Enable routine running of citext's UTF8-specific test cases.

These test cases have been commented out since citext was invented,
because at the time we had no nice way to deal with tests that
have restrictions such as requiring UTF8 encoding.  But now we do
have a convention for that, ie put them into a separate test file
with an early-exit path.  So let's enable these tests to run when
their prerequisites are satisfied.

(We may have to tighten the prerequisites beyond the "encoding = UTF8
and locale != C" checks made here.  But let's put it on the buildfarm
and see what blows up.)

Dag Lem

Discussion: https://postgr.es/m/ygezgoacs4e.fsf_-_@sid.nimrod.no

diff --git a/contrib/citext/Makefile b/contrib/citext/Makefile
index a7de52928d71ba6fe91b454a819bcc528137a776..789932fe36690f902095e0f10fc64437ef351346 100644 (file)
--- a/contrib/citext/Makefile
+++ b/contrib/citext/Makefile
@@ -11,7 +11,7 @@ DATA = citext--1.4.sql \
        citext--1.0--1.1.sql
 PGFILEDESC = "citext - case-insensitive character string data type"
 
-REGRESS = citext
+REGRESS = citext citext_utf8
 
 ifdef USE_PGXS
 PG_CONFIG = pg_config

diff --git a/contrib/citext/expected/citext.out b/contrib/citext/expected/citext.out
index 3bac0534fb86b6211b3f5bd4d5a1d482365cfbe6..5afcc50920e40492bca312b20b961c960466cb0e 100644 (file)
--- a/contrib/citext/expected/citext.out
+++ b/contrib/citext/expected/citext.out
@@ -48,29 +48,6 @@ SELECT 'a'::citext <> 'ab'::citext AS t;
  t
 (1 row)
 
--- Multibyte sanity tests. Uncomment to run.
--- SELECT 'À'::citext =  'À'::citext AS t;
--- SELECT 'À'::citext =  'à'::citext AS t;
--- SELECT 'À'::text   =  'à'::text   AS f; -- text wins.
--- SELECT 'À'::citext <> 'B'::citext AS t;
--- Test combining characters making up canonically equivalent strings.
--- SELECT 'Ä'::text   <> 'Ä'::text   AS t;
--- SELECT 'Ä'::citext <> 'Ä'::citext AS t;
--- Test the Turkish dotted I. The lowercase is a single byte while the
--- uppercase is multibyte. This is why the comparison code can't be optimized
--- to compare string lengths.
--- SELECT 'i'::citext = 'İ'::citext AS t;
--- Regression.
--- SELECT 'láska'::citext <> 'laská'::citext AS t;
--- SELECT 'Ask Bjørn Hansen'::citext = 'Ask Bjørn Hansen'::citext AS t;
--- SELECT 'Ask Bjørn Hansen'::citext = 'ASK BJØRN HANSEN'::citext AS t;
--- SELECT 'Ask Bjørn Hansen'::citext <> 'Ask Bjorn Hansen'::citext AS t;
--- SELECT 'Ask Bjørn Hansen'::citext <> 'ASK BJORN HANSEN'::citext AS t;
--- SELECT citext_cmp('Ask Bjørn Hansen'::citext, 'Ask Bjørn Hansen'::citext) AS zero;
--- SELECT citext_cmp('Ask Bjørn Hansen'::citext, 'ask bjørn hansen'::citext) AS zero;
--- SELECT citext_cmp('Ask Bjørn Hansen'::citext, 'ASK BJØRN HANSEN'::citext) AS zero;
--- SELECT citext_cmp('Ask Bjørn Hansen'::citext, 'Ask Bjorn Hansen'::citext) AS positive;
--- SELECT citext_cmp('Ask Bjorn Hansen'::citext, 'Ask Bjørn Hansen'::citext) AS negative;
 -- Test > and >=
 SELECT 'B'::citext > 'a'::citext AS t;
  t 
@@ -2614,8 +2591,6 @@ SELECT citext_pattern_ge('b'::citext, 'A'::citext) AS true;
  t
 (1 row)
 
--- Multi-byte tests below are disabled like the sanity tests above.
--- Uncomment to run them.
 -- Test ~<~ and ~<=~
 SELECT 'a'::citext ~<~  'B'::citext AS t;
  t 
@@ -2629,7 +2604,6 @@ SELECT 'b'::citext ~<~  'A'::citext AS f;
  f
 (1 row)
 
