Fix crash when libxml set error in @autoreleasepool

- libxml will return first parsing error instead of last one
- option to replace lower ascii chars with whitespace

RSXML/RSSAXParser.h

@@ -61,6 +61,7 @@
 
 
 @interface RSSAXParser : NSObject
+@property (nonatomic, strong, readonly) NSError *parsingError;
 @property (nonatomic, strong, readonly) NSData *currentCharacters;
 @property (nonatomic, strong, readonly) NSString *currentString;
 @property (nonatomic, strong, readonly) NSString *currentStringWithTrimmedWhitespace;

RSXML/RSSAXParser.m

@@ -27,6 +27,8 @@
 #import <libxml/parser.h>
 #import "RSSAXParser.h"
 
+const NSErrorDomain kLIBXMLParserErrorDomain = @"LIBXMLParserErrorDomain";
+
 
 @interface RSSAXParser ()
 @property (nonatomic, weak) id<RSSAXParserDelegate> delegate;
@@ -97,6 +99,8 @@ static xmlSAXHandler saxHandlerStruct;
  */
 - (void)parseBytes:(const void *)bytes numberOfBytes:(NSUInteger)numberOfBytes {
 
+	_parsingError = nil;
+
 	if (self.context == nil) {
 		if (self.isHTMLParser) {
 			xmlCharEncoding characterEncoding = xmlDetectCharEncoding(bytes, (int)numberOfBytes);
@@ -342,6 +346,11 @@ static xmlSAXHandler saxHandlerStruct;
 	}
 }
 
+- (void)xmlParsingErrorOccured:(NSError*)error {
+	if (!self.parsingError) // grep first encountered error
+		_parsingError = error;
+}
+
 @end
 
 
@@ -369,6 +378,20 @@ static void	endElementSAX_HTML(void *context, const xmlChar *localname) {
 	[(__bridge RSSAXParser *)context xmlEndHTMLElement:localname];
 }
 
+static void errorOccuredSAX(void *context, const char *format, ...) {
+	xmlErrorPtr err = xmlGetLastError();
+	if (err && err->level == XML_ERR_FATAL) {
+		int errCode = err->code;
+		char * msg = err->message;
+		NSString *errMsg = [[NSString stringWithFormat:@"%s", msg] stringByTrimmingCharactersInSet:
+							[NSCharacterSet whitespaceAndNewlineCharacterSet]];
+		NSError *error = [NSError errorWithDomain:kLIBXMLParserErrorDomain code:errCode
+										 userInfo:@{ NSLocalizedDescriptionKey: errMsg }];
+		[(__bridge RSSAXParser *)context xmlParsingErrorOccured:error];
+	}
+	xmlResetLastError();
+}
+
 
 static xmlSAXHandler saxHandlerStruct = {
 	nil,					/* internalSubset */
@@ -393,7 +416,7 @@ static xmlSAXHandler saxHandlerStruct = {
 	nil,					/* processingInstruction */
 	nil,					/* comment */
 	nil,					/* warning */
-	nil,					/* error */
+	errorOccuredSAX,		/* error */
 	nil,					/* fatalError //: unused error() get all the errors */
 	nil,					/* getParameterEntity */
 	nil,					/* cdataBlock */

RSXML/RSXMLError.m

@@ -23,7 +23,6 @@
 
 #import "RSXMLError.h"
 
-const NSErrorDomain kLIBXMLParserErrorDomain = @"LIBXMLParserErrorDomain";
 const NSErrorDomain kRSXMLParserErrorDomain = @"RSXMLParserErrorDomain";
 
 const char * parserDescriptionForError(RSXMLError code);

RSXML/RSXMLParser.h

@@ -58,6 +58,7 @@
 
 @interface RSXMLParser<__covariant T> : NSObject <RSXMLParserDelegate, RSSAXParserDelegate>
 @property (nonatomic, readonly, nonnull, copy) NSString *documentURI;
+@property (nonatomic, assign) BOOL dontStopOnLowerAsciiBytes;
 
 + (instancetype)parserWithXMLData:(RSXMLData * _Nonnull)xmlData;
 

RSXML/RSXMLParser.m

@@ -21,8 +21,6 @@
 //  OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 //  SOFTWARE.
 
-#import <libxml/xmlerror.h>
-
 #import "RSXMLParser.h"
 #import "RSXMLData.h"
 #import "RSXMLError.h"
@@ -71,6 +69,22 @@
 	return self;
 }
 
+/**
+ XML allows only specific lower ascii characters (<0x20), namely 0x9, 0xA, and 0xD.
+ See: https://www.w3.org/TR/xml/#charsets
+ */
+- (void)replaceLowerAsciiBytesWithSpace {
+	[_xmlData enumerateByteRangesUsingBlock:^(const void * bytes, NSRange byteRange, BOOL * stop) {
+		NSUInteger max = byteRange.location + byteRange.length;
+		for (NSUInteger i = byteRange.location; i < max; i++) {
+			unsigned char c = ((unsigned char*)bytes)[i];
+			if (c < 0x20 && c != 0x9 && c != 0xA && c != 0xD) {
+				((unsigned char*)bytes)[i] = ' '; // replace lower ascii with blank
+			}
+		}
+	}];
+}
+
 /**
  Parse the XML data on whatever thread this method is called.
  
@@ -82,24 +96,16 @@
 		if (error) *error = _xmlInputError;
 		return nil;
 	}
-	
+	if (_dontStopOnLowerAsciiBytes) {
+		[self replaceLowerAsciiBytesWithSpace];
+	}
 	if ([self respondsToSelector:@selector(xmlParserWillStartParsing)] && ![self xmlParserWillStartParsing])
 		return nil;
 
 	@autoreleasepool {
-		xmlResetLastError();
 		[_parser parseBytes:_xmlData.bytes numberOfBytes:_xmlData.length];
-		if (error) {
-			xmlErrorPtr err = xmlGetLastError();
-			if (err && err->level == XML_ERR_FATAL) {
-				int errCode = err->code;
-				char * msg = err->message;
-				NSString *errMsg = [[NSString stringWithFormat:@"%s", msg] stringByTrimmingCharactersInSet:[NSCharacterSet whitespaceAndNewlineCharacterSet]];
-				*error = [NSError errorWithDomain:kLIBXMLParserErrorDomain code:errCode userInfo:@{NSLocalizedDescriptionKey: errMsg}];
-			}
-			xmlResetLastError();
-		}
 	}
+	if (error) *error = _parser.parsingError;
 	return [self xmlParserWillReturnDocument];
 }
 

RSXMLTests/RSXMLTests.m

@@ -265,6 +265,28 @@
 #pragma clang diagnostic pop
 }
 
+- (void)testLowerAsciiCharacters {
+	NSError *error = nil;
+	RSXMLData *xmlData = [self xmlFile:@"lower-ascii" extension:@"rss"];
+	RSXMLParser *parser = [xmlData getParser];
+	RSParsedFeed *parsedFeed = [parser parseSync:&error];
+	XCTAssertNotNil(error);
+	XCTAssertEqual(parsedFeed.articles.count, 2);
+	parser.dontStopOnLowerAsciiBytes = YES;
+	parsedFeed = [parser parseSync:&error];
+	XCTAssertNil(error);
+	XCTAssertEqual(parsedFeed.articles.count, 5);
+}
+
+- (void)testBrokenXML {
+	NSError *error = nil;
+	RSXMLData *xmlData = [self xmlFile:@"broken" extension:@"rss"];
+	[[xmlData getParser] parseSync:&error];
+	XCTAssertNotNil(error);
+	XCTAssertEqual(error.code, 76);
+	XCTAssertEqualObjects(error.localizedDescription, @"Opening and ending tag mismatch: channel line 0 and rss");
+}
+
 - (void)testDownloadedFeeds {
 	NSError *error = nil;
 	int i = 0;

RSXMLTests/Resources/broken.rss

@@ -0,0 +1,26 @@
+<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"
+	xmlns:content="http://purl.org/rss/1.0/modules/content/"
+	xmlns:wfw="http://wellformedweb.org/CommentAPI/"
+	xmlns:dc="http://purl.org/dc/elements/1.1/"
+	xmlns:atom="http://www.w3.org/2005/Atom"
+	xmlns:sy="http://purl.org/rss/1.0/modules/syndication/"
+	xmlns:slash="http://purl.org/rss/1.0/modules/slash/"
+	>
+
+<channel>
+	<title>Manton Reece</title>
+	<atom:link href="http://www.manton.org/feed" rel="self" type="application/rss+xml" />
+	<link>http://www.manton.org</link>
+	<description></description>
+	<lastBuildDate>Fri, 25 Sep 2015 14:26:40 +0000</lastBuildDate>
+	<language>en-US</language>
+	<sy:updatePeriod>hourly</sy:updatePeriod>
+	<sy:updateFrequency>1</sy:updateFrequency>
+	<generator>http://wordpress.org/?v=4.2.5</generator>
+	<item>
+		<title></title>
+		<link>http://www.manton.org/2015/09/3071.html</link>
+		<comments>http://www.manton.org/2015/09/3071.html#comments</comments>
+		<pubDate>Fri,</pubDate>
+	</item>
+</rss>

RSXMLTests/Resources/lower-ascii.rss

@@ -0,0 +1,30 @@
+<?xml version="1.0" encoding="UTF-8"?><rss version="2.0">
+<channel>
+	<title>Feed Title</title>
+<item>
+		<title>1</title>
+		<link>http://someurl.com/1/</link>
+		<description><![CDATA[Description of first]]></description>
+</item>
+<item>
+		<title>2</title>
+		<link>http://someurl.com/2/</link>
+		<description><![CDATA[Description with  NULL values]]></description>
+</item>
+<item>
+		<title>3</title>
+		<link>http://someurl.com/3/</link>
+		<description><![CDATA[Description of third]]></description>
+</item>
+<item>
+		<title>4</title>
+		<link>http://someurl.com/4/</link>
+		<description><![CDATA[Description of fourth]]></description>
+</item>
+<item>
+		<title>5</title>
+		<link>http://someurl.com/5/</link>
+		<description><![CDATA[Description of fifth]]></description>
+</item>
+	</channel>
+</rss>