summaryrefslogtreecommitdiff
path: root/src/pkg/unicode
diff options
context:
space:
mode:
Diffstat (limited to 'src/pkg/unicode')
-rw-r--r--src/pkg/unicode/digit.go4
-rw-r--r--src/pkg/unicode/digit_test.go4
-rw-r--r--src/pkg/unicode/letter.go104
-rw-r--r--src/pkg/unicode/letter_test.go16
-rw-r--r--src/pkg/unicode/maketables.go456
-rw-r--r--src/pkg/unicode/script_test.go22
-rw-r--r--src/pkg/unicode/tables.go316
7 files changed, 461 insertions, 461 deletions
diff --git a/src/pkg/unicode/digit.go b/src/pkg/unicode/digit.go
index b12ada2d6..471c4dfdc 100644
--- a/src/pkg/unicode/digit.go
+++ b/src/pkg/unicode/digit.go
@@ -6,8 +6,8 @@ package unicode
// IsDigit reports whether the rune is a decimal digit.
func IsDigit(rune int) bool {
- if rune < 0x100 { // quick ASCII (Latin-1, really) check
+ if rune < 0x100 { // quick ASCII (Latin-1, really) check
return '0' <= rune && rune <= '9'
}
- return Is(Digit, rune);
+ return Is(Digit, rune)
}
diff --git a/src/pkg/unicode/digit_test.go b/src/pkg/unicode/digit_test.go
index 3031eafc8..57a625b02 100644
--- a/src/pkg/unicode/digit_test.go
+++ b/src/pkg/unicode/digit_test.go
@@ -5,8 +5,8 @@
package unicode_test
import (
- "testing";
- . "unicode";
+ "testing"
+ . "unicode"
)
var testDigit = []int{
diff --git a/src/pkg/unicode/letter.go b/src/pkg/unicode/letter.go
index b249f2389..8020cd0cf 100644
--- a/src/pkg/unicode/letter.go
+++ b/src/pkg/unicode/letter.go
@@ -6,17 +6,17 @@
package unicode
const (
- MaxRune = 0x10FFFF; // Maximum valid Unicode code point.
- ReplacementChar = 0xFFFD; // Represents invalid code points.
+ MaxRune = 0x10FFFF // Maximum valid Unicode code point.
+ ReplacementChar = 0xFFFD // Represents invalid code points.
)
// The representation of a range of Unicode code points. The range runs from Lo to Hi
// inclusive and has the specified stride.
type Range struct {
- Lo int;
- Hi int;
- Stride int;
+ Lo int
+ Hi int
+ Stride int
}
// The representation of a range of Unicode code points for case conversion.
@@ -29,26 +29,26 @@ type Range struct {
// {UpperLower, UpperLower, UpperLower}
// The constant UpperLower has an otherwise impossible delta value.
type CaseRange struct {
- Lo int;
- Hi int;
- Delta d;
+ Lo int
+ Hi int
+ Delta d
}
// Indices into the Delta arrays inside CaseRanges for case mapping.
const (
- UpperCase = iota;
- LowerCase;
- TitleCase;
- MaxCase;
+ UpperCase = iota
+ LowerCase
+ TitleCase
+ MaxCase
)
-type d [MaxCase]int32 // to make the CaseRanges text shorter
+type d [MaxCase]int32 // to make the CaseRanges text shorter
// If the Delta field of a CaseRange is UpperLower or LowerUpper, it means
// this CaseRange represents a sequence of the form (say)
// Upper Lower Upper Lower.
const (
- UpperLower = MaxRune + 1; // (Cannot be a valid delta.)
+ UpperLower = MaxRune + 1 // (Cannot be a valid delta.)
)
// Is tests whether rune is in the specified table of ranges.
@@ -62,17 +62,17 @@ func Is(ranges []Range, rune int) bool {
if rune < r.Lo {
return false
}
- return (rune-r.Lo)%r.Stride == 0;
+ return (rune-r.Lo)%r.Stride == 0
}
- return false;
+ return false
}
// binary search over ranges
- lo := 0;
- hi := len(ranges);
+ lo := 0
+ hi := len(ranges)
for lo < hi {
- m := lo + (hi-lo)/2;
- r := ranges[m];
+ m := lo + (hi-lo)/2
+ r := ranges[m]
if r.Lo <= rune && rune <= r.Hi {
return (rune-r.Lo)%r.Stride == 0
}
@@ -82,67 +82,67 @@ func Is(ranges []Range, rune int) bool {
lo = m + 1
}
}
- return false;
+ return false
}
// IsUpper reports whether the rune is an upper case letter.
func IsUpper(rune int) bool {
- if rune < 0x80 { // quick ASCII check
+ if rune < 0x80 { // quick ASCII check
return 'A' <= rune && rune <= 'Z'
}
- return Is(Upper, rune);
+ return Is(Upper, rune)
}
// IsLower reports whether the rune is a lower case letter.
func IsLower(rune int) bool {
- if rune < 0x80 { // quick ASCII check
+ if rune < 0x80 { // quick ASCII check
return 'a' <= rune && rune <= 'z'
}
- return Is(Lower, rune);
+ return Is(Lower, rune)
}
// IsTitle reports whether the rune is a title case letter.
func IsTitle(rune int) bool {
- if rune < 0x80 { // quick ASCII check
+ if rune < 0x80 { // quick ASCII check
return false
}
- return Is(Title, rune);
+ return Is(Title, rune)
}
// IsLetter reports whether the rune is a letter.
func IsLetter(rune int) bool {
- if rune < 0x80 { // quick ASCII check
- rune &^= 'a' - 'A';
- return 'A' <= rune && rune <= 'Z';
+ if rune < 0x80 { // quick ASCII check
+ rune &^= 'a' - 'A'
+ return 'A' <= rune && rune <= 'Z'
}
- return Is(Letter, rune);
+ return Is(Letter, rune)
}
// IsSpace reports whether the rune is a white space character.
func IsSpace(rune int) bool {
- if rune <= 0xFF { // quick Latin-1 check
+ if rune <= 0xFF { // quick Latin-1 check
switch rune {
case '\t', '\n', '\v', '\f', '\r', ' ', 0x85, 0xA0:
return true
}
- return false;
+ return false
}
- return Is(White_Space, rune);
+ return Is(White_Space, rune)
}
// To maps the rune to the specified case: UpperCase, LowerCase, or TitleCase
func To(_case int, rune int) int {
if _case < 0 || MaxCase <= _case {
- return ReplacementChar // as reasonable an error as any
+ return ReplacementChar // as reasonable an error as any
}
// binary search over ranges
- lo := 0;
- hi := len(CaseRanges);
+ lo := 0
+ hi := len(CaseRanges)
for lo < hi {
- m := lo + (hi-lo)/2;
- r := CaseRanges[m];
+ m := lo + (hi-lo)/2
+ r := CaseRanges[m]
if r.Lo <= rune && rune <= r.Hi {
- delta := int(r.Delta[_case]);
+ delta := int(r.Delta[_case])
if delta > MaxRune {
// In an Upper-Lower sequence, which always starts with
// an UpperCase letter, the real deltas always look like:
@@ -156,7 +156,7 @@ func To(_case int, rune int) int {
// is odd so we take the low bit from _case.
return r.Lo + ((rune-r.Lo)&^1 | _case&1)
}
- return rune + delta;
+ return rune + delta
}
if rune < r.Lo {
hi = m
@@ -164,38 +164,38 @@ func To(_case int, rune int) int {
lo = m + 1
}
}
- return rune;
+ return rune
}
// ToUpper maps the rune to upper case
func ToUpper(rune int) int {
- if rune < 0x80 { // quick ASCII check
+ if rune < 0x80 { // quick ASCII check
if 'a' <= rune && rune <= 'z' {
rune -= 'a' - 'A'
}
- return rune;
+ return rune
}
- return To(UpperCase, rune);
+ return To(UpperCase, rune)
}
// ToLower maps the rune to lower case
func ToLower(rune int) int {
- if rune < 0x80 { // quick ASCII check
+ if rune < 0x80 { // quick ASCII check
if 'A' <= rune && rune <= 'Z' {
rune += 'a' - 'A'
}
- return rune;
+ return rune
}
- return To(LowerCase, rune);
+ return To(LowerCase, rune)
}
// ToTitle maps the rune to title case
func ToTitle(rune int) int {
- if rune < 0x80 { // quick ASCII check
- if 'a' <= rune && rune <= 'z' { // title case is upper case for ASCII
+ if rune < 0x80 { // quick ASCII check
+ if 'a' <= rune && rune <= 'z' { // title case is upper case for ASCII
rune -= 'a' - 'A'
}
- return rune;
+ return rune
}
- return To(TitleCase, rune);
+ return To(TitleCase, rune)
}
diff --git a/src/pkg/unicode/letter_test.go b/src/pkg/unicode/letter_test.go
index 8e4f5373e..f39fced66 100644
--- a/src/pkg/unicode/letter_test.go
+++ b/src/pkg/unicode/letter_test.go
@@ -5,8 +5,8 @@
package unicode_test
import (
- "testing";
- . "unicode";
+ "testing"
+ . "unicode"
)
var upperTest = []int{
@@ -107,7 +107,7 @@ var spaceTest = []int{
}
type caseT struct {
- cas, in, out int;
+ cas, in, out int
}
var caseTest = []caseT{
@@ -258,12 +258,12 @@ func caseString(c int) string {
case TitleCase:
return "TitleCase"
}
- return "ErrorCase";
+ return "ErrorCase"
}
func TestTo(t *testing.T) {
for _, c := range caseTest {
- r := To(c.cas, c.in);
+ r := To(c.cas, c.in)
if c.out != r {
t.Errorf("To(U+%04X, %s) = U+%04X want U+%04X\n", c.in, caseString(c.cas), r, c.out)
}
@@ -275,7 +275,7 @@ func TestToUpperCase(t *testing.T) {
if c.cas != UpperCase {
continue
}
- r := ToUpper(c.in);
+ r := ToUpper(c.in)
if c.out != r {
t.Errorf("ToUpper(U+%04X) = U+%04X want U+%04X\n", c.in, r, c.out)
}
@@ -287,7 +287,7 @@ func TestToLowerCase(t *testing.T) {
if c.cas != LowerCase {
continue
}
- r := ToLower(c.in);
+ r := ToLower(c.in)
if c.out != r {
t.Errorf("ToLower(U+%04X) = U+%04X want U+%04X\n", c.in, r, c.out)
}
@@ -299,7 +299,7 @@ func TestToTitleCase(t *testing.T) {
if c.cas != TitleCase {
continue
}
- r := ToTitle(c.in);
+ r := ToTitle(c.in)
if c.out != r {
t.Errorf("ToTitle(U+%04X) = U+%04X want U+%04X\n", c.in, r, c.out)
}
diff --git a/src/pkg/unicode/maketables.go b/src/pkg/unicode/maketables.go
index 486742e64..75d16418e 100644
--- a/src/pkg/unicode/maketables.go
+++ b/src/pkg/unicode/maketables.go
@@ -8,26 +8,26 @@
package main
import (
- "bufio";
- "flag";
- "fmt";
- "http";
- "log";
- "os";
- "sort";
- "strconv";
- "strings";
- "regexp";
- "unicode";
+ "bufio"
+ "flag"
+ "fmt"
+ "http"
+ "log"
+ "os"
+ "sort"
+ "strconv"
+ "strings"
+ "regexp"
+ "unicode"
)
func main() {
- flag.Parse();
- loadChars(); // always needed
- printCategories();
- printScriptOrProperty(false);
- printScriptOrProperty(true);
- printCases();
+ flag.Parse()
+ loadChars() // always needed
+ printCategories()
+ printScriptOrProperty(false)
+ printScriptOrProperty(true)
+ printCases()
}
var dataURL = flag.String("data", "", "full URL for UnicodeData.txt; defaults to --url/UnicodeData.txt")
@@ -53,7 +53,7 @@ var test = flag.Bool("test",
var scriptRe = regexp.MustCompile(`([0-9A-F]+)(\.\.[0-9A-F]+)? *; ([A-Za-z_]+)`)
var die = log.New(os.Stderr, nil, "", log.Lexit|log.Lshortfile)
-var category = map[string]bool{"letter": true} // Nd Lu etc. letter is a special case
+var category = map[string]bool{"letter": true} // Nd Lu etc. letter is a special case
// UnicodeData.txt has form:
// 0037;DIGIT SEVEN;Nd;0;EN;;7;7;7;N;;;;;
@@ -61,24 +61,24 @@ var category = map[string]bool{"letter": true} // Nd Lu etc. letter is a special
// See http://www.unicode.org/Public/5.1.0/ucd/UCD.html for full explanation
// The fields:
const (
- FCodePoint = iota;
- FName;
- FGeneralCategory;
- FCanonicalCombiningClass;
- FBidiClass;
- FDecompositionType;
- FDecompositionMapping;
- FNumericType;
- FNumericValue;
- FBidiMirrored;
- FUnicode1Name;
- FISOComment;
- FSimpleUppercaseMapping;
- FSimpleLowercaseMapping;
- FSimpleTitlecaseMapping;
- NumField;
-
- MaxChar = 0x10FFFF; // anything above this shouldn't exist
+ FCodePoint = iota
+ FName
+ FGeneralCategory
+ FCanonicalCombiningClass
+ FBidiClass
+ FDecompositionType
+ FDecompositionMapping
+ FNumericType
+ FNumericValue
+ FBidiMirrored
+ FUnicode1Name
+ FISOComment
+ FSimpleUppercaseMapping
+ FSimpleLowercaseMapping
+ FSimpleTitlecaseMapping
+ NumField
+
+ MaxChar = 0x10FFFF // anything above this shouldn't exist
)
var fieldName = []string{
@@ -101,12 +101,12 @@ var fieldName = []string{
// This contains only the properties we're interested in.
type Char struct {
- field []string; // debugging only; could be deleted if we take out char.dump()
- codePoint uint32; // if zero, this index is not a valid code point.
- category string;
- upperCase int;
- lowerCase int;
- titleCase int;
+ field []string // debugging only; could be deleted if we take out char.dump()
+ codePoint uint32 // if zero, this index is not a valid code point.
+ category string
+ upperCase int
+ lowerCase int
+ titleCase int
}
// Scripts.txt has form:
@@ -115,13 +115,13 @@ type Char struct {
// See http://www.unicode.org/Public/5.1.0/ucd/UCD.html for full explanation
type Script struct {
- lo, hi uint32; // range of code points
- script string;
+ lo, hi uint32 // range of code points
+ script string
}
var chars = make([]Char, MaxChar+1)
var scripts = make(map[string][]Script)
-var props = make(map[string][]Script) // a property looks like a script; can share the format
+var props = make(map[string][]Script) // a property looks like a script; can share the format
var lastChar uint32 = 0
@@ -132,40 +132,40 @@ var lastChar uint32 = 0
type State int
const (
- SNormal State = iota; // known to be zero for the type
- SFirst;
- SLast;
- SMissing;
+ SNormal State = iota // known to be zero for the type
+ SFirst
+ SLast
+ SMissing
)
func parseCategory(line string) (state State) {
- field := strings.Split(line, ";", -1);
+ field := strings.Split(line, ";", -1)
if len(field) != NumField {
die.Logf("%5s: %d fields (expected %d)\n", line, len(field), NumField)
}
- point, err := strconv.Btoui64(field[FCodePoint], 16);
+ point, err := strconv.Btoui64(field[FCodePoint], 16)
if err != nil {
die.Log("%.5s...:", err)
}
- lastChar = uint32(point);
+ lastChar = uint32(point)
if point == 0 {
- return // not interesting and we use 0 as unset
+ return // not interesting and we use 0 as unset
}
if point > MaxChar {
return
}
- char := &chars[point];
- char.field = field;
+ char := &chars[point]
+ char.field = field
if char.codePoint != 0 {
die.Logf("point U+%04x reused\n")
}
- char.codePoint = lastChar;
- char.category = field[FGeneralCategory];
- category[char.category] = true;
+ char.codePoint = lastChar
+ char.category = field[FGeneralCategory]
+ category[char.category] = true
switch char.category {
case "Nd":
// Decimal digit
- _, err := strconv.Atoi(field[FNumericValue]);
+ _, err := strconv.Atoi(field[FNumericValue])
if err != nil {
die.Log("U+%04x: bad numeric field: %s", point, err)
}
@@ -184,66 +184,66 @@ func parseCategory(line string) (state State) {
case strings.Index(field[FName], ", Last>") > 0:
state = SLast
}
- return;
+ return
}
func (char *Char) dump(s string) {
- fmt.Print(s, " ");
+ fmt.Print(s, " ")
for i := 0; i < len(char.field); i++ {
fmt.Printf("%s:%q ", fieldName[i], char.field[i])
}
- fmt.Print("\n");
+ fmt.Print("\n")
}
func (char *Char) letter(u, l, t string) {
- char.upperCase = char.letterValue(u, "U");
- char.lowerCase = char.letterValue(l, "L");
