/*
**********************************************************************
* Copyright (C) 1999-2005, International Business Machines
* Corporation and others. All Rights Reserved.
**********************************************************************
* Date Name Description
* 11/17/99 aliu Creation.
**********************************************************************
*/
#include "unicode/utypes.h"
#if !UCONFIG_NO_TRANSLITERATION
#include "unicode/putil.h"
#include "unicode/translit.h"
#include "unicode/locid.h"
#include "unicode/msgfmt.h"
#include "unicode/rep.h"
#include "unicode/resbund.h"
#include "unicode/unifilt.h"
#include "unicode/uniset.h"
#include "unicode/uscript.h"
#include "unicode/strenum.h"
#include "cpdtrans.h"
#include "nultrans.h"
#include "rbt_data.h"
#include "rbt_pars.h"
#include "rbt.h"
#include "transreg.h"
#include "name2uni.h"
#include "nortrans.h"
#include "remtrans.h"
#include "titletrn.h"
#include "tolowtrn.h"
#include "toupptrn.h"
#include "uni2name.h"
#include "esctrn.h"
#include "unesctrn.h"
#include "tridpars.h"
#include "anytrans.h"
#include "util.h"
#include "hash.h"
#include "mutex.h"
#include "ucln_in.h"
#include "uassert.h"
#include "cmemory.h"
#include "cstring.h"
#include "uinvchar.h"
static const UChar TARGET_SEP = 0x002D; /*-*/
static const UChar ID_DELIM = 0x003B; /*;*/
static const UChar VARIANT_SEP = 0x002F; // '/'
/**
* Prefix for resource bundle key for the display name for a
* transliterator. The ID is appended to this to form the key.
* The resource bundle value should be a String.
*/
static const char RB_DISPLAY_NAME_PREFIX[] = "%Translit%%";
/**
* Prefix for resource bundle key for the display name for a
* transliterator SCRIPT. The ID is appended to this to form the key.
* The resource bundle value should be a String.
*/
static const char RB_SCRIPT_DISPLAY_NAME_PREFIX[] = "%Translit%";
/**
* Resource bundle key for display name pattern.
* The resource bundle value should be a String forming a
* MessageFormat pattern, e.g.:
* "{0,choice,0#|1#{1} Transliterator|2#{1} to {2} Transliterator}".
*/
static const char RB_DISPLAY_NAME_PATTERN[] = "TransliteratorNamePattern";
/**
* Resource bundle key for the list of RuleBasedTransliterator IDs.
* The resource bundle value should be a String[] with each element
* being a valid ID. The ID will be appended to RB_RULE_BASED_PREFIX
* to obtain the class name in which the RB_RULE key will be sought.
*/
static const char RB_RULE_BASED_IDS[] = "RuleBasedTransliteratorIDs";
/**
* The mutex controlling access to registry object.
*/
static UMTX registryMutex = 0;
/**
* System transliterator registry; non-null when initialized.
*/
static TransliteratorRegistry* registry = 0;
// Macro to check/initialize the registry. ONLY USE WITHIN
// MUTEX. Avoids function call when registry is initialized.
#define HAVE_REGISTRY (registry!=0 || initializeRegistry())
// Empty string
static const UChar EMPTY[] = {0}; //""
U_NAMESPACE_BEGIN
UOBJECT_DEFINE_ABSTRACT_RTTI_IMPLEMENTATION(Transliterator)
/**
* Return TRUE if the given UTransPosition is valid for text of
* the given length.
*/
inline UBool positionIsValid(UTransPosition& index, int32_t len) {
return !(index.contextStart < 0 ||
index.start < index.contextStart ||
index.limit < index.start ||
index.contextLimit < index.limit ||
len < index.contextLimit);
}
/**
* Default constructor.
* @param theID the string identifier for this transliterator
* @param theFilter the filter. Any character for which
* filter.contains() returns FALSE will not be
* altered by this transliterator. If filter is
* null then no filtering is applied.
*/
Transliterator::Transliterator(const UnicodeString& theID,
UnicodeFilter* adoptedFilter) :
UObject(), ID(theID), filter(adoptedFilter),
maximumContextLength(0) {
// NUL-terminate the ID string
ID.getTerminatedBuffer();
}
/**
* Destructor.
*/
Transliterator::~Transliterator() {
delete filter;
}
/**
* Copy constructor.
*/
Transliterator::Transliterator(const Transliterator& other) :
UObject(other), ID(other.ID), filter(0),
maximumContextLength(other.maximumContextLength) {
// NUL-terminate the ID string
ID.getTerminatedBuffer();
if (other.filter != 0) {
// We own the filter, so we must have our own copy
filter = (UnicodeFilter*) other.filter->clone();
}
}
Transliterator* Transliterator::clone() const {
return NULL;
}
/**
* Assignment operator.
*/
Transliterator& Transliterator::operator=(const Transliterator& other) {
ID = other.ID;
// NUL-terminate the ID string
ID.getTerminatedBuffer();
maximumContextLength = other.maximumContextLength;
adoptFilter((other.filter == 0) ? 0 : (UnicodeFilter*) other.filter->clone());
return *this;
}
/**
* Transliterates a segment of a string. Transliterator
API.
* @param text the string to be transliterated
* @param start the beginning index, inclusive; 0 <= start
* <= limit
.
* @param limit the ending index, exclusive; start <= limit
* <= text.length()
.
* @return the new limit index, or -1
*/
int32_t Transliterator::transliterate(Replaceable& text,
int32_t start, int32_t limit) const {
if (start < 0 ||
limit < start ||
text.length() < limit) {
return -1;
}
UTransPosition offsets;
offsets.contextStart= start;
offsets.contextLimit = limit;
offsets.start = start;
offsets.limit = limit;
filteredTransliterate(text, offsets, FALSE, TRUE);
return offsets.limit;
}
/**
* Transliterates an entire string in place. Convenience method.
* @param text the string to be transliterated
*/
void Transliterator::transliterate(Replaceable& text) const {
transliterate(text, 0, text.length());
}
/**
* Transliterates the portion of the text buffer that can be
* transliterated unambiguosly after new text has been inserted,
* typically as a result of a keyboard event. The new text in
* insertion
will be inserted into text
* at index.contextLimit
, advancing
* index.contextLimit
by insertion.length()
.
* Then the transliterator will try to transliterate characters of
* text
between index.start
and
* index.contextLimit
. Characters before
* index.start
will not be changed.
*
*
Upon return, values in index
will be updated.
* index.contextStart
will be advanced to the first
* character that future calls to this method will read.
* index.start
and index.contextLimit
will
* be adjusted to delimit the range of text that future calls to
* this method may change.
*
*
Typical usage of this method begins with an initial call
* with index.contextStart
and index.contextLimit
* set to indicate the portion of text
to be
* transliterated, and index.start == index.contextStart
.
* Thereafter, index
can be used without
* modification in future calls, provided that all changes to
* text
are made via this method.
*
*
This method assumes that future calls may be made that will * insert new text into the buffer. As a result, it only performs * unambiguous transliterations. After the last call to this * method, there may be untransliterated text that is waiting for * more input to resolve an ambiguity. In order to perform these * pending transliterations, clients should call {@link * #finishKeyboardTransliteration} after the last call to this * method has been made. * * @param text the buffer holding transliterated and untransliterated text * @param index an array of three integers. * *
index.contextStart
: the beginning index,
* inclusive; 0 <= index.contextStart <= index.contextLimit
.
*
* index.contextLimit
: the ending index, exclusive;
* index.contextStart <= index.contextLimit <= text.length()
.
* insertion
is inserted at
* index.contextLimit
.
*
* index.start
: the next character to be
* considered for transliteration; index.contextStart <=
* index.start <= index.contextLimit
. Characters before
* index.start
will not be changed by future calls
* to this method.index.contextLimit
. If null
then no text
* is inserted.
* @see #START
* @see #LIMIT
* @see #CURSOR
* @see #handleTransliterate
* @exception IllegalArgumentException if index
* is invalid
*/
void Transliterator::transliterate(Replaceable& text,
UTransPosition& index,
const UnicodeString& insertion,
UErrorCode &status) const {
_transliterate(text, index, &insertion, status);
}
/**
* Transliterates the portion of the text buffer that can be
* transliterated unambiguosly after a new character has been
* inserted, typically as a result of a keyboard event. This is a
* convenience method; see {@link
* #transliterate(Replaceable, int[], String)} for details.
* @param text the buffer holding transliterated and
* untransliterated text
* @param index an array of three integers. See {@link
* #transliterate(Replaceable, int[], String)}.
* @param insertion text to be inserted and possibly
* transliterated into the translation buffer at
* index.contextLimit
.
* @see #transliterate(Replaceable, int[], String)
*/
void Transliterator::transliterate(Replaceable& text,
UTransPosition& index,
UChar32 insertion,
UErrorCode& status) const {
UnicodeString str(insertion);
_transliterate(text, index, &str, status);
}
/**
* Transliterates the portion of the text buffer that can be
* transliterated unambiguosly. This is a convenience method; see
* {@link #transliterate(Replaceable, int[], String)} for
* details.
* @param text the buffer holding transliterated and
* untransliterated text
* @param index an array of three integers. See {@link
* #transliterate(Replaceable, int[], String)}.
* @see #transliterate(Replaceable, int[], String)
*/
void Transliterator::transliterate(Replaceable& text,
UTransPosition& index,
UErrorCode& status) const {
_transliterate(text, index, 0, status);
}
/**
* Finishes any pending transliterations that were waiting for
* more characters. Clients should call this method as the last
* call after a sequence of one or more calls to
* transliterate()
.
* @param text the buffer holding transliterated and
* untransliterated text.
* @param index the array of indices previously passed to {@link
* #transliterate}
*/
void Transliterator::finishTransliteration(Replaceable& text,
UTransPosition& index) const {
if (!positionIsValid(index, text.length())) {
return;
}
filteredTransliterate(text, index, FALSE, TRUE);
}
/**
* This internal method does keyboard transliteration. If the
* 'insertion' is non-null then we append it to 'text' before
* proceeding. This method calls through to the pure virtual
* framework method handleTransliterate() to do the actual
* work.
*/
void Transliterator::_transliterate(Replaceable& text,
UTransPosition& index,
const UnicodeString* insertion,
UErrorCode &status) const {
if (U_FAILURE(status)) {
return;
}
if (!positionIsValid(index, text.length())) {
status = U_ILLEGAL_ARGUMENT_ERROR;
return;
}
// int32_t originalStart = index.contextStart;
if (insertion != 0) {
text.handleReplaceBetween(index.limit, index.limit, *insertion);
index.limit += insertion->length();
index.contextLimit += insertion->length();
}
if (index.limit > 0 &&
UTF_IS_LEAD(text.charAt(index.limit - 1))) {
// Oops, there is a dangling lead surrogate in the buffer.
// This will break most transliterators, since they will
// assume it is part of a pair. Don't transliterate until
// more text comes in.
return;
}
filteredTransliterate(text, index, TRUE, TRUE);
#if 0
// TODO
// I CAN'T DO what I'm attempting below now that the Kleene star
// operator is supported. For example, in the rule
// ([:Lu:]+) { x } > $1;
// what is the maximum context length? getMaximumContextLength()
// will return 1, but this is just the length of the ante context
// part of the pattern string -- 1 character, which is a standin
// for a Quantifier, which contains a StringMatcher, which
// contains a UnicodeSet.
// There is a complicated way to make this work again, and that's
// to add a "maximum left context" protocol into the
// UnicodeMatcher hierarchy. At present I'm not convinced this is
// worth it.
// ---
// The purpose of the code below is to keep the context small
// while doing incremental transliteration. When part of the left
// context (between contextStart and start) is no longer needed,
// we try to advance contextStart past that portion. We use the
// maximum context length to do so.
int32_t newCS = index.start;
int32_t n = getMaximumContextLength();
while (newCS > originalStart && n-- > 0) {
--newCS;
newCS -= UTF_CHAR_LENGTH(text.char32At(newCS)) - 1;
}
index.contextStart = uprv_max(newCS, originalStart);
#endif
}
/**
* This method breaks up the input text into runs of unfiltered
* characters. It passes each such run to
* getInstance()
, it
* will return this object, if it has been registered.
