.\" Automatically generated by Pod::Man 2.28 (Pod::Simple 3.28) .\" .\" Standard preamble: .\" ======================================================================== .de Sp \" Vertical space (when we can't use .PP) .if t .sp .5v .if n .sp .. .de Vb \" Begin verbatim text .ft CW .nf .ne \\$1 .. .de Ve \" End verbatim text .ft R .fi .. .\" Set up some character translations and predefined strings. \*(-- will .\" give an unbreakable dash, \*(PI will give pi, \*(L" will give a left .\" double quote, and \*(R" will give a right double quote. \*(C+ will .\" give a nicer C++. Capital omega is used to do unbreakable dashes and .\" therefore won't be available. \*(C` and \*(C' expand to `' in nroff, .\" nothing in troff, for use with C<>. .tr \(*W- .ds C+ C\v'-.1v'\h'-1p'\s-2+\h'-1p'+\s0\v'.1v'\h'-1p' .ie n \{\ . ds -- \(*W- . ds PI pi . if (\n(.H=4u)&(1m=24u) .ds -- \(*W\h'-12u'\(*W\h'-12u'-\" diablo 10 pitch . if (\n(.H=4u)&(1m=20u) .ds -- \(*W\h'-12u'\(*W\h'-8u'-\" diablo 12 pitch . ds L" "" . ds R" "" . ds C` "" . ds C' "" 'br\} .el\{\ . ds -- \|\(em\| . ds PI \(*p . ds L" `` . ds R" '' . ds C` . ds C' 'br\} .\" .\" Escape single quotes in literal strings from groff's Unicode transform. .ie \n(.g .ds Aq \(aq .el .ds Aq ' .\" .\" If the F register is turned on, we'll generate index entries on stderr for .\" titles (.TH), headers (.SH), subsections (.SS), items (.Ip), and index .\" entries marked with X<> in POD. Of course, you'll have to process the .\" output yourself in some meaningful fashion. .\" .\" Avoid warning from groff about undefined register 'F'. .de IX .. .nr rF 0 .if \n(.g .if rF .nr rF 1 .if (\n(rF:(\n(.g==0)) \{ . if \nF \{ . de IX . tm Index:\\$1\t\\n%\t"\\$2" .. . if !\nF==2 \{ . nr % 0 . nr F 2 . \} . \} .\} .rr rF .\" .\" Accent mark definitions (@(#)ms.acc 1.5 88/02/08 SMI; from UCB 4.2). .\" Fear. Run. Save yourself. No user-serviceable parts. . \" fudge factors for nroff and troff .if n \{\ . ds #H 0 . ds #V .8m . ds #F .3m . ds #[ \f1 . ds #] \fP .\} .if t \{\ . ds #H ((1u-(\\\\n(.fu%2u))*.13m) . ds #V .6m . ds #F 0 . ds #[ \& . ds #] \& .\} . \" simple accents for nroff and troff .if n \{\ . ds ' \& . ds ` \& . ds ^ \& . ds , \& . ds ~ ~ . ds / .\} .if t \{\ . ds ' \\k:\h'-(\\n(.wu*8/10-\*(#H)'\'\h"|\\n:u" . ds ` \\k:\h'-(\\n(.wu*8/10-\*(#H)'\`\h'|\\n:u' . ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'^\h'|\\n:u' . ds , \\k:\h'-(\\n(.wu*8/10)',\h'|\\n:u' . ds ~ \\k:\h'-(\\n(.wu-\*(#H-.1m)'~\h'|\\n:u' . ds / \\k:\h'-(\\n(.wu*8/10-\*(#H)'\z\(sl\h'|\\n:u' .\} . \" troff and (daisy-wheel) nroff accents .ds : \\k:\h'-(\\n(.wu*8/10-\*(#H+.1m+\*(#F)'\v'-\*(#V'\z.\h'.2m+\*(#F'.\h'|\\n:u'\v'\*(#V' .ds 8 \h'\*(#H'\(*b\h'-\*(#H' .ds o \\k:\h'-(\\n(.wu+\w'\(de'u-\*(#H)/2u'\v'-.3n'\*(#[\z\(de\v'.3n'\h'|\\n:u'\*(#] .ds d- \h'\*(#H'\(pd\h'-\w'~'u'\v'-.25m'\f2\(hy\fP\v'.25m'\h'-\*(#H' .ds D- D\\k:\h'-\w'D'u'\v'-.11m'\z\(hy\v'.11m'\h'|\\n:u' .ds th \*(#[\v'.3m'\s+1I\s-1\v'-.3m'\h'-(\w'I'u*2/3)'\s-1o\s+1\*(#] .ds Th \*(#[\s+2I\s-2\h'-\w'I'u*3/5'\v'-.3m'o\v'.3m'\*(#] .ds ae a\h'-(\w'a'u*4/10)'e .ds Ae A\h'-(\w'A'u*4/10)'E . \" corrections for vroff .if v .ds ~ \\k:\h'-(\\n(.wu*9/10-\*(#H)'\s-2\u~\d\s+2\h'|\\n:u' .if v .ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'\v'-.4m'^\v'.4m'\h'|\\n:u' . \" for low resolution devices (crt and lpr) .if \n(.H>23 .if \n(.V>19 \ \{\ . ds : e . ds 8 ss . ds o a . ds d- d\h'-1'\(ga . ds D- D\h'-1'\(hy . ds th \o'bp' . ds Th \o'LP' . ds ae ae . ds Ae AE .\} .rm #[ #] #H #V #F C .\" ======================================================================== .\" .IX Title "Lucy::Docs::Tutorial::BeyondSimple 3pm" .TH Lucy::Docs::Tutorial::BeyondSimple 3pm "2015-03-06" "perl v5.20.2" "User Contributed Perl Documentation" .\" For nroff, turn off justification. Always turn off hyphenation; it makes .\" way too many mistakes in technical documents. .if n .ad l .nh .SH "NAME" Lucy::Docs::Tutorial::BeyondSimple \- A more flexible app structure. .SH "DESCRIPTION" .IX Header "DESCRIPTION" .SS "Goal" .IX Subsection "Goal" In this tutorial chapter, we'll refactor the apps we built in Lucy::Docs::Tutorial::Simple so that they look exactly the same from the end user's point of view, but offer the developer greater possibilites for expansion. .PP To achieve this, we'll ditch Lucy::Simple and replace it with the classes that it uses internally: .IP "\(bu" 4 Lucy::Plan::Schema \- Plan out your index. .IP "\(bu" 4 Lucy::Plan::FullTextType \- Field type for full text search. .IP "\(bu" 4 Lucy::Analysis::PolyAnalyzer \- A one-size-fits-all parser/tokenizer. .IP "\(bu" 4 Lucy::Index::Indexer \- Manipulate index content. .IP "\(bu" 4 Lucy::Search::IndexSearcher \- Search an index. .IP "\(bu" 4 Lucy::Search::Hits \- Iterate over hits returned by a Searcher. .SS "Adaptations to indexer.pl" .IX Subsection "Adaptations to indexer.pl" After we load our modules... .PP .Vb 4 \& use Lucy::Plan::Schema; \& use Lucy::Plan::FullTextType; \& use Lucy::Analysis::PolyAnalyzer; \& use Lucy::Index::Indexer; .Ve .PP \&... the first item we're going need is a Schema. .PP The primary job of a Schema is to specify what fields are available and how they're defined. We'll start off with three fields: title, content and url. .PP .Vb 11 \& # Create Schema. \& my $schema = Lucy::Plan::Schema\->new; \& my $polyanalyzer = Lucy::Analysis::PolyAnalyzer\->new( \& language => \*(Aqen\*(Aq, \& ); \& my $type = Lucy::Plan::FullTextType\->new( \& analyzer => $polyanalyzer, \& ); \& $schema\->spec_field( name => \*(Aqtitle\*(Aq, type => $type ); \& $schema\->spec_field( name => \*(Aqcontent\*(Aq, type => $type ); \& $schema\->spec_field( name => \*(Aqurl\*(Aq, type => $type ); .Ve .PP All of the fields are spec'd out using the \*(L"FullTextType\*(R" FieldType, indicating that they will be searchable as \*(L"full text\*(R" \*(-- which means that they can be searched for individual words. The \*(L"analyzer\*(R", which is unique to FullTextType fields, is what breaks up the text into searchable tokens. .PP Next, we'll swap our Lucy::Simple object out for a Lucy::Index::Indexer. The substitution will be straightforward because Simple has merely been serving as a thin wrapper around an inner Indexer, and we'll just be peeling away the wrapper. .PP First, replace the constructor: .PP .Vb 7 \& # Create Indexer. \& my $indexer = Lucy::Index::Indexer\->new( \& index => $path_to_index, \& schema => $schema, \& create => 1, \& truncate => 1, \& ); .Ve .PP Next, have the \f(CW$indexer\fR object \f(CW\*(C`add_doc\*(C'\fR where we were having the \&\f(CW$lucy\fR object \f(CW\*(C`add_doc\*(C'\fR before: .PP .Vb 4 \& foreach my $filename (@filenames) { \& my $doc = parse_file($filename); \& $indexer\->add_doc($doc); \& } .Ve .PP There's only one extra step required: at the end of the app, you must call \&\fIcommit()\fR explicitly to close the indexing session and commit your changes. (Lucy::Simple hides this detail, calling \fIcommit()\fR implicitly when it needs to). .PP .Vb 1 \& $indexer\->commit; .Ve .SS "Adaptations to search.cgi" .IX Subsection "Adaptations to search.cgi" In our search app as in our indexing app, Lucy::Simple has served as a thin wrapper \*(-- this time around Lucy::Search::IndexSearcher and Lucy::Search::Hits. Swapping out Simple for these two classes is also straightforward: .PP .Vb 1 \& use Lucy::Search::IndexSearcher; \& \& my $searcher = Lucy::Search::IndexSearcher\->new( \& index => $path_to_index, \& ); \& my $hits = $searcher\->hits( # returns a Hits object, not a hit count \& query => $q, \& offset => $offset, \& num_wanted => $page_size, \& ); \& my $hit_count = $hits\->total_hits; # get the hit count here \& \& ... \& \& while ( my $hit = $hits\->next ) { \& ... \& } .Ve .SS "Hooray!" .IX Subsection "Hooray!" Congratulations! Your apps do the same thing as before... but now they'll be easier to customize. .PP In our next chapter, Lucy::Docs::Tutorial::FieldType, we'll explore how to assign different behaviors to different fields.