com.vladsch.flexmark.util.sequence.builder.tree

Class SegmentTree

java.lang.Object

com.vladsch.flexmark.util.sequence.builder.tree.SegmentTree

Direct Known Subclasses:

SegmentOffsetTree

public class SegmentTree
extends Object

Binary search tree of sequence segments

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
protected static class	SegmentTree.SegmentTreeData

Field Summary

Fields

Modifier and Type	Field and Description
static int	F_ANCHOR_FLAGS
static int	MAX_VALUE
protected byte[]	segmentBytes
protected int[]	treeData

Constructor Summary

Constructors

Modifier	Constructor and Description
protected	SegmentTree(int[] treeData, byte[] segmentBytes)

Method Summary

Modifier and Type	Method and Description
void	addSegments(@NotNull IBasedSegmentBuilder<?> builder, int startIndex, int endIndex, int startOffset, int endOffset, int startPos, int endPos) Add segments of subsequence of this tree to builder
void	addSegments(@NotNull IBasedSegmentBuilder<?> builder, @NotNull SegmentTreeRange treeRange) Add segments selected by given treeRange
int	aggrLength(int pos)
static int	aggrLength(int pos, int[] treeData)
static @NotNull SegmentTree	build(@NotNull BasedSegmentBuilder builder)
static @NotNull SegmentTree	build(@NotNull Iterable<Seg> segments, @NotNull CharSequence allText)
static @NotNull SegmentTree.SegmentTreeData	buildTreeData(@NotNull Iterable<Seg> segments, @NotNull CharSequence allText, boolean buildIndexData) Build binary tree search data
int	byteOffset(int pos)
static int	byteOffset(int pos, int[] treeData)
int	byteOffsetData(int pos)
static int	byteOffsetData(int pos, int[] treeData)
@Nullable Segment	findSegment(int index, @NotNull BasedSequence baseSeq, @Nullable Segment hint)
static @Nullable Segment	findSegment(int index, int[] treeData, int startPos, int endPos, byte[] segmentBytes, @NotNull BasedSequence baseSeq)
@Nullable Segment	findSegment(int index, int startPos, int endPos, @NotNull BasedSequence baseSeq, @Nullable Segment hint)
@Nullable SegmentTreePos	findSegmentPos(int index)
static @Nullable SegmentTreePos	findSegmentPos(int index, int[] treeData, int startPos, int endPos)
@Nullable SegmentTreePos	findSegmentPos(int index, int startPos, int endPos)
static int	getAnchorOffset(int byteOffsetData)
static int	getByteOffset(int byteOffsetData)
static @NotNull CharSequence	getCharSequence(@NotNull Segment segment, int startIndex, int endIndex, int startPos, int endPos) Get char sequence of segment corresponding to sub-sequence in segment tree
@Nullable Segment	getPrevAnchor(int pos, @NotNull BasedSequence baseSeq)
static @Nullable Segment	getPrevAnchor(int pos, int[] treeData, byte[] segmentBytes, @NotNull BasedSequence baseSeq)
@NotNull Segment	getSegment(int pos, @NotNull BasedSequence baseSeq)
static @NotNull Segment	getSegment(int pos, int[] treeData, byte[] segmentBytes, @NotNull BasedSequence baseSeq)
@NotNull Segment	getSegment(int byteOffset, int pos, int startIndex, @NotNull BasedSequence baseSeq)
byte[]	getSegmentBytes()
@NotNull SegmentOffsetTree	getSegmentOffsetTree(@NotNull BasedSequence baseSeq) Build an offset segment tree from this index segment tree
@NotNull SegmentTreeRange	getSegmentRange(int startIndex, int endIndex, int startPos, int endPos, @NotNull BasedSequence baseSequence, @Nullable Segment hint)
int	getTextEndOffset(Segment segment, @NotNull BasedSequence baseSequence)
int	getTextStartOffset(Segment segment, @NotNull BasedSequence baseSequence)
int[]	getTreeData()
boolean	hasPreviousAnchor(int pos)
static boolean	hasPreviousAnchor(int pos, int[] treeData)
int	previousAnchorOffset(int pos)
static int	previousAnchorOffset(int pos, int[] treeData)
static void	setTreeData(int pos, int[] treeData, int agrrLength, int byteOffset, int prevAnchorOffset)
int	size()
@NotNull String	toString()
@NotNull String	toString(@NotNull BasedSequence baseSeq)

