use of com.facebook.presto.orc.OrcCorruptionException in project presto by prestodb.
the class DecimalInputStream method nextLong.
public long nextLong() throws IOException {
long result = 0;
int offset = 0;
long b;
do {
b = input.read();
if (b == -1) {
throw new OrcCorruptionException(input.getOrcDataSourceId(), "Reading BigInteger past EOF");
}
long work = 0x7f & b;
if (offset >= 63 && (offset != 63 || work > 1)) {
throw new OrcCorruptionException(input.getOrcDataSourceId(), "Decimal does not fit long (invalid table schema?)");
}
result |= work << offset;
offset += 7;
} while (b >= 0x80);
boolean isNegative = (result & 0x01) != 0;
if (isNegative) {
result += 1;
result = -result;
result = result >> 1;
result |= 0x01L << 63;
} else {
result = result >> 1;
result &= MAX_VALUE;
}
return result;
}
use of com.facebook.presto.orc.OrcCorruptionException in project presto by prestodb.
the class SliceDirectBatchStreamReader method readBlock.
@Override
public Block readBlock() throws IOException {
if (!rowGroupOpen) {
openRowGroup();
}
if (readOffset > 0) {
if (presentStream != null) {
// skip ahead the present bit reader, but count the set bits
// and use this as the skip size for the length reader
readOffset = presentStream.countBitsSet(readOffset);
}
if (readOffset > 0) {
if (lengthStream == null) {
throw new OrcCorruptionException(streamDescriptor.getOrcDataSourceId(), "Value is not null but length stream is not present");
}
long dataSkipSize = lengthStream.sum(readOffset);
if (dataSkipSize > 0) {
if (dataStream == null) {
throw new OrcCorruptionException(streamDescriptor.getOrcDataSourceId(), "Value is not null but data stream is not present");
}
dataStream.skip(dataSkipSize);
}
}
}
if (lengthStream == null) {
if (presentStream == null) {
throw new OrcCorruptionException(streamDescriptor.getOrcDataSourceId(), "Value is null but present stream is missing");
}
presentStream.skip(nextBatchSize);
Block nullValueBlock = readAllNullsBlock();
readOffset = 0;
nextBatchSize = 0;
return nullValueBlock;
}
// create new isNullVector and offsetVector for VariableWidthBlock
boolean[] isNullVector = null;
// We will use the offsetVector as the buffer to read the length values from lengthStream,
// and the length values will be converted in-place to an offset vector.
int[] offsetVector = new int[nextBatchSize + 1];
if (presentStream == null) {
lengthStream.next(offsetVector, nextBatchSize);
} else {
isNullVector = new boolean[nextBatchSize];
int nullCount = presentStream.getUnsetBits(nextBatchSize, isNullVector);
if (nullCount == nextBatchSize) {
// all nulls
Block nullValueBlock = readAllNullsBlock();
readOffset = 0;
nextBatchSize = 0;
return nullValueBlock;
}
if (nullCount == 0) {
isNullVector = null;
lengthStream.next(offsetVector, nextBatchSize);
} else {
lengthStream.next(offsetVector, nextBatchSize - nullCount);
unpackLengthNulls(offsetVector, isNullVector, nextBatchSize - nullCount);
}
}
// Calculate the total length for all entries. Note that the values in the offsetVector are still length values now.
long totalLength = 0;
for (int i = 0; i < nextBatchSize; i++) {
totalLength += offsetVector[i];
}
int currentBatchSize = nextBatchSize;
readOffset = 0;
nextBatchSize = 0;
if (totalLength == 0) {
return new VariableWidthBlock(currentBatchSize, EMPTY_SLICE, offsetVector, Optional.ofNullable(isNullVector));
}
if (totalLength > ONE_GIGABYTE) {
throw new GenericInternalException(format("Values in column \"%s\" are too large to process for Presto. %s column values are larger than 1GB [%s]", streamDescriptor.getFieldName(), currentBatchSize, streamDescriptor.getOrcDataSourceId()));
}
if (dataStream == null) {
throw new OrcCorruptionException(streamDescriptor.getOrcDataSourceId(), "Value is not null but data stream is missing");
}
// allocate enough space to read
byte[] data = new byte[toIntExact(totalLength)];
Slice slice = Slices.wrappedBuffer(data);
if (maxCodePointCount < 0) {
// unbounded, simply read all data in on shot
dataStream.next(data, 0, data.length);
convertLengthVectorToOffsetVector(offsetVector);
} else {
// We do the following operations together in the for loop:
// * truncate strings
// * convert original length values in offsetVector into truncated offset values
int currentLength = offsetVector[0];
offsetVector[0] = 0;
for (int i = 1; i <= currentBatchSize; i++) {
int nextLength = offsetVector[i];
if (isNullVector != null && isNullVector[i - 1]) {
checkState(currentLength == 0, "Corruption in slice direct stream: length is non-zero for null entry");
offsetVector[i] = offsetVector[i - 1];
currentLength = nextLength;
continue;
}
int offset = offsetVector[i - 1];
// read data without truncation
dataStream.next(data, offset, offset + currentLength);
// adjust offsetVector with truncated length
int truncatedLength = computeTruncatedLength(slice, offset, currentLength, maxCodePointCount, isCharType);
verify(truncatedLength >= 0);
offsetVector[i] = offset + truncatedLength;
currentLength = nextLength;
}
}
// this can lead to over-retention but unlikely to happen given truncation rarely happens
return new VariableWidthBlock(currentBatchSize, slice, offsetVector, Optional.ofNullable(isNullVector));
}
use of com.facebook.presto.orc.OrcCorruptionException in project presto by prestodb.
the class LongInputStreamV1 method readHeader.
private void readHeader() throws IOException {
int control = input.read();
if (control == -1) {
throw new OrcCorruptionException(input.getOrcDataSourceId(), "Read past end of RLE integer");
}
if (control < 0x80) {
numValuesInRun = control + MIN_REPEAT_SIZE;
used = 0;
repeat = true;
delta = input.read();
if (delta == -1) {
throw new OrcCorruptionException(input.getOrcDataSourceId(), "End of stream in RLE Integer");
}
// convert from 0 to 255 to -128 to 127 by converting to a signed byte
delta = (byte) delta;
repeatBase = input.readVarint(signed);
} else {
numValuesInRun = 0x100 - control;
used = 0;
repeat = false;
}
}
use of com.facebook.presto.orc.OrcCorruptionException in project presto by prestodb.
the class LongInputStreamV1 method next.
@Override
public void next(int[] values, int items) throws IOException {
int offset = 0;
while (items > 0) {
if (used == numValuesInRun) {
numValuesInRun = 0;
used = 0;
readHeader();
}
int chunkSize = min(numValuesInRun - used, items);
if (repeat) {
for (int i = 0; i < chunkSize; i++) {
long literal = repeatBase + ((used + i) * delta);
int value = (int) literal;
if (literal != value) {
throw new OrcCorruptionException(input.getOrcDataSourceId(), "Decoded value out of range for a 32bit number");
}
values[offset + i] = value;
}
} else {
for (int i = 0; i < chunkSize; i++) {
long literal = input.readVarint(signed);
int value = (int) literal;
if (literal != value) {
throw new OrcCorruptionException(input.getOrcDataSourceId(), "Decoded value out of range for a 32bit number");
}
values[offset + i] = value;
}
}
used += chunkSize;
offset += chunkSize;
items -= chunkSize;
}
}
use of com.facebook.presto.orc.OrcCorruptionException in project presto by prestodb.
the class LongInputStreamV1 method next.
@Override
public void next(short[] values, int items) throws IOException {
int offset = 0;
while (items > 0) {
if (used == numValuesInRun) {
numValuesInRun = 0;
used = 0;
readHeader();
}
int chunkSize = min(numValuesInRun - used, items);
if (repeat) {
for (int i = 0; i < chunkSize; i++) {
long literal = repeatBase + ((used + i) * delta);
short value = (short) literal;
if (literal != value) {
throw new OrcCorruptionException(input.getOrcDataSourceId(), "Decoded value out of range for a 16bit number");
}
values[offset + i] = value;
}
} else {
for (int i = 0; i < chunkSize; i++) {
long literal = input.readVarint(signed);
short value = (short) literal;
if (literal != value) {
throw new OrcCorruptionException(input.getOrcDataSourceId(), "Decoded value out of range for a 16bit number");
}
values[offset + i] = value;
}
}
used += chunkSize;
offset += chunkSize;
items -= chunkSize;
}
}
Aggregations