Public Member Functions | Protected Member Functions | List of all members
ibis::fuge Class Reference

A two-level index. More...

#include <ibin.h>

Inheritance diagram for ibis::fuge:
ibis::bin ibis::index

Public Member Functions

virtual void adjustLength (uint32_t nrows)
 Fill the bitmaps to the specified size. More...
 
virtual long append (const char *dt, const char *df, uint32_t nnew)
 Create index for the data in df and append the result to the index in dt.
 
long append (const ibis::fuge &tail)
 
virtual void estimate (const ibis::qContinuousRange &expr, ibis::bitvector &lower, ibis::bitvector &upper) const
 Provide an estimation based on the current index. More...
 
virtual long evaluate (const ibis::qContinuousRange &expr, ibis::bitvector &hits) const
 To evaluate the exact hits. More...
 
virtual long evaluate (const ibis::qDiscreteRange &expr, ibis::bitvector &hits) const
 To evaluate the exact hits. More...
 
 fuge (const ibis::column *c, ibis::fileManager::storage *st, size_t offset=8)
 Reconstruct from content of a file. More...
 
 fuge (const ibis::column *, const char *)
 
 fuge (const ibis::bin &rhs)
 
virtual const char * name () const
 Returns the name of the index, similar to the function type, but returns a string instead. More...
 
virtual void print (std::ostream &out) const
 Prints human readable information. More...
 
virtual int read (const char *idxfile)
 Read the content of the named file.
 
virtual int read (ibis::fileManager::storage *st)
 Read an index from the storage object.
 
virtual INDEX_TYPE type () const
 Returns an index type identifier.
 
virtual int write (const char *dt) const
 Write the index to the named directory or file.
 
- Public Member Functions inherited from ibis::bin
long append (const ibis::bin &tail)
 Append the tail to this index.
 
long append (const array_t< uint32_t > &ind)
 Append a list of integers representing bin numbers.
 
 bin (const ibis::bin &rhs)
 Copy constructor. It performs a deep copy.
 
 bin (const ibis::column *c=0, const char *f=0)
 Constructor. Construct a bitmap index from current data.
 
 bin (const ibis::column *c, ibis::fileManager::storage *st, size_t offset=8)
 
 bin (const ibis::column *c, const char *f, const array_t< double > &bd)
 Constructor. Construct an index with the given bin boundaries.
 
 bin (const ibis::column *c, const char *f, const std::vector< double > &bd)
 Constructor. Construct an index with the given bin boundaries.
 
 bin (const ibis::column *c, uint32_t nb, double *keys, int64_t *offs)
 Reconstruct an object from keys and offsets.
 
 bin (const ibis::column *c, uint32_t nb, double *keys, int64_t *offs, uint32_t *bms)
 Reconstruct an object from keys and offsets.
 
 bin (const ibis::column *c, uint32_t nb, double *keys, int64_t *offs, void *bms, FastBitReadBitmaps rd)
 Reconstruct an object from keys and offsets.
 
virtual void binBoundaries (std::vector< double > &) const
 The function binBoundaries and binWeights return bin boundaries and counts of each bin respectively. More...
 
virtual void binWeights (std::vector< uint32_t > &) const
 
long checkBin (const ibis::qRange &cmp, uint32_t jbin, ibis::bitvector &res) const
 Candidate check using the binned values. More...
 
long checkBin (const ibis::qRange &cmp, uint32_t jbin, const ibis::bitvector &mask, ibis::bitvector &res) const
 Candidate check using the binned values. More...
 
void construct (const char *)
 Construct a binned bitmap index. More...
 
template<typename E >
void construct (const array_t< E > &varr)
 Construction function for in-memory data. More...
 
virtual int contractRange (ibis::qContinuousRange &rng) const
 
virtual indexdup () const
 Duplicate the content of an index object.
 
virtual uint32_t estimate (const ibis::qContinuousRange &expr) const
 Compute an upper bound on the number of hits.
 
virtual void estimate (const ibis::deprecatedJoin &expr, ibis::bitvector64 &lower, ibis::bitvector64 &upper) const
 Estimate the hits for symmetric joins. More...
 
