B4X 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). B4X

Dim success As Boolean = False

'  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

Dim pdf As ChilkatPdf
pdf.Initialize("pdf")
success = pdf.LoadFile("qa_data/pdf/order_records.pdf")
If success = False Then
    Log(pdf.LastErrorText)
    Return
End If


Dim json As ChilkatJsonObject
json.Initialize
Dim jsonOut As ChilkatJsonObject
jsonOut.Initialize

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

success = pdf.ExtractText("search", json, jsonOut)
If success = False Then
    Log(pdf.LastErrorText)
    Return
End If


Log("Order numbers found: " & jsonOut.IntOf("count"))
Dim i As Int = 0
Dim count_i As Int = jsonOut.SizeOfArray("matches")
Do While i < count_i
    jsonOut.I = i
    Log(jsonOut.StringOf("matches[i].text"))
    i = i + 1
Loop

'  Find the e-mail addresses, but stop after the first three.
json.UpdateString("query", "[a-z0-9._]+@[a-z]+[.][a-z]+")
json.UpdateInt("maxResults", 3)
success = pdf.ExtractText("search", json, jsonOut)
If success = False Then
    Log(pdf.LastErrorText)
    Return
End If


Log("First three e-mail addresses:")
i = 0
count_i = jsonOut.SizeOfArray("matches")
Do While i < count_i
    jsonOut.I = i
    Log(jsonOut.StringOf("matches[i].text"))
    i = i + 1
Loop

'  wholeWord: true matches only whole words.  The word "cat" appears once in the PDF,
'  but it is also inside "catalog" and "category".
json.Delete("maxResults")
json.UpdateBool("regex", False)
json.UpdateString("query", "cat")
success = pdf.ExtractText("search", json, jsonOut)
If success = False Then
    Log(pdf.LastErrorText)
    Return
End If

Log("Occurrences of cat (any): " & jsonOut.IntOf("count"))

json.UpdateBool("wholeWord", True)
success = pdf.ExtractText("search", json, jsonOut)
If success = False Then
    Log(pdf.LastErrorText)
    Return
End If

Log("Occurrences of cat (whole word): " & jsonOut.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