tag_remover_nokogiri 0.0.2

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 0ee5b1c651af34648ff509cd22bc7d92bd19d45d
+  data.tar.gz: 358514f7c1c35ed2e493b5dc87e53d24cfe4cf66
+SHA512:
+  metadata.gz: a851331a3a07215fd67e0f2eacc42764f59fcfa6310881835d01411fd633c12ecf08261dad528d905c65b89a4aa13aeb5972ca2d6624c5d9052a8fcdecbb72fb
+  data.tar.gz: 51b2801326b831db6c44d3a43b3d45c96b3667d36af8ccaf3a381dfed7bb56aca050a1e279a12ce11ef9fd1de377b6b63420f3397288a12113c0b00831c8838d

data/.gitignore

@@ -0,0 +1,15 @@
+/.bundle/
+/.yardoc
+/Gemfile.lock
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/
+*.bundle
+*.so
+*.o
+*.a
+*.gem
+mkmf.log

data/.rspec

@@ -0,0 +1 @@
+--color

data/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in tag_remover.gemspec
+gemspec

data/LICENSE.txt

@@ -0,0 +1,22 @@
+Copyright (c) 2014 Daniel Smith
+
+MIT License
+
+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 +1,49 @@
+# TagRemover (Nokogiri edition)
+
+Tag remover let's you remove all elements of specified tags from extremely large XML documents without parsing or loading the whole thing in memory, useful for processing unreasonably large documents without making your server fall over.
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'tag_remover'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install tag_remover
+
+## Usage
+
+The following line will read XML from `input_stream`, and write it out to `output_stream` with all `div` and `img` elements removed.
+
+```ruby
+TagRemover.process input_stream, output_stream, remove_tags: ['div', 'img']
+```
+
+Options include:
+
+  * `remove_tags`: List of tags to remove from the XML file.
+  * `close_streams`: (`true`|`false`) If set, TagRemover will close `input_stream` and `output_stream` once the proccess is over.
+  * [NOT IMPLEMENTED] `format`: (`true`|`false`) If set, then the contents of `output_stream` will be formatted.
+
+TagRemover can be used from the command line with the `rmtags` command. The following is an example that reads input.xml and writes the output to output.xml, removing all `div` and `img` elements:
+
+    $ rmtags input.xml output.xml div img
+
+## Limitations
+
+Tag remover currently only works correctly if the XML is formatted with only one tag per line.
+
+## Contributing
+
+  1. Fork it ( https://github.com/[my-github-username]/tag_remover/fork )
+  2. Create your feature branch (`git checkout -b my-new-feature`)
+  3. Commit your changes (`git commit -am 'Add some feature'`)
+  4. Push to the branch (`git push origin my-new-feature`)
+  5. Create a new Pull Request

data/Rakefile

@@ -0,0 +1,2 @@
+require "bundler/gem_tasks"
+

data/bin/rmtags

@@ -0,0 +1,20 @@
+#!/usr/bin/env ruby
+
+require 'tag_remover'
+
+if ARGV.length < 3
+  puts "Usage: rmtags INPUT_FILE OUTPUT_FILE TAG [TAG, TAG, ...]"
+  exit 1
+end
+
+input_filename = ARGV[0] || 'input.xml'
+output_filename = ARGV[1] || 'output.xml'
+
+tags_to_remove = ARGV[2..-1]
+
+input_file = File.open input_filename, 'r'
+output_file = File.open output_filename, 'w'
+
+TagRemover.process input_file, output_file,
+  remove_tags: tags_to_remove, close_streams: true
+

data/lib/tag_remover.rb

@@ -0,0 +1,128 @@
+require "tag_remover/version"
+require "nokogiri"
+
+module TagRemover
+
+  class Worker
+    def initialize input, output, opts
+      @input = input
+      @output = output
+      @opts = opts
+    end
+
+    def perform
+      @tags_to_remove = @opts[:remove_tags] || []
+
+      @reader = Nokogiri::XML::Reader @input
+
+      @in_tag = nil
+      @depth = 0
+
+      @reader.each do |node|
+        process_node node
+      end
+
+      if @opts[:close_streams]
+        @input.close
+        @output.close
+      end
+    end
+
+    private
+      def process_node node
+        if @in_tag
+          in_tag_str = @tags_to_remove[@in_tag]
+
+          if opening_tag? node, in_tag_str
+            @depth += 1
+          elsif closing_tag? node, in_tag_str
+            @depth -= 1
+            @in_tag = nil if @depth == 0
+          end
+        else
+          found_tag = false
+          @tags_to_remove.each_with_index do |tag_str,index|
+            if opening_tag? node, tag_str
+              @in_tag = index
+              @depth = 1
+              found_tag = true
+            elsif single_tag? node, tag_str
+              found_tag = true
+            end
+            break if found_tag
+          end
+          @output.write stringify(node) unless found_tag
+        end
+      end
+
+      def opening_tag? tag, match = nil
+        return (tag.node_type == Nokogiri::XML::Reader::TYPE_ELEMENT) && !tag.self_closing? && match?(tag, match)
+      end
+
+      def closing_tag? tag, match = nil
+        return (tag.node_type == Nokogiri::XML::Reader::TYPE_END_ELEMENT) && match?(tag, match)
+      end
+
+      def single_tag? tag, match = nil
+        return tag.node_type == Nokogiri::XML::Reader::TYPE_ELEMENT && tag.self_closing? && match?(tag, match)
+      end
+
+      def match? tag, match = nil
+        (match.nil? || tag.name == match)
+      end
+
+      def stringify tag
+        if opening_tag? tag
+          "<#{with_attrs tag}>\n"
+        elsif closing_tag? tag
+          "</#{tag.name}>\n"
+        elsif single_tag? tag
+          "<#{with_attrs tag}/>\n"
+        elsif tag.value?
+          s = tag.value.strip
+          s.empty? ? "" : "#{s}\n"
+        else
+          "#{tag.to_s}\n"
+        end
+      end
+
+      def with_attrs tag
+        return tag.name unless tag.attributes?
+        attrs = tag.attributes.map { |k,v| "#{k}=\"#{v}\""  }.join(' ')
+        "#{tag.name} #{attrs} "
+      end
+
+      def process_tag tag, type
+        if @in_tag
+          in_tag_str = @tags_to_remove[@in_tag]
+
+          if tag =~ opening_tag(in_tag_str)
+            @depth += 1
+          elsif tag =~ closing_tag(in_tag_str)
+            @depth -= 1
+            @in_tag = nil if @depth == 0
+          end
+        else
+          found_tag = false
+          @tags_to_remove.each_with_index do |tag_str,index|
+            if tag =~ opening_tag(tag_str)
+              @in_tag = index
+              @depth = 1
+              found_tag = true
+              break
+            elsif tag =~ single_tag(tag_str)
+              found_tag = true
+              break
+            end
+          end
+
+          @output.write "#{tag}\n" unless found_tag || tag.empty?
+        end
+      end
+  end
+
+  def self.process input, output, opts = {}
+    Worker.new(input, output, opts).perform
+  end
+
+end

data/lib/tag_remover/version.rb

@@ -0,0 +1,3 @@
+module TagRemover
+  VERSION = "0.0.2"
+end

data/spec/spec_helper.rb

@@ -0,0 +1,3 @@
+require 'pry'
+require 'tag_remover'
+

data/spec/tag_remover_spec.rb

@@ -0,0 +1,141 @@
+require 'spec_helper'
+
+describe TagRemover do
+  describe ".process" do
+    it "removes elements" do
+      input = """
+<root>
+  <remove>
+    Some contents
+  </remove>
+  <remove >
+  </remove >
+</root>"""
+
+      output = StringIO.new
+      tags_to_remove = ['remove']
+
+      TagRemover.process input, output, remove_tags: tags_to_remove
+
+      expect(output.string).to eq """<root>
+</root>
+"""
+    end
+
+    it "removes single tags" do
+      input = StringIO.new """<root>
+  <remove/>
+  <remove />
+</root>
+"""
+      output = StringIO.new
+      tags_to_remove = ['remove']
+
+      TagRemover.process input, output, remove_tags: tags_to_remove
+
+      expect(output.string).to eq """<root>
+</root>
+"""
+    end
+
+    it "removes tags with attributes" do
+      input = StringIO.new '''<root>
+  <keep foo="bar" qux="baz" >
+  </keep>
+  <keep fizz="buzz" />
+  <remove x="y" a="b" >
+  </remove>
+  <remove x="y" a="b" />
+</root>
+'''
+      output = StringIO.new
+      tags_to_remove = ['remove']
+
+      TagRemover.process input, output, remove_tags: tags_to_remove
+
+      expect(output.string).to eq '''<root>
+<keep foo="bar" qux="baz" >
+</keep>
+<keep fizz="buzz" />
+</root>
+'''
+    end
+
+    it "deals with multiple tags on one line" do
+      input = StringIO.new '''<root><remove>
+  </remove>
+  <remove/><keep>
+  </keep>
+  <remove>Bad Stuff!
+  </remove>Happy Stuff :)<keep/>
+</root>
+'''
+      output = StringIO.new
+      tags_to_remove = ['remove']
+
+      TagRemover.process input, output, remove_tags: tags_to_remove
+
+      expect(output.string).to eq """<root>
+<keep>
+</keep>
+Happy Stuff :)
+<keep/>
+</root>
+"""
+    end
+
+    it "keeps elements" do
+      input = StringIO.new """<root>
+<keep>
+</keep>
+</root>
+"""
+      tags_to_remove = ['remove']
+
+      output = StringIO.new
+
+      TagRemover.process input, output, remove_tags: tags_to_remove
+
+      expect(output.string).to eq input.string
+    end
+
+    it "is ok with doing nothing" do
+      input = StringIO.new """<root>
+</root>
+"""
+      output = StringIO.new
+
+      TagRemover.process input, output
+
+      expect(output.string).to eq input.string
+    end
+
+    it "removes nested tags" do
+      input = StringIO.new """<root>
+  <remove>
+    <remove>
+    </remove>
+  </remove>
+</root>
+"""
+      tags_to_remove = ['remove']
+      output = StringIO.new
+
+      TagRemover.process input, output, remove_tags: tags_to_remove
+
+      expect(output.string).to eq """<root>
+</root>
+"""
+    end
+
+    it "closes the streams" do
+      input = StringIO.new "<root></root>"
+      output = StringIO.new
+
+      TagRemover.process input, output, close_streams: true
+
+      expect(input).to be_closed
+      expect(output).to be_closed
+    end
+  end
+end

data/tag_remover_nokogiri.gemspec

@@ -0,0 +1,29 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'tag_remover/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "tag_remover_nokogiri"
+  spec.version       = TagRemover::VERSION
+  spec.authors       = ["Daniel Smith"]
+  spec.email         = ["jellymann@gmail.com"]
+  spec.summary       = %q{Remove elements from large XML documents (using nokogiri).}
+  spec.description   = %q{Tag remover let's you remove all elements of specified tags from extremely large XML documents without parsing or loading the whole thing in memory, useful for processing unreasonably large documents without making your server fall over.}
+  spec.homepage      = "https://github.com/jellymann/tag_remover_nokogiri"
+  spec.license       = "MIT"
+
+  spec.files         = `git ls-files -z`.split("\x0")
+  spec.executables   = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
+  spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
+  spec.require_paths = ["lib"]
+
+  spec.required_ruby_version = ">= 1.9.2"
+
+  spec.add_runtime_dependency "nokogiri", "~> 1.5", '>= 1.5.5'
+
+  spec.add_development_dependency "bundler", "~> 1.6"
+  spec.add_development_dependency "rake", "~> 10.0"
+  spec.add_development_dependency "rspec", "~> 3.1"
+  spec.add_development_dependency "pry", "~> 0.10"
+end

metadata

@@ -0,0 +1,138 @@
+--- !ruby/object:Gem::Specification
+name: tag_remover_nokogiri
+version: !ruby/object:Gem::Version
+  version: 0.0.2
+platform: ruby
+authors:
+- Daniel Smith
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2015-02-19 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.5'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.5.5
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.5'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.5.5
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.6'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.6'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.1'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.1'
+- !ruby/object:Gem::Dependency
+  name: pry
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.10'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.10'
+description: Tag remover let's you remove all elements of specified tags from extremely
+  large XML documents without parsing or loading the whole thing in memory, useful
+  for processing unreasonably large documents without making your server fall over.
+email:
+- jellymann@gmail.com
+executables:
+- rmtags
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".rspec"
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- bin/rmtags
+- lib/tag_remover.rb
+- lib/tag_remover/version.rb
+- spec/spec_helper.rb
+- spec/tag_remover_spec.rb
+- tag_remover_nokogiri.gemspec
+homepage: https://github.com/jellymann/tag_remover_nokogiri
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: 1.9.2
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.4.5
+signing_key: 
+specification_version: 4
+summary: Remove elements from large XML documents (using nokogiri).
+test_files:
+- spec/spec_helper.rb
+- spec/tag_remover_spec.rb
+has_rdoc: