Home | History | Annotate | Download | only in test 
      1 # 2007 May 1
      2 #
      3 # The author disclaims copyright to this source code.  In place of
      4 # a legal notice, here is a blessing:
      5 #
      6 #    May you do good and not evil.
      7 #    May you find forgiveness for yourself and forgive others.
      8 #    May you share freely, never taking more than you give.
      9 #
     10 #***********************************************************************
     11 #
     12 # $Id: icu.test,v 1.2 2008/07/12 14:52:20 drh Exp $
     13 #
     14 
     15 set testdir [file dirname $argv0]
     16 source $testdir/tester.tcl
     17 
     18 ifcapable !icu {
     19   finish_test
     20   return
     21 }
     22 
     23 # Create a table to work with.
     24 #
     25 execsql {CREATE TABLE test1(i1 int, i2 int, r1 real, r2 real, t1 text, t2 text)}
     26 execsql {INSERT INTO test1 VALUES(1,2,1.1,2.2,'hello','world')}
     27 proc test_expr {name settings expr result} {
     28   do_test $name [format {
     29     lindex [db eval {
     30       BEGIN; 
     31       UPDATE test1 SET %s; 
     32       SELECT %s FROM test1; 
     33       ROLLBACK;
     34     }] 0
     35   } $settings $expr] $result
     36 }
     37 
     38 # Tests of the REGEXP operator.
     39 #
     40 test_expr icu-1.1 {i1='hello'} {i1 REGEXP 'hello'}  1
     41 test_expr icu-1.2 {i1='hello'} {i1 REGEXP '.ello'}  1
     42 test_expr icu-1.3 {i1='hello'} {i1 REGEXP '.ell'}   0
     43 test_expr icu-1.4 {i1='hello'} {i1 REGEXP '.ell.*'} 1
     44 test_expr icu-1.5 {i1=NULL}    {i1 REGEXP '.ell.*'} {}
     45 
     46 # Some non-ascii characters with defined case mappings
     47 #
     48 set ::EGRAVE "\xC8"
     49 set ::egrave "\xE8"
     50 
     51 set ::OGRAVE "\xD2"
     52 set ::ograve "\xF2"
     53 
     54 # That German letter that looks a bit like a B. The
     55 # upper-case version of which is "SS" (two characters).
     56 #
     57 set ::szlig "\xDF" 
     58 
     59 # Tests of the upper()/lower() functions.
     60 #
     61 test_expr icu-2.1 {i1='HellO WorlD'} {upper(i1)} {HELLO WORLD}
     62 test_expr icu-2.2 {i1='HellO WorlD'} {lower(i1)} {hello world}
     63 test_expr icu-2.3 {i1=$::egrave} {lower(i1)}     $::egrave
     64 test_expr icu-2.4 {i1=$::egrave} {upper(i1)}     $::EGRAVE
     65 test_expr icu-2.5 {i1=$::ograve} {lower(i1)}     $::ograve
     66 test_expr icu-2.6 {i1=$::ograve} {upper(i1)}     $::OGRAVE
     67 test_expr icu-2.3 {i1=$::EGRAVE} {lower(i1)}     $::egrave
     68 test_expr icu-2.4 {i1=$::EGRAVE} {upper(i1)}     $::EGRAVE
     69 test_expr icu-2.5 {i1=$::OGRAVE} {lower(i1)}     $::ograve
     70 test_expr icu-2.6 {i1=$::OGRAVE} {upper(i1)}     $::OGRAVE
     71 
     72 test_expr icu-2.7 {i1=$::szlig} {upper(i1)}      "SS"
     73 test_expr icu-2.8 {i1='SS'} {lower(i1)}          "ss"
     74 
     75 # In turkish (locale="tr_TR"), the lower case version of I
     76 # is "small dotless i" (code point 0x131 (decimal 305)).
     77 #
     78 set ::small_dotless_i "\u0131"
     79 test_expr icu-3.1 {i1='I'} {lower(i1)}           "i"
     80 test_expr icu-3.2 {i1='I'} {lower(i1, 'tr_tr')}  $::small_dotless_i
     81 test_expr icu-3.3 {i1='I'} {lower(i1, 'en_AU')}  "i"
     82 
     83 #--------------------------------------------------------------------
     84 # Test the collation sequence function.
     85 #
     86 do_test icu-4.1 {
     87   execsql {
     88     CREATE TABLE fruit(name);
     89     INSERT INTO fruit VALUES('plum');
     90     INSERT INTO fruit VALUES('cherry');
     91     INSERT INTO fruit VALUES('apricot');
     92     INSERT INTO fruit VALUES('peach');
     93     INSERT INTO fruit VALUES('chokecherry');
     94     INSERT INTO fruit VALUES('yamot');
     95   }
     96 } {}
     97 do_test icu-4.2 {
     98   execsql {
     99     SELECT icu_load_collation('en_US', 'AmericanEnglish');
    100     SELECT icu_load_collation('lt_LT', 'Lithuanian');
    101   }
    102   execsql {
    103     SELECT name FROM fruit ORDER BY name COLLATE AmericanEnglish ASC;
    104   }
    105 } {apricot cherry chokecherry peach plum yamot}
    106 
    107 
    108 # Test collation using Lithuanian rules. In the Lithuanian
    109 # alphabet, "y" comes right after "i".
    110 #
    111 do_test icu-4.3 {
    112   execsql {
    113     SELECT name FROM fruit ORDER BY name COLLATE Lithuanian ASC;
    114   }
    115 } {apricot cherry chokecherry yamot peach plum}
    116 
    117 #-------------------------------------------------------------------------
    118 # Test that it is not possible to call the ICU regex() function with 
    119 # anything other than exactly two arguments. See also:
    120 #
    121 #   http://src.chromium.org/viewvc/chrome/trunk/src/third_party/sqlite/icu-regexp.patch?revision=34807&view=markup
    122 #
    123 do_catchsql_test icu-5.1 { SELECT regexp('a[abc]c.*', 'abc') } {0 1}
    124 do_catchsql_test icu-5.2 { 
    125   SELECT regexp('a[abc]c.*') 
    126 } {1 {wrong number of arguments to function regexp()}}
    127 do_catchsql_test icu-5.3 { 
    128   SELECT regexp('a[abc]c.*', 'abc', 'c') 
    129 } {1 {wrong number of arguments to function regexp()}}
    130 do_catchsql_test icu-5.4 { 
    131   SELECT 'abc' REGEXP 'a[abc]c.*'
    132 } {0 1}
    133 do_catchsql_test icu-5.4 { SELECT 'abc' REGEXP }    {1 {near " ": syntax error}}
    134 do_catchsql_test icu-5.5 { SELECT 'abc' REGEXP, 1 } {1 {near ",": syntax error}}
    135 
    136 finish_test
    137