eSpeak NG is an open source speech synthesizer that supports more than hundred languages and accents.
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

encoding.c 6.2KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169
  1. /*
  2. * Copyright (C) 2017 Reece H. Dunn
  3. *
  4. * This program is free software; you can redistribute it and/or modify
  5. * it under the terms of the GNU General Public License as published by
  6. * the Free Software Foundation; either version 3 of the License, or
  7. * (at your option) any later version.
  8. *
  9. * This program is distributed in the hope that it will be useful,
  10. * but WITHOUT ANY WARRANTY; without even the implied warranty of
  11. * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  12. * GNU General Public License for more details.
  13. *
  14. * You should have received a copy of the GNU General Public License
  15. * along with this program; if not, write see:
  16. * <http://www.gnu.org/licenses/>.
  17. */
  18. #include "config.h"
  19. #include <assert.h>
  20. #include <stdint.h>
  21. #include <stdlib.h>
  22. #include <stdio.h>
  23. #include <espeak-ng/espeak_ng.h>
  24. #include "encoding.h"
  25. void
  26. test_unbound_text_decoder()
  27. {
  28. printf("testing unbound text decoder\n");
  29. espeak_ng_TEXT_DECODER *decoder = create_text_decoder();
  30. assert(decoder != NULL);
  31. assert(text_decoder_eof(decoder) == 1);
  32. destroy_text_decoder(decoder);
  33. }
  34. void
  35. test_unknown_encoding()
  36. {
  37. printf("testing unknown encodings\n");
  38. assert(espeak_ng_EncodingFromName(NULL) == ESPEAKNG_ENCODING_UNKNOWN);
  39. assert(espeak_ng_EncodingFromName("") == ESPEAKNG_ENCODING_UNKNOWN);
  40. assert(espeak_ng_EncodingFromName("abcxyz") == ESPEAKNG_ENCODING_UNKNOWN);
  41. assert(espeak_ng_EncodingFromName("US") == ESPEAKNG_ENCODING_UNKNOWN); // wrong case
  42. espeak_ng_TEXT_DECODER *decoder = create_text_decoder();
  43. assert(text_decoder_decode_string(decoder, "aG\x92\xA0\xDE", 5, ESPEAKNG_ENCODING_UNKNOWN) == ENS_UNKNOWN_TEXT_ENCODING);
  44. assert(text_decoder_eof(decoder) == 1);
  45. destroy_text_decoder(decoder);
  46. }
  47. void
  48. test_us_ascii_encoding()
  49. {
  50. printf("testing US-ASCII encoding\n");
  51. assert(espeak_ng_EncodingFromName("US-ASCII") == ESPEAKNG_ENCODING_US_ASCII);
  52. assert(espeak_ng_EncodingFromName("iso-ir-6") == ESPEAKNG_ENCODING_US_ASCII);
  53. assert(espeak_ng_EncodingFromName("ANSI_X3.4-1968") == ESPEAKNG_ENCODING_US_ASCII);
  54. assert(espeak_ng_EncodingFromName("ANSI_X3.4-1986") == ESPEAKNG_ENCODING_US_ASCII);
  55. assert(espeak_ng_EncodingFromName("ISO_646.irv:1991") == ESPEAKNG_ENCODING_US_ASCII);
  56. assert(espeak_ng_EncodingFromName("ISO646-US") == ESPEAKNG_ENCODING_US_ASCII);
  57. assert(espeak_ng_EncodingFromName("us") == ESPEAKNG_ENCODING_US_ASCII);
  58. assert(espeak_ng_EncodingFromName("IBM367") == ESPEAKNG_ENCODING_US_ASCII);
  59. assert(espeak_ng_EncodingFromName("cp367") == ESPEAKNG_ENCODING_US_ASCII);
  60. assert(espeak_ng_EncodingFromName("csASCII") == ESPEAKNG_ENCODING_US_ASCII);
  61. espeak_ng_TEXT_DECODER *decoder = create_text_decoder();
  62. assert(text_decoder_decode_string(decoder, "aG\x92\xA0\xDE", 5, ESPEAKNG_ENCODING_US_ASCII) == ENS_OK);
  63. assert(text_decoder_eof(decoder) == 0);
  64. assert(text_decoder_getc(decoder) == 'a');
  65. assert(text_decoder_eof(decoder) == 0);
  66. assert(text_decoder_getc(decoder) == 'G');
  67. assert(text_decoder_eof(decoder) == 0);
  68. assert(text_decoder_getc(decoder) == 0xFFFD);
  69. assert(text_decoder_eof(decoder) == 0);
  70. assert(text_decoder_getc(decoder) == 0xFFFD);
  71. assert(text_decoder_eof(decoder) == 0);
  72. assert(text_decoder_getc(decoder) == 0xFFFD);
  73. assert(text_decoder_eof(decoder) == 1);
  74. destroy_text_decoder(decoder);
  75. }
  76. void
  77. test_iso_8859_1_encoding()
  78. {
  79. printf("testing ISO-8859-1 encoding\n");
  80. assert(espeak_ng_EncodingFromName("ISO-8859-1:1987") == ESPEAKNG_ENCODING_ISO_8859_1);
  81. assert(espeak_ng_EncodingFromName("ISO-8859-1") == ESPEAKNG_ENCODING_ISO_8859_1);
  82. assert(espeak_ng_EncodingFromName("ISO_8859-1") == ESPEAKNG_ENCODING_ISO_8859_1);
  83. assert(espeak_ng_EncodingFromName("iso-ir-100") == ESPEAKNG_ENCODING_ISO_8859_1);
  84. assert(espeak_ng_EncodingFromName("latin1") == ESPEAKNG_ENCODING_ISO_8859_1);
  85. assert(espeak_ng_EncodingFromName("l1") == ESPEAKNG_ENCODING_ISO_8859_1);
  86. assert(espeak_ng_EncodingFromName("IBM819") == ESPEAKNG_ENCODING_ISO_8859_1);
  87. assert(espeak_ng_EncodingFromName("cp819") == ESPEAKNG_ENCODING_ISO_8859_1);
  88. assert(espeak_ng_EncodingFromName("csISOLatin1") == ESPEAKNG_ENCODING_ISO_8859_1);
  89. espeak_ng_TEXT_DECODER *decoder = create_text_decoder();
  90. assert(text_decoder_decode_string(decoder, "aG\x92\xA0\xDE", 5, ESPEAKNG_ENCODING_ISO_8859_1) == ENS_OK);
  91. assert(text_decoder_eof(decoder) == 0);
  92. assert(text_decoder_getc(decoder) == 'a');
  93. assert(text_decoder_eof(decoder) == 0);
  94. assert(text_decoder_getc(decoder) == 'G');
  95. assert(text_decoder_eof(decoder) == 0);
  96. assert(text_decoder_getc(decoder) == 0x92);
  97. assert(text_decoder_eof(decoder) == 0);
  98. assert(text_decoder_getc(decoder) == 0xA0);
  99. assert(text_decoder_eof(decoder) == 0);
  100. assert(text_decoder_getc(decoder) == 0xDE);
  101. assert(text_decoder_eof(decoder) == 1);
  102. destroy_text_decoder(decoder);
  103. }
  104. void
  105. test_iso_8859_2_encoding()
  106. {
  107. printf("testing ISO-8859-2 encoding\n");
  108. assert(espeak_ng_EncodingFromName("ISO-8859-2:1987") == ESPEAKNG_ENCODING_ISO_8859_2);
  109. assert(espeak_ng_EncodingFromName("ISO-8859-2") == ESPEAKNG_ENCODING_ISO_8859_2);
  110. assert(espeak_ng_EncodingFromName("ISO_8859-2") == ESPEAKNG_ENCODING_ISO_8859_2);
  111. assert(espeak_ng_EncodingFromName("iso-ir-101") == ESPEAKNG_ENCODING_ISO_8859_2);
  112. assert(espeak_ng_EncodingFromName("latin2") == ESPEAKNG_ENCODING_ISO_8859_2);
  113. assert(espeak_ng_EncodingFromName("l2") == ESPEAKNG_ENCODING_ISO_8859_2);
  114. assert(espeak_ng_EncodingFromName("csISOLatin2") == ESPEAKNG_ENCODING_ISO_8859_2);
  115. espeak_ng_TEXT_DECODER *decoder = create_text_decoder();
  116. assert(text_decoder_decode_string(decoder, "aG\x92\xA0\xDE", 5, ESPEAKNG_ENCODING_ISO_8859_2) == ENS_OK);
  117. assert(text_decoder_eof(decoder) == 0);
  118. assert(text_decoder_getc(decoder) == 'a');
  119. assert(text_decoder_eof(decoder) == 0);
  120. assert(text_decoder_getc(decoder) == 'G');
  121. assert(text_decoder_eof(decoder) == 0);
  122. assert(text_decoder_getc(decoder) == 0x92);
  123. assert(text_decoder_eof(decoder) == 0);
  124. assert(text_decoder_getc(decoder) == 0xA0);
  125. assert(text_decoder_eof(decoder) == 0);
  126. assert(text_decoder_getc(decoder) == 0x0162);
  127. assert(text_decoder_eof(decoder) == 1);
  128. destroy_text_decoder(decoder);
  129. }
  130. int
  131. main(int argc, char **argv)
  132. {
  133. test_unbound_text_decoder();
  134. test_unknown_encoding();
  135. test_us_ascii_encoding();
  136. test_iso_8859_1_encoding();
  137. test_iso_8859_2_encoding();
  138. printf("done\n");
  139. return EXIT_SUCCESS;
  140. }