ox 1.4.2 → 1.4.3

data/README.md

@@ -26,10 +26,10 @@ A fast XML parser and Object marshaller as a Ruby gem.
 
 ## <a name="release">Release Notes</a>
 
-### Release 1.4.2
+### Release 1.4.3
 
- - Made Ox more tolerant when parsing invalid XML files without a prolog.
- - DOCTYPE value was one character too long.
+ - In tolerant mode attribute values can now be surrounded by single quotes.
+ - In tolerant mode attribute values can now be without quotes as long as they do not contain spaces and are followed by a white space character.
 
 ## <a name="description">Description</a>
 

data/ext/ox/ox.c

@@ -355,16 +355,16 @@ load(char *xml, int argc, VALUE *argv, VALUE self) {
         obj = parse(xml, ox_obj_callbacks, 0, options.trace, options.effort);
         break;
     case GenMode:
-        obj = parse(xml, ox_gen_callbacks, 0, options.trace, StrictEffort);
+        obj = parse(xml, ox_gen_callbacks, 0, options.trace, options.effort);
         break;
     case LimMode:
-        obj = parse(xml, ox_limited_callbacks, 0, options.trace, StrictEffort);
+        obj = parse(xml, ox_limited_callbacks, 0, options.trace, options.effort);
         break;
     case NoMode:
         obj = parse(xml, ox_nomode_callbacks, 0, options.trace, options.effort);
         break;
     default:
-        obj = parse(xml, ox_gen_callbacks, 0, options.trace, StrictEffort);
+        obj = parse(xml, ox_gen_callbacks, 0, options.trace, options.effort);
         break;
     }
     free(xml);

data/ext/ox/parse.c

@@ -78,6 +78,23 @@ next_non_white(PInfo pi) {
     }
 }
 
+inline static void
+next_white(PInfo pi) {
+    for (; 1; pi->s++) {
+	switch(*pi->s) {
+	case ' ':
+	case '\t':
+	case '\f':
+	case '\n':
+	case '\r':
+	case '\0':
+	    return;
+	default:
+	    break;
+	}
+    }
+}
+
 VALUE
 parse(char *xml, ParseCallbacks pcb, char **endp, int trace, Effort effort) {
     struct _PInfo	pi;
@@ -599,26 +616,53 @@ read_cdata(PInfo pi) {
     }
 }
 
+inline static void
+next_non_token(PInfo pi) {
+    for (; 1; pi->s++) {
+	switch(*pi->s) {
+	case ' ':
+	case '\t':
+	case '\f':
+	case '\n':
+	case '\r':
+	case '/':
+	case '>':
+	    return;
+	default:
+	    break;
+	}
+    }
+}
+
 /* Assume the value starts immediately and goes until the quote character is
  * reached again. Do not read the character after the terminating quote.
  */
 static char*
 read_quoted_value(PInfo pi) {
-    char	*value;
+    char	*value = 0;
     
-    if ('"' != *pi->s) {
+    if ('"' == *pi->s || ('\'' == *pi->s && StrictEffort != pi->effort)) {
+        char	term = *pi->s;
+        
+        pi->s++;	// skip quote character
+        value = pi->s;
+        for (; *pi->s != term; pi->s++) {
+            if ('\0' == *pi->s) {
+                raise_error("invalid format, document not terminated", pi->str, pi->s);
+            }
+        }
+        *pi->s = '\0'; // terminate value
+        pi->s++;	   // move past quote
+    } else if (StrictEffort == pi->effort) {
 	raise_error("invalid format, expected a quote character", pi->str, pi->s);
-    }
-    pi->s++;	// skip quote character
-    value = pi->s;
-    for (; *pi->s != '"'; pi->s++) {
+    } else {
+        value = pi->s;
+        next_white(pi);
 	if ('\0' == *pi->s) {
 	    raise_error("invalid format, document not terminated", pi->str, pi->s);
-	}
+        }
+        *pi->s++ = '\0'; // terminate value
     }
-    *pi->s = '\0'; // terminate value
-    pi->s++;	   // move past quote
-
     return value;
 }
 

data/ext/ox/sax.c

@@ -131,6 +131,29 @@ next_non_white(SaxDrive dr) {
     return '\0';
 }
 
+/* Starts by reading a character so it is safe to use with an empty or
+ * compacted buffer.
+ */
+inline static char
+next_white(SaxDrive dr) {
+    char        c;
+
+    while ('\0' != (c = sax_drive_get(dr))) {
+	switch(c) {
+	case ' ':
+	case '\t':
+	case '\f':
+	case '\n':
+	case '\r':
+	case '\0':
+	    return c;
+	default:
+	    break;
+	}
+    }
+    return '\0';
+}
+
 inline static int
 is_white(char c) {
     switch(c) {
@@ -727,19 +750,23 @@ read_quoted_value(SaxDrive dr) {
     if (is_white(c)) {
         c = next_non_white(dr);
     }
-    if ('"' != c) {
-        sax_drive_error(dr, "invalid format, attibute value not in quotes", 1);
-        return -1;
-    }
-    dr->str = dr->cur;
-    while ('"' != (c = sax_drive_get(dr))) {
-        if ('\0' == c) {
-            sax_drive_error(dr, "invalid format, quoted value not terminated", 1);
-            return -1;
+    if ('"' == c || '\'' == c) {
+	char	term = c;
+
+        dr->str = dr->cur;
+        while (term != (c = sax_drive_get(dr))) {
+            if ('\0' == c) {
+                sax_drive_error(dr, "invalid format, quoted value not terminated", 1);
+                return -1;
+            }
         }
-    }
+    } else {
+        dr->str = dr->cur - 1;
+        if ('\0' == (c = next_white(dr))) {
+	    sax_drive_error(dr, "invalid format, attibute value not in quotes", 1);
+	}
+    }        
     *(dr->cur - 1) = '\0'; // terminate value
-
     return 0;
 }
 

data/lib/ox/version.rb

@@ -1,5 +1,5 @@
 
 module Ox
   # Current version of the module. 
-  VERSION = '1.4.2'
+  VERSION = '1.4.3'
 end

data/test/bug3.rb

@@ -3,21 +3,19 @@
 $: << '../lib'
 $: << '../ext'
 
-if __FILE__ == $0
-  if (i = ARGV.index('-I'))
-    x,path = ARGV.slice!(i, 2)
-    $: << path
-  end
-end
-
 require 'ox'
 
-def dump(cnt = 100000)
-  cnt.times do |i|
-    xml = Ox.dump([:inc, 1])
-    #puts xml
-    
+def name_it()
+  begin
+    "x".foo
+  rescue Exception => e
+    #puts e.message
+    xml = Ox.dump(e, effort: :tolerant)
+    puts xml
+    o = Ox.load(xml, mode: :object)
+    puts o.message
+    puts Ox.dump(e)
   end
 end
 
-dump()
+name_it()

data/test/func.rb

@@ -222,6 +222,24 @@ class Func < ::Test::Unit::TestCase
     assert_equal('html', doc.nodes[0].value)
   end
 
+  def test_quote_value
+    xml = %{<top name="Pete"/>}
+    doc = Ox.parse(xml)
+    assert_equal('Pete', doc.attributes[:name])
+  end
+
+  def test_single_quote
+    xml = %{<top name='Pete'/>}
+    doc = Ox.load(xml, :effort => :tolerant)
+    assert_equal('Pete', doc.attributes[:name])
+  end
+
+  def test_no_quote
+    xml = %{<top name=Pete />}
+    doc = Ox.load(xml, :effort => :tolerant)
+    assert_equal('Pete', doc.attributes[:name])
+  end
+
   def test_class
     dump_and_load(Bag, false)
   end

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

@@ -127,10 +127,11 @@ encoding = "UTF-8" ?>},
   end
 
   def test_sax_element_attrs
-    parse_compare(%{<top x="57" y="42"/>}, 
+    parse_compare(%{<top x="57" y='42' z=33 />}, 
                   [[:start_element, :top],
                    [:attr, :x, "57"],
                    [:attr, :y, "42"],
+                   [:attr, :z, "33"],
                    [:end_element, :top]])
   end
 

metadata

@@ -1,24 +1,28 @@
---- !ruby/object:Gem::Specification
+--- !ruby/object:Gem::Specification 
 name: ox
-version: !ruby/object:Gem::Version
-  version: 1.4.2
+version: !ruby/object:Gem::Version 
   prerelease: 
+  version: 1.4.3
 platform: ruby
-authors:
+authors: 
 - Peter Ohler
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2011-12-03 00:00:00.000000000Z
+
+date: 2011-12-08 00:00:00 +09:00
+default_executable: 
 dependencies: []
+
 description: A fast XML parser and object serializer that uses only standard C lib.
 email: peter@ohler.com
 executables: []
-extensions:
+
+extensions: 
 - ext/ox/extconf.rb
-extra_rdoc_files:
+extra_rdoc_files: 
 - README.md
-files:
+files: 
 - lib/ox/bag.rb
 - lib/ox/cdata.rb
 - lib/ox/comment.rb
@@ -47,11 +51,9 @@ files:
 - ext/ox/parse.c
 - ext/ox/sax.c
 - test/bench.rb
-- test/big.rb
 - test/bug1.rb
 - test/bug2.rb
 - test/bug3.rb
-- test/bug4.rb
 - test/cache16_test.rb
 - test/cache8_test.rb
 - test/cache_test.rb
@@ -79,36 +81,41 @@ 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
 - LICENSE
 - README.md
+has_rdoc: true
 homepage: https://github.com/ohler55/ox
 licenses: []
+
 post_install_message: 
-rdoc_options:
+rdoc_options: 
 - --main
 - README.md
-require_paths:
+require_paths: 
 - lib
 - ext
-required_ruby_version: !ruby/object:Gem::Requirement
+required_ruby_version: !ruby/object:Gem::Requirement 
   none: false
-  requirements:
-  - - ! '>='
-    - !ruby/object:Gem::Version
-      version: '0'
-required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+required_rubygems_version: !ruby/object:Gem::Requirement 
   none: false
-  requirements:
-  - - ! '>='
-    - !ruby/object:Gem::Version
-      version: '0'
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
 requirements: []
+
 rubyforge_project: ox
-rubygems_version: 1.8.10
+rubygems_version: 1.6.2
 signing_key: 
 specification_version: 3
 summary: A fast XML parser and object serializer.
 test_files: []
+

data/test/big.rb

@@ -1,24 +0,0 @@
-#!/usr/bin/env ruby -wW1
-
-$: << '../lib'
-$: << '../ext'
-
-if __FILE__ == $0
-  while (i = ARGV.index('-I'))
-    x,path = ARGV.slice!(i, 2)
-    $: << path
-  end
-end
-
-require 'ox'
-
-def dump(cnt = 10000)
-  h = { }
-  cnt.times do |i|
-    h[i] = [i * 2, "this is #{i}"]
-  end
-  xml = Ox.dump(h)
-  puts "size: #{xml.size}"
-end
-
-dump(200000)

data/test/bug4.rb

@@ -1,11 +0,0 @@
-#!/usr/bin/env ruby -wW1
-
-$: << '../lib'
-$: << '../ext'
-
-require 'ox'
-
-#xml = File.read('bug4.xml')
-xml = File.read('bug4.xml')
-
-doc = Ox.parse(xml)