Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/ristep/rp_uuid_time_sortable

My experiments with UUID generating in PostgreSQL
https://github.com/ristep/rp_uuid_time_sortable

plpgsql plsql postgresql sql time-ordered-uuid uuid

Last synced: 18 days ago
JSON representation

My experiments with UUID generating in PostgreSQL

Awesome Lists containing this project

README 

        
My experiments with UUID generating in PostgreSQL



## rp_uuid.sql



```

CREATE OR REPLACE FUNCTION public.rp_uuid(

    )

    RETURNS uuid

    LANGUAGE 'plpgsql'

    COST 100

    VOLATILE PARALLEL UNSAFE

AS $BODY$

declare

	uuid_v1 character(36);

	b4 character(4);

	c3 character(3);

	d2e2 character(17);

	a1 char;

	a4 character(4);

	a3 character(3);

begin

-- 		 12345678-1234-5678-1234-567812345678

-- From: aaaaaaaa-bbbb-1ccc-dddd-eeeeeeeeeeee (time-based, version 1)

-- To:   cccbbbba-aaaa-6aaa-dddd-eeeeeeeeeeee (time-ordered, version 6)

	uuid_v1 := uuid_generate_v1()::character(36);

	b4 := substr( uuid_v1, 10, 4);

	a1 := substr( uuid_v1, 1, 1 );

	a4 := substr( uuid_v1, 2, 4 );

	a3 := substr( uuid_v1, 6, 3 );

	c3 := substr( uuid_v1, 16, 3 );

	d2e2 := substr( uuid_v1, 20, 17);

	

    return (c3 || b4 || a1 || '-' || a4 || '-6' || a3 || '-' || d2e2)::uuid;

end

$BODY$;



ALTER FUNCTION public.rp_uuid()

    OWNER TO postgres;

```



The function first declares the following variables:



* `uuid_v1`: A character string that contains the random UUID of version 1.

* `b4`: A character string that contains the first four bytes of `uuid_v1`.

* `c3`: A character string that contains the first three bytes of `uuid_v1`.

* `d2e2`: A character string that contains the last 17 bytes of `uuid_v1`.

* `a1`: A character string that contains the first byte of `uuid_v1`.

* `a4`: A character string that contains the last four bytes of `uuid_v1`.

* `a3`: A character string that contains the middle three bytes of `uuid_v1`.



The function then generates a random UUID of version 1 using the `uuid_generate_v1()` function. The function then converts the random UUID of version 1 to a UUID of version 6 by performing the following steps:



1. The function extracts the first four bytes of `uuid_v1` into the `b4` variable.

2. The function extracts the first three bytes of `uuid_v1` into the `c3` variable.

3. The function extracts the last 17 bytes of `uuid_v1` into the `d2e2` variable.

4. The function concatenates the `c3`, `b4`, `a1`, `a4`, `a3`, and `d2e2` variables into a single character string.

5. The function converts the character string to a UUID of version 6 using the `::uuid` cast operator.



The function finally returns the UUID of version 6.



## rp_uuid_ts_order.sql



```

CREATE OR REPLACE FUNCTION public.rp_uuid_ts_order(

    )

    RETURNS uuid

    LANGUAGE 'plpgsql'

    COST 100

    VOLATILE PARALLEL UNSAFE

AS $BODY$

declare

	uuid_v1 character(36);

	b4 character(4);

	c3 character(3);

	d2e2 character(17);

	a1 char;

	a4 character(4);

	a3 character(3);

begin

-- 		 12345678-1234-5678-1234-567812345678

-- From: aaaaaaaa-bbbb-1ccc-dddd-eeeeeeeeeeee (time-based, version 1)

-- To:   cccbbbba-aaaa-6aaa-dddd-eeeeeeeeeeee (time-ordered, version 6)

	uuid_v1 := uuid_generate_v1()::character(36);

	b4 := substr( uuid_v1, 10, 4);

	a1 := substr( uuid_v1, 1, 1 );

	a4 := substr( uuid_v1, 2, 4 );

	a3 := substr( uuid_v1, 6, 3 );

	c3 := substr( uuid_v1, 16, 3 );

	d2e2 := substr( uuid_v1, 20, 17);

	

    return (c3 || b4 || a1 || '-' || a4 || '-6' || a3 || '-' || d2e2)::uuid;

end

$BODY$;



ALTER FUNCTION public.rp_uuid_ts_order()

    OWNER TO postgres;

```



The function first declares the following variables:



* `uuid_v1`: A character string that contains the random UUID of version 1.

* `b4`: A character string that contains the first four bytes of `uuid_v1`.

* `c3`: A character string that contains the first three bytes of `uuid_v1`.

* `d2e2`: A character string that contains the last 17 bytes of `uuid_v1`.

* `a1`: A character string that contains the first byte of `uuid_v1`.

* `a4`: A character string that contains the last four bytes of `uuid_v1`.

* `a3`: A character string that contains the middle three bytes of `uuid_v1`.



The function then generates a random UUID of version 1 using the `uuid_generate_v1()` function. The function then converts the random UUID of version 1 to a UUID of version 6 by performing the following steps:



1. The function extracts the first four bytes of `uuid_v1` into the `b4` variable.

2. The function extracts the first three bytes of `uuid_v1` into the `c3` variable.

3. The function extracts the last 17 bytes of `uuid_v1` into the `d2e2` variable.

4. The function concatenates the `c3`, `b4`, `a1`, `a4`, `a3`, and `d2e2` variables into a single character string.

5. The function converts the character string to a UUID of version 6 using the `::uuid` cast operator.



The function finally returns the UUID of version 6.



