Merge remote-tracking branch 'upstream/master' into GH28501

Author: avinashpancham

pandas/io/excel/_base.py

@@ -316,33 +316,36 @@ def read_excel(
             "an ExcelFile - ExcelFile already has the engine set"
         )
 
-    data = io.parse(
-        sheet_name=sheet_name,
-        header=header,
-        names=names,
-        index_col=index_col,
-        usecols=usecols,
-        squeeze=squeeze,
-        dtype=dtype,
-        converters=converters,
-        true_values=true_values,
-        false_values=false_values,
-        skiprows=skiprows,
-        nrows=nrows,
-        na_values=na_values,
-        keep_default_na=keep_default_na,
-        na_filter=na_filter,
-        verbose=verbose,
-        parse_dates=parse_dates,
-        date_parser=date_parser,
-        thousands=thousands,
-        comment=comment,
-        skipfooter=skipfooter,
-        convert_float=convert_float,
-        mangle_dupe_cols=mangle_dupe_cols,
-    )
-    if should_close:
-        io.close()
+    try:
+        data = io.parse(
+            sheet_name=sheet_name,
+            header=header,
+            names=names,
+            index_col=index_col,
+            usecols=usecols,
+            squeeze=squeeze,
+            dtype=dtype,
+            converters=converters,
+            true_values=true_values,
+            false_values=false_values,
+            skiprows=skiprows,
+            nrows=nrows,
+            na_values=na_values,
+            keep_default_na=keep_default_na,
+            na_filter=na_filter,
+            verbose=verbose,
+            parse_dates=parse_dates,
+            date_parser=date_parser,
+            thousands=thousands,
+            comment=comment,
+            skipfooter=skipfooter,
+            convert_float=convert_float,
+            mangle_dupe_cols=mangle_dupe_cols,
+        )
+    finally:
+        # make sure to close opened file handles
+        if should_close:
+            io.close()
     return data
 
 

pandas/io/formats/excel.py

@@ -818,6 +818,7 @@ def write(
                 f"Max sheet size is: {self.max_rows}, {self.max_cols}"
             )
 
+        formatted_cells = self.get_formatted_cells()
         if isinstance(writer, ExcelWriter):
             need_save = False
         else:
@@ -829,13 +830,15 @@ def write(
             )
             need_save = True
 
-        formatted_cells = self.get_formatted_cells()
-        writer.write_cells(
-            formatted_cells,
-            sheet_name,
-            startrow=startrow,
-            startcol=startcol,
-            freeze_panes=freeze_panes,
-        )
-        if need_save:
-            writer.save()
+        try:
+            writer.write_cells(
+                formatted_cells,
+                sheet_name,
+                startrow=startrow,
+                startcol=startcol,
+                freeze_panes=freeze_panes,
+            )
+        finally:
+            # make sure to close opened file handles
+            if need_save:
+                writer.close()

pandas/io/json/_json.py

@@ -631,6 +631,7 @@ def _preprocess_data(self, data):
         """
         if hasattr(data, "read") and (not self.chunksize or not self.nrows):
             data = data.read()
+            self.close()
         if not hasattr(data, "read") and (self.chunksize or self.nrows):
             data = StringIO(data)
 

pandas/io/parsers.py

@@ -2066,6 +2066,7 @@ def read(self, nrows=None):
                 return index, columns, col_dict
 
             else:
+                self.close()
                 raise
 
         # Done with first read, next time raise StopIteration
@@ -2449,6 +2450,7 @@ def read(self, rows=None):
             if self._first_chunk:
                 content = []
             else:
+                self.close()
                 raise
 
         # done with first read, next time raise StopIteration

pandas/io/sas/sas7bdat.py

@@ -203,7 +203,6 @@ def _get_properties(self):
         self._path_or_buf.seek(0)
         self._cached_page = self._path_or_buf.read(288)
         if self._cached_page[0 : len(const.magic)] != const.magic:
-            self.close()
             raise ValueError("magic number mismatch (not a SAS file?)")
 
         # Get alignment information
@@ -279,7 +278,6 @@ def _get_properties(self):
         buf = self._path_or_buf.read(self.header_length - 288)
         self._cached_page += buf
         if len(self._cached_page) != self.header_length:
-            self.close()
             raise ValueError("The SAS7BDAT file appears to be truncated.")
 
         self._page_length = self._read_int(
@@ -333,6 +331,7 @@ def _get_properties(self):
     def __next__(self):
         da = self.read(nrows=self.chunksize or 1)
         if da is None:
+            self.close()
             raise StopIteration
         return da
 
@@ -377,7 +376,6 @@ def _parse_metadata(self):
             if len(self._cached_page) <= 0:
                 break
             if len(self._cached_page) != self._page_length:
-                self.close()
                 raise ValueError("Failed to read a meta data page from the SAS file.")
             done = self._process_page_meta()
 

pandas/io/sas/sas_xport.py

@@ -276,14 +276,12 @@ def _read_header(self):
         # read file header
         line1 = self._get_row()
         if line1 != _correct_line1:
-            self.close()
             raise ValueError("Header record is not an XPORT file.")
 
         line2 = self._get_row()
         fif = [["prefix", 24], ["version", 8], ["OS", 8], ["_", 24], ["created", 16]]
         file_info = _split_line(line2, fif)
         if file_info["prefix"] != "SAS     SAS     SASLIB":
-            self.close()
             raise ValueError("Header record has invalid prefix.")
         file_info["created"] = _parse_date(file_info["created"])
         self.file_info = file_info
@@ -297,7 +295,6 @@ def _read_header(self):
         headflag1 = header1.startswith(_correct_header1)
         headflag2 = header2 == _correct_header2
         if not (headflag1 and headflag2):
-            self.close()
             raise ValueError("Member header not found")
         # usually 140, could be 135
         fieldnamelength = int(header1[-5:-2])
@@ -346,7 +343,6 @@ def _read_header(self):
             field["ntype"] = types[field["ntype"]]
             fl = field["field_length"]
             if field["ntype"] == "numeric" and ((fl < 2) or (fl > 8)):
-                self.close()
                 msg = f"Floating field width {fl} is not between 2 and 8."
                 raise TypeError(msg)
 
@@ -361,7 +357,6 @@ def _read_header(self):
 
         header = self._get_row()
         if not header == _correct_obs_header:
-            self.close()
             raise ValueError("Observation header not found.")
 
         self.fields = fields

pandas/tests/io/parser/test_compression.py

@@ -23,7 +23,7 @@ def parser_and_data(all_parsers, csv1):
 
     with open(csv1, "rb") as f:
         data = f.read()
-        expected = parser.read_csv(csv1)
+    expected = parser.read_csv(csv1)
 
     return parser, data, expected
 

pandas/tests/plotting/test_converter.py

@@ -7,6 +7,7 @@
 
 import pandas._config.config as cf
 
+from pandas.compat import is_platform_windows
 from pandas.compat.numpy import np_datetime64_compat
 import pandas.util._test_decorators as td
 
@@ -72,15 +73,22 @@ def test_registering_no_warning(self):
         ax.plot(s.index, s.values)
         plt.close()
 
+    @pytest.mark.xfail(
+        is_platform_windows(),
+        reason="Getting two warnings intermittently, see GH#37746",
+        strict=False,
+    )
     def test_pandas_plots_register(self):
         plt = pytest.importorskip("matplotlib.pyplot")
         s = Series(range(12), index=date_range("2017", periods=12))
         # Set to the "warn" state, in case this isn't the first test run
         with tm.assert_produces_warning(None) as w:
             s.plot()
 
-        assert len(w) == 0
-        plt.close()
+        try:
+            assert len(w) == 0
+        finally:
+            plt.close()
 
     def test_matplotlib_formatters(self):
         units = pytest.importorskip("matplotlib.units")