We must drop whitespace while parsing the input, else libxml2
will include "blank" nodes that interfere with the desired
indentation behavior. The end result is that we didn't indent
nodes separated by whitespace.
Also, it seems that libxml2 may add a trailing newline when working
in DOCUMENT mode. This is semantically insignificant, so strip it.
This is in the gray area between being a bug fix and a definition
change. However, the INDENT option is still pretty new (since v16),
so I think we can get away with changing this in stable branches.
Hence, back-patch to v16.
Jim Jones
Discussion: https://postgr.es/m/
872865a8-548b-48e1-bfcd-
4e38e672c1e4@uni-muenster.de
}
#ifdef USE_LIBXML
- /* Parse the input according to the xmloption */
- doc = xml_parse(data, xmloption_arg, true, GetDatabaseEncoding(),
+
+ /*
+ * Parse the input according to the xmloption.
+ *
+ * preserve_whitespace is set to false in case we are indenting, otherwise
+ * libxml2 will fail to indent elements that have whitespace between them.
+ */
+ doc = xml_parse(data, xmloption_arg, !indent, GetDatabaseEncoding(),
&parsed_xmloptiontype, &content_nodes,
(Node *) &escontext);
if (doc == NULL || escontext.error_occurred)
"could not close xmlSaveCtxtPtr");
}
- result = (text *) xmlBuffer_to_xmltype(buf);
+ /*
+ * xmlDocContentDumpOutput may add a trailing newline, so remove that.
+ */
+ if (xmloption_arg == XMLOPTION_DOCUMENT)
+ {
+ const char *str = (const char *) xmlBufferContent(buf);
+ int len = xmlBufferLength(buf);
+
+ while (len > 0 && (str[len - 1] == '\n' ||
+ str[len - 1] == '\r'))
+ len--;
+
+ result = cstring_to_text_with_len(str, len);
+ }
+ else
+ result = (text *) xmlBuffer_to_xmltype(buf);
}
PG_CATCH();
{
<bar> +
<val x="y">42</val>+
</bar> +
- </foo> +
-
+ </foo>
(1 row)
SELECT xmlserialize(CONTENT '<foo><bar><val x="y">42</val></bar></foo>' AS text INDENT);
<val x="y">42</val> +
<val x="y">text node<val>73</val></val>+
</bar> +
- </foo> +
-
+ </foo>
(1 row)
SELECT xmlserialize(CONTENT '<foo><bar><val x="y">42</val><val x="y">text node<val>73</val></val></bar></foo>' AS text INDENT);
<bar> +
<val>73</val> +
</bar> +
- </foo> +
-
+ </foo>
(1 row)
SELECT xmlserialize(CONTENT '<?xml version="1.0" encoding="UTF-8"?><foo><bar><val>73</val></bar></foo>' AS text INDENT);
xmlserialize
--------------
<!DOCTYPE a>+
- <a/> +
-
+ <a/>
(1 row)
SELECT xmlserialize(CONTENT '<!DOCTYPE a><a/>' AS text INDENT);
--------------
<foo> +
<bar/> +
- </foo> +
-
+ </foo>
(1 row)
SELECT xmlserialize(CONTENT '<foo><bar></bar></foo>' AS text INDENT);
t
(1 row)
+-- indent xml strings containing blank nodes
+SELECT xmlserialize(DOCUMENT '<foo> <bar></bar> </foo>' AS text INDENT);
+ xmlserialize
+--------------
+ <foo> +
+ <bar/> +
+ </foo>
+(1 row)
+
+SELECT xmlserialize(CONTENT 'text node<foo> <bar></bar> </foo>' AS text INDENT);
+ xmlserialize
+--------------
+ text node +
+ <foo> +
+ <bar/> +
+ </foo>
+(1 row)
+
SELECT xml '<foo>bar</foo>' IS DOCUMENT;
?column?
----------
LINE 1: SELECT xmlserialize(CONTENT '<foo><bar><val x="y">42</val><...
^
DETAIL: This functionality requires the server to be built with libxml support.
+-- indent xml strings containing blank nodes
+SELECT xmlserialize(DOCUMENT '<foo> <bar></bar> </foo>' AS text INDENT);
+ERROR: unsupported XML feature
+LINE 1: SELECT xmlserialize(DOCUMENT '<foo> <bar></bar> </foo>'...
+ ^
+DETAIL: This functionality requires the server to be built with libxml support.
+SELECT xmlserialize(CONTENT 'text node<foo> <bar></bar> </foo>' AS text INDENT);
+ERROR: unsupported XML feature
+LINE 1: SELECT xmlserialize(CONTENT 'text node<foo> <bar></bar> ...
+ ^
+DETAIL: This functionality requires the server to be built with libxml support.
SELECT xml '<foo>bar</foo>' IS DOCUMENT;
ERROR: unsupported XML feature
LINE 1: SELECT xml '<foo>bar</foo>' IS DOCUMENT;
<bar> +
<val x="y">42</val>+
</bar> +
- </foo> +
-
+ </foo>
(1 row)
SELECT xmlserialize(CONTENT '<foo><bar><val x="y">42</val></bar></foo>' AS text INDENT);
<val x="y">42</val> +
<val x="y">text node<val>73</val></val>+
</bar> +
- </foo> +
-
+ </foo>
(1 row)
SELECT xmlserialize(CONTENT '<foo><bar><val x="y">42</val><val x="y">text node<val>73</val></val></bar></foo>' AS text INDENT);
<bar> +
<val>73</val> +
</bar> +
- </foo> +
-
+ </foo>
(1 row)
SELECT xmlserialize(CONTENT '<?xml version="1.0" encoding="UTF-8"?><foo><bar><val>73</val></bar></foo>' AS text INDENT);
xmlserialize
--------------
<!DOCTYPE a>+
- <a/> +
-
+ <a/>
(1 row)
SELECT xmlserialize(CONTENT '<!DOCTYPE a><a/>' AS text INDENT);
--------------
<foo> +
<bar/> +
- </foo> +
-
+ </foo>
(1 row)
SELECT xmlserialize(CONTENT '<foo><bar></bar></foo>' AS text INDENT);
t
(1 row)
+-- indent xml strings containing blank nodes
+SELECT xmlserialize(DOCUMENT '<foo> <bar></bar> </foo>' AS text INDENT);
+ xmlserialize
+--------------
+ <foo> +
+ <bar/> +
+ </foo>
+(1 row)
+
+SELECT xmlserialize(CONTENT 'text node<foo> <bar></bar> </foo>' AS text INDENT);
+ xmlserialize
+--------------
+ text node +
+ <foo> +
+ <bar/> +
+ </foo>
+(1 row)
+
SELECT xml '<foo>bar</foo>' IS DOCUMENT;
?column?
----------
-- 'no indent' = not using 'no indent'
SELECT xmlserialize(DOCUMENT '<foo><bar><val x="y">42</val></bar></foo>' AS text) = xmlserialize(DOCUMENT '<foo><bar><val x="y">42</val></bar></foo>' AS text NO INDENT);
SELECT xmlserialize(CONTENT '<foo><bar><val x="y">42</val></bar></foo>' AS text) = xmlserialize(CONTENT '<foo><bar><val x="y">42</val></bar></foo>' AS text NO INDENT);
+-- indent xml strings containing blank nodes
+SELECT xmlserialize(DOCUMENT '<foo> <bar></bar> </foo>' AS text INDENT);
+SELECT xmlserialize(CONTENT 'text node<foo> <bar></bar> </foo>' AS text INDENT);
SELECT xml '<foo>bar</foo>' IS DOCUMENT;
SELECT xml '<foo>bar</foo><bar>foo</bar>' IS DOCUMENT;
projects / postgresql.git / commitdiff