Add MathML support when importing PubMed (#9963)

* add mathml support for medline importer

* add changelog entry

* fix checkstyle issues

* remove remaining tabs

* update resource loading method

CHANGELOG.md

@@ -26,6 +26,7 @@ Note that this project **does not** adhere to [Semantic Versioning](http://semve
 - We added the possibility to automatically fetch entries when an ISBN is pasted on the main table. [#9864](https://github.com/JabRef/jabref/issues/9864)
 - We added the option to disable the automatic linking of files in the entry editor [#5105](https://github.com/JabRef/jabref/issues/5105)
 - We added the link icon for ISBNs in linked identifiers column. [#9819](https://github.com/JabRef/jabref/issues/9819)
+- We added support for parsing MathML in the Medline importer. [#4273](https://github.com/JabRef/jabref/issues/4273)
 
 ### Changed
 

src/main/java/org/jabref/logic/importer/fileformat/MedlineImporter.java

@@ -29,6 +29,7 @@
 import org.jabref.logic.importer.fileformat.medline.MeshHeading;
 import org.jabref.logic.importer.fileformat.medline.OtherId;
 import org.jabref.logic.importer.fileformat.medline.PersonalNameSubject;
+import org.jabref.logic.importer.util.MathMLParser;
 import org.jabref.logic.util.StandardFileType;
 import org.jabref.model.entry.BibEntry;
 import org.jabref.model.entry.Date;
@@ -1082,6 +1083,9 @@ private void handleTextElement(XMLStreamReader reader, List<String> textList, St
             if (isStartXMLEvent(reader)) {
                 String elementName = reader.getName().getLocalPart();
                 switch (elementName) {
+                    case "math" -> {
+                        result.append(MathMLParser.parse(reader));
+                    }
                     case "sup", "sub" -> {
                         reader.next();
                         if (isCharacterXMLEvent(reader)) {

src/main/java/org/jabref/logic/importer/util/MathMLParser.java

@@ -0,0 +1,69 @@
+package org.jabref.logic.importer.util;
+
+import java.io.IOException;
+import java.io.StringReader;
+import java.io.StringWriter;
+import java.net.URISyntaxException;
+import java.net.URL;
+import java.util.Objects;
+
+import javax.xml.stream.XMLStreamException;
+import javax.xml.stream.XMLStreamReader;
+import javax.xml.transform.Result;
+import javax.xml.transform.Source;
+import javax.xml.transform.Transformer;
+import javax.xml.transform.TransformerException;
+import javax.xml.transform.TransformerFactory;
+import javax.xml.transform.stream.StreamResult;
+import javax.xml.transform.stream.StreamSource;
+
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+public class MathMLParser {
+    private static final Logger LOGGER = LoggerFactory.getLogger(MathMLParser.class);
+    private static final String XSLT_FILE_PATH = "/xslt/mathml_latex/mmltex.xsl";
+
+    /**
+     * Parses the MathML element into its corresponding
+     * LaTeX representation, using an XSLT transformation file
+     *
+     * @param reader the stream reader
+     * @return Returns the LaTeX representation
+     */
+    public static String parse(XMLStreamReader reader) {
+        String xmlContent = "";
+        String latexResult = "<Unsupported MathML expression>";
+
+        try {
+            // extract XML content
+            xmlContent = StaxParser.getXMLContent(reader);
+
+            // convert to LaTeX using XSLT file
+            Source xmlSource = new StreamSource(new StringReader(xmlContent));
+
+            URL xsltResource = MathMLParser.class.getResource(XSLT_FILE_PATH);
+            Source xsltSource = new StreamSource(Objects.requireNonNull(xsltResource).openStream(), xsltResource.toURI().toASCIIString());
+
+            TransformerFactory transformerFactory = TransformerFactory.newInstance();
+            Transformer transformer = transformerFactory.newTransformer(xsltSource);
+
+            StringWriter writer = new StringWriter();
+            Result result = new StreamResult(writer);
+            transformer.transform(xmlSource, result);
+
+            latexResult = writer.getBuffer().toString();
+        } catch (XMLStreamException e) {
+            LOGGER.debug("An exception occurred when getting XML content", e);
+        } catch (IOException e) {
+            LOGGER.debug("An I/O exception occurred", e);
+        } catch (URISyntaxException e) {
+            LOGGER.debug("XSLT Source URI invalid", e);
+        } catch (TransformerException e) {
+            LOGGER.debug("An exception occurred during transformation", e);
+        }
+
+        return latexResult;
+    }
+}
+

src/main/java/org/jabref/logic/importer/util/StaxParser.java

@@ -0,0 +1,128 @@
+package org.jabref.logic.importer.util;
+
+import javax.xml.stream.XMLStreamConstants;
+import javax.xml.stream.XMLStreamException;
+import javax.xml.stream.XMLStreamReader;
+
+public class StaxParser {
+
+    /**
+     * Extracts the XML content inside the first
+     * encountered parent tag, including tag elements,
+     * attributes, namespace, prefix and contained text
+     *
+     * @param reader the stream reader
+     * @return Returns the inner XML content
+     */
+    public static String getXMLContent(XMLStreamReader reader) throws XMLStreamException {
+        // skip over START DOCUMENT event
+        while (reader.getEventType() == XMLStreamConstants.START_DOCUMENT && reader.hasNext()) {
+            reader.next();
+        }
+
+        StringBuilder content = new StringBuilder();
+
+        String parentTag = reader.getLocalName();
+        int depth = 1;
+        content.append(getXMLStartTag(reader, true));
+
+        while (reader.hasNext()) {
+            int event = reader.next();
+            if (event == XMLStreamConstants.START_ELEMENT) {
+                String tagName = reader.getLocalName();
+
+                if (tagName.equals(parentTag)) {
+                    // nested tag of same type
+                    depth++;
+                }
+
+                // append the start tag
+                content.append(getXMLStartTag(reader, false));
+            } else if (event == XMLStreamConstants.END_ELEMENT) {
+                String tagName = reader.getLocalName();
+
+                // append the end tag
+                content.append(getXMLEndTag(reader));
+
+                if (tagName.equals(parentTag)) {
+                    depth--;
+
+                    if (depth == 0) {
+                        // reached the closing tag of the first parent tag
+                        break;
+                    }
+                }
+            } else if (event == XMLStreamConstants.CHARACTERS) {
+                content.append(getXMLText(reader));
+            } else if (event == XMLStreamConstants.CDATA) {
+                content.append(getXMLCData(reader));
+            } else if (event == XMLStreamConstants.COMMENT) {
+                content.append(getXMLComment(reader));
+            } else if (event == XMLStreamConstants.PROCESSING_INSTRUCTION) {
+                content.append(getXMLProcessingInstruction(reader));
+            } else if (event == XMLStreamConstants.SPACE || event == XMLStreamConstants.ENTITY_REFERENCE) {
+                content.append(getXMLText(reader));
+            }
+        }
+
+        return content.toString().trim();
+    }
+
+    private static String getXMLStartTag(XMLStreamReader reader, boolean addNamespaceURI) {
+        StringBuilder startTag = new StringBuilder();
+
+        String prefix = reader.getPrefix();
+
+        startTag.append("<")
+                .append(prefix != null && !prefix.isBlank() ? prefix + ":" : "")
+                .append(reader.getName().getLocalPart());
+
+        String namespaceURI = reader.getNamespaceURI();
+        if (addNamespaceURI && namespaceURI != null) {
+            startTag.append(" xmlns")
+                    .append(prefix != null && !prefix.isBlank() ? ":" + prefix : "")
+                    .append("=\"")
+                    .append(namespaceURI)
+                    .append("\"");
+        }
+
+        for (int i = 0; i < reader.getAttributeCount(); i++) {
+            startTag.append(" ").append(reader.getAttributeLocalName(i)).append("=\"").append(reader.getAttributeValue(i)).append("\"");
+        }
+
+        if (reader.isEndElement()) {
+            startTag.append("/");
+        }
+
+        startTag.append(">");
+        return startTag.toString();
+    }
+
+    private static String getXMLEndTag(XMLStreamReader reader) {
+        StringBuilder endTag = new StringBuilder();
+        String prefix = reader.getPrefix();
+
+        endTag.append("</")
+              .append(prefix != null && !prefix.isBlank() ? prefix + ":" : "")
+              .append(reader.getName().getLocalPart())
+              .append(">");
+
+        return endTag.toString();
+    }
+
+    private static String getXMLCData(XMLStreamReader reader) {
+        return "<![CDATA[" + reader.getText() + "]]>";
+    }
+
+    private static String getXMLComment(XMLStreamReader reader) {
+        return "<!--" + reader.getText() + "-->";
+    }
+
+    private static String getXMLProcessingInstruction(XMLStreamReader reader) {
+        return "<?" + reader.getPITarget() + " " + reader.getPIData() + "?>";
+    }
+
+    private static String getXMLText(XMLStreamReader reader) {
+        return reader.getText().trim();
+    }
+}

src/main/resources/xslt/mathml_latex/README

@@ -0,0 +1,97 @@
+README for the XSLT MathML Library
+
+XSLT MathML Library is a set of XSLT stylesheets to transform
+MathML 2.0 to LaTeX.
+
+For more information, see
+http://www.raleigh.ru/MathML/mmltex/index.php?lang=en
+
+Manifest
+--------
+
+README        this file
+mmltex.xsl
+tokens.xsl
+glayout.xsl
+scripts.xsl
+tables.xsl
+entities.xsl
+cmarkup.xsl
+
+Use
+---
+
+There are two ways of using the library:
+
+    * Use a local copy of the library.
+
+        1. Download the distribution (see below).
+
+        2. Unpack the distribution, using unzip.
+
+        3. In your stylesheet import or include either the main
+           stylesheet, mmltex.xsl, or the stylesheet module you
+           wish to use, such as tokens.xsl. This example assumes
+           that the distribution has been extracted into the same
+           directory as your own stylesheet:
+
+           <xsl:import href="mmltex.xsl"/>
+
+    * Import or include either the main stylesheet, or the
+      stylesheet module you wish to use, directly from the library
+      website; http://www.raleigh.ru/MathML/mmltex/. For example:
+
+      <xsl:import href="http://www.raleigh.ru/MathML/mmltex/mmltex.xsl"/>
+
+Obtaining The Library
+---------------------
+
+The XSLT MathML Library is available for download as:
+
+    * Zip file: http://www.raleigh.ru/MathML/mmltex/mmltex.zip
+
+Copyright
+---------
+
+Copyright (C) 2001, 2002 Vasil Yaroshevich
+
+Permission is hereby granted, free of charge, to any person
+obtaining a copy of this software and associated documentation
+files (the ``Software''), to deal in the Software without
+restriction, including without limitation the rights to use,
+copy, modify, merge, publish, distribute, sublicense, and/or
+sell copies of the Software, and to permit persons to whom the
+Software is furnished to do so, subject to the following
+conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+Except as contained in this notice, the names of individuals
+credited with contribution to this software shall not be used in
+advertising or otherwise to promote the sale, use or other
+dealings in this Software without prior written authorization
+from the individuals in question.
+
+Any stylesheet derived from this Software that is publically
+distributed will be identified with a different name and the
+version strings in any derived Software will be changed so that
+no possibility of confusion between the derived package and this
+Software will exist.
+
+Warranty
+--------
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT.  IN NO EVENT SHALL NORMAN WALSH OR ANY OTHER
+CONTRIBUTOR BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+OTHER DEALINGS IN THE SOFTWARE.
+
+Contacting the Author
+---------------------
+
+These stylesheets are maintained by Vasil Yaroshevich, <[email protected]>.