Merge branch 'master' of https://github.com/espeak-ng/espeak-ng

.gitignore

 
 tests/*.test
 !tests/languages.test
+!tests/phoneme-output.test
 
 espeak-ng.pc
 

Makefile.am

 check:	tests/encoding.check \
 	tests/readclause.check \
 	tests/api.check \
+	tests/phoneme-output.check \
 	tests/languages.check
 
 ##### phoneme data:

dictsource/ka_emoji

 😖	შეცბუნებული სახე						// [1F616]
 😗	კოცნის გამომხატველი სახე					// [1F617]
 😘	სახე, რომელიც კოცნას აგზავნის					// [1F618]
-😙	კოცნის გამომხატველი სახე მომღიმარე თვალებით			// [1F619]
+😗	kissing face							// [1F617]
+//😙	კოცნის გამომხატველი სახე მომღიმარე თვალებით			// [1F619] TODO: This breaks speaking "7".
 😚	კოცნის გამომხატველი სახე დახუჭული თვალებით			// [1F61A]
 😛	სახე გამოყოფილი ენით						// [1F61B]
 😜	სახე გამოყოფილი ენითა და ჩაკრული თვალით				// [1F61C]
 😢	მტირალა სახე							// [1F622]
 😣	შეუპოვარი სახე							// [1F623]
 😤	სახე ცხვირიდან გამომავალი ორთქლით				// [1F624]
-😥	იმედგაცრუებული, მაგრამ შვების გამომხატველი სახე			// [1F625]
+😥	disappointed but relieved face					// [1F625]
+//😥	იმედგაცრუებული, მაგრამ შვების გამომხატველი სახე			// [1F625] TODO: This breaks speaking "3".
 😦	შეჭმუხნილი სახე ღია პირით					// [1F626]
 😧	ტანჯული სახე							// [1F627]
 😨	შეშინებული სახე							// [1F628]

src/libespeak-ng/dictionary.c

 						match1.end_type |= p - p_start;
 					}
 					strcpy(end_phonemes, match1.phonemes);
-					memcpy(p_start, word_copy, strlen(word_copy));
+					strcpy(p_start, word_copy);
 					return match1.end_type;
 				}
 			}
 		}
 	}
 
-	memcpy(p_start, word_copy, strlen(word_copy));
+	strcpy(p_start, word_copy);
 
 	return 0;
 }

src/libespeak-ng/tr_languages.c

 
 // ignore these characters
 static const unsigned short chars_ignore_default[] = {
-	0xad,    1, // soft hyphen
-	0x200c,  1, // zero width non-joiner
-	0x200d,  1, // zero width joiner
-	0, 0
+	// U+00AD SOFT HYPHEN
+	//     Used to mark hyphenation points in words for where to split a
+	//     word at the end of a line to provide readable justified text.
+	0xad,   1,
+	// U+200C ZERO WIDTH NON-JOINER
+	//     Used to prevent combined ligatures being displayed in their
+	//     combined form.
+	0x200c, 1,
+	// U+200D ZERO WIDTH JOINER
+	//     Used to indicate an alternative connected form made up of the
+	//     characters surrounding the ZWJ in Devanagari, Kannada, Malayalam
+	//     and Emoji.
+//	0x200d, 1, // Not ignored.
+	// End of the ignored character list.
+	0,      0
 };
 
 // alternatively, ignore characters but allow zero-width-non-joiner (lang-fa)
 static const unsigned short chars_ignore_zwnj_hyphen[] = {
-	0xad,   1,   // soft hyphen
-	0x640,  1,   // igniore Arabic Tatweel (lang=FA)
-	0x200c, '-', // zero width non-joiner, replace with hyphen
-	0x200d, 1,   // zero width joiner
-	0, 0
+	// U+00AD SOFT HYPHEN
+	//     Used to mark hyphenation points in words for where to split a
+	//     word at the end of a line to provide readable justified text.
+	0xad,   1,
+	// U+0640 TATWEEL (KASHIDA)
+	//     Used in Arabic scripts to stretch characters for justifying
+	//     the text.
+	0x640,  1,
+	// U+200C ZERO WIDTH NON-JOINER
+	//     Used to prevent combined ligatures being displayed in their
+	//     combined form.
+	0x200c, '-',
+	// U+200D ZERO WIDTH JOINER
+	//     Used to indicate an alternative connected form made up of the
+	//     characters surrounding the ZWJ in Devanagari, Kannada, Malayalam
+	//     and Emoji.
+//	0x200d, 1, // Not ignored.
+	// End of the ignored character list.
+	0,      0
 };
 
 const unsigned char utf8_ordinal[] = { 0xc2, 0xba, 0 }; // masculine ordinal character, UTF-8

src/libespeak-ng/translate.c

 					if (end2) {
 						RemoveEnding(tr, wordx, end2, word_copy);
 						end_type = TranslateRules(tr, wordx, phonemes, N_WORD_PHONEMES, end_phonemes, wflags|FLAG_NO_TRACE, dictionary_flags);
-						memcpy(wordx, word_copy, strlen(word_copy));
+						strcpy(wordx, word_copy);
 						if ((end_type & SUFX_P) == 0) {
 							// after removing the suffix, the prefix is no longer recognised.
 							// Keep the suffix, but don't use the prefix
 						wordx[-1] = ' ';
 						if (phonemes[0] == phonSWITCH) {
 							// change to another language in order to translate this word
-							memcpy(wordx, word_copy, strlen(word_copy));
+							strcpy(wordx, word_copy);
 							strcpy(word_phonemes, phonemes);
 							return 0;
 						}
 						found = LookupDictList(tr, &wordx, phonemes, dictionary_flags2, end_flags, wtab);  // without prefix and suffix
 						if (phonemes[0] == phonSWITCH) {
 							// change to another language in order to translate this word
-							memcpy(wordx, word_copy, strlen(word_copy));
+							strcpy(wordx, word_copy);
 							strcpy(word_phonemes, phonemes);
 							return 0;
 						}
 							if (phonemes[0] == phonSWITCH) {
 								// change to another language in order to translate this word
 								strcpy(word_phonemes, phonemes);
-								memcpy(wordx, word_copy, strlen(word_copy));
+								strcpy(wordx, word_copy);
 								wordx[-1] = c_temp;
 								return 0;
 							}
 					AppendPhonemes(tr, phonemes, N_WORD_PHONEMES, end_phonemes);
 					end_phonemes[0] = 0;
 				}
-				memcpy(wordx, word_copy, strlen(word_copy));
+				strcpy(wordx, word_copy);
 			}
 
 			wordx[-1] = c_temp;
 		char word[N_WORD_BYTES+1];
 		word[0] = 0;
 		word[1] = ' ';
-		memcpy(word+2, word_out, strlen(word_out));
+		strcpy(word+2, word_out);
 		word_out = word+2;
 
 		while (*word_out && available > 1) {

tests/phoneme-output.test

+#!/bin/sh
+
+test_phonemes() {
+	TEST_LANG=$1
+	EXPECTED=$2
+	TEST_TEXT=$3
+
+	echo "testing ${TEST_LANG} \"${TEST_TEXT}\""
+	ESPEAK_DATA_PATH=`pwd` LD_LIBRARY_PATH=src:${LD_LIBRARY_PATH} \
+		src/espeak-ng -xq -v ${TEST_LANG} "${TEST_TEXT}" > actual.txt
+	echo "${EXPECTED}" > expected.txt
+	diff expected.txt actual.txt || exit 1
+}
+
+test_phonemes en " h@l'oU" "hello"
+
+# Emoji
+
+# ED-3 - emoji_character [http://www.unicode.org/reports/tr51/tr51-12.html#def_emoji_character]
+test_phonemes en " Ekskla#m'eIS@N kw'EstS@n m'A@k" "⁉"
+test_phonemes en " Ekskla#m'eIS@N kw'EstS@n m'A@k r'eInboU" "⁉ 🌈"