abbreviato 0.8.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 3c6f7e4cd1a30ddde713870703ee0b78bc26f384
+  data.tar.gz: 46253968fab63363c865b20c6b53230d7be607e7
+SHA512:
+  metadata.gz: 64f8679f4bfd744e013f4ae0a13f9d712b5e7cf0c55f54e6ec15f84e27f0e054048e5bf5cafdd3ffe21ffaf66c9b539767be8ba9ee8aa1a1672c850999aaaac5
+  data.tar.gz: d63228f14b686c61066f2075cf5b8f670e7f87276d49024c0444370a0ca2df3fafa2a198425979b447d272f2277cd12a095be876279e788afc4ffe70eba7b412

data/LICENSE.txt

@@ -0,0 +1,20 @@
+Copyright (c) 2011 Jorge Manrubia
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.md

@@ -0,0 +1,61 @@
+# abbreviato
+
+*abbreviato* is a Ruby library for truncating HTML strings keeping the markup valid. It is a fork of github.com/jorgemanrubia/truncato but focused on truncating to a bytesize, not on a per-character basis.
+
+## Installing
+
+In your `Gemfile`
+
+```ruby
+gem 'abbreviato'
+```
+
+## Usage
+
+```ruby
+truncated_string, was_truncated = Abbreviato.truncate("<p>some text</p>", max_length: 4) #=> ["<p>s...</p>", true]
+```
+
+The configuration options are:
+
+* `max_length`: The size, in bytes, to truncate (`30` by default)
+* `tail`: The string to append when the truncation occurs ('&hellip;' by default).
+# `fragment`: Indicates whether the document to be truncated is an HTML fragment
+# or an entire document (with `HTML`, `HEAD` & `BODY` tags). Setting to true prevents automatic
+# addition of these tags if they are missing. Defaults to `true`.
+
+
+## Performance
+
+Abbreviato was designed with performance in mind. Its main motivation was that existing libs couldn't truncate a multiple-MB document into a few-KB one in a reasonable time. It uses the [Nokogiri](http://nokogiri.org/) SAX parser.
+
+## Running the tests
+
+```ruby
+bundle exec rake
+```
+
+## Running all checks
+
+```ruby
+bundle exec wwtd
+```
+
+## Updating
+
+Update the version
+```ruby
+bundle exec bump patch
+```
+
+Build
+```ruby
+gem build abbreviato.gemspec
+
+Publish
+```ruby
+gem push abbreviato-x.y.z.gem
+```
+
+
+

data/Rakefile

@@ -0,0 +1,17 @@
+require 'wwtd/tasks'
+require 'bundler/gem_tasks'
+require 'bump/tasks'
+require 'bundler/setup'
+
+Bundler::GemHelper.install_tasks
+
+require 'rspec/core/rake_task'
+RSpec::Core::RakeTask.new(:spec)
+
+require 'rubocop/rake_task'
+RuboCop::RakeTask.new
+
+require 'bundler/audit/task'
+Bundler::Audit::Task.new
+
+task default: :wwtd

data/lib/abbreviato.rb

@@ -0,0 +1,3 @@
+Dir[File.dirname(__FILE__) + '/abbreviato/**/*.rb'].each do |file|
+  require file
+end

data/lib/abbreviato/abbreviato.rb

@@ -0,0 +1,27 @@
+module Abbreviato
+  DEFAULT_OPTIONS = {
+      max_length: 30,
+      tail: '…',
+      fragment: true
+  }.freeze
+
+  # Truncates the source XML string and returns the truncated XML and a boolean flag indicating
+  # whether any truncation took place. It will keep a valid XML structure
+  # and insert a _tail_ text indicating the position where content was removed (...).
+  #
+  # @param [String] source the XML source to truncate
+  # @param [Hash] user_options truncation options
+  # @option user_options [Integer] :max_length Maximum length
+  # @option user_options [String] :tail Text to append when the truncation happens
+  # @option user_options [Boolean] :fragment Indicates whether the document to be truncated is an HTML fragment
+  #     or an entire document (with `HTML`, `HEAD` & `BODY` tags). Setting to true prevents automatic addition of
+  #     these tags if they are missing. Defaults to `true`.
+  # @return [[String] the truncated string, [boolean] whether the string was truncated]
+  def self.truncate(source = '', user_options = {})
+    return [nil, false] if source.nil?
+    truncated_sax_document = TruncatedSaxDocument.new(DEFAULT_OPTIONS.merge(user_options))
+    parser = Nokogiri::HTML::SAX::Parser.new(truncated_sax_document)
+    parser.parse(source) { |context| context.replace_entities = false }
+    [truncated_sax_document.truncated_string, truncated_sax_document.truncated]
+  end
+end

data/lib/abbreviato/truncated_sax_document.rb

@@ -0,0 +1,203 @@
+require 'nokogiri'
+require 'htmlentities'
+
+class TruncatedSaxDocument < Nokogiri::XML::SAX::Document
+  IGNORABLE_TAGS = %w[html head body].freeze
+
+  # These don't have to be closed (which also impacts ongoing length calculations)
+  # http://www.456bereastreet.com/archive/201005/void_empty_elements_and_self-closing_start_tags_in_html/
+  VOID_TAGS = %w[area base br col command hr img input keygen link meta param source wbr].freeze
+
+  attr_reader :truncated_string,
+    :max_length,
+    :tail,
+    :ignored_levels,
+    :truncated
+
+  def initialize(options)
+    @html_coder = HTMLEntities.new
+
+    @max_length = options[:max_length]
+    @tail = options[:tail] || ''
+    @fragment_mode = options[:fragment]
+
+    @truncated_string = ""
+    @closing_tags = []
+    @estimated_length = 0
+    @ignored_levels = 0
+    @truncated = false
+  end
+
+  # This method is called when the parser encounters an open tag
+  def start_element(name, attributes)
+    if max_length_reached? || ignorable_tag?(name)
+      @truncated = true if max_length_reached?
+      return
+    end
+
+    # If already in ignore mode, go in deeper
+    if ignore_mode?
+      enter_ignored_level(name)
+      return
+    end
+
+    string_to_add = opening_tag(name, attributes)
+
+    # Abort if there is not enough space to add the combined opening tag and (potentially) the closing tag
+    length_of_tags = overridden_tag_length(name, string_to_add)
+    if length_of_tags > remaining_length
+      @truncated = true
+      enter_ignored_level(name)
+      return
+    end
+
+    # Save the tag so we can push it on at the end
+    @closing_tags.push name unless single_tag_element?(name)
+
+    append_to_truncated_string(string_to_add, length_of_tags)
+  end
+
+  # This method is called when the parser encounters characters between tags
+  def characters(decoded_string)
+    if max_length_reached? || ignore_mode?
+      @truncated = true
+      return
+    end
+
+    # Use encoded length, so &gt; counts as 4 bytes, not 1 (which is what '>' would give)
+    encoded_string = @html_coder.encode(decoded_string, :named)
+    string_to_append = if encoded_string.bytesize > remaining_length
+      # This is the line which prevents HTML entities getting truncated - treat them as a single char
+      str = @html_coder.encode(truncate_string(decoded_string), :named) || ''
+      str << tail if remaining_length - str.bytesize >= tail.bytesize
+      str
+    else
+      encoded_string
+    end
+    append_to_truncated_string(string_to_append)
+  end
+
+  # This method is called when the parser encounters a comment
+  def comment(string)
+    comment = comment_tag(string)
+    if comment.bytesize <= remaining_length
+      append_to_truncated_string(comment)
+    else
+      @truncated = true
+    end
+  end
+
+  # This method is called when the parser encounters cdata. In practice, this also
+  # gets called for this style of comment inside an element:
+  #
+  #   <style><!--
+  #     /* Font Definitions */
+  #     @font-face
+  #       {font-family:Wingdings;
+  #       panose-1:5 0 0 0 0 0 0 0 0 0;}
+  #   --></style>
+  #
+  def cdata_block(string)
+    if string.bytesize <= remaining_length
+      append_to_truncated_string(string)
+    else
+      @truncated = true
+    end
+  end
+
+  # This method is called when the parser encounters a closing tag
+  def end_element(name)
+    if ignore_mode?
+      exit_ignored_level(name)
+      return
+    end
+
+    # Note that any remaining end tags get added automatically (in `end_document`) as the document is closed
+    return if max_length_reached? || ignorable_tag?(name)
+
+    unless single_tag_element?(name)
+      @closing_tags.pop
+      # Don't count the length when closing a tag - it was accommodated when
+      # the tag was opened
+      append_to_truncated_string(closing_tag(name), 0)
+    end
+  end
+
+  def end_document
+    @closing_tags.reverse_each { |name| append_to_truncated_string(closing_tag(name), 0) }
+  end
+
+  private
+
+  def opening_tag(name, attributes)
+    attributes_string = attributes_to_string(attributes)
+    if single_tag_element? name
+      "<#{name}#{attributes_string}/>"
+    else
+      "<#{name}#{attributes_string}>"
+    end
+  end
+
+  def comment_tag(comment)
+    "<!--#{comment}-->"
+  end
+
+  def closing_tag(name)
+    "</#{name}>"
+  end
+
+  def remaining_length
+    max_length - @estimated_length
+  end
+
+  def single_tag_element?(name)
+    VOID_TAGS.include? name
+  end
+
+  def append_to_truncated_string(string, overridden_length = nil)
+    @truncated_string << string
+    @estimated_length += (overridden_length || string.bytesize)
+  end
+
+  def attributes_to_string(attributes)
+    attributes.inject(' ') do |string, attribute|
+      key, value = attribute
+      string << "#{key}='#{@html_coder.encode value}' "
+    end.rstrip
+  end
+
+  def max_length_reached?
+    @estimated_length >= max_length
+  end
+
+  def truncate_string(string)
+    @truncated = true
+    truncate_length = remaining_length - tail.bytesize
+    (string.byteslice(0, truncate_length) || '').scrub('')
+  end
+
+  def overridden_tag_length(tag_name, rendered_tag_with_attributes)
+    # Start with the opening tag
+    length = rendered_tag_with_attributes.bytesize
+
+    # Add on closing tag if necessary
+    length += closing_tag(tag_name).bytesize unless single_tag_element?(tag_name)
+    length
+  end
+
+  def ignorable_tag?(name)
+    @fragment_mode && IGNORABLE_TAGS.include?(name.downcase)
+  end
+
+  def enter_ignored_level(name)
+    @ignored_levels += 1 unless single_tag_element?(name)
+  end
+
+  def exit_ignored_level(name)
+    @ignored_levels -= 1 unless single_tag_element?(name)
+  end
+
+  def ignore_mode?
+    @ignored_levels > 0
+  end
+end

data/lib/abbreviato/version.rb

@@ -0,0 +1,3 @@
+module Abbreviato
+  VERSION = '0.8.1'.freeze
+end

metadata

@@ -0,0 +1,262 @@
+--- !ruby/object:Gem::Specification
+name: abbreviato
+version: !ruby/object:Gem::Version
+  version: 0.8.1
+platform: ruby
+authors:
+- Jorge Manrubia
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2013-09-10 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 1.6.8
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 1.6.8
+- !ruby/object:Gem::Dependency
+  name: htmlentities
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 4.3.4
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 4.3.4
+- !ruby/object:Gem::Dependency
+  name: awesome_print
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: benchmark-memory
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: brakecheck
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: brakeman
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: bump
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: bundler-audit
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: byebug
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: flay
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 11.3.0
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 11.3.0
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 3.5.0
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 3.5.0
+- !ruby/object:Gem::Dependency
+  name: rspec-benchmark
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: rubocop
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: wwtd
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+description: Truncate HTML to a specific bytesize, while keeping valid markup
+email: jorge.manrubia@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files:
+- LICENSE.txt
+- README.md
+files:
+- LICENSE.txt
+- README.md
+- Rakefile
+- lib/abbreviato.rb
+- lib/abbreviato/abbreviato.rb
+- lib/abbreviato/truncated_sax_document.rb
+- lib/abbreviato/version.rb
+homepage: https://github.com/zendesk/abbreviato
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.5.1
+signing_key: 
+specification_version: 4
+summary: A tool for efficiently truncating HTML strings to a specific bytesize
+test_files: []