ICU 77.1  77.1
All Data Structures Namespaces Files Functions Variables Typedefs Enumerations Enumerator Friends Macros Modules Pages
translit.h
Go to the documentation of this file.
1 // © 2016 and later: Unicode, Inc. and others.
2 // License & terms of use: http://www.unicode.org/copyright.html
3 /*
4 **********************************************************************
5 * Copyright (C) 1999-2014, International Business Machines
6 * Corporation and others. All Rights Reserved.
7 **********************************************************************
8 * Date Name Description
9 * 11/17/99 aliu Creation.
10 **********************************************************************
11 */
12 #ifndef TRANSLIT_H
13 #define TRANSLIT_H
14 
15 #include "unicode/utypes.h"
16 
17 #if U_SHOW_CPLUSPLUS_API
18 
24 #if !UCONFIG_NO_TRANSLITERATION
25 
26 #include "unicode/uobject.h"
27 #include "unicode/unistr.h"
28 #include "unicode/parseerr.h"
29 #include "unicode/utrans.h" // UTransPosition, UTransDirection
30 #include "unicode/strenum.h"
31 
32 U_NAMESPACE_BEGIN
33 
34 class UnicodeFilter;
35 class UnicodeSet;
36 class TransliteratorParser;
37 class NormalizationTransliterator;
38 class TransliteratorIDParser;
39 
491 
492 private:
493 
497  UnicodeString ID;
498 
505  UnicodeFilter* filter;
506 
507  int32_t maximumContextLength;
508 
509  public:
510 
516  union Token {
521  int32_t integer;
526  void* pointer;
527  };
528 
529 #ifndef U_HIDE_INTERNAL_API
535  inline static Token integerToken(int32_t);
536 
542  inline static Token pointerToken(void*);
543 #endif /* U_HIDE_INTERNAL_API */
544 
560  typedef Transliterator* (U_EXPORT2 *Factory)(const UnicodeString& ID, Token context);
561 
562 protected:
563 
573  Transliterator(const UnicodeString& ID, UnicodeFilter* adoptedFilter);
574 
580 
586 
599  const UnicodeString* canon);
600 
601  friend class TransliteratorParser; // for parseID()
602  friend class TransliteratorIDParser; // for createBasicInstance()
603  friend class TransliteratorAlias; // for setID()
604 
605 public:
606 
611  virtual ~Transliterator();
612 
627  virtual Transliterator* clone() const;
628 
644  virtual int32_t transliterate(Replaceable& text,
645  int32_t start, int32_t limit) const;
646 
652  virtual void transliterate(Replaceable& text) const;
653 
718  virtual void transliterate(Replaceable& text, UTransPosition& index,
719  const UnicodeString& insertion,
720  UErrorCode& status) const;
721 
737  virtual void transliterate(Replaceable& text, UTransPosition& index,
738  UChar32 insertion,
739  UErrorCode& status) const;
740 
753  virtual void transliterate(Replaceable& text, UTransPosition& index,
754  UErrorCode& status) const;
755 
766  virtual void finishTransliteration(Replaceable& text,
767  UTransPosition& index) const;
768 
769 private:
770 
786  void _transliterate(Replaceable& text,
787  UTransPosition& index,
788  const UnicodeString* insertion,
789  UErrorCode &status) const;
790 
791 protected:
792 
872  virtual void handleTransliterate(Replaceable& text,
873  UTransPosition& pos,
874  UBool incremental) const = 0;
875 
876 public:
888  virtual void filteredTransliterate(Replaceable& text,
889  UTransPosition& index,
890  UBool incremental) const;
891 
892 private:
893 
921  virtual void filteredTransliterate(Replaceable& text,
922  UTransPosition& index,
923  UBool incremental,
924  UBool rollback) const;
925 
926 public:
927 
941  int32_t getMaximumContextLength() const;
942 
943 protected:
944 
951  void setMaximumContextLength(int32_t maxContextLength);
952 
953 public:
954 
965  virtual const UnicodeString& getID() const;
966 
976  static UnicodeString& U_EXPORT2 getDisplayName(const UnicodeString& ID,
977  UnicodeString& result);
978 
1000  static UnicodeString& U_EXPORT2 getDisplayName(const UnicodeString& ID,
1001  const Locale& inLocale,
1002  UnicodeString& result);
1003 
1011  const UnicodeFilter* getFilter() const;
1012 
1023 
1034  void adoptFilter(UnicodeFilter* adoptedFilter);
1035 
1056 
1073  static Transliterator* U_EXPORT2 createInstance(const UnicodeString& ID,
1074  UTransDirection dir,
1075  UParseError& parseError,
1076  UErrorCode& status);
1077 
1088  static Transliterator* U_EXPORT2 createInstance(const UnicodeString& ID,
1089  UTransDirection dir,
1090  UErrorCode& status);
1091 
1109  static Transliterator* U_EXPORT2 createFromRules(const UnicodeString& ID,
1110  const UnicodeString& rules,
1111  UTransDirection dir,
1112  UParseError& parseError,
1113  UErrorCode& status);
1114 
1127  UBool escapeUnprintable) const;
1128 
1141  int32_t countElements() const;
1142 
1162  const Transliterator& getElement(int32_t index, UErrorCode& ec) const;
1163 
1180 
1195  virtual void handleGetSourceSet(UnicodeSet& result) const;
1196 
1210  virtual UnicodeSet& getTargetSet(UnicodeSet& result) const;
1211 
1212 public:
1213 
1230  static void U_EXPORT2 registerFactory(const UnicodeString& id,
1231  Factory factory,
1232  Token context);
1233 
1255  static void U_EXPORT2 registerInstance(Transliterator* adoptedObj);
1256 
1271  static void U_EXPORT2 registerAlias(const UnicodeString& aliasID,
1272  const UnicodeString& realID);
1273 
1274 protected:
1275 
1276 #ifndef U_HIDE_INTERNAL_API
1286  static void _registerFactory(const UnicodeString& id,
1287  Factory factory,
1288  Token context);
1289 
1293  static void _registerInstance(Transliterator* adoptedObj);
1294 
1298  static void _registerAlias(const UnicodeString& aliasID, const UnicodeString& realID);
1299 
1333  static void _registerSpecialInverse(const UnicodeString& target,
1334  const UnicodeString& inverseTarget,
1335  UBool bidirectional);
1336 #endif /* U_HIDE_INTERNAL_API */
1337 
1338 public:
1339 
1357  static void U_EXPORT2 unregister(const UnicodeString& ID);
1358 
1359 public:
1360 
1371 
1377  static int32_t U_EXPORT2 countAvailableSources();
1378 
1388  static UnicodeString& U_EXPORT2 getAvailableSource(int32_t index,
1389  UnicodeString& result);
1390 
1399  static int32_t U_EXPORT2 countAvailableTargets(const UnicodeString& source);
1400 
1412  static UnicodeString& U_EXPORT2 getAvailableTarget(int32_t index,
1413  const UnicodeString& source,
1414  UnicodeString& result);
1415 
1423  static int32_t U_EXPORT2 countAvailableVariants(const UnicodeString& source,
1424  const UnicodeString& target);
1425 
1439  static UnicodeString& U_EXPORT2 getAvailableVariant(int32_t index,
1440  const UnicodeString& source,
1441  const UnicodeString& target,
1442  UnicodeString& result);
1443 
1444 protected:
1445 
1446 #ifndef U_HIDE_INTERNAL_API
1451  static int32_t _countAvailableSources();
1452 
1457  static UnicodeString& _getAvailableSource(int32_t index,
1458  UnicodeString& result);
1459 
1464  static int32_t _countAvailableTargets(const UnicodeString& source);
1465 
1470  static UnicodeString& _getAvailableTarget(int32_t index,
1471  const UnicodeString& source,
1472  UnicodeString& result);
1473 
1478  static int32_t _countAvailableVariants(const UnicodeString& source,
1479  const UnicodeString& target);
1480 
1485  static UnicodeString& _getAvailableVariant(int32_t index,
1486  const UnicodeString& source,
1487  const UnicodeString& target,
1488  UnicodeString& result);
1489 #endif /* U_HIDE_INTERNAL_API */
1490 
1491 protected:
1492 
1499  void setID(const UnicodeString& id);
1500 
1501 public:
1502 
1513  static UClassID U_EXPORT2 getStaticClassID();
1514 
1530  virtual UClassID getDynamicClassID() const override = 0;
1531 
1532 private:
1533  static UBool initializeRegistry(UErrorCode &status);
1534 
1535 public:
1536 #ifndef U_HIDE_OBSOLETE_API
1544  static int32_t U_EXPORT2 countAvailableIDs();
1545 
1558  static const UnicodeString& U_EXPORT2 getAvailableID(int32_t index);
1559 #endif /* U_HIDE_OBSOLETE_API */
1560 };
1561 
1562 inline int32_t Transliterator::getMaximumContextLength() const {
1563  return maximumContextLength;
1564 }
1565 
1566 inline void Transliterator::setID(const UnicodeString& id) {
1567  ID = id;
1568  // NUL-terminate the ID string, which is a non-aliased copy.
1569  ID.append(static_cast<char16_t>(0));
1570  ID.truncate(ID.length()-1);
1571 }
1572 
1573 #ifndef U_HIDE_INTERNAL_API
1574 inline Transliterator::Token Transliterator::integerToken(int32_t i) {
1575  Token t;
1576  t.integer = i;
1577  return t;
1578 }
1579 
1580 inline Transliterator::Token Transliterator::pointerToken(void* p) {
1581  Token t;
1582  t.pointer = p;
1583  return t;
1584 }
1585 #endif /* U_HIDE_INTERNAL_API */
1586 
1587 U_NAMESPACE_END
1588 
1589 #endif /* #if !UCONFIG_NO_TRANSLITERATION */
1590 
1591 #endif /* U_SHOW_CPLUSPLUS_API */
1592 
1593 #endif
A Locale object represents a specific geographical, political, or cultural region.
Definition: locid.h:195
Replaceable is an abstract base class representing a string of characters that supports the replaceme...
Definition: rep.h:77
Base class for 'pure' C++ implementations of uenum api.
Definition: strenum.h:61
Transliterator is an abstract class that transliterates text from one format to another.
Definition: translit.h:490
static UnicodeString & getDisplayName(const UnicodeString &ID, const Locale &inLocale, UnicodeString &result)
Returns a name for this transliterator that is appropriate for display to the user in the given local...
static Transliterator * createFromRules(const UnicodeString &ID, const UnicodeString &rules, UTransDirection dir, UParseError &parseError, UErrorCode &status)
Returns a Transliterator object constructed from the given rule string.
static UnicodeString & getAvailableTarget(int32_t index, const UnicodeString &source, UnicodeString &result)
Return a registered target specifier for a given source.
virtual void transliterate(Replaceable &text) const
Transliterates an entire string in place.
UnicodeSet & getSourceSet(UnicodeSet &result) const
Returns the set of all characters that may be modified in the input text by this Transliterator.
void adoptFilter(UnicodeFilter *adoptedFilter)
Changes the filter used by this transliterator.
static UnicodeString & _getAvailableSource(int32_t index, UnicodeString &result)
Non-mutexed internal method.
Transliterator *(* Factory)(const UnicodeString &ID, Token context)
A function that creates and returns a Transliterator.
Definition: translit.h:560
virtual UnicodeString & toRules(UnicodeString &result, UBool escapeUnprintable) const
Create a rule string that can be passed to createFromRules() to recreate this transliterator.
static Transliterator * createInstance(const UnicodeString &ID, UTransDirection dir, UErrorCode &status)
Returns a Transliterator object given its ID.
static UnicodeString & _getAvailableTarget(int32_t index, const UnicodeString &source, UnicodeString &result)
Non-mutexed internal method.
static void _registerAlias(const UnicodeString &aliasID, const UnicodeString &realID)
virtual UClassID getDynamicClassID() const override=0
Returns a unique class ID polymorphically.
static UnicodeString & getAvailableSource(int32_t index, UnicodeString &result)
Return a registered source specifier.
static int32_t countAvailableIDs()
Return the number of IDs currently registered with the system.
static void unregister(const UnicodeString &ID)
Unregisters a transliterator or class.
virtual int32_t transliterate(Replaceable &text, int32_t start, int32_t limit) const
Transliterates a segment of a string, with optional filtering.
Transliterator * createInverse(UErrorCode &status) const
Returns this transliterator's inverse.
virtual void handleGetSourceSet(UnicodeSet &result) const
Framework method that returns the set of all characters that may be modified in the input text by thi...
UnicodeFilter * orphanFilter()
Returns the filter used by this transliterator, or nullptr if this transliterator uses no filter.
static Transliterator * createBasicInstance(const UnicodeString &id, const UnicodeString *canon)
Create a transliterator from a basic ID.
virtual ~Transliterator()
Destructor.
static void registerAlias(const UnicodeString &aliasID, const UnicodeString &realID)
Registers an ID string as an alias of another ID string.
static UClassID getStaticClassID()
Return the class ID for this class.
static int32_t countAvailableVariants(const UnicodeString &source, const UnicodeString &target)
Return the number of registered variant specifiers for a given source-target pair.
const Transliterator & getElement(int32_t index, UErrorCode &ec) const
Return an element that makes up this transliterator.
static const UnicodeString & getAvailableID(int32_t index)
Return the index-th available ID.
virtual void transliterate(Replaceable &text, UTransPosition &index, UErrorCode &status) const
Transliterates the portion of the text buffer that can be transliterated unambiguosly.
static int32_t _countAvailableSources()
Non-mutexed internal method.
Transliterator & operator=(const Transliterator &)
Assignment operator.
virtual void handleTransliterate(Replaceable &text, UTransPosition &pos, UBool incremental) const =0
Abstract method that concrete subclasses define to implement their transliteration algorithm.
static UnicodeString & getAvailableVariant(int32_t index, const UnicodeString &source, const UnicodeString &target, UnicodeString &result)
Return a registered variant specifier for a given source-target pair.
virtual void filteredTransliterate(Replaceable &text, UTransPosition &index, UBool incremental) const
Transliterate a substring of text, as specified by index, taking filters into account.
virtual const UnicodeString & getID() const
Returns a programmatic identifier for this transliterator.
const UnicodeFilter * getFilter() const
Returns the filter used by this transliterator, or nullptr if this transliterator uses no filter.
static void _registerSpecialInverse(const UnicodeString &target, const UnicodeString &inverseTarget, UBool bidirectional)
Register two targets as being inverses of one another.
static int32_t _countAvailableTargets(const UnicodeString &source)
Non-mutexed internal method.
virtual void transliterate(Replaceable &text, UTransPosition &index, const UnicodeString &insertion, UErrorCode &status) const
Transliterates the portion of the text buffer that can be transliterated unambiguosly after new text ...
static int32_t countAvailableTargets(const UnicodeString &source)
Return the number of registered target specifiers for a given source specifier.
Transliterator(const UnicodeString &ID, UnicodeFilter *adoptedFilter)
Default constructor.
Transliterator(const Transliterator &)
Copy constructor.
static UnicodeString & getDisplayName(const UnicodeString &ID, UnicodeString &result)
Returns a name for this transliterator that is appropriate for display to the user in the default loc...
static void registerFactory(const UnicodeString &id, Factory factory, Token context)
Registers a factory function that creates transliterators of a given ID.
void setMaximumContextLength(int32_t maxContextLength)
Method for subclasses to use to set the maximum context length.
static Transliterator * createInstance(const UnicodeString &ID, UTransDirection dir, UParseError &parseError, UErrorCode &status)
Returns a Transliterator object given its ID.
static StringEnumeration * getAvailableIDs(UErrorCode &ec)
Return a StringEnumeration over the IDs available at the time of the call, including user-registered ...
virtual UnicodeSet & getTargetSet(UnicodeSet &result) const
Returns the set of all characters that may be generated as replacement text by this transliterator.
static void _registerFactory(const UnicodeString &id, Factory factory, Token context)
static void registerInstance(Transliterator *adoptedObj)
Registers an instance obj of a subclass of Transliterator with the system.
int32_t countElements() const
Return the number of elements that make up this transliterator.
static UnicodeString & _getAvailableVariant(int32_t index, const UnicodeString &source, const UnicodeString &target, UnicodeString &result)
Non-mutexed internal method.
virtual void finishTransliteration(Replaceable &text, UTransPosition &index) const
Finishes any pending transliterations that were waiting for more characters.
static int32_t countAvailableSources()
Return the number of registered source specifiers.
virtual Transliterator * clone() const
Implements Cloneable.
virtual void transliterate(Replaceable &text, UTransPosition &index, UChar32 insertion, UErrorCode &status) const
Transliterates the portion of the text buffer that can be transliterated unambiguosly after a new cha...
static void _registerInstance(Transliterator *adoptedObj)
static int32_t _countAvailableVariants(const UnicodeString &source, const UnicodeString &target)
Non-mutexed internal method.
UObject is the common ICU "boilerplate" class.
Definition: uobject.h:223
UnicodeFilter defines a protocol for selecting a subset of the full range (U+0000 to U+10FFFF) of Uni...
Definition: unifilt.h:65
A mutable set of Unicode characters and multicharacter strings.
Definition: uniset.h:285
UnicodeString is a string class that stores Unicode characters directly and provides similar function...
Definition: unistr.h:296
UBool truncate(int32_t targetLength)
Truncate this UnicodeString to the targetLength.
Definition: unistr.h:5068
UnicodeString & append(const UnicodeString &srcText, int32_t srcStart, int32_t srcLength)
Append the characters in srcText in the range [srcStart, srcStart + srcLength) to the UnicodeString o...
Definition: unistr.h:4960
C API: Parse Error Information.
C++ API: String Enumeration.
A UParseError struct is used to returned detailed information about parsing errors.
Definition: parseerr.h:58
Position structure for utrans_transIncremental() incremental transliteration.
Definition: utrans.h:125
int32_t UChar32
Define UChar32 as a type for single Unicode code points.
Definition: umachine.h:427
int8_t UBool
The ICU boolean type, a signed-byte integer.
Definition: umachine.h:247
A context integer or pointer for a factory function, passed by value.
Definition: translit.h:516
void * pointer
This token, interpreted as a native pointer.
Definition: translit.h:526
int32_t integer
This token, interpreted as a 32-bit integer.
Definition: translit.h:521
C++ API: Unicode String.
C++ API: Common ICU base class UObject.
void * UClassID
UClassID is used to identify classes without using the compiler's RTTI.
Definition: uobject.h:96
C API: Transliterator.
UTransDirection
Direction constant indicating the direction in a transliterator, e.g., the forward or reverse rules o...
Definition: utrans.h:83
Basic definitions for ICU, for both C and C++ APIs.
UErrorCode
Standard ICU4C error code type, a substitute for exceptions.
Definition: utypes.h:430
#define U_I18N_API
Set to export library symbols from inside the i18n library, and to import them from outside.
Definition: utypes.h:316