Tcl 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. 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 PDF used in this example is available at code_block.pdf

set pdf [new_CkPdf]

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

set json [new_CkJsonObject]

set jsonOut [new_CkJsonObject]

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

puts "---- default (code: true) ----"
puts [CkJsonObject_stringOf $jsonOut markdown]

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

puts "---- code: false ----"
puts [CkJsonObject_stringOf $jsonOut markdown]

#  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.

delete_CkPdf $pdf
delete_CkJsonObject $json
delete_CkJsonObject $jsonOut