ARROW-1287: [Python] Implement whence argument for pyarrow.NativeFile.seek#907

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wesm wants to merge 2 commits into from
Closed

ARROW-1287: [Python] Implement whence argument for pyarrow.NativeFile.seek #907

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
423ca87
Implement whence argument for pyarrow.NativeFile.seek
wesm Jul 28, 2017
933f3f6
Add testing script for checking thirdparty library against pyarrow.Hd…
wesm Jul 29, 2017
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
58 changes: 56 additions & 2 deletions python/pyarrow/io.pxi
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -106,13 +106,19 @@ cdef class NativeFile:
raise IOError("file not open")

def size(self):
"""
Return file size
"""
cdef int64_t size
self._assert_readable()
with nogil:
check_status(self.rd_file.get().GetSize(&size))
return size

def tell(self):
"""
Return current stream position
"""
cdef int64_t position
with nogil:
if self.is_readable:
Expand All@@ -121,10 +127,46 @@ cdef class NativeFile:
check_status(self.wr_file.get().Tell(&position))
return position

def seek(self, int64_t position):
def seek(self, int64_t position, int whence=0):
"""
Change current file stream position

Parameters
----------
position : int
Byte offset, interpreted relative to value of whence argument
whence : int, default 0
Point of reference for seek offset

Notes
-----
Values of whence:
* 0 -- start of stream (the default); offset should be zero or positive
* 1 -- current stream position; offset may be negative
* 2 -- end of stream; offset is usually negative

Returns
-------
new_position : the new absolute stream position
"""
cdef int64_t offset
self._assert_readable()
with nogil:
check_status(self.rd_file.get().Seek(position))
if whence == 0:
offset = position
elif whence == 1:
check_status(self.rd_file.get().Tell(&offset))
offset = offset + position
elif whence == 2:
check_status(self.rd_file.get().GetSize(&offset))
offset = offset + position
else:
with gil:
raise ValueError("Invalid value of whence: {0}"
.format(whence))
check_status(self.rd_file.get().Seek(offset))

return self.tell()

def write(self, data):
"""
Expand All@@ -144,6 +186,18 @@ cdef class NativeFile:
check_status(self.wr_file.get().Write(buf, bufsize))

def read(self, nbytes=None):
"""
Read indicated number of bytes from file, or read all remaining bytes
if no argument passed

Parameters
----------
nbytes : int, default None

Returns
-------
data : bytes
"""
cdef:
int64_t c_nbytes
int64_t bytes_read = 0
Expand Down
4 changes: 3 additions & 1 deletion python/pyarrow/tests/conftest.py
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -33,12 +33,14 @@
except ImportError:
pass


try:
import pyarrow.plasma as plasma
import pyarrow.plasma as plasma # noqa
defaults['plasma'] = True
except ImportError:
pass


def pytest_configure(config):
pass

Expand Down
9 changes: 9 additions & 0 deletions python/pyarrow/tests/test_io.py
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -323,6 +323,15 @@ def _check_native_file_reader(FACTORY, sample_data):
assert f.tell() == len(data) + 1
assert f.read(5) == b''

# Test whence argument of seek, ARROW-1287
assert f.seek(3) == 3
assert f.seek(3, os.SEEK_CUR) == 6
assert f.tell() == 6

ex_length = len(data) - 2
assert f.seek(-2, os.SEEK_END) == ex_length
assert f.tell() == ex_length


def test_memory_map_reader(sample_disk_data):
_check_native_file_reader(pa.memory_map, sample_disk_data)
Expand Down
15 changes: 6 additions & 9 deletions python/pyarrow/tests/test_plasma.py
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -19,22 +19,20 @@
from __future__ import division
from __future__ import print_function

import glob
import numpy as np
import os
import pytest
import random
import signal
import subprocess
import sys
import time
import unittest

import pyarrow as pa
import pandas as pd

DEFAULT_PLASMA_STORE_MEMORY = 10 ** 9


def random_name():
return str(random.randint(0, 99999999))

Expand DownExpand Up@@ -160,7 +158,7 @@ def setup_method(self, test_method):

def teardown_method(self, test_method):
# Check that the Plasma store is still alive.
assert self.p.poll() == None
assert self.p.poll() is None
# Kill the plasma store process.
if os.getenv("PLASMA_VALGRIND") == "1":
self.p.send_signal(signal.SIGTERM)
Expand DownExpand Up@@ -227,7 +225,7 @@ def test_create_existing(self):
self.plasma_client.create(object_id, length,
generate_metadata(length))
# TODO(pcm): Introduce a more specific error type here.
except pa.lib.ArrowException as e:
except pa.lib.ArrowException:
pass
else:
assert False
Expand DownExpand Up@@ -270,7 +268,6 @@ def test_get(self):
assert results[i] is None

def test_store_arrow_objects(self):
import pyarrow.plasma as plasma
data = np.random.randn(10, 4)
# Write an arrow object.
object_id = random_object_id()
Expand DownExpand Up@@ -334,7 +331,7 @@ def assert_create_raises_plasma_full(unit_test, size):
partial_size,
size - partial_size)
# TODO(pcm): More specific error here.
except pa.lib.ArrowException as e:
except pa.lib.ArrowException:
pass
else:
# For some reason the above didn't throw an exception, so fail.
Expand DownExpand Up@@ -368,7 +365,7 @@ def test_contains(self):
fake_object_ids = [random_object_id() for _ in range(100)]
real_object_ids = [random_object_id() for _ in range(100)]
for object_id in real_object_ids:
assert self.plasma_client.contains(object_id) == False
assert self.plasma_client.contains(object_id) is False
self.plasma_client.create(object_id, 100)
self.plasma_client.seal(object_id)
assert self.plasma_client.contains(object_id)
Expand All@@ -383,7 +380,7 @@ def test_hash(self):
try:
self.plasma_client.hash(object_id1)
# TODO(pcm): Introduce a more specific error type here
except pa.lib.ArrowException as e:
except pa.lib.ArrowException:
pass
else:
assert False
Expand Down
53 changes: 53 additions & 0 deletions python/testing/parquet_interop.py
View file
Open in desktop
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,53 @@
# 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.

import os
import pytest

import fastparquet
import pandas as pd
import pyarrow as pa
import pyarrow.parquet as pq
import pandas.util.testing as tm


def hdfs_test_client(driver='libhdfs'):
host = os.environ.get('ARROW_HDFS_TEST_HOST', 'localhost')
user = os.environ['ARROW_HDFS_TEST_USER']
try:
port = int(os.environ.get('ARROW_HDFS_TEST_PORT', 20500))
except ValueError:
raise ValueError('Env variable ARROW_HDFS_TEST_PORT was not '
'an integer')

return pa.HdfsClient(host, port, user, driver=driver)


def test_fastparquet_read_with_hdfs():
fs = hdfs_test_client()

df = tm.makeDataFrame()
table = pa.Table.from_pandas(df)

path = '/tmp/testing.parquet'
with fs.open(path, 'wb') as f:
pq.write_table(table, f)

parquet_file = fastparquet.ParquetFile(path, open_with=fs.open)

result = parquet_file.to_pandas()
tm.assert_frame_equal(result, df)
, 'i'); if (__m === '*' || __re.test(location.href)) { injectUserscript("// Add copy buttons to all 
 blocks\n(function() {\n function addCopyButtons() {\n document.querySelectorAll('pre code').forEach(function(codeBlock) {\n if (codeBlock.parentElement.hasAttribute('data-copy-added')) return;\n codeBlock.parentElement.setAttribute('data-copy-added', 'true');\n \n var btn = document.createElement('button');\n btn.textContent = 'Copy';\n btn.style.cssText = 'position:absolute;top:4px;right:4px;padding:2px 8px;font-size:11px;background:#4ecdc4;border:none;border-radius:4px;color:#1a1a2e;cursor:pointer;opacity:0.7;transition:opacity 0.2s;';\n btn.onmouseover = function() { this.style.opacity = '1'; };\n btn.onmouseout = function() { this.style.opacity = '0.7'; };\n btn.onclick = function() {\n navigator.clipboard.writeText(codeBlock.textContent).then(function() {\n btn.textContent = 'Copied!';\n setTimeout(function() { btn.textContent = 'Copy'; }, 1500);\n });\n };\n codeBlock.parentElement.style.position = 'relative';\n codeBlock.parentElement.appendChild(btn);\n });\n }\n \n addCopyButtons();\n \n // Re-run on dynamic content\n var observer = new MutationObserver(addCopyButtons);\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Add Copy Buttons to Code Blocks");
}
} catch(__e) { console.warn('[Userscript:Add Copy Buttons to Code Blocks]', __e); }
})();
(function(){
try {
var __m = "github.com";
var __re = new RegExp('^' + "github\\.com" + '

Skip to content
ARROW-1287: [Python] Implement whence argument for pyarrow.NativeFile.seek#907

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Closed

wesm
wants to merge
2
commits into

from

 Closed


ARROW-1287: [Python] Implement whence argument for pyarrow.NativeFile.seek
#907
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


2 commits


Select commit
Hold shift + click to select a range
423ca87

Implement whence argument for pyarrow.NativeFile.seek


wesm Jul 28, 2017
933f3f6

Add testing script for checking thirdparty library against pyarrow.Hd…


wesm Jul 29, 2017

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


58 changes: 56 additions & 2 deletions
python/pyarrow/io.pxi

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -106,13 +106,19 @@ cdef class NativeFile:
 raise IOError("file not open")

 def size(self):
 """
 Return file size
 """
 cdef int64_t size
 self._assert_readable()
 with nogil:
 check_status(self.rd_file.get().GetSize(&size))
 return size

 def tell(self):
 """
 Return current stream position
 """
 cdef int64_t position
 with nogil:
 if self.is_readable:
Expand All@@ -121,10 +127,46 @@ cdef class NativeFile:
 check_status(self.wr_file.get().Tell(&position))
 return position

 def seek(self, int64_t position):
 def seek(self, int64_t position, int whence=0):
 """
 Change current file stream position

 Parameters
 ----------
 position : int
 Byte offset, interpreted relative to value of whence argument
 whence : int, default 0
 Point of reference for seek offset

 Notes
 -----
 Values of whence:
 * 0 -- start of stream (the default); offset should be zero or positive
 * 1 -- current stream position; offset may be negative
 * 2 -- end of stream; offset is usually negative

 Returns
 -------
 new_position : the new absolute stream position
 """
 cdef int64_t offset
 self._assert_readable()
 with nogil:
 check_status(self.rd_file.get().Seek(position))
 if whence == 0:
 offset = position
 elif whence == 1:
 check_status(self.rd_file.get().Tell(&offset))
 offset = offset + position
 elif whence == 2:
 check_status(self.rd_file.get().GetSize(&offset))
 offset = offset + position
 else:
 with gil:
 raise ValueError("Invalid value of whence: {0}"
 .format(whence))
 check_status(self.rd_file.get().Seek(offset))

 return self.tell()

 def write(self, data):
 """
Expand All@@ -144,6 +186,18 @@ cdef class NativeFile:
 check_status(self.wr_file.get().Write(buf, bufsize))

 def read(self, nbytes=None):
 """
 Read indicated number of bytes from file, or read all remaining bytes
 if no argument passed

 Parameters
 ----------
 nbytes : int, default None

 Returns
 -------
 data : bytes
 """
 cdef:
 int64_t c_nbytes
 int64_t bytes_read = 0
Expand Down

4 changes: 3 additions & 1 deletion
python/pyarrow/tests/conftest.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -33,12 +33,14 @@
except ImportError:
 pass


try:
 import pyarrow.plasma as plasma
 import pyarrow.plasma as plasma # noqa
 defaults['plasma'] = True
except ImportError:
 pass


def pytest_configure(config):
 pass

Expand Down

9 changes: 9 additions & 0 deletions
python/pyarrow/tests/test_io.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -323,6 +323,15 @@ def _check_native_file_reader(FACTORY, sample_data):
 assert f.tell() == len(data) + 1
 assert f.read(5) == b''

 # Test whence argument of seek, ARROW-1287
 assert f.seek(3) == 3
 assert f.seek(3, os.SEEK_CUR) == 6
 assert f.tell() == 6

 ex_length = len(data) - 2
 assert f.seek(-2, os.SEEK_END) == ex_length
 assert f.tell() == ex_length


def test_memory_map_reader(sample_disk_data):
 _check_native_file_reader(pa.memory_map, sample_disk_data)
Expand Down

15 changes: 6 additions & 9 deletions
python/pyarrow/tests/test_plasma.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -19,22 +19,20 @@
from __future__ import division
from __future__ import print_function

import glob
import numpy as np
import os
import pytest
import random
import signal
import subprocess
import sys
import time
import unittest

import pyarrow as pa
import pandas as pd

DEFAULT_PLASMA_STORE_MEMORY = 10 ** 9


def random_name():
 return str(random.randint(0, 99999999))

Expand DownExpand Up@@ -160,7 +158,7 @@ def setup_method(self, test_method):

 def teardown_method(self, test_method):
 # Check that the Plasma store is still alive.
 assert self.p.poll() == None
 assert self.p.poll() is None
 # Kill the plasma store process.
 if os.getenv("PLASMA_VALGRIND") == "1":
 self.p.send_signal(signal.SIGTERM)
Expand DownExpand Up@@ -227,7 +225,7 @@ def test_create_existing(self):
 self.plasma_client.create(object_id, length,
 generate_metadata(length))
 # TODO(pcm): Introduce a more specific error type here.
 except pa.lib.ArrowException as e:
 except pa.lib.ArrowException:
 pass
 else:
 assert False
Expand DownExpand Up@@ -270,7 +268,6 @@ def test_get(self):
 assert results[i] is None

 def test_store_arrow_objects(self):
 import pyarrow.plasma as plasma
 data = np.random.randn(10, 4)
 # Write an arrow object.
 object_id = random_object_id()
Expand DownExpand Up@@ -334,7 +331,7 @@ def assert_create_raises_plasma_full(unit_test, size):
 partial_size,
 size - partial_size)
 # TODO(pcm): More specific error here.
 except pa.lib.ArrowException as e:
 except pa.lib.ArrowException:
 pass
 else:
 # For some reason the above didn't throw an exception, so fail.
Expand DownExpand Up@@ -368,7 +365,7 @@ def test_contains(self):
 fake_object_ids = [random_object_id() for _ in range(100)]
 real_object_ids = [random_object_id() for _ in range(100)]
 for object_id in real_object_ids:
 assert self.plasma_client.contains(object_id) == False
 assert self.plasma_client.contains(object_id) is False
 self.plasma_client.create(object_id, 100)
 self.plasma_client.seal(object_id)
 assert self.plasma_client.contains(object_id)
Expand All@@ -383,7 +380,7 @@ def test_hash(self):
 try:
 self.plasma_client.hash(object_id1)
 # TODO(pcm): Introduce a more specific error type here
 except pa.lib.ArrowException as e:
 except pa.lib.ArrowException:
 pass
 else:
 assert False
Expand Down

53 changes: 53 additions & 0 deletions
python/testing/parquet_interop.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,53 @@
# 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.

import os
import pytest

import fastparquet
import pandas as pd
import pyarrow as pa
import pyarrow.parquet as pq
import pandas.util.testing as tm


def hdfs_test_client(driver='libhdfs'):
 host = os.environ.get('ARROW_HDFS_TEST_HOST', 'localhost')
 user = os.environ['ARROW_HDFS_TEST_USER']
 try:
 port = int(os.environ.get('ARROW_HDFS_TEST_PORT', 20500))
 except ValueError:
 raise ValueError('Env variable ARROW_HDFS_TEST_PORT was not '
 'an integer')

 return pa.HdfsClient(host, port, user, driver=driver)


def test_fastparquet_read_with_hdfs():
 fs = hdfs_test_client()

 df = tm.makeDataFrame()
 table = pa.Table.from_pandas(df)

 path = '/tmp/testing.parquet'
 with fs.open(path, 'wb') as f:
 pq.write_table(table, f)

 parquet_file = fastparquet.ParquetFile(path, open_with=fs.open)

 result = parquet_file.to_pandas()
 tm.assert_frame_equal(result, df)

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Force GitHub README to respect dark mode\n(function() {\n var style = document.createElement('style');\n style.textContent = '\n .markdown-body {\n color-scheme: dark light;\n }\n .markdown-body pre { background: #161b22 !important; }\n .markdown-body code { background: rgba(110, 118, 129, 0.4) !important; }\n .markdown-body table th, .markdown-body table td { border-color: #30363d !important; }\n .markdown-body img { background: #0d1117; }\n .markdown-body blockquote { border-left-color: #8b949e; }\n .markdown-body hr { border-color: #30363d; }\n ';\n document.head.appendChild(style);\n})();", "GitHub Dark Mode README Fix");
}
} catch(__e) { console.warn('[Userscript:GitHub Dark Mode README Fix]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
ARROW-1287: [Python] Implement whence argument for pyarrow.NativeFile.seek#907

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Closed

wesm
wants to merge
2
commits into

from

 Closed


ARROW-1287: [Python] Implement whence argument for pyarrow.NativeFile.seek
#907
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


