bruno-roustant commented on a change in pull request #980: LUCENE-8920: Reduce the memory used by direct addressing of arcs URL: https://github.com/apache/lucene-solr/pull/980#discussion_r344284113
########## File path: lucene/core/src/java/org/apache/lucene/util/fst/FST.java ########## @@ -864,6 +958,64 @@ private long readUnpackedNodeTarget(BytesReader in) throws IOException { return readNextRealArc(arc, in); } + /** + * Reads the presence bits of a direct-addressing node, store them in the provided arc {@link Arc#bitTable()} + * and returns the number of presence bytes. + */ + private int readPresenceBytes(Arc<T> arc, BytesReader in) throws IOException { + int numPresenceBytes = getNumPresenceBytes(arc.numArcs()); + long[] presenceBits = new long[(numPresenceBytes + 7) / Long.BYTES]; + for (int i = 0; i < numPresenceBytes; i++) { + // Read the next unsigned byte, shift it to the left, and appends it to the current long. + presenceBits[i / Long.BYTES] |= (in.readByte() & 0xFFL) << (i * Byte.SIZE); + } + arc.bitTable = presenceBits; + assert checkPresenceBytesAreValid(arc); + return numPresenceBytes; + } + + static boolean checkPresenceBytesAreValid(Arc arc) { + assert (arc.bitTable()[0] & 1L) != 0; // First bit must be set. + assert (arc.bitTable()[arc.bitTable().length - 1] & (1L << (arc.numArcs() - 1))) != 0; // Last bit must be set. + assert countBits(arc.bitTable()) <= arc.numArcs(); // Total bit set (real num arcs) must be <= label range (stored in arc.numArcs()). + return true; + } + + /** + * Counts all bits set in the provided longs. + */ + static int countBits(long[] bits) { Review comment: Ok ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@lucene.apache.org For additional commands, e-mail: issues-h...@lucene.apache.org