diff options
Diffstat (limited to 'src/pkg/strings')
| -rw-r--r-- | src/pkg/strings/reader.go | 20 | ||||
| -rw-r--r-- | src/pkg/strings/strings.go | 164 | ||||
| -rw-r--r-- | src/pkg/strings/strings_test.go | 160 |
3 files changed, 172 insertions, 172 deletions
diff --git a/src/pkg/strings/reader.go b/src/pkg/strings/reader.go index 80c745bb8b..7cefbd24bb 100644 --- a/src/pkg/strings/reader.go +++ b/src/pkg/strings/reader.go @@ -11,28 +11,28 @@ import "os" type Reader string func (r *Reader) Read(b []byte) (n int, err os.Error) { - s := *r; + s := *r if len(s) == 0 { return 0, os.EOF } for n < len(s) && n < len(b) { - b[n] = s[n]; - n++; + b[n] = s[n] + n++ } - *r = s[n:]; - return; + *r = s[n:] + return } func (r *Reader) ReadByte() (b byte, err os.Error) { - s := *r; + s := *r if len(s) == 0 { return 0, os.EOF } - b = s[0]; - *r = s[1:]; - return; + b = s[0] + *r = s[1:] + return } // NewReader returns a new Reader reading from s. // It is similar to bytes.NewBufferString but more efficient and read-only. -func NewReader(s string) *Reader { return (*Reader)(&s) } +func NewReader(s string) *Reader { return (*Reader)(&s) } diff --git a/src/pkg/strings/strings.go b/src/pkg/strings/strings.go index 4e375b4d5b..ae34a5f3c3 100644 --- a/src/pkg/strings/strings.go +++ b/src/pkg/strings/strings.go @@ -6,8 +6,8 @@ package strings import ( - "unicode"; - "utf8"; + "unicode" + "utf8" ) // explode splits s into an array of UTF-8 sequences, one per Unicode character (still strings) up to a maximum of n (n <= 0 means no limit). @@ -16,21 +16,21 @@ func explode(s string, n int) []string { if n <= 0 { n = len(s) } - a := make([]string, n); - var size, rune int; - na := 0; + a := make([]string, n) + var size, rune int + na := 0 for len(s) > 0 { if na+1 >= n { - a[na] = s; - na++; - break; + a[na] = s + na++ + break } - rune, size = utf8.DecodeRuneInString(s); - s = s[size:]; - a[na] = string(rune); - na++; + rune, size = utf8.DecodeRuneInString(s) + s = s[size:] + a[na] = string(rune) + na++ } - return a[0:na]; + return a[0:na] } // Count counts the number of non-overlapping instances of sep in s. @@ -38,24 +38,24 @@ func Count(s, sep string) int { if sep == "" { return utf8.RuneCountInString(s) + 1 } - c := sep[0]; - n := 0; + c := sep[0] + n := 0 for i := 0; i+len(sep) <= len(s); i++ { if s[i] == c && (len(sep) == 1 || s[i:i+len(sep)] == sep) { - n++; - i += len(sep) - 1; + n++ + i += len(sep) - 1 } } - return n; + return n } // 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); + n := len(sep) if n == 0 { return 0 } - c := sep[0]; + c := sep[0] if n == 1 { // special case worth making fast for i := 0; i < len(s); i++ { @@ -63,23 +63,23 @@ func Index(s, sep string) int { return i } } - return -1; + return -1 } for i := 0; i+n <= len(s); i++ { if s[i] == c && (n == 1 || s[i:i+n] == sep) { return i } } - return -1; + return -1 } // LastIndex returns the index of the last instance of sep in s, or -1 if sep is not present in s. func LastIndex(s, sep string) int { - n := len(sep); + n := len(sep) if n == 0 { return len(s) } - c := sep[0]; + c := sep[0] if n == 1 { // special case worth making fast for i := len(s) - 1; i >= 0; i-- { @@ -87,14 +87,14 @@ func LastIndex(s, sep string) int { return i } } - return -1; + return -1 } for i := len(s) - n; i >= 0; i-- { if s[i] == c && (n == 1 || s[i:i+n] == sep) { return i } } - return -1; + return -1 } // Generic split: splits after each instance of sep, @@ -106,26 +106,26 @@ func genSplit(s, sep string, sepSave, n int) []string { if n <= 0 { n = Count(s, sep) + 1 } - c := sep[0]; - start := 0; - a := make([]string, n); - na := 0; + c := sep[0] + start := 0 + a := make([]string, n) + na := 0 for i := 0; i+len(sep) <= len(s) && na+1 < n; i++ { if s[i] == c && (len(sep) == 1 || s[i:i+len(sep)] == sep) { - a[na] = s[start : i+sepSave]; - na++; - start = i + len(sep); - i += len(sep) - 1; + a[na] = s[start : i+sepSave] + na++ + start = i + len(sep) + i += len(sep) - 1 } } - a[na] = s[start:]; - return a[0 : na+1]; + a[na] = s[start:] + 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. -func Split(s, sep string, n int) []string { return genSplit(s, sep, 0, n) } +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. @@ -143,28 +143,28 @@ func Join(a []string, sep string) string { if len(a) == 1 { return a[0] } - n := len(sep) * (len(a) - 1); + n := len(sep) * (len(a) - 1) for i := 0; i < len(a); i++ { n += len(a[i]) } - b := make([]byte, n); - bp := 0; + b := make([]byte, n) + bp := 0 for i := 0; i < len(a); i++ { - s := a[i]; + s := a[i] for j := 0; j < len(s); j++ { - b[bp] = s[j]; - bp++; + b[bp] = s[j] + bp++ } if i+1 < len(a) { - s = sep; + s = sep for j := 0; j < len(s); j++ { - b[bp] = s[j]; - bp++; + b[bp] = s[j] + bp++ } } } - return string(b); + return string(b) } // HasPrefix tests whether the string s begins with prefix. @@ -184,105 +184,105 @@ func Map(mapping func(rune int) int, s string) string { // In the worst case, the string can grow when mapped, making // things unpleasant. But it's so rare we barge in assuming it's // fine. It could also shrink but that falls out naturally. - maxbytes := len(s); // length of b - nbytes := 0; // number of bytes encoded in b - b := make([]byte, maxbytes); + maxbytes := len(s) // length of b + nbytes := 0 // number of bytes encoded in b + b := make([]byte, maxbytes) for _, c := range s { - rune := mapping(c); + rune := mapping(c) if rune >= 0 { - wid := 1; + wid := 1 if rune >= utf8.RuneSelf { wid = utf8.RuneLen(rune) } if nbytes+wid > maxbytes { // Grow the buffer. - maxbytes = maxbytes*2 + utf8.UTFMax; - nb := make([]byte, maxbytes); + maxbytes = maxbytes*2 + utf8.UTFMax + nb := make([]byte, maxbytes) for i, c := range b[0:nbytes] { nb[i] = c } - b = nb; + b = nb } - nbytes += utf8.EncodeRune(rune, b[nbytes:maxbytes]); + nbytes += utf8.EncodeRune(rune, b[nbytes:maxbytes]) } } - return string(b[0:nbytes]); + return string(b[0:nbytes]) } // Repeat returns a new string consisting of count copies of the string s. func Repeat(s string, count int) string { - b := make([]byte, len(s)*count); - bp := 0; + b := make([]byte, len(s)*count) + bp := 0 for i := 0; i < count; i++ { for j := 0; j < len(s); j++ { - b[bp] = s[j]; - bp++; + b[bp] = s[j] + bp++ } } - return string(b); + return string(b) } // ToUpper returns a copy of the string s with all Unicode letters mapped to their upper case. -func ToUpper(s string) string { return Map(unicode.ToUpper, s) } +func ToUpper(s string) string { return Map(unicode.ToUpper, s) } // ToLower returns a copy of the string s with all Unicode letters mapped to their lower case. -func ToLower(s string) string { return Map(unicode.ToLower, s) } +func ToLower(s string) string { return Map(unicode.ToLower, s) } // ToTitle returns a copy of the string s with all Unicode letters mapped to their title case. -func ToTitle(s string) string { return Map(unicode.ToTitle, s) } +func ToTitle(s string) string { return Map(unicode.ToTitle, s) } // Trim returns a slice of the string s, with all leading and trailing white space // removed, as defined by Unicode. func TrimSpace(s string) string { - start, end := 0, len(s); + start, end := 0, len(s) for start < end { - wid := 1; - rune := int(s[start]); + wid := 1 + rune := int(s[start]) if rune >= utf8.RuneSelf { rune, wid = utf8.DecodeRuneInString(s[start:end]) } if !unicode.IsSpace(rune) { break } - start += wid; + start += wid } for start < end { - wid := 1; - rune := int(s[end-1]); + wid := 1 + rune := int(s[end-1]) if rune >= utf8.RuneSelf { // Back up carefully looking for beginning of rune. Mustn't pass start. for wid = 2; start <= end-wid && !utf8.RuneStart(s[end-wid]); wid++ { } - if start > end-wid { // invalid UTF-8 sequence; stop processing + if start > end-wid { // invalid UTF-8 sequence; stop processing return s[start:end] } - rune, wid = utf8.DecodeRuneInString(s[end-wid : end]); + rune, wid = utf8.DecodeRuneInString(s[end-wid : end]) } if !unicode.IsSpace(rune) { break } - end -= wid; + end -= wid } - return s[start:end]; + return s[start:end] } // Bytes returns a new slice containing the bytes in s. func Bytes(s string) []byte { - b := make([]byte, len(s)); + b := make([]byte, len(s)) for i := 0; i < len(s); i++ { b[i] = s[i] } - return b; + return b } // Runes returns a slice of runes (Unicode code points) equivalent to the string s. func Runes(s string) []int { - t := make([]int, utf8.RuneCountInString(s)); - i := 0; + t := make([]int, utf8.RuneCountInString(s)) + i := 0 for _, r := range s { - t[i] = r; - i++; + t[i] = r + i++ } - return t; + return t } diff --git a/src/pkg/strings/strings_test.go b/src/pkg/strings/strings_test.go index e3e7f38aed..eb0f8d1fb5 100644 --- a/src/pkg/strings/strings_test.go +++ b/src/pkg/strings/strings_test.go @@ -5,10 +5,10 @@ package strings_test import ( - . "strings"; - "testing"; - "unicode"; - "utf8"; + . "strings" + "testing" + "unicode" + "utf8" ) func eq(a, b []string) bool { @@ -20,7 +20,7 @@ func eq(a, b []string) bool { return false } } - return true; + return true } var abcd = "abcd" @@ -29,9 +29,9 @@ var commas = "1,2,3,4" var dots = "1....2....3....4" type IndexTest struct { - s string; - sep string; - out int; + s string + sep string + out int } var indexTests = []IndexTest{ @@ -76,22 +76,22 @@ var lastIndexTests = []IndexTest{ // in failure reports. func runIndexTests(t *testing.T, f func(s, sep string) int, funcName string, testCases []IndexTest) { for _, test := range testCases { - actual := f(test.s, test.sep); + actual := f(test.s, test.sep) if actual != test.out { t.Errorf("%s(%q,%q) = %v; want %v", funcName, test.s, test.sep, actual, test.out) } } } -func TestIndex(t *testing.T) { runIndexTests(t, Index, "Index", indexTests) } +func TestIndex(t *testing.T) { runIndexTests(t, Index, "Index", indexTests) } -func TestLastIndex(t *testing.T) { runIndexTests(t, LastIndex, "LastIndex", lastIndexTests) } +func TestLastIndex(t *testing.T) { runIndexTests(t, LastIndex, "LastIndex", lastIndexTests) } type ExplodeTest struct { - s string; - n int; - a []string; + s string + n int + a []string } var explodetests = []ExplodeTest{ @@ -102,12 +102,12 @@ var explodetests = []ExplodeTest{ func TestExplode(t *testing.T) { for _, tt := range explodetests { - a := Split(tt.s, "", tt.n); + a := Split(tt.s, "", tt.n) if !eq(a, tt.a) { - t.Errorf("explode(%q, %d) = %v; want %v", tt.s, tt.n, a, tt.a); - continue; + t.Errorf("explode(%q, %d) = %v; want %v", tt.s, tt.n, a, tt.a) + continue } - s := Join(a, ""); + s := Join(a, "") if s != tt.s { t.Errorf(`Join(explode(%q, %d), "") = %q`, tt.s, tt.n, s) } @@ -115,10 +115,10 @@ func TestExplode(t *testing.T) { } type SplitTest struct { - s string; - sep string; - n int; - a []string; + s string + sep string + n int + a []string } var splittests = []SplitTest{ @@ -138,12 +138,12 @@ var splittests = []SplitTest{ func TestSplit(t *testing.T) { for _, tt := range splittests { - a := Split(tt.s, tt.sep, tt.n); + a := Split(tt.s, tt.sep, tt.n) if !eq(a, tt.a) { - t.Errorf("Split(%q, %q, %d) = %v; want %v", tt.s, tt.sep, tt.n, a, tt.a); - continue; + t.Errorf("Split(%q, %q, %d) = %v; want %v", tt.s, tt.sep, tt.n, a, tt.a) + continue } - s := Join(a, tt.sep); + s := Join(a, tt.sep) if s != tt.s { t.Errorf("Join(Split(%q, %q, %d), %q) = %q", tt.s, tt.sep, tt.n, tt.sep, s) } @@ -168,12 +168,12 @@ var splitaftertests = []SplitTest{ func TestSplitAfter(t *testing.T) { for _, tt := range splitaftertests { - a := SplitAfter(tt.s, tt.sep, tt.n); + a := SplitAfter(tt.s, tt.sep, tt.n) if !eq(a, tt.a) { - t.Errorf(`Split(%q, %q, %d) = %v; want %v`, tt.s, tt.sep, tt.n, a, tt.a); - continue; + t.Errorf(`Split(%q, %q, %d) = %v; want %v`, tt.s, tt.sep, tt.n, a, tt.a) + continue } - s := Join(a, ""); + s := Join(a, "") if s != tt.s { t.Errorf(`Join(Split(%q, %q, %d), %q) = %q`, tt.s, tt.sep, tt.n, tt.sep, s) } @@ -182,14 +182,14 @@ func TestSplitAfter(t *testing.T) { // Test case for any function which accepts and returns a single string. type StringTest struct { - in, out string; + in, out string } // Execute f on each test case. funcName should be the name of f; it's used // in failure reports. func runStringTests(t *testing.T, f func(string) string, funcName string, testCases []StringTest) { for _, tc := range testCases { - actual := f(tc.in); + actual := f(tc.in) if actual != tc.out { t.Errorf("%s(%q) = %q; want %q", funcName, tc.in, actual, tc.out) } @@ -201,7 +201,7 @@ var upperTests = []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 + StringTest{"\u0250\u0250\u0250\u0250\u0250", "\u2C6F\u2C6F\u2C6F\u2C6F\u2C6F"}, // grows one byte per char } var lowerTests = []StringTest{ @@ -209,7 +209,7 @@ var lowerTests = []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 + StringTest{"\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" @@ -223,59 +223,59 @@ var trimSpaceTests = []StringTest{ 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"}, // invalid UTF-8 on end - StringTest{" x\xc0", "x\xc0"}, // invalid UTF-8 on end + StringTest{" x\x80", "x\x80"}, // invalid UTF-8 on end + StringTest{" x\xc0", "x\xc0"}, // invalid UTF-8 on end } func tenRunes(rune int) string { - r := make([]int, 10); + r := make([]int, 10) for i := range r { r[i] = rune } - return string(r); + return string(r) } // User-defined self-inverse mapping function func rot13(rune int) int { - step := 13; + step := 13 if rune >= 'a' && rune <= 'z' { return ((rune - 'a' + step) % 26) + 'a' } if rune >= 'A' && rune <= 'Z' { return ((rune - 'A' + step) % 26) + 'A' } - return rune; + return rune } func TestMap(t *testing.T) { // Run a couple of awful growth/shrinkage tests - a := tenRunes('a'); + a := tenRunes('a') // 1. Grow. This triggers two reallocations in Map. - maxRune := func(rune int) int { return unicode.MaxRune }; - m := Map(maxRune, a); - expect := tenRunes(unicode.MaxRune); + maxRune := func(rune int) int { return unicode.MaxRune } + m := Map(maxRune, a) + expect := tenRunes(unicode.MaxRune) if m != expect { t.Errorf("growing: expected %q got %q", expect, m) } // 2. Shrink - minRune := func(rune int) int { return 'a' }; - m = Map(minRune, tenRunes(unicode.MaxRune)); - expect = a; + minRune := func(rune int) int { return 'a' } + m = Map(minRune, tenRunes(unicode.MaxRune)) + expect = a if m != expect { t.Errorf("shrinking: expected %q got %q", expect, m) } // 3. Rot13 - m = Map(rot13, "a to zed"); - expect = "n gb mrq"; + m = Map(rot13, "a to zed") + expect = "n gb mrq" if m != expect { t.Errorf("rot13: expected %q got %q", expect, m) } // 4. Rot13^2 - m = Map(rot13, Map(rot13, "a to zed")); - expect = "a to zed"; + m = Map(rot13, Map(rot13, "a to zed")) + expect = "a to zed" if m != expect { t.Errorf("rot13: expected %q got %q", expect, m) } @@ -285,50 +285,50 @@ func TestMap(t *testing.T) { if unicode.Is(unicode.Latin, rune) { return rune } - return -1; - }; - m = Map(dropNotLatin, "Hello, 세계"); - expect = "Hello"; + return -1 + } + m = Map(dropNotLatin, "Hello, 세계") + expect = "Hello" if m != expect { t.Errorf("drop: expected %q got %q", expect, m) } } -func TestToUpper(t *testing.T) { runStringTests(t, ToUpper, "ToUpper", upperTests) } +func TestToUpper(t *testing.T) { runStringTests(t, ToUpper, "ToUpper", upperTests) } -func TestToLower(t *testing.T) { runStringTests(t, ToLower, "ToLower", lowerTests) } +func TestToLower(t *testing.T) { runStringTests(t, ToLower, "ToLower", lowerTests) } -func TestTrimSpace(t *testing.T) { runStringTests(t, TrimSpace, "TrimSpace", trimSpaceTests) } +func TestTrimSpace(t *testing.T) { runStringTests(t, TrimSpace, "TrimSpace", trimSpaceTests) } func equal(m string, s1, s2 string, t *testing.T) bool { if s1 == s2 { return true } - e1 := Split(s1, "", 0); - e2 := Split(s2, "", 0); + e1 := Split(s1, "", 0) + e2 := Split(s2, "", 0) for i, c1 := range e1 { if i > len(e2) { break } - r1, _ := utf8.DecodeRuneInString(c1); - r2, _ := utf8.DecodeRuneInString(e2[i]); + r1, _ := utf8.DecodeRuneInString(c1) + r2, _ := utf8.DecodeRuneInString(e2[i]) if r1 != r2 { t.Errorf("%s diff at %d: U+%04X U+%04X", m, i, r1, r2) } } - return false; + return false } func TestCaseConsistency(t *testing.T) { // Make a string of all the runes. - a := make([]int, unicode.MaxRune+1); + a := make([]int, unicode.MaxRune+1) for i := range a { a[i] = i } - s := string(a); + s := string(a) // convert the cases. - upper := ToUpper(s); - lower := ToLower(s); + upper := ToUpper(s) + lower := ToLower(s) // Consistency checks if n := utf8.RuneCountInString(upper); n != unicode.MaxRune+1 { @@ -360,8 +360,8 @@ func TestCaseConsistency(t *testing.T) { } type RepeatTest struct { - in, out string; - count int; + in, out string + count int } var RepeatTests = []RepeatTest{ @@ -376,10 +376,10 @@ var RepeatTests = []RepeatTest{ func TestRepeat(t *testing.T) { for _, tt := range RepeatTests { - a := Repeat(tt.in, tt.count); + a := Repeat(tt.in, tt.count) if !equal("Repeat(s)", a, tt.out, t) { - t.Errorf("Repeat(%v, %d) = %v; want %v", tt.in, tt.count, a, tt.out); - continue; + t.Errorf("Repeat(%v, %d) = %v; want %v", tt.in, tt.count, a, tt.out) + continue } } } @@ -393,13 +393,13 @@ func runesEqual(a, b []int) bool { return false } } - return true; + return true } type RunesTest struct { - in string; - out []int; - lossy bool; + in string + out []int + lossy bool } var RunesTests = []RunesTest{ @@ -414,14 +414,14 @@ var RunesTests = []RunesTest{ func TestRunes(t *testing.T) { for _, tt := range RunesTests { - a := Runes(tt.in); + a := Runes(tt.in) if !runesEqual(a, tt.out) { - t.Errorf("Runes(%q) = %v; want %v", tt.in, a, tt.out); - continue; + t.Errorf("Runes(%q) = %v; want %v", tt.in, a, tt.out) + continue } if !tt.lossy { // can only test reassembly if we didn't lose information - s := string(a); + s := string(a) if s != tt.in { t.Errorf("string(Runes(%q)) = %x; want %x", tt.in, s, tt.in) } |
