wriggler 0.1.0 → 0.5.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 5d35c4b6d7c7da4483e293b47fdbcc06a9348172
-  data.tar.gz: 9a7372283313d57c7ab1d3d39320c544422d5b2c
+  metadata.gz: 1d741f12caa9d0cae037e2689e76ff0aa6adee13
+  data.tar.gz: d84a237b2f9c49ef76df0a1fa7db330d32d031ea
 SHA512:
-  metadata.gz: 0cb56c3f6062e77532fe7676acb7b68140a8b2fe4b9d3b21015b77b159fbc259b295aee19082210444804c632bdc647247f7314fdb82908ea604582b82908790
-  data.tar.gz: f8c9cbd5a96acbb701a9ecd0e5fc50c34e5a0b6ad88f56464ea6c969a2d0fa314f8ffc34dece4f71df8598571cce1db1423c1fa7b4b109f6283f71c93a522a0e
+  metadata.gz: 7fd896183312ea3a2f9ab5e00836dfaf12f7af1486796deedd2f80f1c3f851ae437d29d8c48566a8f89c8ff04148b51c797ad82a8518fd65fb025178f75c80c0
+  data.tar.gz: 0aa7b338518a6285e5bb3aac82ff401b0157a3b72f805b49f2b066851e1aa81f22a7f03924db2625ea50eece17c6492942424664e380fa2c50ab89d5dd0f0b8d

data/dirtest/nested_fldr/test5.xml

@@ -0,0 +1 @@
+<test>If this appears it works</test>

data/dirtest/test1.xml

@@ -1,6 +1,7 @@
 <root>
   <sitcoms>
     <sitcom>
+      <test>This is different</test>
       <name>Married with Children</name>
       <characters>
         <character>Al Bundy</character>

data/dirtest/test4.html

@@ -0,0 +1,7 @@
+<div id = "buttons">
+    <button id="bye">Bye</button>
+    <button id="hello">Hello</button>
+</div>
+<div>
+    <p>1: <span id="greeting">Greeting</span></p>
+</div>

data/lib/wriggler/version.rb

@@ -1,3 +1,3 @@
 module Wriggler
-  VERSION = "0.1.0"
+  VERSION = "0.5.0"
 end

data/lib/wriggler.rb

@@ -1,32 +1,43 @@
 require "wriggler/version"
 require "nokogiri"
+require "find"
 
 module Wriggler
 	attr_reader :content, :directory
 
-  def crawl(tags=[], directory="", subdirectories=true)
-		@content = Hash[tags.map {|k| [k, []]}]		#Hash with content
-		@subdirectories = subdirectories					#Default true for the existence of subdirs
-		@directory = directory 										#Directory to grab files from
+  def self.crawl(tags=[], directory="")
+    @content = Hash[tags.map {|k| [k, []]}]   #Hash with content
+    @directory = directory                    #Current top-level directory
 
-		navigate_directory
-		Writer.write_to_csv(@content)
-	end
+    navigate_directory
+    Writer.write(@content)
+  end
 
   private
 
-  def navigate_directory
+  def self.navigate_directory
  		#Set the cwd to the given dir send to gather all nested files from there
  		Dir.chdir(@directory) 
- 		gather_files
+ 		open_files(gather_files)
   end
 
-  def gather_files
-  	#Gathers all of the HTML or XML files from this and all subdirectories
+  def self.gather_files
+  	#Gathers all of the HTML or XML files from this and all subdirectories into an array
+    file_array = []
+    Find.find(@directory) do |file|
+      file_array << file if file.match(/\.xml\Z/) || file.match(/\.html\Z/)
+    end
+    file_array
+  end
 
+  def self.open_files(file_array)
+    #Opens all the files in the file_array
+    file_array.each do |file|
+      open_next_file(file)
+    end
   end
 
-  def open_next_file(file)
+  def self.open_next_file(file)
   	#Opens the next file on the list, depending on the extension passes it to HTML or XML
   	f = File.open(file)
 
@@ -37,44 +48,52 @@ module Wriggler
   	end
   end
 
-  def is_HTML?(file)
+  def self.is_HTML?(file)
   	#Determines, using a regex check, if it is an HTML file
   	file =~ /.html/
   end
 
-  def is_XML?(file)
+  def self.is_XML?(file)
   	#Determines, using a regex check, if it is an XML file
   	file =~ /.xml/
   end
 
-  def set_HTML(file)
+  def self.set_HTML(file)
   	#Set the HTML file into Nokogiri for crawling
   	doc = Nokogiri::HTML(file)
   	crawl_file(doc)
   end
 
-  def set_XML(file)
+  def self.set_XML(file)
   	#Set the XML file into Nokogiri for crawling
   	doc = Nokogiri::XML(file)
   	crawl_file(doc)
   end
 
-  def crawl_file(doc)
+  def self.crawl_file(doc)
   	#Crawl the Nokogiri Object for the file
   	@content.each_key do |key|
+      arr = []
   		if !doc.xpath("//#{key}").empty?				#Returns an empty array if tag is not present
-  			doc.xpath("//#{key}").map{ |tag| @content.fetch(key) << sanitize(tag.text) }
+  			doc.xpath("//#{key}").map{ |tag| arr << sanitize(tag.text) }
   		end
+      fill_content(arr, key)
   	end
   end
 
-  def sanitize(text)
+  def self.sanitize(text)
   	#Removes any escaped quotes, replaces them
-  	text.gsub(/"/, "'")					
+  	text.gsub(/"/, "'").lstrip.chomp				
+  end
+
+  def self.fill_content(arr, key)
+    #Doesn't shovel if there is no content found for the specific tag
+    !arr.empty? ? (@content.fetch(key) << arr) : nil
   end
 end
 
 module Writer
-	def write_to_csv(content)
+	def write(content)
+    @content = content
 	end
 end

data/test.rb

@@ -1,91 +1,93 @@
 require "nokogiri"
+require "find"
 
 class Wriggler
-	def initialize(tags=[], directory="", subdirectories=true)
-		@content = Hash[tags.map {|k| [k, []]}]		#Hash with content
-		@subdirectories = subdirectories					#Default true for the existence of subdirs
-		@directory = directory 										#Directory to grab files from
+ def initialize(tags=[], directory="", subdirectories=true)
+    @content = Hash[tags.map {|k| [k, []]}]   #Hash with content
+    @directory = directory                    #Current top-level directory
+    @subdirectories = subdirectories          #Default true for the existence of subdirs
 
-		navigate_directory
-		# Writer.write_to_csv(@content)
-	end
+    navigate_directory
+    p @content
+    # Writer.write(@content)
+  end
 
   private
 
   def navigate_directory
- 		#Set the cwd to the given dir send to gather all nested files from there
- 		Dir.chdir(@directory) 
- 		gather_files
+    #Set the cwd to the given dir send to gather all nested files from there
+    Dir.chdir(@directory) 
+    open_files(gather_files)
   end
 
   def gather_files
-  	#Gathers all of the HTML or XML files from this and all subdirectories
-    open_next_file("test1.xml")
-    puts "=============="
-    puts "1:"
-    p @content
-    puts "=============="
-    puts ""
-    open_next_file("test2.xml")
-    puts "=============="
-    puts "2:"
-    p @content
-    puts "=============="
-    puts ""
-    open_next_file("test3.xml")
-    puts "=============="
-    puts "3:"
-    p @content
-    puts "=============="
-    puts ""
+    #Gathers all of the HTML or XML files from this and all subdirectories into an array
+    file_array = []
+    Find.find(@directory) do |f|
+      file_array << f if f.match(/\.xml\Z/) || f.match(/\.html\Z/)
+    end
+    file_array
+  end
+
+  def open_files(file_array)
+    file_array.each do |file|
+      open_next_file(file)
+    end
   end
 
   def open_next_file(file)
-  	#Opens the next file on the list, depending on the extension passes it to HTML or XML
-  	f = File.open(file)
-
-  	if is_html?(file)
-  		set_HTML(f)
-  	elsif is_xml?(file)
-  		set_XML(f)
-  	end
+    #Opens the next file on the list, depending on the extension passes it to HTML or XML
+    f = File.open(file)
+
+    if is_HTML?(file)
+      set_HTML(f)
+    elsif is_XML?(file)
+      set_XML(f)
+    end
   end
 
-  def is_html?(file)
-  	#Determines, using a regex check, if it is an HTML file
-  	file =~ /.html/
+  def is_HTML?(file)
+    #Determines, using a regex check, if it is an HTML file
+    file =~ /.html/
   end
 
-  def is_xml?(file)
-  	#Determines, using a regex check, if it is an XML file
-  	file =~ /.xml/
+  def is_XML?(file)
+    #Determines, using a regex check, if it is an XML file
+    file =~ /.xml/
   end
 
   def set_HTML(file)
-  	#Set the HTML file into Nokogiri for crawling
-  	doc = Nokogiri::HTML(file)
-  	crawl_file(doc)
+    #Set the HTML file into Nokogiri for crawling
+    doc = Nokogiri::HTML(file)
+    crawl_file(doc)
   end
 
   def set_XML(file)
-  	#Set the XML file into Nokogiri for crawling
-  	doc = Nokogiri::XML(file)
-  	crawl_file(doc)
+    #Set the XML file into Nokogiri for crawling
+    doc = Nokogiri::XML(file)
+    crawl_file(doc)
   end
 
   def crawl_file(doc)
-  	#Crawl the Nokogiri Object for the file
-  	@content.each_key do |key|
-  		if !doc.xpath("//#{key}").empty?				#Returns an empty array if tag is not present
-  			doc.xpath("//#{key}").map{ |tag| @content.fetch(key) << sanitize(tag.text) }
-  		end
-  	end
+    #Crawl the Nokogiri Object for the file
+    @content.each_key do |key|
+      arr = []
+      if !doc.xpath("//#{key}").empty?        #Returns an empty array if tag is not present
+        doc.xpath("//#{key}").map{ |tag| arr << sanitize(tag.text) }
+      end
+      fill_content(arr, key)
+    end
   end
 
   def sanitize(text)
-  	#Removes any escaped quotes, replaces them
-  	text.gsub(/"/, "'")					
+    #Removes any escaped quotes, replaces them
+    text.gsub(/"/, "'").lstrip.chomp        
+  end
+
+  def fill_content(arr, key)
+    #Doesn't shovel if there is no content found for the specific tag
+    !arr.empty? ? (@content.fetch(key) << arr) : nil
   end
 end
 
-test = Wriggler.new(["character", "content", "name", "title"], "/Users/47900/Desktop/Ruby/wriggler/dirtest", false)
+test = Wriggler.new(["character", "content", "name", "title", "test"], "/Users/47900/Desktop/Ruby/wriggler/dirtest", false)

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: wriggler
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 0.5.0
 platform: ruby
 authors:
 - Elliott Young
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2015-06-07 00:00:00.000000000 Z
+date: 2015-06-08 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -85,9 +85,11 @@ files:
 - Rakefile
 - bin/console
 - bin/setup
+- dirtest/nested_fldr/test5.xml
 - dirtest/test1.xml
 - dirtest/test2.xml
 - dirtest/test3.xml
+- dirtest/test4.html
 - lib/wriggler.rb
 - lib/wriggler/version.rb
 - test.rb