ENH: Add support for reading 110-format Stata dta files (#58044)

* ENH: Add support for reading 110-format Stata dta files

* Add whatsnew note to v3.0.0.rst

* Add a test data file containing value labels

* Compare version number inclusively when determining whether to use old or new typlist version

* Add a big-endian version of the test data set

Author: cmjcharlton

doc/source/whatsnew/v3.0.0.rst

@@ -44,6 +44,8 @@ Other enhancements
 - :meth:`DataFrame.fillna` and :meth:`Series.fillna` can now accept ``value=None``; for non-object dtype the corresponding NA value will be used (:issue:`57723`)
 - :meth:`Series.cummin` and :meth:`Series.cummax` now supports :class:`CategoricalDtype` (:issue:`52335`)
 - :meth:`Series.plot` now correctly handle the ``ylabel`` parameter for pie charts, allowing for explicit control over the y-axis label (:issue:`58239`)
+- Support reading Stata 110-format (Stata 7) dta files (:issue:`47176`)
+-
 
 .. ---------------------------------------------------------------------------
 .. _whatsnew_300.notable_bug_fixes:

pandas/io/stata.py

@@ -91,7 +91,7 @@
 
 _version_error = (
     "Version of given Stata file is {version}. pandas supports importing "
-    "versions 105, 108, 111 (Stata 7SE), 113 (Stata 8/9), "
+    "versions 105, 108, 110 (Stata 7), 111 (Stata 7SE), 113 (Stata 8/9), "
     "114 (Stata 10/11), 115 (Stata 12), 117 (Stata 13), 118 (Stata 14/15/16),"
     "and 119 (Stata 15/16, over 32,767 variables)."
 )
@@ -1393,7 +1393,7 @@ def _get_seek_variable_labels(self) -> int:
 
     def _read_old_header(self, first_char: bytes) -> None:
         self._format_version = int(first_char[0])
-        if self._format_version not in [104, 105, 108, 111, 113, 114, 115]:
+        if self._format_version not in [104, 105, 108, 110, 111, 113, 114, 115]:
             raise ValueError(_version_error.format(version=self._format_version))
         self._set_encoding()
         self._byteorder = ">" if self._read_int8() == 0x1 else "<"
@@ -1408,7 +1408,7 @@ def _read_old_header(self, first_char: bytes) -> None:
         self._time_stamp = self._get_time_stamp()
 
         # descriptors
-        if self._format_version > 108:
+        if self._format_version >= 111:
             typlist = [int(c) for c in self._path_or_buf.read(self._nvar)]
         else:
             buf = self._path_or_buf.read(self._nvar)

pandas/tests/io/data/stata/stata-compat-110.dta

@@ -225,11 +225,9 @@ def test_read_dta3(self, file, datapath):
 
         tm.assert_frame_equal(parsed, expected)
 
-    @pytest.mark.parametrize(
-        "file", ["stata4_111", "stata4_113", "stata4_114", "stata4_115", "stata4_117"]
-    )
-    def test_read_dta4(self, file, datapath):
-        file = datapath("io", "data", "stata", f"{file}.dta")
+    @pytest.mark.parametrize("version", [110, 111, 113, 114, 115, 117])
+    def test_read_dta4(self, version, datapath):
+        file = datapath("io", "data", "stata", f"stata4_{version}.dta")
         parsed = self.read_dta(file)
 
         expected = DataFrame.from_records(
@@ -271,11 +269,11 @@ def test_read_dta4(self, file, datapath):
         # stata doesn't save .category metadata
         tm.assert_frame_equal(parsed, expected)
 
-    @pytest.mark.parametrize("file", ["stata4_105", "stata4_108"])
-    def test_readold_dta4(self, file, datapath):
+    @pytest.mark.parametrize("version", [105, 108])
+    def test_readold_dta4(self, version, datapath):
         # This test is the same as test_read_dta4 above except that the columns
         # had to be renamed to match the restrictions in older file format
-        file = datapath("io", "data", "stata", f"{file}.dta")
+        file = datapath("io", "data", "stata", f"stata4_{version}.dta")
         parsed = self.read_dta(file)
 
         expected = DataFrame.from_records(
@@ -2002,7 +2000,7 @@ def test_read_write_ea_dtypes(self, dtype_backend, temp_file, tmp_path):
         tm.assert_frame_equal(written_and_read_again.set_index("index"), expected)
 
 
-@pytest.mark.parametrize("version", [105, 108, 111, 113, 114])
+@pytest.mark.parametrize("version", [105, 108, 110, 111, 113, 114])
 def test_backward_compat(version, datapath):
     data_base = datapath("io", "data", "stata")
     ref = os.path.join(data_base, "stata-compat-118.dta")
@@ -2012,7 +2010,7 @@ def test_backward_compat(version, datapath):
     tm.assert_frame_equal(old_dta, expected, check_dtype=False)
 
 
-@pytest.mark.parametrize("version", [105, 108, 111, 113, 114, 118])
+@pytest.mark.parametrize("version", [105, 108, 110, 111, 113, 114, 118])
 def test_bigendian(version, datapath):
     ref = datapath("io", "data", "stata", f"stata-compat-{version}.dta")
     big = datapath("io", "data", "stata", f"stata-compat-be-{version}.dta")