Python 3 support in PL/Python

Behaves more or less unchanged compared to Python 2, but the new language
variant is called plpython3u.  Documentation describing the naming scheme
is included.

config/python.m4

 #
 # Autoconf macros for configuring the build of Python extension modules
 #
-# $PostgreSQL: pgsql/config/python.m4,v 1.16 2009/10/14 21:59:15 petere Exp $
+# $PostgreSQL: pgsql/config/python.m4,v 1.17 2009/12/15 22:59:53 petere Exp $
 #
 
 # PGAC_PATH_PYTHON
@@ -30,10 +30,12 @@ else
     AC_MSG_ERROR([distutils module not found])
 fi
 AC_MSG_CHECKING([Python configuration directory])
+python_majorversion=`${PYTHON} -c "import sys; print(sys.version[[0]])"`
 python_version=`${PYTHON} -c "import sys; print(sys.version[[:3]])"`
 python_configdir=`${PYTHON} -c "from distutils.sysconfig import get_python_lib as f; import os; print(os.path.join(f(plat_specific=1,standard_lib=1),'config'))"`
 python_includespec=`${PYTHON} -c "import distutils.sysconfig; print('-I'+distutils.sysconfig.get_python_inc())"`
 
+AC_SUBST(python_majorversion)[]dnl
 AC_SUBST(python_version)[]dnl
 AC_SUBST(python_configdir)[]dnl
 AC_SUBST(python_includespec)[]dnl

configure

@@ -677,6 +677,7 @@ python_libdir
 python_includespec
 python_configdir
 python_version
+python_majorversion
 PYTHON
 perl_embed_ldflags
 perl_useshrplib
@@ -6964,6 +6965,7 @@ $as_echo "$as_me: error: distutils module not found" >&2;}
 fi
 { $as_echo "$as_me:$LINENO: checking Python configuration directory" >&5
 $as_echo_n "checking Python configuration directory... " >&6; }
+python_majorversion=`${PYTHON} -c "import sys; print(sys.version[0])"`
 python_version=`${PYTHON} -c "import sys; print(sys.version[:3])"`
 python_configdir=`${PYTHON} -c "from distutils.sysconfig import get_python_lib as f; import os; print(os.path.join(f(plat_specific=1,standard_lib=1),'config'))"`
 python_includespec=`${PYTHON} -c "import distutils.sysconfig; print('-I'+distutils.sysconfig.get_python_inc())"`

doc/src/sgml/installation.sgml

-<!-- $PostgreSQL: pgsql/doc/src/sgml/installation.sgml,v 1.332 2009/12/09 16:16:34 mha Exp $ -->
+<!-- $PostgreSQL: pgsql/doc/src/sgml/installation.sgml,v 1.333 2009/12/15 22:59:53 petere Exp $ -->
 
 <chapter id="installation">
  <title><![%standalone-include[<productname>PostgreSQL</>]]>
@@ -195,8 +195,12 @@ su - postgres
      <para>
       To build the <application>PL/Python</> server programming
       language, you need a <productname>Python</productname>
-      installation with the header files and the <application>distutils</application> module.
-      The minimum required version is <productname>Python</productname> 2.2.
+      installation with the header files and
+      the <application>distutils</application> module.  The minimum
+      required version is <productname>Python</productname>
+      2.2.  <productname>Python 3</productname> is supported with
+      version 3.1 or later; but see <xref linkend="plpython-python23">
+      when using Python 3.
      </para>
 
      <para>

doc/src/sgml/plpython.sgml

-<!-- $PostgreSQL: pgsql/doc/src/sgml/plpython.sgml,v 1.41 2009/12/10 20:43:40 petere Exp $ -->
+<!-- $PostgreSQL: pgsql/doc/src/sgml/plpython.sgml,v 1.42 2009/12/15 22:59:53 petere Exp $ -->
 
 <chapter id="plpython">
  <title>PL/Python - Python Procedural Language</title>
@@ -14,7 +14,8 @@
 
  <para>
   To install PL/Python in a particular database, use
-  <literal>createlang plpythonu <replaceable>dbname</></literal>.
+  <literal>createlang plpythonu <replaceable>dbname</></literal> (but
+  see also <xref linkend="plpython-python23">).
  </para>
 
