ferret 0.10.5 → 0.10.6

data/TUTORIAL

@@ -1,7 +1,8 @@
 = Quick Introduction to Ferret
 
 The simplest way to use Ferret is through the Ferret::Index::Index class.
-Start by including the Ferret module.
+This is now aliased by Ferret::I for quick and easy access. Start by including
+the Ferret module.
 
   require 'ferret'
   include Ferret
@@ -41,32 +42,32 @@ could probably just use SimpleSearch. So let's give our documents some fields;
   index << {:title => "Programming Ruby", :content => "blah blah blah"}
   index << {:title => "Programming Ruby", :content => "yada yada yada"}
 
-Or if you are indexing data stored in a database, you'll probably want to
-store the id;
+Note the way that all field-names are Symbols. Although Strings will work, 
+this is a best-practice in Ferret. Or if you are indexing data stored in a
+database, you'll probably want to store the id;
 
   index << {:id => row.id, :title => row.title, :date => row.date}
 
-The methods above while store all of the input data as well tokenizing and
-indexing it. Sometimes we won't want to tokenize (divide the string into
-tokens) the data. For example, we might want to leave the title as a complete
-string and only allow searchs for that complete string. Sometimes we won't
-want to store the data as it's already stored in the database so it'll be a
-waste to store it in the index. Or perhaps we are doing without a database and 
-using Ferret to store all of our data, in which case we might not want to
-index it. For example, if we are storing images in the index, we won't want to
-index them. All of this can be done using Ferret's Ferret::Document module.
-eg;
-
-  include Ferret::Document
-  doc = Document.new
-  doc << Field.new("id",    row.id,    Field::Store::NO,  Field::Index::UNTOKENIZED)
-  doc << Field.new("title", row.title, Field::Store::YES, Field::Index::UNTOKENIZED)
-  doc << Field.new("data",  row.data,  Field::Store::YES, Field::Index::TOKENIZED)
-  doc << Field.new("image", row.image, Field::Store::YES, Field::Index::NO)
-  index << doc
+So far we have been storing and tokenizing all of the input data along with
+term vectors. If we want to change this we need to change the way we setup the
+index. You must create a FieldInfos object describing the index:
+
+  field_infos = FieldInfos.new(:store => :no,
+                               :index => :untokenized_omit_norms,
+                               :term_vector => :no)
+
+The values that you set FieldInfos to have will be used by default by all
+fields. If you want to change the properties for specific fields, you need to
+add a FieldInfo to field_infos.
 
-You can also compress the data that you are storing or store term vectors with
-the data. Read more about this in Ferret::Document::Field.
+  field_infos.add_field(:title, :store => :yes, :index => :yes, :boost => 10.0)
+  field_infos.add_field(:content, :store => :yes,
+                                  :index => :yes,
+                                  :term_vector => :with_positions_offsets)
+
+If you need to add a field to an already open index you do so like this:
+
+  index.field_infos.add_field(:new_field, :store => :yes)
 
 === Searching
 
@@ -76,23 +77,23 @@ Index#search_each. The first method returns a Ferret::Index::TopDocs object.
 The second we'll show here. Lets say we wanted to find all documents with the
 phrase "quick brown fox" in the content field. We'd write;
 
-  index.search_each('content:"quick brown fox"') do |doc, score|
-    puts "Document #{doc} found with a score of #{score}"
+  index.search_each('content:"quick brown fox"') do |id, score|
+    puts "Document #{id} found with a score of #{score}"
   end
 
 But "fast" has a pretty similar meaning to "quick" and we don't mind if the
 fox is a little red. Also, the phrase could be in the title so we'll search
 there as well. So we could expand our search like this;
 
-  index.search_each('title|content:"quick|fast brown|red fox"') do |doc, score|
-    puts "Document #{doc} found with a score of #{score}"
+  index.search_each('title|content:"quick|fast brown|red fox"') do |id, score|
+    puts "Document #{id} found with a score of #{score}"
   end
 
 What if we want to find all documents entered on or after 5th of September,
 2005 with the words "ruby" or "rails" in any field. We could type something like;
 
-  index.search_each('date:( >= 20050905) *:(ruby OR rails)') do |doc, score|
-    puts "Document #{doc} found with a score of #{score}"
+  index.search_each('date:( >= 20050905) *:(ruby OR rails)') do |id, score|
+    puts "Document #{index[id][:title]} found with a score of #{score}"
   end
 
 Ferret has quite a complex query language. To find out more about Ferret's
@@ -100,40 +101,72 @@ query language, see Ferret::QueryParser. You can also construct even more
 complex queries like Ferret::Search::Spans by hand. See Ferret::Search::Query
 for more information.
 
+=== Highlighting
+
+Ferret now has a super-fast highlighting method. See
+Ferret::Index::Index#highlight. Here is an example of how you would use it
+when printing to the console:
+
+  index.search_each('date:( >= 20050905) content:(ruby OR rails)') do |id, score|
+    puts "Document #{index[id][:title]} found with a score of #{score}"
+    highlights = index.highlight("content:(ruby OR rails)", 0,
+                                 :field => :content,
+                                 :pre_tag = "\033[36m",
+                                 :post_tag = "\033[m")
+    puts highlights
+  end
+
+And if you want to highlight a whole document, set :excert_length to :all:
+
+  puts index.highlight(query, doc_id,
+                       :field => :content,
+                       :pre_tag = "\033[36m",
+                       :post_tag = "\033[m",
+                       :excerpt_length => :all)
+
 === Accessing Documents
 
-You may have noticed that when we run a search we only get the document number
+You may have noticed that when we run a search we only get the document id
 back. By itself this isn't much use to us. Getting the data from the index is
-very straightforward. For example if we want the title field form the 3rd
+very straightforward. For example if we want the :title field form the 3rd
 document type;
   
-  index[2]["title"]
+  index[2][:title]
+
+Documents are lazy loading so if you try this:
 
-NOTE: documents are indexed from 0.
+  puts index[2]
 
-The default field is an empty string when you use the simple string document so
-to access those strings you'll have type;
+You will always get an empty Hash. To load all fields, call the load method:
+
+  puts index[2].load
+
+NOTE: documents are indexed from 0. You can also use array-like index
+parameters to access index. For example
+
+  index[1..4]
+  index[10, 10]
+  index[-5]
+
+The default field is :id (although you can change this with index's
+:default_create_field parameter);
 
   index << "This is a document"
-  index[0][""]
+  index[0][:id]
 
 Let's go back to the database example above. If we store all of our documents
 with an id then we can access that field using the id. As long as we called
-our id field "id" we can do this
-
-  id = "89721347"
-  index[id]["title"]
-
-If however we called our id field "key" we'll have to do this;
+our id field :id we can do this
 
-  id = Index::Term.new("key", "89721347")
-  index[id]["title"]
+  index["89721347"]["title"]
 
 Pretty simple huh? You should note though that if there are more then one
 document with the same *id* or *key* then only the first one will be returned
-so it is probably better that you ensure the key is unique somehow. (Ferret
-cannot do that for you)
-
+so it is probably better that you ensure the key is unique somehow. By setting
+Index's :key attribute to :id, Ferret will do this automatically for you. It
+can even handle multiple field primary keys. For example, you could set to
+:key to [:id, :model] and Ferret would keep the documents unique for that pair
+of fields.
 
 === Modifying and Deleting Documents
 
@@ -147,35 +180,33 @@ document;
 
   index << {:title => "Programing Rbuy", :content => "blah blah blah"}
   doc_num = nil
-  index.search('title:"Programing Rbuy"') {|doc, score| doc_num = doc}
-  return unless doc_num
-  doc = index[doc_num]
-  index.delete(doc_num)
+  index.search_each('title:"Programing Rbuy"') {|id, score| doc_id = id}
+  return unless doc_id
+  doc = index[doc_id]
+  index.delete(doc_id)
 
-  # modify doc
-  doc["title"] = "Programming Ruby"
+  # modify doc. It is just a Hash afterall
+  doc[:title] = "Programming Ruby"
 
   index << doc
 
-Again, we can use the the id field as above. This time though every document
-that matches the id will be deleted. Again, it is probably a good idea if you
-somehow ensure that your *ids* are kept unique.
+If you set the :key parameter as described in the last section there is no
+need to delete the document. It will be automatically deleted when you add
+another document with the same key.
+
+Also, we can use the id field, as above, to delete documents. This time though
+every document that matches the id will be deleted. Again, it is probably a
+good idea if you somehow ensure that your *ids* are kept unique.
 
   id = "23453422"
   index.delete(id)
 
-Or;
-
-  id = Index::Term.new("key", "23452345")
-  index.delete(id)
-  
 === Onwards
 
 This is just a small sampling of what Ferret allows you to do.  Ferret, like
 Lucene, is designed to be extended, and allows you to construct your own query
-types, analyzers, and so on. Future versions of Ferret will contain more of
-these, as well as instructions for how to subclass the base modules to create
-your own. For now you can look in the following places for more documentation;
+types, analyzers, and so on. Going onwards you should check out the following
+documentation:
 
 * Ferret::Analysis: for more information on how the data is processed when it
   is tokenized. There are a number of things you can do with your data such as
@@ -188,12 +219,6 @@ your own. For now you can look in the following places for more documentation;
   your own. You may however want to take advantage of the sorting or filtering
   abilities of Ferret to present your data the best way you see fit.
 
-* Ferret::Document: to find out how to create documents. This part of Ferret
-  is relatively straightforward. The main thing that we haven't gone into here
-  is the use of term vectors. These allow you to store and retrieve the
-  positions and offsets of the data which can be very useful in document
-  comparison amoung other things.  == More information
-
 * Ferret::QueryParser: if you want to find out more about what you can do with
   Ferret's Query Parser, this is the place to look. The query parser is one
   area that could use a bit of work so please send your suggestions.

data/ext/q_multi_term.c

@@ -474,6 +474,7 @@ Explanation *multi_tw_explain(Weight *self, IndexReader *ir, int doc_num)
 static Weight *multi_tw_new(Query *query, Searcher *searcher)
 {
     int i;
+    int doc_freq         = 0;
     Weight *self         = w_new(Weight, query);
     const char *field    = MTQ(query)->field;
     PriorityQueue *bt_pq = MTQ(query)->boosted_terms;
@@ -487,10 +488,11 @@ static Weight *multi_tw_new(Query *query, Searcher *searcher)
     self->idf            = 0.0;
 
     for (i = bt_pq->size; i > 0; i--) {
-        self->idf += sim_idf_term(self->similarity, field,
-                                  ((BoostedTerm *)bt_pq->heap[i])->term,
-                                  searcher);
+        doc_freq += searcher->doc_freq(searcher, field,
+                                       ((BoostedTerm *)bt_pq->heap[i])->term);
     }
+    self->idf += sim_idf(self->similarity, doc_freq,
+                         searcher->max_doc(searcher));
 
     return self;
 }

data/ext/q_parser.c

@@ -102,6 +102,9 @@ typedef struct BCArray {
     BooleanClause **clauses;
 } BCArray;
 
+float qp_default_fuzzy_min_sim = 0.5;
+int qp_default_fuzzy_pre_len = 0;
+
 
 
 /* Enabling traces.  */
@@ -123,7 +126,7 @@ typedef struct BCArray {
 #endif
 
 #if ! defined (YYSTYPE) && ! defined (YYSTYPE_IS_DECLARED)
-#line 23 "src/q_parser.y"
+#line 26 "src/q_parser.y"
 typedef union YYSTYPE {
     Query *query;
     BooleanClause *bcls;
@@ -133,7 +136,7 @@ typedef union YYSTYPE {
     char *str;
 } YYSTYPE;
 /* Line 196 of yacc.c.  */
-#line 137 "y.tab.c"
+#line 140 "y.tab.c"
 # define yystype YYSTYPE /* obsolescent; will be withdrawn */
 # define YYSTYPE_IS_DECLARED 1
 # define YYSTYPE_IS_TRIVIAL 1
@@ -142,7 +145,7 @@ typedef union YYSTYPE {
 
 
 /* Copy the second part of user declarations.  */
-#line 31 "src/q_parser.y"
+#line 34 "src/q_parser.y"
 
 static int yylex(YYSTYPE *lvalp, QParser *qp);
 static int yyerror(QParser *qp, char const *msg);
@@ -197,7 +200,7 @@ static Query *get_r_q(QParser *qp, char *field, char *from, char *to,
 
