Tcl Requires Chilkat v11.7.0+

Search for Text in a PDF

See more PDF Text Extraction Examples

Demonstrates the "search" operation, which finds every occurrence of a string in a PDF and returns each match with its page number and the text around it. Matching ignores case unless caseSensitive is true. Tcl

load ./chilkat.dll

set success 0

#  This example requires the Chilkat API to have been previously unlocked.
#  See Global Unlock Sample for sample code.

#  The three-page PDF used in this example is available at search_context.pdf

set pdf [new_CkPdf]

set success [CkPdf_LoadFile $pdf "qa_data/pdf/search_context.pdf"]
if {$success == 0} then {
    puts [CkPdf_lastErrorText $pdf]
    delete_CkPdf $pdf
    exit
}

set json [new_CkJsonObject]

set jsonOut [new_CkJsonObject]

#  The string to find.
CkJsonObject_UpdateString $json "query" "chilkat"

#  The number of characters returned before and after each match.  The default is 40.
CkJsonObject_UpdateInt $json "context" 30

set success [CkPdf_ExtractText $pdf "search" $json $jsonOut]
if {$success == 0} then {
    puts [CkPdf_lastErrorText $pdf]
    delete_CkPdf $pdf
    delete_CkJsonObject $json
    delete_CkJsonObject $jsonOut
    exit
}

#  "count" is the number of matches.  Each match has the page, the matched text as it appears
#  in the PDF, and the text before and after it.
puts "Matches: [CkJsonObject_IntOf $jsonOut count]"

set i 0
set count_i [CkJsonObject_SizeOfArray $jsonOut "matches"]
while {$i < $count_i} {
    CkJsonObject_put_I $jsonOut $i
    puts "page [CkJsonObject_IntOf $jsonOut {matches[i].page}]: ...[CkJsonObject_stringOf $jsonOut {matches[i].before}]{[}[CkJsonObject_stringOf $jsonOut {matches[i].text}]][CkJsonObject_stringOf $jsonOut {matches[i].after}]..."
    set i [expr $i + 1]
}

#  The search ignores case by default.  Set caseSensitive to find only the exact spelling.
CkJsonObject_UpdateBool $json "caseSensitive" 1
CkJsonObject_UpdateString $json "query" "Chilkat"
set success [CkPdf_ExtractText $pdf "search" $json $jsonOut]
if {$success == 0} then {
    puts [CkPdf_lastErrorText $pdf]
    delete_CkPdf $pdf
    delete_CkJsonObject $json
    delete_CkJsonObject $jsonOut
    exit
}

puts "Case-sensitive matches for Chilkat: [CkJsonObject_IntOf $jsonOut count]"

#  Sample output:

#  Matches: 5
#  page 1: ...[Chilkat] River Field Notes The Chilkat...
#  page 1: ...Chilkat River Field Notes The [Chilkat] River runs for about fifty mi...
#  page 2: ...DAY ONE: UPPER [CHILKAT] FLATS Clear and cold, minus e...
#  page 2: ...he river is sometimes spelled [chilkat] in older records, and the val...
#  page 3: ...y because the fish run on the [Chilkat] was thinning. Two tagged bird...
#  Case-sensitive matches for Chilkat: 3

delete_CkPdf $pdf
delete_CkJsonObject $json
delete_CkJsonObject $jsonOut