   <tip>
@@ -42,6 +43,112 @@
   </para>
  </note>
 
+ <sect1 id="plpython-python23">
+  <title>Python 2 vs. Python 3</title>
+
+  <para>
+   PL/Python supports both the Python 2 and Python 3 language
+   variants.  (The PostgreSQL installation instructions might contain
+   more precise information about the exact supported minor versions
+   of Python.)  Because the Python 2 and Python 3 language variants
+   are incompatible in some important aspects, the following naming
+   and transitioning scheme is used by PL/Python to avoid mixing them:
+
+   <itemizedlist>
+    <listitem>
+     <para>
+      The PostgreSQL language named <literal>plpython2u</literal>
+      implements PL/Python based on the Python 2 language variant.
+     </para>
+    </listitem>
+
+    <listitem>
+     <para>
+      The PostgreSQL language named <literal>plpython3u</literal>
+      implements PL/Python based on the Python 3 language variant.
+     </para>
+    </listitem>
+
+    <listitem>
+     <para>
+      The language named <literal>plpythonu</literal> implements
+      PL/Python based on the default Python language variant, which is
+      currently Python 2.  (This default is independent of what any
+      local Python installations might consider to be
+      their <quote>default</quote>, for example,
+      what <filename>/usr/bin/python</filename> might be.)  The
+      default will probably be changed to Python 3 in a distant future
+      release of PostgreSQL, depending on the progress of the
+      migration to Python 3 in the Python community.
+     </para>
+    </listitem>
+   </itemizedlist>
+
+   It depends on the build configuration or the installed packages
+   whether PL/Python for Python 2 or Python 3 or both are available.
+  </para>
+
+  <para>
+   This results in the following usage and migration strategy:
+
+   <itemizedlist>
+    <listitem>
+     <para>
+      Existing users and users who are currently not interested in
+      Python 3 use the language name <literal>plpythonu</literal> and
+      don't have to change anything for the foreseeable future.  It is
+      recommended to gradually <quote>future-proof</quote> the code
+      via migration to Python 2.6/2.7 to simplify the eventual
+      migration to Python 3.
+     </para>
+
+     <para>
+      In practice, many PL/Python functions will migrate to Python 3
+      with few or no changes.
+     </para>
+    </listitem>
+
+    <listitem>
+     <para>
+      Users who know that they have heavily Python 2 dependent code
+      and don't plan to ever change it can make use of
+      the <literal>plpython2u</literal> language name.  This will
+      continue to work into the very distant future, until Python 2
+      support might be completely dropped by PostgreSQL.
+     </para>
+    </listitem>
+
+    <listitem>
+     <para>
+      Users who want to dive into Python 3 can use
+      the <literal>plpython3u</literal> language name, which will keep
+      working forever by today's standards.  In the distant future,
+      when Python 3 might become the default, they might like to
+      remove the <quote>3</quote> for aesthetic reasons.
+     </para>
+    </listitem>
+
+    <listitem>
+     <para>
+      Daredevils, who want to build a Python-3-only operating system
+      environment, can change the build scripts to
+      make <literal>plpythonu</literal> be equivalent
+      to <literal>plpython3u</literal>, keeping in mind that this
+      would make their installation incompatible with most of the rest
+      of the world.
+     </para>
+    </listitem>
+   </itemizedlist>
+  </para>
+
+  <para>
+   See also the
+   document <ulink url="http://docs.python.org/dev/3.0/whatsnew/3.0.html">What's
+   New In Python 3.0</ulink> for more information about porting to
+   Python 3.
+  </para>
+ </sect1>
+
  <sect1 id="plpython-funcs">
   <title>PL/Python Functions</title>
 

src/Makefile.global.in

 # -*-makefile-*-
-# $PostgreSQL: pgsql/src/Makefile.global.in,v 1.259 2009/11/03 21:28:10 petere Exp $
+# $PostgreSQL: pgsql/src/Makefile.global.in,v 1.260 2009/12/15 22:59:54 petere Exp $
 
 #------------------------------------------------------------------------------
 # All PostgreSQL makefiles include this file and use the variables it sets,
@@ -171,6 +171,7 @@ python_libdir		= @python_libdir@
 python_libspec		= @python_libspec@
 python_additional_libs	= @python_additional_libs@
 python_configdir	= @python_configdir@
+python_majorversion	= @python_majorversion@
 python_version		= @python_version@
 
 krb_srvtab = @krb_srvtab@

src/include/catalog/catversion.h

@@ -37,7 +37,7 @@
  * Portions Copyright (c) 1996-2009, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/catalog/catversion.h,v 1.558 2009/12/15 17:57:47 tgl Exp $
+ * $PostgreSQL: pgsql/src/include/catalog/catversion.h,v 1.559 2009/12/15 22:59:54 petere Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -53,6 +53,6 @@
  */
 
