SQL Server Requires Chilkat v11.7.0+

Extract PDF Text to a StringBuilder and Save to a File

See more PDF Text Extraction Examples

Demonstrates ExtractTextSb, which writes the extracted text to a StringBuilder instead of returning it as a JSON string. Use it for large documents. The JSON output still receives the quality report. SQL Server

--
CREATE PROCEDURE ChilkatSample
AS
BEGIN
    DECLARE @hr int
    DECLARE @iTmp0 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 long_report.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/long_report.pdf'
    IF @success = 0
      BEGIN
        EXEC sp_OAGetProperty @pdf, 'LastErrorText', @sTmp0 OUT
        PRINT @sTmp0
        EXEC @hr = sp_OADestroy @pdf
        RETURN
      END


    EXEC sp_OAGetProperty @pdf, 'NumPages', @iTmp0 OUT
    PRINT 'Number of pages: ' + @iTmp0

    --  ExtractTextSb takes the same operation and options as ExtractText, but the text
    --  goes to a StringBuilder.  This avoids building a very large JSON string for
    --  documents with many pages.
    DECLARE @json int
    EXEC @hr = sp_OACreate 'Chilkat.JsonObject', @json OUT

    DECLARE @sbText int
    EXEC @hr = sp_OACreate 'Chilkat.StringBuilder', @sbText OUT

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

    EXEC sp_OAMethod @pdf, 'ExtractTextSb', @success OUT, 'text', @json, @sbText, @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 @sbText
        EXEC @hr = sp_OADestroy @jsonOut
        RETURN
      END


    EXEC sp_OAGetProperty @sbText, 'Length', @iTmp0 OUT

    PRINT 'Extracted ' + @iTmp0 + ' characters.'

    --  Save the text to a file.
    EXEC sp_OAMethod @sbText, 'WriteFile', @success OUT, 'qa_output/long_report.txt', 'utf-8', 0
    IF @success = 0
      BEGIN
        EXEC sp_OAGetProperty @sbText, 'LastErrorText', @sTmp0 OUT
        PRINT @sTmp0
        EXEC @hr = sp_OADestroy @pdf
        EXEC @hr = sp_OADestroy @json
        EXEC @hr = sp_OADestroy @sbText
        EXEC @hr = sp_OADestroy @jsonOut
        RETURN
      END

    --  The JSON output does not contain the text, but it still has the quality report.

    EXEC sp_OAMethod @jsonOut, 'StringOf', @sTmp0 OUT, 'quality.rating'
    PRINT 'Quality: ' + @sTmp0

    EXEC sp_OAMethod @jsonOut, 'StringOf', @sTmp0 OUT, 'quality.pagesNeedingOcr'

    PRINT 'Pages with no text (need OCR): [' + @sTmp0 + ']'

    --  Sample output:

    --  Number of pages: 3
    --  Extracted 4522 characters.
    --  Quality: good
    --  Pages with no text (need OCR): []

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


END
GO