Strigi Namespace Reference

The complete spec implemented by this interface is here: http://xesam.org/main/XesamSearch90. More...

Namespaces
namespace	IndexPluginLoader
Classes
class	AnalysisCaller
class	AnalysisResult
	Indexed representation of a file. More...
class	AnalyzerConfiguration
	This class provides information and functions to control the analysis. More...
class	AnalyzerFactoryFactory
	Provides a list of analyzer factories present within a plugin. More...
class	AnalyzerLoader
class	ArchiveReader
	Provides an API for accessing members of an archive. More...
class	ArInputStream
class	Base64InputStream
class	BufferedStream
	Abstract class providing a buffered input stream. More...
class	BZ2InputStream
class	ClassProperties
class	CpioInputStream
class	DataEventHandler
	Handler interface for handling data events. More...
class	DataEventInputStream
	An InputStream that makes parallel handling of incoming data easier. More...
class	DirAnalyzer
class	DirLister
class	EncodingInputStream
struct	EntryInfo
	Provides information about the current substream. More...
class	EventThroughAnalyzer
class	EventThroughAnalyzerFactory
class	FieldProperties
class	FieldPropertiesDb
	This class is the default implementation for getting at metadata related to properties. More...
class	FieldRegister
	A register for storing the fields associated with an analysis. More...
class	FileInputStream
	Provides buffered access to a file. More...
class	FileLister
class	FileReader
	Reads and decodes a text file into a Unicode stream. More...
class	FileStreamOpener
class	FsFileInputStream
class	GZipCompressInputStream
class	GZipInputStream
class	HtmlSaxAnalyzer
class	HtmlSaxAnalyzerFactory
class	IndexedDocument
class	IndexManager
	Abstract interface that manages access to the IndexReader and IndexWriter instances provided by a particular index backend. More...
class	IndexReader
	Abstract class that provides read access to a Strigi index. More...
class	IndexWriter
	Abstract class that provides write access to a Strigi index. More...
class	InputStreamReader
	Adapter to convert an InputStream (a byte stream) into a Reader (decoded Unicode character stream). More...
class	KmpSearcher
	Class for string search that uses the Knuth-Morris-Pratt algorithm. More...
class	LineEventAnalyzer
class	LZMAInputStream
class	MailInputStream
	This is an implementation for handling email streams as archives. More...
class	MimeEventAnalyzer
class	MimeEventAnalyzerFactory
class	OleInputStream
	Partial implementation of the ole file format according to http://jakarta.apache.org/poi/poifs/fileformat.html. More...
class	ProcessInputStream
class	Query
class	QueryParser
class	RegisteredField
	Represents a field in the ontology of a file. More...
class	RpmInputStream
class	SaxEventAnalyzer
class	SdfInputStream
class	StreamAnalyzer
class	StreamAnalyzerFactory
	The StreamAnalyzerFactory class. More...
class	StreamBase
	Base class for stream read access to a data source. More...
class	StreamBaseBase
	The base of all Streams. More...
class	StreamBuffer
	Provides a buffer for the use of BufferedStream. More...
class	StreamEndAnalyzer
class	StreamEndAnalyzerFactory
class	StreamEventAnalyzer
class	StreamEventAnalyzerFactory
class	StreamLineAnalyzer
	This class is especially well suited for file formats that are based on lines of plain text, i.e. More...
class	StreamLineAnalyzerFactory
	This is the factory for the creation of a StreamLineAnalyzer. More...
class	StreamOpener
	Abstract class that defines an interface for opening streams and statting files. More...
class	StreamSaxAnalyzer
	This class is well suited for analyzing XML based file formats, for example SVG files. More...
class	StreamSaxAnalyzerFactory
	This is the factory for the creation of a StreamSaxAnalyzer. More...
class	StreamThroughAnalyzer
	This class defines an interface for analyzing streams. More...
class	StreamThroughAnalyzerFactory
	The factory class for the StreamThroughAnalyzer. More...
class	StringStream
	Provides access to in-memory data thorugh the StreamBase API. More...
class	StringTerminatedSubStream
	Reads a stream up to a given terminator. More...
class	SubInputStream
	Provides access to part of an InputStream only. More...
class	SubStreamProvider
	Extracts substreams from an InputStream. More...
class	SubStreamProviderProvider
	Creates a SubStreamProvider to extract substreams from a given input stream. More...
class	TarInputStream
	Implementation of SubStreamProvider for reading the tar format. More...
class	Term
class	Variant
	Simple inefficient implementation of a variant type as needed by xesam. More...
class	ZipInputStream
	Partial implementation of the zip file format according to http://www.pkware.com/business_and_developers/developer/popups/appnote.txt http://www.pkware.com/documents/casestudies/APPNOTE.TXT 99% of zip files on my system can be read with this class. More...
Typedefs
typedef BufferedStream< char >	BufferedInputStream
typedef BufferedStream< wchar_t >	BufferedReader
typedef StreamBase< char >	InputStream
typedef StreamBase< wchar_t >	Reader
typedef StringStream< char >	StringInputStream
typedef StringStream< wchar_t >	StringReader
Enumerations
enum	StreamStatus { Ok, Eof, Error }
Functions
STREAMS_EXPORT bool	checkUtf8 (const std::string &)
STREAMS_EXPORT bool	checkUtf8 (const char *p, int32_t length)
STREAMS_EXPORT const char *	checkUtf8 (const std::string &, char &nb)
STREAMS_EXPORT const char *	checkUtf8 (const char *p, int32_t length, char &nb)
STREAMS_EXPORT void	convertNewLines (char *p)
void	deleteIndexManager (Strigi::IndexManager *m)
STREAMS_INLINE_EXPORT int16_t	readBigEndianInt16 (const unsigned char *c)
STREAMS_EXPORT int16_t	readBigEndianInt16 (const char *c)
STREAMS_INLINE_EXPORT int32_t	readBigEndianInt32 (const unsigned char *c)
STREAMS_EXPORT int32_t	readBigEndianInt32 (const char *c)
STREAMS_INLINE_EXPORT int64_t	readBigEndianInt64 (const unsigned char *c)
STREAMS_EXPORT int64_t	readBigEndianInt64 (const char *c)
STREAMS_INLINE_EXPORT uint16_t	readBigEndianUInt16 (const unsigned char *c)
STREAMS_EXPORT uint16_t	readBigEndianUInt16 (const char *c)
STREAMS_INLINE_EXPORT uint32_t	readBigEndianUInt32 (const unsigned char *c)
STREAMS_EXPORT uint32_t	readBigEndianUInt32 (const char *c)
STREAMS_INLINE_EXPORT uint64_t	readBigEndianUInt64 (const unsigned char *c)
STREAMS_EXPORT uint64_t	readBigEndianUInt64 (const char *c)
STREAMS_INLINE_EXPORT int16_t	readLittleEndianInt16 (const unsigned char *c)
STREAMS_INLINE_EXPORT int16_t	readLittleEndianInt16 (const char *c)
STREAMS_INLINE_EXPORT int32_t	readLittleEndianInt32 (const unsigned char *c)
STREAMS_INLINE_EXPORT int32_t	readLittleEndianInt32 (const char *c)
STREAMS_INLINE_EXPORT int64_t	readLittleEndianInt64 (const unsigned char *c)
STREAMS_INLINE_EXPORT int64_t	readLittleEndianInt64 (const char *c)
STREAMS_INLINE_EXPORT uint16_t	readLittleEndianUInt16 (const unsigned char *c)
STREAMS_INLINE_EXPORT uint16_t	readLittleEndianUInt16 (const char *c)
STREAMS_INLINE_EXPORT uint32_t	readLittleEndianUInt32 (const unsigned char *c)
STREAMS_INLINE_EXPORT uint32_t	readLittleEndianUInt32 (const char *c)
STREAMS_INLINE_EXPORT uint64_t	readLittleEndianUInt64 (const unsigned char *c)
STREAMS_INLINE_EXPORT uint64_t	readLittleEndianUInt64 (const char *c)

---

Detailed Description

The complete spec implemented by this interface is here: http://xesam.org/main/XesamSearch90.

This class does the same as the Posix command find $dir -type f -mmin -$age The performance is equal, but there are a couple of advantages:

• the last modification date is given instead of the age of the file in minutes
• the wanted file are returned as two strings for dirpath and filename through a callback function instead of one concatenated string through a pipe.

Strigi is the major namespace for all classes that are used in the analysis of streams.

• no need to spawn a separate process

---

Typedef Documentation

typedef BufferedStream<char> Strigi::BufferedInputStream

Abstract class for a buffered stream of bytes.

Definition at line 93 of file bufferedstream.h.

typedef BufferedStream<wchar_t> Strigi::BufferedReader

Abstract class for a buffered stream of Unicode characters.

Definition at line 96 of file bufferedstream.h.

typedef StreamBase< char > Strigi::InputStream

Abstract class for a stream of bytes.

Definition at line 28 of file streamendanalyzer.h.

typedef StreamBase<wchar_t> Strigi::Reader

Abstract class for a stream of Unicode characters.

Definition at line 199 of file streambase.h.

typedef StringStream<char> Strigi::StringInputStream

An InputStream to read from in-memory data.

Definition at line 74 of file stringstream.h.

typedef StringStream<wchar_t> Strigi::StringReader

A Reader to read from in-memory data.

Definition at line 77 of file stringstream.h.

---

Enumeration Type Documentation

enum Strigi::StreamStatus

Used to indicate the current status of a Stream.

Enumerator:

Ok	Stream is capable of being read from.
Eof	The end of the Stream has been reached.
Error	An error occurred. Use error() to find out more information

Definition at line 32 of file streambase.h.

---

Function Documentation

bool Strigi::checkUtf8

(

const std::string &

p

)

Definition at line 69 of file textutils.cpp.

bool Strigi::checkUtf8	(	const char *	p,
		int32_t	length
	)

Return the position of the first byte that is not valid utf8.

Return value of 0 means that the entire string is valid. If the last character is incomplete the returned value points to the start of that character and nb is set to the number of characters that is missing.

Definition at line 32 of file textutils.cpp.

const char * Strigi::checkUtf8	(	const std::string &	p,
		char &	nb
	)

Definition at line 127 of file textutils.cpp.

const char * Strigi::checkUtf8	(	const char *	p,
		int32_t	length,
		char &	nb
	)

Return the position of the first byte that is not valid utf8.

Return value of 0 means that the entire string is valid. If the last character is incomplete the returned value points to the start of that character and nb is set to the number of characters that is missing. If there is an error, nb == 0.

Definition at line 83 of file textutils.cpp.

void Strigi::convertNewLines

(

char *

p

)

convert the and
in utf8 strings into spaces

Definition at line 135 of file textutils.cpp.

void Strigi::IndexPluginLoader::deleteIndexManager

(

Strigi::IndexManager *

m

)

Definition at line 238 of file indexpluginloader.cpp.

STREAMS_INLINE_EXPORT int16_t Strigi::readBigEndianInt16

(

const unsigned char *

c

)

[inline]

Definition at line 115 of file textutils.h.

int16_t Strigi::readBigEndianInt16

(

const char *

c

)

Definition at line 205 of file textutils.cpp.

STREAMS_INLINE_EXPORT int32_t Strigi::readBigEndianInt32

(

const unsigned char *

c

)

[inline]

Definition at line 121 of file textutils.h.

int32_t Strigi::readBigEndianInt32

(

const char *

c

)

Definition at line 213 of file textutils.cpp.

STREAMS_INLINE_EXPORT int64_t Strigi::readBigEndianInt64

(

const unsigned char *

c

)

[inline]

Definition at line 127 of file textutils.h.

int64_t Strigi::readBigEndianInt64

(

const char *

c

)

Definition at line 221 of file textutils.cpp.

STREAMS_INLINE_EXPORT uint16_t Strigi::readBigEndianUInt16

(

const unsigned char *

c

)

[inline]

Definition at line 118 of file textutils.h.

uint16_t Strigi::readBigEndianUInt16

(

const char *

c

)

Definition at line 209 of file textutils.cpp.

STREAMS_INLINE_EXPORT uint32_t Strigi::readBigEndianUInt32

(

const unsigned char *

c

)

[inline]

Definition at line 124 of file textutils.h.

uint32_t Strigi::readBigEndianUInt32

(

const char *

c

)

Definition at line 217 of file textutils.cpp.

STREAMS_INLINE_EXPORT uint64_t Strigi::readBigEndianUInt64

(

const unsigned char *

c

)

[inline]

Definition at line 130 of file textutils.h.

uint64_t Strigi::readBigEndianUInt64

(

const char *

c

)

Definition at line 225 of file textutils.cpp.

STREAMS_INLINE_EXPORT int16_t Strigi::readLittleEndianInt16

(

const unsigned char *

c

)

[inline]

Definition at line 97 of file textutils.h.

STREAMS_INLINE_EXPORT int16_t Strigi::readLittleEndianInt16

(

const char *

c

)

[inline]

Definition at line 71 of file textutils.h.

STREAMS_INLINE_EXPORT int32_t Strigi::readLittleEndianInt32

(

const unsigned char *

c

)

[inline]

Definition at line 103 of file textutils.h.

STREAMS_INLINE_EXPORT int32_t Strigi::readLittleEndianInt32

(

const char *

c

)

[inline]

Definition at line 77 of file textutils.h.

STREAMS_INLINE_EXPORT int64_t Strigi::readLittleEndianInt64

(

const unsigned char *

c

)

[inline]

Definition at line 109 of file textutils.h.

STREAMS_INLINE_EXPORT int64_t Strigi::readLittleEndianInt64

(

const char *

c

)

[inline]

Definition at line 83 of file textutils.h.

STREAMS_INLINE_EXPORT uint16_t Strigi::readLittleEndianUInt16

(

const unsigned char *

c

)

[inline]

Definition at line 100 of file textutils.h.

STREAMS_INLINE_EXPORT uint16_t Strigi::readLittleEndianUInt16

(

const char *

c

)

[inline]

Definition at line 74 of file textutils.h.

STREAMS_INLINE_EXPORT uint32_t Strigi::readLittleEndianUInt32

(

const unsigned char *

c

)

[inline]

Definition at line 106 of file textutils.h.

STREAMS_INLINE_EXPORT uint32_t Strigi::readLittleEndianUInt32

(

const char *

c

)

[inline]

Definition at line 80 of file textutils.h.

STREAMS_INLINE_EXPORT uint64_t Strigi::readLittleEndianUInt64

(

const unsigned char *

c

)

[inline]

Definition at line 112 of file textutils.h.

STREAMS_INLINE_EXPORT uint64_t Strigi::readLittleEndianUInt64

(

const char *

c

)

[inline]

Definition at line 86 of file textutils.h.