private static void AddUniqueName(
string columnName,
VBuffer <ReadOnlyMemory <char> > slotNames,
ref ValueListBuilder <int> nameIndices,
ref ValueListBuilder <byte> utf8Names)
{
var columnNameBytes = Encoding.UTF8.GetBytes(columnName);
var dotBytes = Encoding.UTF8.GetBytes(".");
foreach (var kvp in slotNames.Items(true))
{
// REVIEW: Add the proper number of zeros to the slot index to make them sort in the right order.
var slotName = (!kvp.Value.IsEmpty ? kvp.Value.ToString() : kvp.Key.ToString(CultureInfo.InvariantCulture));
if (utf8Names.Capacity - utf8Names.Length < slotName.Length * 2 + columnNameBytes.Length + dotBytes.Length)
{
utf8Names.Grow();
}
nameIndices.Append(utf8Names.Length);
utf8Names.AppendRange(columnNameBytes);
utf8Names.AppendRange(dotBytes);
var bytesNumber = Encoding.UTF8.GetBytes(slotName, 0, slotName.Length, utf8Names.Buffer, utf8Names.Length);
utf8Names.Length += bytesNumber;
utf8Names.Append(0);
}
}
private static void AddUniqueName(string name,
ref ValueListBuilder <int> nameIndices,
ref ValueListBuilder <byte> utf8Names)
{
if (utf8Names.Capacity - utf8Names.Length < name.Length * 2 + 2)
{
utf8Names.Grow();
}
nameIndices.Append(utf8Names.Length);
var bytesNumber = Encoding.UTF8.GetBytes(name, 0, name.Length, utf8Names.Buffer, utf8Names.Length);
utf8Names.Length += bytesNumber;
utf8Names.Append(0);
}
private static unsafe void SendViewToNativeAsCsr(IChannel ch, EnvironmentBlock *penv, IDataView view)
{
Contracts.AssertValue(ch);
Contracts.Assert(penv != null);
Contracts.AssertValue(view);
if (penv->dataSink == null)
{
// Environment doesn't want any data!
return;
}
var dataSink = MarshalDelegate <DataSink>(penv->dataSink);
var schema = view.Schema;
var colIndices = new List <int>();
var outputDataKind = InternalDataKind.R4;
int numOutputRows = 0;
int numOutputCols = 0;
for (int col = 0; col < schema.Count; col++)
{
if (schema[col].IsHidden)
{
continue;
}
var fullType = schema[col].Type;
var itemType = fullType.GetItemType();
int valueCount = fullType.GetValueCount();
if (valueCount == 0)
{
throw ch.ExceptNotSupp("Column has variable length vector: " +
schema[col].Name + ". Not supported in python. Drop column before sending to Python");
}
if (itemType.IsStandardScalar())
{
switch (itemType.GetRawKind())
{
default:
throw Contracts.Except("Data type {0} not supported", itemType.GetRawKind());
case InternalDataKind.I1:
case InternalDataKind.I2:
case InternalDataKind.U1:
case InternalDataKind.U2:
case InternalDataKind.R4:
break;
case InternalDataKind.I4:
case InternalDataKind.U4:
case InternalDataKind.I8:
case InternalDataKind.R8:
outputDataKind = InternalDataKind.R8;
break;
}
}
else
{
throw Contracts.Except("Data type {0} not supported", itemType.GetRawKind());
}
colIndices.Add(col);
numOutputCols += valueCount;
}
var nameIndices = new ValueListBuilder <int>(10);
var nameUtf8Bytes = new ValueListBuilder <byte>(100);
AddUniqueName("data", ref nameIndices, ref nameUtf8Bytes);
AddUniqueName("indices", ref nameIndices, ref nameUtf8Bytes);
AddUniqueName("indptr", ref nameIndices, ref nameUtf8Bytes);
AddUniqueName("shape", ref nameIndices, ref nameUtf8Bytes);
var kindList = new List <InternalDataKind> {
outputDataKind,
InternalDataKind.I4,
InternalDataKind.I4,
InternalDataKind.I4
};
var valueCounts = new List <byte> {
1, 1, 1, 1
};
var kinds = kindList.ToArray();
var nameBytes = nameUtf8Bytes.AsSpan();
var names = new byte *[nameIndices.Length];
var valueCountsBytes = valueCounts.ToArray();
fixed(InternalDataKind *prgkind = kinds)
fixed(byte *prgbNames = nameBytes)
fixed(byte **prgname = names)
fixed(byte *prgbValueCount = valueCountsBytes)
{
for (int iid = 0; iid < names.Length; iid++)
{
names[iid] = prgbNames + nameIndices[iid];
}
DataViewBlock block;
block.ccol = nameIndices.Length;
block.crow = view.GetRowCount() ?? 0;
block.names = (sbyte **)prgname;
block.kinds = prgkind;
block.keyCards = null;
block.valueCounts = prgbValueCount;
dataSink(penv, &block, out var setters, out var keyValueSetter);
if (setters == null)
{
return;
}
using (var cursor = view.GetRowCursor(view.Schema.Where(col => colIndices.Contains(col.Index))))
{
CsrData csrData = new CsrData(penv, setters, outputDataKind);
var fillers = new CsrFillerBase[colIndices.Count];
for (int i = 0; i < colIndices.Count; i++)
{
var type = schema[colIndices[i]].Type;
fillers[i] = CsrFillerBase.Create(penv, cursor, colIndices[i], type, outputDataKind, csrData);
}
for (;; numOutputRows++)
{
if (!cursor.MoveNext())
{
break;
}
for (int i = 0; i < fillers.Length; i++)
{
fillers[i].Set();
}
csrData.IncrementRow();
}
csrData.SetShape(numOutputRows, numOutputCols);
}
}
}
private static unsafe void SendViewToNativeAsDataFrame(IChannel ch, EnvironmentBlock *penv, IDataView view, Dictionary <string, ColumnMetadataInfo> infos = null)
{
Contracts.AssertValue(ch);
Contracts.Assert(penv != null);
Contracts.AssertValue(view);
Contracts.AssertValueOrNull(infos);
if (penv->dataSink == null)
{
// Environment doesn't want any data!
return;
}
var dataSink = MarshalDelegate <DataSink>(penv->dataSink);
var schema = view.Schema;
var colIndices = new List <int>(1000);
var kindList = new ValueListBuilder <InternalDataKind>(INDICES_BUFFER_SIZE);
var keyCardList = new ValueListBuilder <int>(INDICES_BUFFER_SIZE);
var nameUtf8Bytes = new ValueListBuilder <byte>(UTF8_BUFFER_SIZE);
var nameIndices = new ValueListBuilder <int>(INDICES_BUFFER_SIZE);
var expandCols = new HashSet <int>(1000);
var valueCounts = new List <byte>(1000);
for (int col = 0; col < schema.Count; col++)
{
if (schema[col].IsHidden)
{
continue;
}
var fullType = schema[col].Type;
var itemType = fullType.GetItemType();
var name = schema[col].Name;
var kind = itemType.GetRawKind();
int keyCard;
byte valueCount = (fullType.GetValueCount() == 0) ? (byte)0 : (byte)1;
if (itemType is KeyDataViewType)
{
// Key types are returned as their signed counterparts in Python, so that -1 can be the missing value.
// For U1 and U2 kinds, we convert to a larger type to prevent overflow. For U4 and U8 kinds, we convert
// to I4 if the key count is known (since KeyCount is an I4), and to I8 otherwise.
switch (kind)
{
case InternalDataKind.U1:
kind = InternalDataKind.I2;
break;
case InternalDataKind.U2:
kind = InternalDataKind.I4;
break;
case InternalDataKind.U4:
// We convert known-cardinality U4 key types to I4.
kind = itemType.GetKeyCount() > 0 ? InternalDataKind.I4 : InternalDataKind.I8;
break;
case InternalDataKind.U8:
// We convert known-cardinality U8 key types to I4.
