483 lines
20 KiB
C++
483 lines
20 KiB
C++
/*
|
|
* Copyright © {1999}, International Business Machines Corporation and others. All Rights Reserved.
|
|
**********************************************************************
|
|
* Date Name Description
|
|
* 10/22/99 alan Creation.
|
|
* 11/11/99 rgillam Complete port from Java.
|
|
**********************************************************************
|
|
*/
|
|
|
|
#ifndef RBBI_H
|
|
#define RBBI_H
|
|
|
|
#include "unicode/utypes.h"
|
|
#include "unicode/brkiter.h"
|
|
#include "unicode/udata.h"
|
|
|
|
class RuleBasedBreakIteratorTables;
|
|
class BreakIterator;
|
|
|
|
/**
|
|
* <p>A subclass of BreakIterator whose behavior is specified using a list of rules.</p>
|
|
*
|
|
* <p>There are two kinds of rules, which are separated by semicolons: <i>substitutions</i>
|
|
* and <i>regular expressions.</i></p>
|
|
*
|
|
* <p>A substitution rule defines a name that can be used in place of an expression. It
|
|
* consists of a name, which is a string of characters contained in angle brackets, an equals
|
|
* sign, and an expression. (There can be no whitespace on either side of the equals sign.)
|
|
* To keep its syntactic meaning intact, the expression must be enclosed in parentheses or
|
|
* square brackets. A substitution is visible after its definition, and is filled in using
|
|
* simple textual substitution. Substitution definitions can contain other substitutions, as
|
|
* long as those substitutions have been defined first. Substitutions are generally used to
|
|
* make the regular expressions (which can get quite complex) shorted and easier to read.
|
|
* They typically define either character categories or commonly-used subexpressions.</p>
|
|
*
|
|
* <p>There is one special substitution. If the description defines a substitution
|
|
* called "<ignore>", the expression must be a [] expression, and the
|
|
* expression defines a set of characters (the "<em>ignore characters</em>") that
|
|
* will be transparent to the BreakIterator. A sequence of characters will break the
|
|
* same way it would if any ignore characters it contains are taken out. Break
|
|
* positions never occur befoer ignore characters.</p>
|
|
*
|
|
* <p>A regular expression uses a subset of the normal Unix regular-expression syntax, and
|
|
* defines a sequence of characters to be kept together. With one significant exception, the
|
|
* iterator uses a longest-possible-match algorithm when matching text to regular
|
|
* expressions. The iterator also treats descriptions containing multiple regular expressions
|
|
* as if they were ORed together (i.e., as if they were separated by |).</p>
|
|
*
|
|
* <p>The special characters recognized by the regular-expression parser are as follows:</p>
|
|
*
|
|
* <blockquote>
|
|
* <table border="1" width="100%">
|
|
* <tr>
|
|
* <td width="6%">*</td>
|
|
* <td width="94%">Specifies that the expression preceding the asterisk may occur any number
|
|
* of times (including not at all).</td>
|
|
* </tr>
|
|
* <tr>
|
|
* <td width="6%">{}</td>
|
|
* <td width="94%">Encloses a sequence of characters that is optional.</td>
|
|
* </tr>
|
|
* <tr>
|
|
* <td width="6%">()</td>
|
|
* <td width="94%">Encloses a sequence of characters. If followed by *, the sequence
|
|
* repeats. Otherwise, the parentheses are just a grouping device and a way to delimit
|
|
* the ends of expressions containing |.</td>
|
|
* </tr>
|
|
* <tr>
|
|
* <td width="6%">|</td>
|
|
* <td width="94%">Separates two alternative sequences of characters. Either one
|
|
* sequence or the other, but not both, matches this expression. The | character can
|
|
* only occur inside ().</td>
|
|
* </tr>
|
|
* <tr>
|
|
* <td width="6%">.</td>
|
|
* <td width="94%">Matches any character.</td>
|
|
* </tr>
|
|
* <tr>
|
|
* <td width="6%">*?</td>
|
|
* <td width="94%">Specifies a non-greedy asterisk. *? works the same way as *, except
|
|
* when there is overlap between the last group of characters in the expression preceding the
|
|
* * and the first group of characters following the *. When there is this kind of
|
|
* overlap, * will match the longest sequence of characters that match the expression before
|
|
* the *, and *? will match the shortest sequence of characters matching the expression
|
|
* before the *?. For example, if you have "xxyxyyyxyxyxxyxyxyy" in the text,
|
|
* "x[xy]*x" will match through to the last x (i.e., "<strong>xxyxyyyxyxyxxyxyx</strong>yy",
|
|
* but "x[xy]*?x" will only match the first two xes ("<strong>xx</strong>yxyyyxyxyxxyxyxyy").</td>
|
|
* </tr>
|
|
* <tr>
|
|
* <td width="6%">[]</td>
|
|
* <td width="94%">Specifies a group of alternative characters. A [] expression will
|
|
* match any single character that is specified in the [] expression. For more on the
|
|
* syntax of [] expressions, see below.</td>
|
|
* </tr>
|
|
* <tr>
|
|
* <td width="6%">/</td>
|
|
* <td width="94%">Specifies where the break position should go if text matches this
|
|
* expression. (e.g., "[a-z]*/[:Zs:]*1" will match if the iterator sees a run
|
|
* of letters, followed by a run of whitespace, followed by a digit, but the break position
|
|
* will actually go before the whitespace). Expressions that don't contain / put the
|
|
* break position at the end of the matching text.</td>
|
|
* </tr>
|
|
* <tr>
|
|
* <td width="6%">\</td>
|
|
* <td width="94%">Escape character. The \ itself is ignored, but causes the next
|
|
* character to be treated as literal character. This has no effect for many
|
|
* characters, but for the characters listed above, this deprives them of their special
|
|
* meaning. (There are no special escape sequences for Unicode characters, or tabs and
|
|
* newlines; these are all handled by a higher-level protocol. In a Java string,
|
|
* "\n" will be converted to a literal newline character by the time the
|
|
* regular-expression parser sees it. Of course, this means that \ sequences that are
|
|
* visible to the regexp parser must be written as \\ when inside a Java string.) All
|
|
* characters in the ASCII range except for letters, digits, and control characters are
|
|
* reserved characters to the parser and must be preceded by \ even if they currently don't
|
|
* mean anything.</td>
|
|
* </tr>
|
|
* <tr>
|
|
* <td width="6%">!</td>
|
|
* <td width="94%">If ! appears at the beginning of a regular expression, it tells the regexp
|
|
* parser that this expression specifies the backwards-iteration behavior of the iterator,
|
|
* and not its normal iteration behavior. This is generally only used in situations
|
|
* where the automatically-generated backwards-iteration brhavior doesn't produce
|
|
* satisfactory results and must be supplemented with extra client-specified rules.</td>
|
|
* </tr>
|
|
* <tr>
|
|
* <td width="6%"><em>(all others)</em></td>
|
|
* <td width="94%">All other characters are treated as literal characters, which must match
|
|
* the corresponding character(s) in the text exactly.</td>
|
|
* </tr>
|
|
* </table>
|
|
* </blockquote>
|
|
*
|
|
* <p>Within a [] expression, a number of other special characters can be used to specify
|
|
* groups of characters:</p>
|
|
*
|
|
* <blockquote>
|
|
* <table border="1" width="100%">
|
|
* <tr>
|
|
* <td width="6%">-</td>
|
|
* <td width="94%">Specifies a range of matching characters. For example
|
|
* "[a-p]" matches all lowercase Latin letters from a to p (inclusive). The -
|
|
* sign specifies ranges of continuous Unicode numeric values, not ranges of characters in a
|
|
* language's alphabetical order: "[a-z]" doesn't include capital letters, nor does
|
|
* it include accented letters such as a-umlaut.</td>
|
|
* </tr>
|
|
* <tr>
|
|
* <td width="6%">::</td>
|
|
* <td width="94%">A pair of colons containing a one- or two-letter code matches all
|
|
* characters in the corresponding Unicode category. The two-letter codes are the same
|
|
* as the two-letter codes in the Unicode database (for example, "[:Sc::Sm:]"
|
|
* matches all currency symbols and all math symbols). Specifying a one-letter code is
|
|
* the same as specifying all two-letter codes that begin with that letter (for example,
|
|
* "[:L:]" matches all letters, and is equivalent to
|
|
* "[:Lu::Ll::Lo::Lm::Lt:]"). Anything other than a valid two-letter Unicode
|
|
* category code or a single letter that begins a Unicode category code is illegal within
|
|
* colons.</td>
|
|
* </tr>
|
|
* <tr>
|
|
* <td width="6%">[]</td>
|
|
* <td width="94%">[] expressions can nest. This has no effect, except when used in
|
|
* conjunction with the ^ token.</td>
|
|
* </tr>
|
|
* <tr>
|
|
* <td width="6%">^</td>
|
|
* <td width="94%">Excludes the character (or the characters in the [] expression) following
|
|
* it from the group of characters. For example, "[a-z^p]" matches all Latin
|
|
* lowercase letters except p. "[:L:^[\u4e00-\u9fff]]" matches all letters
|
|
* except the Han ideographs.</td>
|
|
* </tr>
|
|
* <tr>
|
|
* <td width="6%"><em>(all others)</em></td>
|
|
* <td width="94%">All other characters are treated as literal characters. (For
|
|
* example, "[aeiou]" specifies just the letters a, e, i, o, and u.)</td>
|
|
* </tr>
|
|
* </table>
|
|
* </blockquote>
|
|
*
|
|
* <p>For a more complete explanation, see <a
|
|
* href="http://www.ibm.com/java/education/boundaries/boundaries.html">http://www.ibm.com/java/education/boundaries/boundaries.html</a>.
|
|
* For examples, see the resource data (which is annotated).</p>
|
|
*
|
|
* @author Richard Gillam
|
|
*/
|
|
class U_I18N_API RuleBasedBreakIterator : public BreakIterator {
|
|
|
|
public:
|
|
/**
|
|
* A token used as a character-category value to identify ignore characters
|
|
*/
|
|
static int8_t IGNORE;
|
|
|
|
private:
|
|
/**
|
|
* The state number of the starting state
|
|
*/
|
|
static int16_t START_STATE;
|
|
|
|
/**
|
|
* The state-transition value indicating "stop"
|
|
*/
|
|
static int16_t STOP_STATE;
|
|
|
|
protected:
|
|
/**
|
|
* The character iterator through which this BreakIterator accesses the text
|
|
*/
|
|
CharacterIterator* text;
|
|
|
|
/**
|
|
* The data tables this iterator uses to determine the break positions
|
|
*/
|
|
RuleBasedBreakIteratorTables* tables;
|
|
|
|
private:
|
|
/**
|
|
* Class ID
|
|
*/
|
|
static char fgClassID;
|
|
/*
|
|
* HSYS: To be revisited, once the ctor are made public.
|
|
*/
|
|
protected:
|
|
//=======================================================================
|
|
// constructors
|
|
//=======================================================================
|
|
|
|
// This constructor uses the udata interface to create a BreakIterator whose
|
|
// internal tables live in a memory-mapped file. "image" is a pointer to the
|
|
// beginning of that file.
|
|
RuleBasedBreakIterator(UDataMemory* image);
|
|
|
|
public:
|
|
/**
|
|
* Copy constructor. Will produce a collator with the same behavior,
|
|
* and which iterates over the same text, as the one passed in.
|
|
*/
|
|
RuleBasedBreakIterator(const RuleBasedBreakIterator& that);
|
|
|
|
//=======================================================================
|
|
// boilerplate
|
|
//=======================================================================
|
|
|
|
/**
|
|
* Destructor
|
|
*/
|
|
virtual ~RuleBasedBreakIterator();
|
|
|
|
/**
|
|
* Assignment operator. Sets this iterator to have the same behavior,
|
|
* and iterate over the same text, as the one passed in.
|
|
*/
|
|
RuleBasedBreakIterator& operator=(const RuleBasedBreakIterator& that);
|
|
|
|
/**
|
|
* Equality operator. Returns TRUE if both BreakIterators are of the
|
|
* same class, have the same behavior, and iterate over the same text.
|
|
*/
|
|
virtual UBool operator==(const BreakIterator& that) const;
|
|
|
|
/**
|
|
* Not-equal operator. If operator== returns TRUE, this returns FALSE,
|
|
* and vice versa.
|
|
*/
|
|
UBool operator!=(const BreakIterator& that) const;
|
|
|
|
/**
|
|
* Returns a newly-constructed RuleBasedBreakIterator with the same
|
|
* behavior, and iterating over the same text, as this one.
|
|
*/
|
|
virtual BreakIterator* clone(void) const;
|
|
|
|
/**
|
|
* Compute a hash code for this BreakIterator
|
|
* @return A hash code
|
|
*/
|
|
virtual int32_t hashCode(void) const;
|
|
|
|
/**
|
|
* Returns the description used to create this iterator
|
|
*/
|
|
virtual const UnicodeString& getRules(void) const;
|
|
|
|
//=======================================================================
|
|
// BreakIterator overrides
|
|
//=======================================================================
|
|
|
|
/**
|
|
* Return a CharacterIterator over the text being analyzed. This version
|
|
* of this method returns the actual CharacterIterator we're using internally.
|
|
* Changing the state of this iterator can have undefined consequences. If
|
|
* you need to change it, clone it first.
|
|
* @return An iterator over the text being analyzed.
|
|
*/
|
|
virtual const CharacterIterator& getText(void) const;
|
|
|
|
/**
|
|
* Returns a newly-created CharacterIterator that the caller is to take
|
|
* ownership of.
|
|
* @deprecated This will be removed after 2000-Dec-31.
|
|
* THIS FUNCTION SHOULD NOT BE HERE. IT'S HERE BECAUSE BreakIterator DEFINES
|
|
* IT AS PURE VIRTUAL, FORCING RBBI TO IMPLEMENT IT. IT SHOULD BE REMOVED
|
|
* FROM *BOTH* CLASSES. Use getText() instead.
|
|
*/
|
|
virtual CharacterIterator* createText(void) const;
|
|
|
|
/**
|
|
* Set the iterator to analyze a new piece of text. This function resets
|
|
* the current iteration position to the beginning of the text.
|
|
* @param newText An iterator over the text to analyze. The BreakIterator
|
|
* takes ownership of the character iterator. The caller MUST NOT delete it!
|
|
*/
|
|
virtual void adoptText(CharacterIterator* newText);
|
|
|
|
/**
|
|
* Set the iterator to analyze a new piece of text. This function resets
|
|
* the current iteration position to the beginning of the text.
|
|
* @param newText The text to analyze.
|
|
*/
|
|
virtual void setText(const UnicodeString& newText);
|
|
|
|
/**
|
|
* Set the iterator to analyze a new piece of text. This function resets
|
|
* the current iteration position to the beginning of the text.
|
|
* @param newText The text to analyze.
|
|
* @deprecated
|
|
* THIS FUNCTION SHOULD NOT BE HERE. IT'S HERE BECAUSE BreakIterator DEFINES
|
|
* IT AS PURE VIRTUAL, FORCING RBBI TO IMPLEMENT IT. IT SHOULD BE REMOVED
|
|
* FROM *BOTH* CLASSES. Use the other setText() instead.
|
|
*/
|
|
virtual void setText(const UnicodeString* newText);
|
|
|
|
/**
|
|
* Sets the current iteration position to the beginning of the text.
|
|
* (i.e., the CharacterIterator's starting offset).
|
|
* @return The offset of the beginning of the text.
|
|
*/
|
|
virtual int32_t first(void);
|
|
|
|
/**
|
|
* Sets the current iteration position to the end of the text.
|
|
* (i.e., the CharacterIterator's ending offset).
|
|
* @return The text's past-the-end offset.
|
|
*/
|
|
virtual int32_t last(void);
|
|
|
|
/**
|
|
* Advances the iterator either forward or backward the specified number of steps.
|
|
* Negative values move backward, and positive values move forward. This is
|
|
* equivalent to repeatedly calling next() or previous().
|
|
* @param n The number of steps to move. The sign indicates the direction
|
|
* (negative is backwards, and positive is forwards).
|
|
* @return The character offset of the boundary position n boundaries away from
|
|
* the current one.
|
|
*/
|
|
virtual int32_t next(int32_t n);
|
|
|
|
/**
|
|
* Advances the iterator to the next boundary position.
|
|
* @return The position of the first boundary after this one.
|
|
*/
|
|
virtual int32_t next(void);
|
|
|
|
/**
|
|
* Advances the iterator backwards, to the last boundary preceding this one.
|
|
* @return The position of the last boundary position preceding this one.
|
|
*/
|
|
virtual int32_t previous(void);
|
|
|
|
/**
|
|
* Sets the iterator to refer to the first boundary position following
|
|
* the specified position.
|
|
* @offset The position from which to begin searching for a break position.
|
|
* @return The position of the first break after the current position.
|
|
*/
|
|
virtual int32_t following(int32_t offset);
|
|
|
|
/**
|
|
* Sets the iterator to refer to the last boundary position before the
|
|
* specified position.
|
|
* @offset The position to begin searching for a break from.
|
|
* @return The position of the last boundary before the starting position.
|
|
*/
|
|
virtual int32_t preceding(int32_t offset);
|
|
|
|
/**
|
|
* Returns true if the specfied position is a boundary position. As a side
|
|
* effect, leaves the iterator pointing to the first boundary position at
|
|
* or after "offset".
|
|
* @param offset the offset to check.
|
|
* @return True if "offset" is a boundary position.
|
|
*/
|
|
virtual UBool isBoundary(int32_t offset);
|
|
|
|
/**
|
|
* Returns the current iteration position.
|
|
* @return The current iteration position.
|
|
*/
|
|
virtual int32_t current(void) const;
|
|
|
|
/**
|
|
* Returns a unique class ID POLYMORPHICALLY. Pure virtual override.
|
|
* 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.
|
|
*
|
|
* @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.
|
|
*/
|
|
inline virtual UClassID getDynamicClassID(void) const;
|
|
|
|
/**
|
|
* Returns the class ID for this class. This is useful only for
|
|
* comparing to a return value from getDynamicClassID(). For example:
|
|
*
|
|
* Base* polymorphic_pointer = createPolymorphicObject();
|
|
* if (polymorphic_pointer->getDynamicClassID() ==
|
|
* Derived::getStaticClassID()) ...
|
|
*
|
|
* @return The class ID for all objects of this class.
|
|
*/
|
|
inline static UClassID getStaticClassID(void);
|
|
|
|
virtual BreakIterator * createBufferClone(void *stackBuffer,
|
|
int32_t &BufferSize,
|
|
UErrorCode &status);
|
|
|
|
|
|
protected:
|
|
//=======================================================================
|
|
// implementation
|
|
//=======================================================================
|
|
/**
|
|
* This method is the actual implementation of the next() method. All iteration
|
|
* vectors through here. This method initializes the state machine to state 1
|
|
* and advances through the text character by character until we reach the end
|
|
* of the text or the state machine transitions to state 0. We update our return
|
|
* value every time the state machine passes through a possible end state.
|
|
*/
|
|
virtual int32_t handleNext(void);
|
|
|
|
/**
|
|
* This method backs the iterator back up to a "safe position" in the text.
|
|
* This is a position that we know, without any context, must be a break position.
|
|
* The various calling methods then iterate forward from this safe position to
|
|
* the appropriate position to return. (For more information, see the description
|
|
* of buildBackwardsStateTable() in RuleBasedBreakIterator.Builder.)
|
|
*/
|
|
virtual int32_t handlePrevious(void);
|
|
|
|
/**
|
|
* Dumps caches and performs other actions associated with a complete change
|
|
* in text or iteration position. This function is a no-op in RuleBasedBreakIterator,
|
|
* but subclasses can and do override it.
|
|
*/
|
|
virtual void reset(void);
|
|
|
|
private:
|
|
|
|
/**
|
|
* Constructs a RuleBasedBreakIterator that uses the already-created
|
|
* tables object that is passed in as a parameter.
|
|
*/
|
|
RuleBasedBreakIterator(RuleBasedBreakIteratorTables* adoptTables);
|
|
|
|
friend class BreakIterator;
|
|
|
|
};
|
|
|
|
inline UBool RuleBasedBreakIterator::operator!=(const BreakIterator& that) const {
|
|
return !operator==(that);
|
|
}
|
|
|
|
inline UClassID RuleBasedBreakIterator::getDynamicClassID(void) const {
|
|
return RuleBasedBreakIterator::getStaticClassID();
|
|
}
|
|
|
|
inline UClassID RuleBasedBreakIterator::getStaticClassID(void) {
|
|
return (UClassID)(&fgClassID);
|
|
}
|
|
|
|
#endif
|