├── .gitignore ├── LICENSE ├── README.md ├── decode.go ├── make_table.go ├── table.go ├── table.txt ├── unidecode.go └── unidecode_test.go /.gitignore: -------------------------------------------------------------------------------- 1 | # Compiled Object files, Static and Dynamic libs (Shared Objects) 2 | *.o 3 | *.a 4 | *.so 5 | 6 | # Folders 7 | _obj 8 | _test 9 | 10 | # Architecture specific extensions/prefixes 11 | *.[568vq] 12 | [568vq].out 13 | 14 | *.cgo1.go 15 | *.cgo2.c 16 | _cgo_defun.c 17 | _cgo_gotypes.go 18 | _cgo_export.* 19 | 20 | _testmain.go 21 | 22 | *.exe 23 | *.test 24 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Copyright 2014 Rainy Cape S.L. 2 | 3 | Apache License 4 | Version 2.0, January 2004 5 | http://www.apache.org/licenses/ 6 | 7 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 8 | 9 | 1. Definitions. 10 | 11 | "License" shall mean the terms and conditions for use, reproduction, 12 | and distribution as defined by Sections 1 through 9 of this document. 13 | 14 | "Licensor" shall mean the copyright owner or entity authorized by 15 | the copyright owner that is granting the License. 16 | 17 | "Legal Entity" shall mean the union of the acting entity and all 18 | other entities that control, are controlled by, or are under common 19 | control with that entity. For the purposes of this definition, 20 | "control" means (i) the power, direct or indirect, to cause the 21 | direction or management of such entity, whether by contract or 22 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 23 | outstanding shares, or (iii) beneficial ownership of such entity. 24 | 25 | "You" (or "Your") shall mean an individual or Legal Entity 26 | exercising permissions granted by this License. 27 | 28 | "Source" form shall mean the preferred form for making modifications, 29 | including but not limited to software source code, documentation 30 | source, and configuration files. 31 | 32 | "Object" form shall mean any form resulting from mechanical 33 | transformation or translation of a Source form, including but 34 | not limited to compiled object code, generated documentation, 35 | and conversions to other media types. 36 | 37 | "Work" shall mean the work of authorship, whether in Source or 38 | Object form, made available under the License, as indicated by a 39 | copyright notice that is included in or attached to the work 40 | (an example is provided in the Appendix below). 41 | 42 | "Derivative Works" shall mean any work, whether in Source or Object 43 | form, that is based on (or derived from) the Work and for which the 44 | editorial revisions, annotations, elaborations, or other modifications 45 | represent, as a whole, an original work of authorship. For the purposes 46 | of this License, Derivative Works shall not include works that remain 47 | separable from, or merely link (or bind by name) to the interfaces of, 48 | the Work and Derivative Works thereof. 49 | 50 | "Contribution" shall mean any work of authorship, including 51 | the original version of the Work and any modifications or additions 52 | to that Work or Derivative Works thereof, that is intentionally 53 | submitted to Licensor for inclusion in the Work by the copyright owner 54 | or by an individual or Legal Entity authorized to submit on behalf of 55 | the copyright owner. For the purposes of this definition, "submitted" 56 | means any form of electronic, verbal, or written communication sent 57 | to the Licensor or its representatives, including but not limited to 58 | communication on electronic mailing lists, source code control systems, 59 | and issue tracking systems that are managed by, or on behalf of, the 60 | Licensor for the purpose of discussing and improving the Work, but 61 | excluding communication that is conspicuously marked or otherwise 62 | designated in writing by the copyright owner as "Not a Contribution." 63 | 64 | "Contributor" shall mean Licensor and any individual or Legal Entity 65 | on behalf of whom a Contribution has been received by Licensor and 66 | subsequently incorporated within the Work. 67 | 68 | 2. Grant of Copyright License. Subject to the terms and conditions of 69 | this License, each Contributor hereby grants to You a perpetual, 70 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 71 | copyright license to reproduce, prepare Derivative Works of, 72 | publicly display, publicly perform, sublicense, and distribute the 73 | Work and such Derivative Works in Source or Object form. 74 | 75 | 3. Grant of Patent License. Subject to the terms and conditions of 76 | this License, each Contributor hereby grants to You a perpetual, 77 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 78 | (except as stated in this section) patent license to make, have made, 79 | use, offer to sell, sell, import, and otherwise transfer the Work, 80 | where such license applies only to those patent claims licensable 81 | by such Contributor that are necessarily infringed by their 82 | Contribution(s) alone or by combination of their Contribution(s) 83 | with the Work to which such Contribution(s) was submitted. If You 84 | institute patent litigation against any entity (including a 85 | cross-claim or counterclaim in a lawsuit) alleging that the Work 86 | or a Contribution incorporated within the Work constitutes direct 87 | or contributory patent infringement, then any patent licenses 88 | granted to You under this License for that Work shall terminate 89 | as of the date such litigation is filed. 90 | 91 | 4. Redistribution. You may reproduce and distribute copies of the 92 | Work or Derivative Works thereof in any medium, with or without 93 | modifications, and in Source or Object form, provided that You 94 | meet the following conditions: 95 | 96 | (a) You must give any other recipients of the Work or 97 | Derivative Works a copy of this License; and 98 | 99 | (b) You must cause any modified files to carry prominent notices 100 | stating that You changed the files; and 101 | 102 | (c) You must retain, in the Source form of any Derivative Works 103 | that You distribute, all copyright, patent, trademark, and 104 | attribution notices from the Source form of the Work, 105 | excluding those notices that do not pertain to any part of 106 | the Derivative Works; and 107 | 108 | (d) If the Work includes a "NOTICE" text file as part of its 109 | distribution, then any Derivative Works that You distribute must 110 | include a readable copy of the attribution notices contained 111 | within such NOTICE file, excluding those notices that do not 112 | pertain to any part of the Derivative Works, in at least one 113 | of the following places: within a NOTICE text file distributed 114 | as part of the Derivative Works; within the Source form or 115 | documentation, if provided along with the Derivative Works; or, 116 | within a display generated by the Derivative Works, if and 117 | wherever such third-party notices normally appear. The contents 118 | of the NOTICE file are for informational purposes only and 119 | do not modify the License. You may add Your own attribution 120 | notices within Derivative Works that You distribute, alongside 121 | or as an addendum to the NOTICE text from the Work, provided 122 | that such additional attribution notices cannot be construed 123 | as modifying the License. 124 | 125 | You may add Your own copyright statement to Your modifications and 126 | may provide additional or different license terms and conditions 127 | for use, reproduction, or distribution of Your modifications, or 128 | for any such Derivative Works as a whole, provided Your use, 129 | reproduction, and distribution of the Work otherwise complies with 130 | the conditions stated in this License. 131 | 132 | 5. Submission of Contributions. Unless You explicitly state otherwise, 133 | any Contribution intentionally submitted for inclusion in the Work 134 | by You to the Licensor shall be under the terms and conditions of 135 | this License, without any additional terms or conditions. 136 | Notwithstanding the above, nothing herein shall supersede or modify 137 | the terms of any separate license agreement you may have executed 138 | with Licensor regarding such Contributions. 139 | 140 | 6. Trademarks. This License does not grant permission to use the trade 141 | names, trademarks, service marks, or product names of the Licensor, 142 | except as required for reasonable and customary use in describing the 143 | origin of the Work and reproducing the content of the NOTICE file. 144 | 145 | 7. Disclaimer of Warranty. Unless required by applicable law or 146 | agreed to in writing, Licensor provides the Work (and each 147 | Contributor provides its Contributions) on an "AS IS" BASIS, 148 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 149 | implied, including, without limitation, any warranties or conditions 150 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 151 | PARTICULAR PURPOSE. You are solely responsible for determining the 152 | appropriateness of using or redistributing the Work and assume any 153 | risks associated with Your exercise of permissions under this License. 154 | 155 | 8. Limitation of Liability. In no event and under no legal theory, 156 | whether in tort (including negligence), contract, or otherwise, 157 | unless required by applicable law (such as deliberate and grossly 158 | negligent acts) or agreed to in writing, shall any Contributor be 159 | liable to You for damages, including any direct, indirect, special, 160 | incidental, or consequential damages of any character arising as a 161 | result of this License or out of the use or inability to use the 162 | Work (including but not limited to damages for loss of goodwill, 163 | work stoppage, computer failure or malfunction, or any and all 164 | other commercial damages or losses), even if such Contributor 165 | has been advised of the possibility of such damages. 166 | 167 | 9. Accepting Warranty or Additional Liability. While redistributing 168 | the Work or Derivative Works thereof, You may choose to offer, 169 | and charge a fee for, acceptance of support, warranty, indemnity, 170 | or other liability obligations and/or rights consistent with this 171 | License. However, in accepting such obligations, You may act only 172 | on Your own behalf and on Your sole responsibility, not on behalf 173 | of any other Contributor, and only if You agree to indemnify, 174 | defend, and hold each Contributor harmless for any liability 175 | incurred by, or claims asserted against, such Contributor by reason 176 | of your accepting any such warranty or additional liability. 177 | 178 | END OF TERMS AND CONDITIONS 179 | 180 | APPENDIX: How to apply the Apache License to your work. 181 | 182 | To apply the Apache License to your work, attach the following 183 | boilerplate notice, with the fields enclosed by brackets "{}" 184 | replaced with your own identifying information. (Don't include 185 | the brackets!) The text should be enclosed in the appropriate 186 | comment syntax for the file format. We also recommend that a 187 | file or class name and description of purpose be included on the 188 | same "printed page" as the copyright notice for easier 189 | identification within third-party archives. 190 | 191 | Copyright {yyyy} {name of copyright owner} 192 | 193 | Licensed under the Apache License, Version 2.0 (the "License"); 194 | you may not use this file except in compliance with the License. 195 | You may obtain a copy of the License at 196 | 197 | http://www.apache.org/licenses/LICENSE-2.0 198 | 199 | Unless required by applicable law or agreed to in writing, software 200 | distributed under the License is distributed on an "AS IS" BASIS, 201 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 202 | See the License for the specific language governing permissions and 203 | limitations under the License. 204 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | unidecode 2 | ========= 3 | 4 | Unicode transliterator in Golang - Replaces non-ASCII characters with their ASCII approximations. 5 | 6 | [![GoDoc](https://godoc.org/github.com/rainycape/unidecode?status.svg)](https://godoc.org/github.com/rainycape/unidecode) 7 | -------------------------------------------------------------------------------- /decode.go: -------------------------------------------------------------------------------- 1 | package unidecode 2 | 3 | import ( 4 | "compress/zlib" 5 | "encoding/binary" 6 | "io" 7 | "strings" 8 | ) 9 | 10 | var ( 11 | transliterations [65536][]rune 12 | transCount = rune(len(transliterations)) 13 | getUint16 = binary.LittleEndian.Uint16 14 | ) 15 | 16 | func decodeTransliterations() { 17 | r, err := zlib.NewReader(strings.NewReader(tableData)) 18 | if err != nil { 19 | panic(err) 20 | } 21 | defer r.Close() 22 | tmp1 := make([]byte, 2) 23 | tmp2 := tmp1[:1] 24 | for { 25 | if _, err := io.ReadAtLeast(r, tmp1, 2); err != nil { 26 | if err == io.EOF { 27 | break 28 | } 29 | panic(err) 30 | } 31 | chr := getUint16(tmp1) 32 | if _, err := io.ReadAtLeast(r, tmp2, 1); err != nil { 33 | panic(err) 34 | } 35 | b := make([]byte, int(tmp2[0])) 36 | if _, err := io.ReadFull(r, b); err != nil { 37 | panic(err) 38 | } 39 | transliterations[int(chr)] = []rune(string(b)) 40 | } 41 | } 42 | -------------------------------------------------------------------------------- /make_table.go: -------------------------------------------------------------------------------- 1 | // +build none 2 | 3 | package main 4 | 5 | import ( 6 | "bytes" 7 | "compress/zlib" 8 | "encoding/binary" 9 | "fmt" 10 | "go/format" 11 | "io/ioutil" 12 | "strconv" 13 | "strings" 14 | ) 15 | 16 | func main() { 17 | data, err := ioutil.ReadFile("table.txt") 18 | if err != nil { 19 | panic(err) 20 | } 21 | var buf bytes.Buffer 22 | for _, line := range strings.Split(string(data), "\n") { 23 | if strings.HasPrefix(line, "/*") || line == "" { 24 | continue 25 | } 26 | sep := strings.IndexByte(line, ':') 27 | if sep == -1 { 28 | panic(line) 29 | } 30 | val, err := strconv.ParseInt(line[:sep], 0, 32) 31 | if err != nil { 32 | panic(err) 33 | } 34 | s, err := strconv.Unquote(line[sep+2:]) 35 | if err != nil { 36 | panic(err) 37 | } 38 | if s == "" { 39 | continue 40 | } 41 | if err := binary.Write(&buf, binary.LittleEndian, uint16(val)); err != nil { 42 | panic(err) 43 | } 44 | if err := binary.Write(&buf, binary.LittleEndian, uint8(len(s))); err != nil { 45 | panic(err) 46 | } 47 | buf.WriteString(s) 48 | } 49 | var cbuf bytes.Buffer 50 | w, err := zlib.NewWriterLevel(&cbuf, zlib.BestCompression) 51 | if err != nil { 52 | panic(err) 53 | } 54 | if _, err := w.Write(buf.Bytes()); err != nil { 55 | panic(err) 56 | } 57 | if err := w.Close(); err != nil { 58 | panic(err) 59 | } 60 | buf.Reset() 61 | buf.WriteString("package unidecode\n") 62 | buf.WriteString("// AUTOGENERATED - DO NOT EDIT!\n\n") 63 | fmt.Fprintf(&buf, "var tableData = %q;\n", cbuf.String()) 64 | dst, err := format.Source(buf.Bytes()) 65 | if err != nil { 66 | panic(err) 67 | } 68 | if err := ioutil.WriteFile("table.go", dst, 0644); err != nil { 69 | panic(err) 70 | } 71 | } 72 | -------------------------------------------------------------------------------- /unidecode.go: -------------------------------------------------------------------------------- 1 | // Package unidecode implements a unicode transliterator 2 | // which replaces non-ASCII characters with their ASCII 3 | // approximations. 4 | package unidecode 5 | 6 | //go:generate go run make_table.go 7 | 8 | import ( 9 | "sync" 10 | "unicode" 11 | ) 12 | 13 | const pooledCapacity = 64 14 | 15 | var ( 16 | slicePool sync.Pool 17 | decodingOnce sync.Once 18 | ) 19 | 20 | // Unidecode implements a unicode transliterator, which 21 | // replaces non-ASCII characters with their ASCII 22 | // counterparts. 23 | // Given an unicode encoded string, returns 24 | // another string with non-ASCII characters replaced 25 | // with their closest ASCII counterparts. 26 | // e.g. Unicode("áéíóú") => "aeiou" 27 | func Unidecode(s string) string { 28 | decodingOnce.Do(decodeTransliterations) 29 | l := len(s) 30 | var r []rune 31 | if l > pooledCapacity { 32 | r = make([]rune, 0, len(s)) 33 | } else { 34 | if x := slicePool.Get(); x != nil { 35 | r = x.([]rune)[:0] 36 | } else { 37 | r = make([]rune, 0, pooledCapacity) 38 | } 39 | } 40 | for _, c := range s { 41 | if c <= unicode.MaxASCII { 42 | r = append(r, c) 43 | continue 44 | } 45 | if c > unicode.MaxRune || c > transCount { 46 | /* Ignore reserved chars */ 47 | continue 48 | } 49 | if d := transliterations[c]; d != nil { 50 | r = append(r, d...) 51 | } 52 | } 53 | res := string(r) 54 | if l <= pooledCapacity { 55 | slicePool.Put(r) 56 | } 57 | return res 58 | } 59 | -------------------------------------------------------------------------------- /unidecode_test.go: -------------------------------------------------------------------------------- 1 | package unidecode 2 | 3 | import ( 4 | "testing" 5 | ) 6 | 7 | func testTransliteration(original string, decoded string, t *testing.T) { 8 | if r := Unidecode(original); r != decoded { 9 | t.Errorf("Expected '%s', got '%s'\n", decoded, r) 10 | } 11 | } 12 | 13 | func TestASCII(t *testing.T) { 14 | s := "ABCDEF" 15 | testTransliteration(s, s, t) 16 | } 17 | 18 | func TestKnosos(t *testing.T) { 19 | o := "Κνωσός" 20 | d := "Knosos" 21 | testTransliteration(o, d, t) 22 | } 23 | 24 | func TestBeiJing(t *testing.T) { 25 | o := "\u5317\u4EB0" 26 | d := "Bei Jing " 27 | testTransliteration(o, d, t) 28 | } 29 | 30 | func TestEmoji(t *testing.T) { 31 | o := "Hey Luna t belle 😵😂" 32 | d := "Hey Luna t belle " 33 | testTransliteration(o, d, t) 34 | } 35 | 36 | func BenchmarkUnidecode(b *testing.B) { 37 | cases := []string{ 38 | "ABCDEF", 39 | "Κνωσός", 40 | "\u5317\u4EB0", 41 | } 42 | for ii := 0; ii < b.N; ii++ { 43 | for _, v := range cases { 44 | _ = Unidecode(v) 45 | } 46 | } 47 | } 48 | 49 | func BenchmarkDecodeTable(b *testing.B) { 50 | for ii := 0; ii < b.N; ii++ { 51 | decodeTransliterations() 52 | } 53 | } 54 | 55 | func init() { 56 | decodeTransliterations() 57 | } 58 | --------------------------------------------------------------------------------