mirror of
https://github.com/python/cpython.git
synced 2025-08-30 21:48:47 +00:00

* Add _zstd module for https://peps.python.org/pep-0784/ This commit introduces the `_zstd` module, with bindings to libzstd from the pyzstd project. It also includes the unix build system configuration. Windows build system support will be integrated independently as it depends on integration with cpython-source-deps. * Add _zstd to modules * Fix path for compression.zstd module * Ignore _zstd module like _io * Expand module state macros to improve code quality Also removes module state references from the classes in the _zstd module and instead uses PyType_GetModuleState() * Remove backticks suggested in review Co-authored-by: Stan Ulbrych <89152624+StanFromIreland@users.noreply.github.com> * Use critical sections to lock object state This should avoid races and deadlocks. * Remove compress/decompress and mark module as not reliant on the GIL The `compress`/`decompress` functions will be moved to Python code for simplicity. C implementations can always be re-added in the future. Also, mark _zstd as not requiring the GIL. * Lift critical section to avoid clang warning * Respond to comments by picnixz * Call out pyzstd explicitly in license description Co-authored-by: Adam Turner <9087854+AA-Turner@users.noreply.github.com> * Use a much more robust implementation... ... for `get_zstd_state_from_type` Co-authored-by: Bénédikt Tran <10796600+picnixz@users.noreply.github.com> * Use PyList_GetItemRef for thread safety purposes * Use a macro for the minimum supported version * remove const from primivite types * Use PyMem_New in another spot * Simplify error handling in _get_frame_size * Another simplification of error handling in get_frame_info * Rename _module_state to mod_state * Rewrite comment explaining the context of the code * Add link to pyzstd * Add TODO about refactoring dict training code * Use PyModule_AddObjectRef over PyModule_AddObject PyModule_AddObject is soft-deprecated, so we should use PyModule_AddObjectRef * Check result of OutputBufferGrow * Simplify return logic in `add_constant_to_type` Co-authored-by: Bénédikt Tran <10796600+picnixz@users.noreply.github.com> * Ignore return value of _zstd_clear() Co-authored-by: Bénédikt Tran <10796600+picnixz@users.noreply.github.com> * Remove redundant comments * Remove __reduce__ from ZstdDict We should instead document that to pickle a dictionary a user should use the `.dict_content` attribute. * Use PyUnicode_FromFormat instead of a buffer * Don't use C constants/types in error messages * Make error messages easier to understand for Python users * Lower minimum required version 1.4.0 * Use casts and make slot function signatures correct * Be consistent with CPython on const usage * Make else clauses in line with PEP 7 * Fix over-indented blocks in argument clinic * Add critical section around ZSTD_DCtx_setParameter * Add a TODO about refactoring critical sections * Use Py_UNREACHABLE * Move bytes operations out of Py_BEGIN_ALLOW_THREADS * Add TODO about ensuring a lock is held * Remove asserts that may not be correct * Add TODO to make ZstdDict and others GC objects * Make objects GC tracked * Remove unused include * Fix some memory issues * Fix refleaks on module and in ZstdDict * Update configure to check for ZDICT_finalizeDictionary * Properly check version in configure * exit(1) if check fails * Use AC_RUN_IFELSE * Use a define() to re-use version check * Actually properly set _zstd module status based on version --------- Co-authored-by: Stan Ulbrych <89152624+StanFromIreland@users.noreply.github.com> Co-authored-by: Adam Turner <9087854+AA-Turner@users.noreply.github.com> Co-authored-by: Bénédikt Tran <10796600+picnixz@users.noreply.github.com>
230 lines
7.8 KiB
C
Generated
230 lines
7.8 KiB
C
Generated
/*[clinic input]
|
|
preserve
|
|
[clinic start generated code]*/
|
|
|
|
#if defined(Py_BUILD_CORE) && !defined(Py_BUILD_CORE_MODULE)
|
|
# include "pycore_gc.h" // PyGC_Head
|
|
# include "pycore_runtime.h" // _Py_ID()
|
|
#endif
|
|
#include "pycore_abstract.h" // _PyNumber_Index()
|
|
#include "pycore_critical_section.h"// Py_BEGIN_CRITICAL_SECTION()
|
|
#include "pycore_modsupport.h" // _PyArg_UnpackKeywords()
|
|
|
|
PyDoc_STRVAR(_zstd_ZstdDecompressor___init____doc__,
|
|
"ZstdDecompressor(zstd_dict=None, options=None)\n"
|
|
"--\n"
|
|
"\n"
|
|
"Create a decompressor object for decompressing data incrementally.\n"
|
|
"\n"
|
|
" zstd_dict\n"
|
|
" A ZstdDict object, a pre-trained zstd dictionary.\n"
|
|
" options\n"
|
|
" A dict object that contains advanced decompression parameters.\n"
|
|
"\n"
|
|
"Thread-safe at method level. For one-shot decompression, use the decompress()\n"
|
|
"function instead.");
|
|
|
|
static int
|
|
_zstd_ZstdDecompressor___init___impl(ZstdDecompressor *self,
|
|
PyObject *zstd_dict, PyObject *options);
|
|
|
|
static int
|
|
_zstd_ZstdDecompressor___init__(PyObject *self, PyObject *args, PyObject *kwargs)
|
|
{
|
|
int return_value = -1;
|
|
#if defined(Py_BUILD_CORE) && !defined(Py_BUILD_CORE_MODULE)
|
|
|
|
#define NUM_KEYWORDS 2
|
|
static struct {
|
|
PyGC_Head _this_is_not_used;
|
|
PyObject_VAR_HEAD
|
|
Py_hash_t ob_hash;
|
|
PyObject *ob_item[NUM_KEYWORDS];
|
|
} _kwtuple = {
|
|
.ob_base = PyVarObject_HEAD_INIT(&PyTuple_Type, NUM_KEYWORDS)
|
|
.ob_hash = -1,
|
|
.ob_item = { &_Py_ID(zstd_dict), &_Py_ID(options), },
|
|
};
|
|
#undef NUM_KEYWORDS
|
|
#define KWTUPLE (&_kwtuple.ob_base.ob_base)
|
|
|
|
#else // !Py_BUILD_CORE
|
|
# define KWTUPLE NULL
|
|
#endif // !Py_BUILD_CORE
|
|
|
|
static const char * const _keywords[] = {"zstd_dict", "options", NULL};
|
|
static _PyArg_Parser _parser = {
|
|
.keywords = _keywords,
|
|
.fname = "ZstdDecompressor",
|
|
.kwtuple = KWTUPLE,
|
|
};
|
|
#undef KWTUPLE
|
|
PyObject *argsbuf[2];
|
|
PyObject * const *fastargs;
|
|
Py_ssize_t nargs = PyTuple_GET_SIZE(args);
|
|
Py_ssize_t noptargs = nargs + (kwargs ? PyDict_GET_SIZE(kwargs) : 0) - 0;
|
|
PyObject *zstd_dict = Py_None;
|
|
PyObject *options = Py_None;
|
|
|
|
fastargs = _PyArg_UnpackKeywords(_PyTuple_CAST(args)->ob_item, nargs, kwargs, NULL, &_parser,
|
|
/*minpos*/ 0, /*maxpos*/ 2, /*minkw*/ 0, /*varpos*/ 0, argsbuf);
|
|
if (!fastargs) {
|
|
goto exit;
|
|
}
|
|
if (!noptargs) {
|
|
goto skip_optional_pos;
|
|
}
|
|
if (fastargs[0]) {
|
|
zstd_dict = fastargs[0];
|
|
if (!--noptargs) {
|
|
goto skip_optional_pos;
|
|
}
|
|
}
|
|
options = fastargs[1];
|
|
skip_optional_pos:
|
|
return_value = _zstd_ZstdDecompressor___init___impl((ZstdDecompressor *)self, zstd_dict, options);
|
|
|
|
exit:
|
|
return return_value;
|
|
}
|
|
|
|
PyDoc_STRVAR(_zstd_ZstdDecompressor_unused_data__doc__,
|
|
"A bytes object of un-consumed input data.\n"
|
|
"\n"
|
|
"When ZstdDecompressor object stops after a frame is\n"
|
|
"decompressed, unused input data after the frame. Otherwise this will be b\'\'.");
|
|
#if defined(_zstd_ZstdDecompressor_unused_data_DOCSTR)
|
|
# undef _zstd_ZstdDecompressor_unused_data_DOCSTR
|
|
#endif
|
|
#define _zstd_ZstdDecompressor_unused_data_DOCSTR _zstd_ZstdDecompressor_unused_data__doc__
|
|
|
|
#if !defined(_zstd_ZstdDecompressor_unused_data_DOCSTR)
|
|
# define _zstd_ZstdDecompressor_unused_data_DOCSTR NULL
|
|
#endif
|
|
#if defined(_ZSTD_ZSTDDECOMPRESSOR_UNUSED_DATA_GETSETDEF)
|
|
# undef _ZSTD_ZSTDDECOMPRESSOR_UNUSED_DATA_GETSETDEF
|
|
# define _ZSTD_ZSTDDECOMPRESSOR_UNUSED_DATA_GETSETDEF {"unused_data", (getter)_zstd_ZstdDecompressor_unused_data_get, (setter)_zstd_ZstdDecompressor_unused_data_set, _zstd_ZstdDecompressor_unused_data_DOCSTR},
|
|
#else
|
|
# define _ZSTD_ZSTDDECOMPRESSOR_UNUSED_DATA_GETSETDEF {"unused_data", (getter)_zstd_ZstdDecompressor_unused_data_get, NULL, _zstd_ZstdDecompressor_unused_data_DOCSTR},
|
|
#endif
|
|
|
|
static PyObject *
|
|
_zstd_ZstdDecompressor_unused_data_get_impl(ZstdDecompressor *self);
|
|
|
|
static PyObject *
|
|
_zstd_ZstdDecompressor_unused_data_get(PyObject *self, void *Py_UNUSED(context))
|
|
{
|
|
PyObject *return_value = NULL;
|
|
|
|
Py_BEGIN_CRITICAL_SECTION(self);
|
|
return_value = _zstd_ZstdDecompressor_unused_data_get_impl((ZstdDecompressor *)self);
|
|
Py_END_CRITICAL_SECTION();
|
|
|
|
return return_value;
|
|
}
|
|
|
|
PyDoc_STRVAR(_zstd_ZstdDecompressor_decompress__doc__,
|
|
"decompress($self, /, data, max_length=-1)\n"
|
|
"--\n"
|
|
"\n"
|
|
"Decompress *data*, returning uncompressed bytes if possible, or b\'\' otherwise.\n"
|
|
"\n"
|
|
" data\n"
|
|
" A bytes-like object, zstd data to be decompressed.\n"
|
|
" max_length\n"
|
|
" Maximum size of returned data. When it is negative, the size of\n"
|
|
" output buffer is unlimited. When it is nonnegative, returns at\n"
|
|
" most max_length bytes of decompressed data.\n"
|
|
"\n"
|
|
"If *max_length* is nonnegative, returns at most *max_length* bytes of\n"
|
|
"decompressed data. If this limit is reached and further output can be\n"
|
|
"produced, *self.needs_input* will be set to ``False``. In this case, the next\n"
|
|
"call to *decompress()* may provide *data* as b\'\' to obtain more of the output.\n"
|
|
"\n"
|
|
"If all of the input data was decompressed and returned (either because this\n"
|
|
"was less than *max_length* bytes, or because *max_length* was negative),\n"
|
|
"*self.needs_input* will be set to True.\n"
|
|
"\n"
|
|
"Attempting to decompress data after the end of a frame is reached raises an\n"
|
|
"EOFError. Any data found after the end of the frame is ignored and saved in\n"
|
|
"the self.unused_data attribute.");
|
|
|
|
#define _ZSTD_ZSTDDECOMPRESSOR_DECOMPRESS_METHODDEF \
|
|
{"decompress", _PyCFunction_CAST(_zstd_ZstdDecompressor_decompress), METH_FASTCALL|METH_KEYWORDS, _zstd_ZstdDecompressor_decompress__doc__},
|
|
|
|
static PyObject *
|
|
_zstd_ZstdDecompressor_decompress_impl(ZstdDecompressor *self,
|
|
Py_buffer *data,
|
|
Py_ssize_t max_length);
|
|
|
|
static PyObject *
|
|
_zstd_ZstdDecompressor_decompress(PyObject *self, PyObject *const *args, Py_ssize_t nargs, PyObject *kwnames)
|
|
{
|
|
PyObject *return_value = NULL;
|
|
#if defined(Py_BUILD_CORE) && !defined(Py_BUILD_CORE_MODULE)
|
|
|
|
#define NUM_KEYWORDS 2
|
|
static struct {
|
|
PyGC_Head _this_is_not_used;
|
|
PyObject_VAR_HEAD
|
|
Py_hash_t ob_hash;
|
|
PyObject *ob_item[NUM_KEYWORDS];
|
|
} _kwtuple = {
|
|
.ob_base = PyVarObject_HEAD_INIT(&PyTuple_Type, NUM_KEYWORDS)
|
|
.ob_hash = -1,
|
|
.ob_item = { &_Py_ID(data), &_Py_ID(max_length), },
|
|
};
|
|
#undef NUM_KEYWORDS
|
|
#define KWTUPLE (&_kwtuple.ob_base.ob_base)
|
|
|
|
#else // !Py_BUILD_CORE
|
|
# define KWTUPLE NULL
|
|
#endif // !Py_BUILD_CORE
|
|
|
|
static const char * const _keywords[] = {"data", "max_length", NULL};
|
|
static _PyArg_Parser _parser = {
|
|
.keywords = _keywords,
|
|
.fname = "decompress",
|
|
.kwtuple = KWTUPLE,
|
|
};
|
|
#undef KWTUPLE
|
|
PyObject *argsbuf[2];
|
|
Py_ssize_t noptargs = nargs + (kwnames ? PyTuple_GET_SIZE(kwnames) : 0) - 1;
|
|
Py_buffer data = {NULL, NULL};
|
|
Py_ssize_t max_length = -1;
|
|
|
|
args = _PyArg_UnpackKeywords(args, nargs, NULL, kwnames, &_parser,
|
|
/*minpos*/ 1, /*maxpos*/ 2, /*minkw*/ 0, /*varpos*/ 0, argsbuf);
|
|
if (!args) {
|
|
goto exit;
|
|
}
|
|
if (PyObject_GetBuffer(args[0], &data, PyBUF_SIMPLE) != 0) {
|
|
goto exit;
|
|
}
|
|
if (!noptargs) {
|
|
goto skip_optional_pos;
|
|
}
|
|
{
|
|
Py_ssize_t ival = -1;
|
|
PyObject *iobj = _PyNumber_Index(args[1]);
|
|
if (iobj != NULL) {
|
|
ival = PyLong_AsSsize_t(iobj);
|
|
Py_DECREF(iobj);
|
|
}
|
|
if (ival == -1 && PyErr_Occurred()) {
|
|
goto exit;
|
|
}
|
|
max_length = ival;
|
|
}
|
|
skip_optional_pos:
|
|
return_value = _zstd_ZstdDecompressor_decompress_impl((ZstdDecompressor *)self, &data, max_length);
|
|
|
|
exit:
|
|
/* Cleanup for data */
|
|
if (data.obj) {
|
|
PyBuffer_Release(&data);
|
|
}
|
|
|
|
return return_value;
|
|
}
|
|
/*[clinic end generated code: output=ae703f0465a2906d input=a9049054013a1b77]*/
|