Laboratoire ICAR » Plateforme TXM

package org.txm.macro.pdf

// STANDARD DECLARATIONS

import org.kohsuke.args4j.*

import groovy.transform.Field

import org.txm.rcp.swt.widget.parameters.*

import org.apache.pdfbox.Loader

import org.apache.pdfbox.rendering.PDFRenderer

import org.apache.pdfbox.tools.imageio.ImageIOUtil

import org.apache.pdfbox.rendering.ImageType

// BEGINNING OF PARAMETERS

@Field @Option(name="input_file", usage=".pdf input file", widget="File", required=false, def="")

def input_file

@Field @Option(name="input_dir", usage="The directory containing the .pdf files to read", widget="Folder", required=false, def="")

def input_dir

// Open the parameters input dialog box

if (!ParametersDialog.open(this)) return

// END OF PARAMETERS

if (input_dir != null &&  input_dir.exists()) {

	nFiles = 0

	input_dir.eachFileMatch(~/.*.pdf/) { f ->

		name = f.getName()

		idx = name.lastIndexOf(".")

		if (idx > 0) name = name.substring(0, idx)

		dir = f.getParentFile()

		println "Processing "+name+"..."

		pdfFile = f.getAbsolutePath()

		if (pdfFile.toUpperCase().endsWith(".PDF")) {

			textFile = pdfFile.substring(0, pdfFile.length() - 3) + "txt"

			try {

				doc = Loader.loadPDF(f)

				pdfRenderer = new PDFRenderer(doc)

				for (page = 0; page < doc.getNumberOfPages(); ++page) {

    					bim = pdfRenderer.renderImageWithDPI(page, 300, ImageType.RGB)

    					fos = new FileOutputStream(new File(dir, name + "-" + (page+1) + ".png"))

					ImageIOUtil.writeImage(bim, "png", fos, 300)

				}

				fos.close()

				doc.close()

				nFiles++

			} catch (Exception e) {

				e.printStackTrace()

			}

		}

	}

	println "Processed "+nFiles+" files."

} else {

	name = input_file.getName()

	dir = input_file.getParentFile()

	idx = name.lastIndexOf(".")

	if (idx > 0) name = name.substring(0, idx)

	pdfFile = input_file.getAbsolutePath()

	if (pdfFile.toUpperCase().endsWith(".PDF")) {

		textFile = pdfFile.substring(0, pdfFile.length() - 3) + "txt"

		try {

			doc = Loader.loadPDF(input_file)

			pdfRenderer = new PDFRenderer(doc)

			for (page = 0; page < doc.getNumberOfPages(); ++page) {

    				bim = pdfRenderer.renderImageWithDPI(page, 300, ImageType.RGB)

    				fos = new FileOutputStream(new File(dir, name + "-" + (page+1) + ".png"))

				ImageIOUtil.writeImage(bim, "png", fos, 300)

			}

			fos.close()

			doc.close()

		} catch (Exception e) {

			e.printStackTrace()

		}

	}

}

package org.txm.macro.pdf

// STANDARD DECLARATIONS

import org.kohsuke.args4j.*

import groovy.transform.Field

import org.txm.rcp.swt.widget.parameters.*

import org.apache.pdfbox.Loader

import org.apache.pdfbox.text.PDFTextStripper

// BEGINNING OF PARAMETERS

@Field @Option(name="input_file", usage=".pdf input file", widget="File", required=false, def="")

def input_file

@Field @Option(name="input_dir", usage="The directory containing the .pdf files to read", widget="Folder", required=false, def="")

def input_dir

// Open the parameters input dialog box

if (!ParametersDialog.open(this)) return

// END OF PARAMETERS

if (input_dir != null &&  input_dir.exists()) {

	nFiles = 0

	println "File\tAuthor\tTitle\tSubject\tCreator\tProducer\tCreation date\tModification date\tKeywords\tPages"

	input_dir.eachFileMatch(~/.*.pdf/) { f ->

		pdfFile = f.getAbsolutePath()

		if (pdfFile.toUpperCase().endsWith(".PDF")) {

			try {

				doc = Loader.loadPDF(f)

				pdd = doc.getDocumentInformation()

      				print "\t\""+ ((pdd.getAuthor()==null)?"":pdd.getAuthor())+"\""

      				print "\t\""+ ((pdd.getTitle()==null)?"":pdd.getTitle())+"\""

      				print "\t\""+ ((pdd.getSubject()==null)?"":pdd.getSubject())+"\""

      				print "\t\""+ ((pdd.getCreator()==null)?"":pdd.getCreator())+"\""

      				print "\t\""+ ((pdd.getProducer()==null)?"":pdd.getProducer())+"\""

      				print "\t"+ ((pdd.getCreationDate()==null)?"":pdd.getCreationDate().toZonedDateTime().toInstant())

      				print "\t"+ ((pdd.getModificationDate()==null)?"":pdd.getModificationDate().toZonedDateTime().toInstant())

      				print "\t\""+ ((pdd.getKeywords()==null)?"":pdd.getKeywords())+"\""

      				println "\t"+ doc.getNumberOfPages()

      				doc.close()

				nFiles++

			} catch (Exception e) {

			// e.printStackTrace()

			}

		}

	}

	println "Processed "+nFiles+" files."

} else {

	pdfFile = input_file.getAbsolutePath()

	if (pdfFile.toUpperCase().endsWith(".PDF")) {

		try {

			doc = Loader.loadPDF(input_file)

			pdd = doc.getDocumentInformation()

      			println "Author: "+((pdd.getAuthor()==null)?"":pdd.getAuthor())

      			println "Title: "+ ((pdd.getTitle()==null)?"":pdd.getTitle())

      			println "Subject: "+ ((pdd.getSubject()==null)?"":pdd.getSubject())

      			println "Creator: "+ ((pdd.getCreator()==null)?"":pdd.getCreator())

      			println "Producer: "+ ((pdd.getProducer()==null)?"":pdd.getProducer())

      			println "Creation date: "+ ((pdd.getCreationDate()==null)?"":pdd.getCreationDate().toZonedDateTime().toInstant())

      			println "Modification date: "+ ((pdd.getModificationDate()==null)?"":pdd.getModificationDate().toZonedDateTime().toInstant())

      			println "Keywords: "+ ((pdd.getKeywords()==null)?"":pdd.getKeywords())

      			println "Pages: "+ doc.getNumberOfPages()

			doc.close()

		} catch (Exception e) {

			// e.printStackTrace()

		}

	}

}

@Field @Option(name="input_file", usage=".pdf input file", widget="File", required=false, def="")

def input_file

def input_dir

// END OF PARAMETERS

if (input_dir != null &&  input_dir.exists()) {

	nFiles = 0

	input_dir.eachFileMatch(~/.*.pdf/) { f ->

		name = f.getName()

		println "Processing "+name+"..."

		outputFile = new File(f.getParentFile(), name + ".txt")

		pdfFile = f.getAbsolutePath()

				doc = Loader.loadPDF(f)

				strip = new PDFTextStripper()

				strip.setSortByPosition(true)

				strip.setPageStart("<pb/>")

				// strip.setParagraphStart("\n<p>")

				// strip.setParagraphEnd("</p>")

				writer.print strip.getText(doc)

				doc.close()

				writer.close()

				nFiles++

			e.printStackTrace()

	println "Processed "+nFiles+" files."

} else {

	name = input_file.getName()

	idx = name.lastIndexOf(".")

	if (idx > 0) name = name.substring(0, idx)

	outputFile = new File(input_file.getParentFile(), name + ".txt")

	pdfFile = input_file.getAbsolutePath()

	if (pdfFile.toUpperCase().endsWith(".PDF")) {

		textFile = pdfFile.substring(0, pdfFile.length() - 3) + "txt"

		try {

			outputFile.withWriter("UTF-8") { writer ->

			doc = Loader.loadPDF(input_file)

			strip = new PDFTextStripper()

			println "SpacingTolerance = "+strip.getSpacingTolerance()

			// Set the space width-based tolerance value that is used to estimate where spaces in text should be added. Note that the default value for this has been determined from trial and error. Setting this value larger will reduce the number of spaces added.

			println "AverageCharTolerance = "+strip.getAverageCharTolerance()

			// Set the character width-based tolerance value that is used to estimate where spaces in text should be added. Note that the default value for this has been determined from trial and error. Setting this value larger will reduce the number of spaces added.

			println "IndentThreshold = "+strip.getIndentThreshold()

			// sets the multiple of whitespace character widths for the current text which the current line start can be indented from the previous line start beyond which the current line start is considered to be a paragraph start. The default value is 2.0.

			println "DropThreshold = "+strip.getDropThreshold()

			// sets the minimum whitespace, as a multiple of the max height of the current characters beyond which the current line start is considered to be a paragraph start. The default value is 2.5.

			strip.setSortByPosition(true)

			strip.setPageStart("<pb/>")

			// strip.setParagraphStart("\n<p>")

			// strip.setParagraphEnd("</p>")

			writer.print strip.getText(doc)

			doc.close()

			writer.close()

			}

		} catch (Exception e) {

			e.printStackTrace()

		}

	}

}

// Copyright © 2022 MY_INSTITUTION

// Licensed under the terms of the GNU General Public License version 3 (http://www.gnu.org/licenses/gpl-3.0.html)

// @author mdecorde

// STANDARD DECLARATIONS

package org.txm.macro

import org.kohsuke.args4j.*

import groovy.transform.Field

import org.txm.rcp.swt.widget.parameters.*

import org.txm.Toolbox;

import org.txm.utils.io.FileCopy

import org.txm.rcp.views.fileexplorer.MacroExplorer

// BEGINNING OF PARAMETERS

@Field @Option(name="files", usage="an example file", widget="FilesOpen", metaVar="*.groovy;*.jar", required=true, def="")

def files

// Open the parameters input dialog box

if (!ParametersDialog.open(this)) return

// END OF PARAMETERS

File rootDir = new File(Toolbox.getTxmHomePath(), "scripts/groovy/")

for (File f : files) {

	if (!f.isFile()) continue;

	if (f.getName().endsWith(".jar")) {

		File f2 = new File(rootDir, "lib/"+f.getName())

		if (f2.exists()) {

			println "Updating library $f2"

			f2.delete()

		} else {

			println "New library: $f2"

		}

		FileCopy.copy(f, f2)

	} else if (f.getName().endsWith(".groovy")) {

		String ppackage = "org.txm.macro"

		def content = f.readLines("UTF-8")

		for (def line : content) {

			if (line.startsWith("package org.txm.macro")) {

				ppackage = line.substring(8)

				break

			}

		}

		File f2 = new File(rootDir, "user/"+ppackage.replace(".", "/")+ "/"+ f.getName())

		if (f2.exists()) {

			println "Update macro: $f2"

			f2.delete()

		} else {

			println "New macro: $f2"

		}

		f2.getParentFile().mkdirs()

		FileCopy.copy(f, f2)

	} else {

		println "Ignoring $f"

	}

}

// update macros view

monitor.syncExec(new Runnable() {

		public void run() {

			MacroExplorer.refresh();

		}

	});