Fix location field not exported correctly to office 2007 xml (#1909)

* Fix location field not exported to office 2007 xml
* Add some test for exporting location and address field
Address in xml field is now imported as location
add some javadoc

CHANGELOG.md

@@ -17,13 +17,16 @@ We refer to [GitHub issues](https://github.com/JabRef/jabref/issues) by using `#
 - Made it possible to download multiple entries in one action
 - [#1813](https://github.com/JabRef/jabref/issues/1813) Import/Export preferences dialog default directory set to working directory
 - [#1897](https://github.com/JabRef/jabref/issues/1897) Implemented integrity check for `year` field: Last four nonpunctuation characters should be numerals
+- Address in MS-Office 2007 xml format is now imported as `location`
+
 
 ### Fixed
 - Fixed NullPointerException when opening search result window for an untitled database 
 - Fixed entry table traversal with Tab (no column traversal thus no double jump)
 - Fixed [#1757](https://github.com/JabRef/jabref/issues/1757): Crash after saving illegal argument in entry editor
 - Fixed [#1663](https://github.com/JabRef/jabref/issues/1663): Better multi-monitor support
 - Fixed [#1882](https://github.com/JabRef/jabref/issues/1882): Crash after saving illegal bibtexkey in entry editor
+- Fixed field `location` containing only city is not exported correctly to MS-Office 2007 xml format
 
 ### Removed
 - The non-supported feature of being able to define file directories for any extension is removed. Still, it should work for older databases using the legacy `ps` and `pdf` fields, although we strongly encourage using the `file` field. 

src/main/java/net/sf/jabref/logic/exporter/MSBibExportFormat.java

@@ -43,7 +43,7 @@ public void performExport(final BibDatabaseContext databaseContext, final String
 
         try (VerifyingWriter ps = session.getWriter()) {
             try {
-                DOMSource source = new DOMSource(msBibDatabase.getDOM());
+                DOMSource source = new DOMSource(msBibDatabase.getDomForExport());
                 StreamResult result = new StreamResult(ps);
                 Transformer trans = TransformerFactory.newInstance().newTransformer();
                 trans.setOutputProperty(OutputKeys.INDENT, "yes");

src/main/java/net/sf/jabref/logic/importer/fileformat/MsBibImporter.java

@@ -46,7 +46,7 @@ public ParserResult importDatabase(BufferedReader reader) throws IOException {
         Objects.requireNonNull(reader);
 
         MSBibDatabase dbase = new MSBibDatabase();
-        return new ParserResult(dbase.importEntries(reader));
+        return new ParserResult(dbase.importEntriesFromXml(reader));
     }
 
     @Override

src/main/java/net/sf/jabref/logic/msbib/BibTeXConverter.java

@@ -19,6 +19,11 @@ public class BibTeXConverter {
     private static final String MSBIB_PREFIX = "msbib-";
 
 
+    /**
+     * Converts an {@link MSBibEntry} to a {@link BibEntry} for import
+     * @param entry The MsBibEntry to convert
+     * @return The bib entry
+     */
     public static BibEntry convert(MSBibEntry entry) {
         BibEntry result;
         Map<String, String> fieldValues = new HashMap<>();
@@ -72,7 +77,7 @@ public static BibEntry convert(MSBibEntry entry) {
         parseStandardNumber(entry.standardNumber, fieldValues);
 
         if (entry.address != null) {
-            fieldValues.put(FieldName.ADDRESS, entry.address);
+            fieldValues.put(FieldName.LOCATION, entry.address);
         }
         // TODO: ConferenceName is saved as booktitle when converting from MSBIB to BibTeX
         if (entry.conferenceName != null) {

src/main/java/net/sf/jabref/logic/msbib/MSBibDatabase.java

@@ -26,7 +26,7 @@
 
 /**
  * Microsoft Word bibliography.
- *
+ * The class is uesed both for import and export
  * See http://www.ecma-international.org/publications/standards/Ecma-376.htm
  */
 public class MSBibDatabase {
@@ -39,20 +39,33 @@ public class MSBibDatabase {
     private Set<MSBibEntry> entries;
 
 
+    /**
+     * Creates a {@link MSBibDatabase} for <b>import</b>
+     */
     public MSBibDatabase() {
         entries = new HashSet<>();
     }
 
     // TODO: why an additonal entry list? entries are included inside database!
+    /**
+     * Creates a new {@link MSBibDatabase} for <b>export</b>
+     * @param database The bib database
+     * @param entries List of {@link BibEntry}
+     */
     public MSBibDatabase(BibDatabase database, List<BibEntry> entries) {
         if (entries == null) {
-            addEntries(database.getEntries());
+            addEntriesForExport(database.getEntries());
         } else {
-            addEntries(entries);
+            addEntriesForExport(entries);
         }
     }
 
-    public List<BibEntry> importEntries(BufferedReader reader) {
+    /**
+     * Imports entries from an office xml file
+     * @param reader
+     * @return List of {@link BibEntry}
+     */
+    public List<BibEntry> importEntriesFromXml(BufferedReader reader) {
         entries = new HashSet<>();
         Document inputDocument;
         try {
@@ -83,15 +96,19 @@ public List<BibEntry> importEntries(BufferedReader reader) {
         return bibitems;
     }
 
-    private void addEntries(List<BibEntry> entriesToAdd) {
+    private void addEntriesForExport(List<BibEntry> entriesToAdd) {
         entries = new HashSet<>();
         for (BibEntry entry : entriesToAdd) {
             MSBibEntry newMods = MSBibConverter.convert(entry);
             entries.add(newMods);
         }
     }
 
-    public Document getDOM() {
+    /**
+     * Gets the assembled dom for export
+     * @return XML Document
+     */
+    public Document getDomForExport() {
         Document document = null;
         try {
             DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
@@ -106,7 +123,7 @@ public Document getDOM() {
             rootNode.setAttribute("SelectedStyle", "");
 
             for (MSBibEntry entry : entries) {
-                Node node = entry.getDOM(document);
+                Node node = entry.getEntryDom(document);
                 rootNode.appendChild(node);
             }
             document.appendChild(rootNode);

src/main/java/net/sf/jabref/logic/msbib/MSBibEntry.java

@@ -64,24 +64,32 @@ class MSBibEntry {
 
     private String bibtexEntryType;
 
-    // reduced subset, supports only "CITY , STATE, COUNTRY"
-    // \b(\w+)\s?[,]?\s?(\w+)\s?[,]?\s?(\w+)\b
-    // WORD SPACE , SPACE WORD SPACE , SPACE WORD
-    // tested using http://www.javaregex.com/test.html
-    private static final Pattern ADDRESS_PATTERN = Pattern.compile("\\b(\\w+)\\s?[,]?\\s?(\\w+)\\s?[,]?\\s?(\\w+)\\b");
-
-    // Allows 20.3-2007|||20/3-  2007 etc.
-    // (\d{1,2})\s?[.,-/]\s?(\d{1,2})\s?[.,-/]\s?(\d{2,4})
-    // 1-2 DIGITS SPACE SEPERATOR SPACE 1-2 DIGITS SPACE SEPERATOR SPACE 2-4 DIGITS
-    // tested using http://www.javaregex.com/test.html
+    /**
+     * reduced subset, supports only "CITY , STATE, COUNTRY" <br>
+     *  <b>\b(\w+)\s?[,]?\s?(\w+)\s?[,]?\s?(\w*)\b</b> <br>
+     *  WORD SPACE , SPACE WORD SPACE (Can be zero or more) , SPACE WORD (Can be zero or more) <br>
+     *  Matches both single locations (only city) like Berlin and full locations like Stroudsburg, PA, USA <br>
+     *  tested using http://www.regexpal.com/
+     */
+    private final Pattern ADDRESS_PATTERN = Pattern.compile("\\b(\\w+)\\s?[,]?\\s?(\\w*)\\s?[,]?\\s?(\\w*)\\b");
+
+    /**
+     * Allows 20.3-2007|||20/3-  2007 etc.
+     * <b>(\d{1,2})\s?[.,-/]\s?(\d{1,2})\s?[.,-/]\s?(\d{2,4})</b>
+     * 1-2 DIGITS SPACE SEPERATOR SPACE 1-2 DIGITS SPACE SEPERATOR SPACE 2-4 DIGITS
+     */
     private static final Pattern DATE_PATTERN = Pattern
             .compile("(\\d{1,2})\\s*[.,-/]\\s*(\\d{1,2})\\s*[.,-/]\\s*(\\d{2,4})");
 
