Fix build warnings (#27157)

Author: pilkibun

pandas/_libs/groupby.pyx

@@ -260,7 +260,7 @@ def group_shift_indexer(int64_t[:] out, const int64_t[:] labels,
                         int ngroups, int periods):
     cdef:
         Py_ssize_t N, i, j, ii
-        int offset, sign
+        int offset = 0, sign
         int64_t lab, idxer, idxer_slot
         int64_t[:] label_seen = np.zeros(ngroups, dtype=np.int64)
         int64_t[:, :] label_indexer

pandas/_libs/hashtable.pxd

@@ -41,7 +41,7 @@ cdef class StringHashTable(HashTable):
 
 cdef struct Int64VectorData:
     int64_t *data
-    size_t n, m
+    Py_ssize_t n, m
 
 cdef class Int64Vector:
     cdef Int64VectorData *data

pandas/_libs/hashtable.pyx

@@ -44,7 +44,7 @@ cdef int64_t NPY_NAT = util.get_nat()
 _SIZE_HINT_LIMIT = (1 << 20) + 7
 
 
-cdef size_t _INIT_VEC_CAP = 128
+cdef Py_ssize_t _INIT_VEC_CAP = 128
 
 include "hashtable_class_helper.pxi"
 include "hashtable_func_helper.pxi"

pandas/_libs/hashtable_class_helper.pxi.in

@@ -659,7 +659,7 @@ 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 = <const char **>malloc(n * sizeof(char *))
         for i in range(n):
             val = values[i]
 

pandas/_libs/hashtable_func_helper.pxi.in

@@ -241,7 +241,7 @@ def ismember_{{dtype}}({{scalar}}[:] arr, {{scalar}}[:] values):
 
     # construct the table
     n = len(values)
-    kh_resize_{{ttype}}(table, min(n, len(values)))
+    kh_resize_{{ttype}}(table, n)
 
     {{if dtype == 'object'}}
     for i in range(n):

pandas/_libs/index.pyx

@@ -352,10 +352,10 @@ cdef class IndexEngine:
 
 cdef Py_ssize_t _bin_search(ndarray values, object val) except -1:
     cdef:
-        Py_ssize_t mid, lo = 0, hi = len(values) - 1
+        Py_ssize_t mid = 0, lo = 0, hi = len(values) - 1
         object pval
 
-    if hi >= 0 and val > util.get_value_at(values, hi):
+    if hi == 0 or (hi > 0 and val > util.get_value_at(values, hi)):
         return len(values)
 
     while lo < hi:

pandas/_libs/lib.pyx

@@ -480,7 +480,7 @@ def maybe_indices_to_slice(ndarray[int64_t] indices, int max_len):
 def maybe_booleans_to_slice(ndarray[uint8_t] mask):
     cdef:
         Py_ssize_t i, n = len(mask)
-        Py_ssize_t start, end
+        Py_ssize_t start = 0, end = 0
         bint started = 0, finished = 0
 
     for i in range(n):
@@ -1634,7 +1634,7 @@ def is_datetime_with_singletz_array(values: ndarray) -> bool:
     Doesn't check values are datetime-like types.
     """
     cdef:
-        Py_ssize_t i, j, n = len(values)
+        Py_ssize_t i = 0, j, n = len(values)
         object base_val, base_tz, val, tz
 
     if n == 0:
@@ -1916,8 +1916,8 @@ def maybe_convert_objects(ndarray[object] objects, bint try_float=0,
         ndarray[int64_t] ints
         ndarray[uint64_t] uints
         ndarray[uint8_t] bools
-        ndarray[int64_t] idatetimes
-        ndarray[int64_t] itimedeltas
+        int64_t[:]  idatetimes
+        int64_t[:] itimedeltas
         Seen seen = Seen()
         object val
         float64_t fval, fnan

pandas/_libs/src/parser/tokenizer.c

@@ -424,13 +424,13 @@ static void append_warning(parser_t *self, const char *msg) {
 
     if (self->warn_msg == NULL) {
         self->warn_msg = (char *)malloc(length + 1);
-        strncpy(self->warn_msg, msg, strlen(msg) + 1);
+        snprintf(self->warn_msg, length + 1, "%s", msg);
     } else {
         ex_length = strlen(self->warn_msg);
         newptr = safe_realloc(self->warn_msg, ex_length + length + 1);
         if (newptr != NULL) {
             self->warn_msg = (char *)newptr;
-            strncpy(self->warn_msg + ex_length, msg, strlen(msg) + 1);
+            snprintf(self->warn_msg + ex_length, length + 1, "%s", msg);
         }
     }
 }
@@ -1433,13 +1433,14 @@ PANDAS_INLINE void uppercase(char *p) {
 int to_boolean(const char *item, uint8_t *val) {
     char *tmp;
     int i, status = 0;
-    int bufsize = sizeof(char) * (strlen(item) + 1);
+    size_t length0 = (strlen(item) + 1);
+    int bufsize = length0;
 
     static const char *tstrs[1] = {"TRUE"};
     static const char *fstrs[1] = {"FALSE"};
 
     tmp = malloc(bufsize);
-    strncpy(tmp, item, bufsize);
+    snprintf(tmp,  length0, "%s", item);
     uppercase(tmp);
 
     for (i = 0; i < 1; ++i) {
@@ -1815,7 +1816,7 @@ double round_trip(const char *p, char **q, char decimal, char sci, char tsep,
     double r = PyOS_string_to_double(p, q, 0);
     if (maybe_int != NULL) *maybe_int = 0;
     if (PyErr_Occurred() != NULL) *error = -1;
-    else if (r == Py_HUGE_VAL) *error = Py_HUGE_VAL;
+    else if (r == Py_HUGE_VAL) *error = (int)Py_HUGE_VAL;
     PyErr_Clear();
     return r;
 }