cpython/Objects/stringlib/split.h

/* stringlib: split implementation */

#ifndef STRINGLIB_FASTSEARCH_H
#error must include "stringlib/fastsearch.h" before including this module
#endif

/* Overallocate the initial list to reduce the number of reallocs for small
   split sizes.  Eg, "A A A A A A A A A A".split() (10 elements) has three
   resizes, to sizes 4, 8, then 16.  Most observed string splits are for human
   text (roughly 11 words per line) and field delimited data (usually 1-10
   fields).  For large strings the split algorithms are bandwidth limited
   so increasing the preallocation likely will not improve things.*/

#define MAX_PREALLOC …

/* 5 splits gives 6 elements */
#define PREALLOC_SIZE(maxsplit) …

#define SPLIT_APPEND(data, left, right) …

#define SPLIT_ADD(data, left, right) …


/* Always force the list to the expected size. */
#define FIX_PREALLOC_SIZE(list) …

Py_LOCAL_INLINE(PyObject *)
STRINGLIB(split_whitespace)(PyObject* str_obj,
                           const STRINGLIB_CHAR* str, Py_ssize_t str_len,
                           Py_ssize_t maxcount)
{ … }

Py_LOCAL_INLINE(PyObject *)
STRINGLIB(split_char)(PyObject* str_obj,
                     const STRINGLIB_CHAR* str, Py_ssize_t str_len,
                     const STRINGLIB_CHAR ch,
                     Py_ssize_t maxcount)
{ … }

Py_LOCAL_INLINE(PyObject *)
STRINGLIB(split)(PyObject* str_obj,
                const STRINGLIB_CHAR* str, Py_ssize_t str_len,
                const STRINGLIB_CHAR* sep, Py_ssize_t sep_len,
                Py_ssize_t maxcount)
{ … }

Py_LOCAL_INLINE(PyObject *)
STRINGLIB(rsplit_whitespace)(PyObject* str_obj,
                            const STRINGLIB_CHAR* str, Py_ssize_t str_len,
                            Py_ssize_t maxcount)
{ … }

Py_LOCAL_INLINE(PyObject *)
STRINGLIB(rsplit_char)(PyObject* str_obj,
                      const STRINGLIB_CHAR* str, Py_ssize_t str_len,
                      const STRINGLIB_CHAR ch,
                      Py_ssize_t maxcount)
{ … }

Py_LOCAL_INLINE(PyObject *)
STRINGLIB(rsplit)(PyObject* str_obj,
                 const STRINGLIB_CHAR* str, Py_ssize_t str_len,
                 const STRINGLIB_CHAR* sep, Py_ssize_t sep_len,
                 Py_ssize_t maxcount)
{ … }

Py_LOCAL_INLINE(PyObject *)
STRINGLIB(splitlines)(PyObject* str_obj,
                     const STRINGLIB_CHAR* str, Py_ssize_t str_len,
                     int keepends)
{ … }