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 BibtexEntry makeBibtexEntry() {
BibtexEntry e = new BibtexEntry(IdGenerator.next(), BibtexEntryTypes.INCOLLECTION);
e.setField("title", "Marine finfish larviculture in Europe");
e.setField("bibtexkey", "shields01");
e.setField("year", "2001");
e.setField("author", "Kevin Shields");
return e;
}
public BibtexEntry parseEntry(BibtexEntryType tp) throws IOException {
String id = Util.createNeutralId(); // createId(tp, _db);
BibtexEntry result = new BibtexEntry(id, tp);
skipWhitespace();
consume('{', '(');
int c = peek();
if ((c != '\n') && (c != '\r')) skipWhitespace();
String key = null;
boolean doAgain = true;
while (doAgain) {
doAgain = false;
try {
if (key != null) key = key + parseKey(); // parseTextToken(),
else key = parseKey();
} catch (NoLabelException ex) {
// This exception will be thrown if the entry lacks a key
// altogether, like in "@article{ author = { ...".
// It will also be thrown if a key contains =.
c = (char) peek();
if (Character.isWhitespace(c) || (c == '{') || (c == '\"')) {
String fieldName = ex.getMessage().trim().toLowerCase();
String cont = parseFieldContent(fieldName);
result.setField(fieldName, cont);
} else {
if (key != null) key = key + ex.getMessage() + "=";
else key = ex.getMessage() + "=";
doAgain = true;
}
}
}
if ((key != null) && key.equals("")) key = null;
result.setField(BibtexFields.KEY_FIELD, key);
skipWhitespace();
while (true) {
c = peek();
if ((c == '}') || (c == ')')) {
break;
}
if (c == ',') consume(',');
skipWhitespace();
c = peek();
if ((c == '}') || (c == ')')) {
break;
}
parseField(result);
}
consume('}', ')');
return result;
}
/**
* 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;
}
public void testEntryEditorForFieldAnotherAutoCompleter() {
// construct an EntryEditor ...
JabRef jabref = TestUtils.getInitializedJabRef();
BibtexEntry bibtexEntry = new BibtexEntry();
bibtexEntry.setField("journal", "Testtext");
FieldEditor authorTextField = new FieldTextArea("journal", "New Testtext");
EntryEditor editor = new EntryEditor(jabref.jrf, jabref.jrf.basePanel(), bibtexEntry);
// perform action ...
editor.storeFieldAction.actionPerformed(new ActionEvent(authorTextField, 0, ""));
// test content of stored words in autocompleter ...
AbstractAutoCompleter autoCompleter = jabref.jrf.basePanel().getAutoCompleter("journal");
assertTrue(autoCompleter.indexContainsWord("New Testtext"));
TestUtils.closeJabRef();
}
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);
}
}
@Test
@Ignore
public void testInsertTestData() throws Exception {
entry1 = new BibtexEntry();
JabRefPreferences jabRefPreferences = JabRefPreferences.getInstance();
ExternalFileType fileType = jabRefPreferences.getExternalFileTypeByExt("PDF");
FileListEntry fileListEntry =
new FileListEntry("", ImportDataTest.FILE_IN_DATABASE.getAbsolutePath(), fileType);
FileListTableModel model = new FileListTableModel();
model.addEntry(0, fileListEntry);
entry1.setField("file", model.getStringRepresentation());
database.insertEntry(entry1);
// #################### SETUP END ##################### //
UnlinkedFilesCrawler crawler = new UnlinkedFilesCrawler(database);
CheckableTreeNode treeNode =
crawler.searchDirectory(ImportDataTest.EXISTING_FOLDER, new EntryFromPDFCreator());
Assert.assertNotNull(treeNode);
/** Select all nodes manually. */
@SuppressWarnings("unchecked")
Enumeration<CheckableTreeNode> enumeration = treeNode.breadthFirstEnumeration();
while (enumeration.hasMoreElements()) {
CheckableTreeNode nextElement = enumeration.nextElement();
nextElement.setSelected(true);
}
List<File> resultList = getFileListFromNode(treeNode);
Assert.assertFalse(resultList.isEmpty());
Assert.assertTrue(resultList.contains(ImportDataTest.FILE_NOT_IN_DATABASE));
Assert.assertFalse(resultList.contains(ImportDataTest.FILE_IN_DATABASE));
}
/** Parse the entries in the source, and return a List of BibtexEntry objects. */
@Override
public List<BibtexEntry> importEntries(InputStream stream, OutputPrinter status)
throws IOException {
ArrayList<BibtexEntry> bibitems = new ArrayList<BibtexEntry>();
StringBuilder sb = new StringBuilder();
BufferedReader in = new BufferedReader(ImportFormatReader.getReaderDefaultEncoding(stream));
String str;
while ((str = in.readLine()) != null) {
if (str.length() < 3) {
continue;
}
// begining of a new item
if (str.substring(0, 6).equals("PMID- ")) {
sb.append("::").append(str);
} else {
String beg = str.substring(0, 6);
if (beg.indexOf(" ") > 0) {
sb.append(" ## "); // mark the begining of each field
sb.append(str);
} else {
sb.append("EOLEOL"); // mark the end of each line
sb.append(str.trim());
}
}
}
String[] entries = sb.toString().split("::");
// skip the first entry as it is either empty or has document header
HashMap<String, String> hm = new HashMap<String, String>();
for (String entry : entries) {
String[] fields = entry.split(" ## ");
if (fields.length == 0) {
fields = entry.split("\n");
}
String Type = "";
String pages = "";
String shortauthor = "";
String fullauthor = "";
hm.clear();
for (String field : fields) {
System.out.println(">>>" + field + "<<<");
// empty field don't do anything
if (field.length() <= 2) {
continue;
}
String beg = field.substring(0, 6);
String value = field.substring(6);
value = value.trim();
if (beg.equals("PT - ")) {
// PT = value.replaceAll("JOURNAL ARTICLE", "article").replaceAll("Journal Article",
// "article");
Type = "article"; // make all of them PT?
} else if (beg.equals("TY - ")) {
if ("CONF".equals(value)) {
Type = "inproceedings";
}
} else if (beg.equals("JO - ")) {
hm.put("booktitle", value);
} else if (beg.equals("FAU - ")) {
String tmpauthor = value.replaceAll("EOLEOL", " and ");
// if there is already someone there then append with "and"
if (!"".equals(fullauthor)) {
fullauthor = fullauthor + " and " + tmpauthor;
} else {
fullauthor = tmpauthor;
}
} else if (beg.equals("AU - ")) {
String tmpauthor = value.replaceAll("EOLEOL", " and ").replaceAll(" ", ", ");
// if there is already someone there then append with "and"
if (!"".equals(shortauthor)) {
shortauthor = shortauthor + " and " + tmpauthor;
} else {
shortauthor = tmpauthor;
}
} else if (beg.equals("TI - ")) {
hm.put("title", value.replaceAll("EOLEOL", " "));
} else if (beg.equals("TA - ")) {
hm.put("journal", value.replaceAll("EOLEOL", " "));
} else if (beg.equals("AB - ")) {
hm.put("abstract", value.replaceAll("EOLEOL", " "));
} else if (beg.equals("PG - ")) {
pages = value.replaceAll("-", "--");
} else if (beg.equals("IP - ")) {
hm.put("number", value);
} else if (beg.equals("DP - ")) {
String[] parts = value.split(" "); // sometimes this is just year, sometimes full date
hm.put("year", parts[0]);
} else if (beg.equals("VI - ")) {
hm.put("volume", value);
} else if (beg.equals("AID - ")) {
String[] parts = value.split(" ");
if ("[doi]".equals(parts[1])) {
hm.put("doi", parts[0]);
hm.put("url", "http://dx.doi.org/" + parts[0]);
}
}
}
if (!"".equals(pages)) {
hm.put("pages", pages);
}
if (!"".equals(fullauthor)) {
hm.put("author", fullauthor);
} else if (!"".equals(shortauthor)) {
hm.put("author", shortauthor);
}
BibtexEntry b =
new BibtexEntry(
BibtexFields.DEFAULT_BIBTEXENTRY_ID,
Globals.getEntryType(Type)); // id assumes an existing database so don't
// create one here
b.setField(hm);
// the first bibitem is always empty, presumably as a result of trying
// to parse header informaion. So add only if we have at least author or
// title fields.
if ((hm.get("author") != null) || (hm.get("title") != null)) {
bibitems.add(b);
}
}
return bibitems;
}
public void endElement(String uri, String localName, String qName) {
if (localName.equals("PubmedArticle")) {
// bibitems.add( new Bibitem(null, makeBibtexString(), Globals.nextKey(),"-1" ) );
// check if year ="" then give medline date instead
if (year.equals("")) {
if (!MedlineDate.equals("")) {
// multi-year date format
// System.out.println(MedlineDate);
year = MedlineDate.substring(0, 4);
// Matcher m = Pattern.compile("\\b[0-9]{4}\\b").matcher(MedlineDate);
// if(m.matches())
// year = m.group();
}
}
// Build a string from the collected keywords:
StringBuffer sb = new StringBuffer();
for (Iterator<String> iterator = descriptors.iterator(); iterator.hasNext(); ) {
String s = iterator.next();
sb.append(s);
if (iterator.hasNext()) sb.append(KEYWORD_SEPARATOR);
}
keywords = sb.toString();
BibtexEntry b =
new BibtexEntry(
Util.createNeutralId(), // Globals.DEFAULT_BIBTEXENTRY_ID,
Globals.getEntryType(
"article")); // id assumes an existing database so don't create one here
if (!author.equals("")) {
b.setField(
"author", htmlConverter.formatUnicode(ImportFormatReader.expandAuthorInitials(author)));
// b.setField("author",Util.replaceSpecialCharacters(ImportFormatReader.expandAuthorInitials(author)));
author = "";
}
if (!title.equals("")) b.setField("title", htmlConverter.formatUnicode(title));
// if (!title.equals("")) b.setField("title",Util.replaceSpecialCharacters(title));
if (!journal.equals("")) b.setField("journal", journal);
if (!year.equals("")) b.setField("year", year);
// PENDING [email protected] 2005-05-27 : added call to fixPageRange
if (!page.equals("")) b.setField("pages", fixPageRange(page));
if (!volume.equals("")) b.setField("volume", volume);
if (!language.equals("")) b.setField("language", language);
if (!pst.equals("")) b.setField("medline-pst", pst);
if (!abstractText.equals("")) b.setField("abstract", abstractText.replaceAll("%", "\\\\%"));
if (!keywords.equals("")) b.setField("keywords", keywords);
if (!month.equals("")) b.setField("month", month);
// if (!url.equals("")) b.setField("url",url);
if (!number.equals("")) b.setField("number", number);
if (!doi.equals("")) {
b.setField("doi", doi);
b.setField("url", "http://dx.doi.org/" + doi);
}
if (!pii.equals("")) b.setField("pii", pii);
if (!affiliation.equals("")) {
b.setField("institution", affiliation.replaceAll("#", "\\\\#"));
}
// PENDING [email protected] 2005-05-27 : added "pmid" bibtex field
// Older references do not have doi entries, but every
// medline entry has a unique pubmed ID (aka primary ID).
// Add a bibtex field for the pubmed ID for future use.
if (!pubmedid.equals("")) b.setField("pmid", pubmedid);
bibitems.add(b);
abstractText = "";
author = "";
title = "";
journal = "";
keywords = "";
doi = "";
pii = "";
year = "";
forename = "";
lastName = "";
suffix = "";
abstractText = "";
affiliation = "";
pubmedid = "";
majorTopic = "";
minorTopics = "";
month = "";
volume = "";
language = "";
pst = "";
lastname = "";
suffix = "";
initials = "";
number = "";
page = "";
medlineID = "";
url = "";
MedlineDate = "";
descriptors.clear();
} else if (localName.equals("ArticleTitle")) {
inTitle = false;
} else if (localName.equals("PubDate")) {
inPubDate = false;
} else if (localName.equals("Year")) {
inYear = false;
} else if (localName.equals("PMID")) {
inPubMedID = false;
} else if (localName.equals("MedlineDate")) {
inMedlineDate = false;
} else if (localName.equals("MedlineTA")) {
inJournal = false;
} // journal name
else if (localName.equals("Month")) {
inMonth = false;
} else if (localName.equals("Volume")) {
inVolume = false;
