+// © 2016 and later: Unicode, Inc. and others.
+// License & terms of use: http://www.unicode.org/copyright.html
/********************************************************************
* COPYRIGHT:
- * Copyright (c) 1997-2003, International Business Machines Corporation and
+ * Copyright (c) 1997-2016, International Business Machines Corporation and
* others. All Rights Reserved.
********************************************************************
************************************************************************
#include "jamotest.h"
#include "unicode/utypes.h"
#include "unicode/translit.h"
-#include "rbt.h"
+#include "cmemory.h"
#include "cpdtrans.h"
// SEP is the disambiguation separator used by Latin-Jamo and Jamo-Latin
-#define SEP "'"
+#define SEP "-"
JamoTest::JamoTest()
{
+ UParseError parseError;
UErrorCode status = U_ZERO_ERROR;
- NAME_JAMO = new RuleBasedTransliterator("Name-Jamo",
- JAMO_NAMES_RULES,
- UTRANS_FORWARD, status);
+ NAME_JAMO = Transliterator::createFromRules("Name-Jamo",
+ UnicodeString(JAMO_NAMES_RULES, -1, US_INV),
+ UTRANS_FORWARD, parseError, status);
if (U_FAILURE(status)) {
delete NAME_JAMO;
NAME_JAMO = NULL;
}
status = U_ZERO_ERROR;
- JAMO_NAME = new RuleBasedTransliterator("Jamo-Name",
- JAMO_NAMES_RULES,
- UTRANS_REVERSE, status);
+ JAMO_NAME = Transliterator::createFromRules("Jamo-Name",
+ UnicodeString(JAMO_NAMES_RULES, -1, US_INV),
+ UTRANS_REVERSE, parseError, status);
if (U_FAILURE(status)) {
delete JAMO_NAME;
JAMO_NAME = NULL;
Transliterator* latinJamo = Transliterator::createInstance("Latin-Jamo", UTRANS_FORWARD, parseError, status);
if (latinJamo == 0 || U_FAILURE(status)) {
- errln("FAIL: createInstance() returned 0");
+ dataerrln("FAIL: createInstance() returned 0 - %s", u_errorName(status));
return;
}
// Column 3 is expected value of L2. If the expected
// value of L2 is L1, then L2 is NULL.
+
+ // add tests for the update to fix problems where it didn't follow the standard
+ // see also http://www.unicode.org/cldr/data/charts/transforms/Latin-Hangul.html
+ "gach", "(Gi)(A)(Cf)", NULL,
+ "geumhui", "(Gi)(EU)(Mf)(Hi)(YI)", NULL,
+ "choe", "(Ci)(OE)", NULL,
+ "wo", "(IEUNG)(WEO)", NULL,
+ "Wonpil", "(IEUNG)(WEO)(Nf)(Pi)(I)(L)", "wonpil",
+ "GIPPEUM", "(Gi)(I)(BB)(EU)(Mf)", "gippeum",
+ "EUTTEUM", "(IEUNG)(EU)(DD)(EU)(Mf)", "eutteum",
+ "KKOTNAE", "(GGi)(O)(Tf)(Ni)(AE)", "kkotnae",
+ "gaga", "(Gi)(A)(Gi)(A)", NULL,
+ "gag-a", "(Gi)(A)(Gf)(IEUNG)(A)", NULL,
+ "gak-ka", "(Gi)(A)(Kf)(Ki)(A)", NULL,
+ "gakka", "(Gi)(A)(GGi)(A)", NULL,
+ "gakk-a", "(Gi)(A)(GGf)(IEUNG)(A)", NULL,
+ "gakkka", "(Gi)(A)(GGf)(Ki)(A)", NULL,
+ "gak-kka", "(Gi)(A)(Kf)(GGi)(A)", NULL,
+
"bab", "(Bi)(A)(Bf)", NULL,
- "babb", "(Bi)(A)(Bf)(Bi)(EU)", "bab" SEP "beu",
- "babbba", "(Bi)(A)(Bf)(BB)(A)", NULL,
- "bagg", "(Bi)(A)(GGf)", NULL,
- "baggga", "(Bi)(A)(GGf)(Gi)(A)", NULL,
- "bag" SEP "gga", "(Bi)(A)(Gf)(GGi)(A)", NULL,
+ "babb", "(Bi)(A)(Bf)(Bi)(EU)", "babbeu",
+ "babbba", "(Bi)(A)(Bf)(Bi)(EU)(Bi)(A)", "babbeuba",
+ "bagg", "(Bi)(A)(Gf)(Gi)(EU)", "baggeu",
+ "baggga", "(Bi)(A)(Gf)(Gi)(EU)(Gi)(A)", "baggeuga",
+ //"bag" SEP "gga", "(Bi)(A)(Gf)" SEP "(Gi)(EU)(Gi)(A)", "bag" SEP "geuga",
"kabsa", "(Ki)(A)(Bf)(Si)(A)", NULL,
"kabska", "(Ki)(A)(BS)(Ki)(A)", NULL,
"gabsbka", "(Gi)(A)(BS)(Bi)(EU)(Ki)(A)", "gabsbeuka", // not (Kf)
- "gga", "(GGi)(A)", NULL,
+ "gga", "(Gi)(EU)(Gi)(A)", "geuga",
"bsa", "(Bi)(EU)(Si)(A)", "beusa",
- "agg", "(IEUNG)(A)(GGf)", NULL,
- "agga", "(IEUNG)(A)(GGi)(A)", NULL,
- "la", "(R)(A)", "ra",
+ "agg", "(IEUNG)(A)(Gf)(Gi)(EU)", "aggeu",
+ "agga", "(IEUNG)(A)(Gf)(Gi)(A)", NULL,
+ "la", "(R)(A)", NULL,
"bs", "(Bi)(EU)(Sf)", "beus",
- "kalgga", "(Ki)(A)(L)(GGi)(A)", NULL,
+ "kalgga", "(Ki)(A)(L)(Gi)(EU)(Gi)(A)", "kalgeuga",
// 'r' in a final position is treated like 'l'
"karka", "(Ki)(A)(L)(Ki)(A)", "kalka",
};
- enum { CASE_length = sizeof(CASE) / sizeof(CASE[0]) };
+ enum { CASE_length = UPRV_LENGTHOF(CASE) };
int32_t i;
for (i=0; i<CASE_length; i+=3) {
UnicodeString hangul; hangul.append((UChar)0xBC0F);
UnicodeString jamo = nameToJamo("(Mi)(I)(Cf)");
UnicodeString latin("mic");
+ UnicodeString latin2("mich");
Transliterator *t = NULL;
UErrorCode status = U_ZERO_ERROR;
t = Transliterator::createInstance("NFD", UTRANS_FORWARD, status); // was Hangul-Jamo
if (U_FAILURE(status) || t == 0) {
- errln("FAIL: createInstance failed");
+ dataerrln("FAIL: createInstance failed");
return;
}
expect(*t, hangul, jamo);
t = Transliterator::createInstance("Latin-Jamo", UTRANS_FORWARD, status);
if (U_FAILURE(status) || t == 0) {
- errln("FAIL: createInstance failed");
+ dataerrln("FAIL: createInstance failed - %s", u_errorName(status));
return;
}
expect(*t, latin, jamo);
errln("FAIL: createInstance failed");
return;
}
- expect(*t, jamo, latin);
+ expect(*t, jamo, latin2);
delete t;
t = Transliterator::createInstance("Hangul-Latin", UTRANS_FORWARD, status);
errln("FAIL: createInstance failed");
return;
}
- expect(*t, hangul, latin);
+ expect(*t, hangul, latin2);
delete t;
t = Transliterator::createInstance("Latin-Hangul", UTRANS_FORWARD, status);
void
JamoTest::TestRealText() {
// Test text taken from the Unicode web site
- static const char* WHAT_IS_UNICODE[] = {
+ static const char* const WHAT_IS_UNICODE[] = {
"\\uc720\\ub2c8\\ucf54\\ub4dc\\uc5d0", "\\ub300\\ud574", "?",
"\\uc5b4\\ub5a4", "\\ud50c\\ub7ab\\ud3fc,", "\\uc5b4\\ub5a4",
"\\ubd80\\ubd84\\uc744", "\\ucc28\\uc9c0\\ud558\\uace0", "\\uc788\\uc2b5\\ub2c8\\ub2e4.",
"\\uc720\\ub2c8\\ucf54\\ub4dc\\ub97c",
- "\\ud074\\ub77c\\uc774\\uc5b8\\ud2b8-\\uc11c\\ubc84", "\\ub610\\ub294",
- "\\ub2e4\\uc911-\\uc5f0\\uacb0", "\\uc751\\uc6a9", "\\ud504\\ub85c\\uadf8\\ub7a8\\uacfc",
+ // Replaced a hyphen with a space to make the test case work with CLDR1.5
+ //"\\ud074\\ub77c\\uc774\\uc5b8\\ud2b8-\\uc11c\\ubc84", "\\ub610\\ub294",
+ "\\ud074\\ub77c\\uc774\\uc5b8\\ud2b8 \\uc11c\\ubc84", "\\ub610\\ub294",
+ // Replaced a hyphen with a space.
+ //"\\ub2e4\\uc911-\\uc5f0\\uacb0", "\\uc751\\uc6a9", "\\ud504\\ub85c\\uadf8\\ub7a8\\uacfc",
+ "\\ub2e4\\uc911 \\uc5f0\\uacb0", "\\uc751\\uc6a9", "\\ud504\\ub85c\\uadf8\\ub7a8\\uacfc",
"\\uc6f9", "\\uc0ac\\uc774\\ud2b8\\uc5d0", "\\ud1b5\\ud569\\ud558\\uba74",
"\\ub808\\uac70\\uc2dc", "\\ubb38\\uc790", "\\uc138\\ud2b8", "\\uc0ac\\uc6a9\\uc5d0",
"\\uc788\\uc5b4\\uc11c", "\\uc0c1\\ub2f9\\ud55c", "\\ube44\\uc6a9", "\\uc808\\uac10",
"\\ucc38\\uc870\\ud558\\uc2ed\\uc2dc\\uc624."
};
- enum { WHAT_IS_UNICODE_length = sizeof(WHAT_IS_UNICODE) / sizeof(WHAT_IS_UNICODE[0]) };
+ enum { WHAT_IS_UNICODE_length = UPRV_LENGTHOF(WHAT_IS_UNICODE) };
UParseError parseError;
UErrorCode status = U_ZERO_ERROR;
if (latinJamo == 0 || jamoHangul == 0 || U_FAILURE(status)) {
delete latinJamo;
delete jamoHangul;
- errln("FAIL: createInstance returned NULL");
+ dataerrln("FAIL: createInstance returned NULL - %s", u_errorName(status));
return;
}
Transliterator* jamoLatin = latinJamo->createInverse(status);
int32_t i;
for (i=0; i < WHAT_IS_UNICODE_length; ++i) {
++total;
- UnicodeString hangul = WHAT_IS_UNICODE[i];
+ UnicodeString hangul = UnicodeString(WHAT_IS_UNICODE[i], -1, US_INV);
hangul = hangul.unescape(); // Parse backslash-u escapes
UnicodeString hangulX = hangul;
rt.transliterate(hangulX);
projects / apple / icu.git / blobdiff