Hello community, here is the log from the commit of package python-fastparquet for openSUSE:Factory checked in at 2019-01-28 20:48:35 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ Comparing /work/SRC/openSUSE:Factory/python-fastparquet (Old) and /work/SRC/openSUSE:Factory/.python-fastparquet.new.28833 (New) ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Package is "python-fastparquet" Mon Jan 28 20:48:35 2019 rev:5 rq:668842 version:0.2.1 Changes: -------- --- /work/SRC/openSUSE:Factory/python-fastparquet/python-fastparquet.changes 2018-11-26 10:29:43.165069276 +0100 +++ /work/SRC/openSUSE:Factory/.python-fastparquet.new.28833/python-fastparquet.changes 2019-01-28 20:49:39.917827950 +0100 @@ -1,0 +2,13 @@ +Sat Jan 26 17:05:09 UTC 2019 - Arun Persaud <[email protected]> + +- specfile: + * update copyright year + +- update to version 0.2.1: + * Compat for pandas 0.24.0 refactor (#390) + * Change OverflowError message when failing on large pages (#387) + * Allow for changes in dictionary while reading a row-group column + (#367) + * Correct pypi project names for compression libraries (#385) + +------------------------------------------------------------------- Old: ---- fastparquet-0.2.0.tar.gz New: ---- fastparquet-0.2.1.tar.gz ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ Other differences: ------------------ ++++++ python-fastparquet.spec ++++++ --- /var/tmp/diff_new_pack.ZH9Ks1/_old 2019-01-28 20:49:40.301827545 +0100 +++ /var/tmp/diff_new_pack.ZH9Ks1/_new 2019-01-28 20:49:40.301827545 +0100 @@ -1,7 +1,7 @@ # # spec file for package python-fastparquet # -# Copyright (c) 2018 SUSE LINUX GmbH, Nuernberg, Germany. +# Copyright (c) 2019 SUSE LINUX GmbH, Nuernberg, Germany. # # All modifications and additions to the file contributed by third parties # remain the property of their copyright owners, unless otherwise agreed @@ -20,7 +20,7 @@ # Test files not included %bcond_with test Name: python-fastparquet -Version: 0.2.0 +Version: 0.2.1 Release: 0 Summary: Python support for Parquet file format License: Apache-2.0 ++++++ fastparquet-0.2.0.tar.gz -> fastparquet-0.2.1.tar.gz ++++++ diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/fastparquet-0.2.0/PKG-INFO new/fastparquet-0.2.1/PKG-INFO --- old/fastparquet-0.2.0/PKG-INFO 2018-11-22 17:33:29.000000000 +0100 +++ new/fastparquet-0.2.1/PKG-INFO 2018-12-18 22:36:43.000000000 +0100 @@ -1,6 +1,6 @@ Metadata-Version: 2.1 Name: fastparquet -Version: 0.2.0 +Version: 0.2.1 Summary: Python support for Parquet file format Home-page: https://github.com/dask/fastparquet/ Author: Martin Durant @@ -133,8 +133,8 @@ Classifier: Programming Language :: Python :: 3.7 Classifier: Programming Language :: Python :: Implementation :: CPython Requires-Python: >=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*, -Provides-Extra: lz4 -Provides-Extra: zstandard -Provides-Extra: lzo Provides-Extra: snappy +Provides-Extra: zstandard Provides-Extra: brotli +Provides-Extra: lzo +Provides-Extra: lz4 diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/fastparquet-0.2.0/docs/source/install.rst new/fastparquet-0.2.1/docs/source/install.rst --- old/fastparquet-0.2.0/docs/source/install.rst 2018-06-05 18:15:59.000000000 +0200 +++ new/fastparquet-0.2.1/docs/source/install.rst 2018-12-13 18:40:39.000000000 +0100 @@ -14,8 +14,8 @@ Optional (compression algorithms; gzip is always available): -- snappy -- lzo +- python-snappy +- python-lzo - brotli Installation diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/fastparquet-0.2.0/fastparquet/__init__.py new/fastparquet-0.2.1/fastparquet/__init__.py --- old/fastparquet-0.2.0/fastparquet/__init__.py 2018-11-22 17:31:49.000000000 +0100 +++ new/fastparquet-0.2.1/fastparquet/__init__.py 2018-12-18 22:32:07.000000000 +0100 @@ -11,4 +11,4 @@ from .api import ParquetFile from .util import ParquetException -__version__ = "0.2.0" +__version__ = "0.2.1" diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/fastparquet-0.2.0/fastparquet/core.py new/fastparquet-0.2.1/fastparquet/core.py --- old/fastparquet-0.2.0/fastparquet/core.py 2018-09-04 16:06:56.000000000 +0200 +++ new/fastparquet-0.2.1/fastparquet/core.py 2018-12-13 18:40:39.000000000 +0100 @@ -227,6 +227,15 @@ num = 0 row_idx = 0 while True: + if ph.type == parquet_thrift.PageType.DICTIONARY_PAGE: + dic2 = np.array(read_dictionary_page(infile, schema_helper, ph, cmd)) + dic2 = convert(dic2, se) + if use_cat and (dic2 != dic).any(): + raise RuntimeError("Attempt to read as categorical a column" + "with multiple dictionary pages.") + dic = dic2 + ph = read_thrift(infile, parquet_thrift.PageHeader) + continue if (selfmade and hasattr(cmd, 'statistics') and getattr(cmd.statistics, 'null_count', 1) == 0): skip_nulls = True diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/fastparquet-0.2.0/fastparquet/dataframe.py new/fastparquet-0.2.1/fastparquet/dataframe.py --- old/fastparquet-0.2.0/fastparquet/dataframe.py 2018-08-15 16:44:31.000000000 +0200 +++ new/fastparquet-0.2.1/fastparquet/dataframe.py 2018-12-18 22:30:48.000000000 +0100 @@ -149,7 +149,7 @@ new_block = block.make_block_same_class(values=values) elif getattr(block.dtype, 'tz', None): new_shape = (size, ) - values = np.empty(shape=new_shape, dtype=block.values.values.dtype) + values = np.empty(shape=new_shape, dtype="M8[ns]") new_block = block.make_block_same_class( values=values, dtype=block.values.dtype) else: @@ -174,7 +174,7 @@ views[col] = block.values._codes views[col+'-catdef'] = block.values elif getattr(block.dtype, 'tz', None): - views[col] = block.values.values + views[col] = np.asarray(block.values, dtype='M8[ns]') else: views[col] = block.values[i] diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/fastparquet-0.2.0/fastparquet/thrift_structures.py new/fastparquet-0.2.1/fastparquet/thrift_structures.py --- old/fastparquet-0.2.0/fastparquet/thrift_structures.py 2018-06-05 18:15:59.000000000 +0200 +++ new/fastparquet-0.2.1/fastparquet/thrift_structures.py 2018-12-13 18:40:39.000000000 +0100 @@ -5,6 +5,7 @@ from thrift.protocol.TProtocol import TProtocolException from .parquet_thrift.parquet import ttypes as parquet_thrift +from .util import ParquetException def read_thrift(file_obj, ttype): diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/fastparquet-0.2.0/fastparquet/writer.py new/fastparquet-0.2.1/fastparquet/writer.py --- old/fastparquet-0.2.0/fastparquet/writer.py 2018-09-30 17:02:24.000000000 +0200 +++ new/fastparquet-0.2.1/fastparquet/writer.py 2018-12-13 18:40:39.000000000 +0100 @@ -543,8 +543,13 @@ uncompressed_page_size=l0, compressed_page_size=l1, data_page_header=dph, crc=None) + try: + write_thrift(f, ph) + except OverflowError as err: + raise IOError('Overflow error while writing page; try using a smaller ' + 'value for `row_group_offsets`. Original message: ' + + str(err)) - write_thrift(f, ph) f.write(bdata) compressed_size = f.tell() - start diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/fastparquet-0.2.0/fastparquet.egg-info/PKG-INFO new/fastparquet-0.2.1/fastparquet.egg-info/PKG-INFO --- old/fastparquet-0.2.0/fastparquet.egg-info/PKG-INFO 2018-11-22 17:33:29.000000000 +0100 +++ new/fastparquet-0.2.1/fastparquet.egg-info/PKG-INFO 2018-12-18 22:36:43.000000000 +0100 @@ -1,6 +1,6 @@ Metadata-Version: 2.1 Name: fastparquet -Version: 0.2.0 +Version: 0.2.1 Summary: Python support for Parquet file format Home-page: https://github.com/dask/fastparquet/ Author: Martin Durant @@ -133,8 +133,8 @@ Classifier: Programming Language :: Python :: 3.7 Classifier: Programming Language :: Python :: Implementation :: CPython Requires-Python: >=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*, -Provides-Extra: lz4 -Provides-Extra: zstandard -Provides-Extra: lzo Provides-Extra: snappy +Provides-Extra: zstandard Provides-Extra: brotli +Provides-Extra: lzo +Provides-Extra: lz4 diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/fastparquet-0.2.0/fastparquet.egg-info/SOURCES.txt new/fastparquet-0.2.1/fastparquet.egg-info/SOURCES.txt --- old/fastparquet-0.2.0/fastparquet.egg-info/SOURCES.txt 2018-11-22 17:33:29.000000000 +0100 +++ new/fastparquet-0.2.1/fastparquet.egg-info/SOURCES.txt 2018-12-18 22:36:43.000000000 +0100 @@ -28,7 +28,6 @@ fastparquet.egg-info/PKG-INFO fastparquet.egg-info/SOURCES.txt fastparquet.egg-info/dependency_links.txt -fastparquet.egg-info/pbr.json fastparquet.egg-info/requires.txt fastparquet.egg-info/top_level.txt fastparquet/benchmarks/columns.py diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/fastparquet-0.2.0/fastparquet.egg-info/pbr.json new/fastparquet-0.2.1/fastparquet.egg-info/pbr.json --- old/fastparquet-0.2.0/fastparquet.egg-info/pbr.json 2018-11-22 17:33:29.000000000 +0100 +++ new/fastparquet-0.2.1/fastparquet.egg-info/pbr.json 1970-01-01 01:00:00.000000000 +0100 @@ -1 +0,0 @@ -{"git_version": "65283e2", "is_release": true} \ No newline at end of file diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/fastparquet-0.2.0/setup.py new/fastparquet-0.2.1/setup.py --- old/fastparquet-0.2.0/setup.py 2018-11-22 17:31:49.000000000 +0100 +++ new/fastparquet-0.2.1/setup.py 2018-12-18 22:33:00.000000000 +0100 @@ -54,7 +54,7 @@ setup( name='fastparquet', - version='0.2.0', + version='0.2.1', description='Python support for Parquet file format', author='Martin Durant', author_email='[email protected]',
