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
Show stats Download patch file Download diff file Expand all files Collapse all files

11
source/distro/changelog.txt
View file

@ -2,6 +2,15 @@ Changelog for Writer2LaTeX version 1.0 -> 1.2
---------- version 1.1.5 ---------- ---------- version 1.1.5 ----------
[w2x] Automatic split of files in EPUB export after 150000 characters (to avoid problems with some EPUB readers
which has a limit on the size of the individual files)
[all] Author and date are now included in export of annotations
[w2x] No longer produce <span> and <a> elements without attributes
[w2l] Bugfix: WMF files are now correctly converted to EPS
[all] Added Norwegian Nynorsk translation from Kevin Brubeck Unhammer [all] Added Norwegian Nynorsk translation from Kevin Brubeck Unhammer
[w2x] Only create reference targets for reference marks, bookmarks and sequence numbers if reference exists [w2x] Only create reference targets for reference marks, bookmarks and sequence numbers if reference exists
@ -12,6 +21,8 @@ Changelog for Writer2LaTeX version 1.0 -> 1.2
[w2l] Bugfix: Fixed problem with lost images in some documents [w2l] Bugfix: Fixed problem with lost images in some documents
[w4l] New option page to define interaction with Zotero and with external BibTeX files
[w2l] New option: natbib_options is used to set options for natbib.sty (used by Zotero export) [w2l] New option: natbib_options is used to set options for natbib.sty (used by Zotero export)
[w2l] Added support for Zotero reference marks (with contributions from Kevin Brubeck Unhammer) [w2l] Added support for Zotero reference marks (with contributions from Kevin Brubeck Unhammer)

2098
source/distro/zotero/BibTeX-Writer2LaTeX.js Normal file
View file

File diff suppressed because it is too large Load diff

7
source/java/org/openoffice/da/comp/w2lcommon/filter/GraphicConverterImpl1.java
View file

@ -16,14 +16,13 @@
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, * Foundation, Inc., 59 Temple Place, Suite 330, Boston,
* MA 02111-1307 USA * MA 02111-1307 USA
* *
* Copyright: 2002-2009 by Henrik Just * Copyright: 2002-2010 by Henrik Just
* *
* All Rights Reserved. * All Rights Reserved.
* *
* Version 1.0 (2009-03-08) * Version 1.2 (2010-10-27)
*/ */
//
package org.openoffice.da.comp.w2lcommon.filter; package org.openoffice.da.comp.w2lcommon.filter;
@ -78,7 +77,7 @@ public class GraphicConverterImpl1 implements GraphicConverter {
if (bCrop || bResize) { return false; } if (bCrop || bResize) { return false; }
// We can convert vector formats to eps: // We can convert vector formats to eps:
if (MIMETypes.EPS.equals(sTargetMime) && (MIMETypes.WMF.equals(sSourceMime) && MIMETypes.SVM.equals(sSourceMime))) { if (MIMETypes.EPS.equals(sTargetMime) && (MIMETypes.WMF.equals(sSourceMime) || MIMETypes.SVM.equals(sSourceMime))) {
return true; return true;
} }

4
source/java/writer2latex/api/ConverterFactory.java
View file

@ -20,7 +20,7 @@
* *
* All Rights Reserved. * All Rights Reserved.
* *
* Version 1.2 (2010-10-27) * Version 1.2 (2010-10-30)
* *
*/ */
@ -33,7 +33,7 @@ public class ConverterFactory {
// Version information // Version information
private static final String VERSION = "1.1.5"; private static final String VERSION = "1.1.5";
private static final String DATE = "2010-10-27"; private static final String DATE = "2010-10-30";
/** Return the Writer2LaTeX version in the form /** Return the Writer2LaTeX version in the form
* (major version).(minor version).(patch level)<br/> * (major version).(minor version).(patch level)<br/>

41
source/java/writer2latex/latex/InlineConverter.java
View file

@ -20,7 +20,7 @@
* *
* All Rights Reserved. * All Rights Reserved.
* *
* Version 1.2 (2010-10-04) * Version 1.2 (2010-10-30)
* *
*/ */
@ -583,6 +583,8 @@ public class InlineConverter extends ConverterHelper {
case LaTeXConfig.IGNORE: return; case LaTeXConfig.IGNORE: return;
case LaTeXConfig.COMMENT: case LaTeXConfig.COMMENT:
// Get the unformatted text of all paragraphs and insert each paragraph as a single comment // Get the unformatted text of all paragraphs and insert each paragraph as a single comment
Element creator = null;
Element date = null;
ldp.append("%").nl(); ldp.append("%").nl();
Node child = node.getFirstChild(); Node child = node.getFirstChild();
while (child!=null) { while (child!=null) {
@ -591,8 +593,24 @@ public class InlineConverter extends ConverterHelper {
traversePlainInlineText((Element)child, ldp, oc); traversePlainInlineText((Element)child, ldp, oc);
ldp.nl(); ldp.nl();
} }
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(); child = child.getNextSibling();
} }
if (creator!=null) {
ldp.append("%");
traversePlainInlineText(creator, ldp, oc);
ldp.nl();
}
if (date!=null) {
ldp.append("%")
.append(Misc.formatDate(ofr.getTextContent(date), palette.getI18n().getDefaultLanguage(), null))
.nl();
}
return; return;
case LaTeXConfig.PDFANNOTATION: case LaTeXConfig.PDFANNOTATION:
bHasPdfannotation = true; bHasPdfannotation = true;
@ -608,6 +626,8 @@ public class InlineConverter extends ConverterHelper {
// Get the unformatted text of all paragraphs, separated by spaces // Get the unformatted text of all paragraphs, separated by spaces
ldp.append(sCommand).append("{"); ldp.append(sCommand).append("{");
Element creator = null;
Element date = null;
boolean bFirst = true; boolean bFirst = true;
Node child = node.getFirstChild(); Node child = node.getFirstChild();
while (child!=null) { while (child!=null) {
@ -616,9 +636,24 @@ public class InlineConverter extends ConverterHelper {
traversePlainInlineText((Element)child, ldp, oc); traversePlainInlineText((Element)child, ldp, oc);
bFirst = false; bFirst = false;
} }
child = child.getNextSibling(); 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 (!bFirst) ldp.append(" - ");
traversePlainInlineText(creator, ldp, oc);
}
if (date!=null) {
if (creator!=null) ldp.append(", ");
else if (!bFirst) ldp.append(" ");
ldp.append(Misc.formatDate(ofr.getTextContent(date), palette.getI18n().getDefaultLanguage(), null));
}
ldp.append("}"); ldp.append("}");
} }

20
source/java/writer2latex/latex/i18n/I18n.java
View file

@ -16,11 +16,11 @@
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, * Foundation, Inc., 59 Temple Place, Suite 330, Boston,
* MA 02111-1307 USA * MA 02111-1307 USA
* *
* Copyright: 2002-2009 by Henrik Just * Copyright: 2002-2010 by Henrik Just
* *
* All Rights Reserved. * All Rights Reserved.
* *
* Version 1.2 (2009-03-26) * Version 1.2 (2010-10-30)
* *
*/ */
@ -44,11 +44,11 @@ public abstract class I18n {
// Configuration items // Configuration items
protected LaTeXConfig config; protected LaTeXConfig config;
protected ReplacementTrie stringReplace; protected ReplacementTrie stringReplace;
protected boolean bGreekMath; // Use math mode for greek letters protected boolean bGreekMath; // Use math mode for Greek letters
protected boolean bAlwaysUseDefaultLang; // Ignore sLang parameter to convert() protected boolean bAlwaysUseDefaultLang; // Ignore sLang parameter to convert()
// Collected data // Collected data
protected String sDefaultLanguage; // The default iso language to use protected String sDefaultLanguage; // The default ISO language to use
protected HashSet<String> languages = new HashSet<String>(); // All languages used protected HashSet<String> languages = new HashSet<String>(); // All languages used
// **** Constructors **** // **** Constructors ****
@ -92,7 +92,7 @@ public abstract class I18n {
public abstract void appendDeclarations(LaTeXDocumentPortion pack, LaTeXDocumentPortion decl); public abstract void appendDeclarations(LaTeXDocumentPortion pack, LaTeXDocumentPortion decl);
/** Apply a language language /** Apply a language language
* @param style the OOo style to read attributesfrom * @param style the OOo style to read attributes from
* @param bDecl true if declaration form is required * @param bDecl true if declaration form is required
* @param bInherit true if inherited properties should be used * @param bInherit true if inherited properties should be used
* @param ba the <code>BeforeAfter</code> to add LaTeX code to. * @param ba the <code>BeforeAfter</code> to add LaTeX code to.
@ -111,8 +111,16 @@ public abstract class I18n {
/** Convert a string of characters into LaTeX /** Convert a string of characters into LaTeX
* @param s the source string * @param s the source string
* @param bMathMode true if the string should be rendered in math mode * @param bMathMode true if the string should be rendered in math mode
* @param sLang the iso language of the string * @param sLang the ISO language of the string
* @return the LaTeX string * @return the LaTeX string
*/ */
public abstract String convert(String s, boolean bMathMode, String sLang); public abstract String convert(String s, boolean bMathMode, String sLang);
/** Get the default language (either the document language or the most used language)
*
* @param the default language
*/
public String getDefaultLanguage() {
return sDefaultLanguage;
}
} }

21
source/java/writer2latex/util/Misc.java
View file

@ -20,7 +20,7 @@
* *
* All Rights Reserved. * All Rights Reserved.
* *
* Version 1.2 (2010-10-27) * Version 1.2 (2010-10-30)
* *
*/ */
@ -34,7 +34,12 @@ import java.io.UnsupportedEncodingException;
import java.lang.Math; import java.lang.Math;
import java.net.URLEncoder; import java.net.URLEncoder;
import java.net.URLDecoder; import java.net.URLDecoder;
import java.text.DateFormat;
import java.text.ParseException;
import java.text.SimpleDateFormat;
import java.util.Arrays; import java.util.Arrays;
import java.util.Date;
import java.util.Locale;
//import java.util.Hashtable; //import java.util.Hashtable;
import org.w3c.dom.Element; import org.w3c.dom.Element;
import org.w3c.dom.Node; import org.w3c.dom.Node;
@ -52,6 +57,20 @@ public class Misc{
for (int i=0; i<n; i++) { newArray[i] = array[i]; } for (int i=0; i<n; i++) { newArray[i] = array[i]; }
return newArray; return newArray;
} }
public static final String formatDate(String sDate, String sLanguage, String sCountry) {
SimpleDateFormat sdf = new SimpleDateFormat("yyyy-MM-dd'T'HH:mm:ss");
Date date = null;
try {
date = sdf.parse(sDate);
} catch (ParseException e) {
// If the date cannot be parsed according to the given pattern, return the original string
return sDate;
}
// Return using a default format for the given locale
Locale locale = sCountry!=null ? new Locale(sLanguage,sCountry) : new Locale(sLanguage);
return DateFormat.getDateTimeInstance(DateFormat.LONG, DateFormat.SHORT, locale).format(date);
}
public static final String int2roman(int number) { public static final String int2roman(int number) {
assert number>0; // Only works for positive numbers! assert number>0; // Only works for positive numbers!

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

@ -20,7 +20,7 @@
* *
* All Rights Reserved. * 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 // Set locale to document language
StyleWithProperties style = ofr.isSpreadsheet() ? ofr.getDefaultCellStyle() : ofr.getDefaultParStyle(); StyleWithProperties style = ofr.isSpreadsheet() ? ofr.getDefaultCellStyle() : ofr.getDefaultParStyle();
if (style!=null) { if (style!=null) {
String sLang = style.getProperty(XMLString.FO_LANGUAGE); l10n.setLocale(style.getProperty(XMLString.FO_LANGUAGE), style.getProperty(XMLString.FO_COUNTRY));
String sCountry = style.getProperty(XMLString.FO_COUNTRY);
if (sLang!=null) {
if (sCountry==null) { l10n.setLocale(sLang); }
else { l10n.setLocale(sLang+"-"+sCountry); }
}
} }
// Traverse the body // Traverse the body
@ -463,16 +458,32 @@ public class Converter extends ConverterBase {
public void handleOfficeAnnotation(Node onode, Node hnode) { public void handleOfficeAnnotation(Node onode, Node hnode) {
if (config.xhtmlNotes()) { 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(); StringBuffer buf = new StringBuffer();
Element creator = null;
Element date = null;
Node child = onode.getFirstChild(); Node child = onode.getFirstChild();
while (child!=null) { while (child!=null) {
if (Misc.isElement(child, XMLString.TEXT_P)) { if (Misc.isElement(child, XMLString.TEXT_P)) {
if (buf.length()>0) { buf.append('\n'); } if (buf.length()>0) { buf.append('\n'); }
buf.append(getPlainInlineText(child)); 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(); 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()); Node commentNode = htmlDOM.createComment(buf.toString());
hnode.appendChild(commentNode); hnode.appendChild(commentNode);
} }

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

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

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

@ -20,7 +20,7 @@
* *
* All Rights Reserved. * 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 // Data used to handle splitting over several files
// TODO: Accessor methods for sections // 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 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) 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 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 boolean bAfterHeading=false; // last element was a top level heading
protected Stack<Node> sections = new Stack<Node>(); // stack of nested sections protected Stack<Node> sections = new Stack<Node>(); // stack of nested sections
Element[] currentHeading = new Element[7]; // Last headings (repeated when splitting) 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 // Counters for generated numbers
private ListCounter outlineNumbering; private ListCounter outlineNumbering;
@ -352,6 +357,8 @@ public class TextConverter extends ConverterHelper {
getDrawCv().handleDrawElement((Element)child,(Element)hnode,null,nFloatMode); getDrawCv().handleDrawElement((Element)child,(Element)hnode,null,nFloatMode);
} }
else if (nodeName.equals(XMLString.TEXT_P)) { else if (nodeName.equals(XMLString.TEXT_P)) {
hnode = maybeSplit(hnode);
nCharacterCount+=OfficeReader.getCharacterCount(child);
// is there a block element, we should use? // is there a block element, we should use?
XhtmlStyleMap xpar = config.getXParStyleMap(); XhtmlStyleMap xpar = config.getXParStyleMap();
String sDisplayName = ofr.getParStyles().getDisplayName(Misc.getAttribute(child,XMLString.TEXT_STYLE_NAME)); 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)) { else if(nodeName.equals(XMLString.TEXT_H)) {
int nOutlineLevel = getOutlineLevel((Element)child); int nOutlineLevel = getOutlineLevel((Element)child);
Node rememberNode = hnode; Node rememberNode = hnode;
hnode = maybeSplit(hnode,nOutlineLevel,bAfterHeading); hnode = maybeSplit(hnode,nOutlineLevel);
nCharacterCount+=OfficeReader.getCharacterCount(child);
handleHeading((Element)child,hnode,rememberNode!=hnode); handleHeading((Element)child,hnode,rememberNode!=hnode);
} }
else if (nodeName.equals(XMLString.TEXT_LIST) || // oasis else if (nodeName.equals(XMLString.TEXT_LIST) || // oasis
nodeName.equals(XMLString.TEXT_UNORDERED_LIST) || // old nodeName.equals(XMLString.TEXT_UNORDERED_LIST) || // old
nodeName.equals(XMLString.TEXT_ORDERED_LIST)) // old nodeName.equals(XMLString.TEXT_ORDERED_LIST)) // old
{ {
if (listIsOnlyHeadings(child)) { hnode = maybeSplit(hnode);
if (listIsOnlyHeadings(child)) {
nDontSplitLevel--; nDontSplitLevel--;
hnode = handleFakeList(child,nLevel+1,styleName,hnode); hnode = handleFakeList(child,nLevel+1,styleName,hnode);
nDontSplitLevel++; nDontSplitLevel++;
@ -412,19 +421,21 @@ public class TextConverter extends ConverterHelper {
} }
} }
else if (nodeName.equals(XMLString.TABLE_TABLE)) { else if (nodeName.equals(XMLString.TABLE_TABLE)) {
hnode = maybeSplit(hnode);
getTableCv().handleTable(child,hnode); getTableCv().handleTable(child,hnode);
} }
else if (nodeName.equals(XMLString.TABLE_SUB_TABLE)) { else if (nodeName.equals(XMLString.TABLE_SUB_TABLE)) {
getTableCv().handleTable(child,hnode); getTableCv().handleTable(child,hnode);
} }
else if (nodeName.equals(XMLString.TEXT_SECTION)) { else if (nodeName.equals(XMLString.TEXT_SECTION)) {
hnode = maybeSplit(hnode);
nDontSplitLevel--; nDontSplitLevel--;
hnode = handleSection(child,hnode); hnode = handleSection(child,hnode);
nDontSplitLevel++; nDontSplitLevel++;
} }
else if (nodeName.equals(XMLString.TEXT_TABLE_OF_CONTENT)) { else if (nodeName.equals(XMLString.TEXT_TABLE_OF_CONTENT)) {
if (!ofr.getTocReader((Element)child).isByChapter()) { if (!ofr.getTocReader((Element)child).isByChapter()) {
hnode = maybeSplit(hnode,1,bAfterHeading); hnode = maybeSplit(hnode,1);
} }
handleTOC(child,hnode); handleTOC(child,hnode);
} }
@ -441,11 +452,11 @@ public class TextConverter extends ConverterHelper {
handleUserIndex(child,hnode); handleUserIndex(child,hnode);
} }
else if (nodeName.equals(XMLString.TEXT_ALPHABETICAL_INDEX)) { else if (nodeName.equals(XMLString.TEXT_ALPHABETICAL_INDEX)) {
hnode = maybeSplit(hnode,1,bAfterHeading); hnode = maybeSplit(hnode,1);
handleAlphabeticalIndex(child,hnode); handleAlphabeticalIndex(child,hnode);
} }
else if (nodeName.equals(XMLString.TEXT_BIBLIOGRAPHY)) { else if (nodeName.equals(XMLString.TEXT_BIBLIOGRAPHY)) {
hnode = maybeSplit(hnode,1,bAfterHeading); hnode = maybeSplit(hnode,1);
handleBibliography(child,hnode); handleBibliography(child,hnode);
} }
else if (nodeName.equals(XMLString.OFFICE_ANNOTATION)) { else if (nodeName.equals(XMLString.OFFICE_ANNOTATION)) {
@ -466,7 +477,21 @@ public class TextConverter extends ConverterHelper {
return hnode; 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 if (nDontSplitLevel>1) { // we cannot split due to a nested structure
return node; return node;
} }
@ -478,6 +503,7 @@ public class TextConverter extends ConverterHelper {
} }
if (nSplit>=nLevel && converter.outFileHasContent()) { if (nSplit>=nLevel && converter.outFileHasContent()) {
// No objections, this is a level that causes splitting // No objections, this is a level that causes splitting
nCharacterCount = 0;
return converter.nextOutFile(); return converter.nextOutFile();
} }
return node; return node;
@ -636,7 +662,7 @@ public class TextConverter extends ConverterHelper {
boolean bIsEmpty = OfficeReader.isWhitespaceContent(onode); boolean bIsEmpty = OfficeReader.isWhitespaceContent(onode);
if (config.ignoreEmptyParagraphs() && bIsEmpty) { return; } if (config.ignoreEmptyParagraphs() && bIsEmpty) { return; }
String sStyleName = Misc.getAttribute(onode,XMLString.TEXT_STYLE_NAME); String sStyleName = Misc.getAttribute(onode,XMLString.TEXT_STYLE_NAME);
Element par; Element par;
if (ofr.isSpreadsheet()) { // attach inline text directly to parent (always a table cell) if (ofr.isSpreadsheet()) { // attach inline text directly to parent (always a table cell)
par = (Element) hnode; par = (Element) hnode;
@ -1044,7 +1070,7 @@ public class TextConverter extends ConverterHelper {
nDontSplitLevel++; nDontSplitLevel++;
int nOutlineLevel = getOutlineLevel((Element)onode); int nOutlineLevel = getOutlineLevel((Element)onode);
Node rememberNode = hnode; Node rememberNode = hnode;
hnode = maybeSplit(hnode,nOutlineLevel,bAfterHeading); hnode = maybeSplit(hnode,nOutlineLevel);
handleHeading((Element)child, hnode, rememberNode!=hnode, handleHeading((Element)child, hnode, rememberNode!=hnode,
ofr.getListStyle(sStyleName), nLevel, ofr.getListStyle(sStyleName), nLevel,
bUnNumbered, bRestart, nStartValue); bUnNumbered, bRestart, nStartValue);

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

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

11
source/oxt/writer2xhtml/help/en/org.openoffice.da.writer2xhtml.oxt/export.xhp
View file

@ -143,9 +143,15 @@
<paragraph role="heading" level="3" xml-lang="en-US">Split document at headings</paragraph> <paragraph role="heading" level="3" xml-lang="en-US">Split document at headings</paragraph>
<paragraph role="paragraph" xml-lang="en-US"><ahelp hid="org.openoffice.da.writer2latex.oxt:OptionsSplit" visibility="hidden">Check this to create a new document for each heading</ahelp></paragraph> <paragraph role="paragraph" xml-lang="en-US"><ahelp hid="org.openoffice.da.writer2latex.oxt:OptionsSplit" visibility="hidden">Check this to create a new document for each heading</ahelp></paragraph>
<paragraph role="paragraph" xml-lang="en-US">To make a long Writer document easier to read in the browser, you can use <paragraph role="paragraph" xml-lang="en-US">To make a long Writer document easier to read in the browser, you can use
this option to split the document in several small files. Writer2xhtml will add a simple navigation panel that lets you this option to split the document in several small files.</paragraph>
<paragraph role="paragraph" xml-lang="en-US">For the XHTML export, Writer2xhtml will add a simple navigation panel that lets you
move between pages. The navigation links will be in the same language as the document (as defined move between pages. The navigation links will be in the same language as the document (as defined
under <emph>Tools – Options – Language Settings – Languages</emph>). Note that this option has no effect for headings under <emph>Tools – Options – Language Settings – Languages</emph>).</paragraph>
<paragraph role="paragraph" xml-lang="en-US">For the EPUB export it is highly recommended that you split at headings.
Some EPUB readers have a limitation on the size of the individual files in the document.
To avoid this, Writer2xhtml will always split your document to avoid very large files. This happens even if you have set the
heading level to 0 here.</paragraph>
<paragraph role="paragraph" xml-lang="en-US">Note that this option has no effect for headings
inside tables.</paragraph> inside tables.</paragraph>
<bookmark xml-lang="en-US" branch="hid/org.openoffice.da.writer2xhtml.oxt:OptionsSplitLevel" id="bm_options_splitlevel"/> <bookmark xml-lang="en-US" branch="hid/org.openoffice.da.writer2xhtml.oxt:OptionsSplitLevel" id="bm_options_splitlevel"/>
@ -161,6 +167,7 @@
you can use this option to repeat the parent headings whenever the document is split. If you for example split at you can use this option to repeat the parent headings whenever the document is split. If you for example split at
headings of level 3 and set this option to 2, the headings of level 1 and 2 will be repeated before the heading of level 3, headings of level 3 and set this option to 2, the headings of level 1 and 2 will be repeated before the heading of level 3,
providing precise information as to where in the document the section belongs.</paragraph> providing precise information as to where in the document the section belongs.</paragraph>
<paragraph role="paragraph" xml-lang="en-US">For the EPUB export it is recommended to set this option to 0.</paragraph>
<bookmark xml-lang="en-US" branch="hid/org.openoffice.da.writer2xhtml.oxt:OptionsSaveImagesInSubdir" id="bm_options_saveimagesinsubdir"/> <bookmark xml-lang="en-US" branch="hid/org.openoffice.da.writer2xhtml.oxt:OptionsSaveImagesInSubdir" id="bm_options_saveimagesinsubdir"/>
<paragraph role="paragraph" xml-lang="en-US"><ahelp hid="org.openoffice.da.writer2latex.oxt:OptionsSaveImagesInSubdir" visibility="hidden">Check this to save images in a subdirectory relative to the exported document</ahelp></paragraph> <paragraph role="paragraph" xml-lang="en-US"><ahelp hid="org.openoffice.da.writer2latex.oxt:OptionsSaveImagesInSubdir" visibility="hidden">Check this to save images in a subdirectory relative to the exported document</ahelp></paragraph>

27
source/oxt/writer4latex/help/en/org.openoffice.da.writer4latex.oxt/bibliography.xhp
View file

@ -29,11 +29,22 @@
<bookmark xml-lang="en-US" branch="hid/org.openoffice.da.writer4latex.oxt:BibliographyZoteroBibTeXDir" id="bm_zoterobibtexdir"/> <bookmark xml-lang="en-US" branch="hid/org.openoffice.da.writer4latex.oxt:BibliographyZoteroBibTeXDir" id="bm_zoterobibtexdir"/>
<paragraph role="heading" level="3" xml-lang="en-US">BibTeX folder</paragraph> <paragraph role="heading" level="3" xml-lang="en-US">BibTeX folder</paragraph>
<paragraph role="paragraph" xml-lang="en-US">To use this feature you also have to export your Zotero bibliography databse to BibTeX. <paragraph role="paragraph" xml-lang="en-US">To use this feature you also have to export your Zotero bibliography database
(TODO).</paragraph> to BibTeX.</paragraph>
<paragraph role="paragraph" xml-lang="en-US">Type the full path to the directory containing the exported database or click <paragraph role="paragraph" xml-lang="en-US">Type the full path to the folder containing the exported database or click
<emph>Browse</emph> to find the directory in your file system.</paragraph> <emph>Browse</emph> to find the folder in your file system.</paragraph>
<paragraph role="paragraph" xml-lang="en-US"><ahelp hid="org.openoffice.da.writer4latex.oxt:BibliographyZoteroBibTeXDir" visibility="hidden">Enter the path to the directory containing the BibTeX file exported from Zotero</ahelp></paragraph> <paragraph role="heading" level="4" xml-lang="en-US">Exporting your Zotero database to BibTeX</paragraph>
<paragraph role="paragraph" xml-lang="en-US">To use this feature you must export your Zotero database to the specified
folder.</paragraph>
<paragraph role="paragraph" xml-lang="en-US">The Writer2LaTeX distribution contains a folder named <emph>Zotero</emph>,
which contains a file called <emph>BibTeX-Writer2LaTeX.js</emph>. This file must be added to Zotero to provide a suitable
BibTeX export: In Zotero, choose <emph>Preferences</emph> - <emph>Advanced</emph> and click <emph>Show Data Directory</emph>.
Open the subfolder <emph>Translators</emph>, and copy <emph>BibTeX-Writer2LaTeX.js</emph> to this location.
Finally restart Firefox.</paragraph>
<paragraph role="paragraph" xml-lang="en-US">You can now export your Zotero database: In Zotero, select
<emph>Export Library</emph>, and choose <emph>BibTeX (Writer2LaTeX)</emph> (not <emph>BibTeX</emph>).
Save the file in the folder, you have defined.</paragraph>
<paragraph role="paragraph" xml-lang="en-US"><ahelp hid="org.openoffice.da.writer4latex.oxt:BibliographyZoteroBibTeXDir" visibility="hidden">Enter the path to the folder containing the BibTeX file exported from Zotero</ahelp></paragraph>
<bookmark xml-lang="en-US" branch="hid/org.openoffice.da.writer4latex.oxt:BibliographyNatbibOptions" id="bm_natbiboptions"/> <bookmark xml-lang="en-US" branch="hid/org.openoffice.da.writer4latex.oxt:BibliographyNatbibOptions" id="bm_natbiboptions"/>
<paragraph role="heading" level="3" xml-lang="en-US">Natbib Options</paragraph> <paragraph role="heading" level="3" xml-lang="en-US">Natbib Options</paragraph>
@ -54,9 +65,9 @@
<bookmark xml-lang="en-US" branch="hid/org.openoffice.da.writer4latex.oxt:BibliographyExternalBibTeXDir" id="bm_externalbibtexdir"/> <bookmark xml-lang="en-US" branch="hid/org.openoffice.da.writer4latex.oxt:BibliographyExternalBibTeXDir" id="bm_externalbibtexdir"/>
<paragraph role="heading" level="3" xml-lang="en-US">BibTeX folder</paragraph> <paragraph role="heading" level="3" xml-lang="en-US">BibTeX folder</paragraph>
<paragraph role="paragraph" xml-lang="en-US">Type the full path to the directory containing the BibTeX database(s) or click <paragraph role="paragraph" xml-lang="en-US">Type the full path to the folder containing the BibTeX database(s) or click
<emph>Browse</emph> to find the directory in your file system.</paragraph> <emph>Browse</emph> to find the folder in your file system.</paragraph>
<paragraph role="paragraph" xml-lang="en-US"><ahelp hid="org.openoffice.da.writer4latex.oxt:Bibliography" visibility="hidden">Enter the path to the directory containing the BibTeX files</ahelp></paragraph> <paragraph role="paragraph" xml-lang="en-US"><ahelp hid="org.openoffice.da.writer4latex.oxt:Bibliography" visibility="hidden">Enter the path to the folder containing the BibTeX files</ahelp></paragraph>
</body> </body>
</helpdocument> </helpdocument>