RubyGems - saxxy - Versions diffs - 0.1.0 - Mend

saxxy 0.1.0

Files changed (44) hide show

checksums.yaml +7 -0
data/.gitignore +22 -0
data/.travis.yml +5 -0
data/Gemfile +13 -0
data/LICENSE +22 -0
data/README.md +117 -0
data/Rakefile +12 -0
data/lib/saxxy.rb +2 -0
data/lib/saxxy/activatable.rb +160 -0
data/lib/saxxy/callbacks/libxml.rb +26 -0
data/lib/saxxy/callbacks/nokogiri.rb +30 -0
data/lib/saxxy/callbacks/ox.rb +66 -0
data/lib/saxxy/callbacks/sax.rb +86 -0
data/lib/saxxy/context.rb +88 -0
data/lib/saxxy/context_tree.rb +85 -0
data/lib/saxxy/event.rb +83 -0
data/lib/saxxy/event_registry.rb +122 -0
data/lib/saxxy/node_action.rb +59 -0
data/lib/saxxy/node_rule.rb +90 -0
data/lib/saxxy/parsers/base.rb +28 -0
data/lib/saxxy/parsers/libxml.rb +52 -0
data/lib/saxxy/parsers/nokogiri.rb +28 -0
data/lib/saxxy/parsers/ox.rb +30 -0
data/lib/saxxy/service.rb +47 -0
data/lib/saxxy/utils/agent.rb +66 -0
data/lib/saxxy/utils/callback_array.rb +27 -0
data/lib/saxxy/utils/helpers.rb +13 -0
data/lib/saxxy/version.rb +3 -0
data/saxxy.gemspec +21 -0
data/spec/saxxy/activatable_spec.rb +344 -0
data/spec/saxxy/callbacks/sax_spec.rb +456 -0
data/spec/saxxy/context_spec.rb +51 -0
data/spec/saxxy/context_tree_spec.rb +68 -0
data/spec/saxxy/event_registry_spec.rb +137 -0
data/spec/saxxy/event_spec.rb +49 -0
data/spec/saxxy/node_action_spec.rb +46 -0
data/spec/saxxy/node_rule_spec.rb +99 -0
data/spec/saxxy/parsers/libxml_spec.rb +104 -0
data/spec/saxxy/parsers/nokogiri_spec.rb +200 -0
data/spec/saxxy/parsers/ox_spec.rb +175 -0
data/spec/saxxy/utils/agent_spec.rb +63 -0
data/spec/spec_helper.rb +28 -0
data/spec/support/agent_macros.rb +24 -0
metadata +155 -0

data/spec/saxxy/parsers/libxml_spec.rb ADDED

@@ -0,0 +1,104 @@
+require "spec_helper"
+require "saxxy/utils/agent"
+require "saxxy/context_tree"
+describe "Saxxy::Parsers::Libxml", :not_jruby do
+  def parser(*args)
+    Saxxy::Parsers::Libxml.new(*args)
+  end
+  describe "#initialize" do
+    let(:tree) { Saxxy::ContextTree.new {} }
+    let(:subject) { parser(tree, {foo: :bar}) }
+    it "should set the options" do
+      subject.options.should == {foo: :bar}
+    end
+    it "should set the context tree" do
+      subject.context_tree.should == tree
+    end
+  end
+  context "integration" do
+    let(:valid) do
+      "<html><div><span class='fo'></span></div><div class='f'></div></html>"
+    end
+    let(:not_closed) do
+      "<html><div><span class='fo'></span><div class='f'></div></html>"
+    end
+    let(:not_opened) do
+      "<html><div></span></div><div></div></html>"
+    end
+    let(:tree) do
+      Saxxy::ContextTree.new do
+        on("div", class: nil) do |text, elem, attrs|
+          @counts[:div] += 1
+        end
+        under("div") do
+          on("span", class: /foo?/) do |text, elem, attrs|
+            @counts[:span] += 1
+          end
+        end
+      end
+    end
+    def parse(string, tree)
+      parser(tree).parse_string(string)
+    end
+    before { @counts = { div: 0, span: 0 } }
+    describe "valid html" do
+      it "should change the div count" do
+        pending("Libxml generates double callbacks") do
+          expect { parse(valid, tree) }.to change { @counts[:div] }.from(0).to(1)
+        end
+      end
+      it "should change the span count" do
+        pending("Libxml generates double callbacks") do
+          expect { parse(valid, tree) }.to change { @counts[:span] }.from(0).to(1)
+        end
+      end
+    end
+    describe "not closed div" do
+      it "should change the div count" do
+        pending("Libxml does not handle malformed html") do
+          expect { parse(not_closed, tree) }.to change { @counts[:div] }.from(0).to(1)
+        end
+      end
+      it "should change the span count" do
+        pending("Libxml does not handle malformed html") do
+          expect { parse(not_closed, tree) }.to change { @counts[:span] }.from(0).to(1)
+        end
+      end
+    end
+    describe "not opened span" do
+      it "should change the div count" do
+        pending("Libxml does not handle malformed html") do
+          expect { parse(not_opened, tree) }.to change { @counts[:div] }.from(0).to(2)
+        end
+      end
+      it "should not change the span count" do
+        pending("Libxml does not handle malformed html") do
+          expect { parse(not_opened, tree) }.to_not change { @counts[:span] }
+        end
+      end
+    end
+  end
+end

data/spec/saxxy/parsers/nokogiri_spec.rb ADDED

@@ -0,0 +1,200 @@
+require "spec_helper"
+require "saxxy/utils/agent"
+require "saxxy/context_tree"
+describe Saxxy::Parsers::Nokogiri do
+  def parser(*args)
+    Saxxy::Parsers::Nokogiri.new(*args)
+  end
+  describe "#initialize" do
+    let(:tree) { Saxxy::ContextTree.new {} }
+    let(:subject) { parser(tree, {foo: :bar}) }
+    it "should set the options" do
+      subject.options.should == {foo: :bar}
+    end
+    it "should set the context tree" do
+      subject.context_tree.should == tree
+    end
+  end
+  describe "#parse_io" do
+    let(:tree) { Saxxy::ContextTree.new {} }
+    let(:subject) { parser(tree) }
+    it "should delegate the call to the underlying parser" do
+      obj = Object.new
+      io = IO.new(0)
+      subject.stub(new_parser: obj)
+      obj.should_receive(:parse_io).with(io, 'UTF-8')
+      subject.parse_io(io)
+    end
+  end
+  describe "#parse_file" do
+    let(:tree) { Saxxy::ContextTree.new {} }
+    let(:subject) { parser(tree) }
+    it "should delegate the call to the underlying parser" do
+      obj = Object.new
+      file = File.new(0)
+      subject.stub(new_parser: obj)
+      obj.should_receive(:parse_file).with(file.path, 'UTF-8')
+      subject.parse_file(file.path)
+    end
+  end
+  describe "#parse_string" do
+    let(:tree) { Saxxy::ContextTree.new {} }
+    let(:subject) { parser(tree) }
+    it "should delegate the call to the underlying parsers' parse_memory" do
+      obj = Object.new
+      string = ""
+      subject.stub(new_parser: obj)
+      obj.should_receive(:parse_memory).with(string, 'UTF-8')
+      subject.parse_string(string)
+    end
+  end
+  context "node count" do
+    let(:valid) do
+      "<html><div><span class='fo'></span></div><div class='f'></div></html>"
+    end
+    let(:not_closed) do
+      "<html><div><span class='fo'></span><div class='f'></div></html>"
+    end
+    let(:not_opened) do
+      "<html><div></span></div><div></div></html>"
+    end
+    let(:tree) do
+      Saxxy::ContextTree.new do
+        on("div", class: nil) do |text, elem, attrs|
+          @counts[:div] += 1
+        end
+        under("div") do
+          on("span", class: /foo?/) do |text, elem, attrs|
+            @counts[:span] += 1
+          end
+        end
+      end
+    end
+    def parse(string, tree)
+      parser(tree).parse_string(string)
+    end
+    before { @counts = { div: 0, span: 0 } }
+    describe "valid html" do
+      it "should change the div count" do
+        expect { parse(valid, tree) }.to change { @counts[:div] }.from(0).to(1)
+      end
+      it "should change the span count" do
+        expect { parse(valid, tree) }.to change { @counts[:span] }.from(0).to(1)
+      end
+    end
+    describe "not closed div" do
+      it "should change the div count" do
+        expect { parse(not_closed, tree) }.to change { @counts[:div] }.from(0).to(1)
+      end
+      it "should change the span count" do
+        expect { parse(not_closed, tree) }.to change { @counts[:span] }.from(0).to(1)
+      end
+    end
+    describe "not opened span" do
+      it "should change the div count" do
+        expect { parse(not_opened, tree) }.to change { @counts[:div] }.from(0).to(2)
+      end
+      it "should not change the span count" do
+        expect { parse(not_opened, tree) }.to_not change { @counts[:span] }
+      end
+    end
+  end
+  context "text aggregation" do
+    let(:valid) do
+      "<html>0<div>1<span class='fo'>2</span>3</div><div class='f'>4</div></html>"
+    end
+    let(:not_closed) do
+      "<html>0<div>1<span class='fo'>2</span>3<div>4</div></html>"
+    end
+    let(:not_opened) do
+      "<html>0<div>1</span>23</div><div>4</div></html>"
+    end
+    let(:tree) do
+      Saxxy::ContextTree.new do
+        on("div", class: nil) do |text, elem, attrs|
+          @texts[:div] = (@texts[:div] || "") + text
+        end
+        under("div") do
+          on("span", class: /foo?/) do |text, elem, attrs|
+            @texts[:span] = (@texts[:span] || "") + text
+          end
+        end
+      end
+    end
+    def parse(string, tree)
+      parser(tree).parse_string(string)
+    end
+    before { @texts = { div: nil, span: nil } }
+    describe "valid html" do
+      it "should change the div text" do
+        expect { parse(valid, tree) }.to change { @texts[:div] }.to("123")
+      end
+      it "should change the span text" do
+        expect { parse(valid, tree) }.to change { @texts[:span] }.to("2")
+      end
+    end
+    describe "not closed div" do
+      it "should change the div text" do
+        expect { parse(not_closed, tree) }.to change { @texts[:div] }.to("41234")
+      end
+      it "should change the span text" do
+        expect { parse(not_closed, tree) }.to change { @texts[:span] }.to("2")
+      end
+    end
+    describe "not opened span" do
+      it "should change the div text" do
+        expect { parse(not_opened, tree) }.to change { @texts[:div] }.to("1234")
+      end
+      it "should not change the span text" do
+        expect { parse(not_opened, tree) }.to_not change { @texts[:span] }
+      end
+    end
+  end
+end

data/spec/saxxy/parsers/ox_spec.rb ADDED

@@ -0,0 +1,175 @@
+require "spec_helper"
+require "saxxy/utils/agent"
+require "saxxy/context_tree"
+# We have :not_jruby here because travis-ci does not
+# support C extensions for jruby.
+describe "Saxxy::Parsers::Ox", :not_jruby do
+  def parser(*args)
+    Saxxy::Parsers::Ox.new(*args)
+  end
+  describe "#initialize" do
+    let(:tree) { Saxxy::ContextTree.new {} }
+    let(:subject) { parser(tree, {foo: :bar}) }
+    it "should set the options" do
+      subject.options.should == {foo: :bar}
+    end
+    it "should set the context tree" do
+      subject.context_tree.should == tree
+    end
+  end
+  describe "#parse_*" do
+    let(:tree) { Saxxy::ContextTree.new {} }
+    let(:subject) { parser(tree) }
+    it "#parse_io should delegate the call to parse" do
+      ::Ox.should_receive(:sax_parse)
+      subject.parse_io(StringIO.new(""))
+    end
+    it "#parse_string should delegate the call to parse" do
+      ::Ox.should_receive(:sax_parse)
+      subject.parse_string("")
+    end
+  end
+  context "node count" do
+    let(:valid) do
+      "<html><div><span class='fo'></span></div><div class='f'></div></html>"
+    end
+    let(:not_closed) do
+      "<html><div><span class='fo'></span><div class='f'></div></html>"
+    end
+    let(:not_opened) do
+      "<html><div></span></div><div></div></html>"
+    end
+    let(:tree) do
+      Saxxy::ContextTree.new do
+        on("div", class: nil) do |text, elem, attrs|
+          @counts[:div] += 1
+        end
+        under("div") do
+          on("span", class: /foo?/) do |text, elem, attrs|
+            @counts[:span] += 1
+          end
+        end
+      end
+    end
+    def parse(string, tree)
+      parser(tree).parse_string(string)
+    end
+    before { @counts = { div: 0, span: 0 } }
+    describe "valid html" do
+      it "should change the div count" do
+        expect { parse(valid, tree) }.to change { @counts[:div] }.from(0).to(1)
+      end
+      it "should change the span count" do
+        expect { parse(valid, tree) }.to change { @counts[:span] }.from(0).to(1)
+      end
+    end
+    describe "not closed div" do
+      it "should change the div count" do
+        expect { parse(not_closed, tree) }.to change { @counts[:div] }.from(0).to(1)
+      end
+      it "should change the span count" do
+        expect { parse(not_closed, tree) }.to change { @counts[:span] }.from(0).to(1)
+      end
+    end
+    describe "not opened span" do
+      it "should change the div count" do
+        expect { parse(not_opened, tree) }.to change { @counts[:div] }.from(0).to(2)
+      end
+      it "should not change the span count" do
+        expect { parse(not_opened, tree) }.to_not change { @counts[:span] }
+      end
+    end
+  end
+  context "text aggregation" do
+    let(:valid) do
+      "<html>0<div>1<span class='fo'>2</span>3</div><div class='f'>4</div></html>"
+    end
+    let(:not_closed) do
+      "<html>0<div>1<span class='fo'>2</span>3<div>4</div></html>"
+    end
+    let(:not_opened) do
+      "<html>0<div>1</span>23</div><div>4</div></html>"
+    end
+    let(:tree) do
+      Saxxy::ContextTree.new do
+        on("div", class: nil) do |text, elem, attrs|
+          @texts[:div] = (@texts[:div] || "") + text
+        end
+        under("div") do
+          on("span", class: /foo?/) do |text, elem, attrs|
+            @texts[:span] = (@texts[:span] || "") + text
+          end
+        end
+      end
+    end
+    def parse(string, tree)
+      parser(tree).parse_string(string)
+    end
+    before { @texts = { div: nil, span: nil } }
+    describe "valid html" do
+      it "should change the div text" do
+        expect { parse(valid, tree) }.to change { @texts[:div] }.to("123")
+      end
+      it "should change the span text" do
+        expect { parse(valid, tree) }.to change { @texts[:span] }.to("2")
+      end
+    end
+    describe "not closed div" do
+      it "should change the div text" do
+        expect { parse(not_closed, tree) }.to change { @texts[:div] }.to("41234")
+      end
+      it "should change the span text" do
+        expect { parse(not_closed, tree) }.to change { @texts[:span] }.to("2")
+      end
+    end
+    describe "not opened span" do
+      it "should change the div text" do
+        expect { parse(not_opened, tree) }.to change { @texts[:div] }.to("1234")
+      end
+      it "should not change the span text" do
+        expect { parse(not_opened, tree) }.to_not change { @texts[:span] }
+      end
+    end
+  end
+end