/ Check-in [512e1bdb]
Login

Many hyperlinks are disabled.
Use anonymous login to enable hyperlinks.

Overview
Comment:Fix some documentation issues in fts5.
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | fts5
Files: files | file ages | folders
SHA1:512e1bdb4093b59d1494dfc63391476eadd52aea
User & Date: dan 2015-01-10 20:34:27
Context
2015-01-12
17:58
Optimize the unicode61 tokenizer so that it handles ascii text faster. Make it the default tokenizer. Change the name of the simple tokenizer to "ascii". check-in: f22dbcca user: dan tags: fts5
2015-01-10
20:34
Fix some documentation issues in fts5. check-in: 512e1bdb user: dan tags: fts5
2015-01-07
19:33
Add the fts5 'optimize' command. check-in: e749be56 user: dan tags: fts5
Changes
Hide Diffs Unified Diffs Ignore Whitespace Patch

Changes to ext/fts5/extract_api_docs.tcl.

13
14
15
16
17
18
19

20
21
22
23
24
25
26
27


28
29
30
31
32
33
34
..
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
..
91
92
93
94
95
96
97






















98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114



115
116
117




118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
































































136
137
138
139
140
141
142
# This script extracts the documentation for the API used by fts5 auxiliary 
# functions from header file fts5.h. It outputs html text on stdout that
# is included in the documentation on the web.
# 

set ::fts5_docs_output ""
if {[info commands hd_putsnl]==""} {

  proc output {text} {
    puts $text
  }
} else {
  proc output {text} {
    append ::fts5_docs_output $text
  }
}



set input_file [file join [file dir [info script]] fts5.h]
set fd [open $input_file]
set data [read $fd]
close $fd


................................................................................
# returns a key/value list of structure member names and definitions. i.e.
#
#   iVersion {int iVersion} xUserData {void *(*xUserData)(Fts5Context*)} ...
#
proc get_struct_members {data} {

  # Extract the structure definition from the fts5.h file.
  regexp "struct Fts5ExtensionApi {(.*)};" $data -> defn

  # Remove all comments from the structure definition
  regsub -all {/[*].*?[*]/} $defn {} defn2

  set res [list]
  foreach member [split $defn2 {;}] {

................................................................................
  if {$current_doc != ""} {
    lappend res $current_header $current_doc
  }

  set res
}























# Initialize global array M as a map from Fts5StructureApi member name
# to member definition. i.e.
#
#   iVersion  -> {int iVersion}
#   xUserData -> {void *(*xUserData)(Fts5Context*)}
#   ...
#
array set M [get_struct_members $data]

# Initialize global list D as a map from section name to documentation
# text. Most (all?) section names are structure member names.
#
set D [get_struct_docs $data [array names M]]

foreach {hdr docs} $D {
  if {[info exists M($hdr)]} {
    set hdr $M($hdr)



  }
  output "<h style=\"font-size:1.4em;background-color:#EEEEEE;display:block\"><pre>  $hdr</pre></h>"





  set mode ""
  set bEmpty 1
  foreach line [split [string trim $docs] "\n"] {
    if {[string trim $line]==""} {
      if {$mode != ""} {output "</$mode>"}
      set mode ""
    } elseif {$mode == ""} {
      if {[regexp {^     } $line]} {
        set mode codeblock
      } else {
        set mode p
      }
      output "<$mode>"
    }
    output $line
  }
  if {$mode != ""} {output "</$mode>"}
}

































































set ::fts5_docs_output












>





|


>
>







 







|







 







>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
>
>
>
|
<

>
>
>
>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>







13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
..
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
..
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143

144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
# This script extracts the documentation for the API used by fts5 auxiliary 
# functions from header file fts5.h. It outputs html text on stdout that
# is included in the documentation on the web.
# 

set ::fts5_docs_output ""
if {[info commands hd_putsnl]==""} {
  if {[llength $argv]>0} { set ::extract_api_docs_mode [lindex $argv 0] }
  proc output {text} {
    puts $text
  }
} else {
  proc output {text} {
    append ::fts5_docs_output "$text\n"
  }
}
if {[info exists ::extract_api_docs_mode]==0} {set ::extract_api_docs_mode api}


set input_file [file join [file dir [info script]] fts5.h]
set fd [open $input_file]
set data [read $fd]
close $fd


