feat: using StringBuilder for strings (#32)

* feat: using StringBuilder for strings

* test: stringbuilder creates a different masked array

However this is probably the intended behaviour

* test: encode bytes to a list of integers for testing

* ci: add numpy for testing

.github/workflows/python-package.yml

@@ -33,7 +33,7 @@ jobs:
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip
-        python -m pip install flake8 pytest
+        python -m pip install flake8 pytest numpy
     - name: Test
       run: |
         make test

tests/__init__.py

@@ -0,0 +1 @@
+from .utils import BytesToIntListEncoder

tests/test_index_option.py

@@ -23,7 +23,7 @@ def test_index_option():
     # Element 0 has a different shape because it is a ListOffsetBuilder<NumpyBuilder>
     # instead of just NumpyBuilder
     expected_array_bank1 = {
-        "0": np.ma.masked_array(data=[], mask=[], dtype=np.uint8).reshape((1, 0)),
+        "0": np.ma.masked_array(data=[0], mask=[True], dtype="<U1", fill_value="N/A"),
         "1": np.ma.masked_array(data=[0], mask=[True], dtype=np.uint16),
     }
     expected_array_bank1["2"] = expected_array_bank1["1"]

tests/test_scdms_v8.py

@@ -8,13 +8,19 @@
 
 import awkward_kaitai
 
+from . import BytesToIntListEncoder
+
 
 def test_scdms_v8():
     reader = awkward_kaitai.Reader("test_artifacts/libscdms_v8.so")
     awkward_array = reader.load("example_data/data/scdms_v8.mid")
 
+    parsed_array = json.loads(
+        json.dumps(awkward_array.to_list()[0], cls=BytesToIntListEncoder)
+    )
+
     with gzip.open("tests/scdms_v8.json.gz", "rb") as f:
         expected_content = json.load(f)
 
     # it was list of 1 element, so saved only the element into JSON
-    assert awkward_array.to_list()[0] == expected_content
+    assert parsed_array == expected_content

tests/utils.py

@@ -0,0 +1,13 @@
+import json
+import numpy as np
+
+
+class BytesToIntListEncoder(json.JSONEncoder):
+    """Allows encoding of a bytestring to JSON by turning it into
+    a list of `uint8`"""
+
+    def default(self, o):
+        if isinstance(o, bytes):
+            return np.frombuffer(o, dtype=np.uint8).tolist()
+        else:
+            return super().default(o)