PureBasic 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). PureBasic

IncludeFile "CkPdf.pb"
IncludeFile "CkJsonObject.pb"

Procedure ChilkatExample()

    success.i = 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 order_records.pdf

    pdf.i = CkPdf::ckCreate()
    If pdf.i = 0
        Debug "Failed to create object."
        ProcedureReturn
    EndIf

    success = CkPdf::ckLoadFile(pdf,"qa_data/pdf/order_records.pdf")
    If success = 0
        Debug CkPdf::ckLastErrorText(pdf)
        CkPdf::ckDispose(pdf)
        ProcedureReturn
    EndIf

    json.i = CkJsonObject::ckCreate()
    If json.i = 0
        Debug "Failed to create object."
        ProcedureReturn
    EndIf

    jsonOut.i = CkJsonObject::ckCreate()
    If jsonOut.i = 0
        Debug "Failed to create object."
        ProcedureReturn
    EndIf

    ;  Find every order number.  With regex set to true, the query is a regular expression.
    CkJsonObject::ckUpdateString(json,"query","ORD-[0-9]{4}-[0-9]{4}")
    CkJsonObject::ckUpdateBool(json,"regex",1)
    ;  We only want the matched text, so no context is needed.
    CkJsonObject::ckUpdateInt(json,"context",0)

    success = CkPdf::ckExtractText(pdf,"search",json,jsonOut)
    If success = 0
        Debug CkPdf::ckLastErrorText(pdf)
        CkPdf::ckDispose(pdf)
        CkJsonObject::ckDispose(json)
        CkJsonObject::ckDispose(jsonOut)
        ProcedureReturn
    EndIf

    Debug "Order numbers found: " + Str(CkJsonObject::ckIntOf(jsonOut,"count"))
    i.i = 0
    count_i.i = CkJsonObject::ckSizeOfArray(jsonOut,"matches")
    While i < count_i
        CkJsonObject::setCkI(jsonOut, i)
        Debug CkJsonObject::ckStringOf(jsonOut,"matches[i].text")
        i = i + 1
    Wend

    ;  Find the e-mail addresses, but stop after the first three.
    CkJsonObject::ckUpdateString(json,"query","[a-z0-9._]+@[a-z]+[.][a-z]+")
    CkJsonObject::ckUpdateInt(json,"maxResults",3)
    success = CkPdf::ckExtractText(pdf,"search",json,jsonOut)
    If success = 0
        Debug CkPdf::ckLastErrorText(pdf)
        CkPdf::ckDispose(pdf)
        CkJsonObject::ckDispose(json)
        CkJsonObject::ckDispose(jsonOut)
        ProcedureReturn
    EndIf

    Debug "First three e-mail addresses:"
    i = 0
    count_i = CkJsonObject::ckSizeOfArray(jsonOut,"matches")
    While i < count_i
        CkJsonObject::setCkI(jsonOut, i)
        Debug CkJsonObject::ckStringOf(jsonOut,"matches[i].text")
        i = i + 1
    Wend

    ;  wholeWord: true matches only whole words.  The word "cat" appears once in the PDF,
    ;  but it is also inside "catalog" and "category".
    CkJsonObject::ckDelete(json,"maxResults")
    CkJsonObject::ckUpdateBool(json,"regex",0)
    CkJsonObject::ckUpdateString(json,"query","cat")
    success = CkPdf::ckExtractText(pdf,"search",json,jsonOut)
    If success = 0
        Debug CkPdf::ckLastErrorText(pdf)
        CkPdf::ckDispose(pdf)
        CkJsonObject::ckDispose(json)
        CkJsonObject::ckDispose(jsonOut)
        ProcedureReturn
    EndIf

    Debug "Occurrences of cat (any): " + Str(CkJsonObject::ckIntOf(jsonOut,"count"))

    CkJsonObject::ckUpdateBool(json,"wholeWord",1)
    success = CkPdf::ckExtractText(pdf,"search",json,jsonOut)
    If success = 0
        Debug CkPdf::ckLastErrorText(pdf)
        CkPdf::ckDispose(pdf)
        CkJsonObject::ckDispose(json)
        CkJsonObject::ckDispose(jsonOut)
        ProcedureReturn
    EndIf

    Debug "Occurrences of cat (whole word): " + Str(CkJsonObject::ckIntOf(jsonOut,"count"))

    ;  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


    CkPdf::ckDispose(pdf)
    CkJsonObject::ckDispose(json)
    CkJsonObject::ckDispose(jsonOut)


    ProcedureReturn
EndProcedure