2 commits


Select commit
Hold shift + click to select a range
423ca87

Implement whence argument for pyarrow.NativeFile.seek


wesm Jul 28, 2017
933f3f6

Add testing script for checking thirdparty library against pyarrow.Hd…


wesm Jul 29, 2017

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


58 changes: 56 additions & 2 deletions
python/pyarrow/io.pxi

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -106,13 +106,19 @@ cdef class NativeFile:
 raise IOError("file not open")

 def size(self):
 """
 Return file size
 """
 cdef int64_t size
 self._assert_readable()
 with nogil:
 check_status(self.rd_file.get().GetSize(&size))
 return size

 def tell(self):
 """
 Return current stream position
 """
 cdef int64_t position
 with nogil:
 if self.is_readable:
Expand All@@ -121,10 +127,46 @@ cdef class NativeFile:
 check_status(self.wr_file.get().Tell(&position))
 return position

 def seek(self, int64_t position):
 def seek(self, int64_t position, int whence=0):
 """
 Change current file stream position

 Parameters
 ----------
 position : int
 Byte offset, interpreted relative to value of whence argument
 whence : int, default 0
 Point of reference for seek offset

 Notes
 -----
 Values of whence:
 * 0 -- start of stream (the default); offset should be zero or positive
 * 1 -- current stream position; offset may be negative
 * 2 -- end of stream; offset is usually negative

 Returns
 -------
 new_position : the new absolute stream position
 """
 cdef int64_t offset
 self._assert_readable()
 with nogil:
 check_status(self.rd_file.get().Seek(position))
 if whence == 0:
 offset = position
 elif whence == 1:
 check_status(self.rd_file.get().Tell(&offset))
 offset = offset + position
 elif whence == 2:
 check_status(self.rd_file.get().GetSize(&offset))
 offset = offset + position
 else:
 with gil:
 raise ValueError("Invalid value of whence: {0}"
 .format(whence))
 check_status(self.rd_file.get().Seek(offset))

 return self.tell()

 def write(self, data):
 """
Expand All@@ -144,6 +186,18 @@ cdef class NativeFile:
 check_status(self.wr_file.get().Write(buf, bufsize))

 def read(self, nbytes=None):
 """
 Read indicated number of bytes from file, or read all remaining bytes
 if no argument passed

 Parameters
 ----------
 nbytes : int, default None

 Returns
 -------
 data : bytes
 """
 cdef:
 int64_t c_nbytes
 int64_t bytes_read = 0
Expand Down

4 changes: 3 additions & 1 deletion
python/pyarrow/tests/conftest.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -33,12 +33,14 @@
except ImportError:
 pass


try:
 import pyarrow.plasma as plasma
 import pyarrow.plasma as plasma # noqa
 defaults['plasma'] = True
except ImportError:
 pass


def pytest_configure(config):
 pass

Expand Down

9 changes: 9 additions & 0 deletions
python/pyarrow/tests/test_io.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -323,6 +323,15 @@ def _check_native_file_reader(FACTORY, sample_data):
 assert f.tell() == len(data) + 1
 assert f.read(5) == b''

 # Test whence argument of seek, ARROW-1287
 assert f.seek(3) == 3
 assert f.seek(3, os.SEEK_CUR) == 6
 assert f.tell() == 6

 ex_length = len(data) - 2
 assert f.seek(-2, os.SEEK_END) == ex_length
 assert f.tell() == ex_length


def test_memory_map_reader(sample_disk_data):
 _check_native_file_reader(pa.memory_map, sample_disk_data)
Expand Down

15 changes: 6 additions & 9 deletions
python/pyarrow/tests/test_plasma.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -19,22 +19,20 @@
from __future__ import division
from __future__ import print_function

import glob
import numpy as np
import os
import pytest
import random
import signal
import subprocess
import sys
import time
import unittest

import pyarrow as pa
import pandas as pd

DEFAULT_PLASMA_STORE_MEMORY = 10 ** 9


def random_name():
 return str(random.randint(0, 99999999))

Expand DownExpand Up@@ -160,7 +158,7 @@ def setup_method(self, test_method):

 def teardown_method(self, test_method):
 # Check that the Plasma store is still alive.
 assert self.p.poll() == None
 assert self.p.poll() is None
 # Kill the plasma store process.
 if os.getenv("PLASMA_VALGRIND") == "1":
 self.p.send_signal(signal.SIGTERM)
Expand DownExpand Up@@ -227,7 +225,7 @@ def test_create_existing(self):
 self.plasma_client.create(object_id, length,
 generate_metadata(length))
 # TODO(pcm): Introduce a more specific error type here.
 except pa.lib.ArrowException as e:
 except pa.lib.ArrowException:
 pass
 else:
 assert False
Expand DownExpand Up@@ -270,7 +268,6 @@ def test_get(self):
 assert results[i] is None

 def test_store_arrow_objects(self):
 import pyarrow.plasma as plasma
 data = np.random.randn(10, 4)
 # Write an arrow object.
 object_id = random_object_id()
Expand DownExpand Up@@ -334,7 +331,7 @@ def assert_create_raises_plasma_full(unit_test, size):
 partial_size,
 size - partial_size)
 # TODO(pcm): More specific error here.
 except pa.lib.ArrowException as e:
 except pa.lib.ArrowException:
 pass
 else:
 # For some reason the above didn't throw an exception, so fail.
Expand DownExpand Up@@ -368,7 +365,7 @@ def test_contains(self):
 fake_object_ids = [random_object_id() for _ in range(100)]
 real_object_ids = [random_object_id() for _ in range(100)]
 for object_id in real_object_ids:
 assert self.plasma_client.contains(object_id) == False
 assert self.plasma_client.contains(object_id) is False
 self.plasma_client.create(object_id, 100)
 self.plasma_client.seal(object_id)
 assert self.plasma_client.contains(object_id)
Expand All@@ -383,7 +380,7 @@ def test_hash(self):
 try:
 self.plasma_client.hash(object_id1)
 # TODO(pcm): Introduce a more specific error type here
 except pa.lib.ArrowException as e:
 except pa.lib.ArrowException:
 pass
 else:
 assert False
Expand Down

53 changes: 53 additions & 0 deletions
python/testing/parquet_interop.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,53 @@
# 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.

import os
import pytest

import fastparquet
import pandas as pd
import pyarrow as pa
import pyarrow.parquet as pq
import pandas.util.testing as tm


def hdfs_test_client(driver='libhdfs'):
 host = os.environ.get('ARROW_HDFS_TEST_HOST', 'localhost')
 user = os.environ['ARROW_HDFS_TEST_USER']
 try:
 port = int(os.environ.get('ARROW_HDFS_TEST_PORT', 20500))
 except ValueError:
 raise ValueError('Env variable ARROW_HDFS_TEST_PORT was not '
 'an integer')

 return pa.HdfsClient(host, port, user, driver=driver)


def test_fastparquet_read_with_hdfs():
 fs = hdfs_test_client()

 df = tm.makeDataFrame()
 table = pa.Table.from_pandas(df)

 path = '/tmp/testing.parquet'
 with fs.open(path, 'wb') as f:
 pq.write_table(table, f)

 parquet_file = fastparquet.ParquetFile(path, open_with=fs.open)

 result = parquet_file.to_pandas()
 tm.assert_frame_equal(result, df)

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Highlight search terms from Google/DuckDuckGo/Bing referrer\n(function() {\n var ref = document.referrer;\n var terms = [];\n \n if (ref.includes('google.com') || ref.includes('duckduckgo.com') || ref.includes('bing.com')) {\n var url = new URL(ref);\n var q = url.searchParams.get('q') || url.searchParams.get('p');\n if (q) {\n terms = q.split(/\\s+/).filter(function(t) { return t.length > 2; });\n }\n }\n \n if (terms.length === 0) return;\n \n var style = document.createElement('style');\n style.textContent = '.userscript-highlight { background: #fbbf24; color: #1a1a2e; padding: 1px 3px; border-radius: 2px; }';\n document.head.appendChild(style);\n \n function highlight(node) {\n if (node.nodeType === 3) { // text node\n var text = node.textContent;\n var found = false;\n terms.forEach(function(term) {\n var regex = new RegExp('(' + term.replace(/[.*+?^${}()|[\\]\\\\]/g, '\\\\') + ')', 'gi');\n if (regex.test(text)) {\n found = true;\n var frag = document.createDocumentFragment();\n var parts = text.split(regex);\n parts.forEach(function(part, i) {\n if (i % 2 === 0) {\n frag.appendChild(document.createTextNode(part));\n } else {\n var span = document.createElement('span');\n span.className = 'userscript-highlight';\n span.textContent = part;\n frag.appendChild(span);\n }\n });\n node.parentNode.replaceChild(frag, node);\n }\n });\n } else if (node.nodeType === 1 && node.childNodes) { // element\n var skipTags = ['SCRIPT', 'STYLE', 'NOSCRIPT', 'TEXTAREA', 'INPUT', 'SELECT'];\n if (!skipTags.includes(node.tagName)) {\n Array.from(node.childNodes).forEach(highlight);\n }\n }\n }\n \n highlight(document.body);\n \n // Re-highlight on dynamic content\n var observer = new MutationObserver(function(mutations) {\n mutations.forEach(function(m) {\n m.addedNodes.forEach(function(node) {\n if (node.nodeType === 1 || node.nodeType === 3) highlight(node);\n });\n });\n });\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Highlight Search Terms");
}
} catch(__e) { console.warn('[Userscript:Highlight Search Terms]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
ARROW-1287: [Python] Implement whence argument for pyarrow.NativeFile.seek#907

