Jared Hancock 2024-04-26 17:56:50 -05:00 zatwierdzone przez GitHub
commit 4bcaf88c22
Nie znaleziono w bazie danych klucza dla tego podpisu
ID klucza GPG: B5690EEEBB952194
5 zmienionych plików z 221 dodań i 5 usunięć

Wyświetl plik

@ -140,6 +140,12 @@ Functions
Note: availability of this function depends on :term:`MicroPython port`.
.. function:: finditer(regex_str, string)
Return an iterator yielding ``Match`` objects over all non-overlapping
matches for the RE *regex_str* in *string*. The string is scanned
left-to-right, and matches are returned in the order found.
.. data:: DEBUG
Flag value, display debug information about compiled expression.
@ -154,15 +160,26 @@ Regex objects
Compiled regular expression. Instances of this class are created using
`re.compile()`.
.. method:: regex.match(string)
regex.search(string)
.. method:: regex.match(string, [pos, [endpos]])
regex.search(string, [pos, [endpos]])
regex.finditer(string, [pos, [endpos]])
regex.sub(replace, string, count=0, flags=0, /)
Similar to the module-level functions :meth:`match`, :meth:`search`
and :meth:`sub`.
Similar to the module-level functions :meth:`match`, :meth:`search`,
:meth:`finditer`, and :meth:`sub`.
Using methods is (much) more efficient if the same regex is applied to
multiple strings.
The optional second parameter *pos* gives an index in the string where the
search is to start; it defaults to ``0``. This is not completely equivalent
to slicing the string; the ``'^'`` pattern character matches at the real
beginning of the string and at positions just after a newline, but not
necessarily at the index where the search is to start.
The optional parameter *endpos* limits how far the string will be searched;
it will be as if the string is *endpos* characters long, so only the
characters from *pos* to ``endpos - 1`` will be searched for a match.
.. method:: regex.split(string, max_split=-1, /)
Split a *string* using regex. If *max_split* is given, it specifies

Wyświetl plik

@ -195,10 +195,11 @@ static void re_print(const mp_print_t *print, mp_obj_t self_in, mp_print_kind_t
}
static mp_obj_t re_exec(bool is_anchored, uint n_args, const mp_obj_t *args) {
(void)n_args;
mp_obj_re_t *self;
bool was_compiled = false;
if (mp_obj_is_type(args[0], (mp_obj_type_t *)&re_type)) {
self = MP_OBJ_TO_PTR(args[0]);
was_compiled = true;
} else {
self = MP_OBJ_TO_PTR(mod_re_compile(1, args));
}
@ -206,6 +207,30 @@ static mp_obj_t re_exec(bool is_anchored, uint n_args, const mp_obj_t *args) {
size_t len;
subj.begin_line = subj.begin = mp_obj_str_get_data(args[1], &len);
subj.end = subj.begin + len;
if (was_compiled && n_args > 2) {
// Arg #2 is starting-pos
mp_int_t startpos = mp_obj_get_int(args[2]);
if (startpos > (mp_int_t) len) {
startpos = len;
}
else if (startpos < 0) {
startpos = 0;
}
subj.begin += startpos;
if (n_args > 3) {
// Arg #3 is ending-pos
mp_int_t endpos = mp_obj_get_int(args[3]);
if (endpos > (mp_int_t) len) {
endpos = len;
}
else if (endpos < startpos) {
endpos = startpos;
}
subj.end = subj.begin_line + endpos;
}
}
int caps_num = (self->re.sub + 1) * 2;
mp_obj_match_t *match = m_new_obj_var(mp_obj_match_t, caps, char *, caps_num);
// cast is a workaround for a bug in msvc: it treats const char** as a const pointer instead of a pointer to pointer to const char
@ -400,11 +425,75 @@ MP_DEFINE_CONST_FUN_OBJ_VAR_BETWEEN(re_sub_obj, 3, 5, re_sub_helper);
#endif
#if MICROPY_PY_RE_FINDITER
typedef struct _mp_re_finditer_it_t {
mp_obj_base_t base;
mp_fun_1_t iternext;
mp_obj_t pattern;
mp_obj_t str;
mp_obj_t start;
mp_obj_t end;
} mp_re_finditer_it_t;
static mp_obj_t mp_re_finditer_it_iternext(mp_obj_t self_in) {
mp_re_finditer_it_t *self = MP_OBJ_TO_PTR(self_in);
mp_obj_t args[4] = {
self->pattern,
self->str,
self->start,
self->end
};
int n_args = (self->end == mp_const_none) ? 3 : 4;
mp_obj_t obj_match = re_exec(false, n_args, args);
if (obj_match == mp_const_none) {
return MP_OBJ_STOP_ITERATION;
}
mp_obj_match_t *match = MP_OBJ_TO_PTR(obj_match);
const char *begin = mp_obj_str_get_str(self->str);
self->start = MP_OBJ_NEW_SMALL_INT(match->caps[1] - begin);
return obj_match;
}
static mp_obj_t re_finditer(size_t n_args, const mp_obj_t *args) {
mp_re_finditer_it_t *iter = mp_obj_malloc(mp_re_finditer_it_t, &mp_type_polymorph_iter);
iter->iternext = mp_re_finditer_it_iternext;
iter->str = args[1];
iter->start = MP_OBJ_NEW_SMALL_INT(0);
iter->end = mp_const_none;
if (mp_obj_is_type(args[0], (mp_obj_type_t *)&re_type)) {
iter->pattern = args[0];
if (n_args > 2) {
iter->start = args[2];
if (n_args > 3) {
iter->end = args[3];
}
}
}
else {
iter->pattern = mod_re_compile(1, args);
}
return MP_OBJ_FROM_PTR(iter);
}
MP_DEFINE_CONST_FUN_OBJ_VAR_BETWEEN(re_finditer_obj, 2, 4, re_finditer);
#endif // MICROPY_PY_RE_FINDITER
#if !MICROPY_ENABLE_DYNRUNTIME
static const mp_rom_map_elem_t re_locals_dict_table[] = {
{ MP_ROM_QSTR(MP_QSTR_match), MP_ROM_PTR(&re_match_obj) },
{ MP_ROM_QSTR(MP_QSTR_search), MP_ROM_PTR(&re_search_obj) },
{ MP_ROM_QSTR(MP_QSTR_split), MP_ROM_PTR(&re_split_obj) },
#if MICROPY_PY_RE_FINDITER
{ MP_ROM_QSTR(MP_QSTR_finditer), MP_ROM_PTR(&re_finditer_obj) },
#endif
#if MICROPY_PY_RE_SUB
{ MP_ROM_QSTR(MP_QSTR_sub), MP_ROM_PTR(&re_sub_obj) },
#endif
@ -455,6 +544,9 @@ static const mp_rom_map_elem_t mp_module_re_globals_table[] = {
{ MP_ROM_QSTR(MP_QSTR_compile), MP_ROM_PTR(&mod_re_compile_obj) },
{ MP_ROM_QSTR(MP_QSTR_match), MP_ROM_PTR(&re_match_obj) },
{ MP_ROM_QSTR(MP_QSTR_search), MP_ROM_PTR(&re_search_obj) },
#if MICROPY_PY_RE_FINDITER
{ MP_ROM_QSTR(MP_QSTR_finditer), MP_ROM_PTR(&re_finditer_obj) },
#endif
#if MICROPY_PY_RE_SUB
{ MP_ROM_QSTR(MP_QSTR_sub), MP_ROM_PTR(&re_sub_obj) },
#endif

Wyświetl plik

@ -1663,6 +1663,10 @@ typedef double mp_float_t;
#define MICROPY_PY_RE_MATCH_SPAN_START_END (MICROPY_CONFIG_ROM_LEVEL_AT_LEAST_EVERYTHING)
#endif
#ifndef MICROPY_PY_RE_FINDITER
#define MICROPY_PY_RE_FINDITER (MICROPY_CONFIG_ROM_LEVEL_AT_LEAST_EXTRA_FEATURES)
#endif
#ifndef MICROPY_PY_RE_SUB
#define MICROPY_PY_RE_SUB (MICROPY_CONFIG_ROM_LEVEL_AT_LEAST_EXTRA_FEATURES)
#endif

Wyświetl plik

@ -0,0 +1,25 @@
try:
import re
from re import finditer
except ImportError:
print("SKIP")
raise SystemExit
ms = re.finditer(r"f[a-z]*", "which foot or hand fell fastest")
print(list(x.group(0) for x in ms))
p = re.compile(r"f[a-z]*")
ms = p.finditer("which foot or hand fell fastest")
print(list(x.group(0) for x in ms))
ms = p.finditer("which foot or hand fell fastest", 10)
print(list(x.group(0) for x in ms))
ms = p.finditer("which foot or hand fell fastest", 10, 21)
print(list(x.group(0) for x in ms))
ms = re.finditer(r"\s+", "which foot or hand fell fastest")
print(list(x.group(0) for x in ms))
ms = re.finditer(r"zz", "which foot or hand fell fastest")
print(list(x.group(0) for x in ms))

Wyświetl plik

@ -0,0 +1,78 @@
# test start and end pos specification
try:
import re
except ImportError:
print("SKIP")
raise SystemExit
def print_groups(match):
print("----")
try:
if match is not None:
i = 0
while True:
print(match.group(i))
i += 1
except IndexError:
pass
p = re.compile(r"o")
m = p.match("dog")
print_groups(m)
m = p.match("dog", 1)
print_groups(m)
m = p.match("dog", 2)
print_groups(m)
# No match past end of input
m = p.match("dog", 5)
print_groups(m)
m = p.match("dog", 0, 1)
print_groups(m)
# Caret only matches the actual beginning
p = re.compile(r"^o")
m = p.match("dog", 1)
print_groups(m)
# End at beginning means searching empty string
p = re.compile(r"o")
m = p.match("dog", 1, 1)
print_groups(m)
# End before the beginning doesn't match anything
m = p.match("dog", 2, 1)
print_groups(m)
# Negative starting values don't crash
m = p.search("dog", -2)
print_groups(m)
m = p.search("dog", -2, -5)
print_groups(m)
# Search also works
print("--search")
p = re.compile(r"o")
m = p.search("dog")
print_groups(m)
m = p.search("dog", 1)
print_groups(m)
m = p.search("dog", 2)
print_groups(m)
# Negative starting values don't crash
m = p.search("dog", -2)
print_groups(m)
m = p.search("dog", -2, -5)
print_groups(m)