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

Author: akx

pandas/io/stata.py

@@ -1143,6 +1143,9 @@ 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
@@ -1152,6 +1155,9 @@ def __init__(
             raise ValueError("chunksize must be a positive integer when set.")
 
         # State variables for the file
+        # NB: _path_or_buf is mistyped on purpose, since the alternative is to placate
+        #     mypy by having an assert before every read.
+        self._path_or_buf: IO[bytes] = None  # type: ignore[assignment]
         self._has_string_data = False
         self._missing_values = False
         self._can_read_value_labels = False
@@ -1162,12 +1168,24 @@ 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 self._path_or_buf is None:
+            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())
@@ -1534,6 +1552,7 @@ 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
@@ -1653,6 +1672,7 @@ 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.
@@ -1981,57 +2001,72 @@ 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.
         """
+        self._ensure_open()
         return self._typlist
 
     @property
     def dtyplist(self) -> list[str | np.dtype]:
         """
         Return list of variable types.
         """
+        self._ensure_open()
         return self._dtyplist
 
     @property
     def lbllist(self) -> list[str]:
         """
         Return list of variable labels.
         """
+        self._ensure_open()
         return self._lbllist
 
     @property
     def varlist(self) -> list[str]:
         """
         Return list of variable names.
         """
+        self._ensure_open()
         return self._varlist
 
     @property
     def fmtlist(self) -> list[str]:
         """
         Return list of variable formats.
         """
+        self._ensure_open()
         return self._fmtlist
 
     @property
     def time_stamp(self) -> str:
         """
         Return time stamp of Stata file.
         """
+        self._ensure_open()
         return self._time_stamp
 
     @property
     def format_version(self) -> int:
         """
         Return format version of Stata file.
         """
+        self._ensure_open()
         return self._format_version
 
+    @property
+    def path_or_buf(self) -> IO[bytes]:
+        """
+        Return the file handle of the Stata file being read.
+        """
+        return self._path_or_buf
+
     def variable_labels(self) -> dict[str, str]:
         """
         Return a dict associating each variable name with corresponding label.
@@ -2040,6 +2075,7 @@ 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]]: