[lucy-commits] svn commit: r1243100 - in /incubator/lucy/trunk: core/Lucy/Analysis/PolyAnalyzer.cfh perl/buildlib/Lucy/Build/Binding/Analysis.pm

[nw...@apache.org]

Author: nwellnhof
Date: Sat Feb 11 17:05:39 2012
New Revision: 1243100

URL: http://svn.apache.org/viewvc?rev=1243100&view=rev
Log:
Update Analyzer documentation

Modified:
    incubator/lucy/trunk/core/Lucy/Analysis/PolyAnalyzer.cfh
    incubator/lucy/trunk/perl/buildlib/Lucy/Build/Binding/Analysis.pm

Modified: incubator/lucy/trunk/core/Lucy/Analysis/PolyAnalyzer.cfh
URL: http://svn.apache.org/viewvc/incubator/lucy/trunk/core/Lucy/Analysis/PolyAnalyzer.cfh?rev=1243100&r1=1243099&r2=1243100&view=diff
==============================================================================
--- incubator/lucy/trunk/core/Lucy/Analysis/PolyAnalyzer.cfh (original)
+++ incubator/lucy/trunk/core/Lucy/Analysis/PolyAnalyzer.cfh Sat Feb 11 17:05:39 2012
@@ -26,6 +26,9 @@ parcel Lucy;
  * L<RegexTokenizer|Lucy::Analysis::RegexTokenizer>, and a
  * L<SnowballStemmer|Lucy::Analysis::SnowballStemmer> will be generated for you.
  *
+ * The language parameter is DEPRECATED. Use
+ * L<EasyAnalyzer|Lucy::Analysis::EasyAnalyzer> instead.
+ *
  * Supported languages:
  *
  *     en => English,
@@ -54,11 +57,12 @@ class Lucy::Analysis::PolyAnalyzer
 
     /**
      * @param language An ISO code from the list of supported languages.
+     * DEPRECATED, use L<EasyAnalyzer|Lucy::Analysis::EasyAnalyzer> instead.
      * @param analyzers An array of Analyzers.  The order of the analyzers
      * matters.  Don't put a SnowballStemmer before a RegexTokenizer (can't stem whole
      * documents or paragraphs -- just individual words), or a SnowballStopFilter
      * after a SnowballStemmer (stemmed words, e.g. "themselv", will not appear in a
-     * stoplist).  In general, the sequence should be: normalize, tokenize,
+     * stoplist).  In general, the sequence should be: tokenize, normalize,
      * stopalize, stem.
      */
     public inert PolyAnalyzer*

Modified: incubator/lucy/trunk/perl/buildlib/Lucy/Build/Binding/Analysis.pm
URL: http://svn.apache.org/viewvc/incubator/lucy/trunk/perl/buildlib/Lucy/Build/Binding/Analysis.pm?rev=1243100&r1=1243099&r2=1243100&view=diff
==============================================================================
--- incubator/lucy/trunk/perl/buildlib/Lucy/Build/Binding/Analysis.pm (original)
+++ incubator/lucy/trunk/perl/buildlib/Lucy/Build/Binding/Analysis.pm Sat Feb 11 17:05:39 2012
@@ -54,7 +54,7 @@ sub bind_casefolder {
     my $case_folder = Lucy::Analysis::CaseFolder->new;
 
     my $polyanalyzer = Lucy::Analysis::PolyAnalyzer->new(
-        analyzers => [ $case_folder, $tokenizer, $stemmer ],
+        analyzers => [ $tokenizer, $case_folder, $stemmer ],
     );
 END_SYNOPSIS
     my $constructor = <<'END_CONSTRUCTOR';
@@ -155,7 +155,7 @@ sub bind_normalizer {
     my $normalizer = Lucy::Analysis::Normalizer->new;
     
     my $polyanalyzer = Lucy::Analysis::PolyAnalyzer->new(
-        analyzers => [ $normalizer, $tokenizer, $stemmer ],
+        analyzers => [ $tokenizer, $normalizer, $stemmer ],
     );
 END_SYNOPSIS
     my $constructor = <<'END_CONSTRUCTOR';
@@ -231,7 +231,7 @@ sub bind_regextokenizer {
 
     # Then... once you have a tokenizer, put it into a PolyAnalyzer:
     my $polyanalyzer = Lucy::Analysis::PolyAnalyzer->new(
-        analyzers => [ $case_folder, $word_char_tokenizer, $stemmer ], );
+        analyzers => [ $word_char_tokenizer, $normalizer, $stemmer ], );
 END_SYNOPSIS
     my $constructor = <<'END_CONSTRUCTOR';
     my $word_char_tokenizer = Lucy::Analysis::RegexTokenizer->new(
@@ -257,7 +257,7 @@ sub bind_snowballstemmer {
     my $stemmer = Lucy::Analysis::SnowballStemmer->new( language => 'es' );
     
     my $polyanalyzer = Lucy::Analysis::PolyAnalyzer->new(
-        analyzers => [ $case_folder, $tokenizer, $stemmer ],
+        analyzers => [ $tokenizer, $normalizer, $stemmer ],
     );
 
 This class is a wrapper around the Snowball stemming library, so it supports
@@ -286,7 +286,7 @@ sub bind_snowballstopfilter {
         language => 'fr',
     );
     my $polyanalyzer = Lucy::Analysis::PolyAnalyzer->new(
-        analyzers => [ $case_folder, $tokenizer, $stopfilter, $stemmer ],
+        analyzers => [ $tokenizer, $normalizer, $stopfilter, $stemmer ],
     );
 END_SYNOPSIS
     my $constructor = <<'END_CONSTRUCTOR';
@@ -319,7 +319,7 @@ sub bind_standardtokenizer {
 
     # Then... once you have a tokenizer, put it into a PolyAnalyzer:
     my $polyanalyzer = Lucy::Analysis::PolyAnalyzer->new(
-        analyzers => [ $case_folder, $tokenizer, $stemmer ], );
+        analyzers => [ $tokenizer, $normalizer, $stemmer ], );
 END_SYNOPSIS
     my $constructor = <<'END_CONSTRUCTOR';
     my $tokenizer = Lucy::Analysis::StandardTokenizer->new;