Merge pull request #10376 from JabRef/add-latex-integrity-check

Co-authored-by: Zylence <kirsch.julian@yahoo.com>

CHANGELOG.md

@@ -14,6 +14,7 @@ Note that this project **does not** adhere to [Semantic Versioning](https://semv
 - We added the possibility to find (and add) papers that cite or are cited by a given paper. [#6187](https://github.com/JabRef/jabref/issues/6187)
 - We added an error-specific message for when a download from a URL fails. [#9826](https://github.com/JabRef/jabref/issues/9826)
 - We added support for customizating the citation command (e.g., `[@key1,@key2]`) when [pushing to external applications](https://docs.jabref.org/cite/pushtoapplications). [#10133](https://github.com/JabRef/jabref/issues/10133)
+- We added an integrity check for more special characters. [#8712](https://github.com/JabRef/jabref/issues/8712)
 - We added protected terms described as "Computer science". [#10222](https://github.com/JabRef/jabref/pull/10222)
 
 ### Changed

build.gradle

@@ -206,6 +206,11 @@ dependencies {
         exclude module: 'fastparse_2.13'
     }
 
+    implementation "de.rototor.snuggletex:snuggletex:1.3.0"
+    implementation ("de.rototor.snuggletex:snuggletex-jeuclid:1.3.0") {
+        exclude group: "org.apache.xmlgraphics"
+    }
+
     implementation group: 'com.microsoft.azure', name: 'applicationinsights-core', version: '2.4.1'
     implementation (group: 'com.microsoft.azure', name: 'applicationinsights-logging-log4j2', version: '2.4.1') {
         exclude module: "log4j-core"

src/main/java/module-info.java

@@ -104,6 +104,8 @@
     requires jbibtex;
     requires citeproc.java;
 
+    requires snuggletex.core;
+
     requires org.apache.pdfbox;
     requires org.apache.xmpbox;
     requires com.ibm.icu;
@@ -141,5 +143,4 @@
     requires org.antlr.antlr4.runtime;
     requires org.libreoffice.uno;
     requires de.saxsys.mvvmfx.validation;
-
 }

src/main/java/org/jabref/logic/integrity/IntegrityCheck.java

@@ -38,7 +38,8 @@ public IntegrityCheck(BibDatabaseContext bibDatabaseContext,
                 new EntryLinkChecker(bibDatabaseContext.getDatabase()),
                 new CitationKeyDeviationChecker(bibDatabaseContext, citationKeyPatternPreferences),
                 new CitationKeyDuplicationChecker(bibDatabaseContext.getDatabase()),
-                new AmpersandChecker()
+                new AmpersandChecker(),
+                new LatexIntegrityChecker()
                 ));
         if (bibDatabaseContext.isBiblatexMode()) {
             entryCheckers.addAll(List.of(

src/main/java/org/jabref/logic/integrity/LatexIntegrityChecker.java

@@ -0,0 +1,76 @@
+package org.jabref.logic.integrity;
+
+import java.io.IOException;
+import java.text.MessageFormat;
+import java.util.ArrayList;
+import java.util.HashSet;
+import java.util.List;
+import java.util.Map;
+import java.util.ResourceBundle;
+import java.util.Set;
+
+import org.jabref.logic.l10n.Localization;
+import org.jabref.model.entry.BibEntry;
+import org.jabref.model.entry.field.Field;
+
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+import uk.ac.ed.ph.snuggletex.ErrorCode;
+import uk.ac.ed.ph.snuggletex.InputError;
+import uk.ac.ed.ph.snuggletex.SnuggleEngine;
+import uk.ac.ed.ph.snuggletex.SnuggleInput;
+import uk.ac.ed.ph.snuggletex.SnuggleSession;
+import uk.ac.ed.ph.snuggletex.definitions.CoreErrorCode;
+import uk.ac.ed.ph.snuggletex.definitions.CoreErrorGroup;
+
+public class LatexIntegrityChecker implements EntryChecker {
+
+    private static final Logger LOGGER = LoggerFactory.getLogger(SnuggleSession.class);
+    private static final SnuggleEngine ENGINE = new SnuggleEngine();
+    private static final SnuggleSession SESSION = ENGINE.createSession();
+    private static final ResourceBundle ERROR_MESSAGES = ENGINE.getPackages().get(0).getErrorMessageBundle();
+    private static final Set<ErrorCode> EXCLUDED_ERRORS = new HashSet<>();
+
+    static {
+        // Static configuration.
+        SESSION.getConfiguration().setFailingFast(true);
+
+        // '#' only allowed inside and command/environment definitions.
+        EXCLUDED_ERRORS.add(CoreErrorCode.TTEG04);
+    }
+
+    @Override
+    public List<IntegrityMessage> check(BibEntry entry) {
+        List<IntegrityMessage> results = new ArrayList<>();
+
+        for (Map.Entry<Field, String> field : entry.getFieldMap().entrySet()) {
+            SnuggleInput input = new SnuggleInput(field.getValue());
+            try {
+                SESSION.parseInput(input);
+            } catch (IOException e) {
+                LOGGER.error("Error at parsing", e);
+            }
+            if (!SESSION.getErrors().isEmpty()) {
+                // Retrieve the first error only because it is likely to be more meaningful.
+                // Displaying all (subsequent) faults may lead to confusion.
+                // We further get a slight performance benefit from failing fast (see static config in class header).
+                InputError error = SESSION.getErrors().get(0);
+                ErrorCode errorCode = error.getErrorCode();
+                // Exclude all DOM building errors as this functionality is not used.
+                // Further, exclude individual errors.
+                if (!errorCode.getErrorGroup().equals(CoreErrorGroup.TDE) && !EXCLUDED_ERRORS.contains(errorCode)) {
+                    String jabrefMessageWrapper = errorMessageFormatHelper(errorCode, error.getArguments());
+                    results.add(new IntegrityMessage(jabrefMessageWrapper, entry, field.getKey()));
+                }
+            }
+            SESSION.reset();
+        }
+        return results;
+    }
+
+    public static String errorMessageFormatHelper(ErrorCode snuggleTexErrorCode, Object... arguments) {
+        String snuggletexMessagePattern = LatexIntegrityChecker.ERROR_MESSAGES.getString(snuggleTexErrorCode.getName());
+        String snuggletexErrorMessage = MessageFormat.format(snuggletexMessagePattern, arguments);
+        return Localization.lang("LaTeX Parsing Error: %0", snuggletexErrorMessage);
+    }
+}

src/main/resources/l10n/JabRef_en.properties

@@ -1489,6 +1489,7 @@ changes\ all\ letters\ to\ lower\ case.=changes all letters to lower case.
 CHANGES\ ALL\ LETTERS\ TO\ UPPER\ CASE.=CHANGES ALL LETTERS TO UPPER CASE.
 Changes\ The\ First\ Letter\ Of\ All\ Words\ To\ Capital\ Case\ And\ The\ Remaining\ Letters\ To\ Lower\ Case.=Changes The First Letter Of All Words To Capital Case And The Remaining Letters To Lower Case.
 Cleans\ up\ LaTeX\ code.=Cleans up LaTeX code.
+LaTeX\ Parsing\ Error\:\ %0=LaTeX Parsing Error: %0
 Converts\ HTML\ code\ to\ LaTeX\ code.=Converts HTML code to LaTeX code.
 HTML\ to\ Unicode=HTML to Unicode
 Converts\ HTML\ code\ to\ Unicode.=Converts HTML code to Unicode.