added 'want_exc' param to '_string_to_dts'

Author: anmyachev

pandas/_libs/tslib.pyx

@@ -205,8 +205,7 @@ def _test_parse_iso8601(object ts):
     elif ts == 'today':
         return Timestamp.now().normalize()
 
-    if _string_to_dts(ts, &obj.dts, &out_local, &out_tzoffset) == -1:
-        raise ValueError
+    _string_to_dts(ts, &obj.dts, &out_local, &out_tzoffset, True)
     obj.value = dtstruct_to_dt64(&obj.dts)
     check_dts_bounds(&obj.dts)
     if out_local == 1:
@@ -583,62 +582,55 @@ cpdef array_to_datetime(ndarray[object] values, str errors='raise',
 
                     string_to_dts_failed = _string_to_dts(
                         val, &dts, &out_local,
-                        &out_tzoffset
+                        &out_tzoffset, False
                     )
-                    try:
-                        if string_to_dts_failed:
-                            # An error at this point is a _parsing_ error
-                            # specifically _not_ OutOfBoundsDatetime
-                            if _parse_today_now(val, &iresult[i]):
-                                continue
-                            elif require_iso8601:
-                                # if requiring iso8601 strings, skip trying
-                                # other formats
-                                if is_coerce:
-                                    iresult[i] = NPY_NAT
-                                    continue
-                                elif is_raise:
-                                    raise ValueError("time data {val} doesn't "
-                                                     "match format specified"
-                                                     .format(val=val))
-                                return values, tz_out
-
-                            try:
-                                py_dt = parse_datetime_string(
-                                    val,
-                                    dayfirst=dayfirst,
-                                    yearfirst=yearfirst
-                                )
-                            except Exception:
-                                if is_coerce:
-                                    iresult[i] = NPY_NAT
-                                    continue
-                                raise TypeError("invalid string coercion to "
-                                                "datetime")
-
-                            # If the dateutil parser returned tzinfo,
-                            # capture it to check if all arguments
-                            # have the same tzinfo
-                            tz = py_dt.utcoffset()
-                            if tz is not None:
-                                seen_datetime_offset = 1
-                                # dateutil timezone objects cannot be hashed,
-                                # so store the UTC offsets in seconds instead
-                                out_tzoffset_vals.add(tz.total_seconds())
-                            else:
-                                # Add a marker for naive string,
-                                # to track if we are
-                                # parsing mixed naive and aware strings
-                                out_tzoffset_vals.add('naive')
-
-                            _ts = convert_datetime_to_tsobject(py_dt, None)
-                            iresult[i] = _ts.value
-                    except:
-                        # TODO: What exception are we concerned with here?
-                        if is_coerce:
-                            iresult[i] = NPY_NAT
+                    if string_to_dts_failed:
+                        # An error at this point is a _parsing_ error
+                        # specifically _not_ OutOfBoundsDatetime
+                        if _parse_today_now(val, &iresult[i]):
                             continue
-                        raise
+                        elif require_iso8601:
+                            # if requiring iso8601 strings, skip trying
+                            # other formats
+                            if is_coerce:
+                                iresult[i] = NPY_NAT
+                                continue
+                            elif is_raise:
+                                raise ValueError("time data {val} doesn't "
+                                                    "match format specified"
+                                                    .format(val=val))
+                            return values, tz_out
+
+                        try:
+                            py_dt = parse_datetime_string(
+                                val,
+                                dayfirst=dayfirst,
+                                yearfirst=yearfirst
+                            )
+                        except Exception:
+                            if is_coerce:
+                                iresult[i] = NPY_NAT
+                                continue
+                            raise TypeError("invalid string coercion to "
+                                            "datetime")
+
+                        # If the dateutil parser returned tzinfo,
+                        # capture it to check if all arguments
+                        # have the same tzinfo
+                        tz = py_dt.utcoffset()
+                        if tz is not None:
+                            seen_datetime_offset = 1
+                            # dateutil timezone objects cannot be hashed,
+                            # so store the UTC offsets in seconds instead
+                            out_tzoffset_vals.add(tz.total_seconds())
+                        else:
+                            # Add a marker for naive string,
+                            # to track if we are
+                            # parsing mixed naive and aware strings
+                            out_tzoffset_vals.add('naive')
+
+                        _ts = convert_datetime_to_tsobject(py_dt, None)
+                        iresult[i] = _ts.value
                     if not string_to_dts_failed:
                         # No error reported by string_to_dts, pick back up
                         # where we left off

pandas/_libs/tslibs/conversion.pyx

@@ -445,7 +445,7 @@ cdef _TSObject convert_str_to_tsobject(object ts, object tz, object unit,
     else:
         string_to_dts_failed = _string_to_dts(
             ts, &obj.dts, &out_local,
-            &out_tzoffset
+            &out_tzoffset, False
         )
         if string_to_dts_failed:
             try:

pandas/_libs/tslibs/np_datetime.pxd

@@ -73,4 +73,5 @@ cdef npy_timedelta get_timedelta64_value(object obj) nogil
 cdef NPY_DATETIMEUNIT get_datetime64_unit(object obj) nogil
 
 cdef int _string_to_dts(object val, npy_datetimestruct* dts,
-                        int* out_local, int* out_tzoffset)
+                        int* out_local, int* out_tzoffset,
+                        bint want_exc) except? -1

pandas/_libs/tslibs/np_datetime.pyx

@@ -170,11 +170,12 @@ cdef inline int64_t pydate_to_dt64(date val, npy_datetimestruct *dts):
 
 
 cdef inline int _string_to_dts(object val, npy_datetimestruct* dts,
-                               int* out_local, int* out_tzoffset):
+                               int* out_local, int* out_tzoffset,
+                               bint want_exc) except? -1:
     cdef:
         Py_ssize_t length
         const char* buf
 
     buf = get_c_string_buf_and_size(val, &length)
-    return parse_iso_8601_datetime(buf, length, 0,
+    return parse_iso_8601_datetime(buf, length, want_exc,
                                    dts, out_local, out_tzoffset)

pandas/tests/tslibs/test_parse_iso8601.py

@@ -46,13 +46,18 @@ def test_parsers_iso8601(date_str, exp):
     "20010101 12345Z",
 ])
 def test_parsers_iso8601_invalid(date_str):
-    with pytest.raises(ValueError):
+    msg = "Error parsing datetime string \"{s}\"".format(s=date_str)
+
+    with pytest.raises(ValueError, match=msg):
         tslib._test_parse_iso8601(date_str)
 
 
 def test_parsers_iso8601_invalid_offset_invalid():
     date_str = "2001-01-01 12-34-56"
-    with pytest.raises(ValueError):
+    msg = ("Timezone hours offset out of range "
+           "in datetime string \"{s}\"".format(s=date_str))
+
+    with pytest.raises(ValueError, match=msg):
         tslib._test_parse_iso8601(date_str)