public TermExpression(IXTable source, IXColumn left, CompareOperator op, IXColumn right)
{
_evaluate = EvaluateNormal;
// Save arguments as-is for ToString()
_left = left;
_cOp = op;
_right = right;
// Disallow constant <op> constant [likely error not wrapping column name]
if (_left is ConstantColumn && _right is ConstantColumn)
{
throw new ArgumentException($"({left} {op.ToQueryForm()} {right}) is comparing two constants. Wrap [ColumnNames] in braces.");
}
// If the left side is a constant and the operator can be swapped, move it to the right side.
// Comparers can check if the right side is constant and run a faster loop when that's the case.
if (_left.IsConstantColumn() && !(_right.IsConstantColumn()))
{
if (op.TryInvertCompareOperator(out op))
{
_left = right;
_right = left;
}
}
// Disallow unquoted constants used as strings
if (_right.IsConstantColumn() && _left.ColumnDetails.Type == typeof(String8) && _right.ColumnDetails.Type == typeof(String8))
{
ConstantColumn cRight = _right as ConstantColumn;
if (cRight != null && !cRight.IsNull && cRight.WasUnwrappedLiteral)
{
throw new ArgumentException($"{right} is compared to a string, but is unquoted. Strings must be quoted.");
}
}
// Convert the right side to the left side type if required
// This means constants will always be casted to the other side type.
if (_left.ColumnDetails.Type != _right.ColumnDetails.Type)
{
_right = CastedColumn.Build(source, _right, _left.ColumnDetails.Type, ValueKinds.Invalid);
}
// Get the left and right getters
_leftGetter = _left.CurrentGetter();
_rightGetter = _right.CurrentGetter();
// Null comparison is generic
if (_right.IsNullConstant())
{
if (op == CompareOperator.Equal)
{
_comparer = WhereIsNull;
}
else if (op == CompareOperator.NotEqual)
{
_comparer = WhereIsNotNull;
}
else
{
throw new ArgumentException($"Only equals and not equals operators are supported against null.");
}
}
else if (_left.IsNullConstant())
{
_left = _right;
if (op == CompareOperator.Equal)
{
_comparer = WhereIsNull;
}
else if (op == CompareOperator.NotEqual)
{
_comparer = WhereIsNotNull;
}
else
{
throw new ArgumentException($"Only equals and not equals operators are supported against null.");
}
}
else
{
// Get a comparer which can compare the values
_comparer = TypeProviderFactory.Get(left.ColumnDetails.Type).TryGetComparer(op);
if (_comparer == null)
{
throw new ArgumentException($"No comparer found for type {left.ColumnDetails.Type.Name}.");
}
}
// Optimize Enum to Constant comparisons to use the underlying indices
if (_left.IsEnumColumn() && _right.IsConstantColumn())
{
// Get an optimized comparer against the indices rather than values
IXColumn replacedRight = _right;
_comparer = SetComparer.ConvertToEnumIndexComparer(_left, _comparer, ref replacedRight, source);
// Get the indices on the left side
_leftGetter = _left.IndicesCurrentGetter();
// Use the updated value for the right side
_rightGetter = replacedRight.CurrentGetter();
}
// Allow String8 to constant Contains queries to compare on the raw byte[] and int[]
if (op == CompareOperator.Contains && _right.IsConstantColumn() && _left.ColumnDetails.Type == typeof(String8) && !_left.IsEnumColumn())
{
Func <object> rawGetter = _left.ComponentGetter(ColumnComponent.String8Raw);
if (rawGetter != null)
{
String8 rightValue = (String8)_right.ValuesGetter()().Array.GetValue(0);
String8Comparer string8Comparer = new String8Comparer();
_evaluate = (vector) =>
{
String8Raw raw = (String8Raw)rawGetter();
string8Comparer.WhereContains(raw, rightValue, vector);
};
}
}
}
/// <summary>
/// Build a GroupBy Dictionary for Peek.
/// </summary>
/// <remarks>
/// Peek identifies each distinct common value and the approximate percentage of rows with it.
/// If we have many matching rows, we can sample - the sample will have any common values in it.
/// However, we don't know how many matches we have in advance.
/// Therefore, we build a Dictionary of all rows, 1/8 of rows, 1/64 of rows, and 1/512 of rows.
/// As soon as a given sample has enough samples to be statistically valid, we stop collecting the larger subsets.
/// This strategy allows us to run the overall query only once, end up with a large enough sample, and avoid building giant Dictionaries.
/// </remarks>
/// <param name="cancellationToken">CancellationToken to request early stop</param>
private void BuildDictionary(CancellationToken cancellationToken)
{
// Short-circuit path if there's one key column and it's an EnumColumn
if (_column.IsEnumColumn())
{
BuildSingleEnumColumnDictionary(cancellationToken);
return;
}
// Build a Random instance to sample rows
Random r = new Random();
// Build a Dictionary and CountAggregator for each sample
GroupByDictionary[] dictionaries = new GroupByDictionary[SampleCount];
CountAggregator[] counts = new CountAggregator[SampleCount];
int[][] remapArrays = new int[SampleCount][];
for (int i = 0; i < SampleCount; ++i)
{
dictionaries[i] = new GroupByDictionary(new ColumnDetails[] { _column.ColumnDetails });
counts[i] = new CountAggregator();
}
// Retrieve the column getter
Func <XArray> columnGetter = _column.CurrentGetter();
// Track which sample we'll currently report
int currentSample = 0;
XArray[] arrays = new XArray[1];
int count;
while ((count = _source.Next(XTableExtensions.DefaultBatchSize, cancellationToken)) != 0)
{
// Get the column values
arrays[0] = columnGetter();
// Build the GroupBy count for all rows and successive 1/8 samples
for (int i = 0; i < SampleCount; ++i)
{
// Add these to the Join Dictionary
if (i >= currentSample)
{
// Choose buckets for each row
XArray indicesForRows = dictionaries[i].FindOrAdd(arrays);
// Identify the bucket for each row and aggregate them
counts[i].Add(indicesForRows, dictionaries[i].Count);
// If this sample now has enough values, stop collecting bigger row sets
if (currentSample == i - 1 && counts[i].TotalRowCount > RequiredSampleSize)
{
// If every row was unique, stop early and don't set outputs (zero rows)
if (ShouldStopEarly(dictionaries[currentSample], counts[currentSample]))
{
return;
}
dictionaries[currentSample] = null;
counts[currentSample] = null;
currentSample++;
}
}
// Each successive dictionary has ~1/8 of the rows of the previous one
if (i < SampleCount - 1)
{
ArraySelector sample = Sampler.Eighth(arrays[0].Selector, r, ref remapArrays[i]);
arrays[0] = arrays[0].Reselect(sample);
}
}
}
// Once the loop is done, get the distinct values and aggregation results
PostSortAndFilter(dictionaries[currentSample].DistinctKeys()[0], counts[currentSample].Values, counts[currentSample].TotalRowCount, currentSample == 0);
}