................................................................................
# returns a key/value list of structure member names and definitions. i.e.
#
#   iVersion {int iVersion} xUserData {void *(*xUserData)(Fts5Context*)} ...
#
proc get_struct_members {data} {

  # Extract the structure definition from the fts5.h file.
  regexp "struct Fts5ExtensionApi {(.*?)};" $data -> defn

  # Remove all comments from the structure definition
  regsub -all {/[*].*?[*]/} $defn {} defn2

  set res [list]
  foreach member [split $defn2 {;}] {

................................................................................
  if {$current_doc != ""} {
    lappend res $current_header $current_doc
  }

  set res
}

proc get_tokenizer_docs {data} {
  regexp {(xCreate:.*?)[*]/} $data -> docs

  set res "<dl>\n"
  foreach line [split [string trim $docs] "\n"] {
    regexp {[*][*](.*)} $line -> line
    if {[regexp {^ ?x.*:} $line]} {
      append res "<dt><b>$line</b></dt><dd><p style=margin-top:0>\n"
      continue
    }
    if {[string trim $line] == ""} {
      append res "<p>\n"
    } else {
      append res "$line\n"
    }
  }
  append res "</dl>\n"

  set res
}

proc get_api_docs {data} {
  # Initialize global array M as a map from Fts5StructureApi member name
  # to member definition. i.e.
  #
  #   iVersion  -> {int iVersion}
  #   xUserData -> {void *(*xUserData)(Fts5Context*)}
  #   ...
  #
  array set M [get_struct_members $data]
  
  # Initialize global list D as a map from section name to documentation
  # text. Most (all?) section names are structure member names.
  #
  set D [get_struct_docs $data [array names M]]
  
  foreach {sub docs} $D {
    if {[info exists M($sub)]} {
      set hdr $M($sub)
      set link " id=$sub"
    } else {
      set link ""
    }


    output "<hr color=#eeeee style=\"margin:1em 8.4ex 0 8.4ex;\"$link>"
    set style "padding-left:6ex;font-size:1.4em;display:block"
    output "<h style=\"$style\"><pre>$hdr</pre></h>"
  
    set mode ""
    set bEmpty 1
    foreach line [split [string trim $docs] "\n"] {
      if {[string trim $line]==""} {
        if {$mode != ""} {output "</$mode>"}
        set mode ""
      } elseif {$mode == ""} {
        if {[regexp {^     } $line]} {
          set mode codeblock
        } else {
          set mode p
        }
        output "<$mode>"
      }
      output $line
    }
    if {$mode != ""} {output "</$mode>"}
  }
}

proc get_fts5_struct {data start end} {
  set res ""
  set bOut 0
  foreach line [split $data "\n"] {
    if {$bOut==0} {
      if {[regexp $start $line]} {
        set bOut 1
      }
    }

    if {$bOut} {
      append res "$line\n"
    }

    if {$bOut} {
      if {[regexp $end $line]} {
        set bOut 0
      }
    }
  }

  set map [list /* <i>/* */ */</i>]
  string map $map $res
}

proc main {data} {
  switch $::extract_api_docs_mode {
    fts5_api {
      output [get_fts5_struct $data "typedef struct fts5_api" "^\};"]
    }

    fts5_tokenizer {
      output [get_fts5_struct $data "typedef struct Fts5Tokenizer" "^\};"]
    }

    fts5_extension {
      output [get_fts5_struct $data "typedef.*Fts5ExtensionApi" "^.;"]
    }

    Fts5ExtensionApi {
      set struct [get_fts5_struct $data "^struct Fts5ExtensionApi" "^.;"]
      set map [list]
      foreach {k v} [get_struct_members $data] {
        if {[string match x* $k]==0} continue
        lappend map $k "<a href=#$k>$k</a>"
      }
      output [string map $map $struct]
    }

    api {
      get_api_docs $data
    }

    tokenizer_api {
      output [get_tokenizer_docs $data]
    }

    default {
    }
  }
}
main $data

set ::fts5_docs_output





Changes to ext/fts5/fts5.h.

96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
...
208
209
210
211
212
213
214

215
216
217
218
219
220
221
222
223
224
225
...
236
237
238
239
240
241
242
243
244
245
246
247
248


249
250
251
252
253
254
255
256
257
258
259
260
261

262
263
264
265
266
267
268
** xTokenize:
**   Tokenize text using the tokenizer belonging to the FTS5 table.
**
** xQueryPhrase(pFts5, iPhrase, pUserData, xCallback):
**   This API function is used to query the FTS table for phrase iPhrase
**   of the current query. Specifically, a query equivalent to:
**
**       ... FROM ftstable WHERE ftstable MATCH $p ORDER BY DESC
**
**   with $p set to a phrase equivalent to the phrase iPhrase of the
**   current query is executed. For each row visited, the callback function
**   passed as the fourth argument is invoked. The context and API objects 
**   passed to the callback function may be used to access the properties of
**   each matched row. Invoking Api.xUserData() returns a copy of the pointer
**   passed as the third argument to pUserData.
................................................................................
**
** xCreate:
**   This function is used to allocate and inititalize a tokenizer instance.
**   A tokenizer instance is required to actually tokenize text.
**
**   The first argument passed to this function is a copy of the (void*)
**   pointer provided by the application when the fts5_tokenizer object

**   was registered with SQLite. The second and third arguments are an
**   array of nul-terminated strings containing the tokenizer arguments,
**   if any, specified as part of the CREATE VIRTUAL TABLE statement used
**   to create the fts5 table.
**
**   The final argument is an output variable. If successful, (*ppOut) 
**   should be set to point to the new tokenizer handle and SQLITE_OK
**   returned. If an error occurs, some value other than SQLITE_OK should
**   be returned. In this case, fts5 assumes that the final value of *ppOut 
**   is undefined.
**
................................................................................
**
**   For each token in the input string, the supplied callback xToken() must
**   be invoked. The first argument to it should be a copy of the pointer
**   passed as the second argument to xTokenize(). The next two arguments
**   are a pointer to a buffer containing the token text, and the size of
**   the token in bytes. The 4th and 5th arguments are the byte offsets of
**   the first byte of and first byte immediately following the text from 
**   which the token is derived within the input. The final argument is the
**   token position - the total number of tokens that appear before this one 
**   in the input buffer.
**
**   The xToken() callback must be invoked with non-decreasing values of
**   the iPos parameter.


**
**   If an xToken() callback returns any value other than SQLITE_OK, then
**   the tokenization should be abandoned and the xTokenize() method should
**   immediately return a copy of the xToken() return value. Or, if the
**   input buffer is exhausted, xTokenize() should return SQLITE_OK. Finally,
**   if an error occurs with the xTokenize() implementation itself, it
**   may abandon the tokenization and return any error code other than
**   SQLITE_OK or SQLITE_DONE.
**
*/
typedef struct fts5_tokenizer fts5_tokenizer;
typedef struct Fts5Tokenizer Fts5Tokenizer;


struct fts5_tokenizer {
  int (*xCreate)(void*, const char **azArg, int nArg, Fts5Tokenizer **ppOut);
  void (*xDelete)(Fts5Tokenizer*);
  int (*xTokenize)(Fts5Tokenizer*, 
      void *pCtx,
      const char *pText, int nText, 
      int (*xToken)(







|







 







>
|
|
|
|







 







|
<
<

<
<
>
>










<

<
>







96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
...
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
...
237
238
239
240
241
242
243
244


245


246
247
248
249
250
251
252
253
254
255
256
257

258

259
260
261
262
263
264
265
266
** xTokenize:
**   Tokenize text using the tokenizer belonging to the FTS5 table.
**
** xQueryPhrase(pFts5, iPhrase, pUserData, xCallback):
**   This API function is used to query the FTS table for phrase iPhrase
**   of the current query. Specifically, a query equivalent to:
**
**       ... FROM ftstable WHERE ftstable MATCH $p ORDER BY rowid DESC
**
**   with $p set to a phrase equivalent to the phrase iPhrase of the
**   current query is executed. For each row visited, the callback function
**   passed as the fourth argument is invoked. The context and API objects 
**   passed to the callback function may be used to access the properties of
**   each matched row. Invoking Api.xUserData() returns a copy of the pointer
**   passed as the third argument to pUserData.
................................................................................
**
** xCreate:
**   This function is used to allocate and inititalize a tokenizer instance.
**   A tokenizer instance is required to actually tokenize text.
**
**   The first argument passed to this function is a copy of the (void*)
**   pointer provided by the application when the fts5_tokenizer object
**   was registered with FTS5 (the third argument to xCreateTokenizer()). 
**   The second and third arguments are an array of nul-terminated strings
**   containing the tokenizer arguments, if any, specified following the
**   tokenizer name as part of the CREATE VIRTUAL TABLE statement used
**   to create the FTS5 table.
**
**   The final argument is an output variable. If successful, (*ppOut) 
**   should be set to point to the new tokenizer handle and SQLITE_OK
**   returned. If an error occurs, some value other than SQLITE_OK should
**   be returned. In this case, fts5 assumes that the final value of *ppOut 
**   is undefined.
**
................................................................................
**
**   For each token in the input string, the supplied callback xToken() must
**   be invoked. The first argument to it should be a copy of the pointer
**   passed as the second argument to xTokenize(). The next two arguments
**   are a pointer to a buffer containing the token text, and the size of
**   the token in bytes. The 4th and 5th arguments are the byte offsets of
**   the first byte of and first byte immediately following the text from 
**   which the token is derived within the input.


**


**   FTS5 assumes the xToken() callback is invoked for each token in the 
**   order that they occur within the input text.
**
**   If an xToken() callback returns any value other than SQLITE_OK, then
**   the tokenization should be abandoned and the xTokenize() method should
**   immediately return a copy of the xToken() return value. Or, if the
**   input buffer is exhausted, xTokenize() should return SQLITE_OK. Finally,
**   if an error occurs with the xTokenize() implementation itself, it
**   may abandon the tokenization and return any error code other than
**   SQLITE_OK or SQLITE_DONE.
**
*/

typedef struct Fts5Tokenizer Fts5Tokenizer;

typedef struct fts5_tokenizer fts5_tokenizer;
struct fts5_tokenizer {
  int (*xCreate)(void*, const char **azArg, int nArg, Fts5Tokenizer **ppOut);
  void (*xDelete)(Fts5Tokenizer*);
  int (*xTokenize)(Fts5Tokenizer*, 
      void *pCtx,
      const char *pText, int nText, 
      int (*xToken)(

Changes to ext/fts5/fts5_expr.c.

699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718



719
720
721
722
723
724
725
**
** SQLITE_OK is returned if an error occurs, or an SQLite error code 
** otherwise. It is not considered an error code if an iterator reaches
** EOF.
*/
static int fts5ExprNearNextMatch(
  Fts5Expr *pExpr,                /* Expression that pNear is a part of */
  Fts5ExprNode *pNode,
  int bFromValid,
  i64 iFrom
){
  int rc = SQLITE_OK;
  Fts5ExprNearset *pNear = pNode->pNear;
  while( 1 ){
    int i;

    /* Advance the iterators until they all point to the same rowid */
    rc = fts5ExprNearNextRowidMatch(pExpr, pNode, bFromValid, iFrom);
    if( pNode->bEof || rc!=SQLITE_OK ) break;




    for(i=0; rc==SQLITE_OK && i<pNear->nPhrase; i++){
      Fts5ExprPhrase *pPhrase = pNear->apPhrase[i];
      if( pPhrase->nTerm>1 || pNear->iCol>=0 ){
        int bMatch = 0;
        rc = fts5ExprPhraseIsMatch(pExpr, pNear->iCol, pPhrase, &bMatch);
        if( bMatch==0 ) break;
      }else{







|












>
>
>







699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
**
** SQLITE_OK is returned if an error occurs, or an SQLite error code 
** otherwise. It is not considered an error code if an iterator reaches
** EOF.
*/
static int fts5ExprNearNextMatch(
  Fts5Expr *pExpr,                /* Expression that pNear is a part of */
  Fts5ExprNode *pNode,            /* The "NEAR" node (FTS5_STRING) */
  int bFromValid,
  i64 iFrom
){
  int rc = SQLITE_OK;
  Fts5ExprNearset *pNear = pNode->pNear;
  while( 1 ){
    int i;