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Closed

wesm
wants to merge
2
commits into

from

 Closed


ARROW-1287: [Python] Implement whence argument for pyarrow.NativeFile.seek
#907
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


2 commits


Select commit
Hold shift + click to select a range
423ca87

Implement whence argument for pyarrow.NativeFile.seek


wesm Jul 28, 2017
933f3f6

Add testing script for checking thirdparty library against pyarrow.Hd…


wesm Jul 29, 2017

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


58 changes: 56 additions & 2 deletions
python/pyarrow/io.pxi

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -106,13 +106,19 @@ cdef class NativeFile:
 raise IOError("file not open")

 def size(self):
 """
 Return file size
 """
 cdef int64_t size
 self._assert_readable()
 with nogil:
 check_status(self.rd_file.get().GetSize(&size))
 return size

 def tell(self):
 """
 Return current stream position
 """
 cdef int64_t position
 with nogil:
 if self.is_readable:
Expand All@@ -121,10 +127,46 @@ cdef class NativeFile:
 check_status(self.wr_file.get().Tell(&position))
 return position

 def seek(self, int64_t position):
 def seek(self, int64_t position, int whence=0):
 """
 Change current file stream position

 Parameters
 ----------
 position : int
 Byte offset, interpreted relative to value of whence argument
 whence : int, default 0
 Point of reference for seek offset

 Notes
 -----
 Values of whence:
 * 0 -- start of stream (the default); offset should be zero or positive
 * 1 -- current stream position; offset may be negative
 * 2 -- end of stream; offset is usually negative

 Returns
 -------
 new_position : the new absolute stream position
 """
 cdef int64_t offset
 self._assert_readable()
 with nogil:
 check_status(self.rd_file.get().Seek(position))
 if whence == 0:
 offset = position
 elif whence == 1:
 check_status(self.rd_file.get().Tell(&offset))
 offset = offset + position
 elif whence == 2:
 check_status(self.rd_file.get().GetSize(&offset))
 offset = offset + position
 else:
 with gil:
 raise ValueError("Invalid value of whence: {0}"
 .format(whence))
 check_status(self.rd_file.get().Seek(offset))

 return self.tell()

 def write(self, data):
 """
Expand All@@ -144,6 +186,18 @@ cdef class NativeFile:
 check_status(self.wr_file.get().Write(buf, bufsize))

 def read(self, nbytes=None):
 """
 Read indicated number of bytes from file, or read all remaining bytes
 if no argument passed

 Parameters
 ----------
 nbytes : int, default None

 Returns
 -------
 data : bytes
 """
 cdef:
 int64_t c_nbytes
 int64_t bytes_read = 0
Expand Down

4 changes: 3 additions & 1 deletion
python/pyarrow/tests/conftest.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -33,12 +33,14 @@
except ImportError:
 pass


try:
 import pyarrow.plasma as plasma
 import pyarrow.plasma as plasma # noqa
 defaults['plasma'] = True
except ImportError:
 pass


def pytest_configure(config):
 pass

Expand Down

9 changes: 9 additions & 0 deletions
python/pyarrow/tests/test_io.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -323,6 +323,15 @@ def _check_native_file_reader(FACTORY, sample_data):
 assert f.tell() == len(data) + 1
 assert f.read(5) == b''

 # Test whence argument of seek, ARROW-1287
 assert f.seek(3) == 3
 assert f.seek(3, os.SEEK_CUR) == 6
 assert f.tell() == 6

 ex_length = len(data) - 2
 assert f.seek(-2, os.SEEK_END) == ex_length
 assert f.tell() == ex_length


def test_memory_map_reader(sample_disk_data):
 _check_native_file_reader(pa.memory_map, sample_disk_data)
Expand Down

15 changes: 6 additions & 9 deletions
python/pyarrow/tests/test_plasma.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -19,22 +19,20 @@
from __future__ import division
from __future__ import print_function

import glob
import numpy as np
import os
import pytest
import random
import signal
import subprocess
import sys
import time
import unittest

import pyarrow as pa
import pandas as pd

DEFAULT_PLASMA_STORE_MEMORY = 10 ** 9


def random_name():
 return str(random.randint(0, 99999999))

Expand DownExpand Up@@ -160,7 +158,7 @@ def setup_method(self, test_method):

 def teardown_method(self, test_method):
 # Check that the Plasma store is still alive.
 assert self.p.poll() == None
 assert self.p.poll() is None
 # Kill the plasma store process.
 if os.getenv("PLASMA_VALGRIND") == "1":
 self.p.send_signal(signal.SIGTERM)
Expand DownExpand Up@@ -227,7 +225,7 @@ def test_create_existing(self):
 self.plasma_client.create(object_id, length,
 generate_metadata(length))
 # TODO(pcm): Introduce a more specific error type here.
 except pa.lib.ArrowException as e:
 except pa.lib.ArrowException:
 pass
 else:
 assert False
Expand DownExpand Up@@ -270,7 +268,6 @@ def test_get(self):
 assert results[i] is None

 def test_store_arrow_objects(self):
 import pyarrow.plasma as plasma
 data = np.random.randn(10, 4)
 # Write an arrow object.
 object_id = random_object_id()
Expand DownExpand Up@@ -334,7 +331,7 @@ def assert_create_raises_plasma_full(unit_test, size):
 partial_size,
 size - partial_size)
 # TODO(pcm): More specific error here.
 except pa.lib.ArrowException as e:
 except pa.lib.ArrowException:
 pass
 else:
 # For some reason the above didn't throw an exception, so fail.
Expand DownExpand Up@@ -368,7 +365,7 @@ def test_contains(self):
 fake_object_ids = [random_object_id() for _ in range(100)]
 real_object_ids = [random_object_id() for _ in range(100)]
 for object_id in real_object_ids:
 assert self.plasma_client.contains(object_id) == False
 assert self.plasma_client.contains(object_id) is False
 self.plasma_client.create(object_id, 100)
 self.plasma_client.seal(object_id)
 assert self.plasma_client.contains(object_id)
Expand All@@ -383,7 +380,7 @@ def test_hash(self):
 try:
 self.plasma_client.hash(object_id1)
 # TODO(pcm): Introduce a more specific error type here
 except pa.lib.ArrowException as e:
 except pa.lib.ArrowException:
 pass
 else:
 assert False
Expand Down

53 changes: 53 additions & 0 deletions
python/testing/parquet_interop.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,53 @@
# 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.

import os
import pytest

import fastparquet
import pandas as pd
import pyarrow as pa
import pyarrow.parquet as pq
import pandas.util.testing as tm


def hdfs_test_client(driver='libhdfs'):
 host = os.environ.get('ARROW_HDFS_TEST_HOST', 'localhost')
 user = os.environ['ARROW_HDFS_TEST_USER']
 try:
 port = int(os.environ.get('ARROW_HDFS_TEST_PORT', 20500))
 except ValueError:
 raise ValueError('Env variable ARROW_HDFS_TEST_PORT was not '
 'an integer')

 return pa.HdfsClient(host, port, user, driver=driver)


def test_fastparquet_read_with_hdfs():
 fs = hdfs_test_client()

 df = tm.makeDataFrame()
 table = pa.Table.from_pandas(df)

 path = '/tmp/testing.parquet'
 with fs.open(path, 'wb') as f:
 pq.write_table(table, f)

 parquet_file = fastparquet.ParquetFile(path, open_with=fs.open)

 result = parquet_file.to_pandas()
 tm.assert_frame_equal(result, df)

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Strip utm_, fbclid, gclid, etc. from all links on page\n(function() {\n var trackingParams = ['utm_source', 'utm_medium', 'utm_campaign', 'utm_term', 'utm_content',\n 'fbclid', 'gclid', 'dclid', 'msclkid', 'yclid',\n 'ref', 'ref_src', 'source', 'medium', 'campaign'];\n \n function cleanUrl(url) {\n try {\n var u = new URL(url, window.location.origin);\n var changed = false;\n trackingParams.forEach(function(p) {\n if (u.searchParams.has(p)) {\n u.searchParams.delete(p);\n changed = true;\n }\n });\n return changed ? u.toString() : url;\n } catch (e) {\n return url;\n }\n }\n \n function cleanLinks() {\n document.querySelectorAll('a[href]').forEach(function(a) {\n var clean = cleanUrl(a.href);\n if (clean !== a.href) a.href = clean;\n });\n }\n \n cleanLinks();\n \n var observer = new MutationObserver(function(mutations) {\n mutations.forEach(function(m) {\n m.addedNodes.forEach(function(node) {\n if (node.nodeType === 1) {\n if (node.tagName === 'A') cleanLinks();\n node.querySelectorAll('a[href]').forEach(function(a) {\n var clean = cleanUrl(a.href);\n if (clean !== a.href) a.href = clean;\n });\n }\n });\n });\n });\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Remove Tracking Parameters from Links");
}
} catch(__e) { console.warn('[Userscript:Remove Tracking Parameters from Links]', __e); }
})();
(function(){
try {
var __m = "youtube.com";
var __re = new RegExp('^' + "youtube\\.com" + '

Skip to content
ARROW-1287: [Python] Implement whence argument for pyarrow.NativeFile.seek#907

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Closed

wesm
wants to merge
2
commits into

from

 Closed


ARROW-1287: [Python] Implement whence argument for pyarrow.NativeFile.seek
#907
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


2 commits


Select commit
Hold shift + click to select a range
423ca87

Implement whence argument for pyarrow.NativeFile.seek


wesm Jul 28, 2017
933f3f6

Add testing script for checking thirdparty library against pyarrow.Hd…


wesm Jul 29, 2017

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


58 changes: 56 additions & 2 deletions
python/pyarrow/io.pxi

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -106,13 +106,19 @@ cdef class NativeFile:
 raise IOError("file not open")

 def size(self):
 """
 Return file size
 """
 cdef int64_t size
 self._assert_readable()
 with nogil:
 check_status(self.rd_file.get().GetSize(&size))
 return size

 def tell(self):
 """
 Return current stream position
 """
 cdef int64_t position
 with nogil:
 if self.is_readable:
Expand All@@ -121,10 +127,46 @@ cdef class NativeFile:
 check_status(self.wr_file.get().Tell(&position))
 return position

 def seek(self, int64_t position):
 def seek(self, int64_t position, int whence=0):
 """
 Change current file stream position

 Parameters
 ----------
 position : int
 Byte offset, interpreted relative to value of whence argument
 whence : int, default 0
 Point of reference for seek offset

 Notes
 -----
 Values of whence:
 * 0 -- start of stream (the default); offset should be zero or positive
 * 1 -- current stream position; offset may be negative
 * 2 -- end of stream; offset is usually negative

 Returns
 -------
 new_position : the new absolute stream position
 """
 cdef int64_t offset
 self._assert_readable()
 with nogil:
 check_status(self.rd_file.get().Seek(position))
 if whence == 0:
 offset = position
 elif whence == 1:
 check_status(self.rd_file.get().Tell(&offset))
 offset = offset + position
 elif whence == 2:
 check_status(self.rd_file.get().GetSize(&offset))
 offset = offset + position
 else:
 with gil:
 raise ValueError("Invalid value of whence: {0}"
 .format(whence))
 check_status(self.rd_file.get().Seek(offset))

 return self.tell()

 def write(self, data):
 """
Expand All@@ -144,6 +186,18 @@ cdef class NativeFile:
 check_status(self.wr_file.get().Write(buf, bufsize))

 def read(self, nbytes=None):
 """
 Read indicated number of bytes from file, or read all remaining bytes
 if no argument passed

 Parameters
 ----------
 nbytes : int, default None

 Returns
 -------
 data : bytes
 """
 cdef:
 int64_t c_nbytes
 int64_t bytes_read = 0
Expand Down

4 changes: 3 additions & 1 deletion
python/pyarrow/tests/conftest.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -33,12 +33,14 @@
except ImportError:
 pass


try:
 import pyarrow.plasma as plasma
 import pyarrow.plasma as plasma # noqa
 defaults['plasma'] = True
except ImportError:
 pass


def pytest_configure(config):
 pass

Expand Down

9 changes: 9 additions & 0 deletions
python/pyarrow/tests/test_io.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -323,6 +323,15 @@ def _check_native_file_reader(FACTORY, sample_data):
 assert f.tell() == len(data) + 1
 assert f.read(5) == b''

 # Test whence argument of seek, ARROW-1287
 assert f.seek(3) == 3
 assert f.seek(3, os.SEEK_CUR) == 6
 assert f.tell() == 6

 ex_length = len(data) - 2
 assert f.seek(-2, os.SEEK_END) == ex_length
 assert f.tell() == ex_length


def test_memory_map_reader(sample_disk_data):
 _check_native_file_reader(pa.memory_map, sample_disk_data)
Expand Down

15 changes: 6 additions & 9 deletions
python/pyarrow/tests/test_plasma.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -19,22 +19,20 @@
from __future__ import division
from __future__ import print_function

import glob
import numpy as np
import os
import pytest
import random
import signal
import subprocess
import sys
import time
import unittest

import pyarrow as pa
import pandas as pd

DEFAULT_PLASMA_STORE_MEMORY = 10 ** 9


def random_name():
 return str(random.randint(0, 99999999))

Expand DownExpand Up@@ -160,7 +158,7 @@ def setup_method(self, test_method):

 def teardown_method(self, test_method):
 # Check that the Plasma store is still alive.
 assert self.p.poll() == None
 assert self.p.poll() is None
 # Kill the plasma store process.
 if os.getenv("PLASMA_VALGRIND") == "1":
 self.p.send_signal(signal.SIGTERM)
Expand DownExpand Up@@ -227,7 +225,7 @@ def test_create_existing(self):
 self.plasma_client.create(object_id, length,
 generate_metadata(length))
 # TODO(pcm): Introduce a more specific error type here.
 except pa.lib.ArrowException as e:
 except pa.lib.ArrowException:
 pass
 else:
 assert False
Expand DownExpand Up@@ -270,7 +268,6 @@ def test_get(self):
 assert results[i] is None

 def test_store_arrow_objects(self):
 import pyarrow.plasma as plasma
 data = np.random.randn(10, 4)
 # Write an arrow object.
 object_id = random_object_id()
Expand DownExpand Up@@ -334,7 +331,7 @@ def assert_create_raises_plasma_full(unit_test, size):
 partial_size,
 size - partial_size)
 # TODO(pcm): More specific error here.
 except pa.lib.ArrowException as e:
 except pa.lib.ArrowException:
 pass
 else:
 # For some reason the above didn't throw an exception, so fail.
Expand DownExpand Up@@ -368,7 +365,7 @@ def test_contains(self):
 fake_object_ids = [random_object_id() for _ in range(100)]
 real_object_ids = [random_object_id() for _ in range(100)]
 for object_id in real_object_ids:
 assert self.plasma_client.contains(object_id) == False
 assert self.plasma_client.contains(object_id) is False
 self.plasma_client.create(object_id, 100)
 self.plasma_client.seal(object_id)
 assert self.plasma_client.contains(object_id)
Expand All@@ -383,7 +380,7 @@ def test_hash(self):
 try:
 self.plasma_client.hash(object_id1)
 # TODO(pcm): Introduce a more specific error type here
 except pa.lib.ArrowException as e:
 except pa.lib.ArrowException:
 pass
 else:
 assert False
Expand Down

53 changes: 53 additions & 0 deletions
python/testing/parquet_interop.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,53 @@
# 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.

import os
import pytest

import fastparquet
import pandas as pd
import pyarrow as pa
import pyarrow.parquet as pq
import pandas.util.testing as tm


def hdfs_test_client(driver='libhdfs'):
 host = os.environ.get('ARROW_HDFS_TEST_HOST', 'localhost')
 user = os.environ['ARROW_HDFS_TEST_USER']
 try:
 port = int(os.environ.get('ARROW_HDFS_TEST_PORT', 20500))
 except ValueError:
 raise ValueError('Env variable ARROW_HDFS_TEST_PORT was not '
 'an integer')

 return pa.HdfsClient(host, port, user, driver=driver)


def test_fastparquet_read_with_hdfs():
 fs = hdfs_test_client()

 df = tm.makeDataFrame()
 table = pa.Table.from_pandas(df)

 path = '/tmp/testing.parquet'
 with fs.open(path, 'wb') as f:
 pq.write_table(table, f)

 parquet_file = fastparquet.ParquetFile(path, open_with=fs.open)

 result = parquet_file.to_pandas()
 tm.assert_frame_equal(result, df)

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Auto-enable theater mode on YouTube\n(function() {\n function tryTheater() {\n var btn = document.querySelector('button[aria-label=\"Theater mode\"], ytd-player #player button[title=\"Theater mode\"]');\n if (btn && !btn.classList.contains('activated')) {\n btn.click();\n }\n }\n \n // Try immediately\n tryTheater();\n \n // Try after navigation (SPA)\n var lastUrl = location.href;\n setInterval(function() {\n if (location.href !== lastUrl) {\n lastUrl = location.href;\n setTimeout(tryTheater, 500);\n }\n }, 1000);\n \n // Also try on player load\n var observer = new MutationObserver(tryTheater);\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "YouTube Theater Mode Default");
}
} catch(__e) { console.warn('[Userscript:YouTube Theater Mode Default]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
ARROW-1287: [Python] Implement whence argument for pyarrow.NativeFile.seek#907

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Closed

wesm
wants to merge
2
commits into

from

 Closed


ARROW-1287: [Python] Implement whence argument for pyarrow.NativeFile.seek
#907
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


2 commits


Select commit
Hold shift + click to select a range
423ca87

Implement whence argument for pyarrow.NativeFile.seek


wesm Jul 28, 2017
933f3f6

Add testing script for checking thirdparty library against pyarrow.Hd…


wesm Jul 29, 2017

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


58 changes: 56 additions & 2 deletions
python/pyarrow/io.pxi

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -106,13 +106,19 @@ cdef class NativeFile:
 raise IOError("file not open")

 def size(self):
 """
 Return file size
 """
 cdef int64_t size
 self._assert_readable()
 with nogil:
 check_status(self.rd_file.get().GetSize(&size))
 return size

 def tell(self):
 """
 Return current stream position
 """
 cdef int64_t position
 with nogil:
 if self.is_readable:
Expand All@@ -121,10 +127,46 @@ cdef class NativeFile:
 check_status(self.wr_file.get().Tell(&position))
 return position

 def seek(self, int64_t position):
 def seek(self, int64_t position, int whence=0):
 """
 Change current file stream position

 Parameters
 ----------
 position : int
 Byte offset, interpreted relative to value of whence argument
 whence : int, default 0
 Point of reference for seek offset

 Notes
 -----
 Values of whence:
 * 0 -- start of stream (the default); offset should be zero or positive
 * 1 -- current stream position; offset may be negative
 * 2 -- end of stream; offset is usually negative

 Returns
 -------
 new_position : the new absolute stream position
 """
 cdef int64_t offset
 self._assert_readable()
 with nogil:
 check_status(self.rd_file.get().Seek(position))
 if whence == 0:
 offset = position
 elif whence == 1:
 check_status(self.rd_file.get().Tell(&offset))
 offset = offset + position
 elif whence == 2:
 check_status(self.rd_file.get().GetSize(&offset))
 offset = offset + position
 else:
 with gil:
 raise ValueError("Invalid value of whence: {0}"
 .format(whence))
 check_status(self.rd_file.get().Seek(offset))

 return self.tell()

 def write(self, data):
 """
Expand All@@ -144,6 +186,18 @@ cdef class NativeFile:
 check_status(self.wr_file.get().Write(buf, bufsize))

 def read(self, nbytes=None):
 """
 Read indicated number of bytes from file, or read all remaining bytes
 if no argument passed

 Parameters
 ----------
 nbytes : int, default None

 Returns
 -------
 data : bytes
 """
 cdef:
 int64_t c_nbytes
 int64_t bytes_read = 0
Expand Down

4 changes: 3 additions & 1 deletion
python/pyarrow/tests/conftest.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -33,12 +33,14 @@
except ImportError:
 pass


try:
 import pyarrow.plasma as plasma
 import pyarrow.plasma as plasma # noqa
 defaults['plasma'] = True
except ImportError:
 pass


def pytest_configure(config):
 pass

Expand Down

9 changes: 9 additions & 0 deletions
python/pyarrow/tests/test_io.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -323,6 +323,15 @@ def _check_native_file_reader(FACTORY, sample_data):
 assert f.tell() == len(data) + 1
 assert f.read(5) == b''

 # Test whence argument of seek, ARROW-1287
 assert f.seek(3) == 3
 assert f.seek(3, os.SEEK_CUR) == 6
 assert f.tell() == 6

 ex_length = len(data) - 2
 assert f.seek(-2, os.SEEK_END) == ex_length
 assert f.tell() == ex_length


def test_memory_map_reader(sample_disk_data):
 _check_native_file_reader(pa.memory_map, sample_disk_data)
Expand Down

15 changes: 6 additions & 9 deletions
python/pyarrow/tests/test_plasma.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -19,22 +19,20 @@
from __future__ import division
from __future__ import print_function

import glob
import numpy as np
import os
import pytest
import random
import signal
import subprocess
import sys
import time
import unittest

import pyarrow as pa
import pandas as pd

DEFAULT_PLASMA_STORE_MEMORY = 10 ** 9


def random_name():
 return str(random.randint(0, 99999999))

Expand DownExpand Up@@ -160,7 +158,7 @@ def setup_method(self, test_method):

 def teardown_method(self, test_method):
 # Check that the Plasma store is still alive.
 assert self.p.poll() == None
 assert self.p.poll() is None
 # Kill the plasma store process.
 if os.getenv("PLASMA_VALGRIND") == "1":
 self.p.send_signal(signal.SIGTERM)
Expand DownExpand Up@@ -227,7 +225,7 @@ def test_create_existing(self):
 self.plasma_client.create(object_id, length,
 generate_metadata(length))
 # TODO(pcm): Introduce a more specific error type here.
 except pa.lib.ArrowException as e:
 except pa.lib.ArrowException:
 pass
 else:
 assert False
Expand DownExpand Up@@ -270,7 +268,6 @@ def test_get(self):
 assert results[i] is None

 def test_store_arrow_objects(self):
 import pyarrow.plasma as plasma
 data = np.random.randn(10, 4)
 # Write an arrow object.
 object_id = random_object_id()
Expand DownExpand Up@@ -334,7 +331,7 @@ def assert_create_raises_plasma_full(unit_test, size):
 partial_size,
 size - partial_size)
 # TODO(pcm): More specific error here.
 except pa.lib.ArrowException as e:
 except pa.lib.ArrowException:
 pass
 else:
 # For some reason the above didn't throw an exception, so fail.
Expand DownExpand Up@@ -368,7 +365,7 @@ def test_contains(self):
 fake_object_ids = [random_object_id() for _ in range(100)]
 real_object_ids = [random_object_id() for _ in range(100)]
 for object_id in real_object_ids:
 assert self.plasma_client.contains(object_id) == False
 assert self.plasma_client.contains(object_id) is False
 self.plasma_client.create(object_id, 100)
 self.plasma_client.seal(object_id)
 assert self.plasma_client.contains(object_id)
Expand All@@ -383,7 +380,7 @@ def test_hash(self):
 try:
 self.plasma_client.hash(object_id1)
 # TODO(pcm): Introduce a more specific error type here
 except pa.lib.ArrowException as e:
 except pa.lib.ArrowException:
 pass
 else:
 assert False
Expand Down

53 changes: 53 additions & 0 deletions
python/testing/parquet_interop.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,53 @@
# 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.

import os
import pytest

import fastparquet
import pandas as pd
import pyarrow as pa
import pyarrow.parquet as pq
import pandas.util.testing as tm


def hdfs_test_client(driver='libhdfs'):
 host = os.environ.get('ARROW_HDFS_TEST_HOST', 'localhost')
 user = os.environ['ARROW_HDFS_TEST_USER']
 try:
 port = int(os.environ.get('ARROW_HDFS_TEST_PORT', 20500))
 except ValueError:
 raise ValueError('Env variable ARROW_HDFS_TEST_PORT was not '
 'an integer')

 return pa.HdfsClient(host, port, user, driver=driver)


def test_fastparquet_read_with_hdfs():
 fs = hdfs_test_client()

 df = tm.makeDataFrame()
 table = pa.Table.from_pandas(df)

 path = '/tmp/testing.parquet'
 with fs.open(path, 'wb') as f:
 pq.write_table(table, f)

 parquet_file = fastparquet.ParquetFile(path, open_with=fs.open)

 result = parquet_file.to_pandas()
 tm.assert_frame_equal(result, df)

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Remove or un-stick sticky/fixed headers that block content\n(function() {\n function unstick() {\n document.querySelectorAll('header, nav, [role=\"banner\"], .header, .navbar, .sticky, .fixed-top, [style*=\"position: fixed\"], [style*=\"position:sticky\"]').forEach(function(el) {\n if (el.style.position === 'fixed' || el.style.position === 'sticky' || \n getComputedStyle(el).position === 'fixed' || getComputedStyle(el).position === 'sticky') {\n el.style.position = 'static';\n el.style.top = 'auto';\n el.style.zIndex = 'auto';\n }\n });\n }\n \n unstick();\n \n var observer = new MutationObserver(unstick);\n observer.observe(document.body, { childList: true, subtree: true, attributes: true, attributeFilter: ['style', 'class'] });\n})();", "Kill Sticky Headers");
}
} catch(__e) { console.warn('[Userscript:Kill Sticky Headers]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
ARROW-1287: [Python] Implement whence argument for pyarrow.NativeFile.seek#907

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Closed

wesm
wants to merge
2
commits into

from

 Closed


ARROW-1287: [Python] Implement whence argument for pyarrow.NativeFile.seek
#907
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


2 commits


Select commit
Hold shift + click to select a range
423ca87

Implement whence argument for pyarrow.NativeFile.seek


wesm Jul 28, 2017
933f3f6

Add testing script for checking thirdparty library against pyarrow.Hd…


wesm Jul 29, 2017

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


58 changes: 56 additions & 2 deletions
python/pyarrow/io.pxi

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -106,13 +106,19 @@ cdef class NativeFile:
 raise IOError("file not open")

 def size(self):
 """
 Return file size
 """
 cdef int64_t size
 self._assert_readable()
 with nogil:
 check_status(self.rd_file.get().GetSize(&size))
 return size

 def tell(self):
 """
 Return current stream position
 """
 cdef int64_t position
 with nogil:
 if self.is_readable:
Expand All@@ -121,10 +127,46 @@ cdef class NativeFile:
 check_status(self.wr_file.get().Tell(&position))
 return position

 def seek(self, int64_t position):
 def seek(self, int64_t position, int whence=0):
 """
 Change current file stream position

 Parameters
 ----------
 position : int
 Byte offset, interpreted relative to value of whence argument
 whence : int, default 0
 Point of reference for seek offset

 Notes
 -----
 Values of whence:
 * 0 -- start of stream (the default); offset should be zero or positive
 * 1 -- current stream position; offset may be negative
 * 2 -- end of stream; offset is usually negative

 Returns
 -------
 new_position : the new absolute stream position
 """
 cdef int64_t offset
 self._assert_readable()
 with nogil:
 check_status(self.rd_file.get().Seek(position))
 if whence == 0:
 offset = position
 elif whence == 1:
 check_status(self.rd_file.get().Tell(&offset))
 offset = offset + position
 elif whence == 2:
 check_status(self.rd_file.get().GetSize(&offset))
 offset = offset + position
 else:
 with gil:
 raise ValueError("Invalid value of whence: {0}"
 .format(whence))
 check_status(self.rd_file.get().Seek(offset))

 return self.tell()

 def write(self, data):
 """
Expand All@@ -144,6 +186,18 @@ cdef class NativeFile:
 check_status(self.wr_file.get().Write(buf, bufsize))

 def read(self, nbytes=None):
 """
 Read indicated number of bytes from file, or read all remaining bytes
 if no argument passed

 Parameters
 ----------
 nbytes : int, default None

 Returns
 -------
 data : bytes
 """
 cdef:
 int64_t c_nbytes
 int64_t bytes_read = 0
Expand Down

4 changes: 3 additions & 1 deletion
python/pyarrow/tests/conftest.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -33,12 +33,14 @@
except ImportError:
 pass


try:
 import pyarrow.plasma as plasma
 import pyarrow.plasma as plasma # noqa
 defaults['plasma'] = True
except ImportError:
 pass


def pytest_configure(config):
 pass

Expand Down

9 changes: 9 additions & 0 deletions
python/pyarrow/tests/test_io.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -323,6 +323,15 @@ def _check_native_file_reader(FACTORY, sample_data):
 assert f.tell() == len(data) + 1
 assert f.read(5) == b''

 # Test whence argument of seek, ARROW-1287
 assert f.seek(3) == 3
 assert f.seek(3, os.SEEK_CUR) == 6
 assert f.tell() == 6

 ex_length = len(data) - 2
 assert f.seek(-2, os.SEEK_END) == ex_length
 assert f.tell() == ex_length


def test_memory_map_reader(sample_disk_data):
 _check_native_file_reader(pa.memory_map, sample_disk_data)
Expand Down

15 changes: 6 additions & 9 deletions
python/pyarrow/tests/test_plasma.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -19,22 +19,20 @@
from __future__ import division
from __future__ import print_function

import glob
import numpy as np
import os
import pytest
import random
import signal
import subprocess
import sys
import time
import unittest

import pyarrow as pa
import pandas as pd

DEFAULT_PLASMA_STORE_MEMORY = 10 ** 9


def random_name():
 return str(random.randint(0, 99999999))

Expand DownExpand Up@@ -160,7 +158,7 @@ def setup_method(self, test_method):

 def teardown_method(self, test_method):
 # Check that the Plasma store is still alive.
 assert self.p.poll() == None
 assert self.p.poll() is None
 # Kill the plasma store process.
 if os.getenv("PLASMA_VALGRIND") == "1":
 self.p.send_signal(signal.SIGTERM)
Expand DownExpand Up@@ -227,7 +225,7 @@ def test_create_existing(self):
 self.plasma_client.create(object_id, length,
 generate_metadata(length))
 # TODO(pcm): Introduce a more specific error type here.
 except pa.lib.ArrowException as e:
 except pa.lib.ArrowException:
 pass
 else:
 assert False
Expand DownExpand Up@@ -270,7 +268,6 @@ def test_get(self):
 assert results[i] is None

 def test_store_arrow_objects(self):
 import pyarrow.plasma as plasma
 data = np.random.randn(10, 4)
 # Write an arrow object.
 object_id = random_object_id()
Expand DownExpand Up@@ -334,7 +331,7 @@ def assert_create_raises_plasma_full(unit_test, size):
 partial_size,
 size - partial_size)
 # TODO(pcm): More specific error here.
 except pa.lib.ArrowException as e:
 except pa.lib.ArrowException:
 pass
 else:
 # For some reason the above didn't throw an exception, so fail.
Expand DownExpand Up@@ -368,7 +365,7 @@ def test_contains(self):
 fake_object_ids = [random_object_id() for _ in range(100)]
 real_object_ids = [random_object_id() for _ in range(100)]
 for object_id in real_object_ids:
 assert self.plasma_client.contains(object_id) == False
 assert self.plasma_client.contains(object_id) is False
 self.plasma_client.create(object_id, 100)
 self.plasma_client.seal(object_id)
 assert self.plasma_client.contains(object_id)
Expand All@@ -383,7 +380,7 @@ def test_hash(self):
 try:
 self.plasma_client.hash(object_id1)
 # TODO(pcm): Introduce a more specific error type here
 except pa.lib.ArrowException as e:
 except pa.lib.ArrowException:
 pass
 else:
 assert False
Expand Down

53 changes: 53 additions & 0 deletions
python/testing/parquet_interop.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,53 @@
# 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.

import os
import pytest

import fastparquet
import pandas as pd
import pyarrow as pa
import pyarrow.parquet as pq
import pandas.util.testing as tm


def hdfs_test_client(driver='libhdfs'):
 host = os.environ.get('ARROW_HDFS_TEST_HOST', 'localhost')
 user = os.environ['ARROW_HDFS_TEST_USER']
 try:
 port = int(os.environ.get('ARROW_HDFS_TEST_PORT', 20500))
 except ValueError:
 raise ValueError('Env variable ARROW_HDFS_TEST_PORT was not '
 'an integer')

 return pa.HdfsClient(host, port, user, driver=driver)


def test_fastparquet_read_with_hdfs():
 fs = hdfs_test_client()

 df = tm.makeDataFrame()
 table = pa.Table.from_pandas(df)

 path = '/tmp/testing.parquet'
 with fs.open(path, 'wb') as f:
 pq.write_table(table, f)

 parquet_file = fastparquet.ParquetFile(path, open_with=fs.open)

 result = parquet_file.to_pandas()
 tm.assert_frame_equal(result, df)

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Universal Dark Mode - works on any site\n(function() {\n var enabled = true;\n \n function applyDarkMode() {\n if (!enabled) return;\n \n // Create style element if it doesn't exist\n var style = document.getElementById('universal-dark-mode-style');\n if (!style) {\n style = document.createElement('style');\n style.id = 'universal-dark-mode-style';\n document.head.appendChild(style);\n }\n \n // Dark mode CSS - inverts colors but preserves images/video\n style.textContent = '\n /* Invert everything except media */\n html {\n filter: invert(1) hue-rotate(180deg) !important;\n background: #1a1a2e !important;\n }\n \n /* Restore images, videos, iframes, canvas */\n img, video, iframe, canvas, svg, picture, [style*=\"background-image\"] {\n filter: invert(1) hue-rotate(180deg) !important;\n }\n \n /* Preserve specific elements that should not be inverted */\n .no-dark-mode, .no-dark-mode *,\n [data-theme=\"light\"], [data-theme=\"light\"],\n .ace_editor, .ace_editor *,\n .CodeMirror, .CodeMirror *,\n .monaco-editor, .monaco-editor *,\n .markdown-body pre, .markdown-body pre *,\n .highlight, .highlight *,\n pre code, pre code * {\n filter: none !important;\n }\n \n /* Fix common UI elements */\n .modal, .popup, .dropdown-menu, .tooltip, .popover {\n filter: invert(1) hue-rotate(180deg) !important;\n background: #2d2d44 !important;\n border-color: #444 !important;\n }\n \n /* Scrollbars */\n ::-webkit-scrollbar { background: #1a1a2e !important; }\n ::-webkit-scrollbar-thumb { background: #444 !important; }\n ::-webkit-scrollbar-thumb:hover { background: #555 !important; }\n \n /* Selection */\n ::selection { background: #4ecdc4 !important; color: #1a1a2e !important; }\n ::-moz-selection { background: #4ecdc4 !important; color: #1a1a2e !important; }\n ';\n }\n \n function removeDarkMode() {\n var style = document.getElementById('universal-dark-mode-style');\n if (style) style.remove();\n }\n \n // Toggle with Alt+Shift+D\n document.addEventListener('keydown', function(e) {\n if (e.altKey && e.shiftKey && e.key === 'D') {\n e.preventDefault();\n enabled = !enabled;\n if (enabled) {\n applyDarkMode();\n console.log('[Universal Dark Mode] Enabled');\n } else {\n removeDarkMode();\n console.log('[Universal Dark Mode] Disabled');\n }\n }\n });\n \n // Apply on load\n applyDarkMode();\n \n // Re-apply on dynamic content\n var observer = new MutationObserver(function(mutations) {\n if (enabled && !document.getElementById('universal-dark-mode-style')) {\n applyDarkMode();\n }\n });\n observer.observe(document.head, { childList: true });\n \n console.log('[Universal Dark Mode] Loaded - Press Alt+Shift+D to toggle');\n})();", "Universal Dark Mode");
}
} catch(__e) { console.warn('[Userscript:Universal Dark Mode]', __e); }
})();
})();

