summaryrefslogtreecommitdiffstats
path: root/vendor/golang.org/x/text/encoding
diff options
context:
space:
mode:
authorWim <wim@42.be>2019-09-07 22:46:58 +0200
committerGitHub <noreply@github.com>2019-09-07 22:46:58 +0200
commita3bee01e0af3394c19360b98fd2db1b647f49299 (patch)
treeffc5778361d55d592a718354a37c9251e75fc7f6 /vendor/golang.org/x/text/encoding
parent1dc93ec4f001edd01daccbe408767d4878be25a3 (diff)
downloadmatterbridge-msglm-a3bee01e0af3394c19360b98fd2db1b647f49299.tar.gz
matterbridge-msglm-a3bee01e0af3394c19360b98fd2db1b647f49299.tar.bz2
matterbridge-msglm-a3bee01e0af3394c19360b98fd2db1b647f49299.zip
Update dependencies (#886)
Diffstat (limited to 'vendor/golang.org/x/text/encoding')
-rw-r--r--vendor/golang.org/x/text/encoding/internal/identifier/gen.go142
-rw-r--r--vendor/golang.org/x/text/encoding/japanese/maketables.go161
-rw-r--r--vendor/golang.org/x/text/encoding/korean/maketables.go143
-rw-r--r--vendor/golang.org/x/text/encoding/simplifiedchinese/maketables.go161
-rw-r--r--vendor/golang.org/x/text/encoding/traditionalchinese/maketables.go140
5 files changed, 0 insertions, 747 deletions
diff --git a/vendor/golang.org/x/text/encoding/internal/identifier/gen.go b/vendor/golang.org/x/text/encoding/internal/identifier/gen.go
deleted file mode 100644
index 26cfef9c..00000000
--- a/vendor/golang.org/x/text/encoding/internal/identifier/gen.go
+++ /dev/null
@@ -1,142 +0,0 @@
-// Copyright 2015 The Go Authors. All rights reserved.
-// Use of this source code is governed by a BSD-style
-// license that can be found in the LICENSE file.
-
-// +build ignore
-
-package main
-
-import (
- "bytes"
- "encoding/xml"
- "fmt"
- "io"
- "log"
- "strings"
-
- "golang.org/x/text/internal/gen"
-)
-
-type registry struct {
- XMLName xml.Name `xml:"registry"`
- Updated string `xml:"updated"`
- Registry []struct {
- ID string `xml:"id,attr"`
- Record []struct {
- Name string `xml:"name"`
- Xref []struct {
- Type string `xml:"type,attr"`
- Data string `xml:"data,attr"`
- } `xml:"xref"`
- Desc struct {
- Data string `xml:",innerxml"`
- // Any []struct {
- // Data string `xml:",chardata"`
- // } `xml:",any"`
- // Data string `xml:",chardata"`
- } `xml:"description,"`
- MIB string `xml:"value"`
- Alias []string `xml:"alias"`
- MIME string `xml:"preferred_alias"`
- } `xml:"record"`
- } `xml:"registry"`
-}
-
-func main() {
- r := gen.OpenIANAFile("assignments/character-sets/character-sets.xml")
- reg := &registry{}
- if err := xml.NewDecoder(r).Decode(&reg); err != nil && err != io.EOF {
- log.Fatalf("Error decoding charset registry: %v", err)
- }
- if len(reg.Registry) == 0 || reg.Registry[0].ID != "character-sets-1" {
- log.Fatalf("Unexpected ID %s", reg.Registry[0].ID)
- }
-
- w := &bytes.Buffer{}
- fmt.Fprintf(w, "const (\n")
- for _, rec := range reg.Registry[0].Record {
- constName := ""
- for _, a := range rec.Alias {
- if strings.HasPrefix(a, "cs") && strings.IndexByte(a, '-') == -1 {
- // Some of the constant definitions have comments in them. Strip those.
- constName = strings.Title(strings.SplitN(a[2:], "\n", 2)[0])
- }
- }
- if constName == "" {
- switch rec.MIB {
- case "2085":
- constName = "HZGB2312" // Not listed as alias for some reason.
- default:
- log.Fatalf("No cs alias defined for %s.", rec.MIB)
- }
- }
- if rec.MIME != "" {
- rec.MIME = fmt.Sprintf(" (MIME: %s)", rec.MIME)
- }
- fmt.Fprintf(w, "// %s is the MIB identifier with IANA name %s%s.\n//\n", constName, rec.Name, rec.MIME)
- if len(rec.Desc.Data) > 0 {
- fmt.Fprint(w, "// ")
- d := xml.NewDecoder(strings.NewReader(rec.Desc.Data))
- inElem := true
- attr := ""
- for {
- t, err := d.Token()
- if err != nil {
- if err != io.EOF {
- log.Fatal(err)
- }
- break
- }
- switch x := t.(type) {
- case xml.CharData:
- attr = "" // Don't need attribute info.
- a := bytes.Split([]byte(x), []byte("\n"))
- for i, b := range a {
- if b = bytes.TrimSpace(b); len(b) != 0 {
- if !inElem && i > 0 {
- fmt.Fprint(w, "\n// ")
- }
- inElem = false
- fmt.Fprintf(w, "%s ", string(b))
- }
- }
- case xml.StartElement:
- if x.Name.Local == "xref" {
- inElem = true
- use := false
- for _, a := range x.Attr {
- if a.Name.Local == "type" {
- use = use || a.Value != "person"
- }
- if a.Name.Local == "data" && use {
- // Patch up URLs to use https. From some links, the
- // https version is different from the http one.
- s := a.Value
- s = strings.Replace(s, "http://", "https://", -1)
- s = strings.Replace(s, "/unicode/", "/", -1)
- attr = s + " "
- }
- }
- }
- case xml.EndElement:
- inElem = false
- fmt.Fprint(w, attr)
- }
- }
- fmt.Fprint(w, "\n")
- }
- for _, x := range rec.Xref {
- switch x.Type {
- case "rfc":
- fmt.Fprintf(w, "// Reference: %s\n", strings.ToUpper(x.Data))
- case "uri":
- fmt.Fprintf(w, "// Reference: %s\n", x.Data)
- }
- }
- fmt.Fprintf(w, "%s MIB = %s\n", constName, rec.MIB)
- fmt.Fprintln(w)
- }
- fmt.Fprintln(w, ")")
-
- gen.WriteGoFile("mib.go", "identifier", w.Bytes())
-}
diff --git a/vendor/golang.org/x/text/encoding/japanese/maketables.go b/vendor/golang.org/x/text/encoding/japanese/maketables.go
deleted file mode 100644
index 023957a6..00000000
--- a/vendor/golang.org/x/text/encoding/japanese/maketables.go
+++ /dev/null
@@ -1,161 +0,0 @@
-// Copyright 2013 The Go Authors. All rights reserved.
-// Use of this source code is governed by a BSD-style
-// license that can be found in the LICENSE file.
-
-// +build ignore
-
-package main
-
-// This program generates tables.go:
-// go run maketables.go | gofmt > tables.go
-
-// TODO: Emoji extensions?
-// https://www.unicode.org/faq/emoji_dingbats.html
-// https://www.unicode.org/Public/UNIDATA/EmojiSources.txt
-
-import (
- "bufio"
- "fmt"
- "log"
- "net/http"
- "sort"
- "strings"
-)
-
-type entry struct {
- jisCode, table int
-}
-
-func main() {
- fmt.Printf("// generated by go run maketables.go; DO NOT EDIT\n\n")
- fmt.Printf("// Package japanese provides Japanese encodings such as EUC-JP and Shift JIS.\n")
- fmt.Printf(`package japanese // import "golang.org/x/text/encoding/japanese"` + "\n\n")
-
- reverse := [65536]entry{}
- for i := range reverse {
- reverse[i].table = -1
- }
-
- tables := []struct {
- url string
- name string
- }{
- {"http://encoding.spec.whatwg.org/index-jis0208.txt", "0208"},
- {"http://encoding.spec.whatwg.org/index-jis0212.txt", "0212"},
- }
- for i, table := range tables {
- res, err := http.Get(table.url)
- if err != nil {
- log.Fatalf("%q: Get: %v", table.url, err)
- }
- defer res.Body.Close()
-
- mapping := [65536]uint16{}
-
- scanner := bufio.NewScanner(res.Body)
- for scanner.Scan() {
- s := strings.TrimSpace(scanner.Text())
- if s == "" || s[0] == '#' {
- continue
- }
- x, y := 0, uint16(0)
- if _, err := fmt.Sscanf(s, "%d 0x%x", &x, &y); err != nil {
- log.Fatalf("%q: could not parse %q", table.url, s)
- }
- if x < 0 || 120*94 <= x {
- log.Fatalf("%q: JIS code %d is out of range", table.url, x)
- }
- mapping[x] = y
- if reverse[y].table == -1 {
- reverse[y] = entry{jisCode: x, table: i}
- }
- }
- if err := scanner.Err(); err != nil {
- log.Fatalf("%q: scanner error: %v", table.url, err)
- }
-
- fmt.Printf("// jis%sDecode is the decoding table from JIS %s code to Unicode.\n// It is defined at %s\n",
- table.name, table.name, table.url)
- fmt.Printf("var jis%sDecode = [...]uint16{\n", table.name)
- for i, m := range mapping {
- if m != 0 {
- fmt.Printf("\t%d: 0x%04X,\n", i, m)
- }
- }
- fmt.Printf("}\n\n")
- }
-
- // Any run of at least separation continuous zero entries in the reverse map will
- // be a separate encode table.
- const separation = 1024
-
- intervals := []interval(nil)
- low, high := -1, -1
- for i, v := range reverse {
- if v.table == -1 {
- continue
- }
- if low < 0 {
- low = i
- } else if i-high >= separation {
- if high >= 0 {
- intervals = append(intervals, interval{low, high})
- }
- low = i
- }
- high = i + 1
- }
- if high >= 0 {
- intervals = append(intervals, interval{low, high})
- }
- sort.Sort(byDecreasingLength(intervals))
-
- fmt.Printf("const (\n")
- fmt.Printf("\tjis0208 = 1\n")
- fmt.Printf("\tjis0212 = 2\n")
- fmt.Printf("\tcodeMask = 0x7f\n")
- fmt.Printf("\tcodeShift = 7\n")
- fmt.Printf("\ttableShift = 14\n")
- fmt.Printf(")\n\n")
-
- fmt.Printf("const numEncodeTables = %d\n\n", len(intervals))
- fmt.Printf("// encodeX are the encoding tables from Unicode to JIS code,\n")
- fmt.Printf("// sorted by decreasing length.\n")
- for i, v := range intervals {
- fmt.Printf("// encode%d: %5d entries for runes in [%5d, %5d).\n", i, v.len(), v.low, v.high)
- }
- fmt.Printf("//\n")
- fmt.Printf("// The high two bits of the value record whether the JIS code comes from the\n")
- fmt.Printf("// JIS0208 table (high bits == 1) or the JIS0212 table (high bits == 2).\n")
- fmt.Printf("// The low 14 bits are two 7-bit unsigned integers j1 and j2 that form the\n")
- fmt.Printf("// JIS code (94*j1 + j2) within that table.\n")
- fmt.Printf("\n")
-
- for i, v := range intervals {
- fmt.Printf("const encode%dLow, encode%dHigh = %d, %d\n\n", i, i, v.low, v.high)
- fmt.Printf("var encode%d = [...]uint16{\n", i)
- for j := v.low; j < v.high; j++ {
- x := reverse[j]
- if x.table == -1 {
- continue
- }
- fmt.Printf("\t%d - %d: jis%s<<14 | 0x%02X<<7 | 0x%02X,\n",
- j, v.low, tables[x.table].name, x.jisCode/94, x.jisCode%94)
- }
- fmt.Printf("}\n\n")
- }
-}
-
-// interval is a half-open interval [low, high).
-type interval struct {
- low, high int
-}
-
-func (i interval) len() int { return i.high - i.low }
-
-// byDecreasingLength sorts intervals by decreasing length.
-type byDecreasingLength []interval
-
-func (b byDecreasingLength) Len() int { return len(b) }
-func (b byDecreasingLength) Less(i, j int) bool { return b[i].len() > b[j].len() }
-func (b byDecreasingLength) Swap(i, j int) { b[i], b[j] = b[j], b[i] }
diff --git a/vendor/golang.org/x/text/encoding/korean/maketables.go b/vendor/golang.org/x/text/encoding/korean/maketables.go
deleted file mode 100644
index c84034fb..00000000
--- a/vendor/golang.org/x/text/encoding/korean/maketables.go
+++ /dev/null
@@ -1,143 +0,0 @@
-// Copyright 2013 The Go Authors. All rights reserved.
-// Use of this source code is governed by a BSD-style
-// license that can be found in the LICENSE file.
-
-// +build ignore
-
-package main
-
-// This program generates tables.go:
-// go run maketables.go | gofmt > tables.go
-
-import (
- "bufio"
- "fmt"
- "log"
- "net/http"
- "sort"
- "strings"
-)
-
-func main() {
- fmt.Printf("// generated by go run maketables.go; DO NOT EDIT\n\n")
- fmt.Printf("// Package korean provides Korean encodings such as EUC-KR.\n")
- fmt.Printf(`package korean // import "golang.org/x/text/encoding/korean"` + "\n\n")
-
- res, err := http.Get("http://encoding.spec.whatwg.org/index-euc-kr.txt")
- if err != nil {
- log.Fatalf("Get: %v", err)
- }
- defer res.Body.Close()
-
- mapping := [65536]uint16{}
- reverse := [65536]uint16{}
-
- scanner := bufio.NewScanner(res.Body)
- for scanner.Scan() {
- s := strings.TrimSpace(scanner.Text())
- if s == "" || s[0] == '#' {
- continue
- }
- x, y := uint16(0), uint16(0)
- if _, err := fmt.Sscanf(s, "%d 0x%x", &x, &y); err != nil {
- log.Fatalf("could not parse %q", s)
- }
- if x < 0 || 178*(0xc7-0x81)+(0xfe-0xc7)*94+(0xff-0xa1) <= x {
- log.Fatalf("EUC-KR code %d is out of range", x)
- }
- mapping[x] = y
- if reverse[y] == 0 {
- c0, c1 := uint16(0), uint16(0)
- if x < 178*(0xc7-0x81) {
- c0 = uint16(x/178) + 0x81
- c1 = uint16(x % 178)
- switch {
- case c1 < 1*26:
- c1 += 0x41
- case c1 < 2*26:
- c1 += 0x47
- default:
- c1 += 0x4d
- }
- } else {
- x -= 178 * (0xc7 - 0x81)
- c0 = uint16(x/94) + 0xc7
- c1 = uint16(x%94) + 0xa1
- }
- reverse[y] = c0<<8 | c1
- }
- }
- if err := scanner.Err(); err != nil {
- log.Fatalf("scanner error: %v", err)
- }
-
- fmt.Printf("// decode is the decoding table from EUC-KR code to Unicode.\n")
- fmt.Printf("// It is defined at http://encoding.spec.whatwg.org/index-euc-kr.txt\n")
- fmt.Printf("var decode = [...]uint16{\n")
- for i, v := range mapping {
- if v != 0 {
- fmt.Printf("\t%d: 0x%04X,\n", i, v)
- }
- }
- fmt.Printf("}\n\n")
-
- // Any run of at least separation continuous zero entries in the reverse map will
- // be a separate encode table.
- const separation = 1024
-
- intervals := []interval(nil)
- low, high := -1, -1
- for i, v := range reverse {
- if v == 0 {
- continue
- }
- if low < 0 {
- low = i
- } else if i-high >= separation {
- if high >= 0 {
- intervals = append(intervals, interval{low, high})
- }
- low = i
- }
- high = i + 1
- }
- if high >= 0 {
- intervals = append(intervals, interval{low, high})
- }
- sort.Sort(byDecreasingLength(intervals))
-
- fmt.Printf("const numEncodeTables = %d\n\n", len(intervals))
- fmt.Printf("// encodeX are the encoding tables from Unicode to EUC-KR code,\n")
- fmt.Printf("// sorted by decreasing length.\n")
- for i, v := range intervals {
- fmt.Printf("// encode%d: %5d entries for runes in [%5d, %5d).\n", i, v.len(), v.low, v.high)
- }
- fmt.Printf("\n")
-
- for i, v := range intervals {
- fmt.Printf("const encode%dLow, encode%dHigh = %d, %d\n\n", i, i, v.low, v.high)
- fmt.Printf("var encode%d = [...]uint16{\n", i)
- for j := v.low; j < v.high; j++ {
- x := reverse[j]
- if x == 0 {
- continue
- }
- fmt.Printf("\t%d-%d: 0x%04X,\n", j, v.low, x)
- }
- fmt.Printf("}\n\n")
- }
-}
-
-// interval is a half-open interval [low, high).
-type interval struct {
- low, high int
-}
-
-func (i interval) len() int { return i.high - i.low }
-
-// byDecreasingLength sorts intervals by decreasing length.
-type byDecreasingLength []interval
-
-func (b byDecreasingLength) Len() int { return len(b) }
-func (b byDecreasingLength) Less(i, j int) bool { return b[i].len() > b[j].len() }
-func (b byDecreasingLength) Swap(i, j int) { b[i], b[j] = b[j], b[i] }
diff --git a/vendor/golang.org/x/text/encoding/simplifiedchinese/maketables.go b/vendor/golang.org/x/text/encoding/simplifiedchinese/maketables.go
deleted file mode 100644
index 55016c78..00000000
--- a/vendor/golang.org/x/text/encoding/simplifiedchinese/maketables.go
+++ /dev/null
@@ -1,161 +0,0 @@
-// Copyright 2013 The Go Authors. All rights reserved.
-// Use of this source code is governed by a BSD-style
-// license that can be found in the LICENSE file.
-
-// +build ignore
-
-package main
-
-// This program generates tables.go:
-// go run maketables.go | gofmt > tables.go
-
-import (
- "bufio"
- "fmt"
- "log"
- "net/http"
- "sort"
- "strings"
-)
-
-func main() {
- fmt.Printf("// generated by go run maketables.go; DO NOT EDIT\n\n")
- fmt.Printf("// Package simplifiedchinese provides Simplified Chinese encodings such as GBK.\n")
- fmt.Printf(`package simplifiedchinese // import "golang.org/x/text/encoding/simplifiedchinese"` + "\n\n")
-
- printGB18030()
- printGBK()
-}
-
-func printGB18030() {
- res, err := http.Get("http://encoding.spec.whatwg.org/index-gb18030.txt")
- if err != nil {
- log.Fatalf("Get: %v", err)
- }
- defer res.Body.Close()
-
- fmt.Printf("// gb18030 is the table from http://encoding.spec.whatwg.org/index-gb18030.txt\n")
- fmt.Printf("var gb18030 = [...][2]uint16{\n")
- scanner := bufio.NewScanner(res.Body)
- for scanner.Scan() {
- s := strings.TrimSpace(scanner.Text())
- if s == "" || s[0] == '#' {
- continue
- }
- x, y := uint32(0), uint32(0)
- if _, err := fmt.Sscanf(s, "%d 0x%x", &x, &y); err != nil {
- log.Fatalf("could not parse %q", s)
- }
- if x < 0x10000 && y < 0x10000 {
- fmt.Printf("\t{0x%04x, 0x%04x},\n", x, y)
- }
- }
- fmt.Printf("}\n\n")
-}
-
-func printGBK() {
- res, err := http.Get("http://encoding.spec.whatwg.org/index-gbk.txt")
- if err != nil {
- log.Fatalf("Get: %v", err)
- }
- defer res.Body.Close()
-
- mapping := [65536]uint16{}
- reverse := [65536]uint16{}
-
- scanner := bufio.NewScanner(res.Body)
- for scanner.Scan() {
- s := strings.TrimSpace(scanner.Text())
- if s == "" || s[0] == '#' {
- continue
- }
- x, y := uint16(0), uint16(0)
- if _, err := fmt.Sscanf(s, "%d 0x%x", &x, &y); err != nil {
- log.Fatalf("could not parse %q", s)
- }
- if x < 0 || 126*190 <= x {
- log.Fatalf("GBK code %d is out of range", x)
- }
- mapping[x] = y
- if reverse[y] == 0 {
- c0, c1 := x/190, x%190
- if c1 >= 0x3f {
- c1++
- }
- reverse[y] = (0x81+c0)<<8 | (0x40 + c1)
- }
- }
- if err := scanner.Err(); err != nil {
- log.Fatalf("scanner error: %v", err)
- }
-
- fmt.Printf("// decode is the decoding table from GBK code to Unicode.\n")
- fmt.Printf("// It is defined at http://encoding.spec.whatwg.org/index-gbk.txt\n")
- fmt.Printf("var decode = [...]uint16{\n")
- for i, v := range mapping {
- if v != 0 {
- fmt.Printf("\t%d: 0x%04X,\n", i, v)
- }
- }
- fmt.Printf("}\n\n")
-
- // Any run of at least separation continuous zero entries in the reverse map will
- // be a separate encode table.
- const separation = 1024
-
- intervals := []interval(nil)
- low, high := -1, -1
- for i, v := range reverse {
- if v == 0 {
- continue
- }
- if low < 0 {
- low = i
- } else if i-high >= separation {
- if high >= 0 {
- intervals = append(intervals, interval{low, high})
- }
- low = i
- }
- high = i + 1
- }
- if high >= 0 {
- intervals = append(intervals, interval{low, high})
- }
- sort.Sort(byDecreasingLength(intervals))
-
- fmt.Printf("const numEncodeTables = %d\n\n", len(intervals))
- fmt.Printf("// encodeX are the encoding tables from Unicode to GBK code,\n")
- fmt.Printf("// sorted by decreasing length.\n")
- for i, v := range intervals {
- fmt.Printf("// encode%d: %5d entries for runes in [%5d, %5d).\n", i, v.len(), v.low, v.high)
- }
- fmt.Printf("\n")
-
- for i, v := range intervals {
- fmt.Printf("const encode%dLow, encode%dHigh = %d, %d\n\n", i, i, v.low, v.high)
- fmt.Printf("var encode%d = [...]uint16{\n", i)
- for j := v.low; j < v.high; j++ {
- x := reverse[j]
- if x == 0 {
- continue
- }
- fmt.Printf("\t%d-%d: 0x%04X,\n", j, v.low, x)
- }
- fmt.Printf("}\n\n")
- }
-}
-
-// interval is a half-open interval [low, high).
-type interval struct {
- low, high int
-}
-
-func (i interval) len() int { return i.high - i.low }
-
-// byDecreasingLength sorts intervals by decreasing length.
-type byDecreasingLength []interval
-
-func (b byDecreasingLength) Len() int { return len(b) }
-func (b byDecreasingLength) Less(i, j int) bool { return b[i].len() > b[j].len() }
-func (b byDecreasingLength) Swap(i, j int) { b[i], b[j] = b[j], b[i] }
diff --git a/vendor/golang.org/x/text/encoding/traditionalchinese/maketables.go b/vendor/golang.org/x/text/encoding/traditionalchinese/maketables.go
deleted file mode 100644
index cf7fdb31..00000000
--- a/vendor/golang.org/x/text/encoding/traditionalchinese/maketables.go
+++ /dev/null
@@ -1,140 +0,0 @@
-// Copyright 2013 The Go Authors. All rights reserved.
-// Use of this source code is governed by a BSD-style
-// license that can be found in the LICENSE file.
