On 06.03.23 11:50, I wrote:
I guess this confusion is happening because xml_parse() was being
called with the database encoding from GetDatabaseEncoding().
I added a condition before calling xml_parse() to check if the xml
document has a different encoding than UTF-8
parse_xml_decl(xml_text2xmlChar(data), NULL, NULL, &encodingStr, NULL);
encoding = encodingStr ? xmlChar_to_encoding(encodingStr) : PG_UTF8;
doc = xml_parse(data, XMLOPTION_DOCUMENT, false, encoding, NULL);
It seems that this bug fix didn't change the output of the CI on Debian
+ Meson, 32bit.
I slightly changed the test case to a character that both encodings can
deal with.
v3 attached.
From 759bacecb7e9355f41ebd02cbca38cf893e3cfc0 Mon Sep 17 00:00:00 2001
From: Jim Jones <jim.jo...@uni-muenster.de>
Date: Mon, 6 Mar 2023 14:08:54 +0100
Subject: [PATCH v3] Add CANONICAL format to xmlserialize
This patch introduces the CANONICAL option to xmlserialize, which
serializes xml documents in their canonical form - as described in
the W3C Canonical XML Version 1.1 specification. This option can
be used with the additional parameter WITH [NO] COMMENTS to keep
or remove xml comments from the canonical xml output. This feature
is based on the function xmlC14NDocDumpMemory from the C14N module
of libxml2.
This patch also includes regression tests and documentation.
---
doc/src/sgml/datatype.sgml | 41 +++++++++-
src/backend/executor/execExprInterp.c | 12 ++-
src/backend/parser/gram.y | 14 +++-
src/backend/parser/parse_expr.c | 1 +
src/backend/utils/adt/xml.c | 70 +++++++++++++++++
src/include/nodes/parsenodes.h | 1 +
src/include/nodes/primnodes.h | 9 +++
src/include/parser/kwlist.h | 1 +
src/include/utils/xml.h | 1 +
src/test/regress/expected/xml.out | 108 ++++++++++++++++++++++++++
src/test/regress/expected/xml_1.out | 104 +++++++++++++++++++++++++
src/test/regress/expected/xml_2.out | 108 ++++++++++++++++++++++++++
src/test/regress/sql/xml.sql | 61 +++++++++++++++
13 files changed, 526 insertions(+), 5 deletions(-)
diff --git a/doc/src/sgml/datatype.sgml b/doc/src/sgml/datatype.sgml
index 467b49b199..46ec95dbb8 100644
--- a/doc/src/sgml/datatype.sgml
+++ b/doc/src/sgml/datatype.sgml
@@ -4460,7 +4460,7 @@ xml '<foo>bar</foo>'
<type>xml</type>, uses the function
<function>xmlserialize</function>:<indexterm><primary>xmlserialize</primary></indexterm>
<synopsis>
-XMLSERIALIZE ( { DOCUMENT | CONTENT } <replaceable>value</replaceable> AS <replaceable>type</replaceable> )
+XMLSERIALIZE ( { DOCUMENT | CONTENT } <replaceable>value</replaceable> AS <replaceable>type</replaceable> [ CANONICAL [ WITH [NO] COMMENTS ] ])
</synopsis>
<replaceable>type</replaceable> can be
<type>character</type>, <type>character varying</type>, or
@@ -4470,6 +4470,45 @@ XMLSERIALIZE ( { DOCUMENT | CONTENT } <replaceable>value</replaceable> AS <repla
you to simply cast the value.
</para>
+ <para>
+ The option <type>CANONICAL</type> converts a given
+ XML document to its <ulink url="https://www.w3.org/TR/xml-c14n11/#Terminology";>canonical form</ulink>
+ based on the <ulink url="https://www.w3.org/TR/xml-c14n11/";>W3C Canonical XML 1.1 Specification</ulink>.
+ It is basically designed to provide applications the ability to compare xml documents or test if they
+ have been changed. The optional parameter <type>WITH [NO] COMMENTS</type> removes or keeps XML comments
+ from the given document.
