From dab90561d1d7bd784949c4bdd494b9165129a203 Mon Sep 17 00:00:00 2001
From: Mario Graff <mgraffg@ieee.org>
Date: Tue, 8 Oct 2024 13:59:18 +0000
Subject: [PATCH] Empty str

---
 dialectid/__init__.py         |  2 +-
 dialectid/model.py            |  3 +++
 dialectid/tests/test_model.py | 14 +++++++++++++-
 3 files changed, 17 insertions(+), 2 deletions(-)

diff --git a/dialectid/__init__.py b/dialectid/__init__.py
index 5e07f29..977f124 100644
--- a/dialectid/__init__.py
+++ b/dialectid/__init__.py
@@ -20,7 +20,7 @@
 # OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 # SOFTWARE.
 
-__version__ = '0.0.5'
+__version__ = '0.0.6'
 
 from dialectid.text_repr import BoW, SeqTM
 from dialectid.model import DialectId
\ No newline at end of file
diff --git a/dialectid/model.py b/dialectid/model.py
index ba5684c..17a0fa9 100644
--- a/dialectid/model.py
+++ b/dialectid/model.py
@@ -152,4 +152,7 @@ def encode(self, text):
             except KeyError:
                 continue
         W = self.weights
+        if len(seq) == 0:
+            dtype = getattr(np, f'float{self.precision}') 
+            return np.ones((W.shape[0], 1), dtype=dtype)
         return np.vstack([W[:, x] for x in seq]).T
diff --git a/dialectid/tests/test_model.py b/dialectid/tests/test_model.py
index 5f8a4e8..31085ec 100644
--- a/dialectid/tests/test_model.py
+++ b/dialectid/tests/test_model.py
@@ -91,4 +91,16 @@ def test_DenseBoW_encode():
 
     from dialectid.model import DenseBoW
     dense = DenseBoW(precision=16)
-    assert dense.encode('buenos días').shape[1] == 2
\ No newline at end of file
+    assert dense.encode('buenos días').shape[1] == 2
+
+
+def test_DenseBoW_encode_empty():
+    """Test DenseBoW for empty"""
+
+    # 'ᗩᒪᒪ ᒪIᐯEᔕ ᗰᗩTTEᖇ!!!!!'
+
+    from dialectid.model import DenseBoW
+    dense = DenseBoW(precision=16)
+    X = dense.encode('')
+    assert X.shape[1] == 1
+    assert X.sum() == len(dense.names)