docmago_client 0.2.3 → 0.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: bd6d48c101e5c4d6f4e4bff7e744ca18a1864d5f
-  data.tar.gz: 4b720f936170d548c2128bdb72d7736d8ba7b481
+  metadata.gz: d6d8973a0f28f504ec927f92b7aac8809c177796
+  data.tar.gz: 27d1c2392e28e334e0cd6a930ab8f78a13b672b9
 SHA512:
-  metadata.gz: f19959e38dd442ed00feec70619929a9a205c39e6b67faffc4dd990bbba152373618a988cf5154db5023d9565c48397c8d33102ee0947ab9763775b0c6d6bbf8
-  data.tar.gz: 3c49d6eedc8503318598e23c71493fb245d649a9a950cb0d0c127a4424e31a0d452b40c5fe72e5cd2247474c825a6bbf22713ff61ca20d10145bd4c0a039686a
+  metadata.gz: a6323b2eab8a3b786b97f4a295e64cda4bec417d3f277f2731b33599facf32d6e65dc4d136d07191fdabcfa380f48f43f037c8e7951d000df12f5b903d004f69
+  data.tar.gz: 5929d731a6ec1e56ae8af0e84519b2c1fa2f06341852df0647b8bf3aa83b2008639fdf1e668d3b634e37ac143eff74b39e58d35a0da7aef601bb07e76dbe84f7

data/lib/docmago_client/html_resource_archiver.rb

@@ -1,7 +1,16 @@
+require 'digest'
+require 'open-uri'
 require 'addressable/uri'
 require 'nokogiri'
 require 'zip'
 
+class URI::Parser
+  def split url
+    a = Addressable::URI::parse url
+    [a.scheme, a.userinfo, a.host, a.port, nil, a.path, nil, a.query, a.fragment]
+  end
+end
+
 module DocmagoClient
   class HTMLResourceArchiver
     def initialize(html, base_path='.')
@@ -15,14 +24,17 @@ module DocmagoClient
         zipfile.get_output_stream("document.html") { |f| f.write @html }
         
         fetch_uris.each do |uri|
-          if File.exists?(resolve_uri(uri))
-            path = normalize_uri(uri).start_with?('/') ? normalize_uri(uri)[1..-1] : normalize_uri(uri)
-            zipfile.get_output_stream(path) { |f| f.write(File.read(resolve_uri(uri))) }
-          end
+          uri = Addressable::URI.parse uri.to_s.strip
+          path_digest = Digest::MD5.hexdigest(normalize_uri(uri))
+          
+          file_data   = open(uri).read if uri.absolute?
+          file_data ||= File.read(resolve_uri(uri)) if File.exists?(resolve_uri(uri))
+          
+          zipfile.get_output_stream(path_digest) { |f| f.write file_data } if file_data
         end
       end
     
-      return file_path
+      file_path
     end
   
     private

data/lib/docmago_client/version.rb

@@ -1,3 +1,3 @@
 module DocmagoClient
-  VERSION = "0.2.3"
+  VERSION = "0.3.0"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: docmago_client
 version: !ruby/object:Gem::Version
-  version: 0.2.3
+  version: 0.3.0
 platform: ruby
 authors:
 - Jan Habermann