2004-03-22 22:16:21 +00:00
/********************************************************************
* COPYRIGHT :
2013-03-21 05:48:52 +00:00
* Copyright ( c ) 2004 - 2013 , International Business Machines Corporation and
2004-03-22 22:16:21 +00:00
* others . All Rights Reserved .
* * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * */
/********************************************************************************
*
* File reapits . c
*
* * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * */
/*C API TEST FOR Regular Expressions */
/**
* This is an API test for ICU regular expressions in C . It doesn ' t test very many cases , and doesn ' t
* try to test the full functionality . It just calls each function and verifies that it
* works on a basic level .
*
* More complete testing of regular expression functionality is done with the C + + tests .
* */
# include "unicode/utypes.h"
# if !UCONFIG_NO_REGULAR_EXPRESSIONS
# include <stdlib.h>
# include <string.h>
# include "unicode/uloc.h"
# include "unicode/uregex.h"
# include "unicode/ustring.h"
2010-02-03 02:59:35 +00:00
# include "unicode/utext.h"
2004-03-22 22:16:21 +00:00
# include "cintltst.h"
# define TEST_ASSERT_SUCCESS(status) {if (U_FAILURE(status)) { \
2009-06-09 21:28:13 +00:00
log_data_err ( " Failure at file %s, line %d, error = %s (Are you missing data?) \n " , __FILE__ , __LINE__ , u_errorName ( status ) ) ; } }
2004-03-22 22:16:21 +00:00
# define TEST_ASSERT(expr) {if ((expr)==FALSE) { \
2009-06-09 21:28:13 +00:00
log_data_err ( " Test Failure at file %s, line %d (Are you missing data?) \n " , __FILE__ , __LINE__ ) ; } }
2004-03-22 22:16:21 +00:00
2007-12-11 21:30:10 +00:00
/*
* TEST_SETUP and TEST_TEARDOWN
* macros to handle the boilerplate around setting up regex test cases .
* parameteres to setup :
* pattern : The regex pattern , a ( char * ) null terminated C string .
* testString : The string data , also a ( char * ) C string .
* flags : Regex flags to set when compiling the pattern
*
* Put arbitrary test code between SETUP and TEARDOWN .
* ' re " is the compiled, ready-to-go regular expression.
*/
# define TEST_SETUP(pattern, testString, flags) { \
UChar * srcString = NULL ; \
status = U_ZERO_ERROR ; \
re = uregex_openC ( pattern , flags , NULL , & status ) ; \
TEST_ASSERT_SUCCESS ( status ) ; \
srcString = ( UChar * ) malloc ( ( strlen ( testString ) + 2 ) * sizeof ( UChar ) ) ; \
u_uastrncpy ( srcString , testString , strlen ( testString ) + 1 ) ; \
uregex_setText ( re , srcString , - 1 , & status ) ; \
TEST_ASSERT_SUCCESS ( status ) ; \
if ( U_SUCCESS ( status ) ) {
# define TEST_TEARDOWN \
} \
TEST_ASSERT_SUCCESS ( status ) ; \
uregex_close ( re ) ; \
free ( srcString ) ; \
}
2010-03-03 01:47:00 +00:00
/**
* @ param expected utf - 8 array of bytes to be expected
*/
2006-12-19 06:06:30 +00:00
static void test_assert_string ( const char * expected , const UChar * actual , UBool nulTerm , const char * file , int line ) {
char buf_inside_macro [ 120 ] ;
int32_t len = ( int32_t ) strlen ( expected ) ;
UBool success ;
if ( nulTerm ) {
u_austrncpy ( buf_inside_macro , ( actual ) , len + 1 ) ;
buf_inside_macro [ len + 2 ] = 0 ;
success = ( strcmp ( ( expected ) , buf_inside_macro ) = = 0 ) ;
} else {
u_austrncpy ( buf_inside_macro , ( actual ) , len ) ;
buf_inside_macro [ len + 1 ] = 0 ;
success = ( strncmp ( ( expected ) , buf_inside_macro , len ) = = 0 ) ;
}
if ( success = = FALSE ) {
log_err ( " Failure at file %s, line %d, expected \" %s \" , got \" %s \" \n " ,
file , line , ( expected ) , buf_inside_macro ) ;
}
2004-03-24 01:57:51 +00:00
}
2006-12-19 06:06:30 +00:00
# define TEST_ASSERT_STRING(expected, actual, nulTerm) test_assert_string(expected, actual, nulTerm, __FILE__, __LINE__)
2004-03-24 01:57:51 +00:00
2012-01-31 01:14:41 +00:00
static UBool equals_utf8_utext ( const char * utf8 , UText * utext ) {
int32_t u8i = 0 ;
UChar32 u8c = 0 ;
UChar32 utc = 0 ;
UBool stringsEqual = TRUE ;
utext_setNativeIndex ( utext , 0 ) ;
for ( ; ; ) {
U8_NEXT_UNSAFE ( utf8 , u8i , u8c ) ;
utc = utext_next32 ( utext ) ;
if ( u8c = = 0 & & utc = = U_SENTINEL ) {
break ;
}
if ( u8c ! = utc | | u8c = = 0 ) {
stringsEqual = FALSE ;
break ;
}
}
return stringsEqual ;
}
2010-02-03 02:59:35 +00:00
static void test_assert_utext ( const char * expected , UText * actual , const char * file , int line ) {
utext_setNativeIndex ( actual , 0 ) ;
2012-01-31 01:14:41 +00:00
if ( ! equals_utf8_utext ( expected , actual ) ) {
2010-02-03 02:59:35 +00:00
UChar32 c ;
log_err ( " Failure at file %s, line %d, expected \" %s \" , got \" " , file , line , expected ) ;
c = utext_next32From ( actual , 0 ) ;
while ( c ! = U_SENTINEL ) {
if ( 0x20 < c & & c < 0x7e ) {
log_err ( " %c " , c ) ;
} else {
log_err ( " %#x " , c ) ;
}
c = UTEXT_NEXT32 ( actual ) ;
}
log_err ( " \" \n " ) ;
}
}
2012-01-31 01:14:41 +00:00
/*
* TEST_ASSERT_UTEXT ( const char * expected , const UText * actual )
* Note : Expected is a UTF - 8 encoded string , _not_ the system code page .
*/
2010-02-03 02:59:35 +00:00
# define TEST_ASSERT_UTEXT(expected, actual) test_assert_utext(expected, actual, __FILE__, __LINE__)
2004-03-24 01:57:51 +00:00
2012-01-31 01:14:41 +00:00
static UBool testUTextEqual ( UText * uta , UText * utb ) {
UChar32 ca = 0 ;
UChar32 cb = 0 ;
utext_setNativeIndex ( uta , 0 ) ;
utext_setNativeIndex ( utb , 0 ) ;
do {
ca = utext_next32 ( uta ) ;
cb = utext_next32 ( utb ) ;
if ( ca ! = cb ) {
break ;
}
} while ( ca ! = U_SENTINEL ) ;
return ca = = cb ;
}
2004-03-24 01:57:51 +00:00
2004-03-22 22:16:21 +00:00
static void TestRegexCAPI ( void ) ;
2005-08-31 00:52:22 +00:00
static void TestBug4315 ( void ) ;
2010-02-03 02:59:35 +00:00
static void TestUTextAPI ( void ) ;
2011-01-27 01:12:12 +00:00
static void TestRefreshInput ( void ) ;
2011-03-31 18:33:28 +00:00
static void TestBug8421 ( void ) ;
2004-03-22 22:16:21 +00:00
void addURegexTest ( TestNode * * root ) ;
void addURegexTest ( TestNode * * root )
{
addTest ( root , & TestRegexCAPI , " regex/TestRegexCAPI " ) ;
2005-08-31 00:52:22 +00:00
addTest ( root , & TestBug4315 , " regex/TestBug4315 " ) ;
2010-02-03 02:59:35 +00:00
addTest ( root , & TestUTextAPI , " regex/TestUTextAPI " ) ;
2011-01-27 01:12:12 +00:00
addTest ( root , & TestRefreshInput , " regex/TestRefreshInput " ) ;
2011-03-31 18:33:28 +00:00
addTest ( root , & TestBug8421 , " regex/TestBug8421 " ) ;
2004-03-22 22:16:21 +00:00
}
2008-02-20 03:08:44 +00:00
/*
* Call back function and context struct used for testing
* regular expression user callbacks . This test is mostly the same as
* the corresponding C + + test in intltest .
*/
typedef struct callBackContext {
int32_t maxCalls ;
int32_t numCalls ;
int32_t lastSteps ;
} callBackContext ;
static UBool U_EXPORT2 U_CALLCONV
TestCallbackFn ( const void * context , int32_t steps ) {
callBackContext * info = ( callBackContext * ) context ;
if ( info - > lastSteps + 1 ! = steps ) {
log_err ( " incorrect steps in callback. Expected %d, got %d \n " , info - > lastSteps + 1 , steps ) ;
}
info - > lastSteps = steps ;
info - > numCalls + + ;
return ( info - > numCalls < info - > maxCalls ) ;
}
2004-03-22 22:16:21 +00:00
2008-02-20 03:08:44 +00:00
/*
* Regular Expression C API Tests
*/
2004-06-12 06:16:57 +00:00
static void TestRegexCAPI ( void ) {
2004-03-22 22:16:21 +00:00
UErrorCode status = U_ZERO_ERROR ;
URegularExpression * re ;
UChar pat [ 200 ] ;
2004-04-09 17:06:42 +00:00
UChar * minus1 ;
memset ( & minus1 , - 1 , sizeof ( minus1 ) ) ;
2004-03-22 22:16:21 +00:00
/* Mimimalist open/close */
u_uastrncpy ( pat , " abc* " , sizeof ( pat ) / 2 ) ;
re = uregex_open ( pat , - 1 , 0 , 0 , & status ) ;
2008-02-16 22:58:32 +00:00
if ( U_FAILURE ( status ) ) {
2010-03-03 01:47:00 +00:00
log_data_err ( " Failed to open regular expression, %s:%d, error is \" %s \" (Are you missing data?) \n " , __FILE__ , __LINE__ , u_errorName ( status ) ) ;
2008-02-16 22:58:32 +00:00
return ;
}
2004-03-22 22:16:21 +00:00
uregex_close ( re ) ;
/* Open with all flag values set */
status = U_ZERO_ERROR ;
re = uregex_open ( pat , - 1 ,
2012-02-15 01:36:12 +00:00
UREGEX_CASE_INSENSITIVE | UREGEX_COMMENTS | UREGEX_DOTALL | UREGEX_MULTILINE | UREGEX_UWORD | UREGEX_LITERAL ,
2004-03-22 22:16:21 +00:00
0 , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
uregex_close ( re ) ;
/* Open with an invalid flag */
status = U_ZERO_ERROR ;
re = uregex_open ( pat , - 1 , 0x40000000 , 0 , & status ) ;
TEST_ASSERT ( status = = U_REGEX_INVALID_FLAG ) ;
uregex_close ( re ) ;
2010-02-27 03:40:56 +00:00
/* Open with an unimplemented flag */
status = U_ZERO_ERROR ;
2012-02-15 01:30:55 +00:00
re = uregex_open ( pat , - 1 , UREGEX_CANON_EQ , 0 , & status ) ;
2010-02-27 03:40:56 +00:00
TEST_ASSERT ( status = = U_REGEX_UNIMPLEMENTED ) ;
uregex_close ( re ) ;
2006-02-07 23:20:38 +00:00
/* openC with an invalid parameter */
status = U_ZERO_ERROR ;
re = uregex_openC ( NULL ,
UREGEX_CASE_INSENSITIVE | UREGEX_COMMENTS | UREGEX_DOTALL | UREGEX_MULTILINE | UREGEX_UWORD , 0 , & status ) ;
TEST_ASSERT ( status = = U_ILLEGAL_ARGUMENT_ERROR & & re = = NULL ) ;
/* openC with an invalid parameter */
status = U_USELESS_COLLATOR_ERROR ;
re = uregex_openC ( NULL ,
UREGEX_CASE_INSENSITIVE | UREGEX_COMMENTS | UREGEX_DOTALL | UREGEX_MULTILINE | UREGEX_UWORD , 0 , & status ) ;
TEST_ASSERT ( status = = U_USELESS_COLLATOR_ERROR & & re = = NULL ) ;
2004-03-22 22:16:21 +00:00
/* openC open from a C string */
{
const UChar * p ;
int32_t len ;
status = U_ZERO_ERROR ;
re = uregex_openC ( " abc* " , 0 , 0 , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
p = uregex_pattern ( re , & len , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
2004-12-16 02:54:23 +00:00
/* The TEST_ASSERT_SUCCESS above should change too... */
if ( U_SUCCESS ( status ) ) {
u_uastrncpy ( pat , " abc* " , sizeof ( pat ) / 2 ) ;
TEST_ASSERT ( u_strcmp ( pat , p ) = = 0 ) ;
TEST_ASSERT ( len = = ( int32_t ) strlen ( " abc* " ) ) ;
}
2004-03-22 22:16:21 +00:00
uregex_close ( re ) ;
2004-03-23 05:20:48 +00:00
/* TODO: Open with ParseError parameter */
2004-03-22 22:16:21 +00:00
}
/*
* clone
*/
{
URegularExpression * clone1 ;
URegularExpression * clone2 ;
URegularExpression * clone3 ;
UChar testString1 [ 30 ] ;
UChar testString2 [ 30 ] ;
UBool result ;
status = U_ZERO_ERROR ;
re = uregex_openC ( " abc* " , 0 , 0 , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
clone1 = uregex_clone ( re , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
TEST_ASSERT ( clone1 ! = NULL ) ;
status = U_ZERO_ERROR ;
clone2 = uregex_clone ( re , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
TEST_ASSERT ( clone2 ! = NULL ) ;
uregex_close ( re ) ;
status = U_ZERO_ERROR ;
clone3 = uregex_clone ( clone2 , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
TEST_ASSERT ( clone3 ! = NULL ) ;
u_uastrncpy ( testString1 , " abcccd " , sizeof ( pat ) / 2 ) ;
u_uastrncpy ( testString2 , " xxxabcccd " , sizeof ( pat ) / 2 ) ;
status = U_ZERO_ERROR ;
uregex_setText ( clone1 , testString1 , - 1 , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
result = uregex_lookingAt ( clone1 , 0 , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
TEST_ASSERT ( result = = TRUE ) ;
status = U_ZERO_ERROR ;
uregex_setText ( clone2 , testString2 , - 1 , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
result = uregex_lookingAt ( clone2 , 0 , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
TEST_ASSERT ( result = = FALSE ) ;
result = uregex_find ( clone2 , 0 , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
TEST_ASSERT ( result = = TRUE ) ;
uregex_close ( clone1 ) ;
uregex_close ( clone2 ) ;
uregex_close ( clone3 ) ;
}
/*
* pattern ( )
*/
{
const UChar * resultPat ;
int32_t resultLen ;
u_uastrncpy ( pat , " hello " , sizeof ( pat ) / 2 ) ;
status = U_ZERO_ERROR ;
re = uregex_open ( pat , - 1 , 0 , NULL , & status ) ;
resultPat = uregex_pattern ( re , & resultLen , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
2004-12-16 02:54:23 +00:00
/* The TEST_ASSERT_SUCCESS above should change too... */
if ( U_SUCCESS ( status ) ) {
TEST_ASSERT ( resultLen = = - 1 ) ;
TEST_ASSERT ( u_strcmp ( resultPat , pat ) = = 0 ) ;
}
2004-03-22 22:16:21 +00:00
uregex_close ( re ) ;
status = U_ZERO_ERROR ;
re = uregex_open ( pat , 3 , 0 , NULL , & status ) ;
resultPat = uregex_pattern ( re , & resultLen , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
2004-12-16 02:54:23 +00:00
TEST_ASSERT_SUCCESS ( status ) ;
/* The TEST_ASSERT_SUCCESS above should change too... */
if ( U_SUCCESS ( status ) ) {
TEST_ASSERT ( resultLen = = 3 ) ;
TEST_ASSERT ( u_strncmp ( resultPat , pat , 3 ) = = 0 ) ;
TEST_ASSERT ( u_strlen ( resultPat ) = = 3 ) ;
}
2004-03-22 22:16:21 +00:00
uregex_close ( re ) ;
2004-03-23 05:20:48 +00:00
}
/*
* flags ( )
*/
{
int32_t t ;
status = U_ZERO_ERROR ;
re = uregex_open ( pat , - 1 , 0 , NULL , & status ) ;
t = uregex_flags ( re , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
TEST_ASSERT ( t = = 0 ) ;
uregex_close ( re ) ;
status = U_ZERO_ERROR ;
re = uregex_open ( pat , - 1 , 0 , NULL , & status ) ;
t = uregex_flags ( re , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
TEST_ASSERT ( t = = 0 ) ;
uregex_close ( re ) ;
status = U_ZERO_ERROR ;
re = uregex_open ( pat , - 1 , UREGEX_CASE_INSENSITIVE | UREGEX_DOTALL , NULL , & status ) ;
t = uregex_flags ( re , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
TEST_ASSERT ( t = = ( UREGEX_CASE_INSENSITIVE | UREGEX_DOTALL ) ) ;
uregex_close ( re ) ;
}
/*
* setText ( ) and lookingAt ( )
*/
{
UChar text1 [ 50 ] ;
UChar text2 [ 50 ] ;
UBool result ;
2004-03-26 01:23:01 +00:00
2004-03-23 05:20:48 +00:00
u_uastrncpy ( text1 , " abcccd " , sizeof ( text1 ) / 2 ) ;
u_uastrncpy ( text2 , " abcccxd " , sizeof ( text2 ) / 2 ) ;
status = U_ZERO_ERROR ;
u_uastrncpy ( pat , " abc*d " , sizeof ( pat ) / 2 ) ;
re = uregex_open ( pat , - 1 , 0 , NULL , & status ) ;
2004-03-26 01:23:01 +00:00
TEST_ASSERT_SUCCESS ( status ) ;
/* Operation before doing a setText should fail... */
status = U_ZERO_ERROR ;
uregex_lookingAt ( re , 0 , & status ) ;
TEST_ASSERT ( status = = U_REGEX_INVALID_STATE ) ;
2004-03-23 05:20:48 +00:00
2004-03-26 01:23:01 +00:00
status = U_ZERO_ERROR ;
2004-03-23 05:20:48 +00:00
uregex_setText ( re , text1 , - 1 , & status ) ;
result = uregex_lookingAt ( re , 0 , & status ) ;
TEST_ASSERT ( result = = TRUE ) ;
TEST_ASSERT_SUCCESS ( status ) ;
status = U_ZERO_ERROR ;
uregex_setText ( re , text2 , - 1 , & status ) ;
result = uregex_lookingAt ( re , 0 , & status ) ;
TEST_ASSERT ( result = = FALSE ) ;
TEST_ASSERT_SUCCESS ( status ) ;
status = U_ZERO_ERROR ;
uregex_setText ( re , text1 , - 1 , & status ) ;
result = uregex_lookingAt ( re , 0 , & status ) ;
TEST_ASSERT ( result = = TRUE ) ;
TEST_ASSERT_SUCCESS ( status ) ;
status = U_ZERO_ERROR ;
uregex_setText ( re , text1 , 5 , & status ) ;
result = uregex_lookingAt ( re , 0 , & status ) ;
TEST_ASSERT ( result = = FALSE ) ;
TEST_ASSERT_SUCCESS ( status ) ;
status = U_ZERO_ERROR ;
uregex_setText ( re , text1 , 6 , & status ) ;
result = uregex_lookingAt ( re , 0 , & status ) ;
TEST_ASSERT ( result = = TRUE ) ;
TEST_ASSERT_SUCCESS ( status ) ;
uregex_close ( re ) ;
}
/*
* getText ( )
*/
{
UChar text1 [ 50 ] ;
UChar text2 [ 50 ] ;
const UChar * result ;
int32_t textLength ;
u_uastrncpy ( text1 , " abcccd " , sizeof ( text1 ) / 2 ) ;
u_uastrncpy ( text2 , " abcccxd " , sizeof ( text2 ) / 2 ) ;
status = U_ZERO_ERROR ;
u_uastrncpy ( pat , " abc*d " , sizeof ( pat ) / 2 ) ;
re = uregex_open ( pat , - 1 , 0 , NULL , & status ) ;
uregex_setText ( re , text1 , - 1 , & status ) ;
result = uregex_getText ( re , & textLength , & status ) ;
TEST_ASSERT ( result = = text1 ) ;
TEST_ASSERT ( textLength = = - 1 ) ;
TEST_ASSERT_SUCCESS ( status ) ;
status = U_ZERO_ERROR ;
uregex_setText ( re , text2 , 7 , & status ) ;
result = uregex_getText ( re , & textLength , & status ) ;
TEST_ASSERT ( result = = text2 ) ;
TEST_ASSERT ( textLength = = 7 ) ;
TEST_ASSERT_SUCCESS ( status ) ;
status = U_ZERO_ERROR ;
uregex_setText ( re , text2 , 4 , & status ) ;
result = uregex_getText ( re , & textLength , & status ) ;
TEST_ASSERT ( result = = text2 ) ;
TEST_ASSERT ( textLength = = 4 ) ;
TEST_ASSERT_SUCCESS ( status ) ;
uregex_close ( re ) ;
}
/*
* matches ( )
*/
{
2004-09-15 01:28:15 +00:00
UChar text1 [ 50 ] ;
UBool result ;
int len ;
UChar nullString [ ] = { 0 , 0 , 0 } ;
2004-03-23 05:20:48 +00:00
u_uastrncpy ( text1 , " abcccde " , sizeof ( text1 ) / 2 ) ;
status = U_ZERO_ERROR ;
u_uastrncpy ( pat , " abc*d " , sizeof ( pat ) / 2 ) ;
re = uregex_open ( pat , - 1 , 0 , NULL , & status ) ;
uregex_setText ( re , text1 , - 1 , & status ) ;
result = uregex_matches ( re , 0 , & status ) ;
TEST_ASSERT ( result = = FALSE ) ;
TEST_ASSERT_SUCCESS ( status ) ;
status = U_ZERO_ERROR ;
uregex_setText ( re , text1 , 6 , & status ) ;
result = uregex_matches ( re , 0 , & status ) ;
TEST_ASSERT ( result = = TRUE ) ;
TEST_ASSERT_SUCCESS ( status ) ;
status = U_ZERO_ERROR ;
uregex_setText ( re , text1 , 6 , & status ) ;
result = uregex_matches ( re , 1 , & status ) ;
TEST_ASSERT ( result = = FALSE ) ;
TEST_ASSERT_SUCCESS ( status ) ;
uregex_close ( re ) ;
2004-03-22 22:16:21 +00:00
2004-09-15 01:28:15 +00:00
status = U_ZERO_ERROR ;
re = uregex_openC ( " .? " , 0 , NULL , & status ) ;
uregex_setText ( re , text1 , - 1 , & status ) ;
len = u_strlen ( text1 ) ;
result = uregex_matches ( re , len , & status ) ;
TEST_ASSERT ( result = = TRUE ) ;
TEST_ASSERT_SUCCESS ( status ) ;
status = U_ZERO_ERROR ;
uregex_setText ( re , nullString , - 1 , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
result = uregex_matches ( re , 0 , & status ) ;
TEST_ASSERT ( result = = TRUE ) ;
TEST_ASSERT_SUCCESS ( status ) ;
uregex_close ( re ) ;
2004-03-23 05:20:48 +00:00
}
/*
* lookingAt ( ) Used in setText test .
*/
/*
* find ( ) , findNext , start , end , reset
*/
{
UChar text1 [ 50 ] ;
UBool result ;
u_uastrncpy ( text1 , " 012rx5rx890rxrx... " , sizeof ( text1 ) / 2 ) ;
status = U_ZERO_ERROR ;
re = uregex_openC ( " rx " , 0 , NULL , & status ) ;
uregex_setText ( re , text1 , - 1 , & status ) ;
result = uregex_find ( re , 0 , & status ) ;
TEST_ASSERT ( result = = TRUE ) ;
TEST_ASSERT ( uregex_start ( re , 0 , & status ) = = 3 ) ;
TEST_ASSERT ( uregex_end ( re , 0 , & status ) = = 5 ) ;
TEST_ASSERT_SUCCESS ( status ) ;
result = uregex_find ( re , 9 , & status ) ;
TEST_ASSERT ( result = = TRUE ) ;
TEST_ASSERT ( uregex_start ( re , 0 , & status ) = = 11 ) ;
TEST_ASSERT ( uregex_end ( re , 0 , & status ) = = 13 ) ;
TEST_ASSERT_SUCCESS ( status ) ;
2004-03-22 22:16:21 +00:00
2004-03-23 05:20:48 +00:00
result = uregex_find ( re , 14 , & status ) ;
TEST_ASSERT ( result = = FALSE ) ;
TEST_ASSERT_SUCCESS ( status ) ;
status = U_ZERO_ERROR ;
uregex_reset ( re , 0 , & status ) ;
result = uregex_findNext ( re , & status ) ;
TEST_ASSERT ( result = = TRUE ) ;
TEST_ASSERT ( uregex_start ( re , 0 , & status ) = = 3 ) ;
TEST_ASSERT ( uregex_end ( re , 0 , & status ) = = 5 ) ;
TEST_ASSERT_SUCCESS ( status ) ;
result = uregex_findNext ( re , & status ) ;
TEST_ASSERT ( result = = TRUE ) ;
TEST_ASSERT ( uregex_start ( re , 0 , & status ) = = 6 ) ;
TEST_ASSERT ( uregex_end ( re , 0 , & status ) = = 8 ) ;
TEST_ASSERT_SUCCESS ( status ) ;
status = U_ZERO_ERROR ;
uregex_reset ( re , 12 , & status ) ;
result = uregex_findNext ( re , & status ) ;
TEST_ASSERT ( result = = TRUE ) ;
TEST_ASSERT ( uregex_start ( re , 0 , & status ) = = 13 ) ;
TEST_ASSERT ( uregex_end ( re , 0 , & status ) = = 15 ) ;
TEST_ASSERT_SUCCESS ( status ) ;
result = uregex_findNext ( re , & status ) ;
TEST_ASSERT ( result = = FALSE ) ;
TEST_ASSERT_SUCCESS ( status ) ;
uregex_close ( re ) ;
2004-03-22 22:16:21 +00:00
}
2004-03-23 05:20:48 +00:00
/*
* groupCount
*/
{
int32_t result ;
status = U_ZERO_ERROR ;
re = uregex_openC ( " abc " , 0 , NULL , & status ) ;
result = uregex_groupCount ( re , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
TEST_ASSERT ( result = = 0 ) ;
uregex_close ( re ) ;
status = U_ZERO_ERROR ;
re = uregex_openC ( " abc(def)(ghi(j)) " , 0 , NULL , & status ) ;
result = uregex_groupCount ( re , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
TEST_ASSERT ( result = = 3 ) ;
uregex_close ( re ) ;
}
2004-03-24 01:57:51 +00:00
/*
* group ( )
*/
{
UChar text1 [ 80 ] ;
UChar buf [ 80 ] ;
UBool result ;
int32_t resultSz ;
u_uastrncpy ( text1 , " noise abc interior def, and this is off the end " , sizeof ( text1 ) / 2 ) ;
status = U_ZERO_ERROR ;
re = uregex_openC ( " abc(.*?)def " , 0 , NULL , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
uregex_setText ( re , text1 , - 1 , & status ) ;
result = uregex_find ( re , 0 , & status ) ;
TEST_ASSERT ( result = = TRUE ) ;
/* Capture Group 0, the full match. Should succeed. */
status = U_ZERO_ERROR ;
resultSz = uregex_group ( re , 0 , buf , sizeof ( buf ) / 2 , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
TEST_ASSERT_STRING ( " abc interior def " , buf , TRUE ) ;
TEST_ASSERT ( resultSz = = ( int32_t ) strlen ( " abc interior def " ) ) ;
/* Capture group #1. Should succeed. */
status = U_ZERO_ERROR ;
resultSz = uregex_group ( re , 1 , buf , sizeof ( buf ) / 2 , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
TEST_ASSERT_STRING ( " interior " , buf , TRUE ) ;
TEST_ASSERT ( resultSz = = ( int32_t ) strlen ( " interior " ) ) ;
/* Capture group out of range. Error. */
status = U_ZERO_ERROR ;
uregex_group ( re , 2 , buf , sizeof ( buf ) / 2 , & status ) ;
TEST_ASSERT ( status = = U_INDEX_OUTOFBOUNDS_ERROR ) ;
/* NULL buffer, pure pre-flight */
status = U_ZERO_ERROR ;
resultSz = uregex_group ( re , 0 , NULL , 0 , & status ) ;
TEST_ASSERT ( status = = U_BUFFER_OVERFLOW_ERROR ) ;
TEST_ASSERT ( resultSz = = ( int32_t ) strlen ( " abc interior def " ) ) ;
/* Too small buffer, truncated string */
status = U_ZERO_ERROR ;
memset ( buf , - 1 , sizeof ( buf ) ) ;
resultSz = uregex_group ( re , 0 , buf , 5 , & status ) ;
TEST_ASSERT ( status = = U_BUFFER_OVERFLOW_ERROR ) ;
TEST_ASSERT_STRING ( " abc i " , buf , FALSE ) ;
TEST_ASSERT ( buf [ 5 ] = = ( UChar ) 0xffff ) ;
TEST_ASSERT ( resultSz = = ( int32_t ) strlen ( " abc interior def " ) ) ;
/* Output string just fits buffer, no NUL term. */
status = U_ZERO_ERROR ;
resultSz = uregex_group ( re , 0 , buf , ( int32_t ) strlen ( " abc interior def " ) , & status ) ;
TEST_ASSERT ( status = = U_STRING_NOT_TERMINATED_WARNING ) ;
TEST_ASSERT_STRING ( " abc interior def " , buf , FALSE ) ;
TEST_ASSERT ( resultSz = = ( int32_t ) strlen ( " abc interior def " ) ) ;
TEST_ASSERT ( buf [ strlen ( " abc interior def " ) ] = = ( UChar ) 0xffff ) ;
uregex_close ( re ) ;
}
2007-12-11 21:30:10 +00:00
/*
* Regions
*/
/* SetRegion(), getRegion() do something */
TEST_SETUP ( " .* " , " 0123456789ABCDEF " , 0 )
UChar resultString [ 40 ] ;
TEST_ASSERT ( uregex_regionStart ( re , & status ) = = 0 ) ;
TEST_ASSERT ( uregex_regionEnd ( re , & status ) = = 16 ) ;
uregex_setRegion ( re , 3 , 6 , & status ) ;
TEST_ASSERT ( uregex_regionStart ( re , & status ) = = 3 ) ;
TEST_ASSERT ( uregex_regionEnd ( re , & status ) = = 6 ) ;
TEST_ASSERT ( uregex_findNext ( re , & status ) ) ;
TEST_ASSERT ( uregex_group ( re , 0 , resultString , sizeof ( resultString ) / 2 , & status ) = = 3 )
TEST_ASSERT_STRING ( " 345 " , resultString , TRUE ) ;
TEST_TEARDOWN ;
/* find(start=-1) uses regions */
TEST_SETUP ( " .* " , " 0123456789ABCDEF " , 0 ) ;
uregex_setRegion ( re , 4 , 6 , & status ) ;
TEST_ASSERT ( uregex_find ( re , - 1 , & status ) = = TRUE ) ;
TEST_ASSERT ( uregex_start ( re , 0 , & status ) = = 4 ) ;
TEST_ASSERT ( uregex_end ( re , 0 , & status ) = = 6 ) ;
TEST_TEARDOWN ;
/* find (start >=0) does not use regions */
TEST_SETUP ( " .* " , " 0123456789ABCDEF " , 0 ) ;
uregex_setRegion ( re , 4 , 6 , & status ) ;
TEST_ASSERT ( uregex_find ( re , 0 , & status ) = = TRUE ) ;
TEST_ASSERT ( uregex_start ( re , 0 , & status ) = = 0 ) ;
TEST_ASSERT ( uregex_end ( re , 0 , & status ) = = 16 ) ;
TEST_TEARDOWN ;
/* findNext() obeys regions */
TEST_SETUP ( " . " , " 0123456789ABCDEF " , 0 ) ;
uregex_setRegion ( re , 4 , 6 , & status ) ;
TEST_ASSERT ( uregex_findNext ( re , & status ) = = TRUE ) ;
TEST_ASSERT ( uregex_start ( re , 0 , & status ) = = 4 ) ;
TEST_ASSERT ( uregex_findNext ( re , & status ) = = TRUE ) ;
TEST_ASSERT ( uregex_start ( re , 0 , & status ) = = 5 ) ;
TEST_ASSERT ( uregex_findNext ( re , & status ) = = FALSE ) ;
TEST_TEARDOWN ;
/* matches(start=-1) uses regions */
/* Also, verify that non-greedy *? succeeds in finding the full match. */
TEST_SETUP ( " .*? " , " 0123456789ABCDEF " , 0 ) ;
uregex_setRegion ( re , 4 , 6 , & status ) ;
TEST_ASSERT ( uregex_matches ( re , - 1 , & status ) = = TRUE ) ;
TEST_ASSERT ( uregex_start ( re , 0 , & status ) = = 4 ) ;
TEST_ASSERT ( uregex_end ( re , 0 , & status ) = = 6 ) ;
TEST_TEARDOWN ;
/* matches (start >=0) does not use regions */
TEST_SETUP ( " .*? " , " 0123456789ABCDEF " , 0 ) ;
uregex_setRegion ( re , 4 , 6 , & status ) ;
TEST_ASSERT ( uregex_matches ( re , 0 , & status ) = = TRUE ) ;
TEST_ASSERT ( uregex_start ( re , 0 , & status ) = = 0 ) ;
TEST_ASSERT ( uregex_end ( re , 0 , & status ) = = 16 ) ;
TEST_TEARDOWN ;
/* lookingAt(start=-1) uses regions */
/* Also, verify that non-greedy *? finds the first (shortest) match. */
TEST_SETUP ( " .*? " , " 0123456789ABCDEF " , 0 ) ;
uregex_setRegion ( re , 4 , 6 , & status ) ;
TEST_ASSERT ( uregex_lookingAt ( re , - 1 , & status ) = = TRUE ) ;
TEST_ASSERT ( uregex_start ( re , 0 , & status ) = = 4 ) ;
TEST_ASSERT ( uregex_end ( re , 0 , & status ) = = 4 ) ;
TEST_TEARDOWN ;
/* lookingAt (start >=0) does not use regions */
TEST_SETUP ( " .*? " , " 0123456789ABCDEF " , 0 ) ;
uregex_setRegion ( re , 4 , 6 , & status ) ;
TEST_ASSERT ( uregex_lookingAt ( re , 0 , & status ) = = TRUE ) ;
TEST_ASSERT ( uregex_start ( re , 0 , & status ) = = 0 ) ;
TEST_ASSERT ( uregex_end ( re , 0 , & status ) = = 0 ) ;
TEST_TEARDOWN ;
/* hitEnd() */
TEST_SETUP ( " [a-f]* " , " abcdefghij " , 0 ) ;
TEST_ASSERT ( uregex_find ( re , 0 , & status ) = = TRUE ) ;
TEST_ASSERT ( uregex_hitEnd ( re , & status ) = = FALSE ) ;
TEST_TEARDOWN ;
TEST_SETUP ( " [a-f]* " , " abcdef " , 0 ) ;
TEST_ASSERT ( uregex_find ( re , 0 , & status ) = = TRUE ) ;
TEST_ASSERT ( uregex_hitEnd ( re , & status ) = = TRUE ) ;
TEST_TEARDOWN ;
/* requireEnd */
TEST_SETUP ( " abcd " , " abcd " , 0 ) ;
TEST_ASSERT ( uregex_find ( re , 0 , & status ) = = TRUE ) ;
TEST_ASSERT ( uregex_requireEnd ( re , & status ) = = FALSE ) ;
TEST_TEARDOWN ;
TEST_SETUP ( " abcd$ " , " abcd " , 0 ) ;
TEST_ASSERT ( uregex_find ( re , 0 , & status ) = = TRUE ) ;
TEST_ASSERT ( uregex_requireEnd ( re , & status ) = = TRUE ) ;
TEST_TEARDOWN ;
/* anchoringBounds */
TEST_SETUP ( " abc$ " , " abcdef " , 0 ) ;
TEST_ASSERT ( uregex_hasAnchoringBounds ( re , & status ) = = TRUE ) ;
uregex_useAnchoringBounds ( re , FALSE , & status ) ;
TEST_ASSERT ( uregex_hasAnchoringBounds ( re , & status ) = = FALSE ) ;
TEST_ASSERT ( uregex_find ( re , - 1 , & status ) = = FALSE ) ;
uregex_useAnchoringBounds ( re , TRUE , & status ) ;
uregex_setRegion ( re , 0 , 3 , & status ) ;
TEST_ASSERT ( uregex_find ( re , - 1 , & status ) = = TRUE ) ;
TEST_ASSERT ( uregex_end ( re , 0 , & status ) = = 3 ) ;
TEST_TEARDOWN ;
/* Transparent Bounds */
TEST_SETUP ( " abc(?=def) " , " abcdef " , 0 ) ;
TEST_ASSERT ( uregex_hasTransparentBounds ( re , & status ) = = FALSE ) ;
uregex_useTransparentBounds ( re , TRUE , & status ) ;
TEST_ASSERT ( uregex_hasTransparentBounds ( re , & status ) = = TRUE ) ;
uregex_useTransparentBounds ( re , FALSE , & status ) ;
TEST_ASSERT ( uregex_find ( re , - 1 , & status ) = = TRUE ) ; /* No Region */
uregex_setRegion ( re , 0 , 3 , & status ) ;
TEST_ASSERT ( uregex_find ( re , - 1 , & status ) = = FALSE ) ; /* with region, opaque bounds */
uregex_useTransparentBounds ( re , TRUE , & status ) ;
TEST_ASSERT ( uregex_find ( re , - 1 , & status ) = = TRUE ) ; /* with region, transparent bounds */
TEST_ASSERT ( uregex_end ( re , 0 , & status ) = = 3 ) ;
TEST_TEARDOWN ;
2004-03-24 01:57:51 +00:00
/*
* replaceFirst ( )
*/
{
UChar text1 [ 80 ] ;
UChar text2 [ 80 ] ;
UChar replText [ 80 ] ;
UChar buf [ 80 ] ;
int32_t resultSz ;
u_uastrncpy ( text1 , " Replace xaax x1x x...x. " , sizeof ( text1 ) / 2 ) ;
u_uastrncpy ( text2 , " No match here. " , sizeof ( text2 ) / 2 ) ;
u_uastrncpy ( replText , " <$1> " , sizeof ( replText ) / 2 ) ;
status = U_ZERO_ERROR ;
re = uregex_openC ( " x(.*?)x " , 0 , NULL , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
/* Normal case, with match */
uregex_setText ( re , text1 , - 1 , & status ) ;
resultSz = uregex_replaceFirst ( re , replText , - 1 , buf , sizeof ( buf ) / 2 , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
TEST_ASSERT_STRING ( " Replace <aa> x1x x...x. " , buf , TRUE ) ;
TEST_ASSERT ( resultSz = = ( int32_t ) strlen ( " Replace xaax x1x x...x. " ) ) ;
/* No match. Text should copy to output with no changes. */
status = U_ZERO_ERROR ;
uregex_setText ( re , text2 , - 1 , & status ) ;
resultSz = uregex_replaceFirst ( re , replText , - 1 , buf , sizeof ( buf ) / 2 , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
TEST_ASSERT_STRING ( " No match here. " , buf , TRUE ) ;
TEST_ASSERT ( resultSz = = ( int32_t ) strlen ( " No match here. " ) ) ;
2004-03-23 05:20:48 +00:00
2004-03-24 01:57:51 +00:00
/* Match, output just fills buffer, no termination warning. */
status = U_ZERO_ERROR ;
uregex_setText ( re , text1 , - 1 , & status ) ;
memset ( buf , - 1 , sizeof ( buf ) ) ;
resultSz = uregex_replaceFirst ( re , replText , - 1 , buf , strlen ( " Replace <aa> x1x x...x. " ) , & status ) ;
TEST_ASSERT ( status = = U_STRING_NOT_TERMINATED_WARNING ) ;
TEST_ASSERT_STRING ( " Replace <aa> x1x x...x. " , buf , FALSE ) ;
TEST_ASSERT ( resultSz = = ( int32_t ) strlen ( " Replace xaax x1x x...x. " ) ) ;
TEST_ASSERT ( buf [ resultSz ] = = ( UChar ) 0xffff ) ;
/* Do the replaceFirst again, without first resetting anything.
* Should give the same results .
*/
status = U_ZERO_ERROR ;
memset ( buf , - 1 , sizeof ( buf ) ) ;
resultSz = uregex_replaceFirst ( re , replText , - 1 , buf , strlen ( " Replace <aa> x1x x...x. " ) , & status ) ;
TEST_ASSERT ( status = = U_STRING_NOT_TERMINATED_WARNING ) ;
TEST_ASSERT_STRING ( " Replace <aa> x1x x...x. " , buf , FALSE ) ;
TEST_ASSERT ( resultSz = = ( int32_t ) strlen ( " Replace xaax x1x x...x. " ) ) ;
TEST_ASSERT ( buf [ resultSz ] = = ( UChar ) 0xffff ) ;
/* NULL buffer, zero buffer length */
status = U_ZERO_ERROR ;
resultSz = uregex_replaceFirst ( re , replText , - 1 , NULL , 0 , & status ) ;
TEST_ASSERT ( status = = U_BUFFER_OVERFLOW_ERROR ) ;
TEST_ASSERT ( resultSz = = ( int32_t ) strlen ( " Replace xaax x1x x...x. " ) ) ;
2004-03-22 22:16:21 +00:00
2004-03-24 01:57:51 +00:00
/* Buffer too small by one */
status = U_ZERO_ERROR ;
memset ( buf , - 1 , sizeof ( buf ) ) ;
resultSz = uregex_replaceFirst ( re , replText , - 1 , buf , strlen ( " Replace <aa> x1x x...x. " ) - 1 , & status ) ;
TEST_ASSERT ( status = = U_BUFFER_OVERFLOW_ERROR ) ;
TEST_ASSERT_STRING ( " Replace <aa> x1x x...x " , buf , FALSE ) ;
TEST_ASSERT ( resultSz = = ( int32_t ) strlen ( " Replace xaax x1x x...x. " ) ) ;
TEST_ASSERT ( buf [ resultSz ] = = ( UChar ) 0xffff ) ;
uregex_close ( re ) ;
}
/*
* replaceAll ( )
*/
2004-03-24 18:34:36 +00:00
{
2009-01-08 06:55:22 +00:00
UChar text1 [ 80 ] ; /* "Replace xaax x1x x...x." */
UChar text2 [ 80 ] ; /* "No match Here" */
UChar replText [ 80 ] ; /* "<$1>" */
UChar replText2 [ 80 ] ; /* "<<$1>>" */
const char * pattern = " x(.*?)x " ;
const char * expectedResult = " Replace <aa> <1> <...>. " ;
const char * expectedResult2 = " Replace <<aa>> <<1>> <<...>>. " ;
2004-03-24 18:34:36 +00:00
UChar buf [ 80 ] ;
2009-01-08 06:55:22 +00:00
int32_t resultSize ;
2004-03-24 18:34:36 +00:00
int32_t expectedResultSize ;
2009-01-08 06:55:22 +00:00
int32_t expectedResultSize2 ;
2004-03-24 18:34:36 +00:00
int32_t i ;
u_uastrncpy ( text1 , " Replace xaax x1x x...x. " , sizeof ( text1 ) / 2 ) ;
u_uastrncpy ( text2 , " No match here. " , sizeof ( text2 ) / 2 ) ;
u_uastrncpy ( replText , " <$1> " , sizeof ( replText ) / 2 ) ;
2009-01-08 06:55:22 +00:00
u_uastrncpy ( replText2 , " <<$1>> " , sizeof ( replText2 ) / 2 ) ;
expectedResultSize = strlen ( expectedResult ) ;
expectedResultSize2 = strlen ( expectedResult2 ) ;
2004-03-24 18:34:36 +00:00
status = U_ZERO_ERROR ;
2009-01-08 06:55:22 +00:00
re = uregex_openC ( pattern , 0 , NULL , & status ) ;
2004-03-24 18:34:36 +00:00
TEST_ASSERT_SUCCESS ( status ) ;
/* Normal case, with match */
uregex_setText ( re , text1 , - 1 , & status ) ;
2009-01-08 06:55:22 +00:00
resultSize = uregex_replaceAll ( re , replText , - 1 , buf , sizeof ( buf ) / 2 , & status ) ;
2004-03-24 18:34:36 +00:00
TEST_ASSERT_SUCCESS ( status ) ;
2009-01-08 06:55:22 +00:00
TEST_ASSERT_STRING ( expectedResult , buf , TRUE ) ;
TEST_ASSERT ( resultSize = = expectedResultSize ) ;
2004-03-24 18:34:36 +00:00
/* No match. Text should copy to output with no changes. */
status = U_ZERO_ERROR ;
uregex_setText ( re , text2 , - 1 , & status ) ;
2009-01-08 06:55:22 +00:00
resultSize = uregex_replaceAll ( re , replText , - 1 , buf , sizeof ( buf ) / 2 , & status ) ;
2004-03-24 18:34:36 +00:00
TEST_ASSERT_SUCCESS ( status ) ;
TEST_ASSERT_STRING ( " No match here. " , buf , TRUE ) ;
2009-01-08 06:55:22 +00:00
TEST_ASSERT ( resultSize = = u_strlen ( text2 ) ) ;
2004-03-24 18:34:36 +00:00
/* Match, output just fills buffer, no termination warning. */
status = U_ZERO_ERROR ;
uregex_setText ( re , text1 , - 1 , & status ) ;
memset ( buf , - 1 , sizeof ( buf ) ) ;
2009-01-08 06:55:22 +00:00
resultSize = uregex_replaceAll ( re , replText , - 1 , buf , expectedResultSize , & status ) ;
2004-03-24 18:34:36 +00:00
TEST_ASSERT ( status = = U_STRING_NOT_TERMINATED_WARNING ) ;
2009-01-08 06:55:22 +00:00
TEST_ASSERT_STRING ( expectedResult , buf , FALSE ) ;
TEST_ASSERT ( resultSize = = expectedResultSize ) ;
TEST_ASSERT ( buf [ resultSize ] = = ( UChar ) 0xffff ) ;
2004-03-24 18:34:36 +00:00
/* Do the replaceFirst again, without first resetting anything.
