2000-01-15 02:00:06 +00:00
|
|
|
/********************************************************************
|
|
|
|
* COPYRIGHT:
|
|
|
|
* Copyright (c) 1997-1999, International Business Machines Corporation and
|
|
|
|
* others. All Rights Reserved.
|
|
|
|
********************************************************************/
|
|
|
|
/********************************************************************************
|
1999-08-16 21:50:52 +00:00
|
|
|
*
|
|
|
|
* File CUCDTST.C
|
|
|
|
*
|
|
|
|
* Modification History:
|
|
|
|
* Name Description
|
1999-10-18 22:48:32 +00:00
|
|
|
* Madhu Katragadda Ported for C API, added tests for string functions
|
1999-08-16 21:50:52 +00:00
|
|
|
*********************************************************************************
|
|
|
|
*/
|
1999-11-22 19:39:22 +00:00
|
|
|
|
|
|
|
#include <stdio.h>
|
|
|
|
#include <string.h>
|
1999-12-28 23:57:50 +00:00
|
|
|
#include "unicode/uchar.h"
|
|
|
|
#include "unicode/utypes.h"
|
1999-11-22 19:39:22 +00:00
|
|
|
#include "cstring.h"
|
1999-08-16 21:50:52 +00:00
|
|
|
#include "cintltst.h"
|
|
|
|
#include "cucdtst.h"
|
1999-12-28 23:57:50 +00:00
|
|
|
#include "unicode/utypes.h"
|
|
|
|
#include "unicode/ustring.h"
|
|
|
|
#include "unicode/uloc.h"
|
1999-08-16 21:50:52 +00:00
|
|
|
|
2000-01-17 22:59:59 +00:00
|
|
|
|
1999-11-22 19:39:22 +00:00
|
|
|
/* prototypes --------------------------------------------------------------- */
|
|
|
|
|
|
|
|
static void
|
|
|
|
TestCharNames();
|
|
|
|
|
2000-04-24 22:44:06 +00:00
|
|
|
static void
|
|
|
|
TestMirroring();
|
|
|
|
|
2000-06-12 19:49:49 +00:00
|
|
|
static void
|
|
|
|
TestWhitespace();
|
|
|
|
|
1999-11-22 19:39:22 +00:00
|
|
|
/* test data ---------------------------------------------------------------- */
|
2000-01-14 23:41:58 +00:00
|
|
|
#define MIN(a,b) (a < b ? a : b)
|
1999-11-22 19:39:22 +00:00
|
|
|
|
1999-08-16 21:50:52 +00:00
|
|
|
UChar*** dataTable = 0;
|
|
|
|
const UChar LAST_CHAR_CODE_IN_FILE = 0xFFFD;
|
|
|
|
const char tagStrings[] = "MnMcMeNdNlNoZsZlZpCcCfCsCoCnLuLlLtLmLoPcPdPsPePoSmScSkSoPiPf";
|
|
|
|
const int32_t tagValues[] =
|
|
|
|
{
|
1999-10-07 00:07:53 +00:00
|
|
|
/* Mn */ U_NON_SPACING_MARK,
|
|
|
|
/* Mc */ U_COMBINING_SPACING_MARK,
|
|
|
|
/* Me */ U_ENCLOSING_MARK,
|
|
|
|
/* Nd */ U_DECIMAL_DIGIT_NUMBER,
|
|
|
|
/* Nl */ U_LETTER_NUMBER,
|
|
|
|
/* No */ U_OTHER_NUMBER,
|
|
|
|
/* Zs */ U_SPACE_SEPARATOR,
|
|
|
|
/* Zl */ U_LINE_SEPARATOR,
|
|
|
|
/* Zp */ U_PARAGRAPH_SEPARATOR,
|
|
|
|
/* Cc */ U_CONTROL_CHAR,
|
|
|
|
/* Cf */ U_FORMAT_CHAR,
|
|
|
|
/* Cs */ U_SURROGATE,
|
|
|
|
/* Co */ U_PRIVATE_USE_CHAR,
|
|
|
|
/* Cn */ U_UNASSIGNED,
|
|
|
|
/* Lu */ U_UPPERCASE_LETTER,
|
|
|
|
/* Ll */ U_LOWERCASE_LETTER,
|
|
|
|
/* Lt */ U_TITLECASE_LETTER,
|
|
|
|
/* Lm */ U_MODIFIER_LETTER,
|
|
|
|
/* Lo */ U_OTHER_LETTER,
|
|
|
|
/* Pc */ U_CONNECTOR_PUNCTUATION,
|
|
|
|
/* Pd */ U_DASH_PUNCTUATION,
|
|
|
|
/* Ps */ U_START_PUNCTUATION,
|
|
|
|
/* Pe */ U_END_PUNCTUATION,
|
|
|
|
/* Po */ U_OTHER_PUNCTUATION,
|
|
|
|
/* Sm */ U_MATH_SYMBOL,
|
|
|
|
/* Sc */ U_CURRENCY_SYMBOL,
|
|
|
|
/* Sk */ U_MODIFIER_SYMBOL,
|
|
|
|
/* So */ U_OTHER_SYMBOL,
|
|
|
|
/* Pi */ U_INITIAL_PUNCTUATION,
|
|
|
|
/* Pf */ U_FINAL_PUNCTUATION
|
1999-08-16 21:50:52 +00:00
|
|
|
};
|
|
|
|
const char dirStrings[][5] = {
|
|
|
|
"L",
|
|
|
|
"R",
|
|
|
|
"EN",
|
|
|
|
"ES",
|
|
|
|
"ET",
|
|
|
|
"AN",
|
|
|
|
"CS",
|
|
|
|
"B",
|
|
|
|
"S",
|
|
|
|
"WS",
|
|
|
|
"ON",
|
|
|
|
"LRE",
|
|
|
|
"LRO",
|
|
|
|
"AL",
|
|
|
|
"RLE",
|
|
|
|
"RLO",
|
|
|
|
"PDF",
|
|
|
|
"NSM",
|
|
|
|
"BN"
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
|
|
void addUnicodeTest(TestNode** root)
|
|
|
|
{
|
|
|
|
setUpDataTable();
|
|
|
|
|
|
|
|
addTest(root, &TestUpperLower, "tsutil/cucdtst/TestUpperLower");
|
|
|
|
addTest(root, &TestLetterNumber, "tsutil/cucdtst/TestLetterNumber");
|
|
|
|
addTest(root, &TestMisc, "tsutil/cucdtst/TestMisc");
|
|
|
|
addTest(root, &TestControlPrint, "tsutil/cucdtst/TestControlPrint");
|
|
|
|
addTest(root, &TestIdentifier, "tsutil/cucdtst/TestIdentifier");
|
|
|
|
addTest(root, &TestUnicodeData, "tsutil/cucdtst/TestUnicodeData");
|
|
|
|
addTest(root, &TestStringFunctions, "tsutil/cucdtst/TestStringFunctions");
|
1999-11-22 19:39:22 +00:00
|
|
|
addTest(root, &TestCharNames, "tsutil/cucdtst/TestCharNames");
|
2000-04-24 22:44:06 +00:00
|
|
|
addTest(root, &TestMirroring, "tsutil/cucdtst/TestMirroring");
|
2000-06-12 19:49:49 +00:00
|
|
|
addTest(root, &TestWhitespace, "tsutil/cucdtst/TestWhitespace");
|
1999-08-16 21:50:52 +00:00
|
|
|
}
|
1999-11-22 19:39:22 +00:00
|
|
|
|
1999-08-16 21:50:52 +00:00
|
|
|
/*==================================================== */
|
|
|
|
/* test u_toupper() and u_tolower() */
|
|
|
|
/*==================================================== */
|
|
|
|
void TestUpperLower()
|
|
|
|
{
|
2000-03-22 01:57:16 +00:00
|
|
|
U_STRING_DECL(upperTest, "abcdefg123hij.?:klmno", 21);
|
|
|
|
U_STRING_DECL(lowerTest, "ABCDEFG123HIJ.?:KLMNO", 21);
|
1999-08-16 21:50:52 +00:00
|
|
|
int i;
|
2000-03-22 01:57:16 +00:00
|
|
|
|
|
|
|
U_STRING_INIT(upperTest, "abcdefg123hij.?:klmno", 21);
|
|
|
|
U_STRING_INIT(lowerTest, "ABCDEFG123HIJ.?:KLMNO", 21);
|
|
|
|
|
1999-08-16 21:50:52 +00:00
|
|
|
log_verbose("testing upper lower\n");
|
|
|
|
for (i = 0; i < 21; i++) {
|
|
|
|
|
|
|
|
log_verbose("testing to upper to lower\n");
|
|
|
|
if (u_isalpha(upperTest[i]) && !u_islower(upperTest[i]))
|
|
|
|
{
|
|
|
|
log_err("Failed isLowerCase test at %c\n", upperTest[i]);
|
|
|
|
}
|
|
|
|
else if (u_isalpha(lowerTest[i]) && !u_isupper(lowerTest[i]))
|
|
|
|
{
|
|
|
|
log_err("Failed isUpperCase test at %c\n", lowerTest[i]);
|
|
|
|
}
|
|
|
|
else if (upperTest[i] != u_tolower(lowerTest[i]))
|
|
|
|
{
|
|
|
|
log_err("Failed case conversion from %c To %c :\n", lowerTest[i], upperTest[i]);
|
|
|
|
|
|
|
|
}
|
|
|
|
else if (lowerTest[i] != u_toupper(upperTest[i]))
|
|
|
|
{
|
|
|
|
log_err("Failed case conversion : %c To %c \n", upperTest[i], lowerTest[i]);
|
|
|
|
}
|
|
|
|
else if (upperTest[i] != u_tolower(upperTest[i]))
|
|
|
|
{
|
|
|
|
log_err("Failed case conversion with itself: %c\n", upperTest[i]);
|
|
|
|
}
|
|
|
|
else if (lowerTest[i] != u_toupper(lowerTest[i]))
|
|
|
|
{
|
|
|
|
log_err("Failed case conversion with itself: %c\n", lowerTest[i]);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
log_verbose("done testing upper Lower\n");
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
/* test isLetter(u_isapha()) and isDigit(u_isdigit()) */
|
|
|
|
void TestLetterNumber()
|
|
|
|
{
|
|
|
|
UChar i = 0x0000;
|
|
|
|
|
|
|
|
for (i = 0x0041; i < 0x005B; i++) {
|
|
|
|
log_verbose("Testing for isalpha\n");
|
|
|
|
if (!u_isalpha(i))
|
|
|
|
{
|
|
|
|
log_err("Failed isLetter test at %.4X\n", i);
|
|
|
|
|
|
|
|
}
|
|
|
|
}
|
|
|
|
for (i = 0x0660; i < 0x066A; i++) {
|
|
|
|
log_verbose("Testing for isalpha\n");
|
|
|
|
if (u_isalpha(i))
|
|
|
|
{
|
|
|
|
log_err("Failed isLetter test with numbers at %.4X\n", i);
|
|
|
|
|
|
|
|
}
|
|
|
|
}
|
|
|
|
for (i = 0x0660; i < 0x066A; i++) {
|
|
|
|
log_verbose("Testing for isdigit\n");
|
|
|
|
if (!u_isdigit(i))
|
|
|
|
{
|
|
|
|
log_verbose("Failed isNumber test at %.4X\n", i);
|
|
|
|
}
|
|
|
|
}
|
1999-11-19 18:23:29 +00:00
|
|
|
for (i = 0x0041; i < 0x005B; i++) {
|
|
|
|
log_verbose("Testing for isalnum\n");
|
|
|
|
if (!u_isalnum(i))
|
|
|
|
{
|
|
|
|
log_err("Failed isAlNum test at %.4X\n", i);
|
|
|
|
|
|
|
|
}
|
|
|
|
}
|
|
|
|
for (i = 0x0660; i < 0x066A; i++) {
|
|
|
|
log_verbose("Testing for isalnum\n");
|
|
|
|
if (!u_isalnum(i))
|
|
|
|
{
|
|
|
|
log_err("Failed isAlNum test at %.4X\n", i);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
1999-08-16 21:50:52 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
/* Tests for isDefined(u_isdefined)(, isBaseForm(u_isbase()), isSpaceChar(u_isspace()),u_CharDigitValue(),u_CharCellWidth() */
|
|
|
|
void TestMisc()
|
|
|
|
{
|
|
|
|
const UChar sampleSpaces[] = {0x0020, 0x00a0, 0x2000, 0x2001, 0x2005};
|
2000-03-22 01:57:16 +00:00
|
|
|
const UChar sampleNonSpaces[] = {0x61, 0x62, 0x63, 0x64, 0x74};
|
1999-08-16 21:50:52 +00:00
|
|
|
const UChar sampleUndefined[] = {0xfff1, 0xfff7, 0xfa30};
|
|
|
|
const UChar sampleDefined[] = {0x523E, 0x4f88, 0xfffd};
|
|
|
|
const UChar sampleBase[] = {0x0061, 0x0031, 0x03d2};
|
|
|
|
const UChar sampleNonBase[] = {0x002B, 0x0020, 0x203B};
|
|
|
|
const UChar sampleChars[] = {0x000a, 0x0045, 0x4e00, 0xDC00};
|
|
|
|
const UChar sampleDigits[]= {0x0030, 0x0662, 0x0F23, 0x0ED5};
|
|
|
|
const UChar sampleNonDigits[] = {0x0010, 0x0041, 0x0122, 0x68FE};
|
|
|
|
const int32_t sampleDigitValues[] = {0, 2, 3, 5};
|
|
|
|
|
|
|
|
enum ECellWidths /* pasted in here from unicode.h */
|
|
|
|
{
|
|
|
|
ZERO_WIDTH = 0,
|
|
|
|
HALF_WIDTH = 1,
|
|
|
|
FULL_WIDTH = 2,
|
|
|
|
NEUTRAL = 3
|
|
|
|
};
|
|
|
|
|
|
|
|
const uint16_t sampleCellWidth[] = { ZERO_WIDTH,
|
|
|
|
HALF_WIDTH,
|
|
|
|
FULL_WIDTH,
|
|
|
|
NEUTRAL};
|
|
|
|
int i;
|
2000-05-22 22:24:51 +00:00
|
|
|
char icuVersion[U_MAX_VERSION_STRING_LENGTH];
|
2000-01-14 23:41:58 +00:00
|
|
|
UVersionInfo realVersion;
|
|
|
|
|
2000-01-15 00:03:30 +00:00
|
|
|
memset(icuVersion, 0, U_MAX_VERSION_STRING_LENGTH);
|
1999-08-16 21:50:52 +00:00
|
|
|
for (i = 0; i < 5; i++) {
|
|
|
|
log_verbose("Testing for isspace and nonspaces\n");
|
|
|
|
if (!(u_isspace(sampleSpaces[i])) ||
|
|
|
|
(u_isspace(sampleNonSpaces[i])))
|
|
|
|
{
|
|
|
|
log_err("Space char test error : %d or %d \n", (int32_t)sampleSpaces[i], (int32_t)sampleNonSpaces[i]);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
for (i = 0; i < 3; i++) {
|
|
|
|
log_verbose("Testing for isdefined\n");
|
|
|
|
if ((u_isdefined(sampleUndefined[i])) ||
|
|
|
|
!(u_isdefined(sampleDefined[i])))
|
|
|
|
{
|
|
|
|
log_err("Undefined char test error : %d or %d\n", (int32_t)sampleUndefined[i], (int32_t)sampleDefined[i]);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
for (i = 0; i < 3; i++) {
|
|
|
|
log_verbose("Testing for isbase\n");
|
|
|
|
if ((u_isbase(sampleNonBase[i])) ||
|
|
|
|
!(u_isbase(sampleBase[i])))
|
|
|
|
{
|
|
|
|
log_err("Non-baseform char test error : %d or %d",(int32_t)sampleNonBase[i], (int32_t)sampleBase[i]);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
for (i = 0; i < 4; i++) {
|
|
|
|
log_verbose("Testing for charcellwidth\n");
|
|
|
|
if (u_charCellWidth(sampleChars[i]) != sampleCellWidth[i])
|
|
|
|
{
|
|
|
|
log_err("Cell width char test error : %d \n", (int32_t)sampleChars[i]);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
for (i = 0; i < 4; i++) {
|
|
|
|
log_verbose("Testing for isdigit\n");
|
|
|
|
if ((u_isdigit(sampleDigits[i]) &&
|
|
|
|
(u_charDigitValue(sampleDigits[i])!= sampleDigitValues[i])) ||
|
|
|
|
(u_isdigit(sampleNonDigits[i]))) {
|
|
|
|
log_err("Digit char test error : %d or %d\n", (int32_t)sampleDigits[i], (int32_t)sampleNonDigits[i]);
|
|
|
|
}
|
|
|
|
}
|
2000-01-14 23:41:58 +00:00
|
|
|
/* Tests the ICU version #*/
|
|
|
|
u_getVersion(realVersion);
|
2000-05-22 22:24:51 +00:00
|
|
|
u_versionToString(realVersion, icuVersion);
|
2000-01-14 23:41:58 +00:00
|
|
|
if (strncmp(icuVersion, U_ICU_VERSION, MIN(strlen(icuVersion), strlen(U_ICU_VERSION))) != 0)
|
|
|
|
{
|
2000-04-19 20:00:49 +00:00
|
|
|
log_err("ICU version test failed. Header says=%s, got=%s \n", U_ICU_VERSION, icuVersion);
|
2000-01-14 23:41:58 +00:00
|
|
|
}
|
2000-04-19 20:00:49 +00:00
|
|
|
#if defined(ICU_VERSION)
|
|
|
|
/* test only happens where we have configure.in with VERSION - sanity check. */
|
|
|
|
if(strcmp(U_ICU_VERSION, ICU_VERSION))
|
|
|
|
{
|
|
|
|
log_err("ICU version mismatch: Header says %s, build environment says %s.\n", U_ICU_VERSION, ICU_VERSION);
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
2000-06-02 18:37:21 +00:00
|
|
|
/* test u_versionToString() error checking */
|
|
|
|
u_versionToString(NULL, icuVersion);
|
|
|
|
if(icuVersion[0]!=0) {
|
|
|
|
log_err("u_versionToString() failed to deal with a NULL version array and wrote a non-empty string.\n");
|
|
|
|
}
|
|
|
|
|
|
|
|
/* this just blows up if it does not check... */
|
|
|
|
u_versionToString("1.2.3", NULL);
|
1999-08-16 21:50:52 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
/* Tests for isControl(u_iscntrl()) and isPrintable(u_isprint()) */
|
|
|
|
void TestControlPrint()
|
|
|
|
{
|
|
|
|
const UChar sampleControl[] = {0x001b, 0x0097, 0x0082};
|
2000-03-22 01:57:16 +00:00
|
|
|
const UChar sampleNonControl[] = {0x61, 0x0031, 0x00e2};
|
1999-08-16 21:50:52 +00:00
|
|
|
const UChar samplePrintable[] = {0x0042, 0x005f, 0x2014};
|
2000-05-18 17:49:51 +00:00
|
|
|
const UChar sampleNonPrintable[] = {0x200c, 0x009f, 0x001b};
|
1999-08-16 21:50:52 +00:00
|
|
|
int i;
|
|
|
|
for (i = 0; i < 3; i++) {
|
|
|
|
log_verbose("Testing for iscontrol\n");
|
2000-05-18 17:49:51 +00:00
|
|
|
if (!u_iscntrl(sampleControl[i]))
|
1999-08-16 21:50:52 +00:00
|
|
|
{
|
2000-05-18 17:49:51 +00:00
|
|
|
log_err("Control char test error : %d should be control but is not\n", (int32_t)sampleControl[i]);
|
|
|
|
}
|
|
|
|
if (u_iscntrl(sampleNonControl[i]))
|
|
|
|
{
|
|
|
|
log_err("Control char test error : %d should not be control but is\n", (int32_t)sampleNonControl[i]);
|
1999-08-16 21:50:52 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
for (i = 0; i < 3; i++) {
|
|
|
|
log_verbose("testing for isprintable\n");
|
2000-05-18 17:49:51 +00:00
|
|
|
if (!u_isprint(samplePrintable[i]))
|
|
|
|
{
|
|
|
|
log_err("Printable char test error : %d should be printable but is not\n", (int32_t)samplePrintable[i]);
|
|
|
|
}
|
|
|
|
if (u_isprint(sampleNonPrintable[i]))
|
1999-08-16 21:50:52 +00:00
|
|
|
{
|
2000-05-18 17:49:51 +00:00
|
|
|
log_err("Printable char test error : %d should not be printable but is\n", (int32_t)sampleNonPrintable[i]);
|
1999-08-16 21:50:52 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
/* u_isIDStart(), u_isIDPart(), u_isIDIgnorable()*/
|
|
|
|
void TestIdentifier()
|
|
|
|
{
|
|
|
|
|
|
|
|
|
|
|
|
const UChar sampleUnicodeIDStart[] = {0x0250, 0x00e2, 0x0061};
|
|
|
|
const UChar sampleNonUnicodeIDStart[] = {0x2000, 0x000a, 0x2019};
|
|
|
|
const UChar sampleUnicodeIDPart[] = {0x005f, 0x0032, 0x0045};
|
|
|
|
const UChar sampleNonUnicodeIDPart[] = {0x007f, 0x00a3, 0x0020};
|
|
|
|
const UChar sampleIDIgnore[] = {0x0006, 0x0010, 0x206b};
|
|
|
|
const UChar sampleNonIDIgnore[] = {0x0075, 0x00a3, 0x0061};
|
|
|
|
|
|
|
|
int i;
|
|
|
|
for (i = 0; i < 3; i++) {
|
|
|
|
log_verbose("Testing sampleUnicodeID start \n");
|
|
|
|
/* T_test_logln_ustr((int32_t)i); */
|
|
|
|
if (!(u_isIDStart(sampleUnicodeIDStart[i])) ||
|
|
|
|
(u_isIDStart(sampleNonUnicodeIDStart[i])))
|
|
|
|
{
|
|
|
|
log_err("Unicode ID Start char test error : %d or %d\n", (int32_t)sampleUnicodeIDStart[i],
|
|
|
|
(int32_t)sampleNonUnicodeIDStart[i]);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
for (i = 2; i < 3; i++) { /* nos *** starts with 2 instead of 0, until clarified */
|
|
|
|
log_verbose("Testing sample unicode ID part \n");
|
|
|
|
/* T_test_logln_ustr((int32_t)i); */
|
|
|
|
if (!(u_isIDPart(sampleUnicodeIDPart[i])) ||
|
|
|
|
(u_isIDPart(sampleNonUnicodeIDPart[i])))
|
|
|
|
{
|
|
|
|
log_err("Unicode ID Part char test error : %d or %d", (int32_t)sampleUnicodeIDPart[i], (int32_t)sampleNonUnicodeIDPart[i]);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
for (i = 0; i < 3; i++) {
|
|
|
|
log_verbose("Testing sampleId ignore\n");
|
|
|
|
/*T_test_logln_ustr((int32_t)i); */
|
|
|
|
if (!(u_isIDIgnorable(sampleIDIgnore[i])) ||
|
|
|
|
(u_isIDIgnorable(sampleNonIDIgnore[i])))
|
|
|
|
{
|
|
|
|
log_verbose("ID ignorable char test error : %d or %d\n", (int32_t)sampleIDIgnore[i], (int32_t)sampleNonIDIgnore[i]);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2000-05-18 17:49:51 +00:00
|
|
|
/* tests for u_charType(), u_isTitle(), and u_toTitle(),u_charDirection and u_charScript()*/
|
1999-08-16 21:50:52 +00:00
|
|
|
void TestUnicodeData()
|
|
|
|
{
|
|
|
|
FILE* input = 0;
|
|
|
|
char buffer[1000];
|
|
|
|
char* bufferPtr = 0, *dirPtr = 0;
|
|
|
|
int32_t unicode;
|
2000-05-18 17:49:51 +00:00
|
|
|
int8_t type;
|
1999-08-16 21:50:52 +00:00
|
|
|
char newPath[256];
|
2000-01-15 00:03:30 +00:00
|
|
|
const char *expectVersion = U_UNICODE_VERSION; /* NOTE: this purposely breaks to force the tests to stay in sync with the unicodedata */
|
|
|
|
/* expectVersionArray must be filled from u_versionFromString(expectVersionArray, U_UNICODE_VERSION)
|
|
|
|
once this function is public. */
|
2000-05-22 22:24:51 +00:00
|
|
|
UVersionInfo expectVersionArray;
|
2000-01-12 19:50:27 +00:00
|
|
|
UVersionInfo versionArray;
|
1999-11-08 22:21:11 +00:00
|
|
|
char expectString[256];
|
1999-08-16 21:50:52 +00:00
|
|
|
|
1999-11-18 22:50:13 +00:00
|
|
|
strcpy(newPath, u_getDataDirectory());
|
1999-11-08 22:21:11 +00:00
|
|
|
strcat(newPath, "UnicodeData-");
|
|
|
|
strcat(newPath, expectVersion);
|
|
|
|
strcat(newPath, ".txt");
|
|
|
|
|
2000-05-22 22:24:51 +00:00
|
|
|
u_versionFromString(expectVersionArray, expectVersion);
|
1999-11-08 22:21:11 +00:00
|
|
|
strcpy(expectString, "Unicode Version ");
|
|
|
|
strcat(expectString, expectVersion);
|
2000-01-12 20:20:38 +00:00
|
|
|
u_getUnicodeVersion(versionArray);
|
1999-11-08 22:21:11 +00:00
|
|
|
|
2000-01-15 00:03:30 +00:00
|
|
|
if(memcmp(versionArray, expectVersionArray, U_MAX_VERSION_LENGTH) != 0)
|
1999-11-08 22:21:11 +00:00
|
|
|
{
|
2000-01-11 23:20:26 +00:00
|
|
|
log_err("Testing u_getUnicodeVersion() - expected %s got %d.%d.%d.%d\n", expectString,
|
2000-01-12 20:20:38 +00:00
|
|
|
versionArray[0], versionArray[1], versionArray[2], versionArray[3]);
|
1999-11-08 22:21:11 +00:00
|
|
|
}
|
1999-11-23 04:49:35 +00:00
|
|
|
|
|
|
|
#if defined(ICU_UNICODE_VERSION)
|
|
|
|
/* test only happens where we have configure.in with UNICODE_VERSION - sanity check. */
|
|
|
|
if(strcmp(expectVersion, ICU_UNICODE_VERSION))
|
|
|
|
{
|
|
|
|
log_err("Testing configure.in's UNICODE_VERSION - expected %s got %s\n", expectVersion, ICU_UNICODE_VERSION);
|
|
|
|
}
|
|
|
|
#endif
|
1999-08-16 21:50:52 +00:00
|
|
|
|
|
|
|
input = fopen(newPath, "r");
|
|
|
|
|
|
|
|
if (input == 0) {
|
1999-10-18 22:48:32 +00:00
|
|
|
log_err("Unicode C API test 'fopen' (%s) error\n", newPath);
|
1999-08-16 21:50:52 +00:00
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
for(;;) {
|
|
|
|
bufferPtr = fgets(buffer, 999, input);
|
|
|
|
if (bufferPtr == NULL) break;
|
|
|
|
if (bufferPtr[0] == '#' || bufferPtr[0] == '\n' || bufferPtr[0] == 0) continue;
|
|
|
|
sscanf(bufferPtr, "%X", &unicode);
|
|
|
|
if (!(0 <= unicode && unicode < 65536)) {
|
1999-10-18 22:48:32 +00:00
|
|
|
log_err("Unicode C API test precondition '(0 <= unicode && unicode < 65536)' failed\n");
|
1999-08-16 21:50:52 +00:00
|
|
|
return;
|
|
|
|
}
|
|
|
|
if (unicode == LAST_CHAR_CODE_IN_FILE)
|
|
|
|
break;
|
|
|
|
bufferPtr = strchr(bufferPtr, ';');
|
|
|
|
if (!(bufferPtr != NULL)) {
|
1999-10-18 22:48:32 +00:00
|
|
|
log_err("Unicode C API test condition '(bufferPtr != NULL)' failed\n");
|
1999-08-16 21:50:52 +00:00
|
|
|
return;
|
|
|
|
}
|
|
|
|
bufferPtr = strchr(bufferPtr + 1, ';'); /* go to start of third field */
|
|
|
|
if (!(bufferPtr != NULL)) {
|
1999-10-18 22:48:32 +00:00
|
|
|
log_err("Unicode C API test condition '(bufferPtr != NULL)' failed\n");
|
1999-08-16 21:50:52 +00:00
|
|
|
return;
|
|
|
|
}
|
|
|
|
dirPtr = bufferPtr;
|
|
|
|
dirPtr = strchr(dirPtr + 1, ';');
|
|
|
|
if (!(dirPtr != NULL)) {
|
1999-10-18 22:48:32 +00:00
|
|
|
log_err("Unicode C API test precondition '(dirPtr != NULL)' failed\n");
|
1999-08-16 21:50:52 +00:00
|
|
|
return;
|
|
|
|
}
|
|
|
|
dirPtr = strchr(dirPtr + 1, ';');
|
|
|
|
if (!(dirPtr != NULL)) {
|
1999-10-18 22:48:32 +00:00
|
|
|
log_err("Unicode C API test precondition '(dirPtr != NULL)' failed\n");
|
1999-08-16 21:50:52 +00:00
|
|
|
return;
|
|
|
|
}
|
|
|
|
bufferPtr++;
|
|
|
|
bufferPtr[2] = 0;
|
2000-05-18 17:49:51 +00:00
|
|
|
|
|
|
|
/* we override the general category of some control characters */
|
|
|
|
switch(unicode) {
|
|
|
|
case 9:
|
|
|
|
case 0xb:
|
|
|
|
case 0x1f:
|
|
|
|
type = U_SPACE_SEPARATOR;
|
|
|
|
break;
|
|
|
|
case 0xc:
|
|
|
|
type = U_LINE_SEPARATOR;
|
|
|
|
break;
|
|
|
|
case 0xa:
|
|
|
|
case 0xd:
|
|
|
|
case 0x1c:
|
|
|
|
case 0x1d:
|
|
|
|
case 0x1e:
|
|
|
|
case 0x85:
|
|
|
|
type = U_PARAGRAPH_SEPARATOR;
|
|
|
|
break;
|
|
|
|
default:
|
|
|
|
type = (int8_t)tagValues[MakeProp(bufferPtr)];
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
if (u_charType((UChar)unicode) != type)
|
1999-08-16 21:50:52 +00:00
|
|
|
{
|
|
|
|
log_err("Unicode character type failed at %d\n",unicode);
|
|
|
|
}
|
2000-05-18 17:49:51 +00:00
|
|
|
|
1999-08-16 21:50:52 +00:00
|
|
|
/* test title case */
|
|
|
|
if ((u_totitle((UChar)unicode) != u_toupper((UChar)unicode)) &&
|
|
|
|
!(u_istitle(u_totitle((UChar)unicode))))
|
|
|
|
{
|
|
|
|
log_err("Title case test failed at %d \n", unicode);
|
|
|
|
}
|
|
|
|
bufferPtr = strchr(dirPtr + 1, ';');
|
|
|
|
dirPtr++;
|
|
|
|
bufferPtr[0] = 0;
|
|
|
|
if (u_charDirection((UChar)unicode) != MakeDir(dirPtr))
|
|
|
|
{
|
|
|
|
log_err("Unicode character directionality failed at %d\n", unicode);
|
|
|
|
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
1999-10-07 00:07:53 +00:00
|
|
|
if (u_charScript((UChar)0x0041 != U_BASIC_LATIN)) {
|
1999-08-16 21:50:52 +00:00
|
|
|
log_err("Unicode character script property failed !\n");
|
|
|
|
}
|
|
|
|
if (input)
|
|
|
|
fclose(input);
|
|
|
|
|
|
|
|
|
|
|
|
}
|
|
|
|
/*internal functions ----*/
|
|
|
|
int32_t MakeProp(char* str)
|
|
|
|
{
|
|
|
|
int32_t result = 0;
|
|
|
|
char* matchPosition =0;
|
|
|
|
|
|
|
|
matchPosition = strstr(tagStrings, str);
|
|
|
|
if (matchPosition == 0)
|
|
|
|
{
|
|
|
|
log_err("unrecognized type letter ");
|
|
|
|
log_err(str);
|
|
|
|
}
|
|
|
|
else result = ((matchPosition - tagStrings) / 2);
|
|
|
|
return result;
|
|
|
|
}
|
|
|
|
|
|
|
|
int32_t MakeDir(char* str)
|
|
|
|
{
|
|
|
|
int32_t pos = 0;
|
|
|
|
for (pos = 0; pos < 19; pos++) {
