ox 1.3.2 → 1.3.3

data/README.md

@@ -26,9 +26,12 @@ A fast XML parser and Object marshaller as a Ruby gem.
 
 ## <a name="release">Release Notes</a>
 
-### Release 1.3.2
+### Release 1.3.3
+
+ - Added an option to the SAX parser to convert special characters.
+
+ - The default options encoding is now used as the default for SAX parsing.
 
- - Changed SAX parser API for element and instruction attributes
 
 ## <a name="description">Description</a>
 
@@ -94,26 +97,66 @@ Ox is compatible with Ruby 1.8.7, 1.9.2, JRuby, and RBX.
 ### Generic XML Writing and Parsing:
 
     require 'ox'
-  
+
     doc = Ox::Document.new(:version => '1.0')
-  
+    
     top = Ox::Element.new('top')
     top[:name] = 'sample'
     doc << top
-  
+    
     mid = Ox::Element.new('middle')
     mid[:name] = 'second'
     top << mid
-  
+    
     bot = Ox::Element.new('bottom')
     bot[:name] = 'third'
     mid << bot
-  
+    
     xml = Ox.dump(doc)
-    puts xml
+    
+    # xml =
+    # <top name="sample">
+    #   <middle name="second">
+    #     <bottom name="third"/>
+    #   </middle>
+    # </top>
+    
     doc2 = Ox.parse(xml)
     puts "Same? #{doc == doc2}"
+    # true
+
+### SAX XML Parsing:
 
+    require 'stringio'
+    require 'ox'
+    
+    class Sample < ::Ox::Sax
+      def start_element(name); puts "start: #{name}";        end
+      def end_element(name);   puts "end: #{name}";          end
+      def attr(name, value);   puts "  #{name} => #{value}"; end
+      def text(value);         puts "text #{value}";         end
+    end
+    
+    io = StringIO.new(%{
+    <top name="sample">
+      <middle name="second">
+        <bottom name="third"/>
+      </middle>
+    </top>
+    })
+    
+    handler = Sample.new()
+    Ox.sax_parse(handler, io)
+    # outputs
+    # start: top
+    #   name => sample
+    # start: middle
+    #   name => second
+    # start: bottom
+    #   name => third
+    # end: bottom
+    # end: middle
+    # end: top
 
 ### Object XML format
 

data/ext/ox/ox.c

@@ -94,6 +94,7 @@ VALUE   trace_sym;
 VALUE   strict_sym;
 VALUE   with_dtd_sym;
 VALUE   with_instruct_sym;
+VALUE   convert_special_sym;
 VALUE   with_xml_sym;
 VALUE   empty_string;
 VALUE   zero_fixnum;
@@ -111,7 +112,7 @@ Cache   symbol_cache = 0;
 Cache   class_cache = 0;
 Cache   attr_cache = 0;
 
-static struct _Options  default_options = {
+struct _Options  default_options = {
     { '\0' },           // encoding
     2,                  // indent
     0,                  // trace
@@ -444,16 +445,31 @@ load_file(int argc, VALUE *argv, VALUE self) {
     return load(xml, argc - 1, argv + 1, self);
 }
 
-/* call-seq: sax_parse(handler, io)
+/* call-seq: sax_parse(handler, io, options)
  *
  * Parses an IO stream or file containing an XML document. Raises an exception
  * if the XML is malformed or the classes specified are not valid.
  * @param [Ox::Sax] handler SAX (responds to OX::Sax methods) like handler
  * @param [IO|String] io IO Object to read from
+ * @param [Hash] options parse options
+ * @param [true|false] :convert_special flag indicating special special characters like < are converted
  */
 static VALUE
-sax_parse(VALUE self, VALUE handler, VALUE io) {
-    ox_sax_parse(handler, io);
+sax_parse(int argc, VALUE *argv, VALUE self) {
+    int convert = 0;
+
+    if (argc < 2) {
+        rb_raise(rb_eArgError, "Wrong number of arguments to sax_parse.\n");
+    }
+    if (3 <= argc && rb_cHash == rb_obj_class(argv[2])) {
+        VALUE   h = argv[2];
+        VALUE   v;
+        
+        if (Qnil != (v = rb_hash_lookup(h, convert_special_sym))) {
+            convert = (Qtrue == v);
+        }
+    }
+    ox_sax_parse(argv[0], argv[1], convert);
 
     return Qnil;
 }
@@ -607,7 +623,7 @@ void Init_ox() {
     rb_define_module_function(Ox, "parse_obj", to_obj, 1);
     rb_define_module_function(Ox, "parse", to_gen, 1);
     rb_define_module_function(Ox, "load", load_str, -1);
-    rb_define_module_function(Ox, "sax_parse", sax_parse, 2);
+    rb_define_module_function(Ox, "sax_parse", sax_parse, -1);
 
     rb_define_module_function(Ox, "to_xml", dump, -1);
     rb_define_module_function(Ox, "dump", dump, -1);
@@ -668,6 +684,7 @@ void Init_ox() {
     with_dtd_sym = ID2SYM(rb_intern("with_dtd"));               rb_ary_push(keep, with_dtd_sym);
     with_instruct_sym = ID2SYM(rb_intern("with_instructions")); rb_ary_push(keep, with_instruct_sym);
     with_xml_sym = ID2SYM(rb_intern("with_xml"));               rb_ary_push(keep, with_xml_sym);
+    convert_special_sym = ID2SYM(rb_intern("convert_special")); rb_ary_push(keep, convert_special_sym);
 
     empty_string = rb_str_new2("");                             rb_ary_push(keep, empty_string);
     zero_fixnum = INT2NUM(0);                                   rb_ary_push(keep, zero_fixnum);

data/ext/ox/ox.h

@@ -198,11 +198,13 @@ typedef struct _Options {
 extern VALUE    parse(char *xml, ParseCallbacks pcb, char **endp, int trace, Effort effort);
 extern void     _raise_error(const char *msg, const char *xml, const char *current, const char* file, int line);
 
-extern void     ox_sax_parse(VALUE handler, VALUE io);
+extern void     ox_sax_parse(VALUE handler, VALUE io, int convert);
 
 extern char*    write_obj_to_str(VALUE obj, Options copts);
 extern void     write_obj_to_file(VALUE obj, const char *path, Options copts);
 
+extern struct _Options  default_options;
+
 extern VALUE    Ox;
 
 extern ID       at_id;

data/ext/ox/sax.c

@@ -51,6 +51,7 @@ typedef struct _SaxDrive {
     int         col;
     VALUE       handler;
     int         (*read_func)(struct _SaxDrive *dr);
+    int         convert_special;
     union {
         int     fd;
         VALUE   io;
@@ -69,7 +70,7 @@ typedef struct _SaxDrive {
 #endif
 } *SaxDrive;
 
-static void     sax_drive_init(SaxDrive dr, VALUE handler, VALUE io);
+static void     sax_drive_init(SaxDrive dr, VALUE handler, VALUE io, int convert);
 static void     sax_drive_cleanup(SaxDrive dr);
 static int      sax_drive_read(SaxDrive dr);
 static void     sax_drive_error(SaxDrive dr, const char *msg, int critical);
@@ -84,6 +85,7 @@ static int      read_text(SaxDrive dr);
 static int      read_attrs(SaxDrive dr, char c, char termc, char term2, int is_xml);
 static char     read_name_token(SaxDrive dr);
 static int      read_quoted_value(SaxDrive dr);
+static int      collapse_special(char *str);
 
 static VALUE    io_cb(VALUE rdr);
 static int      read_from_io(SaxDrive dr);
@@ -156,10 +158,10 @@ str2sym(const char *str) {
 
 
 void
-ox_sax_parse(VALUE handler, VALUE io) {
+ox_sax_parse(VALUE handler, VALUE io, int convert) {
     struct _SaxDrive    dr;
     
-    sax_drive_init(&dr, handler, io);
+    sax_drive_init(&dr, handler, io, convert);
 #if 0
     printf("*** sax_parse with these flags\n");
     printf("    has_instruct = %s\n", dr.has_instruct ? "true" : "false");
@@ -177,7 +179,7 @@ ox_sax_parse(VALUE handler, VALUE io) {
 }
 
 static void
-sax_drive_init(SaxDrive dr, VALUE handler, VALUE io) {
+sax_drive_init(SaxDrive dr, VALUE handler, VALUE io, int convert) {
     if (rb_respond_to(io, readpartial_id)) {
         VALUE   rfd;
 
@@ -200,6 +202,7 @@ sax_drive_init(SaxDrive dr, VALUE handler, VALUE io) {
     dr->line = 1;
     dr->col = 0;
     dr->handler = handler;
+    dr->convert_special = convert;
     dr->has_instruct = rb_respond_to(handler, instruct_id);
     dr->has_attr = rb_respond_to(handler, attr_id);
     dr->has_doctype = rb_respond_to(handler, doctype_id);
@@ -210,7 +213,11 @@ sax_drive_init(SaxDrive dr, VALUE handler, VALUE io) {
     dr->has_end_element = rb_respond_to(handler, end_element_id);
     dr->has_error = rb_respond_to(handler, error_id);
 #ifdef HAVE_RUBY_ENCODING_H
-    dr->encoding = 0;
+    if ('\0' == *default_options.encoding) {
+        dr->encoding = 0;
+    } else {
+        dr->encoding = rb_enc_find(default_options.encoding);
+    }
 #endif
 }
 
@@ -586,8 +593,13 @@ read_text(SaxDrive dr) {
     }
     *(dr->cur - 1) = '\0';
     if (dr->has_text) {
-        VALUE       args[1];
-
+        VALUE   args[1];
+        
+        if (dr->convert_special) {
+            if (0 != collapse_special(dr->str) && 0 != strchr(dr->str, '&')) {
+                sax_drive_error(dr, "invalid format, special character does not end with a semicolon", 0);
+            }
+        }
         args[0] = rb_str_new2(dr->str);
 #ifdef HAVE_RUBY_ENCODING_H
         if (0 != dr->encoding) {
@@ -642,6 +654,9 @@ read_attrs(SaxDrive dr, char c, char termc, char term2, int is_xml) {
             VALUE       args[2];
 
             args[0] = name;
+            if (0 != collapse_special(dr->str) && 0 != strchr(dr->str, '&')) {
+                sax_drive_error(dr, "invalid format, special character does not end with a semicolon", 0);
+            }
             args[1] = rb_str_new2(dr->str);
 #ifdef HAVE_RUBY_ENCODING_H
             if (0 != dr->encoding) {
@@ -758,3 +773,56 @@ read_from_fd(SaxDrive dr) {
     }
     return 0;
 }
+
+
+static int
+collapse_special(char *str) {
+    char        *s = str;
+    char        *b = str;
+
+    while ('\0' != *s) {
+        if ('&' == *s) {
+            int         c;
+            char        *end;
+            
+            s++;
+            if ('#' == *s) {
+                s++;
+                c = (int)strtol(s, &end, 10);
+                if (';' != *end) {
+                    return EDOM;
+                }
+                s = end + 1;
+            } else if (0 == strncasecmp(s, "lt;", 3)) {
+                c = '<';
+                s += 3;
+            } else if (0 == strncasecmp(s, "gt;", 3)) {
+                c = '>';
+                s += 3;
+            } else if (0 == strncasecmp(s, "amp;", 4)) {
+                c = '&';
+                s += 4;
+            } else if (0 == strncasecmp(s, "quot;", 5)) {
+                c = '"';
+                s += 5;
+            } else if (0 == strncasecmp(s, "apos;", 5)) {
+                c = '\'';
+                s += 5;
+            } else {
+                c = '?';
+                while (';' != *s++) {
+                    if ('\0' == *s) {
+                        return EDOM;
+                    }
+                }
+                s++;
+            }
+            *b++ = (char)c;
+        } else {
+            *b++ = *s++;
+        }
+    }
+    *b = '\0';
+
+    return 0;
+}

data/lib/ox/document.rb

@@ -16,5 +16,15 @@ module Ox
       @attributes[:standalone] = prolog[:standalone] unless prolog[:standalone].nil?
     end
     
+    # Returns the first Element in the document.
+    def root()
+      unless @nodes.nil?
+        @nodes.each do |n|
+          return n if n.is_a?(::Ox::Element)
+        end
+      end
+      nil
+    end
+
   end # Document
 end # Ox

data/lib/ox/version.rb

@@ -1,5 +1,5 @@
 
 module Ox
   # Current version of the module. 
-  VERSION = '1.3.2'
+  VERSION = '1.3.3'
 end

data/test/perf_sax.rb

@@ -14,7 +14,6 @@ end
 
 require 'optparse'
 require 'ox'
-require 'sample'
 require 'files'
 begin
   require 'nokogiri'

data/test/sax_example.rb

@@ -0,0 +1,37 @@
+#!/usr/bin/env ruby -wW1
+
+$: << '../lib'
+$: << '../ext'
+
+require 'stringio'
+require 'ox'
+
+class Sample < ::Ox::Sax
+  def start_element(name); puts "start: #{name}"; end
+  def end_element(name); puts "end: #{name}"; end
+  def attr(name, value); puts "  #{name} => #{value}"; end
+  def text(value); puts "text #{value}"; end
+end
+
+io = StringIO.new(%{
+<top name="sample">
+  <middle name="second">
+    <bottom name="third"/>
+  </middle>
+</top>
+})
+
+handler = Sample.new()
+Ox.sax_parse(handler, io)
+
+# outputs
+# start: top
+#   name => sample
+# start: middle
+#   name => second
+# start: bottom
+#   name => third
+# end: bottom
+# end: middle
+# end: top
+

data/test/sax_test.rb

@@ -92,10 +92,14 @@ class Func < ::Test::Unit::TestCase
                   [:end_element, :top]])
   end
 
-  def parse_compare(xml, expected, handler_class=AllSax)
+  def parse_compare(xml, expected, handler_class=AllSax, special=false)
     handler = handler_class.new()
     input = StringIO.new(xml)
-    Ox.sax_parse(handler, input)
+    if special
+      Ox.sax_parse(handler, input, :convert_special => true)
+    else
+      Ox.sax_parse(handler, input)
+    end
     assert_equal(expected, handler.calls)
   end
   
@@ -245,6 +249,15 @@ encoding = "UTF-8" ?>},
                   ])
   end
 
+  def test_sax_special
+    parse_compare(%{<top name="A&amp;Z">This is &lt;some&gt; text.</top>},
+                  [[:start_element, :top],
+                   [:attr, :name, 'A&Z'],
+                   [:text, "This is <some> text."],
+                   [:end_element, :top]
+                  ], AllSax, true)
+  end
+
   def test_sax_text_no_term
     parse_compare(%{<top>This is some text.},
                   [[:start_element, :top],

metadata

@@ -5,8 +5,8 @@ version: !ruby/object:Gem::Version
   segments: 
   - 1
   - 3
-  - 2
-  version: 1.3.2
+  - 3
+  version: 1.3.3
 platform: ruby
 authors: 
 - Peter Ohler
@@ -14,7 +14,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2011-09-21 00:00:00 +09:00
+date: 2011-09-24 00:00:00 +09:00
 default_executable: 
 dependencies: []
 
@@ -82,6 +82,7 @@ files:
 - test/perf_sax.rb
 - test/perf_write.rb
 - test/sample.rb
+- test/sax_example.rb
 - test/sax_test.rb
 - test/test.rb
 - test/Sample.graffle