Make plpython_unicode regression test work in more database encodings.

tglsfdc · tglsfdc · commit d661582cb568 · 2014-06-03T12:02:22.000-04:00
This test previously used a data value containing U+0080, and would
therefore fail if the database encoding didn't have an equivalent to
that; which only about half of our supported server encodings do.
We could fall back to using some plain-ASCII character, but that seems
like it's losing most of the point of the test.  Instead switch to using
U+00A0 (no-break space), which translates into all our supported encodings
except the four in the EUC_xx family.

Per buildfarm testing.  Back-patch to 9.1, which is as far back as this
test is expected to succeed everywhere.  (9.0 has the test, but without
back-patching some 9.1 code changes we could not expect to get consistent
results across platforms anyway.)
diff --git a/src/pl/plpython/expected/plpython_unicode.out b/src/pl/plpython/expected/plpython_unicode.out
@@ -1,22 +1,27 @@
 --
 -- Unicode handling
 --
+-- Note: this test case is known to fail if the database encoding is
+-- EUC_CN, EUC_JP, EUC_KR, or EUC_TW, for lack of any equivalent to
+-- U+00A0 (no-break space) in those encodings.  However, testing with
+-- plain ASCII data would be rather useless, so we must live with that.
+--
 SET client_encoding TO UTF8;
 CREATE TABLE unicode_test (
 	testvalue  text NOT NULL
 );
 CREATE FUNCTION unicode_return() RETURNS text AS E'
-return u"\\x80"
+return u"\\xA0"
 ' LANGUAGE plpythonu;
 CREATE FUNCTION unicode_trigger() RETURNS trigger AS E'
-TD["new"]["testvalue"] = u"\\x80"
+TD["new"]["testvalue"] = u"\\xA0"
 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)
+rv = plpy.execute(plan, [u"\\xA0"], 1)
 return rv[0]["testvalue"]
 ' LANGUAGE plpythonu;
 CREATE FUNCTION unicode_plan2() RETURNS text AS E'
@@ -27,20 +32,20 @@ return rv[0]["testvalue"]
 SELECT unicode_return();
  unicode_return 
 ----------------
- \u0080
+  
 (1 row)
 
 INSERT INTO unicode_test (testvalue) VALUES ('test');
 SELECT * FROM unicode_test;
  testvalue 
 -----------
- \u0080
+  
 (1 row)
 
 SELECT unicode_plan1();
  unicode_plan1 
 ---------------
- \u0080
+  
 (1 row)
 
 SELECT unicode_plan2();
diff --git a/src/pl/plpython/sql/plpython_unicode.sql b/src/pl/plpython/sql/plpython_unicode.sql
@@ -1,6 +1,11 @@
 --
 -- Unicode handling
 --
+-- Note: this test case is known to fail if the database encoding is
+-- EUC_CN, EUC_JP, EUC_KR, or EUC_TW, for lack of any equivalent to
+-- U+00A0 (no-break space) in those encodings.  However, testing with
+-- plain ASCII data would be rather useless, so we must live with that.
+--
 
 SET client_encoding TO UTF8;
 
@@ -9,11 +14,11 @@ CREATE TABLE unicode_test (
 );
 
 CREATE FUNCTION unicode_return() RETURNS text AS E'
-return u"\\x80"
+return u"\\xA0"
 ' LANGUAGE plpythonu;
 
 CREATE FUNCTION unicode_trigger() RETURNS trigger AS E'
-TD["new"]["testvalue"] = u"\\x80"
+TD["new"]["testvalue"] = u"\\xA0"
 return "MODIFY"
 ' LANGUAGE plpythonu;
 
@@ -22,7 +27,7 @@ CREATE TRIGGER unicode_test_bi BEFORE INSERT ON unicode_test
 
 CREATE FUNCTION unicode_plan1() RETURNS text AS E'
 plan = plpy.prepare("SELECT $1 AS testvalue", ["text"])
-rv = plpy.execute(plan, [u"\\x80"], 1)
+rv = plpy.execute(plan, [u"\\xA0"], 1)
 return rv[0]["testvalue"]
 ' LANGUAGE plpythonu;
 
