mergefix

python/Cargo.toml

@@ -1,12 +1,13 @@
 [package]
 name = "deltalake-python"
-version = "0.5.0"
+version = "0.5.2"
 authors = ["Qingping Hou <dave2008713@gmail.com>"]
 homepage = "https://github.com/delta-io/delta-rs"
 license = "Apache-2.0"
-description = "Python binding for delta-rs"
+description = "Native Delta Lake Python binding based on delta-rs with Pandas integration"
 readme = "README.md"
 edition = "2018"
+keywords = ["deltalake", "delta", "datalake", "pandas", "arrow"]
 
 [lib]
 name = "deltalake"
@@ -22,7 +23,7 @@ serde_json = "1"
 arrow  = { git = "https://github.com/apache/arrow-rs", rev = "fa5acd971c973161f17e69d5c6b50d6e77c7da03" }
 
 [dependencies.pyo3]
-version = "0.13"
+version = "0.14"
 features = ["extension-module", "abi3", "abi3-py36"]
 
 [dependencies.deltalake]
@@ -38,13 +39,13 @@ classifier = [
     "License :: OSI Approved :: Apache Software License",
     "Programming Language :: Python :: 3 :: Only"
 ]
-project-url = { Repo = "https://github.com/delta-io/delta-rs" }
+project-url = { Repo = "https://github.com/delta-io/delta-rs", Documentation = "https://delta-io.github.io/delta-rs/python/", "Bug Tracker" = "https://github.com/delta-io/delta-rs/issues" }
 requires-dist = [
     "pyarrow>=4",
     'numpy<1.20.0;python_version<="3.6"',
     'dataclasses;python_version<="3.6"',
     'types-dataclasses;python_version<="3.6" and extra == "pandas"',
-    "pandas; extra == 'pandas'",
+    "pandas; extra == 'pandas' or extra == 'devel'",
     "mypy; extra == 'devel'",
     "isort; extra == 'devel'",
     "pytest; extra == 'devel'",

rust/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "deltalake"
-version = "0.4.0"
+version = "0.4.1"
 authors = ["Qingping Hou <dave2008713@gmail.com>"]
 homepage = "https://github.com/delta-io/delta.rs"
 license = "Apache-2.0"

rust/src/delta_arrow.rs

@@ -109,7 +109,7 @@ impl TryFrom<&schema::SchemaDataType> for ArrowDataType {
                     }
                     "date" => {
                         // A calendar date, represented as a year-month-day triple without a
-                        // timezone.
+                        // timezone. Stored as 4 bytes integer representing days sinece 1970-01-01
                         Ok(ArrowDataType::Date32)
                     }
                     "timestamp" => {
@@ -326,7 +326,7 @@ pub(crate) fn delta_log_schema_for_table(
         .fields()
         .iter()
         .map(|f| f.to_owned())
-        .partition(|field| partition_columns.contains(&field.name()));
+        .partition(|field| partition_columns.contains(field.name()));
 
     let mut stats_parsed_fields: Vec<ArrowField> =
         vec![ArrowField::new("numRecords", ArrowDataType::Int64, true)];

rust/tests/checkpoint_writer_test.rs

@@ -34,11 +34,6 @@ async fn write_simple_checkpoint() {
     let checkpoint_path = log_path.join("00000000000000000005.checkpoint.parquet");
     assert!(checkpoint_path.as_path().exists());
 
-    // HACK: seems like a race condition exists reading the file back in.
-    // Without the sleep, frequently fails with:
-    // Error("EOF while parsing a value", line: 1, column: 0)'
-    std::thread::sleep(std::time::Duration::from_secs(1));
-
     // _last_checkpoint should exist and point to the correct version
     let version = get_last_checkpoint_version(&log_path);
     assert_eq!(5, version);
@@ -54,9 +49,6 @@ async fn write_simple_checkpoint() {
     let checkpoint_path = log_path.join("00000000000000000010.checkpoint.parquet");
     assert!(checkpoint_path.as_path().exists());
 
-    // see above
-    std::thread::sleep(std::time::Duration::from_secs(1));
-
     // _last_checkpoint should exist and point to the correct version
     let version = get_last_checkpoint_version(&log_path);
     assert_eq!(10, version);