Add Cython flake8 file

Change-Id: I0ea3c209b98fec7347e8fae62748b7830de5dacf

ci/travis_script_python.sh

@@ -97,6 +97,9 @@ python_version_tests() {
   # Fail fast on style checks
   flake8 pyarrow
 
+  # Check Cython files with some checks turned off
+  flake8 --config=.flake8.cython pyarrow
+
   # Build C++ libraries
   rebuild_arrow_libraries
 

python/.flake8.cython

@@ -0,0 +1,20 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#   http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied.  See the License for the
+# specific language governing permissions and limitations
+# under the License.
+
+[flake8]
+filename = *.pyx,*.px*
+ignore = E211, E901,E225,E226,E227

python/README.md

@@ -49,6 +49,7 @@ build. Check for style errors before submitting your pull request with:
 
 ```
 flake8 pyarrow
+flake8 --config=.flake8.cython pyarrow
 ```
 
 ### Building from Source

python/pyarrow/_config.pyx

@@ -19,6 +19,10 @@
 # distutils: language = c++
 # cython: embedsignature = True
 
+import numpy as np
+import multiprocessing
+import os
+
 cdef extern from 'arrow/python/init.h':
     int arrow_init_numpy() except -1
 
@@ -27,15 +31,13 @@ cdef extern from 'arrow/python/config.h' namespace 'arrow::py':
 
 arrow_init_numpy()
 
-import numpy as np
 set_numpy_nan(np.nan)
 
-import multiprocessing
-import os
 cdef int CPU_COUNT = int(
     os.environ.get('OMP_NUM_THREADS',
                    max(multiprocessing.cpu_count() // 2, 1)))
 
+
 def cpu_count():
     """
     Returns
@@ -49,6 +51,7 @@ def cpu_count():
     """
     return CPU_COUNT
 
+
 def set_cpu_count(count):
     global CPU_COUNT
     CPU_COUNT = max(int(count), 1)

python/pyarrow/_parquet.pxd

@@ -25,17 +25,18 @@ from pyarrow.includes.libarrow cimport (CArray, CSchema, CStatus,
 
 
 cdef extern from "parquet/api/schema.h" namespace "parquet::schema" nogil:
-  cdef cppclass Node:
-    pass
+    cdef cppclass Node:
+        pass
 
-  cdef cppclass GroupNode(Node):
-    pass
+    cdef cppclass GroupNode(Node):
+        pass
 
-  cdef cppclass PrimitiveNode(Node):
-    pass
+    cdef cppclass PrimitiveNode(Node):
+        pass
+
+    cdef cppclass ColumnPath:
+        c_string ToDotString()
 
-  cdef cppclass ColumnPath:
-    c_string ToDotString()
 
 cdef extern from "parquet/api/schema.h" namespace "parquet" nogil:
     enum ParquetType" parquet::Type::type":
@@ -59,8 +60,10 @@ cdef extern from "parquet/api/schema.h" namespace "parquet" nogil:
         ParquetLogicalType_DATE" parquet::LogicalType::DATE"
         ParquetLogicalType_TIME_MILLIS" parquet::LogicalType::TIME_MILLIS"
         ParquetLogicalType_TIME_MICROS" parquet::LogicalType::TIME_MICROS"
-        ParquetLogicalType_TIMESTAMP_MILLIS" parquet::LogicalType::TIMESTAMP_MILLIS"
-        ParquetLogicalType_TIMESTAMP_MICROS" parquet::LogicalType::TIMESTAMP_MICROS"
+        ParquetLogicalType_TIMESTAMP_MILLIS\
+            " parquet::LogicalType::TIMESTAMP_MILLIS"
+        ParquetLogicalType_TIMESTAMP_MICROS\
+            " parquet::LogicalType::TIMESTAMP_MICROS"
         ParquetLogicalType_UINT_8" parquet::LogicalType::UINT_8"
         ParquetLogicalType_UINT_16" parquet::LogicalType::UINT_16"
         ParquetLogicalType_UINT_32" parquet::LogicalType::UINT_32"
@@ -83,8 +86,10 @@ cdef extern from "parquet/api/schema.h" namespace "parquet" nogil:
         ParquetEncoding_PLAIN_DICTIONARY" parquet::Encoding::PLAIN_DICTIONARY"
         ParquetEncoding_RLE" parquet::Encoding::RLE"
         ParquetEncoding_BIT_PACKED" parquet::Encoding::BIT_PACKED"
-        ParquetEncoding_DELTA_BINARY_PACKED" parquet::Encoding::DELTA_BINARY_PACKED"
-        ParquetEncoding_DELTA_LENGTH_BYTE_ARRAY" parquet::Encoding::DELTA_LENGTH_BYTE_ARRAY"
+        ParquetEncoding_DELTA_BINARY_PACKED\
+            " parquet::Encoding::DELTA_BINARY_PACKED"
+        ParquetEncoding_DELTA_LENGTH_BYTE_ARRAY\
+            " parquet::Encoding::DELTA_LENGTH_BYTE_ARRAY"
         ParquetEncoding_DELTA_BYTE_ARRAY" parquet::Encoding::DELTA_BYTE_ARRAY"
         ParquetEncoding_RLE_DICTIONARY" parquet::Encoding::RLE_DICTIONARY"
 
@@ -231,13 +236,15 @@ cdef extern from "parquet/arrow/reader.h" namespace "parquet::arrow" nogil:
 
 
 cdef extern from "parquet/arrow/schema.h" namespace "parquet::arrow" nogil:
-    CStatus FromParquetSchema(const SchemaDescriptor* parquet_schema,
-                              const shared_ptr[const CKeyValueMetadata]& key_value_metadata,
-                              shared_ptr[CSchema]* out)
+    CStatus FromParquetSchema(
+        const SchemaDescriptor* parquet_schema,
+        const shared_ptr[const CKeyValueMetadata]& key_value_metadata,
+        shared_ptr[CSchema]* out)
 
-    CStatus ToParquetSchema(const CSchema* arrow_schema,
-                            const shared_ptr[const CKeyValueMetadata]& key_value_metadata,
-                            shared_ptr[SchemaDescriptor]* out)
+    CStatus ToParquetSchema(
+        const CSchema* arrow_schema,
+        const shared_ptr[const CKeyValueMetadata]& key_value_metadata,
+        shared_ptr[SchemaDescriptor]* out)
 
 
 cdef extern from "parquet/arrow/writer.h" namespace "parquet::arrow" nogil:

python/pyarrow/_parquet.pyx

@@ -279,8 +279,8 @@ cdef class ColumnSchema:
   max_repetition_level: {3}
   physical_type: {4}
   logical_type: {5}""".format(self.name, self.path, self.max_definition_level,
-                       self.max_repetition_level, physical_type,
-                       logical_type)
+                              self.max_repetition_level, physical_type,
+                              logical_type)
 
     property name:
 
@@ -514,7 +514,7 @@ cdef class ParquetReader:
 
         with nogil:
             check_status(self.reader.get()
-                         .ReadSchemaField(field_index, &carray));
+                         .ReadSchemaField(field_index, &carray))
 
         array.init(carray)
         return array
@@ -553,7 +553,8 @@ cdef class ParquetWriter:
 
     def __cinit__(self, where, Schema schema, use_dictionary=None,
                   compression=None, version=None,
-                  MemoryPool memory_pool=None, use_deprecated_int96_timestamps=False):
+                  MemoryPool memory_pool=None,
+                  use_deprecated_int96_timestamps=False):
         cdef:
             shared_ptr[FileOutputStream] filestream
             shared_ptr[WriterProperties] properties

python/pyarrow/array.pxi

@@ -66,8 +66,8 @@ def array(object sequence, DataType type=None, MemoryPool memory_pool=None,
     array : pyarrow.Array
     """
     cdef:
-       shared_ptr[CArray] sp_array
-       CMemoryPool* pool
+        shared_ptr[CArray] sp_array
+        CMemoryPool* pool
 
     pool = maybe_unbox_memory_pool(memory_pool)
     if type is None:
@@ -78,13 +78,13 @@ def array(object sequence, DataType type=None, MemoryPool memory_pool=None,
                 ConvertPySequence(
                     sequence, pool, &sp_array, type.sp_type
                 )
-             )
+            )
         else:
             check_status(
                 ConvertPySequence(
                     sequence, pool, &sp_array, type.sp_type, size
                 )
-             )
+            )
 
     return pyarrow_wrap_array(sp_array)
 
@@ -401,7 +401,6 @@ strides: {2}""".format(self.type, self.shape, self.strides)
             return py_strides
 
 
-
 cdef wrap_array_output(PyObject* output):
     cdef object obj = PyObject_to_object(output)
 

python/pyarrow/feather.pxi

@@ -15,7 +15,7 @@
 # specific language governing permissions and limitations
 # under the License.
 
-#----------------------------------------------------------------------
+# ---------------------------------------------------------------------
 # Implement legacy Feather file format