nokogumbo 0.7 → 0.8

data/README.md

@@ -6,7 +6,7 @@ Nokogumbo provides the ability for a Ruby program to invoke the
 and to access the result as a
 [Nokogiri::HTML::Document](http://nokogiri.org/Nokogiri/HTML/Document.html).
 
-Usage:
+Usage
 -----
 
 ```ruby
@@ -14,14 +14,22 @@ require 'nokogumbo'
 doc = Nokogiri::HTML5(string)
 ```
 
-Because HTML is often fetched via the web, a convenience interface is also
-provided:
+Because HTML is often fetched via the web, a convenience interface to
+HTTP get is also provided:
 
 ```ruby
 require 'nokogumbo'
 doc = Nokogiri::HTML5.get(uri)
 ```
-Notes:
+
+Example
+-----
+```ruby
+require 'nokogumbo'
+puts Nokogiri::HTML5.get('http://nokogiri.org').at('h1 abbr')['title']
+```
+
+Notes
 -----
 
 * The `Nokogiri::HTML5.parse` function takes a string and passes it to the
@@ -43,16 +51,17 @@ rules defined in the HTML5 specification for doing so.
 * Instead of returning `unknown` as the element name for unknown tags, the
 original tag name is returned verbatim.
 
-* The gem itself includes a copy of the Gumbo HTML5 parser.
+* If the Gumbo HTML5 parser is not already installed, the source for the
+parser will be downloaded and compiled into the Gem itself.
 
-Installation:
+Installation
 ============
 
 * Execute `rake gem`
 
 * [sudo] gem install pkg/nokogumbo*.gem
 
-Related efforts:
+Related efforts
 ============
 
 * [ruby-gumbo](https://github.com/galdor/ruby-gumbo#readme) - a ruby binding

data/lib/nokogumbo.rb

@@ -98,7 +98,11 @@ module Nokogiri
         encoding ||= Encoding::ISO_8859_1
 
         # change the encoding to match the detected or inferred encoding
-        body.force_encoding(encoding)
+        begin
+          body.force_encoding(encoding)
+        rescue ArgumentError
+          body.force_encoding(Encoding::ISO_8859_1)
+        end
       end
 
       body.encode(Encoding::UTF_8)

data/work/extconf.rb

@@ -1,7 +1,18 @@
 require 'mkmf'
 $CFLAGS = " -std=c99"
+
+# libxml2 libraries from http://www.xmlsoft.org/
 pkg_config('libxml-2.0')
-nokogiri_lib = Gem.find_files('nokogiri').first
+
+# nokogiri headers from gem install
+nokogiri_lib = Gem.find_files('nokogiri').first or gem 'nokogiri'
 nokogiri_ext = nokogiri_lib.sub(%r(lib/nokogiri$), 'ext/nokogiri')
 find_header('nokogiri.h', nokogiri_ext)
+
+# add in gumbo-parser source from github if not already installed
+unless have_library('gumbo', 'gumbo_parse') or File.exist? 'work/gumbo.h'
+  require 'fileutils'
+  FileUtils.cp Dir['../gumbo-parser/src/*'], '.'
+end
+
 create_makefile('nokogumboc')

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: nokogumbo
 version: !ruby/object:Gem::Version
-  version: '0.7'
+  version: '0.8'
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-08-25 00:00:00.000000000 Z
+date: 2013-08-27 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
@@ -40,31 +40,31 @@ files:
 - README.md
 - work/extconf.rb
 - work/nokogumbo.c
-- work/vector.c
-- work/string_buffer.c
-- work/error.c
-- work/attribute.c
-- work/char_ref.c
-- work/string_piece.c
-- work/tag.c
-- work/util.c
-- work/parser.c
-- work/utf8.c
-- work/tokenizer.c
-- work/utf8.h
-- work/token_type.h
-- work/util.h
-- work/tokenizer_states.h
-- work/error.h
-- work/parser.h
-- work/tokenizer.h
-- work/string_buffer.h
-- work/vector.h
-- work/string_piece.h
-- work/gumbo.h
-- work/attribute.h
-- work/char_ref.h
-- work/insertion_mode.h
+- gumbo-parser/src/utf8.h
+- gumbo-parser/src/token_type.h
+- gumbo-parser/src/util.h
+- gumbo-parser/src/vector.c
+- gumbo-parser/src/string_buffer.c
+- gumbo-parser/src/tokenizer_states.h
+- gumbo-parser/src/error.h
+- gumbo-parser/src/parser.h
+- gumbo-parser/src/error.c
+- gumbo-parser/src/tokenizer.h
+- gumbo-parser/src/string_buffer.h
+- gumbo-parser/src/vector.h
+- gumbo-parser/src/string_piece.h
+- gumbo-parser/src/attribute.c
+- gumbo-parser/src/char_ref.c
+- gumbo-parser/src/string_piece.c
+- gumbo-parser/src/gumbo.h
+- gumbo-parser/src/tag.c
+- gumbo-parser/src/util.c
+- gumbo-parser/src/parser.c
+- gumbo-parser/src/utf8.c
+- gumbo-parser/src/attribute.h
+- gumbo-parser/src/char_ref.h
+- gumbo-parser/src/insertion_mode.h
+- gumbo-parser/src/tokenizer.c
 homepage: https://github.com/rubys/nokogumbo/#readme
 licenses:
 - Apache 2.0