555 lines
21 KiB
C++
555 lines
21 KiB
C++
/*
|
|
**********************************************************************
|
|
* Copyright (C) 1999-2001, International Business Machines
|
|
* Corporation and others. All Rights Reserved.
|
|
**********************************************************************
|
|
* Date Name Description
|
|
* 11/17/99 aliu Creation.
|
|
**********************************************************************
|
|
*/
|
|
#ifndef RBT_H
|
|
#define RBT_H
|
|
|
|
#include "unicode/translit.h"
|
|
#include "unicode/utypes.h"
|
|
#include "unicode/parseerr.h"
|
|
|
|
class TransliterationRuleData;
|
|
|
|
/**
|
|
* <code>RuleBasedTransliterator</code> is a transliterator
|
|
* that reads a set of rules in order to determine how to perform
|
|
* translations. Rule sets are stored in resource bundles indexed by
|
|
* name. Rules within a rule set are separated by semicolons (';').
|
|
* To include a literal semicolon, prefix it with a backslash ('\').
|
|
* Whitespace, as defined by <code>Character.isWhitespace()</code>,
|
|
* is ignored. If the first non-blank character on a line is '#',
|
|
* the entire line is ignored as a comment. </p>
|
|
*
|
|
* <p>Each set of rules consists of two groups, one forward, and one
|
|
* reverse. This is a convention that is not enforced; rules for one
|
|
* direction may be omitted, with the result that translations in
|
|
* that direction will not modify the source text. In addition,
|
|
* bidirectional forward-reverse rules may be specified for
|
|
* symmetrical transformations.</p>
|
|
*
|
|
* <p><b>Rule syntax</b> </p>
|
|
*
|
|
* <p>Rule statements take one of the following forms: </p>
|
|
*
|
|
* <dl>
|
|
* <dt><code>$alefmadda=\u0622;</code></dt>
|
|
* <dd><strong>Variable definition.</strong> The name on the
|
|
* left is assigned the text on the right. In this example,
|
|
* after this statement, instances of the left hand name,
|
|
* "<code>$alefmadda</code>", will be replaced by
|
|
* the Unicode character U+0622. Variable names must begin
|
|
* with a letter and consist only of letters, digits, and
|
|
* underscores. Case is significant. Duplicate names cause
|
|
* an exception to be thrown, that is, variables cannot be
|
|
* redefined. The right hand side may contain well-formed
|
|
* text of any length, including no text at all ("<code>$empty=;</code>").
|
|
* The right hand side may contain embedded <code>UnicodeSet</code>
|
|
* patterns, for example, "<code>$softvowel=[eiyEIY]</code>".</dd>
|
|
* <dd> </dd>
|
|
* <dt><code>ai>$alefmadda;</code></dt>
|
|
* <dd><strong>Forward translation rule.</strong> This rule
|
|
* states that the string on the left will be changed to the
|
|
* string on the right when performing forward
|
|
* transliteration.</dd>
|
|
* <dt> </dt>
|
|
* <dt><code>ai<$alefmadda;</code></dt>
|
|
* <dd><strong>Reverse translation rule.</strong> This rule
|
|
* states that the string on the right will be changed to
|
|
* the string on the left when performing reverse
|
|
* transliteration.</dd>
|
|
* </dl>
|
|
*
|
|
* <dl>
|
|
* <dt><code>ai<>$alefmadda;</code></dt>
|
|
* <dd><strong>Bidirectional translation rule.</strong> This
|
|
* rule states that the string on the right will be changed
|
|
* to the string on the left when performing forward
|
|
* transliteration, and vice versa when performing reverse
|
|
* transliteration.</dd>
|
|
* </dl>
|
|
*
|
|
* <p>Translation rules consist of a <em>match pattern</em> and an <em>output
|
|
* string</em>. The match pattern consists of literal characters,
|
|
* optionally preceded by context, and optionally followed by
|
|
* context. Context characters, like literal pattern characters,
|
|
* must be matched in the text being transliterated. However, unlike
|
|
* literal pattern characters, they are not replaced by the output
|
|
* text. For example, the pattern "<code>abc{def}</code>"
|
|
* indicates the characters "<code>def</code>" must be
|
|
* preceded by "<code>abc</code>" for a successful match.
|
|
* If there is a successful match, "<code>def</code>" will
|
|
* be replaced, but not "<code>abc</code>". The final '<code>}</code>'
|
|
* is optional, so "<code>abc{def</code>" is equivalent to
|
|
* "<code>abc{def}</code>". Another example is "<code>{123}456</code>"
|
|
* (or "<code>123}456</code>") in which the literal
|
|
* pattern "<code>123</code>" must be followed by "<code>456</code>".
|
|
* </p>
|
|
*
|
|
* <p>The output string of a forward or reverse rule consists of
|
|
* characters to replace the literal pattern characters. If the
|
|
* output string contains the character '<code>|</code>', this is
|
|
* taken to indicate the location of the <em>cursor</em> after
|
|
* replacement. The cursor is the point in the text at which the
|
|
* next replacement, if any, will be applied. The cursor is usually
|
|
* placed within the replacement text; however, it can actually be
|
|
* placed into the precending or following context by using the
|
|
* special character '<code>@</code>'. Examples:</p>
|
|
*
|
|
* <blockquote>
|
|
* <p><code>a {foo} z > | @ bar; # foo -> bar, move cursor
|
|
* before a<br>
|
|
* {foo} xyz > bar @@|; # foo -> bar, cursor between
|
|
* y and z</code></p>
|
|
* </blockquote>
|
|
*
|
|
* <p><b>UnicodeSet</b></p>
|
|
*
|
|
* <p><code>UnicodeSet</code> patterns may appear anywhere that
|
|
* makes sense. They may appear in variable definitions.
|
|
* Contrariwise, <code>UnicodeSet</code> patterns may themselves
|
|
* contain variable references, such as "<code>$a=[a-z];$not_a=[^$a]</code>",
|
|
* or "<code>$range=a-z;$ll=[$range]</code>".</p>
|
|
*
|
|
* <p><code>UnicodeSet</code> patterns may also be embedded directly
|
|
* into rule strings. Thus, the following two rules are equivalent:</p>
|
|
*
|
|
* <blockquote>
|
|
* <p><code>$vowel=[aeiou]; $vowel>'*'; # One way to do this<br>
|
|
* [aeiou]>'*';
|
|
* #
|
|
* Another way</code></p>
|
|
* </blockquote>
|
|
*
|
|
* <p>See {@link UnicodeSet} for more documentation and examples.</p>
|
|
*
|
|
* <p><b>Segments</b></p>
|
|
*
|
|
* <p>Segments of the input string can be matched and copied to the
|
|
* output string. This makes certain sets of rules simpler and more
|
|
* general, and makes reordering possible. For example:</p>
|
|
*
|
|
* <blockquote>
|
|
* <p><code>([a-z]) > $1 $1;
|
|
* #
|
|
* double lowercase letters<br>
|
|
* ([:Lu:]) ([:Ll:]) > $2 $1; # reverse order of Lu-Ll pairs</code></p>
|
|
* </blockquote>
|
|
*
|
|
* <p>The segment of the input string to be copied is delimited by
|
|
* "<code>(</code>" and "<code>)</code>". Up to
|
|
* nine segments may be defined. Segments may not overlap. In the
|
|
* output string, "<code>$1</code>" through "<code>$9</code>"
|
|
* represent the input string segments, in left-to-right order of
|
|
* definition.</p>
|
|
*
|
|
* <p><b>Anchors</b></p>
|
|
*
|
|
* <p>Patterns can be anchored to the beginning or the end of the text. This is done with the
|
|
* special characters '<code>^</code>' and '<code>$</code>'. For example:</p>
|
|
*
|
|
* <blockquote>
|
|
* <p><code>^ a > 'BEG_A'; # match 'a' at start of text<br>
|
|
* a > 'A'; # match other instances
|
|
* of 'a'<br>
|
|
* z $ > 'END_Z'; # match 'z' at end of text<br>
|
|
* z > 'Z'; # match other instances
|
|
* of 'z'</code></p>
|
|
* </blockquote>
|
|
*
|
|
* <p>It is also possible to match the beginning or the end of the text using a <code>UnicodeSet</code>.
|
|
* This is done by including a virtual anchor character '<code>$</code>' at the end of the
|
|
* set pattern. Although this is usually the match chafacter for the end anchor, the set will
|
|
* match either the beginning or the end of the text, depending on its placement. For
|
|
* example:</p>
|
|
*
|
|
* <blockquote>
|
|
* <p><code>$x = [a-z$]; # match 'a' through 'z' OR anchor<br>
|
|
* $x 1 > 2; # match '1' after a-z or at the start<br>
|
|
* 3 $x > 4; # match '3' before a-z or at the end</code></p>
|
|
* </blockquote>
|
|
*
|
|
* <p><b>Example</b> </p>
|
|
*
|
|
* <p>The following example rules illustrate many of the features of
|
|
* the rule language. </p>
|
|
*
|
|
* <table border="0" cellpadding="4">
|
|
* <tr>
|
|
* <td valign="top">Rule 1.</td>
|
|
* <td valign="top" nowrap><code>abc{def}>x|y</code></td>
|
|
* </tr>
|
|
* <tr>
|
|
* <td valign="top">Rule 2.</td>
|
|
* <td valign="top" nowrap><code>xyz>r</code></td>
|
|
* </tr>
|
|
* <tr>
|
|
* <td valign="top">Rule 3.</td>
|
|
* <td valign="top" nowrap><code>yz>q</code></td>
|
|
* </tr>
|
|
* </table>
|
|
*
|
|
* <p>Applying these rules to the string "<code>adefabcdefz</code>"
|
|
* yields the following results: </p>
|
|
*
|
|
* <table border="0" cellpadding="4">
|
|
* <tr>
|
|
* <td valign="top" nowrap><code>|adefabcdefz</code></td>
|
|
* <td valign="top">Initial state, no rules match. Advance
|
|
* cursor.</td>
|
|
* </tr>
|
|
* <tr>
|
|
* <td valign="top" nowrap><code>a|defabcdefz</code></td>
|
|
* <td valign="top">Still no match. Rule 1 does not match
|
|
* because the preceding context is not present.</td>
|
|
* </tr>
|
|
* <tr>
|
|
* <td valign="top" nowrap><code>ad|efabcdefz</code></td>
|
|
* <td valign="top">Still no match. Keep advancing until
|
|
* there is a match...</td>
|
|
* </tr>
|
|
* <tr>
|
|
* <td valign="top" nowrap><code>ade|fabcdefz</code></td>
|
|
* <td valign="top">...</td>
|
|
* </tr>
|
|
* <tr>
|
|
* <td valign="top" nowrap><code>adef|abcdefz</code></td>
|
|
* <td valign="top">...</td>
|
|
* </tr>
|
|
* <tr>
|
|
* <td valign="top" nowrap><code>adefa|bcdefz</code></td>
|
|
* <td valign="top">...</td>
|
|
* </tr>
|
|
* <tr>
|
|
* <td valign="top" nowrap><code>adefab|cdefz</code></td>
|
|
* <td valign="top">...</td>
|
|
* </tr>
|
|
* <tr>
|
|
* <td valign="top" nowrap><code>adefabc|defz</code></td>
|
|
* <td valign="top">Rule 1 matches; replace "<code>def</code>"
|
|
* with "<code>xy</code>" and back up the cursor
|
|
* to before the '<code>y</code>'.</td>
|
|
* </tr>
|
|
* <tr>
|
|
* <td valign="top" nowrap><code>adefabcx|yz</code></td>
|
|
* <td valign="top">Although "<code>xyz</code>" is
|
|
* present, rule 2 does not match because the cursor is
|
|
* before the '<code>y</code>', not before the '<code>x</code>'.
|
|
* Rule 3 does match. Replace "<code>yz</code>"
|
|
* with "<code>q</code>".</td>
|
|
* </tr>
|
|
* <tr>
|
|
* <td valign="top" nowrap><code>adefabcxq|</code></td>
|
|
* <td valign="top">The cursor is at the end;
|
|
* transliteration is complete.</td>
|
|
* </tr>
|
|
* </table>
|
|
*
|
|
* <p>The order of rules is significant. If multiple rules may match
|
|
* at some point, the first matching rule is applied. </p>
|
|
*
|
|
* <p>Forward and reverse rules may have an empty output string.
|
|
* Otherwise, an empty left or right hand side of any statement is a
|
|
* syntax error. </p>
|
|
*
|
|
* <p>Single quotes are used to quote any character other than a
|
|
* digit or letter. To specify a single quote itself, inside or
|
|
* outside of quotes, use two single quotes in a row. For example,
|
|
* the rule "<code>'>'>o''clock</code>" changes the
|
|
* string "<code>></code>" to the string "<code>o'clock</code>".
|
|
* </p>
|
|
*
|
|
* <p><b>Notes</b> </p>
|
|
*
|
|
* <p>While a RuleBasedTransliterator is being built, it checks that
|
|
* the rules are added in proper order. For example, if the rule
|
|
* "a>x" is followed by the rule "ab>y",
|
|
* then the second rule will throw an exception. The reason is that
|
|
* the second rule can never be triggered, since the first rule
|
|
* always matches anything it matches. In other words, the first
|
|
* rule <em>masks</em> the second rule. </p>
|
|
*
|
|
* @author Alan Liu
|
|
* @draft
|
|
*/
|
|
class U_I18N_API RuleBasedTransliterator : public Transliterator {
|
|
|
|
/**
|
|
* The data object is immutable, so we can freely share it with
|
|
* other instances of RBT, as long as we do NOT own this object.
|
|
*/
|
|
TransliterationRuleData* data;
|
|
|
|
/**
|
|
* If true, we own the data object and must delete it.
|
|
*/
|
|
UBool isDataOwned;
|
|
|
|
public:
|
|
|
|
/**
|
|
* Constructs a new transliterator from the given rules.
|
|
* @param rules rules, separated by ';'
|
|
* @param direction either FORWARD or REVERSE.
|
|
* @exception IllegalArgumentException if rules are malformed
|
|
* or direction is invalid.
|
|
* @draft
|
|
*/
|
|
RuleBasedTransliterator(const UnicodeString& id,
|
|
const UnicodeString& rules,
|
|
UTransDirection direction,
|
|
UnicodeFilter* adoptedFilter,
|
|
UParseError& parseError,
|
|
UErrorCode& status);
|
|
|
|
/**
|
|
* Constructs a new transliterator from the given rules.
|
|
* @param rules rules, separated by ';'
|
|
* @param direction either FORWARD or REVERSE.
|
|
* @exception IllegalArgumentException if rules are malformed
|
|
* or direction is invalid.
|
|
*/
|
|
RuleBasedTransliterator(const UnicodeString& id,
|
|
const UnicodeString& rules,
|
|
UTransDirection direction,
|
|
UnicodeFilter* adoptedFilter,
|
|
UErrorCode& status);
|
|
|
|
/**
|
|
* Covenience constructor with no filter.
|
|
* @draft
|
|
*/
|
|
RuleBasedTransliterator(const UnicodeString& id,
|
|
const UnicodeString& rules,
|
|
UTransDirection direction,
|
|
UErrorCode& status);
|
|
|
|
/**
|
|
* Covenience constructor with no filter and FORWARD direction.
|
|
* @draft
|
|
*/
|
|
RuleBasedTransliterator(const UnicodeString& id,
|
|
const UnicodeString& rules,
|
|
UErrorCode& status);
|
|
|
|
/**
|
|
* Covenience constructor with FORWARD direction.
|
|
* @draft
|
|
*/
|
|
RuleBasedTransliterator(const UnicodeString& id,
|
|
const UnicodeString& rules,
|
|
UnicodeFilter* adoptedFilter,
|
|
UErrorCode& status);
|
|
|
|
/**
|
|
* Covenience constructor.
|
|
* @draft
|
|
*/
|
|
RuleBasedTransliterator(const UnicodeString& id,
|
|
const TransliterationRuleData* theData,
|
|
UnicodeFilter* adoptedFilter = 0);
|
|
|
|
private:
|
|
|
|
friend Transliterator; // to access following ct
|
|
|
|
/**
|
|
* Internal constructor.
|
|
*/
|
|
RuleBasedTransliterator(const UnicodeString& id,
|
|
TransliterationRuleData* data,
|
|
UBool isDataAdopted);
|
|
|
|
public:
|
|
|
|
/**
|
|
* Copy constructor.
|
|
* @draft
|
|
*/
|
|
RuleBasedTransliterator(const RuleBasedTransliterator&);
|
|
|
|
virtual ~RuleBasedTransliterator();
|
|
|
|
/**
|
|
* Implement Transliterator API.
|
|
* @draft
|
|
*/
|
|
Transliterator* clone(void) const;
|
|
|
|
/**
|
|
* Implements {@link Transliterator#handleTransliterate}.
|
|
* @draft
|
|
*/
|
|
virtual void handleTransliterate(Replaceable& text, UTransPosition& offsets,
|
|
UBool isIncremental) const;
|
|
|
|
/**
|
|
* Return a representation of this transliterator as source rules.
|
|
* These rules will produce an equivalent transliterator if used
|
|
* to construct a new transliterator.
|
|
* @param result the string to receive the rules. Previous
|
|
* contents will be deleted.
|
|
* @param escapeUnprintable if TRUE then convert unprintable
|
|
* character to their hex escape representations, \uxxxx or
|
|
* \Uxxxxxxxx. Unprintable characters are those other than
|
|
* U+000A, U+0020..U+007E.
|
|
*/
|
|
virtual UnicodeString& toRules(UnicodeString& result,
|
|
UBool escapeUnprintable) const;
|
|
|
|
/**
|
|
* Return the class ID for this class. This is useful only for
|
|
* comparing to a return value from getDynamicClassID(). For example:
|
|
* <pre>
|
|
* . Base* polymorphic_pointer = createPolymorphicObject();
|
|
* . if (polymorphic_pointer->getDynamicClassID() ==
|
|
* . Derived::getStaticClassID()) ...
|
|
* </pre>
|
|
* @return The class ID for all objects of this class.
|
|
* @stable
|
|
*/
|
|
static UClassID getStaticClassID(void) { return (UClassID)&fgClassID; }
|
|
|
|
/**
|
|
* Returns a unique class ID <b>polymorphically</b>. This method
|
|
* is to implement a simple version of RTTI, since not all C++
|
|
* compilers support genuine RTTI. Polymorphic operator==() and
|
|
* clone() methods call this method.
|
|
*
|
|
* <p>Concrete subclasses of Transliterator that wish clients to
|
|
* be able to identify them should implement getDynamicClassID()
|
|
* and also a static method and data member:
|
|
*
|
|
* <pre>
|
|
* static UClassID getStaticClassID() { return (UClassID)&fgClassID; }
|
|
* static char fgClassID;
|
|
* </pre>
|
|
*
|
|
* Subclasses that do not implement this method will have a
|
|
* dynamic class ID of Transliterator::getStatisClassID().
|
|
*
|
|
* @return The class ID for this object. All objects of a given
|
|
* class have the same class ID. Objects of other classes have
|
|
* different class IDs.
|
|
*/
|
|
virtual UClassID getDynamicClassID(void) const { return getStaticClassID(); };
|
|
|
|
/**
|
|
* Parse error codes generated by RuleBasedTransliterator.
|
|
* See parseerr.h.
|
|
*/
|
|
enum {
|
|
PARSE_ERROR_BASE = 0x10000,
|
|
BAD_VARIABLE_DEFINITION,
|
|
MALFORMED_RULE,
|
|
MALFORMED_SET,
|
|
MALFORMED_SYMBOL_REFERENCE,
|
|
MALFORMED_UNICODE_ESCAPE,
|
|
MALFORMED_VARIABLE_DEFINITION,
|
|
MALFORMED_VARIABLE_REFERENCE,
|
|
MISMATCHED_SEGMENT_DELIMITERS,
|
|
MISPLACED_ANCHOR_START,
|
|
MISPLACED_CURSOR_OFFSET,
|
|
MISPLACED_QUANTIFIER,
|
|
MISSING_OPERATOR,
|
|
MISSING_SEGMENT_CLOSE,
|
|
MULTIPLE_ANTE_CONTEXTS,
|
|
MULTIPLE_CURSORS,
|
|
MULTIPLE_POST_CONTEXTS,
|
|
TRAILING_BACKSLASH,
|
|
UNDEFINED_SEGMENT_REFERENCE,
|
|
UNDEFINED_VARIABLE,
|
|
UNQUOTED_SPECIAL,
|
|
UNTERMINATED_QUOTE,
|
|
};
|
|
|
|
private:
|
|
|
|
/**
|
|
* Class identifier for RuleBasedTransliterator.
|
|
*/
|
|
static char fgClassID;
|
|
|
|
void _construct(const UnicodeString& rules,
|
|
UTransDirection direction,
|
|
UErrorCode& status,
|
|
UParseError* parseError = 0);
|
|
};
|
|
|
|
/**
|
|
* Constructs a new transliterator from the given rules.
|
|
* @param rules rules, separated by ';'
|
|
* @param direction either FORWARD or REVERSE.
|
|
* @exception IllegalArgumentException if rules are malformed
|
|
* or direction is invalid.
|
|
*/
|
|
inline RuleBasedTransliterator::RuleBasedTransliterator(
|
|
const UnicodeString& id,
|
|
const UnicodeString& rules,
|
|
UTransDirection direction,
|
|
UnicodeFilter* adoptedFilter,
|
|
UParseError& parseError,
|
|
UErrorCode& status) :
|
|
Transliterator(id, adoptedFilter) {
|
|
_construct(rules, direction, status, &parseError);
|
|
}
|
|
|
|
/**
|
|
* Constructs a new transliterator from the given rules.
|
|
* @param rules rules, separated by ';'
|
|
* @param direction either FORWARD or REVERSE.
|
|
* @exception IllegalArgumentException if rules are malformed
|
|
* or direction is invalid.
|
|
*/
|
|
inline RuleBasedTransliterator::RuleBasedTransliterator(
|
|
const UnicodeString& id,
|
|
const UnicodeString& rules,
|
|
UTransDirection direction,
|
|
UnicodeFilter* adoptedFilter,
|
|
UErrorCode& status) :
|
|
Transliterator(id, adoptedFilter) {
|
|
_construct(rules, direction, status);
|
|
}
|
|
|
|
/**
|
|
* Covenience constructor with no filter.
|
|
*/
|
|
inline RuleBasedTransliterator::RuleBasedTransliterator(
|
|
const UnicodeString& id,
|
|
const UnicodeString& rules,
|
|
UTransDirection direction,
|
|
UErrorCode& status) :
|
|
Transliterator(id, 0) {
|
|
_construct(rules, direction, status);
|
|
}
|
|
|
|
/**
|
|
* Covenience constructor with no filter and FORWARD direction.
|
|
*/
|
|
inline RuleBasedTransliterator::RuleBasedTransliterator(
|
|
const UnicodeString& id,
|
|
const UnicodeString& rules,
|
|
UErrorCode& status) :
|
|
Transliterator(id, 0) {
|
|
_construct(rules, UTRANS_FORWARD, status);
|
|
}
|
|
|
|
/**
|
|
* Covenience constructor with FORWARD direction.
|
|
*/
|
|
inline RuleBasedTransliterator::RuleBasedTransliterator(
|
|
const UnicodeString& id,
|
|
const UnicodeString& rules,
|
|
UnicodeFilter* adoptedFilter,
|
|
UErrorCode& status) :
|
|
Transliterator(id, adoptedFilter) {
|
|
_construct(rules, UTRANS_FORWARD, status);
|
|
}
|
|
|
|
#endif
|