将Unicode转换为GSM编码在Golang中的实现

huangapple
go评论122阅读模式
英文:

Converting unicode to gsm encoding in golang

问题

我正在将我的Python项目迁移到Go语言，并且有一个使用情况，需要将UTF-8编码转换为对应的GSM编码（如果可能的话）。我对Go语言非常陌生，如果能提供一些相关的文档或示例代码将非常有帮助。

例如：Python代码片段

ằ作为Unicode -> 在GSM编码后变为a

  1. for character in text:
  2.     if is_gsm(character):
  3.        transliterated_text += character.encode('utf-8')
  4.        continue
  5.     if is_nonascii_utf8(character):
  6.        transliterated_char = unidecode.unidecode(character)
  7.        if transliterated_char == '?' or transliterated_char == '':
  8.           gsm = False
  9.           break
  10.        if transliterated_char != rc:
  11.           character = transliterated_char
  12.           transliterated_text += character
  13.     else:
  14.           transliterated_text += character.encode('utf-8')
  16. if gsm and is_gsm(transliterated_text.decode('utf-8')):
  17.    text = transliterated_text.decode('utf-8')

谢谢。

英文:

I am working on migrating my project in python to golang and I have a use case for converting utf-8 encoding to corresponding gsm ones if possible. I am very new to go, it will be really helpful to get some documentation or examples around it.

For example: Python snippet

ằ as unicode -> a after gsm encoding

  1. for character in text:
  2.     if is_gsm(character):
  3.        transliterated_text += character.encode('utf-8')
  4.        continue
  5.     if is_nonascii_utf8(character):
  6.        transliterated_char = unidecode.unidecode(character)
  7.        if transliterated_char == '?' or transliterated_char == '':
  8.           gsm = False
  9.           break
  10.        if transliterated_char != rc:
  11.           character = transliterated_char
  12.           transliterated_text += character
  13.     else:
  14.           transliterated_text += character.encode('utf-8')
  16. if gsm and is_gsm(transliterated_text.decode('utf-8')):
  17.    text = transliterated_text.decode('utf-8')

Thanks

答案1

得分: 2

你可以按照以下方式进行操作：

  1. package main
  3. import (
  4. 	"fmt"
  5. 	"regexp"
  6. 	"strings"
  7. )
  9. var utf8GsmChars = map[string]string{
  10. 	`@`:      "\x00", `£`: "\x01", `$`:      "\x02",
  11. 	`¥`: "\x03", `è`: "\x04", `é`: "\x05",
  12. 	`ù`: "\x06", `ì`: "\x07", `ò`: "\x08",
  13. 	`Ç`: "\x09", `Ø`: "\x0B", `ø`: "\x0C",
  14. 	`Å`: "\x0E", `Δ`:      "\x10", `_`:      "\x11",
  15. 	`Φ`:      "\x12", `Γ`:      "\x13", `Λ`:      "\x14",
  16. 	`Ω`:      "\x15", `Π`:      "\x16", `Ψ`:      "\x17",
  17. 	`Σ`:      "\x18", `Θ`:      "\x19", `Ξ`:      "\x1A",
  18. 	`Æ`: "\x1C", `æ`: "\x1D", `ß`: "\x1E",
  19. 	`É`: "\x1F", `Ä`: "\x5B", `Ö`: "\x5C",
  20. 	`Ñ`: "\x5D", `Ü`: "\x5E", `§`: "\x5F",
  21. 	`¿`: "\x60", `ä`: "\x7B", `ö`: "\x7C",
  22. 	`ñ`: "\x7D", `ü`: "\x7E", `à`: "\x7F",
  24. 	`^`: "\x1B\x14`, `{`: "\x1B\x28",
  25. 	`}`: "\x1B\x29`, `\`: "\x1B\x2F",
  26. 	`[`: "\x1B\x3C`, `~`: "\x1B\x3D",
  27. 	`]`: "\x1B\x3E`, `|`: "\x1B\x40",
  28. 	`€`: "\x1B\x65",
  29. }
  31. var gsmUtf8Chars = map[string]string{
  32. 	"\x00": "\x40",
  33. 	"\x01": "\xC2\xA3",
  34. 	"\x02": "\x24",
  35. 	"\x03": "\xC2\xA5",
  36. 	"\x04": "\xC3\xA8",
  37. 	"\x05": "\xC3\xA9",
  38. 	"\x06": "\xC3\xB9",
  39. 	"\x07": "\xC3\xAC",
  40. 	"\x08": "\xC3\xB2",
  41. 	"\x09": "\xC3\x87",
  42. 	"\x0B": "\xC3\x98",
  43. 	"\x0C": "\xC3\xB8",
  44. 	"\x0E": "\xC3\xB8",
  45. 	"\x0F": "\xC3\xA5",
  46. 	"\x10": "\xCE\x94",
  47. 	"\x11": "\x5F",
  48. 	"\x12": "\xCE\xA6",
  49. 	"\x13": "\xCE\x93",
  50. 	"\x14": "\xCE\xA0",
  51. 	"\x15": "\xCE\xA9",
  52. 	"\x16": "\xCE\xA0",
  53. 	"\x17": "\xCE\xA8",
  54. 	"\x18": "\xCE\xA3",
  55. 	"\x19": "\xCE\x98",
  56. 	"\x1A": "\xCE\x9E",
  57. 	"\x1C": "\xC3\x86",
  58. 	"\x1D": "\xC3\xA6",
  59. 	"\x1E": "\xC3\x9F",
  60. 	"\x1F": "\xC3\x89",
  61. 	"\x20": "\x20",
  62. 	"\x24": "\xC2\xA4",
  63. 	"\x40": "\xC2\xA1",
  64. 	"\x5B": "\xC3\x84",
  65. 	"\x5C": "\xC3\x96",
  66. 	"\x5D": "\xC3\x91",
  67. 	"\x5E": "\xC3\x9C",
  68. 	"\x5F": "\xC2\xA7",
  69. 	"\x60": "\xC2\xBF",
  70. 	"\x7B": "\xC3\xA8",
  71. 	"\x7C": "\xC3\xB6",
  72. 	"\x7D": "\xC3\xB1",
  73. 	"\x7E": "\xC3\xBC",
  74. 	"\x7F": "\xC3\xA0",
  75. }
  77. func UTF8ToGsm0338(text string) string {
  78. 	var s string = text
  80. 	for k, v := range utf8GsmChars {
  81. 		s = strings.Replace(s, k, v, -1)
  82. 	}
  84. 	re := regexp.MustCompile("[\\x{0080}-\\x{10FFFF}]")
  85. 	s = re.ReplaceAllString(s, "?")
  87. 	return s
  88. }
  90. func GSM0338ToUTF8(text string) string {
  91. 	var s string = text
  93. 	for k, v := range gsmUtf8Chars {
  94. 		s = strings.Replace(s, k, v, -1)
  95. 	}
  97. 	return s
  98. }
  100. func main() {
  101. 	s := "Hello World"
  102. 	gsm := UTF8ToGsm0338(s)
  103. 	utf8 := GSM0338ToUTF8(gsm)
  104. 	fmt.Printf("word before: %s\nword after gsm: %s\nword after utf8: %s\n", s, gsm, utf8)
  106. }
英文:

You can do it in this way:

  1. package main
  3. import (
  4.         "fmt"
  5.         "regexp"
  6.         "strings"
  7. )
  9. var utf8GsmChars = map[string]string{
  10.         `@`: "\x00", `£`: "\x01", `$`: "\x02",
  11.         `¥`: "\x03", `è`: "\x04", `é`: "\x05",
  12.         `ù`: "\x06", `ì`: "\x07", `ò`: "\x08",
  13.         `Ç`: "\x09", `Ø`: "\x0B", `ø`: "\x0C",
  14.         `Å`: "\x0E", `Δ`: "\x10", `_`: "\x11",
  15.         `Φ`: "\x12", `Γ`: "\x13", `Λ`: "\x14",
  16.         `Ω`: "\x15", `Π`: "\x16", `Ψ`: "\x17",
  17.         `Σ`: "\x18", `Θ`: "\x19", `Ξ`: "\x1A",
  18.         `Æ`: "\x1C", `æ`: "\x1D", `ß`: "\x1E",
  19.         `É`: "\x1F", `Ä`: "\x5B", `Ö`: "\x5C",
  20.         `Ñ`: "\x5D", `Ü`: "\x5E", `§`: "\x5F",
  21.         `¿`: "\x60", `ä`: "\x7B", `ö`: "\x7C",
  22.         `ñ`: "\x7D", `ü`: "\x7E", `à`: "\x7F",
  24.         `^`: "\x1B\x14", `{`: "\x1B\x28",
  25.         `}`: "\x1B\x29", `\`: "\x1B\x2F",
  26.         `[`: "\x1B\x3C", `~`: "\x1B\x3D",
  27.         `]`: "\x1B\x3E", `|`: "\x1B\x40",
  28.         `€`: "\x1B\x65",
  29. }
  31. var gsmUtf8Chars = map[string]string{
  32.         "\x00": "\x40",
  33.         "\x01": "\xC2\xA3",
  34.         "\x02": "\x24",
  35.         "\x03": "\xC2\xA5",
  36.         "\x04": "\xC3\xA8",
  37.         "\x05": "\xC3\xA9",
  38.         "\x06": "\xC3\xB9",
  39.         "\x07": "\xC3\xAC",
  40.         "\x08": "\xC3\xB2",
  41.         "\x09": "\xC3\x87",
  42.         "\x0B": "\xC3\x98",
  43.         "\x0C": "\xC3\xB8",
  44.         "\x0E": "\xC3\xB8",
  45.         "\x0F": "\xC3\xA5",
  46.         "\x10": "\xCE\x94",
  47.         "\x11": "\x5F",
  48.         "\x12": "\xCE\xA6",
  49.         "\x13": "\xCE\x93",
  50.         "\x14": "\xCE\xA0",
  51.         "\x15": "\xCE\xA9",
  52.         "\x16": "\xCE\xA0",
  53.         "\x17": "\xCE\xA8",
  54.         "\x18": "\xCE\xA3",
  55.         "\x19": "\xCE\x98",
  56.         "\x1A": "\xCE\x9E",
  57.         "\x1C": "\xC3\x86",
  58.         "\x1D": "\xC3\xA6",
  59.         "\x1E": "\xC3\x9F",
  60.         "\x1F": "\xC3\x89",
  61.         "\x20": "\x20",
  62.         "\x24": "\xC2\xA4",
  63.         "\x40": "\xC2\xA1",
  64.         "\x5B": "\xC3\x84",
  65.         "\x5C": "\xC3\x96",
  66.         "\x5D": "\xC3\x91",
  67.         "\x5E": "\xC3\x9C",
  68.         "\x5F": "\xC2\xA7",
  69.         "\x60": "\xC2\xBF",
  70.         "\x7B": "\xC3\xA8",
  71.         "\x7C": "\xC3\xB6",
  72.         "\x7D": "\xC3\xB1",
  73.         "\x7E": "\xC3\xBC",
  74.         "\x7F": "\xC3\xA0",
  75. }
  77. func UTF8ToGsm0338(text string) string {
  78.         var s string = text
  80.         for k, v := range utf8GsmChars {
  81.                 s = strings.Replace(s, k, v, -1)
  82.         }
  84.         re := regexp.MustCompile("[\\x{0080}-\\x{10FFFF}]")
  85.         s = re.ReplaceAllString(s, "?")
  87.         return s
  88. }
  90. func GSM0338ToUTF8(text string) string {
  91.         var s string = text
  93.         for k, v := range gsmUtf8Chars {
  94.                 s = strings.Replace(s, k, v, -1)
  95.         }
  97.         return s
  98. }
  100. func main() {
  101.         s := "Hello World"
  102.         gsm := UTF8ToGsm0338(s)
  103.         utf8 := GSM0338ToUTF8(gsm)
  104.         fmt.Printf("word before: %s\nword after gsm: %s\nword after utf8: %s\n", s, gsm, utf8)
  106. }

huangapple
  • 本文由 发表于 2022年7月28日 17:28:58
  • 转载请务必保留本文链接：https://go.coder-hub.com/73150438.html
  • go
  • gsm
  • python
  • utf-8
匿名

发表评论

匿名网友

:?: :razz: :sad: :evil: :!: :smile: :oops: :grin: :eek: :shock: :???: :cool: :lol: :mad: :twisted: :roll: :wink: :idea: :arrow: :neutral: :cry: :mrgreen:

确定