FazBrowse GitHub Viewer | Trending |
URL:
| Home
Tools: [Download Repo ZIP]   [Original HTTPS Page]

gh-158451: Reuse PyUnicodeWriter_WriteStr() in PyUnicode_Format() by vstinner · Pull Request #158467 · python/cpython · GitHub

  1. python
  2. cpython

Repository navigation

gh-158451: Reuse PyUnicodeWriter_WriteStr() in PyUnicode_Format() #158467

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
vstinner merged 1 commit into from
Sep 30, 2026
Conversation 0 Commits 1 Checks 53 Files changed
Merged

gh-158451: Reuse PyUnicodeWriter_WriteStr() in PyUnicode_Format() #158467

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension .c  (2) .py  (1) All 2 file types selected
Viewed files
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Unified
Split
Hide whitespace
Diff view
Unified
Split
Hide whitespace
15 changes: 15 additions & 0 deletions Lib/test/test_format.py
Show comments
View file
Open in desktop
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode characters
Show hidden characters
Original file line number Diff line number Diff line change
Expand Up @@ -240,6 +240,8 @@ def test_common_format(self):
testcommon("%d", 42, "42")
testcommon("%d", -42, "-42")
testcommon("%d", 42.0, "42")
testcommon("%#d", 42, "42")
testcommon("%#d", -42, "-42")
testcommon("%#x", 1, "0x1")
testcommon("%#X", 1, "0X1")
testcommon("%#o", 1, "0o1")
Expand All @@ -250,8 +252,12 @@ def test_common_format(self):
testcommon("%#X", 0, "0X0")
testcommon("%x", 0x42, "42")
testcommon("%x", -0x42, "-42")
testcommon("%#x", 0x42, "0x42")
testcommon("%#x", -0x42, "-0x42")
testcommon("%o", 0o42, "42")
testcommon("%o", -0o42, "-42")
testcommon("%#o", 0o42, "0o42")
testcommon("%#o", -0o42, "-0o42")
# alternate float formatting
testcommon('%g', 1.1, '1.1')
testcommon('%#g', 1.1, '1.10000')
Expand Down Expand Up @@ -344,12 +350,21 @@ def test_common_format(self):
"format argument 1: %g requires a real number, not str")

def test_str_format(self):
testformat("%s", "abc", "abc")
testformat("%r", "\u0378", "'\\u0378'") # non printable
testformat("%a", "\u0378", "'\\u0378'") # non printable
testformat("%r", "\u0374", "'\u0374'") # printable
testformat("%a", "\u0374", "'\\u0374'") # printable
testformat('%(x)r', {'x': 1}, '1')

# Some small ints
for fmt in ('s', 'r', 'a'):
with self.subTest(fmt=fmt):
testformat("%" + fmt, 42, "42")
testformat("%#" + fmt, 42, "42")
testformat("%" + fmt, -42, "-42")
testformat("%#" + fmt, -42, "-42")

# Test exception for unknown format characters, etc.
if verbose:
print('Testing exceptions')
Expand Down
38 changes: 22 additions & 16 deletions Objects/unicode_format.c
Show comments
View file
Open in desktop
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode characters
Show hidden characters
Original file line number Diff line number Diff line change
Expand Up @@ -571,6 +571,7 @@ unicode_format_arg_parse(struct unicode_formatter_t *ctx,
arg->ch = FORMAT_READ(ctx);
ctx->fmtpos++;
}
assert(arg->width >= 0);
}
else if (arg->ch >= '0' && arg->ch <= '9') {
arg->width = arg->ch - '0';
Expand All @@ -590,6 +591,7 @@ unicode_format_arg_parse(struct unicode_formatter_t *ctx,
}
arg->width = arg->width*10 + (arg->ch - '0');
}
assert(arg->width >= 0);
}

/* Parse precision. Example: "%.3f" => prec=3 */
Expand Down Expand Up @@ -645,6 +647,7 @@ unicode_format_arg_parse(struct unicode_formatter_t *ctx,
arg->prec = arg->prec*10 + (arg->ch - '0');
}
}
assert(arg->prec >= 0);
}

/* Ignore "h", "l" and "L" format prefix (ex: "%hi" or "%ls") */
Expand Down Expand Up @@ -701,24 +704,27 @@ unicode_format_arg_format(struct unicode_formatter_t *ctx,
case 's':
case 'r':
case 'a':
if (PyLong_CheckExact(v) && arg->width == -1 && arg->prec == -1) {
/* Fast path */
if (_PyLong_FormatWriter(writer, v, 10, arg->flags & F_ALT) == -1)
return -1;
return 1;
if (arg->width < 0 && arg->prec < 0) {
if (arg->ch == 's') {
if (PyUnicodeWriter_WriteStr((PyUnicodeWriter*)writer, v) < 0) {
return -1;
}
return 1;
}
else if (arg->ch == 'r') {
if (PyUnicodeWriter_WriteRepr((PyUnicodeWriter*)writer, v) < 0) {
return -1;
}
return 1;
}
}

if (PyUnicode_CheckExact(v) && arg->ch == 's') {
*p_str = Py_NewRef(v);
}
else {
if (arg->ch == 's')
*p_str = PyObject_Str(v);
else if (arg->ch == 'r')
*p_str = PyObject_Repr(v);
else
*p_str = PyObject_ASCII(v);
}
if (arg->ch == 's')
*p_str = PyObject_Str(v);
else if (arg->ch == 'r')
*p_str = PyObject_Repr(v);
else
*p_str = PyObject_ASCII(v);
break;

case 'i':
Expand Down
18 changes: 10 additions & 8 deletions Objects/unicode_writer.c
Show comments
View file
Open in desktop
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode characters
Show hidden characters
Original file line number Diff line number Diff line change
Expand Up @@ -285,45 +285,47 @@ _PyUnicodeWriter_WriteStr(_PyUnicodeWriter *writer, PyObject *str)


int
PyUnicodeWriter_WriteStr(PyUnicodeWriter *writer, PyObject *obj)
PyUnicodeWriter_WriteStr(PyUnicodeWriter *pub_writer, PyObject *obj)
{
_PyUnicodeWriter *writer = (_PyUnicodeWriter*)pub_writer;
PyTypeObject *type = Py_TYPE(obj);
if (type == &PyUnicode_Type) {
return _PyUnicodeWriter_WriteStr((_PyUnicodeWriter*)writer, obj);
return _PyUnicodeWriter_WriteStr(writer, obj);
}

if (type == &PyLong_Type) {
return _PyLong_FormatWriter((_PyUnicodeWriter*)writer, obj, 10, 0);
return _PyLong_FormatWriter(writer, obj, 10, 0);
}

PyObject *str = PyObject_Str(obj);
if (str == NULL) {
return -1;
}

int res = _PyUnicodeWriter_WriteStr((_PyUnicodeWriter*)writer, str);
int res = _PyUnicodeWriter_WriteStr(writer, str);
Py_DECREF(str);
return res;
}


int
PyUnicodeWriter_WriteRepr(PyUnicodeWriter *writer, PyObject *obj)
PyUnicodeWriter_WriteRepr(PyUnicodeWriter *pub_writer, PyObject *obj)
{
_PyUnicodeWriter *writer = (_PyUnicodeWriter*)pub_writer;
if (obj == NULL) {
return _PyUnicodeWriter_WriteASCIIString((_PyUnicodeWriter*)writer, "<NULL>", 6);
return _PyUnicodeWriter_WriteASCIIString(writer, "<NULL>", 6);
}

if (Py_TYPE(obj) == &PyLong_Type) {
return _PyLong_FormatWriter((_PyUnicodeWriter*)writer, obj, 10, 0);
return _PyLong_FormatWriter(writer, obj, 10, 0);
}

PyObject *repr = PyObject_Repr(obj);
if (repr == NULL) {
return -1;
}

int res = _PyUnicodeWriter_WriteStr((_PyUnicodeWriter*)writer, repr);
int res = _PyUnicodeWriter_WriteStr(writer, repr);
Py_DECREF(repr);
return res;
}
Expand Down
Loading
Back | FazBrowse Home | New Git URL