hpricot 0.7-x86-mswin32

data/ext/hpricot_scan/test.rb

@@ -0,0 +1,4 @@
+require './hpricot_scan.so'
+
+doc = "<doc><person><test>YESSS</test></person><train>SET</train></doc>"
+p Hpricot.scan(doc)

data/extras/mingw-rbconfig.rb

@@ -0,0 +1,176 @@
+
+# This rbconfig.rb corresponds to a Ruby installation for win32 cross-compiled
+# with mingw under i686-linux. It can be used to cross-compile extensions for
+# win32 using said toolchain.
+# 
+# This file assumes that a cross-compiled mingw32 build (compatible with the
+# mswin32 builds) is installed under $HOME/ruby-mingw32.
+
+module Config
+  #RUBY_VERSION == "1.8.5" or
+  #  raise "ruby lib version (1.8.5) doesn't match executable version (#{RUBY_VERSION})"
+
+  mingw32 = ENV['MINGW32_RUBY'] || "#{ENV["HOME"]}/ruby-mingw32"
+  mingwpre = ENV['MINGW32_PREFIX']
+  TOPDIR = File.dirname(__FILE__).chomp!("/lib/ruby/1.8/i386-mingw32")
+  DESTDIR = '' unless defined? DESTDIR
+  CONFIG = {}
+  CONFIG["DESTDIR"] = DESTDIR
+  CONFIG["INSTALL"] = "/usr/bin/install -c"
+  CONFIG["prefix"] = (TOPDIR || DESTDIR + mingw32)
+  CONFIG["EXEEXT"] = ".exe"
+  CONFIG["ruby_install_name"] = "ruby"
+  CONFIG["RUBY_INSTALL_NAME"] = "ruby"
+  CONFIG["RUBY_SO_NAME"] = "msvcrt-ruby18"
+  CONFIG["SHELL"] = "/bin/sh"
+  CONFIG["PATH_SEPARATOR"] = ":"
+  CONFIG["PACKAGE_NAME"] = ""
+  CONFIG["PACKAGE_TARNAME"] = ""
+  CONFIG["PACKAGE_VERSION"] = ""
+  CONFIG["PACKAGE_STRING"] = ""
+  CONFIG["PACKAGE_BUGREPORT"] = ""
+  CONFIG["exec_prefix"] = "$(prefix)"
+  CONFIG["bindir"] = "$(exec_prefix)/bin"
+  CONFIG["sbindir"] = "$(exec_prefix)/sbin"
+  CONFIG["libexecdir"] = "$(exec_prefix)/libexec"
+  CONFIG["datadir"] = "$(prefix)/share"
+  CONFIG["sysconfdir"] = "$(prefix)/etc"
+  CONFIG["sharedstatedir"] = "$(prefix)/com"
+  CONFIG["localstatedir"] = "$(prefix)/var"
+  CONFIG["libdir"] = "$(exec_prefix)/lib"
+  CONFIG["includedir"] = "$(prefix)/include"
+  CONFIG["oldincludedir"] = "/usr/include"
+  CONFIG["infodir"] = "$(prefix)/info"
+  CONFIG["mandir"] = "$(prefix)/man"
+  CONFIG["build_alias"] = "i686-linux"
+  CONFIG["host_alias"] = "#{mingwpre}"
+  CONFIG["target_alias"] = "i386-mingw32"
+  CONFIG["ECHO_C"] = ""
+  CONFIG["ECHO_N"] = "-n"
+  CONFIG["ECHO_T"] = ""
+  CONFIG["LIBS"] = "-lwsock32 "
+  CONFIG["MAJOR"] = "1"
+  CONFIG["MINOR"] = "8"
+  CONFIG["TEENY"] = "4"
+  CONFIG["build"] = "i686-pc-linux"
+  CONFIG["build_cpu"] = "i686"
+  CONFIG["build_vendor"] = "pc"
+  CONFIG["build_os"] = "linux"
+  CONFIG["host"] = "i586-pc-mingw32msvc"
+  CONFIG["host_cpu"] = "i586"
+  CONFIG["host_vendor"] = "pc"
+  CONFIG["host_os"] = "mingw32msvc"
+  CONFIG["target"] = "i386-pc-mingw32"
+  CONFIG["target_cpu"] = "i386"
+  CONFIG["target_vendor"] = "pc"
+  CONFIG["target_os"] = "mingw32"
+  CONFIG["CC"] = "#{mingwpre}-gcc"
+  CONFIG["CFLAGS"] = "-g -O2 "
+  CONFIG["LDFLAGS"] = ""
+  CONFIG["CPPFLAGS"] = ""
+  CONFIG["OBJEXT"] = "o"
+  CONFIG["CPP"] = "#{mingwpre}-gcc -E"
+  CONFIG["EGREP"] = "grep -E"
+  CONFIG["GNU_LD"] = "yes"
+  CONFIG["CPPOUTFILE"] = "-o conftest.i"
+  CONFIG["OUTFLAG"] = "-o "
+  CONFIG["YACC"] = "bison -y"
+  CONFIG["RANLIB"] = "#{mingwpre}-ranlib"
+  CONFIG["AR"] = "#{mingwpre}-ar"
+  CONFIG["NM"] = "#{mingwpre}-nm"
+  CONFIG["WINDRES"] = "#{mingwpre}-windres"
+  CONFIG["DLLWRAP"] = "#{mingwpre}-dllwrap"
+  CONFIG["OBJDUMP"] = "#{mingwpre}-objdump"
+  CONFIG["LN_S"] = "ln -s"
+  CONFIG["SET_MAKE"] = ""
+  CONFIG["INSTALL_PROGRAM"] = "$(INSTALL)"
+  CONFIG["INSTALL_SCRIPT"] = "$(INSTALL)"
+  CONFIG["INSTALL_DATA"] = "$(INSTALL) -m 644"
+  CONFIG["RM"] = "rm -f"
+  CONFIG["CP"] = "cp"
+  CONFIG["MAKEDIRS"] = "mkdir -p"
+  CONFIG["LIBOBJS"] = " fileblocks$(U).o crypt$(U).o flock$(U).o acosh$(U).o win32$(U).o"
+  CONFIG["ALLOCA"] = ""
+  CONFIG["DLDFLAGS"] = " -Wl,--enable-auto-import,--export-all"
+  CONFIG["ARCH_FLAG"] = ""
+  CONFIG["STATIC"] = ""
+  CONFIG["CCDLFLAGS"] = ""
+  CONFIG["LDSHARED"] = "#{mingwpre}-gcc -shared -s"
+  CONFIG["DLEXT"] = "so"
+  CONFIG["DLEXT2"] = "dll"
+  CONFIG["LIBEXT"] = "a"
+  CONFIG["LINK_SO"] = ""
+  CONFIG["LIBPATHFLAG"] = " -L\"%s\""
+  CONFIG["RPATHFLAG"] = ""
+  CONFIG["LIBPATHENV"] = ""
+  CONFIG["TRY_LINK"] = ""
+  CONFIG["STRIP"] = "strip"
+  CONFIG["EXTSTATIC"] = ""
+  CONFIG["setup"] = "Setup"
+  CONFIG["MINIRUBY"] = "ruby -rfake"
+  CONFIG["PREP"] = "fake.rb"
+  CONFIG["RUNRUBY"] = "$(MINIRUBY) -I`cd $(srcdir)/lib; pwd`"
+  CONFIG["EXTOUT"] = ".ext"
+  CONFIG["ARCHFILE"] = ""
+  CONFIG["RDOCTARGET"] = ""
+  CONFIG["XCFLAGS"] = " -DRUBY_EXPORT"
+  CONFIG["XLDFLAGS"] = " -Wl,--stack,0x02000000 -L."
+  CONFIG["LIBRUBY_LDSHARED"] = "#{mingwpre}-gcc -shared -s"
+  CONFIG["LIBRUBY_DLDFLAGS"] = " -Wl,--enable-auto-import,--export-all -Wl,--out-implib=$(LIBRUBY)"
+  CONFIG["rubyw_install_name"] = "rubyw"
+  CONFIG["RUBYW_INSTALL_NAME"] = "rubyw"
+  CONFIG["LIBRUBY_A"] = "lib$(RUBY_SO_NAME)-static.a"
+  CONFIG["LIBRUBY_SO"] = "$(RUBY_SO_NAME).dll"
+  CONFIG["LIBRUBY_ALIASES"] = ""
+  CONFIG["LIBRUBY"] = "lib$(LIBRUBY_SO).a"
+  CONFIG["LIBRUBYARG"] = "$(LIBRUBYARG_SHARED)"
+  CONFIG["LIBRUBYARG_STATIC"] = "-l$(RUBY_SO_NAME)-static"
+  CONFIG["LIBRUBYARG_SHARED"] = "-l$(RUBY_SO_NAME)"
+  CONFIG["SOLIBS"] = "$(LIBS)"
+  CONFIG["DLDLIBS"] = ""
+  CONFIG["ENABLE_SHARED"] = "yes"
+  CONFIG["MAINLIBS"] = ""
+  CONFIG["COMMON_LIBS"] = "m"
+  CONFIG["COMMON_MACROS"] = ""
+  CONFIG["COMMON_HEADERS"] = "windows.h winsock.h"
+  CONFIG["EXPORT_PREFIX"] = ""
+  CONFIG["MINIOBJS"] = "dmydln.o"
+  CONFIG["MAKEFILES"] = "Makefile GNUmakefile"
+  CONFIG["arch"] = "i386-mingw32"
+  CONFIG["sitearch"] = "i386-msvcrt"
+  CONFIG["sitedir"] = "$(prefix)/lib/ruby/site_ruby"
+  CONFIG["configure_args"] = "'--host=#{mingwpre}' '--target=i386-mingw32' '--build=i686-linux' '--prefix=#{mingw32}' 'build_alias=i686-linux' 'host_alias=#{mingwpre}' 'target_alias=i386-mingw32'"
+  CONFIG["NROFF"] = "/usr/bin/nroff"
+  CONFIG["MANTYPE"] = "doc"
+  CONFIG["LTLIBOBJS"] = " fileblocks$(U).lo crypt$(U).lo flock$(U).lo acosh$(U).lo win32$(U).lo"
+  CONFIG["ruby_version"] = "$(MAJOR).$(MINOR)"
+  CONFIG["rubylibdir"] = "$(libdir)/ruby/$(ruby_version)"
+  CONFIG["archdir"] = "$(rubylibdir)/$(arch)"
+  CONFIG["sitelibdir"] = "$(sitedir)/$(ruby_version)"
+  CONFIG["sitearchdir"] = "$(sitelibdir)/$(sitearch)"
+  CONFIG["topdir"] = File.dirname(__FILE__)
+  MAKEFILE_CONFIG = {}
+  CONFIG.each{|k,v| MAKEFILE_CONFIG[k] = v.dup}
+  def Config::expand(val, config = CONFIG)
+    val.gsub!(/\$\$|\$\(([^()]+)\)|\$\{([^{}]+)\}/) do |var|
+      if !(v = $1 || $2)
+	'$'
+      elsif key = config[v = v[/\A[^:]+(?=(?::(.*?)=(.*))?\z)/]]
+	pat, sub = $1, $2
+	config[v] = false
+	Config::expand(key, config)
+	config[v] = key
+	key = key.gsub(/#{Regexp.quote(pat)}(?=\s|\z)/n) {sub} if pat
+	key
+      else
+	var
+      end
+    end
+    val
+  end
+  CONFIG.each_value do |val|
+    Config::expand(val)
+  end
+end
+RbConfig = Config # compatibility for ruby-1.9
+CROSS_COMPILING = nil unless defined? CROSS_COMPILING

data/lib/hpricot.rb

@@ -0,0 +1,26 @@
+# == About hpricot.rb
+#
+# All of Hpricot's various part are loaded when you use <tt>require 'hpricot'</tt>.
+#
+# * hpricot_scan: the scanner (a C extension for Ruby) which turns an HTML stream into tokens.
+# * hpricot/parse.rb: uses the scanner to sort through tokens and give you back a complete document object.
+# * hpricot/tag.rb: sets up objects for the various types of elements in an HTML document.
+# * hpricot/modules.rb: categorizes the various elements using mixins.
+# * hpricot/traverse.rb: methods for searching documents.
+# * hpricot/elements.rb: methods for dealing with a group of elements as an Hpricot::Elements list.
+# * hpricot/inspect.rb: methods for displaying documents in a readable form.
+
+# If available, Nikolai's UTF-8 library will ease use of utf-8 documents.
+# See http://git.bitwi.se/ruby-character-encodings.git/.
+begin
+  require 'encoding/character/utf-8'
+rescue LoadError
+end
+
+require 'hpricot_scan'
+require 'hpricot/tag'
+require 'hpricot/modules'
+require 'hpricot/traverse'
+require 'hpricot/inspect'
+require 'hpricot/parse'
+require 'hpricot/builder'

data/lib/hpricot/blankslate.rb

@@ -0,0 +1,63 @@
+#!/usr/bin/env ruby
+#--
+# Copyright 2004 by Jim Weirich (jim@weirichhouse.org).
+# All rights reserved.
+
+# Permission is granted for use, copying, modification, distribution,
+# and distribution of modified versions of this work as long as the
+# above copyright notice is included.
+#++
+
+module Hpricot
+
+  # BlankSlate provides an abstract base class with no predefined
+  # methods (except for <tt>\_\_send__</tt> and <tt>\_\_id__</tt>).
+  # BlankSlate is useful as a base class when writing classes that
+  # depend upon <tt>method_missing</tt> (e.g. dynamic proxies).
+  class BlankSlate
+    class << self
+
+      # Hide the method named +name+ in the BlankSlate class.  Don't
+      # hide +instance_eval+ or any method beginning with "__".
+      def hide(name)
+	undef_method name if
+	  instance_methods.include?(name.to_s) and
+	  name !~ /^(__|instance_eval)/
+      end
+    end
+
+    instance_methods.each { |m| hide(m) }
+  end
+end
+
+# Since Ruby is very dynamic, methods added to the ancestors of
+# BlankSlate <em>after BlankSlate is defined</em> will show up in the
+# list of available BlankSlate methods.  We handle this by defining a
+# hook in the Object and Kernel classes that will hide any defined
+module Kernel
+  class << self
+    alias_method :hpricot_slate_method_added, :method_added
+
+    # Detect method additions to Kernel and remove them in the
+    # BlankSlate class.
+    def method_added(name)
+      hpricot_slate_method_added(name)
+      return if self != Kernel
+      Hpricot::BlankSlate.hide(name)
+    end
+  end
+end
+
+class Object
+  class << self
+    alias_method :hpricot_slate_method_added, :method_added
+
+    # Detect method additions to Object and remove them in the
+    # BlankSlate class.
+    def method_added(name)
+      hpricot_slate_method_added(name)
+      return if self != Object
+      Hpricot::BlankSlate.hide(name)
+    end
+  end
+end

