SQL Server Requires Chilkat v11.7.0+

Assess PDF Text Quality Before Extracting

See more PDF Text Extraction Examples

Demonstrates the "assess" operation, which returns only the quality report: whether the text can be trusted, which pages are scanned images that need OCR, and how each page's text was found. Use it to triage documents before extracting. (Chilkat does not perform OCR.) SQL Server

--
CREATE PROCEDURE ChilkatSample
AS
BEGIN
    DECLARE @hr int
    DECLARE @iTmp0 int
    DECLARE @sTmp0 nvarchar(4000)
    DECLARE @sTmp1 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 (page 2 is a scanned image with no text) is available at mixed_text_image.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/mixed_text_image.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

    --  "assess" computes the quality report without producing any text.
    --  It is fast, and it is always allowed, even for an encrypted PDF that forbids copying.
    EXEC sp_OAMethod @pdf, 'ExtractText', @success OUT, 'assess', @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

    --  The overall rating is the worst rating among the pages that have text:
    --  "good", "fair", "poor", or "none" when there is no text at all.

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

    --  Is the PDF tagged (does it have a structure tree)?

    EXEC sp_OAMethod @jsonOut, 'BoolOf', @iTmp0 OUT, 'quality.tagged'
    PRINT 'Tagged: ' + @iTmp0

    --  The pages that are images only and would need OCR, such as "2" or "4,9".

    EXEC sp_OAMethod @jsonOut, 'StringOf', @sTmp0 OUT, 'quality.pagesNeedingOcr'
    PRINT 'Pages needing OCR: ' + @sTmp0

    --  The per-page report.
    DECLARE @j int

    DECLARE @count_j int

    DECLARE @i int
    SELECT @i = 0
    DECLARE @count_i int
    EXEC sp_OAMethod @jsonOut, 'SizeOfArray', @count_i OUT, 'quality.pages'
    WHILE @i < @count_i
      BEGIN
        EXEC sp_OASetProperty @jsonOut, 'I', @i
        --  textSource is "text" (real text), "ocrLayer" (invisible text over an image),
        --  "imageOnly" (needs OCR), "mixed", or "empty".

        EXEC sp_OAMethod @jsonOut, 'IntOf', @iTmp0 OUT, 'quality.pages[i].page'

        EXEC sp_OAMethod @jsonOut, 'StringOf', @sTmp0 OUT, 'quality.pages[i].rating'

        EXEC sp_OAMethod @jsonOut, 'StringOf', @sTmp1 OUT, 'quality.pages[i].textSource'
        PRINT 'Page ' + @iTmp0 + ': rating ' + @sTmp0 + ', textSource ' + @sTmp1
        --  Each issue has a machine-readable code and a sentence.
        SELECT @j = 0
        EXEC sp_OAMethod @jsonOut, 'SizeOfArray', @count_j OUT, 'quality.pages[i].issues'
        WHILE @j < @count_j
          BEGIN
            EXEC sp_OASetProperty @jsonOut, 'J', @j

            EXEC sp_OAMethod @jsonOut, 'StringOf', @sTmp0 OUT, 'quality.pages[i].issues[j].code'

            EXEC sp_OAMethod @jsonOut, 'StringOf', @sTmp1 OUT, 'quality.pages[i].issues[j].message'
            PRINT '    ' + @sTmp0 + ': ' + @sTmp1
            SELECT @j = @j + 1
          END
        SELECT @i = @i + 1
      END

    --  Decide what to do with the document:
    EXEC sp_OAMethod @jsonOut, 'StringOf', @sTmp0 OUT, 'quality.rating'
    IF @sTmp0 = 'none'
      BEGIN

        PRINT 'No extractable text; the whole document needs OCR.'
      END
    ELSE
      BEGIN
        EXEC sp_OAMethod @jsonOut, 'StringOf', @sTmp0 OUT, 'quality.pagesNeedingOcr'
        IF @sTmp0 <> ''
          BEGIN

            PRINT 'Some pages need OCR; the remaining pages can be extracted with the text or markdown operation.'
          END
        ELSE
          BEGIN

            PRINT 'All pages can be extracted.'
          END
      END

    --  Sample output:

    --  Rating: good
    --  Tagged: false
    --  Pages needing OCR: 2
    --  Page 1: rating good, textSource text
    --  Page 2: rating none, textSource imageOnly
    --      imageOnly: No text; page is a scanned image
    --  Page 3: rating good, textSource text
    --  Some pages need OCR; the remaining pages can be extracted with the text or markdown operation.

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


END
GO