ferret 0.3.0 → 0.3.1

data/ext/index_io.c

@@ -170,10 +170,10 @@ VALUE
 frt_indexin_read_int(VALUE self)
 {
   GET_MY_BUF;
-  return LONG2NUM(((long)frt_read_byte(self, my_buf) << 24) |
-                  ((long)frt_read_byte(self, my_buf) << 16) |
-                  ((long)frt_read_byte(self, my_buf) << 8) |
-                   (long)frt_read_byte(self, my_buf));
+  return LONG2NUM(((int)frt_read_byte(self, my_buf) << 24) |
+                  ((int)frt_read_byte(self, my_buf) << 16) |
+                  ((int)frt_read_byte(self, my_buf) << 8) |
+                   (int)frt_read_byte(self, my_buf));
 }
 
 VALUE
@@ -194,10 +194,10 @@ static VALUE
 frt_indexin_read_uint(VALUE self)
 {
   GET_MY_BUF;
-  return ULONG2NUM(((unsigned long)frt_read_byte(self, my_buf) << 24) |
-                   ((unsigned long)frt_read_byte(self, my_buf) << 16) |
-                   ((unsigned long)frt_read_byte(self, my_buf) << 8) |
-                    (unsigned long)frt_read_byte(self, my_buf));
+  return ULONG2NUM(((unsigned int)frt_read_byte(self, my_buf) << 24) |
+                   ((unsigned int)frt_read_byte(self, my_buf) << 16) |
+                   ((unsigned int)frt_read_byte(self, my_buf) << 8) |
+                    (unsigned int)frt_read_byte(self, my_buf));
 }
 
 static VALUE

data/ext/segment_term_enum.c

@@ -35,6 +35,7 @@ static VALUE
 frt_ste_init(VALUE self, VALUE input, VALUE field_infos, VALUE is_index)
 {
   int first_int;
+  VALUE rsize;
   GET_STE;
   ste->is_index = RTEST(is_index);
   ste->input = input;
@@ -63,7 +64,8 @@ frt_ste_init(VALUE self, VALUE input, VALUE field_infos, VALUE is_index)
   } else {
     // we have a format version number
     ste->format = first_int;
-    ste->size = FIX2INT(frt_indexin_read_long(input));  // read the size
+    rsize = frt_indexin_read_long(input);
+    ste->size = NUM2INT(rsize);  // read the size
     
     if (ste->format == -1) {
       if (!ste->is_index) {

data/lib/ferret.rb

@@ -22,7 +22,7 @@
 #++
 # :include: ../TUTORIAL
 module Ferret
-  VERSION = '0.3.0'
+  VERSION = '0.3.1'
 end
 
 require 'ferret/utils'

data/lib/ferret/index/index.rb

@@ -335,18 +335,20 @@ module Ferret::Index
     # id:: The number of the document to delete
     def delete(id)
       @dir.synchronize do
+        cnt = 0
         ensure_reader_open()
         if id.is_a?(String)
           t = Term.new("id", id.to_s)
-          return @reader.delete_docs_with_term(t)
+          cnt = @reader.delete_docs_with_term(t)
         elsif id.is_a?(Term)
-          return @reader.delete_docs_with_term(id)
+          cnt = @reader.delete_docs_with_term(id)
         elsif id.is_a?(Integer)
-          return @reader.delete(id)
+          cnt = @reader.delete(id)
         else
           raise ArgumentError, "Cannot delete for id of type #{id.class}"
         end
         flush() if @auto_flush
+        return cnt
       end
     end
 
@@ -485,7 +487,7 @@ module Ferret::Index
       @dir.synchronize do
         ensure_writer_open()
         @writer.optimize()
-        @modified = true
+        flush()
       end
     end
 

data/lib/ferret/index/segment_merger.rb

@@ -242,7 +242,7 @@ module Ferret::Index
       skip_pointer = write_skip()
 
       if (df > 0) 
-        # add an enbegin to the dictionary with pointers to prox and freq files
+        # add an entry to the dictionary with pointers to prox and freq files
         @term_info.set_values!(df, freq_pointer, prox_pointer, (skip_pointer - freq_pointer))
         @term_infos_writer.add(smis[0].term_buffer.term, @term_info)
       end

data/lib/ferret/search/disjunction_sum_scorer.rb

@@ -93,7 +93,7 @@ module Ferret::Search
     # Repeat until at least the minimum number of subscorers match on the same
     # document and all subscorers are after that document or are exhausted.
     # 
-    # On enbegin the +@scorer_queue+ has at least +@minimum_nr_matchers+
+    # On entry the +@scorer_queue+ has at least +@minimum_nr_matchers+
     # available. At least the scorer with the minimum document number will be advanced.
     # returns:: true iff there is a match.
     # 

data/test/unit/index/tc_index.rb

@@ -459,6 +459,12 @@ class IndexTest < Test::Unit::TestCase
         index1 << doc
         index2 << doc
       end
+      5.times do |i|
+        index1.delete(i)
+        index2.delete(i + 5)
+      end
+      index1.optimize
+      index2 << "thirteen"
     rescue Exception => e
       assert(false, "This should not cause an error when auto flush has been set")
     end

data/test/unit/search/tc_index_searcher.rb

@@ -65,6 +65,9 @@ class IndexSearcherTest < Test::Unit::TestCase
     tq = TermQuery.new(Term.new("field", "word2"));
     tq.boost = 100
     check_hits(tq, [1,4,8])
+    #puts @is.explain(tq, 1)
+    #puts @is.explain(tq, 4)
+    #puts @is.explain(tq, 8)
 
     tq = TermQuery.new(Term.new("field", "2342"));
     check_hits(tq, [])

metadata

@@ -3,8 +3,8 @@ rubygems_version: 0.8.11
 specification_version: 1
 name: ferret
 version: !ruby/object:Gem::Version 
-  version: 0.3.0
-date: 2005-12-02 00:00:00 +09:00
+  version: 0.3.1
+date: 2005-12-08 00:00:00 +09:00
 summary: Ruby indexing library.
 require_paths: 
   - lib
@@ -52,8 +52,8 @@ files:
   - ext/dummy.exe
   - ext/segment_term_enum.c
   - ext/terminfo.c
-  - ext/term_infos_reader.c
   - ext/ferret_ext.so
+  - ext/term_infos_reader.c
   - ext/similarity.c
   - lib/ferret.rb
   - lib/ferret/analysis.rb