SQL Server Requires Chilkat v11.7.0+

Get the Text Block Below a PDF Caption

See more PDF Text Extraction Examples

Demonstrates the "label" option with labelValue "below", which captures the block of text directly under a caption such as "Ship To", ending at the next gap or heading. Combined with layout "lines", the lines of an address block are kept separate. 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 packing slip used in this example is available at packing_slip.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/packing_slip.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

    --  The packing slip has the captions "Bill To" and "Ship To" side by side,
    --  each with an address block below it.
    EXEC sp_OAMethod @json, 'UpdateString', @success OUT, 'label', 'Ship To'

    --  "below" means the value is the block of text directly under the label.
    EXEC sp_OAMethod @json, 'UpdateString', @success OUT, 'labelValue', 'below'

    --  With the default "flow" layout the lines of the block would be joined into one paragraph.
    --  "lines" keeps each line of the address on its own line.
    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 'Ship To:'
    EXEC sp_OAMethod @jsonOut, 'StringOf', @sTmp0 OUT, 'text'
    PRINT @sTmp0

    PRINT ''

    EXEC sp_OAMethod @json, 'UpdateString', @success OUT, 'label', 'Bill To'
    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 'Bill To:'
    EXEC sp_OAMethod @jsonOut, 'StringOf', @sTmp0 OUT, 'text'
    PRINT @sTmp0

    PRINT ''

    --  A caption over a short paragraph works the same way.  Here the flow layout is better,
    --  because the two lines are one piece of text.
    EXEC sp_OAMethod @json, 'UpdateString', @success OUT, 'label', 'Special Instructions'
    EXEC sp_OAMethod @json, 'UpdateString', @success OUT, 'layout', 'flow'
    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 'Special Instructions:'
    EXEC sp_OAMethod @jsonOut, 'StringOf', @sTmp0 OUT, 'text'
    PRINT @sTmp0

    --  Sample output:

    --  Ship To:
    --  Frank Delgado
    --  c/o Harbor Pet Boarding
    --  9 Ferry Lane
    --  Portside, WA 98001
    --  
    --  Bill To:
    --  Frank Delgado
    --  Apartment 3B
    --  41 Mill Street
    --  Portside, WA 98000
    --  
    --  Special Instructions:
    --  Leave the carton with the boarding office if no one answers. Do not leave it outside; the cat tree is not packed for rain.

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


END
GO