/// <summary>
/// Construct a Taxonomy writer.
/// </summary>
/// <param name="directory">
/// The <seealso cref="Directory"/> in which to store the taxonomy. Note that
/// the taxonomy is written directly to that directory (not to a
/// subdirectory of it). </param>
/// <param name="openMode">
/// Specifies how to open a taxonomy for writing: <code>APPEND</code>
/// means open an existing index for append (failing if the index does
/// not yet exist). <code>CREATE</code> means create a new index (first
/// deleting the old one if it already existed).
/// <code>APPEND_OR_CREATE</code> appends to an existing index if there
/// is one, otherwise it creates a new index. </param>
/// <param name="cache">
/// A <seealso cref="TaxonomyWriterCache"/> implementation which determines
/// the in-memory caching policy. See for example
/// <seealso cref="LruTaxonomyWriterCache"/> and <seealso cref="Cl2oTaxonomyWriterCache"/>.
/// If null or missing, <seealso cref="#defaultTaxonomyWriterCache()"/> is used. </param>
/// <exception cref="CorruptIndexException">
/// if the taxonomy is corrupted. </exception>
/// <exception cref="LockObtainFailedException">
/// if the taxonomy is locked by another writer. If it is known
/// that no other concurrent writer is active, the lock might
/// have been left around by an old dead process, and should be
/// removed using <seealso cref="#unlock(Directory)"/>. </exception>
/// <exception cref="IOException">
/// if another error occurred. </exception>
public DirectoryTaxonomyWriter(Directory directory, OpenMode openMode, TaxonomyWriterCache cache)
{
dir = directory;
IndexWriterConfig config = CreateIndexWriterConfig(openMode);
indexWriter = OpenIndexWriter(dir, config);
// verify (to some extent) that merge policy in effect would preserve category docids
if (indexWriter != null)
{
Debug.Assert(!(indexWriter.Config.MergePolicy is TieredMergePolicy), "for preserving category docids, merging none-adjacent segments is not allowed");
}
// after we opened the writer, and the index is locked, it's safe to check
// the commit data and read the index epoch
openMode = config.OpenMode.HasValue ? config.OpenMode.Value : OpenMode.CREATE_OR_APPEND;
if (!DirectoryReader.IndexExists(directory))
{
indexEpoch = 1;
}
else
{
string epochStr = null;
IDictionary<string, string> commitData = ReadCommitData(directory);
if (commitData != null && commitData.ContainsKey(INDEX_EPOCH))
{
epochStr = commitData[INDEX_EPOCH];
}
// no commit data, or no epoch in it means an old taxonomy, so set its epoch to 1, for lack
// of a better value.
indexEpoch = epochStr == null ? 1 : Convert.ToInt64(epochStr, 16);
}
if (openMode == OpenMode.CREATE)
{
++indexEpoch;
}
FieldType ft = new FieldType(TextField.TYPE_NOT_STORED);
ft.OmitNorms = true;
parentStreamField = new Field(Consts.FIELD_PAYLOADS, parentStream, ft);
fullPathField = new StringField(Consts.FULL, "", Field.Store.YES);
if (indexWriter == null)
return;
nextID = indexWriter.MaxDoc;
if (cache == null)
{
cache = DefaultTaxonomyWriterCache();
}
this.cache = cache;
if (nextID == 0)
{
cacheIsComplete = true;
// Make sure that the taxonomy always contain the root category
// with category id 0.
AddCategory(new FacetLabel());
}
else
{
// There are some categories on the disk, which we have not yet
// read into the cache, and therefore the cache is incomplete.
// We choose not to read all the categories into the cache now,
// to avoid terrible performance when a taxonomy index is opened
// to add just a single category. We will do it later, after we
// notice a few cache misses.
cacheIsComplete = false;
}
}
/// <summary>
/// Construct a Taxonomy writer.
/// </summary>
/// <param name="directory">
/// The <seealso cref="Directory"/> in which to store the taxonomy. Note that
/// the taxonomy is written directly to that directory (not to a
/// subdirectory of it). </param>
/// <param name="openMode">
/// Specifies how to open a taxonomy for writing: <code>APPEND</code>
/// means open an existing index for append (failing if the index does
/// not yet exist). <code>CREATE</code> means create a new index (first
/// deleting the old one if it already existed).
/// <code>APPEND_OR_CREATE</code> appends to an existing index if there
/// is one, otherwise it creates a new index. </param>
/// <param name="cache">
/// A <seealso cref="TaxonomyWriterCache"/> implementation which determines
/// the in-memory caching policy. See for example
/// <seealso cref="LruTaxonomyWriterCache"/> and <seealso cref="Cl2oTaxonomyWriterCache"/>.
/// If null or missing, <seealso cref="#defaultTaxonomyWriterCache()"/> is used. </param>
/// <exception cref="CorruptIndexException">
/// if the taxonomy is corrupted. </exception>
/// <exception cref="LockObtainFailedException">
/// if the taxonomy is locked by another writer. If it is known
/// that no other concurrent writer is active, the lock might
/// have been left around by an old dead process, and should be
/// removed using <seealso cref="#unlock(Directory)"/>. </exception>
/// <exception cref="IOException">
/// if another error occurred. </exception>
public DirectoryTaxonomyWriter(Directory directory, OpenMode openMode, TaxonomyWriterCache cache)
{
dir = directory;
IndexWriterConfig config = CreateIndexWriterConfig(openMode);
indexWriter = OpenIndexWriter(dir, config);
// verify (to some extent) that merge policy in effect would preserve category docids
if (indexWriter != null)
{
Debug.Assert(!(indexWriter.Config.MergePolicy is TieredMergePolicy), "for preserving category docids, merging none-adjacent segments is not allowed");
}
// after we opened the writer, and the index is locked, it's safe to check
// the commit data and read the index epoch
openMode = config.OpenMode.HasValue ? config.OpenMode.Value : OpenMode.CREATE_OR_APPEND;
if (!DirectoryReader.IndexExists(directory))
{
indexEpoch = 1;
}
else
{
string epochStr = null;
IDictionary <string, string> commitData = ReadCommitData(directory);
if (commitData != null && commitData.ContainsKey(INDEX_EPOCH))
{
epochStr = commitData[INDEX_EPOCH];
}
// no commit data, or no epoch in it means an old taxonomy, so set its epoch to 1, for lack
// of a better value.
indexEpoch = epochStr == null ? 1 : Convert.ToInt64(epochStr, 16);
}
if (openMode == OpenMode.CREATE)
{
++indexEpoch;
}
FieldType ft = new FieldType(TextField.TYPE_NOT_STORED);
ft.OmitNorms = true;
parentStreamField = new Field(Consts.FIELD_PAYLOADS, parentStream, ft);
fullPathField = new StringField(Consts.FULL, "", Field.Store.YES);
if (indexWriter == null)
{
return;
}
nextID = indexWriter.MaxDoc;
if (cache == null)
{
cache = DefaultTaxonomyWriterCache();
}
this.cache = cache;
if (nextID == 0)
{
cacheIsComplete = true;
// Make sure that the taxonomy always contain the root category
// with category id 0.
AddCategory(new FacetLabel());
}
else
{
// There are some categories on the disk, which we have not yet
// read into the cache, and therefore the cache is incomplete.
// We choose not to read all the categories into the cache now,
// to avoid terrible performance when a taxonomy index is opened
// to add just a single category. We will do it later, after we
// notice a few cache misses.
cacheIsComplete = false;
}
}
