Skip to content

gh-97982: Reuse PyUnicode_Count in unicode_count #98025

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 10 commits into from
Oct 12, 2022
Merged

gh-97982: Reuse PyUnicode_Count in unicode_count #98025

Changes from 1 commit
Commits
Show all changes
10 commits
Select commit Hold shift + click to select a range
b239ae5
gh-97982: Reuse `PyUnicode_Count` in `unicode_count`
sobolevn Oct 7, 2022
e9d6358
Address review
sobolevn Oct 7, 2022
886d6e3
Update 2022-10-07-13-09-57.gh-issue-97982.6qR7Qm.rst
sobolevn Oct 7, 2022
482010a
Update 2022-10-07-13-09-57.gh-issue-97982.6qR7Qm.rst
sobolevn Oct 7, 2022
4b2447e
Use `assert()` for unicode objects
sobolevn Oct 7, 2022
35ecc77
Address review
sobolevn Oct 8, 2022
8270d4b
Merge branch 'main' into issue-97982
sobolevn Oct 12, 2022
2dabc73
Use `anylib_count` in `unicode_count_impl`
sobolevn Oct 12, 2022
74f8c1c
Revert "Use `anylib_count` in `unicode_count_impl`"
sobolevn Oct 12, 2022
69a94e2
Add a comment about `anylib_count`
sobolevn Oct 12, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
Revert "Use anylib_count in unicode_count_impl" 
This reverts commit 2dabc73.
  • Loading branch information
@sobolevn
sobolevn committed Oct 12, 2022
commit 74f8c1c564bd3d3ac28dd05faa6053980b8e4f95
56 changes: 37 additions & 19 deletions Objects/unicodeobject.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8964,21 +8964,6 @@ _PyUnicode_InsertThousandsGrouping(
return count;
}

static Py_ssize_t
anylib_count(int kind, PyObject *sstr, const void* sbuf, Py_ssize_t slen,
PyObject *str1, const void *buf1, Py_ssize_t len1, Py_ssize_t maxcount)
{
switch (kind) {
case PyUnicode_1BYTE_KIND:
return ucs1lib_count(sbuf, slen, buf1, len1, maxcount);
case PyUnicode_2BYTE_KIND:
return ucs2lib_count(sbuf, slen, buf1, len1, maxcount);
case PyUnicode_4BYTE_KIND:
return ucs4lib_count(sbuf, slen, buf1, len1, maxcount);
}
Py_UNREACHABLE();
}

static Py_ssize_t
unicode_count_impl(PyObject *str,
PyObject *substr,
Expand Down Expand Up @@ -9012,10 +8997,28 @@ unicode_count_impl(PyObject *str,
goto onError;
}

result = anylib_count(kind1,
str, buf1 + start, end - start,
substr, buf2, len2,
PY_SSIZE_T_MAX);
switch (kind1) {
case PyUnicode_1BYTE_KIND:
result = ucs1lib_count(
((const Py_UCS1*)buf1) + start, end - start,
buf2, len2, PY_SSIZE_T_MAX
);
break;
case PyUnicode_2BYTE_KIND:
result = ucs2lib_count(
((const Py_UCS2*)buf1) + start, end - start,
buf2, len2, PY_SSIZE_T_MAX
);
break;
case PyUnicode_4BYTE_KIND:
result = ucs4lib_count(
((const Py_UCS4*)buf1) + start, end - start,
buf2, len2, PY_SSIZE_T_MAX
);
break;
default:
Py_UNREACHABLE();
}

assert((kind2 != kind1) == (buf2 != PyUnicode_DATA(substr)));
if (kind2 != kind1)
Expand Down Expand Up @@ -9900,6 +9903,21 @@ anylib_find(int kind, PyObject *str1, const void *buf1, Py_ssize_t len1,
Py_UNREACHABLE();
}

static Py_ssize_t
anylib_count(int kind, PyObject *sstr, const void* sbuf, Py_ssize_t slen,
PyObject *str1, const void *buf1, Py_ssize_t len1, Py_ssize_t maxcount)
{
switch (kind) {
case PyUnicode_1BYTE_KIND:
return ucs1lib_count(sbuf, slen, buf1, len1, maxcount);
case PyUnicode_2BYTE_KIND:
return ucs2lib_count(sbuf, slen, buf1, len1, maxcount);
case PyUnicode_4BYTE_KIND:
return ucs4lib_count(sbuf, slen, buf1, len1, maxcount);
}
Py_UNREACHABLE();
}

static void
replace_1char_inplace(PyObject *u, Py_ssize_t pos,
Py_UCS4 u1, Py_UCS4 u2, Py_ssize_t maxcount)
Expand Down