From 8eb7ed676989c15a4254559254e969a5c2e5b37b Mon Sep 17 00:00:00 2001
From: srosse <none@none>
Date: Tue, 27 Jan 2015 12:14:24 +0100
Subject: [PATCH] OO-1402: support <br/> and lists in the html to OpenXML
converter
---
.../util/openxml/HTMLToOpenXMLHandler.java | 30 ++++-
.../core/util/openxml/OpenXMLDocument.java | 127 +++++++++++++++++-
.../util/openxml/OpenXMLDocumentWriter.java | 43 +++++-
.../util/openxml/_resources/numbering.xml | 2 +
.../core/util/openxml/_resources/styles.xml | 8 ++
5 files changed, 202 insertions(+), 8 deletions(-)
create mode 100644 src/main/java/org/olat/core/util/openxml/_resources/numbering.xml
diff --git a/src/main/java/org/olat/core/util/openxml/HTMLToOpenXMLHandler.java b/src/main/java/org/olat/core/util/openxml/HTMLToOpenXMLHandler.java
index e6a7d23eaeb..1f6b681af7e 100644
--- a/src/main/java/org/olat/core/util/openxml/HTMLToOpenXMLHandler.java
+++ b/src/main/java/org/olat/core/util/openxml/HTMLToOpenXMLHandler.java
@@ -25,6 +25,7 @@ import java.util.Collections;
import java.util.Deque;
import java.util.List;
+import org.olat.core.util.openxml.OpenXMLDocument.ListParagraph;
import org.olat.core.util.openxml.OpenXMLDocument.Style;
import org.w3c.dom.Element;
import org.w3c.dom.Node;
@@ -50,8 +51,9 @@ public class HTMLToOpenXMLHandler extends DefaultHandler {
private List<Node> content = new ArrayList<Node>();
private Deque<StyleStatus> styleStack = new ArrayDeque<StyleStatus>();
- private Element currentParagraph;
private Table currentTable;
+ private Element currentParagraph;
+ private ListParagraph currentListParagraph;
public HTMLToOpenXMLHandler(OpenXMLDocument document, Element paragraph) {
this.factory = document;
@@ -76,6 +78,18 @@ public class HTMLToOpenXMLHandler extends DefaultHandler {
return currentParagraph;
}
+ private Element getCurrentListParagraph(boolean create) {
+ if(create || currentParagraph == null) {
+ //flush the text
+ if(textBuffer != null) {
+ flushText();
+ addContent(currentParagraph);
+ }
+ currentParagraph = factory.createListParagraph(currentListParagraph);
+ }
+ return currentParagraph;
+ }
+
private void closeParagraph() {
flushText();
currentParagraph = addContent(currentParagraph);
@@ -229,6 +243,8 @@ public class HTMLToOpenXMLHandler extends DefaultHandler {
styles = setTextPreferences(cssStyles);
}
styleStack.add(new StyleStatus(tag, styles));
+ } else if("br".equals(tag)) {
+ closeParagraph();
} else if("em".equalsIgnoreCase(tag)) {
flushText();
Style[] styles = setTextPreferences(Style.italic);
@@ -249,6 +265,10 @@ public class HTMLToOpenXMLHandler extends DefaultHandler {
int colspan = OpenXMLUtils.getSpanAttribute("colspan", attributes);
int rowspan = OpenXMLUtils.getSpanAttribute("rowspan", attributes);
currentTable.addCellEl(colspan, rowspan);
+ } else if("ul".equals(tag) || "ol".equals(tag)) {
+ currentListParagraph = factory.createListParagraph();
+ } else if("li".equals(tag)) {
+ getCurrentListParagraph(true);
}
}
@@ -282,6 +302,8 @@ public class HTMLToOpenXMLHandler extends DefaultHandler {
if(currentTable != null) {
content.add(currentTable.getTableEl());
}
+ currentTable = null;
+ currentParagraph = null;
} else if("td".equals(tag) || "th".equals(tag)) {
flushText();
currentParagraph = addContent(currentParagraph);
@@ -292,6 +314,11 @@ public class HTMLToOpenXMLHandler extends DefaultHandler {
textBuffer = null;
latex = false;
currentParagraph = null;
+ } else if("ul".equals(tag) || "ol".equals(tag)) {
+ closeParagraph();
+ currentListParagraph = null;
+ } else if("li".equals(tag)) {
+ //do nothing
}
}
@@ -452,6 +479,5 @@ public class HTMLToOpenXMLHandler extends DefaultHandler {
public void unDone() {
done = false;
}
-
}
}
\ No newline at end of file
diff --git a/src/main/java/org/olat/core/util/openxml/OpenXMLDocument.java b/src/main/java/org/olat/core/util/openxml/OpenXMLDocument.java
index f47ce6d4f8f..a21520ebfaa 100644
--- a/src/main/java/org/olat/core/util/openxml/OpenXMLDocument.java
+++ b/src/main/java/org/olat/core/util/openxml/OpenXMLDocument.java
@@ -80,11 +80,13 @@ public class OpenXMLDocument {
private final OpenXMLStyles styles;
private int currentId = 4;
+ private int currentNumberingId = 0;
private String documentHeader;
private Map<File, DocReference> fileToImagesMap = new HashMap<File, DocReference>();
- private List<Node> cursorStack = new ArrayList<Node>();
- private List<HeaderReference> headers = new ArrayList<HeaderReference>();
+ private List<Node> cursorStack = new ArrayList<>();
+ private List<ListParagraph> numbering = new ArrayList<>();
+ private List<HeaderReference> headers = new ArrayList<>();
private VFSContainer mediaContainer;
@@ -131,6 +133,10 @@ public class OpenXMLDocument {
return headers;
}
+ public Collection<ListParagraph> getNumbering() {
+ return numbering;
+ }
+
public Node getCursor() {
return cursorStack.get(cursorStack.size() - 1);
}
@@ -639,6 +645,104 @@ public class OpenXMLDocument {
return cellEl;
}
+ public ListParagraph createListParagraph() {
+ int abstractNumberingId = currentNumberingId++;
+ int numberingId = currentNumberingId++;
+ ListParagraph lp = new ListParagraph(abstractNumberingId, numberingId);
+ numbering.add(lp);
+ return lp;
+ }
+
+ /*
+<w:p>
+ <w:pPr>
+ <w:pStyle w:val="ListParagraph"/>
+ <w:numPr>
+ <w:ilvl w:val="0"/>
+ <w:numId w:val="1"/>
+ </w:numPr>
+ </w:pPr>
+ <w:r>
+ <w:t>One</w:t>
+ </w:r>
+</w:p>
+ */
+ public Element createListParagraph(ListParagraph def) {
+ Element paragraphEl = document.createElement("w:p");
+ Element listEl = (Element)paragraphEl.appendChild(document.createElement("w:pPr"));
+ Element pStyleEl = (Element)listEl.appendChild(document.createElement("w:pStyle"));
+ pStyleEl.setAttribute("w:val", "ListParagraph");
+ Element numberingEl = (Element)listEl.appendChild(document.createElement("w:numPr"));
+ Element ilvlEl = (Element)numberingEl.appendChild(document.createElement("w:ilvl"));
+ ilvlEl.setAttribute("w:val", "0");
+ Element numIdEl = (Element)numberingEl.appendChild(document.createElement("w:numId"));
+ numIdEl.setAttribute("w:val", Integer.toString(def.getNumId()));
+ return paragraphEl;
+ }
+
+ /*
+<w:abstractNum w:abstractNumId="0">
+ <w:lvl w:ilvl="0">
+ <w:start w:val="1"/>
+ <w:numFmt w:val="bullet"/>
+ <w:lvlText w:val="o"/>
+ <w:lvlJc w:val="left"/>
+ <w:pPr>
+ <w:ind w:left="720"
+ w:hanging="360"/>
+ </w:pPr>
+ <w:rPr>
+ <w:rFonts w:ascii="Symbol"
+ w:hAnsi="Symbol"
+ w:hint="default"/>
+ </w:rPr>
+ </w:lvl>
+ */
+ public Element createAbstractNumbering(ListParagraph def, Document doc) {
+ Element numEl = doc.createElement("w:abstractNum");
+ numEl.setAttribute("w:abstractNumId", Integer.toString(def.getAbstractNumId()));
+ numEl.appendChild(createNumberingLevel(doc));
+ return numEl;
+ }
+
+ private Element createNumberingLevel(Document numberingDoc) {
+ Element levelEl = numberingDoc.createElement("w:lvl");
+ levelEl.setAttribute("w:ilvl", "0");
+ Element startEl = (Element)levelEl.appendChild(numberingDoc.createElement("w:start"));
+ startEl.setAttribute("w:val", "1");
+ Element numFmtEl = (Element)levelEl.appendChild(numberingDoc.createElement("w:numFmt"));
+ numFmtEl.setAttribute("w:val", "bullet");
+ Element lvlTextEl = (Element)levelEl.appendChild(numberingDoc.createElement("w:lvlText"));
+ lvlTextEl.setAttribute("w:val", Character.toString((char)0xB7));//bullet
+ Element lvlJcEl = (Element)levelEl.appendChild(numberingDoc.createElement("w:lvlJc"));
+ lvlJcEl.setAttribute("w:val", "left");
+ //pPr
+ Element pPrEl = (Element)levelEl.appendChild(numberingDoc.createElement("w:pPr"));
+ Element indEl = (Element)pPrEl.appendChild(numberingDoc.createElement("w:ind"));
+ indEl.setAttribute("w:left", "720");
+ indEl.setAttribute("w:hanging", "360");
+ //rPr
+ Element rPrEl = (Element)levelEl.appendChild(numberingDoc.createElement("w:rPr"));
+ Element rFontsEl = (Element)rPrEl.appendChild(numberingDoc.createElement("w:rFonts"));
+ rFontsEl.setAttribute("w:ascii", "Symbol");
+ rFontsEl.setAttribute("w:hAnsi", "Symbol");
+ rFontsEl.setAttribute("w:hint", "default");
+ return levelEl;
+ }
+
+ /*
+ <w:num w:numId="1">
+ <w:abstractNumId w:val="0"/>
+ </w:num>
+ */
+ public Element createNumbering(ListParagraph def, Document numberingDoc) {
+ Element numEl = numberingDoc.createElement("w:num");
+ numEl.setAttribute("w:numId", Integer.toString(def.getNumId()));
+ Element abstractNumEl = (Element)numEl.appendChild(numberingDoc.createElement("w:abstractNumId"));
+ abstractNumEl.setAttribute("w:val", Integer.toString(def.getAbstractNumId()));
+ return numEl;
+ }
+
/*
<w:shd w:val="solid" w:color="E9EAF2" w:fill="auto" />
*/
@@ -992,4 +1096,23 @@ public class OpenXMLDocument {
return header;
}
}
+
+ public static class ListParagraph {
+
+ private final int abstractNumId;
+ private final int numId;
+
+ public ListParagraph(int abstractNumId, int numId) {
+ this.abstractNumId = abstractNumId;
+ this.numId = numId;
+ }
+
+ public int getAbstractNumId() {
+ return abstractNumId;
+ }
+
+ public int getNumId() {
+ return numId;
+ }
+ }
}
diff --git a/src/main/java/org/olat/core/util/openxml/OpenXMLDocumentWriter.java b/src/main/java/org/olat/core/util/openxml/OpenXMLDocumentWriter.java
index 2d05fbbc7b4..725680cb167 100644
--- a/src/main/java/org/olat/core/util/openxml/OpenXMLDocumentWriter.java
+++ b/src/main/java/org/olat/core/util/openxml/OpenXMLDocumentWriter.java
@@ -24,6 +24,7 @@ import java.io.IOException;
import java.io.InputStream;
import java.io.OutputStream;
import java.nio.charset.Charset;
+import java.util.Collection;
import java.util.zip.ZipEntry;
import java.util.zip.ZipOutputStream;
@@ -31,9 +32,11 @@ import org.apache.commons.io.IOUtils;
import org.olat.core.logging.OLog;
import org.olat.core.logging.Tracing;
import org.olat.core.util.openxml.OpenXMLDocument.HeaderReference;
+import org.olat.core.util.openxml.OpenXMLDocument.ListParagraph;
import org.w3c.dom.DOMException;
import org.w3c.dom.Document;
import org.w3c.dom.Element;
+import org.w3c.dom.Node;
import org.w3c.dom.NodeList;
/**
@@ -101,6 +104,12 @@ public class OpenXMLDocumentWriter {
//word/media
appendMedias(out, document);
+ //word/numbering
+ ZipEntry numberingDocument = new ZipEntry("word/numbering.xml");
+ out.putNextEntry(numberingDocument);
+ appendNumbering(out, document);
+ out.closeEntry();
+
//word/document.xml
ZipEntry wordDocument = new ZipEntry("word/document.xml");
out.putNextEntry(wordDocument);
@@ -138,6 +147,28 @@ public class OpenXMLDocumentWriter {
}
}
+ private void appendNumbering(ZipOutputStream out, OpenXMLDocument document) {
+ try(InputStream in = OpenXMLDocumentWriter.class.getResourceAsStream("_resources/numbering.xml")) {
+ Collection<ListParagraph> numberingList = document.getNumbering();
+ if(numberingList != null && numberingList.size() > 0) {
+ Document numberingDoc = OpenXMLUtils.createDocument(in);
+ NodeList numberingElList = numberingDoc.getElementsByTagName("w:numbering");
+ Node numberingEl = numberingElList.item(0);
+ for(ListParagraph numberingItem : numberingList) {
+ Element abstractEl = document.createAbstractNumbering(numberingItem, numberingDoc);
+ numberingEl.appendChild(abstractEl);
+ Element numEl = document.createNumbering(numberingItem, numberingDoc);
+ numberingEl.appendChild(numEl);
+ }
+ OpenXMLUtils.writeTo(numberingDoc, out, false);
+ } else {
+ IOUtils.copy(in, out);
+ }
+ } catch (IOException e) {
+ log.error("", e);
+ }
+ }
+
private void appendPredefinedStyles(ZipOutputStream out, OpenXMLStyles styles) {
try(InputStream in = OpenXMLDocumentWriter.class.getResourceAsStream("_resources/styles.xml")) {
if(styles != null) {
@@ -159,12 +190,13 @@ public class OpenXMLDocumentWriter {
/*
<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships">
- <Relationship Id="rId3" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/settings" Target="settings.xml"/>
- <Relationship Id="rId4" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/webSettings" Target="webSettings.xml"/>
- <Relationship Id="rId5" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/fontTable" Target="fontTable.xml"/>
- <Relationship Id="rId6" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/theme" Target="theme/theme1.xml"/>
+ <Relationship Id="rId4" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/settings" Target="settings.xml"/>
+ <Relationship Id="rId5" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/webSettings" Target="webSettings.xml"/>
+ <Relationship Id="rId6" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/fontTable" Target="fontTable.xml"/>
+ <Relationship Id="rId7" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/theme" Target="theme/theme1.xml"/>
<Relationship Id="rId1" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/styles" Target="styles.xml"/>
<Relationship Id="rId2" Type="http://schemas.microsoft.com/office/2007/relationships/stylesWithEffects" Target="stylesWithEffects.xml"/>
+ <Relationship Id="rId3" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/numbering" Target="numbering.xml" />
</Relationships>
*/
protected void createDocumentRelationships(OutputStream out, OpenXMLDocument document) {
@@ -175,6 +207,8 @@ public class OpenXMLDocumentWriter {
addRelationship("rId1", "http://schemas.openxmlformats.org/officeDocument/2006/relationships/styles",
"styles.xml", relationshipsEl, doc);
+ addRelationship("rId2", "http://schemas.openxmlformats.org/officeDocument/2006/relationships/numbering",
+ "numbering.xml", relationshipsEl, doc);
if(document != null) {
for(DocReference docRef:document.getImages()) {
@@ -315,6 +349,7 @@ public class OpenXMLDocumentWriter {
createContentTypesOverride("/docProps/core.xml", CT_CORE_PROPERTIES, typesEl, doc);
createContentTypesOverride("/word/document.xml", CT_WORD_DOCUMENT, typesEl, doc);
createContentTypesOverride("/word/styles.xml", CT_STYLES, typesEl, doc);
+ createContentTypesOverride("/word/numbering.xml", CT_NUMBERING, typesEl, doc);
for(HeaderReference headerRef:document.getHeaders()) {
createContentTypesOverride("/word/" + headerRef.getFilename(), CT_HEADER, typesEl, doc);
diff --git a/src/main/java/org/olat/core/util/openxml/_resources/numbering.xml b/src/main/java/org/olat/core/util/openxml/_resources/numbering.xml
new file mode 100644
index 00000000000..b29a0088f3b
--- /dev/null
+++ b/src/main/java/org/olat/core/util/openxml/_resources/numbering.xml
@@ -0,0 +1,2 @@
+<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+<w:numbering xmlns:wpc="http://schemas.microsoft.com/office/word/2010/wordprocessingCanvas" xmlns:mo="http://schemas.microsoft.com/office/mac/office/2008/main" xmlns:mc="http://schemas.openxmlformats.org/markup-compatibility/2006" xmlns:mv="urn:schemas-microsoft-com:mac:vml" xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:r="http://schemas.openxmlformats.org/officeDocument/2006/relationships" xmlns:m="http://schemas.openxmlformats.org/officeDocument/2006/math" xmlns:v="urn:schemas-microsoft-com:vml" xmlns:wp14="http://schemas.microsoft.com/office/word/2010/wordprocessingDrawing" xmlns:wp="http://schemas.openxmlformats.org/drawingml/2006/wordprocessingDrawing" xmlns:w10="urn:schemas-microsoft-com:office:word" xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main" xmlns:w14="http://schemas.microsoft.com/office/word/2010/wordml" xmlns:wpg="http://schemas.microsoft.com/office/word/2010/wordprocessingGroup" xmlns:wpi="http://schemas.microsoft.com/office/word/2010/wordprocessingInk" xmlns:wne="http://schemas.microsoft.com/office/word/2006/wordml" xmlns:wps="http://schemas.microsoft.com/office/word/2010/wordprocessingShape" mc:Ignorable="w14 wp14"></w:numbering>
\ No newline at end of file
diff --git a/src/main/java/org/olat/core/util/openxml/_resources/styles.xml b/src/main/java/org/olat/core/util/openxml/_resources/styles.xml
index 00978bd4d6f..0fd8bf0801e 100644
--- a/src/main/java/org/olat/core/util/openxml/_resources/styles.xml
+++ b/src/main/java/org/olat/core/util/openxml/_resources/styles.xml
@@ -365,6 +365,14 @@
<w:semiHidden />
<w:unhideWhenUsed />
</w:style>
+ <w:style w:type="paragraph" w:styleId="ListParagraph">
+ <w:name w:val="List Paragraph"/>
+ <w:basedOn w:val="Normal"/>
+ <w:pPr>
+ <w:ind w:left="720"/>
+ <w:contextualSpacing/>
+ </w:pPr>
+ </w:style>
<w:style w:type="character" w:customStyle="1" w:styleId="ooHeading1Zeichen">
<w:name w:val="Ãœberschrift 1 Zeichen" />
<w:basedOn w:val="Absatzstandardschriftart" />
--
GitLab