YQ Connector: move tests from yql to ydb (OSS)

Перенос папки с тестами на Коннектор из папки yql в папку ydb (синхронизируется с github).

14 files changed, 483 insertions, 0 deletions

diff --git a/contrib/clickhouse/src/Functions/JSONPath/Parsers/ParserJSONPath.cpp b/contrib/clickhouse/src/Functions/JSONPath/Parsers/ParserJSONPath.cpp
new file mode 100644
index 00000000000..003e97af38b
--- /dev/null
+++ b/contrib/clickhouse/src/Functions/JSONPath/Parsers/ParserJSONPath.cpp
@@ -0,0 +1,31 @@
+#include <Functions/JSONPath/ASTs/ASTJSONPath.h>
+#include <Functions/JSONPath/ASTs/ASTJSONPathMemberAccess.h>
+#include <Functions/JSONPath/Parsers/ParserJSONPath.h>
+#include <Functions/JSONPath/Parsers/ParserJSONPathQuery.h>
+
+namespace DB
+{
+/**
+ * Entry parser for JSONPath
+ */
+bool ParserJSONPath::parseImpl(Pos & pos, ASTPtr & node, Expected & expected)
+{
+    auto ast_jsonpath = std::make_shared<ASTJSONPath>();
+    ParserJSONPathQuery parser_jsonpath_query;
+
+    /// Push back dot AST and brackets AST to query->children
+    ASTPtr query;
+
+    bool res = parser_jsonpath_query.parse(pos, query, expected);
+
+    if (res)
+    {
+        /// Set ASTJSONPathQuery of ASTJSONPath
+        ast_jsonpath->set(ast_jsonpath->jsonpath_query, query);
+    }
+
+    node = ast_jsonpath;
+    return res;
+}
+
+}
diff --git a/contrib/clickhouse/src/Functions/JSONPath/Parsers/ParserJSONPath.h b/contrib/clickhouse/src/Functions/JSONPath/Parsers/ParserJSONPath.h
new file mode 100644
index 00000000000..7d2c2ad642c
--- /dev/null
+++ b/contrib/clickhouse/src/Functions/JSONPath/Parsers/ParserJSONPath.h
@@ -0,0 +1,21 @@
+#pragma once
+
+#include <Parsers/IParserBase.h>
+
+
+namespace DB
+{
+/**
+ * Entry parser for JSONPath
+ */
+class ParserJSONPath : public IParserBase
+{
+private:
+    const char * getName() const override { return "ParserJSONPath"; }
+    bool parseImpl(Pos & pos, ASTPtr & node, Expected & expected) override;
+
+public:
+    explicit ParserJSONPath() = default;
+};
+
+}
diff --git a/contrib/clickhouse/src/Functions/JSONPath/Parsers/ParserJSONPathMemberAccess.cpp b/contrib/clickhouse/src/Functions/JSONPath/Parsers/ParserJSONPathMemberAccess.cpp
new file mode 100644
index 00000000000..141f25bfe4c
--- /dev/null
+++ b/contrib/clickhouse/src/Functions/JSONPath/Parsers/ParserJSONPathMemberAccess.cpp
@@ -0,0 +1,85 @@
+#include <Functions/JSONPath/ASTs/ASTJSONPathMemberAccess.h>
+#include <Functions/JSONPath/Parsers/ParserJSONPathMemberAccess.h>
+
+#include <Parsers/ASTIdentifier.h>
+#include <Parsers/ASTIdentifier_fwd.h>
+#include <Parsers/ExpressionElementParsers.h>
+#include <Parsers/Lexer.h>
+#include <Common/StringUtils/StringUtils.h>
+
+namespace DB
+{
+/**
+ *
+ * @param pos token iterator
+ * @param node node of ASTJSONPathMemberAccess
+ * @param expected stuff for logging
+ * @return was parse successful
+ */
+bool ParserJSONPathMemberAccess::parseImpl(Pos & pos, ASTPtr & node, Expected & expected)
+{
+    // There's a special case, that a path member can begin with number
+    // some invalid cases as following
+    //   - ".123" is parsed as a number, not a dot and a number
+    //   - ".123abc" is parsed as two parts, a number ".123" and a token "abc"
+    //   - ".abc" is parsed as two parts. a dot and a token "abc"
+    // "$..123abc" is parsed into three parts, ".", ".123" and "abc"
+    if (pos->type != TokenType::Dot && pos->type != TokenType::Number)
+        return false;
+    if (pos->type != TokenType::Number)
+    {
+        ++pos;
+        // Check the case "$..123abc"
+        if (pos->type == TokenType::Number)
+        {
+            return false;
+        }
+    }
+
+    ASTPtr member_name;
+
+    if (pos->type == TokenType::Number)[[unlikely]]
+    {
+        for (const auto * c = pos->begin; c != pos->end; ++c)
+        {
+            if (*c == '.' && c == pos->begin)
+                continue;
+            if (!isNumericASCII(*c))
+            {
+                return false;
+            }
+        }
+        const auto * last_begin = *pos->begin == '.' ? pos->begin + 1 : pos->begin;
+        const auto * last_end = pos->end;
+        ++pos;
+
+        if (pos.isValid() && pos->type == TokenType::BareWord && pos->begin == last_end)
+        {
+            member_name = std::make_shared<ASTIdentifier>(String(last_begin, pos->end));
+            ++pos;
+        }
+        else if (!pos.isValid() && pos->type == TokenType::EndOfStream)
+        {
+            member_name = std::make_shared<ASTIdentifier>(String(last_begin, last_end));
+        }
+        else
+        {
+            return false;
+        }
+    }
+    else
+    {
+        if (pos->type != TokenType::BareWord && pos->type != TokenType::QuotedIdentifier)
+            return false;
+
+        ParserIdentifier name_p;
+        if (!name_p.parse(pos, member_name, expected))
+            return false;
+    }
+
+    auto member_access = std::make_shared<ASTJSONPathMemberAccess>();
+    node = member_access;
+    return tryGetIdentifierNameInto(member_name, member_access->member_name);
+}
+
+}
diff --git a/contrib/clickhouse/src/Functions/JSONPath/Parsers/ParserJSONPathMemberAccess.h b/contrib/clickhouse/src/Functions/JSONPath/Parsers/ParserJSONPathMemberAccess.h
new file mode 100644
index 00000000000..b28bf37d5ef
--- /dev/null
+++ b/contrib/clickhouse/src/Functions/JSONPath/Parsers/ParserJSONPathMemberAccess.h
@@ -0,0 +1,14 @@
+#pragma once
+
+#include <Parsers/IParserBase.h>
+
+namespace DB
+{
+class ParserJSONPathMemberAccess : public IParserBase
+{
+    const char * getName() const override { return "ParserJSONPathMemberAccess"; }
+
+    bool parseImpl(Pos & pos, ASTPtr & node, Expected & expected) override;
+};
+
+}
diff --git a/contrib/clickhouse/src/Functions/JSONPath/Parsers/ParserJSONPathMemberSquareBracketAccess.cpp b/contrib/clickhouse/src/Functions/JSONPath/Parsers/ParserJSONPathMemberSquareBracketAccess.cpp
new file mode 100644
index 00000000000..93e0639ccfe
--- /dev/null
+++ b/contrib/clickhouse/src/Functions/JSONPath/Parsers/ParserJSONPathMemberSquareBracketAccess.cpp
@@ -0,0 +1,44 @@
+#include "ParserJSONPathMemberSquareBracketAccess.h"
+#include <memory>
+#include <Functions/JSONPath/ASTs/ASTJSONPathMemberAccess.h>
+#include <IO/ReadBufferFromMemory.h>
+#include <IO/ReadHelpers.h>
+#include <Parsers/ASTIdentifier.h>
+#include <Parsers/ExpressionElementParsers.h>
+
+namespace DB
+{
+bool ParserJSONPathMemberSquareBracketAccess::parseImpl(Pos & pos, ASTPtr & node, Expected & expected)
+{
+    if (pos->type != TokenType::OpeningSquareBracket)
+        return false;
+    ++pos;
+    ASTPtr member_name;
+    if (pos->type == TokenType::BareWord || pos->type == TokenType::QuotedIdentifier)
+    {
+        ParserIdentifier name_p;
+        if (!name_p.parse(pos, member_name, expected))
+            return false;
+    }
+    else if (pos->type == TokenType::StringLiteral)
+    {
+        ReadBufferFromMemory in(pos->begin, pos->size());
+        String name;
+        readQuotedStringWithSQLStyle(name, in);
+        member_name = std::make_shared<ASTIdentifier>(name);
+        ++pos;
+    }
+    else
+    {
+        return false;
+    }
+    if (pos->type != TokenType::ClosingSquareBracket)
+    {
+        return false;
+    }
+    ++pos;
+    auto member_access = std::make_shared<ASTJSONPathMemberAccess>();
+    node = member_access;
+    return tryGetIdentifierNameInto(member_name, member_access->member_name);
+}
+}
diff --git a/contrib/clickhouse/src/Functions/JSONPath/Parsers/ParserJSONPathMemberSquareBracketAccess.h b/contrib/clickhouse/src/Functions/JSONPath/Parsers/ParserJSONPathMemberSquareBracketAccess.h
new file mode 100644
index 00000000000..b682ec5bb96
--- /dev/null
+++ b/contrib/clickhouse/src/Functions/JSONPath/Parsers/ParserJSONPathMemberSquareBracketAccess.h
@@ -0,0 +1,17 @@
+#pragma once
+#include <Parsers/IParserBase.h>
+// cases
+// - [ident]
+// - ['ident']
+// - ["ident"]
+namespace DB
+{
+class ParserJSONPathMemberSquareBracketAccess : public IParserBase
+{
+private:
+    const char * getName() const override { return "ParserJSONPathMemberSquareBracketAccess"; }
+    bool parseImpl(Pos & pos, ASTPtr & node, Expected & expected) override;
+public:
+    explicit ParserJSONPathMemberSquareBracketAccess() = default;
+};
+}
diff --git a/contrib/clickhouse/src/Functions/JSONPath/Parsers/ParserJSONPathQuery.cpp b/contrib/clickhouse/src/Functions/JSONPath/Parsers/ParserJSONPathQuery.cpp
new file mode 100644
index 00000000000..d8d633a1ec9
--- /dev/null
+++ b/contrib/clickhouse/src/Functions/JSONPath/Parsers/ParserJSONPathQuery.cpp
@@ -0,0 +1,51 @@
+#include <Functions/JSONPath/ASTs/ASTJSONPathQuery.h>
+#include <Functions/JSONPath/Parsers/ParserJSONPathQuery.h>
+#include <Functions/JSONPath/Parsers/ParserJSONPathRoot.h>
+#include <Functions/JSONPath/Parsers/ParserJSONPathMemberAccess.h>
+#include <Functions/JSONPath/Parsers/ParserJSONPathMemberSquareBracketAccess.h>
+#include <Functions/JSONPath/Parsers/ParserJSONPathRange.h>
+#include <Functions/JSONPath/Parsers/ParserJSONPathStar.h>
+
+namespace DB
+
+{
+/**
+ *
+ * @param pos token iterator
+ * @param query node of ASTJSONPathQuery
+ * @param expected stuff for logging
+ * @return was parse successful
+ */
+bool ParserJSONPathQuery::parseImpl(Pos & pos, ASTPtr & query, Expected & expected)
+{
+    query = std::make_shared<ASTJSONPathQuery>();
+    ParserJSONPathMemberAccess parser_jsonpath_member_access;
+    ParserJSONPathMemberSquareBracketAccess parser_jsonpath_member_square_bracket_access;
+    ParserJSONPathRange parser_jsonpath_range;
+    ParserJSONPathStar parser_jsonpath_star;
+    ParserJSONPathRoot parser_jsonpath_root;
+
+    ASTPtr path_root;
+    if (!parser_jsonpath_root.parse(pos, path_root, expected))
+    {
+        return false;
+    }
+    query->children.push_back(path_root);
+
+    ASTPtr accessor;
+    while (parser_jsonpath_member_access.parse(pos, accessor, expected)
+           || parser_jsonpath_member_square_bracket_access.parse(pos, accessor, expected)
+           || parser_jsonpath_range.parse(pos, accessor, expected)
+           || parser_jsonpath_star.parse(pos, accessor, expected))
+    {
+        if (accessor)
+        {
+            query->children.push_back(accessor);
+            accessor = nullptr;
+        }
+    }
+    /// parsing was successful if we reached the end of query by this point
+    return pos->type == TokenType::EndOfStream;
+}
+
+}
diff --git a/contrib/clickhouse/src/Functions/JSONPath/Parsers/ParserJSONPathQuery.h b/contrib/clickhouse/src/Functions/JSONPath/Parsers/ParserJSONPathQuery.h
new file mode 100644
index 00000000000..fbe7321562e
--- /dev/null
+++ b/contrib/clickhouse/src/Functions/JSONPath/Parsers/ParserJSONPathQuery.h
@@ -0,0 +1,14 @@
+#pragma once
+
+#include <Parsers/IParserBase.h>
+
+
+namespace DB
+{
+class ParserJSONPathQuery : public IParserBase
+{
+protected:
+    const char * getName() const override { return "ParserJSONPathQuery"; }
+    bool parseImpl(Pos & pos, ASTPtr & query, Expected & expected) override;
+};
+}
diff --git a/contrib/clickhouse/src/Functions/JSONPath/Parsers/ParserJSONPathRange.cpp b/contrib/clickhouse/src/Functions/JSONPath/Parsers/ParserJSONPathRange.cpp
new file mode 100644
index 00000000000..03c006774c0
--- /dev/null
+++ b/contrib/clickhouse/src/Functions/JSONPath/Parsers/ParserJSONPathRange.cpp
@@ -0,0 +1,94 @@
+#include <Functions/JSONPath/ASTs/ASTJSONPathRange.h>
+#include <Functions/JSONPath/Parsers/ParserJSONPathQuery.h>
+#include <Functions/JSONPath/Parsers/ParserJSONPathRange.h>
+
+#include <Parsers/ASTIdentifier.h>
+#include <Parsers/ASTLiteral.h>
+#include <Parsers/ExpressionElementParsers.h>
+#include <Parsers/CommonParsers.h>
+
+namespace DB
+{
+namespace ErrorCodes
+{
+    extern const int BAD_ARGUMENTS;
+}
+/**
+ *
+ * @param pos token iterator
+ * @param node node of ASTJSONPathQuery
+ * @param expected stuff for logging
+ * @return was parse successful
+ */
+bool ParserJSONPathRange::parseImpl(Pos & pos, ASTPtr & node, Expected & expected)
+{
+
+    if (pos->type != TokenType::OpeningSquareBracket)
+    {
+        return false;
+    }
+    ++pos;
+
+    auto range = std::make_shared<ASTJSONPathRange>();
+    node = range;
+
+    ParserNumber number_p;
+    ASTPtr number_ptr;
+    while (pos->type != TokenType::ClosingSquareBracket)
+    {
+        if (pos->type != TokenType::Number)
+        {
+            return false;
+        }
+
+        std::pair<UInt32, UInt32> range_indices;
+        if (!number_p.parse(pos, number_ptr, expected))
+        {
+            return false;
+        }
+        range_indices.first = static_cast<UInt32>(number_ptr->as<ASTLiteral>()->value.get<UInt32>());
+
+        if (pos->type == TokenType::Comma || pos->type == TokenType::ClosingSquareBracket)
+        {
+            /// Single index case
+            range_indices.second = range_indices.first + 1;
+        }
+        else if (pos->type == TokenType::BareWord)
+        {
+            if (!ParserKeyword("TO").ignore(pos, expected))
+            {
+                return false;
+            }
+            if (!number_p.parse(pos, number_ptr, expected))
+            {
+                return false;
+            }
+            range_indices.second = static_cast<UInt32>(number_ptr->as<ASTLiteral>()->value.get<UInt32>());
+        }
+        else
+        {
+            return false;
+        }
+
+        if (range_indices.first >= range_indices.second)
+        {
+            throw Exception(
+                ErrorCodes::BAD_ARGUMENTS,
+                "Start of range must be greater than end of range, however {} >= {}",
+                range_indices.first,
+                range_indices.second);
+        }
+
+        range->ranges.push_back(std::move(range_indices));
+        if (pos->type != TokenType::ClosingSquareBracket)
+        {
+            ++pos;
+        }
+    }
+    ++pos;
+
+    /// We can't have both ranges and star present, so parse was successful <=> exactly 1 of these conditions is true
+    return !range->ranges.empty() ^ range->is_star;
+}
+
+}
diff --git a/contrib/clickhouse/src/Functions/JSONPath/Parsers/ParserJSONPathRange.h b/contrib/clickhouse/src/Functions/JSONPath/Parsers/ParserJSONPathRange.h
new file mode 100644
index 00000000000..94db29577ab
--- /dev/null
+++ b/contrib/clickhouse/src/Functions/JSONPath/Parsers/ParserJSONPathRange.h
@@ -0,0 +1,18 @@
+#pragma once
+
+#include <Parsers/IParserBase.h>
+
+
+namespace DB
+{
+class ParserJSONPathRange : public IParserBase
+{
+private:
+    const char * getName() const override { return "ParserJSONPathRange"; }
+    bool parseImpl(Pos & pos, ASTPtr & node, Expected & expected) override;
+
+public:
+    explicit ParserJSONPathRange() = default;
+};
+
+}
diff --git a/contrib/clickhouse/src/Functions/JSONPath/Parsers/ParserJSONPathRoot.cpp b/contrib/clickhouse/src/Functions/JSONPath/Parsers/ParserJSONPathRoot.cpp
new file mode 100644
index 00000000000..86cf793fb52
--- /dev/null
+++ b/contrib/clickhouse/src/Functions/JSONPath/Parsers/ParserJSONPathRoot.cpp
@@ -0,0 +1,27 @@
+#include <Functions/JSONPath/ASTs/ASTJSONPathRoot.h>
+#include <Functions/JSONPath/Parsers/ParserJSONPathRoot.h>
+
+#include <Parsers/Lexer.h>
+
+namespace DB
+{
+/**
+ *
+ * @param pos token iterator
+ * @param node node of ASTJSONPathRoot
+ * @param expected stuff for logging
+ * @return was parse successful
+ */
+bool ParserJSONPathRoot::parseImpl(Pos & pos, ASTPtr & node, Expected & expected)
+{
+    if (pos->type != TokenType::DollarSign)
+    {
+        expected.add(pos, "dollar sign (start of jsonpath)");
+        return false;
+    }
+    node = std::make_shared<ASTJSONPathRoot>();
+    ++pos;
+    return true;
+}
+
+}
diff --git a/contrib/clickhouse/src/Functions/JSONPath/Parsers/ParserJSONPathRoot.h b/contrib/clickhouse/src/Functions/JSONPath/Parsers/ParserJSONPathRoot.h
new file mode 100644
index 00000000000..59fed28d63e
--- /dev/null
+++ b/contrib/clickhouse/src/Functions/JSONPath/Parsers/ParserJSONPathRoot.h
@@ -0,0 +1,18 @@
+#pragma once
+
+#include <Parsers/IParserBase.h>
+
+
+namespace DB
+{
+class ParserJSONPathRoot : public IParserBase
+{
+private:
+    const char * getName() const override { return "ParserJSONPathRoot"; }
+    bool parseImpl(Pos & pos, ASTPtr & node, Expected & expected) override;
+
+public:
+    explicit ParserJSONPathRoot() = default;
+};
+
+}
diff --git a/contrib/clickhouse/src/Functions/JSONPath/Parsers/ParserJSONPathStar.cpp b/contrib/clickhouse/src/Functions/JSONPath/Parsers/ParserJSONPathStar.cpp
new file mode 100644
index 00000000000..1338a2064f1
--- /dev/null
+++ b/contrib/clickhouse/src/Functions/JSONPath/Parsers/ParserJSONPathStar.cpp
@@ -0,0 +1,31 @@
+#include <Functions/JSONPath/Parsers/ParserJSONPathStar.h>
+
+#include <Functions/JSONPath/ASTs/ASTJSONPathStar.h>
+
+namespace DB
+{
+bool ParserJSONPathStar::parseImpl(Pos & pos, ASTPtr & node, Expected & expected)
+{
+    if (pos->type != TokenType::OpeningSquareBracket)
+    {
+        return false;
+    }
+    ++pos;
+    if (pos->type != TokenType::Asterisk)
+    {
+        return false;
+    }
+    ++pos;
+    if (pos->type != TokenType::ClosingSquareBracket)
+    {
+        expected.add(pos, "Closing square bracket");
+        return false;
+    }
+    ++pos;
+
+    node = std::make_shared<ASTJSONPathStar>();
+
+    return true;
+}
+
+}
diff --git a/contrib/clickhouse/src/Functions/JSONPath/Parsers/ParserJSONPathStar.h b/contrib/clickhouse/src/Functions/JSONPath/Parsers/ParserJSONPathStar.h
new file mode 100644
index 00000000000..543823357de
--- /dev/null
+++ b/contrib/clickhouse/src/Functions/JSONPath/Parsers/ParserJSONPathStar.h
@@ -0,0 +1,18 @@
+#pragma once
+
+#include <Parsers/IParserBase.h>
+
+
+namespace DB
+{
+class ParserJSONPathStar : public IParserBase
+{
+private:
+    const char * getName() const override { return "ParserJSONPathStar"; }
+    bool parseImpl(Pos & pos, ASTPtr & node, Expected & expected) override;
+
+public:
+    explicit ParserJSONPathStar() = default;
+};
+
+}