 /*							yyyymmddN */
-#define CATALOG_VERSION_NO	200912151
+#define CATALOG_VERSION_NO	200912161
 
 #endif

src/include/catalog/pg_pltemplate.h

@@ -8,7 +8,7 @@
  * Portions Copyright (c) 1996-2009, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/catalog/pg_pltemplate.h,v 1.9 2009/11/29 03:02:27 tgl Exp $
+ * $PostgreSQL: pgsql/src/include/catalog/pg_pltemplate.h,v 1.10 2009/12/15 22:59:54 petere Exp $
  *
  * NOTES
  *	  the genbki.sh script reads this file and generates .bki
@@ -73,5 +73,7 @@ DATA(insert ( "pltclu"		f f "pltclu_call_handler" _null_ _null_ "$libdir/pltcl"
 DATA(insert ( "plperl"		t t "plperl_call_handler" "plperl_inline_handler" "plperl_validator" "$libdir/plperl" _null_ ));
 DATA(insert ( "plperlu"		f f "plperl_call_handler" "plperl_inline_handler" "plperl_validator" "$libdir/plperl" _null_ ));
 DATA(insert ( "plpythonu"	f f "plpython_call_handler" _null_ _null_ "$libdir/plpython" _null_ ));
+DATA(insert ( "plpython2u"	f f "plpython_call_handler" _null_ _null_ "$libdir/plpython2" _null_ ));
+DATA(insert ( "plpython3u"	f f "plpython_call_handler" _null_ _null_ "$libdir/plpython3" _null_ ));
 
 #endif   /* PG_PLTEMPLATE_H */

src/pl/plpython/Makefile

-# $PostgreSQL: pgsql/src/pl/plpython/Makefile,v 1.34 2009/08/14 13:42:16 petere Exp $
+# $PostgreSQL: pgsql/src/pl/plpython/Makefile,v 1.35 2009/12/15 22:59:54 petere Exp $
 
 subdir = src/pl/plpython
 top_builddir = ../../..
@@ -36,7 +36,7 @@ override CPPFLAGS := -I$(srcdir) $(python_includespec) $(CPPFLAGS)
 
 rpathdir = $(python_libdir)
 
-NAME = plpython
+NAME = plpython$(python_majorversion)
 OBJS = plpython.o
 
 
@@ -56,7 +56,12 @@ endif
 
 SHLIB_LINK = $(python_libspec) $(python_additional_libs) $(filter -lintl,$(LIBS))
 
-REGRESS_OPTS = --dbname=$(PL_TESTDB) --load-language=plpythonu
+REGRESS_OPTS = --dbname=$(PL_TESTDB)
+# Only load plpythonu with Python 2.  The test files themselves load
+# the versioned language plpython(2|3)u.
+ifeq ($(python_majorversion),2)
+REGRESS_OPTS += --load-language=plpythonu
+endif
 REGRESS = \
 	plpython_schema \
 	plpython_populate \
@@ -83,13 +88,45 @@ include $(top_srcdir)/src/Makefile.shlib
 all: all-lib
 
 install: all installdirs install-lib
+ifeq ($(python_majorversion),2)
+	cd '$(DESTDIR)$(pkglibdir)' && rm -f plpython$(DLSUFFIX) && $(LN_S) $(shlib) plpython$(DLSUFFIX)
+endif
 
 installdirs: installdirs-lib
 
 uninstall: uninstall-lib
+ifeq ($(python_majorversion),2)
+	rm -f '$(DESTDIR)$(pkglibdir)/plpython$(DLSUFFIX)'
+endif
 