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait

Field Detail

MAX_VALUE

public static final int MAX_VALUE

See Also:

Constant Field Values

F_ANCHOR_FLAGS

public static final int F_ANCHOR_FLAGS

See Also:

Constant Field Values

treeData

protected final int[] treeData

segmentBytes

protected final byte[] segmentBytes

Constructor Detail

SegmentTree

protected SegmentTree(int[] treeData,
                      byte[] segmentBytes)

Method Detail

getTreeData

public int[] getTreeData()

getSegmentBytes

public byte[] getSegmentBytes()

size

public int size()

aggrLength

public int aggrLength(int pos)

byteOffsetData

public int byteOffsetData(int pos)

byteOffset

public int byteOffset(int pos)

getByteOffset

public static int getByteOffset(int byteOffsetData)

getAnchorOffset

public static int getAnchorOffset(int byteOffsetData)

hasPreviousAnchor

public boolean hasPreviousAnchor(int pos)

previousAnchorOffset

public int previousAnchorOffset(int pos)

findSegmentPos

@Nullable
public @Nullable SegmentTreePos findSegmentPos(int index)

getSegment

@NotNull
public @NotNull Segment getSegment(int byteOffset,
                                            int pos,
                                            int startIndex,
                                            @NotNull
                                            @NotNull BasedSequence baseSeq)

findSegment

@Nullable
public @Nullable Segment findSegment(int index,
                                               @NotNull
                                               @NotNull BasedSequence baseSeq,
                                               @Nullable
                                               @Nullable Segment hint)

findSegment

@Nullable
public @Nullable Segment findSegment(int index,
                                               int startPos,
                                               int endPos,
                                               @NotNull
                                               @NotNull BasedSequence baseSeq,
                                               @Nullable
                                               @Nullable Segment hint)

getSegmentRange

@NotNull
public @NotNull SegmentTreeRange getSegmentRange(int startIndex,
                                                          int endIndex,
                                                          int startPos,
                                                          int endPos,
                                                          @NotNull
                                                          @NotNull BasedSequence baseSequence,
                                                          @Nullable
                                                          @Nullable Segment hint)

getTextEndOffset

public int getTextEndOffset(Segment segment,
                            @NotNull
                            @NotNull BasedSequence baseSequence)

getTextStartOffset

public int getTextStartOffset(Segment segment,
                              @NotNull
                              @NotNull BasedSequence baseSequence)

addSegments

public void addSegments(@NotNull
                        @NotNull IBasedSegmentBuilder<?> builder,
                        @NotNull
                        @NotNull SegmentTreeRange treeRange)

Add segments selected by given treeRange

Parameters:

builder - based segment builder

treeRange - treeRange for which to add segments

addSegments

public void addSegments(@NotNull
                        @NotNull IBasedSegmentBuilder<?> builder,
                        int startIndex,
                        int endIndex,
                        int startOffset,
                        int endOffset,
                        int startPos,
                        int endPos)

Add segments of subsequence of this tree to builder

Parameters:

builder - builder to which to add the segments

startIndex - start index of sub-sequence of segment tree

endIndex - end index of sub-sequence of segment tree

startOffset - start offset of the subsequence to use as start anchor

endOffset - end offset of the subsequence to use as end anchor

startPos - start pos of sub-sequence segments in tree

endPos - end pos of sub-sequence segments in tree

getCharSequence

@NotNull
public static @NotNull CharSequence getCharSequence(@NotNull
                                                             @NotNull Segment segment,
                                                             int startIndex,
                                                             int endIndex,
                                                             int startPos,
                                                             int endPos)

Get char sequence of segment corresponding to sub-sequence in segment tree

Parameters:

segment - segment

startIndex - start index of sub-sequence of segment tree

endIndex - end index of sub-sequence of segment tree

startPos - start pos of sub-sequence segments in tree

endPos - end pos of sub-sequence segments in tree

Returns:

subsequence of segment corresponding to part of it which is in the sub-sequence of the tree

findSegmentPos

@Nullable
public @Nullable SegmentTreePos findSegmentPos(int index,
                                                         int startPos,
                                                         int endPos)

getSegment

@NotNull
public @NotNull Segment getSegment(int pos,
                                            @NotNull
                                            @NotNull BasedSequence baseSeq)

getPrevAnchor

@Nullable
public @Nullable Segment getPrevAnchor(int pos,
                                                 @NotNull
                                                 @NotNull BasedSequence baseSeq)

toString

@NotNull
public @NotNull String toString(@NotNull
                                         @NotNull BasedSequence baseSeq)

toString

@NotNull
public @NotNull String toString()

Overrides:

toString in class Object

aggrLength

public static int aggrLength(int pos,
                             int[] treeData)

byteOffsetData

public static int byteOffsetData(int pos,
                                 int[] treeData)

byteOffset

public static int byteOffset(int pos,
                             int[] treeData)

setTreeData

public static void setTreeData(int pos,
                               int[] treeData,
                               int agrrLength,
                               int byteOffset,
                               int prevAnchorOffset)

hasPreviousAnchor

public static boolean hasPreviousAnchor(int pos,
                                        int[] treeData)

previousAnchorOffset

public static int previousAnchorOffset(int pos,
                                       int[] treeData)

findSegmentPos

@Nullable
public static @Nullable SegmentTreePos findSegmentPos(int index,
                                                                int[] treeData,
                                                                int startPos,
                                                                int endPos)

findSegment

@Nullable
public static @Nullable Segment findSegment(int index,
                                                      int[] treeData,
                                                      int startPos,
                                                      int endPos,
                                                      byte[] segmentBytes,
                                                      @NotNull
                                                      @NotNull BasedSequence baseSeq)

getSegment

@NotNull
public static @NotNull Segment getSegment(int pos,
                                                   int[] treeData,
                                                   byte[] segmentBytes,
                                                   @NotNull
                                                   @NotNull BasedSequence baseSeq)

getPrevAnchor

@Nullable
public static @Nullable Segment getPrevAnchor(int pos,
                                                        int[] treeData,
                                                        byte[] segmentBytes,
                                                        @NotNull
                                                        @NotNull BasedSequence baseSeq)

build

@NotNull
public static @NotNull SegmentTree build(@NotNull
                                                  @NotNull Iterable<Seg> segments,
                                                  @NotNull
                                                  @NotNull CharSequence allText)

build

@NotNull
public static @NotNull SegmentTree build(@NotNull
                                                  @NotNull BasedSegmentBuilder builder)

buildTreeData

@NotNull
public static @NotNull SegmentTree.SegmentTreeData buildTreeData(@NotNull
                                                                          @NotNull Iterable<Seg> segments,
                                                                          @NotNull
                                                                          @NotNull CharSequence allText,
                                                                          boolean buildIndexData)

Build binary tree search data

Index data has aggregated lengths with BASE and TEXT segments in the data, Offset data has segment start offset with BASE and ANCHOR segments in the data since TEXT segments have no offset they are skipped

The offset data can be used to pass as treeData to findSegmentPos(int, int[], int, int) with desired offset instead of index to find a segment which can contain the desired offset, with some post processing logic to handle offset segments which are not in the data

Parameters:

segments - segments of the tree

allText - all out of base text

buildIndexData - true to build index search data, false to build base offset tree data

Returns:

segment tree instance with the data

getSegmentOffsetTree

@NotNull
public @NotNull SegmentOffsetTree getSegmentOffsetTree(@NotNull
                                                                @NotNull BasedSequence baseSeq)

Build an offset segment tree from this index segment tree

Efficiently reuses segmentBytes and only computes offset treeData for BASE and ANCHOR segments

Parameters:

baseSeq - base sequence for the sequence for this segment tree

Returns:

SegmentOffsetTree for this segment tree