YT-19324: move YT provider to ydb/library/yql

This commit is formed by the following script: https://paste.yandex-team.ru/6f92e4b8-efc5-4d34-948b-15ee2accd7e7/text.
This commit has zero effect on all projects that depend on YQL.

The summary of changes:
- `yql/providers/yt -> ydb/library/yql/providers/yt `- the whole implementation of YT provider is moved into YDB code base for further export as a part of YT YQL plugin shared library;
- `yql/providers/stat/{expr_nodes,uploader} -> ydb/library/yql/providers/stat/{expr_nodes,uploader}` - a small interface without implementation and the description of stat expr nodes;
- `yql/core/extract_predicate/ut -> ydb/library/yql/core/extract_predicate/ut`;
- `yql/core/{ut,ut_common} -> ydb/library/yql/core/{ut,ut_common}`;
- `yql/core` is gone;
- `yql/library/url_preprocessing -> ydb/library/yql/core/url_preprocessing`.

**NB**: all new targets inside `ydb/` are under `IF (NOT CMAKE_EXPORT)` clause which disables them from open-source cmake generation and ya make build. They will be enabled in the subsequent commits.

1 files changed, 135 insertions, 0 deletions

diff --git a/yt/cpp/mapreduce/interface/format.cpp b/yt/cpp/mapreduce/interface/format.cpp
new file mode 100644
index 0000000000..f8318310a4
--- /dev/null
+++ b/yt/cpp/mapreduce/interface/format.cpp
@@ -0,0 +1,135 @@
+#include "format.h"
+#include "protobuf_format.h"
+
+#include "errors.h"
+
+#include <google/protobuf/descriptor.h>
+#include <google/protobuf/messagext.h>
+
+namespace NYT {
+
+TTableSchema CreateTableSchema(
+    const ::google::protobuf::Descriptor& messageDescriptor,
+    bool keepFieldsWithoutExtension)
+{
+    return NDetail::CreateTableSchemaImpl(messageDescriptor, keepFieldsWithoutExtension);
+}
+
+////////////////////////////////////////////////////////////////////////////////
+
+TFormat::TFormat(const TNode& config)
+    : Config(config)
+{ }
+
+
+TFormat TFormat::Protobuf(
+    const TVector<const ::google::protobuf::Descriptor*>& descriptors,
+    bool withDescriptors)
+{
+    if (withDescriptors) {
+        return TFormat(NDetail::MakeProtoFormatConfigWithDescriptors(descriptors));
+    } else {
+        return TFormat(NDetail::MakeProtoFormatConfigWithTables(descriptors));
+    }
+}
+
+TFormat TFormat::YsonText()
+{
+    TNode config("yson");
+    config.Attributes()("format", "text");
+    return TFormat(config);
+}
+
+TFormat TFormat::YsonBinary()
+{
+    TNode config("yson");
+    config.Attributes()("format", "binary");
+    return TFormat(config);
+}
+
+TFormat TFormat::YaMRLenval()
+{
+    TNode config("yamr");
+    config.Attributes()("lenval", true)("has_subkey", true);
+    return TFormat(config);
+}
+
+TFormat TFormat::Json()
+{
+    return TFormat(TNode("json"));
+}
+
+bool TFormat::IsTextYson() const
+{
+    if (!Config.IsString() || Config.AsString() != "yson") {
+        return false;
+    }
+    if (!Config.HasAttributes()) {
+        return false;
+    }
+    const auto& attributes = Config.GetAttributes();
+    if (!attributes.HasKey("format") || attributes["format"] != TNode("text")) {
+        return false;
+    }
+    return true;
+}
+
+bool TFormat::IsProtobuf() const
+{
+    return Config.IsString() && Config.AsString() == "protobuf";
+}
+
+bool TFormat::IsYamredDsv() const
+{
+    return Config.IsString() && Config.AsString() == "yamred_dsv";
+}
+
+static TString FormatName(const TFormat& format)
+{
+    if (!format.Config.IsString()) {
+        Y_VERIFY(format.Config.IsUndefined());
+        return "<undefined>";
+    }
+    return format.Config.AsString();
+}
+
+TYamredDsvAttributes TFormat::GetYamredDsvAttributes() const
+{
+    if (!IsYamredDsv()) {
+        ythrow TApiUsageError() << "Cannot get yamred_dsv attributes for " << FormatName(*this) << " format";
+    }
+    TYamredDsvAttributes attributes;
+
+    const auto& nodeAttributes = Config.GetAttributes();
+    {
+        const auto& keyColumns = nodeAttributes["key_column_names"];
+        if (!keyColumns.IsList()) {
+            ythrow yexception() << "Ill-formed format: key_column_names is of non-list type: " << keyColumns.GetType();
+        }
+        for (auto& column : keyColumns.AsList()) {
+            if (!column.IsString()) {
+                ythrow yexception() << "Ill-formed format: key_column_names: " << column.GetType();
+            }
+            attributes.KeyColumnNames.push_back(column.AsString());
+        }
+    }
+
+    if (nodeAttributes.HasKey("subkey_column_names")) {
+        const auto& subkeyColumns = nodeAttributes["subkey_column_names"];
+        if (!subkeyColumns.IsList()) {
+            ythrow yexception() << "Ill-formed format: subkey_column_names is not a list: " << subkeyColumns.GetType();
+        }
+        for (const auto& column : subkeyColumns.AsList()) {
+            if (!column.IsString()) {
+                ythrow yexception() << "Ill-formed format: non-string inside subkey_key_column_names: " << column.GetType();
+            }
+            attributes.SubkeyColumnNames.push_back(column.AsString());
+        }
+    }
+
+    return attributes;
+}
+
+////////////////////////////////////////////////////////////////////////////////
+
+} // namespace NYT