+ifeq ($(python_majorversion),3)
+# Adjust regression tests for Python 3 compatibility
+prep3:
+	$(MKDIR_P) python3 python3/sql python3/expected
+	for file in $(srcdir)/sql/*.sql $(srcdir)/expected/*.out; do \
+	  sed -e 's/except \([[:alpha:]][[:alpha:].]*\), *\([[:alpha:]][[:alpha:]]*\):/except \1 as \2:/g' \
+	      -e "s/<type 'exceptions\.\([[:alpha:]]*\)'>/<class '\1'>/g" \
+	      -e "s/<type 'long'>/<class 'int'>/g" \
+	      -e "s/\([0-9][0-9]*\)L/\1/g" \
+	      -e 's/\([ [{]\)u"/\1"/g' \
+	      -e "s/\([ [{]\)u'/\1'/g" \
+	      -e "s/def next/def __next__/g" \
+	      -e "s/LANGUAGE plpythonu/LANGUAGE plpython3u/g" \
+	      -e "s/LANGUAGE plpython2u/LANGUAGE plpython3u/g" \
+	    $$file >`echo $$file | sed 's,$(srcdir),python3,'`; \
+	done
+
+clean3:
+	rm -rf python3/
+
+installcheck: submake prep3
+	$(top_builddir)/src/test/regress/pg_regress --inputdir=./python3 --outputdir=./python3 --psqldir=$(PSQLDIR) $(REGRESS_OPTS) $(REGRESS)
+
+clean: clean3
+else
 installcheck: submake
 	$(top_builddir)/src/test/regress/pg_regress --inputdir=$(srcdir) --psqldir=$(PSQLDIR) $(REGRESS_OPTS) $(REGRESS)
+endif
 
 .PHONY: submake
 submake:

src/pl/plpython/expected/README

@@ -8,3 +8,5 @@ plpython_unicode_0.out		any version, when server encoding != SQL_ASCII and clien
 plpython_unicode_2.out		Python 2.2
 plpython_unicode_3.out		Python 2.3, 2.4
 plpython_unicode_5.out		Python 2.5, 2.6
+
+plpython_types_3.out		Python 3.1

src/pl/plpython/expected/plpython_test.out

 -- first some tests of basic functionality
+CREATE LANGUAGE plpython2u;
 -- really stupid function just to get the module loaded
 CREATE FUNCTION stupid() RETURNS text AS 'return "zarkon"' LANGUAGE plpythonu;
 select stupid();
@@ -7,6 +8,14 @@ select stupid();
  zarkon
 (1 row)
 
+-- check 2/3 versioning
+CREATE FUNCTION stupidn() RETURNS text AS 'return "zarkon"' LANGUAGE plpython2u;
+select stupidn();
+ stupidn 
+---------
+ zarkon
+(1 row)
+
 -- test multiple arguments
 CREATE FUNCTION argument_test_one(u users, a1 text, a2 text) RETURNS text
 	AS

src/pl/plpython/expected/plpython_trigger.out

@@ -67,7 +67,7 @@ SELECT * FROM users;
 -- dump trigger data
 CREATE TABLE trigger_test
 	(i int, v text );
-CREATE FUNCTION trigger_data() returns trigger language plpythonu as $$
+CREATE FUNCTION trigger_data() RETURNS trigger LANGUAGE plpythonu AS $$
 
 if 'relid' in TD:
 	TD['relid'] = "bogus:12345"

src/pl/plpython/plpython.c

 /**********************************************************************
  * plpython.c - python as a procedural language for PostgreSQL
  *
- *	$PostgreSQL: pgsql/src/pl/plpython/plpython.c,v 1.133 2009/12/10 20:43:40 petere Exp $
+ *	$PostgreSQL: pgsql/src/pl/plpython/plpython.c,v 1.134 2009/12/15 22:59:54 petere Exp $
  *
  *********************************************************************
  */
@@ -40,6 +40,48 @@ typedef int Py_ssize_t;
 #define PyBool_FromLong(x) PyInt_FromLong(x)
 #endif
 