--- SELECT 'à'::citext ~<~  'À'::citext AS f;
 SELECT 'a'::citext ~<=~ 'B'::citext AS t;
  t 
 ---
@@ -2642,7 +2616,6 @@ SELECT 'a'::citext ~<=~ 'A'::citext AS t;
  t
 (1 row)
 
--- SELECT 'à'::citext ~<=~ 'À'::citext AS t;
 -- Test ~>~ and ~>=~
 SELECT 'B'::citext ~>~  'a'::citext AS t;
  t 
@@ -2656,7 +2629,6 @@ SELECT 'b'::citext ~>~  'A'::citext AS t;
  t
 (1 row)
 
--- SELECT 'à'::citext ~>~  'À'::citext AS f;
 SELECT 'B'::citext ~>~  'b'::citext AS f;
  f 
 ---
@@ -2669,7 +2641,6 @@ SELECT 'B'::citext ~>=~ 'b'::citext AS t;
  t
 (1 row)
 
--- SELECT 'à'::citext ~>=~ 'À'::citext AS t;
 -- Test implicit casting. citext casts to text, but not vice-versa.
 SELECT 'B'::citext ~<~  'a'::text AS t;  -- text wins.
  t 

diff --git a/contrib/citext/expected/citext_1.out b/contrib/citext/expected/citext_1.out
index 57fc863f7a57821609c816e70e2673095f42771c..8aa2b9e1dbcceb64821bd3ec2672bfdd984f1e56 100644 (file)
--- a/contrib/citext/expected/citext_1.out
+++ b/contrib/citext/expected/citext_1.out
@@ -48,29 +48,6 @@ SELECT 'a'::citext <> 'ab'::citext AS t;
  t
 (1 row)
 
--- Multibyte sanity tests. Uncomment to run.
--- SELECT 'À'::citext =  'À'::citext AS t;
--- SELECT 'À'::citext =  'à'::citext AS t;
--- SELECT 'À'::text   =  'à'::text   AS f; -- text wins.
--- SELECT 'À'::citext <> 'B'::citext AS t;
--- Test combining characters making up canonically equivalent strings.
--- SELECT 'Ä'::text   <> 'Ä'::text   AS t;
--- SELECT 'Ä'::citext <> 'Ä'::citext AS t;
--- Test the Turkish dotted I. The lowercase is a single byte while the
--- uppercase is multibyte. This is why the comparison code can't be optimized
--- to compare string lengths.
--- SELECT 'i'::citext = 'İ'::citext AS t;
--- Regression.
--- SELECT 'láska'::citext <> 'laská'::citext AS t;
--- SELECT 'Ask Bjørn Hansen'::citext = 'Ask Bjørn Hansen'::citext AS t;
--- SELECT 'Ask Bjørn Hansen'::citext = 'ASK BJØRN HANSEN'::citext AS t;
--- SELECT 'Ask Bjørn Hansen'::citext <> 'Ask Bjorn Hansen'::citext AS t;
--- SELECT 'Ask Bjørn Hansen'::citext <> 'ASK BJORN HANSEN'::citext AS t;
--- SELECT citext_cmp('Ask Bjørn Hansen'::citext, 'Ask Bjørn Hansen'::citext) AS zero;
--- SELECT citext_cmp('Ask Bjørn Hansen'::citext, 'ask bjørn hansen'::citext) AS zero;
--- SELECT citext_cmp('Ask Bjørn Hansen'::citext, 'ASK BJØRN HANSEN'::citext) AS zero;
--- SELECT citext_cmp('Ask Bjørn Hansen'::citext, 'Ask Bjorn Hansen'::citext) AS positive;
--- SELECT citext_cmp('Ask Bjorn Hansen'::citext, 'Ask Bjørn Hansen'::citext) AS negative;
 -- Test > and >=
 SELECT 'B'::citext > 'a'::citext AS t;
  t 
@@ -2614,8 +2591,6 @@ SELECT citext_pattern_ge('b'::citext, 'A'::citext) AS true;
  t
 (1 row)
 
--- Multi-byte tests below are disabled like the sanity tests above.
--- Uncomment to run them.
 -- Test ~<~ and ~<=~
 SELECT 'a'::citext ~<~  'B'::citext AS t;
  t 
@@ -2629,7 +2604,6 @@ SELECT 'b'::citext ~<~  'A'::citext AS f;
  f
 (1 row)
 
--- SELECT 'à'::citext ~<~  'À'::citext AS f;
 SELECT 'a'::citext ~<=~ 'B'::citext AS t;
  t 
 ---
@@ -2642,7 +2616,6 @@ SELECT 'a'::citext ~<=~ 'A'::citext AS t;
  t
 (1 row)
 
