UnicodeSet& UnicodeSet::applyPattern(const UnicodeString& pattern,
ParsePosition& pos,
uint32_t options,
const SymbolTable* symbols,
UErrorCode& status) {
if (U_FAILURE(status)) {
return *this;
}
if (isFrozen()) {
status = U_NO_WRITE_PERMISSION;
return *this;
}
// Need to build the pattern in a temporary string because
// _applyPattern calls add() etc., which set pat to empty.
UnicodeString rebuiltPat;
RuleCharacterIterator chars(pattern, symbols, pos);
applyPattern(chars, symbols, rebuiltPat, options, &UnicodeSet::closeOver, status);
if (U_FAILURE(status)) return *this;
if (chars.inVariable()) {
// syntaxError(chars, "Extra chars in variable value");
status = U_MALFORMED_SET;
return *this;
}
setPattern(rebuiltPat);
return *this;
}
void
ChoiceFormat::applyPattern(const UnicodeString& pattern,
UErrorCode& status)
{
UParseError parseError;
applyPattern(pattern, parseError, status);
}
ChoiceFormat::ChoiceFormat(const UnicodeString& newPattern,
UErrorCode& status)
: constructorErrorCode(status),
msgPattern(status)
{
applyPattern(newPattern, status);
}
U_NAMESPACE_BEGIN
// TODO memory debugging provided inside uniset.cpp
// could be made available here but probably obsolete with use of modern
// memory leak checker tools
#define _dbgct(me)
//----------------------------------------------------------------
// Constructors &c
//----------------------------------------------------------------
UnicodeSet::UnicodeSet(const UnicodeString& pattern,
uint32_t options,
const SymbolTable* symbols,
UErrorCode& status) :
len(0), capacity(START_EXTRA), list(0), bmpSet(0), buffer(0),
bufferCapacity(0), patLen(0), pat(NULL), strings(NULL), stringSpan(NULL),
fFlags(0)
{
if(U_SUCCESS(status)){
list = (UChar32*) uprv_malloc(sizeof(UChar32) * capacity);
/* test for NULL */
if(list == NULL) {
status = U_MEMORY_ALLOCATION_ERROR;
}else{
allocateStrings(status);
applyPattern(pattern, options, symbols, status);
}
}
_dbgct(this);
}
void
MessageFormat::applyPattern(const UnicodeString& newPattern,
UErrorCode& status)
{
UParseError parseError;
applyPattern(newPattern,parseError,status);
}
SelectFormat::SelectFormat(const UnicodeString& pat, UErrorCode& status) : parsedValuesHash(NULL) {
if (U_FAILURE(status)) {
return;
}
initHashTable(status);
applyPattern(pat, status);
}
SelectFormat::SelectFormat(const UnicodeString& pat, UErrorCode& status) {
if (U_FAILURE(status)) {
return;
}
init(status);
applyPattern(pat, status);
}
PluralFormat::PluralFormat(const UnicodeString& pat,
UErrorCode& status)
: locale(Locale::getDefault()),
msgPattern(status),
numberFormat(NULL),
offset(0) {
init(NULL, UPLURAL_TYPE_CARDINAL, status);
applyPattern(pat, status);
}
ChoiceFormat::ChoiceFormat(const UnicodeString& newPattern,
UErrorCode& status)
: fChoiceLimits(0),
fClosures(0),
fChoiceFormats(0),
fCount(0)
{
applyPattern(newPattern, status);
}
PluralFormat::PluralFormat(const Locale& loc,
const PluralRules& rules,
const UnicodeString& pat,
UErrorCode& status)
: locale(loc),
msgPattern(status),
numberFormat(NULL),
offset(0) {
init(&rules, UPLURAL_TYPE_COUNT, status);
applyPattern(pat, status);
}
PluralFormat::PluralFormat(const Locale& loc,
UPluralType type,
const UnicodeString& pat,
UErrorCode& status)
: locale(loc),
msgPattern(status),
numberFormat(NULL),
offset(0) {
init(NULL, type, status);
applyPattern(pat, status);
}
/**
* Constructs a set from the given pattern, optionally ignoring
* white space. See the class description for the syntax of the
* pattern language.
