annotate mercurial/cext/charencode.h @ 45095:8e04607023e5

procutil: ensure that procutil.std{out,err}.write() writes all bytes

Python 3 offers different kind of streams and it’s not guaranteed for all of
them that calling write() writes all bytes.

When Python is started in unbuffered mode, sys.std{out,err}.buffer are
instances of io.FileIO, whose write() can write less bytes for
platform-specific reasons (e.g. Linux has a 0x7ffff000 bytes maximum and could
write less if interrupted by a signal; when writing to Windows consoles, it’s
limited to 32767 bytes to avoid the "not enough space" error). This can lead to
silent loss of data, both when using sys.std{out,err}.buffer (which may in fact
not be a buffered stream) and when using the text streams sys.std{out,err}
(I’ve created a CPython bug report for that:
https://bugs.python.org/issue41221).

Python may fix the problem at some point. For now, we implement our own wrapper
for procutil.std{out,err} that calls the raw stream’s write() method until all
bytes have been written. We don’t use sys.std{out,err} for larger writes, so I
think it’s not worth the effort to patch them.

/*
 charencode.h - miscellaneous character encoding

 This software may be used and distributed according to the terms of
 the GNU General Public License, incorporated herein by reference.
*/

#ifndef _HG_CHARENCODE_H_
#define _HG_CHARENCODE_H_

#include <Python.h>
#include "compat.h"

/* This should be kept in sync with normcasespecs in encoding.py. */
enum normcase_spec {
	NORMCASE_LOWER = -1,
	NORMCASE_UPPER = 1,
	NORMCASE_OTHER = 0
};

PyObject *unhexlify(const char *str, Py_ssize_t len);
PyObject *isasciistr(PyObject *self, PyObject *args);
PyObject *asciilower(PyObject *self, PyObject *args);
PyObject *asciiupper(PyObject *self, PyObject *args);
PyObject *make_file_foldmap(PyObject *self, PyObject *args);
PyObject *jsonescapeu8fast(PyObject *self, PyObject *args);

/* clang-format off */
static const int8_t hextable[256] = {
	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
	 0,  1,  2,  3,  4,  5,  6,  7,  8,  9, -1, -1, -1, -1, -1, -1, /* 0-9 */
	-1, 10, 11, 12, 13, 14, 15, -1, -1, -1, -1, -1, -1, -1, -1, -1, /* A-F */
	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
	-1, 10, 11, 12, 13, 14, 15, -1, -1, -1, -1, -1, -1, -1, -1, -1, /* a-f */
	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1
};
/* clang-format on */

static inline int hexdigit(const char *p, Py_ssize_t off)
{
	int8_t val = hextable[(unsigned char)p[off]];

	if (val >= 0) {
		return val;
	}

	PyErr_SetString(PyExc_ValueError, "input contains non-hex character");
	return 0;
}

#endif /* _HG_CHARENCODE_H_ */