Perl Requires Chilkat v11.7.0+

Code Blocks and Code Spans in PDF to Markdown

See more PDF Text Extraction Examples

Demonstrates how monospaced text is converted by the "markdown" operation: a monospaced block becomes a fenced code block and a monospaced run inside a sentence becomes a code span. Set "code" to false to treat it as ordinary text. Perl

use chilkat();

$success = 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 code_block.pdf

$pdf = chilkat::CkPdf->new();
$success = $pdf->LoadFile("qa_data/pdf/code_block.pdf");
if ($success == 0) {
    print $pdf->lastErrorText() . "\r\n";
    exit;
}

$json = chilkat::CkJsonObject->new();
$jsonOut = chilkat::CkJsonObject->new();

$success = $pdf->ExtractText("markdown",$json,$jsonOut);
if ($success == 0) {
    print $pdf->lastErrorText() . "\r\n";
    exit;
}

print "---- default (code: true) ----" . "\r\n";
print $jsonOut->stringOf("markdown") . "\r\n";

$json->UpdateBool("code",0);
$success = $pdf->ExtractText("markdown",$json,$jsonOut);
if ($success == 0) {
    print $pdf->lastErrorText() . "\r\n";
    exit;
}

print "---- code: false ----" . "\r\n";
print $jsonOut->stringOf("markdown") . "\r\n";

#  Sample output:

#  ---- default (code: true) ----
#  <!-- page 1 -->
#  
#  # Extracting Text
#  
#  Load the PDF and call `ExtractText` with the operation and an options object. The result is returned as JSON:
#  
#  ```
#  new Pdf pdf;
#  success = pdf.LoadFile("report.pdf");
#  new JsonObject json;
#  new JsonObject jsonOut;
#  success = pdf.ExtractText("text",json,jsonOut);
#  println jsonOut.StringOf("text");
#  ```
#  
#  An empty options object extracts every page with the default clean-up. Set `pages` to limit the extraction.
#  ---- code: false ----
#  <!-- page 1 -->
#  
#  # Extracting Text
#  
#  Load the PDF and call ExtractText with the operation and an options object. The result is returned as JSON:
#  
#  new Pdf pdf; success = pdf.LoadFile("report.pdf"); new JsonObject json; new JsonObject jsonOut; success = pdf.ExtractText("text",json,jsonOut); println jsonOut.StringOf("text");
#  
#  An empty options object extracts every page with the default clean-up. Set pages to limit the extraction.