Ruby 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). Ruby

require 'chilkat'

success = 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

pdf = Chilkat::CkPdf.new()
success = pdf.LoadFile("qa_data/pdf/order_records.pdf")
if (success == false)
    print pdf.lastErrorText() + "\n";
    exit
end

json = Chilkat::CkJsonObject.new()
jsonOut = Chilkat::CkJsonObject.new()

#  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)
    print pdf.lastErrorText() + "\n";
    exit
end

print "Order numbers found: " + jsonOut.IntOf("count").to_s() + "\n";
i = 0
count_i = jsonOut.SizeOfArray("matches")
while i < count_i
    jsonOut.put_I(i)
    print jsonOut.stringOf("matches[i].text") + "\n";
    i = i + 1
end

#  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)
    print pdf.lastErrorText() + "\n";
    exit
end

print "First three e-mail addresses:" + "\n";
i = 0
count_i = jsonOut.SizeOfArray("matches")
while i < count_i
    jsonOut.put_I(i)
    print jsonOut.stringOf("matches[i].text") + "\n";
    i = i + 1
end

#  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)
    print pdf.lastErrorText() + "\n";
    exit
end

print "Occurrences of cat (any): " + jsonOut.IntOf("count").to_s() + "\n";

json.UpdateBool("wholeWord",true)
success = pdf.ExtractText("search",json,jsonOut)
if (success == false)
    print pdf.lastErrorText() + "\n";
    exit
end

print "Occurrences of cat (whole word): " + jsonOut.IntOf("count").to_s() + "\n";

#  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