* @see #registerInstance
* @see #getAvailableIDs
*/
const UnicodeString& Transliterator::getID(void) const {
return ID;
}
/**
* Returns a name for this transliterator that is appropriate for
* display to the user in the default locale. See {@link
* #getDisplayName(Locale)} for details.
*/
UnicodeString& U_EXPORT2 Transliterator::getDisplayName(const UnicodeString& ID,
UnicodeString& result) {
return getDisplayName(ID, Locale::getDefault(), result);
}
/**
* Returns a name for this transliterator that is appropriate for
* display to the user in the given locale. This name is taken
* from the locale resource data in the standard manner of the
* java.text
package.
*
* If no localized names exist in the system resource bundles,
* a name is synthesized using a localized
* MessageFormat
pattern from the resource data. The
* arguments to this pattern are an integer followed by one or two
* strings. The integer is the number of strings, either 1 or 2.
* The strings are formed by splitting the ID for this
* transliterator at the first TARGET_SEP. If there is no TARGET_SEP, then the
* entire ID forms the only string.
* @param inLocale the Locale in which the display name should be
* localized.
* @see java.text.MessageFormat
*/
UnicodeString& U_EXPORT2 Transliterator::getDisplayName(const UnicodeString& id,
const Locale& inLocale,
UnicodeString& result) {
UErrorCode status = U_ZERO_ERROR;
ResourceBundle bundle(U_ICUDATA_TRANSLIT, inLocale, status);
// Suspend checking status until later...
result.truncate(0);
// Normalize the ID
UnicodeString source, target, variant;
UBool sawSource;
TransliteratorIDParser::IDtoSTV(id, source, target, variant, sawSource);
if (target.length() < 1) {
// No target; malformed id
return result;
}
if (variant.length() > 0) { // Change "Foo" to "/Foo"
variant.insert(0, VARIANT_SEP);
}
UnicodeString ID(source);
ID.append(TARGET_SEP).append(target).append(variant);
// build the char* key
if (uprv_isInvariantUString(ID.getBuffer(), ID.length())) {
char key[200];
uprv_strcpy(key, RB_DISPLAY_NAME_PREFIX);
int32_t length=(int32_t)uprv_strlen(RB_DISPLAY_NAME_PREFIX);
ID.extract(0, (int32_t)(sizeof(key)-length), key+length, (int32_t)(sizeof(key)-length), US_INV);
// Try to retrieve a UnicodeString from the bundle.
UnicodeString resString = bundle.getStringEx(key, status);
if (U_SUCCESS(status) && resString.length() != 0) {
return result = resString; // [sic] assign & return
}
#if !UCONFIG_NO_FORMATTING
// We have failed to get a name from the locale data. This is
// typical, since most transliterators will not have localized
// name data. The next step is to retrieve the MessageFormat
// pattern from the locale data and to use it to synthesize the
// name from the ID.
status = U_ZERO_ERROR;
resString = bundle.getStringEx(RB_DISPLAY_NAME_PATTERN, status);
if (U_SUCCESS(status) && resString.length() != 0) {
MessageFormat msg(resString, inLocale, status);
// Suspend checking status until later...
// We pass either 2 or 3 Formattable objects to msg.
Formattable args[3];
int32_t nargs;
args[0].setLong(2); // # of args to follow
args[1].setString(source);
args[2].setString(target);
nargs = 3;
// Use display names for the scripts, if they exist
UnicodeString s;
length=(int32_t)uprv_strlen(RB_SCRIPT_DISPLAY_NAME_PREFIX);
for (int j=1; j<=2; ++j) {
status = U_ZERO_ERROR;
uprv_strcpy(key, RB_SCRIPT_DISPLAY_NAME_PREFIX);
args[j].getString(s);
if (uprv_isInvariantUString(s.getBuffer(), s.length())) {
s.extract(0, sizeof(key)-length-1, key+length, (int32_t)sizeof(key)-length-1, US_INV);
resString = bundle.getStringEx(key, status);
if (U_SUCCESS(status)) {
args[j] = resString;
}
}
}
status = U_ZERO_ERROR;
FieldPosition pos; // ignored by msg
msg.format(args, nargs, result, pos, status);
if (U_SUCCESS(status)) {
result.append(variant);
return result;
}
}
#endif
}
// We should not reach this point unless there is something
// wrong with the build or the RB_DISPLAY_NAME_PATTERN has
// been deleted from the root RB_LOCALE_ELEMENTS resource.
result = ID;
return result;
}
/**
* Returns the filter used by this transliterator, or null
* if this transliterator uses no filter. Caller musn't delete
* the result!
*/
const UnicodeFilter* Transliterator::getFilter(void) const {
return filter;
}
/**
* Returns the filter used by this transliterator, or
* NULL if this transliterator uses no filter. The
* caller must eventually delete the result. After this call,
* this transliterator's filter is set to NULL.
*/
UnicodeFilter* Transliterator::orphanFilter(void) {
UnicodeFilter *result = filter;
filter = NULL;
return result;
}
/**
* Changes the filter used by this transliterator. If the filter
* is set to null then no filtering will occur.
*
*
Callers must take care if a transliterator is in use by
* multiple threads. The filter should not be changed by one
* thread while another thread may be transliterating.
*/
void Transliterator::adoptFilter(UnicodeFilter* filterToAdopt) {
delete filter;
filter = filterToAdopt;
}
/**
* Returns this transliterator's inverse. See the class
* documentation for details. This implementation simply inverts
* the two entities in the ID and attempts to retrieve the
* resulting transliterator. That is, if getID()
* returns "A-B", then this method will return the result of
* getInstance("B-A")
, or null
if that
* call fails.
*
*
This method does not take filtering into account. The * returned transliterator will have no filter. * *
Subclasses with knowledge of their inverse may wish to
* override this method.
*
* @return a transliterator that is an inverse, not necessarily
* exact, of this transliterator, or null
if no such
* transliterator is registered.
* @see #registerInstance
*/
Transliterator* Transliterator::createInverse(UErrorCode& status) const {
UParseError parseError;
return Transliterator::createInstance(ID, UTRANS_REVERSE,parseError,status);
}
Transliterator* U_EXPORT2
Transliterator::createInstance(const UnicodeString& ID,
UTransDirection dir,
UErrorCode& status)
{
UParseError parseError;
return createInstance(ID, dir, parseError, status);
}
/**
* Returns a Transliterator
object given its ID.
* The ID must be either a system transliterator ID or a ID registered
* using registerInstance()
.
*
* @param ID a valid ID, as enumerated by getAvailableIDs()
* @return A Transliterator
object with the given ID
* @see #registerInstance
* @see #getAvailableIDs
* @see #getID
*/
Transliterator* U_EXPORT2
Transliterator::createInstance(const UnicodeString& ID,
UTransDirection dir,
UParseError& parseError,
UErrorCode& status)
{
if (U_FAILURE(status)) {
return 0;
}
UnicodeString canonID;
UVector list(status);
if (U_FAILURE(status)) {
return NULL;
}
UnicodeSet* globalFilter;
// TODO add code for parseError...currently unused, but
// later may be used by parsing code...
if (!TransliteratorIDParser::parseCompoundID(ID, dir, canonID, list, globalFilter)) {
status = U_INVALID_ID;
return NULL;
}
TransliteratorIDParser::instantiateList(list, status);
if (U_FAILURE(status)) {
return NULL;
}
U_ASSERT(list.size() > 0);
Transliterator* t = NULL;
if (list.size() > 1 || canonID.indexOf(ID_DELIM) >= 0) {
// [NOTE: If it's a compoundID, we instantiate a CompoundTransliterator even if it only
// has one child transliterator. This is so that toRules() will return the right thing
// (without any inactive ID), but our main ID still comes out correct. That is, if we
// instantiate "(Lower);Latin-Greek;", we want the rules to come out as "::Latin-Greek;"
// even though the ID is "(Lower);Latin-Greek;".
t = new CompoundTransliterator(list, parseError, status);
}
else {
t = (Transliterator*)list.elementAt(0);
}
t->setID(canonID);
if (globalFilter != NULL) {
t->adoptFilter(globalFilter);
}
return t;
}
/**
* Create a transliterator from a basic ID. This is an ID
* containing only the forward direction source, target, and
* variant.
* @param id a basic ID of the form S-T or S-T/V.
* @return a newly created Transliterator or null if the ID is
* invalid.
*/
Transliterator* Transliterator::createBasicInstance(const UnicodeString& id,
const UnicodeString* canon) {
UParseError pe;
UErrorCode ec = U_ZERO_ERROR;
TransliteratorAlias* alias = 0;
Transliterator* t = 0;
umtx_init(®istryMutex);
umtx_lock(®istryMutex);
if (HAVE_REGISTRY) {
t = registry->get(id, alias, ec);
}
umtx_unlock(®istryMutex);
if (U_FAILURE(ec)) {
delete t;
delete alias;
return 0;
}
// We may have not gotten a transliterator: Because we can't
// instantiate a transliterator from inside TransliteratorRegistry::
// get() (that would deadlock), we sometimes pass back an alias. This
// contains the data we need to finish the instantiation outside the
// registry mutex. The alias may, in turn, generate another alias, so
// we handle aliases in a loop. The max times through the loop is two.
// [alan]
while (alias != 0) {
U_ASSERT(t==0);
// Rule-based aliases are handled with TransliteratorAlias::
// parse(), followed by TransliteratorRegistry::reget().
// Other aliases are handled with TransliteratorAlias::create().
if (alias->isRuleBased()) {
// Step 1. parse
TransliteratorParser parser;
alias->parse(parser, pe, ec);
delete alias;
alias = 0;
// Step 2. reget
umtx_lock(®istryMutex);
if (HAVE_REGISTRY) {
t = registry->reget(id, parser, alias, ec);
}
umtx_unlock(®istryMutex);
// Step 3. Loop back around!
} else {
t = alias->create(pe, ec);
delete alias;
alias = 0;
break;
}
if (U_FAILURE(ec)) {
delete t;
delete alias;
t = NULL;
break;
}
}
if (t != NULL && canon != NULL) {
t->setID(*canon);
}
return t;
}
/**
* Returns a Transliterator
object constructed from
* the given rule string. This will be a RuleBasedTransliterator,
* if the rule string contains only rules, or a
* CompoundTransliterator, if it contains ID blocks, or a
* NullTransliterator, if it contains ID blocks which parse as
* empty for the given direction.
*/
Transliterator* U_EXPORT2
Transliterator::createFromRules(const UnicodeString& ID,
const UnicodeString& rules,
UTransDirection dir,
UParseError& parseError,
UErrorCode& status)
{
Transliterator* t = NULL;
TransliteratorParser parser;
parser.parse(rules, dir, parseError, status);
if (U_FAILURE(status)) {
return 0;
}
// NOTE: The logic here matches that in TransliteratorRegistry.
if (parser.idBlockVector->size() == 0 && parser.dataVector->size() == 0) {
t = new NullTransliterator();
}
else if (parser.idBlockVector->size() == 0 && parser.dataVector->size() == 1) {
t = new RuleBasedTransliterator(ID, (TransliterationRuleData*)parser.dataVector->orphanElementAt(0), TRUE);
}
else if (parser.idBlockVector->size() == 1 && parser.dataVector->size() == 0) {
// idBlock, no data -- this is an alias. The ID has
// been munged from reverse into forward mode, if
// necessary, so instantiate the ID in the forward
// direction.
if (parser.compoundFilter != NULL) {
UnicodeString filterPattern;
parser.compoundFilter->toPattern(filterPattern, FALSE);
t = createInstance(filterPattern + UnicodeString(ID_DELIM)
+ *((UnicodeString*)parser.idBlockVector->elementAt(0)), UTRANS_FORWARD, parseError, status);
}
else
t = createInstance(*((UnicodeString*)parser.idBlockVector->elementAt(0)), UTRANS_FORWARD, parseError, status);
if (t != NULL) {
t->setID(ID);
}
}
else {
UVector transliterators(status);
int32_t passNumber = 1;
int32_t limit = parser.idBlockVector->size();
if (parser.dataVector->size() > limit)
limit = parser.dataVector->size();
for (int32_t i = 0; i < limit; i++) {
if (i < parser.idBlockVector->size()) {
UnicodeString* idBlock = (UnicodeString*)parser.idBlockVector->elementAt(i);
if (!idBlock->isEmpty()) {
Transliterator* temp = createInstance(*idBlock, UTRANS_FORWARD, parseError, status);
if (temp != NULL && temp->getDynamicClassID() != NullTransliterator::getStaticClassID())
transliterators.addElement(temp, status);
else
delete temp;
}
}
if (!parser.dataVector->isEmpty()) {
TransliterationRuleData* data = (TransliterationRuleData*)parser.dataVector->orphanElementAt(0);
transliterators.addElement(
new RuleBasedTransliterator(UnicodeString(CompoundTransliterator::PASS_STRING) + (passNumber++),
data, TRUE), status);
}
}
t = new CompoundTransliterator(transliterators, passNumber - 1, parseError, status);
t->setID(ID);
t->adoptFilter(parser.orphanCompoundFilter());
}
return t;
}
UnicodeString& Transliterator::toRules(UnicodeString& rulesSource,
UBool escapeUnprintable) const {
// The base class implementation of toRules munges the ID into
// the correct format. That is: foo => ::foo
if (escapeUnprintable) {
rulesSource.truncate(0);
UnicodeString id = getID();
for (int32_t i=0; iTransliterator
with the system. This object must
* implement the clone() method. When
* getInstance() is called with an ID string that is
* equal to obj.getID(), then obj.clone() is
* returned.
*
* @param obj an instance of subclass of
* Transliterator
that defines clone()
* @see #getInstance
* @see #unregister
*/
void U_EXPORT2 Transliterator::registerInstance(Transliterator* adoptedPrototype) {
umtx_init(®istryMutex);
Mutex lock(®istryMutex);
if (HAVE_REGISTRY) {
_registerInstance(adoptedPrototype);
}
}
void Transliterator::_registerInstance(Transliterator* adoptedPrototype) {
registry->put(adoptedPrototype, TRUE);
}
void U_EXPORT2 Transliterator::registerAlias(const UnicodeString& aliasID,
const UnicodeString& realID) {
umtx_init(®istryMutex);
Mutex lock(®istryMutex);
if (HAVE_REGISTRY) {
_registerAlias(aliasID, realID);
}
}
void Transliterator::_registerAlias(const UnicodeString& aliasID,
const UnicodeString& realID) {
registry->put(aliasID, realID, TRUE);
}
/**
* Unregisters a transliterator or class. This may be either
* a system transliterator or a user transliterator or class.
*
* @param ID the ID of the transliterator or class
* @see #registerInstance
*/
void U_EXPORT2 Transliterator::unregister(const UnicodeString& ID) {
umtx_init(®istryMutex);
Mutex lock(®istryMutex);
if (HAVE_REGISTRY) {
registry->remove(ID);
}
}
/**
* == OBSOLETE - remove in ICU 3.4 ==
* Return the number of IDs currently registered with the system.
* To retrieve the actual IDs, call getAvailableID(i) with
* i from 0 to countAvailableIDs() - 1.
*/
int32_t U_EXPORT2 Transliterator::countAvailableIDs(void) {
umtx_init(®istryMutex);
Mutex lock(®istryMutex);
return HAVE_REGISTRY ? registry->countAvailableIDs() : 0;
}
/**
* == OBSOLETE - remove in ICU 3.4 ==
* Return the index-th available ID. index must be between 0
* and countAvailableIDs() - 1, inclusive. If index is out of
* range, the result of getAvailableID(0) is returned.
