upgrade 1.13.1
This commit is contained in:
parent
c30b87ff33
commit
36d820b501
@ -1,65 +0,0 @@
|
||||
From 74abb4f2e73bb61b17d9f1a0ad717c881943b877 Mon Sep 17 00:00:00 2001
|
||||
From: Aaron Patterson <aaron.patterson@gmail.com>
|
||||
Date: Wed, 26 Feb 2020 13:51:43 -0800
|
||||
Subject: [PATCH] Work around a bug in libxml2
|
||||
|
||||
This commit works around a bug in libxml2 where parsing schemas can
|
||||
result in dangling pointers which can lead to a segv.
|
||||
|
||||
Upstream bug is here: https://gitlab.gnome.org/GNOME/libxml2/issues/148
|
||||
|
||||
Fixes #1985
|
||||
---
|
||||
ext/nokogiri/xml_schema.c | 29 +++++++++++++++++++++++++++++
|
||||
1 file changed, 29 insertions(+)
|
||||
|
||||
diff --git a/ext/nokogiri/xml_schema.c b/ext/nokogiri/xml_schema.c
|
||||
index da2774b..439f721 100644
|
||||
--- a/ext/nokogiri/xml_schema.c
|
||||
+++ b/ext/nokogiri/xml_schema.c
|
||||
@@ -133,6 +133,31 @@ static VALUE read_memory(VALUE klass, VALUE content)
|
||||
return rb_schema;
|
||||
}
|
||||
|
||||
+/* Schema creation will remove and deallocate "blank" nodes.
|
||||
+ * If those blank nodes have been exposed to Ruby, they could get freed
|
||||
+ * out from under the VALUE pointer. This function checks to see if any of
|
||||
+ * those nodes have been exposed to Ruby, and if so we should raise an exception.
|
||||
+ */
|
||||
+static int has_blank_nodes_p(VALUE cache)
|
||||
+{
|
||||
+ long i;
|
||||
+
|
||||
+ if (NIL_P(cache)) {
|
||||
+ return 0;
|
||||
+ }
|
||||
+
|
||||
+ for (i = 0; i < RARRAY_LEN(cache); i++) {
|
||||
+ xmlNodePtr node;
|
||||
+ VALUE element = rb_ary_entry(cache, i);
|
||||
+ Data_Get_Struct(element, xmlNode, node);
|
||||
+ if (xmlIsBlankNode(node)) {
|
||||
+ return 1;
|
||||
+ }
|
||||
+ }
|
||||
+
|
||||
+ return 0;
|
||||
+}
|
||||
+
|
||||
/*
|
||||
* call-seq:
|
||||
* from_document(doc)
|
||||
@@ -152,6 +177,10 @@ static VALUE from_document(VALUE klass, VALUE document)
|
||||
/* In case someone passes us a node. ugh. */
|
||||
doc = doc->doc;
|
||||
|
||||
+ if (has_blank_nodes_p(DOC_NODE_CACHE(doc))) {
|
||||
+ rb_raise(rb_eArgError, "Creating a schema from a document that has blank nodes exposed to Ruby is dangerous");
|
||||
+ }
|
||||
+
|
||||
ctx = xmlSchemaNewDocParserCtxt(doc);
|
||||
|
||||
errors = rb_ary_new();
|
||||
--
|
||||
2.23.0
|
||||
|
||||
@ -1,278 +0,0 @@
|
||||
From 9c87439d9afa14a365ff13e73adc809cb2c3d97b Mon Sep 17 00:00:00 2001
|
||||
From: Mike Dalessio <mike.dalessio@gmail.com>
|
||||
Date: Mon, 23 Nov 2020 00:47:02 -0500
|
||||
Subject: [PATCH] feat: XML::Schema and RelaxNG creation accept optional
|
||||
ParseOptions
|
||||
|
||||
I'm trying out a new pattern, which is that the parsed object carries
|
||||
around the ParseOptions it was created with, which should make some
|
||||
testing a bit easier.
|
||||
|
||||
I'm also not implementing the "config block" pattern in use for
|
||||
Documents, because I think the UX is weird and I'm hoping to change
|
||||
everything to use kwargs in a 2.0 release, anyway.
|
||||
---
|
||||
ext/nokogiri/xml_relax_ng.c | 39 ++++++++++++++++++--------
|
||||
ext/nokogiri/xml_schema.c | 46 +++++++++++++++++++++++--------
|
||||
lib/nokogiri/xml/parse_options.rb | 2 ++
|
||||
lib/nokogiri/xml/relax_ng.rb | 4 +--
|
||||
lib/nokogiri/xml/schema.rb | 10 ++++---
|
||||
5 files changed, 72 insertions(+), 29 deletions(-)
|
||||
|
||||
diff --git a/ext/nokogiri/xml_relax_ng.c b/ext/nokogiri/xml_relax_ng.c
|
||||
index e17b11a..f361d27 100644
|
||||
--- a/ext/nokogiri/xml_relax_ng.c
|
||||
+++ b/ext/nokogiri/xml_relax_ng.c
|
||||
@@ -53,16 +53,24 @@ static VALUE validate_document(VALUE self, VALUE document)
|
||||
*
|
||||
* Create a new RelaxNG from the contents of +string+
|
||||
*/
|
||||
-static VALUE read_memory(VALUE klass, VALUE content)
|
||||
+static VALUE read_memory(int argc, VALUE *argv, VALUE klass)
|
||||
{
|
||||
- xmlRelaxNGParserCtxtPtr ctx = xmlRelaxNGNewMemParserCtxt(
|
||||
- (const char *)StringValuePtr(content),
|
||||
- (int)RSTRING_LEN(content)
|
||||
- );
|
||||
+ VALUE content;
|
||||
+ VALUE parse_options;
|
||||
+ xmlRelaxNGParserCtxtPtr ctx;
|
||||
xmlRelaxNGPtr schema;
|
||||
- VALUE errors = rb_ary_new();
|
||||
+ VALUE errors;
|
||||
VALUE rb_schema;
|
||||
+ int scanned_args = 0;
|
||||
+
|
||||
+ scanned_args = rb_scan_args(argc, argv, "11", &content, &parse_options);
|
||||
+ if (scanned_args == 1) {
|
||||
+ parse_options = rb_const_get(rb_const_get(mNokogiriXml, rb_intern("ParseOptions")), rb_intern("DEFAULT_SCHEMA"));
|
||||
+ }
|
||||
|
||||
+ ctx = xmlRelaxNGNewMemParserCtxt((const char *)StringValuePtr(content), (int)RSTRING_LEN(content));
|
||||
+
|
||||
+ errors = rb_ary_new();
|
||||
xmlSetStructuredErrorFunc((void *)errors, Nokogiri_error_array_pusher);
|
||||
|
||||
#ifdef HAVE_XMLRELAXNGSETPARSERSTRUCTUREDERRORS
|
||||
@@ -90,6 +98,7 @@ static VALUE read_memory(VALUE klass, VALUE content)
|
||||
|
||||
rb_schema = Data_Wrap_Struct(klass, 0, dealloc, schema);
|
||||
rb_iv_set(rb_schema, "@errors", errors);
|
||||
+ rb_iv_set(rb_schema, "@parse_options", parse_options);
|
||||
|
||||
return rb_schema;
|
||||
}
|
||||
@@ -100,18 +109,25 @@ static VALUE read_memory(VALUE klass, VALUE content)
|
||||
*
|
||||
* Create a new RelaxNG schema from the Nokogiri::XML::Document +doc+
|
||||
*/
|
||||
-static VALUE from_document(VALUE klass, VALUE document)
|
||||
+static VALUE from_document(int argc, VALUE *argv, VALUE klass)
|
||||
{
|
||||
+ VALUE document;
|
||||
+ VALUE parse_options;
|
||||
xmlDocPtr doc;
|
||||
xmlRelaxNGParserCtxtPtr ctx;
|
||||
xmlRelaxNGPtr schema;
|
||||
VALUE errors;
|
||||
VALUE rb_schema;
|
||||
+ int scanned_args = 0;
|
||||
+
|
||||
+ scanned_args = rb_scan_args(argc, argv, "11", &document, &parse_options);
|
||||
|
||||
Data_Get_Struct(document, xmlDoc, doc);
|
||||
+ doc = doc->doc; /* In case someone passes us a node. ugh. */
|
||||
|
||||
- /* In case someone passes us a node. ugh. */
|
||||
- doc = doc->doc;
|
||||
+ if (scanned_args == 1) {
|
||||
+ parse_options = rb_const_get(rb_const_get(mNokogiriXml, rb_intern("ParseOptions")), rb_intern("DEFAULT_SCHEMA"));
|
||||
+ }
|
||||
|
||||
ctx = xmlRelaxNGNewDocParserCtxt(doc);
|
||||
|
||||
@@ -142,6 +158,7 @@ static VALUE from_document(VALUE klass, VALUE document)
|
||||
|
||||
rb_schema = Data_Wrap_Struct(klass, 0, dealloc, schema);
|
||||
rb_iv_set(rb_schema, "@errors", errors);
|
||||
+ rb_iv_set(rb_schema, "@parse_options", parse_options);
|
||||
|
||||
return rb_schema;
|
||||
}
|
||||
@@ -155,7 +172,7 @@ void init_xml_relax_ng()
|
||||
|
||||
cNokogiriXmlRelaxNG = klass;
|
||||
|
||||
- rb_define_singleton_method(klass, "read_memory", read_memory, 1);
|
||||
- rb_define_singleton_method(klass, "from_document", from_document, 1);
|
||||
+ rb_define_singleton_method(klass, "read_memory", read_memory, -1);
|
||||
+ rb_define_singleton_method(klass, "from_document", from_document, -1);
|
||||
rb_define_private_method(klass, "validate_document", validate_document, 1);
|
||||
}
|
||||
diff --git a/ext/nokogiri/xml_schema.c b/ext/nokogiri/xml_schema.c
|
||||
index 439f721..ea7c3d3 100644
|
||||
--- a/ext/nokogiri/xml_schema.c
|
||||
+++ b/ext/nokogiri/xml_schema.c
|
||||
@@ -93,15 +93,26 @@ static VALUE validate_file(VALUE self, VALUE rb_filename)
|
||||
*
|
||||
* Create a new Schema from the contents of +string+
|
||||
*/
|
||||
-static VALUE read_memory(VALUE klass, VALUE content)
|
||||
+static VALUE read_memory(int argc, VALUE *argv, VALUE klass)
|
||||
{
|
||||
+ VALUE content;
|
||||
+ VALUE parse_options;
|
||||
+ int parse_options_int;
|
||||
+ xmlSchemaParserCtxtPtr ctx;
|
||||
xmlSchemaPtr schema;
|
||||
- xmlSchemaParserCtxtPtr ctx = xmlSchemaNewMemParserCtxt(
|
||||
- (const char *)StringValuePtr(content),
|
||||
- (int)RSTRING_LEN(content)
|
||||
- );
|
||||
+ VALUE errors;
|
||||
VALUE rb_schema;
|
||||
- VALUE errors = rb_ary_new();
|
||||
+ int scanned_args = 0;
|
||||
+
|
||||
+ scanned_args = rb_scan_args(argc, argv, "11", &content, &parse_options);
|
||||
+ if (scanned_args == 1) {
|
||||
+ parse_options = rb_const_get(rb_const_get(mNokogiriXml, rb_intern("ParseOptions")), rb_intern("DEFAULT_SCHEMA"));
|
||||
+ }
|
||||
+ parse_options_int = (int)NUM2INT(rb_funcall(parse_options, rb_intern("to_i"), 0));
|
||||
+
|
||||
+ ctx = xmlSchemaNewMemParserCtxt((const char *)StringValuePtr(content), (int)RSTRING_LEN(content));
|
||||
+
|
||||
+ errors = rb_ary_new();
|
||||
xmlSetStructuredErrorFunc((void *)errors, Nokogiri_error_array_pusher);
|
||||
|
||||
#ifdef HAVE_XMLSCHEMASETPARSERSTRUCTUREDERRORS
|
||||
@@ -109,7 +120,7 @@ static VALUE read_memory(VALUE klass, VALUE content)
|
||||
ctx,
|
||||
Nokogiri_error_array_pusher,
|
||||
(void *)errors
|
||||
- );
|
||||
+ );
|
||||
#endif
|
||||
|
||||
schema = xmlSchemaParse(ctx);
|
||||
@@ -129,6 +140,7 @@ static VALUE read_memory(VALUE klass, VALUE content)
|
||||
|
||||
rb_schema = Data_Wrap_Struct(klass, 0, dealloc, schema);
|
||||
rb_iv_set(rb_schema, "@errors", errors);
|
||||
+ rb_iv_set(rb_schema, "@parse_options", parse_options);
|
||||
|
||||
return rb_schema;
|
||||
}
|
||||
@@ -164,18 +176,27 @@ static int has_blank_nodes_p(VALUE cache)
|
||||
*
|
||||
* Create a new Schema from the Nokogiri::XML::Document +doc+
|
||||
*/
|
||||
-static VALUE from_document(VALUE klass, VALUE document)
|
||||
+static VALUE from_document(int argc, VALUE *argv, VALUE klass)
|
||||
{
|
||||
+ VALUE document;
|
||||
+ VALUE parse_options;
|
||||
+ int parse_options_int;
|
||||
xmlDocPtr doc;
|
||||
xmlSchemaParserCtxtPtr ctx;
|
||||
xmlSchemaPtr schema;
|
||||
VALUE errors;
|
||||
VALUE rb_schema;
|
||||
+ int scanned_args = 0;
|
||||
+
|
||||
+ scanned_args = rb_scan_args(argc, argv, "11", &document, &parse_options);
|
||||
|
||||
Data_Get_Struct(document, xmlDoc, doc);
|
||||
+ doc = doc->doc; /* In case someone passes us a node. ugh. */
|
||||
|
||||
- /* In case someone passes us a node. ugh. */
|
||||
- doc = doc->doc;
|
||||
+ if (scanned_args == 1) {
|
||||
+ parse_options = rb_const_get(rb_const_get(mNokogiriXml, rb_intern("ParseOptions")), rb_intern("DEFAULT_SCHEMA"));
|
||||
+ }
|
||||
+ parse_options_int = (int)NUM2INT(rb_funcall(parse_options, rb_intern("to_i"), 0));
|
||||
|
||||
if (has_blank_nodes_p(DOC_NODE_CACHE(doc))) {
|
||||
rb_raise(rb_eArgError, "Creating a schema from a document that has blank nodes exposed to Ruby is dangerous");
|
||||
@@ -211,6 +232,7 @@ static VALUE from_document(VALUE klass, VALUE document)
|
||||
|
||||
rb_schema = Data_Wrap_Struct(klass, 0, dealloc, schema);
|
||||
rb_iv_set(rb_schema, "@errors", errors);
|
||||
+ rb_iv_set(rb_schema, "@parse_options", parse_options);
|
||||
|
||||
return rb_schema;
|
||||
|
||||
@@ -226,8 +248,8 @@ void init_xml_schema()
|
||||
|
||||
cNokogiriXmlSchema = klass;
|
||||
|
||||
- rb_define_singleton_method(klass, "read_memory", read_memory, 1);
|
||||
- rb_define_singleton_method(klass, "from_document", from_document, 1);
|
||||
+ rb_define_singleton_method(klass, "read_memory", read_memory, -1);
|
||||
+ rb_define_singleton_method(klass, "from_document", from_document, -1);
|
||||
|
||||
rb_define_private_method(klass, "validate_document", validate_document, 1);
|
||||
rb_define_private_method(klass, "validate_file", validate_file, 1);
|
||||
diff --git a/lib/nokogiri/xml/parse_options.rb b/lib/nokogiri/xml/parse_options.rb
|
||||
index 8969578..c6d3d1c 100644
|
||||
--- a/lib/nokogiri/xml/parse_options.rb
|
||||
+++ b/lib/nokogiri/xml/parse_options.rb
|
||||
@@ -72,6 +72,8 @@ module Nokogiri
|
||||
DEFAULT_XML = RECOVER | NONET
|
||||
# the default options used for parsing HTML documents
|
||||
DEFAULT_HTML = RECOVER | NOERROR | NOWARNING | NONET
|
||||
+ # the default options used for parsing XML schemas
|
||||
+ DEFAULT_SCHEMA = NONET
|
||||
|
||||
attr_accessor :options
|
||||
def initialize options = STRICT
|
||||
diff --git a/lib/nokogiri/xml/relax_ng.rb b/lib/nokogiri/xml/relax_ng.rb
|
||||
index 5a645a4..79bc30c 100644
|
||||
--- a/lib/nokogiri/xml/relax_ng.rb
|
||||
+++ b/lib/nokogiri/xml/relax_ng.rb
|
||||
@@ -4,8 +4,8 @@ module Nokogiri
|
||||
###
|
||||
# Create a new Nokogiri::XML::RelaxNG document from +string_or_io+.
|
||||
# See Nokogiri::XML::RelaxNG for an example.
|
||||
- def RelaxNG string_or_io
|
||||
- RelaxNG.new(string_or_io)
|
||||
+ def RelaxNG(string_or_io, options = ParseOptions::DEFAULT_SCHEMA)
|
||||
+ RelaxNG.new(string_or_io, options)
|
||||
end
|
||||
end
|
||||
|
||||
diff --git a/lib/nokogiri/xml/schema.rb b/lib/nokogiri/xml/schema.rb
|
||||
index 65a7bcd..a88f69c 100644
|
||||
--- a/lib/nokogiri/xml/schema.rb
|
||||
+++ b/lib/nokogiri/xml/schema.rb
|
||||
@@ -4,8 +4,8 @@ module Nokogiri
|
||||
###
|
||||
# Create a new Nokogiri::XML::Schema object using a +string_or_io+
|
||||
# object.
|
||||
- def Schema string_or_io
|
||||
- Schema.new(string_or_io)
|
||||
+ def Schema(string_or_io, options = ParseOptions::DEFAULT_SCHEMA)
|
||||
+ Schema.new(string_or_io, options)
|
||||
end
|
||||
end
|
||||
|
||||
@@ -29,12 +29,14 @@ module Nokogiri
|
||||
class Schema
|
||||
# Errors while parsing the schema file
|
||||
attr_accessor :errors
|
||||
+ # The Nokogiri::XML::ParseOptions used to parse the schema
|
||||
+ attr_accessor :parse_options
|
||||
|
||||
###
|
||||
# Create a new Nokogiri::XML::Schema object using a +string_or_io+
|
||||
# object.
|
||||
- def self.new string_or_io
|
||||
- from_document Nokogiri::XML(string_or_io)
|
||||
+ def self.new string_or_io, options = ParseOptions::DEFAULT_SCHEMA
|
||||
+ from_document(Nokogiri::XML(string_or_io), options)
|
||||
end
|
||||
|
||||
###
|
||||
--
|
||||
2.23.0
|
||||
|
||||
@ -1,684 +0,0 @@
|
||||
From 412f4e3a396dd36677ca202df96aa36656f9c800 Mon Sep 17 00:00:00 2001
|
||||
From: Mike Dalessio <mike.dalessio@gmail.com>
|
||||
Date: Fri, 24 Sep 2021 14:13:39 -0400
|
||||
Subject: [PATCH] refactor(jruby): handle errors more consistently
|
||||
|
||||
NokogiriErrorHandler stores RubyException but also accepts (and
|
||||
type-converts) Exception and RaiseException.
|
||||
|
||||
NokgiriHandler uses NokogiriErrorHandler under the hood.
|
||||
|
||||
NokogiriErrorHandler classes use addError consistently everywhere.
|
||||
---
|
||||
ext/java/nokogiri/XmlSaxParserContext.java | 106 +++++-------------
|
||||
ext/java/nokogiri/XmlSaxPushParser.java | 42 +++----
|
||||
.../internals/NokogiriEntityResolver.java | 2 +-
|
||||
.../internals/NokogiriErrorHandler.java | 37 ++++--
|
||||
.../nokogiri/internals/NokogiriHandler.java | 26 +----
|
||||
.../NokogiriNonStrictErrorHandler.java | 17 +--
|
||||
...okogiriNonStrictErrorHandler4NekoHtml.java | 18 +--
|
||||
.../internals/NokogiriStrictErrorHandler.java | 13 ++-
|
||||
.../internals/XmlDomParserContext.java | 27 ++---
|
||||
9 files changed, 115 insertions(+), 173 deletions(-)
|
||||
|
||||
diff --git a/ext/java/nokogiri/XmlSaxParserContext.java b/ext/java/nokogiri/XmlSaxParserContext.java
|
||||
index 5537619..5727a10 100644
|
||||
--- a/ext/java/nokogiri/XmlSaxParserContext.java
|
||||
+++ b/ext/java/nokogiri/XmlSaxParserContext.java
|
||||
@@ -32,33 +32,23 @@
|
||||
|
||||
package nokogiri;
|
||||
|
||||
-import static org.jruby.runtime.Helpers.invoke;
|
||||
-
|
||||
import java.io.IOException;
|
||||
import java.io.InputStream;
|
||||
|
||||
-import nokogiri.internals.NokogiriHandler;
|
||||
-import nokogiri.internals.NokogiriHelpers;
|
||||
-import nokogiri.internals.ParserContext;
|
||||
-import nokogiri.internals.XmlSaxParser;
|
||||
+import static org.jruby.runtime.Helpers.invoke;
|
||||
|
||||
+import nokogiri.internals.*;
|
||||
import org.apache.xerces.parsers.AbstractSAXParser;
|
||||
import org.jruby.Ruby;
|
||||
import org.jruby.RubyClass;
|
||||
import org.jruby.RubyFixnum;
|
||||
-import org.jruby.RubyModule;
|
||||
-import org.jruby.RubyObjectAdapter;
|
||||
import org.jruby.anno.JRubyClass;
|
||||
import org.jruby.anno.JRubyMethod;
|
||||
import org.jruby.exceptions.RaiseException;
|
||||
-import org.jruby.javasupport.JavaEmbedUtils;
|
||||
+import org.jruby.runtime.Helpers;
|
||||
import org.jruby.runtime.ThreadContext;
|
||||
import org.jruby.runtime.builtin.IRubyObject;
|
||||
-import org.xml.sax.ContentHandler;
|
||||
-import org.xml.sax.ErrorHandler;
|
||||
import org.xml.sax.SAXException;
|
||||
-import org.xml.sax.SAXNotRecognizedException;
|
||||
-import org.xml.sax.SAXNotSupportedException;
|
||||
import org.xml.sax.SAXParseException;
|
||||
|
||||
/**
|
||||
@@ -82,6 +72,7 @@ public class XmlSaxParserContext extends ParserContext {
|
||||
protected AbstractSAXParser parser;
|
||||
|
||||
protected NokogiriHandler handler;
|
||||
+ protected NokogiriErrorHandler errorHandler;
|
||||
private boolean replaceEntities = true;
|
||||
private boolean recovery = false;
|
||||
|
||||
@@ -179,24 +170,11 @@ public class XmlSaxParserContext extends ParserContext {
|
||||
return (XmlSaxParserContext) NokogiriService.XML_SAXPARSER_CONTEXT_ALLOCATOR.allocate(runtime, klazz);
|
||||
}
|
||||
|
||||
- /**
|
||||
- * Set a property of the underlying parser.
|
||||
- */
|
||||
- protected void setProperty(String key, Object val)
|
||||
- throws SAXNotRecognizedException, SAXNotSupportedException {
|
||||
- parser.setProperty(key, val);
|
||||
- }
|
||||
-
|
||||
- protected void setContentHandler(ContentHandler handler) {
|
||||
- parser.setContentHandler(handler);
|
||||
- }
|
||||
-
|
||||
- protected void setErrorHandler(ErrorHandler handler) {
|
||||
- parser.setErrorHandler(handler);
|
||||
- }
|
||||
-
|
||||
public final NokogiriHandler getNokogiriHandler() { return handler; }
|
||||
|
||||
+ public final NokogiriErrorHandler
|
||||
+ getNokogiriErrorHandler() { return errorHandler; }
|
||||
+
|
||||
/**
|
||||
* Perform any initialization prior to parsing with the handler
|
||||
* <code>handlerRuby</code>. Convenience hook for subclasses.
|
||||
@@ -221,6 +199,17 @@ public class XmlSaxParserContext extends ParserContext {
|
||||
parser.parse(getInputSource());
|
||||
}
|
||||
|
||||
+ protected static Options
|
||||
+ defaultParseOptions(ThreadContext context)
|
||||
+ {
|
||||
+ return new ParserContext.Options(
|
||||
+ RubyFixnum.fix2long(Helpers.invoke(context,
|
||||
+ ((RubyClass)context.getRuntime().getClassFromPath("Nokogiri::XML::ParseOptions"))
|
||||
+ .getConstant("DEFAULT_XML"),
|
||||
+ "to_i"))
|
||||
+ );
|
||||
+ }
|
||||
+
|
||||
@JRubyMethod
|
||||
public IRubyObject parse_with(ThreadContext context, IRubyObject handlerRuby) {
|
||||
final Ruby runtime = context.getRuntime();
|
||||
@@ -229,14 +218,18 @@ public class XmlSaxParserContext extends ParserContext {
|
||||
throw runtime.newArgumentError("argument must respond_to document");
|
||||
}
|
||||
|
||||
- NokogiriHandler handler = this.handler = new NokogiriHandler(runtime, handlerRuby);
|
||||
- preParse(runtime, handlerRuby, handler);
|
||||
+ /* TODO: how should we pass in parse options? */
|
||||
+ ParserContext.Options options = defaultParseOptions(context);
|
||||
+
|
||||
+ errorHandler = new NokogiriStrictErrorHandler(runtime, options.noError, options.noWarning);
|
||||
+ handler = new NokogiriHandler(runtime, handlerRuby, errorHandler);
|
||||
|
||||
- setContentHandler(handler);
|
||||
- setErrorHandler(handler);
|
||||
+ preParse(runtime, handlerRuby, handler);
|
||||
+ parser.setContentHandler(handler);
|
||||
+ parser.setErrorHandler(handler);
|
||||
|
||||
try{
|
||||
- setProperty("http://xml.org/sax/properties/lexical-handler", handler);
|
||||
+ parser.setProperty("http://xml.org/sax/properties/lexical-handler", handler);
|
||||
}
|
||||
catch (Exception ex) {
|
||||
throw runtime.newRuntimeError("Problem while creating XML SAX Parser: " + ex.toString());
|
||||
@@ -269,8 +262,6 @@ public class XmlSaxParserContext extends ParserContext {
|
||||
|
||||
postParse(runtime, handlerRuby, handler);
|
||||
|
||||
- //maybeTrimLeadingAndTrailingWhitespace(context, handlerRuby);
|
||||
-
|
||||
return runtime.getNil();
|
||||
}
|
||||
|
||||
@@ -310,48 +301,6 @@ public class XmlSaxParserContext extends ParserContext {
|
||||
return context.runtime.newBoolean(recovery);
|
||||
}
|
||||
|
||||
- /**
|
||||
- * If the handler's document is a FragmentHandler, attempt to trim
|
||||
- * leading and trailing whitespace.
|
||||
- *
|
||||
- * This is a bit hackish and depends heavily on the internals of
|
||||
- * FragmentHandler.
|
||||
- */
|
||||
- protected void maybeTrimLeadingAndTrailingWhitespace(ThreadContext context, IRubyObject parser) {
|
||||
- RubyObjectAdapter adapter = JavaEmbedUtils.newObjectAdapter();
|
||||
- RubyModule mod = context.getRuntime().getClassFromPath("Nokogiri::XML::FragmentHandler");
|
||||
-
|
||||
- IRubyObject handler = adapter.getInstanceVariable(parser, "@document");
|
||||
- if (handler == null || handler.isNil() || !adapter.isKindOf(handler, mod))
|
||||
- return;
|
||||
- IRubyObject stack = adapter.getInstanceVariable(handler, "@stack");
|
||||
- if (stack == null || stack.isNil())
|
||||
- return;
|
||||
- // doc is finally a DocumentFragment whose nodes we can check
|
||||
- IRubyObject doc = adapter.callMethod(stack, "first");
|
||||
- if (doc == null || doc.isNil())
|
||||
- return;
|
||||
-
|
||||
- IRubyObject children;
|
||||
-
|
||||
- for (;;) {
|
||||
- children = adapter.callMethod(doc, "children");
|
||||
- IRubyObject first = adapter.callMethod(children, "first");
|
||||
- if (NokogiriHelpers.isBlank(first)) adapter.callMethod(first, "unlink");
|
||||
- else break;
|
||||
- }
|
||||
-
|
||||
- for (;;) {
|
||||
- children = adapter.callMethod(doc, "children");
|
||||
- IRubyObject last = adapter.callMethod(children, "last");
|
||||
- if (NokogiriHelpers.isBlank(last)) adapter.callMethod(last, "unlink");
|
||||
- else break;
|
||||
- }
|
||||
-
|
||||
- // While we have a document, normalize it.
|
||||
- ((XmlNode) doc).normalize();
|
||||
- }
|
||||
-
|
||||
@JRubyMethod(name="column")
|
||||
public IRubyObject column(ThreadContext context) {
|
||||
final Integer number = handler.getColumn();
|
||||
@@ -365,5 +314,4 @@ public class XmlSaxParserContext extends ParserContext {
|
||||
if (number == null) return context.getRuntime().getNil();
|
||||
return RubyFixnum.newFixnum(context.getRuntime(), number.longValue());
|
||||
}
|
||||
-
|
||||
}
|
||||
diff --git a/ext/java/nokogiri/XmlSaxPushParser.java b/ext/java/nokogiri/XmlSaxPushParser.java
|
||||
index 8e65b92..b1b65a9 100644
|
||||
--- a/ext/java/nokogiri/XmlSaxPushParser.java
|
||||
+++ b/ext/java/nokogiri/XmlSaxPushParser.java
|
||||
@@ -32,21 +32,10 @@
|
||||
|
||||
package nokogiri;
|
||||
|
||||
-import static nokogiri.internals.NokogiriHelpers.getNokogiriClass;
|
||||
-import static org.jruby.runtime.Helpers.invoke;
|
||||
-
|
||||
-import java.io.ByteArrayInputStream;
|
||||
-import java.io.IOException;
|
||||
-import java.io.InputStream;
|
||||
-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 org.jruby.Ruby;
|
||||
import org.jruby.RubyClass;
|
||||
+import org.jruby.RubyException;
|
||||
import org.jruby.RubyObject;
|
||||
import org.jruby.anno.JRubyClass;
|
||||
import org.jruby.anno.JRubyMethod;
|
||||
@@ -54,11 +43,14 @@ import org.jruby.exceptions.RaiseException;
|
||||
import org.jruby.runtime.ThreadContext;
|
||||
import org.jruby.runtime.builtin.IRubyObject;
|
||||
|
||||
-import nokogiri.internals.ClosedStreamException;
|
||||
-import nokogiri.internals.NokogiriBlockingQueueInputStream;
|
||||
-import nokogiri.internals.NokogiriHandler;
|
||||
-import nokogiri.internals.NokogiriHelpers;
|
||||
-import nokogiri.internals.ParserContext;
|
||||
+import java.io.ByteArrayInputStream;
|
||||
+import java.io.IOException;
|
||||
+import java.io.InputStream;
|
||||
+import java.util.List;
|
||||
+import java.util.concurrent.*;
|
||||
+
|
||||
+import static nokogiri.internals.NokogiriHelpers.getNokogiriClass;
|
||||
+import static org.jruby.runtime.Helpers.invoke;
|
||||
|
||||
/**
|
||||
* Class for Nokogiri::XML::SAX::PushParser
|
||||
@@ -173,7 +165,8 @@ public class XmlSaxPushParser extends RubyObject {
|
||||
|
||||
if (!options.recover && parserTask.getErrorCount() > errorCount0) {
|
||||
terminateTask(context.runtime);
|
||||
- throw ex = parserTask.getLastError();
|
||||
+ ex = parserTask.getLastError().toThrowable();
|
||||
+ throw ex;
|
||||
}
|
||||
|
||||
return this;
|
||||
@@ -273,14 +266,13 @@ public class XmlSaxPushParser extends RubyObject {
|
||||
|
||||
synchronized final int getErrorCount() {
|
||||
// check for null because thread may not have started yet
|
||||
- if (parser.getNokogiriHandler() == null) return 0;
|
||||
- return parser.getNokogiriHandler().getErrorCount();
|
||||
+ if (parser.getNokogiriErrorHandler() == null) { return 0; }
|
||||
+ return parser.getNokogiriErrorHandler().getErrors().size();
|
||||
}
|
||||
|
||||
- synchronized final RaiseException getLastError() {
|
||||
- return parser.getNokogiriHandler().getLastError();
|
||||
+ synchronized final RubyException getLastError() {
|
||||
+ List<RubyException> errors = parser.getNokogiriErrorHandler().getErrors();
|
||||
+ return errors.get(errors.size() - 1);
|
||||
}
|
||||
-
|
||||
}
|
||||
-
|
||||
}
|
||||
diff --git a/ext/java/nokogiri/internals/NokogiriEntityResolver.java b/ext/java/nokogiri/internals/NokogiriEntityResolver.java
|
||||
index d97da66..48942d0 100644
|
||||
--- a/ext/java/nokogiri/internals/NokogiriEntityResolver.java
|
||||
+++ b/ext/java/nokogiri/internals/NokogiriEntityResolver.java
|
||||
@@ -68,7 +68,7 @@ public class NokogiriEntityResolver implements EntityResolver2 {
|
||||
}
|
||||
|
||||
private void addError(String errorMessage) {
|
||||
- if (handler != null) handler.errors.add(new Exception(errorMessage));
|
||||
+ if (handler != null) { handler.addError(new Exception(errorMessage)); }
|
||||
}
|
||||
|
||||
/**
|
||||
diff --git a/ext/java/nokogiri/internals/NokogiriErrorHandler.java b/ext/java/nokogiri/internals/NokogiriErrorHandler.java
|
||||
index 7980107..13b1725 100644
|
||||
--- a/ext/java/nokogiri/internals/NokogiriErrorHandler.java
|
||||
+++ b/ext/java/nokogiri/internals/NokogiriErrorHandler.java
|
||||
@@ -32,12 +32,16 @@
|
||||
|
||||
package nokogiri.internals;
|
||||
|
||||
-import java.util.ArrayList;
|
||||
-import java.util.List;
|
||||
-
|
||||
+import nokogiri.XmlSyntaxError;
|
||||
import org.apache.xerces.xni.parser.XMLErrorHandler;
|
||||
+import org.jruby.Ruby;
|
||||
+import org.jruby.RubyException;
|
||||
+import org.jruby.exceptions.RaiseException;
|
||||
import org.xml.sax.ErrorHandler;
|
||||
|
||||
+import java.util.ArrayList;
|
||||
+import java.util.List;
|
||||
+
|
||||
/**
|
||||
* Super class of error handlers.
|
||||
*
|
||||
@@ -48,19 +52,36 @@ import org.xml.sax.ErrorHandler;
|
||||
* @author Yoko Harada <yokolet@gmail.com>
|
||||
*/
|
||||
public abstract class NokogiriErrorHandler implements ErrorHandler, XMLErrorHandler {
|
||||
- protected final List<Exception> errors;
|
||||
+ private final Ruby runtime;
|
||||
+ protected final List<RubyException> errors;
|
||||
protected boolean noerror;
|
||||
protected boolean nowarning;
|
||||
|
||||
- public NokogiriErrorHandler(boolean noerror, boolean nowarning) {
|
||||
- this.errors = new ArrayList<Exception>(4);
|
||||
+ public NokogiriErrorHandler(Ruby runtime, boolean noerror, boolean nowarning)
|
||||
+ this.runtime = runtime;
|
||||
+ this.errors = new ArrayList<RubyException>(4);
|
||||
this.noerror = noerror;
|
||||
this.nowarning = nowarning;
|
||||
}
|
||||
|
||||
- List<Exception> getErrors() { return errors; }
|
||||
+ public List<RubyException> getErrors() { return errors; }
|
||||
|
||||
- public void addError(Exception ex) { errors.add(ex); }
|
||||
+ public void addError(Exception ex)
|
||||
+ {
|
||||
+ addError(XmlSyntaxError.createXMLSyntaxError(runtime, ex));
|
||||
+ }
|
||||
+
|
||||
+ public void
|
||||
+ addError(RubyException ex)
|
||||
+ {
|
||||
+ errors.add(ex);
|
||||
+ }
|
||||
+
|
||||
+ public void
|
||||
+ addError(RaiseException ex)
|
||||
+ {
|
||||
+ addError(ex.getException());
|
||||
+ }
|
||||
|
||||
protected boolean usesNekoHtml(String domain) {
|
||||
return "http://cyberneko.org/html".equals(domain);
|
||||
diff --git a/ext/java/nokogiri/internals/NokogiriHandler.java b/ext/java/nokogiri/internals/NokogiriHandler.java
|
||||
index 5e34be1..2da4011 100644
|
||||
--- a/ext/java/nokogiri/internals/NokogiriHandler.java
|
||||
+++ b/ext/java/nokogiri/internals/NokogiriHandler.java
|
||||
@@ -69,23 +69,17 @@ public class NokogiriHandler extends DefaultHandler2 implements XmlDeclHandler {
|
||||
private final Ruby runtime;
|
||||
private final RubyClass attrClass;
|
||||
private final IRubyObject object;
|
||||
-
|
||||
- /**
|
||||
- * Stores parse errors with the most-recent error last.
|
||||
- *
|
||||
- * TODO: should these be stored in the document 'errors' array?
|
||||
- * Currently only string messages are stored there.
|
||||
- */
|
||||
- private final LinkedList<RaiseException> errors = new LinkedList<RaiseException>();
|
||||
+ private NokogiriErrorHandler errorHandler;
|
||||
|
||||
private Locator locator;
|
||||
private boolean needEmptyAttrCheck;
|
||||
|
||||
- public NokogiriHandler(Ruby runtime, IRubyObject object) {
|
||||
+ public NokogiriHandler(Ruby runtime, IRubyObject object, NokogiriErrorHandler errorHandler) {
|
||||
assert object != null;
|
||||
this.runtime = runtime;
|
||||
this.attrClass = (RubyClass) runtime.getClassFromPath("Nokogiri::XML::SAX::Parser::Attribute");
|
||||
this.object = object;
|
||||
+ this.errorHandler = errorHandler;
|
||||
charactersBuilder = new StringBuilder();
|
||||
String objectName = object.getMetaClass().getName();
|
||||
if ("Nokogiri::HTML::SAX::Parser".equals(objectName)) needEmptyAttrCheck = true;
|
||||
@@ -249,9 +243,9 @@ public class NokogiriHandler extends DefaultHandler2 implements XmlDeclHandler {
|
||||
try {
|
||||
final String msg = ex.getMessage();
|
||||
call("error", runtime.newString(msg == null ? "" : msg));
|
||||
- addError(new RaiseException(XmlSyntaxError.createError(runtime, ex), true));
|
||||
+ errorHandler.addError(ex);
|
||||
} catch( RaiseException e) {
|
||||
- addError(e);
|
||||
+ errorHandler.addError(e);
|
||||
throw e;
|
||||
}
|
||||
}
|
||||
@@ -272,16 +266,8 @@ public class NokogiriHandler extends DefaultHandler2 implements XmlDeclHandler {
|
||||
call("warning", runtime.newString(msg == null ? "" : msg));
|
||||
}
|
||||
|
||||
- protected synchronized void addError(RaiseException e) {
|
||||
- errors.add(e);
|
||||
- }
|
||||
-
|
||||
public synchronized int getErrorCount() {
|
||||
- return errors.size();
|
||||
- }
|
||||
-
|
||||
- public synchronized RaiseException getLastError() {
|
||||
- return errors.getLast();
|
||||
+ return errorHandler.getErrors().size();
|
||||
}
|
||||
|
||||
private void call(String methodName) {
|
||||
diff --git a/ext/java/nokogiri/internals/NokogiriNonStrictErrorHandler.java b/ext/java/nokogiri/internals/NokogiriNonStrictErrorHandler.java
|
||||
index 15b622c..f49e13d 100644
|
||||
--- a/ext/java/nokogiri/internals/NokogiriNonStrictErrorHandler.java
|
||||
+++ b/ext/java/nokogiri/internals/NokogiriNonStrictErrorHandler.java
|
||||
@@ -33,6 +33,7 @@
|
||||
package nokogiri.internals;
|
||||
|
||||
import org.apache.xerces.xni.parser.XMLParseException;
|
||||
+import org.jruby.Ruby;
|
||||
import org.xml.sax.SAXException;
|
||||
import org.xml.sax.SAXParseException;
|
||||
|
||||
@@ -43,16 +44,16 @@ import org.xml.sax.SAXParseException;
|
||||
* @author Yoko Harada <yokolet@gmail.com>
|
||||
*/
|
||||
public class NokogiriNonStrictErrorHandler extends NokogiriErrorHandler{
|
||||
- public NokogiriNonStrictErrorHandler(boolean noerror, boolean nowarning) {
|
||||
- super(noerror, nowarning);
|
||||
+ public NokogiriNonStrictErrorHandler(Ruby runtime, boolean noerror, boolean nowarning) {
|
||||
+ super(runtime, noerror, nowarning);
|
||||
}
|
||||
|
||||
public void warning(SAXParseException ex) throws SAXException {
|
||||
- errors.add(ex);
|
||||
+ addError(ex);
|
||||
}
|
||||
|
||||
public void error(SAXParseException ex) throws SAXException {
|
||||
- errors.add(ex);
|
||||
+ addError(ex);
|
||||
}
|
||||
|
||||
public void fatalError(SAXParseException ex) throws SAXException {
|
||||
@@ -61,7 +62,7 @@ public class NokogiriNonStrictErrorHandler extends NokogiriErrorHandler{
|
||||
// found in the prolog, instead it will keep calling this method and we'll
|
||||
// keep inserting the error in the document errors array until we run
|
||||
// out of memory
|
||||
- errors.add(ex);
|
||||
+ addError(ex);
|
||||
String message = ex.getMessage();
|
||||
|
||||
// The problem with Xerces is that some errors will cause the
|
||||
@@ -74,15 +75,15 @@ public class NokogiriNonStrictErrorHandler extends NokogiriErrorHandler{
|
||||
}
|
||||
|
||||
public void error(String domain, String key, XMLParseException e) {
|
||||
- errors.add(e);
|
||||
+ addError(e);
|
||||
}
|
||||
|
||||
public void fatalError(String domain, String key, XMLParseException e) {
|
||||
- errors.add(e);
|
||||
+ addError(e);
|
||||
}
|
||||
|
||||
public void warning(String domain, String key, XMLParseException e) {
|
||||
- errors.add(e);
|
||||
+ addError(e);
|
||||
}
|
||||
|
||||
/*
|
||||
diff --git a/ext/java/nokogiri/internals/NokogiriNonStrictErrorHandler4NekoHtml.java b/ext/java/nokogiri/internals/NokogiriNonStrictErrorHandler4NekoHtml.java
|
||||
index 011af24..a2c6b33 100644
|
||||
--- a/ext/java/nokogiri/internals/NokogiriNonStrictErrorHandler4NekoHtml.java
|
||||
+++ b/ext/java/nokogiri/internals/NokogiriNonStrictErrorHandler4NekoHtml.java
|
||||
@@ -33,6 +33,7 @@
|
||||
package nokogiri.internals;
|
||||
|
||||
import org.apache.xerces.xni.parser.XMLParseException;
|
||||
+import org.jruby.Ruby;
|
||||
import org.xml.sax.SAXException;
|
||||
import org.xml.sax.SAXParseException;
|
||||
|
||||
@@ -50,12 +51,13 @@ import org.xml.sax.SAXParseException;
|
||||
*/
|
||||
public class NokogiriNonStrictErrorHandler4NekoHtml extends NokogiriErrorHandler {
|
||||
|
||||
- public NokogiriNonStrictErrorHandler4NekoHtml(boolean nowarning) {
|
||||
- super(false, nowarning);
|
||||
+ public NokogiriNonStrictErrorHandler4NekoHtml(Ruby runtime, boolean nowarning) {
|
||||
+ super(runtime, false, nowarning);
|
||||
}
|
||||
|
||||
public NokogiriNonStrictErrorHandler4NekoHtml(boolean noerror, boolean nowarning) {
|
||||
- super(noerror, nowarning);
|
||||
+ public NokogiriNonStrictErrorHandler4NekoHtml(Ruby runtime, boolean noerror, boolean nowarning) {
|
||||
+ super(runtime, noerror, nowarning);
|
||||
}
|
||||
|
||||
public void warning(SAXParseException ex) throws SAXException {
|
||||
@@ -63,11 +65,11 @@ public class NokogiriNonStrictErrorHandler4NekoHtml extends NokogiriErrorHandler
|
||||
}
|
||||
|
||||
public void error(SAXParseException ex) throws SAXException {
|
||||
- errors.add(ex);
|
||||
+ addError(ex);
|
||||
}
|
||||
|
||||
public void fatalError(SAXParseException ex) throws SAXException {
|
||||
- errors.add(ex);
|
||||
+ addError(ex);
|
||||
}
|
||||
|
||||
/**
|
||||
@@ -83,7 +85,7 @@ public class NokogiriNonStrictErrorHandler4NekoHtml extends NokogiriErrorHandler
|
||||
* @param e Exception.
|
||||
*/
|
||||
public void error(String domain, String key, XMLParseException e) {
|
||||
- errors.add(e);
|
||||
+ addError(e);
|
||||
}
|
||||
|
||||
/**
|
||||
@@ -99,7 +101,7 @@ public class NokogiriNonStrictErrorHandler4NekoHtml extends NokogiriErrorHandler
|
||||
* @param e Exception.
|
||||
*/
|
||||
public void fatalError(String domain, String key, XMLParseException e) {
|
||||
- errors.add(e);
|
||||
+ addError(e);
|
||||
}
|
||||
|
||||
/**
|
||||
@@ -115,7 +117,7 @@ public class NokogiriNonStrictErrorHandler4NekoHtml extends NokogiriErrorHandler
|
||||
* @param e Exception.
|
||||
*/
|
||||
public void warning(String domain, String key, XMLParseException e) {
|
||||
- errors.add(e);
|
||||
+ addError(e);
|
||||
}
|
||||
|
||||
}
|
||||
diff --git a/ext/java/nokogiri/internals/NokogiriStrictErrorHandler.java b/ext/java/nokogiri/internals/NokogiriStrictErrorHandler.java
|
||||
index 10315fa..fbf9787 100644
|
||||
--- a/ext/java/nokogiri/internals/NokogiriStrictErrorHandler.java
|
||||
+++ b/ext/java/nokogiri/internals/NokogiriStrictErrorHandler.java
|
||||
@@ -33,6 +33,7 @@
|
||||
package nokogiri.internals;
|
||||
|
||||
import org.apache.xerces.xni.parser.XMLParseException;
|
||||
+import org.jruby.Ruby;
|
||||
import org.xml.sax.SAXException;
|
||||
import org.xml.sax.SAXParseException;
|
||||
|
||||
@@ -44,18 +45,18 @@ import org.xml.sax.SAXParseException;
|
||||
* @author Yoko Harada <yokolet@gmail.com>
|
||||
*/
|
||||
public class NokogiriStrictErrorHandler extends NokogiriErrorHandler {
|
||||
- public NokogiriStrictErrorHandler(boolean noerror, boolean nowarning) {
|
||||
- super(noerror, nowarning);
|
||||
+ public NokogiriStrictErrorHandler(Ruby runtime, boolean noerror, boolean nowarning) {
|
||||
+ super(runtime, noerror, nowarning);
|
||||
}
|
||||
|
||||
public void warning(SAXParseException spex) throws SAXException {
|
||||
if (!nowarning) throw spex;
|
||||
- else errors.add(spex);
|
||||
+ else { addError(spex); }
|
||||
}
|
||||
|
||||
public void error(SAXParseException spex) throws SAXException {
|
||||
if (!noerror) throw spex;
|
||||
- else errors.add(spex);
|
||||
+ else { addError(spex); }
|
||||
}
|
||||
|
||||
public void fatalError(SAXParseException spex) throws SAXException {
|
||||
@@ -64,7 +65,7 @@ public class NokogiriStrictErrorHandler extends NokogiriErrorHandler {
|
||||
|
||||
public void error(String domain, String key, XMLParseException e) throws XMLParseException {
|
||||
if (!noerror) throw e;
|
||||
- else errors.add(e);
|
||||
+ else { addError(e); }
|
||||
}
|
||||
|
||||
public void fatalError(String domain, String key, XMLParseException e) throws XMLParseException {
|
||||
@@ -73,6 +74,6 @@ public class NokogiriStrictErrorHandler extends NokogiriErrorHandler {
|
||||
|
||||
public void warning(String domain, String key, XMLParseException e) throws XMLParseException {
|
||||
if (!nowarning) throw e;
|
||||
- if (!usesNekoHtml(domain)) errors.add(e);
|
||||
+ if (!usesNekoHtml(domain)) { addError(e); }
|
||||
}
|
||||
}
|
||||
diff --git a/ext/java/nokogiri/internals/XmlDomParserContext.java b/ext/java/nokogiri/internals/XmlDomParserContext.java
|
||||
index 89af2bc..839399b 100644
|
||||
--- a/ext/java/nokogiri/internals/XmlDomParserContext.java
|
||||
+++ b/ext/java/nokogiri/internals/XmlDomParserContext.java
|
||||
@@ -32,23 +32,17 @@
|
||||
|
||||
package nokogiri.internals;
|
||||
|
||||
-import static nokogiri.internals.NokogiriHelpers.getNokogiriClass;
|
||||
-import static nokogiri.internals.NokogiriHelpers.isBlank;
|
||||
-
|
||||
import java.io.IOException;
|
||||
import java.util.ArrayList;
|
||||
import java.util.List;
|
||||
|
||||
-import nokogiri.NokogiriService;
|
||||
+import static nokogiri.internals.NokogiriHelpers.isBlank;
|
||||
+
|
||||
import nokogiri.XmlDocument;
|
||||
import nokogiri.XmlDtd;
|
||||
import nokogiri.XmlSyntaxError;
|
||||
-
|
||||
import org.apache.xerces.parsers.DOMParser;
|
||||
-import org.jruby.Ruby;
|
||||
-import org.jruby.RubyArray;
|
||||
-import org.jruby.RubyClass;
|
||||
-import org.jruby.RubyFixnum;
|
||||
+import org.jruby.*;
|
||||
import org.jruby.exceptions.RaiseException;
|
||||
import org.jruby.runtime.ThreadContext;
|
||||
import org.jruby.runtime.builtin.IRubyObject;
|
||||
@@ -78,7 +72,6 @@ public class XmlDomParserContext extends ParserContext {
|
||||
protected static final String FEATURE_NOT_EXPAND_ENTITY =
|
||||
"http://apache.org/xml/features/dom/create-entity-ref-nodes";
|
||||
protected static final String FEATURE_VALIDATION = "http://xml.org/sax/features/validation";
|
||||
- private static final String XINCLUDE_FEATURE_ID = "http://apache.org/xml/features/xinclude";
|
||||
private static final String SECURITY_MANAGER = "http://apache.org/xml/properties/security-manager";
|
||||
|
||||
protected ParserContext.Options options;
|
||||
@@ -96,15 +89,15 @@ public class XmlDomParserContext extends ParserContext {
|
||||
this.options = new ParserContext.Options(RubyFixnum.fix2long(options));
|
||||
java_encoding = NokogiriHelpers.getValidEncoding(runtime, encoding);
|
||||
ruby_encoding = encoding;
|
||||
- initErrorHandler();
|
||||
+ initErrorHandler(runtime);
|
||||
initParser(runtime);
|
||||
}
|
||||
|
||||
- protected void initErrorHandler() {
|
||||
+ protected void initErrorHandler(Ruby runtime) {
|
||||
if (options.recover) {
|
||||
- errorHandler = new NokogiriNonStrictErrorHandler(options.noError, options.noWarning);
|
||||
+ errorHandler = new NokogiriNonStrictErrorHandler(runtime, options.noError, options.noWarning);
|
||||
} else {
|
||||
- errorHandler = new NokogiriStrictErrorHandler(options.noError, options.noWarning);
|
||||
+ errorHandler = new NokogiriStrictErrorHandler(runtime, options.noError, options.noWarning);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -176,12 +169,10 @@ public class XmlDomParserContext extends ParserContext {
|
||||
|
||||
public static RubyArray mapErrors(ThreadContext context, NokogiriErrorHandler errorHandler) {
|
||||
final Ruby runtime = context.runtime;
|
||||
- final List<Exception> errors = errorHandler.getErrors();
|
||||
+ final List<RubyException> errors = errorHandler.getErrors();
|
||||
final IRubyObject[] errorsAry = new IRubyObject[errors.size()];
|
||||
for (int i = 0; i < errors.size(); i++) {
|
||||
- XmlSyntaxError xmlSyntaxError = XmlSyntaxError.createXMLSyntaxError(runtime);
|
||||
- xmlSyntaxError.setException(errors.get(i));
|
||||
- errorsAry[i] = xmlSyntaxError;
|
||||
+ errorsAry[i] = errors.get(i);
|
||||
}
|
||||
return runtime.newArrayNoCopy(errorsAry);
|
||||
}
|
||||
--
|
||||
2.27.0
|
||||
|
||||
@ -1,28 +0,0 @@
|
||||
From 382860304b2efbf837cb3fcbbe806c81c27bf6b1 Mon Sep 17 00:00:00 2001
|
||||
From: Mike Dalessio <mike.dalessio@gmail.com>
|
||||
Date: Fri, 24 Sep 2021 14:15:26 -0400
|
||||
Subject: [PATCH] fix(jruby): SAX parser uses an entity resolver
|
||||
|
||||
to avoid XXE injections.
|
||||
|
||||
This behavior now matches the CRuby implementation.
|
||||
---
|
||||
ext/java/nokogiri/XmlSaxParserContext.java | 1 +
|
||||
test/xml/sax/test_parser.rb | 33 ++++++++++++++++++++++
|
||||
2 files changed, 34 insertions(+)
|
||||
|
||||
diff --git a/ext/java/nokogiri/XmlSaxParserContext.java b/ext/java/nokogiri/XmlSaxParserContext.java
|
||||
index 5727a10..e614ce9 100644
|
||||
--- a/ext/java/nokogiri/XmlSaxParserContext.java
|
||||
+++ b/ext/java/nokogiri/XmlSaxParserContext.java
|
||||
@@ -227,6 +227,7 @@ public class XmlSaxParserContext extends ParserContext {
|
||||
preParse(runtime, handlerRuby, handler);
|
||||
parser.setContentHandler(handler);
|
||||
parser.setErrorHandler(handler);
|
||||
+ parser.setEntityResolver(new NokogiriEntityResolver(runtime, errorHandler, options));
|
||||
|
||||
try{
|
||||
parser.setProperty("http://xml.org/sax/properties/lexical-handler", handler);
|
||||
--
|
||||
2.27.0
|
||||
|
||||
Binary file not shown.
27
nokogiri-create-full-tarball.sh
Normal file
27
nokogiri-create-full-tarball.sh
Normal file
@ -0,0 +1,27 @@
|
||||
#!/bin/bash
|
||||
|
||||
if [ $# -lt 2 ]
|
||||
then
|
||||
echo "$0 <name> <version>"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
set -x
|
||||
set -e
|
||||
|
||||
CURRDIR=$(pwd)
|
||||
|
||||
TMPDIRPATH=$(mktemp -d /var/tmp/$1-tar-XXXXXX)
|
||||
pushd $TMPDIRPATH
|
||||
|
||||
git clone https://github.com/sparklemotion/$1.git
|
||||
pushd $1
|
||||
git reset --hard v$2
|
||||
popd
|
||||
|
||||
ln -sf $1 $1-$2
|
||||
tar czf ${CURRDIR}/rubygem-$1-$2-full.tar.gz $1-$2/./
|
||||
|
||||
popd
|
||||
|
||||
rm -rf $TMPDIRPATH
|
||||
10
rubygem-nokogiri-1.11.0.rc4-shutdown-libxml2-warning.patch
Normal file
10
rubygem-nokogiri-1.11.0.rc4-shutdown-libxml2-warning.patch
Normal file
@ -0,0 +1,10 @@
|
||||
--- nokogiri-1.11.0.rc4/lib/nokogiri/version/info.rb.warn 2020-12-31 16:56:11.533949657 +0900
|
||||
+++ nokogiri-1.11.0.rc4/lib/nokogiri/version/info.rb 2020-12-31 16:59:38.576697147 +0900
|
||||
@@ -58,6 +58,7 @@ module Nokogiri
|
||||
|
||||
def warnings
|
||||
warnings = []
|
||||
+ return warnings
|
||||
|
||||
if libxml2?
|
||||
if compiled_libxml_version != loaded_libxml_version
|
||||
BIN
rubygem-nokogiri-1.13.1-full.tar.gz
Normal file
BIN
rubygem-nokogiri-1.13.1-full.tar.gz
Normal file
Binary file not shown.
@ -1,10 +0,0 @@
|
||||
--- nokogiri-1.6.6.4/./lib/nokogiri/version.rb.nowarn 2015-11-20 05:50:37.000000000 +0900
|
||||
+++ nokogiri-1.6.6.4/./lib/nokogiri/version.rb 2015-12-11 14:32:04.151973080 +0900
|
||||
@@ -34,6 +34,7 @@
|
||||
end
|
||||
|
||||
def warnings
|
||||
+ return []
|
||||
return [] unless libxml2?
|
||||
|
||||
if compiled_parser_version != loaded_parser_version
|
||||
@ -1,4 +1,4 @@
|
||||
%global mainver 1.10.5
|
||||
%global mainver 1.13.1
|
||||
%global mainrel 1
|
||||
%global prerpmver %(echo "%{?prever}" | sed -e 's|\\.||g')
|
||||
%global gem_name nokogiri
|
||||
@ -7,20 +7,19 @@
|
||||
Summary: An HTML, XML, SAX, and Reader parser
|
||||
Name: rubygem-%{gem_name}
|
||||
Version: %{mainver}
|
||||
Release: 3
|
||||
License: MIT
|
||||
Release: 1
|
||||
License: MIT and ASL 2.0
|
||||
URL: https://nokogiri.org
|
||||
Source0: https://rubygems.org/gems/%{gem_name}-%{mainver}%{?prever}.gem
|
||||
Source1: https://github.com/sparklemotion/%{gem_name}/archive/v%{mainver}.tar.gz
|
||||
Source1: rubygem-%{gem_name}-%{version}%{?prever}-full.tar.gz
|
||||
Source2: rubygem-%{gem_name}-%{version}%{?prever}-full.tar.gz
|
||||
# Shut down libxml2 version unmatching warning
|
||||
Patch0: %{name}-1.6.6.4-shutdown-libxml2-warning.patch
|
||||
Patch1: CVE-2020-26247-pre.patch
|
||||
Patch2: CVE-2020-26247.patch
|
||||
Patch3: CVE-2021-41098-1.patch
|
||||
Patch4: CVE-2021-41098-2.patch
|
||||
Patch0: %{name}-1.11.0.rc4-shutdown-libxml2-warning.patch
|
||||
BuildRequires: ruby(release) ruby(rubygems) rubygem(minitest) rubygems-devel
|
||||
Obsoletes: ruby-%{gem_name} <= 1.5.2-2
|
||||
BuildRequires: gcc rubygem(pkg-config) libxml2-devel libxslt-devel ruby-devel
|
||||
BuildRequires: gcc libxml2-devel libxslt-devel ruby-devel glibc-all-langpacks rubygem(racc)
|
||||
Requires: rubygem(racc)
|
||||
|
||||
%description
|
||||
Nokogiri parses and searches XML/HTML very quickly, and also has
|
||||
correctly implemented CSS3 selector support as well as XPath support.
|
||||
@ -50,36 +49,35 @@ This package provides non-Gem support for %{gem_name}.
|
||||
%global version %{mainver}%{?prever}
|
||||
|
||||
%prep
|
||||
%setup -q -T -c -a 1
|
||||
TOPDIR=$(pwd)
|
||||
mkdir tmpunpackdir
|
||||
pushd tmpunpackdir
|
||||
gem unpack %{SOURCE0}
|
||||
cd %{gem_name}-%{version}
|
||||
%setup -q -n %{gem_name}-%{version} -a 1
|
||||
mv ../%{gem_name}-%{version}.gemspec .
|
||||
%patch0 -p1
|
||||
%patch1 -p1
|
||||
%patch2 -p1
|
||||
|
||||
#The file exists only in the source code directory,not in the GEM.
|
||||
cd $TOPDIR/%{gem_name}-%{version}
|
||||
%patch3 -p1
|
||||
%patch4 -p1
|
||||
cd -
|
||||
|
||||
gem specification -l --ruby %{SOURCE0} > %{gem_name}.gemspec
|
||||
sed -i \
|
||||
-e 's|, "ports/archives/[^"][^"]*"||g' \
|
||||
-e 's|, "ports/patches/[^"][^"]*"||g' \
|
||||
%{gem_name}.gemspec
|
||||
sed -i -e '\@mini_portile@d' %{gem_name}.gemspec
|
||||
LANG=C.UTF-8 gem build %{gem_name}.gemspec
|
||||
mv %{gem_name}-%{version}.gem $TOPDIR
|
||||
popd
|
||||
rm -rf tmpunpackdir
|
||||
%{gem_name}-%{version}.gemspec
|
||||
sed -i -e '\@mini_portile@d' %{gem_name}-%{version}.gemspec
|
||||
sed -i \
|
||||
ext/nokogiri/extconf.rb \
|
||||
-e "s@^\(def process_recipe.*\)\$@\1 ; return true@" \
|
||||
-e "s@^\(append_cppflags\).*gumbo.*\$@\1(\"-I$(pwd)/gumbo-parser/src\")@" \
|
||||
-e "\@libs.*gumbo@s@File\.join.*@\"$(pwd)/gumbo-parser/src/libgumbo.a\"@" \
|
||||
-e "\@LIBPATH.*gumbo@s|^\(.*\)\$|# \1|" \
|
||||
%{nil}
|
||||
sed -i \
|
||||
gumbo-parser/src/char_ref.c \
|
||||
-e '\@^#line [0-9]@s|^\(.*\)$|// \1|'
|
||||
sed -i \
|
||||
gumbo-parser/src/Makefile \
|
||||
-e 's|^\(CFLAGS.*=.*\)$|\1 -fPIC|'
|
||||
env LANG=C.UTF-8 gem build %{gem_name}-%{version}.gemspec
|
||||
|
||||
%build
|
||||
mkdir -p ./%{gem_dir}
|
||||
export NOKOGIRI_USE_SYSTEM_LIBRARIES=yes
|
||||
%set_build_flags
|
||||
pushd gumbo-parser/src/
|
||||
make libgumbo.a
|
||||
popd
|
||||
%gem_install
|
||||
chmod 0644 .%{gem_dir}/cache/%{gem_name}-%{mainver}%{?prever}.gem
|
||||
rm -f .%{gem_instdir}/lib/*.jar
|
||||
@ -88,6 +86,7 @@ rm -rf .%{gem_instdir}/ext/java
|
||||
%install
|
||||
mkdir -p %{buildroot}%{gem_dir}
|
||||
cp -a ./%{gem_dir}/* %{buildroot}%{gem_dir}
|
||||
cp -a ./gumbo-parser %{buildroot}%{gem_instdir}/
|
||||
find %{buildroot} -name \*.orig_\* | xargs rm -vf
|
||||
mkdir -p %{buildroot}%{gem_extdir_mri}
|
||||
cp -a ./%{gem_extdir_mri}/* %{buildroot}%{gem_extdir_mri}/
|
||||
@ -103,17 +102,24 @@ do
|
||||
chmod 0644 $f
|
||||
done
|
||||
cp -p %{gem_name}-%{version}/[A-Z]* %{buildroot}%{gem_instdir}/
|
||||
rm -rf %{buildroot}%{gem_instdir}/ext/%{gem_name}/
|
||||
rm -rf %{buildroot}%{gem_instdir}/tmp/
|
||||
rm -f %{buildroot}%{gem_instdir}/{.autotest,.require_paths,.gemtest,.travis.yml}
|
||||
rm -f %{buildroot}%{gem_instdir}/appveyor.yml
|
||||
rm -f %{buildroot}%{gem_instdir}/.cross_rubies
|
||||
rm -f %{buildroot}%{gem_instdir}/{build_all,dependencies.yml,test_all}
|
||||
rm -f %{buildroot}%{gem_instdir}/.editorconfig
|
||||
rm -rf %{buildroot}%{gem_instdir}/suppressions/
|
||||
rm -rf %{buildroot}%{gem_instdir}/patches/
|
||||
rm -f %{buildroot}%{gem_instdir}/{Rakefile,Gemfile*}
|
||||
rm -f %{buildroot}%{gem_instdir}/Manifest.txt
|
||||
pushd %{buildroot}%{gem_instdir}
|
||||
rm -rf \
|
||||
Gemfile* \
|
||||
dependencies.yml \
|
||||
ext \
|
||||
*gemspec \
|
||||
patches \
|
||||
ports \
|
||||
%{nil}
|
||||
pushd gumbo-parser
|
||||
rm \
|
||||
Makefile \
|
||||
%{nil}
|
||||
find src -type f | \
|
||||
grep -v README.md | \
|
||||
xargs rm -f
|
||||
popd
|
||||
rm -f %{buildroot}%{gem_cache}
|
||||
|
||||
%check
|
||||
export TZ="Asia/Tokyo"
|
||||
@ -122,8 +128,11 @@ cp -a %{gem_name}-%{version}/test/ ./%{gem_instdir}
|
||||
pushd ./%{gem_instdir}
|
||||
sed -i test/helper.rb \
|
||||
-e '\@require.*simplecov@,\@^end$@d'
|
||||
ruby \
|
||||
-I.:lib:test:ext \
|
||||
sed -i '/require..minitest.reporters./ s/^/#/' test/helper.rb
|
||||
sed -i '/Minitest::Reporters/ s/^/#/' test/helper.rb
|
||||
env \
|
||||
RUBYLIB=".:lib:test:ext" \
|
||||
ruby \
|
||||
-e \
|
||||
"require 'test/helper' ; Dir.glob('test/**/test_*.rb'){|f| require f}" || \
|
||||
exit 1
|
||||
@ -135,29 +144,28 @@ done
|
||||
popd
|
||||
|
||||
%files
|
||||
%defattr(-,root, root,-)
|
||||
%{_bindir}/%{gem_name}
|
||||
%{gem_extdir_mri}/
|
||||
%dir %{gem_instdir}/
|
||||
%doc %{gem_instdir}/[A-Z]*
|
||||
%{gem_instdir}/bin/
|
||||
%{gem_instdir}/lib/
|
||||
%exclude %{gem_dir}/cache/%{gem_name}-%{mainver}%{?prever}.gem
|
||||
%{gem_dir}/specifications/%{gem_name}-%{mainver}%{?prever}.gemspec
|
||||
%if 0
|
||||
|
||||
%files jruby
|
||||
%defattr(-,root,root,-)
|
||||
%{gem_instdir}/ext/java/
|
||||
%endif
|
||||
%dir %{gem_instdir}/gumbo-parser
|
||||
%dir %{gem_instdir}/gumbo-parser/src
|
||||
%doc %{gem_instdir}/gumbo-parser/[A-Z]*
|
||||
%doc %{gem_instdir}/gumbo-parser/src/README.md
|
||||
|
||||
%{gem_dir}/specifications/%{gem_name}-%{mainver}%{?prever}.gemspec
|
||||
|
||||
%files doc
|
||||
%defattr(-,root,root,-)
|
||||
%exclude %{gem_instdir}/tasks/
|
||||
%exclude %{gem_instdir}/test/
|
||||
%{gem_dir}/doc/%{gem_name}-%{mainver}%{?prever}/
|
||||
|
||||
%changelog
|
||||
* Tue Mar 29 2022 liyanan <liyanan32@huawei.com> - 1.13.1-1
|
||||
- update to 1.13.1
|
||||
|
||||
* Tue Oct 12 2021 yaoxin <yaoxin30@huawei.com> - 1.10.5-3
|
||||
- fix CVE-2021-41098
|
||||
|
||||
|
||||
BIN
v1.10.5.tar.gz
BIN
v1.10.5.tar.gz
Binary file not shown.
Loading…
x
Reference in New Issue
Block a user