trunction 0.0.1

data/.gitignore

@@ -0,0 +1,4 @@
+*.gem
+.bundle
+Gemfile.lock
+pkg/*

data/Gemfile

@@ -0,0 +1,7 @@
+source "http://rubygems.org"
+
+# Specify your gem's dependencies in trunction.gemspec
+gemspec
+
+gem "rake"
+gem "rspec"

data/Rakefile

@@ -0,0 +1,9 @@
+require "bundler/gem_tasks"
+
+task :default => :spec
+
+require "rspec/core/rake_task"
+
+RSpec::Core::RakeTask.new do |t|
+  t.pattern = 'spec/**/*_spec.rb'
+end

data/lib/trunction/version.rb

@@ -0,0 +1,3 @@
+module Trunction
+  VERSION = "0.0.1"
+end

data/lib/trunction.rb

@@ -0,0 +1,71 @@
+require "trunction/version"
+require "nokogiri"
+
+module Trunction
+
+  extend self
+
+  def truncate_html(html, max)
+    doc = Nokogiri::HTML::DocumentFragment.parse(html)
+    Truncation.new(doc, max).execute
+    doc.to_html
+  end
+
+  class Truncation
+
+    def initialize(doc, max)
+      @doc = doc
+      @max = max
+      @chars_remaining = max
+    end
+
+    def execute
+      find_the_end
+      remove_everything_else
+    end
+
+    private
+
+    def find_the_end
+      catch(:done) do
+        @doc.traverse do |node|
+          accumulate_text(node) if node.text?
+          record(node)
+        end
+      end
+    end
+
+    def accumulate_text(text_node)
+      @chars_remaining -= text_node.text.length
+      throw(:done) if limit_reached?
+    end
+
+    def limit_reached?
+      @chars_remaining <= 0
+    end
+
+    def record(node)
+      @last_block_element = node if block?(node)
+      @last_element = node
+    end
+
+    def last_node
+      @last_block_element || @last_element
+    end
+
+    def block?(node)
+      node.description && node.description.block?
+    end
+
+    def remove_everything_else
+      node = last_node
+      while node
+        node.next.remove while node.next
+        break unless node.respond_to?(:parent)
+        node = node.parent
+      end
+    end
+
+  end
+
+end

data/spec/spec_helper.rb

@@ -0,0 +1,5 @@
+require "rspec"
+
+RSpec.configure do |config|
+
+end

data/spec/trunction_spec.rb

@@ -0,0 +1,92 @@
+require 'trunction'
+
+describe Trunction do
+
+  let(:total_length) { Nokogiri::HTML::DocumentFragment.parse(input).text.length }
+  let(:ellipsis) { "…" }
+
+  include Trunction
+
+  let(:result) do
+    truncate_html(input, max_length).gsub("\n", '')
+  end
+
+  describe "#truncate_html" do
+
+    context "given multiple paragraphs" do
+
+      let(:input) { "<p>one</p><p>two</p><p>three</p>" }
+
+      context "with max-length longer than input" do
+
+        let(:max_length) { total_length + 1 }
+
+        it "returns input intact" do
+          result.should == input
+        end
+
+      end
+
+      context "with max-length shorter than input" do
+
+        let(:max_length) { total_length - 1 }
+
+        it "drops elements until beneath max-length" do
+          result.should == "<p>one</p><p>two</p>"
+        end
+
+      end
+
+    end
+
+    context "given multiple paragraphs, wrapped in a div" do
+
+      let(:input) { "<div><p>one</p><p>two</p><p>three</p></div>" }
+
+      context "with max-length shorter than input" do
+
+        let(:max_length) { total_length - 1 }
+
+        it "drops elements until beneath max-length" do
+          result.should == "<div><p>one</p><p>two</p></div>"
+        end
+
+      end
+
+    end
+
+    context "a single paragraph with inline elements" do
+
+      let(:input) { "<p><b>one</b>, <b>two</b>, <b>three</b>, <b>four</b></p>" }
+
+      context "with max-length shorter than input" do
+
+        let(:max_length) { total_length - 1 }
+
+        it "drops the last word" do
+          result.should == "<p><b>one</b>, <b>two</b>, <b>three</b>, </p>"
+        end
+
+      end
+
+    end
+
+    context "a final paragraph with inline elements" do
+
+      let(:input) { "<p>one</p><p>two</p><p><b>one</b>, <b>two</b>, <b>three</b>, <b>four</b></p>" }
+
+      context "with max-length shorter than input" do
+
+        let(:max_length) { total_length - 1 }
+
+        it "drops the entire final paragraph" do
+          result.should == "<p>one</p><p>two</p>"
+        end
+
+      end
+
+    end
+
+  end
+
+end

data/trunction.gemspec

@@ -0,0 +1,23 @@
+# -*- encoding: utf-8 -*-
+$:.push File.expand_path("../lib", __FILE__)
+require "trunction/version"
+
+Gem::Specification.new do |s|
+  s.name        = "trunction"
+  s.version     = Trunction::VERSION
+  s.authors     = ["Mike Williams"]
+  s.email       = ["mdub@dogbiscuit.org"]
+  s.homepage    = ""
+  s.summary     = %q{Beat your HTML down to size}
+  s.description = %q{Trunction implements intelligent truncation of HTML text.}
+
+  s.rubyforge_project = "trunction"
+
+  s.files         = `git ls-files`.split("\n")
+  s.test_files    = `git ls-files -- {test,spec,features}/*`.split("\n")
+  s.executables   = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
+  s.require_paths = ["lib"]
+
+  s.add_runtime_dependency "nokogiri"
+
+end

metadata

@@ -0,0 +1,66 @@
+--- !ruby/object:Gem::Specification
+name: trunction
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+  prerelease: 
+platform: ruby
+authors:
+- Mike Williams
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2011-12-05 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: &70261283968360 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: *70261283968360
+description: Trunction implements intelligent truncation of HTML text.
+email:
+- mdub@dogbiscuit.org
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- Gemfile
+- Rakefile
+- lib/trunction.rb
+- lib/trunction/version.rb
+- spec/spec_helper.rb
+- spec/trunction_spec.rb
+- trunction.gemspec
+homepage: ''
+licenses: []
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: trunction
+rubygems_version: 1.8.10
+signing_key: 
+specification_version: 3
+summary: Beat your HTML down to size
+test_files:
+- spec/spec_helper.rb
+- spec/trunction_spec.rb