Commit d9125a1a authored by webchick's avatar webchick
Browse files

#604002 by chx, naxoc, Heine, and kaakuu: Support more Unicode scripts by more precisely

defining the characters to be included in the search index. We now support Devanāgarī and
other scripts. A few billion users are now able to use core search module. WIN.
parent c226c6ac
......@@ -9,78 +9,98 @@
/**
* Matches Unicode character classes to exclude from the search index.
*
* See: http://www.unicode.org/Public/UNIDATA/UCD.html#General_Category_Values
* @see http://unicode.org/glossary
*
* The index only contains the following character classes:
* Lu Letter, Uppercase
* Ll Letter, Lowercase
* Lt Letter, Titlecase
* Lo Letter, Other
* Nd Number, Decimal Digit
* No Number, Other
* Characters with the following General_category (gc) property values are
* excluded from the search index. Also, they are used as word boundaries.
* While this does not fully conform to the Word Boundaries algorithm
* described in http://unicode.org/reports/tr29, as PCRE does not contain the
* Word_Break property table, this simpler algorithm has to do.
* - Cc, Cf, Cn, Co, Cs: Other.
* - Pc, Pd, Pe, Pf, Pi, Po, Ps: Punctuation.
* - Sc, Sk, Sm, So: Symbols.
* - Zl, Zp, Zs: Separators.
*
* Consequently, the index only contains characters with the following
* General_category (gc) property values:
* - Ll, Lm, Lo, Lt, Lu: Letters.
* - Mc, Me, Mn: Combining Marks.
* - Nd, Nl, No: Numbers.
*
* Note that the PCRE property matcher is not used because we wanted to be
* compatible with Unicode 5.2.0 regardless of the PCRE version used (and any
* bugs in PCRE property tables).
*/
define('PREG_CLASS_SEARCH_EXCLUDE',
'\x{0}-\x{2f}\x{3a}-\x{40}\x{5b}-\x{60}\x{7b}-\x{bf}\x{d7}\x{f7}\x{2b0}-' .
'\x{385}\x{387}\x{3f6}\x{482}-\x{489}\x{559}-\x{55f}\x{589}-\x{5c7}\x{5f3}-' .
'\x{61f}\x{640}\x{64b}-\x{65e}\x{66a}-\x{66d}\x{670}\x{6d4}\x{6d6}-\x{6ed}' .
'\x{6fd}\x{6fe}\x{700}-\x{70f}\x{711}\x{730}-\x{74a}\x{7a6}-\x{7b0}\x{901}-' .
'\x{903}\x{93c}\x{93e}-\x{94d}\x{951}-\x{954}\x{962}-\x{965}\x{970}\x{981}-' .
'\x{983}\x{9bc}\x{9be}-\x{9cd}\x{9d7}\x{9e2}\x{9e3}\x{9f2}-\x{a03}\x{a3c}-' .
'\x{a4d}\x{a70}\x{a71}\x{a81}-\x{a83}\x{abc}\x{abe}-\x{acd}\x{ae2}\x{ae3}' .
'\x{af1}-\x{b03}\x{b3c}\x{b3e}-\x{b57}\x{b70}\x{b82}\x{bbe}-\x{bd7}\x{bf0}-' .
'\x{c03}\x{c3e}-\x{c56}\x{c82}\x{c83}\x{cbc}\x{cbe}-\x{cd6}\x{d02}\x{d03}' .
'\x{d3e}-\x{d57}\x{d82}\x{d83}\x{dca}-\x{df4}\x{e31}\x{e34}-\x{e3f}\x{e46}-' .
'\x{e4f}\x{e5a}\x{e5b}\x{eb1}\x{eb4}-\x{ebc}\x{ec6}-\x{ecd}\x{f01}-\x{f1f}' .
'\x{f2a}-\x{f3f}\x{f71}-\x{f87}\x{f90}-\x{fd1}\x{102c}-\x{1039}\x{104a}-' .
'\x{104f}\x{1056}-\x{1059}\x{10fb}\x{10fc}\x{135f}-\x{137c}\x{1390}-\x{1399}' .
'\x{166d}\x{166e}\x{1680}\x{169b}\x{169c}\x{16eb}-\x{16f0}\x{1712}-\x{1714}' .
'\x{1732}-\x{1736}\x{1752}\x{1753}\x{1772}\x{1773}\x{17b4}-\x{17db}\x{17dd}' .
