Artifact 0627683f8ca06035d677d4becc2cd0dc57149ef7:

• File test/fts4unicode.test — part of check-in [0c13570e] at 2012-05-25 17:50:19 on branch fts4-unicode — Add an experimental tokenizer to fts4 - "unicode". This tokenizer works in the same way except that it understands unicode "simple case folding" and recognizes all characters not classified as "Letters" or "Numbers" by unicode as token separators. (user: dan size: 1399)

# 2012 May 25
#
# The author disclaims copyright to this source code.  In place of
# a legal notice, here is a blessing:
#
#    May you do good and not evil.
#    May you find forgiveness for yourself and forgive others.
#    May you share freely, never taking more than you give.
#
#*************************************************************************
#
# The tests in this file focus on testing the "unicode" FTS tokenizer.
#

set testdir [file dirname $argv0]
source $testdir/tester.tcl
ifcapable !fts3 { finish_test ; return }
set ::testprefix fts4unicode

proc do_unicode_token_test {tn input res} {
  set input [string map {' ''} $input]
  uplevel [list do_execsql_test $tn "
    SELECT fts3_tokenizer_test('unicode', '$input');
  " [list [list {*}$res]]]
}

do_unicode_token_test 1.0 {a B c D} {0 a a 1 b B 2 c c 3 d D}
do_unicode_token_test 1.1 {Ä Ö Ü} {0 ä Ä 1 ö Ö 2 ü Ü}
do_unicode_token_test 1.2 {xÄx xÖx xÜx} {0 xäx xÄx 1 xöx xÖx 2 xüx xÜx}

# 0x00DF is a small "sharp s". 0x1E9E is a capital sharp s.
do_unicode_token_test 1.3 "\uDF" "0 \uDF \uDF"
do_unicode_token_test 1.4 "\u1E9E" "0 ß \u1E9E"
do_unicode_token_test 1.5 "\u1E9E" "0 \uDF \u1E9E"

do_unicode_token_test 1.6 "The quick brown fox" {
  0 the The 1 quick quick 2 brown brown 3 fox fox
}
do_unicode_token_test 1.7 "The\u00bfquick\u224ebrown\u2263fox" {
  0 the The 1 quick quick 2 brown brown 3 fox fox
}

finish_test