nokogiri 1.12.2-java → 1.13.0-java

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 42d27c7dd45d6fdec5a7599b83af6952bf897aab942faaeaa94ece156ec97939
-  data.tar.gz: 5972d90845f58fa5ad17fe7ed527063aa4f6a21ea0a5679c86c25b3b661aa709
+  metadata.gz: 7c952d55813c188638a5daba0c1e7ab8f9566c5b7832b098cebd98b3d186ecd6
+  data.tar.gz: f7de12d117ee428672f357a79e55f9c5361667c1aacf14e5748dd42fc97334fb
 SHA512:
-  metadata.gz: 2eda14e0112fe4a191b3802ed95bb9eb095f1ca5a77bfa0a20a38eca5cdfa6c31b1e9f37a94e503dda858853627aa18e053034fb07307d2fbb9ed09dec9dc391
-  data.tar.gz: d50e625bc73a8b9ac13bcd52e41b9a90b98a3bd83abad035aeee608daf6acf9c1d48783a438d13b90ccdd64def40d6dd6aefc4348f29d19ef9b7e69d0816c1a6
+  metadata.gz: 7c0a0d6e1c97a2b6d2e68de975120b934d8b467d7b598e909460f936c8d7d4bf7e52f9fe5dd9e4aeed20cc2ab26f257e78a5050f975177cf940482c524b1c25e
+  data.tar.gz: 9432e3175aca11f91c51bdae39fd549031fafee24775290ed21a1dbedc98a9ce5a6b19aefac4e16298bf88c8694b9a342d33c55da08fcef7681c0efd825f8a82

data/Gemfile

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 source "https://rubygems.org"
 
 gemspec

data/README.md

@@ -2,7 +2,7 @@
 
 # Nokogiri
 
-Nokogiri (鋸) makes it easy and painless to work with XML and HTML from Ruby. It provides a sensible, easy-to-understand API for [reading](https://nokogiri.org/tutorials/parsing_an_html_xml_document.html), writing, [modifying](https://nokogiri.org/tutorials/modifying_an_html_xml_document.html), and [querying](https://nokogiri.org/tutorials/searching_a_xml_html_document.html) documents. It is fast and standards-compliant by relying on native parsers like libxml2 (C) and xerces (Java).
+Nokogiri (鋸) makes it easy and painless to work with XML and HTML from Ruby. It provides a sensible, easy-to-understand API for [reading](https://nokogiri.org/tutorials/parsing_an_html_xml_document.html), writing, [modifying](https://nokogiri.org/tutorials/modifying_an_html_xml_document.html), and [querying](https://nokogiri.org/tutorials/searching_a_xml_html_document.html) documents. It is fast and standards-compliant by relying on native parsers like libxml2 (CRuby) and xerces (JRuby).
 
 ## Guiding Principles
 
@@ -30,7 +30,9 @@ Some guiding principles Nokogiri tries to follow:
 [![Appveyor CI](https://ci.appveyor.com/api/projects/status/xj2pqwvlxwuwgr06/branch/main?svg=true)](https://ci.appveyor.com/project/flavorjones/nokogiri/branch/main)
 
 [![Gem Version](https://badge.fury.io/rb/nokogiri.svg)](https://rubygems.org/gems/nokogiri)
-[![SemVer compatibility](https://api.dependabot.com/badges/compatibility_score?dependency-name=nokogiri&package-manager=bundler&version-scheme=semver)](https://dependabot.com/compatibility-score/?dependency-name=nokogiri&package-manager=bundler)
+[![SemVer compatibility](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=nokogiri&package-manager=bundler&previous-version=1.11.7&new-version=1.12.5)](https://docs.github.com/en/code-security/supply-chain-security/managing-vulnerabilities-in-your-projects-dependencies/about-dependabot-security-updates#about-compatibility-scores)
+
+[![CII Best Practices](https://bestpractices.coreinfrastructure.org/projects/5344/badge)](https://bestpractices.coreinfrastructure.org/projects/5344)
 [![Tidelift dependencies](https://tidelift.com/badges/package/rubygems/nokogiri)](https://tidelift.com/subscription/pkg/rubygems-nokogiri?utm_source=rubygems-nokogiri&utm_medium=referral&utm_campaign=readme)
 
 
@@ -78,7 +80,7 @@ Full information and description of our security policy is in [`SECURITY.md`](SE
 
 ### Semantic Versioning Policy
 
-Nokogiri follows [Semantic Versioning](https://semver.org/) (since 2017 or so). [![Dependabot's SemVer compatibility score for Nokogiri](https://api.dependabot.com/badges/compatibility_score?dependency-name=nokogiri&package-manager=bundler&version-scheme=semver)](https://dependabot.com/compatibility-score/?dependency-name=nokogiri&package-manager=bundler)
+Nokogiri follows [Semantic Versioning](https://semver.org/) (since 2017 or so). [![Dependabot's SemVer compatibility score for Nokogiri](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=nokogiri&package-manager=bundler&previous-version=1.11.7&new-version=1.12.5)](https://docs.github.com/en/code-security/supply-chain-security/managing-vulnerabilities-in-your-projects-dependencies/about-dependabot-security-updates#about-compatibility-scores)
 
 We bump `Major.Minor.Patch` versions following this guidance:
 
@@ -105,8 +107,8 @@ We bump `Major.Minor.Patch` versions following this guidance:
 
 Requirements:
 
-- Ruby >= 2.5
-- JRuby >= 9.2.0.0
+- Ruby >= 2.6
+- JRuby >= 9.3.0.0
 
 
 ### Native Gems: Faster, more reliable installation
@@ -115,12 +117,12 @@ Requirements:
 
 ### Supported Platforms
 
-As of v1.11.0, Nokogiri ships pre-compiled, "native" gems for the following platforms:
+Nokogiri ships pre-compiled, "native" gems for the following platforms:
 
 - Linux: `x86-linux` and `x86_64-linux` (req: `glibc >= 2.17`), including musl platforms like Alpine
 - Darwin/MacOS: `x86_64-darwin` and `arm64-darwin`
 - Windows: `x86-mingw32` and `x64-mingw32`
-- Java: any platform running JRuby 9.2 or higher
+- Java: any platform running JRuby 9.3 or higher
 
 To determine whether your system supports one of these gems, look at the output of `bundle platform` or `ruby -e 'puts Gem::Platform.local.to_s'`.
 

data/bin/nokogiri

@@ -1,61 +1,77 @@
 #!/usr/bin/env ruby
-require 'optparse'
-require 'open-uri'
-require 'uri'
-require 'rubygems'
-require 'nokogiri'
-autoload :IRB, 'irb'
+# frozen_string_literal: true
+
+require "optparse"
+require "open-uri"
+require "uri"
+require "rubygems"
+require "nokogiri"
+autoload :IRB, "irb"
 
 parse_class = Nokogiri
 encoding = nil
 
 # This module provides some tunables with the nokogiri CLI for use in
 # your ~/.nokogirirc.
-module Nokogiri::CLI
-  class << self
-    # Specify the console engine, defaulted to IRB.
-    #
-    # call-seq:
-    #   require 'pry'
-    #   Nokogiri::CLI.console = Pry
-    attr_writer :console
-
-    def console
-      case @console
-      when Symbol
-        Kernel.const_get(@console)
-      else
-        @console
+module Nokogiri
+  module CLI
+    class << self
+      # Specify the console engine, defaulted to IRB.
+      #
+      # call-seq:
+      #   require 'pry'
+      #   Nokogiri::CLI.console = Pry
+      attr_writer :console
+
+      def console
+        case @console
+        when Symbol
+          Kernel.const_get(@console)
+        else
+          @console
+        end
       end
+
+      attr_accessor :rcfile
     end
 
-    attr_accessor :rcfile
+    self.rcfile  = File.expand_path("~/.nokogirirc")
+    self.console = :IRB
   end
+end
 
-  self.rcfile  = File.expand_path('~/.nokogirirc')
-  self.console = :IRB
+def safe_read(uri_or_path)
+  uri = URI.parse(uri_or_path)
+  case uri
+  when URI::HTTP
+    uri.read
+  when URI::File
+    File.read(uri.path)
+  else
+    File.read(uri_or_path)
+  end
 end
 
 opts = OptionParser.new do |opts|
   opts.banner = "Nokogiri: an HTML, XML, SAX, and Reader parser"
-  opts.define_head "Usage: nokogiri <uri|path> [options]"
-  opts.separator ""
-  opts.separator "Examples:"
-  opts.separator "  nokogiri https://www.ruby-lang.org/"
-  opts.separator "  nokogiri ./public/index.html"
-  opts.separator "  curl -s http://www.nokogiri.org | nokogiri -e'p $_.css(\"h1\").length'"
-  opts.separator ""
-  opts.separator "Options:"
+  opts.define_head("Usage: nokogiri <uri|path> [options]")
+  opts.separator("")
+  opts.separator("Examples:")
+  opts.separator("  nokogiri https://www.ruby-lang.org/")
+  opts.separator("  nokogiri ./public/index.html")
+  opts.separator("  curl -s http://www.nokogiri.org | nokogiri -e'p $_.css(\"h1\").length'")
+  opts.separator("")
+  opts.separator("Options:")
 
   opts.on("--type type", "Parse as type: xml or html (default: auto)", [:xml, :html]) do |v|
-    parse_class = {:xml => Nokogiri::XML, :html => Nokogiri::HTML}[v]
+    parse_class = { xml: Nokogiri::XML, html: Nokogiri::HTML }[v]
   end
 
   opts.on("-C file", "Specifies initialization file to load (default #{Nokogiri::CLI.rcfile})") do |v|
     Nokogiri::CLI.rcfile = v
   end
 
-  opts.on("-E", "--encoding encoding", "Read as encoding (default: #{encoding || 'none'})") do |v|
+  opts.on("-E", "--encoding encoding", "Read as encoding (default: #{encoding || "none"})") do |v|
     encoding = v
   end
 
@@ -64,7 +80,7 @@ opts = OptionParser.new do |opts|
   end
 
   opts.on("--rng <uri|path>", "Validate using this rng file.") do |v|
-    @rng = open(v) {|f| Nokogiri::XML::RelaxNG(f)}
+    @rng = Nokogiri::XML::RelaxNG(safe_read(v))
   end
 
   opts.on_tail("-?", "--help", "Show this message") do
@@ -90,15 +106,10 @@ if File.file?(Nokogiri::CLI.rcfile)
   load Nokogiri::CLI.rcfile
 end
 
-if url || $stdin.tty?
-  case uri = (URI(url) rescue url)
-  when URI::HTTP
-    @doc = parse_class.parse(uri.read, url, encoding)
-  else
-    @doc = parse_class.parse(open(url).read, nil, encoding)
-  end
+@doc = if url || $stdin.tty?
+  parse_class.parse(safe_read(url), url, encoding)
 else
-  @doc = parse_class.parse($stdin, nil, encoding)
+  parse_class.parse($stdin, nil, encoding)
 end
 
 $_ = @doc
@@ -107,12 +118,14 @@ if @rng
   @rng.validate(@doc).each do |error|
     puts error.message
   end
-else
-  if @script
-    eval @script, binding, '<main>'
-  else
-    puts "Your document is stored in @doc..."
-    Nokogiri::CLI.console.start
+elsif @script
+  begin
+    eval(@script, binding, "<main>") # rubocop:disable Security/Eval
+  rescue Exception => e # rubocop:disable Lint/RescueException
+    warn("ERROR: Exception raised while evaluating '#{@script}'")
+    raise e
   end
+else
+  puts "Your document is stored in @doc..."
+  Nokogiri::CLI.console.start
 end
-

data/dependencies.yml

@@ -64,11 +64,10 @@ zlib:
   # SHA-256 hash provided on http://zlib.net/
 
 libiconv:
-  version: "1.15"
-  sha256: "ccf536620a45458d26ba83887a983b96827001e92a13847b45e4925cc8913178"
-  # gpg: Signature made Fri Feb  3 00:38:12 2017 CET
+  version: "1.16"
+  sha256: "e6a1b1b589654277ee790cce3734f07876ac4ccfaecbee8afa0b649cf529cc04"
+  # gpg: Signature made Fri 26 Apr 2019 03:36:38 PM EDT
   # gpg:                using RSA key 4F494A942E4616C2
-  # gpg: Good signature from "Bruno Haible (Open Source Development) <bruno@clisp.org>" [unknown]
-  # gpg: WARNING: This key is not certified with a trusted signature!
-  # gpg:          There is no indication that the signature belongs to the owner.
+  # gpg: Good signature from "Bruno Haible (Open Source Development) <bruno@clisp.org>" [expired]
+  # gpg: Note: This key has expired!
   # Primary key fingerprint: 68D9 4D8A AEEA D48A E7DC  5B90 4F49 4A94 2E46 16C2

data/ext/java/nokogiri/Html4SaxPushParser.java

@@ -1,31 +1,26 @@
 package nokogiri;
 
-import static nokogiri.XmlSaxPushParser.terminateExecution;
-import static nokogiri.internals.NokogiriHelpers.getNokogiriClass;
-import static org.jruby.runtime.Helpers.invoke;
-
-import java.io.ByteArrayInputStream;
-import java.io.InputStream;
-import java.io.IOException;
-import java.util.concurrent.Callable;
-import java.util.concurrent.ExecutionException;
-import java.util.concurrent.ExecutorService;
-import java.util.concurrent.Executors;
-import java.util.concurrent.Future;
-import java.util.concurrent.FutureTask;
-import java.util.concurrent.ThreadFactory;
-
-import nokogiri.internals.*;
-
+import nokogiri.internals.ClosedStreamException;
+import nokogiri.internals.NokogiriBlockingQueueInputStream;
+import nokogiri.internals.NokogiriHelpers;
+import nokogiri.internals.ParserContext;
 import org.jruby.Ruby;
 import org.jruby.RubyClass;
 import org.jruby.RubyObject;
 import org.jruby.anno.JRubyClass;
 import org.jruby.anno.JRubyMethod;
-import org.jruby.exceptions.RaiseException;
 import org.jruby.runtime.ThreadContext;
 import org.jruby.runtime.builtin.IRubyObject;
 
+import java.io.ByteArrayInputStream;
+import java.io.IOException;
+import java.io.InputStream;
+import java.util.concurrent.*;
+
+import static nokogiri.XmlSaxPushParser.terminateExecution;
+import static nokogiri.internals.NokogiriHelpers.getNokogiriClass;
+import static org.jruby.runtime.Helpers.invoke;
+
 /**
  * Class for Nokogiri::HTML4::SAX::PushParser
  *
@@ -134,7 +129,7 @@ public class Html4SaxPushParser extends RubyObject
 
     if (!options.recover && parserTask.getErrorCount() > errorCount0) {
       terminateTask(context.runtime);
-      throw parserTask.getLastError();
+      throw parserTask.getLastError().toThrowable();
     }
 
     return this;

data/ext/java/nokogiri/XmlDocumentFragment.java

@@ -17,6 +17,7 @@ import org.jruby.RubyClass;
 import org.jruby.RubyString;
 import org.jruby.anno.JRubyClass;
 import org.jruby.anno.JRubyMethod;
+import org.jruby.runtime.Block;
 import org.jruby.runtime.Helpers;
 import org.jruby.runtime.ThreadContext;
 import org.jruby.runtime.builtin.IRubyObject;
@@ -34,8 +35,6 @@ import org.w3c.dom.NamedNodeMap;
 public class XmlDocumentFragment extends XmlNode
 {
 
-  private XmlElement fragmentContext;
-
   public
   XmlDocumentFragment(Ruby ruby)
   {
@@ -48,9 +47,9 @@ public class XmlDocumentFragment extends XmlNode
     super(ruby, klazz);
   }
 
-  @JRubyMethod(name = "new", meta = true, required = 1, optional = 2)
+  @JRubyMethod(name = "new", meta = true, required = 1, optional = 3)
   public static IRubyObject
-  rbNew(ThreadContext context, IRubyObject cls, IRubyObject[] args)
+  rbNew(ThreadContext context, IRubyObject cls, IRubyObject[] args, Block block)
   {
     if (args.length < 1) {
       throw context.runtime.newArgumentError(args.length, 1);
@@ -75,11 +74,7 @@ public class XmlDocumentFragment extends XmlNode
     fragment.setDocument(context, doc);
     fragment.setNode(context.runtime, doc.getDocument().createDocumentFragment());
 
-    //TODO: Get namespace definitions from doc.
-    if (args.length == 3 && args[2] != null && args[2] instanceof XmlElement) {
-      fragment.fragmentContext = (XmlElement)args[2];
-    }
-    Helpers.invoke(context, fragment, "initialize", args);
+    Helpers.invoke(context, fragment, "initialize", args, block);
     return fragment;
   }
 
@@ -158,12 +153,6 @@ public class XmlDocumentFragment extends XmlNode
     return null;
   }
 
-  public XmlElement
-  getFragmentContext()
-  {
-    return fragmentContext;
-  }
-
   @Override
   public void
   relink_namespace(ThreadContext context)

data/ext/java/nokogiri/XmlNamespace.java

@@ -80,14 +80,6 @@ public class XmlNamespace extends RubyObject
     return href;
   }
 
-  void
-  deleteHref()
-  {
-    href = "http://www.w3.org/XML/1998/namespace";
-    hrefRuby = null;
-    attr.getOwnerElement().removeAttributeNode(attr);
-  }
-
   public static XmlNamespace
   createFromAttr(Ruby runtime, Attr attr)
   {

data/ext/java/nokogiri/XmlNode.java

@@ -12,6 +12,7 @@ import java.util.*;
 import org.apache.xerces.dom.CoreDocumentImpl;
 import org.jruby.Ruby;
 import org.jruby.RubyArray;
+import org.jruby.RubyBoolean;
 import org.jruby.RubyClass;
 import org.jruby.RubyFixnum;
 import org.jruby.RubyInteger;
@@ -35,6 +36,7 @@ import org.w3c.dom.NamedNodeMap;
 import org.w3c.dom.Node;
 import org.w3c.dom.NodeList;
 import org.w3c.dom.Text;
+import org.w3c.dom.Comment;
 
 import nokogiri.internals.HtmlDomParserContext;
 import nokogiri.internals.NokogiriHelpers;
@@ -303,6 +305,14 @@ public class XmlNode extends RubyObject
     IRubyObject name = args[0];
     IRubyObject doc = args[1];
 
+    if (!(doc instanceof XmlNode)) {
+      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.");
+    }
+
     Document document = asXmlNode(context, doc).getOwnerDocument();
     if (document == null) {
       throw context.runtime.newArgumentError("node must have owner document");
@@ -421,7 +431,14 @@ public class XmlNode extends RubyObject
     String nsURI = e.lookupNamespaceURI(prefix);
     this.node = NokogiriHelpers.renameNode(e, nsURI, e.getNodeName());
 
-    if (nsURI == null || nsURI.isEmpty()) { return; }
+    if (nsURI == null || nsURI.isEmpty()) {
+      RubyBoolean ns_inherit =
+        (RubyBoolean)document(context.runtime).getInstanceVariable("@namespace_inheritance");
+      if (ns_inherit.isTrue()) {
+        set_namespace(context, ((XmlNode)parent(context)).namespace(context));
+      }
+      return;
+    }
 
     String currentPrefix = e.getParentNode().lookupPrefix(nsURI);
     String currentURI = e.getParentNode().lookupNamespaceURI(prefix);
@@ -1571,6 +1588,10 @@ public class XmlNode extends RubyObject
     return getNokogiriClass(context.runtime, "Nokogiri::XML::Node").getConstant(type);
   }
 
+  /*
+   * NOTE that the behavior of this function is very difference from the CRuby implementation, see
+   * the docstring in ext/nokogiri/xml_node.c for details.
+   */
   @JRubyMethod
   public IRubyObject
   line(ThreadContext context)
@@ -1578,7 +1599,10 @@ public class XmlNode extends RubyObject
     Node root = getOwnerDocument();
     int[] counter = new int[1];
     count(root, counter);
-    return RubyFixnum.newFixnum(context.runtime, counter[0] + 1);
+    // offset of 2:
+    // - one because humans start counting at 1 not zero
+    // - one to account for the XML declaration present in the output
+    return RubyFixnum.newFixnum(context.runtime, counter[0] + 2);
   }
 
   private boolean
@@ -1591,9 +1615,14 @@ public class XmlNode extends RubyObject
     NodeList list = node.getChildNodes();
     for (int jchild = 0; jchild < list.getLength(); jchild++) {
       Node child = list.item(jchild);
+      String text = null;
 
       if (child instanceof Text) {
-        String text = ((Text)child).getData();
+        text = ((Text)child).getData();
+      } else if (child instanceof Comment) {
+        text = ((Comment)child).getData();
+      }
+      if (text != null) {
         int textLength = text.length();
         for (int jchar = 0; jchar < textLength; jchar++) {
           if (text.charAt(jchar) == '\n') {
@@ -1743,24 +1772,11 @@ public class XmlNode extends RubyObject
       e.appendChild(otherNode);
       otherNode = e;
     } else {
-      addNamespaceURIIfNeeded(otherNode);
       parent.appendChild(otherNode);
     }
     return new Node[] { otherNode };
   }
 
-  private void
-  addNamespaceURIIfNeeded(Node child)
-  {
-    if (this instanceof XmlDocumentFragment && ((XmlDocumentFragment) this).getFragmentContext() != null) {
-      XmlElement fragmentContext = ((XmlDocumentFragment) this).getFragmentContext();
-      String namespace_uri = fragmentContext.node.getNamespaceURI();
-      if (namespace_uri != null && namespace_uri.length() > 0) {
-        NokogiriHelpers.renameNode(child, namespace_uri, child.getNodeName());
-      }
-    }
-  }
-
   protected void
   adoptAsPrevSibling(ThreadContext context,
                      Node parent,

data/ext/java/nokogiri/XmlNodeSet.java

@@ -190,10 +190,6 @@ public class XmlNodeSet extends RubyObject implements NodeList
       result[last++] = n;
     }
 
-    if (nodeOrNamespace instanceof XmlNamespace) {
-      ((XmlNamespace) nodeOrNamespace).deleteHref();
-    }
-
     nodes = Arrays.copyOf(result, last);
 
     if (nodes.length < orig.length) {

data/ext/java/nokogiri/XmlReader.java

@@ -184,6 +184,18 @@ public class XmlReader extends RubyObject
     return RubyBoolean.newBoolean(context.getRuntime(), !readerNode.hasChildren);
   }
 
+  @JRubyMethod
+  public IRubyObject
+  encoding(ThreadContext context)
+  {
+    IRubyObject constructor_encoding = getInstanceVariable("@encoding");
+    if (!constructor_encoding.isNil()) {
+      return constructor_encoding;
+    }
+    // TODO: get the parser's detected encoding
+    return context.getRuntime().getNil();
+  }
+
   @JRubyMethod(meta = true, rest = true)
   public static IRubyObject
   from_io(ThreadContext context, IRubyObject cls, IRubyObject args[])