--- SELECT 'à'::citext ~<=~ 'À'::citext AS t;
 -- Test ~>~ and ~>=~
 SELECT 'B'::citext ~>~  'a'::citext AS t;
  t 
@@ -2656,7 +2629,6 @@ SELECT 'b'::citext ~>~  'A'::citext AS t;
  t
 (1 row)
 
--- SELECT 'à'::citext ~>~  'À'::citext AS f;
 SELECT 'B'::citext ~>~  'b'::citext AS f;
  f 
 ---
@@ -2669,7 +2641,6 @@ SELECT 'B'::citext ~>=~ 'b'::citext AS t;
  t
 (1 row)
 
--- SELECT 'à'::citext ~>=~ 'À'::citext AS t;
 -- Test implicit casting. citext casts to text, but not vice-versa.
 SELECT 'B'::citext ~<~  'a'::text AS t;  -- text wins.
  t 

diff --git a/contrib/citext/expected/citext_utf8.out b/contrib/citext/expected/citext_utf8.out
new file mode 100644 (file)
index 0000000..666b07c
--- /dev/null
+++ b/contrib/citext/expected/citext_utf8.out
@@ -0,0 +1,146 @@
+/*
+ * This test must be run in a database with UTF-8 encoding
+ * and a Unicode-aware locale.
+ */
+SELECT getdatabaseencoding() <> 'UTF8' OR
+       current_setting('lc_ctype') = 'C'
+       AS skip_test \gset
+\if :skip_test
+\quit
+\endif
+set client_encoding = utf8;
+-- CREATE EXTENSION IF NOT EXISTS citext;
+-- Multibyte sanity tests.
+SELECT 'À'::citext =  'À'::citext AS t;
+ t 
+---
+ t
+(1 row)
+
+SELECT 'À'::citext =  'à'::citext AS t;
+ t 
+---
+ t
+(1 row)
+
+SELECT 'À'::text   =  'à'::text   AS f; -- text wins.
+ f 
+---
+ f
+(1 row)
+
+SELECT 'À'::citext <> 'B'::citext AS t;
+ t 
+---
+ t
+(1 row)
+
+-- Test combining characters making up canonically equivalent strings.
+SELECT 'Ä'::text   <> 'Ä'::text   AS t;
+ t 
+---
+ t
+(1 row)
+
+SELECT 'Ä'::citext <> 'Ä'::citext AS t;
+ t 
+---
+ t
+(1 row)
+
+-- Test the Turkish dotted I. The lowercase is a single byte while the
+-- uppercase is multibyte. This is why the comparison code can't be optimized
+-- to compare string lengths.
+SELECT 'i'::citext = 'İ'::citext AS t;
+ t 
+---
+ t
+(1 row)
+
+-- Regression.
+SELECT 'láska'::citext <> 'laská'::citext AS t;
+ t 
+---
+ t
+(1 row)
+
+SELECT 'Ask Bjørn Hansen'::citext = 'Ask Bjørn Hansen'::citext AS t;
+ t 
+---
+ t
+(1 row)
+
+SELECT 'Ask Bjørn Hansen'::citext = 'ASK BJØRN HANSEN'::citext AS t;
+ t 
+---
+ t
+(1 row)
+
+SELECT 'Ask Bjørn Hansen'::citext <> 'Ask Bjorn Hansen'::citext AS t;
+ t 
+---
+ t
+(1 row)
+
+SELECT 'Ask Bjørn Hansen'::citext <> 'ASK BJORN HANSEN'::citext AS t;
+ t 
+---
+ t
+(1 row)
+
+SELECT citext_cmp('Ask Bjørn Hansen'::citext, 'Ask Bjørn Hansen'::citext) = 0 AS t;
+ t 
+---
+ t
+(1 row)
+
+SELECT citext_cmp('Ask Bjørn Hansen'::citext, 'ask bjørn hansen'::citext) = 0 AS t;
+ t 
+---
+ t
+(1 row)
+
+SELECT citext_cmp('Ask Bjørn Hansen'::citext, 'ASK BJØRN HANSEN'::citext) = 0 AS t;
+ t 
+---
+ t
+(1 row)
+
+SELECT citext_cmp('Ask Bjørn Hansen'::citext, 'Ask Bjorn Hansen'::citext) > 0 AS t;
+ t 
+---
+ t
+(1 row)
+
+SELECT citext_cmp('Ask Bjorn Hansen'::citext, 'Ask Bjørn Hansen'::citext) < 0 AS t;
+ t 
+---
+ t
+(1 row)
+
+-- Test ~<~ and ~<=~
+SELECT 'à'::citext ~<~  'À'::citext AS f;
+ f 
+---
+ f
+(1 row)
+
+SELECT 'à'::citext ~<=~ 'À'::citext AS t;
+ t 
+---
+ t
+(1 row)
+
+-- Test ~>~ and ~>=~
+SELECT 'à'::citext ~>~  'À'::citext AS f;
+ f 
+---
+ f
+(1 row)
+
+SELECT 'à'::citext ~>=~ 'À'::citext AS t;
+ t 
+---
+ t
+(1 row)
+

diff --git a/contrib/citext/expected/citext_utf8_1.out b/contrib/citext/expected/citext_utf8_1.out
new file mode 100644 (file)
index 0000000..433e985
--- /dev/null
+++ b/contrib/citext/expected/citext_utf8_1.out
@@ -0,0 +1,9 @@
+/*
+ * This test must be run in a database with UTF-8 encoding
+ * and a Unicode-aware locale.
+ */
+SELECT getdatabaseencoding() <> 'UTF8' OR
+       current_setting('lc_ctype') = 'C'
+       AS skip_test \gset
+\if :skip_test
+\quit

diff --git a/contrib/citext/sql/citext.sql b/contrib/citext/sql/citext.sql
index 55fb1d11a6f6a0c4a88db544ec7dd4b385121e16..8c87be6b1d23f52dc7abed8f48e02db3f223cad9 100644 (file)
--- a/contrib/citext/sql/citext.sql
+++ b/contrib/citext/sql/citext.sql
@@ -19,34 +19,6 @@ SELECT 'a'::citext = 'b'::citext AS f;
 SELECT 'a'::citext = 'ab'::citext AS f;
 SELECT 'a'::citext <> 'ab'::citext AS t;
 
--- Multibyte sanity tests. Uncomment to run.
--- SELECT 'À'::citext =  'À'::citext AS t;
--- SELECT 'À'::citext =  'à'::citext AS t;
--- SELECT 'À'::text   =  'à'::text   AS f; -- text wins.
--- SELECT 'À'::citext <> 'B'::citext AS t;
-
--- Test combining characters making up canonically equivalent strings.
--- SELECT 'Ä'::text   <> 'Ä'::text   AS t;
--- SELECT 'Ä'::citext <> 'Ä'::citext AS t;
-
--- Test the Turkish dotted I. The lowercase is a single byte while the
--- uppercase is multibyte. This is why the comparison code can't be optimized
--- to compare string lengths.
--- SELECT 'i'::citext = 'İ'::citext AS t;
-
--- Regression.
--- SELECT 'láska'::citext <> 'laská'::citext AS t;
-
--- SELECT 'Ask Bjørn Hansen'::citext = 'Ask Bjørn Hansen'::citext AS t;
--- SELECT 'Ask Bjørn Hansen'::citext = 'ASK BJØRN HANSEN'::citext AS t;
--- SELECT 'Ask Bjørn Hansen'::citext <> 'Ask Bjorn Hansen'::citext AS t;
--- SELECT 'Ask Bjørn Hansen'::citext <> 'ASK BJORN HANSEN'::citext AS t;
--- SELECT citext_cmp('Ask Bjørn Hansen'::citext, 'Ask Bjørn Hansen'::citext) AS zero;
--- SELECT citext_cmp('Ask Bjørn Hansen'::citext, 'ask bjørn hansen'::citext) AS zero;
--- SELECT citext_cmp('Ask Bjørn Hansen'::citext, 'ASK BJØRN HANSEN'::citext) AS zero;
--- SELECT citext_cmp('Ask Bjørn Hansen'::citext, 'Ask Bjorn Hansen'::citext) AS positive;
--- SELECT citext_cmp('Ask Bjorn Hansen'::citext, 'Ask Bjørn Hansen'::citext) AS negative;
-
 -- Test > and >=
 SELECT 'B'::citext > 'a'::citext AS t;
 SELECT 'b'::citext >  'A'::citext AS t;
@@ -811,24 +783,17 @@ SELECT citext_pattern_ge('b'::citext, 'a'::citext) AS true;
 SELECT citext_pattern_ge('B'::citext, 'a'::citext) AS true;
 SELECT citext_pattern_ge('b'::citext, 'A'::citext) AS true;
 
--- Multi-byte tests below are disabled like the sanity tests above.
--- Uncomment to run them.
-
 -- Test ~<~ and ~<=~
 SELECT 'a'::citext ~<~  'B'::citext AS t;
 SELECT 'b'::citext ~<~  'A'::citext AS f;
--- SELECT 'à'::citext ~<~  'À'::citext AS f;
 SELECT 'a'::citext ~<=~ 'B'::citext AS t;
 SELECT 'a'::citext ~<=~ 'A'::citext AS t;
--- SELECT 'à'::citext ~<=~ 'À'::citext AS t;
 
 -- Test ~>~ and ~>=~
 SELECT 'B'::citext ~>~  'a'::citext AS t;
 SELECT 'b'::citext ~>~  'A'::citext AS t;
--- SELECT 'à'::citext ~>~  'À'::citext AS f;
 SELECT 'B'::citext ~>~  'b'::citext AS f;
 SELECT 'B'::citext ~>=~ 'b'::citext AS t;
--- SELECT 'à'::citext ~>=~ 'À'::citext AS t;
 
 -- Test implicit casting. citext casts to text, but not vice-versa.
 SELECT 'B'::citext ~<~  'a'::text AS t;  -- text wins.

diff --git a/contrib/citext/sql/citext_utf8.sql b/contrib/citext/sql/citext_utf8.sql
new file mode 100644 (file)
index 0000000..d068000
--- /dev/null
+++ b/contrib/citext/sql/citext_utf8.sql
@@ -0,0 +1,51 @@
+/*
+ * This test must be run in a database with UTF-8 encoding
+ * and a Unicode-aware locale.
+ */
+
+SELECT getdatabaseencoding() <> 'UTF8' OR
+       current_setting('lc_ctype') = 'C'
+       AS skip_test \gset
+\if :skip_test
+\quit
+\endif
+
+set client_encoding = utf8;
+
+-- CREATE EXTENSION IF NOT EXISTS citext;
+
+-- Multibyte sanity tests.
+SELECT 'À'::citext =  'À'::citext AS t;
+SELECT 'À'::citext =  'à'::citext AS t;
+SELECT 'À'::text   =  'à'::text   AS f; -- text wins.
+SELECT 'À'::citext <> 'B'::citext AS t;
+
+-- Test combining characters making up canonically equivalent strings.
+SELECT 'Ä'::text   <> 'Ä'::text   AS t;
+SELECT 'Ä'::citext <> 'Ä'::citext AS t;
+
+-- Test the Turkish dotted I. The lowercase is a single byte while the
+-- uppercase is multibyte. This is why the comparison code can't be optimized
+-- to compare string lengths.
+SELECT 'i'::citext = 'İ'::citext AS t;
+
+-- Regression.
+SELECT 'láska'::citext <> 'laská'::citext AS t;
+
+SELECT 'Ask Bjørn Hansen'::citext = 'Ask Bjørn Hansen'::citext AS t;
+SELECT 'Ask Bjørn Hansen'::citext = 'ASK BJØRN HANSEN'::citext AS t;
+SELECT 'Ask Bjørn Hansen'::citext <> 'Ask Bjorn Hansen'::citext AS t;
+SELECT 'Ask Bjørn Hansen'::citext <> 'ASK BJORN HANSEN'::citext AS t;
+SELECT citext_cmp('Ask Bjørn Hansen'::citext, 'Ask Bjørn Hansen'::citext) = 0 AS t;
+SELECT citext_cmp('Ask Bjørn Hansen'::citext, 'ask bjørn hansen'::citext) = 0 AS t;
+SELECT citext_cmp('Ask Bjørn Hansen'::citext, 'ASK BJØRN HANSEN'::citext) = 0 AS t;
+SELECT citext_cmp('Ask Bjørn Hansen'::citext, 'Ask Bjorn Hansen'::citext) > 0 AS t;
+SELECT citext_cmp('Ask Bjorn Hansen'::citext, 'Ask Bjørn Hansen'::citext) < 0 AS t;
+
+-- Test ~<~ and ~<=~
+SELECT 'à'::citext ~<~  'À'::citext AS f;
+SELECT 'à'::citext ~<=~ 'À'::citext AS t;
+
+-- Test ~>~ and ~>=~
+SELECT 'à'::citext ~>~  'À'::citext AS f;
+SELECT 'à'::citext ~>=~ 'À'::citext AS t;