Fix/improve bytea and boolean support in PL/Python

Before, PL/Python converted data between SQL and Python by going
through a C string representation.  This broke for bytea in two ways:

- On input (function parameters), you would get a Python string that
  contains bytea's particular external representation with backslashes
  etc., instead of a sequence of bytes, which is what you would expect
  in a Python environment.  This problem is exacerbated by the new
  bytea output format.

- On output (function return value), null bytes in the Python string
  would cause truncation before the data gets stored into a bytea
  datum.

This is now fixed by converting directly between the PostgreSQL datum
and the Python representation.

The required generalized infrastructure also allows for other
improvements in passing:

- When returning a boolean value, the SQL datum is now true if and
  only if Python considers the value that was passed out of the
  PL/Python function to be true.  Previously, this determination was
  left to the boolean data type input function.  So, now returning
  'foo' results in true, because Python considers it true, rather than
  false because PostgreSQL considers it false.

- On input, we can convert the integer and float types directly to
  their Python equivalents without having to go through an
  intermediate string representation.

original patch by Caleb Welton, with updates by myself

Author: petere

src/backend/utils/adt/domains.c

@@ -25,7 +25,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/utils/adt/domains.c,v 1.8 2009/01/01 17:23:49 momjian Exp $
+ *	  $PostgreSQL: pgsql/src/backend/utils/adt/domains.c,v 1.9 2009/09/09 19:00:09 petere Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -302,3 +302,40 @@ domain_recv(PG_FUNCTION_ARGS)
 	else
 		PG_RETURN_DATUM(value);
 }
+
+/*
+ * domain_check - check that a datum satisfies the constraints of a
+ * domain.  extra and mcxt can be passed if they are available from,
+ * say, a FmgrInfo structure, or they can be NULL, in which case the
+ * setup is repeated for each call.
+ */
+void
+domain_check(Datum value, bool isnull, Oid domainType, void **extra, MemoryContext mcxt)
+{
+	DomainIOData *my_extra = NULL;
+
+	if (mcxt == NULL)
+		mcxt = CurrentMemoryContext;
+
+	/*
+	 * We arrange to look up the needed info just once per series of calls,
+	 * assuming the domain type doesn't change underneath us.
+	 */
+	if (extra)
+		my_extra = (DomainIOData *) *extra;
+	if (my_extra == NULL)
+	{
+		my_extra = (DomainIOData *) MemoryContextAlloc(mcxt,
+													   sizeof(DomainIOData));
+		domain_state_setup(my_extra, domainType, true, mcxt);
+		if (extra)
+			*extra = (void *) my_extra;
+	}
+	else if (my_extra->domain_type != domainType)
+		domain_state_setup(my_extra, domainType, true, mcxt);
+
+	/*
+	 * Do the necessary checks to ensure it's a valid domain value.
+	 */
+	domain_check_input(value, isnull, my_extra);
+}

src/include/utils/builtins.h

@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1996-2009, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/utils/builtins.h,v 1.338 2009/08/04 16:08:36 tgl Exp $
+ * $PostgreSQL: pgsql/src/include/utils/builtins.h,v 1.339 2009/09/09 19:00:09 petere Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -137,6 +137,7 @@ extern Datum char_text(PG_FUNCTION_ARGS);
 /* domains.c */
 extern Datum domain_in(PG_FUNCTION_ARGS);
 extern Datum domain_recv(PG_FUNCTION_ARGS);
+extern void domain_check(Datum value, bool isnull, Oid domainType, void **extra, MemoryContext mcxt);
 
 /* encode.c */
 extern Datum binary_encode(PG_FUNCTION_ARGS);

src/pl/plpython/expected/plpython_types.out

@@ -32,6 +32,74 @@ CONTEXT:  PL/Python function "test_type_conversion_bool"
 
 (1 row)
 