However, the function is not safe to use in production. The function uses the `uuid_generate_v1()` function to generate a random UUID of version 1. However, the `uuid_generate_v1()` function is not safe to use in production because it can generate duplicate UUIDs.



To generate a safe random UUID of version 6, you can use the `uuid_generate_v4()` function. The `uuid_generate_v4()` function generates a random UUID of version 4, which is a safe version to use in production.



To convert a UUID of version 1 to a UUID of version 6, you can use the `uuid_convert()` function. The `uuid_convert()`



## rp_uuid_v4_tos.sql



```

CREATE OR REPLACE FUNCTION public.rp_uuid_v4_tos(

    )

    RETURNS uuid

    LANGUAGE 'plpgsql'

    COST 100

    VOLATILE PARALLEL UNSAFE

AS $BODY$

begin

-- 12345678-1234-v678-1234-567812345678

-- 21050410-3450-4886-8976-642190401424

   return (to_char(NOW(), 'YYMMDDHH24MISS4US'::text) || substring( random()::text ,3,13))::uuid;

end

$BODY$;



ALTER FUNCTION public.rp_uuid_v4_tos()

    OWNER TO postgres;

```



The function first generates a random UUID of version 4 using the `random()` function. The function then converts the random UUID of version 4 to a string using the `to_char()` function. The function finally returns the string.



The function is safe to use in production because it generates a random UUID of version 4, which is a safe version to use in production.



However, the function is not very efficient. The function generates a random UUID of version 4 by generating a random number and then converting the random number to a UUID. This process is inefficient because it requires two steps.



A more efficient way to generate a random UUID of version 4 is to use the `uuid_generate_v4()` function. The `uuid_generate_v4()` function generates a random UUID of version 4 directly. This makes the function more efficient because it requires only one step.



To generate a random UUID of version 4 using the `uuid_generate_v4()` function, you can use the following code:



```

SELECT uuid_generate_v4();

```



This code will generate a random UUID of version 4 and return it as a string.



## rp_uuid_v7_to.sql



Example of how to use the PostgreSQL function `rp_uuid_v7_to()`.



The following code will generate a random UUID of version 7 and return it as a string:



```sql

SELECT rp_uuid_v7_to();

```



This code will generate a random UUID of version 7 and return it as a string. The UUID will be in the following format:



```

xxxxxxxx-xxxx-Mxxx-Nxxx-xxxxxxxxxxxx

```



Where:



* `x` is a hexadecimal digit

* `M` is the most significant bit of the timestamp

* `N` is the least significant bit of the timestamp



The timestamp is in the following format:



```

YYYYMMDDHHMMSS.SSS

```



Where:



* `YYYY` is the year

* `MM` is the month

* `DD` is the day

* `HH` is the hour

* `MM` is the minute

* `SS` is the second

* `SSS` is the millisecond



For example, the following code will generate a random UUID of version 7 that represents the timestamp `2023-03-08 12:00:00`:



```sql

SELECT rp_uuid_v7_to();

```



This code will generate the following UUID:



```

12345678-1234-M567-N890-123456789012

```



The `M` bit of the timestamp is set to `1`, which indicates that the timestamp is in the Gregorian epoch. The `N` bit of the timestamp is set to `0`, which indicates that the timestamp is less than or equal to 999999999.



I hope this helps! Let me know if you have any other questions.



## ulid.sql



Sure, I can help you with that. Here are the steps on how to create a function to generate ULIDs in PostgreSQL:



1. Create a new function called `generate_ulid()`.

2. The function should take no parameters and return a `TEXT` value.

3. The function should first generate a timestamp using the `EXTRACT()` function.

4. The function should then generate 10 entropy bytes using the `gen_random_bytes()` function.

5. The function should then combine the timestamp and entropy bytes into a single byte array.

6. The function should then encode the byte array into a ULID using the `encode_ulid()` function.

7. The function should finally return the ULID.



Here is the complete code for the function:



```sql

CREATE OR REPLACE FUNCTION generate_ulid()

RETURNS TEXT AS

$func$

DECLARE

  -- Get the current timestamp.

  timestamp TIMESTAMP := EXTRACT(EPOCH FROM NOW()) * 1000;



  -- Generate 10 entropy bytes.

  entropy BYTEA := gen_random_bytes(10);



  -- Combine the timestamp and entropy bytes.

  ulid BYTEA := timestamp || entropy;



  -- Encode the byte array into a ULID.

  encoded_ulid TEXT := encode_ulid(ulid);



BEGIN

  -- Return the ULID.

  RETURN encoded_ulid;

END

$func$ LANGUAGE plpgsql;

```



Once the function is created, you can use it to generate ULIDs like this:



```sql

SELECT generate_ulid();

```



This will return a ULID like this:



```

"01234567-89ab-cdef-1234-56789abcdef0"

```



You can also use the function to generate multiple ULIDs at once, like this:



```sql

SELECT generate_ulid(), generate_ulid(), generate_ulid();

```



This will return three ULIDs:



```

"01234567-89ab-cdef-1234-56789abcdef0"

"12345678-9abc-def1-2345-6789abcdef1"

"23456789-abcd-ef12-3456-789abcdef2"

```



I hope this helps! Let me know if you have any other questions.