*/
const UnicodeString& U_EXPORT2 Transliterator::getAvailableID(int32_t index) {
const UnicodeString* result = NULL;
umtx_init(®istryMutex);
umtx_lock(®istryMutex);
if (HAVE_REGISTRY) {
result = ®istry->getAvailableID(index);
}
umtx_unlock(®istryMutex);
U_ASSERT(result != NULL); // fail if no registry
return *result;
}
StringEnumeration* U_EXPORT2 Transliterator::getAvailableIDs(UErrorCode& ec) {
if (U_FAILURE(ec)) return NULL;
StringEnumeration* result = NULL;
umtx_init(®istryMutex);
umtx_lock(®istryMutex);
if (HAVE_REGISTRY) {
result = registry->getAvailableIDs();
}
umtx_unlock(®istryMutex);
if (result == NULL) {
ec = U_INTERNAL_TRANSLITERATOR_ERROR;
}
return result;
}
int32_t U_EXPORT2 Transliterator::countAvailableSources(void) {
umtx_init(®istryMutex);
Mutex lock(®istryMutex);
return HAVE_REGISTRY ? _countAvailableSources() : 0;
}
UnicodeString& U_EXPORT2 Transliterator::getAvailableSource(int32_t index,
UnicodeString& result) {
umtx_init(®istryMutex);
Mutex lock(®istryMutex);
if (HAVE_REGISTRY) {
_getAvailableSource(index, result);
}
return result;
}
int32_t U_EXPORT2 Transliterator::countAvailableTargets(const UnicodeString& source) {
umtx_init(®istryMutex);
Mutex lock(®istryMutex);
return HAVE_REGISTRY ? _countAvailableTargets(source) : 0;
}
UnicodeString& U_EXPORT2 Transliterator::getAvailableTarget(int32_t index,
const UnicodeString& source,
UnicodeString& result) {
umtx_init(®istryMutex);
Mutex lock(®istryMutex);
if (HAVE_REGISTRY) {
_getAvailableTarget(index, source, result);
}
return result;
}
int32_t U_EXPORT2 Transliterator::countAvailableVariants(const UnicodeString& source,
const UnicodeString& target) {
umtx_init(®istryMutex);
Mutex lock(®istryMutex);
return HAVE_REGISTRY ? _countAvailableVariants(source, target) : 0;
}
UnicodeString& U_EXPORT2 Transliterator::getAvailableVariant(int32_t index,
const UnicodeString& source,
const UnicodeString& target,
UnicodeString& result) {
umtx_init(®istryMutex);
Mutex lock(®istryMutex);
if (HAVE_REGISTRY) {
_getAvailableVariant(index, source, target, result);
}
return result;
}
int32_t Transliterator::_countAvailableSources(void) {
return registry->countAvailableSources();
}
UnicodeString& Transliterator::_getAvailableSource(int32_t index,
UnicodeString& result) {
return registry->getAvailableSource(index, result);
}
int32_t Transliterator::_countAvailableTargets(const UnicodeString& source) {
return registry->countAvailableTargets(source);
}
UnicodeString& Transliterator::_getAvailableTarget(int32_t index,
const UnicodeString& source,
UnicodeString& result) {
return registry->getAvailableTarget(index, source, result);
}
int32_t Transliterator::_countAvailableVariants(const UnicodeString& source,
const UnicodeString& target) {
return registry->countAvailableVariants(source, target);
}
UnicodeString& Transliterator::_getAvailableVariant(int32_t index,
const UnicodeString& source,
const UnicodeString& target,
UnicodeString& result) {
return registry->getAvailableVariant(index, source, target, result);
}
#ifdef U_USE_DEPRECATED_TRANSLITERATOR_API
/**
* Method for subclasses to use to obtain a character in the given
* string, with filtering.
* @deprecated the new architecture provides filtering at the top
* level. This method will be removed Dec 31 2001.
*/
UChar Transliterator::filteredCharAt(const Replaceable& text, int32_t i) const {
UChar c;
const UnicodeFilter* localFilter = getFilter();
return (localFilter == 0) ? text.charAt(i) :
(localFilter->contains(c = text.charAt(i)) ? c : (UChar)0xFFFE);
}
#endif
/**
* If the registry is initialized, return TRUE. If not, initialize it
* and return TRUE. If the registry cannot be initialized, return
* FALSE (rare).
*
* IMPORTANT: Upon entry, registryMutex must be LOCKED. The entirely
* initialization is done with the lock held. There is NO REASON to
* unlock, since no other thread that is waiting on the registryMutex
* cannot itself proceed until the registry is initialized.
*/
UBool Transliterator::initializeRegistry() {
if (registry != 0) {
return TRUE;
}
UErrorCode status = U_ZERO_ERROR;
registry = new TransliteratorRegistry(status);
if (registry == 0 || U_FAILURE(status)) {
delete registry;
registry = 0;
return FALSE; // can't create registry, no recovery
}
/* The following code parses the index table located in
* icu/data/translit/root.txt. The index is an n x 4 table
* that follows this format:
*