DataFlex Requires Chilkat v11.7.0+

Search a PDF with a Regular Expression

See more PDF Text Extraction Examples

Demonstrates searching a PDF with a regular expression (regex: true), limiting the number of results (maxResults), and matching whole words only (wholeWord). DataFlex

Use ChilkatAx-win32.pkg

Procedure Test
    Boolean iSuccess
    Handle hoPdf
    Variant vJson
    Handle hoJson
    Variant vJsonOut
    Handle hoJsonOut
    Integer i
    Integer iCount_i
    String sTemp1
    Integer iTemp1

    Move False To iSuccess

    //  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 order_records.pdf

    Get Create (RefClass(cComChilkatPdf)) To hoPdf
    If (Not(IsComObjectCreated(hoPdf))) Begin
        Send CreateComObject of hoPdf
    End
    Get ComLoadFile Of hoPdf "qa_data/pdf/order_records.pdf" To iSuccess
    If (iSuccess = False) Begin
        Get ComLastErrorText Of hoPdf To sTemp1
        Showln sTemp1
        Procedure_Return
    End

    Get Create (RefClass(cComChilkatJsonObject)) To hoJson
    If (Not(IsComObjectCreated(hoJson))) Begin
        Send CreateComObject of hoJson
    End
    Get Create (RefClass(cComChilkatJsonObject)) To hoJsonOut
    If (Not(IsComObjectCreated(hoJsonOut))) Begin
        Send CreateComObject of hoJsonOut
    End

    //  Find every order number.  With regex set to true, the query is a regular expression.
    Get ComUpdateString Of hoJson "query" "ORD-[0-9]{4}-[0-9]{4}" To iSuccess
    Get ComUpdateBool Of hoJson "regex" True To iSuccess
    //  We only want the matched text, so no context is needed.
    Get ComUpdateInt Of hoJson "context" 0 To iSuccess

    Get pvComObject of hoJson to vJson
    Get pvComObject of hoJsonOut to vJsonOut
    Get ComExtractText Of hoPdf "search" vJson vJsonOut To iSuccess
    If (iSuccess = False) Begin
        Get ComLastErrorText Of hoPdf To sTemp1
        Showln sTemp1
        Procedure_Return
    End

    Get ComIntOf Of hoJsonOut "count" To iTemp1
    Showln "Order numbers found: " iTemp1
    Move 0 To i
    Get ComSizeOfArray Of hoJsonOut "matches" To iCount_i
    While (i < iCount_i)
        Set ComI Of hoJsonOut To i
        Get ComStringOf Of hoJsonOut "matches[i].text" To sTemp1
        Showln sTemp1
        Move (i + 1) To i
    Loop

    //  Find the e-mail addresses, but stop after the first three.
    Get ComUpdateString Of hoJson "query" "[a-z0-9._]+@[a-z]+[.][a-z]+" To iSuccess
    Get ComUpdateInt Of hoJson "maxResults" 3 To iSuccess
    Get pvComObject of hoJson to vJson
    Get pvComObject of hoJsonOut to vJsonOut
    Get ComExtractText Of hoPdf "search" vJson vJsonOut To iSuccess
    If (iSuccess = False) Begin
        Get ComLastErrorText Of hoPdf To sTemp1
        Showln sTemp1
        Procedure_Return
    End

    Showln "First three e-mail addresses:"
    Move 0 To i
    Get ComSizeOfArray Of hoJsonOut "matches" To iCount_i
    While (i < iCount_i)
        Set ComI Of hoJsonOut To i
        Get ComStringOf Of hoJsonOut "matches[i].text" To sTemp1
        Showln sTemp1
        Move (i + 1) To i
    Loop

    //  wholeWord: true matches only whole words.  The word "cat" appears once in the PDF,
    //  but it is also inside "catalog" and "category".
    Get ComDelete Of hoJson "maxResults" To iSuccess
    Get ComUpdateBool Of hoJson "regex" False To iSuccess
    Get ComUpdateString Of hoJson "query" "cat" To iSuccess
    Get pvComObject of hoJson to vJson
    Get pvComObject of hoJsonOut to vJsonOut
    Get ComExtractText Of hoPdf "search" vJson vJsonOut To iSuccess
    If (iSuccess = False) Begin
        Get ComLastErrorText Of hoPdf To sTemp1
        Showln sTemp1
        Procedure_Return
    End

    Get ComIntOf Of hoJsonOut "count" To iTemp1
    Showln "Occurrences of cat (any): " iTemp1

    Get ComUpdateBool Of hoJson "wholeWord" True To iSuccess
    Get pvComObject of hoJson to vJson
    Get pvComObject of hoJsonOut to vJsonOut
    Get ComExtractText Of hoPdf "search" vJson vJsonOut To iSuccess
    If (iSuccess = False) Begin
        Get ComLastErrorText Of hoPdf To sTemp1
        Showln sTemp1
        Procedure_Return
    End

    Get ComIntOf Of hoJsonOut "count" To iTemp1
    Showln "Occurrences of cat (whole word): " iTemp1

    //  Sample output:

    //  Order numbers found: 9
    //  ORD-2026-0301
    //  ORD-2026-0302
    //  ORD-2026-0303
    //  ORD-2026-0304
    //  ORD-2026-0305
    //  ORD-2026-0306
    //  ORD-2026-0307
    //  ORD-2026-0308
    //  ORD-2026-0307
    //  First three e-mail addresses:
    //  alice.moore@example.com
    //  bkumar@example.org
    //  carla@example.net
    //  Occurrences of cat (any): 3
    //  Occurrences of cat (whole word): 1


End_Procedure