From bccca780eef904002512a1a0b5ce617bcb63507b Mon Sep 17 00:00:00 2001 From: Tom Lane Date: Tue, 10 Sep 2024 16:20:31 -0400 Subject: [PATCH] Fix some whitespace issues in XMLSERIALIZE(... INDENT). 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 --- src/backend/utils/adt/xml.c | 27 ++++++++++++++++++++--- src/test/regress/expected/xml.out | 33 ++++++++++++++++++++--------- src/test/regress/expected/xml_1.out | 11 ++++++++++ src/test/regress/expected/xml_2.out | 33 ++++++++++++++++++++--------- src/test/regress/sql/xml.sql | 3 +++ 5 files changed, 84 insertions(+), 23 deletions(-) diff --git a/src/backend/utils/adt/xml.c b/src/backend/utils/adt/xml.c index 447e72b21e..1a07876cd5 100644 --- a/src/backend/utils/adt/xml.c +++ b/src/backend/utils/adt/xml.c @@ -677,8 +677,14 @@ xmltotext_with_options(xmltype *data, XmlOptionType xmloption_arg, bool indent) } #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) @@ -802,7 +808,22 @@ xmltotext_with_options(xmltype *data, XmlOptionType xmloption_arg, bool indent) "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(); { diff --git a/src/test/regress/expected/xml.out b/src/test/regress/expected/xml.out index 93a79cda8f..361a6f9b27 100644 --- a/src/test/regress/expected/xml.out +++ b/src/test/regress/expected/xml.out @@ -485,8 +485,7 @@ SELECT xmlserialize(DOCUMENT '42' AS text + 42+ + - + - + (1 row) SELECT xmlserialize(CONTENT '42' AS text INDENT); @@ -546,8 +545,7 @@ SELECT xmlserialize(DOCUMENT '42text node< 42 + text node73+ + - + - + (1 row) SELECT xmlserialize(CONTENT '42text node73' AS text INDENT); @@ -601,8 +599,7 @@ SELECT xmlserialize(DOCUMENT ' + 73 + + - + - + (1 row) SELECT xmlserialize(CONTENT '73' AS text INDENT); @@ -620,8 +617,7 @@ SELECT xmlserialize(DOCUMENT '' AS text INDENT); xmlserialize -------------- + - + - + (1 row) SELECT xmlserialize(CONTENT '' AS text INDENT); @@ -638,8 +634,7 @@ SELECT xmlserialize(DOCUMENT '' AS text INDENT); -------------- + + - + - + (1 row) SELECT xmlserialize(CONTENT '' AS text INDENT); @@ -663,6 +658,24 @@ SELECT xmlserialize(CONTENT '42' AS text t (1 row) +-- indent xml strings containing blank nodes +SELECT xmlserialize(DOCUMENT ' ' AS text INDENT); + xmlserialize +-------------- + + + + + +(1 row) + +SELECT xmlserialize(CONTENT 'text node ' AS text INDENT); + xmlserialize +-------------- + text node + + + + + + +(1 row) + SELECT xml 'bar' IS DOCUMENT; ?column? ---------- diff --git a/src/test/regress/expected/xml_1.out b/src/test/regress/expected/xml_1.out index 9323b84ae2..d26e10441e 100644 --- a/src/test/regress/expected/xml_1.out +++ b/src/test/regress/expected/xml_1.out @@ -443,6 +443,17 @@ ERROR: unsupported XML feature LINE 1: SELECT xmlserialize(CONTENT '42<... ^ DETAIL: This functionality requires the server to be built with libxml support. +-- indent xml strings containing blank nodes +SELECT xmlserialize(DOCUMENT ' ' AS text INDENT); +ERROR: unsupported XML feature +LINE 1: SELECT xmlserialize(DOCUMENT ' '... + ^ +DETAIL: This functionality requires the server to be built with libxml support. +SELECT xmlserialize(CONTENT 'text node ' AS text INDENT); +ERROR: unsupported XML feature +LINE 1: SELECT xmlserialize(CONTENT 'text node ... + ^ +DETAIL: This functionality requires the server to be built with libxml support. SELECT xml 'bar' IS DOCUMENT; ERROR: unsupported XML feature LINE 1: SELECT xml 'bar' IS DOCUMENT; diff --git a/src/test/regress/expected/xml_2.out b/src/test/regress/expected/xml_2.out index f956322c69..73c2851d3f 100644 --- a/src/test/regress/expected/xml_2.out +++ b/src/test/regress/expected/xml_2.out @@ -471,8 +471,7 @@ SELECT xmlserialize(DOCUMENT '42' AS text + 42+ + - + - + (1 row) SELECT xmlserialize(CONTENT '42' AS text INDENT); @@ -532,8 +531,7 @@ SELECT xmlserialize(DOCUMENT '42text node< 42 + text node73+ + - + - + (1 row) SELECT xmlserialize(CONTENT '42text node73' AS text INDENT); @@ -587,8 +585,7 @@ SELECT xmlserialize(DOCUMENT ' + 73 + + - + - + (1 row) SELECT xmlserialize(CONTENT '73' AS text INDENT); @@ -606,8 +603,7 @@ SELECT xmlserialize(DOCUMENT '' AS text INDENT); xmlserialize -------------- + - + - + (1 row) SELECT xmlserialize(CONTENT '' AS text INDENT); @@ -624,8 +620,7 @@ SELECT xmlserialize(DOCUMENT '' AS text INDENT); -------------- + + - + - + (1 row) SELECT xmlserialize(CONTENT '' AS text INDENT); @@ -649,6 +644,24 @@ SELECT xmlserialize(CONTENT '42' AS text t (1 row) +-- indent xml strings containing blank nodes +SELECT xmlserialize(DOCUMENT ' ' AS text INDENT); + xmlserialize +-------------- + + + + + +(1 row) + +SELECT xmlserialize(CONTENT 'text node ' AS text INDENT); + xmlserialize +-------------- + text node + + + + + + +(1 row) + SELECT xml 'bar' IS DOCUMENT; ?column? ---------- diff --git a/src/test/regress/sql/xml.sql b/src/test/regress/sql/xml.sql index 953bac09e4..f752ecb142 100644 --- a/src/test/regress/sql/xml.sql +++ b/src/test/regress/sql/xml.sql @@ -168,6 +168,9 @@ SELECT xmlserialize(CONTENT '' AS text INDENT); -- 'no indent' = not using 'no indent' SELECT xmlserialize(DOCUMENT '42' AS text) = xmlserialize(DOCUMENT '42' AS text NO INDENT); SELECT xmlserialize(CONTENT '42' AS text) = xmlserialize(CONTENT '42' AS text NO INDENT); +-- indent xml strings containing blank nodes +SELECT xmlserialize(DOCUMENT ' ' AS text INDENT); +SELECT xmlserialize(CONTENT 'text node ' AS text INDENT); SELECT xml 'bar' IS DOCUMENT; SELECT xml 'barfoo' IS DOCUMENT;