query by hal id only

kermitt2 · Feb 25, 2024 · a7227b5 · a7227b5
1 parent 97cd71d
commit a7227b5
Show file tree

Hide file tree

Showing 2 changed files with 21 additions and 5 deletions.
diff --git a/grobid-core/src/main/java/org/grobid/core/data/BiblioItem.java b/grobid-core/src/main/java/org/grobid/core/data/BiblioItem.java
@@ -2119,9 +2119,6 @@ public String toBibTeX(String id, GrobidAnalysisConfig config) {
      * the corresponding field and reset the generic pubnum field.
      */
     public void checkIdentifier() {
-
-        System.out.println(pubnum);
-
         // DOI
         if (!StringUtils.isEmpty(pubnum) && StringUtils.isEmpty(doi)) {
             Matcher doiMatcher = TextUtilities.DOIPattern.matcher(pubnum);

diff --git a/grobid-core/src/main/java/org/grobid/core/utilities/Consolidation.java b/grobid-core/src/main/java/org/grobid/core/utilities/Consolidation.java
@@ -115,7 +115,7 @@ public void close() {
 
     /**
      * Try to consolidate one bibliographical object with crossref metadata lookup web services based on
-     * core metadata
+     * core metadata. In practice, this method is used for consolidating header metadata.  
      */
     public BiblioItem consolidate(BiblioItem bib, String rawCitation, int consolidateMode) throws Exception {
         final List<BiblioItem> results = new ArrayList<>();
@@ -125,6 +125,7 @@ public BiblioItem consolidate(BiblioItem bib, String rawCitation, int consolidat
             theDOI = cleanDOI(theDOI);
         }
         final String doi = theDOI;
+        String halId = bib.getHalId();
         String aut = bib.getFirstAuthorSurname();
         String title = bib.getTitle();
         String journalTitle = bib.getJournal();
@@ -171,6 +172,13 @@ public BiblioItem consolidate(BiblioItem bib, String rawCitation, int consolidat
                     arguments.put("query.bibliographic", rawCitation);
                 }
             }
+            if (StringUtils.isNotBlank(halId)) {
+                // call based on the identified HAL ID
+                if (arguments == null)
+                    arguments = new HashMap<String,String>();
+                if (GrobidProperties.getInstance().getConsolidationService() != GrobidConsolidationService.CROSSREF)
+                    arguments.put("halid", halId);
+            }
             if (StringUtils.isNotBlank(aut)) {
                 // call based on partial metadata
                 if (GrobidProperties.getInstance().getConsolidationService() != GrobidConsolidationService.CROSSREF) {
@@ -309,7 +317,9 @@ public void onError(int status, String message, Exception exception) {
 
 
     /**
-     * Try tp consolidate a list of bibliographical objects in one operation with consolidation services
+     * Try tp consolidate a list of bibliographical objects in one operation with consolidation services.
+     * In practice this method is used for consolidating the metadata of all the extracted bibliographical 
+     * references. 
      */
     public Map<Integer,BiblioItem> consolidate(List<BibDataSet> biblios) {
         if (CollectionUtils.isEmpty(biblios))
@@ -333,6 +343,8 @@ public Map<Integer,BiblioItem> consolidate(List<BibDataSet> biblios) {
             if (StringUtils.isNotBlank(doi)) {
                 doi = BiblioItem.cleanDOI(doi);
             }
+            // first we get the exploitable metadata
+            String halId = theBiblio.getHalId();
             String aut = theBiblio.getFirstAuthorSurname();
             String title = theBiblio.getTitle();
             String journalTitle = theBiblio.getJournal();
@@ -381,6 +393,13 @@ public Map<Integer,BiblioItem> consolidate(List<BibDataSet> biblios) {
                 arguments = new HashMap<String,String>();
                 arguments.put("doi", doi);
             }
+            if (StringUtils.isNotBlank(halId)) {
+                // call based on the identified HAL ID
+                if (arguments == null)
+                    arguments = new HashMap<String,String>();
+                if (GrobidProperties.getInstance().getConsolidationService() != GrobidConsolidationService.CROSSREF)
+                    arguments.put("halid", halId);
+            }
             if (StringUtils.isNotBlank(rawCitation)) {
                 // call with full raw string
                 if (arguments == null)