init commit

README.md

@@ -1 +1,12 @@
-# bib-combiner
+# bib-combiner
+
+A small python tool for combining multiple .bib files and removing duplicates by their IDs (ID: the string used for citation in lalex.)
+
+## Usage
+```bash
+python bib_combiner.py bib1.bib bib2.bib bib3.bib .bib
+```
+output is named `final.bib`.
+
+## Requirements
+see `requiremetns.txt` generated by [pipreqs](https://pypi.org/project/pipreqs/).

bib_combiner.py

@@ -0,0 +1,35 @@
+import os
+import sys
+import bibtexparser
+
+from bibtexparser.bwriter import BibTexWriter
+from bibtexparser.bibdatabase import BibDatabase
+
+if __name__ == "__main__":
+    bibtex_list = sys.argv[1:]
+    print(bibtex_list)
+
+    db_final = BibDatabase()
+    db_final.entries = []
+
+    bib_ids = []
+    bib_total = 0
+    bib_sum = 0
+    duplicate_num = 0
+
+    for bibtex in bibtex_list:
+        with open(bibtex, 'r') as bibtex_file:
+            bib_database = bibtexparser.load(bibtex_file)
+            for bib_dict in bib_database.entries:
+                bib_total += 1
+                if bib_dict['ID'] not in bib_ids:
+                    bib_sum += 1
+                    bib_ids.append(bib_dict['ID'])
+                    db_final.entries.append(bib_dict)
+                else:
+                    duplicate_num += 1
+
+    print(f'Total: {bib_total}, Duplicate:{duplicate_num}, Final:{bib_sum}')
+
+    with open('final.bib', 'w') as bibtex_file:
+        bibtexparser.dump(db_final, bibtex_file)

requirements.txt

@@ -0,0 +1,2 @@
+bibtexparser==1.2.0
+python==3.9