Nigromancia:Para aquellos que necesitan un ejemplo funcional:
DO $$
DECLARE myxml xml;
BEGIN
myxml := XMLPARSE(DOCUMENT convert_from(pg_read_binary_file('MyData.xml'), 'UTF8'));
DROP TABLE IF EXISTS mytable;
CREATE TEMP TABLE mytable AS
SELECT
(xpath('//ID/text()', x))[1]::text AS id
,(xpath('//Name/text()', x))[1]::text AS Name
,(xpath('//RFC/text()', x))[1]::text AS RFC
,(xpath('//Text/text()', x))[1]::text AS Text
,(xpath('//Desc/text()', x))[1]::text AS Desc
FROM unnest(xpath('//record', myxml)) x
;
END$$;
SELECT * FROM mytable;
O con menos ruido
SELECT
(xpath('//ID/text()', myTempTable.myXmlColumn))[1]::text AS id
,(xpath('//Name/text()', myTempTable.myXmlColumn))[1]::text AS Name
,(xpath('//RFC/text()', myTempTable.myXmlColumn))[1]::text AS RFC
,(xpath('//Text/text()', myTempTable.myXmlColumn))[1]::text AS Text
,(xpath('//Desc/text()', myTempTable.myXmlColumn))[1]::text AS Desc
,myTempTable.myXmlColumn as myXmlElement
FROM unnest(
xpath
( '//record'
,XMLPARSE(DOCUMENT convert_from(pg_read_binary_file('MyData.xml'), 'UTF8'))
)
) AS myTempTable(myXmlColumn)
;
Con este archivo XML de ejemplo (MyData.xml):
<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<data-set>
<record>
<ID>1</ID>
<Name>A</Name>
<RFC>RFC 1035[1]</RFC>
<Text>Address record</Text>
<Desc>Returns a 32-bit IPv4 address, most commonly used to map hostnames to an IP address of the host, but it is also used for DNSBLs, storing subnet masks in RFC 1101, etc.</Desc>
</record>
<record>
<ID>2</ID>
<Name>NS</Name>
<RFC>RFC 1035[1]</RFC>
<Text>Name server record</Text>
<Desc>Delegates a DNS zone to use the given authoritative name servers</Desc>
</record>
</data-set>
Nota:
MyData.xml debe estar en el directorio PG_Data (el directorio principal del directorio pg_stat).
por ejemplo, /var/lib/postgresql/9.3/main/MyData.xml
Esto requiere PostGreSQL 9.1+
En general, puede lograrlo sin archivos, así:
SELECT
(xpath('//ID/text()', myTempTable.myXmlColumn))[1]::text AS id
,(xpath('//Name/text()', myTempTable.myXmlColumn))[1]::text AS Name
,(xpath('//RFC/text()', myTempTable.myXmlColumn))[1]::text AS RFC
,(xpath('//Text/text()', myTempTable.myXmlColumn))[1]::text AS Text
,(xpath('//Desc/text()', myTempTable.myXmlColumn))[1]::text AS Desc
,myTempTable.myXmlColumn as myXmlElement
-- Source: https://en.wikipedia.org/wiki/List_of_DNS_record_types
FROM unnest(xpath('//record',
CAST('<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<data-set>
<record>
<ID>1</ID>
<Name>A</Name>
<RFC>RFC 1035[1]</RFC>
<Text>Address record</Text>
<Desc>Returns a 32-bit IPv4 address, most commonly used to map hostnames to an IP address of the host, but it is also used for DNSBLs, storing subnet masks in RFC 1101, etc.</Desc>
</record>
<record>
<ID>2</ID>
<Name>NS</Name>
<RFC>RFC 1035[1]</RFC>
<Text>Name server record</Text>
<Desc>Delegates a DNS zone to use the given authoritative name servers</Desc>
</record>
</data-set>
' AS xml)
)) AS myTempTable(myXmlColumn)
;
Tenga en cuenta que, a diferencia de MS-SQL, xpath text() devuelve NULL en un valor NULL y no una cadena vacía.
Si por alguna razón necesita verificar explícitamente la existencia de NULL, puede usar [not(@xsi:nil="true")]
, al que debe pasar una matriz de espacios de nombres, porque de lo contrario, obtendrá un error (sin embargo, puede omitir todos los espacios de nombres excepto xsi).
SELECT
(xpath('//xmlEncodeTest[1]/text()', myTempTable.myXmlColumn))[1]::text AS c1
,(
xpath('//xmlEncodeTest[1][not(@xsi:nil="true")]/text()', myTempTable.myXmlColumn
,
ARRAY[
-- ARRAY['xmlns','http://www.w3.org/1999/xhtml'], -- defaultns
ARRAY['xsi','http://www.w3.org/2001/XMLSchema-instance'],
ARRAY['xsd','http://www.w3.org/2001/XMLSchema'],
ARRAY['svg','http://www.w3.org/2000/svg'],
ARRAY['xsl','http://www.w3.org/1999/XSL/Transform']
]
)
)[1]::text AS c22
,(xpath('//nixda[1]/text()', myTempTable.myXmlColumn))[1]::text AS c2
--,myTempTable.myXmlColumn as myXmlElement
,xmlexists('//xmlEncodeTest[1]' PASSING BY REF myTempTable.myXmlColumn) AS c1e
,xmlexists('//nixda[1]' PASSING BY REF myTempTable.myXmlColumn) AS c2e
,xmlexists('//xmlEncodeTestAbc[1]' PASSING BY REF myTempTable.myXmlColumn) AS c1ea
FROM unnest(xpath('//row',
CAST('<?xml version="1.0" encoding="utf-8"?>
<table xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
<row>
<xmlEncodeTest xsi:nil="true" />
<nixda>noob</nixda>
</row>
</table>
' AS xml)
)
) AS myTempTable(myXmlColumn)
;
También puede verificar si un campo está contenido en un texto XML, haciendo
,xmlexists('//xmlEncodeTest[1]' PASSING BY REF myTempTable.myXmlColumn) AS c1e
por ejemplo, cuando pasa un valor XML a un procedimiento/función almacenados para CRUD (ver arriba)
Además, tenga en cuenta que la forma correcta de pasar un valor nulo en XML es <elementName xsi:nil="true" />
y no <elementName />
o nada. No hay una forma correcta de pasar NULL en los atributos (solo puede omitir el atributo, pero luego se vuelve difícil/lento inferir la cantidad de columnas y sus nombres en un conjunto de datos grande).
p.ej.
<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<table>
<row column1="a" column2="3" />
<row column1="b" column2="4" column3="true" />
</table>
(es más compacto, pero muy malo si necesita importarlo, especialmente si se trata de archivos XML con varios GB de datos; vea un maravilloso ejemplo de eso en el volcado de datos de stackoverflow)
SELECT
myTempTable.myXmlColumn
,(xpath('//@column1', myTempTable.myXmlColumn))[1]::text AS c1
,(xpath('//@column2', myTempTable.myXmlColumn))[1]::text AS c2
,(xpath('//@column3', myTempTable.myXmlColumn))[1]::text AS c3
,xmlexists('//@column3' PASSING BY REF myTempTable.myXmlColumn) AS c3e
,case when (xpath('//@column3', myTempTable.myXmlColumn))[1]::text is null then 1 else 0 end AS is_null
FROM unnest(xpath('//row', '<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<table>
<row column1="a" column2="3" />
<row column1="b" column2="4" column3="true" />
</table>'
)) AS myTempTable(myXmlColumn)