oga 0.3.2 → 0.3.3

data/ext/java/org/liboga/xml/Lexer.rl

@@ -194,13 +194,23 @@ public class Lexer extends RubyObject
     }
 
     /**
-     * See * Oga::XML::Lexer#literal_html_element? for more information.
+     * @see Oga::XML::Lexer#html_script?
      */
-    public Boolean literal_html_element_p()
+    public Boolean html_script_p()
     {
         ThreadContext context = this.runtime.getCurrentContext();
 
-        return this.callMethod(context, "literal_html_element?").isTrue();
+        return this.callMethod(context, "html_script?").isTrue();
+    }
+
+    /**
+     * @see Oga::XML::Lexer#html_style?
+     */
+    public Boolean html_style_p()
+    {
+        ThreadContext context = this.runtime.getCurrentContext();
+
+        return this.callMethod(context, "html_style?").isTrue();
     }
 }
 

data/ext/ragel/base_lexer.rl

@@ -46,21 +46,31 @@
     # stack.
     #
 
-    newline = '\r\n' | '\n' | '\r';
+    newline    = '\r\n' | '\n' | '\r';
+    whitespace = [ \t];
+    ident_char = [a-zA-Z0-9\-_];
+    identifier = ident_char+;
+
+    whitespace_or_newline = whitespace | newline;
 
     action count_newlines {
         if ( fc == '\n' ) lines++;
     }
 
-    whitespace = [ \t];
-    ident_char = [a-zA-Z0-9\-_];
-    identifier = ident_char+;
+    action advance_newline {
+        advance_line(1);
+    }
+
+    action hold_and_return {
+        fhold;
+        fret;
+    }
 
     # Comments
     #
-    # http://www.w3.org/TR/html-markup/syntax.html#comments
+    # http://www.w3.org/TR/html/syntax.html#comments
     #
-    # Unlike the W3 specification these rules *do* allow character sequences
+    # Unlike the W3C specification these rules *do* allow character sequences
     # such as `--` and `->`. Putting extra checks in for these sequences would
     # actually make the rules/actions more complex.
     #
@@ -98,7 +108,7 @@
 
     # CDATA
     #
-    # http://www.w3.org/TR/html-markup/syntax.html#cdata-sections
+    # http://www.w3.org/TR/html/syntax.html#cdata-sections
     #
     # In HTML CDATA tags have no meaning/are not supported. Oga does
     # support them but treats their contents as plain text.
@@ -232,7 +242,7 @@
 
     # DOCTYPES
     #
-    # http://www.w3.org/TR/html-markup/syntax.html#doctype-syntax
+    # http://www.w3.org/TR/html/syntax.html#the-doctype
     #
     # These rules support the 3 flavours of doctypes:
     #
@@ -240,10 +250,18 @@
     # 2. Deprecated doctypes, the more verbose ones used prior to HTML5.
     # 3. Legacy doctypes
     #
-    doctype_start = '<!DOCTYPE'i whitespace+;
+    doctype_start = '<!DOCTYPE'i (whitespace_or_newline+ $count_newlines);
 
     action start_doctype {
         callback_simple(id_on_doctype_start);
+
+        if ( lines > 0 )
+        {
+            advance_line(lines);
+
+            lines = 0;
+        }
+
         fnext doctype;
     }
 
@@ -277,10 +295,6 @@
         squote => start_string_squote;
         dquote => start_string_dquote;
 
-        # Whitespace inside doctypes is ignored since there's no point in
-        # including it.
-        whitespace;
-
         identifier => {
             callback(id_on_doctype_name, data, encoding, ts, te);
         };
@@ -289,6 +303,10 @@
             callback_simple(id_on_doctype_end);
             fnext main;
         };
+
+        newline => advance_newline;
+
+        whitespace;
     *|;
 
     # XML declaration tags
@@ -338,7 +356,7 @@
 
     # Elements
     #
-    # http://www.w3.org/TR/html-markup/syntax.html#syntax-elements
+    # http://www.w3.org/TR/html/syntax.html#syntax-elements
     #
     # Lexing of elements is broken up into different machines that handle the
     # name/namespace, contents of the open tag and the body of an element. The
@@ -358,6 +376,12 @@
         callback_simple(id_on_element_end);
     }
 
+    action close_element_fnext_main {
+        callback_simple(id_on_element_end);
+
+        fnext main;
+    }
+
     # Machine used for lexing the name/namespace of an element.
     element_name := |*
         identifier ':' => {
@@ -370,16 +394,11 @@
         };
     *|;
 
-    action hold_start_element_head {
-        fhold;
-        fnext element_head;
-    }
-
     # Characters that can be used for unquoted HTML attribute values.
     # See https://html.spec.whatwg.org/multipage/introduction.html#intro-early-example
     # for more info.
     html_unquoted_value = ^(
-        squote | dquote | '`' | '=' | '<' | '>' | whitespace | newline
+        squote | dquote | '`' | '=' | '<' | '>' | whitespace_or_newline
     )+;
 
     # Machine used for processing HTML attribute values.
@@ -399,24 +418,33 @@
             callback_simple(id_on_string_squote);
         };
 
-        any => hold_start_element_head;
+        any => hold_and_return;
     *|;
 
     # Machine used for processing XML attribute values.
     xml_attribute_value := |*
-        squote => start_string_squote;
-        dquote => start_string_dquote;
-        any    => hold_start_element_head;
+        # The following two actions use "fnext" instead of "fcall". Combined
+        # with "element_head" using "fcall" to jump to this machine this means
+        # we can return back to "element_head" after processing a single string.
+        squote => {
+            callback_simple(id_on_string_squote);
+
+            fnext string_squote;
+        };
+
+        dquote => {
+            callback_simple(id_on_string_dquote);
+
+            fnext string_dquote;
+        };
+
+        any => hold_and_return;
     *|;
 
     # Machine used for processing the contents of an element's starting tag.
     # This includes the name, namespace and attributes.
     element_head := |*
-        whitespace;
-
-        newline => {
-            callback_simple(id_advance_line);
-        };
+        newline => advance_newline;
 
         # Attribute names and namespaces.
         identifier ':' => {
@@ -431,11 +459,11 @@
         '=' => {
             if ( html_p )
             {
-                fnext html_attribute_value;
+                fcall html_attribute_value;
             }
             else
             {
-                fnext xml_attribute_value;
+                fcall xml_attribute_value;
             }
         };
 
@@ -443,9 +471,13 @@
         '>' => {
             callback_simple(id_on_element_open_end);
 
-            if ( literal_html_element_p() )
+            if ( html_script_p() )
             {
-                fnext literal_html_element;
+                fnext html_script;
+            }
+            else if ( html_style_p() )
+            {
+                fnext html_style;
             }
             else
             {
@@ -458,12 +490,14 @@
             callback_simple(id_on_element_end);
             fnext main;
         };
+
+        any;
     *|;
 
     # Text
     #
     # http://www.w3.org/TR/xml/#syntax
-    # http://www.w3.org/TR/html-markup/syntax.html#text-syntax
+    # http://www.w3.org/TR/html/syntax.html#text
     #
     # Text content is everything leading up to certain special tags such as "</"
     # and "<?".
@@ -482,6 +516,17 @@
     terminate_text = '</' | '<!' | '<?' | element_start;
     allowed_text   = (any* -- terminate_text) $count_newlines;
 
+    action emit_text {
+        callback(id_on_text, data, encoding, ts, te);
+
+        if ( lines > 0 )
+        {
+            advance_line(lines);
+
+            lines = 0;
+        }
+    }
+
     text := |*
         terminate_text | allowed_text => {
             callback(id_on_text, data, encoding, ts, te);
@@ -517,36 +562,17 @@
     # Certain tags in HTML can contain basically anything except for the literal
     # closing tag. Two examples are script and style tags.  As a result of this
     # we can't use the regular text machine.
-    literal_html_closing_tags = '</script>' | '</style>';
-    literal_html_allowed = (any* -- literal_html_closing_tags) $count_newlines;
-
-    literal_html_element := |*
-        literal_html_allowed => {
-            callback(id_on_text, data, encoding, ts, te);
-
-            if ( lines > 0 )
-            {
-                advance_line(lines);
-
-                lines = 0;
-            }
-        };
-
-        literal_html_allowed %{ mark = p; } literal_html_closing_tags => {
-            callback(id_on_text, data, encoding, ts, mark);
-
-            p    = mark - 1;
-            mark = 0;
 
-            if ( lines > 0 )
-            {
-                advance_line(lines);
+    literal_html_allowed = (^'<'+ | '<'+) $count_newlines;
 
-                lines = 0;
-            }
+    html_script := |*
+        literal_html_allowed => emit_text;
+        '</script>'          => close_element_fnext_main;
+    *|;
 
-            fnext main;
-        };
+    html_style := |*
+        literal_html_allowed => emit_text;
+        '</style>'           => close_element_fnext_main;
     *|;
 
     # The main machine aka the entry point of Ragel.

data/lib/oga/version.rb

@@ -1,3 +1,3 @@
 module Oga
-  VERSION = '0.3.2'
+  VERSION = '0.3.3'
 end # Oga

data/lib/oga/xml/lexer.rb

@@ -40,12 +40,18 @@ module Oga
     class Lexer
       attr_reader :html
 
+      # @return [String]
+      HTML_SCRIPT = 'script'
+
+      # @return [String]
+      HTML_STYLE = 'style'
+
       ##
       # Names of HTML tags of which the content should be lexed as-is.
       #
       # @return [Array]
       #
-      LITERAL_HTML_ELEMENTS = %w{script style}
+      LITERAL_HTML_ELEMENTS = [HTML_SCRIPT, HTML_STYLE]
 
       ##
       # @param [String|IO] data The data to lex. This can either be a String or
@@ -189,12 +195,17 @@ module Oga
       end
 
       ##
-      # Returns true if the current element's content should be lexed as-is.
+      # @return [TrueClass|FalseClass]
       #
+      def html_script?
+        return html? && current_element == HTML_SCRIPT
+      end
+
+      ##
       # @return [TrueClass|FalseClass]
       #
-      def literal_html_element?
-        return html? && LITERAL_HTML_ELEMENTS.include?(current_element)
+      def html_style?
+        return html? && current_element == HTML_STYLE
       end
 
       ##

data/lib/oga/xml/parser.rb

@@ -59,7 +59,7 @@ class Parser < LL::Driver
 
   CONFIG.rules = [
     [3, 0, 0, 1], # 0
-    [3, 1, 4, 22, 6, 0], # 1
+    [3, 1, 4, 23, 6, 0], # 1
     [3, 2, 0, 3], # 2
     [3, 3, 0, 7], # 3
     [3, 4, 0, 9], # 4
@@ -71,8 +71,8 @@ class Parser < LL::Driver
     [3, 10, 1, 6], # 10
     [3, 11, 0, 6, 1, 7], # 11
     [3, 12, 1, 6, 0, 5], # 12
-    [3, 13, 5, 23, 6, 0], # 13
-    [3, 14, 1, 6, 8, 24, 0, 20], # 14
+    [3, 13, 5, 24, 6, 0], # 13
+    [3, 14, 1, 6, 8, 25, 0, 21], # 14
     [3, 15, 1, 6], # 15
     [3, 16, 1, 15, 0, 8, 1, 13], # 16
     [3, 17, 0, 8, 1, 14], # 17
@@ -87,21 +87,23 @@ class Parser < LL::Driver
     [3, 26, 1, 17, 1, 18], # 26
     [3, 27, 0, 16, 0, 13, 1, 16], # 27
     [3, 28, 1, 19, 0, 1, 0, 14], # 28
-    [3, 29, 4, 25, 6, 0], # 29
-    [3, 30, 8, 26, 1, 20, 1, 21], # 30
-    [3, 31, 8, 27, 1, 20], # 31
+    [3, 29, 4, 26, 6, 0], # 29
+    [3, 30, 8, 27, 1, 20, 1, 21], # 30
+    [3, 31, 8, 28, 1, 20], # 31
     [3, 32, 1, 23, 0, 16, 1, 22], # 32
-    [3, 33, 1, 1], # 33
-    [3, 34, 1, 3, 0, 21, 1, 3], # 34
-    [3, 35, 1, 2, 0, 21, 1, 2], # 35
-    [3, 36, 0, 21, 1, 4], # 36
-    [3, 37, 2, 0], # 37
-    [3, 38, 0, 2], # 38
-    [3, 39, 1, 9], # 39
-    [3, 40, 0, 20], # 40
-    [3, 41, 0, 17], # 41
-    [3, 42, 0, 20], # 42
-    [3, 43, 0, 20], # 43
+    [3, 33, 0, 20, 1, 1], # 33
+    [3, 34, 0, 20, 1, 1], # 34
+    [3, 35, 2, 0], # 35
+    [3, 36, 1, 3, 0, 22, 1, 3], # 36
+    [3, 37, 1, 2, 0, 22, 1, 2], # 37
+    [3, 38, 0, 22, 1, 4], # 38
+    [3, 39, 2, 0], # 39
+    [3, 40, 0, 2], # 40
+    [3, 41, 1, 9], # 41
+    [3, 42, 0, 21], # 42
+    [3, 43, 0, 17], # 43
+    [3, 44, 0, 21], # 44
+    [3, 45, 0, 21], # 45
   ].freeze
 
