indri::parse Namespace Reference

File input, parsing, stemming, and stopping classes. More...

Classes
class	AnchorTextAnnotator
class	AnchorTextHarvester
class	AnchorTextWriter
struct	AttributeValuePair
class	Combiner
struct	Combiner::strcompst
struct	Combiner::strhash
struct	Combiner::url_entry
class	Conflater
struct	Conflater::attribute_pattern
struct	Conflater::tag_pattern
struct	conflation_pair
struct	ConflationPattern
class	DateParse
class	DocumentIterator
class	DocumentIteratorFactory
struct	FileClassEnvironment
class	FileClassEnvironmentFactory
struct	FileClassEnvironmentFactory::Specification
	Parsing information for a file class. Used to create a FileClassEnvironment. More...
class	HTMLParser
class	KrovetzStemmer
struct	KrovetzStemmer::cacheEntry
	Two term hashtable entry for caching across calls. More...
struct	KrovetzStemmer::dictEntry
	Dictionary table entry. More...
struct	KrovetzStemmer::eqstr
class	KrovetzStemmerTransformation
class	LessTagExtent
class	MboxDocumentIterator
struct	MetadataPair
class	MetadataPair::key_equal
class	NormalizationTransformation
class	NumericFieldAnnotator
class	ObjectHandler
class	OffsetAnnotationAnnotator
struct	OffsetAnnotationAnnotator::ReadAnnotationTag
class	OffsetMetadataAnnotator
class	PageRank
class	pagerank
struct	pagerank::pagerank_greater
class	Parser
class	ParserFactory
class	PDFDocumentExtractor
class	Porter_Stemmer
class	PorterStemmerTransformation
class	prEntry
struct	prEntry::prEntry_greater
class	RawTextParser
class	StemmerFactory
class	StopperTransformation
struct	StopperTransformation::eqstr
class	Tag
struct	TagEvent
struct	TagExtent
struct	TagExtent::lowest_end_first
class	TaggedDocumentIterator
class	TaggedTextParser
struct	TaggedTextParser::tag_properties
class	TagList
struct	TagList::tag_entry
struct	TermExtent
class	TextDocumentExtractor
class	TextParser
class	TextTokenizer
struct	TokenizedDocument
class	Tokenizer
class	TokenizerFactory
class	Transformation
struct	UnparsedDocument
class	URLTextAnnotator
class	UTF8CaseNormalizationTransformation
class	UTF8Transcoder
class	WARCDocumentIterator
class	WARCRecord
Typedefs
typedef indri::parse::FileClassEnvironmentFactory::Specification	Specification
Enumerations
enum	OffsetAnnotationIndexHint { OAHintDefault, OAHintOrderedAnnotations, OAHintSizeBuffers, OAHintNone }
Variables
const char *	exceptions []
const struct conflation_pair	conflations []
const char *const	headwords []

---

Detailed Description

File input, parsing, stemming, and stopping classes.

---

Typedef Documentation

typedef indri::parse::FileClassEnvironmentFactory::Specification indri::parse::Specification

---

Enumeration Type Documentation

enum indri::parse::OffsetAnnotationIndexHint

Enumeration values: OAHintDefault  OAHintOrderedAnnotations  OAHintSizeBuffers  OAHintNone

---

Variable Documentation

const struct conflation_pair indri::parse::conflations[] [static]

const char* indri::parse::exceptions[] [static]

const char* const indri::parse::headwords[] [static]

---