import "golang.org/x/text/internal/ucd"
Package ucd provides a parser for Unicode Character Database files, the format of which is defined in http://www.unicode.org/reports/tr44/. See http://www.unicode.org/Public/UCD/latest/ucd/ for example files.
It currently does not support substitutions of missing fields.
Code:
package main
import (
"fmt"
"strings"
"golang.org/x/text/internal/ucd"
)
func main() {
// Read rune-by-rune from UnicodeData.
var count int
p := ucd.New(strings.NewReader(unicodeData))
for p.Next() {
count++
if lower := p.Runes(ucd.SimpleLowercaseMapping); lower != nil {
fmt.Printf("lower(%U) -> %U\n", p.Rune(0), lower[0])
}
}
if err := p.Err(); err != nil {
fmt.Println(err)
}
fmt.Println("Number of runes visited:", count)
// Read raw ranges from Scripts.
p = ucd.New(strings.NewReader(scripts), ucd.KeepRanges)
for p.Next() {
start, end := p.Range(0)
fmt.Printf("%04X..%04X: %s\n", start, end, p.String(1))
}
if err := p.Err(); err != nil {
fmt.Println(err)
}
}
// Excerpt from UnicodeData.txt
const unicodeData = `
00B9;SUPERSCRIPT ONE;No;0;EN;<super> 0031;;1;1;N;SUPERSCRIPT DIGIT ONE;;;;
00BA;MASCULINE ORDINAL INDICATOR;Lo;0;L;<super> 006F;;;;N;;;;;
00BB;RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK;Pf;0;ON;;;;;Y;RIGHT POINTING GUILLEMET;;;;
00BC;VULGAR FRACTION ONE QUARTER;No;0;ON;<fraction> 0031 2044 0034;;;1/4;N;FRACTION ONE QUARTER;;;;
00BD;VULGAR FRACTION ONE HALF;No;0;ON;<fraction> 0031 2044 0032;;;1/2;N;FRACTION ONE HALF;;;;
00BE;VULGAR FRACTION THREE QUARTERS;No;0;ON;<fraction> 0033 2044 0034;;;3/4;N;FRACTION THREE QUARTERS;;;;
00BF;INVERTED QUESTION MARK;Po;0;ON;;;;;N;;;;;
00C0;LATIN CAPITAL LETTER A WITH GRAVE;Lu;0;L;0041 0300;;;;N;LATIN CAPITAL LETTER A GRAVE;;;00E0;
00C1;LATIN CAPITAL LETTER A WITH ACUTE;Lu;0;L;0041 0301;;;;N;LATIN CAPITAL LETTER A ACUTE;;;00E1;
00C2;LATIN CAPITAL LETTER A WITH CIRCUMFLEX;Lu;0;L;0041 0302;;;;N;LATIN CAPITAL LETTER A CIRCUMFLEX;;;00E2;
00C3;LATIN CAPITAL LETTER A WITH TILDE;Lu;0;L;0041 0303;;;;N;LATIN CAPITAL LETTER A TILDE;;;00E3;
00C4;LATIN CAPITAL LETTER A WITH DIAERESIS;Lu;0;L;0041 0308;;;;N;LATIN CAPITAL LETTER A DIAERESIS;;;00E4;
# A legacy rune range.
3400;<CJK Ideograph Extension A, First>;Lo;0;L;;;;;N;;;;;
4DB5;<CJK Ideograph Extension A, Last>;Lo;0;L;;;;;N;;;;;
`
// Excerpt from Scripts.txt
const scripts = `
# Property: Script
# ================================================
0000..001F ; Common # Cc [32] <control-0000>..<control-001F>
0020 ; Common # Zs SPACE
0021..0023 ; Common # Po [3] EXCLAMATION MARK..NUMBER SIGN
0024 ; Common # Sc DOLLAR SIGN
`
const (
CodePoint = iota
Name
GeneralCategory
CanonicalCombiningClass
BidiClass
DecompMapping
DecimalValue
DigitValue
NumericValue
BidiMirrored
Unicode1Name
ISOComment
SimpleUppercaseMapping
SimpleLowercaseMapping
SimpleTitlecaseMapping
)UnicodeData.txt fields.
func Parse(r io.ReadCloser, f func(p *Parser))
Parse calls f for each entry in the given reader of a UCD file. It will close the reader upon return. It will call log.Fatal if any error occurred.
This implements the most common usage pattern of using Parser.
An Option is used to configure a Parser.
var (
// KeepRanges prevents the expansion of ranges. The raw ranges can be
// obtained by calling Range(0) on the parser.
KeepRanges Option = keepRanges
)The Part option register a handler for lines starting with a '@'. The text after a '@' is available as the first field. Comments are handled as usual.
type Parser struct {
// contains filtered or unexported fields
}A Parser parses Unicode Character Database (UCD) files.
New returns a Parser for the given Reader.
Bool parses and returns field i as a boolean value.
Comment returns the comments for the current line.
Enum interprets and returns field i as a value that must be one of the values in enum.
Err returns a non-nil error if any error occurred during parsing.
Float parses and returns field i as a decimal value.
Int parses and returns field i as an integer value.
Next parses the next line in the file. It returns true if a line was parsed and false if it reached the end of the file.
Range parses and returns field i as a rune range. A range is inclusive at both ends. If the field only has one rune, first and last will be identical. It supports the legacy format for ranges used in UnicodeData.txt.
Rune parses and returns field i as a rune.
Runes interprets and returns field i as a sequence of runes.
String parses and returns field i as a string value.
Strings parses and returns field i as a space-separated list of strings.
Uint parses and returns field i as an unsigned integer value.
Package ucd imports 9 packages (graph). Updated about 14 hours ago. Refresh now. Tools for package owners.