Use strcpy instead of memcpy+strlen.

This replaces uses of:

	memcpy(dst, src, strlen(src))

with:

	strcpy(dst, src)

This fixes issues with reading past the end of the copied buffer
(e.g. when processing word-based replacements for emoji characters)
by ensuring that the destination buffer is null terminated.

Reported by Michael Curran <[email protected]>

.gitignore

@@ -96,6 +96,7 @@ src/speak-ng
 
 tests/*.test
 !tests/languages.test
+!tests/phoneme-output.test
 
 espeak-ng.pc
 

Makefile.am

@@ -250,6 +250,7 @@ tests_api_test_SOURCES = tests/api.c
 check:	tests/encoding.check \
 	tests/readclause.check \
 	tests/api.check \
+	tests/phoneme-output.check \
 	tests/languages.check
 
 ##### phoneme data:

src/libespeak-ng/dictionary.c

@@ -2394,7 +2394,7 @@ int TranslateRules(Translator *tr, char *p_start, char *phonemes, int ph_size, 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;
 				}
 			}
@@ -2404,7 +2404,7 @@ int TranslateRules(Translator *tr, char *p_start, char *phonemes, int ph_size, c
 		}
 	}
 
-	memcpy(p_start, word_copy, strlen(word_copy));
+	strcpy(p_start, word_copy);
 
 	return 0;
 }

src/libespeak-ng/translate.c

@@ -795,7 +795,7 @@ static int TranslateWord3(Translator *tr, char *word_start, WORD_TAB *wtab, char
 					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
@@ -902,7 +902,7 @@ static int TranslateWord3(Translator *tr, char *word_start, WORD_TAB *wtab, char
 						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;
 						}
@@ -920,7 +920,7 @@ static int TranslateWord3(Translator *tr, char *word_start, WORD_TAB *wtab, char
 						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;
 						}
@@ -960,7 +960,7 @@ static int TranslateWord3(Translator *tr, char *word_start, WORD_TAB *wtab, char
 							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;
 							}
@@ -974,7 +974,7 @@ static int TranslateWord3(Translator *tr, char *word_start, WORD_TAB *wtab, char
 					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;
@@ -1139,7 +1139,7 @@ int TranslateWord(Translator *tr, char *word_start, WORD_TAB *wtab, char *word_o
 		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

@@ -0,0 +1,21 @@
+#!/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" "⁉ 🌈"