ox 1.8.9 → 1.9.0

data/README.md

@@ -34,6 +34,13 @@ A fast XML parser and Object marshaller as a Ruby gem.
 
 ## <a name="release">Release Notes</a>
 
+### Release 1.9.0
+
+ - Added a new feature to Ox::Element.locate() that allows filtering by node Class.
+
+ - Added feature to the Sax parser. If @line is defined in the handler it is set to the line number of the xml file
+   before making callbacks. The same goes for @column but it is updated with the column.
+
 ### Release 1.8.9
 
  - Fixed bug in element start and end name checking.

data/ext/ox/ox.c

@@ -48,8 +48,10 @@ void Init_ox();
 
 VALUE	 Ox = Qnil;
 
+ID	ox_at_column_id;
 ID	ox_at_content_id;
 ID	ox_at_id;
+ID	ox_at_line_id;
 ID	ox_at_value_id;
 ID	ox_attr_id;
 ID	ox_attr_value_id;
@@ -85,8 +87,8 @@ ID	ox_text_id;
 ID	ox_to_c_id;
 ID	ox_to_s_id;
 ID	ox_to_sym_id;
-ID	ox_tv_sec_id;
 ID	ox_tv_nsec_id;
+ID	ox_tv_sec_id;
 ID	ox_tv_usec_id;
 ID	ox_value_id;
 
@@ -804,7 +806,10 @@ void Init_ox() {
     rb_require("date");
     rb_require("stringio");
 
+    ox_at_column_id = rb_intern("@column");
+    ox_at_content_id = rb_intern("@content");
     ox_at_id = rb_intern("at");
+    ox_at_line_id = rb_intern("@line");
     ox_at_value_id = rb_intern("@value");
     ox_attr_id = rb_intern("attr");
     ox_attr_value_id = rb_intern("attr_value");
@@ -812,15 +817,14 @@ void Init_ox() {
     ox_beg_id = rb_intern("@beg");
     ox_cdata_id = rb_intern("cdata");
     ox_comment_id = rb_intern("comment");
-    ox_at_content_id = rb_intern("@content");
     ox_den_id = rb_intern("@den");
     ox_doctype_id = rb_intern("doctype");
-    ox_external_encoding_id = rb_intern("external_encoding");
     ox_end_element_id = rb_intern("end_element");
     ox_end_id = rb_intern("@end");
     ox_end_instruct_id = rb_intern("end_instruct");
     ox_error_id = rb_intern("error");
     ox_excl_id = rb_intern("@excl");
+    ox_external_encoding_id = rb_intern("external_encoding");
     ox_fileno_id = rb_intern("fileno");
     ox_force_encoding_id = rb_intern("force_encoding");
     ox_inspect_id = rb_intern("inspect");
@@ -833,18 +837,18 @@ void Init_ox() {
     ox_nodes_id = rb_intern("@nodes");
     ox_num_id = rb_intern("@num");
     ox_parse_id = rb_intern("parse");
-    ox_readpartial_id = rb_intern("readpartial");
     ox_read_id = rb_intern("read");
+    ox_readpartial_id = rb_intern("readpartial");
     ox_start_element_id = rb_intern("start_element");
     ox_string_id = rb_intern("string");
     ox_text_id = rb_intern("text");
-    ox_value_id = rb_intern("value");
     ox_to_c_id = rb_intern("to_c");
     ox_to_s_id = rb_intern("to_s");
     ox_to_sym_id = rb_intern("to_sym");
-    ox_tv_sec_id = rb_intern("tv_sec");
     ox_tv_nsec_id = rb_intern("tv_nsec");
+    ox_tv_sec_id = rb_intern("tv_sec");
     ox_tv_usec_id = rb_intern("tv_usec");
+    ox_value_id = rb_intern("value");
 
     ox_time_class = rb_const_get(rb_cObject, rb_intern("Time"));
     ox_date_class = rb_const_get(rb_cObject, rb_intern("Date"));

data/ext/ox/ox.h

@@ -222,8 +222,10 @@ extern struct _Options	ox_default_options;
 
 extern VALUE	Ox;
 
+extern ID	ox_at_column_id;
 extern ID	ox_at_content_id;
 extern ID	ox_at_id;
+extern ID	ox_at_line_id;
 extern ID	ox_at_value_id;
 extern ID	ox_attr_id;
 extern ID	ox_attr_value_id;

data/ext/ox/sax.c

@@ -72,6 +72,8 @@ typedef struct _SaxDrive {
     int         has_start_element;
     int         has_end_element;
     int         has_error;
+    int		has_line;
+    int		has_column;
 #if HAS_ENCODING_SUPPORT
     rb_encoding *encoding;
 #elif HAS_PRIVATE_ENCODING
@@ -253,6 +255,8 @@ ox_sax_parse(VALUE handler, VALUE io, int convert) {
     printf("    has_start_element = %s\n", dr.has_start_element ? "true" : "false");
     printf("    has_end_element = %s\n", dr.has_end_element ? "true" : "false");
     printf("    has_error = %s\n", dr.has_error ? "true" : "false");
+    printf("    has_line = %s\n", dr.has_line ? "true" : "false");
+    printf("    has_column = %s\n", dr.has_column ? "true" : "false");
 #endif
     read_children(&dr, 1);
     sax_drive_cleanup(&dr);
@@ -338,6 +342,8 @@ sax_drive_init(SaxDrive dr, VALUE handler, VALUE io, int convert) {
     dr->has_start_element = respond_to(handler, ox_start_element_id);
     dr->has_end_element = respond_to(handler, ox_end_element_id);
     dr->has_error = respond_to(handler, ox_error_id);
+    dr->has_line = (Qtrue == rb_ivar_defined(handler, ox_at_line_id));
+    dr->has_column = (Qtrue == rb_ivar_defined(handler, ox_at_column_id));
 #if HAS_ENCODING_SUPPORT
     if ('\0' == *ox_default_options.encoding) {
 	VALUE	encoding;
@@ -424,6 +430,12 @@ sax_drive_error(SaxDrive dr, const char *msg, int critical) {
         args[0] = rb_str_new2(msg);
         args[1] = INT2FIX(dr->line);
         args[2] = INT2FIX(dr->col);
+	if (dr->has_line) {
+	    rb_ivar_set(dr->handler, ox_at_line_id, args[1]);
+	}
+	if (dr->has_column) {
+	    rb_ivar_set(dr->handler, ox_at_column_id, args[2]);
+	}
         rb_funcall2(dr->handler, ox_error_id, 3, args);
     } else if (critical) {
         sax_drive_cleanup(dr);
@@ -577,6 +589,12 @@ read_instruction(SaxDrive dr) {
     if (dr->has_instruct) {
         VALUE       args[1];
 
+	if (dr->has_line) {
+	    rb_ivar_set(dr->handler, ox_at_line_id, INT2FIX(dr->line));
+	}
+	if (dr->has_column) {
+	    rb_ivar_set(dr->handler, ox_at_column_id, INT2FIX(dr->col));
+	}
         args[0] = target;
         rb_funcall2(dr->handler, ox_instruct_id, 1, args);
     }
@@ -603,6 +621,12 @@ read_instruction(SaxDrive dr) {
 		rb_funcall(args[0], ox_force_encoding_id, 1, dr->encoding);
 	    }
 #endif
+	    if (dr->has_line) {
+		rb_ivar_set(dr->handler, ox_at_line_id, INT2FIX(dr->line));
+	    }
+	    if (dr->has_column) {
+		rb_ivar_set(dr->handler, ox_at_column_id, INT2FIX(dr->col));
+	    }
 	    rb_funcall2(dr->handler, ox_text_id, 1, args);
 	}
 	dr->cur = cend;
@@ -616,6 +640,12 @@ read_instruction(SaxDrive dr) {
     if (dr->has_end_instruct) {
         VALUE       args[1];
 
+	if (dr->has_line) {
+	    rb_ivar_set(dr->handler, ox_at_line_id, INT2FIX(dr->line));
+	}
+	if (dr->has_column) {
+	    rb_ivar_set(dr->handler, ox_at_column_id, INT2FIX(dr->col));
+	}
         args[0] = target;
         rb_funcall2(dr->handler, ox_end_instruct_id, 1, args);
     }
@@ -641,6 +671,12 @@ read_doctype(SaxDrive dr) {
     if (dr->has_doctype) {
         VALUE       args[1];
 
+	if (dr->has_line) {
+	    rb_ivar_set(dr->handler, ox_at_line_id, INT2FIX(dr->line));
+	}
+	if (dr->has_column) {
+	    rb_ivar_set(dr->handler, ox_at_column_id, INT2FIX(dr->col));
+	}
         args[0] = rb_str_new2(dr->str);
         rb_funcall2(dr->handler, ox_doctype_id, 1, args);
     }
@@ -688,6 +724,12 @@ read_cdata(SaxDrive dr) {
 	    rb_funcall(args[0], ox_force_encoding_id, 1, dr->encoding);
         }
 #endif
+	if (dr->has_line) {
+	    rb_ivar_set(dr->handler, ox_at_line_id, INT2FIX(dr->line));
+	}
+	if (dr->has_column) {
+	    rb_ivar_set(dr->handler, ox_at_column_id, INT2FIX(dr->col));
+	}
         rb_funcall2(dr->handler, ox_cdata_id, 1, args);
     }
     dr->str = 0;
@@ -736,6 +778,12 @@ read_comment(SaxDrive dr) {
 	    rb_funcall(args[0], ox_force_encoding_id, 1, dr->encoding);
         }
 #endif
+	if (dr->has_line) {
+	    rb_ivar_set(dr->handler, ox_at_line_id, INT2FIX(dr->line));
+	}
+	if (dr->has_column) {
+	    rb_ivar_set(dr->handler, ox_at_column_id, INT2FIX(dr->col));
+	}
         rb_funcall2(dr->handler, ox_comment_id, 1, args);
     }
     dr->str = 0;
@@ -761,6 +809,12 @@ read_element(SaxDrive dr) {
     if (dr->has_start_element) {
         VALUE       args[1];
 
+	if (dr->has_line) {
+	    rb_ivar_set(dr->handler, ox_at_line_id, INT2FIX(dr->line));
+	}
+	if (dr->has_column) {
+	    rb_ivar_set(dr->handler, ox_at_column_id, INT2FIX(dr->col));
+	}
         args[0] = name;
         rb_funcall2(dr->handler, ox_start_element_id, 1, args);
     }
@@ -786,6 +840,12 @@ read_element(SaxDrive dr) {
         if (dr->has_end_element) {
             VALUE       args[1];
 
+	    if (dr->has_line) {
+		rb_ivar_set(dr->handler, ox_at_line_id, INT2FIX(dr->line));
+	    }
+	    if (dr->has_column) {
+		rb_ivar_set(dr->handler, ox_at_column_id, INT2FIX(dr->col));
+	    }
             args[0] = name;
             rb_funcall2(dr->handler, ox_end_element_id, 1, args);
         }
@@ -794,6 +854,12 @@ read_element(SaxDrive dr) {
             return -1;
         }
 	if (0 != ename && 0 != strcmp(ename, dr->str)) {
+	    if (dr->has_line) {
+		rb_ivar_set(dr->handler, ox_at_line_id, INT2FIX(dr->line));
+	    }
+	    if (dr->has_column) {
+		rb_ivar_set(dr->handler, ox_at_column_id, INT2FIX(dr->col));
+	    }
 	    //printf("*** ename: %s  close: %s\n", ename, dr->str);
             sax_drive_error(dr, "invalid format, element start and end names do not match", 1);
 	    return -1;
@@ -801,6 +867,12 @@ read_element(SaxDrive dr) {
         if (0 != dr->has_end_element) {
             VALUE       args[1];
 
+	    if (dr->has_line) {
+		rb_ivar_set(dr->handler, ox_at_line_id, INT2FIX(dr->line));
+	    }
+	    if (dr->has_column) {
+		rb_ivar_set(dr->handler, ox_at_column_id, INT2FIX(dr->col));
+	    }
             args[0] = name;
             rb_funcall2(dr->handler, ox_end_element_id, 1, args);
         }
@@ -826,6 +898,12 @@ read_text(SaxDrive dr) {
     if (dr->has_value) {
         VALUE   args[1];
 
+	if (dr->has_line) {
+	    rb_ivar_set(dr->handler, ox_at_line_id, INT2FIX(dr->line));
+	}
+	if (dr->has_column) {
+	    rb_ivar_set(dr->handler, ox_at_column_id, INT2FIX(dr->col));
+	}
 	*args = dr->value_obj;
         rb_funcall2(dr->handler, ox_value_id, 1, args);
     } else if (dr->has_text) {
@@ -846,6 +924,12 @@ read_text(SaxDrive dr) {
 	    rb_funcall(args[0], ox_force_encoding_id, 1, dr->encoding);
         }
 #endif
+	if (dr->has_line) {
+	    rb_ivar_set(dr->handler, ox_at_line_id, INT2FIX(dr->line));
+	}
+	if (dr->has_column) {
+	    rb_ivar_set(dr->handler, ox_at_column_id, INT2FIX(dr->col));
+	}
         rb_funcall2(dr->handler, ox_text_id, 1, args);
     }
     dr->str = 0;
@@ -897,6 +981,12 @@ read_attrs(SaxDrive dr, char c, char termc, char term2, int is_xml) {
         if (dr->has_attr_value) {
             VALUE       args[2];
 
+	    if (dr->has_line) {
+		rb_ivar_set(dr->handler, ox_at_line_id, INT2FIX(dr->line));
+	    }
+	    if (dr->has_column) {
+		rb_ivar_set(dr->handler, ox_at_column_id, INT2FIX(dr->col));
+	    }
             args[0] = name;
             args[1] = dr->value_obj;
             rb_funcall2(dr->handler, ox_attr_value_id, 2, args);
@@ -917,6 +1007,12 @@ read_attrs(SaxDrive dr, char c, char termc, char term2, int is_xml) {
 		rb_funcall(args[1], ox_force_encoding_id, 1, dr->encoding);
 	    }
 #endif
+	    if (dr->has_line) {
+		rb_ivar_set(dr->handler, ox_at_line_id, INT2FIX(dr->line));
+	    }
+	    if (dr->has_column) {
+		rb_ivar_set(dr->handler, ox_at_column_id, INT2FIX(dr->col));
+	    }
             rb_funcall2(dr->handler, ox_attr_id, 2, args);
         }
         c = next_non_white(dr);

data/lib/ox/element.rb

@@ -106,9 +106,9 @@ module Ox
     # should be matched. Note that unlike XPath, the element index starts at 0
     # similar to Ruby be contrary to XPath.
     #
-    # Element names can also be wildcard characters. A * indicates any
-    # decendent should be followed. A ? indicates any single Element can
-    # match the wildcard.
+    # Element names can also be wildcard characters. A * indicates any decendent should be followed. A ? indicates any
+    # single Element can match the wildcard. A ^ character followed by the name of a Class will match any node of the
+    # specified class. Valid class names are Element, Comment, String (or Text), CData, DocType.
     #
     # Examples are:
     # * <code>element.locate("Family/Pete/*")</code> returns all children of the Pete Element.
@@ -116,6 +116,7 @@ module Ox
     # * <code>element.locate("Family/?[<3]")</code> returns the first 3 elements in the Family Element.
     # * <code>element.locate("Family/?/@age")</code> returns the arg attribute for each child in the Family Element.
     # * <code>element.locate("Family/*/@type")</code> returns the type attribute value for decendents of the Family.
+    # * <code>element.locate("Family/^Comment")</code> returns any comments that are a child of Family.
     #
     # @param [String] path path to the Nodes to locate
     def locate(path)
@@ -178,6 +179,22 @@ module Ox
         end
         if '?' == name or '*' == name
           match = nodes
+        elsif '^' == name[0..0] # 1.8.7 thinks name[0] is a fixnum
+          case name[1..-1]
+           when 'Element'
+            match = nodes.select { |e| e.is_a?(Element) }
+           when 'String', 'Text'
+            match = nodes.select { |e| e.is_a?(String) }
+          when 'Comment'
+            match = nodes.select { |e| e.is_a?(Comment) }
+          when 'CData'
+            match = nodes.select { |e| e.is_a?(CData) }
+          when 'DocType'
+            match = nodes.select { |e| e.is_a?(DocType) }
+          else
+            #puts "*** no match on #{name}"
+            match = []
+          end
         else
           match = nodes.select { |e| e.is_a?(Element) and name == e.name }
         end

data/lib/ox/sax.rb

@@ -43,9 +43,14 @@ module Ox
   #    def start_element(name); end
   #    def end_element(name); end
   #
+  # Initializing @line in the initializer will cause that variable to be updated before each callback with the XML line
+  # number. The same is true for the @column but it will be updated with the column in the XML file that is the end of
+  # the element or node just read. Not this is the end not the start of the node, attribute, or text.
   class Sax
     # Create a new instance of the Sax handler class.
     def initialize()
+      #@line = nil
+      #@column = nil
     end
 
     # To make the desired methods active while parsing the desired method

data/lib/ox/version.rb

@@ -1,5 +1,5 @@
 
 module Ox
   # Current version of the module. 
-  VERSION = '1.8.9'
+  VERSION = '1.9.0'
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: ox
 version: !ruby/object:Gem::Version
-  version: 1.8.9
+  version: 1.9.0
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-02-21 00:00:00.000000000 Z
+date: 2013-02-25 00:00:00.000000000 Z
 dependencies: []
 description: ! "A fast XML parser and object serializer that uses only standard C
   lib.\n            \nOptimized XML (Ox), as the name implies was written to provide