'\x{17f0}-\x{180e}\x{1843}\x{18a9}\x{1920}-\x{1945}\x{19b0}-\x{19c0}\x{19c8}' .
'\x{19c9}\x{19de}-\x{19ff}\x{1a17}-\x{1a1f}\x{1d2c}-\x{1d61}\x{1d78}\x{1d9b}-' .
'\x{1dc3}\x{1fbd}\x{1fbf}-\x{1fc1}\x{1fcd}-\x{1fcf}\x{1fdd}-\x{1fdf}\x{1fed}-' .
'\x{1fef}\x{1ffd}-\x{2070}\x{2074}-\x{207e}\x{2080}-\x{2101}\x{2103}-\x{2106}' .
'\x{2108}\x{2109}\x{2114}\x{2116}-\x{2118}\x{211e}-\x{2123}\x{2125}\x{2127}' .
'\x{2129}\x{212e}\x{2132}\x{213a}\x{213b}\x{2140}-\x{2144}\x{214a}-\x{2b13}' .
'\x{2ce5}-\x{2cff}\x{2d6f}\x{2e00}-\x{3005}\x{3007}-\x{303b}\x{303d}-\x{303f}' .
'\x{3099}-\x{309e}\x{30a0}\x{30fb}\x{30fd}\x{30fe}\x{3190}-\x{319f}\x{31c0}-' .
'\x{31cf}\x{3200}-\x{33ff}\x{4dc0}-\x{4dff}\x{a015}\x{a490}-\x{a716}\x{a802}' .
'\x{a806}\x{a80b}\x{a823}-\x{a82b}\x{d800}-\x{f8ff}\x{fb1e}\x{fb29}\x{fd3e}' .
'\x{fd3f}\x{fdfc}-\x{fe6b}\x{feff}-\x{ff0f}\x{ff1a}-\x{ff20}\x{ff3b}-\x{ff40}' .
'\x{ff5b}-\x{ff65}\x{ff70}\x{ff9e}\x{ff9f}\x{ffe0}-\x{fffd}');
'\x{0}-\x{2F}\x{3A}-\x{40}\x{5B}-\x{60}\x{7B}-\x{A9}\x{AB}-\x{B1}\x{B4}' .
'\x{B6}-\x{B8}\x{BB}\x{BF}\x{D7}\x{F7}\x{2C2}-\x{2C5}\x{2D2}-\x{2DF}' .
'\x{2E5}-\x{2EB}\x{2ED}\x{2EF}-\x{2FF}\x{375}\x{37E}-\x{385}\x{387}\x{3F6}' .
'\x{482}\x{55A}-\x{55F}\x{589}-\x{58A}\x{5BE}\x{5C0}\x{5C3}\x{5C6}' .
'\x{5F3}-\x{60F}\x{61B}-\x{61F}\x{66A}-\x{66D}\x{6D4}\x{6DD}\x{6E9}' .
'\x{6FD}-\x{6FE}\x{700}-\x{70F}\x{7F6}-\x{7F9}\x{830}-\x{83E}' .
'\x{964}-\x{965}\x{970}\x{9F2}-\x{9F3}\x{9FA}-\x{9FB}\x{AF1}\x{B70}' .
'\x{BF3}-\x{BFA}\x{C7F}\x{CF1}-\x{CF2}\x{D79}\x{DF4}\x{E3F}\x{E4F}' .
'\x{E5A}-\x{E5B}\x{F01}-\x{F17}\x{F1A}-\x{F1F}\x{F34}\x{F36}\x{F38}' .
'\x{F3A}-\x{F3D}\x{F85}\x{FBE}-\x{FC5}\x{FC7}-\x{FD8}\x{104A}-\x{104F}' .
'\x{109E}-\x{109F}\x{10FB}\x{1360}-\x{1368}\x{1390}-\x{1399}\x{1400}' .
'\x{166D}-\x{166E}\x{1680}\x{169B}-\x{169C}\x{16EB}-\x{16ED}' .
'\x{1735}-\x{1736}\x{17B4}-\x{17B5}\x{17D4}-\x{17D6}\x{17D8}-\x{17DB}' .
'\x{1800}-\x{180A}\x{180E}\x{1940}-\x{1945}\x{19DE}-\x{19FF}' .
'\x{1A1E}-\x{1A1F}\x{1AA0}-\x{1AA6}\x{1AA8}-\x{1AAD}\x{1B5A}-\x{1B6A}' .
