litvinovg/w2phtml
1
0
Fork 0
Code Issues 1 Pull requests Projects Releases 21 Packages Wiki Activity Actions

Zotero integration + EPUB split + a few other fixes

Browse source 
git-svn-id: svn://svn.code.sf.net/p/writer2latex/code/trunk@76 f0f2a975-2e09-46c8-9428-3b39399b9f3c
This commit is contained in:
henrikjust 2010-10-30 10:35:46 +00:00
parent b415705e47
commit 2174e5cbf5
13 changed files with 2323 additions and 74 deletions
Download patch file Download diff file Expand all files Collapse all files

27
source/java/writer2latex/xhtml/Converter.java
View file

@ -20,7 +20,7 @@
*
* All Rights Reserved.
*
* Version 1.2 (2010-05-17)
* Version 1.2 (2010-10-30)
*
*/
@ -201,12 +201,7 @@ public class Converter extends ConverterBase {
// Set locale to document language
StyleWithProperties style = ofr.isSpreadsheet() ? ofr.getDefaultCellStyle() : ofr.getDefaultParStyle();
if (style!=null) {
String sLang = style.getProperty(XMLString.FO_LANGUAGE);
String sCountry = style.getProperty(XMLString.FO_COUNTRY);
if (sLang!=null) {
if (sCountry==null) { l10n.setLocale(sLang); }
else { l10n.setLocale(sLang+"-"+sCountry); }
}
l10n.setLocale(style.getProperty(XMLString.FO_LANGUAGE), style.getProperty(XMLString.FO_COUNTRY));
}
// Traverse the body
@ -463,16 +458,32 @@ public class Converter extends ConverterBase {
public void handleOfficeAnnotation(Node onode, Node hnode) {
if (config.xhtmlNotes()) {
// Extract the text from the paragraphs, seperate paragraphs with newline
// Extract the text from the paragraphs, separate paragraphs with newline
StringBuffer buf = new StringBuffer();
Element creator = null;
Element date = null;
Node child = onode.getFirstChild();
while (child!=null) {
if (Misc.isElement(child, XMLString.TEXT_P)) {
if (buf.length()>0) { buf.append('\n'); }
buf.append(getPlainInlineText(child));
}
else if (Misc.isElement(child, XMLString.DC_CREATOR)) {
creator = (Element) child;
}
else if (Misc.isElement(child, XMLString.DC_DATE)) {
date = (Element) child;
}
child = child.getNextSibling();
}
if (creator!=null) {
if (buf.length()>0) { buf.append('\n'); }
buf.append(getPlainInlineText(creator));
}
if (date!=null) {
if (buf.length()>0) { buf.append('\n'); }
buf.append(Misc.formatDate(ofr.getTextContent(date), l10n.getLocale().getLanguage(), l10n.getLocale().getCountry()));
}
Node commentNode = htmlDOM.createComment(buf.toString());
hnode.appendChild(commentNode);
}

61
source/java/writer2latex/xhtml/L10n.java
View file

@ -26,6 +26,8 @@
package writer2latex.xhtml;
import java.util.Locale;
// This class handles localized strings (used for navigation)
public class L10n {
public final static int UP = 0;
@ -39,21 +41,36 @@ public class L10n {
public final static int DIRECTORY = 8;
public final static int DOCUMENT = 9;
private Locale locale = null;
private String sLocale="en-US";
public void setLocale(String sLocale) {
if (sLocale!=null) { this.sLocale = sLocale;}
}
public void setLocale(String sLanguage, String sCountry) {
if (sLanguage!=null) {
if (sCountry!=null) { sLocale = sLanguage + "-" + sCountry; }
else { sLocale = sLanguage; }
if (sCountry!=null) {
locale = new Locale(sLanguage,sCountry);
}
else {
locale = new Locale(sLanguage);
}
}
else {
locale = Locale.getDefault();
}
if (locale.getCountry().length()>0) {
sLocale = locale.getLanguage()+"-"+locale.getCountry();
}
else {
sLocale = locale.getLanguage();
}
}
public Locale getLocale() {
return locale;
}
public String get(int nString) {
if (sLocale.startsWith("de")) { // german
if (sLocale.startsWith("de")) { // German
switch (nString) {
case UP: return "Nach oben";
case FIRST : return "Anfang";
@ -67,7 +84,7 @@ public class L10n {
case DOCUMENT: return "Dokument";
}
}
if (sLocale.startsWith("fr")) { // french
if (sLocale.startsWith("fr")) { // French
switch (nString) {
case UP: return "Haut";
case FIRST : return "D\u00e9but";
@ -81,7 +98,7 @@ public class L10n {
case DOCUMENT: return "Document";
}
}
if (sLocale.startsWith("es")) { // spanish
if (sLocale.startsWith("es")) { // Spanish
switch (nString) {
case UP: return "Arriba";
case FIRST : return "Primero";
@ -95,7 +112,7 @@ public class L10n {
case DOCUMENT: return "Documento";
}
}
if (sLocale.startsWith("it")) { // italian
if (sLocale.startsWith("it")) { // Italian
switch (nString) {
case UP: return "Su";
case FIRST : return "Inizio";
@ -109,7 +126,7 @@ public class L10n {
case DOCUMENT: return "Documento";
}
}
if (sLocale.startsWith("pt")) { // (brazilian) portuguese
if (sLocale.startsWith("pt")) { // (Brazilian) Portuguese
switch (nString) {
case UP: return "Acima";
case FIRST : return "Primeiro";
@ -123,7 +140,7 @@ public class L10n {
case DOCUMENT: return "Documento";
}
}
if (sLocale.startsWith("cs")) { // czech
if (sLocale.startsWith("cs")) { // Czech
switch (nString) {
case UP: return "Nahoru";
case FIRST : return "Prvn\u00ed";
@ -137,7 +154,7 @@ public class L10n {
case DOCUMENT: return "Dokument";
}
}
if (sLocale.startsWith("nl")) { // dutch
if (sLocale.startsWith("nl")) { // Dutch
switch (nString) {
case UP: return "Omhoog";
case FIRST : return "Eerste";
@ -151,7 +168,7 @@ public class L10n {
case DOCUMENT: return "Document";
}
}
if (sLocale.startsWith("da")) { // danish
if (sLocale.startsWith("da")) { // Danish
switch (nString) {
case UP: return "Op";
case FIRST : return "F\u00F8rste";
@ -165,7 +182,7 @@ public class L10n {
case DOCUMENT: return "Dokument";
}
}
if (sLocale.startsWith("nn")) { // nynorsk
if (sLocale.startsWith("nn")) { // Nynorsk
switch (nString) {
case UP: return "Opp";
case FIRST : return "F\u00f8rste";
@ -179,7 +196,7 @@ public class L10n {
case DOCUMENT: return "Dokument";
}
}
if (sLocale.startsWith("pl")) { // polish
if (sLocale.startsWith("pl")) { // Polish
switch (nString) {
case UP: return "W g\u00f3r\u0119";
case FIRST : return "Pierwsza";
@ -193,7 +210,7 @@ public class L10n {
case DOCUMENT: return "Dokument";
}
}
if (sLocale.startsWith("fi")) { // finnish
if (sLocale.startsWith("fi")) { // Finnish
switch (nString) {
case UP: return "Yl\u00f6s";
case FIRST : return "Ensimm\u00e4inen";
@ -207,7 +224,7 @@ public class L10n {
case DOCUMENT: return "Dokumentti";
}
}
if (sLocale.startsWith("ru")) { // russian
if (sLocale.startsWith("ru")) { // Russian
switch (nString) {
case UP: return "\u0412\u0432\u0435\u0440\u0445";
case FIRST : return "\u041f\u0435\u0440\u0432\u0430\u044f";
@ -221,7 +238,7 @@ public class L10n {
case DOCUMENT: return "\u0414\u043e\u043a\u0443\u043c\u0435\u043d\u0442";
}
}
if (sLocale.startsWith("uk")) { // ukrainian
if (sLocale.startsWith("uk")) { // Ukrainian
switch (nString) {
case UP: return "\u041d\u0430\u0433\u043e\u0440\u0443";
case FIRST : return "\u041f\u0435\u0440\u0448\u0430";
@ -235,7 +252,7 @@ public class L10n {
case DOCUMENT: return "\u0414\u043e\u043a\u0443\u043c\u0435\u043d\u0442";
}
}
if (sLocale.startsWith("tr")) { // turkish
if (sLocale.startsWith("tr")) { // Turkish
switch (nString) {
case UP: return "Yukar\u0131";
case FIRST : return "\u0130lk";
@ -249,7 +266,7 @@ public class L10n {
case DOCUMENT: return "D\u00f6k\u00fcman";
}
}
if (sLocale.startsWith("hr")) { // croatian
if (sLocale.startsWith("hr")) { // Croatian
switch (nString) {
case UP: return "Up";
case FIRST : return "Prvi";
@ -262,7 +279,7 @@ public class L10n {
case DOCUMENT: return "Document";
}
}
// english - default
// English - default
switch (nString) {
case UP: return "Up";
case FIRST : return "First";

44
source/java/writer2latex/xhtml/TextConverter.java
View file

@ -20,7 +20,7 @@
*
* All Rights Reserved.
*
* Version 1.2 (2010-07-02)
* Version 1.2 (2010-10-30)
*
*/
@ -79,6 +79,10 @@ public class TextConverter extends ConverterHelper {
// Data used to handle splitting over several files
// TODO: Accessor methods for sections
// Some (Sony?) EPUB readers have a limit on the file size of individual files
// In any case very large files could be a performance problem, hence we do automatic splitting
// after this number of characters. TODO: Make configurable.
private static final int EPUB_CHARACTER_COUNT_TRESHOLD = 150000;
int nSplit = 0; // The outline level at which to split files (0=no split)
int nRepeatLevels = 5; // The number of levels to repeat when splitting (0=no repeat)
private int nLastSplitLevel = 1; // The outline level at which the last split occured
@ -86,6 +90,7 @@ public class TextConverter extends ConverterHelper {
boolean bAfterHeading=false; // last element was a top level heading
protected Stack<Node> sections = new Stack<Node>(); // stack of nested sections
Element[] currentHeading = new Element[7]; // Last headings (repeated when splitting)
private int nCharacterCount = 0; // The number of text characters in the current document
// Counters for generated numbers
private ListCounter outlineNumbering;
@ -352,6 +357,8 @@ public class TextConverter extends ConverterHelper {
getDrawCv().handleDrawElement((Element)child,(Element)hnode,null,nFloatMode);
}
else if (nodeName.equals(XMLString.TEXT_P)) {
hnode = maybeSplit(hnode);
nCharacterCount+=OfficeReader.getCharacterCount(child);
// is there a block element, we should use?
XhtmlStyleMap xpar = config.getXParStyleMap();
String sDisplayName = ofr.getParStyles().getDisplayName(Misc.getAttribute(child,XMLString.TEXT_STYLE_NAME));
@ -395,14 +402,16 @@ public class TextConverter extends ConverterHelper {
else if(nodeName.equals(XMLString.TEXT_H)) {
int nOutlineLevel = getOutlineLevel((Element)child);
Node rememberNode = hnode;
hnode = maybeSplit(hnode,nOutlineLevel,bAfterHeading);
hnode = maybeSplit(hnode,nOutlineLevel);
nCharacterCount+=OfficeReader.getCharacterCount(child);
handleHeading((Element)child,hnode,rememberNode!=hnode);
}
else if (nodeName.equals(XMLString.TEXT_LIST) || // oasis
nodeName.equals(XMLString.TEXT_UNORDERED_LIST) || // old
nodeName.equals(XMLString.TEXT_ORDERED_LIST)) // old
{
if (listIsOnlyHeadings(child)) {
hnode = maybeSplit(hnode);
if (listIsOnlyHeadings(child)) {
nDontSplitLevel--;
hnode = handleFakeList(child,nLevel+1,styleName,hnode);
nDontSplitLevel++;
@ -412,19 +421,21 @@ public class TextConverter extends ConverterHelper {
}
}
else if (nodeName.equals(XMLString.TABLE_TABLE)) {
hnode = maybeSplit(hnode);
getTableCv().handleTable(child,hnode);
}
else if (nodeName.equals(XMLString.TABLE_SUB_TABLE)) {
getTableCv().handleTable(child,hnode);
}
else if (nodeName.equals(XMLString.TEXT_SECTION)) {
hnode = maybeSplit(hnode);
nDontSplitLevel--;
hnode = handleSection(child,hnode);
nDontSplitLevel++;
}
else if (nodeName.equals(XMLString.TEXT_TABLE_OF_CONTENT)) {
if (!ofr.getTocReader((Element)child).isByChapter()) {
hnode = maybeSplit(hnode,1,bAfterHeading);
hnode = maybeSplit(hnode,1);
}
handleTOC(child,hnode);
}
@ -441,11 +452,11 @@ public class TextConverter extends ConverterHelper {
handleUserIndex(child,hnode);
}
else if (nodeName.equals(XMLString.TEXT_ALPHABETICAL_INDEX)) {
hnode = maybeSplit(hnode,1,bAfterHeading);
hnode = maybeSplit(hnode,1);
handleAlphabeticalIndex(child,hnode);
}
else if (nodeName.equals(XMLString.TEXT_BIBLIOGRAPHY)) {
hnode = maybeSplit(hnode,1,bAfterHeading);
hnode = maybeSplit(hnode,1);
handleBibliography(child,hnode);
}
else if (nodeName.equals(XMLString.OFFICE_ANNOTATION)) {
@ -466,7 +477,21 @@ public class TextConverter extends ConverterHelper {
return hnode;
}
private Node maybeSplit(Node node, int nLevel, boolean bAfterHeading) {
private Node maybeSplit(Node node) {
if (converter.isOPS() && nCharacterCount>EPUB_CHARACTER_COUNT_TRESHOLD) {
return doMaybeSplit(node, 0);
}
return node;
}
private Node maybeSplit(Node node, int nLevel) {
if (converter.isOPS() && nCharacterCount>EPUB_CHARACTER_COUNT_TRESHOLD) {
return doMaybeSplit(node, 0);
}
return doMaybeSplit(node, nLevel);
}
private Node doMaybeSplit(Node node, int nLevel) {
if (nDontSplitLevel>1) { // we cannot split due to a nested structure
return node;
}
@ -478,6 +503,7 @@ public class TextConverter extends ConverterHelper {
}
if (nSplit>=nLevel && converter.outFileHasContent()) {
// No objections, this is a level that causes splitting
nCharacterCount = 0;
return converter.nextOutFile();
}
return node;
@ -636,7 +662,7 @@ public class TextConverter extends ConverterHelper {
boolean bIsEmpty = OfficeReader.isWhitespaceContent(onode);
if (config.ignoreEmptyParagraphs() && bIsEmpty) { return; }
String sStyleName = Misc.getAttribute(onode,XMLString.TEXT_STYLE_NAME);
Element par;
if (ofr.isSpreadsheet()) { // attach inline text directly to parent (always a table cell)
par = (Element) hnode;
@ -1044,7 +1070,7 @@ public class TextConverter extends ConverterHelper {
nDontSplitLevel++;
int nOutlineLevel = getOutlineLevel((Element)onode);
Node rememberNode = hnode;
hnode = maybeSplit(hnode,nOutlineLevel,bAfterHeading);
hnode = maybeSplit(hnode,nOutlineLevel);
handleHeading((Element)child, hnode, rememberNode!=hnode,
ofr.getListStyle(sStyleName), nLevel,
bUnNumbered, bRestart, nStartValue);

25
source/java/writer2latex/xhtml/XhtmlDocument.java
View file

@ -20,7 +20,7 @@
*
* All Rights Reserved.
*
* Version 1.2 (2010-06-19)
* Version 1.2 (2010-10-27)
*
*/
@ -598,11 +598,16 @@ public class XhtmlDocument extends DOMDocument {
else if (node.hasChildNodes()) {
int nNextLevel = (nLevel<0 || blockThis((Element)node)) ? -1 : nLevel+1;
// Print start tag
if (nLevel>=0) { writeSpaces(nLevel,osw); }
osw.write("<"+node.getNodeName());
writeAttributes(node,osw);
osw.write(">");
if (nNextLevel>=0) { osw.write("\n"); }
boolean bRedundantElement = !node.hasAttributes() &&
(node.getNodeName().equals("a") || node.getNodeName().equals("span"));
if (!bRedundantElement) {
// Writer2xhtml may produce <a> and <span> without attributes, these are removed here
if (nLevel>=0) { writeSpaces(nLevel,osw); }
osw.write("<"+node.getNodeName());
writeAttributes(node,osw);
osw.write(">");
if (nNextLevel>=0) { osw.write("\n"); }
}
// Print children
Node child = node.getFirstChild();
while (child!=null) {
@ -610,9 +615,11 @@ public class XhtmlDocument extends DOMDocument {
child = child.getNextSibling();
}
// Print end tag
if (nNextLevel>=0) { writeSpaces(nLevel,osw); }
osw.write("</"+node.getNodeName()+">");
if (nLevel>=0) { osw.write("\n"); }
if (!bRedundantElement) {
if (nNextLevel>=0) { writeSpaces(nLevel,osw); }
osw.write("</"+node.getNodeName()+">");
if (nLevel>=0) { osw.write("\n"); }
}
}
else { // empty element
if (nLevel>=0) { writeSpaces(nLevel,osw); }