nokogiri 1.11.6 → 1.12.1

data/ext/nokogiri/xml_schema.c

@@ -274,6 +274,8 @@ noko_init_xml_schema()
 {
   cNokogiriXmlSchema = rb_define_class_under(mNokogiriXml, "Schema", rb_cObject);
 
+  rb_undef_alloc_func(cNokogiriXmlSchema);
+
   rb_define_singleton_method(cNokogiriXmlSchema, "read_memory", read_memory, -1);
   rb_define_singleton_method(cNokogiriXmlSchema, "from_document", from_document, -1);
 

data/ext/nokogiri/xml_xpath_context.c

@@ -154,20 +154,20 @@ Nokogiri_marshal_xpath_funcall_and_return_values(xmlXPathParserContextPtr ctx, i
     do {
       obj = valuePop(ctx);
       switch (obj->type) {
-      case XPATH_STRING:
-        argv[i] = NOKOGIRI_STR_NEW2(obj->stringval);
-        break;
-      case XPATH_BOOLEAN:
-        argv[i] = obj->boolval == 1 ? Qtrue : Qfalse;
-        break;
-      case XPATH_NUMBER:
-        argv[i] = rb_float_new(obj->floatval);
-        break;
-      case XPATH_NODESET:
-        argv[i] = noko_xml_node_set_wrap(obj->nodesetval, doc);
-        break;
-      default:
-        argv[i] = NOKOGIRI_STR_NEW2(xmlXPathCastToString(obj));
+        case XPATH_STRING:
+          argv[i] = NOKOGIRI_STR_NEW2(obj->stringval);
+          break;
+        case XPATH_BOOLEAN:
+          argv[i] = obj->boolval == 1 ? Qtrue : Qfalse;
+          break;
+        case XPATH_NUMBER:
+          argv[i] = rb_float_new(obj->floatval);
+          break;
+        case XPATH_NODESET:
+          argv[i] = noko_xml_node_set_wrap(obj->nodesetval, doc);
+          break;
+        default:
+          argv[i] = NOKOGIRI_STR_NEW2(xmlXPathCastToString(obj));
       }
       xmlXPathFreeNodeSetList(obj);
     } while (i-- > 0);
@@ -181,43 +181,43 @@ Nokogiri_marshal_xpath_funcall_and_return_values(xmlXPathParserContextPtr ctx, i
   free(argv);
 
   switch (TYPE(result)) {
-  case T_FLOAT:
-  case T_BIGNUM:
-  case T_FIXNUM:
-    xmlXPathReturnNumber(ctx, NUM2DBL(result));
-    break;
-  case T_STRING:
-    xmlXPathReturnString(
-      ctx,
-      xmlCharStrdup(StringValueCStr(result))
-    );
-    break;
-  case T_TRUE:
-    xmlXPathReturnTrue(ctx);
-    break;
-  case T_FALSE:
-    xmlXPathReturnFalse(ctx);
-    break;
-  case T_NIL:
-    break;
-  case T_ARRAY: {
-    VALUE args[2];
-    args[0] = doc;
-    args[1] = result;
-    node_set = rb_class_new_instance(2, args, cNokogiriXmlNodeSet);
-    Data_Get_Struct(node_set, xmlNodeSet, xml_node_set);
-    xmlXPathReturnNodeSet(ctx, xmlXPathNodeSetMerge(NULL, xml_node_set));
-  }
-  break;
-  case T_DATA:
-    if (rb_obj_is_kind_of(result, cNokogiriXmlNodeSet)) {
-      Data_Get_Struct(result, xmlNodeSet, xml_node_set);
-      /* Copy the node set, otherwise it will get GC'd. */
-      xmlXPathReturnNodeSet(ctx, xmlXPathNodeSetMerge(NULL, xml_node_set));
+    case T_FLOAT:
+    case T_BIGNUM:
+    case T_FIXNUM:
+      xmlXPathReturnNumber(ctx, NUM2DBL(result));
+      break;
+    case T_STRING:
+      xmlXPathReturnString(
+        ctx,
+        xmlCharStrdup(StringValueCStr(result))
+      );
+      break;
+    case T_TRUE:
+      xmlXPathReturnTrue(ctx);
+      break;
+    case T_FALSE:
+      xmlXPathReturnFalse(ctx);
       break;
+    case T_NIL:
+      break;
+    case T_ARRAY: {
+      VALUE args[2];
+      args[0] = doc;
+      args[1] = result;
+      node_set = rb_class_new_instance(2, args, cNokogiriXmlNodeSet);
+      Data_Get_Struct(node_set, xmlNodeSet, xml_node_set);
+      xmlXPathReturnNodeSet(ctx, xmlXPathNodeSetMerge(NULL, xml_node_set));
     }
-  default:
-    rb_raise(rb_eRuntimeError, "Invalid return type");
+    break;
+    case T_DATA:
+      if (rb_obj_is_kind_of(result, cNokogiriXmlNodeSet)) {
+        Data_Get_Struct(result, xmlNodeSet, xml_node_set);
+        /* Copy the node set, otherwise it will get GC'd. */
+        xmlXPathReturnNodeSet(ctx, xmlXPathNodeSetMerge(NULL, xml_node_set));
+        break;
+      }
+    default:
+      rb_raise(rb_eRuntimeError, "Invalid return type");
   }
 }
 
@@ -314,22 +314,22 @@ evaluate(int argc, VALUE *argv, VALUE self)
   assert(DOC_RUBY_OBJECT_TEST(ctx->doc));
 
   switch (xpath->type) {
-  case XPATH_STRING:
-    thing = NOKOGIRI_STR_NEW2(xpath->stringval);
-    xmlFree(xpath->stringval);
-    break;
-  case XPATH_NODESET:
-    thing = noko_xml_node_set_wrap(xpath->nodesetval,
-                                   DOC_RUBY_OBJECT(ctx->doc));
-    break;
-  case XPATH_NUMBER:
-    thing = rb_float_new(xpath->floatval);
-    break;
-  case XPATH_BOOLEAN:
-    thing = xpath->boolval == 1 ? Qtrue : Qfalse;
-    break;
-  default:
-    thing = noko_xml_node_set_wrap(NULL, DOC_RUBY_OBJECT(ctx->doc));
+    case XPATH_STRING:
+      thing = NOKOGIRI_STR_NEW2(xpath->stringval);
+      xmlFree(xpath->stringval);
+      break;
+    case XPATH_NODESET:
+      thing = noko_xml_node_set_wrap(xpath->nodesetval,
+                                     DOC_RUBY_OBJECT(ctx->doc));
+      break;
+    case XPATH_NUMBER:
+      thing = rb_float_new(xpath->floatval);
+      break;
+    case XPATH_BOOLEAN:
+      thing = xpath->boolval == 1 ? Qtrue : Qfalse;
+      break;
+    default:
+      thing = noko_xml_node_set_wrap(NULL, DOC_RUBY_OBJECT(ctx->doc));
   }
 
   xmlXPathFreeNodeSetList(xpath);
@@ -373,6 +373,8 @@ noko_init_xml_xpath_context(void)
    */
   cNokogiriXmlXpathContext = rb_define_class_under(mNokogiriXml, "XPathContext", rb_cObject);
 
+  rb_undef_alloc_func(cNokogiriXmlXpathContext);
+
   rb_define_singleton_method(cNokogiriXmlXpathContext, "new", new, 1);
 
   rb_define_method(cNokogiriXmlXpathContext, "evaluate", evaluate, -1);

data/ext/nokogiri/xslt_stylesheet.c

@@ -64,7 +64,6 @@ parse_stylesheet_doc(VALUE klass, VALUE xmldocobj)
   VALUE errstr, exception;
   xsltStylesheetPtr ss ;
   Data_Get_Struct(xmldocobj, xmlDoc, xml);
-  exsltRegisterAll();
 
   errstr = rb_str_new(0, 0);
   xsltSetGenericErrorFunc((void *)errstr, xslt_generic_error_handler);
@@ -257,6 +256,8 @@ noko_init_xslt_stylesheet()
 
   cNokogiriXsltStylesheet = rb_define_class_under(mNokogiriXslt, "Stylesheet", rb_cObject);
 
+  rb_undef_alloc_func(cNokogiriXsltStylesheet);
+
   rb_define_singleton_method(cNokogiriXsltStylesheet, "parse_stylesheet_doc", parse_stylesheet_doc, 1);
   rb_define_method(cNokogiriXsltStylesheet, "serialize", serialize, 1);
   rb_define_method(cNokogiriXsltStylesheet, "transform", transform, -1);

data/gumbo-parser/CHANGES.md

@@ -0,0 +1,63 @@
+## Gumbo 0.10.1 (2015-04-30)
+
+Same as 0.10.0, but with the version number bumped because the last version-number commit to v0.9.4 makes GitHub think that v0.9.4 is the latest version and so it's not highlighted on the webpage.
+
+## Gumbo 0.10.0 (2015-04-30)
+
+* Full support for `<template>` tag (kevinhendricks, nostrademons).
+* Some fixes for `<rtc>`/`<rt>` handling (kevinhendricks, vmg).
+* All html5lib-trunk tests pass now! (kevinhendricks, vmg, nostrademons)
+* Support for fragment parsing (vmg)
+* A couple additional example programs (kevinhendricks)
+* Performance improvements totaling an estimated 30-40% total improvement (vmg, nostrademons).
+
+## Gumbo 0.9.4 (2015-04-30)
+
+* Additional Visual Studio fixes (lowjoel, nostrademons)
+* Fixed some unused variable warnings.
+* Fix for glibtoolize vs. libtoolize build errors on Mac.
+* Fixed `CDATA` end tag handling.
+
+## Gumbo 0.9.3 (2015-02-17)
+
+* Bugfix for `&AElig;` entities (rgrove)
+* Fix `CDATA` handling; `CDATA` sections now generate a `GUMBO_NODE_CDATA` node rather
+than plain text.
+* Fix `get_title example` to handle whitespace nodes (gsnedders)
+* Visual Studio compilation fixes (fishioon)
+* Take the namespace into account when determining whether a node matches a
+certain tag (aroben)
+* Replace the varargs tag functions with a tagset bytevector, for a 20-30%
+speedup in overall parse time (kevinhendricks, vmg)
+* Add MacOS X support to Travis CI, and fix the deployment/DLL issues this
+uncovered (nostrademons, kevinhendricks, vmg)
+
+## Gumbo 0.9.2 (2014-09-21)
+
+* Performance improvements: Ragel-based char ref decoder and DFA-based UTF8
+decoder, totaling speedups of up to 300%.
+* Added benchmarking program and some sample data.
+* Fixed a compiler error under Visual Studio.
+* Fix an error in the ctypes bindings that could lead to memory corruption in
+the Python bindings.
+* Fix duplicate attributes when parsing `<isindex>` tags.
+* Don't leave semicolons behind when consuming entity references (rgrove)
+* Internally rename some functions in preparation for an amalgamation file
+(jdeng)
+* Add proper cflags for gyp builds (skabbes)
+
+## Gumbo 0.9.1 (2014-08-07)
+
+* First version listed on PyPi.
+* Autotools files excluded from GitHub and generated via autogen.sh. (endgame)
+* Numerous compiler warnings fixed. (bnoordhuis, craigbarnes)
+* Google security audit passed.
+* Gyp support (tfarina)
+* Naming convention for structs changed to avoid C reserved words.
+* Fix several integer and buffer overflows (Maxime2)
+* Some Visual Studio compiler support (bugparty)
+* Python3 compatibility for the ctypes bindings.
+
+## Gumbo 0.9.0 (2013-08-13)
+
+* Initial release open-sourced by Google.

data/gumbo-parser/Makefile

@@ -0,0 +1,101 @@
+.PHONY: all clean check coverage
+
+gumbo_objs := $(patsubst %.c,build/%.o,$(wildcard src/*.c))
+test_objs := $(patsubst %.cc,build/%.o,$(wildcard test/*.cc))
+gtest_lib := googletest/make/gtest_main.a
+
+# make SANITIZEFLAGS='-fsanitize=undefined -fsanitize=address'
+SANITIZEFLAGS :=
+CPPFLAGS := -Isrc
+CFLAGS := -std=c99 -Os -Wall
+CXXFLAGS := -isystem googletest/include -std=c++11 -Os -Wall
+LDFLAGS := -pthread
+
+all: check
+
+src/%.c: src/%.rl
+	ragel -F1 -o $@ $<
+
+build/src:
+	mkdir -p $@
+
+build/test:
+	mkdir -p $@
+
+build/src/%.o: src/%.c build/src/flags | build/src
+	$(CC) -MMD $(CPPFLAGS) $(CFLAGS) $(SANITIZEFLAGS) -c -o $@ $<
+
+build/test/%.o: test/%.cc build/test/flags | build/test
+	$(CXX) -MMD $(CPPFLAGS) $(CXXFLAGS) $(SANITIZEFLAGS) -c -o $@ $<
+
+build/run_tests: $(gumbo_objs) $(test_objs) $(gtest_lib)
+	$(CXX) -o $@ $+ $(LDFLAGS) $(SANITIZEFLAGS)
+
+check: build/run_tests
+	./build/run_tests
+
+coverage:
+	$(RM) build/{src,test}/*.gcda
+	$(RM) build/*.info
+	$(MAKE) CPPFLAGS='-Isrc -DNDEBUG=1' \
+		CFLAGS='-std=c99 --coverage -g -O0' \
+		CXXFLAGS='-isystem googletest/include -std=c++11 --coverage -g -O0' \
+		LDFLAGS='--coverage' \
+		build/run_tests
+	lcov	--no-external \
+		--initial \
+		--capture \
+		--base-directory . \
+		--directory build \
+		--output-file build/coverage-pre.info
+	awk	-F '[:,]' \
+		'/^SF:/ { delete defs } /^FN:/ { defs[$$2]=1 } /^DA:/ { if ($$3 == 0 && $$2 in defs) next } { print }' \
+		build/coverage-pre.info > build/coverage-initial.info
+	./build/run_tests
+	lcov	--no-external \
+		--capture \
+		--base-directory . \
+		--directory build \
+		--rc lcov_branch_coverage=1 \
+		--output-file build/coverage-test.info
+	lcov	--add-tracefile build/coverage-initial.info \
+		--add-tracefile build/coverage-test.info \
+		--rc lcov_branch_coverage=1 \
+		--output-file build/coverage.info
+	lcov	--remove build/coverage.info '$(CURDIR)/googletest/*' \
+		--rc lcov_branch_coverage=1 \
+		--output-file build/coverage.info
+	genhtml --branch-coverage \
+		--output-directory build/coverage \
+		build/coverage.info
+
+clean:
+	$(RM) -r build
+
+build/src/flags: | build/src
+	@echo 'old_CC := $(CC)' > $@
+	@echo 'old_CPPFLAGS := $(CPPFLAGS)' >> $@
+	@echo 'old_CFLAGS := $(CFLAGS)' >>$@
+	@echo 'old_SANITIZEFLAGS := $(SANITIZEFLAGS)' >> $@
+	@echo 'old_LDFLAGS := $(LDFLAGS)' >> $@
+
+build/test/flags: | build/test
+	@echo 'old_CXX := $(CXX)' > $@
+	@echo 'old_CPPFLAGS := $(CPPFLAGS)' >> $@
+	@echo 'old_CXXFLAGS := $(CXXFLAGS)' >> $@
+	@echo 'old_SANITIZEFLAGS := $(SANITIZEFLAGS)' >> $@
+	@echo 'old_LDFLAGS := $(LDFLAGS)' >> $@
+
+ifeq (,$(filter clean coverage,$(MAKECMDGOALS)))
+# Ensure that the flags are up to date.
+-include build/src/flags build/test/flags
+ifneq ($(old_CC) | $(old_CPPFLAGS) | $(old_CFLAGS) | $(old_SANITIZEFLAGS) | $(old_LDFLAGS),$(CC) | $(CPPFLAGS) | $(CFLAGS) | $(SANITIZEFLAGS) | $(LDFLAGS))
+.PHONY: build/src/flags
+endif
+ifneq ($(old_CXX) | $(old_CPPFLAGS) | $(old_CXXFLAGS) | $(old_SANITIZEFLAGS) | $(old_LDFLAGS),$(CXX) | $(CPPFLAGS) | $(CXXFLAGS) | $(SANITIZEFLAGS) | $(LDFLAGS))
+.PHONY: build/test/flags
+endif
+
+# Include dependencies.
+-include $(test_objs:.o=.d) $(gumbo_objs:.o=.d)
+endif

data/gumbo-parser/THANKS

@@ -0,0 +1,27 @@
+Gumbo HTML parser THANKS file
+
+Gumbo was originally written by Jonathan Tang, but many people helped out through suggestions, question-answering, code reviews, bugfixes, and organizational support.  Here is a list of these people.  Help me keep it complete and exempt of errors.
+
+Adam Barth
+Adam Roben
+Ben Noordhuis
+Bowen Han
+Constantinos Michael
+Craig Barnes
+Geoffrey Sneddon
+Ian Hickson
+Jack Deng
+Joel Low
+Jonathan Shneier
+Kevin Hendricks
+Mason Tang
+Maxim Zakharov
+Michal Zalewski
+Neal Norwitz
+Othar Hansson
+Ryan Grove
+Stefan Haustein
+Steffen Meschkat
+Steven Kabbes
+Thiago Farina
+Vicent Marti

data/gumbo-parser/src/Makefile

@@ -0,0 +1,34 @@
+# this Makefile is used by ext/nokogiri/extconf.rb
+# to enable a mini_portile2 recipe to build the gumbo parser
+.PHONY: clean
+
+CFLAGS += -std=c99 -Wall
+
+# allow the ENV var to override this
+RANLIB ?= ranlib
+
+gumbo_objs := \
+	ascii.o \
+	attribute.o \
+	char_ref.o \
+	error.o \
+	foreign_attrs.o \
+	parser.o \
+	string_buffer.o \
+	string_piece.o \
+	svg_attrs.o \
+	svg_tags.o \
+	tag.o \
+	tag_lookup.o \
+	token_buffer.o \
+	tokenizer.o \
+	utf8.o \
+	util.o \
+	vector.o
+
+libgumbo.a: $(gumbo_objs)
+	$(AR) $(ARFLAGS) $@ $(gumbo_objs)
+	- ($(RANLIB) $@ || true) >/dev/null 2>&1
+
+clean:
+	rm -f $(gumbo_objs) libgumbo.a

data/gumbo-parser/src/README.md

@@ -0,0 +1,41 @@
+libgumbo
+========
+
+This is an internal fork of the [libgumbo] library, which was copied and
+later modified under the terms of the Apache 2.0 [license]. See `lua-gumbo`
+commit [`0a04728`] for details of the original import.
+
+Since importing the code, the following notable fixes and improvements
+have been made:
+
+* `91cef89`: Re-implement `adjust_foreign_attributes()` with a gperf hash
+* `b11abe7`: Pass `TagSet` arrays into functions by reference instead of value
+* `b73dc03`: Simplify `maybe_replace_codepoint()` function
+* `d5d0bb3`: Remove special handling of `<menuitem>` tag
+* `7bd5162`: Remove special handling of `<isindex>` tag
+* `a5c1b0e`: Use `realloc(3)` instead of `malloc(3)` in `enlarge_vector_if_full()`
+* `dcbebd7`: Use `realloc(3)` instead of `malloc(3)` in `maybe_resize_string_buffer()`
+* `df15262`: Make `destroy_node()` function non-recursive
+* `2df37f5`: Fix signedness of some format specifiers
+* `176553e`: Add maximum element nesting limit
+* `bed0f4a`: Annotate `gumbo_debug()` with `PRINTF` macro and fix warnings
+* `7ffc218`: Annotate `print_message()` with `PRINTF` macro and fix warnings
+* `1bd8ab5`, `9136507`, `53a1f9a`: Deduplicate some identical `TagSet` arrays
+* `a7a9065`: Add some GCC/Clang function attributes
+* `8d3d4e4`: Remove custom allocator support
+* `8d3b006`: Fix recording of source positions for `</form>` end tags
+* `1a8d763`: Replace linear search in `maybe_replace_codepoint()` with a lookup table
+* `6dca79e`: Replace `strcasecmp()` and `strncasecmp()` with ascii-only equivalents
+* `17ab1d2`: Fix `TAGSET_INCLUDES` macro to work properly with multiple bit flags
+* `7e56d45`: Re-implement `gumbo_normalize_svg_tagname()` with a gperf hash
+* `a518d35`: Replace linear array search in `adjust_svg_attributes()` with a gperf hash
+* `a4a7433`: Fix duplicate `TagSet` initializer being ignored in `is_special_node()`
+* `8137fcd`: Add support for `<dialog>` tag
+* `4b35471`: Add missing `static` qualifiers to hide symbols that shouldn't be extern
+* `df57c59`, `03101f3`, `ea62330`: Replace use of locale-dependant `ctype.h` functions
+  with custom, ASCII-only equivalents
+
+
+[libgumbo]: https://github.com/google/gumbo-parser/tree/aa91b27b02c0c80c482e24348a457ed7c3c088e0/src
+[license]: https://github.com/google/gumbo-parser/blob/aa91b27b02c0c80c482e24348a457ed7c3c088e0/COPYING
+[`0a04728`]: https://gitlab.com/craigbarnes/lua-gumbo/commit/0a047282815af86f3367a7d95fefcfe5723ece48