'\x{1B74}-\x{1B7C}\x{1C3B}-\x{1C3F}\x{1C7E}-\x{1C7F}\x{1CD3}\x{1FBD}' .
'\x{1FBF}-\x{1FC1}\x{1FCD}-\x{1FCF}\x{1FDD}-\x{1FDF}\x{1FED}-\x{1FEF}' .
'\x{1FFD}-\x{206F}\x{207A}-\x{207E}\x{208A}-\x{208E}\x{20A0}-\x{20B8}' .
'\x{2100}-\x{2101}\x{2103}-\x{2106}\x{2108}-\x{2109}\x{2114}' .
'\x{2116}-\x{2118}\x{211E}-\x{2123}\x{2125}\x{2127}\x{2129}\x{212E}' .
'\x{213A}-\x{213B}\x{2140}-\x{2144}\x{214A}-\x{214D}\x{214F}' .
'\x{2190}-\x{244A}\x{249C}-\x{24E9}\x{2500}-\x{2775}\x{2794}-\x{2B59}' .
'\x{2CE5}-\x{2CEA}\x{2CF9}-\x{2CFC}\x{2CFE}-\x{2CFF}\x{2E00}-\x{2E2E}' .
'\x{2E30}-\x{3004}\x{3008}-\x{3020}\x{3030}\x{3036}-\x{3037}' .
'\x{303D}-\x{303F}\x{309B}-\x{309C}\x{30A0}\x{30FB}\x{3190}-\x{3191}' .
'\x{3196}-\x{319F}\x{31C0}-\x{31E3}\x{3200}-\x{321E}\x{322A}-\x{3250}' .
'\x{3260}-\x{327F}\x{328A}-\x{32B0}\x{32C0}-\x{33FF}\x{4DC0}-\x{4DFF}' .
'\x{A490}-\x{A4C6}\x{A4FE}-\x{A4FF}\x{A60D}-\x{A60F}\x{A673}\x{A67E}' .
'\x{A6F2}-\x{A716}\x{A720}-\x{A721}\x{A789}-\x{A78A}\x{A828}-\x{A82B}' .
'\x{A836}-\x{A839}\x{A874}-\x{A877}\x{A8CE}-\x{A8CF}\x{A8F8}-\x{A8FA}' .
'\x{A92E}-\x{A92F}\x{A95F}\x{A9C1}-\x{A9CD}\x{A9DE}-\x{A9DF}' .
'\x{AA5C}-\x{AA5F}\x{AA77}-\x{AA79}\x{AADE}-\x{AADF}\x{ABEB}' .
'\x{D800}-\x{F8FF}\x{FB29}\x{FD3E}-\x{FD3F}\x{FDFC}-\x{FDFD}' .
'\x{FE10}-\x{FE19}\x{FE30}-\x{FE6B}\x{FEFF}-\x{FF0F}\x{FF1A}-\x{FF20}' .
'\x{FF3B}-\x{FF40}\x{FF5B}-\x{FF65}\x{FFE0}-\x{FFFD}');
/**
* Matches all 'N' Unicode character classes (numbers)
*/
define('PREG_CLASS_NUMBERS',
'\x{30}-\x{39}\x{b2}\x{b3}\x{b9}\x{bc}-\x{be}\x{660}-\x{669}\x{6f0}-\x{6f9}' .
'\x{966}-\x{96f}\x{9e6}-\x{9ef}\x{9f4}-\x{9f9}\x{a66}-\x{a6f}\x{ae6}-\x{aef}' .
'\x{b66}-\x{b6f}\x{be7}-\x{bf2}\x{c66}-\x{c6f}\x{ce6}-\x{cef}\x{d66}-\x{d6f}' .
'\x{e50}-\x{e59}\x{ed0}-\x{ed9}\x{f20}-\x{f33}\x{1040}-\x{1049}\x{1369}-' .
'\x{137c}\x{16ee}-\x{16f0}\x{17e0}-\x{17e9}\x{17f0}-\x{17f9}\x{1810}-\x{1819}' .
'\x{1946}-\x{194f}\x{2070}\x{2074}-\x{2079}\x{2080}-\x{2089}\x{2153}-\x{2183}' .
'\x{2460}-\x{249b}\x{24ea}-\x{24ff}\x{2776}-\x{2793}\x{3007}\x{3021}-\x{3029}' .