data/lib/hpricot/builder.rb

@@ -0,0 +1,216 @@
+require 'hpricot/tags'
+require 'fast_xs'
+require 'hpricot/blankslate'
+require 'hpricot/htmlinfo'
+
+module Hpricot
+  # XML unescape
+  def self.uxs(str)
+    str.to_s.
+        gsub(/\&(\w+);/) { [NamedCharacters[$1] || ??].pack("U*") }.
+        gsub(/\&\#(\d+);/) { [$1.to_i].pack("U*") }
+  end
+
+  def self.build(ele = Doc.new, assigns = {}, &blk)
+    ele.extend Builder
+    assigns.each do |k, v|
+      ele.instance_variable_set("@#{k}", v)
+    end
+    ele.instance_eval(&blk)
+    ele
+  end
+
+  module Builder
+
+    @@default = {
+      :indent => 0,
+      :output_helpers => true,
+      :output_xml_instruction => true,
+      :output_meta_tag => true,
+      :auto_validation => true,
+      :tagset => Hpricot::XHTMLTransitional,
+      :root_attributes => {
+        :xmlns => 'http://www.w3.org/1999/xhtml', :'xml:lang' => 'en', :lang => 'en'
+      }
+    }
+
+    def self.set(option, value)
+      @@default[option] = value
+    end
+
+    def add_child ele
+      ele.parent = self
+      self.children ||= []
+      self.children << ele
+      ele
+    end
+
+    # Write a +string+ to the HTML stream, making sure to escape it.
+    def text!(string)
+      add_child Text.new(string.fast_xs)
+    end
+
+    # Write a +string+ to the HTML stream without escaping it.
+    def text(string)
+      add_child Text.new(string)
+      nil
+    end
+    alias_method :<<, :text
+    alias_method :concat, :text
+
+    # Create a tag named +tag+. Other than the first argument which is the tag name,
+    # the arguments are the same as the tags implemented via method_missing.
+    def tag!(tag, *args, &block)
+      ele_id = nil
+      if @auto_validation and @tagset
+          if !@tagset.tagset.has_key?(tag)
+              raise InvalidXhtmlError, "no element `#{tag}' for #{tagset.doctype}"
+          elsif args.last.respond_to?(:to_hash)
+              attrs = args.last.to_hash
+
+              if @tagset.forms.include?(tag) and attrs[:id]
+                attrs[:name] ||= attrs[:id]
+              end
+
+              attrs.each do |k, v|
+                  atname = k.to_s.downcase.intern
+                  unless k =~ /:/ or @tagset.tagset[tag].include? atname
+                      raise InvalidXhtmlError, "no attribute `#{k}' on #{tag} elements"
+                  end
+                  if atname == :id
+                      ele_id = v.to_s
+                      if @elements.has_key? ele_id
+                          raise InvalidXhtmlError, "id `#{ele_id}' already used (id's must be unique)."
+                      end
+                  end
+              end
+          end
+      end
+
+      # turn arguments into children or attributes
+      childs = []
+      attrs = args.grep(Hash)
+      childs.concat((args - attrs).flatten.map do |x|
+        if x.respond_to? :to_html
+          Hpricot.make(x.to_html)
+        elsif x
+          Text.new(x.fast_xs)
+        end
+      end.flatten)
+      attrs = attrs.inject({}) do |hsh, ath|
+        ath.each do |k, v|
+          hsh[k] = v.to_s.fast_xs if v
+        end
+        hsh
+      end
+
+      # create the element itself
+      tag = tag.to_s
+      f = Elem.new(tag, attrs, childs, ETag.new(tag))
+
+      # build children from the block
+      if block
+        build(f, &block)
+      end
+
+      add_child f
+      f
+    end
+
+    def build(*a, &b)
+      Hpricot.build(*a, &b)
+    end
+
+    # Every HTML tag method goes through an html_tag call.  So, calling <tt>div</tt> is equivalent
+    # to calling <tt>html_tag(:div)</tt>.  All HTML tags in Hpricot's list are given generated wrappers
+    # for this method.
+    #
+    # If the @auto_validation setting is on, this method will check for many common mistakes which
+    # could lead to invalid XHTML.
+    def html_tag(sym, *args, &block)
+      if @auto_validation and @tagset.self_closing.include?(sym) and block
+        raise InvalidXhtmlError, "the `#{sym}' element is self-closing, please remove the block"
+      elsif args.empty? and block.nil?
+        CssProxy.new(self, sym)
+      else
+        tag!(sym, *args, &block)
+      end
+    end
+
+    XHTMLTransitional.tags.each do |k|
+      class_eval %{
+        def #{k}(*args, &block)
+          html_tag(#{k.inspect}, *args, &block)
+        end
+      }
+    end
+
+    def doctype(target, pub, sys)
+      add_child DocType.new(target, pub, sys)
+    end
+
+    remove_method :head
+
+    # Builds a head tag.  Adds a <tt>meta</tt> tag inside with Content-Type
+    # set to <tt>text/html; charset=utf-8</tt>.
+    def head(*args, &block)
+      tag!(:head, *args) do
+        tag!(:meta, "http-equiv" => "Content-Type", "content" => "text/html; charset=utf-8") if @output_meta_tag
+        instance_eval(&block)
+      end
+    end
+
+    # Builds an html tag.  An XML 1.0 instruction and an XHTML 1.0 Transitional doctype
+    # are prepended.  Also assumes <tt>:xmlns => "http://www.w3.org/1999/xhtml",
+    # :lang => "en"</tt>.
+    def xhtml_transitional(attrs = {}, &block)
+      # self.tagset = Hpricot::XHTMLTransitional
+      xhtml_html(attrs, &block)
+    end
+
+    # Builds an html tag with XHTML 1.0 Strict doctype instead.
+    def xhtml_strict(attrs = {}, &block)
+      # self.tagset = Hpricot::XHTMLStrict
+      xhtml_html(attrs, &block)
+    end
+
+    private
+
+    def xhtml_html(attrs = {}, &block)
+      instruct! if @output_xml_instruction
+      doctype(:html, *@@default[:tagset].doctype)
+      tag!(:html, @@default[:root_attributes].merge(attrs), &block)
+    end
+
+  end
+
+  # Class used by Markaby::Builder to store element options.  Methods called
+  # against the CssProxy object are added as element classes or IDs.
+  #
+  # See the README for examples.
+  class CssProxy < BlankSlate
+
+    # Creates a CssProxy object.
+    def initialize(builder, sym)
+      @builder, @sym, @attrs = builder, sym, {}
+    end
+
+    # Adds attributes to an element.  Bang methods set the :id attribute.
+    # Other methods add to the :class attribute.
+    def method_missing(id_or_class, *args, &block)
+      if (idc = id_or_class.to_s) =~ /!$/
+        @attrs[:id] = $`
+      else
+        @attrs[:class] = @attrs[:class].nil? ? idc : "#{@attrs[:class]} #{idc}".strip
+      end
+
+      if block or args.any?
+        args.push(@attrs)
+        return @builder.tag!(@sym, *args, &block)
+      end
+
+      return self
+    end
+
+  end
+end