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

4 files changed, 141 insertions, 0 deletions

diff --git a/src/test/regress/expected/xml.out b/src/test/regress/expected/xml.out
index 2085fa03911..0aae60016bc 100644
--- a/src/test/regress/expected/xml.out
+++ b/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');
diff --git a/src/test/regress/expected/xml_1.out b/src/test/regress/expected/xml_1.out
index 7f866969734..d1a03b51a3d 100644
--- a/src/test/regress/expected/xml_1.out
+++ b/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');
diff --git a/src/test/regress/expected/xml_2.out b/src/test/regress/expected/xml_2.out
index 510b09bd03f..9756b6e8865 100644
--- a/src/test/regress/expected/xml_2.out
+++ b/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');
diff --git a/src/test/regress/sql/xml.sql b/src/test/regress/sql/xml.sql
index 8057a461788..71431d8a556 100644
--- a/src/test/regress/sql/xml.sql
+++ b/src/test/regress/sql/xml.sql
@@ -149,10 +149,17 @@ PREPARE foo (xml) AS SELECT xmlconcat('<foo/>', $1);
 SET XML OPTION DOCUMENT;
 EXECUTE foo ('<bar/>');
 EXECUTE foo ('bad');
+SELECT xml '<!DOCTYPE a><a/><b/>';
 
 SET XML OPTION CONTENT;
 EXECUTE foo ('<bar/>');
 EXECUTE foo ('good');
+SELECT xml '<!-- in SQL:2006+ a doc is content too--> <?y z?> <!DOCTYPE a><a/>';
+SELECT xml '<?xml version="1.0"?> <!-- hi--> <!DOCTYPE a><a/>';
+SELECT xml '<!DOCTYPE a><a/>';
+SELECT xml '<!-- hi--> oops <!DOCTYPE a><a/>';
+SELECT xml '<!-- hi--> <oops/> <!DOCTYPE a><a/>';
+SELECT xml '<!DOCTYPE a><a/><b/>';
 
 
 -- Test backwards parsing