* @param pattern a string specifying what characters are in the set
*/
UnicodeSet::UnicodeSet(const UnicodeString& pattern,
UErrorCode& status) :
len(0), capacity(START_EXTRA), bufferCapacity(0),
list(0), buffer(0), strings(0)
{
if(U_SUCCESS(status)){
list = (UChar32*) uprv_malloc(sizeof(UChar32) * capacity);
/* test for NULL */
if(list == NULL) {
status = U_MEMORY_ALLOCATION_ERROR;
}else{
allocateStrings();
applyPattern(pattern, USET_IGNORE_SPACE, NULL, status);
}
}
_dbgct(this);
}
UnicodeSet::UnicodeSet(const UnicodeString& pattern, ParsePosition& pos,
uint32_t options,
const SymbolTable* symbols,
UErrorCode& status) :
len(0), capacity(START_EXTRA), bufferCapacity(0),
list(0), buffer(0), strings(0)
{
if(U_SUCCESS(status)){
list = (UChar32*) uprv_malloc(sizeof(UChar32) * capacity);
/* test for NULL */
if(list == NULL) {
status = U_MEMORY_ALLOCATION_ERROR;
}else{
allocateStrings();
applyPattern(pattern, pos, options, symbols, status);
}
}
_dbgct(this);
}
UnicodeSet& UnicodeSet::applyPattern(const UnicodeString& pattern,
uint32_t options,
const SymbolTable* symbols,
UErrorCode& status) {
ParsePosition pos(0);
applyPattern(pattern, pos, options, symbols, status);
if (U_FAILURE(status)) return *this;
int32_t i = pos.getIndex();
if (options & USET_IGNORE_SPACE) {
// Skip over trailing whitespace
ICU_Utility::skipWhitespace(pattern, i, TRUE);
}
if (i != pattern.length()) {
status = U_ILLEGAL_ARGUMENT_ERROR;
}
return *this;
}
MessageFormat::MessageFormat(const UnicodeString& pattern,
UErrorCode& success)
: fLocale(Locale::getDefault()), // Uses the default locale
formatAliases(NULL),
formatAliasesCapacity(0),
subformats(NULL),
subformatCount(0),
subformatCapacity(0),
argTypes(NULL),
argTypeCount(0),
argTypeCapacity(0),
defaultNumberFormat(NULL),
defaultDateFormat(NULL)
{
if (!allocateSubformats(DEFAULT_INITIAL_CAPACITY) ||
!allocateArgTypes(DEFAULT_INITIAL_CAPACITY)) {
success = U_MEMORY_ALLOCATION_ERROR;
return;
}
applyPattern(pattern, success);
setLocaleIDs(fLocale.getName(), fLocale.getName());
}
SelectFormat::SelectFormat(const UnicodeString& pat,
UErrorCode& status) : msgPattern(status) {
applyPattern(pat, status);
}
void
ChoiceFormat::setChoices(const double* limits,
const UBool* closures,
const UnicodeString* formats,
int32_t count,
UErrorCode &errorCode) {
if (U_FAILURE(errorCode)) {
return;
}
if (limits == NULL || formats == NULL) {
errorCode = U_ILLEGAL_ARGUMENT_ERROR;
return;
}
// Reconstruct the original input pattern.
// Modified version of the pre-ICU 4.8 toPattern() implementation.
UnicodeString result;
for (int32_t i = 0; i < count; ++i) {
if (i != 0) {
result += VERTICAL_BAR;
}
UnicodeString buf;
if (uprv_isPositiveInfinity(limits[i])) {
result += INFINITY;
} else if (uprv_isNegativeInfinity(limits[i])) {
result += MINUS;
result += INFINITY;
} else {
result += dtos(limits[i], buf);
}
if (closures != NULL && closures[i]) {
result += LESS_THAN;
} else {
result += LESS_EQUAL;
}
// Append formats[i], using quotes if there are special
// characters. Single quotes themselves must be escaped in
// either case.
const UnicodeString& text = formats[i];
int32_t textLength = text.length();
int32_t nestingLevel = 0;
for (int32_t j = 0; j < textLength; ++j) {
UChar c = text[j];
if (c == SINGLE_QUOTE && nestingLevel == 0) {
// Double each top-level apostrophe.
result.append(c);
} else if (c == VERTICAL_BAR && nestingLevel == 0) {
// Surround each pipe symbol with apostrophes for quoting.
// If the next character is an apostrophe, then that will be doubled,
// and although the parser will see the apostrophe pairs beginning
// and ending one character earlier than our doubling, the result
// is as desired.
// | -> '|'
// |' -> '|'''
// |'' -> '|''''' etc.
result.append(SINGLE_QUOTE).append(c).append(SINGLE_QUOTE);
continue; // Skip the append(c) at the end of the loop body.
} else if (c == LEFT_CURLY_BRACE) {
++nestingLevel;
} else if (c == RIGHT_CURLY_BRACE && nestingLevel > 0) {
--nestingLevel;
}
result.append(c);
}
}
// Apply the reconstructed pattern.
applyPattern(result, errorCode);
}
PluralFormat::PluralFormat(const PluralRules& rules, const UnicodeString& pat, UErrorCode& status) {
init(&rules, Locale::getDefault(), status);
applyPattern(pat, status);
}
PluralFormat::PluralFormat(const Locale& loc, const PluralRules& rules, const UnicodeString& pat, UErrorCode& status) {
init(&rules, loc, status);
applyPattern(pat, status);
}
/**
* Modifies this set to represent the set specified by the given
* pattern, optionally ignoring white space. See the class
* description for the syntax of the pattern language.
* @param pattern a string specifying what characters are in the set
* @param ignoreSpaces if <code>true</code>, all spaces in the
* pattern are ignored. Spaces are those characters for which
* <code>uprv_isRuleWhiteSpace()</code> is <code>true</code>.
* Characters preceded by '\\' are escaped, losing any special
* meaning they otherwise have. Spaces may be included by
* escaping them.
* @exception <code>IllegalArgumentException</code> if the pattern
* contains a syntax error.
*/
UnicodeSet& UnicodeSet::applyPattern(const UnicodeString& pattern,
UErrorCode& status) {
return applyPattern(pattern, USET_IGNORE_SPACE, NULL, status);
}
