Merge pull request #44662 from evillique/ulid

Add generateULID function

.gitmodules

@@ -296,6 +296,9 @@
 [submodule "contrib/libdivide"]
 	path = contrib/libdivide
 	url = https://github.com/ridiculousfish/libdivide
+[submodule "contrib/ulid-c"]
+	path = contrib/ulid-c
+	url = https://github.com/ClickHouse/ulid-c.git
 [submodule "contrib/aws-crt-cpp"]
 	path = contrib/aws-crt-cpp
 	url = https://github.com/ClickHouse/aws-crt-cpp

contrib/CMakeLists.txt

@@ -191,6 +191,8 @@ add_contrib (xxHash-cmake xxHash)
 
 add_contrib (google-benchmark-cmake google-benchmark)
 
+add_contrib (ulid-c-cmake ulid-c)
+
 # Put all targets defined here and in subdirectories under "contrib/<immediate-subdir>" folders in GUI-based IDEs.
 # Some of third-party projects may override CMAKE_FOLDER or FOLDER property of their targets, so they would not appear
 # in "contrib/..." as originally planned, so we workaround this by fixing FOLDER properties of all targets manually,

contrib/ulid-c

@@ -0,0 +1 @@
+Subproject commit c433b6783cf918b8f996dacd014cb2b68c7de419

contrib/ulid-c-cmake/CMakeLists.txt

@@ -0,0 +1,16 @@
+option (ENABLE_ULID "Enable ulid" ${ENABLE_LIBRARIES})
+
+if (NOT ENABLE_ULID)
+    message(STATUS "Not using ulid")
+    return()
+endif()
+
+set (LIBRARY_DIR "${ClickHouse_SOURCE_DIR}/contrib/ulid-c")
+
+set (SRCS
+    "${LIBRARY_DIR}/src/ulid.c"
+)
+
+add_library(_ulid ${SRCS})
+target_include_directories(_ulid SYSTEM PUBLIC "${LIBRARY_DIR}/include")
+add_library(ch_contrib::ulid ALIAS _ulid)

docs/en/sql-reference/functions/ulid-functions.md

@@ -0,0 +1,53 @@
+---
+slug: /en/sql-reference/functions/ulid-functions
+sidebar_position: 54
+sidebar_label: ULID
+---
+
+# Functions for Working with ULID
+
+## generateULID
+
+Generates the [ULID](https://github.com/ulid/spec).
+
+**Syntax**
+
+``` sql
+generateULID([x])
+```
+
+**Arguments**
+
+-   `x` — [Expression](../../sql-reference/syntax.md#syntax-expressions) resulting in any of the [supported data types](../../sql-reference/data-types/index.md#data_types). The resulting value is discarded, but the expression itself if used for bypassing [common subexpression elimination](../../sql-reference/functions/index.md#common-subexpression-elimination) if the function is called multiple times in one query. Optional parameter.
+
+**Returned value**
+
+The [FixedString](../data-types/fixedstring.md) type value.
+
+**Usage example**
+
+``` sql
+SELECT generateULID()
+```
+
+``` text
+┌─generateULID()─────────────┐
+│ 01GNB2S2FGN2P93QPXDNB4EN2R │
+└────────────────────────────┘
+```
+
+**Usage example if it is needed to generate multiple values in one row**
+
+```sql
+SELECT generateULID(1), generateULID(2)
+```
+
+``` text
+┌─generateULID(1)────────────┬─generateULID(2)────────────┐
+│ 01GNB2SGG4RHKVNT9ZGA4FFMNP │ 01GNB2SGG4V0HMQVH4VBVPSSRB │
+└────────────────────────────┴────────────────────────────┘
+```
+
+## See Also
+
+-   [UUID](../../sql-reference/functions/uuid-functions.md)

src/CMakeLists.txt

@@ -550,6 +550,10 @@ if (ENABLE_NLP)
     dbms_target_link_libraries (PUBLIC ch_contrib::nlp_data)
 endif()
 
+if (TARGET ch_contrib::ulid)
+    dbms_target_link_libraries (PUBLIC ch_contrib::ulid)
+endif()
+
 if (TARGET ch_contrib::bzip2)
     target_link_libraries (clickhouse_common_io PRIVATE ch_contrib::bzip2)
 endif()

src/Common/config.h.in

@@ -56,3 +56,4 @@
 #cmakedefine01 USE_BLAKE3
 #cmakedefine01 USE_SKIM
 #cmakedefine01 USE_OPENSSL_INTREE
+#cmakedefine01 USE_ULID

src/Functions/generateULID.cpp

@@ -0,0 +1,94 @@
+#include "config.h"
+
+#if USE_ULID
+
+#include <Columns/ColumnFixedString.h>
+#include <DataTypes/DataTypeFixedString.h>
+#include <Functions/FunctionFactory.h>
+#include <Functions/FunctionHelpers.h>
+#include <Functions/IFunction.h>
+#include <Interpreters/Context.h>
+
+#include <ulid.h>
+
+
+namespace DB
+{
+
+namespace ErrorCodes
+{
+    extern const int NUMBER_OF_ARGUMENTS_DOESNT_MATCH;
+}
+
+class FunctionGenerateULID : public IFunction
+{
+public:
+    static constexpr size_t ULID_LENGTH = 26;
+
+    static constexpr auto name = "generateULID";
+
+    static FunctionPtr create(ContextPtr /*context*/)
+    {
+        return std::make_shared<FunctionGenerateULID>();
+    }
+
+    String getName() const override { return name; }
+
+    size_t getNumberOfArguments() const override { return 0; }
+
+    bool isVariadic() const override { return true; }
+    bool isDeterministic() const override { return false; }
+    bool isDeterministicInScopeOfQuery() const override { return false; }
+    bool isSuitableForShortCircuitArgumentsExecution(const DataTypesWithConstInfo & /*arguments*/) const override { return false; }
+
+    DataTypePtr getReturnTypeImpl(const DataTypes & arguments) const override
+    {
+        if (arguments.size() > 1)
+            throw Exception(
+                ErrorCodes::NUMBER_OF_ARGUMENTS_DOESNT_MATCH,
+                "Number of arguments for function {} doesn't match: passed {}, should be 0 or 1.",
+                getName(), arguments.size());
+
+        return std::make_shared<DataTypeFixedString>(ULID_LENGTH);
+    }
+
+    bool useDefaultImplementationForConstants() const override { return true; }
+
+    ColumnPtr executeImpl(const ColumnsWithTypeAndName & /*arguments*/, const DataTypePtr &, size_t input_rows_count) const override
+    {
+        auto col_res = ColumnFixedString::create(ULID_LENGTH);
+        auto & vec_res = col_res->getChars();
+
+        vec_res.resize(input_rows_count * ULID_LENGTH);
+
+        ulid_generator generator;
+        ulid_generator_init(&generator, 0);
+
+        for (size_t offset = 0, size = vec_res.size(); offset < size; offset += ULID_LENGTH)
+            ulid_generate(&generator, reinterpret_cast<char *>(&vec_res[offset]));
+
+        return col_res;
+    }
+};
+
+
+REGISTER_FUNCTION(GenerateULID)
+{
+    factory.registerFunction<FunctionGenerateULID>(
+    {
+        R"(
+Generates a Universally Unique Lexicographically Sortable Identifier (ULID).
+This function takes an optional argument, the value of which is discarded to generate different values in case the function is called multiple times.
+The function returns a value of type FixedString(26).
+)",
+        Documentation::Examples{
+            {"ulid", "SELECT generateULID()"},
+            {"multiple", "SELECT generateULID(1), generateULID(2)"}},
+        Documentation::Categories{"ULID"}
+    },
+    FunctionFactory::CaseSensitive);
+}
+
+}
+
+#endif

src/configure_config.cmake

@@ -94,6 +94,9 @@ endif()
 if (ENABLE_NLP)
     set(USE_NLP 1)
 endif()
+if (TARGET ch_contrib::ulid)
+    set(USE_ULID 1)
+endif()
 if (TARGET ch_contrib::llvm)
     set(USE_EMBEDDED_COMPILER 1)
 endif()

tests/queries/0_stateless/02515_generate_ulid.reference

@@ -0,0 +1 @@
+1	FixedString(26)

tests/queries/0_stateless/02515_generate_ulid.sql

@@ -0,0 +1,3 @@
+-- Tags: no-fasttest
+
+SELECT generateULID(1) != generateULID(2), toTypeName(generateULID());