CLN: Enable codespell for all files (#51804)

* CLN: enable codespell for all files

* Fix for all files

* Add cython and c

* add ignore words list

Author: luke396

.pre-commit-config.yaml

@@ -42,7 +42,7 @@ repos:
     rev: v2.2.2
     hooks:
     -   id: codespell
-        types_or: [python, rst, markdown]
+        types_or: [python, rst, markdown, cython, c]
         additional_dependencies: [tomli]
 -   repo: https://github.com/MarcoGorelli/cython-lint
     rev: v0.12.5

pandas/_libs/hashing.pyx

@@ -55,7 +55,7 @@ def hash_object_array(
         char **vecs
         char *cdata
         object val
-        list datas = []
+        list data_list = []
 
     k = <bytes>key.encode(encoding)
     kb = <uint8_t *>k
@@ -97,7 +97,7 @@ def hash_object_array(
 
         # keep the references alive through the end of the
         # function
-        datas.append(data)
+        data_list.append(data)
         vecs[i] = cdata
 
     result = np.empty(n, dtype=np.uint64)

pandas/_libs/lib.pyx

@@ -2650,7 +2650,7 @@ def maybe_convert_objects(ndarray[object] objects,
             seen.object_ = True
 
     if not convert_numeric:
-        # Note: we count "bool" as numeric here. This is becase
+        # Note: we count "bool" as numeric here. This is because
         #  np.array(list_of_items) will convert bools just like it will numeric
         #  entries.
         return objects

pandas/_libs/missing.pyx

@@ -52,7 +52,7 @@ cdef:
 cpdef bint check_na_tuples_nonequal(object left, object right):
     """
     When we have NA in one of the tuples but not the other we have to check here,
-    because our regular checks fail before with ambigous boolean value.
+    because our regular checks fail before with ambiguous boolean value.
 
     Parameters
     ----------

pandas/_libs/src/parser/tokenizer.c

@@ -1828,7 +1828,7 @@ char* _str_copy_decimal_str_c(const char *s, char **endpos, char decimal,
 double round_trip(const char *p, char **q, char decimal, char sci, char tsep,
                   int skip_trailing, int *error, int *maybe_int) {
     // 'normalize' representation to C-locale; replace decimal with '.' and
-    // remove t(housand)sep.
+    // remove thousands separator.
     char *endptr;
     char *pc = _str_copy_decimal_str_c(p, &endptr, decimal, tsep);
     // This is called from a nogil block in parsers.pyx

pandas/_libs/src/ujson/lib/ultrajson.h

@@ -187,7 +187,7 @@ typedef struct __JSONObjectEncoder {
                                 size_t *_outLen);
 
   /*
-  Begin iteration of an iteratable object (JS_ARRAY or JS_OBJECT)
+  Begin iteration of an iterable object (JS_ARRAY or JS_OBJECT)
   Implementor should setup iteration state in ti->prv
   */
   JSPFN_ITERBEGIN iterBegin;
@@ -199,7 +199,7 @@ typedef struct __JSONObjectEncoder {
   JSPFN_ITERNEXT iterNext;
 
   /*
-  Ends the iteration of an iteratable object.
+  Ends the iteration of an iterable object.
   Any iteration state stored in ti->prv can be freed here
   */
   JSPFN_ITEREND iterEnd;

pandas/_libs/testing.pyx

@@ -187,7 +187,7 @@ cpdef assert_almost_equal(a, b,
         return True
 
     if isna(a) and not isna(b) or not isna(a) and isna(b):
-        # boolean value of pd.NA is ambigous
+        # boolean value of pd.NA is ambiguous
         raise AssertionError(f"{a} != {b}")
 
     if a == b:

pandas/_libs/tslibs/timedeltas.pyx

@@ -1106,7 +1106,7 @@ cdef class _Timedelta(timedelta):
 
     def total_seconds(self) -> float:
         """Total seconds in the duration."""
-        # We need to override bc we overrided days/seconds/microseconds
+        # We need to override bc we overrode days/seconds/microseconds
         # TODO: add nanos/1e9?
         return self.days * 24 * 3600 + self.seconds + self.microseconds / 1_000_000
 

pandas/_libs/tslibs/timestamps.pyx

@@ -2344,7 +2344,7 @@ default 'raise'
         Monday == 1 ... Sunday == 7.
         """
         # same as super().isoweekday(), but that breaks because of how
-        #  we have overriden year, see note in create_timestamp_from_ts
+        #  we have overridden year, see note in create_timestamp_from_ts
         return self.weekday() + 1
 
     def weekday(self):
@@ -2354,7 +2354,7 @@ default 'raise'
         Monday == 0 ... Sunday == 6.
         """
         # same as super().weekday(), but that breaks because of how
-        #  we have overriden year, see note in create_timestamp_from_ts
+        #  we have overridden year, see note in create_timestamp_from_ts
         return ccalendar.dayofweek(self.year, self.month, self.day)
 
 

pyproject.toml

@@ -273,7 +273,7 @@ ignore = [
   "PLR2004",
   # Outer loop variable overwritten by inner assignment
   "PLW2901",
-  # Consider `elif` instead of `else` then `if` to remove indendation level
+  # Consider `elif` instead of `else` then `if` to remove indentation level
   "PLR5501",
 ]
 
@@ -607,5 +607,5 @@ exclude_lines = [
 directory = "coverage_html_report"
 
 [tool.codespell]
-ignore-words-list = "blocs, coo, hist, nd, sav, ser, recuse"
+ignore-words-list = "blocs, coo, hist, nd, sav, ser, recuse, nin, timere"
 ignore-regex = 'https://([\w/\.])+'