FIX: StataReader: defer opening file to when data is required

Author: akx

pandas/io/stata.py

@@ -1118,6 +1118,8 @@ def __init__(self) -> None:
 class StataReader(StataParser, abc.Iterator):
     __doc__ = _stata_reader_doc
 
+    _path_or_buf: IO[bytes]  # Will be assigned by `_open_file`.
+
     def __init__(
         self,
         path_or_buf: FilePath | ReadBuffer[bytes],
@@ -1144,6 +1146,9 @@ def __init__(
         self._preserve_dtypes = preserve_dtypes
         self._columns = columns
         self._order_categoricals = order_categoricals
+        self._original_path_or_buf = path_or_buf
+        self._compression = compression
+        self._storage_options = storage_options
         self._encoding = ""
         self._chunksize = chunksize
         self._using_iterator = False
@@ -1153,6 +1158,7 @@ def __init__(
             raise ValueError("chunksize must be a positive integer when set.")
 
         # State variables for the file
+        self._close_file: Callable[[], None] | None = None
         self._has_string_data = False
         self._missing_values = False
         self._can_read_value_labels = False
@@ -1163,12 +1169,24 @@ def __init__(
         self._lines_read = 0
 
         self._native_byteorder = _set_endianness(sys.byteorder)
+
+    def _ensure_open(self) -> None:
+        """
+        Ensure the file has been opened and its header data read.
+        """
+        if not hasattr(self, "_path_or_buf"):
+            self._open_file()
+
+    def _open_file(self) -> None:
+        """
+        Open the file (with compression options, etc.), and read header information.
+        """
         with get_handle(
-            path_or_buf,
+            self._original_path_or_buf,
             "rb",
-            storage_options=storage_options,
+            storage_options=self._storage_options,
             is_text=False,
-            compression=compression,
+            compression=self._compression,
         ) as handles:
             # Copy to BytesIO, and ensure no encoding
             self._path_or_buf = BytesIO(handles.handle.read())
@@ -1535,6 +1553,7 @@ def _decode(self, s: bytes) -> str:
             return s.decode("latin-1")
 
     def _read_value_labels(self) -> None:
+        self._ensure_open()
         if self._value_labels_read:
             # Don't read twice
             return
@@ -1654,6 +1673,7 @@ def read(
         columns: Sequence[str] | None = None,
         order_categoricals: bool | None = None,
     ) -> DataFrame:
+        self._ensure_open()
         # Handle empty file or chunk.  If reading incrementally raise
         # StopIteration.  If reading the whole thing return an empty
         # data frame.
@@ -1982,48 +2002,15 @@ def data_label(self) -> str:
         """
         Return data label of Stata file.
         """
+        self._ensure_open()
         return self._data_label
 
-    @property
-    def typlist(self) -> list[int | str]:
-        """
-        Return list of variable types.
-        """
-        return self._typlist
-
-    @property
-    def dtyplist(self) -> list[str | np.dtype]:
-        """
-        Return list of variable types.
-        """
-        return self._dtyplist
-
-    @property
-    def lbllist(self) -> list[str]:
-        """
-        Return list of variable labels.
-        """
-        return self._lbllist
-
-    @property
-    def varlist(self) -> list[str]:
-        """
-        Return list of variable names.
-        """
-        return self._varlist
-
-    @property
-    def fmtlist(self) -> list[str]:
-        """
-        Return list of variable formats.
-        """
-        return self._fmtlist
-
     @property
     def time_stamp(self) -> str:
         """
         Return time stamp of Stata file.
         """
+        self._ensure_open()
         return self._time_stamp
 
     def variable_labels(self) -> dict[str, str]:
@@ -2034,6 +2021,7 @@ def variable_labels(self) -> dict[str, str]:
         -------
         dict
         """
+        self._ensure_open()
         return dict(zip(self._varlist, self._variable_labels))
 
     def value_labels(self) -> dict[str, dict[float, str]]:

pandas/tests/io/test_stata.py

@@ -742,10 +742,8 @@ def test_minimal_size_col(self):
             original.to_stata(path, write_index=False)
 
             with StataReader(path) as sr:
-                typlist = sr.typlist
-                variables = sr.varlist
-                formats = sr.fmtlist
-                for variable, fmt, typ in zip(variables, formats, typlist):
+                sr._ensure_open()  # The `_*list` variables are initialized here
+                for variable, fmt, typ in zip(sr._varlist, sr._fmtlist, sr._typlist):
                     assert int(variable[1:]) == int(fmt[1:-1])
                     assert int(variable[1:]) == typ