Checking in vendor folder for ease of using go get.

vendor/golang.org/x/text/encoding/korean/all_test.go

@@ -0,0 +1,94 @@
+// 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.
+
+package korean
+
+import (
+	"strings"
+	"testing"
+
+	"golang.org/x/text/encoding"
+	"golang.org/x/text/encoding/internal"
+	"golang.org/x/text/encoding/internal/enctest"
+	"golang.org/x/text/transform"
+)
+
+func dec(e encoding.Encoding) (dir string, t transform.Transformer, err error) {
+	return "Decode", e.NewDecoder(), nil
+}
+func enc(e encoding.Encoding) (dir string, t transform.Transformer, err error) {
+	return "Encode", e.NewEncoder(), internal.ErrASCIIReplacement
+}
+
+func TestNonRepertoire(t *testing.T) {
+	// Pick n large enough to cause an overflow in the destination buffer of
+	// transform.String.
+	const n = 10000
+	testCases := []struct {
+		init      func(e encoding.Encoding) (string, transform.Transformer, error)
+		e         encoding.Encoding
+		src, want string
+	}{
+		{dec, EUCKR, "\xfe\xfe", "\ufffd"},
+		// {dec, EUCKR, "א", "\ufffd"}, // TODO: why is this different?
+
+		{enc, EUCKR, "א", ""},
+		{enc, EUCKR, "aא", "a"},
+		{enc, EUCKR, "\uac00א", "\xb0\xa1"},
+		// TODO: should we also handle Jamo?
+
+		{dec, EUCKR, "\x80", "\ufffd"},
+		{dec, EUCKR, "\xff", "\ufffd"},
+		{dec, EUCKR, "\x81", "\ufffd"},
+		{dec, EUCKR, "\xb0\x40", "\ufffd@"},
+		{dec, EUCKR, "\xb0\xff", "\ufffd"},
+		{dec, EUCKR, "\xd0\x20", "\ufffd "},
+		{dec, EUCKR, "\xd0\xff", "\ufffd"},
+
+		{dec, EUCKR, strings.Repeat("\x81", n), strings.Repeat("걖", n/2)},
+	}
+	for _, tc := range testCases {
+		dir, tr, wantErr := tc.init(tc.e)
+
+		dst, _, err := transform.String(tr, tc.src)
+		if err != wantErr {
+			t.Errorf("%s %v(%q): got %v; want %v", dir, tc.e, tc.src, err, wantErr)
+		}
+		if got := string(dst); got != tc.want {
+			t.Errorf("%s %v(%q):\ngot  %q\nwant %q", dir, tc.e, tc.src, got, tc.want)
+		}
+	}
+}
+
+func TestBasics(t *testing.T) {
+	// The encoded forms can be verified by the iconv program:
+	// $ echo 月日は百代 | iconv -f UTF-8 -t SHIFT-JIS | xxd
+	testCases := []struct {
+		e       encoding.Encoding
+		encoded string
+		utf8    string
+	}{{
+		// Korean tests.
+		//
+		// "A\uac02\uac35\uac56\ud401B\ud408\ud620\ud624C\u4f3d\u8a70D" is a
+		// nonsense string that contains ASCII, Hangul and CJK ideographs.
+		//
+		// "세계야, 안녕" translates as "Hello, world".
+		e:       EUCKR,
+		encoded: "A\x81\x41\x81\x61\x81\x81\xc6\xfeB\xc7\xa1\xc7\xfe\xc8\xa1C\xca\xa1\xfd\xfeD",
+		utf8:    "A\uac02\uac35\uac56\ud401B\ud408\ud620\ud624C\u4f3d\u8a70D",
+	}, {
+		e:       EUCKR,
+		encoded: "\xbc\xbc\xb0\xe8\xbe\xdf\x2c\x20\xbe\xc8\xb3\xe7",
+		utf8:    "세계야, 안녕",
+	}}
+
+	for _, tc := range testCases {
+		enctest.TestEncoding(t, tc.e, tc.encoded, tc.utf8, "", "")
+	}
+}
+
+func TestFiles(t *testing.T) { enctest.TestFile(t, EUCKR) }
+
+func BenchmarkEncoding(b *testing.B) { enctest.Benchmark(b, EUCKR) }