-
-// +build ignore
-
-package main
-
-// This program generates tables.go:
-// go run maketables.go | gofmt > tables.go
-
-import (
- "bufio"
- "fmt"
- "log"
- "net/http"
- "sort"
- "strings"
-)
-
-func main() {
- fmt.Printf("// generated by go run maketables.go; DO NOT EDIT\n\n")
- fmt.Printf("// Package traditionalchinese provides Traditional Chinese encodings such as Big5.\n")
- fmt.Printf(`package traditionalchinese // import "golang.org/x/text/encoding/traditionalchinese"` + "\n\n")
-
- res, err := http.Get("http://encoding.spec.whatwg.org/index-big5.txt")
- if err != nil {
- log.Fatalf("Get: %v", err)
- }
- defer res.Body.Close()
-
- mapping := [65536]uint32{}
- reverse := [65536 * 4]uint16{}
-
- scanner := bufio.NewScanner(res.Body)
- for scanner.Scan() {
- s := strings.TrimSpace(scanner.Text())
- if s == "" || s[0] == '#' {
- continue
- }
- x, y := uint16(0), uint32(0)
- if _, err := fmt.Sscanf(s, "%d 0x%x", &x, &y); err != nil {
- log.Fatalf("could not parse %q", s)
- }
- if x < 0 || 126*157 <= x {
- log.Fatalf("Big5 code %d is out of range", x)
- }
- mapping[x] = y
-
- // The WHATWG spec http://encoding.spec.whatwg.org/#indexes says that
- // "The index pointer for code point in index is the first pointer
- // corresponding to code point in index", which would normally mean
- // that the code below should be guarded by "if reverse[y] == 0", but
- // last instead of first seems to match the behavior of
- // "iconv -f UTF-8 -t BIG5". For example, U+8005 者 occurs twice in
- // http://encoding.spec.whatwg.org/index-big5.txt, as index 2148
- // (encoded as "\x8e\xcd") and index 6543 (encoded as "\xaa\xcc")
- // and "echo 者 | iconv -f UTF-8 -t BIG5 | xxd" gives "\xaa\xcc".
- c0, c1 := x/157, x%157
- if c1 < 0x3f {
- c1 += 0x40
- } else {
- c1 += 0x62
- }
- reverse[y] = (0x81+c0)<<8 | c1
- }
- if err := scanner.Err(); err != nil {
- log.Fatalf("scanner error: %v", err)
- }
-
- fmt.Printf("// decode is the decoding table from Big5 code to Unicode.\n")
- fmt.Printf("// It is defined at http://encoding.spec.whatwg.org/index-big5.txt\n")
- fmt.Printf("var decode = [...]uint32{\n")
- for i, v := range mapping {
- if v != 0 {
- fmt.Printf("\t%d: 0x%08X,\n", i, v)
- }
- }
- fmt.Printf("}\n\n")
-
- // Any run of at least separation continuous zero entries in the reverse map will
- // be a separate encode table.
- const separation = 1024
-
- intervals := []interval(nil)
- low, high := -1, -1
- for i, v := range reverse {
- if v == 0 {
- continue
- }
- if low < 0 {
- low = i
- } else if i-high >= separation {
- if high >= 0 {
- intervals = append(intervals, interval{low, high})
- }
- low = i
- }
- high = i + 1
- }
- if high >= 0 {
- intervals = append(intervals, interval{low, high})
- }
- sort.Sort(byDecreasingLength(intervals))
-
- fmt.Printf("const numEncodeTables = %d\n\n", len(intervals))
- fmt.Printf("// encodeX are the encoding tables from Unicode to Big5 code,\n")
- fmt.Printf("// sorted by decreasing length.\n")
- for i, v := range intervals {
- fmt.Printf("// encode%d: %5d entries for runes in [%6d, %6d).\n", i, v.len(), v.low, v.high)
- }
- fmt.Printf("\n")
-
- for i, v := range intervals {
- fmt.Printf("const encode%dLow, encode%dHigh = %d, %d\n\n", i, i, v.low, v.high)
- fmt.Printf("var encode%d = [...]uint16{\n", i)
- for j := v.low; j < v.high; j++ {
- x := reverse[j]
- if x == 0 {
- continue
- }
- fmt.Printf("\t%d-%d: 0x%04X,\n", j, v.low, x)
- }
- fmt.Printf("}\n\n")
- }
-}
-
-// interval is a half-open interval [low, high).
-type interval struct {
- low, high int
-}
-
-func (i interval) len() int { return i.high - i.low }
-
-// byDecreasingLength sorts intervals by decreasing length.
-type byDecreasingLength []interval
-
-func (b byDecreasingLength) Len() int { return len(b) }
-func (b byDecreasingLength) Less(i, j int) bool { return b[i].len() > b[j].len() }
-func (b byDecreasingLength) Swap(i, j int) { b[i], b[j] = b[j], b[i] }