Last active
March 10, 2019 12:23
-
-
Save ezhov-da/e212de7dc017461e399fd38549762097 to your computer and use it in GitHub Desktop.
groovy pdf wpc
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
<pre> | |
apply plugin: 'idea' | |
compile group: 'org.apache.pdfbox', name: 'pdfbox', version: '2.0.6' | |
package ru.ezhov.groovy.pdf | |
import org.apache.pdfbox.pdmodel.PDDocument | |
import org.apache.pdfbox.text.PDFTextStripper | |
import org.apache.pdfbox.text.PDFTextStripperByArea | |
import java.util.regex.Matcher | |
import java.util.regex.Pattern | |
PDDocument document = | |
PDDocument.load(new File("E:/MDM/WPC_ScriptingReference_5320if2_03.pdf")) | |
if (!document.isEncrypted()) { | |
PDFTextStripperByArea stripper = new PDFTextStripperByArea() | |
stripper.setSortByPosition(true) | |
PDFTextStripper tStripper = new PDFTextStripper() | |
tStripper.setAddMoreFormatting(true) | |
String pdfFileInText = tStripper.getText(document) | |
String[] lines = pdfFileInText.split("\\r?\\n") | |
Pattern pattern = Pattern.compile("^\\d+") | |
StringBuilder stringBuilder = new StringBuilder() | |
for (String line : lines) { | |
Matcher matcher = pattern.matcher(line); | |
//Очищаем от мусора | |
if (!line.startsWith("WebSphere Product") && !matcher.find()) { | |
//добавляем отступы для некорневых элементов | |
String resultLine = "" | |
if (stringSet.contains(line)) { | |
resultLine = line | |
} else { | |
String[] linesTab = line.split("\\r\\n") | |
if (linesTab.length != 0) { | |
if (linesTab.length > 2) { | |
resultLine = resultLine + "\t" + linesTab[0] + "\n" | |
resultLine = resultLine + "\t\t" + linesTab[1] + "\n" | |
resultLine = resultLine + "\t" + linesTab[0]; | |
} else { | |
resultLine = resultLine + "\t" + linesTab[0] + "\n" | |
resultLine = resultLine + "\t\t" + linesTab[1] + "\n" | |
} | |
} | |
} | |
System.out.println(resultLine) | |
stringBuilder.append(resultLine) | |
stringBuilder.append("\n") | |
} | |
} | |
System.out.println(stringBuilder) | |
// try (FileWriter fileWriter = new FileWriter(new File("E:/script-tabbed.txt"));) { | |
// fileWriter.write(stringBuilder.toString()); | |
// } | |
} | |
</pre> |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment