Xbase++ 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). Xbase++

LOCAL nSuccess
LOCAL oPdf
LOCAL oJson
LOCAL oJsonOut
LOCAL i
LOCAL nCount_i

nSuccess := 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

oPdf := CreateObject("Chilkat.Pdf")
nSuccess := oPdf:LoadFile("qa_data/pdf/order_records.pdf")
IF (nSuccess == 0)
    ? oPdf:LastErrorText
    oPdf:destroy()
    RETURN
ENDIF

oJson := CreateObject("Chilkat.JsonObject")
oJsonOut := CreateObject("Chilkat.JsonObject")

//  Find every order number.  With regex set to true, the query is a regular expression.
oJson:UpdateString("query", "ORD-[0-9]{4}-[0-9]{4}")
oJson:UpdateBool("regex", 1)
//  We only want the matched text, so no context is needed.
oJson:UpdateInt("context", 0)

nSuccess := oPdf:ExtractText("search", oJson, oJsonOut)
IF (nSuccess == 0)
    ? oPdf:LastErrorText
    oPdf:destroy()
    oJson:destroy()
    oJsonOut:destroy()
    RETURN
ENDIF

? "Order numbers found: " + Str(oJsonOut:IntOf("count"))
i := 0
nCount_i := oJsonOut:SizeOfArray("matches")
DO WHILE i < nCount_i
    oJsonOut:I := i
    ? oJsonOut:StringOf("matches[i].text")
    i := i + 1
ENDDO

//  Find the e-mail addresses, but stop after the first three.
oJson:UpdateString("query", "[a-z0-9._]+@[a-z]+[.][a-z]+")
oJson:UpdateInt("maxResults", 3)
nSuccess := oPdf:ExtractText("search", oJson, oJsonOut)
IF (nSuccess == 0)
    ? oPdf:LastErrorText
    oPdf:destroy()
    oJson:destroy()
    oJsonOut:destroy()
    RETURN
ENDIF

? "First three e-mail addresses:"
i := 0
nCount_i := oJsonOut:SizeOfArray("matches")
DO WHILE i < nCount_i
    oJsonOut:I := i
    ? oJsonOut:StringOf("matches[i].text")
    i := i + 1
ENDDO

//  wholeWord: true matches only whole words.  The word "cat" appears once in the PDF,
//  but it is also inside "catalog" and "category".
oJson:Delete("maxResults")
oJson:UpdateBool("regex", 0)
oJson:UpdateString("query", "cat")
nSuccess := oPdf:ExtractText("search", oJson, oJsonOut)
IF (nSuccess == 0)
    ? oPdf:LastErrorText
    oPdf:destroy()
    oJson:destroy()
    oJsonOut:destroy()
    RETURN
ENDIF

? "Occurrences of cat (any): " + Str(oJsonOut:IntOf("count"))

oJson:UpdateBool("wholeWord", 1)
nSuccess := oPdf:ExtractText("search", oJson, oJsonOut)
IF (nSuccess == 0)
    ? oPdf:LastErrorText
    oPdf:destroy()
    oJson:destroy()
    oJsonOut:destroy()
    RETURN
ENDIF

? "Occurrences of cat (whole word): " + Str(oJsonOut:IntOf("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

oPdf:destroy()
oJson:destroy()
oJsonOut:destroy()