mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-08-03 16:39:00 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 8

Issue #16147: Rewrite PyUnicode_FromFormatV() to use _PyUnicodeWriter API

Browse source 
* Simplify the code: replace 4 steps with one unique step using the
   _PyUnicodeWriter API. PyUnicode_Format() has the same design. It avoids to
   store intermediate results which require to allocate an array of pointers on
   the heap.
 * Use the _PyUnicodeWriter API for speed (and its convinient API):
   overallocate the buffer to reduce the number of "realloc()"
 * Implement "width" and "precision" in Python, don't rely on sprintf(). It
   avoids to need of a temporary buffer allocated on the heap: only use a small
   buffer allocated in the stack.
 * Add _PyUnicodeWriter_WriteCstr() function
 * Split PyUnicode_FromFormatV() into two functions: add
   unicode_fromformat_arg().
 * Inline parse_format_flags(): the format of an argument is now only parsed
   once, it's no more needed to have a subfunction.
 * Optimize PyUnicode_FromFormatV() for characters between two "%" arguments:
   search the next "%" and copy the substring in one chunk, instead of copying
   character per character.
This commit is contained in:
Victor Stinner 2012-10-06 23:03:36 +02:00
parent 2a09b6e849
commit e215d960be
3 changed files with 380 additions and 500 deletions
Download patch file Download diff file Expand all files Collapse all files

16
Lib/test/test_unicode.py
View file

@ -1769,6 +1769,22 @@ class UnicodeTest(string_tests.CommonTest,
self.assertEqual(PyUnicode_FromFormat(b'%llu', c_ulonglong(123)), '123')
self.assertEqual(PyUnicode_FromFormat(b'%zu', c_size_t(123)), '123')
# test padding (width and/or precision)
self.assertEqual(PyUnicode_FromFormat(b'%010i', c_int(123)), '123'.rjust(10, '0'))
self.assertEqual(PyUnicode_FromFormat(b'%100i', c_int(123)), '123'.rjust(100))
self.assertEqual(PyUnicode_FromFormat(b'%.100i', c_int(123)), '123'.rjust(100, '0'))
self.assertEqual(PyUnicode_FromFormat(b'%100.80i', c_int(123)), '123'.rjust(80, '0').rjust(100))
self.assertEqual(PyUnicode_FromFormat(b'%010u', c_uint(123)), '123'.rjust(10, '0'))
self.assertEqual(PyUnicode_FromFormat(b'%100u', c_uint(123)), '123'.rjust(100))
self.assertEqual(PyUnicode_FromFormat(b'%.100u', c_uint(123)), '123'.rjust(100, '0'))
self.assertEqual(PyUnicode_FromFormat(b'%100.80u', c_uint(123)), '123'.rjust(80, '0').rjust(100))
self.assertEqual(PyUnicode_FromFormat(b'%010x', c_int(0x123)), '123'.rjust(10, '0'))
self.assertEqual(PyUnicode_FromFormat(b'%100x', c_int(0x123)), '123'.rjust(100))
self.assertEqual(PyUnicode_FromFormat(b'%.100x', c_int(0x123)), '123'.rjust(100, '0'))
self.assertEqual(PyUnicode_FromFormat(b'%100.80x', c_int(0x123)), '123'.rjust(80, '0').rjust(100))
# test %A
text = PyUnicode_FromFormat(b'%%A:%A', 'abc\xe9\uabcd\U0010ffff')
self.assertEqual(text, r"%A:'abc\xe9\uabcd\U0010ffff'")