1 files changed, 81 insertions, 125 deletions

diff --git a/core/io/xml_parser.cpp b/core/io/xml_parser.cpp
index 53e7da91a7..1574634aad 100644
--- a/core/io/xml_parser.cpp
+++ b/core/io/xml_parser.cpp
@@ -5,8 +5,8 @@
 /*                           GODOT ENGINE                                */
 /*                      https://godotengine.org                          */
 /*************************************************************************/
-/* Copyright (c) 2007-2020 Juan Linietsky, Ariel Manzur.                 */
-/* Copyright (c) 2014-2020 Godot Engine contributors (cf. AUTHORS.md).   */
+/* Copyright (c) 2007-2021 Juan Linietsky, Ariel Manzur.                 */
+/* Copyright (c) 2014-2021 Godot Engine contributors (cf. AUTHORS.md).   */
 /*                                                                       */
 /* Permission is hereby granted, free of charge, to any person obtaining */
 /* a copy of this software and associated documentation files (the       */
@@ -30,66 +30,12 @@
 
 #include "xml_parser.h"
 
-#include "core/print_string.h"
+#include "core/string/print_string.h"
 
 //#define DEBUG_XML
 
 VARIANT_ENUM_CAST(XMLParser::NodeType);
 
-static bool _equalsn(const CharType *str1, const CharType *str2, int len) {
-	int i;
-	for (i = 0; i < len && str1[i] && str2[i]; ++i)
-		if (str1[i] != str2[i])
-			return false;
-
-	// if one (or both) of the strings was smaller then they
-	// are only equal if they have the same length
-	return (i == len) || (str1[i] == 0 && str2[i] == 0);
-}
-
-String XMLParser::_replace_special_characters(const String &origstr) {
-
-	int pos = origstr.find("&");
-	int oldPos = 0;
-
-	if (pos == -1)
-		return origstr;
-
-	String newstr;
-
-	while (pos != -1 && pos < origstr.length() - 2) {
-		// check if it is one of the special characters
-
-		int specialChar = -1;
-		for (int i = 0; i < (int)special_characters.size(); ++i) {
-			const CharType *p = &origstr[pos] + 1;
-
-			if (_equalsn(&special_characters[i][1], p, special_characters[i].length() - 1)) {
-				specialChar = i;
-				break;
-			}
-		}
-
-		if (specialChar != -1) {
-			newstr += (origstr.substr(oldPos, pos - oldPos));
-			newstr += (special_characters[specialChar][0]);
-			pos += special_characters[specialChar].length();
-		} else {
-			newstr += (origstr.substr(oldPos, pos - oldPos + 1));
-			pos += 1;
-		}
-
-		// find next &
-		oldPos = pos;
-		pos = origstr.find("&", pos);
-	}
-
-	if (oldPos < origstr.length() - 1)
-		newstr += (origstr.substr(oldPos, origstr.length() - oldPos));
-
-	return newstr;
-}
-
 static inline bool _is_white_space(char c) {
 	return (c == ' ' || c == '\t' || c == '\n' || c == '\r');
 }
@@ -100,17 +46,20 @@ bool XMLParser::_set_text(char *start, char *end) {
 	// only white space, so that this text won't be reported
 	if (end - start < 3) {
 		char *p = start;
-		for (; p != end; ++p)
-			if (!_is_white_space(*p))
+		for (; p != end; ++p) {
+			if (!_is_white_space(*p)) {
 				break;
+			}
+		}
 
-		if (p == end)
+		if (p == end) {
 			return false;
+		}
 	}
 
 	// set current text to the parsed text, and replace xml special characters
 	String s = String::utf8(start, (int)(end - start));
-	node_name = _replace_special_characters(s);
+	node_name = s.xml_unescape();
 
 	// current XML node type is text
 	node_type = NODE_TEXT;
@@ -126,8 +75,9 @@ void XMLParser::_parse_closing_xml_element() {
 	++P;
 	const char *pBeginClose = P;
 
-	while (*P != '>')
+	while (*P != '>') {
 		++P;
+	}
 
 	node_name = String::utf8(pBeginClose, (int)(P - pBeginClose));
 #ifdef DEBUG_XML
@@ -141,16 +91,17 @@ void XMLParser::_ignore_definition() {
 
 	char *F = P;
 	// move until end marked with '>' reached
-	while (*P != '>')
+	while (*P != '>') {
 		++P;
+	}
 	node_name.parse_utf8(F, P - F);
 	++P;
 }
 
 bool XMLParser::_parse_cdata() {
-
-	if (*(P + 1) != '[')
+	if (*(P + 1) != '[') {
 		return false;
+	}
 
 	node_type = NODE_CDATA;
 
@@ -161,11 +112,12 @@ bool XMLParser::_parse_cdata() {
 		++count;
 	}
 
-	if (!*P)
+	if (!*P) {
 		return true;
+	}
 
 	char *cDataBegin = P;
-	char *cDataEnd = 0;
+	char *cDataEnd = nullptr;
 
 	// find end of CDATA
 	while (*P && !cDataEnd) {
@@ -178,10 +130,11 @@ bool XMLParser::_parse_cdata() {
 		++P;
 	}
 
-	if (cDataEnd)
+	if (cDataEnd) {
 		node_name = String::utf8(cDataBegin, (int)(cDataEnd - cDataBegin));
-	else
+	} else {
 		node_name = "";
+	}
 #ifdef DEBUG_XML
 	print_line("XML CDATA: " + node_name);
 #endif
@@ -190,7 +143,6 @@ bool XMLParser::_parse_cdata() {
 }
 
 void XMLParser::_parse_comment() {
-
 	node_type = NODE_COMMENT;
 	P += 1;
 
@@ -200,10 +152,11 @@ void XMLParser::_parse_comment() {
 
 	// move until end of comment reached
 	while (count) {
-		if (*P == '>')
+		if (*P == '>') {
 			--count;
-		else if (*P == '<')
+		} else if (*P == '<') {
 			++count;
+		}
 
 		++P;
 	}
@@ -217,7 +170,6 @@ void XMLParser::_parse_comment() {
 }
 
 void XMLParser::_parse_opening_xml_element() {
-
 	node_type = NODE_ELEMENT;
 	node_empty = false;
 	attributes.clear();
@@ -226,46 +178,52 @@ void XMLParser::_parse_opening_xml_element() {
 	const char *startName = P;
 
 	// find end of element
-	while (*P != '>' && !_is_white_space(*P))
+	while (*P != '>' && !_is_white_space(*P)) {
 		++P;
+	}
 
 	const char *endName = P;
 
 	// find attributes
 	while (*P != '>') {
-		if (_is_white_space(*P))
+		if (_is_white_space(*P)) {
 			++P;
-		else {
+		} else {
 			if (*P != '/') {
 				// we've got an attribute
 
 				// read the attribute names
 				const char *attributeNameBegin = P;
 
-				while (!_is_white_space(*P) && *P != '=')
+				while (!_is_white_space(*P) && *P != '=') {
 					++P;
+				}
 
 				const char *attributeNameEnd = P;
 				++P;
 
 				// read the attribute value
 				// check for quotes and single quotes, thx to murphy
-				while ((*P != '\"') && (*P != '\'') && *P)
+				while ((*P != '\"') && (*P != '\'') && *P) {
 					++P;
+				}
 
-				if (!*P) // malformatted xml file
+				if (!*P) { // malformatted xml file
 					return;
+				}
 
 				const char attributeQuoteChar = *P;
 
 				++P;
 				const char *attributeValueBegin = P;
 
-				while (*P != attributeQuoteChar && *P)
+				while (*P != attributeQuoteChar && *P) {
 					++P;
+				}
 
-				if (!*P) // malformatted xml file
+				if (!*P) { // malformatted xml file
 					return;
+				}
 
 				const char *attributeValueEnd = P;
 				++P;
@@ -277,7 +235,7 @@ void XMLParser::_parse_opening_xml_element() {
 				String s = String::utf8(attributeValueBegin,
 						(int)(attributeValueEnd - attributeValueBegin));
 
-				attr.value = _replace_special_characters(s);
+				attr.value = s.xml_unescape();
 				attributes.push_back(attr);
 			} else {
 				// tag is closed directly
@@ -304,21 +262,23 @@ void XMLParser::_parse_opening_xml_element() {
 }
 
 void XMLParser::_parse_current_node() {
-
 	char *start = P;
 	node_offset = P - data;
 
 	// more forward until '<' found
-	while (*P != '<' && *P)
+	while (*P != '<' && *P) {
 		++P;
+	}
 
-	if (!*P)
+	if (!*P) {
 		return;
+	}
 
 	if (P - start > 0) {
 		// we found some text, store it
-		if (_set_text(start, P))
+		if (_set_text(start, P)) {
 			return;
+		}
 	}
 
 	++P;
@@ -332,8 +292,9 @@ void XMLParser::_parse_current_node() {
 			_ignore_definition();
 			break;
 		case '!':
-			if (!_parse_cdata())
+			if (!_parse_cdata()) {
 				_parse_comment();
+			}
 			break;
 		default:
 			_parse_opening_xml_element();
@@ -342,22 +303,19 @@ void XMLParser::_parse_current_node() {
 }
 
 uint64_t XMLParser::get_node_offset() const {
-
 	return node_offset;
-};
+}
 
 Error XMLParser::seek(uint64_t p_pos) {
-
 	ERR_FAIL_COND_V(!data, ERR_FILE_EOF);
 	ERR_FAIL_COND_V(p_pos >= length, ERR_FILE_EOF);
 
 	P = data + p_pos;
 
 	return read();
-};
+}
 
 void XMLParser::_bind_methods() {
-
 	ClassDB::bind_method(D_METHOD("read"), &XMLParser::read);
 	ClassDB::bind_method(D_METHOD("get_node_type"), &XMLParser::get_node_type);
 	ClassDB::bind_method(D_METHOD("get_node_name"), &XMLParser::get_node_name);
@@ -383,10 +341,9 @@ void XMLParser::_bind_methods() {
 	BIND_ENUM_CONSTANT(NODE_COMMENT);
 	BIND_ENUM_CONSTANT(NODE_CDATA);
 	BIND_ENUM_CONSTANT(NODE_UNKNOWN);
-};
+}
 
 Error XMLParser::read() {
-
 	// if not end reached, parse the node
 	if (P && (P - data) < (int64_t)length - 1 && *P != 0) {
 		_parse_current_node();
@@ -397,11 +354,10 @@ Error XMLParser::read() {
 }
 
 XMLParser::NodeType XMLParser::get_node_type() {
-
 	return node_type;
 }
-String XMLParser::get_node_data() const {
 
+String XMLParser::get_node_data() const {
 	ERR_FAIL_COND_V(node_type != NODE_TEXT, "");
 	return node_name;
 }
@@ -410,31 +366,32 @@ String XMLParser::get_node_name() const {
 	ERR_FAIL_COND_V(node_type == NODE_TEXT, "");
 	return node_name;
 }
-int XMLParser::get_attribute_count() const {
 
+int XMLParser::get_attribute_count() const {
 	return attributes.size();
 }
-String XMLParser::get_attribute_name(int p_idx) const {
 
+String XMLParser::get_attribute_name(int p_idx) const {
 	ERR_FAIL_INDEX_V(p_idx, attributes.size(), "");
 	return attributes[p_idx].name;
 }
-String XMLParser::get_attribute_value(int p_idx) const {
 
+String XMLParser::get_attribute_value(int p_idx) const {
 	ERR_FAIL_INDEX_V(p_idx, attributes.size(), "");
 	return attributes[p_idx].value;
 }
-bool XMLParser::has_attribute(const String &p_name) const {
 
+bool XMLParser::has_attribute(const String &p_name) const {
 	for (int i = 0; i < attributes.size(); i++) {
-		if (attributes[i].name == p_name)
+		if (attributes[i].name == p_name) {
 			return true;
+		}
 	}
 
 	return false;
 }
-String XMLParser::get_attribute_value(const String &p_name) const {
 
+String XMLParser::get_attribute_value(const String &p_name) const {
 	int idx = -1;
 	for (int i = 0; i < attributes.size(); i++) {
 		if (attributes[i].name == p_name) {
@@ -449,7 +406,6 @@ String XMLParser::get_attribute_value(const String &p_name) const {
 }
 
 String XMLParser::get_attribute_value_safe(const String &p_name) const {
-
 	int idx = -1;
 	for (int i = 0; i < attributes.size(); i++) {
 		if (attributes[i].name == p_name) {
@@ -458,19 +414,23 @@ String XMLParser::get_attribute_value_safe(const String &p_name) const {
 		}
 	}
 
-	if (idx < 0)
+	if (idx < 0) {
 		return "";
+	}
 	return attributes[idx].value;
 }
-bool XMLParser::is_empty() const {
 
+bool XMLParser::is_empty() const {
 	return node_empty;
 }
 
 Error XMLParser::open_buffer(const Vector<uint8_t> &p_buffer) {
-
 	ERR_FAIL_COND_V(p_buffer.size() == 0, ERR_INVALID_DATA);
 
+	if (data) {
+		memdelete_arr(data);
+	}
+
 	length = p_buffer.size();
 	data = memnew_arr(char, length + 1);
 	copymem(data, p_buffer.ptr(), length);
@@ -480,7 +440,6 @@ Error XMLParser::open_buffer(const Vector<uint8_t> &p_buffer) {
 }
 
 Error XMLParser::open(const String &p_path) {
-
 	Error err;
 	FileAccess *file = FileAccess::open(p_path, FileAccess::READ, &err);
 
@@ -489,6 +448,10 @@ Error XMLParser::open(const String &p_path) {
 	length = file->get_len();
 	ERR_FAIL_COND_V(length < 1, ERR_FILE_CORRUPT);
 
+	if (data) {
+		memdelete_arr(data);
+	}
+
 	data = memnew_arr(char, length + 1);
 	file->get_buffer((uint8_t *)data, length);
 	data[length] = 0;
@@ -500,10 +463,10 @@ Error XMLParser::open(const String &p_path) {
 }
 
 void XMLParser::skip_section() {
-
 	// skip if this element is empty anyway.
-	if (is_empty())
+	if (is_empty()) {
 		return;
+	}
 
 	// read until we've reached the last element in this section
 	int tagcount = 1;
@@ -512,40 +475,33 @@ void XMLParser::skip_section() {
 		if (get_node_type() == XMLParser::NODE_ELEMENT &&
 				!is_empty()) {
 			++tagcount;
-		} else if (get_node_type() == XMLParser::NODE_ELEMENT_END)
+		} else if (get_node_type() == XMLParser::NODE_ELEMENT_END) {
 			--tagcount;
+		}
 	}
 }
 
 void XMLParser::close() {
-
-	if (data)
+	if (data) {
 		memdelete_arr(data);
-	data = NULL;
+	}
+	data = nullptr;
 	length = 0;
-	P = NULL;
+	P = nullptr;
 	node_empty = false;
 	node_type = NODE_NONE;
 	node_offset = 0;
 }
 
 int XMLParser::get_current_line() const {
-
 	return 0;
 }
 
 XMLParser::XMLParser() {
-
-	data = NULL;
-	close();
-	special_characters.push_back("&amp;");
-	special_characters.push_back("<lt;");
-	special_characters.push_back(">gt;");
-	special_characters.push_back("\"quot;");
-	special_characters.push_back("'apos;");
 }
-XMLParser::~XMLParser() {
 
-	if (data)
+XMLParser::~XMLParser() {
+	if (data) {
 		memdelete_arr(data);
+	}
 }