picolena 0.1.5 → 0.1.6

data/lib/picolena/templates/lib/tasks/index.rake

@@ -1,10 +1,10 @@
 desc 'Ferret index maintenance tasks'
-namespace :index do  
+namespace :index do
   desc 'Clear indexes'
   task :clear => :environment do
     Indexer.clear! :all
   end
-  
+
   desc 'Create index'
   task :create => :environment do
     Indexer.index_every_directory(remove_first=true)
@@ -14,7 +14,12 @@ namespace :index do
   task :update => :environment do
     Indexer.index_every_directory
   end
-  
+
+  desc 'Returns the number of indexed documents'
+  task :size => :environment do
+    puts "#{Indexer.doc_count} documents are currently indexed in #{Picolena::IndexSavePath}"
+  end
+
   # Search index with query "some query" :
   # rake index:search query="some query"
   desc 'Search index'

data/lib/picolena/templates/lib/tasks/install_dependencies.rake

@@ -14,14 +14,14 @@ namespace :install_dependencies do
   # odt2txt package not available on previous versions
   desc 'Install required packages on Ubuntu'
   task :on_ubuntu => :on_debian
-  
+
   desc 'Install required gems and programs on Windows'
   task :on_windows_xp do
     #NOTE: Long way to go before it runs on XP.
     $stderr.puts "Implement me!"
   end
 
-  desc 'Install required gems and packages on Mac Os'  
+  desc 'Install required gems and packages on Mac Os'
   task :on_mac_os do
     $stderr.puts "Implement me!"
   end

data/lib/picolena/templates/lib/tasks/log.rake

@@ -1,6 +1,6 @@
 desc 'Ferret index maintenance tasks'
 
-namespace :log do  
+namespace :log do
   desc 'Parse log files for queries'
   task :queries do
     show_action_regexp=/Processing DocumentsController#show \(for ([\d\.]+) at ([\d\- :]+)\) \[GET\]/

data/lib/picolena/templates/public/.htaccess

@@ -5,14 +5,14 @@ Options +FollowSymLinks +ExecCGI
 
 # If you don't want Rails to look in certain directories,
 # use the following rewrite rules so that Apache won't rewrite certain requests
-# 
+#
 # Example:
 #   RewriteCond %{REQUEST_URI} ^/notrails.*
 #   RewriteRule .* - [L]
 
 # Redirect all requests not available on the filesystem to Rails
 # By default the cgi dispatcher is used which is very slow
-# 
+#
 # For better performance replace the dispatcher with the fastcgi one
 #
 # Example:
@@ -33,7 +33,7 @@ RewriteRule ^(.*)$ dispatch.cgi [QSA,L]
 
 # In case Rails experiences terminal errors
 # Instead of displaying this message you can supply a file here which will be rendered instead
-# 
+#
 # Example:
 #   ErrorDocument 500 /500.html
 

data/lib/picolena/templates/public/stylesheets/style.css

@@ -96,14 +96,14 @@ h1, h2, h3, h4, h5, h6, p, form {
    border-left-color:#696;
    border-right-color:#363;
    border-bottom-color:#363;}
-   
+
 #mainimg input.btn:hover{
    color:#EE8907;}
 
 #mainimg input.text_field{
     border: 2px solid #88b000;
     background: #fff;
-	margin-right: 5px; 
+	margin-right: 5px;
 }
 
 #contentarea hr {

data/lib/picolena/templates/script/spec_server

@@ -23,7 +23,7 @@ module Spec
               active_connections.delete(name)
             end
           end
-        end        
+        end
 
         if ActionController.const_defined?(:Dispatcher)
           dispatcher = ::ActionController::Dispatcher.new($stdout)

data/lib/picolena/templates/spec/controllers/application_controller_spec.rb

@@ -5,12 +5,12 @@ describe ApplicationController do
     get 'access_denied'
     response.headers["Status"].should == "403 Forbidden"
   end
-  
+
   it "should render 'Access denied' text when denying access" do
     get 'access_denied'
     response.body.should == 'Access denied'
   end
-  
+
   it "should flash a warning if given a wrong request" do
     get 'unknown_request'
     response.should be_redirect

data/lib/picolena/templates/spec/controllers/documents_controller_spec.rb

@@ -2,11 +2,11 @@ require File.dirname(__FILE__) + '/../spec_helper'
 
 describe "DocumentsController called from unknown IP" do
   controller_name "documents"
-  
+
   before(:all) do
     @backup=Picolena::WhiteListIPs
   end
-  
+
   it "should deny access" do
     # Displays a warning otherwise
     Picolena.send(:remove_const, :WhiteListIPs) && Picolena::WhiteListIPs=/Something that won't match/
@@ -23,75 +23,75 @@ describe "DocumentsController called from unknown IP" do
   end
 end
 
-describe DocumentsController do  
+describe DocumentsController do
   it "GET 'index' should be succesful" do
     get 'index'
     response.should be_success
   end
-  
+
   it "POST 'check_query' should check query and redirect to show" do
     post 'check_query', {:query => 'basic test'}
     response.should be_redirect
-    response.should redirect_to(document_url('basic test')) 
+    response.should redirect_to(document_url('basic test'))
   end
-  
+
   it "POST 'check_query' should accept . and redirect to show" do
     post 'check_query', {:query => 'basic.test'}
     response.should be_redirect
     response.should redirect_to(:action=>'show', :id=>'basic.test')
   end
-  
+
   it "POST 'check_query' should accept ? and redirect to show" do
     post 'check_query', {:query => '?ric'}
     response.should be_redirect
-    response.should redirect_to(:action=>'show', :id=>'?ric') 
+    response.should redirect_to(:action=>'show', :id=>'?ric')
   end
-  
+
   it "POST 'check_query' should accept empty query but should redirect to index" do
     post 'check_query', {:query => ''}
     response.should be_redirect
     response.should redirect_to(:action=>'index')
   end
-  
+
   it "GET 'show' should find corresponding docs" do
     get 'show', :id=>'forschung an fachhochschulen nachhaltige energietechnik'
     response.should be_success
     assigns[:matching_documents].any?{|doc| doc.filename=="zafh.net.html"}.should be_true
   end
-  
+
   it "GET 'show' should accept * in queries" do
     lambda{get 'show', :id=>'*ric'}.should_not raise_error
     response.should be_success
     assigns[:matching_documents].entries.should_not be_empty
     assigns[:matching_documents].any?{|doc| doc.matching_content.join.starts_with?("<<Éric>> Mößer\n\n\f")}.should be_true
   end
-  
+
   it "GET 'show' should accept ? in queries" do
     lambda{get 'show', :id=>'?ric'}.should_not raise_error(ActionController::RoutingError)
     response.should be_success
     assigns[:matching_documents].entries.should_not be_empty
     assigns[:matching_documents].any?{|doc| doc.filename=="basic.tex"}.should be_true
   end
-    
+
   it "GET 'show' should accept . in queries" do
     lambda{get 'show', :id=>'basic.pdf'}.should_not raise_error(ActionController::RoutingError)
     response.should be_success
     assigns[:matching_documents].entries.should_not be_empty
     assigns[:matching_documents].any?{|doc| doc.matching_content.join.starts_with?("just another content test in a pdf file")}.should be_true
   end
-  
+
   it "GET 'show' should accept combined queries" do
     get 'show', :id=>'test filetype:pdf'
     response.should be_success
     assigns[:matching_documents].entries.should_not be_empty
   end
-  
+
   it "GET 'show' should accept empty query but should redirect to index" do
     lambda{get 'show', :id=>''}.should_not raise_error
     response.should be_success
     assigns[:matching_documents].entries.should be_empty
   end
-  
+
   it "GET 'download' should be successful with correct ID" do
     get 'show', :id=>'basic.pdf'
     response.should be_success
@@ -101,7 +101,7 @@ describe DocumentsController do
     assigns[:document].complete_path == d.complete_path
     response.should be_success
   end
-  
+
   it "GET 'download' should redirect if wrong id" do
     probably_unique_id="Not a document".base26_hash
     get 'download', :id=>probably_unique_id

data/lib/picolena/templates/spec/helpers/application_helper_spec.rb

@@ -1,11 +1,11 @@
 require File.dirname(__FILE__) + '/../spec_helper'
 
 describe ApplicationHelper do
-  
+
   #Delete this example and add some real ones or delete this file
   it "should include the ApplicationHelper" do
     included_modules = self.metaclass.send :included_modules
     included_modules.should include(ApplicationHelper)
   end
-  
+
 end

data/lib/picolena/templates/spec/helpers/documents_helper_spec.rb

@@ -1,11 +1,11 @@
 require File.dirname(__FILE__) + '/../spec_helper'
 
-describe DocumentsHelper do  
+describe DocumentsHelper do
   it "shouldn't raise if matching not in content field"
 
   PlainTextExtractor.supported_extensions.each{|ext|
-    it "should have an icon for .#{ext} filetype" do 
-      icon_for(ext.to_s).should_not be_nil
+    it "should have an icon for .#{ext} filetype" do
+      icon_for(ext).should_not be_nil
     end
   }
 end

data/lib/picolena/templates/spec/models/basic_finder_spec.rb

@@ -8,24 +8,24 @@ describe "Finder without index on disk" do
     @new_index_path=File.join(Dir::tmpdir,'ferret_tst')
     Picolena::IndexSavePath.replace(@new_index_path)
   end
-  
+
   before(:each) do
     Indexer.clear!
   end
-  
+
   it "should create index" do
     Picolena::IndexedDirectories.replace({'spec/test_dirs/indexed/just_one_doc'=>'//justonedoc/'})
     lambda {@finder_with_new_index=Finder.new("test moi")}.should change(Indexer, :index_exists?).from(false).to(true)
     File.exists?(File.join(@new_index_path,'_0.cfs')).should be_true
     Indexer.index.size.should >0
   end
-  
+
   it "should raise if index is still empty after trying to create it" do
     Picolena::IndexedDirectories.replace({'spec/test_dirs/empty_folder'=>'//empty_folder/'})
     lambda {Finder.new("doesn't matter anyway")}.should raise_error(IndexError, "no document found")
     File.exists?(File.join(@new_index_path,'_0.cfs')).should be_false
   end
-  
+
   after(:all) do
     Picolena::IndexedDirectories.replace(@original_indexed_dirs)
     Picolena::IndexSavePath.replace(@original_index_path)
@@ -45,11 +45,11 @@ fields={
   :language           => :language
 }
 
-describe "Basic Finder" do  
+describe "Basic Finder" do
   before(:all) do
     Indexer.index_every_directory(remove_first=true)
   end
-  
+
   it "should accept one parameter as query, and 2 optionals for paginating" do
     lambda {Finder.new}.should raise_error(ArgumentError, "wrong number of arguments (0 for 1)")
     # show first page with 10 results per page
@@ -65,37 +65,37 @@ describe "Basic Finder" do
   it "should return matching documents if executed successfully" do
     finder_with_valid_query=Finder.new("district heating")
     finder_with_valid_query.should respond_to(:matching_documents)
-    
+
     matching_documents=finder_with_valid_query.matching_documents
     matching_documents.should_not be_empty
-    
+
     matching_documents_filenames=matching_documents.collect{|d| d.filename}
     matching_documents_filenames.should include("Simulation of district heating systems for evaluation of real-time control strategies.pdf")
     matching_documents_filenames.should include("Types of malfunction in DH substations.doc")
   end
-  
+
   it "should know if it has been executed" do
     @finder=Finder.new("some query")
     lambda {@finder.execute!}.should change(@finder, :executed?).from(false).to(true)
   end
-    
+
   it "should not warn anything if index is up to date"
-  
+
   it "should warn if index is not up to date"
-  
+
   fields.each_pair do |description,field_name|
     it "should index #{description} as :#{field_name}" do
       Indexer.index.field_infos[field_name].should be_an_instance_of(Ferret::Index::FieldInfo)
     end
   end
-  
+
   it "should know how much time was needed for execution" do
     finder=Finder.new("yet another stupid query")
     finder.executed?.should be_nil
     finder.time_needed.should > 0
     finder.executed?.should be_true
   end
-  
+
   it "should not need more than 100ms to find documents" do
     finder=Finder.new("district heating")
     finder.execute!

data/lib/picolena/templates/spec/models/document_spec.rb

@@ -1,7 +1,6 @@
 require File.dirname(__FILE__) + '/../spec_helper'
 
 basic_pdf_attribute={
-  :size=>9380,
   :dirname=>File.join(RAILS_ROOT, 'spec/test_dirs/indexed/basic'),
   :basename=>'basic',
   :complete_path=>File.join(RAILS_ROOT, '/spec/test_dirs/indexed/basic/basic.pdf'),
@@ -13,18 +12,18 @@ describe Document do
   before(:each) do
     @valid_random_doc=Document.find(:random) rescue Document.new("spec/test_dirs/indexed/basic/basic.pdf")
   end
-  
+
   it "should be an existing file" do
     lambda {Document.new("/patapouf.txt")}.should raise_error(Errno::ENOENT)
     lambda {@valid_random_doc}.should_not raise_error
     lambda {Document.new("spec/test_dirs/not_indexed/Rakefile")}.should_not raise_error(Errno::ENOENT)
   end
-  
+
   it "should belong to an indexed directory" do
     lambda {@valid_random_doc}.should_not raise_error
     lambda {Document.new("spec/test_dirs/not_indexed/Rakefile")}.should raise_error(ArgumentError, "required document is not in indexed directory")
   end
-  
+
   basic_pdf_attribute.each{|attribute,expected_value|
     it "should know its #{attribute}" do
       @valid_random_doc.should respond_to(attribute)
@@ -32,31 +31,24 @@ describe Document do
       @basic_pdf.send(attribute).should == expected_value
     end
   }
-  
-  it "should know which user it belongs to, if specified" do
-    @valid_random_doc.should respond_to(:user)
-    @valid_random_doc.user.should be_nil
-    @valid_random_doc.user="eric"
-    @valid_random_doc.user.should == "eric"
-  end
-  
+
   it "should know its content" do
     another_doc=Document.new("spec/test_dirs/indexed/basic/plain.txt")
     another_doc.content.should == "just a content test\nin a txt file"
   end
- 
+
   it "should know its alias_path" do
     @valid_random_doc.should respond_to(:alias_path)
     @valid_random_doc.alias_path.starts_with?("http://picolena.devjavu.com/browser/trunk/lib/picolena/templates/spec/test_dirs/indexed").should be_true
   end
-  
+
   it "should let finder specify its score" do
     @valid_random_doc.should respond_to(:score)
     @valid_random_doc.score.should be_nil
     @valid_random_doc.score=25
     @valid_random_doc.score.should == 25
   end
-  
+
   it "should let finder specify its matching content" do
     @valid_random_doc.should respond_to(:matching_content)
     @valid_random_doc.matching_content.should be_nil

data/lib/picolena/templates/spec/models/finder_spec.rb

@@ -3,9 +3,20 @@ require File.dirname(__FILE__) + '/../spec_helper'
 def revert_changes!(file,content)
   File.open(file,'w'){|might_have_been_modified|
     might_have_been_modified.write content
-  }  
+  }
 end
 
+
+def matching_document_for(query)
+   # Returns matching document for any given query only if
+   # exactly one document is found.
+   # Specs don't pass otherwise.
+  matching_documents=Finder.new(query).matching_documents
+  matching_documents.size.should == 1
+  matching_documents.first
+end
+
+
 describe Finder do
   before(:all) do
     # SVN doesn't like non-ascii filenames.
@@ -13,7 +24,7 @@ describe Finder do
 
     # To be sure this file has the right content
     revert_changes!("spec/test_dirs/indexed/others/placeholder.txt","Absorption and Adsorption cooling machines!!!")
-    
+
     once_upon_a_time=Time.local(1982,2,16,20,42)
     a_bit_later=Time.local(1983,12,9,9)
     nineties=Time.local(1990)
@@ -23,84 +34,80 @@ describe Finder do
     File.utime(0, nineties, 'spec/test_dirs/indexed/others/placeholder.txt')
     Indexer.index_every_directory(remove_first=true)
   end
-  
+
   it "should find documents according to their basename when specified with basename:query" do
     matching_documents_filename=Finder.new("basename:crossed").matching_documents.collect{|d| d.filename}
     matching_documents_filename.should include("crossed.txt")
     matching_documents_filename.should include("crossed.text")
   end
-  
+
   it "should find documents according to their filename when specified with file:query or filename:query" do
     Finder.new("filename:crossed.text").matching_documents.collect{|d| d.content}.should include("txt inside!")
     Finder.new("file:crossed.txt").matching_documents.collect{|d| d.content}.should include("text inside!")
   end
-  
+
   it "should find documents according to their extension when specified with filetype:query" do
     Finder.new("filetype:odt").matching_documents.should_not be_empty
     Finder.new("filetype:pdf").matching_documents.should_not be_empty
   end
-  
+
   it "should find documents according to their filename/basename/filetype even when unspecified" do
     Finder.new("crossed.text").matching_documents.should_not be_empty
     Finder.new("html").matching_documents.collect{|d| d.filename}.should include("zafh.net.html")
     Finder.new("crossed").total_hits.should >= 2
   end
-  
+
   it "should give a boost to basename, filename and filetype in index" do
     index=Indexer.index
     index.field_infos[:basename].boost.should > 1.0
     index.field_infos[:filename].boost.should > 1.0
     index.field_infos[:filetype].boost.should > 1.0
   end
-  
+
   it "should also index unreadable files with known mimetypes" do
     Finder.new("unreadable.pdf").matching_documents.should_not be_empty
     Finder.new("too_small.doc").matching_documents.should_not be_empty
   end
-  
+
   it "should also index files with unknown mimetypes" do
-    Finder.new("filetype:xyz").matching_document.basename.should == "ghjopdfg"
-    Finder.new("filetype:abc").matching_document.filename.should == "asfg.abc"
-    Finder.new("unreadable.png").matching_document.size.should == 19696
-    #Support for xls has been added meanwhile. The test is still valid though.
-    Finder.new("table.xls").matching_document.size.should == 8704
+    matching_document_for("filetype:xyz").basename.should == "ghjopdfg"
+    matching_document_for("filetype:abc").filename.should == "asfg.abc"
   end
-  
+
   it "should also index files with upper/mixed case extension" do
     Finder.new("filetype:pdf").matching_documents.entries.find{|doc| doc.filename=="other_basic.PDF"}.should_not be_nil
     Finder.new("filetype:doc").matching_documents.entries.find{|doc| doc.filename=="other_too_small.dOc"}.should_not be_nil
   end
-  
+
   it "should also index content of files with upper/mixed case extension" do
     Finder.new("'just another content test\nin a pdf file'").matching_documents.entries.find{|doc| doc.filename=="other_basic.PDF"}.should_not be_nil
   end
-  
+
   it "should also accept utf8 queries" do
     lambda{Finder.new("Éric Mößer")}.should_not raise_error
   end
-  
+
   it "should find documents according to their utf8 content" do
-    Finder.new("Éric Mößer ext:pdf").matching_document.basename.should == "utf8"
-    Finder.new("no me hace daño").matching_document.size.should == 30
-    Finder.new("Éric Mößer filetype:pdf").matching_document.filename.should == "utf8.pdf"
+    matching_document_for("Éric Mößer ext:pdf").basename.should == "utf8"
+    matching_document_for("no me hace daño").filename.should == "utf8.txt"
+    matching_document_for("Éric Mößer filetype:pdf").filename.should == "utf8.pdf"
   end
-  
+
   it "should find documents according to their utf8 filenames" do
-    Finder.new("bäñüßé").matching_document.content.should == "just to know if files are indexed with utf8 filenames"
+    matching_document_for("bäñüßé").content.should == "just to know if files are indexed with utf8 filenames"
   end
-  
+
   it "should find documents according to their modification date" do
-    #FIXME: Specs don't pass in /tmp folder. They do pass in any other directory, though. Why???
     Finder.new("date:<1982").matching_documents.should be_empty
-    Finder.new("19831209*").matching_document.basename.should == "office2003-word-template"
-    Finder.new("date:<1983").matching_document.filename.should == "basic.pdf"
-    Finder.new("date:>=1989 AND date:<=1992").matching_document.filename.should == "placeholder.txt"
+    matching_document_for("19831209*").basename.should == "office2003-word-template"
+    matching_document_for("date:<1983").filename.should == "basic.pdf"
+    matching_document_for("date:>=1989 AND date:<=1992").filename.should == "placeholder.txt"
   end
 
