KeywordInContextIndexBuilder.st
author Stefan Vogel <sv@exept.de>
Fri, 18 Jan 2008 20:40:51 +0100
changeset 1922 be14f1a04953
parent 1375 e034d3e027f2
child 2536 8907a20de2dc
permissions -rw-r--r--
#add:beforeIndex: - make immune against redefinition of #add: using #add:beforeIndex in subclasses (and leading to recursion).
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
1375
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
     1
"
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
     2
 COPYRIGHT (c) 2003 by eXept Software AG
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
     3
              All Rights Reserved
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
     4
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
     5
 This software is furnished under a license and may be used
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
     6
 only in accordance with the terms of that license and with the
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
     7
 inclusion of the above copyright notice.   This software may not
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
     8
 be provided or otherwise made available to, or used by, any
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
     9
 other person.  No title to or ownership of the software is
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    10
 hereby transferred.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    11
"
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    12
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    13
"{ Package: 'stx:libbasic2' }"
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    14
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    15
Object subclass:#KeywordInContextIndexBuilder
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    16
	instanceVariableNames:'keywordToLinesMapping excluded separatorAlgorithm'
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    17
	classVariableNames:''
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    18
	poolDictionaries:''
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    19
	category:'Collections-Support'
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    20
!
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    21
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    22
!KeywordInContextIndexBuilder class methodsFor:'documentation'!
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    23
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    24
copyright
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    25
"
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    26
 COPYRIGHT (c) 2003 by eXept Software AG
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    27
              All Rights Reserved
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    28
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    29
 This software is furnished under a license and may be used
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    30
 only in accordance with the terms of that license and with the
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    31
 inclusion of the above copyright notice.   This software may not
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    32
 be provided or otherwise made available to, or used by, any
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    33
 other person.  No title to or ownership of the software is
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    34
 hereby transferred.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    35
"
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    36
!
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    37
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    38
documentation
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    39
"
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    40
    A support class for building a KWIC (Keyword in Context) indices.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    41
    (for example, to build a KWIC index on html pages or class documentation).
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    42
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    43
    [author:]
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    44
        Claus Gittinger (cg@alan)
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    45
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    46
    [instance variables:]
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    47
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    48
    [class variables:]
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    49
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    50
    [see also:]
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    51
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    52
"
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    53
!
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    54
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    55
examples
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    56
"
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    57
                                                                [exBegin]
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    58
    |kwic|
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    59
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    60
    kwic := KeywordInContextIndexBuilder new.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    61
    kwic excluded:#('the' 'and' 'a' 'an').
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    62
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    63
    kwic addLine:'bla bla bla' reference:1.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    64
    kwic addLine:'one two three' reference:2.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    65
    kwic addLine:'a cat and a dog' reference:3.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    66
    kwic addLine:'the man in the middle' reference:4.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    67
    kwic addLine:'the man with the dog' reference:5.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    68
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    69
    kwic 
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    70
        entriesDo:[:word :left :right :ref |
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    71
            Transcript 
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    72
                show:((left contractTo:20) leftPaddedTo:20);
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    73
                space;
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    74
                show:((word contractTo:10) leftPaddedTo:10);
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    75
                space;
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    76
                show:((right contractTo:20) leftPaddedTo:20);
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    77
                cr    
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    78
        ].
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    79
                                                                [exEnd]
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    80
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    81
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    82
  KWIC index over method selector components:
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    83
                                                                [exBegin]
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    84
    |kwic|
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    85
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    86
    kwic := KeywordInContextIndexBuilder new.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    87
    Smalltalk allClassesDo:[:eachClass |
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    88
        eachClass instAndClassSelectorsAndMethodsDo:[:sel :mthd |
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    89
            kwic addLine:sel reference:mthd.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    90
        ]
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    91
    ].
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    92
    kwic 
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    93
                                                                [exEnd]
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    94
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    95
  KWIC index over method selector components, with word separation:
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    96
                                                                [exBegin]
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    97
    |kwic|
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    98
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
    99
    kwic := KeywordInContextIndexBuilder forMethodSelectorIndex.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   100
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   101
    Smalltalk allClassesDo:[:eachClass |
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   102
        eachClass instAndClassSelectorsAndMethodsDo:[:sel :mthd |
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   103
            kwic addLine:sel reference:mthd.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   104
        ]
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   105
    ].
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   106
    kwic
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   107
                                                                [exEnd]
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   108
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   109
  KWIC index over method comments:
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   110
                                                                [exBegin]
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   111
    |kwic|
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   112
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   113
    kwic := KeywordInContextIndexBuilder forMethodComments.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   114
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   115
    Smalltalk allClassesDo:[:eachClass |
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   116
        eachClass instAndClassSelectorsAndMethodsDo:[:sel :mthd |
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   117
            |comment|
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   118
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   119
            (sel == #documentation) ifTrue:[
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   120
                comment := mthd comment.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   121
                comment notNil ifTrue:[
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   122
                    kwic addLine:comment reference:mthd mclass ignoreCase:true.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   123
                ]
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   124
            ] ifFalse:[
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   125
                (sel ~~ #examples
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   126
                and:[ sel ~~ #copyright
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   127
                and:[ sel ~~ #version]]) ifTrue:[
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   128
                    comment := mthd comment.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   129
                    comment notNil ifTrue:[
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   130
                        kwic addLine:comment reference:mthd ignoreCase:true.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   131
                    ]
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   132
                ]
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   133
            ]
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   134
        ]
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   135
    ].
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   136
    kwic
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   137
                                                                [exEnd]
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   138
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   139
  KWIC index over class comments:
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   140
                                                                [exBegin]
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   141
    |kwic|
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   142
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   143
    kwic := KeywordInContextIndexBuilder forMethodComments.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   144
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   145
    Smalltalk allClassesDo:[:eachClass |
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   146
        |mthd comment|
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   147
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   148
        mthd := eachClass theMetaclass compiledMethodAt:#documentation.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   149
        mthd notNil ifTrue:[
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   150
            comment := mthd comment.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   151
            comment notNil ifTrue:[
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   152
                kwic addLine:comment reference:eachClass theNonMetaclass ignoreCase:true.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   153
            ]
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   154
        ]
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   155
    ].
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   156
    kwic
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   157
                                                                [exEnd]
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   158
"
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   159
! !
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   160
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   161
!KeywordInContextIndexBuilder class methodsFor:'instance creation'!
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   162
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   163
forMethodComments
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   164
    "return an indexer for method comments"
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   165
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   166
    |sepChars sep kwic|
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   167
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   168
    sepChars := '.,;:_ !![]()''"#?<>|' , Character return, Character lf, Character tab.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   169
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   170
    sep := [:lines | lines asString asCollectionOfSubstringsSeparatedByAny:sepChars].
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   171
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   172
    kwic := self new.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   173
    kwic separatorAlgorithm:sep.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   174
    kwic excluded:#('the' 'and' 'a' 'an' 'for' 'with' 'no').
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   175
    ^ kwic
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   176
!
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   177
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   178
forMethodSelectorIndex
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   179
    "return an indexer for method selector components, with word separation at case boundaries"
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   180
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   181
    |sep kwic sepUCWords|
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   182
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   183
    sepUCWords := [:word :keyWords| 
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   184
                    |s w c lastC last2C frag|
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   185
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   186
                    word asLowercase = word ifTrue:[
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   187
                        keyWords add:word.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   188
                    ] ifFalse:[
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   189
                        s := word readStream.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   190
                        w := '' writeStream.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   191
                        [s atEnd] whileFalse:[
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   192
                            c := s next.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   193
                            (c isUppercase) ifTrue:[
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   194
                                (lastC notNil and:[lastC isUppercase not]) ifTrue:[
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   195
                                    keyWords add:w contents.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   196
                                    w := '' writeStream.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   197
                                ].
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   198
                            ] ifFalse:[
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   199
                                (last2C notNil and:[last2C isUppercase and:[lastC isUppercase]]) ifTrue:[
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   200
                                    c isLetter ifTrue:[
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   201
                                        frag := w contents.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   202
                                        w := '' writeStream.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   203
                                        w nextPut:(frag last).
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   204
                                        keyWords add:(frag allButLast).
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   205
                                    ] ifFalse:[
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   206
                                       ' frag := w contents.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   207
                                        w := '' writeStream.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   208
                                        keyWords add:frag. '.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   209
                                    ].
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   210
                                ].
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   211
                            ].
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   212
                            w nextPut:c.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   213
                            last2C := lastC.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   214
                            lastC := c.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   215
                        ].
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   216
                    ].
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   217
                  ].
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   218
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   219
    sep := [:line | 
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   220
                |words keyWords|
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   221
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   222
                words := line asCollectionOfSubstringsSeparatedByAny:'.,;:_ '.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   223
                keyWords := OrderedCollection new.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   224
                words do:[:eachWord | sepUCWords value:eachWord value:keyWords].
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   225
                keyWords
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   226
            ].
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   227
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   228
    kwic := self new.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   229
    kwic separatorAlgorithm:sep.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   230
    ^ kwic
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   231
!
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   232
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   233
new
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   234
    ^ self basicNew initialize
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   235
! !
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   236
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   237
!KeywordInContextIndexBuilder methodsFor:'accessing'!
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   238
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   239
excluded:something
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   240
    excluded := something asSet.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   241
!
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   242
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   243
separatorAlgorithm:something
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   244
    separatorAlgorithm := something.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   245
! !
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   246
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   247
!KeywordInContextIndexBuilder methodsFor:'building'!
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   248
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   249
addLine:aLine reference:opaqueReference
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   250
    self addLine:aLine reference:opaqueReference ignoreCase:false
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   251
!
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   252
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   253
addLine:aLine reference:opaqueReference ignoreCase:ignoreCase
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   254
    (separatorAlgorithm value:aLine) do:[:eachWord |
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   255
        |set word|
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   256
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   257
        ignoreCase ifTrue:[
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   258
            word := eachWord asLowercase.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   259
        ] ifFalse:[
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   260
            word := eachWord asLowercase.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   261
        ].
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   262
        (excluded includes:word) ifFalse:[
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   263
            set := keywordToLinesMapping at:word ifAbsent:nil.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   264
            set isNil ifTrue:[
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   265
                set := Set new.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   266
                keywordToLinesMapping at:word put:set
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   267
            ].
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   268
            set add:(aLine -> opaqueReference).
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   269
        ]
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   270
    ].
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   271
! !
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   272
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   273
!KeywordInContextIndexBuilder methodsFor:'enumerating'!
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   274
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   275
entriesDo:aBlock
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   276
    keywordToLinesMapping keys asSortedCollection do:[:eachKey |
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   277
        |setOfMatches lcKey|
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   278
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   279
        setOfMatches := keywordToLinesMapping at:eachKey.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   280
        lcKey := eachKey asLowercase.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   281
        setOfMatches do:[:eachAssoc |
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   282
            |text ref lines idx lIdx context left right word prevLine nextLine|
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   283
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   284
            text := eachAssoc key.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   285
            ref := eachAssoc value.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   286
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   287
            lines := text asCollectionOfLines.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   288
            idx := lines findFirst:[:line | line asLowercase includesString:lcKey].
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   289
            idx ~~ 0 ifTrue:[
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   290
                context := lines at:idx.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   291
                idx > 1 ifTrue:[
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   292
                    prevLine := (lines at:idx-1).
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   293
                    context := prevLine , ' ' , context.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   294
                ].
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   295
                idx < lines size ifTrue:[
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   296
                    nextLine := (lines at:idx+1).
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   297
                    context :=  context , ' ' , nextLine.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   298
                ].
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   299
                lIdx := context asLowercase findString:lcKey.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   300
                left := (context copyTo:lIdx - 1) withoutSeparators.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   301
                right := (context copyFrom:lIdx + lcKey size) withoutSeparators.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   302
                word := (context copyFrom:lIdx to:lIdx + lcKey size - 1) withoutSeparators.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   303
                aBlock value:word value:left value:right value:ref.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   304
            ].
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   305
        ]
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   306
    ]
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   307
! !
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   308
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   309
!KeywordInContextIndexBuilder methodsFor:'initialization'!
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   310
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   311
initialize
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   312
    keywordToLinesMapping := Dictionary new.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   313
    excluded := Set new.
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   314
    separatorAlgorithm := [:line | line asCollectionOfSubstringsSeparatedByAny:' .:,;-'].
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   315
! !
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   316
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   317
!KeywordInContextIndexBuilder class methodsFor:'documentation'!
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   318
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   319
version
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   320
    ^ '$Header: /cvs/stx/stx/libbasic2/KeywordInContextIndexBuilder.st,v 1.1 2003-12-08 16:03:24 cg Exp $'
e034d3e027f2 initial checkin
Claus Gittinger <cg@exept.de>
parents:
diff changeset
   321
! !