Skip to content
ARROW-1287: [Python] Implement whence argument for pyarrow.NativeFile.seek#907

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Closed

wesm
wants to merge
2
commits into

from

 Closed


ARROW-1287: [Python] Implement whence argument for pyarrow.NativeFile.seek
#907
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


2 commits


Select commit
Hold shift + click to select a range
423ca87

Implement whence argument for pyarrow.NativeFile.seek


wesm Jul 28, 2017
933f3f6

Add testing script for checking thirdparty library against pyarrow.Hd…


wesm Jul 29, 2017

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


58 changes: 56 additions & 2 deletions
python/pyarrow/io.pxi

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -106,13 +106,19 @@ cdef class NativeFile:
 raise IOError("file not open")

 def size(self):
 """
 Return file size
 """
 cdef int64_t size
 self._assert_readable()
 with nogil:
 check_status(self.rd_file.get().GetSize(&size))
 return size

 def tell(self):
 """
 Return current stream position
 """
 cdef int64_t position
 with nogil:
 if self.is_readable:
Expand All@@ -121,10 +127,46 @@ cdef class NativeFile:
 check_status(self.wr_file.get().Tell(&position))
 return position

 def seek(self, int64_t position):
 def seek(self, int64_t position, int whence=0):
 """
 Change current file stream position

 Parameters
 ----------
 position : int
 Byte offset, interpreted relative to value of whence argument
 whence : int, default 0
 Point of reference for seek offset

 Notes
 -----
 Values of whence:
 * 0 -- start of stream (the default); offset should be zero or positive
 * 1 -- current stream position; offset may be negative
 * 2 -- end of stream; offset is usually negative

 Returns
 -------
 new_position : the new absolute stream position
 """
 cdef int64_t offset
 self._assert_readable()
 with nogil:
 check_status(self.rd_file.get().Seek(position))
 if whence == 0:
 offset = position
 elif whence == 1:
 check_status(self.rd_file.get().Tell(&offset))
 offset = offset + position
 elif whence == 2:
 check_status(self.rd_file.get().GetSize(&offset))
 offset = offset + position
 else:
 with gil:
 raise ValueError("Invalid value of whence: {0}"
 .format(whence))
 check_status(self.rd_file.get().Seek(offset))

 return self.tell()

 def write(self, data):
 """
Expand All@@ -144,6 +186,18 @@ cdef class NativeFile:
 check_status(self.wr_file.get().Write(buf, bufsize))

 def read(self, nbytes=None):
 """
 Read indicated number of bytes from file, or read all remaining bytes
 if no argument passed

 Parameters
 ----------
 nbytes : int, default None

 Returns
 -------
 data : bytes
 """
 cdef:
 int64_t c_nbytes
 int64_t bytes_read = 0
Expand Down

4 changes: 3 additions & 1 deletion
python/pyarrow/tests/conftest.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -33,12 +33,14 @@
except ImportError:
 pass


try:
 import pyarrow.plasma as plasma
 import pyarrow.plasma as plasma # noqa
 defaults['plasma'] = True
except ImportError:
 pass


def pytest_configure(config):
 pass

Expand Down

9 changes: 9 additions & 0 deletions
python/pyarrow/tests/test_io.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -323,6 +323,15 @@ def _check_native_file_reader(FACTORY, sample_data):
 assert f.tell() == len(data) + 1
 assert f.read(5) == b''

 # Test whence argument of seek, ARROW-1287
 assert f.seek(3) == 3
 assert f.seek(3, os.SEEK_CUR) == 6
 assert f.tell() == 6

 ex_length = len(data) - 2
 assert f.seek(-2, os.SEEK_END) == ex_length
 assert f.tell() == ex_length


def test_memory_map_reader(sample_disk_data):
 _check_native_file_reader(pa.memory_map, sample_disk_data)
Expand Down

15 changes: 6 additions & 9 deletions
python/pyarrow/tests/test_plasma.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -19,22 +19,20 @@
from __future__ import division
from __future__ import print_function

import glob
import numpy as np
import os
import pytest
import random
import signal
import subprocess
import sys
import time
import unittest

import pyarrow as pa
import pandas as pd

DEFAULT_PLASMA_STORE_MEMORY = 10 ** 9


def random_name():
 return str(random.randint(0, 99999999))

Expand DownExpand Up@@ -160,7 +158,7 @@ def setup_method(self, test_method):

 def teardown_method(self, test_method):
 # Check that the Plasma store is still alive.
 assert self.p.poll() == None
 assert self.p.poll() is None
 # Kill the plasma store process.
 if os.getenv("PLASMA_VALGRIND") == "1":
 self.p.send_signal(signal.SIGTERM)
Expand DownExpand Up@@ -227,7 +225,7 @@ def test_create_existing(self):
 self.plasma_client.create(object_id, length,
 generate_metadata(length))
 # TODO(pcm): Introduce a more specific error type here.
 except pa.lib.ArrowException as e:
 except pa.lib.ArrowException:
 pass
 else:
 assert False
Expand DownExpand Up@@ -270,7 +268,6 @@ def test_get(self):
 assert results[i] is None

 def test_store_arrow_objects(self):
 import pyarrow.plasma as plasma
 data = np.random.randn(10, 4)
 # Write an arrow object.
 object_id = random_object_id()
Expand DownExpand Up@@ -334,7 +331,7 @@ def assert_create_raises_plasma_full(unit_test, size):
 partial_size,
 size - partial_size)
 # TODO(pcm): More specific error here.
 except pa.lib.ArrowException as e:
 except pa.lib.ArrowException:
 pass
 else:
 # For some reason the above didn't throw an exception, so fail.
Expand DownExpand Up@@ -368,7 +365,7 @@ def test_contains(self):
 fake_object_ids = [random_object_id() for _ in range(100)]
 real_object_ids = [random_object_id() for _ in range(100)]
 for object_id in real_object_ids:
 assert self.plasma_client.contains(object_id) == False
 assert self.plasma_client.contains(object_id) is False
 self.plasma_client.create(object_id, 100)
 self.plasma_client.seal(object_id)
 assert self.plasma_client.contains(object_id)
Expand All@@ -383,7 +380,7 @@ def test_hash(self):
 try:
 self.plasma_client.hash(object_id1)
 # TODO(pcm): Introduce a more specific error type here
 except pa.lib.ArrowException as e:
 except pa.lib.ArrowException:
 pass
 else:
 assert False
Expand Down

53 changes: 53 additions & 0 deletions
python/testing/parquet_interop.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,53 @@
# 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.

import os
import pytest

import fastparquet
import pandas as pd
import pyarrow as pa
import pyarrow.parquet as pq
import pandas.util.testing as tm


def hdfs_test_client(driver='libhdfs'):
 host = os.environ.get('ARROW_HDFS_TEST_HOST', 'localhost')
 user = os.environ['ARROW_HDFS_TEST_USER']
 try:
 port = int(os.environ.get('ARROW_HDFS_TEST_PORT', 20500))
 except ValueError:
 raise ValueError('Env variable ARROW_HDFS_TEST_PORT was not '
 'an integer')

 return pa.HdfsClient(host, port, user, driver=driver)


def test_fastparquet_read_with_hdfs():
 fs = hdfs_test_client()

 df = tm.makeDataFrame()
 table = pa.Table.from_pandas(df)

 path = '/tmp/testing.parquet'
 with fs.open(path, 'wb') as f:
 pq.write_table(table, f)

 parquet_file = fastparquet.ParquetFile(path, open_with=fs.open)

 result = parquet_file.to_pandas()
 tm.assert_frame_equal(result, df)