recordsearch 1.0.0 → 1.1.0

data/History.txt

@@ -1,6 +1,6 @@
-== 1.0.0 2007-11-19
+== 1.1.0 2009-09-30
 
-* renamed project to recordsearch, as there is another project already with the same name (binarysearch).
+* changes to make it work on Ruby 1.9.1
 
 == 0.0.2 2007-10-25
 

data/README.txt

@@ -1,4 +1,4 @@
-= Record Search 1.0
+= Record Search 1.1
 
 == What is recordsearch?
 

data/lib/recordsearch/indexer.rb

@@ -1,7 +1,7 @@
 module RecordSearch
    # Builds an index file using as source data +data_source+, which can be a
    # subclass of RecordSearch::DataSource or an object with a next method.
-   def self.index(data_source, db, db_idx=nil)
+  def self.index(data_source, db, db_idx=nil)
      db_idx = db + '.idx' if db_idx.nil?
      records = 0
 

data/lib/recordsearch/search.rb

@@ -1,5 +1,3 @@
-require 'readbytes'
-
 module RecordSearch
 
   class Search
@@ -61,11 +59,23 @@ module RecordSearch
     # Reads and parses the line at position +index+.
     def read(index)
       @db_idx.seek(index * INDEX_SIZE)
-      pos = @db_idx.readbytes(INDEX_SIZE).unpack('L')[0]
+      pos = readbytes(INDEX_SIZE).unpack('L')[0]
       @db.seek(pos)
       parse(@db.gets)
     end
 
+    # my own version of IO#readbytes as 1.9 doesn't have it
+    def readbytes(n)
+      s = @db_idx.read(INDEX_SIZE)
+      if s.nil?
+        raise EOFError
+      elsif s.size != n
+        raise IOError, "truncated"
+      end
+
+      s
+    end
+
     # Parse a record read from the file. This method raises an exception.
     # You must implement this method to parse the file according to your needs.
     def parse(what)

data/lib/recordsearch/version.rb

@@ -1,7 +1,7 @@
 module RecordSearch 
   module VERSION #:nodoc:
     MAJOR = 1
-    MINOR = 0
+    MINOR = 1
     TINY  = 0
 
     STRING = [MAJOR, MINOR, TINY].join('.')

data/script/txt2html

@@ -22,9 +22,9 @@ class Fixnum
     return 'th' if (10..19).include?(self % 100)
     # others
     case self % 10
-    when 1: return 'st'
-    when 2: return 'nd'
-    when 3: return 'rd'
+    when 1 then return 'st'
+    when 2 then return 'nd'
+    when 3 then return 'rd'
     else    return 'th'
     end
   end

data/website/index.html

@@ -33,72 +33,34 @@
     <h1>Text Record Search</h1>
     <div id="version" class="clickable" onclick='document.location = "http://rubyforge.org/projects/recordsearch"; return false'>
       <p>Get Version</p>
-      <a href="http://rubyforge.org/projects/recordsearch" class="numbers">1.0.0</a>
+      <a href="http://rubyforge.org/projects/recordsearch" class="numbers">1.1.0</a>
     </div>
-    <h1>&#x2192; &#8216;recordsearch&#8217;</h1>
-
-
-	<h2>What</h2>
-
-
-	<p>With <code>recordsearch</code> you can do binary searches on a text file. I created this library as a few weeks after participating in the <a href="http://www.rubyquiz.com/quiz139.html">Ruby Quiz #139</a> I found myself needing something similar in a project I was working on.</p>
-
-
-	<h2>Installing</h2>
-
-
-	<p><pre class='syntax'><span class="ident">sudo</span> <span class="ident">gem</span> <span class="ident">install</span> <span class="ident">recordsearch</span></pre></p>
-
-
-	<p>Or download the gem and install manually.</p>
-
-
-	<h2>The basics</h2>
-
-
-	<p>The approach <code>recordsearch</code> uses is to pre process the text file to generate first an index and storing it in a file before being able to begin searching. It&#8217;s assumed the records are of variable size, it should not make much sense to use an index if you have records of fixed size. After the index is created you can begin to do searches.</p>
-
-
-	<p>Bear in mind I created this library to suit my needs, so, for example, when the index is being created, the contents of the original file is used to create another as I needed to transform the original file.</p>
-
-
-	<h2>Demonstration of usage</h2>
-
-
-	<p>Suppose we have a ~40MB file with a list of inflected words and their corresponding <a href="http://en.wikipedia.org/wiki/Lemma_%28linguistics%29">lemma</a> in <i>big_file.txt</i>. Each line of the file has the format <i>&#8220;inflected_word  lemma&#8221;</i>.</p>
-
-
-	<p>First we require the needed files:</p>
-
-
-	<p><pre class='syntax'>
+    <h1>&#8216;recordsearch&#8217;</h1>
+<h2>What</h2>
+<p>With <code>recordsearch</code> you can do binary searches on a text file. I created this library as a few weeks after participating in the <a href="http://www.rubyquiz.com/quiz139.html">Ruby Quiz #139</a> I found myself needing something similar in a project I was working on.</p>
+<h2>Installing</h2>
+<p><pre class='syntax'><span class="ident">sudo</span> <span class="ident">gem</span> <span class="ident">install</span> <span class="ident">recordsearch</span></pre></p>
+<p>Or download the gem and install manually.</p>
+<h2>The basics</h2>
+<p>The approach <code>recordsearch</code> uses is to pre process the text file to generate first an index and storing it in a file before being able to begin searching. It&#8217;s assumed the records are of variable size, it should not make much sense to use an index if you have records of fixed size. After the index is created you can begin to do searches.</p>
+<p>Bear in mind I created this library to suit my needs, so, for example, when the index is being created, the contents of the original file is used to create another as I needed to transform the original file.</p>
+<h2>Demonstration of usage</h2>
+<p>Suppose we have a ~40MB file with a list of inflected words and their corresponding <a href="http://en.wikipedia.org/wiki/Lemma_%28linguistics%29">lemma</a> in <i>big_file.txt</i>. Each line of the file has the format <i>&#8220;inflected_word  lemma&#8221;</i>.</p>
+<p>First we require the needed files:</p>
+<p><pre class='syntax'>
 <span class="ident">require</span> <span class="punct">'</span><span class="string">rubygems</span><span class="punct">'</span>
 <span class="ident">require</span> <span class="punct">'</span><span class="string">recordsearch</span><span class="punct">'</span>
 </pre></p>
-
-
-	<h3>Creating the index</h3>
-
-
-	<p>We have to create the index first, to do this, we need a subclass of <a href="http://recordsearch.rubyforge.org/rdoc/classes/RecordSearch/DataSource.html">RecordSearch::DataSource</a> . In this example we are using a <a href="http://recordsearch.rubyforge.org/rdoc/classes/RecordSearch/FileDataSource.html">RecordSearch::FileDataSource</a> which only reads each line from the file.</p>
-
-
-	<p><pre class='syntax'>
+<h3>Creating the index</h3>
+<p>We have to create the index first, to do this, we need a subclass of <a href="http://recordsearch.rubyforge.org/rdoc/classes/RecordSearch/DataSource.html">RecordSearch::DataSource</a> . In this example we are using a <a href="http://recordsearch.rubyforge.org/rdoc/classes/RecordSearch/FileDataSource.html">RecordSearch::FileDataSource</a> which only reads each line from the file.</p>
+<p><pre class='syntax'>
 <span class="ident">data_source</span> <span class="punct">=</span> <span class="constant">RecordSearch</span><span class="punct">::</span><span class="constant">FileDataSource</span><span class="punct">.</span><span class="ident">new</span><span class="punct">('</span><span class="string">big_file.txt</span><span class="punct">')</span>
 <span class="constant">RecordSearch</span><span class="punct">::</span><span class="ident">index</span><span class="punct">(</span><span class="ident">data_source</span><span class="punct">,</span> <span class="punct">'</span><span class="string">searchable_file</span><span class="punct">')</span>
 </pre></p>
-
-
-	<p>After this, <i>searchable_file</i> and <i>searchable_file.idx</i> have been created. This is one of the quirks the library has, if you don&#8217;t need to change the contents of <i>big_file.txt</i> you end up with <i>searchable_file</i> which is an exact duplicate of the original.</p>
-
-
-	<h3>Searching</h3>
-
-
-	<p>To search we need to subclass <a href="http://recordsearch.rubyforge.org/rdoc/classes/RecordSearch/Search.html">RecordSearch::Search</a> and implement the methods <code>parse</code>, <code>gt</code> and <code>eq</code>. In this example <i>parse</i> reads a line, and split it in an array with it&#8217;s first element as the inflected word and the second element the lemma.</p>
-
-
-	<p><pre class='syntax'>
+<p>After this, <i>searchable_file</i> and <i>searchable_file.idx</i> have been created. This is one of the quirks the library has, if you don&#8217;t need to change the contents of <i>big_file.txt</i> you end up with <i>searchable_file</i> which is an exact duplicate of the original.</p>
+<h3>Searching</h3>
+<p>To search we need to subclass <a href="http://recordsearch.rubyforge.org/rdoc/classes/RecordSearch/Search.html">RecordSearch::Search</a> and implement the methods <code>parse</code>, <code>gt</code> and <code>eq</code>. In this example <i>parse</i> reads a line, and split it in an array with it&#8217;s first element as the inflected word and the second element the lemma.</p>
+<p><pre class='syntax'>
 <span class="keyword">class </span><span class="class">MySearch</span> <span class="punct">&lt;</span> <span class="constant">RecordSearch</span><span class="punct">::</span><span class="constant">Search</span>
   <span class="keyword">def </span><span class="method">initialize</span>
     <span class="keyword">super</span><span class="punct">('</span><span class="string">searchable_file</span><span class="punct">')</span>
@@ -117,48 +79,27 @@
   <span class="keyword">end</span>
 <span class="keyword">end</span>
 </pre></p>
-
-
-	<p>And we search like this:
+<p>And we search like this:<br />
 <pre class='syntax'>
 <span class="ident">my_search</span> <span class="punct">=</span> <span class="constant">MySearch</span><span class="punct">.</span><span class="ident">new</span>
 <span class="ident">my_search</span><span class="punct">.</span><span class="ident">search</span><span class="punct">('</span><span class="string">item</span><span class="punct">')</span>
 </pre></p>
-
-
-	<h2>Forum</h2>
-
-
-There are two forums:
-<ul>
-<li><a href="http://rubyforge.org/forum/forum.php?forum_id=19017">open-discussion</a></li>
-<li><a href="http://rubyforge.org/forum/forum.php?forum_id=19018">help</a></li>
+<h2>Forum</h2>
+<p>There are two forums:<br />
+<ul><br />
+<li><a href="http://rubyforge.org/forum/forum.php?forum_id=19017">open-discussion</a></li><br />
+<li><a href="http://rubyforge.org/forum/forum.php?forum_id=19018">help</a></li></p>
 </ul>
-
-	<h2>Documentacion</h2>
-
-
-	<p>The rdoc documentation is in the page <a href="http://recordsearch.rubyforge.org/rdoc">RecordSearch <span class="caps">API</span></a> and you can also see the <a href="http://recordsearch.rubyforge.org/coverage">test coverage report</a></p>
-
-
-	<h2>Source</h2>
-
-
-	<p>You can get the source using svn using this url <code>svn://rubyforge.org/var/svn/recordsearch/trunk</code> for anonymous access or go the the <a href="http://rubyforge.org/projects/recordsearch">RecordSearch</a> RubyForge page.</p>
-
-
-	<h2>License</h2>
-
-
-	<p>This code is free to use under the terms of the <span class="caps">GPL</span> license.</p>
-
-
-	<h2>Contact</h2>
-
-
-	<p>Comments are welcome. Send an email to <a href="mailto:lparravi@gmail.com">Luis Parravicini</a> or post a message to one of the available forums.</p>
+<h2>Documentacion</h2>
+<p>The rdoc documentation is in the page <a href="http://recordsearch.rubyforge.org/rdoc">RecordSearch <span class="caps">API</span></a> and you can also see the <a href="http://recordsearch.rubyforge.org/coverage">test coverage report</a></p>
+<h2>Source</h2>
+<p>You can get the source using svn using this url <code>svn://rubyforge.org/var/svn/recordsearch/trunk</code> for anonymous access or go the the <a href="http://rubyforge.org/projects/recordsearch">RecordSearch</a> RubyForge page.</p>
+<h2>License</h2>
+<p>This code is free to use under the terms of the <span class="caps">GPL</span> license.</p>
+<h2>Contact</h2>
+<p>Comments are welcome. Send an email to <a href="mailto:lparravi@gmail.com">Luis Parravicini</a> or post a message to one of the available forums.</p>
     <p class="coda">
-      <a href="http://ktulu.com.ar">Luis Parravicini</a>, 20th November 2007<br>
+      <a href="http://ktulu.com.ar">Luis Parravicini</a>, 1st October 2009<br>
       Theme extended from <a href="http://rb2js.rubyforge.org/">Paul Battley</a>
     </p>
 </div>

data/website/index.txt

@@ -1,6 +1,6 @@
 h1. Text Record Search
 
-h1. → 'recordsearch'
+h1. 'recordsearch'
 
 
 h2. What

metadata

@@ -1,33 +1,39 @@
 --- !ruby/object:Gem::Specification 
-rubygems_version: 0.9.4
-specification_version: 1
 name: recordsearch
 version: !ruby/object:Gem::Version 
-  version: 1.0.0
-date: 2007-11-20 00:00:00 -03:00
-summary: Search on a text file using binary search
-require_paths: 
-- lib
-email: lparravi@gmail.com
-homepage: http://recordsearch.rubyforge.org
-rubyforge_project: recordsearch
-description: Search on a text file using binary search
-autorequire: 
-default_executable: 
-bindir: bin
-has_rdoc: true
-required_ruby_version: !ruby/object:Gem::Version::Requirement 
-  requirements: 
-  - - ">"
-    - !ruby/object:Gem::Version 
-      version: 0.0.0
-  version: 
+  version: 1.1.0
 platform: ruby
-signing_key: 
-cert_chain: 
-post_install_message: 
 authors: 
 - Luis Parravicini
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2009-10-01 00:00:00 -03:00
+default_executable: 
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  name: hoe
+  type: :development
+  version_requirement: 
+  version_requirements: !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: 2.3.3
+    version: 
+description: Search on a text file using binary search
+email: lparravi@gmail.com
+executables: []
+
+extensions: []
+
+extra_rdoc_files: 
+- History.txt
+- License.txt
+- Manifest.txt
+- README.txt
+- website/index.txt
 files: 
 - History.txt
 - License.txt
@@ -56,24 +62,36 @@ files:
 - website/javascripts/rounded_corners_lite.inc.js
 - website/stylesheets/screen.css
 - website/template.rhtml
-test_files: 
-- test/test_helper.rb
-- test/test_index.rb
-- test/test_recordsearch.rb
+has_rdoc: true
+homepage: http://recordsearch.rubyforge.org
+licenses: []
+
+post_install_message: 
 rdoc_options: 
 - --main
 - README.txt
-extra_rdoc_files: 
-- History.txt
-- License.txt
-- Manifest.txt
-- README.txt
-- website/index.txt
-executables: []
-
-extensions: []
-
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
 requirements: []
 
-dependencies: []
-
+rubyforge_project: recordsearch
+rubygems_version: 1.3.5
+signing_key: 
+specification_version: 3
+summary: Search on a text file using binary search
+test_files: 
+- test/test_recordsearch.rb
+- test/test_helper.rb
+- test/test_index.rb