You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lucene.apache.org by rm...@apache.org on 2011/08/30 01:13:23 UTC
svn commit: r1163047 [3/15] - in /lucene/dev/branches/flexscoring: ./
dev-tools/idea/lucene/contrib/ lucene/ lucene/contrib/
lucene/contrib/demo/src/java/org/apache/lucene/demo/
lucene/contrib/demo/src/java/org/apache/lucene/demo/xmlparser/ lucene/cont...
Modified: lucene/dev/branches/flexscoring/lucene/src/java/org/apache/lucene/document/Document.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/flexscoring/lucene/src/java/org/apache/lucene/document/Document.java?rev=1163047&r1=1163046&r2=1163047&view=diff
==============================================================================
--- lucene/dev/branches/flexscoring/lucene/src/java/org/apache/lucene/document/Document.java (original)
+++ lucene/dev/branches/flexscoring/lucene/src/java/org/apache/lucene/document/Document.java Mon Aug 29 23:13:10 2011
@@ -17,61 +17,55 @@ package org.apache.lucene.document;
* limitations under the License.
*/
-import java.util.*; // for javadoc
+import java.util.*;
+
+import org.apache.lucene.index.IndexReader; // for javadoc
+import org.apache.lucene.index.IndexableField;
import org.apache.lucene.search.IndexSearcher; // for javadoc
import org.apache.lucene.search.ScoreDoc; // for javadoc
-import org.apache.lucene.index.IndexReader; // for javadoc
+import org.apache.lucene.util.BytesRef;
/** Documents are the unit of indexing and search.
*
* A Document is a set of fields. Each field has a name and a textual value.
- * A field may be {@link Fieldable#isStored() stored} with the document, in which
+ * A field may be {@link IndexableField#stored() stored} with the document, in which
* case it is returned with search hits on the document. Thus each document
* should typically contain one or more stored fields which uniquely identify
* it.
*
- * <p>Note that fields which are <i>not</i> {@link Fieldable#isStored() stored} are
+ * <p>Note that fields which are <i>not</i> {@link IndexableField#stored() stored} are
* <i>not</i> available in documents retrieved from the index, e.g. with {@link
* ScoreDoc#doc} or {@link IndexReader#document(int)}.
*/
-public final class Document {
- List<Fieldable> fields = new ArrayList<Fieldable>();
- private float boost = 1.0f;
+public final class Document implements Iterable<IndexableField> {
+
+ private final List<IndexableField> fields = new ArrayList<IndexableField>();
/** Constructs a new document with no fields. */
public Document() {}
+ @Override
+ public Iterator<IndexableField> iterator() {
- /** Sets a boost factor for hits on any field of this document. This value
- * will be multiplied into the score of all hits on this document.
- *
- * <p>The default value is 1.0.
- *
- * <p>Values are multiplied into the value of {@link Fieldable#getBoost()} of
- * each field in this document. Thus, this method in effect sets a default
- * boost for the fields of this document.
- *
- * @see Fieldable#setBoost(float)
- */
- public void setBoost(float boost) {
- this.boost = boost;
- }
+ return new Iterator<IndexableField>() {
+ private int fieldUpto = 0;
+
+ @Override
+ public boolean hasNext() {
+ return fieldUpto < fields.size();
+ }
- /** Returns, at indexing time, the boost factor as set by {@link #setBoost(float)}.
- *
- * <p>Note that once a document is indexed this value is no longer available
- * from the index. At search time, for retrieved documents, this method always
- * returns 1. This however does not mean that the boost value set at indexing
- * time was ignored - it was just combined with other indexing time factors and
- * stored elsewhere, for better indexing and search performance. (For more
- * information see the "norm(t,d)" part of the scoring formula in
- * {@link org.apache.lucene.search.similarities.Similarity Similarity}.)
- *
- * @see #setBoost(float)
- */
- public float getBoost() {
- return boost;
+ @Override
+ public void remove() {
+ throw new UnsupportedOperationException();
+ }
+
+ @Override
+ public IndexableField next() {
+ return fields.get(fieldUpto++);
+ }
+ };
}
/**
@@ -84,7 +78,7 @@ public final class Document {
* a document has to be deleted from an index and a new changed version of that
* document has to be added.</p>
*/
- public final void add(Fieldable field) {
+ public final void add(IndexableField field) {
fields.add(field);
}
@@ -99,9 +93,9 @@ public final class Document {
* document has to be added.</p>
*/
public final void removeField(String name) {
- Iterator<Fieldable> it = fields.iterator();
+ Iterator<IndexableField> it = fields.iterator();
while (it.hasNext()) {
- Fieldable field = it.next();
+ IndexableField field = it.next();
if (field.name().equals(name)) {
it.remove();
return;
@@ -119,148 +113,15 @@ public final class Document {
* document has to be added.</p>
*/
public final void removeFields(String name) {
- Iterator<Fieldable> it = fields.iterator();
+ Iterator<IndexableField> it = fields.iterator();
while (it.hasNext()) {
- Fieldable field = it.next();
+ IndexableField field = it.next();
if (field.name().equals(name)) {
it.remove();
}
}
}
- /** Returns a field with the given name if any exist in this document, or
- * null. If multiple fields exists with this name, this method returns the
- * first value added.
- * Do not use this method with lazy loaded fields or {@link NumericField}.
- * @deprecated use {@link #getFieldable} instead and cast depending on
- * data type.
- * @throws ClassCastException if you try to retrieve a numerical or
- * lazy loaded field.
- */
- @Deprecated
- public final Field getField(String name) {
- return (Field) getFieldable(name);
- }
-
-
- /** Returns a field with the given name if any exist in this document, or
- * null. If multiple fields exists with this name, this method returns the
- * first value added.
- */
- public Fieldable getFieldable(String name) {
- for (Fieldable field : fields) {
- if (field.name().equals(name))
- return field;
- }
- return null;
- }
-
- /** Returns the string value of the field with the given name if any exist in
- * this document, or null. If multiple fields exist with this name, this
- * method returns the first value added. If only binary fields with this name
- * exist, returns null.
- * For {@link NumericField} it returns the string value of the number. If you want
- * the actual {@code NumericField} instance back, use {@link #getFieldable}.
- */
- public final String get(String name) {
- for (Fieldable field : fields) {
- if (field.name().equals(name) && (!field.isBinary()))
- return field.stringValue();
- }
- return null;
- }
-
- /** Returns a List of all the fields in a document.
- * <p>Note that fields which are <i>not</i> {@link Fieldable#isStored() stored} are
- * <i>not</i> available in documents retrieved from the
- * index, e.g. {@link IndexSearcher#doc(int)} or {@link
- * IndexReader#document(int)}.
- */
- public final List<Fieldable> getFields() {
- return fields;
- }
-
- private final static Field[] NO_FIELDS = new Field[0];
-
- /**
- * Returns an array of {@link Field}s with the given name.
- * This method returns an empty array when there are no
- * matching fields. It never returns null.
- * Do not use this method with lazy loaded fields or {@link NumericField}.
- *
- * @param name the name of the field
- * @return a <code>Field[]</code> array
- * @deprecated use {@link #getFieldable} instead and cast depending on
- * data type.
- * @throws ClassCastException if you try to retrieve a numerical or
- * lazy loaded field.
- */
- @Deprecated
- public final Field[] getFields(String name) {
- List<Field> result = new ArrayList<Field>();
- for (Fieldable field : fields) {
- if (field.name().equals(name)) {
- result.add((Field) field);
- }
- }
-
- if (result.size() == 0)
- return NO_FIELDS;
-
- return result.toArray(new Field[result.size()]);
- }
-
-
- private final static Fieldable[] NO_FIELDABLES = new Fieldable[0];
-
- /**
- * Returns an array of {@link Fieldable}s with the given name.
- * This method returns an empty array when there are no
- * matching fields. It never returns null.
- *
- * @param name the name of the field
- * @return a <code>Fieldable[]</code> array
- */
- public Fieldable[] getFieldables(String name) {
- List<Fieldable> result = new ArrayList<Fieldable>();
- for (Fieldable field : fields) {
- if (field.name().equals(name)) {
- result.add(field);
- }
- }
-
- if (result.size() == 0)
- return NO_FIELDABLES;
-
- return result.toArray(new Fieldable[result.size()]);
- }
-
-
- private final static String[] NO_STRINGS = new String[0];
-
- /**
- * Returns an array of values of the field specified as the method parameter.
- * This method returns an empty array when there are no
- * matching fields. It never returns null.
- * For {@link NumericField}s it returns the string value of the number. If you want
- * the actual {@code NumericField} instances back, use {@link #getFieldables}.
- * @param name the name of the field
- * @return a <code>String[]</code> of field values
- */
- public final String[] getValues(String name) {
- List<String> result = new ArrayList<String>();
- for (Fieldable field : fields) {
- if (field.name().equals(name) && (!field.isBinary()))
- result.add(field.stringValue());
- }
-
- if (result.size() == 0)
- return NO_STRINGS;
-
- return result.toArray(new String[result.size()]);
- }
-
- private final static byte[][] NO_BYTES = new byte[0][];
/**
* Returns an array of byte arrays for of the fields that have the name specified
@@ -271,17 +132,18 @@ public final class Document {
* @param name the name of the field
* @return a <code>byte[][]</code> of binary field values
*/
- public final byte[][] getBinaryValues(String name) {
- List<byte[]> result = new ArrayList<byte[]>();
- for (Fieldable field : fields) {
- if (field.name().equals(name) && (field.isBinary()))
- result.add(field.getBinaryValue());
+ public final BytesRef[] getBinaryValues(String name) {
+ final List<BytesRef> result = new ArrayList<BytesRef>();
+ for (IndexableField field : fields) {
+ if (field.name().equals(name)) {
+ final BytesRef bytes = field.binaryValue();
+ if (bytes != null) {
+ result.add(bytes);
+ }
+ }
}
- if (result.size() == 0)
- return NO_BYTES;
-
- return result.toArray(new byte[result.size()][]);
+ return result.toArray(new BytesRef[result.size()]);
}
/**
@@ -293,10 +155,72 @@ public final class Document {
* @param name the name of the field.
* @return a <code>byte[]</code> containing the binary field value or <code>null</code>
*/
- public final byte[] getBinaryValue(String name) {
- for (Fieldable field : fields) {
- if (field.name().equals(name) && (field.isBinary()))
- return field.getBinaryValue();
+ public final BytesRef getBinaryValue(String name) {
+ for (IndexableField field : fields) {
+ if (field.name().equals(name)) {
+ final BytesRef bytes = field.binaryValue();
+ if (bytes != null) {
+ return bytes;
+ }
+ }
+ }
+ return null;
+ }
+
+ /** Returns a field with the given name if any exist in this document, or
+ * null. If multiple fields exists with this name, this method returns the
+ * first value added.
+ */
+ public final IndexableField getField(String name) {
+ for (IndexableField field : fields) {
+ if (field.name().equals(name)) {
+ return field;
+ }
+ }
+ return null;
+ }
+
+ /**
+ * Returns an array of {@link IndexableField}s with the given name.
+ * This method returns an empty array when there are no
+ * matching fields. It never returns null.
+ *
+ * @param name the name of the field
+ * @return a <code>Fieldable[]</code> array
+ */
+ public IndexableField[] getFields(String name) {
+ List<IndexableField> result = new ArrayList<IndexableField>();
+ for (IndexableField field : fields) {
+ if (field.name().equals(name)) {
+ result.add(field);
+ }
+ }
+
+ return result.toArray(new IndexableField[result.size()]);
+ }
+
+ /** Returns a List of all the fields in a document.
+ * <p>Note that fields which are <i>not</i> stored are
+ * <i>not</i> available in documents retrieved from the
+ * index, e.g. {@link IndexSearcher#doc(int)} or {@link
+ * IndexReader#document(int)}.
+ */
+ public final List<IndexableField> getFields() {
+ return fields;
+ }
+
+ /** Returns the string value of the field with the given name if any exist in
+ * this document, or null. If multiple fields exist with this name, this
+ * method returns the first value added. If only binary fields with this name
+ * exist, returns null.
+ * For {@link NumericField} it returns the string value of the number. If you want
+ * the actual {@code NumericField} instance back, use {@link #getField}.
+ */
+ public final String get(String name) {
+ for (IndexableField field : fields) {
+ if (field.name().equals(name) && field.stringValue() != null) {
+ return field.stringValue();
+ }
}
return null;
}
@@ -307,7 +231,7 @@ public final class Document {
StringBuilder buffer = new StringBuilder();
buffer.append("Document<");
for (int i = 0; i < fields.size(); i++) {
- Fieldable field = fields.get(i);
+ IndexableField field = fields.get(i);
buffer.append(field.toString());
if (i != fields.size()-1)
buffer.append(" ");
Modified: lucene/dev/branches/flexscoring/lucene/src/java/org/apache/lucene/document/Field.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/flexscoring/lucene/src/java/org/apache/lucene/document/Field.java?rev=1163047&r1=1163046&r2=1163047&view=diff
==============================================================================
--- lucene/dev/branches/flexscoring/lucene/src/java/org/apache/lucene/document/Field.java (original)
+++ lucene/dev/branches/flexscoring/lucene/src/java/org/apache/lucene/document/Field.java Mon Aug 29 23:13:10 2011
@@ -21,514 +21,325 @@ import java.io.Reader;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.index.FieldInfo.IndexOptions;
-import org.apache.lucene.index.IndexWriter;
+import org.apache.lucene.index.IndexableField;
+import org.apache.lucene.index.values.PerDocFieldValues;
+import org.apache.lucene.index.values.ValueType;
+import org.apache.lucene.util.BytesRef;
/**
- A field is a section of a Document. Each field has two parts, a name and a
- value. Values may be free text, provided as a String or as a Reader, or they
- may be atomic keywords, which are not further processed. Such keywords may
- be used to represent dates, urls, etc. Fields are optionally stored in the
- index, so that they may be returned with hits on the document.
- */
+ * A field is a section of a Document. Each field has two parts, a name and a
+ * value. Values may be free text, provided as a String or as a Reader, or they
+ * may be atomic keywords, which are not further processed. Such keywords may be
+ * used to represent dates, urls, etc. Fields are optionally stored in the
+ * index, so that they may be returned with hits on the document.
+ */
-public final class Field extends AbstractField implements Fieldable {
+public class Field implements IndexableField {
+
+ protected FieldType type;
+ protected String name = "body";
+ // the data object for all different kind of field values
+ protected Object fieldsData;
+ // pre-analyzed tokenStream for indexed fields
+ protected TokenStream tokenStream;
+ // length/offset for all primitive types
+ protected PerDocFieldValues docValues;
- /** Specifies whether and how a field should be stored. */
- public static enum Store {
+ protected float boost = 1.0f;
- /** Store the original field value in the index. This is useful for short texts
- * like a document's title which should be displayed with the results. The
- * value is stored in its original form, i.e. no analyzer is used before it is
- * stored.
- */
- YES {
- @Override
- public boolean isStored() { return true; }
- },
-
- /** Do not store the field value in the index. */
- NO {
- @Override
- public boolean isStored() { return false; }
- };
-
- public abstract boolean isStored();
- }
-
- /** Specifies whether and how a field should be indexed. */
- public static enum Index {
-
- /** Do not index the field value. This field can thus not be searched,
- * but one can still access its contents provided it is
- * {@link Field.Store stored}. */
- NO {
- @Override
- public boolean isIndexed() { return false; }
- @Override
- public boolean isAnalyzed() { return false; }
- @Override
- public boolean omitNorms() { return true; }
- },
-
- /** Index the tokens produced by running the field's
- * value through an Analyzer. This is useful for
- * common text. */
- ANALYZED {
- @Override
- public boolean isIndexed() { return true; }
- @Override
- public boolean isAnalyzed() { return true; }
- @Override
- public boolean omitNorms() { return false; }
- },
-
- /** Index the field's value without using an Analyzer, so it can be searched.
- * As no analyzer is used the value will be stored as a single term. This is
- * useful for unique Ids like product numbers.
- */
- NOT_ANALYZED {
- @Override
- public boolean isIndexed() { return true; }
- @Override
- public boolean isAnalyzed() { return false; }
- @Override
- public boolean omitNorms() { return false; }
- },
-
- /** Expert: Index the field's value without an Analyzer,
- * and also disable the indexing of norms. Note that you
- * can also separately enable/disable norms by calling
- * {@link Field#setOmitNorms}. No norms means that
- * index-time field and document boosting and field
- * length normalization are disabled. The benefit is
- * less memory usage as norms take up one byte of RAM
- * per indexed field for every document in the index,
- * during searching. Note that once you index a given
- * field <i>with</i> norms disabled, enabling norms will
- * have no effect. In other words, for this to have the
- * above described effect on a field, one instance of
- * that field must be indexed with NOT_ANALYZED_NO_NORMS
- * at some point. */
- NOT_ANALYZED_NO_NORMS {
- @Override
- public boolean isIndexed() { return true; }
- @Override
- public boolean isAnalyzed() { return false; }
- @Override
- public boolean omitNorms() { return true; }
- },
-
- /** Expert: Index the tokens produced by running the
- * field's value through an Analyzer, and also
- * separately disable the storing of norms. See
- * {@link #NOT_ANALYZED_NO_NORMS} for what norms are
- * and why you may want to disable them. */
- ANALYZED_NO_NORMS {
- @Override
- public boolean isIndexed() { return true; }
- @Override
- public boolean isAnalyzed() { return true; }
- @Override
- public boolean omitNorms() { return true; }
- };
-
- /** Get the best representation of the index given the flags. */
- public static Index toIndex(boolean indexed, boolean analyzed) {
- return toIndex(indexed, analyzed, false);
- }
-
- /** Expert: Get the best representation of the index given the flags. */
- public static Index toIndex(boolean indexed, boolean analyzed, boolean omitNorms) {
-
- // If it is not indexed nothing else matters
- if (!indexed) {
- return Index.NO;
- }
-
- // typical, non-expert
- if (!omitNorms) {
- if (analyzed) {
- return Index.ANALYZED;
- }
- return Index.NOT_ANALYZED;
- }
-
- // Expert: Norms omitted
- if (analyzed) {
- return Index.ANALYZED_NO_NORMS;
- }
- return Index.NOT_ANALYZED_NO_NORMS;
- }
-
- public abstract boolean isIndexed();
- public abstract boolean isAnalyzed();
- public abstract boolean omitNorms();
+ public Field(String name, FieldType type) {
+ this.name = name;
+ this.type = type;
}
-
- /** Specifies whether and how a field should have term vectors. */
- public static enum TermVector {
-
- /** Do not store term vectors.
- */
- NO {
- @Override
- public boolean isStored() { return false; }
- @Override
- public boolean withPositions() { return false; }
- @Override
- public boolean withOffsets() { return false; }
- },
-
- /** Store the term vectors of each document. A term vector is a list
- * of the document's terms and their number of occurrences in that document. */
- YES {
- @Override
- public boolean isStored() { return true; }
- @Override
- public boolean withPositions() { return false; }
- @Override
- public boolean withOffsets() { return false; }
- },
-
- /**
- * Store the term vector + token position information
- *
- * @see #YES
- */
- WITH_POSITIONS {
- @Override
- public boolean isStored() { return true; }
- @Override
- public boolean withPositions() { return true; }
- @Override
- public boolean withOffsets() { return false; }
- },
+
+ public Field(String name, FieldType type, Reader reader) {
+ if (name == null) {
+ throw new NullPointerException("name cannot be null");
+ }
+ if (reader == null) {
+ throw new NullPointerException("reader cannot be null");
+ }
- /**
- * Store the term vector + Token offset information
- *
- * @see #YES
- */
- WITH_OFFSETS {
- @Override
- public boolean isStored() { return true; }
- @Override
- public boolean withPositions() { return false; }
- @Override
- public boolean withOffsets() { return true; }
- },
+ this.name = name;
+ this.fieldsData = reader;
+ this.type = type;
+ }
+
+ public Field(String name, FieldType type, TokenStream tokenStream) {
+ if (name == null) {
+ throw new NullPointerException("name cannot be null");
+ }
+ if (tokenStream == null) {
+ throw new NullPointerException("tokenStream cannot be null");
+ }
- /**
- * Store the term vector + Token position and offset information
- *
- * @see #YES
- * @see #WITH_POSITIONS
- * @see #WITH_OFFSETS
- */
- WITH_POSITIONS_OFFSETS {
- @Override
- public boolean isStored() { return true; }
- @Override
- public boolean withPositions() { return true; }
- @Override
- public boolean withOffsets() { return true; }
- };
-
- /** Get the best representation of a TermVector given the flags. */
- public static TermVector toTermVector(boolean stored, boolean withOffsets, boolean withPositions) {
-
- // If it is not stored, nothing else matters.
- if (!stored) {
- return TermVector.NO;
- }
-
- if (withOffsets) {
- if (withPositions) {
- return Field.TermVector.WITH_POSITIONS_OFFSETS;
- }
- return Field.TermVector.WITH_OFFSETS;
- }
-
- if (withPositions) {
- return Field.TermVector.WITH_POSITIONS;
- }
- return Field.TermVector.YES;
- }
-
- public abstract boolean isStored();
- public abstract boolean withPositions();
- public abstract boolean withOffsets();
+ this.name = name;
+ this.fieldsData = null;
+ this.tokenStream = tokenStream;
+ this.type = type;
}
+ public Field(String name, FieldType type, byte[] value) {
+ this(name, type, value, 0, value.length);
+ }
+
+ public Field(String name, FieldType type, byte[] value, int offset, int length) {
+ this.fieldsData = new BytesRef(value, offset, length);
+ this.type = type;
+ this.name = name;
+ }
+
+ public Field(String name, FieldType type, BytesRef bytes) {
+ this.fieldsData = bytes;
+ this.type = type;
+ this.name = name;
+ }
- /** The value of the field as a String, or null. If null, the Reader value or
- * binary value is used. Exactly one of stringValue(),
- * readerValue(), and getBinaryValue() must be set. */
- public String stringValue() { return fieldsData instanceof String ? (String)fieldsData : null; }
-
- /** The value of the field as a Reader, or null. If null, the String value or
- * binary value is used. Exactly one of stringValue(),
- * readerValue(), and getBinaryValue() must be set. */
- public Reader readerValue() { return fieldsData instanceof Reader ? (Reader)fieldsData : null; }
+ public Field(String name, FieldType type, String value) {
+ if (name == null) {
+ throw new IllegalArgumentException("name cannot be null");
+ }
+ if (value == null) {
+ throw new IllegalArgumentException("value cannot be null");
+ }
+ if (!type.stored() && !type.indexed()) {
+ throw new IllegalArgumentException("it doesn't make sense to have a field that "
+ + "is neither indexed nor stored");
+ }
+ if (!type.indexed() && !type.tokenized() && (type.storeTermVectors())) {
+ throw new IllegalArgumentException("cannot store term vector information "
+ + "for a field that is not indexed");
+ }
- /** The TokesStream for this field to be used when indexing, or null. If null, the Reader value
- * or String value is analyzed to produce the indexed tokens. */
- public TokenStream tokenStreamValue() { return tokenStream; }
-
+ this.type = type;
+ this.name = name;
+ this.fieldsData = value;
+ }
- /** <p>Expert: change the value of this field. This can
- * be used during indexing to re-use a single Field
- * instance to improve indexing speed by avoiding GC cost
- * of new'ing and reclaiming Field instances. Typically
- * a single {@link Document} instance is re-used as
- * well. This helps most on small documents.</p>
+ /**
+ * The value of the field as a String, or null. If null, the Reader value or
+ * binary value is used. Exactly one of stringValue(), readerValue(), and
+ * getBinaryValue() must be set.
+ */
+ public String stringValue() {
+ return fieldsData instanceof String ? (String) fieldsData : null;
+ }
+
+ /**
+ * The value of the field as a Reader, or null. If null, the String value or
+ * binary value is used. Exactly one of stringValue(), readerValue(), and
+ * getBinaryValue() must be set.
+ */
+ public Reader readerValue() {
+ return fieldsData instanceof Reader ? (Reader) fieldsData : null;
+ }
+
+ /**
+ * The TokesStream for this field to be used when indexing, or null. If null,
+ * the Reader value or String value is analyzed to produce the indexed tokens.
+ */
+ public TokenStream tokenStreamValue() {
+ return tokenStream;
+ }
+
+ /**
+ * <p>
+ * Expert: change the value of this field. This can be used during indexing to
+ * re-use a single Field instance to improve indexing speed by avoiding GC
+ * cost of new'ing and reclaiming Field instances. Typically a single
+ * {@link Document} instance is re-used as well. This helps most on small
+ * documents.
+ * </p>
*
- * <p>Each Field instance should only be used once
- * within a single {@link Document} instance. See <a
- * href="http://wiki.apache.org/lucene-java/ImproveIndexingSpeed">ImproveIndexingSpeed</a>
- * for details.</p> */
+ * <p>
+ * Each Field instance should only be used once within a single
+ * {@link Document} instance. See <a
+ * href="http://wiki.apache.org/lucene-java/ImproveIndexingSpeed"
+ * >ImproveIndexingSpeed</a> for details.
+ * </p>
+ */
public void setValue(String value) {
- if (isBinary) {
- throw new IllegalArgumentException("cannot set a String value on a binary field");
+ if (isBinary()) {
+ throw new IllegalArgumentException(
+ "cannot set a String value on a binary field");
}
fieldsData = value;
}
-
- /** Expert: change the value of this field. See <a href="#setValue(java.lang.String)">setValue(String)</a>. */
+
+ /**
+ * Expert: change the value of this field. See <a
+ * href="#setValue(java.lang.String)">setValue(String)</a>.
+ */
public void setValue(Reader value) {
- if (isBinary) {
- throw new IllegalArgumentException("cannot set a Reader value on a binary field");
+ if (isBinary()) {
+ throw new IllegalArgumentException(
+ "cannot set a Reader value on a binary field");
}
- if (isStored) {
- throw new IllegalArgumentException("cannot set a Reader value on a stored field");
+ if (stored()) {
+ throw new IllegalArgumentException(
+ "cannot set a Reader value on a stored field");
}
fieldsData = value;
}
-
- /** Expert: change the value of this field. See <a href="#setValue(java.lang.String)">setValue(String)</a>. */
+
+ /**
+ * Expert: change the value of this field. See <a
+ * href="#setValue(java.lang.String)">setValue(String)</a>.
+ */
public void setValue(byte[] value) {
- if (!isBinary) {
- throw new IllegalArgumentException("cannot set a byte[] value on a non-binary field");
+ if (!isBinary()) {
+ throw new IllegalArgumentException(
+ "cannot set a byte[] value on a non-binary field");
}
- fieldsData = value;
- binaryLength = value.length;
- binaryOffset = 0;
+ fieldsData = new BytesRef(value);
}
-
- /** Expert: change the value of this field. See <a href="#setValue(java.lang.String)">setValue(String)</a>. */
+
+ /**
+ * Expert: change the value of this field. See <a
+ * href="#setValue(java.lang.String)">setValue(String)</a>.
+ */
+ /*
public void setValue(byte[] value, int offset, int length) {
if (!isBinary) {
- throw new IllegalArgumentException("cannot set a byte[] value on a non-binary field");
+ throw new IllegalArgumentException(
+ "cannot set a byte[] value on a non-binary field");
}
fieldsData = value;
binaryLength = length;
binaryOffset = offset;
}
+ */
- /** Expert: sets the token stream to be used for indexing and causes isIndexed() and isTokenized() to return true.
- * May be combined with stored values from stringValue() or getBinaryValue() */
+ /**
+ * Expert: sets the token stream to be used for indexing and causes
+ * isIndexed() and isTokenized() to return true. May be combined with stored
+ * values from stringValue() or getBinaryValue()
+ */
public void setTokenStream(TokenStream tokenStream) {
- this.isIndexed = true;
- this.isTokenized = true;
+ if (!indexed() || !tokenized()) {
+ throw new IllegalArgumentException(
+ "cannot set token stream on non indexed and tokenized field");
+ }
this.tokenStream = tokenStream;
}
+
+ public String name() {
+ return name;
+ }
+
+ public float boost() {
+ return boost;
+ }
- /**
- * Create a field by specifying its name, value and how it will
- * be saved in the index. Term vectors will not be stored in the index.
- *
- * @param name The name of the field
- * @param value The string to process
- * @param store Whether <code>value</code> should be stored in the index
- * @param index Whether the field should be indexed, and if so, if it should
- * be tokenized before indexing
- * @throws NullPointerException if name or value is <code>null</code>
- * @throws IllegalArgumentException if the field is neither stored nor indexed
+ /** Sets the boost factor hits on this field. This value will be
+ * multiplied into the score of all hits on this this field of this
+ * document.
+ *
+ * <p>The boost is used to compute the norm factor for the field. By
+ * default, in the {@link org.apache.lucene.search.similarities.Similarity#computeNorm(FieldInvertState)} method,
+ * the boost value is multiplied by the length normalization factor and then
+ * rounded by {@link org.apache.lucene.search.similarities.DefaultSimilarity#encodeNormValue(float)} before it is stored in the
+ * index. One should attempt to ensure that this product does not overflow
+ * the range of that encoding.
+ *
+ * @see org.apache.lucene.search.similarities.Similarity#computeNorm(FieldInvertState)
+ * @see org.apache.lucene.search.similarities.DefaultSimilarity#encodeNormValue(float)
*/
- public Field(String name, String value, Store store, Index index) {
- this(name, value, store, index, TermVector.NO);
+ public void setBoost(float boost) {
+ this.boost = boost;
}
- /**
- * Create a field by specifying its name, value and how it will
- * be saved in the index.
- *
- * @param name The name of the field
- * @param value The string to process
- * @param store Whether <code>value</code> should be stored in the index
- * @param index Whether the field should be indexed, and if so, if it should
- * be tokenized before indexing
- * @param termVector Whether term vector should be stored
- * @throws NullPointerException if name or value is <code>null</code>
- * @throws IllegalArgumentException in any of the following situations:
- * <ul>
- * <li>the field is neither stored nor indexed</li>
- * <li>the field is not indexed but termVector is <code>TermVector.YES</code></li>
- * </ul>
- */
- public Field(String name, String value, Store store, Index index, TermVector termVector) {
- if (name == null)
- throw new NullPointerException("name cannot be null");
- if (value == null)
- throw new NullPointerException("value cannot be null");
- if (name.length() == 0 && value.length() == 0)
- throw new IllegalArgumentException("name and value cannot both be empty");
- if (index == Index.NO && store == Store.NO)
- throw new IllegalArgumentException("it doesn't make sense to have a field that "
- + "is neither indexed nor stored");
- if (index == Index.NO && termVector != TermVector.NO)
- throw new IllegalArgumentException("cannot store term vector information "
- + "for a field that is not indexed");
-
- this.name = name;
-
- this.fieldsData = value;
-
- this.isStored = store.isStored();
-
- this.isIndexed = index.isIndexed();
- this.isTokenized = index.isAnalyzed();
- this.omitNorms = index.omitNorms();
- if (index == Index.NO) {
- // note: now this reads even wierder than before
- this.indexOptions = IndexOptions.DOCS_AND_FREQS_AND_POSITIONS;
- }
+ public boolean numeric() {
+ return false;
+ }
- this.isBinary = false;
+ public Number numericValue() {
+ return null;
+ }
- setStoreTermVector(termVector);
+ public NumericField.DataType numericDataType() {
+ return null;
}
- /**
- * Create a tokenized and indexed field that is not stored. Term vectors will
- * not be stored. The Reader is read only when the Document is added to the index,
- * i.e. you may not close the Reader until {@link IndexWriter#addDocument(Document)}
- * has been called.
- *
- * @param name The name of the field
- * @param reader The reader with the content
- * @throws NullPointerException if name or reader is <code>null</code>
- */
- public Field(String name, Reader reader) {
- this(name, reader, TermVector.NO);
+ public BytesRef binaryValue() {
+ if (!isBinary()) {
+ return null;
+ } else {
+ return (BytesRef) fieldsData;
+ }
}
-
- /**
- * Create a tokenized and indexed field that is not stored, optionally with
- * storing term vectors. The Reader is read only when the Document is added to the index,
- * i.e. you may not close the Reader until {@link IndexWriter#addDocument(Document)}
- * has been called.
- *
- * @param name The name of the field
- * @param reader The reader with the content
- * @param termVector Whether term vector should be stored
- * @throws NullPointerException if name or reader is <code>null</code>
- */
- public Field(String name, Reader reader, TermVector termVector) {
- if (name == null)
- throw new NullPointerException("name cannot be null");
- if (reader == null)
- throw new NullPointerException("reader cannot be null");
-
- this.name = name;
- this.fieldsData = reader;
-
- this.isStored = false;
-
- this.isIndexed = true;
- this.isTokenized = true;
-
- this.isBinary = false;
-
- setStoreTermVector(termVector);
+
+ /** methods from inner FieldType */
+
+ public boolean isBinary() {
+ return fieldsData instanceof BytesRef;
}
-
- /**
- * Create a tokenized and indexed field that is not stored. Term vectors will
- * not be stored. This is useful for pre-analyzed fields.
- * The TokenStream is read only when the Document is added to the index,
- * i.e. you may not close the TokenStream until {@link IndexWriter#addDocument(Document)}
- * has been called.
- *
- * @param name The name of the field
- * @param tokenStream The TokenStream with the content
- * @throws NullPointerException if name or tokenStream is <code>null</code>
- */
- public Field(String name, TokenStream tokenStream) {
- this(name, tokenStream, TermVector.NO);
+
+ public boolean stored() {
+ return type.stored();
}
- /**
- * Create a tokenized and indexed field that is not stored, optionally with
- * storing term vectors. This is useful for pre-analyzed fields.
- * The TokenStream is read only when the Document is added to the index,
- * i.e. you may not close the TokenStream until {@link IndexWriter#addDocument(Document)}
- * has been called.
- *
- * @param name The name of the field
- * @param tokenStream The TokenStream with the content
- * @param termVector Whether term vector should be stored
- * @throws NullPointerException if name or tokenStream is <code>null</code>
- */
- public Field(String name, TokenStream tokenStream, TermVector termVector) {
- if (name == null)
- throw new NullPointerException("name cannot be null");
- if (tokenStream == null)
- throw new NullPointerException("tokenStream cannot be null");
-
- this.name = name;
- this.fieldsData = null;
- this.tokenStream = tokenStream;
-
- this.isStored = false;
-
- this.isIndexed = true;
- this.isTokenized = true;
-
- this.isBinary = false;
-
- setStoreTermVector(termVector);
+ public boolean indexed() {
+ return type.indexed();
+ }
+
+ public boolean tokenized() {
+ return type.tokenized();
+ }
+
+ public boolean omitNorms() {
+ return type.omitNorms();
+ }
+
+ public IndexOptions indexOptions() {
+ return type.indexOptions();
}
+
+ public boolean storeTermVectors() {
+ return type.storeTermVectors();
+ }
+
+ public boolean storeTermVectorOffsets() {
+ return type.storeTermVectorOffsets();
+ }
+
+ public boolean storeTermVectorPositions() {
+ return type.storeTermVectorPositions();
+ }
+
+ /** Prints a Field for human consumption. */
+ @Override
+ public String toString() {
+ StringBuilder result = new StringBuilder();
+ result.append(type.toString());
+ result.append('<');
+ result.append(name);
+ result.append(':');
+ if (fieldsData != null && type.lazy() == false) {
+ result.append(fieldsData);
+ }
+
+ result.append('>');
+ return result.toString();
+ }
- /**
- * Create a stored field with binary value. Optionally the value may be compressed.
- *
- * @param name The name of the field
- * @param value The binary value
- */
- public Field(String name, byte[] value) {
- this(name, value, 0, value.length);
+ public void setDocValues(PerDocFieldValues docValues) {
+ this.docValues = docValues;
}
- /**
- * Create a stored field with binary value. Optionally the value may be compressed.
- *
- * @param name The name of the field
- * @param value The binary value
- * @param offset Starting offset in value where this Field's bytes are
- * @param length Number of bytes to use for this Field, starting at offset
- */
- public Field(String name, byte[] value, int offset, int length) {
+ @Override
+ public PerDocFieldValues docValues() {
+ return null;
+ }
+
+ @Override
+ public ValueType docValuesType() {
+ return null;
+ }
- if (name == null)
- throw new IllegalArgumentException("name cannot be null");
- if (value == null)
- throw new IllegalArgumentException("value cannot be null");
-
- this.name = name;
- fieldsData = value;
-
- isStored = true;
- isIndexed = false;
- isTokenized = false;
- indexOptions = IndexOptions.DOCS_AND_FREQS_AND_POSITIONS;
- omitNorms = true;
-
- isBinary = true;
- binaryLength = length;
- binaryOffset = offset;
-
- setStoreTermVector(TermVector.NO);
+ /** Returns FieldType for this field. */
+ public FieldType getFieldType() {
+ return type;
}
}
Modified: lucene/dev/branches/flexscoring/lucene/src/java/org/apache/lucene/document/IndexDocValuesField.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/flexscoring/lucene/src/java/org/apache/lucene/document/IndexDocValuesField.java?rev=1163047&r1=1163046&r2=1163047&view=diff
==============================================================================
--- lucene/dev/branches/flexscoring/lucene/src/java/org/apache/lucene/document/IndexDocValuesField.java (original)
+++ lucene/dev/branches/flexscoring/lucene/src/java/org/apache/lucene/document/IndexDocValuesField.java Mon Aug 29 23:13:10 2011
@@ -20,16 +20,13 @@ import java.io.Reader;
import java.util.Comparator;
import org.apache.lucene.analysis.TokenStream;
-import org.apache.lucene.document.Field.Index;
-import org.apache.lucene.document.Field.Store;
-import org.apache.lucene.document.Field.TermVector;
import org.apache.lucene.index.values.PerDocFieldValues;
import org.apache.lucene.index.values.ValueType;
import org.apache.lucene.util.BytesRef;
/**
* <p>
- * This class provides a {@link AbstractField} that enables storing of typed
+ * This class provides a {@link Field} that enables storing of typed
* per-document values for scoring, sorting or value retrieval. Here's an
* example usage, adding an int value:
*
@@ -54,16 +51,14 @@ import org.apache.lucene.util.BytesRef;
* </pre>
*
* <p>
- * If doc values are stored in addition to an indexed ({@link Index}) or stored
- * ({@link Store}) value it's recommended to use the {@link IndexDocValuesField}'s
- * {@link #set(AbstractField)} API:
+ * If doc values are stored in addition to an indexed ({@link FieldType#setIndexed(boolean)}) or stored
+ * ({@link FieldType#setStored(boolean)}) value it's recommended to pass the appropriate {@link FieldType}
+ * when creating the field:
*
* <pre>
- * IndexDocValuesField field = new IndexDocValuesField(name);
- * Field indexedField = new Field(name, stringValue, Stored.NO, Indexed.ANALYZED);
+ * IndexDocValuesField field = new IndexDocValuesField(name, StringField.TYPE_STORED);
* Document document = new Document();
- * document.add(indexedField);
- * field.set(indexedField);
+ * document.add(field);
* for(all documents) {
* ...
* field.setInt(value)
@@ -73,7 +68,8 @@ import org.apache.lucene.util.BytesRef;
* </pre>
*
* */
-public class IndexDocValuesField extends AbstractField implements PerDocFieldValues {
+// TODO: maybe rename to DocValuesField?
+public class IndexDocValuesField extends Field implements PerDocFieldValues {
protected BytesRef bytes;
protected double doubleValue;
@@ -85,21 +81,27 @@ public class IndexDocValuesField extends
* Creates a new {@link IndexDocValuesField} with the given name.
*/
public IndexDocValuesField(String name) {
- super(name, Store.NO, Index.NO, TermVector.NO);
- setDocValues(this);
+ this(name, new FieldType());
}
- /**
- * Creates a {@link IndexDocValuesField} prototype
- */
- IndexDocValuesField() {
- this("");
+ public IndexDocValuesField(String name, FieldType type) {
+ this(name, type, null);
+ }
+
+ public IndexDocValuesField(String name, FieldType type, String value) {
+ super(name, type);
+ fieldsData = value;
+ }
+
+ @Override
+ public PerDocFieldValues docValues() {
+ return this;
}
/**
* Sets the given <code>long</code> value and sets the field's {@link ValueType} to
* {@link ValueType#VAR_INTS} unless already set. If you want to change the
- * default type use {@link #setType(ValueType)}.
+ * default type use {@link #setDocValuesType(ValueType)}.
*/
public void setInt(long value) {
setInt(value, false);
@@ -124,7 +126,7 @@ public class IndexDocValuesField extends
/**
* Sets the given <code>int</code> value and sets the field's {@link ValueType} to
* {@link ValueType#VAR_INTS} unless already set. If you want to change the
- * default type use {@link #setType(ValueType)}.
+ * default type use {@link #setDocValuesType(ValueType)}.
*/
public void setInt(int value) {
setInt(value, false);
@@ -149,7 +151,7 @@ public class IndexDocValuesField extends
/**
* Sets the given <code>short</code> value and sets the field's {@link ValueType} to
* {@link ValueType#VAR_INTS} unless already set. If you want to change the
- * default type use {@link #setType(ValueType)}.
+ * default type use {@link #setDocValuesType(ValueType)}.
*/
public void setInt(short value) {
setInt(value, false);
@@ -174,11 +176,12 @@ public class IndexDocValuesField extends
/**
* Sets the given <code>byte</code> value and sets the field's {@link ValueType} to
* {@link ValueType#VAR_INTS} unless already set. If you want to change the
- * default type use {@link #setType(ValueType)}.
+ * default type use {@link #setDocValuesType(ValueType)}.
*/
public void setInt(byte value) {
setInt(value, false);
}
+
/**
* Sets the given <code>byte</code> value as a 8 bit signed integer.
*
@@ -198,7 +201,7 @@ public class IndexDocValuesField extends
/**
* Sets the given <code>float</code> value and sets the field's {@link ValueType}
* to {@link ValueType#FLOAT_32} unless already set. If you want to
- * change the type use {@link #setType(ValueType)}.
+ * change the type use {@link #setDocValuesType(ValueType)}.
*/
public void setFloat(float value) {
if (type == null) {
@@ -210,7 +213,7 @@ public class IndexDocValuesField extends
/**
* Sets the given <code>double</code> value and sets the field's {@link ValueType}
* to {@link ValueType#FLOAT_64} unless already set. If you want to
- * change the default type use {@link #setType(ValueType)}.
+ * change the default type use {@link #setDocValuesType(ValueType)}.
*/
public void setFloat(double value) {
if (type == null) {
@@ -241,7 +244,7 @@ public class IndexDocValuesField extends
if (value == null) {
throw new IllegalArgumentException("value must not be null");
}
- setType(type);
+ setDocValuesType(type);
if (bytes == null) {
bytes = new BytesRef(value);
} else {
@@ -289,7 +292,7 @@ public class IndexDocValuesField extends
/**
* Sets the {@link ValueType} for this field.
*/
- public void setType(ValueType type) {
+ public void setDocValuesType(ValueType type) {
if (type == null) {
throw new IllegalArgumentException("Type must not be null");
}
@@ -297,13 +300,6 @@ public class IndexDocValuesField extends
}
/**
- * Returns the field's {@link ValueType}
- */
- public ValueType type() {
- return type;
- }
-
- /**
* Returns always <code>null</code>
*/
public Reader readerValue() {
@@ -313,36 +309,54 @@ public class IndexDocValuesField extends
/**
* Returns always <code>null</code>
*/
- public String stringValue() {
+ public TokenStream tokenStreamValue() {
return null;
}
- /**
- * Returns always <code>null</code>
- */
- public TokenStream tokenStreamValue() {
- return null;
+ @Override
+ public ValueType docValuesType() {
+ return type;
}
- /**
- * Sets this {@link IndexDocValuesField} to the given {@link AbstractField} and
- * returns the given field. Any modifications to this instance will be visible
- * to the given field.
- */
- public <T extends AbstractField> T set(T field) {
- field.setDocValues(this);
- return field;
+ @Override
+ public String toString() {
+ final String value;
+ switch (type) {
+ case BYTES_FIXED_DEREF:
+ case BYTES_FIXED_SORTED:
+ case BYTES_FIXED_STRAIGHT:
+ case BYTES_VAR_DEREF:
+ case BYTES_VAR_SORTED:
+ case BYTES_VAR_STRAIGHT:
+ value = "bytes:bytes.utf8ToString();";
+ break;
+ case VAR_INTS:
+ value = "int:" + longValue;
+ break;
+ case FLOAT_32:
+ value = "float32:" + doubleValue;
+ break;
+ case FLOAT_64:
+ value = "float64:" + doubleValue;
+ break;
+ default:
+ throw new IllegalArgumentException("unknown type: " + type);
+ }
+ return "<" + name() + ": IndexDocValuesField " + value + ">";
}
/**
- * Sets a new {@link PerDocFieldValues} instance on the given field with the
- * given type and returns it.
- *
+ * Returns an IndexDocValuesField holding the value from
+ * the provided string field, as the specified type. The
+ * incoming field must have a string value. The name, {@link
+ * FieldType} and string value are carried over from the
+ * incoming Field.
*/
- public static <T extends AbstractField> T set(T field, ValueType type) {
- if (field instanceof IndexDocValuesField)
- return field;
- final IndexDocValuesField valField = new IndexDocValuesField();
+ public static IndexDocValuesField build(Field field, ValueType type) {
+ if (field instanceof IndexDocValuesField) {
+ return (IndexDocValuesField) field;
+ }
+ final IndexDocValuesField valField = new IndexDocValuesField(field.name(), field.getFieldType(), field.stringValue());
switch (type) {
case BYTES_FIXED_DEREF:
case BYTES_FIXED_SORTED:
@@ -350,9 +364,7 @@ public class IndexDocValuesField extends
case BYTES_VAR_DEREF:
case BYTES_VAR_SORTED:
case BYTES_VAR_STRAIGHT:
- BytesRef ref = field.isBinary() ? new BytesRef(field.getBinaryValue(),
- field.getBinaryOffset(), field.getBinaryLength()) : new BytesRef(
- field.stringValue());
+ BytesRef ref = field.isBinary() ? field.binaryValue() : new BytesRef(field.stringValue());
valField.setBytes(ref, type);
break;
case VAR_INTS:
@@ -367,7 +379,6 @@ public class IndexDocValuesField extends
default:
throw new IllegalArgumentException("unknown type: " + type);
}
- return valField.set(field);
+ return valField;
}
-
}
Modified: lucene/dev/branches/flexscoring/lucene/src/java/org/apache/lucene/document/NumericField.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/flexscoring/lucene/src/java/org/apache/lucene/document/NumericField.java?rev=1163047&r1=1163046&r2=1163047&view=diff
==============================================================================
--- lucene/dev/branches/flexscoring/lucene/src/java/org/apache/lucene/document/NumericField.java (original)
+++ lucene/dev/branches/flexscoring/lucene/src/java/org/apache/lucene/document/NumericField.java Mon Aug 29 23:13:10 2011
@@ -22,28 +22,30 @@ import java.io.Reader;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.NumericTokenStream;
import org.apache.lucene.index.FieldInfo.IndexOptions;
+import org.apache.lucene.document.NumericField.DataType;
import org.apache.lucene.util.NumericUtils;
import org.apache.lucene.search.NumericRangeQuery; // javadocs
import org.apache.lucene.search.NumericRangeFilter; // javadocs
import org.apache.lucene.search.FieldCache; // javadocs
/**
- * <p>This class provides a {@link Field} that enables indexing
- * of numeric values for efficient range filtering and
- * sorting. Here's an example usage, adding an int value:
+ * <p>
+ * This class provides a {@link Field} that enables indexing of numeric values
+ * for efficient range filtering and sorting. Here's an example usage, adding an
+ * int value:
+ *
* <pre>
- * document.add(new NumericField(name).setIntValue(value));
+ * document.add(new NumericField(name).setIntValue(value));
* </pre>
- *
- * For optimal performance, re-use the
- * <code>NumericField</code> and {@link Document} instance for more than
- * one document:
- *
+ *
+ * For optimal performance, re-use the <code>NumericField</code> and
+ * {@link Document} instance for more than one document:
+ *
* <pre>
* NumericField field = new NumericField(name);
* Document document = new Document();
* document.add(field);
- *
+ *
* for(all documents) {
* ...
* field.setIntValue(value)
@@ -74,7 +76,7 @@ import org.apache.lucene.search.FieldCac
*
* <p>By default, a <code>NumericField</code>'s value is not stored but
* is indexed for range filtering and sorting. You can use
- * the {@link #NumericField(String,Field.Store,boolean)}
+ * the {@link #NumericField(String, FieldType)}
* constructor if you need to change these defaults.</p>
*
* <p>You may add the same field name as a <code>NumericField</code> to
@@ -102,7 +104,7 @@ import org.apache.lucene.search.FieldCac
* default value, 4, was selected for a reasonable tradeoff
* of disk space consumption versus performance. You can
* use the expert constructor {@link
- * #NumericField(String,int,Field.Store,boolean)} if you'd
+ * #NumericField(String,int,FieldType)} if you'd
* like to change the value. Note that you must also
* specify a congruent value when creating {@link
* NumericRangeQuery} or {@link NumericRangeFilter}.
@@ -129,94 +131,136 @@ import org.apache.lucene.search.FieldCac
*
* @since 2.9
*/
-public final class NumericField extends AbstractField {
-
+public final class NumericField extends Field {
+
/** Data type of the value in {@link NumericField}.
* @since 3.2
*/
public static enum DataType { INT, LONG, FLOAT, DOUBLE }
+ public static final FieldType TYPE_UNSTORED = new FieldType();
+ public static final FieldType TYPE_STORED = new FieldType();
+ static {
+ TYPE_UNSTORED.setIndexed(true);
+ TYPE_UNSTORED.setTokenized(true);
+ TYPE_UNSTORED.setOmitNorms(true);
+ TYPE_UNSTORED.setIndexOptions(IndexOptions.DOCS_ONLY);
+ TYPE_UNSTORED.freeze();
+
+ TYPE_STORED.setIndexed(true);
+ TYPE_STORED.setStored(true);
+ TYPE_STORED.setTokenized(true);
+ TYPE_STORED.setOmitNorms(true);
+ TYPE_STORED.setIndexOptions(IndexOptions.DOCS_ONLY);
+ TYPE_STORED.freeze();
+ }
+
+ //public static enum DataType { INT, LONG, FLOAT, DOUBLE }
+
+ private DataType dataType;
private transient NumericTokenStream numericTS;
- private DataType type;
private final int precisionStep;
-
+
/**
- * Creates a field for numeric values using the default <code>precisionStep</code>
- * {@link NumericUtils#PRECISION_STEP_DEFAULT} (4). The instance is not yet initialized with
- * a numeric value, before indexing a document containing this field,
- * set a value using the various set<em>???</em>Value() methods.
- * This constructor creates an indexed, but not stored field.
- * @param name the field name
+ * Creates a field for numeric values using the default
+ * <code>precisionStep</code> {@link NumericUtils#PRECISION_STEP_DEFAULT} (4).
+ * The instance is not yet initialized with a numeric value, before indexing a
+ * document containing this field, set a value using the various set
+ * <em>???</em>Value() methods. This constructor creates an indexed, but not
+ * stored field.
+ *
+ * @param name
+ * the field name
*/
public NumericField(String name) {
- this(name, NumericUtils.PRECISION_STEP_DEFAULT, Field.Store.NO, true);
+ this(name, NumericUtils.PRECISION_STEP_DEFAULT, NumericField.TYPE_UNSTORED);
}
/**
- * Creates a field for numeric values using the default <code>precisionStep</code>
- * {@link NumericUtils#PRECISION_STEP_DEFAULT} (4). The instance is not yet initialized with
- * a numeric value, before indexing a document containing this field,
- * set a value using the various set<em>???</em>Value() methods.
- * @param name the field name
- * @param store if the field should be stored, {@link Document#getFieldable}
- * then returns {@code NumericField} instances on search results.
- * @param index if the field should be indexed using {@link NumericTokenStream}
+ * Creates a field for numeric values using the default
+ * <code>precisionStep</code> {@link NumericUtils#PRECISION_STEP_DEFAULT} (4).
+ * The instance is not yet initialized with a numeric value, before indexing a
+ * document containing this field, set a value using the various set
+ * <em>???</em>Value() methods.
+ *
+ * @param name
+ * the field name
+ * @param type
+ * if the defualt field should be altered, e.g. stored,
+ * {@link Document#getField} then returns {@code NumericField}
+ * instances on search results, or indexed using
+ * {@link NumericTokenStream}
*/
- public NumericField(String name, Field.Store store, boolean index) {
- this(name, NumericUtils.PRECISION_STEP_DEFAULT, store, index);
+ public NumericField(String name, FieldType type) {
+ this(name, NumericUtils.PRECISION_STEP_DEFAULT, type);
}
/**
* Creates a field for numeric values with the specified
- * <code>precisionStep</code>. The instance is not yet initialized with
- * a numeric value, before indexing a document containing this field,
- * set a value using the various set<em>???</em>Value() methods.
- * This constructor creates an indexed, but not stored field.
- * @param name the field name
- * @param precisionStep the used <a href="../search/NumericRangeQuery.html#precisionStepDesc">precision step</a>
+ * <code>precisionStep</code>. The instance is not yet initialized with a
+ * numeric value, before indexing a document containing this field, set a
+ * value using the various set<em>???</em>Value() methods. This constructor
+ * creates an indexed, but not stored field.
+ *
+ * @param name
+ * the field name
+ * @param precisionStep
+ * the used <a
+ * href="../search/NumericRangeQuery.html#precisionStepDesc"
+ * >precision step</a>
*/
public NumericField(String name, int precisionStep) {
- this(name, precisionStep, Field.Store.NO, true);
+ this(name, precisionStep, NumericField.TYPE_UNSTORED);
}
-
+
/**
* Creates a field for numeric values with the specified
- * <code>precisionStep</code>. The instance is not yet initialized with
- * a numeric value, before indexing a document containing this field,
- * set a value using the various set<em>???</em>Value() methods.
- * @param name the field name
- * @param precisionStep the used <a href="../search/NumericRangeQuery.html#precisionStepDesc">precision step</a>
- * @param store if the field should be stored, {@link Document#getFieldable}
- * then returns {@code NumericField} instances on search results.
- * @param index if the field should be indexed using {@link NumericTokenStream}
+ * <code>precisionStep</code>. The instance is not yet initialized with a
+ * numeric value, before indexing a document containing this field, set a
+ * value using the various set<em>???</em>Value() methods.
+ *
+ * @param name
+ * the field name
+ * @param precisionStep
+ * the used <a
+ * href="../search/NumericRangeQuery.html#precisionStepDesc"
+ * >precision step</a>
+ * @param type
+ * if the defualt field should be altered, e.g. stored,
+ * {@link Document#getField} then returns {@code NumericField}
+ * instances on search results, or indexed using
+ * {@link NumericTokenStream}
*/
- public NumericField(String name, int precisionStep, Field.Store store, boolean index) {
- super(name, store, index ? Field.Index.ANALYZED_NO_NORMS : Field.Index.NO, Field.TermVector.NO);
+ public NumericField(String name, int precisionStep, FieldType type) {
+ super(name, type);
this.precisionStep = precisionStep;
- setIndexOptions(IndexOptions.DOCS_ONLY);
}
-
+
/** Returns a {@link NumericTokenStream} for indexing the numeric value. */
- public TokenStream tokenStreamValue() {
- if (!isIndexed())
- return null;
+ public TokenStream tokenStreamValue() {
+ if (!indexed()) return null;
if (numericTS == null) {
- // lazy init the TokenStream as it is heavy to instantiate (attributes,...),
+ // lazy init the TokenStream as it is heavy to instantiate
+ // (attributes,...),
// if not needed (stored field loading)
numericTS = new NumericTokenStream(precisionStep);
// initialize value in TokenStream
if (fieldsData != null) {
- assert type != null;
+ assert dataType != null;
final Number val = (Number) fieldsData;
- switch (type) {
+ switch (dataType) {
case INT:
- numericTS.setIntValue(val.intValue()); break;
+ numericTS.setIntValue(val.intValue());
+ break;
case LONG:
- numericTS.setLongValue(val.longValue()); break;
+ numericTS.setLongValue(val.longValue());
+ break;
case FLOAT:
- numericTS.setFloatValue(val.floatValue()); break;
+ numericTS.setFloatValue(val.floatValue());
+ break;
case DOUBLE:
- numericTS.setDoubleValue(val.doubleValue()); break;
+ numericTS.setDoubleValue(val.doubleValue());
+ break;
default:
assert false : "Should never get here";
}
@@ -226,26 +270,27 @@ public final class NumericField extends
}
/** Returns always <code>null</code> for numeric fields */
- @Override
- public byte[] getBinaryValue(byte[] result){
- return null;
- }
-
- /** Returns always <code>null</code> for numeric fields */
public Reader readerValue() {
return null;
}
-
- /** Returns the numeric value as a string. This format is also returned if you call {@link Document#get(String)}
- * on search results. It is recommended to use {@link Document#getFieldable} instead
- * that returns {@code NumericField} instances. You can then use {@link #getNumericValue}
- * to return the stored value. */
- public String stringValue() {
+
+ /**
+ * Returns the numeric value as a string. It is recommended to
+ * use {@link Document#getField} instead that returns {@code NumericField}
+ * instances. You can then use {@link #numericValue} to return the stored
+ * value.
+ */
+ @Override
+ public String stringValue() {
return (fieldsData == null) ? null : fieldsData.toString();
}
- /** Returns the current numeric value as a subclass of {@link Number}, <code>null</code> if not yet initialized. */
- public Number getNumericValue() {
+ /**
+ * Returns the current numeric value as a subclass of {@link Number},
+ * <code>null</code> if not yet initialized.
+ */
+ @Override
+ public Number numericValue() {
return (Number) fieldsData;
}
@@ -254,63 +299,79 @@ public final class NumericField extends
return precisionStep;
}
- /** Returns the data type of the current value, {@code null} if not yet set.
+ /**
+ * Returns the data type of the current value, {@code null} if not yet set.
+ *
* @since 3.2
*/
- public DataType getDataType() {
- return type;
+ @Override
+ public DataType numericDataType() {
+ return dataType;
}
-
+
+ @Override
+ public boolean numeric() {
+ return true;
+ }
+
/**
* Initializes the field with the supplied <code>long</code> value.
- * @param value the numeric value
+ *
+ * @param value
+ * the numeric value
* @return this instance, because of this you can use it the following way:
- * <code>document.add(new NumericField(name, precisionStep).setLongValue(value))</code>
+ * <code>document.add(new NumericField(name, precisionStep).setLongValue(value))</code>
*/
public NumericField setLongValue(final long value) {
if (numericTS != null) numericTS.setLongValue(value);
fieldsData = Long.valueOf(value);
- type = DataType.LONG;
+ dataType = DataType.LONG;
return this;
}
/**
* Initializes the field with the supplied <code>int</code> value.
- * @param value the numeric value
+ *
+ * @param value
+ * the numeric value
* @return this instance, because of this you can use it the following way:
- * <code>document.add(new NumericField(name, precisionStep).setIntValue(value))</code>
+ * <code>document.add(new NumericField(name, precisionStep).setIntValue(value))</code>
*/
public NumericField setIntValue(final int value) {
if (numericTS != null) numericTS.setIntValue(value);
fieldsData = Integer.valueOf(value);
- type = DataType.INT;
+ dataType = DataType.INT;
return this;
}
/**
* Initializes the field with the supplied <code>double</code> value.
- * @param value the numeric value
+ *
+ * @param value
+ * the numeric value
* @return this instance, because of this you can use it the following way:
- * <code>document.add(new NumericField(name, precisionStep).setDoubleValue(value))</code>
+ * <code>document.add(new NumericField(name, precisionStep).setDoubleValue(value))</code>
*/
public NumericField setDoubleValue(final double value) {
if (numericTS != null) numericTS.setDoubleValue(value);
fieldsData = Double.valueOf(value);
- type = DataType.DOUBLE;
+ dataType = DataType.DOUBLE;
return this;
}
/**
* Initializes the field with the supplied <code>float</code> value.
- * @param value the numeric value
+ *
+ * @param value
+ * the numeric value
* @return this instance, because of this you can use it the following way:
- * <code>document.add(new NumericField(name, precisionStep).setFloatValue(value))</code>
+ * <code>document.add(new NumericField(name, precisionStep).setFloatValue(value))</code>
*/
public NumericField setFloatValue(final float value) {
if (numericTS != null) numericTS.setFloatValue(value);
fieldsData = Float.valueOf(value);
- type = DataType.FLOAT;
+ dataType = DataType.FLOAT;
return this;
}
-
+
}
Modified: lucene/dev/branches/flexscoring/lucene/src/java/org/apache/lucene/document/package.html
URL: http://svn.apache.org/viewvc/lucene/dev/branches/flexscoring/lucene/src/java/org/apache/lucene/document/package.html?rev=1163047&r1=1163046&r2=1163047&view=diff
==============================================================================
--- lucene/dev/branches/flexscoring/lucene/src/java/org/apache/lucene/document/package.html (original)
+++ lucene/dev/branches/flexscoring/lucene/src/java/org/apache/lucene/document/package.html Mon Aug 29 23:13:10 2011
@@ -22,16 +22,16 @@
<body>
<p>The logical representation of a {@link org.apache.lucene.document.Document} for indexing and searching.</p>
<p>The document package provides the user level logical representation of content to be indexed and searched. The
-package also provides utilities for working with {@link org.apache.lucene.document.Document}s and {@link org.apache.lucene.document.Fieldable}s.</p>
-<h2>Document and Fieldable</h2>
-<p>A {@link org.apache.lucene.document.Document} is a collection of {@link org.apache.lucene.document.Fieldable}s. A
- {@link org.apache.lucene.document.Fieldable} is a logical representation of a user's content that needs to be indexed or stored.
- {@link org.apache.lucene.document.Fieldable}s have a number of properties that tell Lucene how to treat the content (like indexed, tokenized,
- stored, etc.) See the {@link org.apache.lucene.document.Field} implementation of {@link org.apache.lucene.document.Fieldable}
+package also provides utilities for working with {@link org.apache.lucene.document.Document}s and {@link org.apache.lucene.index.IndexableField}s.</p>
+<h2>Document and IndexableField</h2>
+<p>A {@link org.apache.lucene.document.Document} is a collection of {@link org.apache.lucene.index.IndexableField}s. A
+ {@link org.apache.lucene.index.IndexableField} is a logical representation of a user's content that needs to be indexed or stored.
+ {@link org.apache.lucene.index.IndexableField}s have a number of properties that tell Lucene how to treat the content (like indexed, tokenized,
+ stored, etc.) See the {@link org.apache.lucene.document.Field} implementation of {@link org.apache.lucene.index.IndexableField}
for specifics on these properties.
</p>
<p>Note: it is common to refer to {@link org.apache.lucene.document.Document}s having {@link org.apache.lucene.document.Field}s, even though technically they have
-{@link org.apache.lucene.document.Fieldable}s.</p>
+{@link org.apache.lucene.index.IndexableField}s.</p>
<h2>Working with Documents</h2>
<p>First and foremost, a {@link org.apache.lucene.document.Document} is something created by the user application. It is your job
to create Documents based on the content of the files you are working with in your application (Word, txt, PDF, Excel or any other format.)
@@ -44,13 +44,5 @@ package also provides utilities for work
(remember, Lucene only searches text). {@link org.apache.lucene.document.NumericField} is a special helper class
to simplify indexing of numeric values (and also dates) for fast range range queries with {@link org.apache.lucene.search.NumericRangeQuery}
(using a special sortable string representation of numeric values).</p>
-<p>The {@link org.apache.lucene.document.FieldSelector} class provides a mechanism to tell Lucene how to load Documents from
-storage. If no FieldSelector is used, all Fieldables on a Document will be loaded. As an example of the FieldSelector usage, consider
- the common use case of
-displaying search results on a web page and then having users click through to see the full document. In this scenario, it is often
- the case that there are many small fields and one or two large fields (containing the contents of the original file). Before the FieldSelector,
-the full Document had to be loaded, including the large fields, in order to display the results. Now, using the FieldSelector, one
-can {@link org.apache.lucene.document.FieldSelectorResult#LAZY_LOAD} the large fields, thus only loading the large fields
-when a user clicks on the actual link to view the original content.</p>
</body>
</html>
Modified: lucene/dev/branches/flexscoring/lucene/src/java/org/apache/lucene/index/CheckIndex.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/flexscoring/lucene/src/java/org/apache/lucene/index/CheckIndex.java?rev=1163047&r1=1163046&r2=1163047&view=diff
==============================================================================
--- lucene/dev/branches/flexscoring/lucene/src/java/org/apache/lucene/index/CheckIndex.java (original)
+++ lucene/dev/branches/flexscoring/lucene/src/java/org/apache/lucene/index/CheckIndex.java Mon Aug 29 23:13:10 2011
@@ -17,6 +17,16 @@ package org.apache.lucene.index;
* limitations under the License.
*/
+import org.apache.lucene.document.FieldType; // for javadocs
+import org.apache.lucene.search.DocIdSetIterator;
+import org.apache.lucene.search.IndexSearcher;
+import org.apache.lucene.search.TermQuery;
+import org.apache.lucene.store.Directory;
+import org.apache.lucene.store.IOContext;
+import org.apache.lucene.store.IndexInput;
+import org.apache.lucene.document.Document;
+import org.apache.lucene.index.codecs.CodecProvider;
+import org.apache.lucene.index.codecs.DefaultSegmentInfosWriter;
import java.io.File;
import java.io.IOException;
import java.io.PrintStream;
@@ -28,21 +38,11 @@ import java.util.HashMap;
import java.util.List;
import java.util.Map;
-import org.apache.lucene.document.AbstractField; // for javadocs
-import org.apache.lucene.document.Document;
import org.apache.lucene.index.codecs.BlockTreeTermsReader;
-import org.apache.lucene.index.codecs.CodecProvider;
-import org.apache.lucene.index.codecs.DefaultSegmentInfosWriter;
import org.apache.lucene.index.codecs.PerDocValues;
import org.apache.lucene.index.values.IndexDocValues;
import org.apache.lucene.index.values.ValuesEnum;
-import org.apache.lucene.search.DocIdSetIterator;
-import org.apache.lucene.search.IndexSearcher;
-import org.apache.lucene.search.TermQuery;
-import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
-import org.apache.lucene.store.IOContext;
-import org.apache.lucene.store.IndexInput;
import org.apache.lucene.util.Bits;
import org.apache.lucene.util.BytesRef;
import org.apache.lucene.util.StringHelper;
@@ -189,7 +189,7 @@ public class CheckIndex {
/** True if at least one of the fields in this segment
* has position data
- * @see AbstractField#setIndexOptions(org.apache.lucene.index.FieldInfo.IndexOptions) */
+ * @see FieldType#setIndexOptions(org.apache.lucene.index.FieldInfo.IndexOptions) */
public boolean hasProx;
/** Map that includes certain
Modified: lucene/dev/branches/flexscoring/lucene/src/java/org/apache/lucene/index/DirectoryReader.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/flexscoring/lucene/src/java/org/apache/lucene/index/DirectoryReader.java?rev=1163047&r1=1163046&r2=1163047&view=diff
==============================================================================
--- lucene/dev/branches/flexscoring/lucene/src/java/org/apache/lucene/index/DirectoryReader.java (original)
+++ lucene/dev/branches/flexscoring/lucene/src/java/org/apache/lucene/index/DirectoryReader.java Mon Aug 29 23:13:10 2011
@@ -29,8 +29,6 @@ import java.util.Map;
import java.util.Set;
import java.util.concurrent.ConcurrentHashMap;
-import org.apache.lucene.document.Document;
-import org.apache.lucene.document.FieldSelector;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.IOContext;
import org.apache.lucene.store.Lock;
@@ -559,12 +557,11 @@ class DirectoryReader extends IndexReade
return maxDoc;
}
- // inherit javadoc
@Override
- public Document document(int n, FieldSelector fieldSelector) throws CorruptIndexException, IOException {
+ public void document(int docID, StoredFieldVisitor visitor) throws CorruptIndexException, IOException {
ensureOpen();
- int i = readerIndex(n); // find segment num
- return subReaders[i].document(n - starts[i], fieldSelector); // dispatch to segment reader
+ int i = readerIndex(docID); // find segment num
+ subReaders[i].document(docID - starts[i], visitor); // dispatch to segment reader
}
@Override
Modified: lucene/dev/branches/flexscoring/lucene/src/java/org/apache/lucene/index/DocFieldConsumerPerField.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/flexscoring/lucene/src/java/org/apache/lucene/index/DocFieldConsumerPerField.java?rev=1163047&r1=1163046&r2=1163047&view=diff
==============================================================================
--- lucene/dev/branches/flexscoring/lucene/src/java/org/apache/lucene/index/DocFieldConsumerPerField.java (original)
+++ lucene/dev/branches/flexscoring/lucene/src/java/org/apache/lucene/index/DocFieldConsumerPerField.java Mon Aug 29 23:13:10 2011
@@ -18,11 +18,10 @@ package org.apache.lucene.index;
*/
import java.io.IOException;
-import org.apache.lucene.document.Fieldable;
abstract class DocFieldConsumerPerField {
/** Processes all occurrences of a single field */
- abstract void processFields(Fieldable[] fields, int count) throws IOException;
+ abstract void processFields(IndexableField[] fields, int count) throws IOException;
abstract void abort();
abstract FieldInfo getFieldInfo();
}
Modified: lucene/dev/branches/flexscoring/lucene/src/java/org/apache/lucene/index/DocFieldConsumersPerField.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/flexscoring/lucene/src/java/org/apache/lucene/index/DocFieldConsumersPerField.java?rev=1163047&r1=1163046&r2=1163047&view=diff
==============================================================================
--- lucene/dev/branches/flexscoring/lucene/src/java/org/apache/lucene/index/DocFieldConsumersPerField.java (original)
+++ lucene/dev/branches/flexscoring/lucene/src/java/org/apache/lucene/index/DocFieldConsumersPerField.java Mon Aug 29 23:13:10 2011
@@ -18,7 +18,6 @@ package org.apache.lucene.index;
*/
import java.io.IOException;
-import org.apache.lucene.document.Fieldable;
final class DocFieldConsumersPerField extends DocFieldConsumerPerField {
@@ -35,7 +34,7 @@ final class DocFieldConsumersPerField ex
}
@Override
- public void processFields(Fieldable[] fields, int count) throws IOException {
+ public void processFields(IndexableField[] fields, int count) throws IOException {
one.processFields(fields, count);
two.processFields(fields, count);
}
Modified: lucene/dev/branches/flexscoring/lucene/src/java/org/apache/lucene/index/DocFieldProcessor.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/flexscoring/lucene/src/java/org/apache/lucene/index/DocFieldProcessor.java?rev=1163047&r1=1163046&r2=1163047&view=diff
==============================================================================
--- lucene/dev/branches/flexscoring/lucene/src/java/org/apache/lucene/index/DocFieldProcessor.java (original)
+++ lucene/dev/branches/flexscoring/lucene/src/java/org/apache/lucene/index/DocFieldProcessor.java Mon Aug 29 23:13:10 2011
@@ -22,15 +22,13 @@ import java.util.Collection;
import java.util.Comparator;
import java.util.HashMap;
import java.util.HashSet;
-import java.util.List;
import java.util.Map;
-import org.apache.lucene.document.Document;
-import org.apache.lucene.document.Fieldable;
import org.apache.lucene.index.DocumentsWriterPerThread.DocState;
import org.apache.lucene.index.codecs.Codec;
-import org.apache.lucene.index.codecs.PerDocConsumer;
import org.apache.lucene.index.codecs.DocValuesConsumer;
+import org.apache.lucene.index.codecs.PerDocConsumer;
+import org.apache.lucene.index.values.PerDocFieldValues;
import org.apache.lucene.util.ArrayUtil;
import org.apache.lucene.util.IOUtils;
@@ -89,7 +87,7 @@ final class DocFieldProcessor extends Do
consumers.finish(state.numDocs);
};
// close perDocConsumer during flush to ensure all files are flushed due to PerCodec CFS
- IOUtils.closeSafely(true, perDocConsumers.values());
+ IOUtils.close(perDocConsumers.values());
}
@Override
@@ -110,7 +108,7 @@ final class DocFieldProcessor extends Do
}
}
try {
- IOUtils.closeSafely(true, perDocConsumers.values());
+ IOUtils.closeWhileHandlingException(perDocConsumers.values());
// TODO add abort to PerDocConsumer!
} catch (IOException e) {
// ignore on abort!
@@ -199,22 +197,16 @@ final class DocFieldProcessor extends Do
consumer.startDocument();
fieldsWriter.startDocument();
- final Document doc = docState.doc;
-
fieldCount = 0;
final int thisFieldGen = fieldGen++;
- final List<Fieldable> docFields = doc.getFields();
- final int numDocFields = docFields.size();
-
// Absorb any new fields first seen in this document.
// Also absorb any changes to fields we had already
// seen before (eg suddenly turning on norms or
// vectors, etc.):
- for(int i=0;i<numDocFields;i++) {
- Fieldable field = docFields.get(i);
+ for(IndexableField field : docState.doc) {
final String fieldName = field.name();
// Make sure we have a PerField allocated
@@ -231,21 +223,22 @@ final class DocFieldProcessor extends Do
// needs to be more "pluggable" such that if I want
// to have a new "thing" my Fields can do, I can
// easily add it
- FieldInfo fi = fieldInfos.addOrUpdate(fieldName, field.isIndexed(), field.isTermVectorStored(),
- field.isStorePositionWithTermVector(), field.isStoreOffsetWithTermVector(),
- field.getOmitNorms(), false, field.getIndexOptions(), field.docValuesType());
+ FieldInfo fi = fieldInfos.addOrUpdate(fieldName, field.indexed(), field.storeTermVectors(),
+ field.storeTermVectorPositions(), field.storeTermVectorOffsets(),
+ field.omitNorms(), false, field.indexOptions(), field.docValuesType());
fp = new DocFieldProcessorPerField(this, fi);
fp.next = fieldHash[hashPos];
fieldHash[hashPos] = fp;
totalFieldCount++;
- if (totalFieldCount >= fieldHash.length/2)
+ if (totalFieldCount >= fieldHash.length/2) {
rehash();
+ }
} else {
- fieldInfos.addOrUpdate(fp.fieldInfo.name, field.isIndexed(), field.isTermVectorStored(),
- field.isStorePositionWithTermVector(), field.isStoreOffsetWithTermVector(),
- field.getOmitNorms(), false, field.getIndexOptions(), field.docValuesType());
+ fieldInfos.addOrUpdate(fp.fieldInfo.name, field.indexed(), field.storeTermVectors(),
+ field.storeTermVectorPositions(), field.storeTermVectorOffsets(),
+ field.omitNorms(), false, field.indexOptions(), field.docValuesType());
}
if (thisFieldGen != fp.lastGen) {
@@ -266,12 +259,12 @@ final class DocFieldProcessor extends Do
fp.addField(field);
- if (field.isStored()) {
+ if (field.stored()) {
fieldsWriter.addField(field, fp.fieldInfo);
}
- if (field.hasDocValues()) {
- final DocValuesConsumer docValuesConsumer = docValuesConsumer(docState, fp.fieldInfo);
- docValuesConsumer.add(docState.docID, field.getDocValues());
+ final PerDocFieldValues docValues = field.docValues();
+ if (docValues != null) {
+ docValuesConsumer(docState, fp.fieldInfo).add(docState.docID, docValues);
}
}
@@ -339,5 +332,4 @@ final class DocFieldProcessor extends Do
docValues.put(fieldInfo.name, docValuesConsumer);
return docValuesConsumer;
}
-
}
Modified: lucene/dev/branches/flexscoring/lucene/src/java/org/apache/lucene/index/DocFieldProcessorPerField.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/flexscoring/lucene/src/java/org/apache/lucene/index/DocFieldProcessorPerField.java?rev=1163047&r1=1163046&r2=1163047&view=diff
==============================================================================
--- lucene/dev/branches/flexscoring/lucene/src/java/org/apache/lucene/index/DocFieldProcessorPerField.java (original)
+++ lucene/dev/branches/flexscoring/lucene/src/java/org/apache/lucene/index/DocFieldProcessorPerField.java Mon Aug 29 23:13:10 2011
@@ -17,7 +17,6 @@ package org.apache.lucene.index;
* limitations under the License.
*/
-import org.apache.lucene.document.Fieldable;
import org.apache.lucene.util.ArrayUtil;
import org.apache.lucene.util.RamUsageEstimator;
@@ -34,17 +33,17 @@ final class DocFieldProcessorPerField {
int lastGen = -1;
int fieldCount;
- Fieldable[] fields = new Fieldable[1];
+ IndexableField[] fields = new IndexableField[1];
public DocFieldProcessorPerField(final DocFieldProcessor docFieldProcessor, final FieldInfo fieldInfo) {
this.consumer = docFieldProcessor.consumer.addField(fieldInfo);
this.fieldInfo = fieldInfo;
}
- public void addField(Fieldable field) {
+ public void addField(IndexableField field) {
if (fieldCount == fields.length) {
int newSize = ArrayUtil.oversize(fieldCount + 1, RamUsageEstimator.NUM_BYTES_OBJECT_REF);
- Fieldable[] newArray = new Fieldable[newSize];
+ IndexableField[] newArray = new IndexableField[newSize];
System.arraycopy(fields, 0, newArray, 0, fieldCount);
fields = newArray;
}
Modified: lucene/dev/branches/flexscoring/lucene/src/java/org/apache/lucene/index/DocInverterPerField.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/flexscoring/lucene/src/java/org/apache/lucene/index/DocInverterPerField.java?rev=1163047&r1=1163046&r2=1163047&view=diff
==============================================================================
--- lucene/dev/branches/flexscoring/lucene/src/java/org/apache/lucene/index/DocInverterPerField.java (original)
+++ lucene/dev/branches/flexscoring/lucene/src/java/org/apache/lucene/index/DocInverterPerField.java Mon Aug 29 23:13:10 2011
@@ -19,7 +19,6 @@ package org.apache.lucene.index;
import java.io.IOException;
import java.io.Reader;
-import org.apache.lucene.document.Fieldable;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.tokenattributes.OffsetAttribute;
import org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute;
@@ -61,27 +60,32 @@ final class DocInverterPerField extends
}
@Override
- public void processFields(final Fieldable[] fields,
+ public void processFields(final IndexableField[] fields,
final int count) throws IOException {
- fieldState.reset(docState.doc.getBoost());
+ fieldState.reset();
final boolean doInvert = consumer.start(fields, count);
for(int i=0;i<count;i++) {
- final Fieldable field = fields[i];
+ final IndexableField field = fields[i];
// TODO FI: this should be "genericized" to querying
// consumer if it wants to see this particular field
// tokenized.
- if (field.isIndexed() && doInvert) {
+ if (field.indexed() && doInvert) {
if (i > 0)
fieldState.position += docState.analyzer == null ? 0 : docState.analyzer.getPositionIncrementGap(fieldInfo.name);
- if (!field.isTokenized()) { // un-tokenized field
- String stringValue = field.stringValue();
+ // TODO (LUCENE-2309): this analysis logic should be
+ // outside of indexer -- field should simply give us
+ // a TokenStream, even for multi-valued fields
+
+ if (!field.tokenized()) { // un-tokenized field
+ final String stringValue = field.stringValue();
+ assert stringValue != null;
final int valueLength = stringValue.length();
parent.singleToken.reinit(stringValue, 0, valueLength);
fieldState.attributeSource = parent.singleToken;
@@ -103,17 +107,17 @@ final class DocInverterPerField extends
final TokenStream stream;
final TokenStream streamValue = field.tokenStreamValue();
- if (streamValue != null)
+ if (streamValue != null) {
stream = streamValue;
- else {
+ } else {
// the field does not have a TokenStream,
// so we have to obtain one from the analyzer
final Reader reader; // find or make Reader
final Reader readerValue = field.readerValue();
- if (readerValue != null)
+ if (readerValue != null) {
reader = readerValue;
- else {
+ } else {
String stringValue = field.stringValue();
if (stringValue == null) {
throw new IllegalArgumentException("field must have either TokenStream, String or Reader value");
@@ -189,7 +193,7 @@ final class DocInverterPerField extends
}
fieldState.offset += docState.analyzer == null ? 0 : docState.analyzer.getOffsetGap(field);
- fieldState.boost *= field.getBoost();
+ fieldState.boost *= field.boost();
}
// LUCENE-2387: don't hang onto the field, so GC can