kind = itemType.GetKeyCount() > 0 ? InternalDataKind.I4 : InternalDataKind.I8;
break;
}
keyCard = itemType.GetKeyCountAsInt32();
if (!schema[col].HasKeyValues())
{
keyCard = -1;
}
}
else if (itemType.IsStandardScalar())
{
switch (itemType.GetRawKind())
{
default:
throw Contracts.Except("Data type {0} not handled", itemType.GetRawKind());
case InternalDataKind.I1:
case InternalDataKind.I2:
case InternalDataKind.I4:
case InternalDataKind.I8:
case InternalDataKind.U1:
case InternalDataKind.U2:
case InternalDataKind.U4:
case InternalDataKind.U8:
case InternalDataKind.R4:
case InternalDataKind.R8:
case InternalDataKind.BL:
case InternalDataKind.TX:
case InternalDataKind.DT:
break;
}
keyCard = -1;
}
else
{
throw Contracts.Except("Data type {0} not handled", itemType.GetRawKind());
}
int nSlots;
ColumnMetadataInfo info;
if (infos != null && infos.TryGetValue(name, out info) && info.Expand)
{
expandCols.Add(col);
Contracts.Assert(fullType.IsKnownSizeVector());
nSlots = fullType.GetVectorSize();
if (info.SlotNames != null)
{
Contracts.Assert(info.SlotNames.Length == nSlots);
for (int i = 0; i < nSlots; i++)
{
AddUniqueName(info.SlotNames[i], ref nameIndices, ref nameUtf8Bytes);
}
}
else if (schema[col].HasSlotNames(nSlots))
{
var romNames = default(VBuffer <ReadOnlyMemory <char> >);
schema[col].Annotations.GetValue(AnnotationUtils.Kinds.SlotNames, ref romNames);
AddUniqueName(name, romNames, ref nameIndices, ref nameUtf8Bytes);
}
else
{
for (int i = 0; i < nSlots; i++)
{
AddUniqueName(name + "." + i, ref nameIndices, ref nameUtf8Bytes);
}
}
}
else
{
nSlots = 1;
AddUniqueName(name, ref nameIndices, ref nameUtf8Bytes);
}
colIndices.Add(col);
for (int i = 0; i < nSlots; i++)
{
kindList.Append(kind);
keyCardList.Append(keyCard);
valueCounts.Add(valueCount);
}
}
ch.Assert(kindList.Length == keyCardList.Length);
ch.Assert(kindList.Length == nameIndices.Length);
var kinds = kindList.AsSpan();
var keyCards = keyCardList.AsSpan();
var nameBytes = nameUtf8Bytes.AsSpan();
var names = new byte *[nameIndices.Length];
var valueCountsBytes = valueCounts.ToArray();
fixed(InternalDataKind *prgkind = kinds)
fixed(byte *prgbNames = nameBytes)
fixed(byte **prgname = names)
fixed(int *prgkeyCard = keyCards)
fixed(byte *prgbValueCount = valueCountsBytes)
{
for (int iid = 0; iid < names.Length; iid++)
{
names[iid] = prgbNames + nameIndices[iid];
}
DataViewBlock block;
block.ccol = nameIndices.Length;
block.crow = view.GetRowCount() ?? 0;
block.names = (sbyte **)prgname;
block.kinds = prgkind;
block.keyCards = prgkeyCard;
block.valueCounts = prgbValueCount;
dataSink(penv, &block, out var setters, out var keyValueSetter);
if (setters == null)
{
// REVIEW: What should we do?
return;
}
ch.Assert(keyValueSetter != null);
var kvSet = MarshalDelegate <KeyValueSetter>(keyValueSetter);
using (var cursor = view.GetRowCursor(view.Schema.Where(col => colIndices.Contains(col.Index))))
{
var fillers = new BufferFillerBase[colIndices.Count];
var pyColumn = 0;
var keyIndex = 0;
for (int i = 0; i < colIndices.Count; i++)
{
var type = schema[colIndices[i]].Type;
var itemType = type.GetItemType();
if ((itemType is KeyDataViewType) && schema[colIndices[i]].HasKeyValues())
{
ch.Assert(schema[colIndices[i]].HasKeyValues());
var keyValues = default(VBuffer <ReadOnlyMemory <char> >);
schema[colIndices[i]].Annotations.GetValue(AnnotationUtils.Kinds.KeyValues, ref keyValues);
for (int slot = 0; slot < type.GetValueCount(); slot++)
{
foreach (var kvp in keyValues.Items())
{
if (kvp.Value.IsEmpty)
{
kvSet(penv, keyIndex, kvp.Key, null, 0);
}
else
{
byte[] bt = Encoding.UTF8.GetBytes(kvp.Value.ToString());
fixed(byte *pt = bt)
kvSet(penv, keyIndex, kvp.Key, (sbyte *)pt, bt.Length);
}
}
keyIndex++;
}
}
fillers[i] = BufferFillerBase.Create(penv, cursor, pyColumn, colIndices[i], prgkind[pyColumn], type, setters[pyColumn]);
if ((type is VectorDataViewType) && (type.GetVectorSize() > 0))
{
pyColumn += type.GetVectorSize();
}
else
{
pyColumn++;
}
}
for (int crow = 0; ; crow++)
{
// Advance to the next row.
if (!cursor.MoveNext())
{
break;
}
// Fill values for the current row.
for (int i = 0; i < fillers.Length; i++)
{
fillers[i].Set();
}
}
}
}
}
