adding pyproject.toml

pyproject.toml

@@ -0,0 +1,24 @@
+[project]
+name = "mediawiki-dump-tools"
+version = "0.1.0"
+description = "Add your description here"
+readme = "README.md"
+requires-python = ">=3.11"
+dependencies = [
+    "deltas>=0.7.0",
+    "mw>=0.4.0",
+    "mwpersistence>=0.2.4",
+    "mwreverts>=0.1.5",
+    "mwxml>=0.3.6",
+    "pyarrow>=20.0.0",
+    "yamlconf",
+]
+
+[tool.uv.sources]
+yamlconf = { git = "https://github.com/groceryheist/yamlconf" }
+
+[dependency-groups]
+dev = [
+    "pandas>=2.1.0",
+    "pytest>=8.3.5",
+]

wikiq

@@ -250,13 +250,13 @@ class RevDataBase():
         pa.field("revid", pa.int64()),
         pa.field("date_time", pa.timestamp('ms')),
         pa.field("articleid",pa.int64()),
-        pa.field("editorid",pa.int64()),
+        pa.field("editorid",pa.int64(), nullable=True),
         pa.field("title",pa.string()),
         pa.field("namespace",pa.int32()),
         pa.field("deleted",pa.bool_()),
-        pa.field("test_chars",pa.int32()),
-        pa.field("revert",pa.bool_()),
-        pa.field("reverteds",pa.list_(pa.int64())),
+        pa.field("text_chars",pa.int32()),
+        pa.field("revert",pa.bool_(), nullable=True),
+        pa.field("reverteds",pa.list_(pa.int64()), nullable=True),
         pa.field("sha1",pa.string()),
         pa.field("minor",pa.bool_()),
         pa.field("editor",pa.string()),