   CONFIG.table = [
@@ -125,14 +127,15 @@ class Parser < LL::Driver
     [-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, 31, 30, -1, -1, -1, -1, -1, -1], # 17
     [-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, 32, -1, -1, -1, -1, -1], # 18
     [-1, 33, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1], # 19
-    [-1, -1, 35, 34, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1], # 20
-    [37, 37, 37, 37, 36, 37, 37, 37, 37, 37, 37, 37, 37, 37, 37, 37, 37, 37, 37, 37, 37, 37, 37, 37, 37, 37, 37, 37], # 21
-    [-1, 38, -1, -1, -1, 38, -1, -1, -1, -1, 38, -1, -1, 38, -1, -1, 38, -1, -1, -1, -1, -1, 38, -1, 38, -1, -1, -1], # 22
-    [-1, -1, -1, -1, -1, -1, -1, -1, -1, 39, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1], # 23
-    [-1, -1, 40, 40, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1], # 24
-    [-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, 41, 41, -1, -1, -1, -1, -1, -1], # 25
-    [-1, -1, 42, 42, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1], # 26
-    [-1, -1, 43, 43, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1], # 27
+    [35, 34, 35, 35, 35, 35, 35, 35, 35, 35, 35, 35, 35, 35, 35, 35, 35, 35, 35, 35, 35, 35, 35, 35, 35, 35, 35, 35], # 20
+    [-1, -1, 37, 36, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1], # 21
+    [39, 39, 39, 39, 38, 39, 39, 39, 39, 39, 39, 39, 39, 39, 39, 39, 39, 39, 39, 39, 39, 39, 39, 39, 39, 39, 39, 39], # 22
+    [-1, 40, -1, -1, -1, 40, -1, -1, -1, -1, 40, -1, -1, 40, -1, -1, 40, -1, -1, -1, -1, -1, 40, -1, 40, -1, -1, -1], # 23
+    [-1, -1, -1, -1, -1, -1, -1, -1, -1, 41, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1], # 24
+    [-1, -1, 42, 42, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1], # 25
+    [-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, 43, 43, -1, -1, -1, -1, -1, -1], # 26
+    [-1, -1, 44, 44, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1], # 27
+    [-1, -1, 45, 45, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1], # 28
   ].freeze
 
   CONFIG.actions = [
@@ -169,17 +172,19 @@ class Parser < LL::Driver
     [:_rule_30, 3], # 30
     [:_rule_31, 2], # 31
     [:_rule_32, 3], # 32
-    [:_rule_33, 1], # 33
-    [:_rule_34, 3], # 34
-    [:_rule_35, 3], # 35
-    [:_rule_36, 2], # 36
-    [:_rule_37, 0], # 37
-    [:_rule_38, 1], # 38
-    [:_rule_39, 1], # 39
+    [:_rule_33, 2], # 33
+    [:_rule_34, 2], # 34
+    [:_rule_35, 0], # 35
+    [:_rule_36, 3], # 36
+    [:_rule_37, 3], # 37
+    [:_rule_38, 2], # 38
+    [:_rule_39, 0], # 39
     [:_rule_40, 1], # 40
     [:_rule_41, 1], # 41
     [:_rule_42, 1], # 42
     [:_rule_43, 1], # 43
+    [:_rule_44, 1], # 44
+    [:_rule_45, 1], # 45
   ].freeze
 
   ##
@@ -568,31 +573,35 @@ class Parser < LL::Driver
   end
 
   def _rule_33(val)
-     on_text(val[0]) 
+    
+      text = val[1] ? val[0] + val[1] : val[0]
+
+      on_text(text)
+    
   end
 
   def _rule_34(val)
-     val[1] 
+     val[1] ? val[0] + val[1] : val[0] 
   end
 
   def _rule_35(val)
-     val[1] 
+     nil 
   end
 
   def _rule_36(val)
-     val[0] + val[1] 
+     val[1] 
   end
 
   def _rule_37(val)
-     '' 
+     val[1] 
   end
 
   def _rule_38(val)
-    val[0]
+     val[0] + val[1] 
   end
 
   def _rule_39(val)
-    val[0]
+     '' 
   end
 
   def _rule_40(val)
@@ -610,6 +619,14 @@ class Parser < LL::Driver
   def _rule_43(val)
     val[0]
   end
+
+  def _rule_44(val)
+    val[0]
+  end
+
+  def _rule_45(val)
+    val[0]
+  end
 end
 end
 end