Accept XML documents when xmloption = content, as required by SQL:2006+.

Previously we were using the SQL:2003 definition, which doesn't allow
this, but that creates a serious dump/restore gotcha: there is no
setting of xmloption that will allow all valid XML data.  Hence,
switch to the 2006 definition.

Since libxml doesn't accept <!DOCTYPE> directives in the mode we
use for CONTENT parsing, the implementation is to detect <!DOCTYPE>
in the input and switch to DOCUMENT parsing mode.  This should not
cost much, because <!DOCTYPE> should be close to the front of the
input if it's there at all.  It's possible that this causes the
error messages for malformed input to be slightly different than
they were before, if said input includes <!DOCTYPE>; but that does
not seem like a big problem.

In passing, buy back a few cycles in parsing of large XML documents
by not doing strlen() of the whole input in parse_xml_decl().

Back-patch because dump/restore failures are not nice.  This change
shouldn't break any cases that worked before, so it seems safe to
back-patch.

Chapman Flack (revised a bit by me)

Discussion: https://postgr.es/m/CAN-V+g-6JqUQEQZ55Q3toXEN6d5Ez5uvzL4VR+8KtvJKj31taw@mail.gmail.com

Author: tglsfdc

doc/src/sgml/datatype.sgml

@@ -4208,9 +4208,11 @@ a0ee-bc99-9c0b-4ef8-bb6d-6bb9-bd38-0a11
    <para>
     The <type>xml</type> type can store well-formed
     <quote>documents</quote>, as defined by the XML standard, as well
-    as <quote>content</quote> fragments, which are defined by the
-    production <literal>XMLDecl? content</literal> in the XML
-    standard.  Roughly, this means that content fragments can have
+    as <quote>content</quote> fragments, which are defined by reference
+    to the more permissive
+    <ulink url="https://www.w3.org/TR/2010/REC-xpath-datamodel-20101214/#DocumentNode"><quote>document node</quote></ulink>
+    of the XQuery and XPath data model.
+    Roughly, this means that content fragments can have
     more than one top-level element or character node.  The expression
     <literal><replaceable>xmlvalue</replaceable> IS DOCUMENT</literal>
     can be used to evaluate whether a particular <type>xml</type>
@@ -4285,16 +4287,6 @@ SET xmloption TO { DOCUMENT | CONTENT };
     data are allowed.
    </para>
 
-   <note>
-    <para>
-     With the default XML option setting, you cannot directly cast
-     character strings to type <type>xml</type> if they contain a
-     document type declaration, because the definition of XML content
-     fragment does not accept them.  If you need to do that, either
-     use <literal>XMLPARSE</literal> or change the XML option.
-    </para>
-   </note>
-
    </sect2>
 
    <sect2>

src/backend/utils/adt/xml.c

@@ -141,6 +141,7 @@ static int parse_xml_decl(const xmlChar *str, size_t *lenp,
 			   xmlChar **version, xmlChar **encoding, int *standalone);
 static bool print_xml_decl(StringInfo buf, const xmlChar *version,
 			   pg_enc encoding, int standalone);
+static bool xml_doctype_in_content(const xmlChar *str);
 static xmlDocPtr xml_parse(text *data, XmlOptionType xmloption_arg,
 		  bool preserve_whitespace, int encoding);
 static text *xml_xmlnodetoxmltype(xmlNodePtr cur, PgXmlErrorContext *xmlerrcxt);
@@ -1243,8 +1244,15 @@ parse_xml_decl(const xmlChar *str, size_t *lenp,
 	if (xmlStrncmp(p, (xmlChar *) "<?xml", 5) != 0)
 		goto finished;
 
-	/* if next char is name char, it's a PI like <?xml-stylesheet ...?> */
-	utf8len = strlen((const char *) (p + 5));
+	/*
+	 * If next char is a name char, it's a PI like <?xml-stylesheet ...?>
+	 * rather than an XMLDecl, so we have done what we came to do and found no
+	 * XMLDecl.
+	 *
+	 * We need an input length value for xmlGetUTF8Char, but there's no need
+	 * to count the whole document size, so use strnlen not strlen.
+	 */
+	utf8len = strnlen((const char *) (p + 5), MAX_MULTIBYTE_CHAR_LEN);
 	utf8char = xmlGetUTF8Char(p + 5, &utf8len);
 	if (PG_XMLISNAMECHAR(utf8char))
 		goto finished;
@@ -1415,6 +1423,88 @@ print_xml_decl(StringInfo buf, const xmlChar *version,
 		return false;
 }
 
+/*
+ * Test whether an input that is to be parsed as CONTENT contains a DTD.
+ *
+ * The SQL/XML:2003 definition of CONTENT ("XMLDecl? content") is not
+ * satisfied by a document with a DTD, which is a bit of a wart, as it means
+ * the CONTENT type is not a proper superset of DOCUMENT.  SQL/XML:2006 and
+ * later fix that, by redefining content with reference to the "more
+ * permissive" Document Node of the XQuery/XPath Data Model, such that any
+ * DOCUMENT value is indeed also a CONTENT value.  That definition is more
+ * useful, as CONTENT becomes usable for parsing input of unknown form (think
+ * pg_restore).
+ *
+ * As used below in parse_xml when parsing for CONTENT, libxml does not give
+ * us the 2006+ behavior, but only the 2003; it will choke if the input has
+ * a DTD.  But we can provide the 2006+ definition of CONTENT easily enough,
+ * by detecting this case first and simply doing the parse as DOCUMENT.
+ *
+ * A DTD can be found arbitrarily far in, but that would be a contrived case;
+ * it will ordinarily start within a few dozen characters.  The only things
+ * that can precede it are an XMLDecl (here, the caller will have called
+ * parse_xml_decl already), whitespace, comments, and processing instructions.
+ * This function need only return true if it sees a valid sequence of such
+ * things leading to <!DOCTYPE.  It can simply return false in any other
+ * cases, including malformed input; that will mean the input gets parsed as
+ * CONTENT as originally planned, with libxml reporting any errors.
+ *
+ * This is only to be called from xml_parse, when pg_xml_init has already
+ * been called.  The input is already in UTF8 encoding.
+ */
+static bool
+xml_doctype_in_content(const xmlChar *str)
+{
+	const xmlChar *p = str;
+
+	for (;;)
+	{
+		const xmlChar *e;
+
+		SKIP_XML_SPACE(p);
+		if (*p != '<')
+			return false;
+		p++;
+
+		if (*p == '!')
+		{
+			p++;
+
+			/* if we see <!DOCTYPE, we can return true */
+			if (xmlStrncmp(p, (xmlChar *) "DOCTYPE", 7) == 0)
+				return true;
+
+			/* otherwise, if it's not a comment, fail */
+			if (xmlStrncmp(p, (xmlChar *) "--", 2) != 0)
+				return false;
+			/* find end of comment: find -- and a > must follow */
+			p = xmlStrstr(p + 2, (xmlChar *) "--");
+			if (!p || p[2] != '>')
+				return false;
+			/* advance over comment, and keep scanning */
+			p += 3;
+			continue;
+		}
+
+		/* otherwise, if it's not a PI <?target something?>, fail */
+		if (*p != '?')
+			return false;
+		p++;
+
+		/* find end of PI (the string ?> is forbidden within a PI) */
+		e = xmlStrstr(p, (xmlChar *) "?>");
+		if (!e)
+			return false;
+
+		/* we don't check PIs carefully, but do reject "xml" target */
+		if (e - p >= 3 && xmlStrncasecmp(p, (xmlChar *) "xml", 3) == 0)
+			return false;
+
+		/* advance over PI, keep scanning */
+		p = e + 2;
+	}
+}
+
 
 /*
  * Convert a C string to XML internal representation
@@ -1450,14 +1540,38 @@ xml_parse(text *data, XmlOptionType xmloption_arg, bool preserve_whitespace,
 	/* Use a TRY block to ensure we clean up correctly */
 	PG_TRY();
 	{
+		bool		parse_as_document = false;
+		int			res_code;
+		size_t		count = 0;
+		xmlChar    *version = NULL;
+		int			standalone = 0;
+
 		xmlInitParser();
 
 		ctxt = xmlNewParserCtxt();
 		if (ctxt == NULL || xmlerrcxt->err_occurred)
 			xml_ereport(xmlerrcxt, ERROR, ERRCODE_OUT_OF_MEMORY,
 						"could not allocate parser context");
 
+		/* Decide whether to parse as document or content */
 		if (xmloption_arg == XMLOPTION_DOCUMENT)
+			parse_as_document = true;
+		else
+		{
+			/* Parse and skip over the XML declaration, if any */
+			res_code = parse_xml_decl(utf8string,
+									  &count, &version, NULL, &standalone);
+			if (res_code != 0)
+				xml_ereport_by_code(ERROR, ERRCODE_INVALID_XML_CONTENT,
+									"invalid XML content: invalid XML declaration",
+									res_code);
+
+			/* Is there a DOCTYPE element? */
+			if (xml_doctype_in_content(utf8string + count))
+				parse_as_document = true;
+		}
+
+		if (parse_as_document)
 		{
 			/*
 			 * Note, that here we try to apply DTD defaults
@@ -1472,23 +1586,18 @@ xml_parse(text *data, XmlOptionType xmloption_arg, bool preserve_whitespace,
 								 XML_PARSE_NOENT | XML_PARSE_DTDATTR
 								 | (preserve_whitespace ? 0 : XML_PARSE_NOBLANKS));
 			if (doc == NULL || xmlerrcxt->err_occurred)
-				xml_ereport(xmlerrcxt, ERROR, ERRCODE_INVALID_XML_DOCUMENT,
-							"invalid XML document");
+			{
+				/* Use original option to decide which error code to throw */
+				if (xmloption_arg == XMLOPTION_DOCUMENT)
+					xml_ereport(xmlerrcxt, ERROR, ERRCODE_INVALID_XML_DOCUMENT,
+								"invalid XML document");
+				else
+					xml_ereport(xmlerrcxt, ERROR, ERRCODE_INVALID_XML_CONTENT,
+								"invalid XML content");
+			}
 		}
 		else
 		{
-			int			res_code;
-			size_t		count;
-			xmlChar    *version;
-			int			standalone;
-
-			res_code = parse_xml_decl(utf8string,
-									  &count, &version, NULL, &standalone);
-			if (res_code != 0)
-				xml_ereport_by_code(ERROR, ERRCODE_INVALID_XML_CONTENT,
-									"invalid XML content: invalid XML declaration",
-									res_code);
-
 			doc = xmlNewDoc(version);
 			Assert(doc->encoding == NULL);
 			doc->encoding = xmlStrdup((const xmlChar *) "UTF-8");

src/test/regress/expected/xml.out

@@ -532,6 +532,13 @@ LINE 1: EXECUTE foo ('bad');
 DETAIL:  line 1: Start tag expected, '<' not found
 bad
 ^
+SELECT xml '<!DOCTYPE a><a/><b/>';
+ERROR:  invalid XML document
+LINE 1: SELECT xml '<!DOCTYPE a><a/><b/>';
+                   ^
+DETAIL:  line 1: Extra content at the end of the document
+<!DOCTYPE a><a/><b/>
+                ^
 SET XML OPTION CONTENT;
 EXECUTE foo ('<bar/>');
   xmlconcat   
@@ -545,6 +552,45 @@ EXECUTE foo ('good');
  <foo/>good
 (1 row)
 
+SELECT xml '<!-- in SQL:2006+ a doc is content too--> <?y z?> <!DOCTYPE a><a/>';
+                                xml                                 
+--------------------------------------------------------------------
+ <!-- in SQL:2006+ a doc is content too--> <?y z?> <!DOCTYPE a><a/>
+(1 row)
+
+SELECT xml '<?xml version="1.0"?> <!-- hi--> <!DOCTYPE a><a/>';
+             xml              
+------------------------------
+  <!-- hi--> <!DOCTYPE a><a/>
+(1 row)
+
+SELECT xml '<!DOCTYPE a><a/>';
+       xml        
+------------------
+ <!DOCTYPE a><a/>
+(1 row)
+
+SELECT xml '<!-- hi--> oops <!DOCTYPE a><a/>';
+ERROR:  invalid XML content
+LINE 1: SELECT xml '<!-- hi--> oops <!DOCTYPE a><a/>';
+                   ^
+DETAIL:  line 1: StartTag: invalid element name
+<!-- hi--> oops <!DOCTYPE a><a/>
+                 ^
+SELECT xml '<!-- hi--> <oops/> <!DOCTYPE a><a/>';
+ERROR:  invalid XML content
+LINE 1: SELECT xml '<!-- hi--> <oops/> <!DOCTYPE a><a/>';
+                   ^
+DETAIL:  line 1: StartTag: invalid element name
+<!-- hi--> <oops/> <!DOCTYPE a><a/>
+                    ^
+SELECT xml '<!DOCTYPE a><a/><b/>';
+ERROR:  invalid XML content
+LINE 1: SELECT xml '<!DOCTYPE a><a/><b/>';
+                   ^
+DETAIL:  line 1: Extra content at the end of the document
+<!DOCTYPE a><a/><b/>
+                ^
 -- Test backwards parsing
 CREATE VIEW xmlview1 AS SELECT xmlcomment('test');
 CREATE VIEW xmlview2 AS SELECT xmlconcat('hello', 'you');

src/test/regress/expected/xml_1.out

@@ -429,11 +429,53 @@ EXECUTE foo ('<bar/>');
 ERROR:  prepared statement "foo" does not exist
 EXECUTE foo ('bad');
 ERROR:  prepared statement "foo" does not exist
+SELECT xml '<!DOCTYPE a><a/><b/>';
+ERROR:  unsupported XML feature
+LINE 1: SELECT xml '<!DOCTYPE a><a/><b/>';
+                   ^
+DETAIL:  This functionality requires the server to be built with libxml support.
+HINT:  You need to rebuild PostgreSQL using --with-libxml.
 SET XML OPTION CONTENT;
 EXECUTE foo ('<bar/>');
 ERROR:  prepared statement "foo" does not exist
 EXECUTE foo ('good');
 ERROR:  prepared statement "foo" does not exist
+SELECT xml '<!-- in SQL:2006+ a doc is content too--> <?y z?> <!DOCTYPE a><a/>';
+ERROR:  unsupported XML feature
+LINE 1: SELECT xml '<!-- in SQL:2006+ a doc is content too--> <?y z?...
+                   ^
+DETAIL:  This functionality requires the server to be built with libxml support.
+HINT:  You need to rebuild PostgreSQL using --with-libxml.
+SELECT xml '<?xml version="1.0"?> <!-- hi--> <!DOCTYPE a><a/>';
+ERROR:  unsupported XML feature
+LINE 1: SELECT xml '<?xml version="1.0"?> <!-- hi--> <!DOCTYPE a><a/...
+                   ^
+DETAIL:  This functionality requires the server to be built with libxml support.
+HINT:  You need to rebuild PostgreSQL using --with-libxml.
+SELECT xml '<!DOCTYPE a><a/>';
+ERROR:  unsupported XML feature
+LINE 1: SELECT xml '<!DOCTYPE a><a/>';
+                   ^
+DETAIL:  This functionality requires the server to be built with libxml support.
+HINT:  You need to rebuild PostgreSQL using --with-libxml.
+SELECT xml '<!-- hi--> oops <!DOCTYPE a><a/>';
+ERROR:  unsupported XML feature
+LINE 1: SELECT xml '<!-- hi--> oops <!DOCTYPE a><a/>';
+                   ^
+DETAIL:  This functionality requires the server to be built with libxml support.
+HINT:  You need to rebuild PostgreSQL using --with-libxml.
+SELECT xml '<!-- hi--> <oops/> <!DOCTYPE a><a/>';
+ERROR:  unsupported XML feature
+LINE 1: SELECT xml '<!-- hi--> <oops/> <!DOCTYPE a><a/>';
+                   ^
+DETAIL:  This functionality requires the server to be built with libxml support.
+HINT:  You need to rebuild PostgreSQL using --with-libxml.
+SELECT xml '<!DOCTYPE a><a/><b/>';
+ERROR:  unsupported XML feature
+LINE 1: SELECT xml '<!DOCTYPE a><a/><b/>';
+                   ^
+DETAIL:  This functionality requires the server to be built with libxml support.
+HINT:  You need to rebuild PostgreSQL using --with-libxml.
 -- Test backwards parsing
 CREATE VIEW xmlview1 AS SELECT xmlcomment('test');
 CREATE VIEW xmlview2 AS SELECT xmlconcat('hello', 'you');

src/test/regress/expected/xml_2.out

@@ -512,6 +512,13 @@ LINE 1: EXECUTE foo ('bad');
 DETAIL:  line 1: Start tag expected, '<' not found
 bad
 ^
+SELECT xml '<!DOCTYPE a><a/><b/>';
+ERROR:  invalid XML document
+LINE 1: SELECT xml '<!DOCTYPE a><a/><b/>';
+                   ^
+DETAIL:  line 1: Extra content at the end of the document
+<!DOCTYPE a><a/><b/>
+                ^
 SET XML OPTION CONTENT;
 EXECUTE foo ('<bar/>');
   xmlconcat   
@@ -525,6 +532,45 @@ EXECUTE foo ('good');
  <foo/>good
 (1 row)
 
+SELECT xml '<!-- in SQL:2006+ a doc is content too--> <?y z?> <!DOCTYPE a><a/>';
+                                xml                                 
+--------------------------------------------------------------------
+ <!-- in SQL:2006+ a doc is content too--> <?y z?> <!DOCTYPE a><a/>
+(1 row)
+
+SELECT xml '<?xml version="1.0"?> <!-- hi--> <!DOCTYPE a><a/>';
+             xml              
+------------------------------
+  <!-- hi--> <!DOCTYPE a><a/>
+(1 row)
+
+SELECT xml '<!DOCTYPE a><a/>';
+       xml        
+------------------
+ <!DOCTYPE a><a/>
+(1 row)
+
+SELECT xml '<!-- hi--> oops <!DOCTYPE a><a/>';
+ERROR:  invalid XML content
+LINE 1: SELECT xml '<!-- hi--> oops <!DOCTYPE a><a/>';
+                   ^
+DETAIL:  line 1: StartTag: invalid element name
+<!-- hi--> oops <!DOCTYPE a><a/>
+                 ^
+SELECT xml '<!-- hi--> <oops/> <!DOCTYPE a><a/>';
+ERROR:  invalid XML content
+LINE 1: SELECT xml '<!-- hi--> <oops/> <!DOCTYPE a><a/>';
+                   ^
+DETAIL:  line 1: StartTag: invalid element name
+<!-- hi--> <oops/> <!DOCTYPE a><a/>
+                    ^
+SELECT xml '<!DOCTYPE a><a/><b/>';
+ERROR:  invalid XML content
+LINE 1: SELECT xml '<!DOCTYPE a><a/><b/>';
+                   ^
+DETAIL:  line 1: Extra content at the end of the document
+<!DOCTYPE a><a/><b/>
+                ^
 -- Test backwards parsing
 CREATE VIEW xmlview1 AS SELECT xmlcomment('test');
 CREATE VIEW xmlview2 AS SELECT xmlconcat('hello', 'you');