From 5c6bc0e556391dc00d413971d7b94f642e23bbb4 Mon Sep 17 00:00:00 2001 From: "Reece H. Dunn" Date: Sat, 22 Apr 2017 18:54:21 +0100 Subject: [PATCH] Armenian emphasis mark (U+055B) is used for interjections, so treat it as an exclamation mark. --- src/libespeak-ng/tokenizer.c | 2 -- tests/tokenizer.c | 2 +- 2 files changed, 1 insertion(+), 3 deletions(-) diff --git a/src/libespeak-ng/tokenizer.c b/src/libespeak-ng/tokenizer.c index a4ad1fc9..d9858b75 100644 --- a/src/libespeak-ng/tokenizer.c +++ b/src/libespeak-ng/tokenizer.c @@ -38,7 +38,6 @@ static const unsigned short punct_chars[] = { 0x00a1, // inverted exclamation 0x00bf, // inverted question - 0x055b, // Armenian emphasis mark 0 }; @@ -46,7 +45,6 @@ static const unsigned short punct_chars[] = { static const unsigned int punct_attributes[] = { CLAUSE_SEMICOLON | CLAUSE_OPTIONAL_SPACE_AFTER, // inverted exclamation CLAUSE_SEMICOLON | CLAUSE_OPTIONAL_SPACE_AFTER, // inverted question - CLAUSE_PERIOD | CLAUSE_PUNCTUATION_IN_WORD, // Armenian emphasis mark 0 }; diff --git a/tests/tokenizer.c b/tests/tokenizer.c index 6e27fce3..4719aa84 100644 --- a/tests/tokenizer.c +++ b/tests/tokenizer.c @@ -66,7 +66,7 @@ test_armenian() { printf("testing Armenian (Armn) script classification\n"); - assert(clause_type_from_codepoint(0x055B) == (CLAUSE_PERIOD | CLAUSE_PUNCTUATION_IN_WORD)); + assert(clause_type_from_codepoint(0x055B) == (CLAUSE_EXCLAMATION | CLAUSE_PUNCTUATION_IN_WORD)); assert(clause_type_from_codepoint(0x055C) == (CLAUSE_EXCLAMATION | CLAUSE_PUNCTUATION_IN_WORD)); assert(clause_type_from_codepoint(0x055D) == CLAUSE_COMMA); assert(clause_type_from_codepoint(0x055E) == (CLAUSE_QUESTION | CLAUSE_PUNCTUATION_IN_WORD));