nokogiri 1.8.5 → 1.13.9

data/patches/libxml2/0001-Revert-Do-not-URI-escape-in-server-side-includes.patch

@@ -1,78 +0,0 @@
-From c5538465c08a8ea248a370bf55bc39cd3385e4af Mon Sep 17 00:00:00 2001
-From: Mike Dalessio <mike.dalessio@gmail.com>
-Date: Thu, 29 Mar 2018 14:09:00 -0400
-Subject: [PATCH] Revert "Do not URI escape in server side includes"
-
-This reverts commit 960f0e275616cadc29671a218d7fb9b69eb35588.
----
- HTMLtree.c | 49 +++++++++++--------------------------------------
- 1 file changed, 11 insertions(+), 38 deletions(-)
-
-diff --git a/HTMLtree.c b/HTMLtree.c
-index 2fd0c9c..67160c5 100644
---- a/HTMLtree.c
-+++ b/HTMLtree.c
-@@ -717,49 +717,22 @@ htmlAttrDumpOutput(xmlOutputBufferPtr buf, xmlDocPtr doc, xmlAttrPtr cur,
- 		 (!xmlStrcasecmp(cur->name, BAD_CAST "src")) ||
- 		 ((!xmlStrcasecmp(cur->name, BAD_CAST "name")) &&
- 		  (!xmlStrcasecmp(cur->parent->name, BAD_CAST "a"))))) {
-+		xmlChar *escaped;
- 		xmlChar *tmp = value;
--		/* xmlURIEscapeStr() escapes '"' so it can be safely used. */
--		xmlBufCCat(buf->buffer, "\"");
- 
- 		while (IS_BLANK_CH(*tmp)) tmp++;
- 
--		/* URI Escape everything, except server side includes. */
--		for ( ; ; ) {
--		    xmlChar *escaped;
--		    xmlChar endChar;
--		    xmlChar *end = NULL;
--		    xmlChar *start = (xmlChar *)xmlStrstr(tmp, BAD_CAST "<!--");
--		    if (start != NULL) {
--			end = (xmlChar *)xmlStrstr(tmp, BAD_CAST "-->");
--			if (end != NULL) {
--			    *start = '\0';
--			}
--		    }
--
--		    /* Escape the whole string, or until start (set to '\0'). */
--		    escaped = xmlURIEscapeStr(tmp, BAD_CAST"@/:=?;#%&,+");
--		    if (escaped != NULL) {
--		        xmlBufCat(buf->buffer, escaped);
--		        xmlFree(escaped);
--		    } else {
--		        xmlBufCat(buf->buffer, tmp);
--		    }
--
--		    if (end == NULL) { /* Everything has been written. */
--			break;
--		    }
--
--		    /* Do not escape anything within server side includes. */
--		    *start = '<'; /* Restore the first character of "<!--". */
--		    end += 3; /* strlen("-->") */
--		    endChar = *end;
--		    *end = '\0';
--		    xmlBufCat(buf->buffer, start);
--		    *end = endChar;
--		    tmp = end;
-+		/*
-+		 * the < and > have already been escaped at the entity level
-+		 * And doing so here breaks server side includes
-+		 */
-+		escaped = xmlURIEscapeStr(tmp, BAD_CAST"@/:=?;#%&,+<>");
-+		if (escaped != NULL) {
-+		    xmlBufWriteQuotedString(buf->buffer, escaped);
-+		    xmlFree(escaped);
-+		} else {
-+		    xmlBufWriteQuotedString(buf->buffer, value);
- 		}
--
--		xmlBufCCat(buf->buffer, "\"");
- 	    } else {
- 		xmlBufWriteQuotedString(buf->buffer, value);
- 	    }
--- 
-2.9.5
-

data/patches/libxml2/0002-Fix-nullptr-deref-with-XPath-logic-ops.patch

@@ -1,54 +0,0 @@
-From a436374994c47b12d5de1b8b1d191a098fa23594 Mon Sep 17 00:00:00 2001
-From: Nick Wellnhofer <wellnhofer@aevum.de>
-Date: Mon, 30 Jul 2018 12:54:38 +0200
-Subject: [PATCH] Fix nullptr deref with XPath logic ops
-
-If the XPath stack is corrupted, for example by a misbehaving extension
-function, the "and" and "or" XPath operators could dereference NULL
-pointers. Check that the XPath stack isn't empty and optimize the
-logic operators slightly.
-
-Closes: https://gitlab.gnome.org/GNOME/libxml2/issues/5
-
-Also see
-https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=901817
-https://bugzilla.redhat.com/show_bug.cgi?id=1595985
-
-This is CVE-2018-14404.
-
-Thanks to Guy Inbar for the report.
----
- xpath.c | 10 ++++------
- 1 file changed, 4 insertions(+), 6 deletions(-)
-
-diff --git a/xpath.c b/xpath.c
-index 3fae0bf..5e3bb9f 100644
---- a/xpath.c
-+++ b/xpath.c
-@@ -13234,9 +13234,8 @@ xmlXPathCompOpEval(xmlXPathParserContextPtr ctxt, xmlXPathStepOpPtr op)
- 		return(0);
- 	    }
-             xmlXPathBooleanFunction(ctxt, 1);
--            arg1 = valuePop(ctxt);
--            arg1->boolval &= arg2->boolval;
--            valuePush(ctxt, arg1);
-+            if (ctxt->value != NULL)
-+                ctxt->value->boolval &= arg2->boolval;
- 	    xmlXPathReleaseObject(ctxt->context, arg2);
-             return (total);
-         case XPATH_OP_OR:
-@@ -13252,9 +13251,8 @@ xmlXPathCompOpEval(xmlXPathParserContextPtr ctxt, xmlXPathStepOpPtr op)
- 		return(0);
- 	    }
-             xmlXPathBooleanFunction(ctxt, 1);
--            arg1 = valuePop(ctxt);
--            arg1->boolval |= arg2->boolval;
--            valuePush(ctxt, arg1);
-+            if (ctxt->value != NULL)
-+                ctxt->value->boolval |= arg2->boolval;
- 	    xmlXPathReleaseObject(ctxt->context, arg2);
-             return (total);
-         case XPATH_OP_EQUAL:
--- 
-2.17.1
-

data/patches/libxml2/0003-Fix-infinite-loop-in-LZMA-decompression.patch

@@ -1,50 +0,0 @@
-From 2240fbf5912054af025fb6e01e26375100275e74 Mon Sep 17 00:00:00 2001
-From: Nick Wellnhofer <wellnhofer@aevum.de>
-Date: Mon, 30 Jul 2018 13:14:11 +0200
-Subject: [PATCH] Fix infinite loop in LZMA decompression
-MIME-Version: 1.0
-Content-Type: text/plain; charset=UTF-8
-Content-Transfer-Encoding: 8bit
-
-Check the liblzma error code more thoroughly to avoid infinite loops.
-
-Closes: https://gitlab.gnome.org/GNOME/libxml2/issues/13
-Closes: https://bugzilla.gnome.org/show_bug.cgi?id=794914
-
-This is CVE-2018-9251 and CVE-2018-14567.
-
-Thanks to Dongliang Mu and Simon Wörner for the reports.
----
- xzlib.c | 9 +++++++++
- 1 file changed, 9 insertions(+)
-
-diff --git a/xzlib.c b/xzlib.c
-index a839169..0ba88cf 100644
---- a/xzlib.c
-+++ b/xzlib.c
-@@ -562,6 +562,10 @@ xz_decomp(xz_statep state)
-                          "internal error: inflate stream corrupt");
-                 return -1;
-             }
-+            /*
-+             * FIXME: Remapping a couple of error codes and falling through
-+             * to the LZMA error handling looks fragile.
-+             */
-             if (ret == Z_MEM_ERROR)
-                 ret = LZMA_MEM_ERROR;
-             if (ret == Z_DATA_ERROR)
-@@ -587,6 +591,11 @@ xz_decomp(xz_statep state)
-             xz_error(state, LZMA_PROG_ERROR, "compression error");
-             return -1;
-         }
-+        if ((state->how != GZIP) &&
-+            (ret != LZMA_OK) && (ret != LZMA_STREAM_END)) {
-+            xz_error(state, ret, "lzma error");
-+            return -1;
-+        }
-     } while (strm->avail_out && ret != LZMA_STREAM_END);
- 
-     /* update available output and crc check value */
--- 
-2.17.1
-

data/patches/sort-patches-by-date

@@ -1,25 +0,0 @@
-#! /usr/bin/env ruby
-
-require "date"
-
-dir = ARGV[0] || raise("ERROR: arg1 must be dir")
-
-Dir.chdir dir
-
-files_and_times = {}
-Dir["*.patch"].sort.each do |filename|
-  dateline = `cat #{filename} | grep "Date:"`
-  datestr = dateline.split("Date:").last.strip
-  time = DateTime.parse datestr
-  files_and_times[filename] = time
-end
-
-count = 0
-files_and_times.sort_by {|k,v| v}.each do |filename, time|
-  count += 1
-  _, patch_name = filename.split("-", 2)
-  new_filename = sprintf("%4.4d-%s", count, patch_name)
-  printf "mv -f %s %s # %s\n", filename, new_filename, time
-end
-
-STDERR.print "\n**\n** REMEMBER TO UPDATE THE Manifest.txt FILE\n**\n"

data/suppressions/README.txt

@@ -1 +0,0 @@
-This directory contains valgrind suppression files generated by the hoe-debugging gem.

data/suppressions/nokogiri_ruby-2.supp

@@ -1,10 +0,0 @@
-{
-   <insert_a_suppression_name_here>
-   Memcheck:Free
-   fun:free
-   fun:__libc_freeres
-   fun:_vgnU_freeres
-   fun:__run_exit_handlers
-   fun:exit
-   fun:(below main)
-}

data/tasks/test.rb

@@ -1,100 +0,0 @@
-namespace :test do
-  desc "run test suite with aggressive GC"
-  task :gc => :build do
-    ENV['NOKOGIRI_GC'] = "true"
-    Rake::Task["test"].invoke
-  end
-
-  task :installed do
-    ENV['RUBY_FLAGS'] = "-w -Itest:."
-    sh 'rake test'
-  end
-
-  desc "find call-seq in the rdoc"
-  task :rdoc_call_seq => 'docs' do
-    Dir['doc/**/*.html'].each { |docfile|
-      next if docfile =~ /\.src/
-      puts "FAIL: #{docfile}" if File.read(docfile) =~ /call-seq/
-    }
-  end
-
-  desc "find all undocumented things"
-  task :rdoc => 'docs' do
-    base = File.expand_path(File.join(File.dirname(__FILE__), '..', 'doc'))
-    require 'test/unit'
-    test = Class.new(Test::Unit::TestCase)
-    Dir["#{base}/**/*.html"].each { |docfile|
-      test.class_eval(<<-eotest)
-        def test_#{docfile.sub("#{base}/", '').gsub(/[\/\.-]/, '_')}
-          assert_no_match(
-            /Not documented/,
-            File.read('#{docfile}'),
-            '#{docfile} has undocumented things'
-          )
-        end
-      eotest
-    }
-  end
-
-  desc "Test against multiple versions of libxml2 (MULTIXML2_DIR=directory)"
-  task :multixml2 do
-    MULTI_XML = File.join(ENV['HOME'], '.multixml2')
-    unless File.exists?(MULTI_XML)
-      %w{ versions install build }.each { |x|
-        FileUtils.mkdir_p(File.join(MULTI_XML, x))
-      }
-      Dir.chdir File.join(MULTI_XML, 'versions') do
-        require 'net/ftp'
-        puts "Contacting xmlsoft.org ..."
-        ftp = Net::FTP.new('xmlsoft.org')
-        ftp.login('anonymous', 'anonymous')
-        ftp.chdir('libxml2')
-        ftp.list('libxml2-2.*.tar.gz').each do |x|
-          file = x[/[^\s]*$/]
-          puts "Downloading #{file}"
-          ftp.getbinaryfile(file)
-        end
-      end
-    end
-
-    # Build any libxml2 versions in $HOME/.multixml2/versions that
-    # haven't been built yet
-    Dir[File.join(MULTI_XML, 'versions','*.tar.gz')].each do |f|
-      filename = File.basename(f, '.tar.gz')
-
-      install_dir = File.join(MULTI_XML, 'install', filename)
-      next if File.exists?(install_dir)
-
-      Dir.chdir File.join(MULTI_XML, 'versions') do
-        system "tar zxvf #{f} -C #{File.join(MULTI_XML, 'build')}"
-      end
-
-      Dir.chdir File.join(MULTI_XML, 'build', filename) do
-        system "./configure --without-http --prefix=#{install_dir}"
-        system "make && make install"
-      end
-    end
-
-    test_results = {}
-    libxslt = Dir[File.join(MULTI_XML, 'install', 'libxslt*')].first
-
-    directories = ENV['MULTIXML2_DIR'] ? [ENV['MULTIXML2_DIR']] : Dir[File.join(MULTI_XML, 'install', '*')]
-    directories.sort.reverse_each do |xml2_version|
-      next unless xml2_version =~ /libxml2/
-      extopts = "--with-xml2-include=#{xml2_version}/include/libxml2 --with-xml2-lib=#{xml2_version}/lib --with-xslt-dir=#{libxslt} --with-iconv-dir=/usr"
-      cmd = "#{$0} clean test EXTOPTS='#{extopts}' LD_LIBRARY_PATH='#{xml2_version}/lib'"
-
-      version = File.basename(xml2_version)
-      result = system(cmd)
-      test_results[version] = {
-        :result => result,
-        :cmd    => cmd
-      }
-    end
-    test_results.sort_by { |k,v| k }.each do |k,v|
-      passed = v[:result]
-      puts "#{k}: #{passed ? 'PASS' : 'FAIL'}"
-      puts "repro: #{v[:cmd]}" unless passed
-    end
-  end
-end

data/test/css/test_nthiness.rb

@@ -1,226 +0,0 @@
-require "helper"
-
-module Nokogiri
-  module CSS
-    class TestNthiness < Nokogiri::TestCase
-      def setup
-        super
-        doc = <<EOF
-<html>
-<table>
-  <tr><td>row1 </td></tr>
-  <tr><td>row2 </td></tr>
-  <tr><td>row3 </td></tr>
-  <tr><td>row4 </td></tr>
-  <tr><td>row5 </td></tr>
-  <tr><td>row6 </td></tr>
-  <tr><td>row7 </td></tr>
-  <tr><td>row8 </td></tr>
-  <tr><td>row9 </td></tr>
-  <tr><td>row10 </td></tr>
-  <tr><td>row11 </td></tr>
-  <tr><td>row12 </td></tr>
-  <tr><td>row13 </td></tr>
-  <tr><td>row14 </td></tr>
-</table>
-<div>
-  <b>bold1 </b>
-  <i>italic1 </i>
-  <b class="a">bold2 </b>
-  <em class="a">emphasis1 </em>
-  <i>italic2 </i>
-  <p>para1 </p>
-  <b class="a">bold3 </b>
-</div>
-<div>
-  <i class="b">italic3 </i>
-  <em>emphasis2 </em>
-  <i class="b">italic4 </i>
-  <em>emphasis3 </em>
-  <i class="c">italic5 </i>
-  <span><i class="b">italic6 </i></span>  
-  <i>italic7 </i>
-</div>
-<div>
-  <p>para2 </p>
-  <p>para3 </p>
-</div>
-<div>
-  <p>para4 </p>
-</div>
-
-<div>
-  <h2></h2>
-  <h1 class='c'>header1 </h1>
-  <h2></h2>
-</div>
-<div>
-  <h1 class='c'>header2 </h1>
-  <h1 class='c'>header3 </h1>
-</div>
-<div>
-  <h1 class='c'>header4</h1>
-</div>
-  
-<p class='empty'></p>
-<p class='not-empty'><b></b></p>
-</html>
-EOF
-        @parser = Nokogiri.HTML doc
-      end
-
-
-      def test_even
-        assert_result_rows [2,4,6,8,10,12,14], @parser.search("table//tr:nth(even)")
-      end
-
-      def test_odd
-        assert_result_rows [1,3,5,7,9,11,13], @parser.search("table//tr:nth(odd)")
-      end
-
-      def test_n
-        assert_result_rows((1..14).to_a, @parser.search("table//tr:nth(n)"))
-      end
-
-      def test_2n
-        assert_equal @parser.search("table//tr:nth(even)").inner_text, @parser.search("table//tr:nth(2n)").inner_text
-      end
-
-      def test_2np1
-        assert_equal @parser.search("table//tr:nth(odd)").inner_text, @parser.search("table//tr:nth(2n+1)").inner_text
-      end
-
-      def test_4np3
-        assert_result_rows [3,7,11], @parser.search("table//tr:nth(4n+3)")
-      end
-
-      def test_3np4
-        assert_result_rows [4,7,10,13], @parser.search("table//tr:nth(3n+4)")
-      end
-
-      def test_mnp3
-        assert_result_rows [1,2,3], @parser.search("table//tr:nth(-n+3)")
-      end
-
-      def test_4nm1
-        assert_result_rows [3,7,11], @parser.search("table//tr:nth(4n-1)")
-      end
-
-      def test_np3
-        assert_result_rows [3,4,5,6,7,8,9,10,11,12,13,14], @parser.search("table//tr:nth(n+3)")
-      end
-
-      def test_first
-        assert_result_rows [1], @parser.search("table//tr:first")
-        assert_result_rows [1], @parser.search("table//tr:first()")
-      end
-
-      def test_last
-        assert_result_rows [14], @parser.search("table//tr:last")
-        assert_result_rows [14], @parser.search("table//tr:last()")
-      end
-
-      def test_first_child
-        assert_result_rows [1], @parser.search("div/b:first-child"), "bold"
-        assert_result_rows [1], @parser.search("table//tr:first-child")
-        assert_result_rows [2,4],  @parser.search("div/h1.c:first-child"), "header"
-      end
-
-      def test_last_child
-        assert_result_rows [3], @parser.search("div/b:last-child"), "bold"
-        assert_result_rows [14], @parser.search("table//tr:last-child")
-        assert_result_rows [3,4], @parser.search("div/h1.c:last-child"), "header"
-      end
-      
-      def test_nth_child
-        assert_result_rows [2], @parser.search("div/b:nth-child(3)"), "bold"
-        assert_result_rows [5], @parser.search("table//tr:nth-child(5)")
-        assert_result_rows [1,3], @parser.search("div/h1.c:nth-child(2)"), "header"
-        assert_result_rows [3,4], @parser.search("div/i.b:nth-child(2n+1)"), "italic"
-      end
-
-      def test_first_of_type
-        assert_result_rows [1], @parser.search("table//tr:first-of-type")
-        assert_result_rows [1], @parser.search("div/b:first-of-type"), "bold"
-        assert_result_rows [2], @parser.search("div/b.a:first-of-type"), "bold"
-        assert_result_rows [3], @parser.search("div/i.b:first-of-type"), "italic"
-      end
-
-      def test_last_of_type
-        assert_result_rows [14], @parser.search("table//tr:last-of-type")
-        assert_result_rows [3], @parser.search("div/b:last-of-type"), "bold"
-        assert_result_rows [2,7], @parser.search("div/i:last-of-type"), "italic"
-        assert_result_rows [2,6,7], @parser.search("div i:last-of-type"), "italic"
-        assert_result_rows [4], @parser.search("div/i.b:last-of-type"), "italic"
-      end
-      
-      def test_nth_of_type
-        assert_result_rows [1], @parser.search("div/b:nth-of-type(1)"), "bold"
-        assert_result_rows [2], @parser.search("div/b:nth-of-type(2)"), "bold"
-        assert_result_rows [2], @parser.search("div/.a:nth-of-type(1)"), "bold"
-        assert_result_rows [2,4,7], @parser.search("div i:nth-of-type(2n)"), "italic"
-        assert_result_rows [1,3,5,6], @parser.search("div i:nth-of-type(2n+1)"), "italic"
-        assert_result_rows [1], @parser.search("div .a:nth-of-type(2n)"), "emphasis"
-        assert_result_rows [2,3], @parser.search("div .a:nth-of-type(2n+1)"), "bold"
-      end
-      
-      def test_nth_last_of_type
-        assert_result_rows [14], @parser.search("table//tr:nth-last-of-type(1)")
-        assert_result_rows [12], @parser.search("table//tr:nth-last-of-type(3)")
-        assert_result_rows [2,6,7], @parser.search("div i:nth-last-of-type(1)"), "italic"
-        assert_result_rows [1,5], @parser.search("div i:nth-last-of-type(2)"), "italic"        
-        assert_result_rows [4], @parser.search("div/i.b:nth-last-of-type(1)"), "italic"
-        assert_result_rows [3], @parser.search("div/i.b:nth-last-of-type(2)"), "italic"
-      end
-
-      def test_only_of_type
-        assert_result_rows [1,4], @parser.search("div/p:only-of-type"), "para"
-        assert_result_rows [5], @parser.search("div/i.c:only-of-type"), "italic"
-      end
-
-      def test_only_child
-        assert_result_rows [4], @parser.search("div/p:only-child"), "para"
-        assert_result_rows [4], @parser.search("div/h1.c:only-child"), "header"
-      end
-
-      def test_empty
-        result = @parser.search("p:empty")
-        assert_equal 1, result.size, "unexpected number of rows returned: '#{result.inner_text}'"
-        assert_equal 'empty', result.first['class']
-      end
-
-      def test_parent
-        result = @parser.search("p:parent")
-        assert_equal 5, result.size
-        0.upto(3) do |j|
-          assert_equal "para#{j+1} ", result[j].inner_text
-        end
-        assert_equal "not-empty", result[4]['class']
-      end
-
-      def test_siblings
-        doc = <<-EOF
-<html><body><div>
-<p id="1">p1 </p>
-<p id="2">p2 </p>
-<p id="3">p3 </p>
-<p id="4">p4 </p>
-<p id="5">p5 </p>
-EOF
-        parser = Nokogiri.HTML doc
-        assert_equal 2, parser.search("#3 ~ p").size
-        assert_equal "p4 p5 ", parser.search("#3 ~ p").inner_text
-        assert_equal 0, parser.search("#5 ~ p").size
-
-        assert_equal 1, parser.search("#3 + p").size
-        assert_equal "p4 ", parser.search("#3 + p").inner_text
-        assert_equal 0, parser.search("#5 + p").size
-      end
-
-      def assert_result_rows intarray, result, word="row"
-        assert_equal intarray.size, result.size, "unexpected number of rows returned: '#{result.inner_text}'"
-        assert_equal intarray.map{|j| "#{word}#{j}"}.join(' '), result.inner_text.strip, result.inner_text
-      end
-    end
-  end
-end