- char.titleCase = char.letterValue(t, "T");
+ char.upperCase = char.letterValue(u, "U")
+ char.lowerCase = char.letterValue(l, "L")
+ char.titleCase = char.letterValue(t, "T")
}
func (char *Char) letterValue(s string, cas string) int {
if s == "" {
return 0
}
- v, err := strconv.Btoui64(s, 16);
+ v, err := strconv.Btoui64(s, 16)
if err != nil {
- char.dump(cas);
- die.Logf("U+%04x: bad letter(%s): %s", char.codePoint, s, err);
+ char.dump(cas)
+ die.Logf("U+%04x: bad letter(%s): %s", char.codePoint, s, err)
}
- return int(v);
+ return int(v)
}
func allCategories() []string {
- a := make([]string, len(category));
- i := 0;
+ a := make([]string, len(category))
+ i := 0
for k := range category {
- a[i] = k;
- i++;
+ a[i] = k
+ i++
}
- return a;
+ return a
}
func all(scripts map[string][]Script) []string {
- a := make([]string, len(scripts));
- i := 0;
+ a := make([]string, len(scripts))
+ i := 0
for k := range scripts {
- a[i] = k;
- i++;
+ a[i] = k
+ i++
}
- return a;
+ return a
}
// Extract the version number from the URL
func version() string {
// Break on slashes and look for the first numeric field
- fields := strings.Split(*url, "/", 0);
+ fields := strings.Split(*url, "/", 0)
for _, f := range fields {
if len(f) > 0 && '0' <= f[0] && f[0] <= '9' {
return f
}
}
- die.Log("unknown version");
- return "Unknown";
+ die.Log("unknown version")
+ return "Unknown"
}
func letterOp(code int) bool {
@@ -251,29 +251,29 @@ func letterOp(code int) bool {
case "Lu", "Ll", "Lt", "Lm", "Lo":
return true
}
- return false;
+ return false
}
func loadChars() {
if *dataURL == "" {
flag.Set("data", *url+"UnicodeData.txt")
}
- resp, _, err := http.Get(*dataURL);
+ resp, _, err := http.Get(*dataURL)
if err != nil {
die.Log(err)
}
if resp.StatusCode != 200 {
die.Log("bad GET status for UnicodeData.txt", resp.Status)
}
- input := bufio.NewReader(resp.Body);
- var first uint32 = 0;
+ input := bufio.NewReader(resp.Body)
+ var first uint32 = 0
for {
- line, err := input.ReadString('\n');
+ line, err := input.ReadString('\n')
if err != nil {
if err == os.EOF {
break
}
- die.Log(err);
+ die.Log(err)
}
switch parseCategory(line[0 : len(line)-1]) {
case SNormal:
@@ -284,19 +284,19 @@ func loadChars() {
if first != 0 {
die.Logf("bad state first at U+%04X", lastChar)
}
- first = lastChar;
+ first = lastChar
case SLast:
if first == 0 {
die.Logf("bad state last at U+%04X", lastChar)
}
for i := first + 1; i <= lastChar; i++ {
- chars[i] = chars[first];
- chars[i].codePoint = i;
+ chars[i] = chars[first]
+ chars[i].codePoint = i
}
- first = 0;
+ first = 0
}
}
- resp.Body.Close();
+ resp.Body.Close()
}
func printCategories() {
@@ -304,13 +304,13 @@ func printCategories() {
return
}
// Find out which categories to dump
- list := strings.Split(*tablelist, ",", 0);
+ list := strings.Split(*tablelist, ",", 0)
if *tablelist == "all" {
list = allCategories()
}
if *test {
- fullCategoryTest(list);
- return;
+ fullCategoryTest(list)
+ return
}
fmt.Printf(
"// Generated by running\n"+
@@ -318,22 +318,22 @@ func printCategories() {
"// DO NOT EDIT\n\n"+
"package unicode\n\n",
*tablelist,
- *dataURL);
+ *dataURL)
- fmt.Println("// Version is the Unicode edition from which the tables are derived.");
- fmt.Printf("const Version = %q\n\n", version());
+ fmt.Println("// Version is the Unicode edition from which the tables are derived.")
+ fmt.Printf("const Version = %q\n\n", version())
if *tablelist == "all" {
- fmt.Println("// Categories is the set of Unicode data tables.");
- fmt.Println("var Categories = map[string] []Range {");
+ fmt.Println("// Categories is the set of Unicode data tables.")
+ fmt.Println("var Categories = map[string] []Range {")
for k, _ := range category {
fmt.Printf("\t%q: %s,\n", k, k)
}
- fmt.Printf("}\n\n");
+ fmt.Printf("}\n\n")
}
- decl := make(sort.StringArray, len(list));
- ndecl := 0;
+ decl := make(sort.StringArray, len(list))
+ ndecl := 0
for _, name := range list {
if _, ok := category[name]; !ok {
die.Log("unknown category", name)
@@ -342,7 +342,7 @@ func printCategories() {
// name to store the data. This stops godoc dumping all the tables but keeps them
// available to clients.
// Cases deserving special comments
- varDecl := "";
+ varDecl := ""
switch name {
case "letter":
varDecl = "\tLetter = letter; // Letter is the set of Unicode letters.\n"
@@ -360,24 +360,24 @@ func printCategories() {
"\t%s = _%s; // %s is the set of Unicode characters in category %s.\n",
name, name, name, name)
}
- decl[ndecl] = varDecl;
- ndecl++;
- if name == "letter" { // special case
+ decl[ndecl] = varDecl
+ ndecl++
+ if name == "letter" { // special case
dumpRange(
"var letter = []Range {\n",
- letterOp);
- continue;
+ letterOp)
+ continue
}
dumpRange(
fmt.Sprintf("var _%s = []Range {\n", name),
- func(code int) bool { return chars[code].category == name });
+ func(code int) bool { return chars[code].category == name })
}
- decl.Sort();
- fmt.Println("var (");
+ decl.Sort()
+ fmt.Println("var (")
for _, d := range decl {
fmt.Print(d)
}
- fmt.Println(")\n");
+ fmt.Println(")\n")
}
type Op func(code int) bool
@@ -385,8 +385,8 @@ type Op func(code int) bool
const format = "\tRange{0x%04x, 0x%04x, %d},\n"
func dumpRange(header string, inCategory Op) {
- fmt.Print(header);
- next := 0;
+ fmt.Print(header)
+ next := 0
// one Range for each iteration
for {
// look for start of range
@@ -399,22 +399,22 @@ func dumpRange(header string, inCategory Op) {
}
// start of range
- lo := next;
- hi := next;
- stride := 1;
+ lo := next
+ hi := next
+ stride := 1
// accept lo
- next++;
+ next++
// look for another character to set the stride
for next < len(chars) && !inCategory(next) {
next++
}
if next >= len(chars) {
// no more characters
- fmt.Printf(format, lo, hi, stride);
- break;
+ fmt.Printf(format, lo, hi, stride)
+ break
}
// set stride
- stride = next - lo;
+ stride = next - lo
// check for length of run. next points to first jump in stride
for i := next; i < len(chars); i++ {
if inCategory(i) == (((i - lo) % stride) == 0) {
@@ -427,11 +427,11 @@ func dumpRange(header string, inCategory Op) {
break
}
}
- fmt.Printf(format, lo, hi, stride);
+ fmt.Printf(format, lo, hi, stride)
// next range: start looking where this range ends
- next = hi + 1;
+ next = hi + 1
}
- fmt.Print("}\n\n");
+ fmt.Print("}\n\n")
}
func fullCategoryTest(list []string) {
@@ -439,7 +439,7 @@ func fullCategoryTest(list []string) {
if _, ok := category[name]; !ok {
die.Log("unknown category", name)
}
- r, ok := unicode.Categories[name];
+ r, ok := unicode.Categories[name]
if !ok {
die.Log("unknown table", name)
}
@@ -456,8 +456,8 @@ func fullCategoryTest(list []string) {
func verifyRange(name string, inCategory Op, table []unicode.Range) {
for i := range chars {
- web := inCategory(i);
- pkg := unicode.Is(table, i);
+ web := inCategory(i)
+ pkg := unicode.Is(table, i)
if web != pkg {
fmt.Fprintf(os.Stderr, "%s: U+%04X: web=%t pkg=%t\n", name, i, web, pkg)
}
@@ -465,61 +465,61 @@ func verifyRange(name string, inCategory Op, table []unicode.Range) {
}
func parseScript(line string, scripts map[string][]Script) {
- comment := strings.Index(line, "#");
+ comment := strings.Index(line, "#")
if comment >= 0 {
line = line[0:comment]
}
- line = strings.TrimSpace(line);
+ line = strings.TrimSpace(line)
if len(line) == 0 {
return
}
- field := strings.Split(line, ";", -1);
+ field := strings.Split(line, ";", -1)
if len(field) != 2 {
die.Logf("%s: %d fields (expected 2)\n", line, len(field))
}
- matches := scriptRe.MatchStrings(line);
+ matches := scriptRe.MatchStrings(line)
if len(matches) != 4 {
die.Logf("%s: %d matches (expected 3)\n", line, len(matches))
}
- lo, err := strconv.Btoui64(matches[1], 16);
+ lo, err := strconv.Btoui64(matches[1], 16)
if err != nil {
die.Log("%.5s...:", err)
}
- hi := lo;
- if len(matches[2]) > 2 { // ignore leading ..
- hi, err = strconv.Btoui64(matches[2][2:], 16);
+ hi := lo
+ if len(matches[2]) > 2 { // ignore leading ..
+ hi, err = strconv.Btoui64(matches[2][2:], 16)
if err != nil {
die.Log("%.5s...:", err)
}
}
- name := matches[3];
- s, ok := scripts[name];
+ name := matches[3]
+ s, ok := scripts[name]
if !ok || len(s) == cap(s) {
- ns := make([]Script, len(s), len(s)+100);
+ ns := make([]Script, len(s), len(s)+100)
for i, sc := range s {
ns[i] = sc
}
- s = ns;
+ s = ns
}
- s = s[0 : len(s)+1];
- s[len(s)-1] = Script{uint32(lo), uint32(hi), name};
- scripts[name] = s;
+ s = s[0 : len(s)+1]
+ s[len(s)-1] = Script{uint32(lo), uint32(hi), name}
+ scripts[name] = s
}
// The script tables have a lot of adjacent elements. Fold them together.
func foldAdjacent(r []Script) []unicode.Range {
- s := make([]unicode.Range, 0, len(r));
- j := 0;
+ s := make([]unicode.Range, 0, len(r))
+ j := 0
for i := 0; i < len(r); i++ {
if j > 0 && int(r[i].lo) == s[j-1].Hi+1 {
s[j-1].Hi = int(r[i].hi)
} else {
- s = s[0 : j+1];
- s[j] = unicode.Range{int(r[i].lo), int(r[i].hi), 1};
- j++;
+ s = s[0 : j+1]
+ s[j] = unicode.Range{int(r[i].lo), int(r[i].hi), 1}
+ j++
}
}
- return s;
+ return s
}
func fullScriptTest(list []string, installed map[string][]unicode.Range, scripts map[string][]Script) {
@@ -527,7 +527,7 @@ func fullScriptTest(list []string, installed map[string][]unicode.Range, scripts
if _, ok := scripts[name]; !ok {
die.Log("unknown script", name)
}
- _, ok := installed[name];
+ _, ok := installed[name]
if !ok {
die.Log("unknown table", name)
}
@@ -543,50 +543,50 @@ func fullScriptTest(list []string, installed map[string][]unicode.Range, scripts
// PropList.txt has the same format as Scripts.txt so we can share its parser.
func printScriptOrProperty(doProps bool) {
- flag := "scripts";
- flaglist := *scriptlist;
- file := "Scripts.txt";
- table := scripts;
- installed := unicode.Scripts;
+ flag := "scripts"
+ flaglist := *scriptlist
+ file := "Scripts.txt"
+ table := scripts
+ installed := unicode.Scripts
if doProps {
- flag = "props";
- flaglist = *proplist;
- file = "PropList.txt";
- table = props;
- installed = unicode.Properties;
+ flag = "props"
+ flaglist = *proplist
+ file = "PropList.txt"
+ table = props
+ installed = unicode.Properties
}
if flaglist == "" {
return
}
- var err os.Error;
- resp, _, err := http.Get(*url + file);
+ var err os.Error
+ resp, _, err := http.Get(*url + file)
if err != nil {
die.Log(err)
}
if resp.StatusCode != 200 {
die.Log("bad GET status for ", file, ":", resp.Status)
}
- input := bufio.NewReader(resp.Body);
+ input := bufio.NewReader(resp.Body)
for {
- line, err := input.ReadString('\n');
+ line, err := input.ReadString('\n')
if err != nil {
if err == os.EOF {
break
}
- die.Log(err);
+ die.Log(err)
}
- parseScript(line[0:len(line)-1], table);
+ parseScript(line[0:len(line)-1], table)
}
- resp.Body.Close();
+ resp.Body.Close()
// Find out which scripts to dump
- list := strings.Split(flaglist, ",", 0);
+ list := strings.Split(flaglist, ",", 0)
if flaglist == "all" {
list = all(table)
}
if *test {
- fullScriptTest(list, installed, table);
- return;
+ fullScriptTest(list, installed, table)
+ return
}
fmt.Printf(
@@ -595,23 +595,23 @@ func printScriptOrProperty(doProps bool) {
"// DO NOT EDIT\n\n",
flag,
flaglist,
- *url);
+ *url)
if flaglist == "all" {
if doProps {
- fmt.Println("// Properties is the set of Unicode property tables.");
- fmt.Println("var Properties = map[string] []Range {");
+ fmt.Println("// Properties is the set of Unicode property tables.")
+ fmt.Println("var Properties = map[string] []Range {")
} else {
- fmt.Println("// Scripts is the set of Unicode script tables.");
- fmt.Println("var Scripts = map[string] []Range {");
+ fmt.Println("// Scripts is the set of Unicode script tables.")
+ fmt.Println("var Scripts = map[string] []Range {")
}
for k, _ := range table {
fmt.Printf("\t%q: %s,\n", k, k)
}
- fmt.Printf("}\n\n");
+ fmt.Printf("}\n\n")
}
- decl := make(sort.StringArray, len(list));
- ndecl := 0;
+ decl := make(sort.StringArray, len(list))
+ ndecl := 0
for _, name := range list {
if doProps {
decl[ndecl] = fmt.Sprintf(
@@ -622,36 +622,36 @@ func printScriptOrProperty(doProps bool) {
"\t%s = _%s;\t// %s is the set of Unicode characters in script %s.\n",
name, name, name, name)
}
- ndecl++;
- fmt.Printf("var _%s = []Range {\n", name);
- ranges := foldAdjacent(table[name]);
+ ndecl++
+ fmt.Printf("var _%s = []Range {\n", name)
+ ranges := foldAdjacent(table[name])
for _, s := range ranges {
fmt.Printf(format, s.Lo, s.Hi, s.Stride)
}
- fmt.Printf("}\n\n");
+ fmt.Printf("}\n\n")
}
- decl.Sort();
- fmt.Println("var (");
+ decl.Sort()
+ fmt.Println("var (")
for _, d := range decl {
fmt.Print(d)
}
- fmt.Println(")\n");
+ fmt.Println(")\n")
}
const (
- CaseUpper = 1 << iota;
- CaseLower;
- CaseTitle;
- CaseNone = 0; // must be zero
- CaseMissing = -1; // character not present; not a valid case state
+ CaseUpper = 1 << iota
+ CaseLower
+ CaseTitle
+ CaseNone = 0 // must be zero
+ CaseMissing = -1 // character not present; not a valid case state
)
type caseState struct {
- point int;
- _case int;
- deltaToUpper int;
- deltaToLower int;
- deltaToTitle int;
+ point int
+ _case int
+ deltaToUpper int
+ deltaToLower int
+ deltaToTitle int
}
// Is d a continuation of the state of c?
@@ -660,9 +660,9 @@ func (c *caseState) adjacent(d *caseState) bool {
c, d = d, c
}
switch {
- case d.point != c.point+1: // code points not adjacent (shouldn't happen)
+ case d.point != c.point+1: // code points not adjacent (shouldn't happen)
return false
- case d._case != c._case: // different cases
+ case d._case != c._case: // different cases
return c.upperLowerAdjacent(d)
case c._case == CaseNone:
return false
@@ -675,7 +675,7 @@ func (c *caseState) adjacent(d *caseState) bool {
case d.deltaToTitle != c.deltaToTitle:
return false
}
- return true;
+ return true
}
// Is d the same as c, but opposite in upper/lower case? this would make it
@@ -709,7 +709,7 @@ func (c *caseState) upperLowerAdjacent(d *caseState) bool {
case d.deltaToTitle != -1:
return false
}
- return true;
+ return true
}
// Does this character start an UpperLower sequence?
@@ -724,7 +724,7 @@ func (c *caseState) isUpperLower() bool {
case c.deltaToTitle != 0:
return false
}
- return true;
+ return true
}
// Does this character start a LowerUpper sequence?
@@ -739,16 +739,16 @@ func (c *caseState) isLowerUpper() bool {
case c.deltaToTitle != -1:
return false
}
- return true;
+ return true
}
func getCaseState(i int) (c *caseState) {
- c = &caseState{point: i, _case: CaseNone};
- ch := &chars[i];
+ c = &caseState{point: i, _case: CaseNone}
+ ch := &chars[i]
switch int(ch.codePoint) {
case 0:
- c._case = CaseMissing; // Will get NUL wrong but that doesn't matter
- return;
+ c._case = CaseMissing // Will get NUL wrong but that doesn't matter
+ return
case ch.upperCase:
c._case = CaseUpper
case ch.lowerCase:
@@ -765,7 +765,7 @@ func getCaseState(i int) (c *caseState) {
if ch.titleCase != 0 {
c.deltaToTitle = ch.titleCase - i
}
- return;
+ return
}
func printCases() {
@@ -773,8 +773,8 @@ func printCases() {
return
}
if *test {
- fullCaseTest();
- return;
+ fullCaseTest()
+ return
}
fmt.Printf(
"// Generated by running\n"+
@@ -784,25 +784,25 @@ func printCases() {
"// non-self mappings.\n"+
"var CaseRanges = _CaseRanges\n"+
"var _CaseRanges = []CaseRange {\n",
- *dataURL);
+ *dataURL)
- var startState *caseState; // the start of a run; nil for not active
- var prevState = &caseState{}; // the state of the previous character
+ var startState *caseState // the start of a run; nil for not active
+ var prevState = &caseState{} // the state of the previous character
for i := range chars {
- state := getCaseState(i);
+ state := getCaseState(i)
if state.adjacent(prevState) {
- prevState = state;
- continue;
+ prevState = state
+ continue
}
// end of run (possibly)
- printCaseRange(startState, prevState);
- startState = nil;
+ printCaseRange(startState, prevState)
+ startState = nil
if state._case != CaseMissing && state._case != CaseNone {
startState = state
}
- prevState = state;
+ prevState = state
}
- fmt.Printf("}\n");
+ fmt.Printf("}\n")
}
func printCaseRange(lo, hi *caseState) {
@@ -818,9 +818,9 @@ func printCaseRange(lo, hi *caseState) {
fmt.Printf("\tCaseRange{0x%04X, 0x%04X, d{UpperLower, UpperLower, UpperLower}},\n",
lo.point, hi.point)
case hi.point > lo.point && lo.isLowerUpper():
- die.Log("LowerUpper sequence: should not happen: U+%04X. If it's real, need to fix To()", lo.point);
+ die.Log("LowerUpper sequence: should not happen: U+%04X. If it's real, need to fix To()", lo.point)
fmt.Printf("\tCaseRange{0x%04X, 0x%04X, d{LowerUpper, LowerUpper, LowerUpper}},\n",
- lo.point, hi.point);
+ lo.point, hi.point)
default:
fmt.Printf("\tCaseRange{0x%04X, 0x%04X, d{%d, %d, %d}},\n",
lo.point, hi.point,
@@ -833,23 +833,23 @@ func caseIt(rune, cased int) int {
if cased == 0 {
return rune
}
- return cased;
+ return cased
}
func fullCaseTest() {
for i, c := range chars {
- lower := unicode.ToLower(i);
- want := caseIt(i, c.lowerCase);
+ lower := unicode.ToLower(i)
+ want := caseIt(i, c.lowerCase)
if lower != want {
fmt.Fprintf(os.Stderr, "lower U+%04X should be U+%04X is U+%04X\n", i, want, lower)
}
- upper := unicode.ToUpper(i);
- want = caseIt(i, c.upperCase);
+ upper := unicode.ToUpper(i)
+ want = caseIt(i, c.upperCase)
if upper != want {
fmt.Fprintf(os.Stderr, "upper U+%04X should be U+%04X is U+%04X\n", i, want, upper)
}
- title := unicode.ToTitle(i);
- want = caseIt(i, c.titleCase);
+ title := unicode.ToTitle(i)
+ want = caseIt(i, c.titleCase)
if title != want {
fmt.Fprintf(os.Stderr, "title U+%04X should be U+%04X is U+%04X\n", i, want, title)
}
diff --git a/src/pkg/unicode/script_test.go b/src/pkg/unicode/script_test.go
index 316de2d25..b3e980b1c 100644
--- a/src/pkg/unicode/script_test.go
+++ b/src/pkg/unicode/script_test.go
@@ -5,13 +5,13 @@
package unicode_test
import (
- "testing";
- . "unicode";
+ "testing"
+ . "unicode"
)
type T struct {
- rune int;
- script string;
+ rune int
+ script string
}
// Hand-chosen tests from Unicode 5.1.0, mostly to discover when new
@@ -112,7 +112,7 @@ var inTest = []T{
T{0xa216, "Yi"},
}
-var outTest = []T{ // not really worth being thorough
+var outTest = []T{ // not really worth being thorough
T{0x20, "Telugu"},
}
@@ -185,7 +185,7 @@ var inPropTest = []T{
}
func TestScripts(t *testing.T) {
- notTested := make(map[string]bool);
+ notTested := make(map[string]bool)
for k := range Scripts {
notTested[k] = true
}
@@ -196,7 +196,7 @@ func TestScripts(t *testing.T) {
if !Is(Scripts[test.script], test.rune) {
t.Errorf("IsScript(%#x, %s) = false, want true\n", test.rune, test.script)
}
- notTested[test.script] = false, false;
+ notTested[test.script] = false, false
}
for _, test := range outTest {
if Is(Scripts[test.script], test.rune) {
@@ -209,7 +209,7 @@ func TestScripts(t *testing.T) {
}
func TestCategories(t *testing.T) {
- notTested := make(map[string]bool);
+ notTested := make(map[string]bool)
for k := range Categories {
notTested[k] = true
}
@@ -220,7 +220,7 @@ func TestCategories(t *testing.T) {
if !Is(Categories[test.script], test.rune) {
t.Errorf("IsCategory(%#x, %s) = false, want true\n", test.rune, test.script)
}
- notTested[test.script] = false, false;
+ notTested[test.script] = false, false
}
for k := range notTested {
t.Error("not tested:", k)
@@ -228,7 +228,7 @@ func TestCategories(t *testing.T) {
}
func TestProperties(t *testing.T) {
- notTested := make(map[string]bool);
+ notTested := make(map[string]bool)
for k := range Properties {
notTested[k] = true
}
@@ -239,7 +239,7 @@ func TestProperties(t *testing.T) {
if !Is(Properties[test.script], test.rune) {
t.Errorf("IsCategory(%#x, %s) = false, want true\n", test.rune, test.script)
}
- notTested[test.script] = false, false;
+ notTested[test.script] = false, false
}
for k := range notTested {
t.Error("not tested:", k)
diff --git a/src/pkg/unicode/tables.go b/src/pkg/unicode/tables.go
index 4a4dbe02b..10e4fae6d 100644
--- a/src/pkg/unicode/tables.go
+++ b/src/pkg/unicode/tables.go
@@ -1921,40 +1921,40 @@ var _Lo = []Range{
}
var (
- Cc = _Cc; // Cc is the set of Unicode characters in category Cc.
- Cf = _Cf; // Cf is the set of Unicode characters in category Cf.
- Co = _Co; // Co is the set of Unicode characters in category Co.
- Cs = _Cs; // Cs is the set of Unicode characters in category Cs.
- Digit = _Nd; // Digit is the set of Unicode characters with the "decimal digit" property.
- Nd = _Nd; // Nd is the set of Unicode characters in category Nd.
- Letter = letter; // Letter is the set of Unicode letters.
- Lm = _Lm; // Lm is the set of Unicode characters in category Lm.
- Lo = _Lo; // Lo is the set of Unicode characters in category Lo.
- Lower = _Ll; // Lower is the set of Unicode lower case letters.
- Ll = _Ll; // Ll is the set of Unicode characters in category Ll.
- Mc = _Mc; // Mc is the set of Unicode characters in category Mc.
- Me = _Me; // Me is the set of Unicode characters in category Me.
- Mn = _Mn; // Mn is the set of Unicode characters in category Mn.
- Nl = _Nl; // Nl is the set of Unicode characters in category Nl.
- No = _No; // No is the set of Unicode characters in category No.
- Pc = _Pc; // Pc is the set of Unicode characters in category Pc.
- Pd = _Pd; // Pd is the set of Unicode characters in category Pd.
- Pe = _Pe; // Pe is the set of Unicode characters in category Pe.
- Pf = _Pf; // Pf is the set of Unicode characters in category Pf.
- Pi = _Pi; // Pi is the set of Unicode characters in category Pi.
- Po = _Po; // Po is the set of Unicode characters in category Po.
- Ps = _Ps; // Ps is the set of Unicode characters in category Ps.
- Sc = _Sc; // Sc is the set of Unicode characters in category Sc.
- Sk = _Sk; // Sk is the set of Unicode characters in category Sk.
- Sm = _Sm; // Sm is the set of Unicode characters in category Sm.
- So = _So; // So is the set of Unicode characters in category So.
- Title = _Lt; // Title is the set of Unicode title case letters.
- Lt = _Lt; // Lt is the set of Unicode characters in category Lt.
- Upper = _Lu; // Upper is the set of Unicode upper case letters.
- Lu = _Lu; // Lu is the set of Unicode characters in category Lu.
- Zl = _Zl; // Zl is the set of Unicode characters in category Zl.
- Zp = _Zp; // Zp is the set of Unicode characters in category Zp.
- Zs = _Zs; // Zs is the set of Unicode characters in category Zs.
+ Cc = _Cc // Cc is the set of Unicode characters in category Cc.
+ Cf = _Cf // Cf is the set of Unicode characters in category Cf.
+ Co = _Co // Co is the set of Unicode characters in category Co.
+ Cs = _Cs // Cs is the set of Unicode characters in category Cs.
+ Digit = _Nd // Digit is the set of Unicode characters with the "decimal digit" property.
+ Nd = _Nd // Nd is the set of Unicode characters in category Nd.
+ Letter = letter // Letter is the set of Unicode letters.
+ Lm = _Lm // Lm is the set of Unicode characters in category Lm.
+ Lo = _Lo // Lo is the set of Unicode characters in category Lo.
+ Lower = _Ll // Lower is the set of Unicode lower case letters.
+ Ll = _Ll // Ll is the set of Unicode characters in category Ll.
+ Mc = _Mc // Mc is the set of Unicode characters in category Mc.
+ Me = _Me // Me is the set of Unicode characters in category Me.
+ Mn = _Mn // Mn is the set of Unicode characters in category Mn.
+ Nl = _Nl // Nl is the set of Unicode characters in category Nl.
+ No = _No // No is the set of Unicode characters in category No.
+ Pc = _Pc // Pc is the set of Unicode characters in category Pc.
+ Pd = _Pd // Pd is the set of Unicode characters in category Pd.
+ Pe = _Pe // Pe is the set of Unicode characters in category Pe.
+ Pf = _Pf // Pf is the set of Unicode characters in category Pf.
+ Pi = _Pi // Pi is the set of Unicode characters in category Pi.
+ Po = _Po // Po is the set of Unicode characters in category Po.
+ Ps = _Ps // Ps is the set of Unicode characters in category Ps.
+ Sc = _Sc // Sc is the set of Unicode characters in category Sc.
+ Sk = _Sk // Sk is the set of Unicode characters in category Sk.
+ Sm = _Sm // Sm is the set of Unicode characters in category Sm.
+ So = _So // So is the set of Unicode characters in category So.
+ Title = _Lt // Title is the set of Unicode title case letters.
+ Lt = _Lt // Lt is the set of Unicode characters in category Lt.
+ Upper = _Lu // Upper is the set of Unicode upper case letters.
+ Lu = _Lu // Lu is the set of Unicode characters in category Lu.
+ Zl = _Zl // Zl is the set of Unicode characters in category Zl.
+ Zp = _Zp // Zp is the set of Unicode characters in category Zp.
+ Zs = _Zs // Zs is the set of Unicode characters in category Zs.
)
// Generated by running
@@ -2990,98 +2990,98 @@ var _Gothic = []Range{
}
var (
- Arabic = _Arabic; // Arabic is the set of Unicode characters in script Arabic.
- Armenian = _Armenian; // Armenian is the set of Unicode characters in script Armenian.
- Avestan = _Avestan; // Avestan is the set of Unicode characters in script Avestan.
- Balinese = _Balinese; // Balinese is the set of Unicode characters in script Balinese.
- Bamum = _Bamum; // Bamum is the set of Unicode characters in script Bamum.
- Bengali = _Bengali; // Bengali is the set of Unicode characters in script Bengali.
- Bopomofo = _Bopomofo; // Bopomofo is the set of Unicode characters in script Bopomofo.
- Braille = _Braille; // Braille is the set of Unicode characters in script Braille.
- Buginese = _Buginese; // Buginese is the set of Unicode characters in script Buginese.
- Buhid = _Buhid; // Buhid is the set of Unicode characters in script Buhid.
- Canadian_Aboriginal = _Canadian_Aboriginal; // Canadian_Aboriginal is the set of Unicode characters in script Canadian_Aboriginal.
- Carian = _Carian; // Carian is the set of Unicode characters in script Carian.
- Cham = _Cham; // Cham is the set of Unicode characters in script Cham.
- Cherokee = _Cherokee; // Cherokee is the set of Unicode characters in script Cherokee.
- Common = _Common; // Common is the set of Unicode characters in script Common.
- Coptic = _Coptic; // Coptic is the set of Unicode characters in script Coptic.
- Cuneiform = _Cuneiform; // Cuneiform is the set of Unicode characters in script Cuneiform.
- Cypriot = _Cypriot; // Cypriot is the set of Unicode characters in script Cypriot.
- Cyrillic = _Cyrillic; // Cyrillic is the set of Unicode characters in script Cyrillic.
- Deseret = _Deseret; // Deseret is the set of Unicode characters in script Deseret.
- Devanagari = _Devanagari; // Devanagari is the set of Unicode characters in script Devanagari.
- Egyptian_Hieroglyphs = _Egyptian_Hieroglyphs; // Egyptian_Hieroglyphs is the set of Unicode characters in script Egyptian_Hieroglyphs.
- Ethiopic = _Ethiopic; // Ethiopic is the set of Unicode characters in script Ethiopic.
- Georgian = _Georgian; // Georgian is the set of Unicode characters in script Georgian.
- Glagolitic = _Glagolitic; // Glagolitic is the set of Unicode characters in script Glagolitic.
- Gothic = _Gothic; // Gothic is the set of Unicode characters in script Gothic.
- Greek = _Greek; // Greek is the set of Unicode characters in script Greek.
- Gujarati = _Gujarati; // Gujarati is the set of Unicode characters in script Gujarati.
- Gurmukhi = _Gurmukhi; // Gurmukhi is the set of Unicode characters in script Gurmukhi.
- Han = _Han; // Han is the set of Unicode characters in script Han.
- Hangul = _Hangul; // Hangul is the set of Unicode characters in script Hangul.
- Hanunoo = _Hanunoo; // Hanunoo is the set of Unicode characters in script Hanunoo.
- Hebrew = _Hebrew; // Hebrew is the set of Unicode characters in script Hebrew.
- Hiragana = _Hiragana; // Hiragana is the set of Unicode characters in script Hiragana.
- Imperial_Aramaic = _Imperial_Aramaic; // Imperial_Aramaic is the set of Unicode characters in script Imperial_Aramaic.
- Inherited = _Inherited; // Inherited is the set of Unicode characters in script Inherited.
- Inscriptional_Pahlavi = _Inscriptional_Pahlavi; // Inscriptional_Pahlavi is the set of Unicode characters in script Inscriptional_Pahlavi.
- Inscriptional_Parthian = _Inscriptional_Parthian; // Inscriptional_Parthian is the set of Unicode characters in script Inscriptional_Parthian.
- Javanese = _Javanese; // Javanese is the set of Unicode characters in script Javanese.
- Kaithi = _Kaithi; // Kaithi is the set of Unicode characters in script Kaithi.
- Kannada = _Kannada; // Kannada is the set of Unicode characters in script Kannada.
- Katakana = _Katakana; // Katakana is the set of Unicode characters in script Katakana.
- Kayah_Li = _Kayah_Li; // Kayah_Li is the set of Unicode characters in script Kayah_Li.
- Kharoshthi = _Kharoshthi; // Kharoshthi is the set of Unicode characters in script Kharoshthi.
- Khmer = _Khmer; // Khmer is the set of Unicode characters in script Khmer.
- Lao = _Lao; // Lao is the set of Unicode characters in script Lao.
- Latin = _Latin; // Latin is the set of Unicode characters in script Latin.
- Lepcha = _Lepcha; // Lepcha is the set of Unicode characters in script Lepcha.
- Limbu = _Limbu; // Limbu is the set of Unicode characters in script Limbu.
- Linear_B = _Linear_B; // Linear_B is the set of Unicode characters in script Linear_B.
- Lisu = _Lisu; // Lisu is the set of Unicode characters in script Lisu.
- Lycian = _Lycian; // Lycian is the set of Unicode characters in script Lycian.
- Lydian = _Lydian; // Lydian is the set of Unicode characters in script Lydian.
- Malayalam = _Malayalam; // Malayalam is the set of Unicode characters in script Malayalam.
- Meetei_Mayek = _Meetei_Mayek; // Meetei_Mayek is the set of Unicode characters in script Meetei_Mayek.
- Mongolian = _Mongolian; // Mongolian is the set of Unicode characters in script Mongolian.
- Myanmar = _Myanmar; // Myanmar is the set of Unicode characters in script Myanmar.
- New_Tai_Lue = _New_Tai_Lue; // New_Tai_Lue is the set of Unicode characters in script New_Tai_Lue.
- Nko = _Nko; // Nko is the set of Unicode characters in script Nko.
- Ogham = _Ogham; // Ogham is the set of Unicode characters in script Ogham.
- Ol_Chiki = _Ol_Chiki; // Ol_Chiki is the set of Unicode characters in script Ol_Chiki.
- Old_Italic = _Old_Italic; // Old_Italic is the set of Unicode characters in script Old_Italic.
- Old_Persian = _Old_Persian; // Old_Persian is the set of Unicode characters in script Old_Persian.
- Old_South_Arabian = _Old_South_Arabian; // Old_South_Arabian is the set of Unicode characters in script Old_South_Arabian.
- Old_Turkic = _Old_Turkic; // Old_Turkic is the set of Unicode characters in script Old_Turkic.
- Oriya = _Oriya; // Oriya is the set of Unicode characters in script Oriya.
- Osmanya = _Osmanya; // Osmanya is the set of Unicode characters in script Osmanya.
- Phags_Pa = _Phags_Pa; // Phags_Pa is the set of Unicode characters in script Phags_Pa.
- Phoenician = _Phoenician; // Phoenician is the set of Unicode characters in script Phoenician.
- Rejang = _Rejang; // Rejang is the set of Unicode characters in script Rejang.
- Runic = _Runic; // Runic is the set of Unicode characters in script Runic.
- Samaritan = _Samaritan; // Samaritan is the set of Unicode characters in script Samaritan.
- Saurashtra = _Saurashtra; // Saurashtra is the set of Unicode characters in script Saurashtra.
- Shavian = _Shavian; // Shavian is the set of Unicode characters in script Shavian.
- Sinhala = _Sinhala; // Sinhala is the set of Unicode characters in script Sinhala.
- Sundanese = _Sundanese; // Sundanese is the set of Unicode characters in script Sundanese.
- Syloti_Nagri = _Syloti_Nagri; // Syloti_Nagri is the set of Unicode characters in script Syloti_Nagri.
- Syriac = _Syriac; // Syriac is the set of Unicode characters in script Syriac.
- Tagalog = _Tagalog; // Tagalog is the set of Unicode characters in script Tagalog.
- Tagbanwa = _Tagbanwa; // Tagbanwa is the set of Unicode characters in script Tagbanwa.
- Tai_Le = _Tai_Le; // Tai_Le is the set of Unicode characters in script Tai_Le.
- Tai_Tham = _Tai_Tham; // Tai_Tham is the set of Unicode characters in script Tai_Tham.
- Tai_Viet = _Tai_Viet; // Tai_Viet is the set of Unicode characters in script Tai_Viet.
- Tamil = _Tamil; // Tamil is the set of Unicode characters in script Tamil.
- Telugu = _Telugu; // Telugu is the set of Unicode characters in script Telugu.
- Thaana = _Thaana; // Thaana is the set of Unicode characters in script Thaana.
- Thai = _Thai; // Thai is the set of Unicode characters in script Thai.
- Tibetan = _Tibetan; // Tibetan is the set of Unicode characters in script Tibetan.
- Tifinagh = _Tifinagh; // Tifinagh is the set of Unicode characters in script Tifinagh.
- Ugaritic = _Ugaritic; // Ugaritic is the set of Unicode characters in script Ugaritic.
- Vai = _Vai; // Vai is the set of Unicode characters in script Vai.
- Yi = _Yi; // Yi is the set of Unicode characters in script Yi.
+ Arabic = _Arabic // Arabic is the set of Unicode characters in script Arabic.
+ Armenian = _Armenian // Armenian is the set of Unicode characters in script Armenian.
+ Avestan = _Avestan // Avestan is the set of Unicode characters in script Avestan.
+ Balinese = _Balinese // Balinese is the set of Unicode characters in script Balinese.
+ Bamum = _Bamum // Bamum is the set of Unicode characters in script Bamum.
+ Bengali = _Bengali // Bengali is the set of Unicode characters in script Bengali.
+ Bopomofo = _Bopomofo // Bopomofo is the set of Unicode characters in script Bopomofo.
+ Braille = _Braille // Braille is the set of Unicode characters in script Braille.
+ Buginese = _Buginese // Buginese is the set of Unicode characters in script Buginese.
+ Buhid = _Buhid // Buhid is the set of Unicode characters in script Buhid.
+ Canadian_Aboriginal = _Canadian_Aboriginal // Canadian_Aboriginal is the set of Unicode characters in script Canadian_Aboriginal.
+ Carian = _Carian // Carian is the set of Unicode characters in script Carian.
+ Cham = _Cham // Cham is the set of Unicode characters in script Cham.
+ Cherokee = _Cherokee // Cherokee is the set of Unicode characters in script Cherokee.
+ Common = _Common // Common is the set of Unicode characters in script Common.
+ Coptic = _Coptic // Coptic is the set of Unicode characters in script Coptic.
+ Cuneiform = _Cuneiform // Cuneiform is the set of Unicode characters in script Cuneiform.
+ Cypriot = _Cypriot // Cypriot is the set of Unicode characters in script Cypriot.
+ Cyrillic = _Cyrillic // Cyrillic is the set of Unicode characters in script Cyrillic.
+ Deseret = _Deseret // Deseret is the set of Unicode characters in script Deseret.
+ Devanagari = _Devanagari // Devanagari is the set of Unicode characters in script Devanagari.
+ Egyptian_Hieroglyphs = _Egyptian_Hieroglyphs // Egyptian_Hieroglyphs is the set of Unicode characters in script Egyptian_Hieroglyphs.
+ Ethiopic = _Ethiopic // Ethiopic is the set of Unicode characters in script Ethiopic.
+ Georgian = _Georgian // Georgian is the set of Unicode characters in script Georgian.
+ Glagolitic = _Glagolitic // Glagolitic is the set of Unicode characters in script Glagolitic.
+ Gothic = _Gothic // Gothic is the set of Unicode characters in script Gothic.
+ Greek = _Greek // Greek is the set of Unicode characters in script Greek.
+ Gujarati = _Gujarati // Gujarati is the set of Unicode characters in script Gujarati.
+ Gurmukhi = _Gurmukhi // Gurmukhi is the set of Unicode characters in script Gurmukhi.
+ Han = _Han // Han is the set of Unicode characters in script Han.
+ Hangul = _Hangul // Hangul is the set of Unicode characters in script Hangul.
+ Hanunoo = _Hanunoo // Hanunoo is the set of Unicode characters in script Hanunoo.
+ Hebrew = _Hebrew // Hebrew is the set of Unicode characters in script Hebrew.
+ Hiragana = _Hiragana // Hiragana is the set of Unicode characters in script Hiragana.
+ Imperial_Aramaic = _Imperial_Aramaic // Imperial_Aramaic is the set of Unicode characters in script Imperial_Aramaic.
+ Inherited = _Inherited // Inherited is the set of Unicode characters in script Inherited.
+ Inscriptional_Pahlavi = _Inscriptional_Pahlavi // Inscriptional_Pahlavi is the set of Unicode characters in script Inscriptional_Pahlavi.
+ Inscriptional_Parthian = _Inscriptional_Parthian // Inscriptional_Parthian is the set of Unicode characters in script Inscriptional_Parthian.
+ Javanese = _Javanese // Javanese is the set of Unicode characters in script Javanese.
+ Kaithi = _Kaithi // Kaithi is the set of Unicode characters in script Kaithi.
+ Kannada = _Kannada // Kannada is the set of Unicode characters in script Kannada.
+ Katakana = _Katakana // Katakana is the set of Unicode characters in script Katakana.
+ Kayah_Li = _Kayah_Li // Kayah_Li is the set of Unicode characters in script Kayah_Li.
+ Kharoshthi = _Kharoshthi // Kharoshthi is the set of Unicode characters in script Kharoshthi.
+ Khmer = _Khmer // Khmer is the set of Unicode characters in script Khmer.
+ Lao = _Lao // Lao is the set of Unicode characters in script Lao.
+ Latin = _Latin // Latin is the set of Unicode characters in script Latin.
+ Lepcha = _Lepcha // Lepcha is the set of Unicode characters in script Lepcha.
+ Limbu = _Limbu // Limbu is the set of Unicode characters in script Limbu.
+ Linear_B = _Linear_B // Linear_B is the set of Unicode characters in script Linear_B.
+ Lisu = _Lisu // Lisu is the set of Unicode characters in script Lisu.
+ Lycian = _Lycian // Lycian is the set of Unicode characters in script Lycian.
+ Lydian = _Lydian // Lydian is the set of Unicode characters in script Lydian.
+ Malayalam = _Malayalam // Malayalam is the set of Unicode characters in script Malayalam.
+ Meetei_Mayek = _Meetei_Mayek // Meetei_Mayek is the set of Unicode characters in script Meetei_Mayek.
+ Mongolian = _Mongolian // Mongolian is the set of Unicode characters in script Mongolian.
+ Myanmar = _Myanmar // Myanmar is the set of Unicode characters in script Myanmar.
+ New_Tai_Lue = _New_Tai_Lue // New_Tai_Lue is the set of Unicode characters in script New_Tai_Lue.
+ Nko = _Nko // Nko is the set of Unicode characters in script Nko.
+ Ogham = _Ogham // Ogham is the set of Unicode characters in script Ogham.
+ Ol_Chiki = _Ol_Chiki // Ol_Chiki is the set of Unicode characters in script Ol_Chiki.
+ Old_Italic = _Old_Italic // Old_Italic is the set of Unicode characters in script Old_Italic.
+ Old_Persian = _Old_Persian // Old_Persian is the set of Unicode characters in script Old_Persian.
+ Old_South_Arabian = _Old_South_Arabian // Old_South_Arabian is the set of Unicode characters in script Old_South_Arabian.
+ Old_Turkic = _Old_Turkic // Old_Turkic is the set of Unicode characters in script Old_Turkic.
+ Oriya = _Oriya // Oriya is the set of Unicode characters in script Oriya.
+ Osmanya = _Osmanya // Osmanya is the set of Unicode characters in script Osmanya.
+ Phags_Pa = _Phags_Pa // Phags_Pa is the set of Unicode characters in script Phags_Pa.
+ Phoenician = _Phoenician // Phoenician is the set of Unicode characters in script Phoenician.
+ Rejang = _Rejang // Rejang is the set of Unicode characters in script Rejang.
+ Runic = _Runic // Runic is the set of Unicode characters in script Runic.
+ Samaritan = _Samaritan // Samaritan is the set of Unicode characters in script Samaritan.
+ Saurashtra = _Saurashtra // Saurashtra is the set of Unicode characters in script Saurashtra.
+ Shavian = _Shavian // Shavian is the set of Unicode characters in script Shavian.
+ Sinhala = _Sinhala // Sinhala is the set of Unicode characters in script Sinhala.
+ Sundanese = _Sundanese // Sundanese is the set of Unicode characters in script Sundanese.
+ Syloti_Nagri = _Syloti_Nagri // Syloti_Nagri is the set of Unicode characters in script Syloti_Nagri.
+ Syriac = _Syriac // Syriac is the set of Unicode characters in script Syriac.
+ Tagalog = _Tagalog // Tagalog is the set of Unicode characters in script Tagalog.
+ Tagbanwa = _Tagbanwa // Tagbanwa is the set of Unicode characters in script Tagbanwa.
+ Tai_Le = _Tai_Le // Tai_Le is the set of Unicode characters in script Tai_Le.
