Get total number of lines in pdf text field using unipdf

pdf_form_text_field_total_line.go

package main

import (
	"fmt"
	"log"
	"os"

	"github.com/unidoc/unipdf/v3/common/license"
	"github.com/unidoc/unipdf/v3/contentstream"
	"github.com/unidoc/unipdf/v3/core"
	"github.com/unidoc/unipdf/v3/model"
)

func init() {
	// Make sure to load your metered License API key prior to using the library.
	// If you need a key, you can sign up and create a free one at https://cloud.unidoc.io
	err := license.SetMeteredKey(os.Getenv(`UNIDOC_LICENSE_API_KEY`))
	if err != nil {
		panic(err)
	}
}

func main() {
	inputPath := os.Args[1]

	f, err := os.Open(inputPath)
	if err != nil {
		log.Fatal(err)
	}
	defer f.Close()

	pdfReader, err := model.NewPdfReader(f)
	if err != nil {
		log.Fatal(err)
	}

	acroForm := pdfReader.AcroForm
	if acroForm == nil {
		log.Fatal(" No formdata present\n")
	}

	fields := acroForm.AllFields()

	for idx, field := range fields {
		fmt.Printf("=====\n")
		fmt.Printf("Field %d\n", idx+1)

		if !field.IsTerminal() {
			fmt.Printf("- Skipping over non-terminal field\n")
			continue
		}

		ctx := field.GetContext()
		switch t := ctx.(type) {
		case *model.PdfFieldText:
			processTextField(t)
		}
	}
}

func processTextField(textField *model.PdfFieldText) error {
	if str, ok := core.GetString(textField.V); ok {
		fmt.Printf(" - Decoded: '%s'\n", str.Decoded())
	}

	for _, wa := range textField.Annotations {
		if apDict, has := core.GetDict(wa.AP); has {
			n, has := core.GetStream(apDict.Get("N"))
			if has {
				decoded, err := core.DecodeStream(n)
				if err != nil {
					fmt.Printf("Decoding error: %v\n", err)
					return err
				}

				parser := contentstream.NewContentStreamParser(string(decoded))
				ops, err := parser.Parse()
				if err != nil {
					return err
				}

				line := 0
				for _, op := range *ops {
					if op.Operand == "Td" && op.Params[1].String() != "0" {
						line++
					}
				}

				fmt.Printf("- Total line: %d\n", line)
			}
		}
	}

	return nil
}