STYLE: prohibit parsing exeption messages

doc/source/reference/testing.rst

@@ -32,19 +32,26 @@ Exceptions and warnings
    errors.CSSWarning
    errors.DatabaseError
    errors.DataError
+   errors.DataOneDimensionalError
+   errors.DiffArrayLengthError
+   errors.DotMismatchShapeError
    errors.DtypeWarning
    errors.DuplicateLabelError
    errors.EmptyDataError
    errors.IncompatibilityWarning
    errors.IndexingError
+   errors.IndexSpecifiedError
    errors.InvalidColumnName
    errors.InvalidComparison
    errors.InvalidIndexError
    errors.InvalidVersion
    errors.IntCastingNaNError
    errors.LossySetitemError
    errors.MergeError
+   errors.NATypeError
    errors.NoBufferPresent
+   errors.NoObjectConcatenateError
+   errors.NotObjectError
    errors.NullFrequencyError
    errors.NumbaUtilError
    errors.NumExprClobberingError
@@ -61,6 +68,7 @@ Exceptions and warnings
    errors.SettingWithCopyError
    errors.SettingWithCopyWarning
    errors.SpecificationError
+   errors.SupplyTzDetypeError
    errors.UndefinedVariableError
    errors.UnsortedIndexError
    errors.UnsupportedFunctionCall

pandas/_libs/missing.pyx

@@ -4,6 +4,7 @@ from sys import maxsize
 
 cimport cython
 from cython cimport Py_ssize_t
+
 import numpy as np
 
 cimport numpy as cnp
@@ -30,6 +31,7 @@ from pandas._libs.tslibs.np_datetime cimport (
 )
 
 from pandas._libs.ops_dispatch import maybe_dispatch_ufunc_to_dunder_op
+from pandas.errors import NATypeError
 
 cdef:
     float64_t INF = <float64_t>np.inf
@@ -410,7 +412,7 @@ class NAType(C_NAType):
             return self.__repr__()
 
     def __bool__(self):
-        raise TypeError("boolean value of NA is ambiguous")
+        raise NATypeError("boolean value of NA is ambiguous")
 
     def __hash__(self):
         # GH 30013: Ensure hash is large enough to avoid hash collisions with integers

pandas/_libs/reduction.pyx

@@ -6,6 +6,8 @@ cnp.import_array()
 
 from pandas._libs.util cimport is_array
 
+from pandas.errors import NotObjectError
+
 
 cdef cnp.dtype _dtype_obj = np.dtype("object")
 
@@ -18,8 +20,7 @@ cpdef check_result_array(object obj, object dtype):
         if dtype != _dtype_obj:
             # If it is object dtype, the function can be a reduction/aggregation
             #  and still return an ndarray e.g. test_agg_over_numpy_arrays
-            raise ValueError("Must produce aggregated value")
-
+            raise NotObjectError("Must produce aggregated value")
 
 cpdef inline extract_result(object res):
     """ extract the result object, it might be a 0-dim ndarray

pandas/core/apply.py

@@ -33,7 +33,10 @@
     NDFrameT,
     npt,
 )
-from pandas.errors import SpecificationError
+from pandas.errors import (
+    DiffArrayLengthError,
+    SpecificationError,
+)
 from pandas.util._decorators import cache_readonly
 
 from pandas.core.dtypes.cast import is_nested_object
@@ -864,15 +867,14 @@ def wrap_results_for_axis(
 
         try:
             result = self.obj._constructor(data=results)
-        except ValueError as err:
-            if "All arrays must be of the same length" in str(err):
-                # e.g. result = [[2, 3], [1.5], ['foo', 'bar']]
-                #  see test_agg_listlike_result GH#29587
-                res = self.obj._constructor_sliced(results)
-                res.index = res_index
-                return res
-            else:
-                raise
+        except DiffArrayLengthError:
+            # e.g. result = [[2, 3], [1.5], ['foo', 'bar']]
+            #  see test_agg_listlike_result GH#29587
+            res = self.obj._constructor_sliced(results)
+            res.index = res_index
+            return res
+        except ValueError:
+            raise
 
         if not isinstance(results[0], ABCSeries):
             if len(result.index) == len(self.res_columns):

pandas/core/arrays/datetimes.py

@@ -50,7 +50,10 @@
     TimeNonexistent,
     npt,
 )
-from pandas.errors import PerformanceWarning
+from pandas.errors import (
+    PerformanceWarning,
+    SupplyTzDetypeError,
+)
 from pandas.util._exceptions import find_stack_level
 from pandas.util._validators import validate_inclusive
 
@@ -2367,9 +2370,8 @@ def _validate_tz_from_dtype(
             # We also need to check for the case where the user passed a
             #  tz-naive dtype (i.e. datetime64[ns])
             if tz is not None and not timezones.tz_compare(tz, dtz):
-                raise ValueError(
-                    "cannot supply both a tz and a "
-                    "timezone-naive dtype (i.e. datetime64[ns])"
+                raise SupplyTzDetypeError(
+                    "cannot supply both a tz and a timezone-naive dtype"
                 )
 
     return tz

pandas/core/construction.py

@@ -27,6 +27,10 @@
     DtypeObj,
     T,
 )
+from pandas.errors import (
+    DataOneDimensionalError,
+    IndexSpecifiedError,
+)
 
 from pandas.core.dtypes.base import (
     ExtensionDtype,
@@ -540,7 +544,9 @@ def sanitize_array(
 
     if not is_list_like(data):
         if index is None:
-            raise ValueError("index must be specified when data is not list-like")
+            raise IndexSpecifiedError(
+                "index must be specified when data is not list-like"
+            )
         data = construct_1d_arraylike_from_scalar(data, len(index), dtype)
         return data
 
@@ -666,7 +672,7 @@ def _sanitize_ndim(
         if isinstance(data, np.ndarray):
             if allow_2d:
                 return result
-            raise ValueError("Data must be 1-dimensional")
+            raise DataOneDimensionalError("Data must be 1-dimensional")
         if is_object_dtype(dtype) and isinstance(dtype, ExtensionDtype):
             # i.e. PandasDtype("O")
 

pandas/core/dtypes/cast.py

@@ -41,6 +41,7 @@
 from pandas.errors import (
     IntCastingNaNError,
     LossySetitemError,
+    SupplyTzDetypeError,
 )
 
 from pandas.core.dtypes.common import (
@@ -1177,14 +1178,15 @@ def maybe_cast_to_datetime(
     else:
         try:
             dta = DatetimeArray._from_sequence(value, dtype=dtype)
-        except ValueError as err:
-            # We can give a Series-specific exception message.
-            if "cannot supply both a tz and a timezone-naive dtype" in str(err):
-                raise ValueError(
-                    "Cannot convert timezone-aware data to "
-                    "timezone-naive dtype. Use "
-                    "pd.Series(values).dt.tz_localize(None) instead."
-                ) from err
+
+        except SupplyTzDetypeError as err:
+            raise ValueError(
+                "Cannot convert timezone-aware data to "
+                "timezone-naive dtype. Use "
+                "pd.Series(values).dt.tz_localize(None) instead."
+            ) from err
+
+        except ValueError:
             raise
 
         return dta

pandas/core/dtypes/missing.py

@@ -20,6 +20,7 @@
     NaT,
     iNaT,
 )
+from pandas.errors import NATypeError
 
 from pandas.core.dtypes.common import (
     DT64NS_DTYPE,
@@ -580,9 +581,9 @@ def _array_equivalent_object(left: np.ndarray, right: np.ndarray, strict_nan: bo
             try:
                 if np.any(np.asarray(left_value != right_value)):
                     return False
-            except TypeError as err:
-                if "boolean value of NA is ambiguous" in str(err):
-                    return False
+            except NATypeError:
+                return False
+            except TypeError:
                 raise
     return True
 

pandas/core/frame.py

@@ -92,7 +92,10 @@
     function as nv,
     np_percentile_argname,
 )
-from pandas.errors import InvalidIndexError
+from pandas.errors import (
+    DotMismatchShapeError,
+    InvalidIndexError,
+)
 from pandas.util._decorators import (
     Appender,
     Substitution,
@@ -1570,7 +1573,7 @@ def dot(self, other: AnyArrayLike | DataFrame) -> DataFrame | Series:
             lvals = self.values
             rvals = np.asarray(other)
             if lvals.shape[1] != rvals.shape[0]:
-                raise ValueError(
+                raise DotMismatchShapeError(
                     f"Dot product shape mismatch, {lvals.shape} vs {rvals.shape}"
                 )
 
@@ -1609,12 +1612,12 @@ def __rmatmul__(self, other) -> DataFrame:
         """
         try:
             return self.T.dot(np.transpose(other)).T
-        except ValueError as err:
-            if "shape mismatch" not in str(err):
-                raise
+        except DotMismatchShapeError as err:
             # GH#21581 give exception message for original shapes
             msg = f"shapes {np.shape(other)} and {self.shape} not aligned"
             raise ValueError(msg) from err
+        except ValueError:
+            raise
 
     # ----------------------------------------------------------------------
     # IO methods (to / from other formats)

pandas/core/groupby/generic.py

@@ -44,7 +44,10 @@
     SingleManager,
     TakeIndexer,
 )
-from pandas.errors import SpecificationError
+from pandas.errors import (
+    NoObjectConcatenateError,
+    SpecificationError,
+)
 from pandas.util._decorators import (
     Appender,
     Substitution,
@@ -1177,12 +1180,10 @@ def aggregate(self, func=None, *args, engine=None, engine_kwargs=None, **kwargs)
                 gba = GroupByApply(self, [func], args=(), kwargs={})
                 try:
                     result = gba.agg()
-
-                except ValueError as err:
-                    if "No objects to concatenate" not in str(err):
-                        raise
+                except NoObjectConcatenateError:
                     result = self._aggregate_frame(func)
-
+                except ValueError:
+                    raise
                 else:
                     sobj = self._selected_obj
 

pandas/core/indexes/base.py

@@ -60,7 +60,9 @@
 )
 from pandas.compat.numpy import function as nv
 from pandas.errors import (
+    DataOneDimensionalError,
     DuplicateLabelError,
+    IndexSpecifiedError,
     InvalidIndexError,
 )
 from pandas.util._decorators import (
@@ -500,11 +502,11 @@ def __new__(
 
         try:
             arr = sanitize_array(data, None, dtype=dtype, copy=copy)
-        except ValueError as err:
-            if "index must be specified when data is not list-like" in str(err):
-                raise cls._raise_scalar_data_error(data) from err
-            if "Data must be 1-dimensional" in str(err):
-                raise ValueError("Index data must be 1-dimensional") from err
+        except IndexSpecifiedError as err:
+            raise cls._raise_scalar_data_error(data) from err
+        except DataOneDimensionalError as err:
+            raise ValueError("Index data must be 1-dimensional") from err
+        except ValueError:
             raise
         arr = ensure_wrapped_if_datetimelike(arr)
 

pandas/core/internals/construction.py

@@ -21,6 +21,7 @@
     Manager,
     npt,
 )
+from pandas.errors import DiffArrayLengthError
 
 from pandas.core.dtypes.cast import (
     construct_1d_arraylike_from_scalar,
@@ -623,7 +624,7 @@ def _extract_index(data) -> Index:
     if have_raw_arrays:
         lengths = list(set(raw_lengths))
         if len(lengths) > 1:
-            raise ValueError("All arrays must be of the same length")
+            raise DiffArrayLengthError("All arrays must be of the same length")
 
         if have_dicts:
             raise ValueError(

pandas/core/resample.py

@@ -42,6 +42,7 @@
 from pandas.errors import (
     AbstractMethodError,
     DataError,
+    NotObjectError,
 )
 from pandas.util._decorators import (
     Appender,
@@ -459,18 +460,14 @@ def _groupby_and_aggregate(self, how, *args, **kwargs):
             #  on Series, raising AttributeError or KeyError
             #  (depending on whether the column lookup uses getattr/__getitem__)
             result = grouped.apply(how, *args, **kwargs)
+        except NotObjectError:
+            # we have a non-reducing function; try to evaluate
 
-        except ValueError as err:
-            if "Must produce aggregated value" in str(err):
-                # raised in _aggregate_named
-                # see test_apply_without_aggregation, test_apply_with_mutated_index
-                pass
-            else:
-                raise
-
-            # we have a non-reducing function
-            # try to evaluate
+            # raised in _aggregate_named
+            # see test_apply_without_aggregation, test_apply_with_mutated_index
             result = grouped.apply(how, *args, **kwargs)
+        except ValueError:
+            raise
 
         return self._wrap_result(result)
 

pandas/core/reshape/concat.py

@@ -22,6 +22,7 @@
     AxisInt,
     HashableT,
 )
+from pandas.errors import NoObjectConcatenateError
 from pandas.util._decorators import cache_readonly
 
 from pandas.core.dtypes.concat import concat_compat
@@ -420,7 +421,7 @@ def __init__(
             objs = list(objs)
 
         if len(objs) == 0:
-            raise ValueError("No objects to concatenate")
+            raise NoObjectConcatenateError("No objects to concatenate")
 
         if keys is None:
             objs = list(com.not_none(*objs))