virtual void estimate (const ibis::deprecatedJoin &expr, const ibis::bitvector &mask, ibis::bitvector64 &lower, ibis::bitvector64 &upper) const
 
virtual void estimate (const ibis::deprecatedJoin &expr, const ibis::bitvector &mask, const ibis::qRange *const range1, const ibis::qRange *const range2, ibis::bitvector64 &lower, ibis::bitvector64 &upper) const
 Evaluating a join condition with one (likely composite) index.
 
virtual int64_t estimate (const ibis::deprecatedJoin &expr, const ibis::bitvector &mask, const ibis::qRange *const range1, const ibis::qRange *const range2) const
 
virtual void estimate (const ibis::bin &idx2, const ibis::deprecatedJoin &expr, ibis::bitvector64 &lower, ibis::bitvector64 &upper) const
 Estimate the number of hits for nonsymmetric joins.
 
virtual void estimate (const ibis::bin &idx2, const ibis::deprecatedJoin &expr, const ibis::bitvector &mask, ibis::bitvector64 &lower, ibis::bitvector64 &upper) const
 
virtual void estimate (const ibis::bin &idx2, const ibis::deprecatedJoin &expr, const ibis::bitvector &mask, const ibis::qRange *const range1, const ibis::qRange *const range2, ibis::bitvector64 &lower, ibis::bitvector64 &upper) const
 
virtual int64_t estimate (const ibis::bin &idx2, const ibis::deprecatedJoin &expr) const
 
virtual int64_t estimate (const ibis::bin &idx2, const ibis::deprecatedJoin &expr, const ibis::bitvector &mask) const
 
virtual int64_t estimate (const ibis::bin &idx2, const ibis::deprecatedJoin &expr, const ibis::bitvector &mask, const ibis::qRange *const range1, const ibis::qRange *const range2) const
 
virtual double estimateCost (const ibis::qContinuousRange &expr) const
 Estimate the cost of evaluating a range condition.
 
virtual double estimateCost (const ibis::qDiscreteRange &expr) const
 Estimate the cost of evaluating a range condition.
 
virtual int expandRange (ibis::qContinuousRange &rng) const
 The functions expandRange and contractRange expands or contracts the boundaries of a range condition so that the new range will have exact answers using the function estimate. More...
 
virtual long getCumulativeDistribution (std::vector< double > &bds, std::vector< uint32_t > &cts) const
 Compute the cumulative distribution from the binned index.
 
virtual long getDistribution (std::vector< double > &bbs, std::vector< uint32_t > &cts) const
 Compute a histogram from the binned index.
 
virtual double getMax () const
 Compute the actual maximum value from the binned index.
 
virtual double getMin () const
 Compute the actual minimum value from the binned index.
 
virtual double getSum () const
 Compute the approximate value of the sum from the binned index.
 
array_t< uint32_t > * indices (const ibis::bitvector &mask) const
 
virtual void locate (const ibis::qContinuousRange &expr, uint32_t &cand0, uint32_t &cand1) const
 Find the outer boundaries of the range expression. More...
 
virtual void locate (const ibis::qContinuousRange &expr, uint32_t &cand0, uint32_t &cand1, uint32_t &hit0, uint32_t &hit1) const
 Find the bins related to the range expression. More...
 
virtual uint32_t numBins () const
 
int read (int fdes, size_t offset, const char *fname, const char *header)
 Read an ibis::bin embedded inside a file. More...
 
virtual long select (const ibis::qContinuousRange &, void *) const
 Select the rows that satisfy the range condition. More...
 
virtual long select (const ibis::qContinuousRange &, void *, ibis::bitvector &) const
 Select the rows that satisfy the range condition. More...
 
virtual void serialSizes (uint64_t &, uint64_t &, uint64_t &) const
 Compute the size of arrays that would be generated by the serializatioin function (write). More...
 
virtual void speedTest (std::ostream &out) const
 Time some logical operations and print out their speed.
 
virtual float undecidable (const ibis::qContinuousRange &expr, ibis::bitvector &iffy) const
 Mark the position of the rows that can not be decided with this index. More...
 
virtual int write (ibis::array_t< double > &, ibis::array_t< int64_t > &, ibis::array_t< uint32_t > &) const
 Save index to three arrays. Serialize the index in memory.
 
