CLN: use stdlib Iterator instead of BaseIterator (pandas-dev#30370)

Author: jbrockmendel

pandas/io/common.py

@@ -2,6 +2,7 @@
 
 import bz2
 import codecs
+from collections.abc import Iterator
 import gzip
 from io import BufferedIOBase, BytesIO
 import mmap
@@ -49,18 +50,6 @@
 _VALID_URLS.discard("")
 
 
-class BaseIterator:
-    """Subclass this and provide a "__next__()" method to obtain an iterator.
-    Useful only when the object being iterated is non-reusable (e.g. OK for a
-    parser, not for an in-memory table, yes for its iterator)."""
-
-    def __iter__(self) -> "BaseIterator":
-        return self
-
-    def __next__(self):
-        raise AbstractMethodError(self)
-
-
 def is_url(url) -> bool:
     """
     Check to see if a URL has a valid protocol.
@@ -515,7 +504,7 @@ def closed(self):
         return self.fp is None
 
 
-class _MMapWrapper(BaseIterator):
+class _MMapWrapper(Iterator):
     """
     Wrapper for the Python's mmap class so that it can be properly read in
     by Python's csv.reader class.
@@ -552,7 +541,7 @@ def __next__(self) -> str:
         return newline
 
 
-class UTF8Recoder(BaseIterator):
+class UTF8Recoder(Iterator):
     """
     Iterator that reads an encoded stream and re-encodes the input to UTF-8
     """
@@ -566,7 +555,7 @@ def read(self, bytes: int = -1) -> bytes:
     def readline(self) -> bytes:
         return self.reader.readline().encode("utf-8")
 
-    def next(self) -> bytes:
+    def __next__(self) -> bytes:
         return next(self.reader).encode("utf-8")
 
     def close(self):

pandas/io/json/_json.py

@@ -1,4 +1,5 @@
 from collections import OrderedDict
+from collections.abc import Iterator
 import functools
 from io import StringIO
 from itertools import islice
@@ -19,7 +20,6 @@
 from pandas.core.reshape.concat import concat
 
 from pandas.io.common import (
-    BaseIterator,
     get_filepath_or_buffer,
     get_handle,
     infer_compression,
@@ -616,7 +616,7 @@ def read_json(
     return result
 
 
-class JsonReader(BaseIterator):
+class JsonReader(Iterator):
     """
     JsonReader provides an interface for reading in a JSON file.
 

pandas/io/parsers.py

@@ -3,6 +3,7 @@
 """
 
 from collections import defaultdict
+from collections.abc import Iterator
 import csv
 import datetime
 from io import StringIO
@@ -62,7 +63,6 @@
 from pandas.core.tools import datetimes as tools
 
 from pandas.io.common import (
-    BaseIterator,
     UTF8Recoder,
     get_filepath_or_buffer,
     get_handle,
@@ -786,7 +786,7 @@ def read_fwf(
     return _read(filepath_or_buffer, kwds)
 
 
-class TextFileReader(BaseIterator):
+class TextFileReader(Iterator):
     """
 
     Passed dialect overrides any of the related parser options
@@ -3582,7 +3582,7 @@ def _get_col_names(colspec, columns):
     return colnames
 
 
-class FixedWidthReader(BaseIterator):
+class FixedWidthReader(Iterator):
     """
     A reader of fixed-width lines.
     """

pandas/io/sas/sas7bdat.py

@@ -13,6 +13,7 @@
 Reference for binary data compression:
   http://collaboration.cmc.ec.gc.ca/science/rpn/biblio/ddj/Website/articles/CUJ/1992/9210/ross/ross.htm
 """
+from collections.abc import Iterator
 from datetime import datetime
 import struct
 
@@ -22,7 +23,7 @@
 
 import pandas as pd
 
-from pandas.io.common import BaseIterator, get_filepath_or_buffer
+from pandas.io.common import get_filepath_or_buffer
 from pandas.io.sas._sas import Parser
 import pandas.io.sas.sas_constants as const
 
@@ -36,7 +37,7 @@ class _column:
 
 
 # SAS7BDAT represents a SAS data file in SAS7BDAT format.
-class SAS7BDATReader(BaseIterator):
+class SAS7BDATReader(Iterator):
     """
     Read SAS files in SAS7BDAT format.
 

pandas/io/sas/sas_xport.py

@@ -7,7 +7,7 @@
 
 https://support.sas.com/techsup/technote/ts140.pdf
 """
-
+from collections.abc import Iterator
 from datetime import datetime
 from io import BytesIO
 import struct
@@ -19,7 +19,7 @@
 
 import pandas as pd
 
-from pandas.io.common import BaseIterator, get_filepath_or_buffer
+from pandas.io.common import get_filepath_or_buffer
 
 _correct_line1 = (
     "HEADER RECORD*******LIBRARY HEADER RECORD!!!!!!!"
@@ -251,7 +251,7 @@ def _parse_float_vec(vec):
     return ieee
 
 
-class XportReader(BaseIterator):
+class XportReader(Iterator):
     __doc__ = _xport_reader_doc
 
     def __init__(

pandas/io/stata.py

@@ -9,7 +9,7 @@
 You can find more information on http://presbrey.mit.edu/PyDTA and
 http://www.statsmodels.org/devel/
 """
-
+from collections.abc import Iterator
 import datetime
 from io import BytesIO
 import os
@@ -44,7 +44,7 @@
 from pandas.core.frame import DataFrame
 from pandas.core.series import Series
 
-from pandas.io.common import BaseIterator, get_filepath_or_buffer, stringify_path
+from pandas.io.common import get_filepath_or_buffer, stringify_path
 
 _version_error = (
     "Version of given Stata file is not 104, 105, 108, "
@@ -1010,7 +1010,7 @@ def __init__(self):
         )
 
 
-class StataReader(StataParser, BaseIterator):
+class StataReader(StataParser, Iterator):
     __doc__ = _stata_reader_doc
 
     def __init__(