    /* Advance the iterators until they all point to the same rowid */
    rc = fts5ExprNearNextRowidMatch(pExpr, pNode, bFromValid, iFrom);
    if( pNode->bEof || rc!=SQLITE_OK ) break;

    /* Check that each phrase in the nearset matches the current row.
    ** Populate the pPhrase->poslist buffers at the same time. If any
    ** phrase is not a match, break out of the loop early.  */
    for(i=0; rc==SQLITE_OK && i<pNear->nPhrase; i++){
      Fts5ExprPhrase *pPhrase = pNear->apPhrase[i];
      if( pPhrase->nTerm>1 || pNear->iCol>=0 ){
        int bMatch = 0;
        rc = fts5ExprPhraseIsMatch(pExpr, pNear->iCol, pPhrase, &bMatch);
        if( bMatch==0 ) break;
      }else{

Added ext/fts5/test/fts5near.test.



































































































































>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
# 2014 Jan 08
#
# 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.
#
#***********************************************************************
#
# Tests focused on the NEAR operator.
#

source [file join [file dirname [info script]] fts5_common.tcl]
set testprefix fts5near

proc do_near_test {tn doc near res} {
  uplevel [list do_execsql_test $tn "
    DELETE FROM t1;
    INSERT INTO t1 VALUES('$doc');
    SELECT count(*) FROM t1 WHERE t1 MATCH '$near';
  " $res]
}

execsql { 
  CREATE VIRTUAL TABLE t1 USING fts5(x, tokenize = 'simple tokenchars .') 
}

do_near_test 1.1 ". . a . . . b . ." { NEAR(a b, 5) } 1
do_near_test 1.2 ". . a . . . b . ." { NEAR(a b, 4) } 1
do_near_test 1.3 ". . a . . . b . ." { NEAR(a b, 3) } 1
do_near_test 1.4 ". . a . . . b . ." { NEAR(a b, 2) } 0

do_near_test 1.5 ". . a . . . b . ." { NEAR(b a, 5) } 1
do_near_test 1.6 ". . a . . . b . ." { NEAR(b a, 4) } 1
do_near_test 1.7 ". . a . . . b . ." { NEAR(b a, 3) } 1
do_near_test 1.8 ". . a . . . b . ." { NEAR(b a, 2) } 0

do_near_test 1.9  ". a b . . . c . ." { NEAR("a b" c, 3) } 1
do_near_test 1.10 ". a b . . . c . ." { NEAR("a b" c, 2) } 0
do_near_test 1.11 ". a b . . . c . ." { NEAR(c "a b", 3) } 1
do_near_test 1.12 ". a b . . . c . ." { NEAR(c "a b", 2) } 0

do_near_test 1.13 ". a b . . . c d ." { NEAR(a+b c+d, 3) } 1
do_near_test 1.14 ". a b . . . c d ." { NEAR(a+b c+d, 2) } 0
do_near_test 1.15 ". a b . . . c d ." { NEAR(c+d a+b, 3) } 1
do_near_test 1.16 ". a b . . . c d ." { NEAR(c+d a+b, 2) } 0

do_near_test 1.17 ". a b . . . c d ." { NEAR(a b c d, 5) } 1
do_near_test 1.18 ". a b . . . c d ." { NEAR(a b c d, 4) } 0
do_near_test 1.19 ". a b . . . c d ." { NEAR(a+b c d, 4) } 1

do_near_test 1.20 "a b c d e f g h i" { NEAR(b+c a+b+c+d i, 5) } 1
do_near_test 1.21 "a b c d e f g h i" { NEAR(b+c a+b+c+d i, 4) } 0

do_near_test 1.22 "a b c d e f g h i" { NEAR(a+b+c+d i b+c, 5) } 1
do_near_test 1.23 "a b c d e f g h i" { NEAR(a+b+c+d i b+c, 4) } 0

do_near_test 1.24 "a b c d e f g h i" { NEAR(i a+b+c+d b+c, 5) } 1
do_near_test 1.25 "a b c d e f g h i" { NEAR(i a+b+c+d b+c, 4) } 0


finish_test