SQL Server Requires Chilkat v11.7.0+

Rejoin Words Hyphenated at Line Ends

See more PDF Text Extraction Examples

Demonstrates the "dehyphenate" clean-up option (true by default). A word broken at the end of a line ("docu-" / "ment") is rejoined, while a hyphen that belongs to the word ("self-service") is kept. Set the option to false to keep the lines exactly as printed. 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 PDF used in this example is available at hyphenated.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/hyphenated.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 paragraph breaks "document", "self-service", "underlying" and "re-issued" at line ends.
    --  The default rejoins them.  "self-service" keeps its hyphen because the word appears with it,
    --  unbroken, elsewhere on the page; "re-issued" appears nowhere else, so it becomes "reissued".
    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 (dehyphenate: true) ----'
    EXEC sp_OAMethod @jsonOut, 'StringOf', @sTmp0 OUT, 'text'
    PRINT @sTmp0

    EXEC sp_OAMethod @json, 'UpdateBool', @success OUT, 'dehyphenate', 0
    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 '---- dehyphenate: false ----'
    EXEC sp_OAMethod @jsonOut, 'StringOf', @sTmp0 OUT, 'text'
    PRINT @sTmp0

    --  Sample output:

    --  ---- default (dehyphenate: true) ----
    --  Self-Service Kiosk Notes
    --  
    --  The new self-service kiosk in the lobby prints a visitor badge from the document number on the reservation. Staff should direct first-time visitors to the self-service kiosk rather than the desk, and should keep the paper tray topped up. The underlying software restarts itself overnight; a badge that fails to print is reissued at the desk on request.
    --  ---- dehyphenate: false ----
    --  Self-Service Kiosk Notes
    --  
    --  The new self-service kiosk in the lobby prints a visitor badge from the docu- ment number on the reservation. Staff should direct first-time visitors to the self- service kiosk rather than the desk, and should keep the paper tray topped up. The under- lying software restarts itself overnight; a badge that fails to print is re- issued at the desk on request.

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


END
GO