Add transforms feature

This provides a mechanism for specifying conversions between SQL data
types and procedural languages.  As examples, there are transforms
for hstore and ltree for PL/Perl and PL/Python.

reviews by Pavel Stěhule and Andres Freund

src/pl/plperl/GNUmakefile

@@ -99,15 +99,17 @@ Util.c: Util.xs plperl_helpers.h
 install: all install-lib install-data
 
 installdirs: installdirs-lib
-	$(MKDIR_P) '$(DESTDIR)$(datadir)/extension'
+	$(MKDIR_P) '$(DESTDIR)$(datadir)/extension' '$(DESTDIR)$(includedir_server)'
 
 uninstall: uninstall-lib uninstall-data
 
 install-data: installdirs
 	$(INSTALL_DATA) $(addprefix $(srcdir)/, $(DATA)) '$(DESTDIR)$(datadir)/extension/'
+	$(INSTALL_DATA) $(srcdir)/plperl.h $(srcdir)/ppport.h '$(DESTDIR)$(includedir_server)'
 
 uninstall-data:
 	rm -f $(addprefix '$(DESTDIR)$(datadir)/extension'/, $(notdir $(DATA)))
+	rm -f $(addprefix '$(DESTDIR)$(includedir_server)'/, plperl.h ppport.h)
 
 .PHONY: install-data uninstall-data
 

src/pl/plperl/plperl.c

@@ -20,6 +20,7 @@
 #include "access/xact.h"
 #include "catalog/pg_language.h"
 #include "catalog/pg_proc.h"
+#include "catalog/pg_proc_fn.h"
 #include "catalog/pg_type.h"
 #include "commands/event_trigger.h"
 #include "commands/trigger.h"
@@ -110,6 +111,8 @@ typedef struct plperl_proc_desc
 	SV		   *reference;		/* CODE reference for Perl sub */
 	plperl_interp_desc *interp; /* interpreter it's created in */
 	bool		fn_readonly;	/* is function readonly (not volatile)? */
+	Oid			lang_oid;
+	List	   *trftypes;
 	bool		lanpltrusted;	/* is it plperl, rather than plperlu? */
 	bool		fn_retistuple;	/* true, if function returns tuple */
 	bool		fn_retisset;	/* true, if function returns set */
@@ -210,6 +213,7 @@ typedef struct plperl_array_info
 	bool	   *nulls;
 	int		   *nelems;
 	FmgrInfo	proc;
+	FmgrInfo	transform_proc;
 } plperl_array_info;
 
 /**********************************************************************
@@ -1272,6 +1276,7 @@ plperl_sv_to_datum(SV *sv, Oid typid, int32 typmod,
 				   bool *isnull)
 {
 	FmgrInfo	tmp;
+	Oid			funcid;
 
 	/* we might recurse */
 	check_stack_depth();
@@ -1295,6 +1300,8 @@ plperl_sv_to_datum(SV *sv, Oid typid, int32 typmod,
 		/* must call typinput in case it wants to reject NULL */
 		return InputFunctionCall(finfo, NULL, typioparam, typmod);
 	}
+	else if ((funcid = get_transform_tosql(typid, current_call_data->prodesc->lang_oid, current_call_data->prodesc->trftypes)))
+		return OidFunctionCall1(funcid, PointerGetDatum(sv));
 	else if (SvROK(sv))
 	{
 		/* handle references */
@@ -1407,6 +1414,7 @@ plperl_ref_from_pg_array(Datum arg, Oid typid)
 				typdelim;
 	Oid			typioparam;
 	Oid			typoutputfunc;
+	Oid			transform_funcid;
 	int			i,
 				nitems,
 			   *dims;
@@ -1414,14 +1422,17 @@ plperl_ref_from_pg_array(Datum arg, Oid typid)
 	SV		   *av;
 	HV		   *hv;
 
-	info = palloc(sizeof(plperl_array_info));
+	info = palloc0(sizeof(plperl_array_info));
 
 	/* get element type information, including output conversion function */
 	get_type_io_data(elementtype, IOFunc_output,
 					 &typlen, &typbyval, &typalign,
 					 &typdelim, &typioparam, &typoutputfunc);
 
-	perm_fmgr_info(typoutputfunc, &info->proc);
+	if ((transform_funcid = get_transform_fromsql(elementtype, current_call_data->prodesc->lang_oid, current_call_data->prodesc->trftypes)))
+		perm_fmgr_info(transform_funcid, &info->transform_proc);
+	else
+		perm_fmgr_info(typoutputfunc, &info->proc);
 
 	info->elem_is_rowtype = type_is_rowtype(elementtype);
 
@@ -1502,8 +1513,10 @@ make_array_ref(plperl_array_info *info, int first, int last)
 		{
 			Datum		itemvalue = info->elements[i];
 
-			/* Handle composite type elements */
-			if (info->elem_is_rowtype)
+			if (info->transform_proc.fn_oid)
+				av_push(result, (SV *) DatumGetPointer(FunctionCall1(&info->transform_proc, itemvalue)));
+			else if (info->elem_is_rowtype)
+				/* Handle composite type elements */
 				av_push(result, plperl_hash_from_datum(itemvalue));
 			else
 			{
@@ -1812,6 +1825,8 @@ plperl_inline_handler(PG_FUNCTION_ARGS)
 	desc.proname = "inline_code_block";
 	desc.fn_readonly = false;
 
+	desc.lang_oid = codeblock->langOid;
+	desc.trftypes = NIL;
 	desc.lanpltrusted = codeblock->langIsTrusted;
 
 	desc.fn_retistuple = false;
@@ -2076,6 +2091,8 @@ plperl_call_perl_func(plperl_proc_desc *desc, FunctionCallInfo fcinfo)
 	SV		   *retval;
 	int			i;
 	int			count;
+	Oid		   *argtypes = NULL;
+	int			nargs = 0;
 
 	ENTER;
 	SAVETMPS;
@@ -2083,6 +2100,9 @@ plperl_call_perl_func(plperl_proc_desc *desc, FunctionCallInfo fcinfo)
 	PUSHMARK(SP);
 	EXTEND(sp, desc->nargs);
 
+	if (fcinfo->flinfo->fn_oid)
+		get_func_signature(fcinfo->flinfo->fn_oid, &argtypes, &nargs);
+
 	for (i = 0; i < desc->nargs; i++)
 	{
 		if (fcinfo->argnull[i])
@@ -2096,9 +2116,12 @@ plperl_call_perl_func(plperl_proc_desc *desc, FunctionCallInfo fcinfo)
 		else
 		{
 			SV		   *sv;
+			Oid			funcid;
 
 			if (OidIsValid(desc->arg_arraytype[i]))
 				sv = plperl_ref_from_pg_array(fcinfo->arg[i], desc->arg_arraytype[i]);
+			else if ((funcid = get_transform_fromsql(argtypes[i], current_call_data->prodesc->lang_oid, current_call_data->prodesc->trftypes)))
+				sv = (SV *) DatumGetPointer(OidFunctionCall1(funcid, fcinfo->arg[i]));
 			else
 			{
 				char	   *tmp;
@@ -2569,6 +2592,7 @@ free_plperl_function(plperl_proc_desc *prodesc)
 	/* (FmgrInfo subsidiary info will get leaked ...) */
 	if (prodesc->proname)
 		free(prodesc->proname);
+	list_free(prodesc->trftypes);
 	free(prodesc);
 }
 
@@ -2631,6 +2655,7 @@ compile_plperl_function(Oid fn_oid, bool is_trigger, bool is_event_trigger)
 		HeapTuple	typeTup;
 		Form_pg_language langStruct;
 		Form_pg_type typeStruct;
+		Datum		protrftypes_datum;
 		Datum		prosrcdatum;
 		bool		isnull;
 		char	   *proc_source;
@@ -2661,6 +2686,16 @@ compile_plperl_function(Oid fn_oid, bool is_trigger, bool is_event_trigger)
 		prodesc->fn_readonly =
 			(procStruct->provolatile != PROVOLATILE_VOLATILE);
 
+		{
+			MemoryContext oldcxt;
+
+			protrftypes_datum = SysCacheGetAttr(PROCOID, procTup,
+												Anum_pg_proc_protrftypes, &isnull);
+			oldcxt = MemoryContextSwitchTo(TopMemoryContext);
+			prodesc->trftypes = isnull ? NIL : oid_array_to_list(protrftypes_datum);
+			MemoryContextSwitchTo(oldcxt);
+		}
+
 		/************************************************************
 		 * Lookup the pg_language tuple by Oid
 		 ************************************************************/
@@ -2673,6 +2708,7 @@ compile_plperl_function(Oid fn_oid, bool is_trigger, bool is_event_trigger)
 				 procStruct->prolang);
 		}
 		langStruct = (Form_pg_language) GETSTRUCT(langTup);
+		prodesc->lang_oid = HeapTupleGetOid(langTup);
 		prodesc->lanpltrusted = langStruct->lanpltrusted;
 		ReleaseSysCache(langTup);
 
@@ -2906,9 +2942,12 @@ plperl_hash_from_tuple(HeapTuple tuple, TupleDesc tupdesc)
 		else
 		{
 			SV		   *sv;
+			Oid			funcid;
 
 			if (OidIsValid(get_base_element_type(tupdesc->attrs[i]->atttypid)))
 				sv = plperl_ref_from_pg_array(attr, tupdesc->attrs[i]->atttypid);
+			else if ((funcid = get_transform_fromsql(tupdesc->attrs[i]->atttypid, current_call_data->prodesc->lang_oid, current_call_data->prodesc->trftypes)))
+				sv = (SV *) DatumGetPointer(OidFunctionCall1(funcid, attr));
 			else
 			{
 				char	   *outputstr;

src/pl/plperl/plperl_helpers.h

@@ -1,6 +1,8 @@
 #ifndef PL_PERL_HELPERS_H
 #define PL_PERL_HELPERS_H
 
+#include "mb/pg_wchar.h"
+
 /*
  * convert from utf8 to database encoding
  *

src/pl/plpython/Makefile

@@ -123,54 +123,22 @@ all: all-lib
 install: all install-lib install-data
 
 installdirs: installdirs-lib
-	$(MKDIR_P) '$(DESTDIR)$(datadir)/extension'
+	$(MKDIR_P) '$(DESTDIR)$(datadir)/extension' '$(DESTDIR)$(includedir_server)'
 
 uninstall: uninstall-lib uninstall-data
 
 install-data: installdirs
 	$(INSTALL_DATA) $(addprefix $(srcdir)/, $(DATA)) '$(DESTDIR)$(datadir)/extension/'
+	$(INSTALL_DATA) $(srcdir)/plpython.h $(srcdir)/plpy_util.h '$(DESTDIR)$(includedir_server)'
 
 uninstall-data:
 	rm -f $(addprefix '$(DESTDIR)$(datadir)/extension'/, $(notdir $(DATA)))
+	rm -f $(addprefix '$(DESTDIR)$(includedir_server)'/, plpython.h plpy_util.h)
 
 .PHONY: install-data uninstall-data
 
 
-ifeq ($(python_majorversion),3)
-# Adjust regression tests for Python 3 compatibility
-#
-# Mention those regression test files that need to be mangled in the
-# variable REGRESS_PLPYTHON3_MANGLE.  They will be copied to a
-# subdirectory python3/ and have their Python syntax and other bits
-# adjusted to work with Python 3.
-
-# Note that the order of the tests needs to be preserved in this
-# expression.
-REGRESS := $(foreach test,$(REGRESS),$(if $(filter $(test),$(REGRESS_PLPYTHON3_MANGLE)),python3/$(test),$(test)))
-
-.PHONY: pgregress-python3-mangle
-pgregress-python3-mangle:
-	$(MKDIR_P) sql/python3 expected/python3 results/python3
-	for file in $(patsubst %,$(srcdir)/sql/%.sql,$(REGRESS_PLPYTHON3_MANGLE)) $(patsubst %,$(srcdir)/expected/%*.out,$(REGRESS_PLPYTHON3_MANGLE)); 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" \
-	      -e "s/EXTENSION plpythonu/EXTENSION plpython3u/g" \
-	      -e "s/EXTENSION plpython2u/EXTENSION plpython3u/g" \
-	    $$file >`echo $$file | sed 's,^.*/\([^/][^/]*/\)\([^/][^/]*\)$$,\1python3/\2,'` || exit; \
-	done
-
-check installcheck: pgregress-python3-mangle
-
-pg_regress_clean_files += sql/python3/ expected/python3/ results/python3/
-
-endif # Python 3
+include $(srcdir)/regress-python3-mangle.mk
 
 
 check: all submake

src/pl/plpython/plpy_main.c

@@ -278,6 +278,7 @@ plpython_inline_handler(PG_FUNCTION_ARGS)
 
 	MemSet(&proc, 0, sizeof(PLyProcedure));
 	proc.pyname = PLy_strdup("__plpython_inline_block");
+	proc.langid = codeblock->langOid;
 	proc.result.out.d.typoid = VOIDOID;
 
 	/*

src/pl/plpython/plpy_procedure.c

@@ -10,9 +10,12 @@
 #include "access/transam.h"
 #include "funcapi.h"
 #include "catalog/pg_proc.h"
+#include "catalog/pg_proc_fn.h"
 #include "catalog/pg_type.h"
 #include "utils/builtins.h"
 #include "utils/hsearch.h"
+#include "utils/inval.h"
+#include "utils/memutils.h"
 #include "utils/syscache.h"
 
 #include "plpython.h"
@@ -26,6 +29,7 @@
 static HTAB *PLy_procedure_cache = NULL;
 
 static PLyProcedure *PLy_procedure_create(HeapTuple procTup, Oid fn_oid, bool is_trigger);
+static void invalidate_procedure_caches(Datum arg, int cacheid, uint32 hashvalue);
 static bool PLy_procedure_argument_valid(PLyTypeInfo *arg);
 static bool PLy_procedure_valid(PLyProcedure *proc, HeapTuple procTup);
 static char *PLy_procedure_munge_source(const char *name, const char *src);
@@ -41,6 +45,29 @@ init_procedure_caches(void)
 	hash_ctl.entrysize = sizeof(PLyProcedureEntry);
 	PLy_procedure_cache = hash_create("PL/Python procedures", 32, &hash_ctl,
 									  HASH_ELEM | HASH_BLOBS);
+	CacheRegisterSyscacheCallback(TRFTYPELANG,
+								  invalidate_procedure_caches,
+								  (Datum) 0);
+}
+
+static void
+invalidate_procedure_caches(Datum arg, int cacheid, uint32 hashvalue)
+{
+	HASH_SEQ_STATUS status;
+	PLyProcedureEntry *hentry;
+
+	Assert(PLy_procedure_cache != NULL);
+
+	/* flush all entries */
+	hash_seq_init(&status, PLy_procedure_cache);
+
+	while ((hentry = (PLyProcedureEntry *) hash_seq_search(&status)))
+	{
+		if (hash_search(PLy_procedure_cache,
+						(void *) &hentry->key,
+						HASH_REMOVE, NULL) == NULL)
+			elog(ERROR, "hash table corrupted");
+	}
 }
 
 /*
@@ -165,6 +192,16 @@ PLy_procedure_create(HeapTuple procTup, Oid fn_oid, bool is_trigger)
 	for (i = 0; i < FUNC_MAX_ARGS; i++)
 		PLy_typeinfo_init(&proc->args[i]);
 	proc->nargs = 0;
+	proc->langid = procStruct->prolang;
+	{
+		MemoryContext oldcxt;
+
+		Datum protrftypes_datum = SysCacheGetAttr(PROCOID, procTup,
+												  Anum_pg_proc_protrftypes, &isnull);
+		oldcxt = MemoryContextSwitchTo(TopMemoryContext);
+		proc->trftypes = isnull ? NIL : oid_array_to_list(protrftypes_datum);
+		MemoryContextSwitchTo(oldcxt);
+	}
 	proc->code = proc->statics = NULL;
 	proc->globals = NULL;
 	proc->is_setof = procStruct->proretset;
@@ -219,7 +256,7 @@ PLy_procedure_create(HeapTuple procTup, Oid fn_oid, bool is_trigger)
 			else
 			{
 				/* do the real work */
-				PLy_output_datum_func(&proc->result, rvTypeTup);
+				PLy_output_datum_func(&proc->result, rvTypeTup, proc->langid, proc->trftypes);
 			}
 
 			ReleaseSysCache(rvTypeTup);
@@ -293,7 +330,9 @@ PLy_procedure_create(HeapTuple procTup, Oid fn_oid, bool is_trigger)
 					default:
 						PLy_input_datum_func(&(proc->args[pos]),
 											 types[i],
-											 argTypeTup);
+											 argTypeTup,
+											 proc->langid,
+											 proc->trftypes);
 						break;
 				}
 

src/pl/plpython/plpy_procedure.h

@@ -27,6 +27,8 @@ typedef struct PLyProcedure
 	char	  **argnames;		/* Argument names */
 	PLyTypeInfo args[FUNC_MAX_ARGS];
 	int			nargs;
+	Oid			langid;			/* OID of plpython pg_language entry */
+	List	   *trftypes;		/* OID list of transform types */
 	PyObject   *code;			/* compiled procedure code */
 	PyObject   *statics;		/* data saved across calls, local scope */
 	PyObject   *globals;		/* data saved across calls, global scope */

src/pl/plpython/plpy_spi.c

@@ -76,6 +76,7 @@ PLy_spi_prepare(PyObject *self, PyObject *args)
 	PG_TRY();
 	{
 		int			i;
+		PLyExecutionContext *exec_ctx = PLy_current_execution_context();
 
 		/*
 		 * the other loop might throw an exception, if PLyTypeInfo member
@@ -128,7 +129,7 @@ PLy_spi_prepare(PyObject *self, PyObject *args)
 			optr = NULL;
 
 			plan->types[i] = typeId;
-			PLy_output_datum_func(&plan->args[i], typeTup);
+			PLy_output_datum_func(&plan->args[i], typeTup, exec_ctx->curr_proc->langid, exec_ctx->curr_proc->trftypes);
 			ReleaseSysCache(typeTup);
 		}
 

src/pl/plpython/plpy_typeio.c

@@ -29,8 +29,8 @@
 
 
 /* I/O function caching */
-static void PLy_input_datum_func2(PLyDatumToOb *arg, Oid typeOid, HeapTuple typeTup);
-static void PLy_output_datum_func2(PLyObToDatum *arg, HeapTuple typeTup);
+static void PLy_input_datum_func2(PLyDatumToOb *arg, Oid typeOid, HeapTuple typeTup, Oid langid, List *trftypes);
+static void PLy_output_datum_func2(PLyObToDatum *arg, HeapTuple typeTup, Oid langid, List *trftypes);
 
 /* conversion from Datums to Python objects */
 static PyObject *PLyBool_FromBool(PLyDatumToOb *arg, Datum d);
@@ -43,6 +43,7 @@ static PyObject *PLyLong_FromInt64(PLyDatumToOb *arg, Datum d);
 static PyObject *PLyLong_FromOid(PLyDatumToOb *arg, Datum d);
 static PyObject *PLyBytes_FromBytea(PLyDatumToOb *arg, Datum d);
 static PyObject *PLyString_FromDatum(PLyDatumToOb *arg, Datum d);
+static PyObject *PLyObject_FromTransform(PLyDatumToOb *arg, Datum d);
 static PyObject *PLyList_FromArray(PLyDatumToOb *arg, Datum d);
 
 /* conversion from Python objects to Datums */
@@ -50,6 +51,7 @@ static Datum PLyObject_ToBool(PLyObToDatum *arg, int32 typmod, PyObject *plrv);
 static Datum PLyObject_ToBytea(PLyObToDatum *arg, int32 typmod, PyObject *plrv);
 static Datum PLyObject_ToComposite(PLyObToDatum *arg, int32 typmod, PyObject *plrv);
 static Datum PLyObject_ToDatum(PLyObToDatum *arg, int32 typmod, PyObject *plrv);
+static Datum PLyObject_ToTransform(PLyObToDatum *arg, int32 typmod, PyObject *plrv);
 static Datum PLySequence_ToArray(PLyObToDatum *arg, int32 typmod, PyObject *plrv);
 
 /* conversion from Python objects to composite Datums (used by triggers and SRFs) */
@@ -102,27 +104,28 @@ PLy_typeinfo_dealloc(PLyTypeInfo *arg)
  * PostgreSQL, and vice versa.
  */
 void
-PLy_input_datum_func(PLyTypeInfo *arg, Oid typeOid, HeapTuple typeTup)
+PLy_input_datum_func(PLyTypeInfo *arg, Oid typeOid, HeapTuple typeTup, Oid langid, List *trftypes)
 {
 	if (arg->is_rowtype > 0)
 		elog(ERROR, "PLyTypeInfo struct is initialized for Tuple");
 	arg->is_rowtype = 0;
-	PLy_input_datum_func2(&(arg->in.d), typeOid, typeTup);
+	PLy_input_datum_func2(&(arg->in.d), typeOid, typeTup, langid, trftypes);
 }
 
 void
-PLy_output_datum_func(PLyTypeInfo *arg, HeapTuple typeTup)
+PLy_output_datum_func(PLyTypeInfo *arg, HeapTuple typeTup, Oid langid, List *trftypes)
 {
 	if (arg->is_rowtype > 0)
 		elog(ERROR, "PLyTypeInfo struct is initialized for a Tuple");
 	arg->is_rowtype = 0;
-	PLy_output_datum_func2(&(arg->out.d), typeTup);
+	PLy_output_datum_func2(&(arg->out.d), typeTup, langid, trftypes);
 }
 
 void
 PLy_input_tuple_funcs(PLyTypeInfo *arg, TupleDesc desc)
 {
 	int			i;
+	PLyExecutionContext *exec_ctx = PLy_current_execution_context();
 
 	if (arg->is_rowtype == 0)
 		elog(ERROR, "PLyTypeInfo struct is initialized for a Datum");
@@ -181,7 +184,9 @@ PLy_input_tuple_funcs(PLyTypeInfo *arg, TupleDesc desc)
 
 		PLy_input_datum_func2(&(arg->in.r.atts[i]),
 							  desc->attrs[i]->atttypid,
-							  typeTup);
+							  typeTup,
+							  exec_ctx->curr_proc->langid,
+							  exec_ctx->curr_proc->trftypes);
 
 		ReleaseSysCache(typeTup);
 	}
@@ -191,6 +196,7 @@ void
 PLy_output_tuple_funcs(PLyTypeInfo *arg, TupleDesc desc)
 {
 	int			i;
+	PLyExecutionContext *exec_ctx = PLy_current_execution_context();
 
 	if (arg->is_rowtype == 0)
 		elog(ERROR, "PLyTypeInfo struct is initialized for a Datum");
@@ -243,7 +249,9 @@ PLy_output_tuple_funcs(PLyTypeInfo *arg, TupleDesc desc)
 			elog(ERROR, "cache lookup failed for type %u",
 				 desc->attrs[i]->atttypid);
 
-		PLy_output_datum_func2(&(arg->out.r.atts[i]), typeTup);
+		PLy_output_datum_func2(&(arg->out.r.atts[i]), typeTup,
+							   exec_ctx->curr_proc->langid,
+							   exec_ctx->curr_proc->trftypes);
 
 		ReleaseSysCache(typeTup);
 	}
@@ -362,10 +370,12 @@ PLyObject_ToCompositeDatum(PLyTypeInfo *info, TupleDesc desc, PyObject *plrv)
 }
 
 static void
-PLy_output_datum_func2(PLyObToDatum *arg, HeapTuple typeTup)
+PLy_output_datum_func2(PLyObToDatum *arg, HeapTuple typeTup, Oid langid, List *trftypes)
 {
 	Form_pg_type typeStruct = (Form_pg_type) GETSTRUCT(typeTup);
 	Oid			element_type;
+	Oid			base_type;
+	Oid			funcid;
 
 	perm_fmgr_info(typeStruct->typinput, &arg->typfunc);
 	arg->typoid = HeapTupleGetOid(typeTup);
@@ -374,12 +384,24 @@ PLy_output_datum_func2(PLyObToDatum *arg, HeapTuple typeTup)
 	arg->typbyval = typeStruct->typbyval;
 
 	element_type = get_base_element_type(arg->typoid);
+	base_type = getBaseType(element_type ? element_type : arg->typoid);
 
 	/*
 	 * Select a conversion function to convert Python objects to PostgreSQL
-	 * datums.  Most data types can go through the generic function.
+	 * datums.
 	 */
-	switch (getBaseType(element_type ? element_type : arg->typoid))
+
+	if ((funcid = get_transform_tosql(base_type, langid, trftypes)))
+	{
+		arg->func = PLyObject_ToTransform;
+		perm_fmgr_info(funcid, &arg->typtransform);
+	}
+	else if (typeStruct->typtype == TYPTYPE_COMPOSITE)
+	{
+		arg->func = PLyObject_ToComposite;
+	}
+	else
+	switch (base_type)
 	{
 		case BOOLOID:
 			arg->func = PLyObject_ToBool;
@@ -392,12 +414,6 @@ PLy_output_datum_func2(PLyObToDatum *arg, HeapTuple typeTup)
 			break;
 	}
 
-	/* Composite types need their own input routine, though */
-	if (typeStruct->typtype == TYPTYPE_COMPOSITE)
-	{
-		arg->func = PLyObject_ToComposite;
-	}
-
 	if (element_type)
 	{
 		char		dummy_delim;
@@ -408,6 +424,7 @@ PLy_output_datum_func2(PLyObToDatum *arg, HeapTuple typeTup)
 
 		arg->elm = PLy_malloc0(sizeof(*arg->elm));
 		arg->elm->func = arg->func;
+		arg->elm->typtransform = arg->typtransform;
 		arg->func = PLySequence_ToArray;
 
 		arg->elm->typoid = element_type;
@@ -420,12 +437,12 @@ PLy_output_datum_func2(PLyObToDatum *arg, HeapTuple typeTup)
 }
 
 static void
-PLy_input_datum_func2(PLyDatumToOb *arg, Oid typeOid, HeapTuple typeTup)
+PLy_input_datum_func2(PLyDatumToOb *arg, Oid typeOid, HeapTuple typeTup, Oid langid, List *trftypes)
 {
 	Form_pg_type typeStruct = (Form_pg_type) GETSTRUCT(typeTup);
-
-	/* It's safe to handle domains of array types as its base array type. */
-	Oid			element_type = get_base_element_type(typeOid);
+	Oid			element_type;
+	Oid			base_type;
+	Oid			funcid;
 
 	/* Get the type's conversion information */
 	perm_fmgr_info(typeStruct->typoutput, &arg->typfunc);
@@ -437,7 +454,17 @@ PLy_input_datum_func2(PLyDatumToOb *arg, Oid typeOid, HeapTuple typeTup)
 	arg->typalign = typeStruct->typalign;
 
 	/* Determine which kind of Python object we will convert to */
-	switch (getBaseType(element_type ? element_type : typeOid))
+
+	element_type = get_base_element_type(typeOid);
+	base_type = getBaseType(element_type ? element_type : typeOid);
+
+	if ((funcid = get_transform_fromsql(base_type, langid, trftypes)))
+	{
+		arg->func = PLyObject_FromTransform;
+		perm_fmgr_info(funcid, &arg->typtransform);
+	}
+	else
+	switch (base_type)
 	{
 		case BOOLOID:
 			arg->func = PLyBool_FromBool;
@@ -478,6 +505,7 @@ PLy_input_datum_func2(PLyDatumToOb *arg, Oid typeOid, HeapTuple typeTup)
 
 		arg->elm = PLy_malloc0(sizeof(*arg->elm));
 		arg->elm->func = arg->func;
+		arg->elm->typtransform = arg->typtransform;
 		arg->func = PLyList_FromArray;
 		arg->elm->typoid = element_type;
 		arg->elm->typmod = -1;
@@ -596,6 +624,12 @@ PLyString_FromDatum(PLyDatumToOb *arg, Datum d)
 	return r;
 }
 
+static PyObject *
+PLyObject_FromTransform(PLyDatumToOb *arg, Datum d)
+{
+	return (PyObject *) DatumGetPointer(FunctionCall1(&arg->typtransform, d));
+}
+
 static PyObject *
 PLyList_FromArray(PLyDatumToOb *arg, Datum d)
 {
@@ -747,16 +781,15 @@ PLyObject_ToComposite(PLyObToDatum *arg, int32 typmod, PyObject *plrv)
 
 
 /*
- * Generic conversion function: Convert PyObject to cstring and
- * cstring into PostgreSQL type.
+ * Convert Python object to C string in server encoding.
  */
-static Datum
-PLyObject_ToDatum(PLyObToDatum *arg, int32 typmod, PyObject *plrv)
+char *
+PLyObject_AsString(PyObject *plrv)
 {
-	PyObject   *volatile plrv_bo = NULL;
-	Datum		rv;
-
-	Assert(plrv != Py_None);
+	PyObject   *plrv_bo;
+	char	   *plrv_sc;
+	size_t		plen;
+	size_t		slen;
 
 	if (PyUnicode_Check(plrv))
 		plrv_bo = PLyUnicode_Bytes(plrv);
@@ -786,36 +819,47 @@ PLyObject_ToDatum(PLyObToDatum *arg, int32 typmod, PyObject *plrv)
 	if (!plrv_bo)
 		PLy_elog(ERROR, "could not create string representation of Python object");
 
-	PG_TRY();
-	{
-		char	   *plrv_sc = PyBytes_AsString(plrv_bo);
-		size_t		plen = PyBytes_Size(plrv_bo);
-		size_t		slen = strlen(plrv_sc);
-
-		if (slen < plen)
-			ereport(ERROR,
-					(errcode(ERRCODE_DATATYPE_MISMATCH),
-					 errmsg("could not convert Python object into cstring: Python string representation appears to contain null bytes")));
-		else if (slen > plen)
-			elog(ERROR, "could not convert Python object into cstring: Python string longer than reported length");
-		pg_verifymbstr(plrv_sc, slen, false);
-		rv = InputFunctionCall(&arg->typfunc,
-							   plrv_sc,
-							   arg->typioparam,
-							   typmod);
-	}
-	PG_CATCH();
-	{
-		Py_XDECREF(plrv_bo);
-		PG_RE_THROW();
-	}
-	PG_END_TRY();
+	plrv_sc = pstrdup(PyBytes_AsString(plrv_bo));
+	plen = PyBytes_Size(plrv_bo);
+	slen = strlen(plrv_sc);
 
 	Py_XDECREF(plrv_bo);
 
-	return rv;
+	if (slen < plen)
+		ereport(ERROR,
+				(errcode(ERRCODE_DATATYPE_MISMATCH),
+				 errmsg("could not convert Python object into cstring: Python string representation appears to contain null bytes")));
+	else if (slen > plen)
+		elog(ERROR, "could not convert Python object into cstring: Python string longer than reported length");
+	pg_verifymbstr(plrv_sc, slen, false);
+
+	return plrv_sc;
 }
 
+
+/*
+ * Generic conversion function: Convert PyObject to cstring and
+ * cstring into PostgreSQL type.
+ */
+static Datum
+PLyObject_ToDatum(PLyObToDatum *arg, int32 typmod, PyObject *plrv)
+{
+	Assert(plrv != Py_None);
+
+	return InputFunctionCall(&arg->typfunc,
+							 PLyObject_AsString(plrv),
+							 arg->typioparam,
+							 typmod);
+}
+
+
+static Datum
+PLyObject_ToTransform(PLyObToDatum *arg, int32 typmod, PyObject *plrv)
+{
+	return FunctionCall1(&arg->typtransform, PointerGetDatum(plrv));
+}
+
+
 static Datum
 PLySequence_ToArray(PLyObToDatum *arg, int32 typmod, PyObject *plrv)
 {
@@ -869,12 +913,15 @@ static Datum
 PLyString_ToComposite(PLyTypeInfo *info, TupleDesc desc, PyObject *string)
 {
 	HeapTuple	typeTup;
+	PLyExecutionContext *exec_ctx = PLy_current_execution_context();
 
 	typeTup = SearchSysCache1(TYPEOID, ObjectIdGetDatum(desc->tdtypeid));
 	if (!HeapTupleIsValid(typeTup))
 		elog(ERROR, "cache lookup failed for type %u", desc->tdtypeid);
 
-	PLy_output_datum_func2(&info->out.d, typeTup);
+	PLy_output_datum_func2(&info->out.d, typeTup,
+						   exec_ctx->curr_proc->langid,
+						   exec_ctx->curr_proc->trftypes);
 
 	ReleaseSysCache(typeTup);
 

src/pl/plpython/plpy_typeio.h

@@ -17,6 +17,7 @@ typedef struct PLyDatumToOb
 {
 	PLyDatumToObFunc func;
 	FmgrInfo	typfunc;		/* The type's output function */
+	FmgrInfo	typtransform;	/* from-SQL transform */
 	Oid			typoid;			/* The OID of the type */
 	int32		typmod;			/* The typmod of the type */
 	Oid			typioparam;
@@ -48,6 +49,7 @@ typedef struct PLyObToDatum
 {
 	PLyObToDatumFunc func;
 	FmgrInfo	typfunc;		/* The type's input function */
+	FmgrInfo	typtransform;	/* to-SQL transform */
 	Oid			typoid;			/* The OID of the type */
 	int32		typmod;			/* The typmod of the type */
 	Oid			typioparam;
@@ -91,8 +93,8 @@ typedef struct PLyTypeInfo
 extern void PLy_typeinfo_init(PLyTypeInfo *arg);
 extern void PLy_typeinfo_dealloc(PLyTypeInfo *arg);
 
-extern void PLy_input_datum_func(PLyTypeInfo *arg, Oid typeOid, HeapTuple typeTup);
-extern void PLy_output_datum_func(PLyTypeInfo *arg, HeapTuple typeTup);
+extern void PLy_input_datum_func(PLyTypeInfo *arg, Oid typeOid, HeapTuple typeTup, Oid langid, List *trftypes);
+extern void PLy_output_datum_func(PLyTypeInfo *arg, HeapTuple typeTup, Oid langid, List *trftypes);
 
 extern void PLy_input_tuple_funcs(PLyTypeInfo *arg, TupleDesc desc);
 extern void PLy_output_tuple_funcs(PLyTypeInfo *arg, TupleDesc desc);
@@ -105,4 +107,7 @@ extern Datum PLyObject_ToCompositeDatum(PLyTypeInfo *info, TupleDesc desc, PyObj
 /* conversion from heap tuples to Python dictionaries */
 extern PyObject *PLyDict_FromTuple(PLyTypeInfo *info, HeapTuple tuple, TupleDesc desc);
 
+/* conversion from Python objects to C strings */
+extern char *PLyObject_AsString(PyObject *plrv);
+
 #endif   /* PLPY_TYPEIO_H */

src/pl/plpython/plpy_util.c

@@ -142,19 +142,30 @@ PLyUnicode_AsString(PyObject *unicode)
  * unicode object.  Reference ownership is passed to the caller.
  */
 PyObject *
-PLyUnicode_FromString(const char *s)
+PLyUnicode_FromStringAndSize(const char *s, Py_ssize_t size)
 {
 	char	   *utf8string;
 	PyObject   *o;
 
-	utf8string = pg_server_to_any(s, strlen(s), PG_UTF8);
+	utf8string = pg_server_to_any(s, size, PG_UTF8);
 
-	o = PyUnicode_FromString(utf8string);
-
-	if (utf8string != s)
+	if (utf8string == s)
+	{
+		o = PyUnicode_FromStringAndSize(s, size);
+	}
+	else
+	{
+		o = PyUnicode_FromString(utf8string);
 		pfree(utf8string);
+	}
 
 	return o;
 }
 
+PyObject *
+PLyUnicode_FromString(const char *s)
+{
+	return PLyUnicode_FromStringAndSize(s, strlen(s));
+}
+
 #endif   /* PY_MAJOR_VERSION >= 3 */

src/pl/plpython/plpy_util.h

@@ -16,6 +16,7 @@ extern char *PLyUnicode_AsString(PyObject *unicode);
 
 #if PY_MAJOR_VERSION >= 3
 extern PyObject *PLyUnicode_FromString(const char *s);
+extern PyObject *PLyUnicode_FromStringAndSize(const char *s, Py_ssize_t size);
 #endif
 
 #endif   /* PLPY_UTIL_H */

src/pl/plpython/plpython.h

@@ -91,6 +91,7 @@ typedef int Py_ssize_t;
 #define PyString_Check(x) 0
 #define PyString_AsString(x) PLyUnicode_AsString(x)
 #define PyString_FromString(x) PLyUnicode_FromString(x)
+#define PyString_FromStringAndSize(x, size) PLyUnicode_FromStringAndSize(x, size)
 #endif
 
 /*

src/pl/plpython/regress-python3-mangle.mk

@@ -0,0 +1,35 @@
+ifeq ($(python_majorversion),3)
+# Adjust regression tests for Python 3 compatibility
+#
+# Mention those regression test files that need to be mangled in the
+# variable REGRESS_PLPYTHON3_MANGLE.  They will be copied to a
+# subdirectory python3/ and have their Python syntax and other bits
+# adjusted to work with Python 3.
+
+# Note that the order of the tests needs to be preserved in this
+# expression.
+REGRESS := $(foreach test,$(REGRESS),$(if $(filter $(test),$(REGRESS_PLPYTHON3_MANGLE)),python3/$(test),$(test)))
+
+.PHONY: pgregress-python3-mangle
+pgregress-python3-mangle:
+	$(MKDIR_P) sql/python3 expected/python3 results/python3
+	for file in $(patsubst %,$(srcdir)/sql/%.sql,$(REGRESS_PLPYTHON3_MANGLE)) $(patsubst %,$(srcdir)/expected/%*.out,$(REGRESS_PLPYTHON3_MANGLE)); 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" \
+	      -e "s/EXTENSION \([^ ]*_\)*plpythonu/EXTENSION \1plpython3u/g" \
+	      -e "s/EXTENSION \([^ ]*_\)*plpython2u/EXTENSION \1plpython3u/g" \
+	    $$file >`echo $$file | sed 's,^.*/\([^/][^/]*/\)\([^/][^/]*\)$$,\1python3/\2,'` || exit; \
+	done
+
+check installcheck: pgregress-python3-mangle
+
+pg_regress_clean_files += sql/python3/ expected/python3/ results/python3/
+
+endif # Python 3