'\x{3038}-\x{303a}\x{3192}-\x{3195}\x{3220}-\x{3229}\x{3251}-\x{325f}\x{3280}-' .
'\x{3289}\x{32b1}-\x{32bf}\x{ff10}-\x{ff19}');
'\x{30}-\x{39}\x{b2}\x{b3}\x{b9}\x{bc}-\x{be}\x{660}-\x{669}\x{6f0}-\x{6f9}' .
'\x{966}-\x{96f}\x{9e6}-\x{9ef}\x{9f4}-\x{9f9}\x{a66}-\x{a6f}\x{ae6}-\x{aef}' .
'\x{b66}-\x{b6f}\x{be7}-\x{bf2}\x{c66}-\x{c6f}\x{ce6}-\x{cef}\x{d66}-\x{d6f}' .
'\x{e50}-\x{e59}\x{ed0}-\x{ed9}\x{f20}-\x{f33}\x{1040}-\x{1049}\x{1369}-' .
'\x{137c}\x{16ee}-\x{16f0}\x{17e0}-\x{17e9}\x{17f0}-\x{17f9}\x{1810}-\x{1819}' .
'\x{1946}-\x{194f}\x{2070}\x{2074}-\x{2079}\x{2080}-\x{2089}\x{2153}-\x{2183}' .
'\x{2460}-\x{249b}\x{24ea}-\x{24ff}\x{2776}-\x{2793}\x{3007}\x{3021}-\x{3029}' .
'\x{3038}-\x{303a}\x{3192}-\x{3195}\x{3220}-\x{3229}\x{3251}-\x{325f}\x{3280}-' .
'\x{3289}\x{32b1}-\x{32bf}\x{ff10}-\x{ff19}');
/**
* Matches all 'P' Unicode character classes (punctuation)
*/
define('PREG_CLASS_PUNCTUATION',
'\x{21}-\x{23}\x{25}-\x{2a}\x{2c}-\x{2f}\x{3a}\x{3b}\x{3f}\x{40}\x{5b}-\x{5d}' .
'\x{5f}\x{7b}\x{7d}\x{a1}\x{ab}\x{b7}\x{bb}\x{bf}\x{37e}\x{387}\x{55a}-\x{55f}' .
'\x{589}\x{58a}\x{5be}\x{5c0}\x{5c3}\x{5f3}\x{5f4}\x{60c}\x{60d}\x{61b}\x{61f}' .
'\x{66a}-\x{66d}\x{6d4}\x{700}-\x{70d}\x{964}\x{965}\x{970}\x{df4}\x{e4f}' .
'\x{e5a}\x{e5b}\x{f04}-\x{f12}\x{f3a}-\x{f3d}\x{f85}\x{104a}-\x{104f}\x{10fb}' .
'\x{1361}-\x{1368}\x{166d}\x{166e}\x{169b}\x{169c}\x{16eb}-\x{16ed}\x{1735}' .
'\x{1736}\x{17d4}-\x{17d6}\x{17d8}-\x{17da}\x{1800}-\x{180a}\x{1944}\x{1945}' .
'\x{2010}-\x{2027}\x{2030}-\x{2043}\x{2045}-\x{2051}\x{2053}\x{2054}\x{2057}' .
'\x{207d}\x{207e}\x{208d}\x{208e}\x{2329}\x{232a}\x{23b4}-\x{23b6}\x{2768}-' .
'\x{2775}\x{27e6}-\x{27eb}\x{2983}-\x{2998}\x{29d8}-\x{29db}\x{29fc}\x{29fd}' .
'\x{3001}-\x{3003}\x{3008}-\x{3011}\x{3014}-\x{301f}\x{3030}\x{303d}\x{30a0}' .
'\x{30fb}\x{fd3e}\x{fd3f}\x{fe30}-\x{fe52}\x{fe54}-\x{fe61}\x{fe63}\x{fe68}' .
'\x{fe6a}\x{fe6b}\x{ff01}-\x{ff03}\x{ff05}-\x{ff0a}\x{ff0c}-\x{ff0f}\x{ff1a}' .
'\x{ff1b}\x{ff1f}\x{ff20}\x{ff3b}-\x{ff3d}\x{ff3f}\x{ff5b}\x{ff5d}\x{ff5f}-' .
'\x{ff65}');
'\x{21}-\x{23}\x{25}-\x{2a}\x{2c}-\x{2f}\x{3a}\x{3b}\x{3f}\x{40}\x{5b}-\x{5d}' .
