| /sqlite-3.40.0/ext/fts2/ |
| H A D | README.tokenizers | 5 the text tokenizer implementation to be used when indexing text 6 by specifying a "tokenizer" clause as part of the CREATE VIRTUAL TABLE 10 <columns ...> [, tokenizer <tokenizer-name> [<tokenizer-args>]] 17 arguments to pass to the selected tokenizer implementation. The 19 tokenizer. 27 Registering a new FTS2 tokenizer is similar to registering a new 35 tokenizer types with a database handle. Instead, the pointer must 41 SELECT fts2_tokenizer(<tokenizer-name>); 44 Where <tokenizer-name> is a string identifying the tokenizer and 47 it is registered as tokenizer <tokenizer-name> and a copy of it [all …]
|
| /sqlite-3.40.0/ext/fts3/ |
| H A D | README.tokenizers | 5 the text tokenizer implementation to be used when indexing text 10 <columns ...> [, tokenize <tokenizer-name> [<tokenizer-args>]] 17 arguments to pass to the selected tokenizer implementation. The 19 tokenizer. 23 FTS3 allows users to provide custom tokenizer implementations. The 27 Registering a new FTS3 tokenizer is similar to registering a new 35 tokenizer types with a database handle. Instead, the pointer must 41 SELECT fts3_tokenizer(<tokenizer-name>); 44 Where <tokenizer-name> is a string identifying the tokenizer and 47 it is registered as tokenizer <tokenizer-name> and a copy of it [all …]
|
| /sqlite-3.40.0/ext/fts5/test/ |
| H A D | fts5tokenizer.test | 48 } {1 {no such tokenizer: nosuch}} 52 } {1 {error in tokenizer constructor}} 78 " {1 {error in tokenizer constructor}} 138 } {1 {error in tokenizer constructor}} 141 } {1 {error in tokenizer constructor}} 186 } {1 {error in tokenizer constructor}} 189 } {1 {error in tokenizer constructor}} 194 } {1 {error in tokenizer constructor}} 199 } {1 {error in tokenizer constructor}} 202 # Porter tokenizer with very large tokens. [all …]
|
| H A D | fts5unicode2.test | 12 # The tests in this file focus on testing the "unicode" FTS tokenizer. 39 set tokenizer [concat unicode61 {*}[lrange $args 0 end-2]] 43 sqlite3_fts5_tokenize -subst db $tokenizer $input 183 # Make sure the unicode61 tokenizer does not crash if it is passed a 361 proc do_tokenize {tokenizer txt} { 363 foreach {b c} [sqlite3_fts5_tokenize -subst db $tokenizer $txt] { 372 # using tokenizer $tokenizer. The test passes if the tokenizer successfully 375 proc do_isspace_test {tn tokenizer lCp} { 378 uplevel [list do_test $tn [list do_tokenize $tokenizer $txt] {hello world}]
|
| H A D | fts5unicode.test | 24 proc tokenize_test {tn tokenizer input output} { 27 foreach {z s e} [sqlite3_fts5_tokenize db {$tokenizer} {$input}] { 42 # Check that "unicode61" really is the default tokenizer.
|
| H A D | fts5trigram.test | 12 # Tests for the fts5 "trigram" tokenizer. 128 } {1 {error in tokenizer constructor}} 131 } {1 {error in tokenizer constructor}}
|
| H A D | fts5ea.test | 84 # Experiment with a tokenizer that considers " to be a token character. 91 # Experiment with a tokenizer that considers " to be a token character.
|
| H A D | fts5fault6.test | 105 # OOM in the ASCII tokenizer with very large tokens. 107 # Also the unicode tokenizer. 138 # OOM while initializing a unicode61 tokenizer.
|
| H A D | fts5tok2.test | 20 # Simple test cases. Using the default (ascii) tokenizer.
|
| H A D | fts5synonym.test | 41 # Test a tokenizer that supports synonyms by adding extra entries to the 72 # 3.1.*: A tokenizer that declares the very first token to be colocated. 74 # 3.2.*: A tokenizer that reports two identical tokens at the same position.
|
| H A D | fts5tok1.test | 21 # Simple test cases. Using the default (ascii) tokenizer.
