sdsykes-ferret 0.11.6.19

data/test/unit/utils/tc_number_tools.rb

@@ -0,0 +1,117 @@
+require File.dirname(__FILE__) + "/../../test_helper"
+require 'ferret/number_tools'
+
+
+class NumberToolsTest < Test::Unit::TestCase
+  include Ferret::Utils
+
+  def test_to_i_lex_near_zero()
+    (-10..10).each do |num|
+      assert(num.to_s_lex > (num-1).to_s_lex,
+             "Strings should sort correctly but " +
+             "#{num.to_s_lex} <= #{(num-1).to_s_lex}")
+      assert_equal(num, num.to_s_lex.to_i_lex)
+    end
+  end
+
+  def test_to_i_pad_near_zero()
+    (1..10).each do |num|
+      assert(num.to_s_pad(3) > (num-1).to_s_pad(3),
+             "Strings should sort correctly but " +
+             "#{num.to_s_pad(3)} <= #{(num-1).to_s_pad(3)}")
+      assert_equal(num, num.to_s_pad(3).to_i)
+    end
+  end
+
+  def test_to_i_lex_larger_numbers
+    100.times do
+      num1 = rand(10000000000000000000000000000000000)
+      num2 = rand(10000000000000000000000000000000000)
+      num1 *= -1 if rand(2) == 0
+      num2 *= -1 if rand(2) == 0
+
+      assert_equal(num1, num1.to_s_lex.to_i_lex)
+      assert_equal(num2, num2.to_s_lex.to_i_lex)
+      assert_equal(num1 < num2, num1.to_s_lex < num2.to_s_lex, 
+                   "Strings should sort correctly but " +
+                   "#{num1} < #{num2} == #{num1 < num2} but " +
+                   "#{num1.to_s_lex} < #{num2.to_s_lex} == " +
+                   "#{num1.to_s_lex < num2.to_s_lex}")
+    end
+  end
+
+  def test_to_i_pad
+    100.times do
+      num1 = rand(10000000000000000000000000000000000)
+      num2 = rand(10000000000000000000000000000000000)
+      assert_equal(num1, num1.to_s_pad(35).to_i)
+      assert_equal(num2, num2.to_s_pad(35).to_i)
+      assert_equal(num1 < num2, num1.to_s_pad(35) < num2.to_s_pad(35), 
+                   "Strings should sort correctly but " +
+                   "#{num1} < #{num2} == #{num1 < num2} but " +
+                   "#{num1.to_s_pad(35)} < #{num2.to_s_pad(35)} == " +
+                   "#{num1.to_s_pad(35) < num2.to_s_pad(35)}")
+    end
+  end
+  
+  def test_time_to_s_lex
+    t_num = Time.now.to_i - 365*24*60*60 # prevent range error
+
+    10.times do
+      t1 = Time.now - rand(t_num)
+      t2 = Time.now - rand(t_num)
+      assert_equal(t1.to_s, t1.to_s_lex(:second).to_time_lex.to_s)
+      assert_equal(t2.to_s, t2.to_s_lex(:second).to_time_lex.to_s)
+      [:year, :month, :day, :hour, :minute, :second, :millisecond].each do |prec|
+        t1_x = t1.to_s_lex(prec).to_time_lex
+        t2_x = t2.to_s_lex(prec).to_time_lex
+        assert_equal(t1_x < t2_x, t1.to_s_lex(prec) < t2.to_s_lex(prec), 
+                     "Strings should sort correctly but " +
+                     "#{t1_x} < #{t2_x} == #{t1_x < t2_x} but " +
+                     "#{t1.to_s_lex(prec)} < #{t2.to_s_lex(prec)} == " +
+                     "#{t1.to_s_lex(prec) < t2.to_s_lex(prec)}")
+      end
+    end
+  end
+
+  def test_date_to_s_lex
+    10.times do
+      d1 = Date.civil(rand(2200), rand(12) + 1, rand(28) + 1)
+      d2 = Date.civil(rand(2200), rand(12) + 1, rand(28) + 1)
+      assert_equal(d1.to_s, d1.to_s_lex(:day).to_date_lex.to_s)
+      assert_equal(d2.to_s, d2.to_s_lex(:day).to_date_lex.to_s)
+      [:year, :month, :day].each do |prec|
+        d1_x = d1.to_s_lex(prec).to_date_lex
+        d2_x = d2.to_s_lex(prec).to_date_lex
+        assert_equal(d1_x < d2_x, d1.to_s_lex(prec) < d2.to_s_lex(prec), 
+                     "Strings should sort correctly but " +
+                     "#{d1_x} < #{d2_x} == #{d1_x < d2_x} but " +
+                     "#{d1.to_s_lex(prec)} < #{d2.to_s_lex(prec)} == " +
+                     "#{d1.to_s_lex(prec) < d2.to_s_lex(prec)}")
+      end
+
+    end
+  end
+
+  def test_date_time_to_s_lex
+    10.times do
+      d1 = "#{rand(600) + 1600}-#{rand(12)+1}-#{rand(28)+1} " +
+           "#{rand(24)}:#{rand(60)}:#{rand(60)}"
+      d2 = "#{rand(600) + 1600}-#{rand(12)+1}-#{rand(28)+1} " +
+           "#{rand(24)}:#{rand(60)}:#{rand(60)}"
+      d1 = DateTime.strptime(d1, "%Y-%m-%d %H:%M:%S")
+      d2 = DateTime.strptime(d2, "%Y-%m-%d %H:%M:%S")
+      assert_equal(d1.to_s, d1.to_s_lex(:second).to_date_time_lex.to_s)
+      assert_equal(d2.to_s, d2.to_s_lex(:second).to_date_time_lex.to_s)
+      [:year, :month, :day, :hour, :minute, :second].each do |prec|
+        d1_x = d1.to_s_lex(prec).to_date_lex
+        d2_x = d2.to_s_lex(prec).to_date_lex
+        assert_equal(d1_x < d2_x, d1.to_s_lex(prec) < d2.to_s_lex(prec), 
+                     "Strings should sort correctly but " +
+                     "#{d1_x} < #{d2_x} == #{d1_x < d2_x} but " +
+                     "#{d1.to_s_lex(prec)} < #{d2.to_s_lex(prec)} == " +
+                     "#{d1.to_s_lex(prec) < d2.to_s_lex(prec)}")
+      end
+    end
+  end
+end

data/test/unit/utils/tc_priority_queue.rb

@@ -0,0 +1,106 @@
+require File.dirname(__FILE__) + "/../../test_helper"
+
+
+class PriorityQueueTest < Test::Unit::TestCase
+  include Ferret::Utils
+
+  PQ_STRESS_SIZE = 1000
+
+  def test_pq()
+    pq = PriorityQueue.new(4)
+    assert_equal(0, pq.size)
+    assert_equal(4, pq.capacity)
+    pq.insert("bword")
+    assert_equal(1, pq.size)
+    assert_equal("bword", pq.top)
+
+    pq.insert("cword")
+    assert_equal(2, pq.size)
+    assert_equal("bword", pq.top)
+
+    pq << "dword"
+    assert_equal(3, pq.size)
+    assert_equal("bword", pq.top)
+    
+    pq << "eword"
+    assert_equal(4, pq.size)
+    assert_equal("bword", pq.top)
+
+    pq << "aword"
+    assert_equal(4, pq.size)
+    assert_equal("bword", pq.top, "aword < all other elements so ignore")
+
+    pq << "fword"
+    assert_equal(4, pq.size)
+    assert_equal("cword", pq.top, "bword got pushed off the bottom of the queue")
+
+    assert_equal("cword", pq.pop())
+    assert_equal(3, pq.size)
+    assert_equal("dword", pq.pop())
+    assert_equal(2, pq.size)
+    assert_equal("eword", pq.pop())
+    assert_equal(1, pq.size)
+    assert_equal("fword", pq.pop())
+    assert_equal(0, pq.size)
+    assert_nil(pq.top)
+    assert_nil(pq.pop)
+  end
+
+  def test_pq_clear()
+    pq = PriorityQueue.new(3)
+    pq << "word1"
+    pq << "word2"
+    pq << "word3"
+    assert_equal(3, pq.size)
+    pq.clear()
+    assert_equal(0, pq.size)
+    assert_nil(pq.top)
+    assert_nil(pq.pop)
+  end
+
+  #define PQ_STRESS_SIZE 1000
+  def test_stress_pq
+    pq = PriorityQueue.new(PQ_STRESS_SIZE)
+    PQ_STRESS_SIZE.times do
+      pq.insert("<#{rand(PQ_STRESS_SIZE)}>")
+    end
+
+    prev = pq.pop()
+    (PQ_STRESS_SIZE - 1).times do
+      curr = pq.pop()
+      assert(prev <= curr, "#{prev} should be less than #{curr}")
+      prev = curr
+    end
+    pq.clear()
+  end
+
+  def test_pq_block
+    pq = PriorityQueue.new(21) {|a, b| a > b}
+    100.times do
+      pq.insert("<#{rand(50)}>")
+    end
+
+    prev = pq.pop()
+    20.times do
+      curr = pq.pop()
+      assert(prev >= curr, "#{prev} should be greater than #{curr}")
+      prev = curr
+    end
+    assert_equal 0, pq.size 
+  end
+
+  def test_pq_proc
+    pq = PriorityQueue.new({:less_than => lambda {|a, b| a.size > b.size}, :capacity => 21})
+    100.times do
+      pq.insert("x" * rand(50))
+    end
+
+    prev = pq.pop()
+    20.times do
+      curr = pq.pop()
+      assert(prev.size >= curr.size, "#{prev} should be greater than #{curr}")
+      prev = curr
+    end
+    assert_equal 0, pq.size 
+  end
+end

metadata

@@ -0,0 +1,285 @@
+--- !ruby/object:Gem::Specification 
+name: sdsykes-ferret
+version: !ruby/object:Gem::Version 
+  prerelease: false
+  segments: 
+  - 0
+  - 11
+  - 6
+  - 19
+  version: 0.11.6.19
+platform: ruby
+authors: 
+- David Balmain
+autorequire: ferret
+bindir: bin
+cert_chain: []
+
+date: 2007-11-28 00:00:00 +02:00
+default_executable: ferret-browser
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  name: rake
+  prerelease: false
+  requirement: &id001 !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">"
+      - !ruby/object:Gem::Version 
+        segments: 
+        - 0
+        - 0
+        - 0
+        version: 0.0.0
+  type: :runtime
+  version_requirements: *id001
+description: Ferret is a port of the Java Lucene project. It is a powerful indexing and search library.
+email: dbalmain@gmail.com
+executables: 
+- ferret-browser
+extensions: 
+- ext/extconf.rb
+extra_rdoc_files: 
+- README
+- TODO
+- TUTORIAL
+- MIT-LICENSE
+- ext/r_index.c
+- ext/r_analysis.c
+- ext/r_utils.c
+- ext/r_search.c
+- ext/r_qparser.c
+- ext/r_store.c
+- ext/ferret.c
+files: 
+- setup.rb
+- TODO
+- TUTORIAL
+- Rakefile
+- CHANGELOG
+- README
+- MIT-LICENSE
+- ext/lang.h
+- ext/q_filtered_query.c
+- ext/stem_ISO_8859_1_spanish.h
+- ext/stem_ISO_8859_1_spanish.c
+- ext/global.c
+- ext/stem_UTF_8_italian.c
+- ext/modules.h
+- ext/stem_UTF_8_portuguese.c
+- ext/stem_ISO_8859_1_dutch.c
+- ext/store.h
+- ext/stem_UTF_8_spanish.h
+- ext/array.c
+- ext/stem_ISO_8859_1_finnish.c
+- ext/stem_ISO_8859_1_finnish.h
+- ext/stem_UTF_8_finnish.h
+- ext/stem_ISO_8859_1_italian.h
+- ext/analysis.h
+- ext/q_wildcard.c
+- ext/except.h
+- ext/stem_UTF_8_english.c
+- ext/stem_ISO_8859_1_german.h
+- ext/api.c
+- ext/r_index.c
+- ext/hashset.c
+- ext/stem_ISO_8859_1_german.c
+- ext/stem_ISO_8859_1_swedish.h
+- ext/utilities.c
+- ext/stem_UTF_8_spanish.c
+- ext/stem_UTF_8_dutch.h
+- ext/stem_ISO_8859_1_danish.c
+- ext/q_match_all.c
+- ext/stem_UTF_8_german.c
+- ext/compound_io.c
+- ext/hash.h
+- ext/q_prefix.c
+- ext/stopwords.c
+- ext/stem_ISO_8859_1_italian.c
+- ext/bitvector.h
+- ext/stem_ISO_8859_1_dutch.h
+- ext/bitvector.c
+- ext/r_analysis.c
+- ext/mempool.h
+- ext/config.h
+- ext/stem_UTF_8_german.h
+- ext/stem_UTF_8_porter.c
+- ext/stem_ISO_8859_1_norwegian.c
+- ext/threading.h
+- ext/stem_UTF_8_norwegian.c
+- ext/stem_ISO_8859_1_swedish.c
+- ext/stem_UTF_8_portuguese.h
+- ext/search.h
+- ext/hash.c
+- ext/stem_UTF_8_swedish.c
+- ext/fs_store.c
+- ext/stem_UTF_8_french.h
+- ext/stem_UTF_8_finnish.c
+- ext/stem_UTF_8_danish.c
+- ext/stem_UTF_8_porter.h
+- ext/ferret.c
+- ext/term_vectors.c
+- ext/posh.c
+- ext/stem_ISO_8859_1_norwegian.h
+- ext/helper.c
+- ext/mempool.c
+- ext/r_utils.c
+- ext/document.c
+- ext/stem_KOI8_R_russian.c
+- ext/stem_KOI8_R_russian.h
+- ext/r_search.c
+- ext/libstemmer.c
+- ext/api.h
+- ext/stem_ISO_8859_1_portuguese.c
+- ext/r_qparser.c
+- ext/multimapper.h
+- ext/stem_ISO_8859_1_french.c
+- ext/stem_UTF_8_danish.h
+- ext/stem_ISO_8859_1_portuguese.h
+- ext/hashset.h
+- ext/q_parser.c
+- ext/analysis.c
+- ext/r_store.c
+- ext/stem_UTF_8_swedish.h
+- ext/stem_UTF_8_italian.h
+- ext/q_phrase.c
+- ext/q_term.c
+- ext/priorityqueue.h
+- ext/libstemmer.h
+- ext/filter.c
+- ext/q_span.c
+- ext/multimapper.c
+- ext/index.h
+- ext/helper.h
+- ext/similarity.h
+- ext/stem_UTF_8_french.c
+- ext/header.h
+- ext/index.c
+- ext/posh.h
+- ext/document.h
+- ext/similarity.c
+- ext/stem_UTF_8_russian.c
+- ext/win32.h
+- ext/q_fuzzy.c
+- ext/search.c
+- ext/stem_ISO_8859_1_porter.c
+- ext/stem_UTF_8_russian.h
+- ext/ram_store.c
+- ext/stem_ISO_8859_1_porter.h
+- ext/except.c
+- ext/q_range.c
+- ext/sort.c
+- ext/q_multi_term.c
+- ext/q_const_score.c
+- ext/q_boolean.c
+- ext/stem_UTF_8_norwegian.h
+- ext/priorityqueue.c
+- ext/array.h
+- ext/stem_ISO_8859_1_danish.h
+- ext/store.c
+- ext/stem_UTF_8_english.h
+- ext/stem_ISO_8859_1_english.h
+- ext/stem_ISO_8859_1_french.h
+- ext/stem_ISO_8859_1_english.c
+- ext/ferret.h
+- ext/global.h
+- ext/stem_UTF_8_dutch.c
+- ext/inc/lang.h
+- ext/inc/threading.h
+- lib/ferret_version.rb
+- lib/ferret/field_infos.rb
+- lib/ferret/browser/webrick.rb
+- lib/ferret/browser.rb
+- lib/ferret/document.rb
+- lib/ferret/index.rb
+- lib/ferret/number_tools.rb
+- lib/ferret.rb
+- lib/ferret/browser/views/home/index.rhtml
+- lib/ferret/browser/views/help/index.rhtml
+- lib/ferret/browser/views/document/list.rhtml
+- lib/ferret/browser/views/document/show.rhtml
+- lib/ferret/browser/views/term/index.rhtml
+- lib/ferret/browser/views/term/termdocs.rhtml
+- lib/ferret/browser/views/error/index.rhtml
+- lib/ferret/browser/views/layout.rhtml
+- lib/ferret/browser/views/term-vector/index.rhtml
+- lib/ferret/browser/s/style.css
+- lib/ferret/browser/s/global.js
+- test/unit/index/th_doc.rb
+- test/unit/index/tc_index_writer.rb
+- test/unit/index/tc_index.rb
+- test/unit/index/tc_index_reader.rb
+- test/unit/ts_index.rb
+- test/unit/tc_document.rb
+- test/unit/ts_query_parser.rb
+- test/unit/utils/tc_bit_vector.rb
+- test/unit/utils/tc_priority_queue.rb
+- test/unit/utils/tc_number_tools.rb
+- test/unit/ts_analysis.rb
+- test/unit/query_parser/tc_query_parser.rb
+- test/unit/search/tc_search_and_sort.rb
+- test/unit/search/tc_sort.rb
+- test/unit/search/tc_index_searcher.rb
+- test/unit/search/tc_sort_field.rb
+- test/unit/search/tm_searcher.rb
+- test/unit/search/tc_fuzzy_query.rb
+- test/unit/search/tc_filter.rb
+- test/unit/search/tc_multiple_search_requests.rb
+- test/unit/search/tc_spans.rb
+- test/unit/search/tc_multi_searcher.rb
+- test/unit/ts_search.rb
+- test/unit/ts_store.rb
+- test/unit/store/tc_fs_store.rb
+- test/unit/store/tm_store.rb
+- test/unit/store/tm_store_lock.rb
+- test/unit/store/tc_ram_store.rb
+- test/unit/ts_utils.rb
+- test/unit/analysis/tc_token_stream.rb
+- test/unit/analysis/tc_analyzer.rb
+- test/unit/ts_largefile.rb
+- test/unit/largefile/tc_largefile.rb
+- test/test_all.rb
+- test/threading/thread_safety_index_test.rb
+- test/threading/number_to_spoken.rb
+- test/threading/thread_safety_read_write_test.rb
+- test/threading/thread_safety_test.rb
+- test/test_helper.rb
+- bin/ferret-browser
+- ext/extconf.rb
+has_rdoc: true
+homepage: http://ferret.davebalmain.com/trac
+licenses: []
+
+post_install_message: 
+rdoc_options: 
+- --title
+- Ferret -- Ruby Indexer
+- --main
+- README
+- --line-numbers
+- TUTORIAL
+- TODO
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      segments: 
+      - 0
+      version: "0"
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      segments: 
+      - 0
+      version: "0"
+requirements: []
+
+rubyforge_project: ferret
+rubygems_version: 1.3.6
+signing_key: 
+specification_version: 3
+summary: Ruby indexing library.
+test_files: []
+