|
|
|
|
if (strcmp(str, dirStrings[pos]) == 0) {
|
|
|
|
return pos;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return -1;
|
|
|
|
}
|
|
|
|
/*----------------*/
|
|
|
|
|
|
|
|
|
|
|
|
static char* raw[3][4] = {
|
|
|
|
|
|
|
|
/* First String */
|
|
|
|
{ "English_", "French_", "Croatian_", "English_"},
|
|
|
|
/* Second String */
|
|
|
|
{ "United States", "France", "Croatia", "Unites States"},
|
|
|
|
|
|
|
|
/* Concatenated string */
|
|
|
|
{ "English_United States", "French_France", "Croatian_Croatia", "English_United States"}
|
|
|
|
};
|
|
|
|
|
|
|
|
void setUpDataTable()
|
|
|
|
{
|
|
|
|
int32_t i,j;
|
|
|
|
dataTable = calloc(sizeof(UChar**),3);
|
|
|
|
|
|
|
|
for (i = 0; i < 3; i++) {
|
|
|
|
dataTable[i] = calloc(sizeof(UChar*),4);
|
|
|
|
for (j = 0; j < 4; j++){
|
|
|
|
dataTable[i][j] = (UChar*) malloc(sizeof(UChar)*(strlen(raw[i][j])+1));
|
|
|
|
u_uastrcpy(dataTable[i][j],raw[i][j]);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
}
|
|
|
|
/*Tests for u_strcat(),u_strcmp(), u_strlen(), u_strcpy(),u_strncat(),u_strncmp(),u_strncpy, u_uastrcpy(),u_austrcpy(); */
|
|
|
|
void TestStringFunctions()
|
|
|
|
{
|
|
|
|
|
|
|
|
int32_t i,j,k;
|
|
|
|
UChar* temp =0;
|
|
|
|
char test[20];
|
|
|
|
log_verbose("Testing u_strlen()\n");
|
|
|
|
if( u_strlen(dataTable[0][0])!= u_strlen(dataTable[0][3]) || u_strlen(dataTable[0][0]) == u_strlen(dataTable[0][2]))
|
|
|
|
log_err("There is an error in u_strlen()");
|
|
|
|
|
|
|
|
log_verbose("Testing u_strcpy() and u_strcmp)\n");
|
|
|
|
temp=(UChar*)malloc(sizeof(UChar*) * 1);
|
|
|
|
|
|
|
|
for(i=0;i<3;++i){
|
|
|
|
for(j=0;j<4;++j)
|
|
|
|
{
|
|
|
|
log_verbose("Testing %s \n", austrdup(dataTable[i][j]));
|
|
|
|
temp=(UChar*)realloc(temp, sizeof(UChar)*(u_strlen(dataTable[i][j]) + 1));
|
|
|
|
u_strcpy(temp,dataTable[i][j]);
|
|
|
|
|
|
|
|
if(u_strcmp(temp,dataTable[i][j])!=0)
|
|
|
|
log_err("something threw an error in u_strcpy() or u_strcmp()\n");
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
log_verbose("testing u_strcat()\n");
|
|
|
|
i=0;
|
|
|
|
for(j=0; j<2;++j)
|
|
|
|
{
|
|
|
|
temp=(UChar*)realloc(temp, sizeof(UChar)*(u_strlen(dataTable[i+2][j]) +1));
|
|
|
|
u_strcpy(temp,dataTable[i][j]);
|
|
|
|
u_strcat(temp,dataTable[i+1][j]);
|
|
|
|
if(u_strcmp(temp,dataTable[i+2][j])!=0)
|
|
|
|
log_err("something threw an error in u_strcat()\n");
|
|
|
|
|
|
|
|
}
|
|
|
|
log_verbose("Testing u_strncmp()\n");
|
|
|
|
for(i=0,j=0;j<4; ++j)
|
|
|
|
{
|
|
|
|
k=u_strlen(dataTable[i][j]);
|
|
|
|
if(u_strncmp(dataTable[i][j],dataTable[i+2][j],k)!=0)
|
|
|
|
log_err("Something threw an error in u_strncmp\n");
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
log_verbose("Testing u_strncat \n");
|
|
|
|
for(i=0,j=0;j<4; ++j)
|
|
|
|
{
|
|
|
|
k=u_strlen(dataTable[i][j]);
|
|
|
|
|
|
|
|
u_uastrcpy(temp,"");
|
|
|
|
|
|
|
|
if(u_strcmp(u_strncat(temp,dataTable[i+2][j],k),dataTable[i][j])!=0)
|
|
|
|
log_err("something threw an error in u_strncat or u_uastrcpy()\n");
|
|
|
|
|
|
|
|
}
|
|
|
|
|
|
|
|
log_verbose("Testing u_strncpy()\n");
|
|
|
|
for(i=0,j=0;j<4; ++j)
|
|
|
|
{
|
|
|
|
k=u_strlen(dataTable[i][j]);
|
|
|
|
u_uastrcpy(temp,"");
|
|
|
|
u_strncpy(temp,dataTable[i+2][j],k);
|
|
|
|
|
|
|
|
if(u_strcmp(temp,dataTable[i][j])!=0)
|
|
|
|
log_err("something threw an error in u_strncpy()\n");
|
|
|
|
}
|
|
|
|
|
|
|
|
log_verbose("Testing if u_strchr() works fine\n");
|
|
|
|
|
|
|
|
for(i=2,j=0;j<4;j++)
|
|
|
|
{
|
|
|
|
|
|
|
|
log_verbose("%s ", austrdup(u_strchr(dataTable[i][j],'_')));
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
log_verbose("Testing u_austrcpy()");
|
|
|
|
u_austrcpy(test,dataTable[0][0]);
|
|
|
|
if(strcmp(test,raw[0][0])!=0)
|
|
|
|
log_err("There is an error in u_austrcpy()");
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
}
|
|
|
|
|
1999-11-22 19:39:22 +00:00
|
|
|
/* test u_charName() -------------------------------------------------------- */
|
1999-08-16 21:50:52 +00:00
|
|
|
|
1999-11-22 19:39:22 +00:00
|
|
|
static struct { uint32_t code; const char *name; } names[]={
|
|
|
|
0x0061, "LATIN SMALL LETTER A",
|
|
|
|
0x0284, "LATIN SMALL LETTER DOTLESS J WITH STROKE AND HOOK",
|
|
|
|
0x3401, "CJK UNIFIED IDEOGRAPH-3401",
|
|
|
|
0x7fed, "CJK UNIFIED IDEOGRAPH-7FED",
|
|
|
|
0xac00, "HANGUL SYLLABLE GA",
|
|
|
|
0xd7a3, "HANGUL SYLLABLE HIH"
|
|
|
|
};
|
1999-08-16 21:50:52 +00:00
|
|
|
|
1999-11-22 19:39:22 +00:00
|
|
|
static void
|
|
|
|
TestCharNames() {
|
|
|
|
static char name[80];
|
|
|
|
UErrorCode errorCode=U_ZERO_ERROR;
|
|
|
|
UTextOffset length;
|
|
|
|
int i;
|
1999-08-16 21:50:52 +00:00
|
|
|
|
1999-11-22 19:39:22 +00:00
|
|
|
log_verbose("Testing u_charName()\n");
|
|
|
|
for(i=0; i<sizeof(names)/sizeof(names[0]); ++i) {
|
|
|
|
length=u_charName(names[i].code, U_UNICODE_CHAR_NAME, name, sizeof(name), &errorCode);
|
|
|
|
if(U_FAILURE(errorCode)) {
|
1999-12-08 23:31:17 +00:00
|
|
|
log_err("u_charName(0x%lx) error %s\n", names[i].code, u_errorName(errorCode));
|
1999-11-22 19:39:22 +00:00
|
|
|
return;
|
|
|
|
}
|
1999-12-28 23:57:50 +00:00
|
|
|
if(length<=0 || 0!=uprv_strcmp(name, names[i].name)) {
|
1999-11-22 19:39:22 +00:00
|
|
|
log_err("u_charName(0x%lx) gets %s instead of %s\n", names[i].code, name, names[i].name);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
2000-04-24 22:44:06 +00:00
|
|
|
|
|
|
|
/* test u_isMirrored() and u_charMirror() ----------------------------------- */
|
|
|
|
|
|
|
|
static void
|
|
|
|
TestMirroring() {
|
|
|
|
log_verbose("Testing u_isMirrored()\n");
|
|
|
|
if(!(u_isMirrored(0x28) && u_isMirrored(0xbb) && u_isMirrored(0x2045) && u_isMirrored(0x232a) &&
|
|
|
|
!u_isMirrored(0x27) && !u_isMirrored(0x61) && !u_isMirrored(0x284) && !u_isMirrored(0x3400)
|
|
|
|
)
|
|
|
|
) {
|
|
|
|
log_err("u_isMirrored() does not work correctly\n");
|
|
|
|
}
|
|
|
|
|
|
|
|
log_verbose("Testing u_charMirror()\n");
|
|
|
|
if(!(u_charMirror(0x3c)==0x3e && u_charMirror(0x5d)==0x5b && u_charMirror(0x208d)==0x208e && u_charMirror(0x3017)==0x3016 &&
|
|
|
|
u_charMirror(0x2e)==0x2e && u_charMirror(0x6f3)==0x6f3 && u_charMirror(0x301c)==0x301c && u_charMirror(0xa4ab)==0xa4ab
|
|
|
|
)
|
|
|
|
) {
|
|
|
|
log_err("u_charMirror() does not work correctly\n");
|
|
|
|
}
|
|
|
|
}
|
2000-06-12 19:49:49 +00:00
|
|
|
|
|
|
|
/* test u_isWhitespace() ---------------------------------------------------- */
|
|
|
|
|
|
|
|
static void
|
|
|
|
TestWhitespace() {
|
|
|
|
static const UChar32
|
|
|
|
whitespaces[]={
|
|
|
|
9, 0xa, 0xb, 0xc, 0xd, 0x1c, 0x1d, 0x1e, 0x1f, 0x20, 0x2028, 0x2029,
|
|
|
|
0x1680, 0x2000, 0x200b, 0x3000
|
|
|
|
},
|
|
|
|
nonWhitespaces[]={
|
|
|
|
0xa0, 0x202f, 0xfeff, 0x61, 0x200e, 0x4efa, 0x30014
|
|
|
|
};
|
|
|
|
|
|
|
|
int i;
|
|
|
|
|
|
|
|
log_verbose("Testing u_isWhitespace()\n");
|
|
|
|
for(i=0; i<sizeof(whitespaces)/sizeof(whitespaces[0]); ++i) {
|
|
|
|
if(!u_isWhitespace(whitespaces[i])) {
|
|
|
|
log_err("u_isWhitespace(0x%lx) does not return TRUE as expected\n", whitespaces[i]);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
for(i=0; i<sizeof(nonWhitespaces)/sizeof(nonWhitespaces[0]); ++i) {
|
|
|
|
if(u_isWhitespace(nonWhitespaces[i])) {
|
|
|
|
log_err("u_isWhitespace(0x%lx) does not return FALSE as expected\n", nonWhitespaces[i]);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|