vendor/golang.org/x/text/encoding/korean/euckr.go

@@ -0,0 +1,177 @@
+// 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.
+
+package korean
+
+import (
+	"unicode/utf8"
+
+	"golang.org/x/text/encoding"
+	"golang.org/x/text/encoding/internal"
+	"golang.org/x/text/encoding/internal/identifier"
+	"golang.org/x/text/transform"
+)
+
+// All is a list of all defined encodings in this package.
+var All = []encoding.Encoding{EUCKR}
+
+// EUCKR is the EUC-KR encoding, also known as Code Page 949.
+var EUCKR encoding.Encoding = &eucKR
+
+var eucKR = internal.Encoding{
+	&internal.SimpleEncoding{eucKRDecoder{}, eucKREncoder{}},
+	"EUC-KR",
+	identifier.EUCKR,
+}
+
+type eucKRDecoder struct{ transform.NopResetter }
+
+func (eucKRDecoder) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
+	r, size := rune(0), 0
+loop:
+	for ; nSrc < len(src); nSrc += size {
+		switch c0 := src[nSrc]; {
+		case c0 < utf8.RuneSelf:
+			r, size = rune(c0), 1
+
+		case 0x81 <= c0 && c0 < 0xff:
+			if nSrc+1 >= len(src) {
+				if !atEOF {
+					err = transform.ErrShortSrc
+					break loop
+				}
+				r, size = utf8.RuneError, 1
+				break
+			}
+			c1 := src[nSrc+1]
+			size = 2
+			if c0 < 0xc7 {
+				r = 178 * rune(c0-0x81)
+				switch {
+				case 0x41 <= c1 && c1 < 0x5b:
+					r += rune(c1) - (0x41 - 0*26)
+				case 0x61 <= c1 && c1 < 0x7b:
+					r += rune(c1) - (0x61 - 1*26)
+				case 0x81 <= c1 && c1 < 0xff:
+					r += rune(c1) - (0x81 - 2*26)
+				default:
+					goto decError
+				}
+			} else if 0xa1 <= c1 && c1 < 0xff {
+				r = 178*(0xc7-0x81) + rune(c0-0xc7)*94 + rune(c1-0xa1)
+			} else {
+				goto decError
+			}
+			if int(r) < len(decode) {
+				r = rune(decode[r])
+				if r != 0 {
+					break
+				}
+			}
+		decError:
+			r = utf8.RuneError
+			if c1 < utf8.RuneSelf {
+				size = 1
+			}
+
+		default:
+			r, size = utf8.RuneError, 1
+			break
+		}
+
+		if nDst+utf8.RuneLen(r) > len(dst) {
+			err = transform.ErrShortDst
+			break
+		}
+		nDst += utf8.EncodeRune(dst[nDst:], r)
+	}
+	return nDst, nSrc, err
+}
+
+type eucKREncoder struct{ transform.NopResetter }
+
+func (eucKREncoder) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
+	r, size := rune(0), 0
+	for ; nSrc < len(src); nSrc += size {
+		r = rune(src[nSrc])
+
+		// Decode a 1-byte rune.
+		if r < utf8.RuneSelf {
+			size = 1
+
+			if nDst >= len(dst) {
+				err = transform.ErrShortDst
+				break
+			}
+			dst[nDst] = uint8(r)
+			nDst++
+			continue
+
+		} else {
+			// Decode a multi-byte rune.
+			r, size = utf8.DecodeRune(src[nSrc:])
+			if size == 1 {
+				// All valid runes of size 1 (those below utf8.RuneSelf) were
+				// handled above. We have invalid UTF-8 or we haven't seen the
+				// full character yet.
+				if !atEOF && !utf8.FullRune(src[nSrc:]) {
+					err = transform.ErrShortSrc
+					break
+				}
+			}
+
+			// func init checks that the switch covers all tables.
+			switch {
+			case encode0Low <= r && r < encode0High:
+				if r = rune(encode0[r-encode0Low]); r != 0 {
+					goto write2
+				}
+			case encode1Low <= r && r < encode1High:
+				if r = rune(encode1[r-encode1Low]); r != 0 {
+					goto write2
+				}
+			case encode2Low <= r && r < encode2High:
+				if r = rune(encode2[r-encode2Low]); r != 0 {
+					goto write2
+				}
+			case encode3Low <= r && r < encode3High:
+				if r = rune(encode3[r-encode3Low]); r != 0 {
+					goto write2
+				}
+			case encode4Low <= r && r < encode4High:
+				if r = rune(encode4[r-encode4Low]); r != 0 {
+					goto write2
+				}
+			case encode5Low <= r && r < encode5High:
+				if r = rune(encode5[r-encode5Low]); r != 0 {
+					goto write2
+				}
+			case encode6Low <= r && r < encode6High:
+				if r = rune(encode6[r-encode6Low]); r != 0 {
+					goto write2
+				}
+			}
+			err = internal.ErrASCIIReplacement
+			break
+		}
+
+	write2:
+		if nDst+2 > len(dst) {
+			err = transform.ErrShortDst
+			break
+		}
+		dst[nDst+0] = uint8(r >> 8)
+		dst[nDst+1] = uint8(r)
+		nDst += 2
+		continue
+	}
+	return nDst, nSrc, err
+}
+
+func init() {
+	// Check that the hard-coded encode switch covers all tables.
+	if numEncodeTables != 7 {
+		panic("bad numEncodeTables")
+	}
+}

vendor/golang.org/x/text/encoding/korean/maketables.go

@@ -0,0 +1,143 @@
+// 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] }