- Public Member Functions inherited from ibis::index
void addBins (uint32_t ib, uint32_t ie, ibis::bitvector &res) const
 Add the sum of bits[ib] through bits[ie-1] to res. More...
 
void addBins (uint32_t ib, uint32_t ie, ibis::bitvector &res, const ibis::bitvector &tot) const
 Compute the sum of bit vectors [ib, ie). More...
 
bool empty () const
 The index object is considered empty if there is no bitmap or getNRows returns 0. More...
 
virtual void estimate (const ibis::qDiscreteRange &expr, ibis::bitvector &lower, ibis::bitvector &upper) const
 Estimate the hits for discrete ranges, i.e., those translated from 'a IN (x, y, ..)'. More...
 
virtual uint32_t estimate (const ibis::qDiscreteRange &expr) const
 
virtual void estimate (const ibis::index &idx2, const ibis::deprecatedJoin &expr, ibis::bitvector64 &lower, ibis::bitvector64 &upper) const
 Estimate the pairs for the range join operator.
 
virtual void estimate (const ibis::index &idx2, const ibis::deprecatedJoin &expr, const ibis::bitvector &mask, ibis::bitvector64 &lower, ibis::bitvector64 &upper) const
 Estimate the pairs for the range join operator. More...
 
virtual void estimate (const ibis::index &idx2, const ibis::deprecatedJoin &expr, const ibis::bitvector &mask, const ibis::qRange *const range1, const ibis::qRange *const range2, ibis::bitvector64 &lower, ibis::bitvector64 &upper) const
 
virtual int64_t estimate (const ibis::index &idx2, const ibis::deprecatedJoin &expr) const
 Estimate an upper bound for the number of pairs.
 
virtual int64_t estimate (const ibis::index &idx2, const ibis::deprecatedJoin &expr, const ibis::bitvector &mask) const
 Estimate an upper bound for the number of pairs produced from marked records. More...
 
virtual int64_t estimate (const ibis::index &idx2, const ibis::deprecatedJoin &expr, const ibis::bitvector &mask, const ibis::qRange *const range1, const ibis::qRange *const range2) const
 
virtual const ibis::bitvectorgetBitvector (uint32_t i) const
 Return a pointer to the ith bitvector used in the index (may be 0).
 
uint32_t getNRows () const
 Return the number of rows represented by this object.
 
virtual uint32_t numBitvectors () const
 Returns the number of bit vectors used by the index.
 
float sizeInBytes () const
 Estiamte the size of this index object measured in bytes. More...
 
void sumBins (uint32_t ib, uint32_t ie, ibis::bitvector &res) const
 Sum up bits[ib:ie-1] and place the result in res. More...
 
void sumBins (uint32_t ib, uint32_t ie, ibis::bitvector &res, uint32_t ib0, uint32_t ie0) const
 Compute a new sum for bit vectors [ib, ie) by taking advantage of the old sum for bitvectors [ib0, ie0). More...
 
void sumBins (uint32_t ib, uint32_t ie, ibis::bitvector &res, uint32_t *buf) const
 Sum up bits[ib:ie-1] and place the result in res. More...
 
void sumBins (const ibis::array_t< uint32_t > &, ibis::bitvector &) const
 Sum up the bits in in the specified bins.
 
virtual float undecidable (const ibis::qDiscreteRange &expr, ibis::bitvector &iffy) const
 
virtual ~index ()
 The destructor.
 

Protected Member Functions

virtual void clear ()
 Clear the existing content. More...
 
virtual size_t getSerialSize () const throw ()
 Estimate the size of the serialized version of the index. More...
 
- Protected Member Functions inherited from ibis::bin
void addBounds (double lbd, double rbd, uint32_t nbins, uint32_t eqw)
 The function used by setBoudaries() to actually generate the bounds.
 
 bin (const ibis::column *c, const uint32_t nbits, ibis::fileManager::storage *st, size_t offset=8)
 !< The minimal values in each bin. More...
 
void binning (const char *f, const std::vector< double > &bd)
 Generate bins according to the specified boundaries. More...
 
void binning (const char *f, const array_t< double > &bd)
 
void binning (const char *f)
 Read the data file and partition the values into bins according to the specified bin boundary. More...
 
template<typename E >
void binning (const array_t< E > &varr)
 
template<typename E >
void binning (const array_t< E > &varr, const array_t< double > &bd)
 
template<typename E >
void binningT (const char *fname)
 Read the data file, partition the values, and write out the bin ordered data with .bin suffix. More...
 
long binOrder (const char *fname) const
 Write bin-ordered values.
 
template<typename E >
long binOrderT (const char *fname) const
 Write bin-ordered values.
 
template<typename E >
long checkBin0 (const ibis::qRange &cmp, uint32_t jbin, ibis::bitvector &res) const
 
template<typename E >
long checkBin1 (const ibis::qRange &cmp, uint32_t jbin, const ibis::bitvector &mask, ibis::bitvector &res) const
 
virtual double computeSum () const
 Compute the sum of values from the information in the index. More...
 
void convertGranules (granuleMap &gmap)
 Convert the granule map into binned index. More...
 
void divideBitmaps (const array_t< bitvector * > &bms, std::vector< unsigned > &parts) const
 Partition the bitmaps into groups of takes about the same amount of storage. More...
 
virtual uint32_t locate (const double &val) const
 Find the bin containing val. More...
 
template<typename E >
void mapGranules (const array_t< E > &, granuleMap &gmap) const
 
template<typename T >
long mergeValues (const ibis::qContinuousRange &, ibis::array_t< T > &) const
 Extract values only. More...
 
template<typename T >
long mergeValues (const ibis::qContinuousRange &, ibis::array_t< T > &, ibis::bitvector &) const
 Extract values and record the positions. More...
 
void printGranules (std::ostream &out, const granuleMap &gmap) const
 
void readBinBoundaries (const char *name, uint32_t nb)
 Read a file containing a list of floating-point numbers. More...
 
template<typename E >
void scanAndPartition (const array_t< E > &, unsigned)
 
void scanAndPartition (const char *, unsigned, uint32_t nbins=0)
 Partition the range based on the (approximate) histogram of the data. More...
 
void setBoundaries (const char *f)
 Set bin boundaries. More...
 
void setBoundaries (array_t< double > &bnds, const ibis::bin &bin0) const
 
void setBoundaries (array_t< double > &bnds, const ibis::bin &idx1, const array_t< uint32_t > cnt1, const array_t< uint32_t > cnt0) const
 
template<typename E >
void setBoundaries (const array_t< E > &varr)
 
void swap (bin &rhs)
 Swap the content of the index.
 
int write32 (int fptr) const
 Write the content to a file already open.
 
int write64 (int fptr) const
 write the content to a file already open.
 
- Protected Member Functions inherited from ibis::index
virtual void activate () const
 Regenerate all bitvectors from the underlying storage. More...
 
virtual void activate (uint32_t i) const
 Regenerate the ith bitvector from the underlying storage.
 
virtual void activate (uint32_t i, uint32_t j) const
 Regenerate bitvectors i (inclusive) through j (exclusive) from the underlying storage. More...
 
void computeMinMax (const char *f, double &min, double &max) const
 
void dataFileName (std::string &name, const char *f=0) const
 Generate data file name from "f". More...
 
 index (const ibis::column *c=0)
 Default constructor. More...
 
 index (const ibis::column *c, ibis::fileManager::storage *s)
 Constructor with a storage object. More...
 
 index (const index &)
 Copy constructor.
 
void indexFileName (std::string &name, const char *f=0) const
 Generates index file name from "f". More...
 
void initBitmaps (int fdes)
 Prepare the bitmaps using the given file descriptor. More...
 
void initBitmaps (ibis::fileManager::storage *st)
 Prepare bitmaps from the given storage object. More...
 
void initBitmaps (uint32_t *st)
 Prepare bitmaps from the given raw pointer. More...
 
void initBitmaps (void *ctx, FastBitReadBitmaps rd)
 Prepare bitmaps from the user provided function pointer and context. More...
 
int initOffsets (int64_t *, size_t)
 Initialize the offsets from the given data array. More...
 
int initOffsets (int fdes, const char offsize, size_t start, uint32_t nobs)
 Read in the offset array. More...
 
int initOffsets (ibis::fileManager::storage *st, size_t start, uint32_t nobs)
 Regenerate the offsets array from the given storage object. More...
 
void mapValues (const char *f, VMap &bmap) const
 Map the positions of each individual value. More...
 
void mapValues (const char *f, histogram &hist, uint32_t count=0) const
 Generate a histogram. More...
 
indexoperator= (const index &)
 Assignment operator.
 
void optionalUnpack (array_t< ibis::bitvector * > &bits, const char *opt)
 A function to decide whether to uncompress the bitvectors. More...
 

Additional Inherited Members

- Public Types inherited from ibis::bin
typedef std::map< double, granule * > granuleMap
 
- Public Types inherited from ibis::index
typedef std::map< double, uint32_t > histogram
 
enum  INDEX_TYPE {
  BINNING =0, RANGE, MESA, AMBIT,
  PALE, PACK, ZONE, RELIC,
  ROSTER, SKIVE, FADE, SBIAD,
  SAPID, EGALE, MOINS, ENTRE,
  BAK, BAK2, KEYWORDS, MESH,
  BAND, DIREKTE, GENERIC, BYLT,
  FUZZ, ZONA, FUGE, SLICE,
  EXTERN
}
 The integer values of this enum type are used in the index files to differentiate the indexes. More...
 
typedef std::map< double, ibis::bitvector * > VMap
 
- Static Public Member Functions inherited from ibis::bin
static uint32_t parseNbins (const ibis::column &)
 Parse the index specs to determine eqw and nbins. More...
 
static unsigned parsePrec (const ibis::column &)
 Parse the index spec to extract precision.
 
static unsigned parseScale (const ibis::column &)
 Parse the specification about scaling. More...
 
static unsigned parseScale (const char *)
 
- Static Public Member Functions inherited from ibis::index
static void addBits (const array_t< bitvector * > &bits, uint32_t ib, uint32_t ie, ibis::bitvector &res)
 Add the pile[ib:ie-1] to res. More...
 
static indexcreate (const column *c, const char *name=0, const char *spec=0, int inEntirety=0)
 Index factory. More...
 
static void divideCounts (array_t< uint32_t > &bounds, const array_t< uint32_t > &cnt)
 Determine how to split the array cnt, so that each group has roughly the same total value. More...
 
static bool isIndex (const char *f, INDEX_TYPE t)
 Is the named file an index file? Read the header of the named file to determine if it contains an index of the specified type. More...
 
template<typename E >
static void mapValues (const array_t< E > &val, VMap &bmap)
 
template<typename E >
static void mapValues (const array_t< E > &val, histogram &hist, uint32_t count=0)
 
template<typename E >
static void mapValues (const array_t< E > &val, array_t< E > &bounds, std::vector< uint32_t > &cnts)
 
template<typename E1 , typename E2 >
static void mapValues (const array_t< E1 > &val1, const array_t< E2 > &val2, array_t< E1 > &bnd1, array_t< E2 > &bnd2, std::vector< uint32_t > &cnts)
 Compute a two-dimensional histogram. More...
 
static void printHeader (std::ostream &, const char *)
 
static void setBases (array_t< uint32_t > &bases, uint32_t card, uint32_t nbase=2)
 Fill the array bases with the values that cover the range [0, card). More...
 
static void sumBits (const array_t< bitvector * > &bits, uint32_t ib, uint32_t ie, ibis::bitvector &res)
 Sum up pile[ib:ie-1] and place the result in res. More...
 
static void sumBits (const array_t< bitvector * > &bits, const ibis::bitvector &tot, uint32_t ib, uint32_t ie, ibis::bitvector &res)
 Sum up pile[ib:ie-1] and add the result to res. More...
 
- Static Protected Member Functions inherited from ibis::index
static void indexFileName (std::string &name, const ibis::column *col1, const ibis::column *col2, const char *f=0)
 Generate the index file name for the composite index fromed on two columns. More...
 
- Protected Attributes inherited from ibis::bin
array_t< double > bounds
 !< Number of bitvectors.
 
array_t< double > maxval
 !< The nominal boundaries.
 
array_t< double > minval
 !< The maximal values in each bin.
 
uint32_t nobs
 
- Protected Attributes inherited from ibis::index
array_t< ibis::bitvector * > bits
 A list of bitvectors.
 
bitmapReaderbreader
 The functor to read serialized bitmaps from a more complex source.
 
const ibis::columncol
 Pointer to the column this index is for.
 
const char * fname
 The name of the file containing the index.
 
uint32_t nrows
 The number of rows represented by the index. More...
 
array_t< int32_t > offset32
 Starting positions of the bitvectors.
 
array_t< int64_t > offset64
 Starting positions of the bitvectors. More...
 
ibis::fileManager::storagestr
 The underlying storage. More...
 

Detailed Description

A two-level index.

The top (coarse) level uses the interval encoding and the bottom (fine) level uses the equality encoding. Similar to class ibis::fuzz, the fine level bitmaps are kept together as in ibis::bin and the coarse level bitmaps are placed at the end of the index file.

Constructor & Destructor Documentation

ibis::fuge::fuge ( const ibis::column c,
ibis::fileManager::storage st,
size_t  start = 8 
)

Reconstruct from content of a file.

The leading portion of the index file is the same as ibis::bin, which allows the constructor of the base class to work properly. The content following the last bitvector in ibis::bin is as follows,

See also
ibis::fuge::writeCoarse.
nc (uint32_t) -- number of coarse bins.
cbounds (unsigned[nc+1]) -- boundaries of the coarse bins.
coffsets([nc-ceil(nc/2)+2]) -- starting positions (32/64-bit).
cbits (bitvector[nc-ceil(nc/2)+1]) -- bitvectors.

References ibis::fileManager::storage::begin(), ibis::array_t< T >::clear(), clear(), ibis::index::col, ibis::fileManager::storage::isFileMap(), ibis::part::name(), ibis::column::name(), ibis::index::nrows, ibis::index::offset32, ibis::index::offset64, print(), ibis::fileManager::storage::size(), and ibis::array_t< T >::swap().

Member Function Documentation

void ibis::fuge::adjustLength ( uint32_t  nr)
virtual

Fill the bitmaps to the specified size.

Fill the bitvectors with zeros so that they all contain nrows bits.

Truncate the bitvectors if they have more bits.

Reimplemented from ibis::bin.

References ibis::bin::adjustLength().

virtual void ibis::fuge::clear ( )
inlineprotectedvirtual

Clear the existing content.

Free the bitmap objectes common to all index objects.

Reimplemented from ibis::bin.

References ibis::bin::clear().

Referenced by fuge().

void ibis::fuge::estimate ( const ibis::qContinuousRange expr,
ibis::bitvector lower,
ibis::bitvector upper 
) const
virtual

Provide an estimation based on the current index.

Set bits in lower are hits for certain, set bits in upper are candidates. Set bits in (upper - lower) should be checked to verifies which ones are actually hits. If the bitvector upper contain less bits than bitvector lower, the content of upper is assumed to be the same as lower.

Note
This function will not do anything if the estimated cost is high.

Reimplemented from ibis::bin.

References ibis::bitvector::clear(), ibis::bitvector::copy(), and ibis::bitvector::set().

long ibis::fuge::evaluate ( const ibis::qContinuousRange expr,
ibis::bitvector hits 
) const
virtual

To evaluate the exact hits.

On success, return the number of hits, otherwise a negative value is returned.

Reimplemented from ibis::bin.

References ibis::bitvector::cnt(), and ibis::bitvector::size().

virtual long ibis::fuge::evaluate ( const ibis::qDiscreteRange ,
ibis::bitvector  
) const
inlinevirtual

To evaluate the exact hits.

On success, return the number of hits, otherwise a negative value is returned.

Reimplemented from ibis::bin.

References ibis::index::evaluate().

size_t ibis::fuge::getSerialSize ( ) const
throw (
)
protectedvirtual

Estimate the size of the serialized version of the index.

Return the size in bytes.

Reimplemented from ibis::bin.

References ibis::bitvector::size().

virtual const char* ibis::fuge::name ( ) const
inlinevirtual

Returns the name of the index, similar to the function type, but returns a string instead.

Reimplemented from ibis::bin.

void ibis::fuge::print ( std::ostream &  out) const
virtual

Prints human readable information.

Outputs information about the index as text to the specified output stream.

Reimplemented from ibis::bin.

Referenced by fuge().


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

Make It A Bit Faster
Contact us
Disclaimers
FastBit source code
FastBit mailing list archive