+/*
+ * Python 2/3 strings/unicode/bytes handling.  Python 2 has strings
+ * and unicode, Python 3 has strings, which are unicode on the C
+ * level, and bytes.  The porting convention, which is similarly used
+ * in Python 2.6, is that "Unicode" is always unicode, and "Bytes" are
+ * bytes in Python 3 and strings in Python 2.  Since we keep
+ * supporting Python 2 and its usual strings, we provide a
+ * compatibility layer for Python 3 that when asked to convert a C
+ * string to a Python string it converts the C string from the
+ * PostgreSQL server encoding to a Python Unicode object.
+ */
+
+#if PY_VERSION_HEX < 0x02060000
+/* This is exactly the compatibility layer that Python 2.6 uses. */
+#define PyBytes_AsString PyString_AsString
+#define PyBytes_FromStringAndSize PyString_FromStringAndSize
+#define PyBytes_Size PyString_Size
+#define PyObject_Bytes PyObject_Str
+#endif
+
+#if PY_MAJOR_VERSION >= 3
+#define PyString_Check(x) 0
+#define PyString_AsString(x) PLyUnicode_AsString(x)
+#define PyString_FromString(x) PLyUnicode_FromString(x)
+#endif
+
+/*
+ * Python 3 only has long.
+ */
+#if PY_MAJOR_VERSION >= 3
+#define PyInt_FromLong(x) PyLong_FromLong(x)
+#endif
+
+/*
+ * PyVarObject_HEAD_INIT was added in Python 2.6.  Its use is
+ * necessary to handle both Python 2 and 3.  This replacement
+ * definition is for Python <=2.5
+ */
+#ifndef PyVarObject_HEAD_INIT
+#define PyVarObject_HEAD_INIT(type, size) 		\
+		PyObject_HEAD_INIT(type) size,
+#endif
 
 #include "postgres.h"
 
@@ -246,7 +288,11 @@ static char *PLy_strdup(const char *);
 static void PLy_free(void *);
 
 static PyObject*PLyUnicode_Str(PyObject *unicode);
+static PyObject*PLyUnicode_Bytes(PyObject *unicode);
 static char *PLyUnicode_AsString(PyObject *unicode);
+#if PY_MAJOR_VERSION >= 3
+static PyObject *PLyUnicode_FromString(const char *s);
+#endif
 
 /* sub handlers for functions and triggers */
 static Datum PLy_function_handler(FunctionCallInfo fcinfo, PLyProcedure *);
@@ -288,7 +334,7 @@ static PyObject *PLyFloat_FromNumeric(PLyDatumToOb *arg, Datum d);
 static PyObject *PLyInt_FromInt16(PLyDatumToOb *arg, Datum d);
 static PyObject *PLyInt_FromInt32(PLyDatumToOb *arg, Datum d);
 static PyObject *PLyLong_FromInt64(PLyDatumToOb *arg, Datum d);
-static PyObject *PLyString_FromBytea(PLyDatumToOb *arg, Datum d);
+static PyObject *PLyBytes_FromBytea(PLyDatumToOb *arg, Datum d);
 static PyObject *PLyString_FromDatum(PLyDatumToOb *arg, Datum d);
 static PyObject *PLyList_FromArray(PLyDatumToOb *arg, Datum d);
 
@@ -1760,7 +1806,7 @@ PLy_input_datum_func2(PLyDatumToOb *arg, Oid typeOid, HeapTuple typeTup)
 			arg->func = PLyLong_FromInt64;
 			break;
 		case BYTEAOID:
-			arg->func = PLyString_FromBytea;
+			arg->func = PLyBytes_FromBytea;
 			break;
 		default:
 			arg->func = PLyString_FromDatum;
@@ -1859,13 +1905,13 @@ PLyLong_FromInt64(PLyDatumToOb *arg, Datum d)
 }
 
 static PyObject *
-PLyString_FromBytea(PLyDatumToOb *arg, Datum d)
+PLyBytes_FromBytea(PLyDatumToOb *arg, Datum d)
 {
 	text     *txt = DatumGetByteaP(d);
 	char     *str = VARDATA(txt);
 	size_t    size = VARSIZE(txt) - VARHDRSZ;
 
-	return PyString_FromStringAndSize(str, size);
+	return PyBytes_FromStringAndSize(str, size);
 }
 
 static PyObject *
@@ -2001,14 +2047,14 @@ PLyObject_ToBytea(PLyTypeInfo *info,
 
 	Assert(plrv != Py_None);
 
-	plrv_so = PyObject_Str(plrv);
+	plrv_so = PyObject_Bytes(plrv);
 	if (!plrv_so)
-		PLy_elog(ERROR, "could not create string representation of Python object");
+		PLy_elog(ERROR, "could not create bytes representation of Python object");
 
 	PG_TRY();
 	{
-		char *plrv_sc = PyString_AsString(plrv_so);
-		size_t len = PyString_Size(plrv_so);
+		char *plrv_sc = PyBytes_AsString(plrv_so);
+		size_t len = PyBytes_Size(plrv_so);
 		size_t size = len + VARHDRSZ;
 		bytea *result = palloc(size);
 
