if (memOnly == false
&& ((StoreFileScanner) kvs).shouldSeek(scan, columns)) {
scanners.add(kvs);
}if (!scan.isGetScan()) {
return true;
}
byte[] row = scan.getStartRow();
switch (this.bloomFilterType) {
case ROW:
return passesBloomFilter(row, 0, row.length, null, 0, 0);
case ROWCOL:
if (columns != null && columns.size() == 1) {
byte[] column = columns.first();
return passesBloomFilter(row, 0, row.length, column, 0, column.length);
}
// For multi-column queries the Bloom filter is checked from the
// seekExact operation.
return true;
default:
return true;
}// Seek all scanners to the start of the Row (or if the exact matching row
// key does not exist, then to the start of the next matching Row).
if (matcher.isExactColumnQuery()) {
for (KeyValueScanner scanner : scanners)
scanner.seekExactly(matcher.getStartKey(), false);
} else {
for (KeyValueScanner scanner : scanners)
scanner.seek(matcher.getStartKey());
}public boolean seekExactly(KeyValue kv, boolean forward)
throws IOException {
if (reader.getBloomFilterType() != StoreFile.BloomType.ROWCOL ||
kv.getRowLength() == 0 || kv.getQualifierLength() == 0) {
return forward ? reseek(kv) : seek(kv);
}
boolean isInBloom = reader.passesBloomFilter(kv.getBuffer(),
kv.getRowOffset(), kv.getRowLength(), kv.getBuffer(),
kv.getQualifierOffset(), kv.getQualifierLength());
if (isInBloom) {
// This row/column might be in this store file. Do a normal seek.
return forward ? reseek(kv) : seek(kv);
}
// Create a fake key/value, so that this scanner only bubbles up to the top
// of the KeyValueHeap in StoreScanner after we scanned this row/column in
// all other store files. The query matcher will then just skip this fake
// key/value and the store scanner will progress to the next column.
cur = kv.createLastOnRowCol();
return true;
}由于Bloom Filter是须要事先知道过滤项的。对于顺序scan是没有事先办法知道rowkey的。
而get是指明了rowkey所以能够用Bloom Filter,scan指明column同理。
原文:http://www.cnblogs.com/yutingliuyl/p/6812531.html