|
| H A D | fts5fault9.test | 84 # Test OOM injection with the xPhraseFirstColumn() API and a tokenizer
|
| /sqlite-3.40.0/test/ |
| H A D | fts3atoken.test | 46 # 1: Verify that there is no such fts3 tokenizer as 'blah'. 49 # retrieved value as tokenizer 'blah'. 55 # tokenizer 'blah' (it was not possible in step 1). 64 } {1 {unknown tokenizer: blah}} 163 } {1 {unknown tokenizer: nosuchtokenizer}} 168 # to test the test function as the tokenizer implementations. 262 # Test empty tokenizer names. 266 } {1 {unknown tokenizer: }} 269 } {1 {unknown tokenizer: }} 272 } {1 {unknown tokenizer: }} [all …]
|
| H A D | fts2token.test | 44 # 1: Verify that there is no such fts2 tokenizer as 'blah'. 46 # 2: Query for the built-in tokenizer 'simple'. Insert a copy of the 47 # retrieved value as tokenizer 'blah'. 49 # 3: Test that the value returned for tokenizer 'blah' is now the 53 # tokenizer 'blah' (it was not possible in step 1). 55 # 5: Test that the table created to use tokenizer 'blah' is usable. 61 } {1 {unknown tokenizer: blah}} 94 } {1 {unknown tokenizer: nosuchtokenizer}} 99 # to test the test function as the tokenizer implementations. 120 # Test cases fts2token-4.* test the ICU tokenizer. In practice, this [all …]
|
| H A D | fts3expr4.test | 27 proc test_fts3expr {tokenizer expr} { 28 db one {SELECT fts3_exprtest($tokenizer, $expr, 'a', 'b', 'c')} 50 # is passed to the tokenizer.
|
| H A D | fts4unicode.test | 12 # The tests in this file focus on testing the "unicode" FTS tokenizer. 174 # Make sure the unicode61 tokenizer does not crash if it is passed a 339 proc do_tokenize {tokenizer txt} { 341 foreach {a b c} [db one {SELECT fts3_tokenizer_test($tokenizer, $txt)}] { 350 # using tokenizer $tokenizer. The test passes if the tokenizer successfully 353 proc do_isspace_test {tn tokenizer lCp} { 356 uplevel [list do_test $tn [list do_tokenize $tokenizer $txt] {hello world}]
|
| H A D | fts3tok1.test | 22 # Simple test cases. Using the default (simple) tokenizer. 106 } {1 {unknown tokenizer: nosuchtokenizer}} 120 } {1 {unknown tokenizer}}
|
| H A D | tokenize.test | 12 # focus of this script testing the tokenizer
|
| H A D | fts1k.test | 37 } "unknown tokenizer: \x80"
|
| H A D | fts2l.test | 37 } "unknown tokenizer: \x80"
|
| H A D | fts3al.test | 37 } "unknown tokenizer: \x80"
|
| H A D | fts3malloc.test | 37 # OOM in tokenizer code have been fixed. 61 } {unknown tokenizer: unknown}
|
| H A D | fts4langid.test | 42 # 4.* - Test that if one is provided, the tokenizer xLanguage method 43 # is called to configure the tokenizer before tokenizing query
|
| /sqlite-3.40.0/ext/fts5/ |
| H A D | fts5_tcl.c | 692 fts5_tokenizer tokenizer; in f5tTokenize() local 723 rc = pApi->xFindTokenizer(pApi, azArg[0], &pUserdata, &tokenizer); in f5tTokenize() 729 rc = tokenizer.xCreate(pUserdata, &azArg[1], nArg-1, &pTok); in f5tTokenize() 740 rc = tokenizer.xTokenize( in f5tTokenize() 743 tokenizer.xDelete(pTok); in f5tTokenize()
|
| H A D | fts5_tokenize.c | 552 fts5_tokenizer tokenizer; /* Parent tokenizer module */ member 564 p->tokenizer.xDelete(p->pTokenizer); in fts5PorterDelete() 591 rc = pApi->xFindTokenizer(pApi, zBase, &pUserdata, &pRet->tokenizer); in fts5PorterCreate() 598 rc = pRet->tokenizer.xCreate(pUserdata, azArg2, nArg2, &pRet->pTokenizer); in fts5PorterCreate() 1256 return p->tokenizer.xTokenize( in fts5PorterTokenize()
|