+ </para>
+
+ <para>
+ Example:
+
+<screen><![CDATA[
+SELECT
+ xmlserialize(DOCUMENT
+ '<foo>
+ <!-- a comment -->
+ <bar c="3" b="2" a="1">42</bar>
+ <empty/>
+ </foo>'::xml AS text CANONICAL);
+ xmlserialize
+-----------------------------------------------------------
+ <foo><bar a="1" b="2" c="3">42</bar><empty></empty></foo>
+(1 row)
+
+SELECT
+ xmlserialize(DOCUMENT
+ '<foo>
+ <!-- a comment -->
+ <bar c="3" b="2" a="1">42</bar>
+ <empty/>
+ </foo>'::xml AS text CANONICAL WITH COMMENTS);
+ xmlserialize
+-----------------------------------------------------------------------------
+ <foo><!-- a comment --><bar a="1" b="2" c="3">42</bar><empty></empty></foo>
+(1 row)
+
+]]></screen>
+ </para>
<para>
When a character string value is cast to or from type
<type>xml</type> without going through <type>XMLPARSE</type> or
diff --git a/src/backend/executor/execExprInterp.c b/src/backend/executor/execExprInterp.c
index 19351fe34b..f8f10f0ed9 100644
--- a/src/backend/executor/execExprInterp.c
+++ b/src/backend/executor/execExprInterp.c
@@ -3829,6 +3829,8 @@ ExecEvalXmlExpr(ExprState *state, ExprEvalStep *op)
{
Datum *argvalue = op->d.xmlexpr.argvalue;
bool *argnull = op->d.xmlexpr.argnull;
+ XmlSerializeFormat format = op->d.xmlexpr.xexpr->format;
+ text *data;
/* argument type is known to be xml */
Assert(list_length(xexpr->args) == 1);
@@ -3837,9 +3839,15 @@ ExecEvalXmlExpr(ExprState *state, ExprEvalStep *op)
return;
value = argvalue[0];
- *op->resvalue = PointerGetDatum(xmltotext_with_xmloption(DatumGetXmlP(value),
- xexpr->xmloption));
*op->resnull = false;
+
+ data = xmltotext_with_xmloption(DatumGetXmlP(value),
+ xexpr->xmloption);
+
+ if (format == XMLDEFAULT_FORMAT)
+ *op->resvalue = PointerGetDatum(data);
+ else if (format == XMLCANONICAL || format == XMLCANONICAL_WITH_COMMENTS)
+ *op->resvalue = PointerGetDatum(xmlserialize_canonical(data,format));
}
break;
diff --git a/src/backend/parser/gram.y b/src/backend/parser/gram.y
index a0138382a1..af5f3dfdfd 100644
--- a/src/backend/parser/gram.y
+++ b/src/backend/parser/gram.y
@@ -619,6 +619,7 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query);
%type <defelt> xmltable_column_option_el
%type <list> xml_namespace_list
%type <target> xml_namespace_el
+%type <ival> opt_xml_serialize_format
%type <node> func_application func_expr_common_subexpr
%type <node> func_expr func_expr_windowless
@@ -676,7 +677,7 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query);
BACKWARD BEFORE BEGIN_P BETWEEN BIGINT BINARY BIT
BOOLEAN_P BOTH BREADTH BY
- CACHE CALL CALLED CASCADE CASCADED CASE CAST CATALOG_P CHAIN CHAR_P
+ CACHE CALL CALLED CANONICAL CASCADE CASCADED CASE CAST CATALOG_P CHAIN CHAR_P
CHARACTER CHARACTERISTICS CHECK CHECKPOINT CLASS CLOSE
CLUSTER COALESCE COLLATE COLLATION COLUMN COLUMNS COMMENT COMMENTS COMMIT
COMMITTED COMPRESSION CONCURRENTLY CONFIGURATION CONFLICT
@@ -15532,13 +15533,14 @@ func_expr_common_subexpr:
$$ = makeXmlExpr(IS_XMLROOT, NULL, NIL,
list_make3($3, $5, $6), @1);
}
- | XMLSERIALIZE '(' document_or_content a_expr AS SimpleTypename ')'
+ | XMLSERIALIZE '(' document_or_content a_expr AS SimpleTypename opt_xml_serialize_format ')'
{
XmlSerialize *n = makeNode(XmlSerialize);
n->xmloption = $3;
n->expr = $4;
n->typeName = $6;
+ n->format = $7;
n->location = @1;
$$ = (Node *) n;
}
@@ -15622,6 +15624,12 @@ xml_passing_mech:
| BY VALUE_P
;
+opt_xml_serialize_format:
+ CANONICAL { $$ = XMLCANONICAL; }
+ | CANONICAL WITH NO COMMENTS { $$ = XMLCANONICAL; }
+ | CANONICAL WITH COMMENTS { $$ = XMLCANONICAL_WITH_COMMENTS; }
+ | /*EMPTY*/ { $$ = XMLDEFAULT_FORMAT; }
+ ;
/*
* Aggregate decoration clauses
@@ -16737,6 +16745,7 @@ unreserved_keyword:
| CACHE
| CALL
| CALLED
+ | CANONICAL
| CASCADE
| CASCADED
| CATALOG_P
@@ -17259,6 +17268,7 @@ bare_label_keyword:
| CACHE
| CALL
| CALLED
+ | CANONICAL
| CASCADE
| CASCADED
| CASE
diff --git a/src/backend/parser/parse_expr.c b/src/backend/parser/parse_expr.c
index 78221d2e0f..799a345067 100644
--- a/src/backend/parser/parse_expr.c
+++ b/src/backend/parser/parse_expr.c
@@ -2332,6 +2332,7 @@ transformXmlSerialize(ParseState *pstate, XmlSerialize *xs)
xexpr->xmloption = xs->xmloption;
xexpr->location = xs->location;
+ xexpr->format = xs->format;
/* We actually only need these to be able to parse back the expression. */
xexpr->type = targetType;
xexpr->typmod = targetTypmod;
diff --git a/src/backend/utils/adt/xml.c b/src/backend/utils/adt/xml.c
index 079bcb1208..f618be524b 100644
--- a/src/backend/utils/adt/xml.c
+++ b/src/backend/utils/adt/xml.c
@@ -56,6 +56,7 @@
#include <libxml/xmlwriter.h>
#include <libxml/xpath.h>
#include <libxml/xpathInternals.h>
+#include <libxml/c14n.h>
/*
* We used to check for xmlStructuredErrorContext via a configure test; but
@@ -4818,3 +4819,72 @@ XmlTableDestroyOpaque(TableFuncScanState *state)
NO_XML_SUPPORT();
#endif /* not USE_LIBXML */
}
+
+xmltype *
+xmlserialize_canonical(text *data, XmlSerializeFormat format)
+{
+#ifdef USE_LIBXML
+
+ xmlDocPtr doc;
+ xmlChar *xmlbuf = NULL;
+ xmlChar *encodingStr = NULL;
+ int nbytes;
+ int with_comments = 0; /* 0 = remove xml comments (default) */
+ int encoding;
+ StringInfoData buf;
+
+
+ if (format != XMLCANONICAL && format != XMLCANONICAL_WITH_COMMENTS)
+ elog(ERROR,"invalid canonical xml option");
+ else if (format == XMLCANONICAL_WITH_COMMENTS)
+ with_comments = 1;
+
+ /*
+ * Parses the encoding from the header, so that xml_parse() knows what
+ * it is dealing with. If not explicitly declared, we assume UTF-8.
+ */
+ parse_xml_decl(xml_text2xmlChar(data), NULL, NULL, &encodingStr, NULL);
+ encoding = encodingStr ? xmlChar_to_encoding(encodingStr) : PG_UTF8;
+
+ doc = xml_parse(data, XMLOPTION_DOCUMENT, false, encoding, NULL);
+
+ if(!doc)
+ elog(ERROR, "could not parse the given XML document");
+
+ /*
+ * int
+ * xmlC14NDocDumpMemory (
+ * xmlDocPtr doc, # the XML document for canonization
+ * xmlNodeSetPtr nodes, # the nodes set to be included in the canonized image
+ * or NULL if all document nodes should be included
+ * int mode, # 0 = Original C14N 1.0 (Outdated)
+ * 1 = Exclusive C14N 1.0 (Outdated)
+ * 2 = C14N 1.1
+ * xmlChar **inclusive_ns_prefixes, # the list of inclusive namespace prefixes ended with
+ * a NULL or NULL if there is no inclusive namespaces
+ * (only for exclusive canonicalization, ignored otherwise)
+ * int with_comments, # include comments in the result (!=0) or not (==0)
+ * xmlChar **xmlbuf # the memory pointer for allocated canonical XML text;
+ * )
+ * Returns: the number of bytes written on success or a negative value on fail.
+ */
+
+ nbytes = xmlC14NDocDumpMemory(doc, NULL, 2, NULL, with_comments, &xmlbuf);
+
+ xmlFreeDoc(doc);
+
+ if(nbytes < 0)
+ elog(ERROR,"could not canonicalize the given XML document");
+
+ initStringInfo(&buf);
+ appendStringInfoString(&buf, (const char *) xmlbuf);
+
+ xmlFree(xmlbuf);
+
+ return stringinfo_to_xmltype(&buf);
+
+#else
+ NO_XML_SUPPORT();
+ return 0;
+#endif
+}
\ No newline at end of file
diff --git a/src/include/nodes/parsenodes.h b/src/include/nodes/parsenodes.h
index f7d7f10f7d..8ba0984266 100644
--- a/src/include/nodes/parsenodes.h
+++ b/src/include/nodes/parsenodes.h
@@ -842,6 +842,7 @@ typedef struct XmlSerialize
Node *expr;
TypeName *typeName;
int location; /* token location, or -1 if unknown */
+ XmlSerializeFormat format; /* serialization format */
} XmlSerialize;
/* Partitioning related definitions */
diff --git a/src/include/nodes/primnodes.h b/src/include/nodes/primnodes.h
index b4292253cc..79fdcc2650 100644
--- a/src/include/nodes/primnodes.h
+++ b/src/include/nodes/primnodes.h
@@ -1471,6 +1471,13 @@ typedef enum XmlOptionType
XMLOPTION_CONTENT
} XmlOptionType;
+typedef enum XmlSerializeFormat
+{
+ XMLCANONICAL, /* canonical form without xml comments */
+ XMLCANONICAL_WITH_COMMENTS, /* canonical form with xml comments */
+ XMLDEFAULT_FORMAT /* unformatted xml representation */
+} XmlSerializeFormat;
+
typedef struct XmlExpr
{
Expr xpr;
@@ -1491,6 +1498,8 @@ typedef struct XmlExpr
int32 typmod pg_node_attr(query_jumble_ignore);
/* token location, or -1 if unknown */
int location;
+ /* serialization format: XMLCANONICAL, XMLCANONICAL_WITH_COMMENTS, XMLINDENT */
+ XmlSerializeFormat format pg_node_attr(query_jumble_ignore);
} XmlExpr;
/* ----------------
diff --git a/src/include/parser/kwlist.h b/src/include/parser/kwlist.h
index bb36213e6f..c1b1a720fe 100644
--- a/src/include/parser/kwlist.h
+++ b/src/include/parser/kwlist.h
@@ -67,6 +67,7 @@ PG_KEYWORD("by", BY, UNRESERVED_KEYWORD, BARE_LABEL)
PG_KEYWORD("cache", CACHE, UNRESERVED_KEYWORD, BARE_LABEL)
PG_KEYWORD("call", CALL, UNRESERVED_KEYWORD, BARE_LABEL)
PG_KEYWORD("called", CALLED, UNRESERVED_KEYWORD, BARE_LABEL)
+PG_KEYWORD("canonical", CANONICAL, UNRESERVED_KEYWORD, BARE_LABEL)
PG_KEYWORD("cascade", CASCADE, UNRESERVED_KEYWORD, BARE_LABEL)
PG_KEYWORD("cascaded", CASCADED, UNRESERVED_KEYWORD, BARE_LABEL)
PG_KEYWORD("case", CASE, RESERVED_KEYWORD, BARE_LABEL)
diff --git a/src/include/utils/xml.h b/src/include/utils/xml.h
index 311da06cd6..745ebefe24 100644
--- a/src/include/utils/xml.h
+++ b/src/include/utils/xml.h
@@ -90,4 +90,5 @@ extern PGDLLIMPORT int xmloption; /* XmlOptionType, but int for guc enum */
extern PGDLLIMPORT const TableFuncRoutine XmlTableRoutine;
+xmltype *xmlserialize_canonical(text *data, XmlSerializeFormat format);
#endif /* XML_H */
diff --git a/src/test/regress/expected/xml.out b/src/test/regress/expected/xml.out
index ad852dc2f7..5c205a0d88 100644
--- a/src/test/regress/expected/xml.out
+++ b/src/test/regress/expected/xml.out
@@ -486,6 +486,114 @@ SELECT xmlserialize(content 'good' as char(10));
SELECT xmlserialize(document 'bad' as text);
ERROR: not an XML document
+-- xmlserialize: canonical
+CREATE TABLE xmltest_serialize (id int, doc xml);
+INSERT INTO xmltest_serialize VALUES
+ (1,'<?xml version="1.0" encoding="ISO-8859-1"?>
+ <!DOCTYPE doc SYSTEM "doc.dtd" [
+ <!ENTITY val "42">
+ <!ATTLIST xyz attr CDATA "default">
+ ]>
+
+ <!-- attributes and namespces will be sorted -->
+ <foo a:attr="out" b:attr="sorted" attr2="all" attr="I am"
+ xmlns:b="http://www.ietf.org";
+ xmlns:a="http://www.w3.org";
+ xmlns="http://example.org";>
+
+ <!-- Normalization of whitespace in start and end tags -->
+ <!-- Elimination of superfluous namespace declarations, as already declared in <foo> -->
+ <bar xmlns="" xmlns:a="http://www.w3.org"; >&val;</bar >
+
+ <!-- empty element will be converted to start-end tag pair -->
+ <empty/>
+
+ <!-- text will be transcoded to UTF-8 -->
+ <transcode>1</transcode>
+
+ <!-- default attribute will be added -->
+ <!-- whitespace inside tag will be preserved -->
+ <whitespace> 321 </whitespace>
+
+ <!-- empty namespace will be removed of child tag -->
+ <emptyns xmlns="" >
+ <emptyns_child xmlns=""></emptyns_child>
+ </emptyns>
+
+ <!-- CDATA section will be replaced by its value -->
+ <compute><![CDATA[value>"0" && value<"10" ?"valid":"error"]]></compute>
+ </foo>
+ <!-- comment outside doc -->'::xml),
+ (2,'<foo>
+ <bar>
+ <!-- important comment -->
+ <val x="y">42</val>
+ </bar>
+ </foo> '::xml);
+SELECT xmlserialize(DOCUMENT doc AS text CANONICAL) FROM xmltest_serialize WHERE id = 1;
+ xmlserialize
+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+ <foo xmlns="http://example.org"; xmlns:a="http://www.w3.org"; xmlns:b="http://www.ietf.org"; attr="I am" attr2="all" b:attr="sorted" a:attr="out"><bar xmlns="">42</bar><empty></empty><transcode>1</transcode><whitespace> 321 </whitespace><emptyns xmlns=""><emptyns_child></emptyns_child></emptyns><compute>value>"0" && value<"10" ?"valid":"error"</compute></foo>
+(1 row)
+
+SELECT xmlserialize(DOCUMENT doc AS text CANONICAL WITH COMMENTS) FROM xmltest_serialize WHERE id = 2;
+ xmlserialize
+---------------------------------------------------------------------
+ <foo><bar><!-- important comment --><val x="y">42</val></bar></foo>
+(1 row)
+
+SELECT xmlserialize(DOCUMENT doc AS text CANONICAL) = xmlserialize(DOCUMENT doc AS text CANONICAL WITH NO COMMENTS) FROM xmltest_serialize;
+ ?column?
+----------
+ t
+ t
+(2 rows)
+
+SELECT xmlserialize(CONTENT doc AS text CANONICAL) FROM xmltest_serialize WHERE id = 1;
+ xmlserialize
+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+ <foo xmlns="http://example.org"; xmlns:a="http://www.w3.org"; xmlns:b="http://www.ietf.org"; attr="I am" attr2="all" b:attr="sorted" a:attr="out"><bar xmlns="">42</bar><empty></empty><transcode>1</transcode><whitespace> 321 </whitespace><emptyns xmlns=""><emptyns_child></emptyns_child></emptyns><compute>value>"0" && value<"10" ?"valid":"error"</compute></foo>
+(1 row)
+
+SELECT xmlserialize(CONTENT doc AS text CANONICAL WITH COMMENTS) FROM xmltest_serialize WHERE id = 2;
+ xmlserialize
+---------------------------------------------------------------------
+ <foo><bar><!-- important comment --><val x="y">42</val></bar></foo>
+(1 row)
+
+SELECT xmlserialize(CONTENT doc AS text CANONICAL) = xmlserialize(CONTENT doc AS text CANONICAL WITH NO COMMENTS) FROM xmltest_serialize;
+ ?column?
+----------
+ t
+ t
+(2 rows)
+
+SELECT xmlserialize(DOCUMENT NULL AS text CANONICAL);
+ xmlserialize
+--------------
+
+(1 row)
+
+SELECT xmlserialize(CONTENT NULL AS text CANONICAL);
+ xmlserialize
+--------------
+
+(1 row)
+
+\set VERBOSITY terse
+SELECT xmlserialize(DOCUMENT '' AS text CANONICAL);
+ERROR: not an XML document
+SELECT xmlserialize(DOCUMENT ' ' AS text CANONICAL);
+ERROR: not an XML document
+SELECT xmlserialize(DOCUMENT 'foo' AS text CANONICAL);
+ERROR: not an XML document
+SELECT xmlserialize(CONTENT '' AS text CANONICAL);
+ERROR: invalid XML document
+SELECT xmlserialize(CONTENT ' ' AS text CANONICAL);
+ERROR: invalid XML document
+SELECT xmlserialize(CONTENT 'foo' AS text CANONICAL);
+ERROR: invalid XML document
+\set VERBOSITY default
SELECT xml '<foo>bar</foo>' IS DOCUMENT;
?column?
----------
diff --git a/src/test/regress/expected/xml_1.out b/src/test/regress/expected/xml_1.out
index 70fe34a04f..cb372c39e2 100644
--- a/src/test/regress/expected/xml_1.out
+++ b/src/test/regress/expected/xml_1.out
@@ -309,6 +309,110 @@ ERROR: unsupported XML feature
LINE 1: SELECT xmlserialize(document 'bad' as text);
^
DETAIL: This functionality requires the server to be built with libxml support.
+-- xmlserialize: canonical
+CREATE TABLE xmltest_serialize (id int, doc xml);
+INSERT INTO xmltest_serialize VALUES
+ (1,'<?xml version="1.0" encoding="ISO-8859-1"?>
+ <!DOCTYPE doc SYSTEM "doc.dtd" [
+ <!ENTITY val "42">
+ <!ATTLIST xyz attr CDATA "default">
+ ]>
+
+ <!-- attributes and namespces will be sorted -->
+ <foo a:attr="out" b:attr="sorted" attr2="all" attr="I am"
+ xmlns:b="http://www.ietf.org";
+ xmlns:a="http://www.w3.org";
+ xmlns="http://example.org";>
+
+ <!-- Normalization of whitespace in start and end tags -->
+ <!-- Elimination of superfluous namespace declarations, as already declared in <foo> -->
+ <bar xmlns="" xmlns:a="http://www.w3.org"; >&val;</bar >
+
+ <!-- empty element will be converted to start-end tag pair -->
+ <empty/>
+
+ <!-- text will be transcoded to UTF-8 -->
+ <transcode>1</transcode>
+
+ <!-- default attribute will be added -->
+ <!-- whitespace inside tag will be preserved -->
+ <whitespace> 321 </whitespace>
+
+ <!-- empty namespace will be removed of child tag -->
+ <emptyns xmlns="" >
+ <emptyns_child xmlns=""></emptyns_child>
+ </emptyns>
+
+ <!-- CDATA section will be replaced by its value -->
+ <compute><![CDATA[value>"0" && value<"10" ?"valid":"error"]]></compute>
+ </foo>
+ <!-- comment outside doc -->'::xml),
+ (2,'<foo>
+ <bar>
+ <!-- important comment -->
+ <val x="y">42</val>
+ </bar>
+ </foo> '::xml);
+ERROR: unsupported XML feature
+LINE 2: (1,'<?xml version="1.0" encoding="ISO-8859-1"?>
+ ^
+DETAIL: This functionality requires the server to be built with libxml support.
+SELECT xmlserialize(DOCUMENT doc AS text CANONICAL) FROM xmltest_serialize WHERE id = 1;
+ xmlserialize
+--------------
+(0 rows)
+
+SELECT xmlserialize(DOCUMENT doc AS text CANONICAL WITH COMMENTS) FROM xmltest_serialize WHERE id = 2;
+ xmlserialize
+--------------
+(0 rows)
+
+SELECT xmlserialize(DOCUMENT doc AS text CANONICAL) = xmlserialize(DOCUMENT doc AS text CANONICAL WITH NO COMMENTS) FROM xmltest_serialize;
+ ?column?
+----------
+(0 rows)
+
+SELECT xmlserialize(CONTENT doc AS text CANONICAL) FROM xmltest_serialize WHERE id = 1;
+ xmlserialize
+--------------
+(0 rows)
+
+SELECT xmlserialize(CONTENT doc AS text CANONICAL WITH COMMENTS) FROM xmltest_serialize WHERE id = 2;
+ xmlserialize
+--------------
+(0 rows)
+
+SELECT xmlserialize(CONTENT doc AS text CANONICAL) = xmlserialize(CONTENT doc AS text CANONICAL WITH NO COMMENTS) FROM xmltest_serialize;
+ ?column?
+----------
+(0 rows)
+
+SELECT xmlserialize(DOCUMENT NULL AS text CANONICAL);
+ xmlserialize
+--------------
+
+(1 row)
+
+SELECT xmlserialize(CONTENT NULL AS text CANONICAL);
+ xmlserialize
+--------------
+
+(1 row)
+
+\set VERBOSITY terse
+SELECT xmlserialize(DOCUMENT '' AS text CANONICAL);
+ERROR: unsupported XML feature at character 30
+SELECT xmlserialize(DOCUMENT ' ' AS text CANONICAL);
+ERROR: unsupported XML feature at character 30
+SELECT xmlserialize(DOCUMENT 'foo' AS text CANONICAL);
+ERROR: unsupported XML feature at character 30
+SELECT xmlserialize(CONTENT '' AS text CANONICAL);
+ERROR: unsupported XML feature at character 29
+SELECT xmlserialize(CONTENT ' ' AS text CANONICAL);
+ERROR: unsupported XML feature at character 29
+SELECT xmlserialize(CONTENT 'foo' AS text CANONICAL);
+ERROR: unsupported XML feature at character 29
+\set VERBOSITY default
SELECT xml '<foo>bar</foo>' IS DOCUMENT;
ERROR: unsupported XML feature
LINE 1: SELECT xml '<foo>bar</foo>' IS DOCUMENT;
diff --git a/src/test/regress/expected/xml_2.out b/src/test/regress/expected/xml_2.out
index 4f029d0072..5a05aad34c 100644
--- a/src/test/regress/expected/xml_2.out
+++ b/src/test/regress/expected/xml_2.out
@@ -466,6 +466,114 @@ SELECT xmlserialize(content 'good' as char(10));
SELECT xmlserialize(document 'bad' as text);
ERROR: not an XML document
+-- xmlserialize: canonical
+CREATE TABLE xmltest_serialize (id int, doc xml);
+INSERT INTO xmltest_serialize VALUES
+ (1,'<?xml version="1.0" encoding="ISO-8859-1"?>
+ <!DOCTYPE doc SYSTEM "doc.dtd" [
+ <!ENTITY val "42">
+ <!ATTLIST xyz attr CDATA "default">
+ ]>
+
+ <!-- attributes and namespces will be sorted -->
+ <foo a:attr="out" b:attr="sorted" attr2="all" attr="I am"
+ xmlns:b="http://www.ietf.org";
+ xmlns:a="http://www.w3.org";
+ xmlns="http://example.org";>
+
+ <!-- Normalization of whitespace in start and end tags -->
+ <!-- Elimination of superfluous namespace declarations, as already declared in <foo> -->
+ <bar xmlns="" xmlns:a="http://www.w3.org"; >&val;</bar >
+
+ <!-- empty element will be converted to start-end tag pair -->
+ <empty/>
+
+ <!-- text will be transcoded to UTF-8 -->
+ <transcode>1</transcode>
+
+ <!-- default attribute will be added -->
+ <!-- whitespace inside tag will be preserved -->
+ <whitespace> 321 </whitespace>
+
+ <!-- empty namespace will be removed of child tag -->
+ <emptyns xmlns="" >
+ <emptyns_child xmlns=""></emptyns_child>
+ </emptyns>
+
+ <!-- CDATA section will be replaced by its value -->
+ <compute><![CDATA[value>"0" && value<"10" ?"valid":"error"]]></compute>
+ </foo>
+ <!-- comment outside doc -->'::xml),
+ (2,'<foo>
+ <bar>
+ <!-- important comment -->
+ <val x="y">42</val>
+ </bar>
+ </foo> '::xml);
+SELECT xmlserialize(DOCUMENT doc AS text CANONICAL) FROM xmltest_serialize WHERE id = 1;
+ xmlserialize
+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+ <foo xmlns="http://example.org"; xmlns:a="http://www.w3.org"; xmlns:b="http://www.ietf.org"; attr="I am" attr2="all" b:attr="sorted" a:attr="out"><bar xmlns="">42</bar><empty></empty><transcode>1</transcode><whitespace> 321 </whitespace><emptyns xmlns=""><emptyns_child></emptyns_child></emptyns><compute>value>"0" && value<"10" ?"valid":"error"</compute></foo>
+(1 row)
+
+SELECT xmlserialize(DOCUMENT doc AS text CANONICAL WITH COMMENTS) FROM xmltest_serialize WHERE id = 2;
+ xmlserialize
+---------------------------------------------------------------------
+ <foo><bar><!-- important comment --><val x="y">42</val></bar></foo>
+(1 row)
+
+SELECT xmlserialize(DOCUMENT doc AS text CANONICAL) = xmlserialize(DOCUMENT doc AS text CANONICAL WITH NO COMMENTS) FROM xmltest_serialize;
+ ?column?
+----------
+ t
+ t
+(2 rows)
+
+SELECT xmlserialize(CONTENT doc AS text CANONICAL) FROM xmltest_serialize WHERE id = 1;
+ xmlserialize
+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+ <foo xmlns="http://example.org"; xmlns:a="http://www.w3.org"; xmlns:b="http://www.ietf.org"; attr="I am" attr2="all" b:attr="sorted" a:attr="out"><bar xmlns="">42</bar><empty></empty><transcode>1</transcode><whitespace> 321 </whitespace><emptyns xmlns=""><emptyns_child></emptyns_child></emptyns><compute>value>"0" && value<"10" ?"valid":"error"</compute></foo>
+(1 row)
+
+SELECT xmlserialize(CONTENT doc AS text CANONICAL WITH COMMENTS) FROM xmltest_serialize WHERE id = 2;
+ xmlserialize
+---------------------------------------------------------------------
+ <foo><bar><!-- important comment --><val x="y">42</val></bar></foo>
+(1 row)
+
+SELECT xmlserialize(CONTENT doc AS text CANONICAL) = xmlserialize(CONTENT doc AS text CANONICAL WITH NO COMMENTS) FROM xmltest_serialize;
+ ?column?
+----------
+ t
+ t
+(2 rows)
+
+SELECT xmlserialize(DOCUMENT NULL AS text CANONICAL);
+ xmlserialize
+--------------
+
+(1 row)
+
+SELECT xmlserialize(CONTENT NULL AS text CANONICAL);
+ xmlserialize
+--------------
+
+(1 row)
+
+\set VERBOSITY terse
+SELECT xmlserialize(DOCUMENT '' AS text CANONICAL);
+ERROR: not an XML document
+SELECT xmlserialize(DOCUMENT ' ' AS text CANONICAL);
+ERROR: not an XML document
+SELECT xmlserialize(DOCUMENT 'foo' AS text CANONICAL);
+ERROR: not an XML document
+SELECT xmlserialize(CONTENT '' AS text CANONICAL);
+ERROR: invalid XML document
+SELECT xmlserialize(CONTENT ' ' AS text CANONICAL);
+ERROR: invalid XML document
+SELECT xmlserialize(CONTENT 'foo' AS text CANONICAL);
+ERROR: invalid XML document
+\set VERBOSITY default
SELECT xml '<foo>bar</foo>' IS DOCUMENT;
?column?
----------
diff --git a/src/test/regress/sql/xml.sql b/src/test/regress/sql/xml.sql
index 24e40d2653..90ede4b799 100644
--- a/src/test/regress/sql/xml.sql
+++ b/src/test/regress/sql/xml.sql
@@ -132,6 +132,67 @@ SELECT xmlserialize(content data as character varying(20)) FROM xmltest;
SELECT xmlserialize(content 'good' as char(10));
SELECT xmlserialize(document 'bad' as text);
+-- xmlserialize: canonical
+CREATE TABLE xmltest_serialize (id int, doc xml);
+INSERT INTO xmltest_serialize VALUES
+ (1,'<?xml version="1.0" encoding="ISO-8859-1"?>
+ <!DOCTYPE doc SYSTEM "doc.dtd" [
+ <!ENTITY val "42">
+ <!ATTLIST xyz attr CDATA "default">
+ ]>
+
+ <!-- attributes and namespces will be sorted -->
+ <foo a:attr="out" b:attr="sorted" attr2="all" attr="I am"
+ xmlns:b="http://www.ietf.org";
+ xmlns:a="http://www.w3.org";
+ xmlns="http://example.org";>
+
+ <!-- Normalization of whitespace in start and end tags -->
+ <!-- Elimination of superfluous namespace declarations, as already declared in <foo> -->
+ <bar xmlns="" xmlns:a="http://www.w3.org"; >&val;</bar >
+
+ <!-- empty element will be converted to start-end tag pair -->
+ <empty/>
+
+ <!-- text will be transcoded to UTF-8 -->
+ <transcode>1</transcode>
+
+ <!-- default attribute will be added -->
+ <!-- whitespace inside tag will be preserved -->
+ <whitespace> 321 </whitespace>
+
+ <!-- empty namespace will be removed of child tag -->
+ <emptyns xmlns="" >
+ <emptyns_child xmlns=""></emptyns_child>
+ </emptyns>
+
+ <!-- CDATA section will be replaced by its value -->
+ <compute><![CDATA[value>"0" && value<"10" ?"valid":"error"]]></compute>
+ </foo>
+ <!-- comment outside doc -->'::xml),
+ (2,'<foo>
+ <bar>
+ <!-- important comment -->
+ <val x="y">42</val>
+ </bar>
+ </foo> '::xml);
+
+SELECT xmlserialize(DOCUMENT doc AS text CANONICAL) FROM xmltest_serialize WHERE id = 1;
+SELECT xmlserialize(DOCUMENT doc AS text CANONICAL WITH COMMENTS) FROM xmltest_serialize WHERE id = 2;
+SELECT xmlserialize(DOCUMENT doc AS text CANONICAL) = xmlserialize(DOCUMENT doc AS text CANONICAL WITH NO COMMENTS) FROM xmltest_serialize;
+SELECT xmlserialize(CONTENT doc AS text CANONICAL) FROM xmltest_serialize WHERE id = 1;
+SELECT xmlserialize(CONTENT doc AS text CANONICAL WITH COMMENTS) FROM xmltest_serialize WHERE id = 2;
+SELECT xmlserialize(CONTENT doc AS text CANONICAL) = xmlserialize(CONTENT doc AS text CANONICAL WITH NO COMMENTS) FROM xmltest_serialize;
+SELECT xmlserialize(DOCUMENT NULL AS text CANONICAL);
+SELECT xmlserialize(CONTENT NULL AS text CANONICAL);
+\set VERBOSITY terse
+SELECT xmlserialize(DOCUMENT '' AS text CANONICAL);
+SELECT xmlserialize(DOCUMENT ' ' AS text CANONICAL);
+SELECT xmlserialize(DOCUMENT 'foo' AS text CANONICAL);
+SELECT xmlserialize(CONTENT '' AS text CANONICAL);
+SELECT xmlserialize(CONTENT ' ' AS text CANONICAL);
+SELECT xmlserialize(CONTENT 'foo' AS text CANONICAL);
+\set VERBOSITY default
SELECT xml '<foo>bar</foo>' IS DOCUMENT;
SELECT xml '<foo>bar</foo><bar>foo</bar>' IS DOCUMENT;
--
2.25.1
