nokogiri 1.15.7-java → 1.16.0-java

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 010e980be6c895a3d263cbfe2fa971e3c7d9fd2e470bc55dbc328106d62fef2d
-  data.tar.gz: b3fa0eabb5dcfd9f0cc526bc275ef1f317e6a30a21d596ac7babf11661548b8c
+  metadata.gz: 143fbb80846d635867bc5a1fe2a561ae9f86806c90e1e621f2a849846b7a9b39
+  data.tar.gz: 17c2f47f92d2588e16a3638a17fc4199816f141132e1afd9757af43c75a26288
 SHA512:
-  metadata.gz: 4d339a34ffa47797bb50479b47d3d7553f52089fae368478ea6244ed47f31196eca34fd0103c22cca3a91d1bd32d1055b00d497a8e5fc71e8e6e9fc3dd2715a1
-  data.tar.gz: 68e46a6cf1930112069b8a850cf635cbced63988d6040c49d59f36c68b26a58f471976b8b3a4f0648d33c4ec0eaff1ca9ee6097266b6230eef9ad4d54fd45fcd
+  metadata.gz: ad769e6a57a7db341a89e361209b889d5ce94693ef129038bf2066e4fd943179cf49c59ebdca326a1e4cc58883280d755f6dd589e5600dbc0df60dd3c3609862
+  data.tar.gz: 8e45bb445abbb907edd74dd954192068e7a0e8a1cc3ff52693bca831fa9b13291bc0441f3ff26df2b7123636c5323cf2cb892a27ba6b10e86d4c9f97ad9403bd

data/Gemfile

@@ -7,33 +7,30 @@ gemspec
 group :development do
   # bootstrapping
   gem "bundler", "~> 2.3"
-  gem "rake", "= 13.0.6"
+  gem "rake", "13.1.0"
 
   # building extensions
-  gem "rake-compiler", "= 1.2.1"
-  gem "rake-compiler-dock", "= 1.3.0"
-
-  # documentation
-  gem "hoe-markdown", "= 1.4.0"
+  gem "rake-compiler", "1.2.5"
+  gem "rake-compiler-dock", "1.4.0"
 
   # parser generator
   gem "rexical", "= 1.0.7"
 
   # tests
-  gem "minitest", "5.18.0"
-  gem "minitest-reporters", "1.6.0"
-  gem "ruby_memcheck", "1.3.2"
+  gem "minitest", "5.20.0"
+  gem "minitest-parallel_fork", "2.0.0"
+  gem "ruby_memcheck", "2.3.0"
   gem "rubyzip", "~> 2.3.2"
   gem "simplecov", "= 0.21.2"
 
   # rubocop
   if Gem::Requirement.new("~> 3.0").satisfied_by?(Gem::Version.new(RUBY_VERSION))
-    gem "rubocop", "1.51.0"
-    gem "rubocop-minitest", "0.31.0"
+    gem "rubocop", "1.59.0"
+    gem "rubocop-minitest", "0.34.2"
     gem "rubocop-packaging", "0.5.2"
-    gem "rubocop-performance", "1.18.0"
+    gem "rubocop-performance", "1.20.1"
     gem "rubocop-rake", "= 0.6.0"
-    gem "rubocop-shopify", "2.13.0"
+    gem "rubocop-shopify", "2.14.0"
   end
 end
 
@@ -41,5 +38,5 @@ end
 # `bundle config set --local without rdoc`
 # Then re-run `bundle install`.
 group :rdoc do
-  gem "rdoc", "6.5.0"
+  gem "rdoc", "6.6.2"
 end

data/README.md

@@ -55,6 +55,7 @@ There are a few ways to ask exploratory questions:
 
 - The Nokogiri mailing list is active at https://groups.google.com/group/nokogiri-talk
 - Open an issue using the "Help Request" template at https://github.com/sparklemotion/nokogiri/issues
+- Open a discussion at https://github.com/sparklemotion/nokogiri/discussions
 
 Please do not mail the maintainers at their personal addresses.
 
@@ -90,6 +91,8 @@ We bump `Major.Minor.Patch` versions following this guidance:
 - Updating packaged libraries for non-security-related reasons.
 - Dropping support for EOLed Ruby versions. [Some folks find this objectionable](https://github.com/sparklemotion/nokogiri/issues/1568), but [SemVer says this is OK if the public API hasn't changed](https://semver.org/#what-should-i-do-if-i-update-my-own-dependencies-without-changing-the-public-api).
 - Backwards-incompatible changes to internal or private methods and constants. These are detailed in the "Changes" section of each changelog entry.
+- Removal of deprecated methods or parameters, after a generous transition period; usually when those methods or parameters are rarely-used or dangerous to the user. Essentially, removals that do not justify a major version bump.
+
 
 `Patch`:
 
@@ -111,7 +114,7 @@ You can help sponsor the maintainers of this software through one of these organ
 
 Requirements:
 
-- Ruby >= 2.7
+- Ruby >= 3.0
 - JRuby >= 9.4.0.0
 
 

data/dependencies.yml

@@ -1,7 +1,8 @@
+
 libxml2:
-  version: "2.11.7"
-  sha256: "fb27720e25eaf457f94fd3d7189bcf2626c6dccf4201553bc8874d50e3560162"
-  # sha-256 hash provided in https://download.gnome.org/sources/libxml2/2.11/libxml2-2.11.7.sha256sum
+  version: "2.12.3"
+  sha256: "8c8f1092340a89ff32bc44ad5c9693aff9bc8a7a3e161bb239666e5d15ac9aaa"
+  # sha-256 hash provided in https://download.gnome.org/sources/libxml2/2.12/libxml2-2.12.3.sha256sum
 
 libxslt:
   version: "1.1.39"
@@ -9,8 +10,8 @@ libxslt:
   # sha-256 hash provided in https://download.gnome.org/sources/libxslt/1.1/libxslt-1.1.39.sha256sum
 
 zlib:
-  version: "1.2.13"
-  sha256: "b3a24de97a8fdbc835b9833169501030b8977031bcb54b3b3ac13740f846ab30"
+  version: "1.3"
+  sha256: "ff0ba4c292013dbc27530b3a81e1f9a813cd39de01ca5e0f8bf355702efa593e"
   # SHA-256 hash provided on http://zlib.net/
 
 libiconv:

data/ext/java/nokogiri/XmlCdata.java

@@ -51,8 +51,7 @@ public class XmlCdata extends XmlText
       throw context.runtime.newTypeError(msg);
     }
     if (!(rbDocument instanceof XmlDocument)) {
-      // TODO: deprecate allowing Node
-      context.runtime.getWarnings().warn("Passing a Node as the first parameter to CDATA.new is deprecated. Please pass a Document instead. This will become an error in a future release of Nokogiri.");
+      context.runtime.getWarnings().warn("Passing a Node as the first parameter to CDATA.new is deprecated. Please pass a Document instead. This will become an error in Nokogiri v1.17.0."); // TODO: deprecated in v1.15.3, remove in v1.17.0
     }
 
     Document document = ((XmlNode) rbDocument).getOwnerDocument();

data/ext/java/nokogiri/XmlNode.java

@@ -311,8 +311,7 @@ public class XmlNode extends RubyObject
       throw context.runtime.newArgumentError("document must be a Nokogiri::XML::Node");
     }
     if (!(doc instanceof XmlDocument)) {
-      // TODO: deprecate allowing Node
-      context.runtime.getWarnings().warn("Passing a Node as the second parameter to Node.new is deprecated. Please pass a Document instead, or prefer an alternative constructor like Node#add_child. This will become an error in a future release of Nokogiri.");
+      context.runtime.getWarnings().warn("Passing a Node as the second parameter to Node.new is deprecated. Please pass a Document instead, or prefer an alternative constructor like Node#add_child. This will become an error in Nokogiri v1.17.0."); // TODO: deprecated in v1.13.0, remove in v1.17.0
     }
 
     Document document = asXmlNode(context, doc).getOwnerDocument();

data/ext/java/nokogiri/XmlReader.java

@@ -138,14 +138,6 @@ public class XmlReader extends RubyObject
     return currentNode().getAttributeCount();
   }
 
-  @JRubyMethod
-  public IRubyObject
-  attribute_nodes(ThreadContext context)
-  {
-    context.runtime.getWarnings().warn("Reader#attribute_nodes is deprecated and will be removed in a future version of Nokogiri. Please use Reader#attribute_hash instead.");
-    return currentNode().getAttributesNodes();
-  }
-
   @JRubyMethod
   public IRubyObject
   attribute_hash(ThreadContext context)

data/ext/java/nokogiri/XmlSchema.java

@@ -154,8 +154,7 @@ public class XmlSchema extends RubyObject
       throw context.runtime.newTypeError(msg);
     }
     if (!(rbDocument instanceof XmlDocument)) {
-      // TODO: deprecate allowing Node
-      context.runtime.getWarnings().warn("Passing a Node as the first parameter to Schema.from_document is deprecated. Please pass a Document instead. This will become an error in a future release of Nokogiri.");
+      context.runtime.getWarnings().warn("Passing a Node as the first parameter to Schema.from_document is deprecated. Please pass a Document instead. This will become an error in Nokogiri v1.17.0."); // TODO: deprecated in v1.15.3, remove in v1.17.0
     }
 
     XmlDocument doc = ((XmlDocument)((XmlNode) rbDocument).document(context));

data/ext/java/nokogiri/XmlText.java

@@ -58,8 +58,7 @@ public class XmlText extends XmlNode
       throw context.runtime.newTypeError(msg);
     }
     if (!(rbDocument instanceof XmlDocument)) {
-      // TODO: deprecate allowing Node
-      context.runtime.getWarnings().warn("Passing a Node as the second parameter to Text.new is deprecated. Please pass a Document instead. This will become an error in a future release of Nokogiri.");
+      context.runtime.getWarnings().warn("Passing a Node as the second parameter to Text.new is deprecated. Please pass a Document instead. This will become an error in Nokogiri v1.17.0."); // TODO: deprecated in v1.15.3, remove in v1.17.0
     }
 
     Document document = asXmlNode(context, rbDocument).getOwnerDocument();

data/ext/nokogiri/extconf.rb

@@ -443,7 +443,7 @@ def process_recipe(name, version, static_p, cross_p, cacheable_p = true)
     # We use 'host' to set compiler prefix for cross-compiling. Prefer host_alias over host. And
     # prefer i686 (what external dev tools use) to i386 (what ruby's configure.ac emits).
     recipe.host = RbConfig::CONFIG["host_alias"].empty? ? RbConfig::CONFIG["host"] : RbConfig::CONFIG["host_alias"]
-    recipe.host = recipe.host.gsub(/i386/, "i686")
+    recipe.host = recipe.host.gsub("i386", "i686")
 
     recipe.target = File.join(PACKAGE_ROOT_DIR, "ports") if cacheable_p
     recipe.configure_options << "--libdir=#{File.join(recipe.path, "lib")}"
@@ -651,8 +651,7 @@ append_cppflags(ENV["CPPFLAGS"].split) unless ENV["CPPFLAGS"].nil?
 append_ldflags(ENV["LDFLAGS"].split) unless ENV["LDFLAGS"].nil?
 $LIBS = concat_flags($LIBS, ENV["LIBS"])
 
-# nokogumbo code uses C90/C99 features, let's make sure older compilers won't give
-# errors/warnings. see #2302
+# libgumbo uses C90/C99 features, see #2302
 append_cflags(["-std=c99", "-Wno-declaration-after-statement"])
 
 # gumbo html5 serialization is slower with O3, let's make sure we use O2
@@ -919,6 +918,7 @@ else
       "--with-c14n",
       "--with-debug",
       "--with-threads",
+      "--without-tls", # see https://github.com/sparklemotion/nokogiri/issues/3031
       "CPPFLAGS=#{cppflags}",
       "CFLAGS=#{cflags}",
     ]
@@ -1087,7 +1087,6 @@ have_func("xmlRelaxNGSetParserStructuredErrors") # introduced in libxml 2.6.24
 have_func("xmlRelaxNGSetValidStructuredErrors") # introduced in libxml 2.6.21
 have_func("xmlSchemaSetValidStructuredErrors") # introduced in libxml 2.6.23
 have_func("xmlSchemaSetParserStructuredErrors") # introduced in libxml 2.6.23
-have_func("rb_gc_location") # introduced in Ruby 2.7
 have_func("rb_category_warning") # introduced in Ruby 3.0
 
 other_library_versions_string = OTHER_LIBRARY_VERSIONS.map { |k, v| [k, v].join(":") }.join(",")

data/ext/nokogiri/html4_sax_push_parser.c

@@ -32,7 +32,7 @@ native_write(VALUE self, VALUE _chunk, VALUE _last_chunk)
 
   if ((status != 0) && !(ctx->options & XML_PARSE_RECOVER)) {
     // TODO: there appear to be no tests for this block
-    xmlErrorPtr e = xmlCtxtGetLastError(ctx);
+    xmlErrorConstPtr e = xmlCtxtGetLastError(ctx);
     Nokogiri_error_raise(NULL, e);
   }
 

data/ext/nokogiri/test_global_handlers.c

@@ -3,7 +3,7 @@
 static VALUE foreign_error_handler_block = Qnil;
 
 static void
-foreign_error_handler(void *user_data, xmlErrorPtr c_error)
+foreign_error_handler(void *user_data, xmlErrorConstPtr c_error)
 {
   rb_funcall(foreign_error_handler_block, rb_intern("call"), 0);
 }

data/ext/nokogiri/xml_cdata.c

@@ -33,8 +33,7 @@ rb_xml_cdata_s_new(int argc, VALUE *argv, VALUE klass)
 
   if (!rb_obj_is_kind_of(rb_document, cNokogiriXmlDocument)) {
     xmlNodePtr deprecated_node_type_arg;
-    // TODO: deprecate allowing Node
-    NOKO_WARN_DEPRECATION("Passing a Node as the first parameter to CDATA.new is deprecated. Please pass a Document instead. This will become an error in a future release of Nokogiri.");
+    NOKO_WARN_DEPRECATION("Passing a Node as the first parameter to CDATA.new is deprecated. Please pass a Document instead. This will become an error in Nokogiri v1.17.0."); // TODO: deprecated in v1.15.3, remove in v1.17.0
     Noko_Node_Get_Struct(rb_document, xmlNode, deprecated_node_type_arg);
     c_document = deprecated_node_type_arg->doc;
   } else {

data/ext/nokogiri/xml_document.c

@@ -337,7 +337,7 @@ read_io(VALUE klass,
   xmlSetStructuredErrorFunc(NULL, NULL);
 
   if (doc == NULL) {
-    xmlErrorPtr error;
+    xmlErrorConstPtr error;
 
     xmlFreeDoc(doc);
 
@@ -383,7 +383,7 @@ read_memory(VALUE klass,
   xmlSetStructuredErrorFunc(NULL, NULL);
 
   if (doc == NULL) {
-    xmlErrorPtr error;
+    xmlErrorConstPtr error;
 
     xmlFreeDoc(doc);
 
@@ -537,7 +537,7 @@ create_entity(int argc, VALUE *argv, VALUE self)
         );
 
   if (NULL == ptr) {
-    xmlErrorPtr error = xmlGetLastError();
+    xmlErrorConstPtr error = xmlGetLastError();
     if (error) {
       rb_exc_raise(Nokogiri_wrap_xml_syntax_error(error));
     } else {

data/ext/nokogiri/xml_namespace.c

@@ -42,7 +42,6 @@ _xml_namespace_dealloc(void *ptr)
   xmlFree(ns);
 }
 
-#ifdef HAVE_RB_GC_LOCATION
 static void
 _xml_namespace_update_references(void *ptr)
 {
@@ -51,9 +50,6 @@ _xml_namespace_update_references(void *ptr)
     ns->_private = (void *)rb_gc_location((VALUE)ns->_private);
   }
 }
-#else
-#  define _xml_namespace_update_references 0
-#endif
 
 static const rb_data_type_t nokogiri_xml_namespace_type_with_dealloc = {
   .wrap_struct_name = "Nokogiri::XML::Namespace#with_dealloc",

data/ext/nokogiri/xml_node.c

@@ -28,7 +28,6 @@ _xml_node_mark(void *ptr)
   }
 }
 
-#ifdef HAVE_RB_GC_LOCATION
 static void
 _xml_node_update_references(void *ptr)
 {
@@ -38,9 +37,6 @@ _xml_node_update_references(void *ptr)
     node->_private = (void *)rb_gc_location((VALUE)node->_private);
   }
 }
-#else
-#  define _xml_node_update_references 0
-#endif
 
 static const rb_data_type_t nokogiri_node_type = {
   .wrap_struct_name = "Nokogiri::XML::Node",
@@ -961,7 +957,7 @@ internal_subset(VALUE self)
  * - +new_parent_doc+
  *   The new node's parent Document. Defaults to the this node's document.
  *
- * [Returns] The new Nokgiri::XML::Node
+ * [Returns] The new Nokogiri::XML::Node
  */
 static VALUE
 duplicate_node(int argc, VALUE *argv, VALUE self)
@@ -1853,19 +1849,13 @@ is_one_of(xmlNodePtr node, char const *const *tagnames, size_t num_tagnames)
   if (name == NULL) { // fragments don't have a name
     return false;
   }
-
-  if (node->ns != NULL) {
-    // if the node has a namespace, it's in a foreign context and is not one of the HTML tags we're
-    // matching against.
-    return false;
-  }
-
   for (size_t idx = 0; idx < num_tagnames; ++idx) {
     if (!strcmp(name, tagnames[idx])) {
       return true;
     }
   }
   return false;
+
 }
 
 static void
@@ -2064,8 +2054,7 @@ rb_xml_node_new(int argc, VALUE *argv, VALUE klass)
     rb_raise(rb_eArgError, "document must be a Nokogiri::XML::Node");
   }
   if (!rb_obj_is_kind_of(rb_document_node, cNokogiriXmlDocument)) {
-    // TODO: deprecate allowing Node
-    NOKO_WARN_DEPRECATION("Passing a Node as the second parameter to Node.new is deprecated. Please pass a Document instead, or prefer an alternative constructor like Node#add_child. This will become an error in a future release of Nokogiri.");
+    NOKO_WARN_DEPRECATION("Passing a Node as the second parameter to Node.new is deprecated. Please pass a Document instead, or prefer an alternative constructor like Node#add_child. This will become an error in Nokogiri v1.17.0."); // TODO: deprecated in v1.13.0, remove in v1.17.0
   }
   Noko_Node_Get_Struct(rb_document_node, xmlNode, c_document_node);
 
@@ -2144,7 +2133,7 @@ process_xincludes(VALUE self, VALUE options)
   xmlSetStructuredErrorFunc(NULL, NULL);
 
   if (rcode < 0) {
-    xmlErrorPtr error;
+    xmlErrorConstPtr error;
 
     error = xmlGetLastError();
     if (error) {
@@ -2180,6 +2169,8 @@ in_context(VALUE self, VALUE _str, VALUE _options)
 
   /* Twiddle global variable because of a bug in libxml2.
    * http://git.gnome.org/browse/libxml2/commit/?id=e20fb5a72c83cbfc8e4a8aa3943c6be8febadab7
+   *
+   * TODO: this is fixed, and HTML_PARSE_NOIMPLIED is defined, in libxml2 2.7.7
    */
 #ifndef HTML_PARSE_NOIMPLIED
   htmlHandleOmittedElem(0);

data/ext/nokogiri/xml_reader.c

@@ -166,48 +166,6 @@ rb_xml_reader_namespaces(VALUE rb_reader)
   return rb_namespaces ;
 }
 
-/*
-  :call-seq: attribute_nodes() → Array<Nokogiri::XML::Attr>
-
-  Get the attributes of the current node as an Array of XML:Attr
-
-  ⚠ This method is deprecated and unsafe to use. It will be removed in a future version of Nokogiri.
-
-  See related: #attribute_hash, #attributes
- */
-static VALUE
-rb_xml_reader_attribute_nodes(VALUE rb_reader)
-{
-  xmlTextReaderPtr c_reader;
-  xmlNodePtr c_node;
-  VALUE attr_nodes;
-  int j;
-
-  // TODO: deprecated, remove in Nokogiri v1.15, see https://github.com/sparklemotion/nokogiri/issues/2598
-  // After removal, we can also remove all the "node_has_a_document" special handling from xml_node.c
-  NOKO_WARN_DEPRECATION("Reader#attribute_nodes is deprecated and will be removed in a future version of Nokogiri. Please use Reader#attribute_hash instead.");
-
-  TypedData_Get_Struct(rb_reader, xmlTextReader, &xml_reader_type, c_reader);
-
-  if (! has_attributes(c_reader)) {
-    return rb_ary_new() ;
-  }
-
-  c_node = xmlTextReaderExpand(c_reader);
-  if (c_node == NULL) {
-    return Qnil;
-  }
-
-  attr_nodes = noko_xml_node_attrs(c_node);
-
-  /* ensure that the Reader won't be GCed as long as a node is referenced */
-  for (j = 0 ; j < RARRAY_LEN(attr_nodes) ; j++) {
-    rb_iv_set(rb_ary_entry(attr_nodes, j), "@reader", rb_reader);
-  }
-
-  return attr_nodes;
-}
-
 /*
   :call-seq: attribute_hash() → Hash<String ⇒ String>
 
@@ -554,7 +512,7 @@ static VALUE
 read_more(VALUE self)
 {
   xmlTextReaderPtr reader;
-  xmlErrorPtr error;
+  xmlErrorConstPtr error;
   VALUE error_list;
   int ret;
 
@@ -778,7 +736,6 @@ noko_init_xml_reader(void)
   rb_define_method(cNokogiriXmlReader, "attribute", reader_attribute, 1);
   rb_define_method(cNokogiriXmlReader, "attribute_at", attribute_at, 1);
   rb_define_method(cNokogiriXmlReader, "attribute_count", attribute_count, 0);
-  rb_define_method(cNokogiriXmlReader, "attribute_nodes", rb_xml_reader_attribute_nodes, 0);
   rb_define_method(cNokogiriXmlReader, "attribute_hash", rb_xml_reader_attribute_hash, 0);
   rb_define_method(cNokogiriXmlReader, "attributes?", attributes_eh, 0);
   rb_define_method(cNokogiriXmlReader, "base_uri", rb_xml_reader_base_uri, 0);

data/ext/nokogiri/xml_relax_ng.c

@@ -93,7 +93,7 @@ xml_relax_ng_parse_schema(
   xmlRelaxNGFreeParserCtxt(c_parser_context);
 
   if (NULL == c_schema) {
-    xmlErrorPtr error = xmlGetLastError();
+    xmlErrorConstPtr error = xmlGetLastError();
     if (error) {
       Nokogiri_error_raise(NULL, error);
     } else {

data/ext/nokogiri/xml_sax_parser_context.c

@@ -59,6 +59,10 @@ parse_io(VALUE klass, VALUE io, VALUE encoding)
                                (xmlInputReadCallback)noko_io_read,
                                (xmlInputCloseCallback)noko_io_close,
                                (void *)io, enc);
+  if (!ctxt) {
+    rb_raise(rb_eRuntimeError, "failed to create xml sax parser context");
+  }
+
   if (ctxt->sax) {
     xmlFree(ctxt->sax);
     ctxt->sax = NULL;

data/ext/nokogiri/xml_sax_push_parser.c

@@ -59,7 +59,7 @@ native_write(VALUE self, VALUE _chunk, VALUE _last_chunk)
 
   if (xmlParseChunk(ctx, chunk, size, Qtrue == _last_chunk ? 1 : 0)) {
     if (!(ctx->options & XML_PARSE_RECOVER)) {
-      xmlErrorPtr e = xmlCtxtGetLastError(ctx);
+      xmlErrorConstPtr e = xmlCtxtGetLastError(ctx);
       Nokogiri_error_raise(NULL, e);
     }
   }

data/ext/nokogiri/xml_schema.c

@@ -146,7 +146,7 @@ xml_schema_parse_schema(
   xmlSchemaFreeParserCtxt(c_parser_context);
 
   if (NULL == c_schema) {
-    xmlErrorPtr error = xmlGetLastError();
+    xmlErrorConstPtr error = xmlGetLastError();
     if (error) {
       Nokogiri_error_raise(NULL, error);
     } else {
@@ -222,8 +222,7 @@ rb_xml_schema_s_from_document(int argc, VALUE *argv, VALUE klass)
 
   if (!rb_obj_is_kind_of(rb_document, cNokogiriXmlDocument)) {
     xmlNodePtr deprecated_node_type_arg;
-    // TODO: deprecate allowing Node
-    NOKO_WARN_DEPRECATION("Passing a Node as the first parameter to Schema.from_document is deprecated. Please pass a Document instead. This will become an error in a future release of Nokogiri.");
+    NOKO_WARN_DEPRECATION("Passing a Node as the first parameter to Schema.from_document is deprecated. Please pass a Document instead. This will become an error in Nokogiri v1.17.0."); // TODO: deprecated in v1.15.3, remove in v1.17.0
     Noko_Node_Get_Struct(rb_document, xmlNode, deprecated_node_type_arg);
     c_document = deprecated_node_type_arg->doc;
   } else {

data/ext/nokogiri/xml_syntax_error.c

@@ -26,7 +26,7 @@ Nokogiri_structured_error_func_restore(libxmlStructuredErrorHandlerState *handle
 }
 
 void
-Nokogiri_error_array_pusher(void *ctx, xmlErrorPtr error)
+Nokogiri_error_array_pusher(void *ctx, xmlErrorConstPtr error)
 {
   VALUE list = (VALUE)ctx;
   Check_Type(list, T_ARRAY);
@@ -34,13 +34,13 @@ Nokogiri_error_array_pusher(void *ctx, xmlErrorPtr error)
 }
 
 void
-Nokogiri_error_raise(void *ctx, xmlErrorPtr error)
+Nokogiri_error_raise(void *ctx, xmlErrorConstPtr error)
 {
   rb_exc_raise(Nokogiri_wrap_xml_syntax_error(error));
 }
 
 VALUE
-Nokogiri_wrap_xml_syntax_error(xmlErrorPtr error)
+Nokogiri_wrap_xml_syntax_error(xmlErrorConstPtr error)
 {
   VALUE msg, e, klass;
 

data/ext/nokogiri/xml_text.c

@@ -28,8 +28,7 @@ rb_xml_text_s_new(int argc, VALUE *argv, VALUE klass)
 
   if (!rb_obj_is_kind_of(rb_document, cNokogiriXmlDocument)) {
     xmlNodePtr deprecated_node_type_arg;
-    // TODO: deprecate allowing Node
-    NOKO_WARN_DEPRECATION("Passing a Node as the second parameter to Text.new is deprecated. Please pass a Document instead. This will become an error in a future release of Nokogiri.");
+    NOKO_WARN_DEPRECATION("Passing a Node as the second parameter to Text.new is deprecated. Please pass a Document instead. This will become an error in Nokogiri v1.17.0."); // TODO: deprecated in v1.15.3, remove in v1.17.0
     Noko_Node_Get_Struct(rb_document, xmlNode, deprecated_node_type_arg);
     c_document = deprecated_node_type_arg->doc;
   } else {

data/ext/nokogiri/xml_xpath_context.c

@@ -321,11 +321,8 @@ handler_lookup(void *data, const xmlChar *c_name, const xmlChar *c_ns_uri)
   VALUE rb_handler = (VALUE)data;
   if (rb_respond_to(rb_handler, rb_intern((const char *)c_name))) {
     if (c_ns_uri == NULL) {
-      NOKO_WARN_DEPRECATION(
-        "A custom XPath or CSS handler function named '%s' is being invoked without a namespace."
-        " Please update your query to reference this function as 'nokogiri:%s'."
-        " Invoking custom handler functions without a namespace is deprecated and support will be removed in a future release of Nokogiri.",
-        c_name, c_name);
+      NOKO_WARN_DEPRECATION("A custom XPath or CSS handler function named '%s' is being invoked without a namespace. Please update your query to reference this function as 'nokogiri:%s'. Invoking custom handler functions without a namespace is deprecated and will become an error in Nokogiri v1.17.0.",
+                            c_name, c_name); // deprecated in v1.15.0, remove in v1.17.0
     }
     return method_caller;
   }

data/gumbo-parser/Makefile

@@ -13,6 +13,20 @@ LDFLAGS := -pthread
 
 all: check
 
+fuzzers: fuzzer-normal fuzzer-asan fuzzer-ubsan fuzzer-msan
+
+fuzzer-normal:
+	./fuzzer/build.sh
+
+fuzzer-asan:
+	SANITIZER=asan ./fuzzer/build.sh
+
+fuzzer-ubsan:
+	SANITIZER=ubsan ./fuzzer/build.sh
+
+fuzzer-msan:
+	SANITIZER=msan ./fuzzer/build.sh
+
 # don't try to regenerate ragel or gperf files in CI, that should be a development-only action and
 # the generated files should be committed to SCM
 ifneq ($(CI),true)
@@ -81,6 +95,7 @@ coverage:
 
 clean:
 	$(RM) -r build
+	$(RM) -r fuzzer/build fuzzer/src-* fuzzer/gumbo_corpus
 
 build/src/flags: | build/src
 	@echo 'old_CC := $(CC)' > $@

data/lib/nokogiri/css/parser_extras.rb

@@ -23,7 +23,7 @@ module Nokogiri
 
         # Get the css selector in +string+ from the cache
         def [](string)
-          return nil unless cache_on?
+          return unless cache_on?
 
           @mutex.synchronize { @cache[string] }
         end

data/lib/nokogiri/css/xpath_visitor.rb

@@ -302,7 +302,7 @@ module Nokogiri
       end
 
       def read_a_and_positive_b(values)
-        op = values[2]
+        op = values[2].strip
         if op == "+"
           a = values[0].to_i
           b = values[3].to_i
@@ -335,25 +335,5 @@ module Nokogiri
         end
       end
     end
-
-    module XPathVisitorAlwaysUseBuiltins # :nodoc:
-      def self.new
-        warn(
-          "Nokogiri::CSS::XPathVisitorAlwaysUseBuiltins is deprecated and will be removed in a future version of Nokogiri",
-          { uplevel: 1 },
-        )
-        XPathVisitor.new(builtins: :always)
-      end
-    end
-
-    module XPathVisitorOptimallyUseBuiltins # :nodoc:
-      def self.new
-        warn(
-          "Nokogiri::CSS::XPathVisitorOptimallyUseBuiltins is deprecated and will be removed in a future version of Nokogiri",
-          { uplevel: 1 },
-        )
-        XPathVisitor.new(builtins: :optimal)
-      end
-    end
   end
 end

data/lib/nokogiri/html4/document.rb

@@ -92,7 +92,7 @@ module Nokogiri
         title = XML::Node.new("title", self) << tnode
         if (head = at_xpath("//head"))
           head << title
-        elsif (meta = (at_xpath("//meta[@charset]") || meta_content_type))
+        elsif (meta = at_xpath("//meta[@charset]") || meta_content_type)
           # better put after charset declaration
           meta.add_next_sibling(title)
         else

data/lib/nokogiri/html4/encoding_reader.rb

@@ -94,7 +94,7 @@ module Nokogiri
         # no support for a call without len
 
         unless @firstchunk
-          (@firstchunk = @io.read(len)) || (return nil)
+          (@firstchunk = @io.read(len)) || return
 
           # This implementation expects that the first call from
           # htmlReadIO() is made with a length long enough (~1KB) to

data/lib/nokogiri/html5.rb

@@ -239,23 +239,6 @@ module Nokogiri
         DocumentFragment.parse(string, encoding, options)
       end
 
-      # Fetch and parse a HTML document from the web, following redirects,
-      # handling https, and determining the character encoding using HTML5
-      # rules.  +uri+ may be a +String+ or a +URI+.  +options+ contains
-      # http headers and special options.  Everything which is not a
-      # special option is considered a header.  Special options include:
-      #  * :follow_limit => number of redirects which are followed
-      #  * :basic_auth => [username, password]
-      def get(uri, options = {})
-        # TODO: deprecate
-        warn(
-          "Nokogiri::HTML5.get is deprecated and will be removed in a future version of Nokogiri.",
-          uplevel: 1,
-          category: :deprecated,
-        )
-        get_impl(uri, options)
-      end
-
       # :nodoc:
       def read_and_encode(string, encoding)
         # Read the string with the given encoding.
@@ -283,55 +266,6 @@ module Nokogiri
 
       private
 
-      def get_impl(uri, options = {})
-        headers = options.clone
-        headers = { follow_limit: headers } if Numeric === headers # deprecated
-        limit = headers[:follow_limit] ? headers.delete(:follow_limit).to_i : 10
-
-        require "net/http"
-        uri = URI(uri) unless URI === uri
-
-        http = Net::HTTP.new(uri.host, uri.port)
-
-        # TLS / SSL support
-        http.use_ssl = true if uri.scheme == "https"
-
-        # Pass through Net::HTTP override values, which currently include:
-        #   :ca_file, :ca_path, :cert, :cert_store, :ciphers,
-        #   :close_on_empty_response, :continue_timeout, :key, :open_timeout,
-        #   :read_timeout, :ssl_timeout, :ssl_version, :use_ssl,
-        #   :verify_callback, :verify_depth, :verify_mode
-        options.each do |key, _value|
-          http.send("#{key}=", headers.delete(key)) if http.respond_to?("#{key}=")
-        end
-
-        request = Net::HTTP::Get.new(uri.request_uri)
-
-        # basic authentication
-        auth = headers.delete(:basic_auth)
-        auth ||= [uri.user, uri.password] if uri.user && uri.password
-        request.basic_auth(auth.first, auth.last) if auth
-
-        # remaining options are treated as headers
-        headers.each { |key, value| request[key.to_s] = value.to_s }
-
-        response = http.request(request)
-
-        case response
-        when Net::HTTPSuccess
-          doc = parse(reencode(response.body, response["content-type"]), options)
-          doc.instance_variable_set(:@response, response)
-          doc.class.send(:attr_reader, :response)
-          doc
-        when Net::HTTPRedirection
-          response.value if limit <= 1
-          location = URI.join(uri, response["location"])
-          get_impl(location, options.merge(follow_limit: limit - 1))
-        else
-          response.value
-        end
-      end
-
       # Charset sniffing is a complex and controversial topic that understandably isn't done _by
       # default_ by the Ruby Net::HTTP library.  This being said, it is a very real problem for
       # consumers of HTML as the default for HTML is iso-8859-1, most "good" producers use utf-8, and

data/lib/nokogiri/version/constant.rb

@@ -2,5 +2,5 @@
 
 module Nokogiri
   # The version of Nokogiri you are using
-  VERSION = "1.15.7"
+  VERSION = "1.16.0"
 end

data/lib/nokogiri/version/info.rb

@@ -94,11 +94,14 @@ module Nokogiri
           nokogiri["version"] = Nokogiri::VERSION
 
           unless jruby?
-            #  enable gems like nokogumbo to build with the following in their extconf.rb:
+            #  enable gems to build against Nokogiri with the following in their extconf.rb:
             #
             #    append_cflags(Nokogiri::VERSION_INFO["nokogiri"]["cppflags"])
             #    append_ldflags(Nokogiri::VERSION_INFO["nokogiri"]["ldflags"])
             #
+            #  though, this won't work on all platform and versions of Ruby, and won't be supported
+            #  forever, see https://github.com/sparklemotion/nokogiri/discussions/2746 for context.
+            #
             cppflags = ["-I#{header_directory.shellescape}"]
             ldflags = []
 
@@ -108,7 +111,8 @@ module Nokogiri
             end
 
             if windows?
-              # on windows, nokogumbo needs to link against nokogiri.so to resolve symbols. see #2167
+              # on windows, third party libraries that wish to link against nokogiri
+              # should link against nokogiri.so to resolve symbols. see #2167
               lib_directory = File.expand_path(File.join(File.dirname(__FILE__), "../#{ruby_minor}"))
               unless File.exist?(lib_directory)
                 lib_directory = File.expand_path(File.join(File.dirname(__FILE__), ".."))
@@ -136,9 +140,6 @@ module Nokogiri
               libxml["source"] = "packaged"
               libxml["precompiled"] = libxml2_precompiled?
               libxml["patches"] = Nokogiri::LIBXML2_PATCHES
-
-              # this is for nokogumbo and shouldn't be forever
-              libxml["libxml2_path"] = header_directory
             else
               libxml["source"] = "system"
             end

data/lib/nokogiri/xml/attr.rb

@@ -18,8 +18,6 @@ module Nokogiri
       #  - +value+ → (String) The value of the attribute.
       #  - +namespace+ → (Namespace, nil) The Namespace of the attribute, or +nil+ if there is no namespace.
       #
-      #  ⚡ This is an experimental feature, available since v1.14.0
-      #
       #  *Example*
       #
       #    doc = Nokogiri::XML.parse(<<~XML)
@@ -52,6 +50,8 @@ module Nokogiri
       #    #        href = "http://nokogiri.org/ns/noko"
       #    #        })}
       #
+      #  Since v1.14.0
+      #
       def deconstruct_keys(keys)
         { name: name, value: value, namespace: namespace }
       end

data/lib/nokogiri/xml/document.rb

@@ -329,7 +329,7 @@ module Nokogiri
       # Validate this Document against it's DTD.  Returns a list of errors on
       # the document or +nil+ when there is no DTD.
       def validate
-        return nil unless internal_subset
+        return unless internal_subset
 
         internal_subset.validate(self)
       end
@@ -426,8 +426,6 @@ module Nokogiri
       #  instructions. If you have a use case and would like this functionality, please let us know
       #  by opening an issue or a discussion on the github project.
       #
-      #  ⚡ This is an experimental feature, available since v1.14.0
-      #
       #  *Example*
       #
       #    doc = Nokogiri::XML.parse(<<~XML)
@@ -454,6 +452,8 @@ module Nokogiri
       #    doc.deconstruct_keys([:root])
       #    # => {:root=>nil}
       #
+      #  Since v1.14.0
+      #
       def deconstruct_keys(keys)
         { root: root }
       end

data/lib/nokogiri/xml/document_fragment.rb

@@ -154,8 +154,6 @@ module Nokogiri
       #  root elements, you should deconstruct the array returned by
       #  <tt>DocumentFragment#elements</tt>.
       #
-      #  ⚡ This is an experimental feature, available since v1.14.0
-      #
       #  *Example*
       #
       #    frag = Nokogiri::HTML5.fragment(<<~HTML)
@@ -187,6 +185,8 @@ module Nokogiri
       #    #       }),
       #    #     #(Element:0x398 { name = "div", children = [ #(Text "End")] })]
       #
+      #  Since v1.14.0
+      #
       def deconstruct
         children.to_a
       end

data/lib/nokogiri/xml/namespace.rb

@@ -16,8 +16,6 @@ module Nokogiri
       #  - +prefix+ → (String, nil) The namespace's prefix, or +nil+ if there is no prefix (e.g., default namespace).
       #  - +href+ → (String) The namespace's URI
       #
-      #  ⚡ This is an experimental feature, available since v1.14.0
-      #
       #  *Example*
       #
       #    doc = Nokogiri::XML.parse(<<~XML)
@@ -43,6 +41,7 @@ module Nokogiri
       #    doc.root.elements.last.namespace.deconstruct_keys([:prefix, :href])
       #    # => {:prefix=>"noko", :href=>"http://nokogiri.org/ns/noko"}
       #
+      #  Since v1.14.0
       #
       def deconstruct_keys(keys)
         { prefix: prefix, href: href }

data/lib/nokogiri/xml/node.rb

@@ -1049,29 +1049,35 @@ module Nokogiri
 
         return Nokogiri::XML::NodeSet.new(document) if contents.empty?
 
-        # libxml2 does not obey the +recover+ option after encountering errors during +in_context+
-        # parsing, and so this horrible hack is here to try to emulate recovery behavior.
-        #
-        # Unfortunately, this means we're no longer parsing "in context" and so namespaces that
-        # would have been inherited from the context node won't be handled correctly. This hack was
-        # written in 2010, and I regret it, because it's silently degrading functionality in a way
-        # that's not easily prevented (or even detected).
-        #
-        # I think preferable behavior would be to either:
-        #
-        # a. add an error noting that we "fell back" and pointing the user to turning off the +recover+ option
-        # b. don't recover, but raise a sensible exception
-        #
-        # For context and background: https://github.com/sparklemotion/nokogiri/issues/313
-        # FIXME bug report: https://github.com/sparklemotion/nokogiri/issues/2092
         error_count = document.errors.length
         node_set = in_context(contents, options.to_i)
-        if node_set.empty? && (document.errors.length > error_count)
-          if options.recover?
+        if document.errors.length > error_count
+          raise document.errors[error_count] unless options.recover?
+
+          if node_set.empty?
+            # libxml2 < 2.13 does not obey the +recover+ option after encountering errors during
+            # +in_context+ parsing, and so this horrible hack is here to try to emulate recovery
+            # behavior.
+            #
+            # (Note that HTML4 fragment parsing seems to have been fixed in abd74186, and XML
+            # fragment parsing is fixed in 1c106edf. Both are in 2.13.)
+            #
+            # Unfortunately, this means we're no longer parsing "in context" and so namespaces that
+            # would have been inherited from the context node won't be handled correctly. This hack
+            # was written in 2010, and I regret it, because it's silently degrading functionality in
+            # a way that's not easily prevented (or even detected).
+            #
+            # I think preferable behavior would be to either:
+            #
+            # a. add an error noting that we "fell back" and pointing the user to turning off the
+            #    +recover+ option
+            # b. don't recover, but raise a sensible exception
+            #
+            # For context and background:
+            # - https://github.com/sparklemotion/nokogiri/issues/313
+            # - https://github.com/sparklemotion/nokogiri/issues/2092
             fragment = document.related_class("DocumentFragment").parse(contents)
             node_set = fragment.children
-          else
-            raise document.errors[error_count]
           end
         end
         node_set
@@ -1165,7 +1171,7 @@ module Nokogiri
       # Fetch the Nokogiri::HTML4::ElementDescription for this node.  Returns
       # nil on XML documents and on unknown tags.
       def description
-        return nil if document.xml?
+        return if document.xml?
 
         Nokogiri::HTML4::ElementDescription[name]
       end
@@ -1254,8 +1260,8 @@ module Nokogiri
       # Compare two Node objects with respect to their Document.  Nodes from
       # different documents cannot be compared.
       def <=>(other)
-        return nil unless other.is_a?(Nokogiri::XML::Node)
-        return nil unless document == other.document
+        return unless other.is_a?(Nokogiri::XML::Node)
+        return unless document == other.document
 
         compare(other)
       end
@@ -1278,6 +1284,7 @@ module Nokogiri
       #   end
       #
       def serialize(*args, &block)
+        # TODO: deprecate non-hash options, see 46c68ed 2009-06-20 for context
         options = if args.first.is_a?(Hash)
           args.shift
         else
@@ -1429,8 +1436,6 @@ module Nokogiri
       #  - +content+ → (String) The contents of all the text nodes in this node's subtree. See #content.
       #  - +inner_html+ → (String) The inner markup for the children of this node. See #inner_html.
       #
-      #  ⚡ This is an experimental feature, available since v1.14.0
-      #
       #  *Example*
       #
       #    doc = Nokogiri::XML.parse(<<~XML)
@@ -1465,6 +1470,8 @@ module Nokogiri
       #    #         value = "def"
       #    #         })]}
       #
+      #  Since v1.14.0
+      #
       def deconstruct_keys(keys)
         requested_keys = DECONSTRUCT_KEYS & keys
         {}.tap do |values|

data/lib/nokogiri/xml/node_set.rb

@@ -372,7 +372,7 @@ module Nokogiri
       # Removes the last element from set and returns it, or +nil+ if
       # the set is empty
       def pop
-        return nil if length == 0
+        return if length == 0
 
         delete(last)
       end
@@ -381,7 +381,7 @@ module Nokogiri
       # Returns the first element of the NodeSet and removes it.  Returns
       # +nil+ if the set is empty.
       def shift
-        return nil if length == 0
+        return if length == 0
 
         delete(first)
       end
@@ -435,7 +435,7 @@ module Nokogiri
       #
       #  Returns the members of this NodeSet as an array, to use in pattern matching.
       #
-      #  ⚡ This is an experimental feature, available since v1.14.0
+      #  Since v1.14.0
       #
       def deconstruct
         to_a

data/lib/nokogiri/xml/searchable.rb

@@ -199,7 +199,7 @@ module Nokogiri
       #
       # Search this node's immediate children using CSS selector +selector+
       def >(selector) # rubocop:disable Naming/BinaryOperatorParameterName
-        ns = (document.root&.namespaces || {})
+        ns = document.root&.namespaces || {}
         xpath(CSS.xpath_for(selector, prefix: "./", ns: ns).first)
       end
 
@@ -229,7 +229,7 @@ module Nokogiri
       def xpath_impl(node, path, handler, ns, binds)
         ctx = XPathContext.new(node)
         ctx.register_namespaces(ns)
-        path = path.gsub(/xmlns:/, " :") unless Nokogiri.uses_libxml?
+        path = path.gsub("xmlns:", " :") unless Nokogiri.uses_libxml?
 
         binds&.each do |key, value|
           ctx.register_variable(key.to_s, value)
@@ -269,7 +269,7 @@ module Nokogiri
         end
         ns, binds = hashes.reverse
 
-        ns ||= (document.root&.namespaces || {})
+        ns ||= document.root&.namespaces || {}
 
         [params, handler, ns, binds]
       end

data/lib/nokogiri/xml/syntax_error.rb

@@ -63,7 +63,7 @@ module Nokogiri
       end
 
       def location_to_s
-        return nil if nil_or_zero?(line) && nil_or_zero?(column)
+        return if nil_or_zero?(line) && nil_or_zero?(column)
 
         "#{line}:#{column}"
       end

data/lib/nokogiri/xml.rb

@@ -11,7 +11,7 @@ module Nokogiri
 
   module XML
     # Original C14N 1.0 spec canonicalization
-    XML_C14N_1_0 =       0
+    XML_C14N_1_0 = 0
     # Exclusive C14N 1.0 spec canonicalization
     XML_C14N_EXCLUSIVE_1_0 = 1
     # C14N 1.1 spec canonicalization

data/lib/nokogiri/xslt.rb

@@ -101,7 +101,7 @@ module Nokogiri
         params.flatten.each_slice(2).with_object([]) do |kv, quoted_params|
           key, value = kv.map(&:to_s)
           value = if value.include?("'")
-            "concat('#{value.gsub(/'/, %q{', "'", '})}')"
+            "concat('#{value.gsub("'", %q{', "'", '})}')"
           else
             "'#{value}'"
           end

data/lib/nokogiri.rb

@@ -94,7 +94,7 @@ module Nokogiri
 
     # :nodoc:
     def install_default_aliases
-      warn("Nokogiri.install_default_aliases is deprecated and will be removed in a future version of Nokogiri. Please call Nokogiri::EncodingHandler.install_default_aliases instead.")
+      warn("Nokogiri.install_default_aliases is deprecated. Please call Nokogiri::EncodingHandler.install_default_aliases instead. This will become an error in Nokogiri v1.17.0.", uplevel: 1, category: :deprecated) # deprecated in v1.14.0, remove in v1.17.0
       Nokogiri::EncodingHandler.install_default_aliases
     end
   end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: nokogiri
 version: !ruby/object:Gem::Version
-  version: 1.15.7
+  version: 1.16.0
 platform: java
 authors:
 - Mike Dalessio
@@ -20,15 +20,15 @@ authors:
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2024-12-02 00:00:00.000000000 Z
+date: 2023-12-27 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
-  name: jar-dependencies
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - '='
       - !ruby/object:Gem::Version
         version: 0.4.1
+  name: jar-dependencies
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
@@ -37,12 +37,13 @@ dependencies:
       - !ruby/object:Gem::Version
         version: 0.4.1
 - !ruby/object:Gem::Dependency
-  name: racc
+  force_ruby_platform: false
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '1.4'
+  name: racc
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
@@ -336,7 +337,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: 2.7.0
+      version: 3.0.0
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="