* Should give the same results .
*/
status = U_ZERO_ERROR ;
memset ( buf , - 1 , sizeof ( buf ) ) ;
2009-01-08 06:55:22 +00:00
resultSize = uregex_replaceAll ( re , replText , - 1 , buf , strlen ( " Replace xaax x1x x...x. " ) , & status ) ;
2004-03-24 18:34:36 +00:00
TEST_ASSERT ( status = = U_STRING_NOT_TERMINATED_WARNING ) ;
TEST_ASSERT_STRING ( " Replace <aa> <1> <...>. " , buf , FALSE ) ;
2009-01-08 06:55:22 +00:00
TEST_ASSERT ( resultSize = = ( int32_t ) strlen ( " Replace <aa> <1> <...>. " ) ) ;
TEST_ASSERT ( buf [ resultSize ] = = ( UChar ) 0xffff ) ;
2004-03-24 18:34:36 +00:00
/* NULL buffer, zero buffer length */
status = U_ZERO_ERROR ;
2009-01-08 06:55:22 +00:00
resultSize = uregex_replaceAll ( re , replText , - 1 , NULL , 0 , & status ) ;
2004-03-24 18:34:36 +00:00
TEST_ASSERT ( status = = U_BUFFER_OVERFLOW_ERROR ) ;
2009-01-08 06:55:22 +00:00
TEST_ASSERT ( resultSize = = ( int32_t ) strlen ( " Replace <aa> <1> <...>. " ) ) ;
2004-03-24 18:34:36 +00:00
/* Buffer too small. Try every size, which will tickle edge cases
* in uregex_appendReplacement ( used by replaceAll ) */
for ( i = 0 ; i < expectedResultSize ; i + + ) {
char expected [ 80 ] ;
status = U_ZERO_ERROR ;
memset ( buf , - 1 , sizeof ( buf ) ) ;
2009-01-08 06:55:22 +00:00
resultSize = uregex_replaceAll ( re , replText , - 1 , buf , i , & status ) ;
2004-03-24 18:34:36 +00:00
TEST_ASSERT ( status = = U_BUFFER_OVERFLOW_ERROR ) ;
2009-01-08 06:55:22 +00:00
strcpy ( expected , expectedResult ) ;
2004-03-24 18:34:36 +00:00
expected [ i ] = 0 ;
TEST_ASSERT_STRING ( expected , buf , FALSE ) ;
2009-01-08 06:55:22 +00:00
TEST_ASSERT ( resultSize = = expectedResultSize ) ;
2004-03-24 18:34:36 +00:00
TEST_ASSERT ( buf [ i ] = = ( UChar ) 0xffff ) ;
}
2009-01-08 06:55:22 +00:00
/* Buffer too small. Same as previous test, except this time the replacement
* text is longer than the match capture group , making the length of the complete
* replacement longer than the original string .
*/
for ( i = 0 ; i < expectedResultSize2 ; i + + ) {
char expected [ 80 ] ;
status = U_ZERO_ERROR ;
memset ( buf , - 1 , sizeof ( buf ) ) ;
resultSize = uregex_replaceAll ( re , replText2 , - 1 , buf , i , & status ) ;
TEST_ASSERT ( status = = U_BUFFER_OVERFLOW_ERROR ) ;
strcpy ( expected , expectedResult2 ) ;
expected [ i ] = 0 ;
TEST_ASSERT_STRING ( expected , buf , FALSE ) ;
TEST_ASSERT ( resultSize = = expectedResultSize2 ) ;
TEST_ASSERT ( buf [ i ] = = ( UChar ) 0xffff ) ;
}
2004-03-24 18:34:36 +00:00
uregex_close ( re ) ;
}
2004-03-24 01:57:51 +00:00
/*
* appendReplacement ( )
*/
2004-03-26 01:23:01 +00:00
{
UChar text [ 100 ] ;
UChar repl [ 100 ] ;
UChar buf [ 100 ] ;
UChar * bufPtr ;
int32_t bufCap ;
status = U_ZERO_ERROR ;
re = uregex_openC ( " .* " , 0 , 0 , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
u_uastrncpy ( text , " whatever " , sizeof ( text ) / 2 ) ;
u_uastrncpy ( repl , " some other " , sizeof ( repl ) / 2 ) ;
uregex_setText ( re , text , - 1 , & status ) ;
/* match covers whole target string */
uregex_find ( re , 0 , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
bufPtr = buf ;
bufCap = sizeof ( buf ) / 2 ;
uregex_appendReplacement ( re , repl , - 1 , & bufPtr , & bufCap , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
TEST_ASSERT_STRING ( " some other " , buf , TRUE ) ;
/* Match has \u \U escapes */
uregex_find ( re , 0 , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
bufPtr = buf ;
bufCap = sizeof ( buf ) / 2 ;
2004-03-26 20:20:21 +00:00
u_uastrncpy ( repl , " abc \\ u0041 \\ U00000042 \\ \\ $ \\ abc " , sizeof ( repl ) / 2 ) ;
2004-03-26 01:23:01 +00:00
uregex_appendReplacement ( re , repl , - 1 , & bufPtr , & bufCap , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
2004-03-26 20:20:21 +00:00
TEST_ASSERT_STRING ( " abcAB \\ $ abc " , buf , TRUE ) ;
2004-03-26 01:23:01 +00:00
2009-03-26 23:04:40 +00:00
/* Bug 6813, parameter check of NULL destCapacity; crashed before fix. */
status = U_ZERO_ERROR ;
uregex_find ( re , 0 , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
bufPtr = buf ;
status = U_BUFFER_OVERFLOW_ERROR ;
uregex_appendReplacement ( re , repl , - 1 , & bufPtr , NULL , & status ) ;
TEST_ASSERT ( status = = U_BUFFER_OVERFLOW_ERROR ) ;
2004-04-23 18:02:55 +00:00
uregex_close ( re ) ;
2004-03-26 01:23:01 +00:00
}
2004-03-24 01:57:51 +00:00
/*
2004-03-26 01:23:01 +00:00
* appendTail ( ) . Checked in ReplaceFirst ( ) , replaceAll ( ) .
2004-03-24 01:57:51 +00:00
*/
/*
* split ( )
*/
2004-03-24 18:34:36 +00:00
{
UChar textToSplit [ 80 ] ;
UChar text2 [ 80 ] ;
UChar buf [ 200 ] ;
UChar * fields [ 10 ] ;
int32_t numFields ;
int32_t requiredCapacity ;
int32_t spaceNeeded ;
2004-03-26 01:23:01 +00:00
int32_t sz ;
2004-03-24 18:34:36 +00:00
u_uastrncpy ( textToSplit , " first : second: third " , sizeof ( textToSplit ) / 2 ) ;
u_uastrncpy ( text2 , " No match here. " , sizeof ( text2 ) / 2 ) ;
status = U_ZERO_ERROR ;
re = uregex_openC ( " : " , 0 , NULL , & status ) ;
2004-03-26 01:23:01 +00:00
/* Simple split */
2004-03-24 18:34:36 +00:00
uregex_setText ( re , textToSplit , - 1 , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
2004-12-16 02:54:23 +00:00
/* The TEST_ASSERT_SUCCESS call above should change too... */
if ( U_SUCCESS ( status ) ) {
memset ( fields , - 1 , sizeof ( fields ) ) ;
numFields =
uregex_split ( re , buf , sizeof ( buf ) / 2 , & requiredCapacity , fields , 10 , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
/* The TEST_ASSERT_SUCCESS call above should change too... */
if ( U_SUCCESS ( status ) ) {
TEST_ASSERT ( numFields = = 3 ) ;
TEST_ASSERT_STRING ( " first " , fields [ 0 ] , TRUE ) ;
TEST_ASSERT_STRING ( " second " , fields [ 1 ] , TRUE ) ;
TEST_ASSERT_STRING ( " third " , fields [ 2 ] , TRUE ) ;
TEST_ASSERT ( fields [ 3 ] = = NULL ) ;
spaceNeeded = u_strlen ( textToSplit ) -
( numFields - 1 ) + /* Field delimiters do not appear in output */
numFields ; /* Each field gets a NUL terminator */
2004-03-24 18:34:36 +00:00
2004-12-16 02:54:23 +00:00
TEST_ASSERT ( spaceNeeded = = requiredCapacity ) ;
}
}
2004-03-24 18:34:36 +00:00
2004-04-23 18:02:55 +00:00
uregex_close ( re ) ;
2004-03-26 01:23:01 +00:00
/* Split with too few output strings available */
status = U_ZERO_ERROR ;
re = uregex_openC ( " : " , 0 , NULL , & status ) ;
uregex_setText ( re , textToSplit , - 1 , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
2004-12-16 02:54:23 +00:00
/* The TEST_ASSERT_SUCCESS call above should change too... */
if ( U_SUCCESS ( status ) ) {
2004-03-26 01:23:01 +00:00
memset ( fields , - 1 , sizeof ( fields ) ) ;
numFields =
2004-12-16 02:54:23 +00:00
uregex_split ( re , buf , sizeof ( buf ) / 2 , & requiredCapacity , fields , 2 , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
/* The TEST_ASSERT_SUCCESS call above should change too... */
if ( U_SUCCESS ( status ) ) {
TEST_ASSERT ( numFields = = 2 ) ;
2004-03-26 01:23:01 +00:00
TEST_ASSERT_STRING ( " first " , fields [ 0 ] , TRUE ) ;
2004-12-16 02:54:23 +00:00
TEST_ASSERT_STRING ( " second: third " , fields [ 1 ] , TRUE ) ;
TEST_ASSERT ( ! memcmp ( & fields [ 2 ] , & minus1 , sizeof ( UChar * ) ) ) ;
spaceNeeded = u_strlen ( textToSplit ) -
( numFields - 1 ) + /* Field delimiters do not appear in output */
numFields ; /* Each field gets a NUL terminator */
TEST_ASSERT ( spaceNeeded = = requiredCapacity ) ;
/* Split with a range of output buffer sizes. */
spaceNeeded = u_strlen ( textToSplit ) -
( numFields - 1 ) + /* Field delimiters do not appear in output */
numFields ; /* Each field gets a NUL terminator */
for ( sz = 0 ; sz < spaceNeeded + 1 ; sz + + ) {
memset ( fields , - 1 , sizeof ( fields ) ) ;
status = U_ZERO_ERROR ;
numFields =
uregex_split ( re , buf , sz , & requiredCapacity , fields , 10 , & status ) ;
if ( sz > = spaceNeeded ) {
TEST_ASSERT_SUCCESS ( status ) ;
TEST_ASSERT_STRING ( " first " , fields [ 0 ] , TRUE ) ;
TEST_ASSERT_STRING ( " second " , fields [ 1 ] , TRUE ) ;
TEST_ASSERT_STRING ( " third " , fields [ 2 ] , TRUE ) ;
} else {
TEST_ASSERT ( status = = U_BUFFER_OVERFLOW_ERROR ) ;
}
TEST_ASSERT ( numFields = = 3 ) ;
TEST_ASSERT ( fields [ 3 ] = = NULL ) ;
TEST_ASSERT ( spaceNeeded = = requiredCapacity ) ;
}
2004-03-26 01:23:01 +00:00
}
}
2004-12-16 02:54:23 +00:00
2004-04-23 18:02:55 +00:00
uregex_close ( re ) ;
2004-03-24 18:34:36 +00:00
}
2004-03-26 01:23:01 +00:00
/* Split(), part 2. Patterns with capture groups. The capture group text
* comes out as additional fields . */
{
UChar textToSplit [ 80 ] ;
UChar buf [ 200 ] ;
UChar * fields [ 10 ] ;
int32_t numFields ;
int32_t requiredCapacity ;
int32_t spaceNeeded ;
int32_t sz ;
u_uastrncpy ( textToSplit , " first <tag-a> second<tag-b> third " , sizeof ( textToSplit ) / 2 ) ;
status = U_ZERO_ERROR ;
re = uregex_openC ( " <(.*?)> " , 0 , NULL , & status ) ;
uregex_setText ( re , textToSplit , - 1 , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
2004-12-16 02:54:23 +00:00
/* The TEST_ASSERT_SUCCESS call above should change too... */
if ( U_SUCCESS ( status ) ) {
memset ( fields , - 1 , sizeof ( fields ) ) ;
numFields =
uregex_split ( re , buf , sizeof ( buf ) / 2 , & requiredCapacity , fields , 10 , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
2004-03-26 01:23:01 +00:00
2004-12-16 02:54:23 +00:00
/* The TEST_ASSERT_SUCCESS call above should change too... */
if ( U_SUCCESS ( status ) ) {
TEST_ASSERT ( numFields = = 5 ) ;
TEST_ASSERT_STRING ( " first " , fields [ 0 ] , TRUE ) ;
TEST_ASSERT_STRING ( " tag-a " , fields [ 1 ] , TRUE ) ;
TEST_ASSERT_STRING ( " second " , fields [ 2 ] , TRUE ) ;
TEST_ASSERT_STRING ( " tag-b " , fields [ 3 ] , TRUE ) ;
TEST_ASSERT_STRING ( " third " , fields [ 4 ] , TRUE ) ;
TEST_ASSERT ( fields [ 5 ] = = NULL ) ;
spaceNeeded = strlen ( " first .tag-a. second.tag-b. third. " ) ; /* "." at NUL positions */
TEST_ASSERT ( spaceNeeded = = requiredCapacity ) ;
}
}
2004-03-26 01:23:01 +00:00
/* Split with too few output strings available (2) */
status = U_ZERO_ERROR ;
memset ( fields , - 1 , sizeof ( fields ) ) ;
numFields =
uregex_split ( re , buf , sizeof ( buf ) / 2 , & requiredCapacity , fields , 2 , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
2004-12-16 02:54:23 +00:00
/* The TEST_ASSERT_SUCCESS call above should change too... */
if ( U_SUCCESS ( status ) ) {
TEST_ASSERT ( numFields = = 2 ) ;
TEST_ASSERT_STRING ( " first " , fields [ 0 ] , TRUE ) ;
TEST_ASSERT_STRING ( " second<tag-b> third " , fields [ 1 ] , TRUE ) ;
TEST_ASSERT ( ! memcmp ( & fields [ 2 ] , & minus1 , sizeof ( UChar * ) ) ) ;
spaceNeeded = strlen ( " first . second<tag-b> third. " ) ; /* "." at NUL positions */
TEST_ASSERT ( spaceNeeded = = requiredCapacity ) ;
}
2004-03-26 01:23:01 +00:00
/* Split with too few output strings available (3) */
status = U_ZERO_ERROR ;
memset ( fields , - 1 , sizeof ( fields ) ) ;
numFields =
uregex_split ( re , buf , sizeof ( buf ) / 2 , & requiredCapacity , fields , 3 , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
2004-12-16 02:54:23 +00:00
/* The TEST_ASSERT_SUCCESS call above should change too... */
if ( U_SUCCESS ( status ) ) {
TEST_ASSERT ( numFields = = 3 ) ;
TEST_ASSERT_STRING ( " first " , fields [ 0 ] , TRUE ) ;
TEST_ASSERT_STRING ( " tag-a " , fields [ 1 ] , TRUE ) ;
TEST_ASSERT_STRING ( " second<tag-b> third " , fields [ 2 ] , TRUE ) ;
TEST_ASSERT ( ! memcmp ( & fields [ 3 ] , & minus1 , sizeof ( UChar * ) ) ) ;
spaceNeeded = strlen ( " first .tag-a. second<tag-b> third. " ) ; /* "." at NUL positions */
TEST_ASSERT ( spaceNeeded = = requiredCapacity ) ;
}
2004-03-26 01:23:01 +00:00
/* Split with just enough output strings available (5) */
status = U_ZERO_ERROR ;
memset ( fields , - 1 , sizeof ( fields ) ) ;
numFields =
uregex_split ( re , buf , sizeof ( buf ) / 2 , & requiredCapacity , fields , 5 , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
2004-12-16 02:54:23 +00:00
/* The TEST_ASSERT_SUCCESS call above should change too... */
if ( U_SUCCESS ( status ) ) {
TEST_ASSERT ( numFields = = 5 ) ;
TEST_ASSERT_STRING ( " first " , fields [ 0 ] , TRUE ) ;
TEST_ASSERT_STRING ( " tag-a " , fields [ 1 ] , TRUE ) ;
TEST_ASSERT_STRING ( " second " , fields [ 2 ] , TRUE ) ;
TEST_ASSERT_STRING ( " tag-b " , fields [ 3 ] , TRUE ) ;
TEST_ASSERT_STRING ( " third " , fields [ 4 ] , TRUE ) ;
TEST_ASSERT ( ! memcmp ( & fields [ 5 ] , & minus1 , sizeof ( UChar * ) ) ) ;
2004-03-26 01:23:01 +00:00
2004-12-16 02:54:23 +00:00
spaceNeeded = strlen ( " first .tag-a. second.tag-b. third. " ) ; /* "." at NUL positions */
TEST_ASSERT ( spaceNeeded = = requiredCapacity ) ;
}
2004-03-26 01:23:01 +00:00
/* Split, end of text is a field delimiter. */
status = U_ZERO_ERROR ;
sz = strlen ( " first <tag-a> second<tag-b> " ) ;
uregex_setText ( re , textToSplit , sz , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
2004-12-16 02:54:23 +00:00
/* The TEST_ASSERT_SUCCESS call above should change too... */
if ( U_SUCCESS ( status ) ) {
memset ( fields , - 1 , sizeof ( fields ) ) ;
numFields =
uregex_split ( re , buf , sizeof ( buf ) / 2 , & requiredCapacity , fields , 9 , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
/* The TEST_ASSERT_SUCCESS call above should change too... */
if ( U_SUCCESS ( status ) ) {
2011-04-15 00:48:39 +00:00
TEST_ASSERT ( numFields = = 5 ) ;
2004-12-16 02:54:23 +00:00
TEST_ASSERT_STRING ( " first " , fields [ 0 ] , TRUE ) ;
TEST_ASSERT_STRING ( " tag-a " , fields [ 1 ] , TRUE ) ;
TEST_ASSERT_STRING ( " second " , fields [ 2 ] , TRUE ) ;
TEST_ASSERT_STRING ( " tag-b " , fields [ 3 ] , TRUE ) ;
2011-04-15 00:48:39 +00:00
TEST_ASSERT_STRING ( " " , fields [ 4 ] , TRUE ) ;
TEST_ASSERT ( fields [ 5 ] = = NULL ) ;
2004-12-16 02:54:23 +00:00
TEST_ASSERT ( fields [ 8 ] = = NULL ) ;
TEST_ASSERT ( ! memcmp ( & fields [ 9 ] , & minus1 , sizeof ( UChar * ) ) ) ;
2011-04-15 00:48:39 +00:00
spaceNeeded = strlen ( " first .tag-a. second.tag-b.. " ) ; /* "." at NUL positions */
2004-12-16 02:54:23 +00:00
TEST_ASSERT ( spaceNeeded = = requiredCapacity ) ;
}
}
2004-03-26 01:23:01 +00:00
uregex_close ( re ) ;
}
2008-02-20 03:08:44 +00:00
/*
* set / getTimeLimit
*/
TEST_SETUP ( " abc$ " , " abcdef " , 0 ) ;
TEST_ASSERT ( uregex_getTimeLimit ( re , & status ) = = 0 ) ;
uregex_setTimeLimit ( re , 1000 , & status ) ;
TEST_ASSERT ( uregex_getTimeLimit ( re , & status ) = = 1000 ) ;
TEST_ASSERT_SUCCESS ( status ) ;
uregex_setTimeLimit ( re , - 1 , & status ) ;
TEST_ASSERT ( status = = U_ILLEGAL_ARGUMENT_ERROR ) ;
status = U_ZERO_ERROR ;
TEST_ASSERT ( uregex_getTimeLimit ( re , & status ) = = 1000 ) ;
TEST_TEARDOWN ;
/*
* set / get Stack Limit
*/
TEST_SETUP ( " abc$ " , " abcdef " , 0 ) ;
TEST_ASSERT ( uregex_getStackLimit ( re , & status ) = = 8000000 ) ;
uregex_setStackLimit ( re , 40000 , & status ) ;
TEST_ASSERT ( uregex_getStackLimit ( re , & status ) = = 40000 ) ;
TEST_ASSERT_SUCCESS ( status ) ;
uregex_setStackLimit ( re , - 1 , & status ) ;
TEST_ASSERT ( status = = U_ILLEGAL_ARGUMENT_ERROR ) ;
status = U_ZERO_ERROR ;
TEST_ASSERT ( uregex_getStackLimit ( re , & status ) = = 40000 ) ;
TEST_TEARDOWN ;
/*
* Get / Set callback functions
* This test is copied from intltest regex / Callbacks
* The pattern and test data will run long enough to cause the callback
* to be invoked . The nested ' + ' operators give exponential time
* behavior with increasing string length .
*/
TEST_SETUP ( " ((.)+ \\ 2)+x " , " aaaaaaaaaaaaaaaaaaab " , 0 )
callBackContext cbInfo = { 4 , 0 , 0 } ;
const void * pContext = & cbInfo ;
2008-02-25 22:32:11 +00:00
URegexMatchCallback * returnedFn = & TestCallbackFn ;
2008-02-20 03:08:44 +00:00
/* Getting the callback fn when it hasn't been set must return NULL */
uregex_getMatchCallback ( re , & returnedFn , & pContext , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
TEST_ASSERT ( returnedFn = = NULL ) ;
TEST_ASSERT ( pContext = = NULL ) ;
/* Set thecallback and do a match. */
/* The callback function should record that it has been called. */
uregex_setMatchCallback ( re , & TestCallbackFn , & cbInfo , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
TEST_ASSERT ( cbInfo . numCalls = = 0 ) ;
TEST_ASSERT ( uregex_matches ( re , - 1 , & status ) = = FALSE ) ;
TEST_ASSERT_SUCCESS ( status ) ;
TEST_ASSERT ( cbInfo . numCalls > 0 ) ;
/* Getting the callback should return the values that were set above. */
uregex_getMatchCallback ( re , & returnedFn , & pContext , & status ) ;
TEST_ASSERT ( returnedFn = = & TestCallbackFn ) ;
TEST_ASSERT ( pContext = = & cbInfo ) ;
TEST_TEARDOWN ;
2004-03-22 22:16:21 +00:00
}
2008-02-20 03:08:44 +00:00
2005-12-22 20:15:40 +00:00
static void TestBug4315 ( void ) {
2006-08-20 05:08:35 +00:00
UErrorCode theICUError = U_ZERO_ERROR ;
URegularExpression * theRegEx ;
2005-09-02 21:57:12 +00:00
UChar * textBuff ;
2006-08-20 05:08:35 +00:00
const char * thePattern ;
2005-09-02 21:57:12 +00:00
UChar theString [ 100 ] ;
UChar * destFields [ 24 ] ;
2005-09-02 23:49:51 +00:00
int32_t neededLength1 ;
int32_t neededLength2 ;
2005-08-31 00:52:22 +00:00
2005-09-02 21:57:12 +00:00
int32_t wordCount = 0 ;
int32_t destFieldsSize = 24 ;
2005-08-31 00:52:22 +00:00
2006-08-20 05:08:35 +00:00
thePattern = " ck " ;
2005-08-31 00:52:22 +00:00
u_uastrcpy ( theString , " The quick brown fox jumped over the slow black turtle. " ) ;
/* open a regex */
theRegEx = uregex_openC ( thePattern , 0 , NULL , & theICUError ) ;
TEST_ASSERT_SUCCESS ( theICUError ) ;
/* set the input string */
uregex_setText ( theRegEx , theString , u_strlen ( theString ) , & theICUError ) ;
TEST_ASSERT_SUCCESS ( theICUError ) ;
/* split */
2005-09-02 21:57:12 +00:00
/*explicitly pass NULL and 0 to force the overflow error -> this is where the
* error occurs ! */
2005-09-02 23:49:51 +00:00
wordCount = uregex_split ( theRegEx , NULL , 0 , & neededLength1 , destFields ,
2005-08-31 00:52:22 +00:00
destFieldsSize , & theICUError ) ;
TEST_ASSERT ( theICUError = = U_BUFFER_OVERFLOW_ERROR ) ;
TEST_ASSERT ( wordCount = = 3 ) ;
if ( theICUError = = U_BUFFER_OVERFLOW_ERROR )
{
theICUError = U_ZERO_ERROR ;
2005-09-02 23:49:51 +00:00
textBuff = ( UChar * ) malloc ( sizeof ( UChar ) * ( neededLength1 + 1 ) ) ;
wordCount = uregex_split ( theRegEx , textBuff , neededLength1 + 1 , & neededLength2 ,
2005-08-31 00:52:22 +00:00
destFields , destFieldsSize , & theICUError ) ;
TEST_ASSERT ( wordCount = = 3 ) ;
TEST_ASSERT_SUCCESS ( theICUError ) ;
2005-09-02 23:49:51 +00:00
TEST_ASSERT ( neededLength1 = = neededLength2 ) ;
2005-08-31 00:52:22 +00:00
TEST_ASSERT_STRING ( " The qui " , destFields [ 0 ] , TRUE ) ;
TEST_ASSERT_STRING ( " brown fox jumped over the slow bla " , destFields [ 1 ] , TRUE ) ;
TEST_ASSERT_STRING ( " turtle. " , destFields [ 2 ] , TRUE ) ;
TEST_ASSERT ( destFields [ 3 ] = = NULL ) ;
free ( textBuff ) ;
}
2005-11-17 21:31:01 +00:00
uregex_close ( theRegEx ) ;
2005-08-31 00:52:22 +00:00
}
2010-02-03 02:59:35 +00:00
/* Based on TestRegexCAPI() */
static void TestUTextAPI ( void ) {
UErrorCode status = U_ZERO_ERROR ;
URegularExpression * re ;
UText patternText = UTEXT_INITIALIZER ;
UChar pat [ 200 ] ;
2010-03-03 01:47:00 +00:00
const char patternTextUTF8 [ 5 ] = { 0x61 , 0x62 , 0x63 , 0x2a , 0x00 } ;
2010-02-03 02:59:35 +00:00
/* Mimimalist open/close */
2010-03-03 01:47:00 +00:00
utext_openUTF8 ( & patternText , patternTextUTF8 , - 1 , & status ) ;
2010-02-03 02:59:35 +00:00
re = uregex_openUText ( & patternText , 0 , 0 , & status ) ;
if ( U_FAILURE ( status ) ) {
2010-03-03 01:47:00 +00:00
log_data_err ( " Failed to open regular expression, %s:%d, error is \" %s \" (Are you missing data?) \n " , __FILE__ , __LINE__ , u_errorName ( status ) ) ;
2010-02-24 16:17:03 +00:00
utext_close ( & patternText ) ;
2010-02-03 02:59:35 +00:00
return ;
}
uregex_close ( re ) ;
/* Open with all flag values set */
status = U_ZERO_ERROR ;
re = uregex_openUText ( & patternText ,
UREGEX_CASE_INSENSITIVE | UREGEX_COMMENTS | UREGEX_DOTALL | UREGEX_MULTILINE | UREGEX_UWORD ,
0 , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
uregex_close ( re ) ;
/* Open with an invalid flag */
status = U_ZERO_ERROR ;
re = uregex_openUText ( & patternText , 0x40000000 , 0 , & status ) ;
TEST_ASSERT ( status = = U_REGEX_INVALID_FLAG ) ;
uregex_close ( re ) ;
/* open with an invalid parameter */
status = U_ZERO_ERROR ;
re = uregex_openUText ( NULL ,
UREGEX_CASE_INSENSITIVE | UREGEX_COMMENTS | UREGEX_DOTALL | UREGEX_MULTILINE | UREGEX_UWORD , 0 , & status ) ;
TEST_ASSERT ( status = = U_ILLEGAL_ARGUMENT_ERROR & & re = = NULL ) ;
/*
* clone
*/
{
URegularExpression * clone1 ;
URegularExpression * clone2 ;
URegularExpression * clone3 ;
UChar testString1 [ 30 ] ;
UChar testString2 [ 30 ] ;
UBool result ;
status = U_ZERO_ERROR ;
re = uregex_openUText ( & patternText , 0 , 0 , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
clone1 = uregex_clone ( re , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
TEST_ASSERT ( clone1 ! = NULL ) ;
status = U_ZERO_ERROR ;
clone2 = uregex_clone ( re , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
TEST_ASSERT ( clone2 ! = NULL ) ;
uregex_close ( re ) ;
status = U_ZERO_ERROR ;
clone3 = uregex_clone ( clone2 , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
TEST_ASSERT ( clone3 ! = NULL ) ;
u_uastrncpy ( testString1 , " abcccd " , sizeof ( pat ) / 2 ) ;
u_uastrncpy ( testString2 , " xxxabcccd " , sizeof ( pat ) / 2 ) ;
status = U_ZERO_ERROR ;
uregex_setText ( clone1 , testString1 , - 1 , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
result = uregex_lookingAt ( clone1 , 0 , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
TEST_ASSERT ( result = = TRUE ) ;
status = U_ZERO_ERROR ;
uregex_setText ( clone2 , testString2 , - 1 , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
result = uregex_lookingAt ( clone2 , 0 , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
TEST_ASSERT ( result = = FALSE ) ;
result = uregex_find ( clone2 , 0 , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
TEST_ASSERT ( result = = TRUE ) ;
uregex_close ( clone1 ) ;
uregex_close ( clone2 ) ;
uregex_close ( clone3 ) ;
}
/*
* pattern ( ) and patternText ( )
*/
{
const UChar * resultPat ;
int32_t resultLen ;
UText * resultText ;
2010-03-03 01:47:00 +00:00
const char str_hello [ ] = { 0x68 , 0x65 , 0x6c , 0x6c , 0x6f , 0x00 } ; /* hello */
const char str_hel [ ] = { 0x68 , 0x65 , 0x6c , 0x00 } ; /* hel */
2010-02-03 02:59:35 +00:00
u_uastrncpy ( pat , " hello " , sizeof ( pat ) / 2 ) ; /* for comparison */
status = U_ZERO_ERROR ;
2010-03-03 01:47:00 +00:00
utext_openUTF8 ( & patternText , str_hello , - 1 , & status ) ;
2010-02-03 02:59:35 +00:00
re = uregex_open ( pat , - 1 , 0 , NULL , & status ) ;
resultPat = uregex_pattern ( re , & resultLen , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
/* The TEST_ASSERT_SUCCESS above should change too... */
if ( U_SUCCESS ( status ) ) {
TEST_ASSERT ( resultLen = = - 1 ) ;
TEST_ASSERT ( u_strcmp ( resultPat , pat ) = = 0 ) ;
}
resultText = uregex_patternUText ( re , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
2010-03-03 01:47:00 +00:00
TEST_ASSERT_UTEXT ( str_hello , resultText ) ;
2010-02-03 02:59:35 +00:00
uregex_close ( re ) ;
status = U_ZERO_ERROR ;
re = uregex_open ( pat , 3 , 0 , NULL , & status ) ;
resultPat = uregex_pattern ( re , & resultLen , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
/* The TEST_ASSERT_SUCCESS above should change too... */
if ( U_SUCCESS ( status ) ) {
TEST_ASSERT ( resultLen = = 3 ) ;
TEST_ASSERT ( u_strncmp ( resultPat , pat , 3 ) = = 0 ) ;
TEST_ASSERT ( u_strlen ( resultPat ) = = 3 ) ;
}
resultText = uregex_patternUText ( re , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
2010-03-03 01:47:00 +00:00
TEST_ASSERT_UTEXT ( str_hel , resultText ) ;
2010-02-03 02:59:35 +00:00
uregex_close ( re ) ;
}
/*
* setUText ( ) and lookingAt ( )
*/
{
UText text1 = UTEXT_INITIALIZER ;
UText text2 = UTEXT_INITIALIZER ;
UBool result ;
2010-03-03 01:47:00 +00:00
const char str_abcccd [ ] = { 0x62 , 0x63 , 0x64 , 0x64 , 0x64 , 0x65 , 0x00 } ; /* abcccd */
const char str_abcccxd [ ] = { 0x62 , 0x63 , 0x64 , 0x64 , 0x64 , 0x79 , 0x65 , 0x00 } ; /* abcccxd */
const char str_abcd [ ] = { 0x62 , 0x63 , 0x64 , 0x2b , 0x65 , 0x00 } ; /* abc*d */
2010-02-03 02:59:35 +00:00
status = U_ZERO_ERROR ;
2010-03-03 01:47:00 +00:00
utext_openUTF8 ( & text1 , str_abcccd , - 1 , & status ) ;
utext_openUTF8 ( & text2 , str_abcccxd , - 1 , & status ) ;
2010-02-03 02:59:35 +00:00
2010-03-03 01:47:00 +00:00
utext_openUTF8 ( & patternText , str_abcd , - 1 , & status ) ;
2010-02-03 02:59:35 +00:00
re = uregex_openUText ( & patternText , 0 , NULL , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
/* Operation before doing a setText should fail... */
status = U_ZERO_ERROR ;
uregex_lookingAt ( re , 0 , & status ) ;
TEST_ASSERT ( status = = U_REGEX_INVALID_STATE ) ;
status = U_ZERO_ERROR ;
uregex_setUText ( re , & text1 , & status ) ;
result = uregex_lookingAt ( re , 0 , & status ) ;
TEST_ASSERT ( result = = TRUE ) ;
TEST_ASSERT_SUCCESS ( status ) ;
status = U_ZERO_ERROR ;
uregex_setUText ( re , & text2 , & status ) ;
result = uregex_lookingAt ( re , 0 , & status ) ;
TEST_ASSERT ( result = = FALSE ) ;
TEST_ASSERT_SUCCESS ( status ) ;
status = U_ZERO_ERROR ;
uregex_setUText ( re , & text1 , & status ) ;
result = uregex_lookingAt ( re , 0 , & status ) ;
TEST_ASSERT ( result = = TRUE ) ;
TEST_ASSERT_SUCCESS ( status ) ;
uregex_close ( re ) ;
utext_close ( & text1 ) ;
utext_close ( & text2 ) ;
}
/*
* getText ( ) and getUText ( )
*/
{
UText text1 = UTEXT_INITIALIZER ;
UText text2 = UTEXT_INITIALIZER ;
UChar text2Chars [ 20 ] ;
UText * resultText ;
const UChar * result ;
int32_t textLength ;
2010-03-03 01:47:00 +00:00
const char str_abcccd [ ] = { 0x62 , 0x63 , 0x64 , 0x64 , 0x64 , 0x65 , 0x00 } ; /* abcccd */
const char str_abcccxd [ ] = { 0x62 , 0x63 , 0x64 , 0x64 , 0x64 , 0x79 , 0x65 , 0x00 } ; /* abcccxd */
const char str_abcd [ ] = { 0x62 , 0x63 , 0x64 , 0x2b , 0x65 , 0x00 } ; /* abc*d */
2010-02-03 02:59:35 +00:00
status = U_ZERO_ERROR ;
2010-03-03 01:47:00 +00:00
utext_openUTF8 ( & text1 , str_abcccd , - 1 , & status ) ;
u_uastrncpy ( text2Chars , str_abcccxd , sizeof ( text2 ) / 2 ) ;
2010-02-03 02:59:35 +00:00
utext_openUChars ( & text2 , text2Chars , - 1 , & status ) ;
2010-03-03 01:47:00 +00:00
utext_openUTF8 ( & patternText , str_abcd , - 1 , & status ) ;
2010-02-03 02:59:35 +00:00
re = uregex_openUText ( & patternText , 0 , NULL , & status ) ;
/* First set a UText */
uregex_setUText ( re , & text1 , & status ) ;
resultText = uregex_getUText ( re , NULL , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
TEST_ASSERT ( resultText ! = & text1 ) ;
utext_setNativeIndex ( resultText , 0 ) ;
utext_setNativeIndex ( & text1 , 0 ) ;
2012-01-31 01:14:41 +00:00
TEST_ASSERT ( testUTextEqual ( resultText , & text1 ) ) ;
2010-02-03 02:59:35 +00:00
utext_close ( resultText ) ;
result = uregex_getText ( re , & textLength , & status ) ; /* flattens UText into buffer */
2013-03-21 05:48:52 +00:00
( void ) result ; /* Suppress set but not used warning. */
2010-02-03 02:59:35 +00:00
TEST_ASSERT ( textLength = = - 1 | | textLength = = 6 ) ;
resultText = uregex_getUText ( re , NULL , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
TEST_ASSERT ( resultText ! = & text1 ) ;
utext_setNativeIndex ( resultText , 0 ) ;
utext_setNativeIndex ( & text1 , 0 ) ;
2012-01-31 01:14:41 +00:00
TEST_ASSERT ( testUTextEqual ( resultText , & text1 ) ) ;
2010-02-03 02:59:35 +00:00
utext_close ( resultText ) ;
/* Then set a UChar * */
uregex_setText ( re , text2Chars , 7 , & status ) ;
resultText = uregex_getUText ( re , NULL , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
utext_setNativeIndex ( resultText , 0 ) ;
utext_setNativeIndex ( & text2 , 0 ) ;
2012-01-31 01:14:41 +00:00
TEST_ASSERT ( testUTextEqual ( resultText , & text2 ) ) ;
2010-02-03 02:59:35 +00:00
utext_close ( resultText ) ;
result = uregex_getText ( re , & textLength , & status ) ;
TEST_ASSERT ( textLength = = 7 ) ;
uregex_close ( re ) ;
utext_close ( & text1 ) ;
utext_close ( & text2 ) ;
}
/*
* matches ( )
*/
{
UText text1 = UTEXT_INITIALIZER ;
UBool result ;
UText nullText = UTEXT_INITIALIZER ;
2010-03-03 01:47:00 +00:00
const char str_abcccde [ ] = { 0x61 , 0x62 , 0x63 , 0x63 , 0x63 , 0x64 , 0x65 , 0x00 } ; /* abcccde */
const char str_abcd [ ] = { 0x61 , 0x62 , 0x63 , 0x2a , 0x64 , 0x00 } ; /* abc*d */
2010-02-03 02:59:35 +00:00
status = U_ZERO_ERROR ;
2010-03-03 01:47:00 +00:00
utext_openUTF8 ( & text1 , str_abcccde , - 1 , & status ) ;
utext_openUTF8 ( & patternText , str_abcd , - 1 , & status ) ;
2010-02-03 02:59:35 +00:00
re = uregex_openUText ( & patternText , 0 , NULL , & status ) ;
uregex_setUText ( re , & text1 , & status ) ;
result = uregex_matches ( re , 0 , & status ) ;
TEST_ASSERT ( result = = FALSE ) ;
TEST_ASSERT_SUCCESS ( status ) ;
uregex_close ( re ) ;
status = U_ZERO_ERROR ;
re = uregex_openC ( " .? " , 0 , NULL , & status ) ;
uregex_setUText ( re , & text1 , & status ) ;
result = uregex_matches ( re , 7 , & status ) ;
TEST_ASSERT ( result = = TRUE ) ;
TEST_ASSERT_SUCCESS ( status ) ;
status = U_ZERO_ERROR ;
utext_openUTF8 ( & nullText , " " , - 1 , & status ) ;
uregex_setUText ( re , & nullText , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
result = uregex_matches ( re , 0 , & status ) ;
TEST_ASSERT ( result = = TRUE ) ;
TEST_ASSERT_SUCCESS ( status ) ;
uregex_close ( re ) ;
utext_close ( & text1 ) ;
utext_close ( & nullText ) ;
}
/*
* lookingAt ( ) Used in setText test .
*/
/*
* find ( ) , findNext , start , end , reset
*/
{
UChar text1 [ 50 ] ;
UBool result ;
u_uastrncpy ( text1 , " 012rx5rx890rxrx... " , sizeof ( text1 ) / 2 ) ;
status = U_ZERO_ERROR ;
re = uregex_openC ( " rx " , 0 , NULL , & status ) ;
uregex_setText ( re , text1 , - 1 , & status ) ;
result = uregex_find ( re , 0 , & status ) ;
TEST_ASSERT ( result = = TRUE ) ;
TEST_ASSERT ( uregex_start ( re , 0 , & status ) = = 3 ) ;
TEST_ASSERT ( uregex_end ( re , 0 , & status ) = = 5 ) ;
TEST_ASSERT_SUCCESS ( status ) ;
result = uregex_find ( re , 9 , & status ) ;
TEST_ASSERT ( result = = TRUE ) ;
TEST_ASSERT ( uregex_start ( re , 0 , & status ) = = 11 ) ;
TEST_ASSERT ( uregex_end ( re , 0 , & status ) = = 13 ) ;
TEST_ASSERT_SUCCESS ( status ) ;
result = uregex_find ( re , 14 , & status ) ;
TEST_ASSERT ( result = = FALSE ) ;
TEST_ASSERT_SUCCESS ( status ) ;
status = U_ZERO_ERROR ;
uregex_reset ( re , 0 , & status ) ;
result = uregex_findNext ( re , & status ) ;
TEST_ASSERT ( result = = TRUE ) ;
TEST_ASSERT ( uregex_start ( re , 0 , & status ) = = 3 ) ;
TEST_ASSERT ( uregex_end ( re , 0 , & status ) = = 5 ) ;
TEST_ASSERT_SUCCESS ( status ) ;
result = uregex_findNext ( re , & status ) ;
TEST_ASSERT ( result = = TRUE ) ;
TEST_ASSERT ( uregex_start ( re , 0 , & status ) = = 6 ) ;
TEST_ASSERT ( uregex_end ( re , 0 , & status ) = = 8 ) ;
TEST_ASSERT_SUCCESS ( status ) ;
status = U_ZERO_ERROR ;
uregex_reset ( re , 12 , & status ) ;
result = uregex_findNext ( re , & status ) ;
TEST_ASSERT ( result = = TRUE ) ;
TEST_ASSERT ( uregex_start ( re , 0 , & status ) = = 13 ) ;
TEST_ASSERT ( uregex_end ( re , 0 , & status ) = = 15 ) ;
TEST_ASSERT_SUCCESS ( status ) ;
result = uregex_findNext ( re , & status ) ;
TEST_ASSERT ( result = = FALSE ) ;
TEST_ASSERT_SUCCESS ( status ) ;
uregex_close ( re ) ;
}
/*
* group ( )
*/
{
UChar text1 [ 80 ] ;
UText * actual ;
UBool result ;
2010-03-03 01:47:00 +00:00
const char str_abcinteriordef [ ] = { 0x61 , 0x62 , 0x63 , 0x20 , 0x69 , 0x6e , 0x74 , 0x65 , 0x72 , 0x69 , 0x6f , 0x72 , 0x20 , 0x64 , 0x65 , 0x66 , 0x00 } ; /* abc interior def */
const char str_interior [ ] = { 0x20 , 0x69 , 0x6e , 0x74 , 0x65 , 0x72 , 0x69 , 0x6f , 0x72 , 0x20 , 0x00 } ; /* ' interior ' */
2010-02-03 02:59:35 +00:00
u_uastrncpy ( text1 , " noise abc interior def, and this is off the end " , sizeof ( text1 ) / 2 ) ;
status = U_ZERO_ERROR ;
re = uregex_openC ( " abc(.*?)def " , 0 , NULL , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
uregex_setText ( re , text1 , - 1 , & status ) ;
result = uregex_find ( re , 0 , & status ) ;
TEST_ASSERT ( result = = TRUE ) ;
/* Capture Group 0, the full match. Should succeed. */
status = U_ZERO_ERROR ;
2010-09-18 03:07:17 +00:00
actual = uregex_groupUTextDeep ( re , 0 , NULL , & status ) ;
2010-02-03 02:59:35 +00:00
TEST_ASSERT_SUCCESS ( status ) ;
2010-03-03 01:47:00 +00:00
TEST_ASSERT_UTEXT ( str_abcinteriordef , actual ) ;
2010-02-03 02:59:35 +00:00
utext_close ( actual ) ;
2010-09-18 03:07:17 +00:00
/* Capture Group 0 with shallow clone API. Should succeed. */
status = U_ZERO_ERROR ;
{
int64_t group_len ;
int32_t len16 ;
UErrorCode shallowStatus = U_ZERO_ERROR ;
int64_t nativeIndex ;
2010-09-21 23:06:16 +00:00
UChar * groupChars ;
UText groupText = UTEXT_INITIALIZER ;
2010-09-18 03:07:17 +00:00
actual = uregex_groupUText ( re , 0 , NULL , & group_len , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
nativeIndex = utext_getNativeIndex ( actual ) ;
/* Following returns U_INDEX_OUTOFBOUNDS_ERROR... looks like a bug in ucstrFuncs UTextFuncs [utext.cpp] */
/* len16 = utext_extract(actual, nativeIndex, nativeIndex + group_len, NULL, 0, &shallowStatus); */
2011-06-10 18:56:08 +00:00
len16 = ( int32_t ) group_len ;
2010-09-18 03:07:17 +00:00
2010-09-21 23:06:16 +00:00
groupChars = ( UChar * ) malloc ( sizeof ( UChar ) * ( len16 + 1 ) ) ;
2010-09-18 03:07:17 +00:00
utext_extract ( actual , nativeIndex , nativeIndex + group_len , groupChars , len16 + 1 , & shallowStatus ) ;
2010-09-21 23:06:16 +00:00
2010-09-18 03:07:17 +00:00
utext_openUChars ( & groupText , groupChars , len16 , & shallowStatus ) ;
TEST_ASSERT_UTEXT ( str_abcinteriordef , & groupText ) ;
utext_close ( & groupText ) ;
2010-09-27 05:51:41 +00:00
free ( groupChars ) ;
2010-09-18 03:07:17 +00:00
}
utext_close ( actual ) ;
2010-02-03 02:59:35 +00:00
/* Capture group #1. Should succeed. */
status = U_ZERO_ERROR ;
2010-09-18 03:07:17 +00:00
actual = uregex_groupUTextDeep ( re , 1 , NULL , & status ) ;
2010-02-03 02:59:35 +00:00
TEST_ASSERT_SUCCESS ( status ) ;
2010-03-03 01:47:00 +00:00
TEST_ASSERT_UTEXT ( str_interior , actual ) ;
2010-02-03 02:59:35 +00:00
utext_close ( actual ) ;
/* Capture group out of range. Error. */
status = U_ZERO_ERROR ;
2010-09-18 03:07:17 +00:00
actual = uregex_groupUTextDeep ( re , 2 , NULL , & status ) ;
2010-02-03 02:59:35 +00:00
TEST_ASSERT ( status = = U_INDEX_OUTOFBOUNDS_ERROR ) ;
TEST_ASSERT ( utext_nativeLength ( actual ) = = 0 ) ;
utext_close ( actual ) ;
uregex_close ( re ) ;
}
/*
* replaceFirst ( )
*/
{
UChar text1 [ 80 ] ;
UChar text2 [ 80 ] ;
UText replText = UTEXT_INITIALIZER ;
UText * result ;
2010-03-03 01:47:00 +00:00
const char str_Replxxx [ ] = { 0x52 , 0x65 , 0x70 , 0x6c , 0x61 , 0x63 , 0x65 , 0x20 , 0x3c , 0x61 , 0x61 , 0x3e , 0x20 , 0x78 , 0x31 , 0x78 , 0x20 , 0x78 , 0x2e , 0x2e , 0x2e , 0x78 , 0x2e , 0x00 } ; /* Replace <aa> x1x x...x. */
const char str_Nomatchhere [ ] = { 0x4e , 0x6f , 0x20 , 0x6d , 0x61 , 0x74 , 0x63 , 0x68 , 0x20 , 0x68 , 0x65 , 0x72 , 0x65 , 0x2e , 0x00 } ; /* No match here. */
const char str_u00411U00000042a [ ] = { 0x5c , 0x5c , 0x5c , 0x75 , 0x30 , 0x30 , 0x34 , 0x31 , 0x24 , 0x31 , 0x5c , 0x55 , 0x30 , 0x30 , 0x30 , 0x30 , 0x30 , 0x30 , 0x34 , 0x32 , 0x24 , 0x5c , 0x61 , 0x00 } ; /* \\\u0041$1\U00000042$\a */
const char str_1x [ ] = { 0x3c , 0x24 , 0x31 , 0x3e , 0x00 } ; /* <$1> */
const char str_ReplaceAaaBax1xxx [ ] = { 0x52 , 0x65 , 0x70 , 0x6c , 0x61 , 0x63 , 0x65 , 0x20 , 0x5c , 0x41 , 0x61 , 0x61 , 0x42 , 0x24 , 0x61 , 0x20 , 0x78 , 0x31 , 0x78 , 0x20 , 0x78 , 0x2e , 0x2e , 0x2e , 0x78 , 0x2e , 0x00 } ; /* Replace \AaaB$a x1x x...x. */
2010-02-03 02:59:35 +00:00
status = U_ZERO_ERROR ;
u_uastrncpy ( text1 , " Replace xaax x1x x...x. " , sizeof ( text1 ) / 2 ) ;
u_uastrncpy ( text2 , " No match here. " , sizeof ( text2 ) / 2 ) ;
2010-03-03 01:47:00 +00:00
utext_openUTF8 ( & replText , str_1x , - 1 , & status ) ;
2010-02-03 02:59:35 +00:00
re = uregex_openC ( " x(.*?)x " , 0 , NULL , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
/* Normal case, with match */
uregex_setText ( re , text1 , - 1 , & status ) ;
result = uregex_replaceFirstUText ( re , & replText , NULL , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
2010-03-03 01:47:00 +00:00
TEST_ASSERT_UTEXT ( str_Replxxx , result ) ;
2010-02-03 02:59:35 +00:00
utext_close ( result ) ;
/* No match. Text should copy to output with no changes. */
uregex_setText ( re , text2 , - 1 , & status ) ;
result = uregex_replaceFirstUText ( re , & replText , NULL , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
2010-03-03 01:47:00 +00:00
TEST_ASSERT_UTEXT ( str_Nomatchhere , result ) ;
2010-02-03 02:59:35 +00:00
utext_close ( result ) ;
/* Unicode escapes */
uregex_setText ( re , text1 , - 1 , & status ) ;
2010-03-03 01:47:00 +00:00
utext_openUTF8 ( & replText , str_u00411U00000042a , - 1 , & status ) ;
2010-02-03 02:59:35 +00:00
result = uregex_replaceFirstUText ( re , & replText , NULL , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
2010-03-03 01:47:00 +00:00
TEST_ASSERT_UTEXT ( str_ReplaceAaaBax1xxx , result ) ;
2010-02-03 02:59:35 +00:00
utext_close ( result ) ;
uregex_close ( re ) ;
utext_close ( & replText ) ;
}
/*
* replaceAll ( )
*/
{
UChar text1 [ 80 ] ;
UChar text2 [ 80 ] ;
UText replText = UTEXT_INITIALIZER ;
UText * result ;
2010-03-03 01:47:00 +00:00
const char str_1 [ ] = { 0x3c , 0x24 , 0x31 , 0x3e , 0x00 } ; /* <$1> */
const char str_Replaceaa1 [ ] = { 0x52 , 0x65 , 0x70 , 0x6c , 0x61 , 0x63 , 0x65 , 0x20 , 0x3c , 0x61 , 0x61 , 0x3e , 0x20 , 0x3c , 0x31 , 0x3e , 0x20 , 0x3c , 0x2e , 0x2e , 0x2e , 0x3e , 0x2e , 0x00 } ; /* Replace <aa> <1> <...>. */
const char str_Nomatchhere [ ] = { 0x4e , 0x6f , 0x20 , 0x6d , 0x61 , 0x74 , 0x63 , 0x68 , 0x20 , 0x68 , 0x65 , 0x72 , 0x65 , 0x2e , 0x00 } ; /* No match here. */
2010-02-03 02:59:35 +00:00
status = U_ZERO_ERROR ;
u_uastrncpy ( text1 , " Replace xaax x1x x...x. " , sizeof ( text1 ) / 2 ) ;
u_uastrncpy ( text2 , " No match here. " , sizeof ( text2 ) / 2 ) ;
2010-03-03 01:47:00 +00:00
utext_openUTF8 ( & replText , str_1 , - 1 , & status ) ;
2010-02-03 02:59:35 +00:00
re = uregex_openC ( " x(.*?)x " , 0 , NULL , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
/* Normal case, with match */
uregex_setText ( re , text1 , - 1 , & status ) ;
result = uregex_replaceAllUText ( re , & replText , NULL , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
2010-03-03 01:47:00 +00:00
TEST_ASSERT_UTEXT ( str_Replaceaa1 , result ) ;
2010-02-03 02:59:35 +00:00
utext_close ( result ) ;
/* No match. Text should copy to output with no changes. */
uregex_setText ( re , text2 , - 1 , & status ) ;
result = uregex_replaceAllUText ( re , & replText , NULL , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
2010-03-03 01:47:00 +00:00
TEST_ASSERT_UTEXT ( str_Nomatchhere , result ) ;
2010-02-03 02:59:35 +00:00
utext_close ( result ) ;
uregex_close ( re ) ;
utext_close ( & replText ) ;
}
/*
* appendReplacement ( )
*/
{
UChar text [ 100 ] ;
UChar repl [ 100 ] ;
UChar buf [ 100 ] ;
UChar * bufPtr ;
int32_t bufCap ;
status = U_ZERO_ERROR ;
re = uregex_openC ( " .* " , 0 , 0 , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
u_uastrncpy ( text , " whatever " , sizeof ( text ) / 2 ) ;
u_uastrncpy ( repl , " some other " , sizeof ( repl ) / 2 ) ;
uregex_setText ( re , text , - 1 , & status ) ;
/* match covers whole target string */
uregex_find ( re , 0 , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
bufPtr = buf ;
bufCap = sizeof ( buf ) / 2 ;
uregex_appendReplacement ( re , repl , - 1 , & bufPtr , & bufCap , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
TEST_ASSERT_STRING ( " some other " , buf , TRUE ) ;
/* Match has \u \U escapes */
uregex_find ( re , 0 , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
bufPtr = buf ;
bufCap = sizeof ( buf ) / 2 ;
u_uastrncpy ( repl , " abc \\ u0041 \\ U00000042 \\ \\ $ \\ abc " , sizeof ( repl ) / 2 ) ;
uregex_appendReplacement ( re , repl , - 1 , & bufPtr , & bufCap , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
TEST_ASSERT_STRING ( " abcAB \\ $ abc " , buf , TRUE ) ;
uregex_close ( re ) ;
}
/*
* appendReplacement ( ) , appendTail ( ) checked in replaceFirst ( ) , replaceAll ( ) .
