SQL Server Requires Chilkat v11.7.0+

Extract the Values of PDF Form Fields

See more PDF Text Extraction Examples

Demonstrates the "formFields" filter. The values of AcroForm fields (text fields, choices, check boxes) are not part of the page's text and are left out by default; "include" places each value at its field's position in the reading order, where a label capture can pick it up. SQL Server

--
CREATE PROCEDURE ChilkatSample
AS
BEGIN
    DECLARE @hr int
    DECLARE @sTmp0 nvarchar(4000)
    DECLARE @success int
    SELECT @success = 0

    --  This example requires the Chilkat API to have been previously unlocked.
    --  See Global Unlock Sample for sample code.

    --  The filled-in form used in this example is available at filled_form.pdf

    DECLARE @pdf int
    EXEC @hr = sp_OACreate 'Chilkat.Pdf', @pdf OUT
    IF @hr <> 0
    BEGIN
        PRINT 'Failed to create ActiveX component'
        RETURN
    END

    EXEC sp_OAMethod @pdf, 'LoadFile', @success OUT, 'qa_data/pdf/filled_form.pdf'
    IF @success = 0
      BEGIN
        EXEC sp_OAGetProperty @pdf, 'LastErrorText', @sTmp0 OUT
        PRINT @sTmp0
        EXEC @hr = sp_OADestroy @pdf
        RETURN
      END

    DECLARE @json int
    EXEC @hr = sp_OACreate 'Chilkat.JsonObject', @json OUT

    DECLARE @jsonOut int
    EXEC @hr = sp_OACreate 'Chilkat.JsonObject', @jsonOut OUT

    --  By default only the page's own text is returned: the captions, without the values typed into the fields.
    EXEC sp_OAMethod @json, 'UpdateString', @success OUT, 'layout', 'lines'
    EXEC sp_OAMethod @pdf, 'ExtractText', @success OUT, 'text', @json, @jsonOut
    IF @success = 0
      BEGIN
        EXEC sp_OAGetProperty @pdf, 'LastErrorText', @sTmp0 OUT
        PRINT @sTmp0
        EXEC @hr = sp_OADestroy @pdf
        EXEC @hr = sp_OADestroy @json
        EXEC @hr = sp_OADestroy @jsonOut
        RETURN
      END

    PRINT '---- default ----'
    EXEC sp_OAMethod @jsonOut, 'StringOf', @sTmp0 OUT, 'text'
    PRINT @sTmp0

    --  With formFields included, each field's value appears where the field is on the page.
    --  A checked check box appears as [x]; an unchecked one has no value.
    EXEC sp_OAMethod @json, 'UpdateString', @success OUT, 'formFields', 'include'
    EXEC sp_OAMethod @pdf, 'ExtractText', @success OUT, 'text', @json, @jsonOut
    IF @success = 0
      BEGIN
        EXEC sp_OAGetProperty @pdf, 'LastErrorText', @sTmp0 OUT
        PRINT @sTmp0
        EXEC @hr = sp_OADestroy @pdf
        EXEC @hr = sp_OADestroy @json
        EXEC @hr = sp_OADestroy @jsonOut
        RETURN
      END

    PRINT '---- formFields: include ----'
    EXEC sp_OAMethod @jsonOut, 'StringOf', @sTmp0 OUT, 'text'
    PRINT @sTmp0

    --  A field value can be captured by the caption beside it, as for any other text.
    EXEC sp_OAMethod @json, 'UpdateString', @success OUT, 'label', 'Email'
    EXEC sp_OAMethod @pdf, 'ExtractText', @success OUT, 'text', @json, @jsonOut
    IF @success = 0
      BEGIN
        EXEC sp_OAGetProperty @pdf, 'LastErrorText', @sTmp0 OUT
        PRINT @sTmp0
        EXEC @hr = sp_OADestroy @pdf
        EXEC @hr = sp_OADestroy @json
        EXEC @hr = sp_OADestroy @jsonOut
        RETURN
      END

    EXEC sp_OAMethod @jsonOut, 'StringOf', @sTmp0 OUT, 'text'
    PRINT 'Email: ' + @sTmp0

    --  Sample output:

    --  ---- default ----
    --  Membership Application
    --  Name:
    --  Email:
    --  Phone:
    --  Newsletter: Yes, send me the monthly newsletter
    --  Volunteer: I am willing to volunteer
    --  ---- formFields: include ----
    --  Membership Application
    --  Name: Dana Whitfield
    --  Email: dana.whitfield@example.com
    --  Phone: 555-0142
    --  Newsletter: [x] Yes, send me the monthly newsletter
    --  Volunteer: I am willing to volunteer
    --  Email: dana.whitfield@example.com

    EXEC @hr = sp_OADestroy @pdf
    EXEC @hr = sp_OADestroy @json
    EXEC @hr = sp_OADestroy @jsonOut


END
GO