+-- test various other ways to express Booleans in Python
+CREATE FUNCTION test_type_conversion_bool_other(n int) RETURNS bool AS $$
+# numbers
+if n == 0:
+   ret = 0
+elif n == 1:
+   ret = 5
+# strings
+elif n == 2:
+   ret = ''
+elif n == 3:
+   ret = 'fa' # true in Python, false in PostgreSQL
+# containers
+elif n == 4:
+   ret = []
+elif n == 5:
+   ret = [0]
+plpy.info(ret, not not ret)
+return ret
+$$ LANGUAGE plpythonu;
+SELECT * FROM test_type_conversion_bool_other(0);
+INFO:  (0, False)
+CONTEXT:  PL/Python function "test_type_conversion_bool_other"
+ test_type_conversion_bool_other 
+---------------------------------
+ f
+(1 row)
+
+SELECT * FROM test_type_conversion_bool_other(1);
+INFO:  (5, True)
+CONTEXT:  PL/Python function "test_type_conversion_bool_other"
+ test_type_conversion_bool_other 
+---------------------------------
+ t
+(1 row)
+
+SELECT * FROM test_type_conversion_bool_other(2);
+INFO:  ('', False)
+CONTEXT:  PL/Python function "test_type_conversion_bool_other"
+ test_type_conversion_bool_other 
+---------------------------------
+ f
+(1 row)
+
+SELECT * FROM test_type_conversion_bool_other(3);
+INFO:  ('fa', True)
+CONTEXT:  PL/Python function "test_type_conversion_bool_other"
+ test_type_conversion_bool_other 
+---------------------------------
+ t
+(1 row)
+
+SELECT * FROM test_type_conversion_bool_other(4);
+INFO:  ([], False)
+CONTEXT:  PL/Python function "test_type_conversion_bool_other"
+ test_type_conversion_bool_other 
+---------------------------------
+ f
+(1 row)
+
+SELECT * FROM test_type_conversion_bool_other(5);
+INFO:  ([0], True)
+CONTEXT:  PL/Python function "test_type_conversion_bool_other"
+ test_type_conversion_bool_other 
+---------------------------------
+ t
+(1 row)
+
 CREATE FUNCTION test_type_conversion_char(x char) RETURNS char AS $$
 plpy.info(x, type(x))
 return x
@@ -278,13 +346,21 @@ plpy.info(x, type(x))
 return x
 $$ LANGUAGE plpythonu;
 SELECT * FROM test_type_conversion_bytea('hello world');
-INFO:  ('\\x68656c6c6f20776f726c64', <type 'str'>)
+INFO:  ('hello world', <type 'str'>)
 CONTEXT:  PL/Python function "test_type_conversion_bytea"
  test_type_conversion_bytea 
 ----------------------------
  \x68656c6c6f20776f726c64
 (1 row)
 
+SELECT * FROM test_type_conversion_bytea(E'null\\000byte');
+INFO:  ('null\x00byte', <type 'str'>)
+CONTEXT:  PL/Python function "test_type_conversion_bytea"
+ test_type_conversion_bytea 
+----------------------------
+ \x6e756c6c0062797465
+(1 row)
+
 SELECT * FROM test_type_conversion_bytea(null);
 INFO:  (None, <type 'NoneType'>)
 CONTEXT:  PL/Python function "test_type_conversion_bytea"
@@ -304,17 +380,31 @@ try:
 except ValueError, e:
     return 'FAILED: ' + str(e)
 $$ LANGUAGE plpythonu;
-/* This will currently fail because the bytea datum is presented to
-   Python as a string in bytea-encoding, which Python doesn't understand. */
 SELECT test_type_unmarshal(x) FROM test_type_marshal() x;
-   test_type_unmarshal    
---------------------------
- FAILED: bad marshal data
+ test_type_unmarshal 
+---------------------
+ hello world
 (1 row)
 
 --
 -- Domains
 --
+CREATE DOMAIN booltrue AS bool CHECK (VALUE IS TRUE OR VALUE IS NULL);
+CREATE FUNCTION test_type_conversion_booltrue(x booltrue, y bool) RETURNS booltrue AS $$
+return y
+$$ LANGUAGE plpythonu;
+SELECT * FROM test_type_conversion_booltrue(true, true);
+ test_type_conversion_booltrue 
+-------------------------------
+ t
+(1 row)
+
+SELECT * FROM test_type_conversion_booltrue(false, true);
+ERROR:  value for domain booltrue violates check constraint "booltrue_check"
+SELECT * FROM test_type_conversion_booltrue(true, false);
+ERROR:  value for domain booltrue violates check constraint "booltrue_check"
+CONTEXT:  while creating return value
+PL/Python function "test_type_conversion_booltrue"
 CREATE DOMAIN uint2 AS int2 CHECK (VALUE >= 0);
 CREATE FUNCTION test_type_conversion_uint2(x uint2, y int) RETURNS uint2 AS $$
 plpy.info(x, type(x))
@@ -342,13 +432,29 @@ CONTEXT:  PL/Python function "test_type_conversion_uint2"
                           1
 (1 row)
 
+CREATE DOMAIN nnint AS int CHECK (VALUE IS NOT NULL);
+CREATE FUNCTION test_type_conversion_nnint(x nnint, y int) RETURNS nnint AS $$
+return y
+$$ LANGUAGE plpythonu;
+SELECT * FROM test_type_conversion_nnint(10, 20);
+ test_type_conversion_nnint 
+----------------------------
+                         20
+(1 row)
+
+SELECT * FROM test_type_conversion_nnint(null, 20);
+ERROR:  value for domain nnint violates check constraint "nnint_check"
+SELECT * FROM test_type_conversion_nnint(10, null);
+ERROR:  value for domain nnint violates check constraint "nnint_check"
+CONTEXT:  while creating return value
+PL/Python function "test_type_conversion_nnint"
 CREATE DOMAIN bytea10 AS bytea CHECK (octet_length(VALUE) = 10 AND VALUE IS NOT NULL);
 CREATE FUNCTION test_type_conversion_bytea10(x bytea10, y bytea) RETURNS bytea10 AS $$
 plpy.info(x, type(x))
 return y
 $$ LANGUAGE plpythonu;
 SELECT * FROM test_type_conversion_bytea10('hello wold', 'hello wold');
-INFO:  ('\\x68656c6c6f20776f6c64', <type 'str'>)
+INFO:  ('hello wold', <type 'str'>)
 CONTEXT:  PL/Python function "test_type_conversion_bytea10"
  test_type_conversion_bytea10 
 ------------------------------
@@ -358,15 +464,15 @@ CONTEXT:  PL/Python function "test_type_conversion_bytea10"
 SELECT * FROM test_type_conversion_bytea10('hello world', 'hello wold');
 ERROR:  value for domain bytea10 violates check constraint "bytea10_check"
 SELECT * FROM test_type_conversion_bytea10('hello word', 'hello world');
-INFO:  ('\\x68656c6c6f20776f7264', <type 'str'>)
+INFO:  ('hello word', <type 'str'>)
 CONTEXT:  PL/Python function "test_type_conversion_bytea10"
 ERROR:  value for domain bytea10 violates check constraint "bytea10_check"
 CONTEXT:  while creating return value
 PL/Python function "test_type_conversion_bytea10"
 SELECT * FROM test_type_conversion_bytea10(null, 'hello word');
 ERROR:  value for domain bytea10 violates check constraint "bytea10_check"
 SELECT * FROM test_type_conversion_bytea10('hello word', null);
-INFO:  ('\\x68656c6c6f20776f7264', <type 'str'>)
+INFO:  ('hello word', <type 'str'>)
 CONTEXT:  PL/Python function "test_type_conversion_bytea10"
 ERROR:  value for domain bytea10 violates check constraint "bytea10_check"
 CONTEXT:  while creating return value