*/
/*
* splitUText ( )
*/
{
UChar textToSplit [ 80 ] ;
UChar text2 [ 80 ] ;
UText * fields [ 10 ] ;
int32_t numFields ;
2010-02-25 19:19:53 +00:00
int32_t i ;
2010-02-03 02:59:35 +00:00
u_uastrncpy ( textToSplit , " first : second: third " , sizeof ( textToSplit ) / 2 ) ;
u_uastrncpy ( text2 , " No match here. " , sizeof ( text2 ) / 2 ) ;
status = U_ZERO_ERROR ;
re = uregex_openC ( " : " , 0 , NULL , & status ) ;
/* Simple split */
uregex_setText ( re , textToSplit , - 1 , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
/* The TEST_ASSERT_SUCCESS call above should change too... */
if ( U_SUCCESS ( status ) ) {
memset ( fields , 0 , sizeof ( fields ) ) ;
numFields = uregex_splitUText ( re , fields , 10 , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
/* The TEST_ASSERT_SUCCESS call above should change too... */
if ( U_SUCCESS ( status ) ) {
2010-03-03 01:47:00 +00:00
const char str_first [ ] = { 0x66 , 0x69 , 0x72 , 0x73 , 0x74 , 0x20 , 0x00 } ; /* 'first ' */
const char str_second [ ] = { 0x20 , 0x73 , 0x65 , 0x63 , 0x6f , 0x6e , 0x64 , 0x00 } ; /* ' second' */
const char str_third [ ] = { 0x20 , 0x20 , 0x74 , 0x68 , 0x69 , 0x72 , 0x64 , 0x00 } ; /* ' third' */
2010-02-03 02:59:35 +00:00
TEST_ASSERT ( numFields = = 3 ) ;
2010-03-03 01:47:00 +00:00
TEST_ASSERT_UTEXT ( str_first , fields [ 0 ] ) ;
TEST_ASSERT_UTEXT ( str_second , fields [ 1 ] ) ;
TEST_ASSERT_UTEXT ( str_third , fields [ 2 ] ) ;
2010-02-03 02:59:35 +00:00
TEST_ASSERT ( fields [ 3 ] = = NULL ) ;
}
2010-02-25 19:19:53 +00:00
for ( i = 0 ; i < numFields ; i + + ) {
utext_close ( fields [ i ] ) ;
}
2010-02-03 02:59:35 +00:00
}
uregex_close ( re ) ;
/* Split with too few output strings available */
status = U_ZERO_ERROR ;
re = uregex_openC ( " : " , 0 , NULL , & status ) ;
uregex_setText ( re , textToSplit , - 1 , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
/* The TEST_ASSERT_SUCCESS call above should change too... */
if ( U_SUCCESS ( status ) ) {
fields [ 0 ] = NULL ;
fields [ 1 ] = NULL ;
fields [ 2 ] = & patternText ;
numFields = uregex_splitUText ( re , fields , 2 , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
/* The TEST_ASSERT_SUCCESS call above should change too... */
if ( U_SUCCESS ( status ) ) {
2010-03-03 01:47:00 +00:00
const char str_first [ ] = { 0x66 , 0x69 , 0x72 , 0x73 , 0x74 , 0x20 , 0x00 } ; /* first */
const char str_secondthird [ ] = { 0x20 , 0x73 , 0x65 , 0x63 , 0x6f , 0x6e , 0x64 , 0x3a , 0x20 , 0x20 , 0x74 , 0x68 , 0x69 , 0x72 , 0x64 , 0x00 } ; /* second: third */
2010-02-03 02:59:35 +00:00
TEST_ASSERT ( numFields = = 2 ) ;
2010-03-03 01:47:00 +00:00
TEST_ASSERT_UTEXT ( str_first , fields [ 0 ] ) ;
TEST_ASSERT_UTEXT ( str_secondthird , fields [ 1 ] ) ;
2010-02-03 02:59:35 +00:00
TEST_ASSERT ( fields [ 2 ] = = & patternText ) ;
}
2010-02-25 19:19:53 +00:00
for ( i = 0 ; i < numFields ; i + + ) {
utext_close ( fields [ i ] ) ;
}
2010-02-03 02:59:35 +00:00
}
uregex_close ( re ) ;
}
/* splitUText(), part 2. Patterns with capture groups. The capture group text
* comes out as additional fields . */
{
UChar textToSplit [ 80 ] ;
UText * fields [ 10 ] ;
int32_t numFields ;
2010-02-25 19:19:53 +00:00
int32_t i ;
2010-02-03 02:59:35 +00:00
u_uastrncpy ( textToSplit , " first <tag-a> second<tag-b> third " , sizeof ( textToSplit ) / 2 ) ;
status = U_ZERO_ERROR ;
re = uregex_openC ( " <(.*?)> " , 0 , NULL , & status ) ;
uregex_setText ( re , textToSplit , - 1 , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
/* The TEST_ASSERT_SUCCESS call above should change too... */
if ( U_SUCCESS ( status ) ) {
memset ( fields , 0 , sizeof ( fields ) ) ;
numFields = uregex_splitUText ( re , fields , 10 , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
/* The TEST_ASSERT_SUCCESS call above should change too... */
if ( U_SUCCESS ( status ) ) {
2010-03-03 01:47:00 +00:00
const char str_first [ ] = { 0x66 , 0x69 , 0x72 , 0x73 , 0x74 , 0x20 , 0x00 } ; /* first */
const char str_taga [ ] = { 0x74 , 0x61 , 0x67 , 0x2d , 0x61 , 0x00 } ; /* tag-a */
const char str_second [ ] = { 0x20 , 0x73 , 0x65 , 0x63 , 0x6f , 0x6e , 0x64 , 0x00 } ; /* second */
const char str_tagb [ ] = { 0x74 , 0x61 , 0x67 , 0x2d , 0x62 , 0x00 } ; /* tag-b */
const char str_third [ ] = { 0x20 , 0x20 , 0x74 , 0x68 , 0x69 , 0x72 , 0x64 , 0x00 } ; /* third */
2010-02-03 02:59:35 +00:00
TEST_ASSERT ( numFields = = 5 ) ;
2010-03-03 01:47:00 +00:00
TEST_ASSERT_UTEXT ( str_first , fields [ 0 ] ) ;
TEST_ASSERT_UTEXT ( str_taga , fields [ 1 ] ) ;
TEST_ASSERT_UTEXT ( str_second , fields [ 2 ] ) ;
TEST_ASSERT_UTEXT ( str_tagb , fields [ 3 ] ) ;
TEST_ASSERT_UTEXT ( str_third , fields [ 4 ] ) ;
2010-02-03 02:59:35 +00:00
TEST_ASSERT ( fields [ 5 ] = = NULL ) ;
}
2010-02-25 19:19:53 +00:00
for ( i = 0 ; i < numFields ; i + + ) {
utext_close ( fields [ i ] ) ;
}
2010-02-03 02:59:35 +00:00
}
/* Split with too few output strings available (2) */
status = U_ZERO_ERROR ;
fields [ 0 ] = NULL ;
fields [ 1 ] = NULL ;
fields [ 2 ] = & patternText ;
numFields = uregex_splitUText ( re , fields , 2 , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
/* The TEST_ASSERT_SUCCESS call above should change too... */
if ( U_SUCCESS ( status ) ) {
2010-03-03 01:47:00 +00:00
const char str_first [ ] = { 0x66 , 0x69 , 0x72 , 0x73 , 0x74 , 0x20 , 0x00 } ; /* first */
const char str_secondtagbthird [ ] = { 0x20 , 0x73 , 0x65 , 0x63 , 0x6f , 0x6e , 0x64 , 0x3c , 0x74 , 0x61 , 0x67 , 0x2d , 0x62 , 0x3e , 0x20 , 0x20 , 0x74 , 0x68 , 0x69 , 0x72 , 0x64 , 0x00 } ; /* second<tag-b> third */
2010-02-03 02:59:35 +00:00
TEST_ASSERT ( numFields = = 2 ) ;
2010-03-03 01:47:00 +00:00
TEST_ASSERT_UTEXT ( str_first , fields [ 0 ] ) ;
TEST_ASSERT_UTEXT ( str_secondtagbthird , fields [ 1 ] ) ;
2010-02-03 02:59:35 +00:00
TEST_ASSERT ( fields [ 2 ] = = & patternText ) ;
}
2010-02-25 19:19:53 +00:00
for ( i = 0 ; i < numFields ; i + + ) {
utext_close ( fields [ i ] ) ;
}
2010-02-03 02:59:35 +00:00
/* Split with too few output strings available (3) */
status = U_ZERO_ERROR ;
fields [ 0 ] = NULL ;
fields [ 1 ] = NULL ;
fields [ 2 ] = NULL ;
fields [ 3 ] = & patternText ;
numFields = uregex_splitUText ( re , fields , 3 , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
/* The TEST_ASSERT_SUCCESS call above should change too... */
if ( U_SUCCESS ( status ) ) {
2010-03-03 01:47:00 +00:00
const char str_first [ ] = { 0x66 , 0x69 , 0x72 , 0x73 , 0x74 , 0x20 , 0x00 } ; /* first */
const char str_taga [ ] = { 0x74 , 0x61 , 0x67 , 0x2d , 0x61 , 0x00 } ; /* tag-a */
const char str_secondtagbthird [ ] = { 0x20 , 0x73 , 0x65 , 0x63 , 0x6f , 0x6e , 0x64 , 0x3c , 0x74 , 0x61 , 0x67 , 0x2d , 0x62 , 0x3e , 0x20 , 0x20 , 0x74 , 0x68 , 0x69 , 0x72 , 0x64 , 0x00 } ; /* second<tag-b> third */
2010-02-03 02:59:35 +00:00
TEST_ASSERT ( numFields = = 3 ) ;
2010-03-03 01:47:00 +00:00
TEST_ASSERT_UTEXT ( str_first , fields [ 0 ] ) ;
TEST_ASSERT_UTEXT ( str_taga , fields [ 1 ] ) ;
TEST_ASSERT_UTEXT ( str_secondtagbthird , fields [ 2 ] ) ;
2010-02-03 02:59:35 +00:00
TEST_ASSERT ( fields [ 3 ] = = & patternText ) ;
}
2010-02-25 19:19:53 +00:00
for ( i = 0 ; i < numFields ; i + + ) {
utext_close ( fields [ i ] ) ;
}
2010-02-03 02:59:35 +00:00
/* Split with just enough output strings available (5) */
status = U_ZERO_ERROR ;
fields [ 0 ] = NULL ;
fields [ 1 ] = NULL ;
fields [ 2 ] = NULL ;
fields [ 3 ] = NULL ;
fields [ 4 ] = NULL ;
fields [ 5 ] = & patternText ;
numFields = uregex_splitUText ( re , fields , 5 , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
/* The TEST_ASSERT_SUCCESS call above should change too... */
if ( U_SUCCESS ( status ) ) {
2010-03-03 01:47:00 +00:00
const char str_first [ ] = { 0x66 , 0x69 , 0x72 , 0x73 , 0x74 , 0x20 , 0x00 } ; /* first */
const char str_taga [ ] = { 0x74 , 0x61 , 0x67 , 0x2d , 0x61 , 0x00 } ; /* tag-a */
const char str_second [ ] = { 0x20 , 0x73 , 0x65 , 0x63 , 0x6f , 0x6e , 0x64 , 0x00 } ; /* second */
const char str_tagb [ ] = { 0x74 , 0x61 , 0x67 , 0x2d , 0x62 , 0x00 } ; /* tag-b */
const char str_third [ ] = { 0x20 , 0x20 , 0x74 , 0x68 , 0x69 , 0x72 , 0x64 , 0x00 } ; /* third */
2010-02-03 02:59:35 +00:00
TEST_ASSERT ( numFields = = 5 ) ;
2010-03-03 01:47:00 +00:00
TEST_ASSERT_UTEXT ( str_first , fields [ 0 ] ) ;
TEST_ASSERT_UTEXT ( str_taga , fields [ 1 ] ) ;
TEST_ASSERT_UTEXT ( str_second , fields [ 2 ] ) ;
TEST_ASSERT_UTEXT ( str_tagb , fields [ 3 ] ) ;
TEST_ASSERT_UTEXT ( str_third , fields [ 4 ] ) ;
2010-02-03 02:59:35 +00:00
TEST_ASSERT ( fields [ 5 ] = = & patternText ) ;
}
2010-02-25 19:19:53 +00:00
for ( i = 0 ; i < numFields ; i + + ) {
utext_close ( fields [ i ] ) ;
}
2010-02-03 02:59:35 +00:00
/* Split, end of text is a field delimiter. */
status = U_ZERO_ERROR ;
uregex_setText ( re , textToSplit , strlen ( " first <tag-a> second<tag-b> " ) , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
/* The TEST_ASSERT_SUCCESS call above should change too... */
if ( U_SUCCESS ( status ) ) {
memset ( fields , 0 , sizeof ( fields ) ) ;
fields [ 9 ] = & patternText ;
numFields = uregex_splitUText ( re , fields , 9 , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
/* The TEST_ASSERT_SUCCESS call above should change too... */
if ( U_SUCCESS ( status ) ) {
2010-03-03 01:47:00 +00:00
const char str_first [ ] = { 0x66 , 0x69 , 0x72 , 0x73 , 0x74 , 0x20 , 0x00 } ; /* first */
const char str_taga [ ] = { 0x74 , 0x61 , 0x67 , 0x2d , 0x61 , 0x00 } ; /* tag-a */
const char str_second [ ] = { 0x20 , 0x73 , 0x65 , 0x63 , 0x6f , 0x6e , 0x64 , 0x00 } ; /* second */
const char str_tagb [ ] = { 0x74 , 0x61 , 0x67 , 0x2d , 0x62 , 0x00 } ; /* tag-b */
2011-04-15 00:48:39 +00:00
const char str_empty [ ] = { 0x00 } ;
2010-03-03 01:47:00 +00:00
2011-04-15 00:48:39 +00:00
TEST_ASSERT ( numFields = = 5 ) ;
2010-03-03 01:47:00 +00:00
TEST_ASSERT_UTEXT ( str_first , fields [ 0 ] ) ;
TEST_ASSERT_UTEXT ( str_taga , fields [ 1 ] ) ;
TEST_ASSERT_UTEXT ( str_second , fields [ 2 ] ) ;
TEST_ASSERT_UTEXT ( str_tagb , fields [ 3 ] ) ;
2011-04-15 00:48:39 +00:00
TEST_ASSERT_UTEXT ( str_empty , fields [ 4 ] ) ;
TEST_ASSERT ( fields [ 5 ] = = NULL ) ;
2010-02-03 02:59:35 +00:00
TEST_ASSERT ( fields [ 8 ] = = NULL ) ;
TEST_ASSERT ( fields [ 9 ] = = & patternText ) ;
}
2010-02-25 19:19:53 +00:00
for ( i = 0 ; i < numFields ; i + + ) {
utext_close ( fields [ i ] ) ;
}
2010-02-03 02:59:35 +00:00
}
uregex_close ( re ) ;
}
2010-02-25 19:19:53 +00:00
utext_close ( & patternText ) ;
2010-02-03 02:59:35 +00:00
}
2011-01-27 01:12:12 +00:00
static void TestRefreshInput ( void ) {
/*
* RefreshInput changes out the input of a URegularExpression without
* changing anything else in the match state . Used with Java JNI ,
* when Java moves the underlying string storage . This test
* runs a find ( ) loop , moving the text after the first match .
* The right number of matches should still be found .
*/
UChar testStr [ ] = { 0x41 , 0x20 , 0x42 , 0x20 , 0x43 , 0x0 } ; /* = "A B C" */
UChar movedStr [ ] = { 0 , 0 , 0 , 0 , 0 , 0 } ;
UErrorCode status = U_ZERO_ERROR ;
URegularExpression * re ;
UText ut1 = UTEXT_INITIALIZER ;
UText ut2 = UTEXT_INITIALIZER ;
re = uregex_openC ( " [ABC] " , 0 , 0 , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
utext_openUChars ( & ut1 , testStr , - 1 , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
uregex_setUText ( re , & ut1 , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
/* Find the first match "A" in the original string */
TEST_ASSERT ( uregex_findNext ( re , & status ) ) ;
TEST_ASSERT ( uregex_start ( re , 0 , & status ) = = 0 ) ;
/* Move the string, kill the original string. */
u_strcpy ( movedStr , testStr ) ;
u_memset ( testStr , 0 , u_strlen ( testStr ) ) ;
utext_openUChars ( & ut2 , movedStr , - 1 , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
uregex_refreshUText ( re , & ut2 , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
/* Find the following two matches, now working in the moved string. */
TEST_ASSERT ( uregex_findNext ( re , & status ) ) ;
TEST_ASSERT ( uregex_start ( re , 0 , & status ) = = 2 ) ;
TEST_ASSERT ( uregex_findNext ( re , & status ) ) ;
TEST_ASSERT ( uregex_start ( re , 0 , & status ) = = 4 ) ;
TEST_ASSERT ( FALSE = = uregex_findNext ( re , & status ) ) ;
uregex_close ( re ) ;
}
2011-03-31 18:33:28 +00:00
static void TestBug8421 ( void ) {
/* Bug 8421: setTimeLimit on a regular expresssion before setting text to be matched
* was failing .
*/
URegularExpression * re ;
UErrorCode status = U_ZERO_ERROR ;
int32_t limit = - 1 ;
re = uregex_openC ( " abc " , 0 , 0 , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
limit = uregex_getTimeLimit ( re , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
TEST_ASSERT ( limit = = 0 ) ;
uregex_setTimeLimit ( re , 100 , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
limit = uregex_getTimeLimit ( re , & status ) ;
TEST_ASSERT_SUCCESS ( status ) ;
TEST_ASSERT ( limit = = 100 ) ;
uregex_close ( re ) ;
}
2004-03-22 22:16:21 +00:00
# endif /* !UCONFIG_NO_REGULAR_EXPRESSIONS */