   it "should not concatenate cells from xls file" do
     Finder.new("content:ABC").matching_documents.select{|doc| doc.extname==".xls"}.should be_empty
   end
-  
+
   it "should not raise if an indexed document has been moved/deleted, but just ignore it" do
     @basic_dir='spec/test_dirs/indexed/basic/'
     @from=File.join(@basic_dir,'another_plain.text')
@@ -114,29 +121,29 @@ describe Finder do
       File.rename(@to,@from) if File.exists?(@to)
     end
   end
-  
+
   it "should not index content of binary files"
-  
+
   # Ferret sometimes SEGFAULT crashed with '*.pdf' queries
   it "should not crash while looking for *.pdf" do
     @finder=Finder.new("some query")
     lambda{@finder=Finder.new("*.pdf")}.should_not raise_error
     @finder.matching_documents.should_not be_empty
   end
-  
+
   it "should use ? as placeholder" do
-    Finder.new("A?sorption machines").matching_document.matching_content.should include("<<Absorption>> and <<Adsorption>> cooling <<machines>>!!!")
+    matching_document_for("A?sorption machines").matching_content.should include("<<Absorption>> and <<Adsorption>> cooling <<machines>>!!!")
   end
-  
+
   it "should use * as placeholder" do
-    results=Finder.new("A*ption machines").matching_document.matching_content.should include("<<Absorption>> and <<Adsorption>> cooling <<machines>>!!!")
+    results=matching_document_for("A*ption machines").matching_content.should include("<<Absorption>> and <<Adsorption>> cooling <<machines>>!!!")
   end
-  
+
   it "should not index those stupid Thumbs.db files" do
     Finder.new("Thumbs.db").matching_documents.should be_empty
     Finder.new("filetype:db").matching_documents.should_not be_empty
   end
-  
+
   it "should keep content cached" do
     filename = "spec/test_dirs/indexed/others/placeholder.txt"
     content_before = "Absorption and Adsorption cooling machines!!!"
@@ -148,7 +155,7 @@ describe Finder do
     some_doc.content.should_not == content_before
     some_doc.cached.should == content_before
   end
-  
+
   after(:all) do
     revert_changes!("spec/test_dirs/indexed/others/placeholder.txt","Absorption and Adsorption cooling machines!!!")
   end

data/lib/picolena/templates/spec/models/host_indexing_system_spec.rb

@@ -6,19 +6,19 @@ describe "Host indexing system" do
        IO.popen("which #{dependency}"){|i| i.read.should_not be_empty}
     end
   end
-  
+
   it "should have a language guesser installed" do
     PlainTextExtractor.language_guesser.should_not be_nil
   end
-  
+
   it "should know which IP addresses are allowed (config/custom/white_list_ip.yml)" do
     File.should be_readable('config/custom/white_list_ip.yml')
   end
-  
+
   it "should know which directories are to be indexed (config/custom/indexed_directories.yml)" do
     File.should be_readable('config/custom/indexed_directories.yml')
   end
-  
+
   it "should be able to calculate base26 hash from strings" do
     "test_dirs/indexed/010/decrepito.pdf".base26_hash(5).should == "rails"
     "test_dirs/indexed/migrations/000_restreins.rb".base26_hash(5).should == "ricou"
@@ -26,7 +26,7 @@ describe "Host indexing system" do
     "test_dirs/indexed/1148/plots.odt".base26_hash(8).should == "picolehn"
     "whatever.pdf".base26_hash(10).should == "bbuxhynait"
   end
-  
+
   it "should not use too small a hash for Document#probably_unique_id" do
     Picolena::HashLength.should_not < 10
   end

data/lib/picolena/templates/spec/models/index_directories_spec.rb

@@ -4,11 +4,11 @@ describe "IndexedDirectories" do
   it "should be defined" do
     lambda {Picolena::IndexedDirectories}.should_not raise_error(NameError)
   end
-  
+
   it "should not be empty" do
     Picolena::IndexedDirectories.should_not be_empty
   end
-  
+
   it "should only contain existing directories" do
     Picolena::IndexedDirectories.keys.all?{|dir|
       File.should be_directory(dir)