@@ -2040,22 +2086,30 @@ PLyObject_ToDatum(PLyTypeInfo *info,
 				  PLyObToDatum *arg,
 				  PyObject *plrv)
 {
-	PyObject *volatile plrv_so = NULL;
+	PyObject *volatile plrv_bo = NULL;
 	Datum     rv;
 
 	Assert(plrv != Py_None);
 
 	if (PyUnicode_Check(plrv))
-		plrv_so = PLyUnicode_Str(plrv);
+		plrv_bo = PLyUnicode_Bytes(plrv);
 	else
-		plrv_so = PyObject_Str(plrv);
-	if (!plrv_so)
+	{
+#if PY_MAJOR_VERSION >= 3
+		PyObject *s = PyObject_Str(plrv);
+		plrv_bo = PLyUnicode_Bytes(s);
+		Py_XDECREF(s);
+#else
+		plrv_bo = PyObject_Str(plrv);
+#endif
+	}
+	if (!plrv_bo)
 		PLy_elog(ERROR, "could not create string representation of Python object");
 
 	PG_TRY();
 	{
-		char *plrv_sc = PyString_AsString(plrv_so);
-		size_t plen = PyString_Size(plrv_so);
+		char *plrv_sc = PyBytes_AsString(plrv_bo);
+		size_t plen = PyBytes_Size(plrv_bo);
 		size_t slen = strlen(plrv_sc);
 
 		if (slen < plen)
@@ -2068,12 +2122,12 @@ PLyObject_ToDatum(PLyTypeInfo *info,
 	}
 	PG_CATCH();
 	{
-		Py_XDECREF(plrv_so);
+		Py_XDECREF(plrv_bo);
 		PG_RE_THROW();
 	}
 	PG_END_TRY();
 
-	Py_XDECREF(plrv_so);
+	Py_XDECREF(plrv_bo);
 
 	return rv;
 }
@@ -2368,8 +2422,7 @@ static PyMethodDef PLy_plan_methods[] = {
 };
 
 static PyTypeObject PLy_PlanType = {
-	PyObject_HEAD_INIT(NULL)
-	0,							/* ob_size */
+	PyVarObject_HEAD_INIT(NULL, 0)
 	"PLyPlan",					/* tp_name */
 	sizeof(PLyPlanObject),		/* tp_size */
 	0,							/* tp_itemsize */
@@ -2420,8 +2473,7 @@ static PyMethodDef PLy_result_methods[] = {
 };
 
 static PyTypeObject PLy_ResultType = {
-	PyObject_HEAD_INIT(NULL)
-	0,							/* ob_size */
+	PyVarObject_HEAD_INIT(NULL, 0)
 	"PLyResult",				/* tp_name */
 	sizeof(PLyResultObject),	/* tp_size */
 	0,							/* tp_itemsize */
@@ -2480,6 +2532,15 @@ static PyMethodDef PLy_methods[] = {
 	{NULL, NULL, 0, NULL}
 };
 
+#if PY_MAJOR_VERSION >= 3
+static PyModuleDef PLy_module = {
+	PyModuleDef_HEAD_INIT,		/* m_base */
+	"plpy",						/* m_name */
+	NULL,						/* m_doc */
+	-1,							/* m_size */
+	PLy_methods,				/* m_methods */
+};
+#endif
 
 /* plan object methods */
 static PyObject *
@@ -3067,6 +3128,15 @@ PLy_spi_execute_fetch_result(SPITupleTable *tuptable, int rows, int status)
  * language handler and interpreter initialization
  */
 
+#if PY_MAJOR_VERSION >= 3
+static PyMODINIT_FUNC
+PyInit_plpy(void)
+{
+	return PyModule_Create(&PLy_module);
+}
+#endif
+
+
 /*
  * _PG_init()			- library load-time initialization
  *
@@ -3083,7 +3153,13 @@ _PG_init(void)
 
 	pg_bindtextdomain(TEXTDOMAIN);
 
+#if PY_MAJOR_VERSION >= 3
+	PyImport_AppendInittab("plpy", PyInit_plpy);
+#endif
 	Py_Initialize();
+#if PY_MAJOR_VERSION >= 3
+	PyImport_ImportModule("plpy");
+#endif
 	PLy_init_interp();
 	PLy_init_plpy();
 	if (PyErr_Occurred())
@@ -3129,7 +3205,11 @@ PLy_init_plpy(void)
 	if (PyType_Ready(&PLy_ResultType) < 0)
 		elog(ERROR, "could not initialize PLy_ResultType");
 
+#if PY_MAJOR_VERSION >= 3
+	plpy = PyModule_Create(&PLy_module);
+#else
 	plpy = Py_InitModule("plpy", PLy_methods);
+#endif
 	plpy_dict = PyModule_GetDict(plpy);
 
 	/* PyDict_SetItemString(plpy, "PlanType", (PyObject *) &PLy_PlanType); */
@@ -3475,12 +3555,29 @@ PLy_free(void *ptr)
 }
 
 /*
- * Convert a Python unicode object to a Python string object in
+ * Convert a Unicode object to a Python string.
+ */
+static PyObject*
+PLyUnicode_Str(PyObject *unicode)
+{
+#if PY_MAJOR_VERSION >= 3
+	/* In Python 3, this is a noop. */
+	Py_INCREF(unicode);
+	return unicode;
+#else
+	/* In Python 2, this means converting the Unicode to bytes in the
+	 * server encoding. */
+	return PLyUnicode_Bytes(unicode);
+#endif
+}
+
+/*
+ * Convert a Python unicode object to a Python string/bytes object in
  * PostgreSQL server encoding.  Reference ownership is passed to the
  * caller.
  */
 static PyObject*
-PLyUnicode_Str(PyObject *unicode)
+PLyUnicode_Bytes(PyObject *unicode)
 {
 	PyObject *rv;
 	const char *serverenc;
@@ -3502,13 +3599,44 @@ PLyUnicode_Str(PyObject *unicode)
 /*
  * Convert a Python unicode object to a C string in PostgreSQL server
  * encoding.  No Python object reference is passed out of this
- * function.
+ * function.  The result is palloc'ed.
+ *
+ * Note that this function is disguised as PyString_AsString() when
+ * using Python 3.  That function retuns a pointer into the internal
+ * memory of the argument, which isn't exactly the interface of this
+ * function.  But in either case you get a rather short-lived
+ * reference that you ought to better leave alone.
  */
 static char *
 PLyUnicode_AsString(PyObject *unicode)
 {
-	PyObject *o = PLyUnicode_Str(unicode);
-	char *rv = PyString_AsString(o);
+	PyObject *o = PLyUnicode_Bytes(unicode);
+	char *rv = pstrdup(PyBytes_AsString(o));
 	Py_XDECREF(o);
 	return rv;
 }
+
+#if PY_MAJOR_VERSION >= 3
+/*
+ * Convert a C string in the PostgreSQL server encoding to a Python
+ * unicode object.  Reference ownership is passed to the caller.
+ */
+static PyObject *
+PLyUnicode_FromString(const char *s)
+{
+    char       *utf8string;
+	PyObject   *o;
+
+    utf8string = (char *) pg_do_encoding_conversion((unsigned char *) s,
+													strlen(s),
+													GetDatabaseEncoding(),
+													PG_UTF8);
+
+	o = PyUnicode_FromString(utf8string);
+
+    if (utf8string != s)
+        pfree(utf8string);
+
+	return o;
+}
+#endif /* PY_MAJOR_VERSION >= 3 */

src/pl/plpython/sql/plpython_test.sql

 -- first some tests of basic functionality
+CREATE LANGUAGE plpython2u;
 
 -- really stupid function just to get the module loaded
 CREATE FUNCTION stupid() RETURNS text AS 'return "zarkon"' LANGUAGE plpythonu;
 
 select stupid();
 
+-- check 2/3 versioning
+CREATE FUNCTION stupidn() RETURNS text AS 'return "zarkon"' LANGUAGE plpython2u;
+
+select stupidn();
 
 -- test multiple arguments
 CREATE FUNCTION argument_test_one(u users, a1 text, a2 text) RETURNS text

src/pl/plpython/sql/plpython_trigger.sql

@@ -67,7 +67,7 @@ SELECT * FROM users;
 CREATE TABLE trigger_test
 	(i int, v text );
 
-CREATE FUNCTION trigger_data() returns trigger language plpythonu as $$
+CREATE FUNCTION trigger_data() RETURNS trigger LANGUAGE plpythonu AS $$
 
 if 'relid' in TD:
 	TD['relid'] = "bogus:12345"