Google Cloud Storage support using gcsfs

bnaul · bnaul · commit c722d607bd39 · 2018-05-24T06:15:12.000+09:00
diff --git a/ci/appveyor-27.yaml b/ci/appveyor-27.yaml
@@ -6,6 +6,7 @@ dependencies:
   - beautifulsoup4
   - bottleneck
   - dateutil
+  - gcsfs
   - html5lib
   - jinja2=2.8
   - lxml
diff --git a/ci/check_imports.py b/ci/check_imports.py
@@ -5,6 +5,7 @@
 
 blacklist = {
     'bs4',
+    'gcsfs',
     'html5lib',
     'ipython',
     'jinja2'
diff --git a/ci/circle-36-locale.yaml b/ci/circle-36-locale.yaml
@@ -5,6 +5,7 @@ channels:
 dependencies:
   - beautifulsoup4
   - cython
+  - gcsfs
   - html5lib
   - ipython
   - jinja2
diff --git a/ci/circle-36-locale_slow.yaml b/ci/circle-36-locale_slow.yaml
@@ -5,6 +5,7 @@ channels:
 dependencies:
   - beautifulsoup4
   - cython
+  - gcsfs
   - html5lib
   - ipython
   - jinja2
diff --git a/ci/requirements-optional-conda.txt b/ci/requirements-optional-conda.txt
@@ -3,6 +3,7 @@ blosc
 bottleneck
 fastparquet
 feather-format
+gcsfs
 html5lib
 ipython>=5.6.0
 ipykernel
diff --git a/ci/requirements-optional-pip.txt b/ci/requirements-optional-pip.txt
@@ -26,4 +26,4 @@ sqlalchemy
 xarray
 xlrd
 xlsxwriter
-xlwt
+xlwt
diff --git a/ci/travis-27.yaml b/ci/travis-27.yaml
@@ -9,6 +9,7 @@ dependencies:
   - fastparquet
   - feather-format
   - flake8=3.4.1
+  - gcsfs
   - html5lib
   - ipython
   - jemalloc=4.5.0.post
diff --git a/ci/travis-36-slow.yaml b/ci/travis-36-slow.yaml
@@ -5,6 +5,7 @@ channels:
 dependencies:
   - beautifulsoup4
   - cython
+  - gcsfs
   - html5lib
   - lxml
   - matplotlib
diff --git a/ci/travis-36.yaml b/ci/travis-36.yaml
@@ -8,6 +8,7 @@ dependencies:
   - dask
   - fastparquet
   - feather-format
+  - gcsfs
   - geopandas
   - html5lib
   - ipython
diff --git a/doc/source/install.rst b/doc/source/install.rst
@@ -276,6 +276,7 @@ Optional Dependencies
 * `Jinja2 <http://jinja.pocoo.org/>`__: Template engine for conditional HTML formatting.
 * `s3fs <http://s3fs.readthedocs.io/>`__: necessary for Amazon S3 access (s3fs >= 0.0.7).
 * `blosc <https://pypi.org/project/blosc>`__: for msgpack compression using ``blosc``
+* `gcsfs <http://gcsfs.readthedocs.io/>`__: necessary for Google Cloud Storage access (gcsfs >= 0.1.0).
 * One of
   `qtpy  <https://github.com/spyder-ide/qtpy>`__ (requires PyQt or PySide),
   `PyQt5 <https://www.riverbankcomputing.com/software/pyqt/download5>`__,
diff --git a/pandas/io/common.py b/pandas/io/common.py
@@ -88,7 +88,7 @@ def _is_url(url):
     """
     try:
         return parse_url(url).scheme in _VALID_URLS
-    except:
+    except Exception:
         return False
 
 
@@ -165,7 +165,15 @@ def is_s3_url(url):
     """Check for an s3, s3n, or s3a url"""
     try:
         return parse_url(url).scheme in ['s3', 's3n', 's3a']
-    except:  # noqa
+    except Exception:
+        return False
+
+
+def is_gcs_url(url):
+    """Check for a gcs url"""
+    try:
+        return parse_url(url).scheme in ['gcs', 'gs']
+    except Exception:
         return False
 
 
@@ -208,6 +216,13 @@ def get_filepath_or_buffer(filepath_or_buffer, encoding=None,
                                          compression=compression,
                                          mode=mode)
 
+    if is_gcs_url(filepath_or_buffer):
+        from pandas.io import gcs
+        return gcs.get_filepath_or_buffer(filepath_or_buffer,
+                                          encoding=encoding,
+                                          compression=compression,
+                                          mode=mode)
+
     if isinstance(filepath_or_buffer, (compat.string_types,
                                        compat.binary_type,
                                        mmap.mmap)):
diff --git a/pandas/io/excel.py b/pandas/io/excel.py
@@ -46,7 +46,7 @@
 io : string, path object (pathlib.Path or py._path.local.LocalPath),
     file-like object, pandas ExcelFile, or xlrd workbook.
     The string could be a URL. Valid URL schemes include http, ftp, s3,
-    and file. For file URLs, a host is expected. For instance, a local
+    gcs, and file. For file URLs, a host is expected. For instance, a local
     file could be file://localhost/path/to/workbook.xlsx
 sheet_name : string, int, mixed list of strings/ints, or None, default 0
 
diff --git a/pandas/io/gcs.py b/pandas/io/gcs.py
@@ -0,0 +1,16 @@
+""" GCS support for remote file interactivity """
+try:
+    import gcsfs
+except ImportError:
+    raise ImportError("The gcsfs library is required to handle GCS files")
+
+
+def get_filepath_or_buffer(filepath_or_buffer, encoding=None,
+                           compression=None, mode=None):
+
+    if mode is None:
+        mode = 'rb'
+
+    fs = gcsfs.GCSFileSystem()
+    filepath_or_buffer = fs.open(filepath_or_buffer, mode)
+    return filepath_or_buffer, None, compression, True
diff --git a/pandas/io/json/json.py b/pandas/io/json/json.py
@@ -231,9 +231,9 @@ def read_json(path_or_buf=None, orient=None, typ='frame', dtype=True,
     Parameters
     ----------
     path_or_buf : a valid JSON string or file-like, default: None
-        The string could be a URL. Valid URL schemes include http, ftp, s3, and
-        file. For file URLs, a host is expected. For instance, a local file
-        could be ``file://localhost/path/to/table.json``
+        The string could be a URL. Valid URL schemes include http, ftp, s3,
+        gcs, and file. For file URLs, a host is expected. For instance, a local
+        file could be ``file://localhost/path/to/table.json``
 
     orient : string,
         Indication of expected JSON string format.
diff --git a/pandas/tests/io/test_gcs.py b/pandas/tests/io/test_gcs.py
@@ -0,0 +1,25 @@
+from pandas import DataFrame, read_csv
+from pandas.compat import BytesIO
+from pandas.io.common import is_gcs_url
+
+
+def test_is_gcs_url():
+    assert is_gcs_url("gcs://pandas/somethingelse.com")
+    assert is_gcs_url("gs://pandas/somethingelse.com")
+    assert not is_gcs_url("s3://pandas/somethingelse.com")
+
+
+def test_read_csv_gcs():
+    try:
+        from unittest.mock import patch
+    except ImportError:
+        from mock import patch
+
+    with patch('gcsfs.GCSFileSystem') as MockFileSystem:
+        instance = MockFileSystem.return_value
+        instance.open.return_value = BytesIO(b'a,b\n1,2\n3,4')
+        df = read_csv('gs://test/test.csv')
+
+    assert isinstance(df, DataFrame)
+    assert len(df == 2)
+    assert all(df.columns == ['a', 'b'])
diff --git a/pandas/util/_print_versions.py b/pandas/util/_print_versions.py
@@ -96,6 +96,7 @@ def show_versions(as_json=False):
         ("fastparquet", lambda mod: mod.__version__),
         ("pandas_gbq", lambda mod: mod.__version__),
         ("pandas_datareader", lambda mod: mod.__version__),
+        ("gcsfs", lambda mod: mod.__version__),
     ]
 
     deps_blob = list()

-Original file line number
+Diff line change
 xarray
 xlrd
 xlsxwriter
 -xlwt
 +xlwt