@Override public AbstractUndoableEdit remove(BibtexEntry[] entries) { if (!supportsRemove()) { return null; } if (entries != null && entries.length > 0) { NamedCompound ce = new NamedCompound(Globals.lang("remove from group")); boolean modified = false; for (BibtexEntry entry : entries) { if (getSearchRule().applyRule(SearchRule.NULL_QUERY, entry)) { String oldContent = entry.getField(searchField); removeMatches(entry); // Store undo information. ce.addEdit( new UndoableFieldChange(entry, searchField, oldContent, entry.getField(searchField))); modified = true; } } if (modified) { ce.end(); } return modified ? ce : null; } return null; }
private void parseField(BibtexEntry entry) throws IOException { String key = parseTextToken().toLowerCase(); // Util.pr("Field: _"+key+"_"); skipWhitespace(); consume('='); String content = parseFieldContent(key); // Now, if the field in question is set up to be fitted automatically // with braces around // capitals, we should remove those now when reading the field: if (Globals.prefs.putBracesAroundCapitals(key)) { content = Util.removeBracesAroundCapitals(content); } if (content.length() > 0) { if (entry.getField(key) == null) entry.setField(key, content); else { // The following hack enables the parser to deal with multiple // author or // editor lines, stringing them together instead of getting just // one of them. // Multiple author or editor lines are not allowed by the bibtex // format, but // at least one online database exports bibtex like that, making // it inconvenient // for users if JabRef didn't accept it. if (key.equals("author") || key.equals("editor")) entry.setField(key, entry.getField(key) + " and " + content); } } }
public void mouseClicked(MouseEvent e) { if (e.isPopupTrigger()) { processPopupTrigger(e); return; } // if (e.) final int col = entryTable.columnAtPoint(e.getPoint()), row = entryTable.rowAtPoint(e.getPoint()); if (col < PAD) { BibtexEntry entry = sortedEntries.get(row); BasePanel p = entryHome.get(entry); switch (col) { case FILE_COL: Object o = entry.getField(GUIGlobals.FILE_FIELD); if (o != null) { FileListTableModel tableModel = new FileListTableModel(); tableModel.setContent((String) o); if (tableModel.getRowCount() == 0) return; FileListEntry fl = tableModel.getEntry(0); (new ExternalFileMenuItem( frame, entry, "", fl.getLink(), null, p.metaData(), fl.getType())) .actionPerformed(null); } break; case URL_COL: Object link = entry.getField("url"); try { if (link != null) Util.openExternalViewer(p.metaData(), (String) link, "url"); } catch (IOException ex) { ex.printStackTrace(); } break; } } }
public Object getColumnValue(BibtexEntry entry, int column) { if (column < PAD) { Object o; switch (column) { case FILE_COL: o = entry.getField(GUIGlobals.FILE_FIELD); if (o != null) { FileListTableModel model = new FileListTableModel(); model.setContent((String) o); fileLabel.setToolTipText(model.getToolTipHTMLRepresentation()); if (model.getRowCount() > 0) fileLabel.setIcon(model.getEntry(0).getType().getIcon()); return fileLabel; } else return null; case URL_COL: o = entry.getField("url"); if (o != null) { urlLabel.setToolTipText((String) o); return urlLabel; } else return null; default: return null; } } else { String field = fields[column - PAD]; if (field.equals("author") || field.equals("editor")) { // For name fields, tap into a MainTableFormat instance and use // the same name formatting as is used in the entry table: if (frame.basePanel() != null) return frame.basePanel().tableFormat.formatName(entry.getField(field)); } return entry.getField(field); } }
/** * updates field values according to keywords * * @param ce indicates the undo named compound. May be null */ public static void syncSpecialFieldsFromKeywords(BibtexEntry be, NamedCompound ce) { if (be.getField("keywords") == null) { return; } ArrayList<String> keywordList = Util.getSeparatedKeywords(be.getField("keywords")); SpecialFieldsUtils.importKeywordsForField(keywordList, Priority.getInstance(), be, ce); SpecialFieldsUtils.importKeywordsForField(keywordList, Rank.getInstance(), be, ce); SpecialFieldsUtils.importKeywordsForField(keywordList, Quality.getInstance(), be, ce); SpecialFieldsUtils.importKeywordsForField(keywordList, Relevance.getInstance(), be, ce); SpecialFieldsUtils.importKeywordsForField(keywordList, ReadStatus.getInstance(), be, ce); SpecialFieldsUtils.importKeywordsForField(keywordList, Printed.getInstance(), be, ce); }
/** * Removes matches of searchString in the entry's field. This is only possible if the search * expression is not a regExp. */ private void removeMatches(BibtexEntry entry) { String content = entry.getField(searchField); if (content == null) { return; // nothing to modify } StringBuffer sbOrig = new StringBuffer(content); StringBuffer sbLower = new StringBuffer(content.toLowerCase()); StringBuffer haystack = caseSensitive ? sbOrig : sbLower; String needle = caseSensitive ? searchExpression : searchExpression.toLowerCase(); int i; int j; int k; final String separator = Globals.prefs.get(JabRefPreferences.GROUP_KEYWORD_SEPARATOR); while ((i = haystack.indexOf(needle)) >= 0) { sbOrig.replace(i, i + needle.length(), ""); sbLower.replace(i, i + needle.length(), ""); // reduce spaces at i to 1 j = i; k = i; while (j - 1 >= 0 && separator.indexOf(haystack.charAt(j - 1)) >= 0) { --j; } while (k < haystack.length() && separator.indexOf(haystack.charAt(k)) >= 0) { ++k; } sbOrig.replace(j, k, j >= 0 && k < sbOrig.length() ? separator : ""); sbLower.replace(j, k, j >= 0 && k < sbOrig.length() ? separator : ""); } String result = sbOrig.toString().trim(); entry.setField(searchField, !result.isEmpty() ? result : null); }
@Override public AbstractUndoableEdit add(BibtexEntry[] entries) { if (!supportsAdd()) { return null; } if (entries != null && entries.length > 0) { NamedCompound ce = new NamedCompound(Globals.lang("add entries to group")); boolean modified = false; for (BibtexEntry entry : entries) { if (!getSearchRule().applyRule(SearchRule.NULL_QUERY, entry)) { String oldContent = entry.getField(searchField); String pre = Globals.prefs.get(JabRefPreferences.GROUP_KEYWORD_SEPARATOR); String newContent = (oldContent == null ? "" : oldContent + pre) + searchExpression; entry.setField(searchField, newContent); // Store undo information. ce.addEdit(new UndoableFieldChange(entry, searchField, oldContent, newContent)); modified = true; } } if (modified) { ce.end(); } return modified ? ce : null; } return null; }
/** * If the user has signalled the opening of a context menu, the event gets redirected to this * method. Here we open a file link menu if the user is pointing at a file link icon. Otherwise * a general context menu should be shown. * * @param e The triggering mouse event. */ public void processPopupTrigger(MouseEvent e) { BibtexEntry entry = sortedEntries.get(entryTable.rowAtPoint(e.getPoint())); BasePanel p = entryHome.get(entry); int col = entryTable.columnAtPoint(e.getPoint()); JPopupMenu menu = new JPopupMenu(); int count = 0; if (col == FILE_COL) { // We use a FileListTableModel to parse the field content: Object o = entry.getField(GUIGlobals.FILE_FIELD); FileListTableModel fileList = new FileListTableModel(); fileList.setContent((String) o); // If there are one or more links, open the first one: for (int i = 0; i < fileList.getRowCount(); i++) { FileListEntry flEntry = fileList.getEntry(i); String description = flEntry.getDescription(); if ((description == null) || (description.trim().length() == 0)) description = flEntry.getLink(); menu.add( new ExternalFileMenuItem( p.frame(), entry, description, flEntry.getLink(), flEntry.getType().getIcon(), p.metaData(), flEntry.getType())); count++; } } if (count > 0) menu.show(entryTable, e.getX(), e.getY()); }
public boolean compare(BibtexEntry entry) { // specification of fields to search is done in the search expression itself String[] searchKeys = entry.getAllFields().toArray(new String[entry.getAllFields().size()]); boolean noSuchField = true; // this loop iterates over all regular keys, then over pseudo keys like "type" for (int i = 0; i < searchKeys.length + 1; i++) { String content; if (i - searchKeys.length == 0) { // PSEUDOFIELD_TYPE if (!fieldPattern.matcher("entrytype").matches()) continue; content = entry.getType().getName(); } else { String searchKey = searchKeys[i]; if (!fieldPattern.matcher(searchKey).matches()) continue; content = entry.getField(searchKey); } noSuchField = false; if (content == null) continue; // paranoia if (matchInField(content)) { return true; } } return noSuchField && operator == ComparisonOperator.DOES_NOT_CONTAIN; }
/** * Check the database to find out whether any of a set of fields are used for any of the entries. * * @param database The bib database. * @param fields The set of fields to look for. * @return true if at least one of the given fields is set in at least one entry, false otherwise. */ private boolean linksFound(BibtexDatabase database, String[] fields) { for (BibtexEntry entry : database.getEntries()) { for (String field : fields) { if (entry.getField(field) != null) { return true; } } } return false; }
/** * @param e - Field to be handled * @param value - may be null to state that field should be emptied * @param be - BibTeXEntry to be handled * @param ce - Filled with undo info (if necessary) * @param nullFieldIfValueIsTheSame - true: field is nulled if value is the same than the current * value in be */ public static void updateField( SpecialField e, String value, BibtexEntry be, NamedCompound ce, boolean nullFieldIfValueIsTheSame) { Util.updateField(be, e.getFieldName(), value, ce, nullFieldIfValueIsTheSame); // we cannot use "value" here as updateField has side effects: "nullFieldIfValueIsTheSame" nulls // the field if value is the same SpecialFieldsUtils.exportFieldToKeywords(e, be.getField(e.getFieldName()), be, ce); }
@Override public boolean contains(BibtexEntry entry) { String content = entry.getField(searchField); if (content == null) { return false; } if (regExp) { return pattern.matcher(content).find(); } if (caseSensitive) { return KeywordGroup.containsWord(searchExpression, content); } return KeywordGroup.containsWord(searchExpression.toLowerCase(), content.toLowerCase()); }
public static void removeDOIfromBibtexEntryField( BibtexEntry bes, String fieldName, NamedCompound ce) { String origValue = bes.getField(fieldName); String value = origValue; value = value.replaceAll(REGEXP_DOI_WITH_HTTP_PREFIX, ""); value = value.replaceAll(REGEXP_PLAINDOI, ""); value = value.trim(); if (value.isEmpty()) { value = null; } if (!origValue.equals(value)) { ce.addEdit(new UndoableFieldChange(bes, fieldName, origValue, value)); bes.setField(fieldName, value); } }
private void insertFields(String[] fields, BibtexEntry entry, XmlDocument xmlDocument) { DocumentWrapper document = new DocumentWrapper(xmlDocument); for (String field : fields) { if (entry.getField(field) != null) { continue; } if (field.equalsIgnoreCase("author")) { entry.setField(field, document.getAuthors("and")); } if (field.equalsIgnoreCase("title")) { entry.setField(field, document.getTitle()); } if (field.equalsIgnoreCase("abstract")) { entry.setField(field, document.getAbstract()); } if (field.equalsIgnoreCase("keywords")) { entry.setField(field, document.getKeyWords()); } if (field.equalsIgnoreCase("doi")) { entry.setField(field, document.getDoi()); } if (field.equalsIgnoreCase("pages")) { entry.setField(field, document.getPages()); } if (field.equalsIgnoreCase("volume")) { entry.setField(field, document.getVolume()); } if (field.equalsIgnoreCase("number")) { entry.setField(field, document.getNumber()); } if (field.equalsIgnoreCase("year")) { entry.setField(field, document.getYear()); } if (field.equalsIgnoreCase("month")) { entry.setField(field, document.getMonth()); } if (field.equalsIgnoreCase("day")) { entry.setField(field, document.getDay()); } if (field.equalsIgnoreCase("booktitle")) { entry.setField(field, document.getVenue()); } if (field.equalsIgnoreCase("journal")) { entry.setField(field, document.getVenue()); } } }
@Override public boolean applyRule(String query, BibtexEntry bibtexEntry) { String searchString = query; if (!caseSensitive) { searchString = searchString.toLowerCase(); } List<String> words = new SentenceAnalyzer(searchString).getWords(); // We need match for all words: boolean[] matchFound = new boolean[words.size()]; for (String field : bibtexEntry.getAllFields()) { Object fieldContentAsObject = bibtexEntry.getField(field); if (fieldContentAsObject != null) { String fieldContent = ContainBasedSearchRule.REMOVE_LATEX_COMMANDS.format(fieldContentAsObject.toString()); if (!caseSensitive) { fieldContent = fieldContent.toLowerCase(); } int index = 0; // Check if we have a match for each of the query words, ignoring // those words for which we already have a match: for (String word : words) { matchFound[index] = matchFound[index] || fieldContent.contains(word); index++; } } } for (boolean aMatchFound : matchFound) { if (!aMatchFound) { return false; // Didn't match all words. } } return true; // Matched all words. }
private void parse(ImportInspector dialog, String text, int startIndex, int firstEntryNumber) { piv = startIndex; int entryNumber = firstEntryNumber; if (importBibtex) { // TODO: Login ArrayList<String> idSelected = new ArrayList<String>(); String id; while ((id = parseNextEntryId(text, piv)) != null && shouldContinue) { idSelected.add(id); entryNumber++; } try { BibtexDatabase dbase = parseBibtexDatabase(idSelected, includeAbstract); Collection<BibtexEntry> items = dbase.getEntries(); for (BibtexEntry entry : items) { dialog.addEntry(cleanup(entry)); dialog.setProgress(parsed + unparseable, hits); parsed++; } } catch (IOException e) { e.printStackTrace(); } // for } else { BibtexEntry entry; while ((entry = parseNextEntry(text, piv)) != null && shouldContinue) { if (entry.getField("title") != null) { dialog.addEntry(entry); dialog.setProgress(parsed + unparseable, hits); parsed++; } entryNumber++; } } }
public void run() { if (!goOn) return; for (int i = 0; i < entries.length; i++) { BibtexEntry entry = entries[i]; // Make a list of all PDFs linked from this entry: List<File> files = new ArrayList<File>(); // First check the (legacy) "pdf" field: String pdf = entry.getField("pdf"); String dir = panel.metaData().getFileDirectory("pdf"); File f = Util.expandFilename(pdf, new String[] {dir, "."}); if (f != null) files.add(f); // Then check the "file" field: dir = panel.metaData().getFileDirectory(GUIGlobals.FILE_FIELD); String field = entry.getField(GUIGlobals.FILE_FIELD); if (field != null) { FileListTableModel tm = new FileListTableModel(); tm.setContent(field); for (int j = 0; j < tm.getRowCount(); j++) { FileListEntry flEntry = tm.getEntry(j); if ((flEntry.getType() != null) && (flEntry.getType().getName().toLowerCase().equals("pdf"))) { f = Util.expandFilename(flEntry.getLink(), new String[] {dir, "."}); if (f != null) files.add(f); } } } optDiag.progressArea.append(entry.getCiteKey() + "\n"); if (files.size() == 0) { skipped++; optDiag.progressArea.append(" " + Globals.lang("Skipped - No PDF linked") + ".\n"); } else for (File file : files) { if (!file.exists()) { skipped++; optDiag.progressArea.append( " " + Globals.lang("Skipped - PDF does not exist") + ":\n"); optDiag.progressArea.append(" " + file.getPath() + "\n"); } else { try { XMPUtil.writeXMP(file, entry, database); optDiag.progressArea.append(" " + Globals.lang("Ok") + ".\n"); entriesChanged++; } catch (Exception e) { optDiag.progressArea.append( " " + Globals.lang("Error while writing") + " '" + file.getPath() + "':\n"); optDiag.progressArea.append(" " + e.getLocalizedMessage() + "\n"); errors++; } } } if (optDiag.canceled) { optDiag.progressArea.append("\n" + Globals.lang("Operation canceled.\n")); break; } } optDiag.progressArea.append( "\n" + Globals.lang( "Finished writing XMP for %0 file (%1 skipped, %2 errors).", String.valueOf(entriesChanged), String.valueOf(skipped), String.valueOf(errors))); optDiag.done(); }
private static void exportFieldToKeywords(SpecialField e, BibtexEntry be, NamedCompound ce) { SpecialFieldsUtils.exportFieldToKeywords(e, be.getField(e.getFieldName()), be, ce); }
private BibtexEntry cleanup(BibtexEntry entry) { if (entry == null) { return null; } // clean up title String title = entry.getField("title"); if (title != null) { // USe the alt-text and replace image links title = title.replaceAll("[ ]?img src=[^ ]+ alt=\"([^\"]+)\">[ ]?", "\\$$1\\$"); // Try to sort out most of the /spl / conversions // Deal with this specific nested type first title = title.replaceAll("/sub /spl infin//", "\\$_\\\\infty\\$"); title = title.replaceAll("/sup /spl infin//", "\\$\\^\\\\infty\\$"); // Replace general expressions title = title.replaceAll("/[sS]pl ([^/]+)/", "\\$\\\\$1\\$"); // Deal with subscripts and superscripts if (Globals.prefs.getBoolean(JabRefPreferences.USE_CONVERT_TO_EQUATION)) { title = title.replaceAll("/sup ([^/]+)/", "\\$\\^\\{$1\\}\\$"); title = title.replaceAll("/sub ([^/]+)/", "\\$_\\{$1\\}\\$"); title = title.replaceAll("\\(sup\\)([^(]+)\\(/sup\\)", "\\$\\^\\{$1\\}\\$"); title = title.replaceAll("\\(sub\\)([^(]+)\\(/sub\\)", "\\_\\{$1\\}\\$"); } else { title = title.replaceAll("/sup ([^/]+)/", "\\\\textsuperscript\\{$1\\}"); title = title.replaceAll("/sub ([^/]+)/", "\\\\textsubscript\\{$1\\}"); title = title.replaceAll("\\(sup\\)([^(]+)\\(/sup\\)", "\\\\textsuperscript\\{$1\\}"); title = title.replaceAll("\\(sub\\)([^(]+)\\(/sub\\)", "\\\\textsubscript\\{$1\\}"); } // Replace \infin with \infty title = title.replaceAll("\\\\infin", "\\\\infty"); // Unit formatting if (Globals.prefs.getBoolean(JabRefPreferences.USE_UNIT_FORMATTER_ON_SEARCH)) { title = unitFormatter.format(title); } // Automatic case keeping if (Globals.prefs.getBoolean(JabRefPreferences.USE_CASE_KEEPER_ON_SEARCH)) { title = caseKeeper.format(title); } // Write back entry.setField("title", title); } // clean up author /* String author = (String)entry.getField("author"); if (author != null) { if (author.indexOf("a href=") >= 0) { // Author parsing failed because it was empty entry.setField("author",""); // Maybe not needed anymore due to another change } else { author = author.replaceAll("\\s+", " "); author = author.replaceAll("\\.", ". "); author = author.replaceAll("([^;]+),([^;]+),([^;]+)","$1,$3,$2"); // Change order in case of Jr. etc author = author.replaceAll(" ", " "); author = author.replaceAll("\\. -", ".-"); author = author.replaceAll("; ", " and "); author = author.replaceAll(" ,", ","); author = author.replaceAll(" ", " "); author = author.replaceAll("[ ,;]+$", ""); entry.setField("author", author); } }*/ // clean up month String month = entry.getField("month"); if (month != null && !month.isEmpty()) { month = month.replaceAll("\\.", ""); month = month.toLowerCase(); Pattern monthPattern = Pattern.compile("(\\d*+)\\s*([a-z]*+)-*(\\d*+)\\s*([a-z]*+)"); Matcher mm = monthPattern.matcher(month); String date = month; if (mm.find()) { if (mm.group(3).isEmpty()) { if (!mm.group(2).isEmpty()) { date = "#" + mm.group(2).substring(0, 3) + "#"; if (!mm.group(1).isEmpty()) { date += " " + mm.group(1) + ","; } } else { date = mm.group(1) + ","; } } else if (mm.group(2).isEmpty()) { if (!mm.group(4).isEmpty()) { date = "#" + mm.group(4).substring(0, 3) + "# " + mm.group(1) + "--" + mm.group(3) + ","; } else { date += ","; } } else { date = "#" + mm.group(2).substring(0, 3) + "# " + mm.group(1) + "--#" + mm.group(4).substring(0, 3) + "# " + mm.group(3) + ","; } } // date = date.trim(); // if (!date.isEmpty()) { entry.setField("month", date); // } } // clean up pages String field = "pages"; String pages = entry.getField(field); if (pages != null) { String[] pageNumbers = pages.split("-"); if (pageNumbers.length == 2) { if (pageNumbers[0].equals(pageNumbers[1])) { // single page entry.setField(field, pageNumbers[0]); } else { entry.setField(field, pages.replaceAll("-", "--")); } } } // clean up publication field BibtexEntryType type = entry.getType(); String sourceField = ""; if (type.getName().equals("Article")) { sourceField = "journal"; entry.clearField("booktitle"); } else if (type.getName().equals("Inproceedings")) { sourceField = "booktitle"; } String fullName = entry.getField(sourceField); if (fullName != null) { if (type.getName().equals("Article")) { int ind = fullName.indexOf(": Accepted for future publication"); if (ind > 0) { fullName = fullName.substring(0, ind); entry.setField("year", "to be published"); entry.clearField("month"); entry.clearField("pages"); entry.clearField("number"); } String[] parts = fullName.split("[\\[\\]]"); // [see also...], [legacy...] fullName = parts[0]; if (parts.length == 3) { fullName += parts[2]; } if (entry.getField("note").equals("Early Access")) { entry.setField("year", "to be published"); entry.clearField("month"); entry.clearField("pages"); entry.clearField("number"); } } else { fullName = fullName .replace("Conference Proceedings", "Proceedings") .replace("Proceedings of", "Proceedings") .replace("Proceedings.", "Proceedings"); fullName = fullName.replaceAll("International", "Int."); fullName = fullName.replaceAll("Symposium", "Symp."); fullName = fullName.replaceAll("Conference", "Conf."); fullName = fullName.replaceAll(" on", " ").replace(" ", " "); } Matcher m1 = publicationPattern.matcher(fullName); String abrvPattern = ".*[^,] '?\\d+\\)?"; if (m1.find()) { String prefix = m1.group(2).trim(); String postfix = m1.group(1).trim(); String abrv = ""; String[] parts = prefix.split("\\. ", 2); if (parts.length == 2) { if (parts[0].matches(abrvPattern)) { prefix = parts[1]; abrv = parts[0]; } else { prefix = parts[0]; abrv = parts[1]; } } if (!prefix.matches(abrvPattern)) { fullName = prefix + " " + postfix + " " + abrv; fullName = fullName.trim(); } else { fullName = postfix + " " + prefix; } } if (type.getName().equals("Article")) { fullName = fullName.replace(" - ", "-"); // IEE Proceedings- fullName = fullName.trim(); if (Globals.prefs.getBoolean(JabRefPreferences.USE_IEEE_ABRV)) { fullName = Globals.journalAbbrev.getMedlineAbbreviation(fullName).orElse(fullName); } } if (type.getName().equals("Inproceedings")) { Matcher m2 = proceedingPattern.matcher(fullName); if (m2.find()) { String prefix = m2.group(2); String postfix = m2.group(1).replaceAll("\\.$", ""); if (!prefix.matches(abrvPattern)) { String abrv = ""; String[] parts = postfix.split("\\. ", 2); if (parts.length == 2) { if (parts[0].matches(abrvPattern)) { postfix = parts[1]; abrv = parts[0]; } else { postfix = parts[0]; abrv = parts[1]; } } fullName = prefix.trim() + " " + postfix.trim() + " " + abrv; } else { fullName = postfix.trim() + " " + prefix.trim(); } } fullName = fullName.trim(); fullName = fullName.replaceAll("^[tT]he ", "").replaceAll("^\\d{4} ", "").replaceAll("[,.]$", ""); String year = entry.getField("year"); fullName = fullName.replaceAll(", " + year + "\\.?", ""); if (!fullName.contains("Abstract") && !fullName.contains("Summaries") && !fullName.contains("Conference Record")) { fullName = "Proc. " + fullName; } } entry.setField(sourceField, fullName); } // clean up abstract String abstr = entry.getField("abstract"); if (abstr != null) { // Try to sort out most of the /spl / conversions // Deal with this specific nested type first abstr = abstr.replaceAll("/sub /spl infin//", "\\$_\\\\infty\\$"); abstr = abstr.replaceAll("/sup /spl infin//", "\\$\\^\\\\infty\\$"); // Replace general expressions abstr = abstr.replaceAll("/[sS]pl ([^/]+)/", "\\$\\\\$1\\$"); // Deal with subscripts and superscripts if (Globals.prefs.getBoolean(JabRefPreferences.USE_CONVERT_TO_EQUATION)) { abstr = abstr.replaceAll("/sup ([^/]+)/", "\\$\\^\\{$1\\}\\$"); abstr = abstr.replaceAll("/sub ([^/]+)/", "\\$_\\{$1\\}\\$"); abstr = abstr.replaceAll("\\(sup\\)([^(]+)\\(/sup\\)", "\\$\\^\\{$1\\}\\$"); abstr = abstr.replaceAll("\\(sub\\)([^(]+)\\(/sub\\)", "\\_\\{$1\\}\\$"); } else { abstr = abstr.replaceAll("/sup ([^/]+)/", "\\\\textsuperscript\\{$1\\}"); abstr = abstr.replaceAll("/sub ([^/]+)/", "\\\\textsubscript\\{$1\\}"); abstr = abstr.replaceAll("\\(sup\\)([^(]+)\\(/sup\\)", "\\\\textsuperscript\\{$1\\}"); abstr = abstr.replaceAll("\\(sub\\)([^(]+)\\(/sub\\)", "\\\\textsubscript\\{$1\\}"); } // Replace \infin with \infty abstr = abstr.replaceAll("\\\\infin", "\\\\infty"); // Write back entry.setField("abstract", abstr); } // Clean up url String url = entry.getField("url"); if (url != null) { entry.setField("url", "http://ieeexplore.ieee.org" + url.replace("tp=&", "")); } return entry; }
private BibtexEntry parseNextEntry(String allText, int startIndex) { BibtexEntry entry = null; int index = allText.indexOf("<div class=\"detail", piv); int endIndex = allText.indexOf("</div>", index); if (index >= 0 && endIndex > 0) { endIndex += 6; piv = endIndex; String text = allText.substring(index, endIndex); BibtexEntryType type = null; String sourceField = null; String typeName = ""; Matcher typeMatcher = typePattern.matcher(text); if (typeMatcher.find()) { typeName = typeMatcher.group(1); if (typeName.equalsIgnoreCase("IEEE Journals & Magazines") || typeName.equalsIgnoreCase("IEEE Early Access Articles") || typeName.equalsIgnoreCase("IET Journals & Magazines") || typeName.equalsIgnoreCase("AIP Journals & Magazines") || typeName.equalsIgnoreCase("AVS Journals & Magazines") || typeName.equalsIgnoreCase("IBM Journals & Magazines") || typeName.equalsIgnoreCase("TUP Journals & Magazines") || typeName.equalsIgnoreCase("BIAI Journals & Magazines")) { type = BibtexEntryType.getType("article"); sourceField = "journal"; } else if (typeName.equalsIgnoreCase("IEEE Conference Publications") || typeName.equalsIgnoreCase("IET Conference Publications") || typeName.equalsIgnoreCase("VDE Conference Publications")) { type = BibtexEntryType.getType("inproceedings"); sourceField = "booktitle"; } else if (typeName.equalsIgnoreCase("IEEE Standards") || typeName.equalsIgnoreCase("Standards")) { type = BibtexEntryType.getType("standard"); sourceField = "number"; } else if (typeName.equalsIgnoreCase("IEEE eLearning Library Courses")) { type = BibtexEntryType.getType("Electronic"); sourceField = "note"; } else if (typeName.equalsIgnoreCase("Wiley-IEEE Press eBook Chapters") || typeName.equalsIgnoreCase("MIT Press eBook Chapters") || typeName.equalsIgnoreCase("IEEE USA Books & eBooks")) { type = BibtexEntryType.getType("inCollection"); sourceField = "booktitle"; } } if (type == null) { type = BibtexEntryType.getType("misc"); sourceField = "note"; System.err.println("Type detection failed. Use MISC instead."); unparseable++; System.err.println(text); } entry = new BibtexEntry(IdGenerator.next(), type); if (typeName.equalsIgnoreCase("IEEE Standards")) { entry.setField("organization", "IEEE"); } if (typeName.equalsIgnoreCase("Wiley-IEEE Press eBook Chapters")) { entry.setField("publisher", "Wiley-IEEE Press"); } else if (typeName.equalsIgnoreCase("MIT Press eBook Chapters")) { entry.setField("publisher", "MIT Press"); } else if (typeName.equalsIgnoreCase("IEEE USA Books & eBooks")) { entry.setField("publisher", "IEEE USA"); } if (typeName.equalsIgnoreCase("IEEE Early Access Articles")) { entry.setField("note", "Early Access"); } Set<String> fields = fieldPatterns.keySet(); for (String field : fields) { Matcher fieldMatcher = Pattern.compile(fieldPatterns.get(field)).matcher(text); if (fieldMatcher.find()) { entry.setField(field, htmlConverter.format(fieldMatcher.group(1))); if (field.equals("title") && fieldMatcher.find()) { String sec_title = htmlConverter.format(fieldMatcher.group(1)); if (entry.getType() == BibtexEntryType.getStandardType("standard")) { sec_title = sec_title.replaceAll("IEEE Std ", ""); } entry.setField(sourceField, sec_title); } if (field.equals("pages") && fieldMatcher.groupCount() == 2) { entry.setField(field, fieldMatcher.group(1) + "-" + fieldMatcher.group(2)); } } } Matcher authorMatcher = authorPattern.matcher(text); // System.out.println(text); StringBuilder authorNames = new StringBuilder(""); int authorCount = 0; while (authorMatcher.find()) { if (authorCount >= 1) { authorNames.append(" and "); } authorNames.append(htmlConverter.format(authorMatcher.group(1))); // System.out.println(authorCount + ": " + authorMatcher.group(1)); authorCount++; } entry.setField("author", authorNames.toString()); if (entry.getField("author") == null || entry.getField("author").startsWith("a href") || entry .getField("author") .startsWith("Topic(s)")) { // Fix for some documents without authors entry.setField("author", ""); } if (entry.getType() == BibtexEntryType.getStandardType("inproceedings") && entry.getField("author").equals("")) { entry.setType(BibtexEntryType.getStandardType("proceedings")); } if (includeAbstract) { index = text.indexOf("id=\"abstract"); if (index >= 0) { endIndex = text.indexOf("</div>", index) + 6; text = text.substring(index, endIndex); Matcher absMatcher = absPattern.matcher(text); if (absMatcher.find()) { // Clean-up abstract String abstr = absMatcher.group(1); abstr = abstr.replaceAll("<span class='snippet'>([\\w]+)</span>", "$1"); entry.setField("abstract", htmlConverter.format(abstr)); } } } } if (entry == null) { return null; } else { return cleanup(entry); } }