} else if (localName.equals("Language")) {
inLanguage = false;
} else if (localName.equals("PublicationStatus")) {
inPst = false;
} else if (localName.equals("AuthorList")) {
author = join(authors.toArray(), " and ");
inAuthorList = false;
} else if (localName.equals("Author")) {
// forename sometimes has initials with " " in middle: is pattern [A-Z] [A-Z]
// when above is the case replace it with initials
if (forename.length() == 3 && forename.charAt(1) == ' ') {
forename = initials;
}
// Put together name with last name first, and enter suffix in between if present:
if (lastname.indexOf(" ") > 0) author = "{" + lastname + "}";
else author = lastname;
if (suffix.length() > 0) author = author + ", " + suffix;
if (forename.length() > 0) author = author + ", " + forename;
// author = initials + " " + lastname;
authors.add(author);
inAuthor = false;
forename = "";
initials = "";
lastname = "";
suffix = "";
} else if (localName.equals("DescriptorName")) inDescriptorName = false;
else if (localName.equals("QualifierName")) inQualifierName = false;
else if (localName.equals("MeshHeading")) {
inMeshHeader = false;
if (minorTopics.equals("")) descriptors.add(majorTopic);
else descriptors.add(majorTopic + ", " + minorTopics);
} else if (localName.equals("LastName")) {
inLastName = false;
} else if (localName.equals("Suffix")) {
inSuffix = false;
} else if (localName.equals("ForeName") || localName.equals("FirstName")) {
inForename = false;
} else if (localName.equals("Issue")) {
inIssue = false;
} else if (localName.equals("MedlinePgn")) {
inMedlinePgn = false;
} // pagenumber
else if (localName.equals("URL")) {
inUrl = false;
} else if (localName.equals("Initials")) {
// initials= '.' + initials + '.';
inInitials = false;
} else if (localName.equals("AbstractText")) {
inAbstractText = false;
} else if (localName.equals("Affiliation")) {
inAffiliation = false;
} else if (localName.equals("ArticleId")) {
if (inDoi) inDoi = false;
else if (inPii) inPii = false;
}
}
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);
}
}
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;
}
/** Parse the entries in the source, and return a List of BibtexEntry objects. */
public List<BibtexEntry> importEntries(InputStream stream, OutputPrinter status)
throws IOException {
ArrayList<BibtexEntry> bibitems = new ArrayList<BibtexEntry>();
StringBuffer sb = new StringBuffer();
HashMap<String, String> hm = new HashMap<String, String>();
BufferedReader in = new BufferedReader(ImportFormatReader.getReaderDefaultEncoding(stream));
String Type = null;
String str;
boolean first = true;
line = 1;
str = readLine(in);
while (true) {
if (str == null || str.length() == 0) { // end of record
if (!hm.isEmpty()) { // have a record
if (Type == null) {
addNote(hm, "Publication Type: [NOT SPECIFIED]");
addNote(hm, "[PERHAPS NOT FULL FORMAT]");
Type = "article";
}
// post-process Journal article
if (Type.equals("article") && hm.get("booktitle") != null) {
String booktitle = hm.get("booktitle");
hm.remove("booktitle");
hm.put("journal", booktitle);
}
BibtexEntry b =
new BibtexEntry(BibtexFields.DEFAULT_BIBTEXENTRY_ID, Globals.getEntryType(Type));
// create one here
b.setField(hm);
bibitems.add(b);
}
hm.clear(); // ready for next record
first = true;
if (str == null) break; // end of file
str = readLine(in);
continue;
}
int fline = line; // save this before reading field contents
Matcher fm = FIELD_PATTERN.matcher(str);
if (fm.find()) {
// save the field name (long and short)
String fabbr = fm.group(1);
String fname = fm.group(2);
// read the contents of the field
sb.setLength(0); // clear the buffer
while ((str = readLine(in)) != null) {
if (!str.startsWith(" ")) // field contents?
break; // nope
if (sb.length() > 0) {
sb.append(" ");
}
sb.append(str.substring(4)); // skip spaces
}
String fstr = sb.toString();
if (fstr.length() == 0) {
int line1 = line - 1;
throw new IOException("illegal empty field at line " + line1);
}
// replace [Lt] with <
fm = LT_PATTERN.matcher(fstr);
if (fm.find()) fstr = fm.replaceAll("<");
// check for start of new record
if (fabbr.equals("DN") && fname.equalsIgnoreCase("Database Name")) {
if (!first) {
throw new IOException("format error at line " + fline + ": DN out of order");
}
first = false;
} else if (first) {
throw new IOException("format error at line " + fline + ": missing DN");
}
if (fabbr.equals("PT")) {
Type = null;
String flow = fstr.toLowerCase();
String[] types = flow.split("; ");
for (String type : types) {
if ((type.contains("article")) || (type.contains("journal article"))) {
Type = "article";
break;
} else if (type.equals("dissertation")) {
Type = "phdthesis";
break;
} else if (type.equals("conference")) {
Type = "inproceedings";
break;
} else if (type.equals("book monograph") && Type == null) {
Type = "book";
break;
} else if (type.equals("report") && Type == null) {
Type = "techreport";
break;
}
}
if (Type == null) {
Type = "misc";
}
}
String ftype = null;
if (fabbr.equals("AB")) ftype = "abstract";
else if (fabbr.equals("AF")) ftype = "affiliation";
else if (fabbr.equals("AU")) {
ftype = "author";
if (fstr.contains(";")) fstr = fstr.replaceAll("; ", " and ");
} else if (fabbr.equals("CA")) ftype = "organization";
else if (fabbr.equals("DE")) ftype = "keywords";
else if (fabbr.equals("DO")) ftype = "doi";
else if (fabbr.equals("ED")) ftype = "editor";
else if (fabbr.equals("IB")) ftype = "ISBN";
else if (fabbr.equals("IS")) ftype = "ISSN";
else if (fabbr.equals("JN")) ftype = "journal";
else if (fabbr.equals("LA")) ftype = "language";
else if (fabbr.equals("PB")) ftype = "publisher";
else if (fabbr.equals("PY")) {
ftype = "year";
if (hm.get("year") != null) {
String oyear = hm.get("year");
if (!fstr.equals(oyear)) {
addNote(hm, "Source Year: " + oyear + ".");
// System.out.println(fstr + " != " + oyear);
}
}
} else if (fabbr.equals("RL")) {
ftype = "url";
String[] lines = fstr.split(" ");
StringBuilder urls = new StringBuilder();
for (int ii = 0; ii < lines.length; ++ii) {
if (lines[ii].startsWith("[URL:")) urls.append(lines[ii].substring(5));
else if (lines[ii].endsWith("]")) {
int len = lines[ii].length();
urls.append(lines[ii].substring(0, len - 1));
if (ii < lines.length - 1) urls.append("\n");
} else urls.append(lines[ii]);
}
fstr = urls.toString();
} else if (fabbr.equals("SO")) {
ftype = "booktitle";
// see if we can extract journal information
// compact vol(no):page-page:
Matcher pm = VOLNOPP_PATTERN.matcher(fstr);
if (pm.find()) {
hm.put("volume", pm.group(1));
hm.put("number", pm.group(2));
hm.put("pages", pm.group(3));
fstr = pm.replaceFirst("");
}
// pages
pm = PAGES_PATTERN.matcher(fstr);
StringBuilder pages = new StringBuilder();
while (pm.find()) {
if (pages.length() > 0) pages.append(",");
String pp = pm.group(1);
if (pp == null) pp = pm.group(2);
if (pp == null) pp = pm.group(3);
pages.append(pp);
fstr = pm.replaceFirst("");
pm = PAGES_PATTERN.matcher(fstr);
}
if (pages.length() > 0) hm.put("pages", pages.toString());
// volume:
pm = VOLUME_PATTERN.matcher(fstr);
if (pm.find()) {
hm.put("volume", pm.group(1));
fstr = pm.replaceFirst("");
}
// number:
pm = NUMBER_PATTERN.matcher(fstr);
if (pm.find()) {
hm.put("number", pm.group(1));
fstr = pm.replaceFirst("");
}
// journal date:
fstr = parseDate(hm, fstr);
// strip trailing whitespace
Pattern pp = Pattern.compile(",?\\s*$");
pm = pp.matcher(fstr);
if (pm.find()) fstr = pm.replaceFirst("");
if (fstr.equals("")) continue;
// System.out.println("SOURCE: \"" + fstr + "\"");
} else if (fabbr.equals("TI")) ftype = "title";
else if (fabbr.equals("RE")) continue; // throw away References
if (ftype != null) {
hm.put(ftype, fstr);
} else {
addNote(hm, fname + ": " + fstr + ".");
}
} else str = readLine(in);
}
return bibitems;
}
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());
}
}
}
