Feature/doi column

.gitignore

@@ -205,3 +205,5 @@ cython_debug/
 marimo/_static/
 marimo/_lsp/
 __marimo__/
+/populate/.dbeaver/
+/populate/.project

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "welearn-database"
-version = "1.4.2"
+version = "1.4.3"
 description = "All stuff related to relationnal database from the WeLearn project"
 authors = [
     {name = "Théo",email = "theo.nardin@cri-paris.org"}
@@ -18,10 +18,10 @@ dependencies = [
 [tool.poetry]
 
 [tool.poetry.group.dev.dependencies]
-mypy = "^1.16.0"
-bandit = "^1.8.6"
-isort = "^6.1.0"
-black = "^25.9.0"
+mypy = "^2.1.0"
+bandit = "^1.9.4"
+isort = "^8.0.1"
+black = "26.3.1"
 
 [build-system]
 requires = ["poetry-core>=2.0.0,<3.0.0"]

tests/test_document_related.py

@@ -14,7 +14,7 @@
     ProcessState,
     WeLearnDocument,
 )
-from welearn_database.exceptions import InvalidURLScheme
+from welearn_database.exceptions import ContentIsTooShort, InvalidDOI, InvalidURLScheme
 
 
 class TestWeLearnDocument(TestCase):
@@ -72,7 +72,7 @@ def test_validate_full_content(self):
         )
 
     def test_validate_too_short_full_content(self):
-        with self.assertRaises(ValueError):
+        with self.assertRaises(ContentIsTooShort):
             WeLearnDocument(
                 title="Test Document",
                 url="https://example.com/test-document",
@@ -99,6 +99,52 @@ def test_full_content(self):
             "This is a test document, used for unit testing, please ignore. Thank you!",
         )
 
+    def test_doi(self):
+        test_doc = WeLearnDocument(
+            title="Test Document",
+            url="https://example.com/test-document",
+            full_content="This is a test document, used for unit testing, please ignore. Thank you!",
+            description="A short description of the test document.",
+            lang="en",
+            corpus="Test Corpus",
+            details={"author": "Test Author", "doi": "10.1000/xyz123"},
+            doi="10.1000/xyz123",
+        )
+
+        self.assertEqual(test_doc.doi, "10.1000/xyz123")
+
+    def test_invalid_doi(self):
+        with self.assertRaises(InvalidDOI):
+            WeLearnDocument(
+                title="Test Document",
+                url="https://example.com/test-document",
+                full_content="This is a test document, used for unit testing, please ignore. Thank you!",
+                description="A short description of the test document.",
+                lang="en",
+                corpus="Test Corpus",
+                details={
+                    "author": "Test Author",
+                    "doi": "11.1590/s0100-879x2002000500007",
+                },
+                doi="11.1590/s0100-879x2002000500007",
+            )
+
+    def test_unclean_doi(self):
+        with self.assertRaises(InvalidDOI):
+            WeLearnDocument(
+                title="Test Document",
+                url="https://example.com/test-document",
+                full_content="This is a test document, used for unit testing, please ignore. Thank you!",
+                description="A short description of the test document.",
+                lang="en",
+                corpus="Test Corpus",
+                details={
+                    "author": "Test Author",
+                    "doi": "https://doi.org/10.1000/xyz123",
+                },
+                doi="https://doi.org/10.1000/xyz123",
+            )
+
     def test_description(self):
         test_doc = WeLearnDocument(
             title="Test Document",
@@ -284,7 +330,9 @@ def test_none_trace_in_db(self):
             .first()
         )
         self.assertIsNotNone(doc_from_db)
-        self.assertEqual(doc_from_db.trace, None)
+        self.assertIsNone(
+            doc_from_db.trace,
+        )
 
     def test_view_qty_document(self):
         engine = create_engine("sqlite://")
@@ -335,9 +383,7 @@ def test_view_qty_document(self):
         test_session.execute(text("DROP TABLE IF EXISTS qty_document_in_qdrant"))
         test_session.commit()
 
-        test_session.execute(
-            text(
-                """
+        test_session.execute(text("""
             CREATE VIEW document_related.qty_document_in_qdrant AS
             SELECT COUNT(1) AS document_in_qdrant
             FROM (
@@ -346,9 +392,7 @@ def test_view_qty_document(self):
                 WHERE title = 'document_in_qdrant'
                 GROUP BY document_id
             ) latest;
-        """
-            )
-        )
+        """))
         test_session.commit()
 
         result = test_session.query(QtyDocumentInQdrant).first()

welearn_database/alembic/versions/f1ce0ad2845b_add_doi_column_to_document.py

@@ -0,0 +1,30 @@
+"""add doi column to document
+
+Revision ID: f1ce0ad2845b
+Revises: f8602200fa99
+Create Date: 2026-04-29 15:39:51.079086
+
+"""
+
+from typing import Sequence, Union
+
+import sqlalchemy as sa
+from alembic import op
+
+# revision identifiers, used by Alembic.
+revision: str = "f1ce0ad2845b"
+down_revision: Union[str, None] = "b049924f7067"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "welearn_document",
+        sa.Column("doi", sa.String(), nullable=True, unique=True),
+        schema="document_related",
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("welearn_document", "doi", schema="document_related")