 
 /* Line 219 of yacc.c.  */
-#line 201 "y.tab.c"
+#line 204 "y.tab.c"
 
 #if ! defined (YYSIZE_T) && defined (__SIZE_TYPE__)
 # define YYSIZE_T __SIZE_TYPE__
@@ -436,12 +439,12 @@ static const yysigned_char yyrhs[] =
 /* YYRLINE[YYN] -- source line where rule number YYN was defined.  */
 static const unsigned char yyrline[] =
 {
-       0,    99,    99,   100,   102,   103,   104,   105,   107,   108,
-     109,   111,   112,   114,   115,   116,   117,   118,   119,   121,
-     122,   123,   125,   127,   127,   129,   129,   129,   132,   133,
-     135,   136,   137,   138,   140,   141,   142,   143,   144,   146,
-     147,   148,   149,   150,   151,   152,   153,   154,   155,   156,
-     157
+       0,   102,   102,   103,   105,   106,   107,   108,   110,   111,
+     112,   114,   115,   117,   118,   119,   120,   121,   122,   124,
+     125,   126,   128,   130,   130,   132,   132,   132,   135,   136,
+     138,   139,   140,   141,   143,   144,   145,   146,   147,   149,
+     150,   151,   152,   153,   154,   155,   156,   157,   158,   159,
+     160
 };
 #endif
 
@@ -1249,217 +1252,217 @@ yyreduce:
   switch (yyn)
     {
         case 2:
-#line 99 "src/q_parser.y"
+#line 102 "src/q_parser.y"
     { qp->result = (yyval.query) = NULL; }
     break;
 
   case 3:
-#line 100 "src/q_parser.y"
+#line 103 "src/q_parser.y"
     { qp->result = (yyval.query) = get_bool_q((yyvsp[0].bclss)); }
     break;
 
   case 4:
-#line 102 "src/q_parser.y"
+#line 105 "src/q_parser.y"
     { (yyval.bclss) = first_cls((yyvsp[0].bcls)); }
     break;
 
   case 5:
-#line 103 "src/q_parser.y"
+#line 106 "src/q_parser.y"
     { (yyval.bclss) = add_and_cls((yyvsp[-2].bclss), (yyvsp[0].bcls)); }
     break;
 
   case 6:
-#line 104 "src/q_parser.y"
+#line 107 "src/q_parser.y"
     { (yyval.bclss) = add_or_cls((yyvsp[-2].bclss), (yyvsp[0].bcls)); }
     break;
 
   case 7:
-#line 105 "src/q_parser.y"
+#line 108 "src/q_parser.y"
     { (yyval.bclss) = add_default_cls(qp, (yyvsp[-1].bclss), (yyvsp[0].bcls)); }
     break;
 
   case 8:
-#line 107 "src/q_parser.y"
+#line 110 "src/q_parser.y"
     { (yyval.bcls) = get_bool_cls((yyvsp[0].query), BC_MUST); }
     break;
 
   case 9:
-#line 108 "src/q_parser.y"
+#line 111 "src/q_parser.y"
     { (yyval.bcls) = get_bool_cls((yyvsp[0].query), BC_MUST_NOT); }
     break;
 
   case 10:
-#line 109 "src/q_parser.y"
+#line 112 "src/q_parser.y"
     { (yyval.bcls) = get_bool_cls((yyvsp[0].query), BC_SHOULD); }
     break;
 
   case 12:
-#line 112 "src/q_parser.y"
+#line 115 "src/q_parser.y"
     { if ((yyvsp[-2].query)) sscanf((yyvsp[0].str),"%f",&((yyvsp[-2].query)->boost)); (yyval.query)=(yyvsp[-2].query); }
     break;
 
   case 14:
-#line 115 "src/q_parser.y"
+#line 118 "src/q_parser.y"
     { (yyval.query) = get_bool_q((yyvsp[-1].bclss)); }
     break;
 
   case 19:
-#line 121 "src/q_parser.y"
+#line 124 "src/q_parser.y"
     { FLDS((yyval.query), get_term_q(qp, field, (yyvsp[0].str))); }
     break;
 
   case 20:
-#line 122 "src/q_parser.y"
+#line 125 "src/q_parser.y"
     { FLDS((yyval.query), get_fuzzy_q(qp, field, (yyvsp[-2].str), (yyvsp[0].str))); }
     break;
 
   case 21:
-#line 123 "src/q_parser.y"
+#line 126 "src/q_parser.y"
     { FLDS((yyval.query), get_fuzzy_q(qp, field, (yyvsp[-1].str), NULL)); }
     break;
 
   case 22:
-#line 125 "src/q_parser.y"
+#line 128 "src/q_parser.y"
     { FLDS((yyval.query), get_wild_q(qp, field, (yyvsp[0].str))); }
     break;
 
   case 23:
-#line 127 "src/q_parser.y"
+#line 130 "src/q_parser.y"
     { qp->fields = qp->def_fields; }
     break;
 
   case 24:
-#line 128 "src/q_parser.y"
+#line 131 "src/q_parser.y"
     { (yyval.query) = (yyvsp[-1].query); }
     break;
 
   case 25:
-#line 129 "src/q_parser.y"
+#line 132 "src/q_parser.y"
     { qp->fields = qp->all_fields; }
     break;
 
   case 26:
-#line 129 "src/q_parser.y"
+#line 132 "src/q_parser.y"
     {qp->fields = qp->def_fields;}
     break;
 
   case 27:
-#line 130 "src/q_parser.y"
+#line 133 "src/q_parser.y"
     { (yyval.query) = (yyvsp[-1].query); }
     break;
 
   case 28:
-#line 132 "src/q_parser.y"
+#line 135 "src/q_parser.y"
     { (yyval.hashset) = first_field(qp, (yyvsp[0].str)); }
     break;
 
   case 29:
-#line 133 "src/q_parser.y"
+#line 136 "src/q_parser.y"
     { (yyval.hashset) = add_field(qp, (yyvsp[0].str));}
     break;
 
   case 30:
-#line 135 "src/q_parser.y"
+#line 138 "src/q_parser.y"
     { (yyval.query) = get_phrase_q(qp, (yyvsp[-1].phrase), NULL); }
     break;
 
   case 31:
-#line 136 "src/q_parser.y"
+#line 139 "src/q_parser.y"
     { (yyval.query) = get_phrase_q(qp, (yyvsp[-3].phrase), (yyvsp[0].str)); }
     break;
 
   case 32:
-#line 137 "src/q_parser.y"
+#line 140 "src/q_parser.y"
     { (yyval.query) = NULL; }
     break;
 
   case 33:
-#line 138 "src/q_parser.y"
+#line 141 "src/q_parser.y"
     { (yyval.query) = NULL; }
     break;
 
   case 34:
-#line 140 "src/q_parser.y"
+#line 143 "src/q_parser.y"
     { (yyval.phrase) = ph_first_word((yyvsp[0].str)); }
     break;
 
   case 35:
-#line 141 "src/q_parser.y"
+#line 144 "src/q_parser.y"
     { (yyval.phrase) = ph_first_word(NULL); }
     break;
 
   case 36:
-#line 142 "src/q_parser.y"
+#line 145 "src/q_parser.y"
     { (yyval.phrase) = ph_add_word((yyvsp[-1].phrase), (yyvsp[0].str)); }
     break;
 
   case 37:
-#line 143 "src/q_parser.y"
+#line 146 "src/q_parser.y"
     { (yyval.phrase) = ph_add_word((yyvsp[-2].phrase), NULL); }
     break;
 
   case 38:
-#line 144 "src/q_parser.y"
+#line 147 "src/q_parser.y"
     { (yyval.phrase) = ph_add_multi_word((yyvsp[-2].phrase), (yyvsp[0].str));  }
     break;
 
   case 39:
-#line 146 "src/q_parser.y"
+#line 149 "src/q_parser.y"
     { FLDS((yyval.query), get_r_q(qp, field, (yyvsp[-2].str),  (yyvsp[-1].str),  true,  true)); }
     break;
 
   case 40:
-#line 147 "src/q_parser.y"
+#line 150 "src/q_parser.y"
     { FLDS((yyval.query), get_r_q(qp, field, (yyvsp[-2].str),  (yyvsp[-1].str),  true,  false)); }
     break;
 
   case 41:
-#line 148 "src/q_parser.y"
+#line 151 "src/q_parser.y"
     { FLDS((yyval.query), get_r_q(qp, field, (yyvsp[-2].str),  (yyvsp[-1].str),  false, true)); }
     break;
 
   case 42:
-#line 149 "src/q_parser.y"
+#line 152 "src/q_parser.y"
     { FLDS((yyval.query), get_r_q(qp, field, (yyvsp[-2].str),  (yyvsp[-1].str),  false, false)); }
     break;
 
   case 43:
-#line 150 "src/q_parser.y"
+#line 153 "src/q_parser.y"
     { FLDS((yyval.query), get_r_q(qp, field, NULL,(yyvsp[-1].str),  false, false)); }
     break;
 
   case 44:
-#line 151 "src/q_parser.y"
+#line 154 "src/q_parser.y"
     { FLDS((yyval.query), get_r_q(qp, field, NULL,(yyvsp[-1].str),  false, true)); }
     break;
 
   case 45:
-#line 152 "src/q_parser.y"
+#line 155 "src/q_parser.y"
     { FLDS((yyval.query), get_r_q(qp, field, (yyvsp[-1].str),  NULL,true,  false)); }
     break;
 
   case 46:
-#line 153 "src/q_parser.y"
+#line 156 "src/q_parser.y"
     { FLDS((yyval.query), get_r_q(qp, field, (yyvsp[-1].str),  NULL,false, false)); }
     break;
 
   case 47:
-#line 154 "src/q_parser.y"
+#line 157 "src/q_parser.y"
     { FLDS((yyval.query), get_r_q(qp, field, NULL,(yyvsp[0].str),  false, false)); }
     break;
 
   case 48:
-#line 155 "src/q_parser.y"
+#line 158 "src/q_parser.y"
     { FLDS((yyval.query), get_r_q(qp, field, NULL,(yyvsp[0].str),  false, true)); }
     break;
 
   case 49:
-#line 156 "src/q_parser.y"
+#line 159 "src/q_parser.y"
     { FLDS((yyval.query), get_r_q(qp, field, (yyvsp[0].str),  NULL,true,  false)); }
     break;
 
   case 50:
-#line 157 "src/q_parser.y"
+#line 160 "src/q_parser.y"
     { FLDS((yyval.query), get_r_q(qp, field, (yyvsp[0].str),  NULL,false, false)); }
     break;
 
@@ -1468,7 +1471,7 @@ yyreduce:
     }
 
 /* Line 1126 of yacc.c.  */
-#line 1472 "y.tab.c"
+#line 1475 "y.tab.c"
 
   yyvsp -= yylen;
   yyssp -= yylen;
@@ -1736,7 +1739,7 @@ yyreturn:
 }
 
 
-#line 159 "src/q_parser.y"
+#line 162 "src/q_parser.y"
 
 
 const char *special_char = "&:()[]{}!\"~^|<>=*?+-";
@@ -2009,11 +2012,11 @@ static Query *get_fuzzy_q(QParser *qp, char *field, char *word, char *slop_str)
     }
     else {
         /* it only makes sense to find one term in a fuzzy query */
-        float slop = DEF_MIN_SIM;
+        float slop = qp_default_fuzzy_min_sim;
         if (slop_str) {
             sscanf(slop_str, "%f", &slop);
         }
-        q = fuzq_new_conf(field, token->text, slop, DEF_PRE_LEN,
+        q = fuzq_new_conf(field, token->text, slop, qp_default_fuzzy_pre_len,
                           qp->max_clauses);
     }
     return q;

data/ext/r_qparser.c

@@ -503,3 +503,4 @@ Init_QueryParser(void)
 
     Init_QueryParseException();
 }
+

data/ext/r_search.c

@@ -1240,6 +1240,32 @@ frt_fq_init(int argc, VALUE *argv, VALUE self)
     return self;
 }
 
+/*
+ *  call-seq:
+ *     FuzzyQuery.prefix_length -> prefix_length
+ *
+ *  Get the +:prefix_length+ for the query.
+ */
+static VALUE
+frt_fq_pre_len(VALUE self)
+{
+    GET_Q();
+    return INT2FIX(((FuzzyQuery *)q)->pre_len);
+}
+
+/*
+ *  call-seq:
+ *     FuzzyQuery.min_similarity -> min_similarity
+ *
+ *  Get the +:min_similarity+ for the query.
+ */
+static VALUE
+frt_fq_min_sim(VALUE self)
+{
+    GET_Q();
+    return rb_float_new((double)((FuzzyQuery *)q)->min_sim);
+}
+
 /*
  *  call-seq:
  *     FuzzyQuery.default_min_similarity -> number
@@ -1252,6 +1278,7 @@ frt_fq_get_dms(VALUE self)
     return rb_cvar_get(cFuzzyQuery, id_default_min_similarity);
 }
 
+extern float qp_default_fuzzy_min_sim;
 /*
  *  call-seq:
  *     FuzzyQuery.default_min_similarity = min_sim -> min_sim
@@ -1269,6 +1296,7 @@ frt_fq_set_dms(VALUE self, VALUE val)
         rb_raise(rb_eArgError,
                  "%f < 0.0. :min_similarity must be > 0.0", min_sim);
     }
+    qp_default_fuzzy_min_sim = (float)min_sim;
     rb_cvar_set(cFuzzyQuery, id_default_min_similarity, val, Qfalse);
     return val;
 }
@@ -1285,6 +1313,7 @@ frt_fq_get_dpl(VALUE self)
     return rb_cvar_get(cFuzzyQuery, id_default_prefix_length);
 }
 
+extern int qp_default_fuzzy_pre_len;
 /*
  *  call-seq:
  *     FuzzyQuery.default_prefix_length = prefix_length -> prefix_length
@@ -1294,15 +1323,17 @@ frt_fq_get_dpl(VALUE self)
 static VALUE
 frt_fq_set_dpl(VALUE self, VALUE val)
 {
-    int pre_len = INT2FIX(val);
+    int pre_len = FIX2INT(val);
     if (pre_len < 0) {
         rb_raise(rb_eArgError,
                  "%d < 0. :prefix_length must be >= 0", pre_len);
     }
+    qp_default_fuzzy_pre_len = pre_len;
     rb_cvar_set(cFuzzyQuery, id_default_prefix_length, val, Qfalse);
     return val;
 }
 
+
 /****************************************************************************
  *
  * MatchAllQuery Methods
@@ -3159,7 +3190,9 @@ Init_FuzzyQuery(void)
     rb_define_singleton_method(cFuzzyQuery, "default_prefix_length=",
                                frt_fq_set_dpl, 1);
 
-    rb_define_method(cFuzzyQuery, "initialize", frt_fq_init, -1);
+    rb_define_method(cFuzzyQuery, "initialize",     frt_fq_init, -1);
+    rb_define_method(cFuzzyQuery, "prefix_length",  frt_fq_pre_len, 0);
+    rb_define_method(cFuzzyQuery, "min_similarity", frt_fq_min_sim, 0);
 }
 
 /*

data/lib/ferret/index.rb

@@ -684,7 +684,7 @@ module Ferret::Index
             @qp = Ferret::QueryParser.new(@options)
           end
           # we need to set this ever time, in case a new field has been added
-          @qp.fields = @reader.field_names
+          @qp.fields = @reader.field_names unless options[:all_fields]
           query = @qp.parse(query)
         end
         return query

data/lib/ferret_version.rb

@@ -1,3 +1,3 @@
 module Ferret
-  VERSION = '0.10.5'
+  VERSION = '0.10.6'
 end

metadata

@@ -3,8 +3,8 @@ rubygems_version: 0.8.11
 specification_version: 1
 name: ferret
 version: !ruby/object:Gem::Version 
-  version: 0.10.5
-date: 2006-09-19 00:00:00 +09:00
+  version: 0.10.6
+date: 2006-09-21 00:00:00 +09:00
 summary: Ruby indexing library.
 require_paths: 
 - lib