Necromancing:For dem, der har brug for et fungerende eksempel:
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;
Eller med mindre støj
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)
;
Med dette eksempel på XML-fil (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>
Bemærk:
MyData.xml skal være i PG_Data-mappen (forælder-mappen til pg_stat-mappen).
f.eks. /var/lib/postgresql/9.3/main/MyData.xml
Dette kræver PostGreSQL 9.1+
Samlet set kan du opnå det filløst, sådan her:
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)
;
Bemærk, at i modsætning til i MS-SQL, returnerer xpath text() NULL på en NULL-værdi og ikke en tom streng.
Hvis du af en eller anden grund har brug for eksplicit at kontrollere eksistensen af NULL, kan du bruge [not(@xsi:nil="true")]
, som du skal sende en række navnerum til, for ellers får du en fejl (du kan dog udelade alle navnerum undtagen 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)
;
Du kan også kontrollere, om et felt er indeholdt i en XML-tekst, ved at gøre
,xmlexists('//xmlEncodeTest[1]' PASSING BY REF myTempTable.myXmlColumn) AS c1e
for eksempel når du sender en XML-værdi til en lagret procedure/funktion for CRUD.(se ovenfor)
Bemærk også, at den korrekte måde at sende en null-værdi i XML på er <elementName xsi:nil="true" />
og ikke <elementName />
eller ingenting. Der er ingen korrekt måde at sende NULL i attributter (du kan kun udelade attributten, men så bliver det svært/langsomt at udlede antallet af kolonner og deres navne i et stort datasæt).
for eksempel.
<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<table>
<row column1="a" column2="3" />
<row column1="b" column2="4" column3="true" />
</table>
(er mere kompakt, men meget dårligt, hvis du skal importere det, især hvis det er fra XML-filer med flere GB data - se et vidunderligt eksempel på det i stackoverflow-datadumpet)
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)