'\x{5f}\x{7b}\x{7d}\x{a1}\x{ab}\x{b7}\x{bb}\x{bf}\x{37e}\x{387}\x{55a}-\x{55f}' .
'\x{589}\x{58a}\x{5be}\x{5c0}\x{5c3}\x{5f3}\x{5f4}\x{60c}\x{60d}\x{61b}\x{61f}' .
'\x{66a}-\x{66d}\x{6d4}\x{700}-\x{70d}\x{964}\x{965}\x{970}\x{df4}\x{e4f}' .
'\x{e5a}\x{e5b}\x{f04}-\x{f12}\x{f3a}-\x{f3d}\x{f85}\x{104a}-\x{104f}\x{10fb}' .
'\x{1361}-\x{1368}\x{166d}\x{166e}\x{169b}\x{169c}\x{16eb}-\x{16ed}\x{1735}' .
'\x{1736}\x{17d4}-\x{17d6}\x{17d8}-\x{17da}\x{1800}-\x{180a}\x{1944}\x{1945}' .
'\x{2010}-\x{2027}\x{2030}-\x{2043}\x{2045}-\x{2051}\x{2053}\x{2054}\x{2057}' .
'\x{207d}\x{207e}\x{208d}\x{208e}\x{2329}\x{232a}\x{23b4}-\x{23b6}\x{2768}-' .
'\x{2775}\x{27e6}-\x{27eb}\x{2983}-\x{2998}\x{29d8}-\x{29db}\x{29fc}\x{29fd}' .
'\x{3001}-\x{3003}\x{3008}-\x{3011}\x{3014}-\x{301f}\x{3030}\x{303d}\x{30a0}' .
'\x{30fb}\x{fd3e}\x{fd3f}\x{fe30}-\x{fe52}\x{fe54}-\x{fe61}\x{fe63}\x{fe68}' .
'\x{fe6a}\x{fe6b}\x{ff01}-\x{ff03}\x{ff05}-\x{ff0a}\x{ff0c}-\x{ff0f}\x{ff1a}' .
'\x{ff1b}\x{ff1f}\x{ff20}\x{ff3b}-\x{ff3d}\x{ff3f}\x{ff5b}\x{ff5d}\x{ff5f}-' .
'\x{ff65}');
/**
* Matches all CJK characters that are candidates for auto-splitting
......@@ -386,7 +406,9 @@ function search_simplify($text) {
$text = preg_replace('/([' . PREG_CLASS_NUMBERS . ']+)[' . PREG_CLASS_PUNCTUATION . ']+(?=[' . PREG_CLASS_NUMBERS . '])/u', '\1', $text);
// The dot, underscore and dash are simply removed. This allows meaningful
// search behavior with acronyms and URLs.
// search behavior with acronyms and URLs. No need to use the unicode modifer
// here because 0-127 ASCII characters can't match higher UTF-8 characters as
// the leftmost bit of those are 1.
$text = preg_replace('/[._-]+/', '', $text);
// With the exception of the rules above, we consider all punctuation,
......
......@@ -566,3 +566,37 @@ class SearchCommentTestCase extends DrupalWebTestCase {
$this->assertNoText($comment_body, t('Comment body text not found in search results.'));
}
}
/**
* Test search_simplify() on every Unicode character.
*/
class SearchSimplifyTestCase extends DrupalWebTestCase {
public static function getInfo() {
return array(
'name' => 'Search simplify',
'description' => 'Check that simplification works as intended.',
'group' => 'Search',
);
}
function testSearchSimplify() {
$input = file_get_contents(DRUPAL_ROOT . '/modules/search/tests/UnicodeTest.txt');
$strings = explode(chr(10), $input);
foreach ($strings as $key => $string) {
$simplified = search_simplify($string);
if ($key % 2) {
$this->assertIdentical($simplified, ' ', "Line $key is excluded from the index");
}
else {
$this->assertTrue(drupal_strlen($simplified) >= drupal_strlen($string), "Nothing is removed on line $key.");
}
}
$string = '';
for ($i = 0; $i < 32; $i++) {
$string .= chr($i);
}
// Diff really does not like files starting with \0 so test it separately.
$this->assertIdentical(' ', search_simplify($string), t('Search simplify works for ASCII control characters.'));
}
}
\ No newline at end of file
This diff is collapsed.
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment