Fixing typo in cython casting lint, and making it azure friendly (#23486)

Author: datapythonista

ci/code_checks.sh

@@ -49,7 +49,7 @@ if [[ -z "$CHECK" || "$CHECK" == "lint" ]]; then
     # Note: this grep pattern is (intended to be) equivalent to the python
     # regex r'(?<![ ->])> '
     MSG='Linting .pyx code for spacing conventions in casting' ; echo $MSG
-    ! grep -r -E --include '*.pyx' --include '*.pxi.in' '> ' pandas/_libs | grep -v '[ ->]> '
+    ! grep -r -E --include '*.pyx' --include '*.pxi.in' '[a-zA-Z0-9*]> ' pandas/_libs
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
     # readability/casting: Warnings about C casting instead of C++ casting

pandas/_libs/algos.pyx

@@ -128,11 +128,11 @@ def is_lexsorted(list_of_arrays: list) -> bint:
     nlevels = len(list_of_arrays)
     n = len(list_of_arrays[0])
 
-    cdef int64_t **vecs = <int64_t**> malloc(nlevels * sizeof(int64_t*))
+    cdef int64_t **vecs = <int64_t**>malloc(nlevels * sizeof(int64_t*))
     for i in range(nlevels):
         arr = list_of_arrays[i]
         assert arr.dtype.name == 'int64'
-        vecs[i] = <int64_t*> cnp.PyArray_DATA(arr)
+        vecs[i] = <int64_t*>cnp.PyArray_DATA(arr)
 
     # Assume uniqueness??
     with nogil:

pandas/_libs/groupby.pyx

@@ -44,7 +44,7 @@ cdef inline float64_t median_linear(float64_t* a, int n) nogil:
         if na_count == n:
             return NaN
 
-        tmp = <float64_t*> malloc((n - na_count) * sizeof(float64_t))
+        tmp = <float64_t*>malloc((n - na_count) * sizeof(float64_t))
 
         j = 0
         for i in range(n):
@@ -121,7 +121,7 @@ def group_median_float64(ndarray[float64_t, ndim=2] out,
     counts[:] = _counts[1:]
 
     data = np.empty((K, N), dtype=np.float64)
-    ptr = <float64_t*> cnp.PyArray_DATA(data)
+    ptr = <float64_t*>cnp.PyArray_DATA(data)
 
     take_2d_axis1_float64_float64(values.T, indexer, out=data)
 

pandas/_libs/hashing.pyx

@@ -54,8 +54,8 @@ def hash_object_array(object[:] arr, object key, object encoding='utf8'):
     n = len(arr)
 
     # create an array of bytes
-    vecs = <char **> malloc(n * sizeof(char *))
-    lens = <uint64_t*> malloc(n * sizeof(uint64_t))
+    vecs = <char **>malloc(n * sizeof(char *))
+    lens = <uint64_t*>malloc(n * sizeof(uint64_t))
 
     for i in range(n):
         val = arr[i]

pandas/_libs/hashtable_class_helper.pxi.in

@@ -590,13 +590,13 @@ cdef class StringHashTable(HashTable):
         cdef:
             Py_ssize_t i, n = len(values)
             ndarray[int64_t] labels = np.empty(n, dtype=np.int64)
-            int64_t *resbuf = <int64_t*> labels.data
+            int64_t *resbuf = <int64_t*>labels.data
             khiter_t k
             kh_str_t *table = self.table
             const char *v
             const char **vecs
 
-        vecs = <const char **> malloc(n * sizeof(char *))
+        vecs = <const char **>malloc(n * sizeof(char *))
         for i in range(n):
             val = values[i]
             v = util.get_c_string(val)
@@ -639,7 +639,7 @@ cdef class StringHashTable(HashTable):
             const char *v
             const char **vecs
 
-        vecs = <const char **> malloc(n * sizeof(char *))
+        vecs = <const char **>malloc(n * sizeof(char *))
         uindexer = np.empty(n, dtype=np.int64)
         for i in range(n):
             val = values[i]
@@ -674,7 +674,7 @@ cdef class StringHashTable(HashTable):
             int64_t[:] locs = np.empty(n, dtype=np.int64)
 
         # these by-definition *must* be strings
-        vecs = <char **> malloc(n * sizeof(char *))
+        vecs = <char **>malloc(n * sizeof(char *))
         for i in range(n):
             val = values[i]
 
@@ -707,7 +707,7 @@ cdef class StringHashTable(HashTable):
             khiter_t k
 
         # these by-definition *must* be strings
-        vecs = <const char **> malloc(n * sizeof(char *))
+        vecs = <const char **>malloc(n * sizeof(char *))
         for i in range(n):
             val = values[i]
 

pandas/_libs/parsers.pyx

@@ -361,7 +361,7 @@ cdef class TextReader:
             if not isinstance(encoding, bytes):
                 encoding = encoding.encode('utf-8')
             encoding = encoding.lower()
-            self.c_encoding = <char*> encoding
+            self.c_encoding = <char*>encoding
         else:
             self.c_encoding = NULL
 
@@ -611,7 +611,7 @@ cdef class TextReader:
             for i in self.skiprows:
                 parser_add_skiprow(self.parser, i)
         else:
-            self.parser.skipfunc = <PyObject *> self.skiprows
+            self.parser.skipfunc = <PyObject *>self.skiprows
 
     cdef _setup_parser_source(self, source):
         cdef:
@@ -668,7 +668,7 @@ cdef class TextReader:
                 source = icom.UTF8Recoder(source,
                                           self.encoding.decode('utf-8'))
                 self.encoding = b'utf-8'
-                self.c_encoding = <char*> self.encoding
+                self.c_encoding = <char*>self.encoding
 
             self.handle = source
 
@@ -1444,7 +1444,7 @@ cdef _string_box_factorize(parser_t *parser, int64_t col,
             pyval = PyBytes_FromString(word)
 
             k = kh_put_strbox(table, word, &ret)
-            table.vals[k] = <PyObject*> pyval
+            table.vals[k] = <PyObject*>pyval
 
         result[i] = pyval
 
@@ -1498,7 +1498,7 @@ cdef _string_box_utf8(parser_t *parser, int64_t col,
             pyval = PyUnicode_FromString(word)
 
             k = kh_put_strbox(table, word, &ret)
-            table.vals[k] = <PyObject *> pyval
+            table.vals[k] = <PyObject *>pyval
 
         result[i] = pyval
 
@@ -1556,7 +1556,7 @@ cdef _string_box_decode(parser_t *parser, int64_t col,
             pyval = PyUnicode_Decode(word, size, encoding, errors)
 
             k = kh_put_strbox(table, word, &ret)
-            table.vals[k] = <PyObject *> pyval
+            table.vals[k] = <PyObject *>pyval
 
         result[i] = pyval
 
@@ -1648,7 +1648,7 @@ cdef _to_fw_string(parser_t *parser, int64_t col, int64_t line_start,
         ndarray result
 
     result = np.empty(line_end - line_start, dtype='|S%d' % width)
-    data = <char*> result.data
+    data = <char*>result.data
 
     with nogil:
         _to_fw_string_nogil(parser, col, line_start, line_end, width, data)
@@ -1695,7 +1695,7 @@ cdef _try_double(parser_t *parser, int64_t col,
 
     lines = line_end - line_start
     result = np.empty(lines, dtype=np.float64)
-    data = <double *> result.data
+    data = <double *>result.data
     na_fset = kset_float64_from_list(na_flist)
     if parser.double_converter_nogil != NULL:  # if it can run without the GIL
         with nogil:
@@ -1803,7 +1803,7 @@ cdef _try_uint64(parser_t *parser, int64_t col,
 
     lines = line_end - line_start
     result = np.empty(lines, dtype=np.uint64)
-    data = <uint64_t *> result.data
+    data = <uint64_t *>result.data
 
     uint_state_init(&state)
     coliter_setup(&it, parser, col, line_start)
@@ -1879,7 +1879,7 @@ cdef _try_int64(parser_t *parser, int64_t col,
 
     lines = line_end - line_start
     result = np.empty(lines, dtype=np.int64)
-    data = <int64_t *> result.data
+    data = <int64_t *>result.data
     coliter_setup(&it, parser, col, line_start)
     with nogil:
         error = _try_int64_nogil(parser, col, line_start, line_end,
@@ -1951,7 +1951,7 @@ cdef _try_bool_flex(parser_t *parser, int64_t col,
 
     lines = line_end - line_start
     result = np.empty(lines, dtype=np.uint8)
-    data = <uint8_t *> result.data
+    data = <uint8_t *>result.data
     with nogil:
         error = _try_bool_flex_nogil(parser, col, line_start, line_end,
                                      na_filter, na_hashset, true_hashset,

pandas/_libs/reduction.pyx

@@ -467,7 +467,7 @@ cdef class Slider:
         self.buf.strides[0] = self.stride
 
     cpdef advance(self, Py_ssize_t k):
-        self.buf.data = <char*> self.buf.data + self.stride * k
+        self.buf.data = <char*>self.buf.data + self.stride * k
 
     cdef move(self, int start, int end):
         """
@@ -572,7 +572,7 @@ cdef class BlockSlider:
         self.idx_slider = Slider(
             self.frame.index.values, self.dummy.index.values)
 
-        self.base_ptrs = <char**> malloc(sizeof(char*) * len(self.blocks))
+        self.base_ptrs = <char**>malloc(sizeof(char*) * len(self.blocks))
         for i, block in enumerate(self.blocks):
             self.base_ptrs[i] = (<ndarray>block).data
 

pandas/_libs/sparse.pyx

@@ -342,8 +342,8 @@ cdef class BlockIndex(SparseIndex):
         self.blengths = np.ascontiguousarray(blengths, dtype=np.int32)
 
         # in case we need
-        self.locbuf = <int32_t*> self.blocs.data
-        self.lenbuf = <int32_t*> self.blengths.data
+        self.locbuf = <int32_t*>self.blocs.data
+        self.lenbuf = <int32_t*>self.blengths.data
 
         self.length = length
         self.nblocks = np.int32(len(self.blocs))
@@ -853,7 +853,7 @@ def get_reindexer(ndarray[object, ndim=1] values, dict index_map):
 #                  SparseIndex index):
 
 #         self.index = index
-#         self.buf = <float64_t*> values.data
+#         self.buf = <float64_t*>values.data
 
 
 def reindex_integer(ndarray[float64_t, ndim=1] values,

pandas/_libs/tslibs/conversion.pyx

@@ -920,7 +920,7 @@ def tz_localize_to_utc(ndarray[int64_t] vals, object tz, object ambiguous=None,
 
     trans, deltas, typ = get_dst_info(tz)
 
-    tdata = <int64_t*> cnp.PyArray_DATA(trans)
+    tdata = <int64_t*>cnp.PyArray_DATA(trans)
     ntrans = len(trans)
 
     # Determine whether each date lies left of the DST transition (store in

pandas/_libs/tslibs/period.pyx

@@ -1260,7 +1260,7 @@ cdef object _period_strftime(int64_t value, int freq, object fmt):
             fmt = fmt.replace(pat, repl)
             found_pat[i] = True
 
-    formatted = c_strftime(&dts, <char*> fmt)
+    formatted = c_strftime(&dts, <char*>fmt)
 
     result = util.char_to_string(formatted)
     free(formatted)