Added organize feature (#64)

* Added organize feature

* Added changes from suggestion

Suggestion: https://github.com/unidoc/unipdf-cli/pull/64/files#r1770322097

* Apply suggestions from code review

Co-authored-by: Ade Anom A <[email protected]>

* Applied suggestions from code review

- Comment: https://github.com/unidoc/unipdf-cli/pull/64/files/3898c2938786d339d44b7affb4becfddfc704452#r1770271470

---------

Co-authored-by: Ade Anom A <[email protected]>

internal/cli/organize.go

@@ -0,0 +1,75 @@
+/*
+ * This file is subject to the terms and conditions defined in
+ * file 'LICENSE.md', which is part of this source code package.
+ */
+
+package cli
+
+import (
+	"errors"
+	"fmt"
+
+	"github.com/spf13/cobra"
+	"github.com/unidoc/unipdf-cli/pkg/pdf"
+)
+
+const organizeCmdDesc = `Split PDF files.
+
+The command is used to organize one or more page ranges from the input file
+and save the result as the output file.
+If no page range is specified, all the pages from the input file will be
+copied to the output file.
+
+An example of the pages parameter: 1-3,4,6-7
+Only pages 1,2,3 (1-3), 4 and 6,7 (6-7) will be present in the output file,
+while page number 5 is skipped.
+`
+
+var organizeCmdExample = fmt.Sprintf("%s\n%s\n",
+	fmt.Sprintf("%s organize input_file.pdf output_file.pdf 1-2", appName),
+	fmt.Sprintf("%s organize -p pass input_file.pd output_file.pdf 1-2,4", appName),
+)
+
+// organizeCmd represents the split command.
+var organizeCmd = &cobra.Command{
+	Use:                   "organize [FLAG]... INPUT_FILE OUTPUT_FILE [PAGES]",
+	Short:                 "Organize PDF files",
+	Long:                  organizeCmdDesc,
+	Example:               organizeCmdExample,
+	DisableFlagsInUseLine: true,
+	Run: func(cmd *cobra.Command, args []string) {
+		inputPath := args[0]
+		outputPath := args[1]
+		password, _ := cmd.Flags().GetString("password")
+
+		// Parse page range.
+		var err error
+		var pages []int
+
+		if len(args) > 2 {
+			if pages, err = parsePageRangeUnsorted(args[2]); err != nil {
+				printUsageErr(cmd, "Invalid page range specified\n")
+			}
+		}
+
+		if err := pdf.Organize(inputPath, outputPath, password, pages); err != nil {
+			printErr("Error: %s\n", err)
+		}
+
+		fmt.Printf("Successfully organized file %s\n", inputPath)
+		fmt.Printf("Output file saved to %s\n", outputPath)
+	},
+	Args: func(_ *cobra.Command, args []string) error {
+		if len(args) < 2 {
+			return errors.New("must provide at least the input and output files")
+		}
+
+		return nil
+	},
+}
+
+func init() {
+	rootCmd.AddCommand(organizeCmd)
+
+	organizeCmd.Flags().StringP("password", "p", "", "input file password")
+}

internal/cli/utils.go

@@ -39,7 +39,6 @@ func parsePageRange(pageRange string) ([]int, error) {
 		}
 
 		indices := strings.Split(rng, "-")
-
 		lenIndices := len(indices)
 		if lenIndices > 2 {
 			return nil, errors.New("invalid page range")
@@ -86,6 +85,61 @@ func parsePageRange(pageRange string) ([]int, error) {
 	return pages, nil
 }
 
+func parsePageRangeUnsorted(pageRange string) ([]int, error) {
+	var pages []int
+
+	rngs := strings.Split(removeSpaces(pageRange), ",")
+	for _, rng := range rngs {
+		if rng == "" {
+			continue
+		}
+
+		indices := strings.Split(rng, "-")
+		lenIndices := len(indices)
+		if lenIndices > 2 {
+			return nil, errors.New("invalid page range")
+		}
+		if lenIndices == 2 {
+			start, err := strconv.Atoi(indices[0])
+			if err != nil {
+				return nil, errors.New("invalid start page number")
+			}
+			if start < 1 {
+				return nil, errors.New("page range start must be greater than 0")
+			}
+
+			end, err := strconv.Atoi(indices[1])
+			if err != nil {
+				return nil, errors.New("invalid end page number")
+			}
+			if end < 1 {
+				return nil, errors.New("page range end must be greater than 0")
+			}
+
+			if start > end {
+				return nil, errors.New("page range end must be greater than the start")
+			}
+
+			for page := start; page <= end; page++ {
+				pages = append(pages, page)
+			}
+
+			continue
+		}
+
+		page, err := strconv.Atoi(indices[0])
+		if err != nil {
+			return nil, errors.New("invalid page number")
+		}
+
+		pages = append(pages, page)
+	}
+
+	pages = uniqueIntSlice(pages)
+
+	return pages, nil
+}
+
 func parseInputPaths(inputPaths []string, recursive bool, matcher fileMatcher) ([]string, error) {
 	var err error
 	var files []string

pkg/pdf/organize.go

@@ -0,0 +1,152 @@
+/*
+ * This file is subject to the terms and conditions defined in
+ * file 'LICENSE.md', which is part of this source code package.
+ */
+
+package pdf
+
+import (
+	"github.com/unidoc/unipdf/v3/common"
+	unipdf "github.com/unidoc/unipdf/v3/model"
+)
+
+// Organize extracts the provided page list from PDF file specified by the
+// inputPath parameter then merges the individual pages and saves the
+// resulting file at the location specified by the outputPath parameter.
+// A password can be passed in for encrypted input files.
+func Organize(inputPath, outputPath, password string, pages []int) error {
+	// Read input file.
+	pdfReader, _, _, _, err := readPDF(inputPath, password)
+	if err != nil {
+		return err
+	}
+
+	// Add selected pages to the writer.
+	pdfWriter := unipdf.NewPdfWriter()
+
+	for i := 0; i < len(pages); i++ {
+		page, err := pdfReader.GetPage(pages[i])
+		if err != nil {
+			return err
+		}
+
+		err = pdfWriter.AddPage(page)
+		if err != nil {
+			return err
+		}
+	}
+
+	// Copy PDF version.
+	version := pdfReader.PdfVersion()
+	pdfWriter.SetVersion(version.Major, version.Minor)
+
+	// Copy PDF info.
+	info, err := pdfReader.GetPdfInfo()
+	if err != nil {
+		common.Log.Debug("ERROR: %v", err)
+	} else {
+		pdfWriter.SetDocInfo(info)
+	}
+
+	// Copy Catalog Metadata.
+	if meta, ok := pdfReader.GetCatalogMetadata(); ok {
+		if err := pdfWriter.SetCatalogMetadata(meta); err != nil {
+			return err
+		}
+	}
+
+	// Copy catalog mark information.
+	if markInfo, ok := pdfReader.GetCatalogMarkInfo(); ok {
+		if err := pdfWriter.SetCatalogMarkInfo(markInfo); err != nil {
+			return err
+		}
+	}
+
+	// Copy AcroForm.
+	err = pdfWriter.SetForms(pdfReader.AcroForm)
+	if err != nil {
+		common.Log.Debug("ERROR: %v", err)
+		return err
+	}
+
+	// Copy viewer preferences.
+	if pref, ok := pdfReader.GetCatalogViewerPreferences(); ok {
+		if err := pdfWriter.SetCatalogViewerPreferences(pref); err != nil {
+			return err
+		}
+	}
+
+	// Copy language preferences.
+	if lang, ok := pdfReader.GetCatalogLanguage(); ok {
+		if err := pdfWriter.SetCatalogLanguage(lang); err != nil {
+			return err
+		}
+	}
+
+	// Copy document outlines.
+	pdfWriter.AddOutlineTree(pdfReader.GetOutlineTree())
+
+	// Copy OC Properties.
+	props, err := pdfReader.GetOCProperties()
+	if err != nil {
+		common.Log.Debug("ERROR: %v", err)
+	} else {
+		err = pdfWriter.SetOCProperties(props)
+		if err != nil {
+			common.Log.Debug("ERROR: %v", err)
+		}
+	}
+
+	// Copy page labels.
+	labelObj, err := pdfReader.GetPageLabels()
+	if err != nil {
+		common.Log.Debug("ERROR: %v", err)
+	} else {
+		err = pdfWriter.SetPageLabels(labelObj)
+		if err != nil {
+			common.Log.Debug("ERROR: %v", err)
+		}
+	}
+
+	// Copy named destinations.
+	namedDest, err := pdfReader.GetNamedDestinations()
+	if err != nil {
+		common.Log.Debug("ERROR: %v", err)
+	} else {
+		err = pdfWriter.SetNamedDestinations(namedDest)
+		if err != nil {
+			common.Log.Debug("ERROR: %v", err)
+		}
+	}
+
+	// Copy name dictionary.
+	nameDict, err := pdfReader.GetNameDictionary()
+	if err != nil {
+		common.Log.Debug("ERROR: %v", err)
+	} else {
+		err = pdfWriter.SetNameDictionary(nameDict)
+		if err != nil {
+			common.Log.Debug("ERROR: %v", err)
+		}
+	}
+
+        // Copy StructTreeRoot dictionary.
+	structTreeRoot, found := pdfReader.GetCatalogStructTreeRoot()
+	if found {
+		err := pdfWriter.SetCatalogStructTreeRoot(structTreeRoot)
+		if err != nil {
+			common.Log.Debug("ERROR: %v", err)
+		}
+	}
+
+	// Copy global page rotation.
+	if pdfReader.Rotate != nil {
+		if err := pdfWriter.SetRotation(*pdfReader.Rotate); err != nil {
+			common.Log.Debug("ERROR: %v", err)
+		}
+	}
+
+	// Write output file.
+	safe := inputPath == outputPath
+	return writePDF(outputPath, &pdfWriter, safe)
+}