mirrors/cosmopolitan
1
0
Fork 0
mirror of https://github.com/jart/cosmopolitan.git synced 2025-07-29 14:00:29 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Productionize new APE loader and more

Browse source 
The APE_NO_MODIFY_SELF loader payload has been moved out of the examples
folder and improved so that it works on BSD systems, and permits general
elf program headers. This brings its quality up enough that it should be
acceptable to use by default for many programs, e.g. Python, Lua, SQLite
and Python. It's the responsibility of the user to define an appropriate
TMPDIR if /tmp is considered an adversarial environment. Mac OS shall be
supported by APE_NO_MODIFY_SELF soon.

Fixes and improvements have been made to program_executable_name as it's
now the one true way to get the absolute path of the executing image.

This change fixes a memory leak in linenoise history loading, introduced
by performance optimizations in 51904e2687
This change fixes a longstanding regression with Mach system calls, that
23ae9dfceb back in February which impacted
our sched_yield() implementation, which is why no one noticed until now.

The Blinkenlights PC emulator has been improved. We now fix rendering on
XNU and BSD by not making the assumption that the kernel terminal driver
understands UTF8 since that seems to break its internal modeling of \r\n
which is now being addressed by using \e[𝑦H instead. The paneling is now
more compact in real mode so you won't need to make your font as tiny if
you're only emulating an 8086 program. The CLMUL ISA is now emulated too

This change also makes improvement to time. CLOCK_MONOTONIC now does the
right thing on Windows NT. The nanosecond time module functions added in
Python 3.7 have been backported.

This change doubles the performance of Argon2 password stretching simply
by not using its copy_block and xor_block helper functions, as they were
trivial to inline thus resulting in us needing to iterate over each 1024
byte block four fewer times.

This change makes code size improvements. _PyUnicode_ToNumeric() was 64k
in size and now it's 10k. The CJK codec lookup tables now use lazy delta
zigzag deflate (δzd) encoding which reduces their size from 600k to 200k
plus the code bloat caused by macro abuse in _decimal.c is now addressed
so our fully-loaded statically-linked hermetically-sealed Python virtual
interpreter container is now 9.4 megs in the default build mode and 5.5m
in MODE=tiny which leaves plenty of room for chibicc.

The pydoc web server now accommodates the use case of people who work by
SSH'ing into a different machine w/ python.com -m pydoc -p8080 -h0.0.0.0

Finally Python Capsulae delenda est and won't be supported in the future
This commit is contained in:
Justine Tunney 2021-10-02 08:17:04 -07:00
parent 9cb54218ab
commit 47a53e143b
270 changed files with 214544 additions and 23331 deletions
Download patch file Download diff file Expand all files Collapse all files

160
third_party/python/Modules/cjkcodecs/cjkcodecs.h vendored
View file

@ -9,6 +9,7 @@
#include "third_party/python/Include/pyerrors.h"
#include "third_party/python/Include/pymacro.h"
#include "third_party/python/Modules/cjkcodecs/multibytecodec.h"
#include "third_party/python/Modules/cjkcodecs/somanyencodings.h"
/* clang-format off */
/* a unicode "undefined" code point */
@ -25,42 +26,7 @@
#define M MULTIC
#define D DBCINV
struct dbcs_index {
const ucs2_t *map;
unsigned char bottom, top;
};
typedef struct dbcs_index decode_map;
struct widedbcs_index {
const Py_UCS4 *map;
unsigned char bottom, top;
};
typedef struct widedbcs_index widedecode_map;
struct unim_index {
const DBCHAR *map;
unsigned char bottom, top;
};
typedef struct unim_index encode_map;
struct unim_index_bytebased {
const unsigned char *map;
unsigned char bottom, top;
};
struct dbcs_map {
const char *charset;
const struct unim_index *encmap;
const struct dbcs_index *decmap;
};
struct pair_encodemap {
Py_UCS4 uniseq;
DBCHAR code;
};
static const MultibyteCodec *codec_list;
static const struct dbcs_map *mapping_list;
#define CODEC_INIT(encoding) \
static int encoding##_codec_init(const void *config)
@ -134,7 +100,7 @@ static const struct dbcs_map *mapping_list;
#define OUTCHAR(c) \
do { \
if (_PyUnicodeWriter_WriteChar(writer, (c)) < 0) \
return MBERR_EXCEPTION; \
return MBERR_EXCEPTION; \
} while (0)
#define OUTCHAR2(c1, c2) \
@ -184,29 +150,23 @@ static const struct dbcs_map *mapping_list;
(*outbuf)[3] = (c4); \
} while (0)
#define _TRYMAP_ENC(m, assi, val) \
((m)->map != NULL && (val) >= (m)->bottom && \
(val)<= (m)->top && ((assi) = (m)->map[(val) - \
(m)->bottom]) != NOCHAR)
#define TRYMAP_ENC(charset, assi, uni) \
_TRYMAP_ENC(&charset##_encmap[(uni) >> 8], assi, (uni) & 0xff)
#define _TRYMAP_ENC(__m, m, assi, val) \
(m.map && (val) >= m.bottom && (val)<= m.top && \
((assi) = (__m() + m.map - 1)[(val) - m.bottom]) != NOCHAR)
#define TRYMAP_ENC(M, assi, uni) \
_TRYMAP_ENC(__##M##_encmap, M##_encmap()[(uni) >> 8], assi, (uni) & 0xff)
#define _TRYMAP_DEC(m, assi, val) \
((m)->map != NULL && \
(val) >= (m)->bottom && \
(val)<= (m)->top && \
((assi) = (m)->map[(val) - (m)->bottom]) != UNIINV)
#define TRYMAP_DEC(charset, assi, c1, c2) \
_TRYMAP_DEC(&charset##_decmap[c1], assi, c2)
#define _TRYMAP_DEC(__m, m, assi, val) \
(m.map && (val) >= m.bottom && (val) <= m.top && \
((assi) = (__m() + m.map - 1)[(val) - m.bottom]) != UNIINV)
#define TRYMAP_DEC(M, assi, c1, c2) \
_TRYMAP_DEC(__##M##_decmap, M##_decmap()[c1], assi, c2)
#define BEGIN_MAPPINGS_LIST static const struct dbcs_map _mapping_list[] = {
#define MAPPING_ENCONLY(enc) {#enc, (void*)enc##_encmap, NULL},
#define MAPPING_DECONLY(enc) {#enc, NULL, (void*)enc##_decmap},
#define MAPPING_ENCDEC(enc) {#enc, (void*)enc##_encmap, (void*)enc##_decmap},
#define END_MAPPINGS_LIST \
{"", NULL, NULL} }; \
static const struct dbcs_map *mapping_list = \
(const struct dbcs_map *)_mapping_list;
#define BEGIN_MAPPINGS_LIST
#define MAPPING_ENCONLY(enc)
#define MAPPING_DECONLY(enc)
#define MAPPING_ENCDEC(enc)
#define END_MAPPINGS_LIST
#define BEGIN_CODECS_LIST static const MultibyteCodec _codec_list[] = {
#define _STATEFUL_METHODS(enc) \
@ -237,13 +197,10 @@ static const struct dbcs_map *mapping_list;
static const MultibyteCodec *codec_list = \
(const MultibyteCodec *)_codec_list;
static PyObject *
getmultibytecodec(void)
{
static PyObject *cofunc = NULL;
if (cofunc == NULL) {
PyObject *mod = PyImport_ImportModuleNoBlock("_multibytecodec");
if (mod == NULL)
@ -260,7 +217,6 @@ getcodec(PyObject *self, PyObject *encoding)
PyObject *codecobj, *r, *cofunc;
const MultibyteCodec *codec;
const char *enc;
if (!PyUnicode_Check(encoding)) {
PyErr_SetString(PyExc_TypeError,
"encoding name must be a string.");
@ -269,64 +225,40 @@ getcodec(PyObject *self, PyObject *encoding)
enc = PyUnicode_AsUTF8(encoding);
if (enc == NULL)
return NULL;
cofunc = getmultibytecodec();
if (cofunc == NULL)
return NULL;
for (codec = codec_list; codec->encoding[0]; codec++)
if (strcmp(codec->encoding, enc) == 0)
break;
if (codec->encoding[0] == '\0') {
PyErr_SetString(PyExc_LookupError,
"no such codec is supported.");
return NULL;
}
codecobj = PyCapsule_New((void *)codec, PyMultibyteCodec_CAPSULE_NAME, NULL);
if (codecobj == NULL)
return NULL;
r = PyObject_CallFunctionObjArgs(cofunc, codecobj, NULL);
Py_DECREF(codecobj);
return r;
}
static struct PyMethodDef __methods[] = {
{"getcodec", (PyCFunction)getcodec, METH_O, ""},
{NULL, NULL},
{0},
};
static int
register_maps(PyObject *module)
{
const struct dbcs_map *h;
for (h = mapping_list; h->charset[0] != '\0'; h++) {
char mhname[256] = "__map_";
int r;
strcpy(mhname + sizeof("__map_") - 1, h->charset);
r = PyModule_AddObject(module, mhname,
PyCapsule_New((void *)h, PyMultibyteCodec_CAPSULE_NAME, NULL));
if (r == -1)
return -1;
}
return 0;
}
#ifdef USING_BINARY_PAIR_SEARCH
static DBCHAR
find_pairencmap(ucs2_t body, ucs2_t modifier,
const struct pair_encodemap *haystack, int haystacksize)
const struct CjkPairEncodeMap *haystack,
int haystacksize)
{
int pos, min, max;
Py_UCS4 value = body << 16 | modifier;
min = 0;
max = haystacksize;
for (pos = haystacksize >> 1; min != max; pos = (min + max) >> 1) {
if (value < haystack[pos].uniseq) {
if (max != pos) {
@ -342,7 +274,6 @@ find_pairencmap(ucs2_t body, ucs2_t modifier,
}
break;
}
if (value == haystack[pos].uniseq) {
return haystack[pos].code;
}
@ -350,48 +281,6 @@ find_pairencmap(ucs2_t body, ucs2_t modifier,
}
#endif
#ifdef USING_IMPORTED_MAPS
#define IMPORT_MAP(locale, charset, encmap, decmap) \
importmap("_codecs_" #locale, "__map_" #charset, \
(const void**)encmap, (const void**)decmap)
static int
importmap(const char *modname, const char *symbol,
const void **encmap, const void **decmap)
{
PyObject *o, *mod;
mod = PyImport_ImportModule(modname);
if (mod == NULL)
return -1;
o = PyObject_GetAttrString(mod, symbol);
if (o == NULL)
goto errorexit;
else if (!PyCapsule_IsValid(o, PyMultibyteCodec_CAPSULE_NAME)) {
PyErr_SetString(PyExc_ValueError,
"map data must be a Capsule.");
goto errorexit;
}
else {
struct dbcs_map *map;
map = PyCapsule_GetPointer(o, PyMultibyteCodec_CAPSULE_NAME);
if (encmap != NULL)
*encmap = map->encmap;
if (decmap != NULL)
*decmap = map->decmap;
Py_DECREF(o);
}
Py_DECREF(mod);
return 0;
errorexit:
Py_DECREF(mod);
return -1;
}
#endif
#define I_AM_A_MODULE_FOR(loc) \
static struct PyModuleDef __module = { \
PyModuleDef_HEAD_INIT, \
@ -399,18 +288,11 @@ errorexit:
NULL, \
0, \
__methods, \
NULL, \
NULL, \
NULL, \
NULL \
}; \
PyMODINIT_FUNC \
PyInit__codecs_##loc(void) \
{ \
PyObject *m = PyModule_Create(&__module); \
if (m != NULL) \
(void)register_maps(m); \
return m; \
return PyModule_Create(&__module); \
}
#endif