ox 2.11.0 → 2.13.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 837c0ef02149244d49ab2779216dbafc40c46cf1af3354d6ef35779929176476
-  data.tar.gz: b749a74dee9e1ff268cf69ca6dfff6edcb5681e2c4abe90a07a10442689cc484
+  metadata.gz: 4121ea0bb75760d8b57c9904bf884c44455e1d2613b3826b3765004b006c65a0
+  data.tar.gz: cb5fbf251430612e4c46feca429a0b8d0e60fee8191a250ec540d709966ca20d
 SHA512:
-  metadata.gz: f18d97d2e7c3087a07983f32b4d1e061e46866e5d17734689e8af68c8c004b669c008cb7321246123b060d44099624e2c039065727886ba146a412a7f8cae166
-  data.tar.gz: 90f9b3fcc779a2ac25e7a317a3fa17f028c4f9008bb8e57c6dc26693965add3cb116f7e9b250d64038f9928d027ee178f7e633320152202f94a1d896edff6f63
+  metadata.gz: 66995249fcc36e945629c09fe93bac6702b03e644d8fe310068f74f5dd1db47e65f98a86a7390f4cdefe865aa1976239caf283b393d725b1f6aae0cdc6a4d71c
+  data.tar.gz: 447fa33cc0ac30e78e56823f83b1be8d09dedc7763cb0fb820366c20cfe86ce9aafd6649fd3d0bcc8f90885f60325dae756ec32b44786cd482f9f0f7fb98a7ca

data/CHANGELOG.md

@@ -4,6 +4,52 @@ All changes to the Ox gem are documented here. Releases follow semantic versioni
 
 ## [Unreleased]
 
+## [2.13.3] - 2020-09-03
+
+### Changed
+
+- mkmf have macros used instead of ad-hoc determinations.
+
+## [2.13.2] - 2020-02-05
+
+Skip and missed sequence
+
+### Fixed
+
+- Add ' sequence.
+
+- `:skip_off` no longer misses spaces between elements.
+
+## [2.13.1] - 2020-01-30
+
+HTML Sequences
+
+### Added
+
+- All HTML 4 sequence are now supported.
+
+## [2.13.0] - 2020-01-25
+
+HTML Escape Sequences
+
+### Added
+
+- All HTML 4 escape sequences are now parsed.
+
+## [2.12.1] - 2020-01-05
+
+Ruby 2.7.0
+
+### Fixed
+
+- Updated for Ruby 2.7.0. More strict type checking. Function signature changes, and `Object#taint` deprecated.
+
+## [2.12.0] - 2019-12-18
+
+### Added
+
+- Add `no_empty` option to not allow <xyz/> and use <xyz></xyz> instead.
+
 ## [2.11.0] - 2019-06-14
 
 ### Changed

data/README.md

@@ -2,6 +2,7 @@
 A fast XML parser and Object marshaller as a Ruby gem.
 
 [![Build Status](https://secure.travis-ci.org/ohler55/ox.svg?branch=master)](http://travis-ci.org/ohler55/ox) [![TideLift](https://tidelift.com/badges/github/ohler55/ox)](https://tidelift.com/subscription/pkg/rubygems-ox?utm_source=rubygems-ox&utm_medium=referral&utm_campaign=readme)
+[![Financial Contributors on Open Collective](https://opencollective.com/ohler/all/badge.svg?label=financial+contributors)](https://opencollective.com/ohler) 
 
 ## Installation
     gem install ox
@@ -22,7 +23,7 @@ A fast XML parser and Object marshaller as a Ruby gem.
 
 ## Support
 
-[Get supported Ox with a Tidelift Subscription.](https://tidelift.com/subscription/pkg/rubygems-ox?utm_source=rubygems-ox&utm_medium=referral&utm_campaign=readme)
+[Get supported Ox with a Tidelift Subscription.](https://tidelift.com/subscription/pkg/rubygems-ox?utm_source=rubygems-ox&utm_medium=referral&utm_campaign=readme) Security updates are [supported](https://tidelift.com/security).
 
 ## Links of Interest
 
@@ -108,7 +109,13 @@ obj2 = Ox.parse_obj(xml)
 ```ruby
 require 'ox'
 
-doc = Ox::Document.new(:version => '1.0')
+doc = Ox::Document.new
+
+instruct = Ox::Instruct.new(:xml)
+instruct[:version] = '1.0'
+instruct[:encoding] = 'UTF-8'
+instruct[:standalone] = 'yes'
+doc << instruct
 
 top = Ox::Element.new('top')
 top[:name] = 'sample'
@@ -120,20 +127,31 @@ top << mid
 
 bot = Ox::Element.new('bottom')
 bot[:name] = 'third'
+bot << 'text at bottom'
 mid << bot
 
+other_elements = Ox::Element.new('otherElements')
+other_elements << Ox::CData.new('<sender>John Smith</sender>')
+other_elements << Ox::Comment.new('Director\'s commentary')
+# other_elements << Ox::DocType.new('content')
+other_elements << Ox::Raw.new('<warning>Be carefull with this! Direct inject into XML!</warning>')
+top << other_elements
+
+
 xml = Ox.dump(doc)
 
 # xml =
+# <?xml version="1.0" encoding="UTF-8" standalone="yes"?>
 # <top name="sample">
 #   <middle name="second">
-#     <bottom name="third"/>
+#     <bottom name="third">text at bottom</bottom>
 #   </middle>
+#   <otherElements>
+#     <![CDATA[<sender>John Smith</sender>]]>
+#     <!-- Director's commentary -->
+#     <warning>Be carefull with this! Direct inject into XML!</warning>
+#   </otherElements>
 # </top>
-
-doc2 = Ox.parse(xml)
-puts "Same? #{doc == doc2}"
-# true
 ```
 
 ### HTML Parsing:
@@ -306,3 +324,33 @@ Ox supports circular references where attributes of one Object can refer to
 an Object that refers back to the first Object. When this option is used an
 Object ID is added to each XML Object element as the value of the 'a'
 attribute.
+
+## Contributors
+
+### Code Contributors
+
+This project exists thanks to all the people who contribute. [[Contribute](CONTRIBUTING.md)].
+<a href="https://github.com/ohler55/ox/graphs/contributors"><img src="https://opencollective.com/ohler/contributors.svg?width=890&button=false" /></a>
+
+### Financial Contributors
+
+Become a financial contributor and help us sustain our community. [[Contribute](https://opencollective.com/ohler/contribute)]
+
+#### Individuals
+
+<a href="https://opencollective.com/ohler"><img src="https://opencollective.com/ohler/individuals.svg?width=890"></a>
+
+#### Organizations
+
+Support this project with your organization. Your logo will show up here with a link to your website. [[Contribute](https://opencollective.com/ohler/contribute)]
+
+<a href="https://opencollective.com/ohler/organization/0/website"><img src="https://opencollective.com/ohler/organization/0/avatar.svg"></a>
+<a href="https://opencollective.com/ohler/organization/1/website"><img src="https://opencollective.com/ohler/organization/1/avatar.svg"></a>
+<a href="https://opencollective.com/ohler/organization/2/website"><img src="https://opencollective.com/ohler/organization/2/avatar.svg"></a>
+<a href="https://opencollective.com/ohler/organization/3/website"><img src="https://opencollective.com/ohler/organization/3/avatar.svg"></a>
+<a href="https://opencollective.com/ohler/organization/4/website"><img src="https://opencollective.com/ohler/organization/4/avatar.svg"></a>
+<a href="https://opencollective.com/ohler/organization/5/website"><img src="https://opencollective.com/ohler/organization/5/avatar.svg"></a>
+<a href="https://opencollective.com/ohler/organization/6/website"><img src="https://opencollective.com/ohler/organization/6/avatar.svg"></a>
+<a href="https://opencollective.com/ohler/organization/7/website"><img src="https://opencollective.com/ohler/organization/7/avatar.svg"></a>
+<a href="https://opencollective.com/ohler/organization/8/website"><img src="https://opencollective.com/ohler/organization/8/avatar.svg"></a>
+<a href="https://opencollective.com/ohler/organization/9/website"><img src="https://opencollective.com/ohler/organization/9/avatar.svg"></a>

data/ext/ox/builder.c

@@ -8,6 +8,10 @@
 #include <stdio.h>
 #include <string.h>
 
+#include "ruby.h"
+#if HAVE_RB_ENC_ASSOCIATE
+#include "ruby/encoding.h"
+#endif
 #include "ox.h"
 #include "buf.h"
 #include "err.h"
@@ -17,7 +21,7 @@
 typedef struct _element {
     char	*name;
     char	buf[64];
-    int		len;
+    long	len;
     bool	has_child;
     bool	non_text_child;
 } *Element;
@@ -124,7 +128,7 @@ append_string(Builder b, const char *str, size_t size, const char *table, bool s
 	char	buf[256];
 	char	*end = buf + sizeof(buf) - 1;
 	char	*bp = buf;
-	int	i = size;
+	size_t	i = size;
 	int	fcnt;
 
 	for (; '\0' != *str && 0 < i; i--, str++) {
@@ -183,7 +187,7 @@ append_string(Builder b, const char *str, size_t size, const char *table, bool s
 static void
 append_sym_str(Builder b, VALUE v) {
     const char	*s;
-    int		len;
+    long	len;
 
     switch (rb_type(v)) {
     case T_STRING:
@@ -219,7 +223,9 @@ i_am_a_child(Builder b, bool is_text) {
 }
 
 static int
-append_attr(VALUE key, VALUE value, Builder b) {
+append_attr(VALUE key, VALUE value, VALUE bv) {
+    Builder	b = (Builder)bv;
+
     buf_append(&b->buf, ' ');
     b->col++;
     b->pos++;
@@ -329,7 +335,7 @@ to_s(Builder b) {
     rstr = rb_str_new(b->buf.head, buf_len(&b->buf));
 
     if ('\0' != *b->encoding) {
-#if HAS_ENCODING_SUPPORT
+#if HAVE_RB_ENC_ASSOCIATE
 	rb_enc_associate(rstr, rb_enc_find(b->encoding));
 #endif
     }
@@ -600,7 +606,7 @@ builder_element(int argc, VALUE *argv, VALUE self) {
     Builder		b = (Builder)DATA_PTR(self);
     Element		e;
     const char		*name;
-    int			len;
+    long		len;
 
     if (1 > argc) {
 	rb_raise(ox_arg_error_class, "missing element name");
@@ -662,7 +668,7 @@ static VALUE
 builder_void_element(int argc, VALUE *argv, VALUE self) {
     Builder	b = (Builder)DATA_PTR(self);
     const char	*name;
-    int		len;
+    long	len;
 
     if (1 > argc) {
 	rb_raise(ox_arg_error_class, "missing element name");

data/ext/ox/dump.c

@@ -54,7 +54,7 @@ static void	dump_obj(ID aid, VALUE obj, int depth, Out out);
 static void	dump_gen_doc(VALUE obj, int depth, Out out);
 static void	dump_gen_element(VALUE obj, int depth, Out out);
 static void	dump_gen_instruct(VALUE obj, int depth, Out out);
-static int	dump_gen_attr(VALUE key, VALUE value, Out out);
+static int	dump_gen_attr(VALUE key, VALUE value, VALUE ov);
 static int	dump_gen_nodes(VALUE obj, int depth, Out out);
 static void	dump_gen_val_node(VALUE obj, int depth,
 				  const char *pre, size_t plen,
@@ -67,12 +67,12 @@ static void	grow(Out out, size_t len);
 
 static void	dump_value(Out out, const char *value, size_t size);
 static void	dump_str_value(Out out, const char *value, size_t size, const char *table);
-static int	dump_var(ID key, VALUE value, Out out);
+static int	dump_var(ID key, VALUE value, VALUE ov);
 static void	dump_num(Out out, VALUE obj);
 static void	dump_date(Out out, VALUE obj);
 static void	dump_time_thin(Out out, VALUE obj);
 static void	dump_time_xsd(Out out, VALUE obj);
-static int	dump_hash(VALUE key, VALUE value, Out out);
+static int	dump_hash(VALUE key, VALUE value, VALUE ov);
 
 static int	is_xml_friendly(const uchar *str, int len, const char *table);
 
@@ -301,7 +301,14 @@ dump_start(Out out, Element e) {
 	fill_attr(out, 'i', s, end - s);
     }
     if (e->closed) {
-	*out->cur++ = '/';
+	if (out->opts->no_empty) {
+	    *out->cur++ = '>';
+	    *out->cur++ = '<';
+	    *out->cur++ = '/';
+	    *out->cur++ = e->type;
+	} else {
+	    *out->cur++ = '/';
+	}
     }
     *out->cur++ = '>';
     *out->cur = '\0';
@@ -448,17 +455,14 @@ static void
 dump_time_thin(Out out, VALUE obj) {
     char		buf[64];
     char		*b = buf + sizeof(buf) - 1;
-#if HAS_RB_TIME_TIMESPEC
+#if HAVE_RB_TIME_TIMESPEC
     struct timespec	ts = rb_time_timespec(obj);
     time_t		sec = ts.tv_sec;
     long		nsec = ts.tv_nsec;
 #else
     time_t		sec = NUM2LONG(rb_funcall2(obj, ox_tv_sec_id, 0, 0));
-#if HAS_NANO_TIME
     long		nsec = NUM2LONG(rb_funcall2(obj, ox_tv_nsec_id, 0, 0));
-#else
-    long		nsec = NUM2LONG(rb_funcall2(obj, ox_tv_usec_id, 0, 0)) * 1000;
-#endif
+    //long		nsec = NUM2LONG(rb_funcall2(obj, ox_tv_usec_id, 0, 0)) * 1000;
 #endif
     char		*dot = b - 10;
     long		size;
@@ -513,11 +517,8 @@ dump_time_xsd(Out out, VALUE obj) {
     long		nsec = ts.tv_nsec;
 #else
     time_t		sec = NUM2LONG(rb_funcall2(obj, ox_tv_sec_id, 0, 0));
-#if HAS_NANO_TIME
     long		nsec = NUM2LONG(rb_funcall2(obj, ox_tv_nsec_id, 0, 0));
-#else
-    long		nsec = NUM2LONG(rb_funcall2(obj, ox_tv_usec_id, 0, 0)) * 1000;
-#endif
+    //long		nsec = NUM2LONG(rb_funcall2(obj, ox_tv_usec_id, 0, 0)) * 1000;
 #endif
     int			tzhour, tzmin;
     char		tzsign = '+';
@@ -802,7 +803,7 @@ dump_obj(ID aid, VALUE obj, int depth, Out out) {
     }
     case T_STRUCT:
     {
-#if HAS_RSTRUCT
+#ifdef RSTRUCT_GET
 	VALUE	clas;
 
 	if (0 != out->circ_cache && check_circular(out, obj, &e)) {
@@ -824,7 +825,7 @@ dump_obj(ID aid, VALUE obj, int depth, Out out) {
 	} else {
 	    char	num_buf[16];
 	    int		d2 = depth + 1;
-#if UNIFY_FIXNUM_AND_BIGNUM
+#ifdef RUBY_INTEGER_UNIFICATION
 		long i;
 		long cnt = NUM2LONG(rb_struct_size(obj));
 #else // UNIFY_FIXNUM_AND_INTEGER
@@ -870,7 +871,7 @@ dump_obj(ID aid, VALUE obj, int depth, Out out) {
 	    dump_gen_element(obj, depth + 1, out);
 	    out->w_end(out, &e);
 	} else { /* Object */
-#if HAS_IVAR_HELPERS
+#if HAVE_RB_IVAR_FOREACH
 	    e.type = (Qtrue == rb_obj_is_kind_of(obj, rb_eException)) ? ExceptionCode : ObjectCode;
 	    cnt = (int)rb_ivar_count(obj);
 	    e.closed = (0 >= cnt);
@@ -998,7 +999,9 @@ dump_obj(ID aid, VALUE obj, int depth, Out out) {
 }
 
 static int
-dump_var(ID key, VALUE value, Out out) {
+dump_var(ID key, VALUE value, VALUE ov) {
+    Out	out = (Out)ov;
+
     if (T_DATA == rb_type(value) && key == ox_mesg_id) {
 	/* There is a secret recipe that keeps Exception mesg attributes as a
 	 * T_DATA until it is needed. The safe way around this hack is to call
@@ -1015,7 +1018,9 @@ dump_var(ID key, VALUE value, Out out) {
 }
 
 static int
-dump_hash(VALUE key, VALUE value, Out out) {
+dump_hash(VALUE key, VALUE value, VALUE ov) {
+    Out	out = (Out)ov;
+
     dump_obj(0, key, out->depth, out);
     dump_obj(0, value, out->depth, out);
 
@@ -1105,6 +1110,11 @@ dump_gen_element(VALUE obj, int depth, Out out) {
 	*out->cur++ = '<';
 	*out->cur++ = '/';
 	fill_value(out, name, nlen);
+    } else if (out->opts->no_empty) {
+	*out->cur++ = '>';
+	*out->cur++ = '<';
+	*out->cur++ = '/';
+	fill_value(out, name, nlen);
     } else {
 	*out->cur++ = '/';
     }
@@ -1186,16 +1196,13 @@ dump_gen_nodes(VALUE obj, int depth, Out out) {
 }
 
 static int
-dump_gen_attr(VALUE key, VALUE value, Out out) {
+dump_gen_attr(VALUE key, VALUE value, VALUE ov) {
+    Out	out = (Out)ov;
+
     const char	*ks;
     size_t	klen;
     size_t	size;
 
-#if HAS_PRIVATE_ENCODING
-    // There seems to be a bug in jruby for converting symbols to strings and preserving the encoding. This is a work
-    // around.
-    ks = rb_str_ptr(rb_String(key));
-#else
     switch (rb_type(key)) {
     case T_SYMBOL:
 	ks = rb_id2name(SYM2ID(key));
@@ -1208,7 +1215,6 @@ dump_gen_attr(VALUE key, VALUE value, Out out) {
 	ks = StringValuePtr(key);
 	break;
     }
-#endif
     klen = strlen(ks);
     value = rb_String(value);
     size = 4 + klen + RSTRING_LEN(value);

data/ext/ox/extconf.rb

@@ -6,7 +6,6 @@ dir_config(extension_name)
 parts = RUBY_DESCRIPTION.split(' ')
 type = parts[0].downcase()
 type = 'ree' if 'ruby' == type && RUBY_DESCRIPTION.include?('Ruby Enterprise Edition')
-is_windows = RbConfig::CONFIG['host_os'] =~ /(mingw|mswin)/
 platform = RUBY_PLATFORM
 version = RUBY_VERSION.split('.')
 puts ">>>>> Creating Makefile for #{type} version #{RUBY_VERSION} on #{platform} <<<<<"
@@ -18,41 +17,8 @@ dflags = {
   'RUBY_VERSION_MAJOR' => version[0],
   'RUBY_VERSION_MINOR' => version[1],
   'RUBY_VERSION_MICRO' => version[2],
-  'HAS_RB_TIME_TIMESPEC' => ('ruby' == type && ('1.9.3' == RUBY_VERSION)) ? 1 : 0,
-  #'HAS_RB_TIME_TIMESPEC' => ('ruby' == type && ('1.9.3' == RUBY_VERSION || '2' <= version[0])) ? 1 : 0,
-  'HAS_TM_GMTOFF' => ('ruby' == type && (('1' == version[0] && '9' == version[1]) || '2' <= version[0]) && 
-                      !(platform.include?('cygwin') || platform.include?('solaris') || platform.include?('linux') || RUBY_PLATFORM =~ /(win|w)32$/)) ? 1 : 0,
-  'HAS_ENCODING_SUPPORT' => (('ruby' == type || 'rubinius' == type || 'macruby' == type) &&
-                             (('1' == version[0] && '9' == version[1]) || '2' <= version[0])) ? 1 : 0,
-  'HAS_ONIG' => (('ruby' == type || 'jruby' == type || 'rubinius' == type) &&
-                 (('1' == version[0] && '9' == version[1]) || '2' <= version[0])) ? 1 : 0,
-  'HAS_PRIVATE_ENCODING' => ('jruby' == type && '1' == version[0] && '9' == version[1]) ? 1 : 0,
-  'HAS_NANO_TIME' => ('ruby' == type && ('1' == version[0] && '9' == version[1]) || '2' <= version[0]) ? 1 : 0,
-  'HAS_RSTRUCT' => ('ruby' == type || 'ree' == type) ? 1 : 0,
-  'HAS_IVAR_HELPERS' => ('ruby' == type && !is_windows && (('1' == version[0] && '9' == version[1]) || '2' <= version[0])) ? 1 : 0,
-  'HAS_PROC_WITH_BLOCK' => ('ruby' == type && ('1' == version[0] && '9' == version[1]) || '2' <= version[0]) ? 1 : 0,
-  'HAS_GC_GUARD' => ('jruby' != type && 'rubinius' != type) ? 1 : 0,
-  'HAS_BIGDECIMAL' => ('jruby' != type) ? 1 : 0,
-  'HAS_TOP_LEVEL_ST_H' => ('ree' == type || ('ruby' == type &&  '1' == version[0] && '8' == version[1])) ? 1 : 0,
-  'NEEDS_UIO' => (RUBY_PLATFORM =~ /(win|w)32$/) ? 0 : 1,
-  'HAS_DATA_OBJECT_WRAP' => ('ruby' == type && '2' == version[0] && '3' <= version[1]) ? 1 : 0,
-  'UNIFY_FIXNUM_AND_BIGNUM' => ('ruby' == type && '2' == version[0] && '4' <= version[1]) ? 1 : 0,
 }
 
-if RUBY_PLATFORM =~ /(win|w)32$/ || RUBY_PLATFORM =~ /solaris2\.10/
-  dflags['NEEDS_STPCPY'] = nil
-end
-
-if ['i386-darwin10.0.0', 'x86_64-darwin10.8.0'].include? RUBY_PLATFORM
-  dflags['NEEDS_STPCPY'] = nil
-  dflags['HAS_IVAR_HELPERS'] = 0 if ('ruby' == type && '1.9.1' == RUBY_VERSION)
-elsif 'x86_64-linux' == RUBY_PLATFORM && '1.9.3' == RUBY_VERSION && '2011-10-30' == RUBY_RELEASE_DATE
-  begin
-    dflags['NEEDS_STPCPY'] = nil if `more /etc/issue`.include?('CentOS release 5.4')
-  rescue Exception
-  end
-end
-
 dflags.each do |k,v|
   if v.nil?
     $CPPFLAGS += " -D#{k}"
@@ -62,6 +28,22 @@ dflags.each do |k,v|
 end
 $CPPFLAGS += ' -Wall'
 #puts "*** $CPPFLAGS: #{$CPPFLAGS}"
+CONFIG['warnflags'].slice!(/ -Wsuggest-attribute=format/)
+CONFIG['warnflags'].slice!(/ -Wdeclaration-after-statement/)
+CONFIG['warnflags'].slice!(/ -Wmissing-noreturn/)
+
+have_func('rb_time_timespec')
+have_func('rb_enc_associate')
+have_func('rb_enc_find')
+have_func('rb_struct_alloc_noinit')
+have_func('rb_obj_encoding')
+have_func('rb_ivar_foreach')
+
+have_header('ruby/st.h')
+have_header('sys/uio.h')
+
+have_struct_member('struct tm', 'tm_gmtoff')
+
 create_makefile(extension_name)
 
 %x{make clean}