CODEWITHSUNDEEP
xmlxquerymarklogicxbrl
Mick Remmerswaal
Mick Remmerswaal

Reputation: 123

Enforcing XML contentType while uploading MarkLogic

While uploading files with a clear .xml extend via a http-server made. MarkLogic saves it in my local database as a .txt file.

This means I can't run my query's against it.

Uploader:

declare function local:uploadFile()
{
let $filename := xdmp:get-request-field-filename("upload")
let $file := xdmp:get-request-field("upload")
let $collection := "semansysdocs"

return
  xdmp:document-insert(
    $filename,
    $file,
    xdmp:default-permissions(),
    (xdmp:default-collections(), $collection)
  )
};

Example document(filename: Prod223_1982_03975172_20170430.xml):

<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="http://www.companieshouse.gov.uk/ef/xbrl/uk/fr/gaap/ae/2009-06-21/stylesheet/CH-AE-dormant-stylesheet.xsl"?>
<xbrl
    xmlns="http://www.xbrl.org/2003/instance"
    xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
    xmlns:ae="http://www.companieshouse.gov.uk/ef/xbrl/uk/fr/gaap/ae/2009-06-21"
    xmlns:gc="http://www.xbrl.org/uk/fr/gcd/2004-12-01"
    xmlns:html="http://www.w3.org/1999/xhtml"
    xmlns:iso4217="http://www.xbrl.org/2003/iso4217"
    xmlns:link="http://www.xbrl.org/2003/linkbase"
    xmlns:pt="http://www.xbrl.org/uk/fr/gaap/pt/2004-12-01"
    xmlns:xbrli="http://www.xbrl.org/2003/instance"
    xmlns:xlink="http://www.w3.org/1999/xlink">
    <link:schemaRef xlink:arcrole="http://www.w3.org/1999/xlink/properties/linkbase" 
xlink:href="http://www.companieshouse.gov.uk/ef/xbrl/uk/fr/gaap/ae/2009-06-21/uk-gaap-ae-2009-06-21.xsd" 
xlink:type="simple"/>
    <ae:CompanyDormant contextRef="y2017">true</ae:CompanyDormant>
    <gc:EntityNames>
        <gc:EntityCurrentLegalName contextRef="y2017">HUNTS GROUP PLC</gc:EntityCurrentLegalName>
    </gc:EntityNames>
    <ae:CompanyIdentifyingNumbers>
        <ae:CompaniesHouseRegisteredNumber contextRef="y2017">03975172</ae:CompaniesHouseRegisteredNumber>
    </ae:CompanyIdentifyingNumbers>
    <gc:StatementDatesPeriodsCovered>
        <gc:BalanceSheetDate contextRef="e2017">2017-04-30</gc:BalanceSheetDate>
    </gc:StatementDatesPeriodsCovered>
    <pt:ShareholderFunds precision="6" contextRef="e2017" unitRef="GBP">12500</pt:ShareholderFunds>
    <pt:ShareholderFunds precision="6" contextRef="e2016" unitRef="GBP">12500</pt:ShareholderFunds>
    <pt:NetAssetsLiabilitiesIncludingPensionAssetLiability precision="5" contextRef="e2017" unitRef="GBP">12500</pt:NetAssetsLiabilitiesIncludingPensionAssetLiability>
    <pt:NetAssetsLiabilitiesIncludingPensionAssetLiability precision="5" contextRef="e2016" unitRef="GBP">12500</pt:NetAssetsLiabilitiesIncludingPensionAssetLiability>
    <pt:CashBankInHand precision="5" contextRef="e2017" unitRef="GBP">12500</pt:CashBankInHand>
    <pt:CashBankInHand precision="5" contextRef="e2016" unitRef="GBP">12500</pt:CashBankInHand>
    <pt:EquityAuthorisedDetails>
        <pt:TypeOrdinaryShare contextRef="y2017">Ordinary</pt:TypeOrdinaryShare>
        <pt:NumberOrdinarySharesAuthorised precision="INF" contextRef="e2017" unitRef="shares">50000</pt:NumberOrdinarySharesAuthorised>
        <pt:ParValueOrdinaryShare precision="INF" contextRef="y2017" unitRef="GBP">1</pt:ParValueOrdinaryShare>
    </pt:EquityAuthorisedDetails>
    <pt:DetailsOrdinarySharesAllotted>
        <pt:TypeOrdinaryShare contextRef="y2017">Ordinary</pt:TypeOrdinaryShare>
        <pt:ParValueOrdinaryShare precision="INF" contextRef="y2017" unitRef="GBP">1</pt:ParValueOrdinaryShare>
        <pt:ValueOrdinarySharesAllotted precision="5" contextRef="e2017" unitRef="GBP">12500</pt:ValueOrdinarySharesAllotted>
        <pt:ValueOrdinarySharesAllotted precision="5" contextRef="e2016" unitRef="GBP">12500</pt:ValueOrdinarySharesAllotted>
        <pt:NumberOrdinarySharesAllotted precision="INF" contextRef="e2017" unitRef="shares">12500</pt:NumberOrdinarySharesAllotted>
    </pt:DetailsOrdinarySharesAllotted>
    <pt:DateApproval contextRef="e2017">2017-10-13</pt:DateApproval>
    <pt:ApprovalDetails>
        <pt:NameApprovingDirector contextRef="y2017">Mr. David Charles Hunt</pt:NameApprovingDirector>
    </pt:ApprovalDetails>
    <ae:CompanyEntitledToExemptionUnderSection480CompaniesAct2006 contextRef="y2017">true</ae:CompanyEntitledToExemptionUnderSection480CompaniesAct2006>
    <ae:MembersHaveNotRequiredCompanyToObtainAnAudit contextRef="y2017">true</ae:MembersHaveNotRequiredCompanyToObtainAnAudit>
    <ae:DirectorsAcknowledgeTheirResponsibilitiesUnderCompaniesAct contextRef="y2017">true</ae:DirectorsAcknowledgeTheirResponsibilitiesUnderCompaniesAct>
    <ae:AccountsAreInAccordanceWithSpecialProvisionsCompaniesActRelatingToSmallCompanies contextRef="y2017">true</ae:AccountsAreInAccordanceWithSpecialProvisionsCompaniesActRelatingToSmallCompanies>
    <unit id="shares">
        <measure>xbrli:shares</measure>
    </unit>
    <unit id="GBP">
        <measure>iso4217:GBP</measure>
    </unit>
    <unit id="pure">
        <measure>xbrli:pure</measure>
    </unit>
    <context id="y2017">
        <entity>
            <identifier scheme="/results">HUNTS GROUP PLC</identifier>
        </entity>
        <period>
            <startDate>2016-05-01</startDate>
            <endDate>2017-04-30</endDate>
        </period>
    </context>
    <context id="y2016">
        <entity>
            <identifier scheme="/results">HUNTS GROUP PLC</identifier>
        </entity>
        <period>
            <startDate>2015-05-01</startDate>
            <endDate>2016-04-30</endDate>
        </period>
    </context>
    <context id="s2016">
        <entity>
            <identifier scheme="/results">HUNTS GROUP PLC</identifier>
        </entity>
        <period>
            <instant>2015-04-30</instant>
        </period>
    </context>
    <context id="e2016">
        <entity>
            <identifier scheme="/results">HUNTS GROUP PLC</identifier>
        </entity>
        <period>
            <instant>2016-04-30</instant>
        </period>
    </context>
    <context id="s2017">
        <entity>
            <identifier scheme="/results">HUNTS GROUP PLC</identifier>
        </entity>
        <period>
            <instant>2016-04-30</instant>
        </period>
    </context>
    <context id="e2017">
        <entity>
            <identifier scheme="/results">HUNTS GROUP PLC</identifier>
        </entity>
        <period>
            <instant>2017-04-30</instant>
        </period>
    </context>
    <ae:CompaniesHouseDocumentAuthentication contextRef="y2017"></ae:CompaniesHouseDocumentAuthentication>
    <ae:DateAccountsReceived contextRef="e2017">2017-10-16</ae:DateAccountsReceived>
</xbrl>

As you can see, is this a XBRL document, which is roughly XML+. I can't specify the contentType within the xdmp:document-insert(), you guys any idea how to enforce a XML contentType?

Upvotes: 2

Views: 88

Answers (2)

Emil Zegers
Emil Zegers

Reputation: 82

When using code below, some known content types / file extensions will be ingested as you would expect:

let $file := xdmp:get-request-field("upload")
let $filename := xdmp:get-request-field-filename("upload")
let $contenttype := xdmp:get-request-field-content-type("upload")
let $extension := fn:replace($filename, '.*\.', '')
let $insert := switch ($contenttype)
    case "text/xml"
    case "text/xhtml"
    case "text/csv"
    case "text/plain"
    case "application/json"
        return xdmp:document-insert($filename,xdmp:unquote($file))
    case "application/octet-stream"
        return switch ($extension)
        case "gpx"
            return xdmp:document-insert($filename,xdmp:unquote(xdmp:quote(binary{xs:hexBinary($file)})))
        default
            return xdmp:document-insert($filename,$file)
    default
        return xdmp:document-insert($filename,$file)
return fn:concat("file '",$filename,"' uploaded, contenttype: ",$contenttype," extension: ",$extension)

Result of uploading various file formats

Upvotes: 4

David Ennis -CleverLlamas.com
David Ennis -CleverLlamas.com

Reputation: 7770

Before inserting it, you need to parse it back into XML (it was text coming over the wire, I guess). This is done with xdmp:unquote()

....
let $file := xdmp:unquote(xdmp:get-request-field("upload"))
....

Please note that the above is simplified. You may need to set other options based on your need - see the docs for details.

Separate from that - you state the the document is .txt .. I assume that you mean it is a text node. MarkLogic will not add any .txt to the name of a file in the URI. If you see that, then that is what is being sent in the request field.

Upvotes: 4

Related Questions