Fix Unicode support in PL/Python

Check calls of PyUnicode_AsEncodedString() for NULL return, probably
because the encoding name is not known.  Add special treatment for
SQL_ASCII, which Python definitely does not know.

Since using SQL_ASCII produces errors in the regression tests when
non-ASCII characters are involved, we have to put back various regression
test result variants.
This commit is contained in:
Peter Eisentraut 2009-09-13 22:07:06 +00:00
parent 6689ce3e6a
commit eb62398f39
5 changed files with 175 additions and 4 deletions

View File

@ -2,3 +2,8 @@ Guide to alternative expected files:
plpython_error_2.out Python 2.2, 2.3, 2.4
plpython_error.out Python 2.5, 2.6
plpython_unicode.out any version, when server encoding != SQL_ASCII; else ...
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

View File

@ -0,0 +1,52 @@
--
-- Unicode handling
--
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: PL/Python: could not convert Python Unicode object to PostgreSQL server encoding
DETAIL: exceptions.UnicodeError: ASCII encoding error: ordinal not in range(128)
CONTEXT: while creating return value
PL/Python function "unicode_return"
INSERT INTO unicode_test (testvalue) VALUES ('test');
ERROR: PL/Python: could not convert Python Unicode object to PostgreSQL server encoding
DETAIL: exceptions.UnicodeError: ASCII encoding error: 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();
WARNING: PL/Python: plpy.Error: unrecognized error in PLy_spi_execute_plan
CONTEXT: PL/Python function "unicode_plan1"
ERROR: PL/Python: could not convert Python Unicode object to PostgreSQL server encoding
DETAIL: exceptions.UnicodeError: ASCII encoding error: ordinal not in range(128)
CONTEXT: PL/Python function "unicode_plan1"
SELECT unicode_plan2();
unicode_plan2
---------------
foobar
(1 row)

View File

@ -0,0 +1,52 @@
--
-- Unicode handling
--
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: PL/Python: could not convert Python Unicode object to PostgreSQL server encoding
DETAIL: exceptions.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: PL/Python: could not convert Python Unicode object to PostgreSQL server encoding
DETAIL: exceptions.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();
WARNING: PL/Python: plpy.Error: unrecognized error in PLy_spi_execute_plan
CONTEXT: PL/Python function "unicode_plan1"
ERROR: PL/Python: could not convert Python Unicode object to PostgreSQL server encoding
DETAIL: exceptions.UnicodeEncodeError: 'ascii' codec can't encode character u'\x80' in position 0: ordinal not in range(128)
CONTEXT: PL/Python function "unicode_plan1"
SELECT unicode_plan2();
unicode_plan2
---------------
foobar
(1 row)

View File

@ -0,0 +1,52 @@
--
-- Unicode handling
--
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: PL/Python: could not convert Python Unicode object to PostgreSQL server encoding
DETAIL: <type 'exceptions.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: PL/Python: could not convert Python Unicode object to PostgreSQL server encoding
DETAIL: <type 'exceptions.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();
WARNING: PL/Python: <class 'plpy.Error'>: unrecognized error in PLy_spi_execute_plan
CONTEXT: PL/Python function "unicode_plan1"
ERROR: PL/Python: could not convert Python Unicode object to PostgreSQL server encoding
DETAIL: <type 'exceptions.UnicodeEncodeError'>: 'ascii' codec can't encode character u'\x80' in position 0: ordinal not in range(128)
CONTEXT: PL/Python function "unicode_plan1"
SELECT unicode_plan2();
unicode_plan2
---------------
foobar
(1 row)

View File

@ -1,7 +1,7 @@
/**********************************************************************
* plpython.c - python as a procedural language for PostgreSQL
*
* $PostgreSQL: pgsql/src/pl/plpython/plpython.c,v 1.129 2009/09/12 22:13:12 petere Exp $
* $PostgreSQL: pgsql/src/pl/plpython/plpython.c,v 1.130 2009/09/13 22:07:06 petere Exp $
*
*********************************************************************
*/
@ -3343,11 +3343,21 @@ PLy_free(void *ptr)
static PyObject*
PLyUnicode_Str(PyObject *unicode)
{
PyObject *rv;
const char *serverenc;
/*
* This assumes that the PostgreSQL encoding names are acceptable
* to Python, but that appears to be the case.
* Python understands almost all PostgreSQL encoding names, but it
* doesn't know SQL_ASCII.
*/
return PyUnicode_AsEncodedString(unicode, GetDatabaseEncodingName(), "strict");
if (GetDatabaseEncoding() == PG_SQL_ASCII)
serverenc = "ascii";
else
serverenc = GetDatabaseEncodingName();
rv = PyUnicode_AsEncodedString(unicode, serverenc, "strict");
if (rv == NULL)
PLy_elog(ERROR, "could not convert Python Unicode object to PostgreSQL server encoding");
return rv;
}
/*