diff --git a/gemeinsamforschen/pom.xml b/gemeinsamforschen/pom.xml
index 15a482c2f3fe879d70afb4e03b123ba13f601305..718c97172441539e8dc78d185ffae66c786afbca 100644
--- a/gemeinsamforschen/pom.xml
+++ b/gemeinsamforschen/pom.xml
@@ -301,6 +301,15 @@
<artifactId>poi-scratchpad</artifactId>
<version>3.15</version>
</dependency>
+ <dependency>
+ <groupId>net.sourceforge.htmlcleaner</groupId>
+ <artifactId>htmlcleaner</artifactId>
+ <version>2.22</version>
+ </dependency>
+ <dependency>
+ <groupId>org.jsoup</groupId>
+ <artifactId>jsoup</artifactId>
+ <version>1.12.1</version>
+ </dependency>
</dependencies>
-
</project>
\ No newline at end of file
diff --git a/gemeinsamforschen/selenium/Automatisierungen.side b/gemeinsamforschen/selenium/Automatisierungen.side
index 345ecc514ff79dfd3df4d37092996b9f3a5cf39b..f2161821af0a36c91982782d2608606da51081c8 100644
--- a/gemeinsamforschen/selenium/Automatisierungen.side
+++ b/gemeinsamforschen/selenium/Automatisierungen.side
@@ -13,13 +13,6 @@
"target": "http://localhost:8080/gemeinsamforschen_war_exploded/",
"targets": [],
"value": ""
- }, {
- "id": "4cdd2c67-b330-4ebf-9dad-06784ae81bbe",
- "comment": "",
- "command": "setWindowSize",
- "target": "1024x768",
- "targets": [],
- "value": ""
}, {
"id": "e8ca50ce-88c8-4882-8051-b122be32fdc0",
"comment": "",
diff --git a/gemeinsamforschen/src/main/java/unipotsdam/gf/modules/fileManagement/FileManagementService.java b/gemeinsamforschen/src/main/java/unipotsdam/gf/modules/fileManagement/FileManagementService.java
index 736ba575680f8ce2c328fe0030c3858f03c87c9e..7d26a9a38a1b8052d808a46cab45f72a08994286 100644
--- a/gemeinsamforschen/src/main/java/unipotsdam/gf/modules/fileManagement/FileManagementService.java
+++ b/gemeinsamforschen/src/main/java/unipotsdam/gf/modules/fileManagement/FileManagementService.java
@@ -7,13 +7,18 @@ import com.itextpdf.text.pdf.PdfPCell;
import com.itextpdf.text.pdf.PdfPTable;
import com.itextpdf.text.pdf.PdfWriter;
import com.itextpdf.tool.xml.XMLWorkerHelper;
-import com.itextpdf.tool.xml.exceptions.CssResolverException;
import org.apache.commons.io.IOUtils;
import org.apache.poi.openxml4j.opc.OPCPackage;
import org.apache.poi.xslf.usermodel.XMLSlideShow;
import org.apache.poi.xslf.usermodel.XSLFSlide;
import org.codehaus.plexus.util.FileUtils;
import org.glassfish.jersey.media.multipart.FormDataContentDisposition;
+import org.htmlcleaner.HtmlCleaner;
+import org.htmlcleaner.HtmlSerializer;
+import org.htmlcleaner.SimpleHtmlSerializer;
+import org.htmlcleaner.TagNode;
+import org.jsoup.Jsoup;
+import org.jsoup.select.Elements;
import unipotsdam.gf.modules.project.Project;
import unipotsdam.gf.modules.user.User;
@@ -75,7 +80,8 @@ public class FileManagementService {
public void saveStringAsPDF(User user, Project project, String fileContent, FormDataContentDisposition fileDetail,
FileRole fileRole, FileType fileType) throws IOException, DocumentException {
- fileContent = correctingTags(fileContent);
+ fileContent = cleanHTML(fileContent);
+ //fileContent = manipulateIndentation(fileContent);
InputStream inputStream = IOUtils.toInputStream(fileContent);
saveFileAsPDF(user, project, inputStream, fileDetail, fileRole, fileType);
@@ -84,28 +90,7 @@ public class FileManagementService {
private String saveHTMLAsPDF(InputStream inputStream, String filenameWithoutExtension) throws IOException, DocumentException {
String fileName = filenameWithoutExtension + ".pdf";
String path = getFullPath(fileName);
- /*
- Document document = new Document();
-
-
- PdfWriter writer = PdfWriter.getInstance(document, new FileOutputStream(filename));
- document.open();
- TODO: css is not applied correctly, that's why an indent, doesn't work, need fix
- example:
- HTML PDF
- 1. 1.
- 2. 2.
- a. 3.
-
- CSSResolver cssResolver = XMLWorkerHelper.getInstance().getDefaultCssResolver(false);
- cssResolver.addCssFile("https://cdnjs.cloudflare.com/ajax/libs/quill/1.3.6/quill.snow.css", true);
- HtmlPipelineContext htmlContext = new HtmlPipelineContext(null);
- CssResolverPipeline pipeline = new CssResolverPipeline(cssResolver, new HtmlPipeline(htmlContext, new PdfWriterPipeline(document, writer)));
- XMLWorker worker = new XMLWorker(pipeline, true);
- XMLParser parser = new XMLParser(worker);
- parser.parse(inputStream);
- */
Document document = new Document();
PdfWriter writer = PdfWriter.getInstance(document, new FileOutputStream(path));
document.open();
@@ -114,11 +99,30 @@ public class FileManagementService {
return fileName;
}
- private String correctingTags(String fileContent) {
- String correctedFileContent = fileContent.replaceAll("<br>", "<br/>");
- correctedFileContent = correctedFileContent.replaceAll("\">", "\"/>");
- return correctedFileContent;
+ private String cleanHTML(String fileContent) {
+ HtmlCleaner htmlCleaner = new HtmlCleaner();
+ TagNode tagNode = htmlCleaner.clean(fileContent);
+ HtmlSerializer htmlSerializer = new SimpleHtmlSerializer(htmlCleaner.getProperties());
+ return htmlSerializer.getAsString(tagNode);
+ }
+ String manipulateIndentation(String fileContent) {
+ /*
+ todo:
+ implementation hier
+ -------------------
+ - wenn text zurueckkommt, dann TextNode erzeugen, die text von vorheriger node beinhaltet, aber davor jeweilige aufzaehlungszeichen hinzufuegt
+ - am ende alle <ol> und </ol> loeschen (wenn noetig)
+ */
+ org.jsoup.nodes.Document document = Jsoup.parse(fileContent);
+
+ Elements elements = document.select("ol");
+ elements.forEach(element -> {
+ JsoupConverter converter = new JsoupConverter();
+ String fullText = converter.convertElementsToTextNodes(element.childNodes());
+ element.text(fullText);
+ });
+ return fileContent;
}
private String getDocumentFromFile(InputStream inputStream, String fileNameWithoutExtension) throws IOException {
diff --git a/gemeinsamforschen/src/main/java/unipotsdam/gf/modules/fileManagement/JsoupConverter.java b/gemeinsamforschen/src/main/java/unipotsdam/gf/modules/fileManagement/JsoupConverter.java
new file mode 100644
index 0000000000000000000000000000000000000000..e9ba3a2e7466dda6b222cb70d908d44b30c5cbc3
--- /dev/null
+++ b/gemeinsamforschen/src/main/java/unipotsdam/gf/modules/fileManagement/JsoupConverter.java
@@ -0,0 +1,166 @@
+package unipotsdam.gf.modules.fileManagement;
+
+import org.jsoup.nodes.Element;
+import org.jsoup.nodes.Node;
+import org.jsoup.nodes.TextNode;
+import unipotsdam.gf.modules.fileManagement.Util.IndentationLetterFormat;
+import unipotsdam.gf.modules.fileManagement.Util.RomanConverter;
+
+import java.util.Arrays;
+import java.util.HashMap;
+import java.util.List;
+import java.util.Objects;
+import java.util.stream.Collectors;
+
+import static unipotsdam.gf.modules.fileManagement.Util.IndentationLetterFormat.LETTER;
+import static unipotsdam.gf.modules.fileManagement.Util.IndentationLetterFormat.NUMBER;
+import static unipotsdam.gf.modules.fileManagement.Util.IndentationLetterFormat.ROMAN;
+
+public class JsoupConverter {
+
+ private HashMap<Integer, String> nextIndentationLetterMap;
+ private int lastSeenIndentationLevel = 0;
+
+ public JsoupConverter() {
+ nextIndentationLetterMap = new HashMap<>();
+ nextIndentationLetterMap.put(0, "1");
+ nextIndentationLetterMap.put(1, "a");
+ nextIndentationLetterMap.put(2, "1");
+ nextIndentationLetterMap.put(3, "1");
+ nextIndentationLetterMap.put(4, "a");
+ nextIndentationLetterMap.put(5, "1");
+ nextIndentationLetterMap.put(6, "1");
+ nextIndentationLetterMap.put(7, "a");
+ nextIndentationLetterMap.put(8, "1");
+ }
+
+
+ public String convertElementsToTextNodes(List<Node> nodes) {
+ String fullText = "";
+ for (Node node : nodes) {
+ if (!(node instanceof Element)) {
+ continue;
+ }
+ int indentationLevel = extractIndentationLevel(node);
+ String indentationText;
+
+ IndentationLetterFormat letterFormat = getTextFormat(indentationLevel);
+ if (Objects.isNull(letterFormat)) {
+ continue;
+ }
+ // TODO:
+ // 1. indentation for roman is not reseted correctly
+ // 2. everything is encoded, so \t and \n are cut off. Also < is encoded, so <br> is not possible
+ // to fix this: solution could be to just add "fake" tags(!t! for tab, !n! for newline) and replace them in the string later
+ // 3. Test indentation again
+ if (indentationLevel != lastSeenIndentationLevel && indentationLevel > 2) {
+ resetLevelCounter(indentationLevel);
+ }
+ indentationText = generateIndentationText(letterFormat, indentationLevel);
+ increaseLevelCounter(indentationLevel);
+ lastSeenIndentationLevel = indentationLevel;
+ fullText += indentationText + ((Element) node).text() + "\t";
+ TextNode textNode = new TextNode(fullText);
+ node.replaceWith(textNode);
+ }
+ return fullText;
+ }
+
+ /*
+ todo: helperclass/parser
+ ------------------
+ - fuer roemische zahlen: RomanConverter
+ - Irgendein helper, der automatisch richtiges Format waehlt (zahl, buchstabe oder römisch)
+ * bei buchstaben wird a-z, aa-zz etc benoetigt
+ -> generator generiert a-z, wenn z erreicht + 1 buchstabe von a bis z etc
+ - Ebenen 1-9 als counter (hashmap? mit key css class)
+ - last ebene seen variable
+ - handle class method
+ * wenn selbe Ebene: nummer/buchstabe in format rausgeben, counter + 1
+ * wenn tiefere ebene:
+ -> aktuelle ebene zwischen 1 und 2?: post number, counter + 1
+ -> aktuelle ebene groeßer als 2: reset counter, post, counter + 1
+ * wenn hoehere ebene:
+ -> post und counter + 1
+ * auf anzahl tabs achten
+ */
+
+ private int extractIndentationLevel(Node node) {
+ String attributes = node.attr("class");
+ if (attributes.isEmpty()) {
+ return 0;
+ }
+ List<String> classNames = Arrays.asList(attributes.split(" "));
+ List<String> indentClassList = classNames.stream().filter(cssClass -> cssClass.contains("ql-indent-")).collect(Collectors.toList());
+ if (indentClassList.isEmpty()) {
+ return 0;
+ }
+ String indentCssClass = indentClassList.get(0);
+ return Integer.parseInt(Arrays.asList(indentCssClass.split("-")).get(2));
+ }
+
+ private IndentationLetterFormat getTextFormat(int indentationLevel) {
+ IndentationLetterFormat letterFormat;
+ switch (indentationLevel) {
+ case 0:
+ case 3:
+ case 6:
+ letterFormat = NUMBER;
+ break;
+ case 1:
+ case 4:
+ case 7:
+ letterFormat = LETTER;
+ break;
+ case 2:
+ case 5:
+ case 8:
+ letterFormat = ROMAN;
+ break;
+ default:
+ letterFormat = null;
+ }
+ return letterFormat;
+ }
+
+ private void increaseLevelCounter(int indentationLevel) {
+ String indentationLetter = nextIndentationLetterMap.get(indentationLevel);
+ String nextIndentationLetter;
+ if (indentationLetter.matches("[0-9]+")) {
+ nextIndentationLetter = String.valueOf(Integer.parseInt(indentationLetter) + 1);
+ } else {
+ nextIndentationLetter = generateFollowupString(indentationLetter);
+ }
+ nextIndentationLetterMap.put(indentationLevel, nextIndentationLetter);
+ }
+
+ private void resetLevelCounter(int indentationLevel) {
+ String indentationLetter = nextIndentationLetterMap.get(indentationLevel);
+ String nextIndentationLetter = indentationLetter.matches("[0-9]+") ? "1" : "a";
+ nextIndentationLetterMap.put(indentationLevel, nextIndentationLetter);
+ }
+
+ private String generateFollowupString(String previousString) {
+ // TODO: make working for aa-zz etc and fix
+ char lastLetter = previousString.charAt(previousString.length() - 1);
+ return Character.toString(++lastLetter);
+ }
+
+ private String generateIndentationText(IndentationLetterFormat letterFormat, int indentationLevel) {
+ String indentationText;
+ String indentationLetter = nextIndentationLetterMap.get(indentationLevel);
+ switch (letterFormat) {
+ case ROMAN:
+ indentationText = RomanConverter.getRomanNumber(Integer.valueOf(indentationLetter)) + ". ";
+ break;
+ case NUMBER:
+ case LETTER:
+ indentationText = indentationLetter + ". ";
+ break;
+ default:
+ indentationText = "";
+ }
+
+ return indentationText;
+ }
+}
diff --git a/gemeinsamforschen/src/main/java/unipotsdam/gf/modules/fileManagement/Util/IndentationLetterFormat.java b/gemeinsamforschen/src/main/java/unipotsdam/gf/modules/fileManagement/Util/IndentationLetterFormat.java
new file mode 100644
index 0000000000000000000000000000000000000000..8a44eacb3eeca42333b53468f43e6d7efea5dd38
--- /dev/null
+++ b/gemeinsamforschen/src/main/java/unipotsdam/gf/modules/fileManagement/Util/IndentationLetterFormat.java
@@ -0,0 +1,8 @@
+package unipotsdam.gf.modules.fileManagement.Util;
+
+public enum IndentationLetterFormat {
+
+ NUMBER,
+ ROMAN,
+ LETTER
+}
diff --git a/gemeinsamforschen/src/main/java/unipotsdam/gf/modules/fileManagement/Util/RomanConverter.java b/gemeinsamforschen/src/main/java/unipotsdam/gf/modules/fileManagement/Util/RomanConverter.java
new file mode 100644
index 0000000000000000000000000000000000000000..7363a3fae7fc5247cff842bc4dc5eb3f926fb4a8
--- /dev/null
+++ b/gemeinsamforschen/src/main/java/unipotsdam/gf/modules/fileManagement/Util/RomanConverter.java
@@ -0,0 +1,24 @@
+package unipotsdam.gf.modules.fileManagement.Util;
+
+import static java.lang.String.join;
+import static java.util.Collections.nCopies;
+
+public class RomanConverter {
+
+ public static String getRomanNumber(int number) {
+ return join("", nCopies(number, "I"))
+ .replace("IIIII", "V")
+ .replace("IIII", "IV")
+ .replace("VV", "X")
+ .replace("VIV", "IX")
+ .replace("XXXXX", "L")
+ .replace("XXXX", "XL")
+ .replace("LL", "C")
+ .replace("LXL", "XC")
+ .replace("CCCCC", "D")
+ .replace("CCCC", "CD")
+ .replace("DD", "M")
+ .replace("DCD", "CM");
+ }
+
+}
diff --git a/gemeinsamforschen/src/main/java/unipotsdam/gf/process/DossierCreationProcess.java b/gemeinsamforschen/src/main/java/unipotsdam/gf/process/DossierCreationProcess.java
index ec2111c5685bda94e2521cbbc69022082b57c5e5..bbb620815af1a07e234e98e030b60edd1b07b364 100644
--- a/gemeinsamforschen/src/main/java/unipotsdam/gf/process/DossierCreationProcess.java
+++ b/gemeinsamforschen/src/main/java/unipotsdam/gf/process/DossierCreationProcess.java
@@ -74,7 +74,7 @@ public class DossierCreationProcess {
public FullSubmission addSubmission(
FullSubmissionPostRequest fullSubmissionPostRequest, User user, Project project) throws DocumentException, IOException {
- FormDataContentDispositionBuilder builder = FormDataContentDisposition.name("dossierUpload").fileName("dossier_" + user.getName() + ".pdf");
+ FormDataContentDispositionBuilder builder = FormDataContentDisposition.name("dossierUpload").fileName("dossier_" + user.getEmail() + ".pdf");
fileManagementService.saveStringAsPDF(user, project, fullSubmissionPostRequest.getHtml(), builder.build(),
FileRole.DOSSIER, FileType.HTML);
diff --git a/gemeinsamforschen/src/test/java/unipotsdam/gf/modules/fileManagement/FileManagementServiceTest.java b/gemeinsamforschen/src/test/java/unipotsdam/gf/modules/fileManagement/FileManagementServiceTest.java
new file mode 100644
index 0000000000000000000000000000000000000000..e57ec394e47b8867f2a947266463cd68f5f68d8c
--- /dev/null
+++ b/gemeinsamforschen/src/test/java/unipotsdam/gf/modules/fileManagement/FileManagementServiceTest.java
@@ -0,0 +1,15 @@
+package unipotsdam.gf.modules.fileManagement;
+
+import org.junit.Test;
+
+public class FileManagementServiceTest {
+
+ @Test
+ public void manipulateIndentation() {
+ String fileContent = "<h1>kekse</h1><p><br></p><p>Das ist ein beispieltext um zu testen, wie man intentation fixen kann.</p><p>Ich mag zuege sehr abcdefg</p><p><br></p><ol><li>1</li><li class=\"ql-indent-1\">a</li><li class=\"ql-indent-1\">b</li><li>2</li><li class=\"ql-indent-2\">i</li><li class=\"ql-indent-1\">bcd</li><li class=\"ql-indent-1\">abcd</li><li class=\"ql-indent-2\">i</li><li class=\"ql-indent-2\">ii</li><li class=\"ql-indent-2\">iii</li><li class=\"ql-indent-2\">iv</li><li class=\"ql-indent-1\">efgh</li><li class=\"ql-indent-2\">i</li><li class=\"ql-indent-2\">ii</li><li class=\"ql-indent-3\">1innen</li><li class=\"ql-indent-4\">ainnen</li><li class=\"ql-indent-3\">2innen</li><li class=\"ql-indent-4\">binnen</li></ol>";
+ FileManagementService fileManagementService = new FileManagementService();
+
+ fileManagementService.manipulateIndentation(fileContent);
+
+ }
+}
\ No newline at end of file