dw::Hyphenator Class Reference

#include <hyphenator.hh>

Public Member Functions
	Hyphenator (const char *patFile, const char *excFile, int pack=256)
	~Hyphenator ()
int *	hyphenateWord (core::Platform *platform, const char *word, int *numBreaks)
void	saveTrie (FILE *fp)
Public Member Functions inherited from lout::object::Object
virtual	~Object ()
	The destructor is defined as virtual (but not abstract), so that destruction of Object's works properly. More...
virtual bool	equals (Object *other)
	Returns, whether two objects are equal. More...
virtual int	hashValue ()
	Return a hash value for the object. More...
virtual Object *	clone ()
	Return an exact copy of the object. More...
virtual void	intoStringBuffer (misc::StringBuffer *sb)
	Store a textual representation of the object in a misc::StringBuffer. More...
const char *	toString ()
	Use object::Object::intoStringBuffer to return a textual representation of the object. More...
virtual size_t	sizeOf ()
	Return the number of bytes, this object totally uses. More...

Static Public Member Functions
static Hyphenator *	getHyphenator (const char *language)
static bool	isHyphenationCandidate (const char *word)

Private Member Functions
void	insertPattern (TrieBuilder *trieBuilder, char *s)
void	insertException (char *s)
void	hyphenateSingleWord (core::Platform *platform, char *wordLc, int offset, lout::misc::SimpleVector< int > *breakPos)
bool	isCharPartOfActualWord (char *s)

Private Attributes
Trie *	trie
lout::container::typed::HashTable < lout::object::ConstString, lout::container::typed::Vector < lout::object::Integer > > *	exceptions

Static Private Attributes
static lout::container::typed::HashTable < lout::object::String, Hyphenator > *	hyphenators

Constructor & Destructor Documentation

dw::Hyphenator::Hyphenator	(	const char *	patFile,
		const char *	excFile,
		int	pack = 256
	)

References dw::TrieBuilder::createTrie(), and LEN.

dw::Hyphenator::~Hyphenator

(

)

Member Function Documentation

Hyphenator * dw::Hyphenator::getHyphenator ( const char *  language )

static

Referenced by hyphenateWord().

void dw::Hyphenator::hyphenateSingleWord ( core::Platform *  platform, char *  wordLc, int  offset, lout::misc::SimpleVector< int > *  breakPos  )

private

Hyphenate a single word, which only consists of lowercase characters. Store break positions + "offset" in "breakPos".

References lout::misc::SimpleVector< T >::get(), lout::container::typed::Vector< T >::get(), lout::object::Integer::getValue(), lout::misc::SimpleVector< T >::increase(), lout::misc::max(), lout::misc::min(), lout::unicode::nextUtf8Char(), lout::unicode::numUtf8Chars(), lout::misc::SimpleVector< T >::set(), lout::misc::SimpleVector< T >::setSize(), lout::misc::SimpleVector< T >::size(), and lout::container::typed::Collection< T >::size().

int * dw::Hyphenator::hyphenateWord	(	core::Platform *	platform,
		const char *	word,
		int *	numBreaks
	)

Given a word, returns a list of the possible hyphenation points.

References lout::misc::SimpleVector< T >::detachArray(), dw::core::Platform::nextGlyph(), lout::misc::SimpleVector< T >::size(), and dw::core::Platform::textToLower().

Referenced by hyphenateWord(), and dw::Textblock::hyphenateWord().

void dw::Hyphenator::insertException ( char *  s )

private

References lout::container::typed::Vector< T >::put(), and lout::container::typed::Collection< T >::size().

void dw::Hyphenator::insertPattern ( TrieBuilder *  trieBuilder, char *  s  )

private

References lout::misc::SimpleVector< T >::getArray(), dw::TrieBuilder::insert(), lout::misc::SimpleVector< T >::set(), and lout::misc::SimpleVector< T >::setSize().

bool dw::Hyphenator::isCharPartOfActualWord ( char *  s )

private

Test whether the character on which "s" points (UTF-8) is an actual part of the word. Other characters at the beginning and end are ignored.

TODO Currently only suitable for English and German. TODO Only lowercase. (Uppercase not needed.)

References lout::unicode::decodeUtf8(), and lout::unicode::isAlpha().

bool dw::Hyphenator::isHyphenationCandidate ( const char *  word )

static

Simple test to avoid much costs. Passing it does not mean that the word can be hyphenated.

void dw::Hyphenator::saveTrie ( FILE *  fp )

inline

References dw::Trie::save().

Referenced by main().

Member Data Documentation

lout::container::typed::HashTable<lout::object::ConstString, lout::container::typed::Vector <lout::object::Integer> >* dw::Hyphenator::exceptions

private

HashTable< String, Hyphenator > * dw::Hyphenator::hyphenators

staticprivate

Initial value:

=
   new HashTable <String, Hyphenator> (true, true)

Trie* dw::Hyphenator::trie

private

---

The documentation for this class was generated from the following files:

• dw/hyphenator.hh
• dw/hyphenator.cc