 
     public MSBibEntry() {
-
+        //empty
     }
 
+    /**
+     * Createa new {@link MsBibEntry} to import from an xml element
+     * @param entry
+     */
     public MSBibEntry(Element entry) {
         populateFromXml(entry);
     }
@@ -128,14 +136,17 @@ private void populateFromXml(Element entry) {
         String city = getXmlElementTextContent("City", entry);
         String state = getXmlElementTextContent("StateProvince", entry);
         String country = getXmlElementTextContent("CountryRegion", entry);
+
         StringBuilder addressBuffer = new StringBuilder();
         if (city != null) {
-            addressBuffer.append(city).append(", ");
+            addressBuffer.append(city);
         }
-        if (state != null) {
-            addressBuffer.append(state).append(' ');
+        if (((state != null) && !state.isEmpty()) && ((city != null) && !city.isEmpty())) {
+            addressBuffer.append(",").append(' ');
+            addressBuffer.append(state);
         }
-        if (country != null) {
+        if ((country != null) && !country.isEmpty()) {
+            addressBuffer.append(",").append(' ');
             addressBuffer.append(country);
         }
         address = addressBuffer.toString().trim();
@@ -231,7 +242,12 @@ private List<PersonName> getSpecificAuthors(String type, Element authors) {
         return result;
     }
 
-    public Element getDOM(Document document) {
+    /**
+     * Gets the dom representation for one entry, used for export
+     * @param document XmlDocument
+     * @return XmlElement represenation of one entry
+     */
+    public Element getEntryDom(Document document) {
         Element rootNode = document.createElementNS(MSBibDatabase.NAMESPACE, MSBibDatabase.PREFIX + "Source");
 
         for (Map.Entry<String, String> entry : fields.entrySet()) {
@@ -318,18 +334,18 @@ private void addAuthor(Document document, Element allAuthors, String entryName,
         allAuthors.appendChild(authorTop);
     }
 
-    private void addAddress(Document document, Element parent, String address) {
-        if (address == null) {
+    private void addAddress(Document document, Element parent, String addressToSplit) {
+        if (addressToSplit == null) {
             return;
         }
 
-        Matcher matcher = ADDRESS_PATTERN.matcher(address);
+        Matcher matcher = ADDRESS_PATTERN.matcher(addressToSplit);
         if (matcher.matches() && (matcher.groupCount() >= 3)) {
             addField(document, parent, "City", matcher.group(1));
             addField(document, parent, "StateProvince", matcher.group(2));
             addField(document, parent, "CountryRegion", matcher.group(3));
         } else {
-            addField(document, parent, "City", address);
+            addField(document, parent, "City", addressToSplit);
         }
     }
 }

src/test/resources/net/sf/jabref/logic/exporter/MsBibExportFormatTest2.xml

@@ -15,6 +15,8 @@
 <b:Pages>237-248</b:Pages>
 <b:JournalName>Wirtschaftsinformatik</b:JournalName>
 <b:City>a</b:City>
+<b:StateProvince/>
+<b:CountryRegion/>
 <b:ThesisType>type</b:ThesisType>
 </b:Source>
 </b:Sources>

src/test/resources/net/sf/jabref/logic/exporter/MsBibLocationTest.bib

@@ -0,0 +1,10 @@
+% Encoding: UTF-8
+
+@InProceedings{LocationTest,
+  author    = {LocationTest},
+  location  = {Berlin},
+  owner     = {Christoph Schwentker},
+  timestamp = {2016.09.04},
+}
+
+@Comment{jabref-meta: databaseType:biblatex;}

src/test/resources/net/sf/jabref/logic/exporter/MsBibLocationTest.xml

@@ -0,0 +1,20 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<b:Sources xmlns:b="http://schemas.openxmlformats.org/officeDocument/2006/bibliography" xmlns="http://schemas.openxmlformats.org/officeDocument/2006/bibliography" SelectedStyle="">
+<b:Source>
+<b:BIBTEX_Entry>inproceedings</b:BIBTEX_Entry>
+<b:SourceType>ConferenceProceedings</b:SourceType>
+<b:Tag>LocationTest</b:Tag>
+<b:Author>
+<b:Author>
+<b:NameList>
+<b:Person>
+<b:Last>LocationTest</b:Last>
+</b:Person>
+</b:NameList>
+</b:Author>
+</b:Author>
+<b:City>Berlin</b:City>
+<b:StateProvince/>
+<b:CountryRegion/>
+</b:Source>
+</b:Sources>

src/test/resources/net/sf/jabref/logic/exporter/MsBibMultiAddressTest.bib

@@ -0,0 +1,11 @@
+% Encoding: UTF-8
+
+@InProceedings{MultiAddressTest,
+  author    = {MultiAddressTest},
+  location  = {Berlin},
+  address   = {Stroudsburg, PA, USA},
+  owner     = {Christoph Schwentker},
+  timestamp = {2016.09.04},
+}
+
+@Comment{jabref-meta: databaseType:biblatex;}

src/test/resources/net/sf/jabref/logic/exporter/MsBibMultiAddressTest.xml

@@ -0,0 +1,20 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<b:Sources xmlns:b="http://schemas.openxmlformats.org/officeDocument/2006/bibliography" xmlns="http://schemas.openxmlformats.org/officeDocument/2006/bibliography" SelectedStyle="">
+<b:Source>
+<b:BIBTEX_Entry>inproceedings</b:BIBTEX_Entry>
+<b:SourceType>ConferenceProceedings</b:SourceType>
+<b:Tag>MultiAddressTest</b:Tag>
+<b:Author>
+<b:Author>
+<b:NameList>
+<b:Person>
+<b:Last>MultiAddressTest</b:Last>
+</b:Person>
+</b:NameList>
+</b:Author>
+</b:Author>
+<b:City>Stroudsburg</b:City>
+<b:StateProvince>PA</b:StateProvince>
+<b:CountryRegion>USA</b:CountryRegion>
+</b:Source>
+</b:Sources>

src/test/resources/net/sf/jabref/logic/importer/fileformat/MsBibLocationTest.bib

@@ -0,0 +1,8 @@
+% Encoding: UTF-8
+
+@InProceedings{LocationTest,
+  author    = {LocationTest},
+  location  = {Berlin},
+}
+
+@Comment{jabref-meta: databaseType:biblatex;}

src/test/resources/net/sf/jabref/logic/importer/fileformat/MsBibLocationTest.xml

@@ -0,0 +1,20 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<b:Sources xmlns:b="http://schemas.openxmlformats.org/officeDocument/2006/bibliography" xmlns="http://schemas.openxmlformats.org/officeDocument/2006/bibliography" SelectedStyle="">
+<b:Source>
+<b:BIBTEX_Entry>inproceedings</b:BIBTEX_Entry>
+<b:SourceType>ConferenceProceedings</b:SourceType>
+<b:Tag>LocationTest</b:Tag>
+<b:Author>
+<b:Author>
+<b:NameList>
+<b:Person>
+<b:Last>LocationTest</b:Last>
+</b:Person>
+</b:NameList>
+</b:Author>
+</b:Author>
+<b:City>Berlin</b:City>
+<b:StateProvince/>
+<b:CountryRegion/>
+</b:Source>
+</b:Sources>

src/test/resources/net/sf/jabref/logic/importer/fileformat/MsBibMultiLocationAddressTest.bib

@@ -0,0 +1,8 @@
+% Encoding: UTF-8
+
+@InProceedings{LocationTest,
+  author    = {LocationTest},
+  location  = {Stroudsburg, PA, USA},
+}
+
+@Comment{jabref-meta: databaseType:biblatex;}

src/test/resources/net/sf/jabref/logic/importer/fileformat/MsBibMultiLocationAddressTest.xml

@@ -0,0 +1,20 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<b:Sources xmlns:b="http://schemas.openxmlformats.org/officeDocument/2006/bibliography" xmlns="http://schemas.openxmlformats.org/officeDocument/2006/bibliography" SelectedStyle="">
+<b:Source>
+<b:BIBTEX_Entry>inproceedings</b:BIBTEX_Entry>
+<b:SourceType>ConferenceProceedings</b:SourceType>
+<b:Tag>LocationTest</b:Tag>
+<b:Author>
+<b:Author>
+<b:NameList>
+<b:Person>
+<b:Last>LocationTest</b:Last>
+</b:Person>
+</b:NameList>
+</b:Author>
+</b:Author>
+<b:City>Stroudsburg</b:City>
+<b:StateProvince>PA</b:StateProvince>
+<b:CountryRegion>USA</b:CountryRegion>
+</b:Source>
+</b:Sources>