Perform conversion from Python unicode to string/bytes object via UTF-8.

We used to convert the unicode object directly to a string in the server
encoding by calling Python's PyUnicode_AsEncodedString function. In other
words, we used Python's routines to do the encoding. However, that has a
few problems. First of all, it required keeping a mapping table of Python
encoding names and PostgreSQL encodings. But the real killer was that Python
doesn't support EUC_TW and MULE_INTERNAL encodings at all.

Instead, convert the Python unicode object to UTF-8, and use PostgreSQL's
encoding conversion functions to convert from UTF-8 to server encoding. We
were already doing the same in the other direction in PLyUnicode_FromString,
so this is more consistent, too.

Note: This makes SQL_ASCII to behave more leniently. We used to map
SQL_ASCII to Python's 'ascii', which on Python means strict 7-bit ASCII
only, so you got an error if the python string contained anything but pure
ASCII. You no longer get an error; you get the UTF-8 representation of the
string instead.

Backpatch to 9.0, where these conversions were introduced.

Jan Urbański

src/pl/plpython/expected/plpython_unicode_3.out

@@ -1,54 +0,0 @@
---
--- Unicode handling
---
-SET client_encoding TO UTF8;
-CREATE TABLE unicode_test (
-	testvalue  text NOT NULL
-);
-CREATE FUNCTION unicode_return() RETURNS text AS E'
-return u"\\x80"
-' LANGUAGE plpythonu;
-CREATE FUNCTION unicode_trigger() RETURNS trigger AS E'
-TD["new"]["testvalue"] = u"\\x80"
-return "MODIFY"
-' LANGUAGE plpythonu;
-CREATE TRIGGER unicode_test_bi BEFORE INSERT ON unicode_test
-  FOR EACH ROW EXECUTE PROCEDURE unicode_trigger();
-CREATE FUNCTION unicode_plan1() RETURNS text AS E'
-plan = plpy.prepare("SELECT $1 AS testvalue", ["text"])
-rv = plpy.execute(plan, [u"\\x80"], 1)
-return rv[0]["testvalue"]
-' LANGUAGE plpythonu;
-CREATE FUNCTION unicode_plan2() RETURNS text AS E'
-plan = plpy.prepare("SELECT $1 || $2 AS testvalue", ["text", u"text"])
-rv = plpy.execute(plan, ["foo", "bar"], 1)
-return rv[0]["testvalue"]
-' LANGUAGE plpythonu;
-SELECT unicode_return();
-ERROR:  could not convert Python Unicode object to PostgreSQL server encoding
-DETAIL:  UnicodeEncodeError: 'ascii' codec can't encode character u'\x80' in position 0: ordinal not in range(128)
-CONTEXT:  while creating return value
-PL/Python function "unicode_return"
-INSERT INTO unicode_test (testvalue) VALUES ('test');
-ERROR:  could not convert Python Unicode object to PostgreSQL server encoding
-DETAIL:  UnicodeEncodeError: 'ascii' codec can't encode character u'\x80' in position 0: ordinal not in range(128)
-CONTEXT:  while modifying trigger row
-PL/Python function "unicode_trigger"
-SELECT * FROM unicode_test;
- testvalue 
------------
-(0 rows)
-
-SELECT unicode_plan1();
-ERROR:  spiexceptions.InternalError: could not convert Python Unicode object to PostgreSQL server encoding
-DETAIL:  UnicodeEncodeError: 'ascii' codec can't encode character u'\x80' in position 0: ordinal not in range(128)
-CONTEXT:  Traceback (most recent call last):
-  PL/Python function "unicode_plan1", line 3, in <module>
-    rv = plpy.execute(plan, [u"\x80"], 1)
-PL/Python function "unicode_plan1"
-SELECT unicode_plan2();
- unicode_plan2 
----------------
- foobar
-(1 row)
-

src/pl/plpython/plpy_util.c

@@ -61,66 +61,56 @@ PLy_free(void *ptr)
 PyObject *
 PLyUnicode_Bytes(PyObject *unicode)
 {
-	PyObject   *rv;
+	PyObject	*bytes, *rv;
-	const char *serverenc;
+	char		*utf8string, *encoded;
 
-	/*
+	/* First encode the Python unicode object with UTF-8. */
-	 * Map PostgreSQL encoding to a Python encoding name.
+	bytes = PyUnicode_AsUTF8String(unicode);
-	 */
+	if (bytes == NULL)
-	switch (GetDatabaseEncoding())
+		PLy_elog(ERROR, "could not convert Python Unicode object to bytes");
-	{
+
-		case PG_SQL_ASCII:
+	utf8string = PyBytes_AsString(bytes);
-			/*
+	if (utf8string == NULL) {
-			 * Mapping SQL_ASCII to Python's 'ascii' is a bit bogus. Python's
+		Py_DECREF(bytes);
-			 * 'ascii' means true 7-bit only ASCII, while PostgreSQL's
+		PLy_elog(ERROR, "could not extract bytes from encoded string");
-			 * SQL_ASCII means that anything is allowed, and the system doesn't
-			 * try to interpret the bytes in any way. But not sure what else
-			 * to do, and we haven't heard any complaints...
-			 */
-			serverenc = "ascii";
-			break;
-		case PG_WIN1250:
-			serverenc = "cp1250";
-			break;
-		case PG_WIN1251:
-			serverenc = "cp1251";
-			break;
-		case PG_WIN1252:
-			serverenc = "cp1252";
-			break;
-		case PG_WIN1253:
-			serverenc = "cp1253";
-			break;
-		case PG_WIN1254:
-			serverenc = "cp1254";
-			break;
-		case PG_WIN1255:
-			serverenc = "cp1255";
-			break;
-		case PG_WIN1256:
-			serverenc = "cp1256";
-			break;
-		case PG_WIN1257:
-			serverenc = "cp1257";
-			break;
-		case PG_WIN1258:
-			serverenc = "cp1258";
-			break;
-		case PG_WIN866:
-			serverenc = "cp866";
-			break;
-		case PG_WIN874:
-			serverenc = "cp874";
-			break;
-		default:
-			/* Other encodings have the same name in Python. */
-			serverenc = GetDatabaseEncodingName();
-			break;
 	}
 
-	rv = PyUnicode_AsEncodedString(unicode, serverenc, "strict");
+	/*
-	if (rv == NULL)
+	 * Then convert to server encoding if necessary.
-		PLy_elog(ERROR, "could not convert Python Unicode object to PostgreSQL server encoding");
+	 *
+	 * PyUnicode_AsEncodedString could be used to encode the object directly
+	 * in the server encoding, but Python doesn't support all the encodings
+	 * that PostgreSQL does (EUC_TW and MULE_INTERNAL). UTF-8 is used as an
+	 * intermediary in PLyUnicode_FromString as well.
+	 */
+	if (GetDatabaseEncoding() != PG_UTF8)
+	{
+		PG_TRY();
+		{
+			encoded = (char *) pg_do_encoding_conversion(
+				(unsigned char *) utf8string,
+				strlen(utf8string),
+				PG_UTF8,
+				GetDatabaseEncoding());
+		}
+		PG_CATCH();
+		{
+			Py_DECREF(bytes);
+			PG_RE_THROW();
+		}
+		PG_END_TRY();
+	}
+	else
+		encoded = utf8string;
+
+	/* finally, build a bytes object in the server encoding */
+	rv = PyBytes_FromStringAndSize(encoded, strlen(encoded));
+
+	/* if pg_do_encoding_conversion allocated memory, free it now */
+	if (utf8string != encoded)
+		pfree(encoded);
+
+	Py_DECREF(bytes);
 	return rv;
 }