}, + {"x", "x", 0}, + {"abc", "a", 0}, + {"abc", "b", 1}, + {"abc", "c", 2}, + {"abc", "x", -1}, } var lastIndexTests = []IndexTest{ - IndexTest{"", "", 0}, - IndexTest{"", "a", -1}, - IndexTest{"", "foo", -1}, - IndexTest{"fo", "foo", -1}, - IndexTest{"foo", "foo", 0}, - IndexTest{"foo", "f", 0}, - IndexTest{"oofofoofooo", "f", 7}, - IndexTest{"oofofoofooo", "foo", 7}, - IndexTest{"barfoobarfoo", "foo", 9}, - IndexTest{"foo", "", 3}, - IndexTest{"foo", "o", 2}, - IndexTest{"abcABCabc", "A", 3}, - IndexTest{"abcABCabc", "a", 6}, + {"", "", 0}, + {"", "a", -1}, + {"", "foo", -1}, + {"fo", "foo", -1}, + {"foo", "foo", 0}, + {"foo", "f", 0}, + {"oofofoofooo", "f", 7}, + {"oofofoofooo", "foo", 7}, + {"barfoobarfoo", "foo", 9}, + {"foo", "", 3}, + {"foo", "o", 2}, + {"abcABCabc", "A", 3}, + {"abcABCabc", "a", 6}, } var indexAnyTests = []IndexTest{ - IndexTest{"", "", -1}, - IndexTest{"", "a", -1}, - IndexTest{"", "abc", -1}, - IndexTest{"a", "", -1}, - IndexTest{"a", "a", 0}, - IndexTest{"aaa", "a", 0}, - IndexTest{"abc", "xyz", -1}, - IndexTest{"abc", "xcz", 2}, - IndexTest{"a☺b☻c☹d", "uvw☻xyz", 2 + len("☺")}, - IndexTest{"aRegExp*", ".(|)*+?^$[]", 7}, - IndexTest{dots + dots + dots, " ", -1}, + {"", "", -1}, + {"", "a", -1}, + {"", "abc", -1}, + {"a", "", -1}, + {"a", "a", 0}, + {"aaa", "a", 0}, + {"abc", "xyz", -1}, + {"abc", "xcz", 2}, + {"a☺b☻c☹d", "uvw☻xyz", 2 + len("☺")}, + {"aRegExp*", ".(|)*+?^$[]", 7}, + {dots + dots + dots, " ", -1}, +} +var lastIndexAnyTests = []IndexTest{ + {"", "", -1}, + {"", "a", -1}, + {"", "abc", -1}, + {"a", "", -1}, + {"a", "a", 0}, + {"aaa", "a", 2}, + {"abc", "xyz", -1}, + {"abc", "ab", 1}, + {"a☺b☻c☹d", "uvw☻xyz", 2 + len("☺")}, + {"a.RegExp*", ".(|)*+?^$[]", 8}, + {dots + dots + dots, " ", -1}, } // Execute f on each test case. funcName should be the name of f; it's used @@ -98,9 +111,10 @@ func runIndexTests(t *testing.T, f func(s, sep string) int, funcName string, tes } } -func TestIndex(t *testing.T) { runIndexTests(t, Index, "Index", indexTests) } -func TestLastIndex(t *testing.T) { runIndexTests(t, LastIndex, "LastIndex", lastIndexTests) } -func TestIndexAny(t *testing.T) { runIndexTests(t, IndexAny, "IndexAny", indexAnyTests) } +func TestIndex(t *testing.T) { runIndexTests(t, Index, "Index", indexTests) } +func TestLastIndex(t *testing.T) { runIndexTests(t, LastIndex, "LastIndex", lastIndexTests) } +func TestIndexAny(t *testing.T) { runIndexTests(t, IndexAny, "IndexAny", indexAnyTests) } +func TestLastIndexAny(t *testing.T) { runIndexTests(t, LastIndexAny, "LastIndexAny", lastIndexAnyTests) } type ExplodeTest struct { s string @@ -109,9 +123,10 @@ type ExplodeTest struct { } var explodetests = []ExplodeTest{ - ExplodeTest{abcd, 4, []string{"a", "b", "c", "d"}}, - ExplodeTest{faces, 3, []string{"☺", "☻", "☹"}}, - ExplodeTest{abcd, 2, []string{"a", "bcd"}}, + {"", -1, []string{}}, + {abcd, 4, []string{"a", "b", "c", "d"}}, + {faces, 3, []string{"☺", "☻", "☹"}}, + {abcd, 2, []string{"a", "bcd"}}, } func TestExplode(t *testing.T) { @@ -136,19 +151,19 @@ type SplitTest struct { } var splittests = []SplitTest{ - SplitTest{abcd, "a", 0, nil}, - SplitTest{abcd, "a", -1, []string{"", "bcd"}}, - SplitTest{abcd, "z", -1, []string{"abcd"}}, - SplitTest{abcd, "", -1, []string{"a", "b", "c", "d"}}, - SplitTest{commas, ",", -1, []string{"1", "2", "3", "4"}}, - SplitTest{dots, "...", -1, []string{"1", ".2", ".3", ".4"}}, - SplitTest{faces, "☹", -1, []string{"☺☻", ""}}, - SplitTest{faces, "~", -1, []string{faces}}, - SplitTest{faces, "", -1, []string{"☺", "☻", "☹"}}, - SplitTest{"1 2 3 4", " ", 3, []string{"1", "2", "3 4"}}, - SplitTest{"1 2", " ", 3, []string{"1", "2"}}, - SplitTest{"123", "", 2, []string{"1", "23"}}, - SplitTest{"123", "", 17, []string{"1", "2", "3"}}, + {abcd, "a", 0, nil}, + {abcd, "a", -1, []string{"", "bcd"}}, + {abcd, "z", -1, []string{"abcd"}}, + {abcd, "", -1, []string{"a", "b", "c", "d"}}, + {commas, ",", -1, []string{"1", "2", "3", "4"}}, + {dots, "...", -1, []string{"1", ".2", ".3", ".4"}}, + {faces, "☹", -1, []string{"☺☻", ""}}, + {faces, "~", -1, []string{faces}}, + {faces, "", -1, []string{"☺", "☻", "☹"}}, + {"1 2 3 4", " ", 3, []string{"1", "2", "3 4"}}, + {"1 2", " ", 3, []string{"1", "2"}}, + {"123", "", 2, []string{"1", "23"}}, + {"123", "", 17, []string{"1", "2", "3"}}, } func TestSplit(t *testing.T) { @@ -169,19 +184,19 @@ func TestSplit(t *testing.T) { } var splitaftertests = []SplitTest{ - SplitTest{abcd, "a", -1, []string{"a", "bcd"}}, - SplitTest{abcd, "z", -1, []string{"abcd"}}, - SplitTest{abcd, "", -1, []string{"a", "b", "c", "d"}}, - SplitTest{commas, ",", -1, []string{"1,", "2,", "3,", "4"}}, - SplitTest{dots, "...", -1, []string{"1...", ".2...", ".3...", ".4"}}, - SplitTest{faces, "☹", -1, []string{"☺☻☹", ""}}, - SplitTest{faces, "~", -1, []string{faces}}, - SplitTest{faces, "", -1, []string{"☺", "☻", "☹"}}, - SplitTest{"1 2 3 4", " ", 3, []string{"1 ", "2 ", "3 4"}}, - SplitTest{"1 2 3", " ", 3, []string{"1 ", "2 ", "3"}}, - SplitTest{"1 2", " ", 3, []string{"1 ", "2"}}, - SplitTest{"123", "", 2, []string{"1", "23"}}, - SplitTest{"123", "", 17, []string{"1", "2", "3"}}, + {abcd, "a", -1, []string{"a", "bcd"}}, + {abcd, "z", -1, []string{"abcd"}}, + {abcd, "", -1, []string{"a", "b", "c", "d"}}, + {commas, ",", -1, []string{"1,", "2,", "3,", "4"}}, + {dots, "...", -1, []string{"1...", ".2...", ".3...", ".4"}}, + {faces, "☹", -1, []string{"☺☻☹", ""}}, + {faces, "~", -1, []string{faces}}, + {faces, "", -1, []string{"☺", "☻", "☹"}}, + {"1 2 3 4", " ", 3, []string{"1 ", "2 ", "3 4"}}, + {"1 2 3", " ", 3, []string{"1 ", "2 ", "3"}}, + {"1 2", " ", 3, []string{"1 ", "2"}}, + {"123", "", 2, []string{"1", "23"}}, + {"123", "", 17, []string{"1", "2", "3"}}, } func TestSplitAfter(t *testing.T) { @@ -204,17 +219,17 @@ type FieldsTest struct { } var fieldstests = []FieldsTest{ - FieldsTest{"", []string{}}, - FieldsTest{" ", []string{}}, - FieldsTest{" \t ", []string{}}, - FieldsTest{" abc ", []string{"abc"}}, - FieldsTest{"1 2 3 4", []string{"1", "2", "3", "4"}}, - FieldsTest{"1 2 3 4", []string{"1", "2", "3", "4"}}, - FieldsTest{"1\t\t2\t\t3\t4", []string{"1", "2", "3", "4"}}, - FieldsTest{"1\u20002\u20013\u20024", []string{"1", "2", "3", "4"}}, - FieldsTest{"\u2000\u2001\u2002", []string{}}, - FieldsTest{"\n™\t™\n", []string{"™", "™"}}, - FieldsTest{faces, []string{faces}}, + {"", []string{}}, + {" ", []string{}}, + {" \t ", []string{}}, + {" abc ", []string{"abc"}}, + {"1 2 3 4", []string{"1", "2", "3", "4"}}, + {"1 2 3 4", []string{"1", "2", "3", "4"}}, + {"1\t\t2\t\t3\t4", []string{"1", "2", "3", "4"}}, + {"1\u20002\u20013\u20024", []string{"1", "2", "3", "4"}}, + {"\u2000\u2001\u2002", []string{}}, + {"\n™\t™\n", []string{"™", "™"}}, + {faces, []string{faces}}, } func TestFields(t *testing.T) { @@ -230,10 +245,10 @@ func TestFields(t *testing.T) { func TestFieldsFunc(t *testing.T) { pred := func(c int) bool { return c == 'X' } var fieldsFuncTests = []FieldsTest{ - FieldsTest{"", []string{}}, - FieldsTest{"XX", []string{}}, - FieldsTest{"XXhiXXX", []string{"hi"}}, - FieldsTest{"aXXbXXXcX", []string{"a", "b", "c"}}, + {"", []string{}}, + {"XX", []string{}}, + {"XXhiXXX", []string{"hi"}}, + {"aXXbXXXcX", []string{"a", "b", "c"}}, } for _, tt := range fieldsFuncTests { a := FieldsFunc(tt.s, pred) @@ -261,40 +276,40 @@ func runStringTests(t *testing.T, f func(string) string, funcName string, testCa } var upperTests = []StringTest{ - StringTest{"", ""}, - StringTest{"abc", "ABC"}, - StringTest{"AbC123", "ABC123"}, - StringTest{"azAZ09_", "AZAZ09_"}, - StringTest{"\u0250\u0250\u0250\u0250\u0250", "\u2C6F\u2C6F\u2C6F\u2C6F\u2C6F"}, // grows one byte per char + {"", ""}, + {"abc", "ABC"}, + {"AbC123", "ABC123"}, + {"azAZ09_", "AZAZ09_"}, + {"\u0250\u0250\u0250\u0250\u0250", "\u2C6F\u2C6F\u2C6F\u2C6F\u2C6F"}, // grows one byte per char } var lowerTests = []StringTest{ - StringTest{"", ""}, - StringTest{"abc", "abc"}, - StringTest{"AbC123", "abc123"}, - StringTest{"azAZ09_", "azaz09_"}, - StringTest{"\u2C6D\u2C6D\u2C6D\u2C6D\u2C6D", "\u0251\u0251\u0251\u0251\u0251"}, // shrinks one byte per char + {"", ""}, + {"abc", "abc"}, + {"AbC123", "abc123"}, + {"azAZ09_", "azaz09_"}, + {"\u2C6D\u2C6D\u2C6D\u2C6D\u2C6D", "\u0251\u0251\u0251\u0251\u0251"}, // shrinks one byte per char } const space = "\t\v\r\f\n\u0085\u00a0\u2000\u3000" var trimSpaceTests = []StringTest{ - StringTest{"", ""}, - StringTest{"abc", "abc"}, - StringTest{space + "abc" + space, "abc"}, - StringTest{" ", ""}, - StringTest{" \t\r\n \t\t\r\r\n\n ", ""}, - StringTest{" \t\r\n x\t\t\r\r\n\n ", "x"}, - StringTest{" \u2000\t\r\n x\t\t\r\r\ny\n \u3000", "x\t\t\r\r\ny"}, - StringTest{"1 \t\r\n2", "1 \t\r\n2"}, - StringTest{" x\x80", "x\x80"}, - StringTest{" x\xc0", "x\xc0"}, - StringTest{"x \xc0\xc0 ", "x \xc0\xc0"}, - StringTest{"x \xc0", "x \xc0"}, - StringTest{"x \xc0 ", "x \xc0"}, - StringTest{"x \xc0\xc0 ", "x \xc0\xc0"}, - StringTest{"x ☺\xc0\xc0 ", "x ☺\xc0\xc0"}, - StringTest{"x ☺ ", "x ☺"}, + {"", ""}, + {"abc", "abc"}, + {space + "abc" + space, "abc"}, + {" ", ""}, + {" \t\r\n \t\t\r\r\n\n ", ""}, + {" \t\r\n x\t\t\r\r\n\n ", "x"}, + {" \u2000\t\r\n x\t\t\r\r\ny\n \u3000", "x\t\t\r\r\ny"}, + {"1 \t\r\n2", "1 \t\r\n2"}, + {" x\x80", "x\x80"}, + {" x\xc0", "x\xc0"}, + {"x \xc0\xc0 ", "x \xc0\xc0"}, + {"x \xc0", "x \xc0"}, + {"x \xc0 ", "x \xc0"}, + {"x \xc0\xc0 ", "x \xc0\xc0"}, + {"x ☺\xc0\xc0 ", "x ☺\xc0\xc0"}, + {"x ☺ ", "x ☺"}, } func tenRunes(rune int) string { @@ -397,48 +412,29 @@ type TrimTest struct { } var trimTests = []TrimTest{ - TrimTest{Trim, "abba", "a", "bb"}, - TrimTest{Trim, "abba", "ab", ""}, - TrimTest{TrimLeft, "abba", "ab", ""}, - TrimTest{TrimRight, "abba", "ab", ""}, - TrimTest{TrimLeft, "abba", "a", "bba"}, - TrimTest{TrimRight, "abba", "a", "abb"}, - TrimTest{Trim, "<tag>", "<>", "tag"}, - TrimTest{Trim, "* listitem", " *", "listitem"}, - TrimTest{Trim, `"quote"`, `"`, "quote"}, - TrimTest{Trim, "\u2C6F\u2C6F\u0250\u0250\u2C6F\u2C6F", "\u2C6F", "\u0250\u0250"}, + {Trim, "abba", "a", "bb"}, + {Trim, "abba", "ab", ""}, + {TrimLeft, "abba", "ab", ""}, + {TrimRight, "abba", "ab", ""}, + {TrimLeft, "abba", "a", "bba"}, + {TrimRight, "abba", "a", "abb"}, + {Trim, "<tag>", "<>", "tag"}, + {Trim, "* listitem", " *", "listitem"}, + {Trim, `"quote"`, `"`, "quote"}, + {Trim, "\u2C6F\u2C6F\u0250\u0250\u2C6F\u2C6F", "\u2C6F", "\u0250\u0250"}, //empty string tests - TrimTest{Trim, "abba", "", "abba"}, - TrimTest{Trim, "", "123", ""}, - TrimTest{Trim, "", "", ""}, - TrimTest{TrimLeft, "abba", "", "abba"}, - TrimTest{TrimLeft, "", "123", ""}, - TrimTest{TrimLeft, "", "", ""}, - TrimTest{TrimRight, "abba", "", "abba"}, - TrimTest{TrimRight, "", "123", ""}, - TrimTest{TrimRight, "", "", ""}, - TrimTest{TrimRight, "☺\xc0", "☺", "☺\xc0"}, -} - -// naiveTrimRight implements a version of TrimRight -// by scanning forwards from the start of s. -func naiveTrimRight(s string, cutset string) string { - i := -1 - for j, r := range s { - if IndexRune(cutset, r) == -1 { - i = j - } - } - if i >= 0 && s[i] >= utf8.RuneSelf { - _, wid := utf8.DecodeRuneInString(s[i:]) - i += wid - } else { - i++ - } - return s[0:i] + {Trim, "abba", "", "abba"}, + {Trim, "", "123", ""}, + {Trim, "", "", ""}, + {TrimLeft, "abba", "", "abba"}, + {TrimLeft, "", "123", ""}, + {TrimLeft, "", "", ""}, + {TrimRight, "abba", "", "abba"}, + {TrimRight, "", "123", ""}, + {TrimRight, "", "", ""}, + {TrimRight, "☺\xc0", "☺", "☺\xc0"}, } - func TestTrim(t *testing.T) { for _, tc := range trimTests { actual := tc.f(tc.in, tc.cutset) @@ -456,16 +452,14 @@ func TestTrim(t *testing.T) { if actual != tc.out { t.Errorf("%s(%q, %q) = %q; want %q", name, tc.in, tc.cutset, actual, tc.out) } - // test equivalence of TrimRight to naive version - if tc.f == TrimRight { - naive := naiveTrimRight(tc.in, tc.cutset) - if naive != actual { - t.Errorf("TrimRight(%q, %q) = %q, want %q", tc.in, tc.cutset, actual, naive) - } - } } } +type predicate struct { + f func(r int) bool + name string +} + var isSpace = predicate{unicode.IsSpace, "IsSpace"} var isDigit = predicate{unicode.IsDigit, "IsDigit"} var isUpper = predicate{unicode.IsUpper, "IsUpper"} @@ -476,11 +470,6 @@ var isValidRune = predicate{ "IsValidRune", } -type predicate struct { - f func(r int) bool - name string -} - type TrimFuncTest struct { f predicate in, out string @@ -496,13 +485,13 @@ func not(p predicate) predicate { } var trimFuncTests = []TrimFuncTest{ - TrimFuncTest{isSpace, space + " hello " + space, "hello"}, - TrimFuncTest{isDigit, "\u0e50\u0e5212hello34\u0e50\u0e51", "hello"}, - TrimFuncTest{isUpper, "\u2C6F\u2C6F\u2C6F\u2C6FABCDhelloEF\u2C6F\u2C6FGH\u2C6F\u2C6F", "hello"}, - TrimFuncTest{not(isSpace), "hello" + space + "hello", space}, - TrimFuncTest{not(isDigit), "hello\u0e50\u0e521234\u0e50\u0e51helo", "\u0e50\u0e521234\u0e50\u0e51"}, - TrimFuncTest{isValidRune, "ab\xc0a\xc0cd", "\xc0a\xc0"}, - TrimFuncTest{not(isValidRune), "\xc0a\xc0", "a"}, + {isSpace, space + " hello " + space, "hello"}, + {isDigit, "\u0e50\u0e5212hello34\u0e50\u0e51", "hello"}, + {isUpper, "\u2C6F\u2C6F\u2C6F\u2C6FABCDhelloEF\u2C6F\u2C6FGH\u2C6F\u2C6F", "hello"}, + {not(isSpace), "hello" + space + "hello", space}, + {not(isDigit), "hello\u0e50\u0e521234\u0e50\u0e51helo", "\u0e50\u0e521234\u0e50\u0e51"}, + {isValidRune, "ab\xc0a\xc0cd", "\xc0a\xc0"}, + {not(isValidRune), "\xc0a\xc0", "a"}, } func TestTrimFunc(t *testing.T) { @@ -521,24 +510,25 @@ type IndexFuncTest struct { } var indexFuncTests = []IndexFuncTest{ - IndexFuncTest{"", isValidRune, -1, -1}, - IndexFuncTest{"abc", isDigit, -1, -1}, - IndexFuncTest{"0123", isDigit, 0, 3}, - IndexFuncTest{"a1b", isDigit, 1, 1}, - IndexFuncTest{space, isSpace, 0, len(space) - 3}, // last rune in space is 3 bytes - IndexFuncTest{"\u0e50\u0e5212hello34\u0e50\u0e51", isDigit, 0, 18}, - IndexFuncTest{"\u2C6F\u2C6F\u2C6F\u2C6FABCDhelloEF\u2C6F\u2C6FGH\u2C6F\u2C6F", isUpper, 0, 34}, - IndexFuncTest{"12\u0e50\u0e52hello34\u0e50\u0e51", not(isDigit), 8, 12}, - - // broken unicode tests - IndexFuncTest{"\x801", isDigit, 1, 1}, - IndexFuncTest{"\x80abc", isDigit, -1, -1}, - IndexFuncTest{"\xc0a\xc0", isValidRune, 1, 1}, - IndexFuncTest{"\xc0a\xc0", not(isValidRune), 0, 2}, - IndexFuncTest{"\xc0☺\xc0", not(isValidRune), 0, 4}, - IndexFuncTest{"\xc0☺\xc0\xc0", not(isValidRune), 0, 5}, - IndexFuncTest{"ab\xc0a\xc0cd", not(isValidRune), 2, 4}, - IndexFuncTest{"a\xe0\x80cd", not(isValidRune), 1, 2}, + {"", isValidRune, -1, -1}, + {"abc", isDigit, -1, -1}, + {"0123", isDigit, 0, 3}, + {"a1b", isDigit, 1, 1}, + {space, isSpace, 0, len(space) - 3}, // last rune in space is 3 bytes + {"\u0e50\u0e5212hello34\u0e50\u0e51", isDigit, 0, 18}, + {"\u2C6F\u2C6F\u2C6F\u2C6FABCDhelloEF\u2C6F\u2C6FGH\u2C6F\u2C6F", isUpper, 0, 34}, + {"12\u0e50\u0e52hello34\u0e50\u0e51", not(isDigit), 8, 12}, + + // tests of invalid UTF-8 + {"\x801", isDigit, 1, 1}, + {"\x80abc", isDigit, -1, -1}, + {"\xc0a\xc0", isValidRune, 1, 1}, + {"\xc0a\xc0", not(isValidRune), 0, 2}, + {"\xc0☺\xc0", not(isValidRune), 0, 4}, + {"\xc0☺\xc0\xc0", not(isValidRune), 0, 5}, + {"ab\xc0a\xc0cd", not(isValidRune), 2, 4}, + {"a\xe0\x80cd", not(isValidRune), 1, 2}, + {"\x80\x80\x80\x80", not(isValidRune), 0, 3}, } func TestIndexFunc(t *testing.T) { @@ -619,13 +609,13 @@ type RepeatTest struct { } var RepeatTests = []RepeatTest{ - RepeatTest{"", "", 0}, - RepeatTest{"", "", 1}, - RepeatTest{"", "", 2}, - RepeatTest{"-", "", 0}, - RepeatTest{"-", "-", 1}, - RepeatTest{"-", "----------", 10}, - RepeatTest{"abc ", "abc abc abc ", 3}, + {"", "", 0}, + {"", "", 1}, + {"", "", 2}, + {"-", "", 0}, + {"-", "-", 1}, + {"-", "----------", 10}, + {"abc ", "abc abc abc ", 3}, } func TestRepeat(t *testing.T) { @@ -657,13 +647,13 @@ type RunesTest struct { } var RunesTests = []RunesTest{ - RunesTest{"", []int{}, false}, - RunesTest{" ", []int{32}, false}, - RunesTest{"ABC", []int{65, 66, 67}, false}, - RunesTest{"abc", []int{97, 98, 99}, false}, - RunesTest{"\u65e5\u672c\u8a9e", []int{26085, 26412, 35486}, false}, - RunesTest{"ab\x80c", []int{97, 98, 0xFFFD, 99}, true}, - RunesTest{"ab\xc0c", []int{97, 98, 0xFFFD, 99}, true}, + {"", []int{}, false}, + {" ", []int{32}, false}, + {"ABC", []int{65, 66, 67}, false}, + {"abc", []int{97, 98, 99}, false}, + {"\u65e5\u672c\u8a9e", []int{26085, 26412, 35486}, false}, + {"ab\x80c", []int{97, 98, 0xFFFD, 99}, true}, + {"ab\xc0c", []int{97, 98, 0xFFFD, 99}, true}, } func TestRunes(t *testing.T) { @@ -713,25 +703,25 @@ type ReplaceTest struct { } var ReplaceTests = []ReplaceTest{ - ReplaceTest{"hello", "l", "L", 0, "hello"}, - ReplaceTest{"hello", "l", "L", -1, "heLLo"}, - ReplaceTest{"hello", "x", "X", -1, "hello"}, - ReplaceTest{"", "x", "X", -1, ""}, - ReplaceTest{"radar", "r", "<r>", -1, "<r>ada<r>"}, - ReplaceTest{"", "", "<>", -1, "<>"}, - ReplaceTest{"banana", "a", "<>", -1, "b<>n<>n<>"}, - ReplaceTest{"banana", "a", "<>", 1, "b<>nana"}, - ReplaceTest{"banana", "a", "<>", 1000, "b<>n<>n<>"}, - ReplaceTest{"banana", "an", "<>", -1, "b<><>a"}, - ReplaceTest{"banana", "ana", "<>", -1, "b<>na"}, - ReplaceTest{"banana", "", "<>", -1, "<>b<>a<>n<>a<>n<>a<>"}, - ReplaceTest{"banana", "", "<>", 10, "<>b<>a<>n<>a<>n<>a<>"}, - ReplaceTest{"banana", "", "<>", 6, "<>b<>a<>n<>a<>n<>a"}, - ReplaceTest{"banana", "", "<>", 5, "<>b<>a<>n<>a<>na"}, - ReplaceTest{"banana", "", "<>", 1, "<>banana"}, - ReplaceTest{"banana", "a", "a", -1, "banana"}, - ReplaceTest{"banana", "a", "a", 1, "banana"}, - ReplaceTest{"☺☻☹", "", "<>", -1, "<>☺<>☻<>☹<>"}, + {"hello", "l", "L", 0, "hello"}, + {"hello", "l", "L", -1, "heLLo"}, + {"hello", "x", "X", -1, "hello"}, + {"", "x", "X", -1, ""}, + {"radar", "r", "<r>", -1, "<r>ada<r>"}, + {"", "", "<>", -1, "<>"}, + {"banana", "a", "<>", -1, "b<>n<>n<>"}, + {"banana", "a", "<>", 1, "b<>nana"}, + {"banana", "a", "<>", 1000, "b<>n<>n<>"}, + {"banana", "an", "<>", -1, "b<><>a"}, + {"banana", "ana", "<>", -1, "b<>na"}, + {"banana", "", "<>", -1, "<>b<>a<>n<>a<>n<>a<>"}, + {"banana", "", "<>", 10, "<>b<>a<>n<>a<>n<>a<>"}, + {"banana", "", "<>", 6, "<>b<>a<>n<>a<>n<>a"}, + {"banana", "", "<>", 5, "<>b<>a<>n<>a<>na"}, + {"banana", "", "<>", 1, "<>banana"}, + {"banana", "a", "a", -1, "banana"}, + {"banana", "a", "a", 1, "banana"}, + {"☺☻☹", "", "<>", -1, "<>☺<>☻<>☹<>"}, } func TestReplace(t *testing.T) { @@ -741,3 +731,46 @@ func TestReplace(t *testing.T) { } } } + +type TitleTest struct { + in, out string +} + +var TitleTests = []TitleTest{ + {"", ""}, + {"a", "A"}, + {" aaa aaa aaa ", " Aaa Aaa Aaa "}, + {" Aaa Aaa Aaa ", " Aaa Aaa Aaa "}, + {"123a456", "123a456"}, + {"double-blind", "Double-Blind"}, + {"ÿøû", "Ÿøû"}, +} + +func TestTitle(t *testing.T) { + for _, tt := range TitleTests { + if s := Title(tt.in); s != tt.out { + t.Errorf("Title(%q) = %q, want %q", tt.in, s, tt.out) + } + } +} + +type ContainsTest struct { + str, substr string + expected bool +} + +var ContainsTests = []ContainsTest{ + {"abc", "bc", true}, + {"abc", "bcd", false}, + {"abc", "", true}, + {"", "a", false}, +} + +func TestContains(t *testing.T) { + for _, ct := range ContainsTests { + if Contains(ct.str, ct.substr) != ct.expected { + t.Errorf("Contains(%s, %s) = %v, want %v", + ct.str, ct.substr, !ct.expected, ct.expected) + } + } +} |