+ Tai_Tham = _Tai_Tham // Tai_Tham is the set of Unicode characters in script Tai_Tham.
+ Tai_Viet = _Tai_Viet // Tai_Viet is the set of Unicode characters in script Tai_Viet.
+ Tamil = _Tamil // Tamil is the set of Unicode characters in script Tamil.
+ Telugu = _Telugu // Telugu is the set of Unicode characters in script Telugu.
+ Thaana = _Thaana // Thaana is the set of Unicode characters in script Thaana.
+ Thai = _Thai // Thai is the set of Unicode characters in script Thai.
+ Tibetan = _Tibetan // Tibetan is the set of Unicode characters in script Tibetan.
+ Tifinagh = _Tifinagh // Tifinagh is the set of Unicode characters in script Tifinagh.
+ Ugaritic = _Ugaritic // Ugaritic is the set of Unicode characters in script Ugaritic.
+ Vai = _Vai // Vai is the set of Unicode characters in script Vai.
+ Yi = _Yi // Yi is the set of Unicode characters in script Yi.
)
// Generated by running
@@ -3943,38 +3943,38 @@ var _White_Space = []Range{
}
var (
- ASCII_Hex_Digit = _ASCII_Hex_Digit; // ASCII_Hex_Digit is the set of Unicode characters with property ASCII_Hex_Digit.
- Bidi_Control = _Bidi_Control; // Bidi_Control is the set of Unicode characters with property Bidi_Control.
- Dash = _Dash; // Dash is the set of Unicode characters with property Dash.
- Deprecated = _Deprecated; // Deprecated is the set of Unicode characters with property Deprecated.
- Diacritic = _Diacritic; // Diacritic is the set of Unicode characters with property Diacritic.
- Extender = _Extender; // Extender is the set of Unicode characters with property Extender.
- Hex_Digit = _Hex_Digit; // Hex_Digit is the set of Unicode characters with property Hex_Digit.
- Hyphen = _Hyphen; // Hyphen is the set of Unicode characters with property Hyphen.
- IDS_Binary_Operator = _IDS_Binary_Operator; // IDS_Binary_Operator is the set of Unicode characters with property IDS_Binary_Operator.
- IDS_Trinary_Operator = _IDS_Trinary_Operator; // IDS_Trinary_Operator is the set of Unicode characters with property IDS_Trinary_Operator.
- Ideographic = _Ideographic; // Ideographic is the set of Unicode characters with property Ideographic.
- Join_Control = _Join_Control; // Join_Control is the set of Unicode characters with property Join_Control.
- Logical_Order_Exception = _Logical_Order_Exception; // Logical_Order_Exception is the set of Unicode characters with property Logical_Order_Exception.
- Noncharacter_Code_Point = _Noncharacter_Code_Point; // Noncharacter_Code_Point is the set of Unicode characters with property Noncharacter_Code_Point.
- Other_Alphabetic = _Other_Alphabetic; // Other_Alphabetic is the set of Unicode characters with property Other_Alphabetic.
- Other_Default_Ignorable_Code_Point = _Other_Default_Ignorable_Code_Point; // Other_Default_Ignorable_Code_Point is the set of Unicode characters with property Other_Default_Ignorable_Code_Point.
- Other_Grapheme_Extend = _Other_Grapheme_Extend; // Other_Grapheme_Extend is the set of Unicode characters with property Other_Grapheme_Extend.
- Other_ID_Continue = _Other_ID_Continue; // Other_ID_Continue is the set of Unicode characters with property Other_ID_Continue.
- Other_ID_Start = _Other_ID_Start; // Other_ID_Start is the set of Unicode characters with property Other_ID_Start.
- Other_Lowercase = _Other_Lowercase; // Other_Lowercase is the set of Unicode characters with property Other_Lowercase.
- Other_Math = _Other_Math; // Other_Math is the set of Unicode characters with property Other_Math.
- Other_Uppercase = _Other_Uppercase; // Other_Uppercase is the set of Unicode characters with property Other_Uppercase.
- Pattern_Syntax = _Pattern_Syntax; // Pattern_Syntax is the set of Unicode characters with property Pattern_Syntax.
- Pattern_White_Space = _Pattern_White_Space; // Pattern_White_Space is the set of Unicode characters with property Pattern_White_Space.
- Quotation_Mark = _Quotation_Mark; // Quotation_Mark is the set of Unicode characters with property Quotation_Mark.
- Radical = _Radical; // Radical is the set of Unicode characters with property Radical.
- STerm = _STerm; // STerm is the set of Unicode characters with property STerm.
- Soft_Dotted = _Soft_Dotted; // Soft_Dotted is the set of Unicode characters with property Soft_Dotted.
- Terminal_Punctuation = _Terminal_Punctuation; // Terminal_Punctuation is the set of Unicode characters with property Terminal_Punctuation.
- Unified_Ideograph = _Unified_Ideograph; // Unified_Ideograph is the set of Unicode characters with property Unified_Ideograph.
- Variation_Selector = _Variation_Selector; // Variation_Selector is the set of Unicode characters with property Variation_Selector.
- White_Space = _White_Space; // White_Space is the set of Unicode characters with property White_Space.
+ ASCII_Hex_Digit = _ASCII_Hex_Digit // ASCII_Hex_Digit is the set of Unicode characters with property ASCII_Hex_Digit.
+ Bidi_Control = _Bidi_Control // Bidi_Control is the set of Unicode characters with property Bidi_Control.
+ Dash = _Dash // Dash is the set of Unicode characters with property Dash.
+ Deprecated = _Deprecated // Deprecated is the set of Unicode characters with property Deprecated.
+ Diacritic = _Diacritic // Diacritic is the set of Unicode characters with property Diacritic.
+ Extender = _Extender // Extender is the set of Unicode characters with property Extender.
+ Hex_Digit = _Hex_Digit // Hex_Digit is the set of Unicode characters with property Hex_Digit.
+ Hyphen = _Hyphen // Hyphen is the set of Unicode characters with property Hyphen.
+ IDS_Binary_Operator = _IDS_Binary_Operator // IDS_Binary_Operator is the set of Unicode characters with property IDS_Binary_Operator.
+ IDS_Trinary_Operator = _IDS_Trinary_Operator // IDS_Trinary_Operator is the set of Unicode characters with property IDS_Trinary_Operator.
+ Ideographic = _Ideographic // Ideographic is the set of Unicode characters with property Ideographic.
+ Join_Control = _Join_Control // Join_Control is the set of Unicode characters with property Join_Control.
+ Logical_Order_Exception = _Logical_Order_Exception // Logical_Order_Exception is the set of Unicode characters with property Logical_Order_Exception.
+ Noncharacter_Code_Point = _Noncharacter_Code_Point // Noncharacter_Code_Point is the set of Unicode characters with property Noncharacter_Code_Point.
+ Other_Alphabetic = _Other_Alphabetic // Other_Alphabetic is the set of Unicode characters with property Other_Alphabetic.
+ Other_Default_Ignorable_Code_Point = _Other_Default_Ignorable_Code_Point // Other_Default_Ignorable_Code_Point is the set of Unicode characters with property Other_Default_Ignorable_Code_Point.
+ Other_Grapheme_Extend = _Other_Grapheme_Extend // Other_Grapheme_Extend is the set of Unicode characters with property Other_Grapheme_Extend.
+ Other_ID_Continue = _Other_ID_Continue // Other_ID_Continue is the set of Unicode characters with property Other_ID_Continue.
+ Other_ID_Start = _Other_ID_Start // Other_ID_Start is the set of Unicode characters with property Other_ID_Start.
+ Other_Lowercase = _Other_Lowercase // Other_Lowercase is the set of Unicode characters with property Other_Lowercase.
+ Other_Math = _Other_Math // Other_Math is the set of Unicode characters with property Other_Math.
+ Other_Uppercase = _Other_Uppercase // Other_Uppercase is the set of Unicode characters with property Other_Uppercase.
+ Pattern_Syntax = _Pattern_Syntax // Pattern_Syntax is the set of Unicode characters with property Pattern_Syntax.
+ Pattern_White_Space = _Pattern_White_Space // Pattern_White_Space is the set of Unicode characters with property Pattern_White_Space.
+ Quotation_Mark = _Quotation_Mark // Quotation_Mark is the set of Unicode characters with property Quotation_Mark.
+ Radical = _Radical // Radical is the set of Unicode characters with property Radical.
+ STerm = _STerm // STerm is the set of Unicode characters with property STerm.
+ Soft_Dotted = _Soft_Dotted // Soft_Dotted is the set of Unicode characters with property Soft_Dotted.
+ Terminal_Punctuation = _Terminal_Punctuation // Terminal_Punctuation is the set of Unicode characters with property Terminal_Punctuation.
+ Unified_Ideograph = _Unified_Ideograph // Unified_Ideograph is the set of Unicode characters with property Unified_Ideograph.
+ Variation_Selector = _Variation_Selector // Variation_Selector is the set of Unicode characters with property Variation_Selector.
+ White_Space = _White_Space // White_Space is the set of Unicode characters with property White_Space.
)
// Generated by running
generated by cgit v1.2.3 (git 2.46.0) at 2025-10-28 23:32:00 +0000