nokogumbo 1.0 → 1.1

checksums.yaml

@@ -1,15 +1,15 @@
 ---
 !binary "U0hBMQ==":
   metadata.gz: !binary |-
-    YzMwY2Q3N2Y1YWRmNDhiYzYzNzdmMDZmOGNkYzU3YmE4YThmMGMwMg==
+    MDM0N2MwNTE2MzI0MmFjNTZmYzQ5YTk2MDMwNWQ1YzVlNTk5NTMzYQ==
   data.tar.gz: !binary |-
-    YzZlNDYxNzNhNzA3NzQ0OGE4ZTAyZTYxYWM2MWVkNGU0MzZjMjU1Yw==
+    OTNlOWZkMDc0NTc3N2U5MjY1ODhlNTEwMmMxMmMxOTBiYTA0NTViZA==
 !binary "U0hBNTEy":
   metadata.gz: !binary |-
-    NDdmOGQ5Nzc0M2FkYTM4NzMwYmNkMjk0ZTMyMzYzYTYzMDBmNzMxNTczNTFl
-    ZjIwMjAwNmRmM2EyZGRkNmU1NDM5Y2M0MjNkM2ZiZjk5YzgwNDc1YWZiNTQ2
-    MDk2MTBlN2QzZGNjNjAyZWExODZlNGY1YTE3Y2JjYjY1NTQwNDQ=
+    YjI2NzhjYzE0ZjQ1OTA3MDRiNWJjOGZkNzRlZDNhOTQ2N2ViODZjNDFlOWE3
+    Zjk1MTY0MmQ2ZDgwMTQxYzczNDQxYTFmYjdiNGY3ZjAwZDYxNzVlNjE2MWJh
+    NDQyYzk5MGU5ZTZlNDdkZWUxMjE3ZjhmNWIxZWIzYzFkZDRkYTA=
   data.tar.gz: !binary |-
-    NTgwODgxYWU4NzMyMDk1M2VkZjEyZTAzMTBiODQ3N2I1OTUxYzBkNTQyMGQx
-    MWUwYTI3OGZhMmNhOTU0MTBiMmZlMDBlZjg4NDgyODc2ODJkMzkyNDJhZmMx
-    ZmYzODA0YTI2Njk4MjQxNGI1NDAyMzdiN2UyZWEzMzBkMWJkZTg=
+    YjE4NDhmMTIxNTI5MThlM2Q1MmRkNmVkNWRmYmFjNjllYzQ3YTFkMWJmNWI1
+    MWRkNDI2NzY0MWRhNjVlMjNjNmQ2NWZjOTQ3YzUwNzc3ZmNiMDBjNTBlZTBk
+    YTZkYzU2NTQ3NDNmMzIxNzA4NzQ3ZDI2NmFjY2Y3YWU3MmFmNTY=

data/gumbo-parser/src/tokenizer.c

@@ -442,7 +442,7 @@ static void finish_token(GumboParser* parser, GumboToken* token) {
   reset_token_start_point(tokenizer);
   token->original_text.length =
       tokenizer->_token_start - token->original_text.data;
-  if (token->original_text.data[token->original_text.length - 1] == '\r') {
+  if (token->original_text.length > 0 && token->original_text.data[token->original_text.length - 1] == '\r') {
     // The UTF8 iterator will ignore carriage returns in the input stream, which
     // means that the next token may start one past a \r character.  The pointer
     // arithmetic above results in that \r being appended to the original text

data/lib/nokogumbo.rb

@@ -26,26 +26,48 @@ module Nokogiri
 
     # Fetch and parse a HTML document from the web, following redirects,
     # handling https, and determining the character encoding using HTML5
-    # rules.  +uri+ may be a +String+ or a +URI+.  +limit+ controls the
-    # number of redirects that will be followed.
-    def self.get(uri, limit=10)
+    # rules.  +uri+ may be a +String+ or a +URI+.  +options+ contains
+    # http headers and special options.  Everything which is not a
+    # special option is considered a header.  Special options include:
+    #  * :follow_limit => number of redirects which are followed
+    #  * :basic_auth => [username, password]
+    def self.get(uri, options={})
+      headers = options.clone
+      headers = {:follow_limit => headers} if Numeric === headers # deprecated
+      limit=headers[:follow_limit] ? headers.delete(:follow_limit).to_i : 10
+
       require 'net/http'
       uri = URI(uri) unless URI === uri
 
       http = Net::HTTP.new(uri.host, uri.port)
+
+      # TLS / SSL support
       if uri.scheme == 'https'
         http.use_ssl = true 
         http.verify_mode = OpenSSL::SSL::VERIFY_NONE
       end
+
       request = Net::HTTP::Get.new(uri.request_uri)
+
+      # basic authentication
+      auth = headers.delete(:basic_auth)
+      auth ||= [uri.user, uri.password] if uri.user and uri.password
+      request.basic_auth auth.first, auth.last if auth
+
+      # remaining options are treated as headers
+      headers.each {|key, value| request[key.to_s] = value.to_s}
+
       response = http.request(request)
 
       case response
       when Net::HTTPSuccess
-        parse(reencode(response.body, response['content-type']))
+        doc = parse(reencode(response.body, response['content-type']))
+        doc.instance_variable_set('@response', response)
+        doc.class.send(:attr_reader, :response)
+        doc
       when Net::HTTPRedirection
         response.value if limit <= 1
-        get(response['location'], limit-1)
+        get(response['location'], options.merge(:follow_limit => limit-1))
       else
         response.value
       end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: nokogumbo
 version: !ruby/object:Gem::Version
-  version: '1.0'
+  version: '1.1'
 platform: ruby
 authors:
 - Sam Ruby
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-09-10 00:00:00.000000000 Z
+date: 2013-09-12 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri