2014-05-03 18:27:38 -04:00
|
|
|
/*
|
2017-06-30 03:22:17 -04:00
|
|
|
* This file is part of the MicroPython project, http://micropython.org/
|
2014-05-03 18:27:38 -04:00
|
|
|
*
|
|
|
|
* The MIT License (MIT)
|
|
|
|
*
|
|
|
|
* Copyright (c) 2013, 2014 Damien P. George
|
|
|
|
*
|
|
|
|
* Permission is hereby granted, free of charge, to any person obtaining a copy
|
|
|
|
* of this software and associated documentation files (the "Software"), to deal
|
|
|
|
* in the Software without restriction, including without limitation the rights
|
|
|
|
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
|
|
|
* copies of the Software, and to permit persons to whom the Software is
|
|
|
|
* furnished to do so, subject to the following conditions:
|
|
|
|
*
|
|
|
|
* The above copyright notice and this permission notice shall be included in
|
|
|
|
* all copies or substantial portions of the Software.
|
|
|
|
*
|
|
|
|
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
|
|
|
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
|
|
|
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
|
|
|
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
|
|
|
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
|
|
|
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
|
|
|
* THE SOFTWARE.
|
|
|
|
*/
|
all: Unify header guard usage.
The code conventions suggest using header guards, but do not define how
those should look like and instead point to existing files. However, not
all existing files follow the same scheme, sometimes omitting header guards
altogether, sometimes using non-standard names, making it easy to
accidentally pick a "wrong" example.
This commit ensures that all header files of the MicroPython project (that
were not simply copied from somewhere else) follow the same pattern, that
was already present in the majority of files, especially in the py folder.
The rules are as follows.
Naming convention:
* start with the words MICROPY_INCLUDED
* contain the full path to the file
* replace special characters with _
In addition, there are no empty lines before #ifndef, between #ifndef and
one empty line before #endif. #endif is followed by a comment containing
the name of the guard macro.
py/grammar.h cannot use header guards by design, since it has to be
included multiple times in a single C file. Several other files also do not
need header guards as they are only used internally and guaranteed to be
included only once:
* MICROPY_MPHALPORT_H
* mpconfigboard.h
* mpconfigport.h
* mpthreadport.h
* pin_defs_*.h
* qstrdefs*.h
2017-06-29 17:14:58 -04:00
|
|
|
#ifndef MICROPY_INCLUDED_PY_QSTR_H
|
|
|
|
#define MICROPY_INCLUDED_PY_QSTR_H
|
2014-12-28 20:02:19 -05:00
|
|
|
|
|
|
|
#include "py/mpconfig.h"
|
|
|
|
#include "py/misc.h"
|
2014-05-03 18:27:38 -04:00
|
|
|
|
2014-06-03 13:15:46 -04:00
|
|
|
// See qstrdefs.h for a list of qstr's that are available as constants.
|
2014-01-21 16:40:13 -05:00
|
|
|
// Reference them as MP_QSTR_xxxx.
|
|
|
|
//
|
2021-01-16 03:18:31 -05:00
|
|
|
// Note: it would be possible to define MP_QSTR_xxx as qstr_from_str("xxx")
|
2014-01-21 16:40:13 -05:00
|
|
|
// for qstrs that are referenced this way, but you don't want to have them in ROM.
|
|
|
|
|
2019-09-25 01:53:30 -04:00
|
|
|
// first entry in enum will be MP_QSTRnull=0, which indicates invalid/no qstr
|
2014-01-21 16:40:13 -05:00
|
|
|
enum {
|
2020-02-26 23:36:53 -05:00
|
|
|
#ifndef NO_QSTR
|
2015-01-11 12:52:45 -05:00
|
|
|
#define QDEF(id, str) id,
|
2020-02-26 23:36:53 -05:00
|
|
|
#include "genhdr/qstrdefs.generated.h"
|
2015-01-11 12:52:45 -05:00
|
|
|
#undef QDEF
|
2020-02-26 23:36:53 -05:00
|
|
|
#endif
|
2016-01-31 17:24:16 -05:00
|
|
|
MP_QSTRnumber_of, // no underscore so it can't clash with any of the above
|
2014-04-12 12:53:05 -04:00
|
|
|
};
|
2014-01-21 16:40:13 -05:00
|
|
|
|
2015-12-17 07:45:22 -05:00
|
|
|
typedef size_t qstr;
|
2014-01-21 16:40:13 -05:00
|
|
|
|
2015-01-01 18:30:53 -05:00
|
|
|
typedef struct _qstr_pool_t {
|
|
|
|
struct _qstr_pool_t *prev;
|
2015-12-17 07:41:40 -05:00
|
|
|
size_t total_prev_len;
|
|
|
|
size_t alloc;
|
|
|
|
size_t len;
|
2015-01-01 18:30:53 -05:00
|
|
|
const byte *qstrs[];
|
|
|
|
} qstr_pool_t;
|
|
|
|
|
2018-02-15 02:12:01 -05:00
|
|
|
#define QSTR_TOTAL() (MP_STATE_VM(last_pool)->total_prev_len + MP_STATE_VM(last_pool)->len)
|
2014-01-21 16:40:13 -05:00
|
|
|
|
|
|
|
void qstr_init(void);
|
|
|
|
|
2015-11-27 07:23:18 -05:00
|
|
|
mp_uint_t qstr_compute_hash(const byte *data, size_t len);
|
2019-09-25 01:53:30 -04:00
|
|
|
qstr qstr_find_strn(const char *str, size_t str_len); // returns MP_QSTRnull if not found
|
2014-01-22 09:35:10 -05:00
|
|
|
|
2014-01-21 16:40:13 -05:00
|
|
|
qstr qstr_from_str(const char *str);
|
2015-11-27 07:23:18 -05:00
|
|
|
qstr qstr_from_strn(const char *str, size_t len);
|
2014-01-21 16:40:13 -05:00
|
|
|
|
2014-07-03 08:25:24 -04:00
|
|
|
mp_uint_t qstr_hash(qstr q);
|
2015-04-04 10:53:11 -04:00
|
|
|
const char *qstr_str(qstr q);
|
2015-11-27 07:23:18 -05:00
|
|
|
size_t qstr_len(qstr q);
|
|
|
|
const byte *qstr_data(qstr q, size_t *len);
|
2014-01-29 13:56:46 -05:00
|
|
|
|
2015-12-17 07:41:40 -05:00
|
|
|
void qstr_pool_info(size_t *n_pool, size_t *n_qstr, size_t *n_str_data_bytes, size_t *n_total_bytes);
|
2015-02-10 06:02:28 -05:00
|
|
|
void qstr_dump_data(void);
|
2014-12-28 20:02:19 -05:00
|
|
|
|
py: Implement "common word" compression scheme for error messages.
The idea here is that there's a moderate amount of ROM used up by exception
text. Obviously we try to keep the messages short, and the code can enable
terse errors, but it still adds up. Listed below is the total string data
size for various ports:
bare-arm 2860
minimal 2876
stm32 8926 (PYBV11)
cc3200 3751
esp32 5721
This commit implements compression of these strings. It takes advantage of
the fact that these strings are all 7-bit ascii and extracts the top 128
frequently used words from the messages and stores them packed (dropping
their null-terminator), then uses (0x80 | index) inside strings to refer to
these common words. Spaces are automatically added around words, saving
more bytes. This happens transparently in the build process, mirroring the
steps that are used to generate the QSTR data. The MP_COMPRESSED_ROM_TEXT
macro wraps any literal string that should compressed, and it's
automatically decompressed in mp_decompress_rom_string.
There are many schemes that could be used for the compression, and some are
included in py/makecompresseddata.py for reference (space, Huffman, ngram,
common word). Results showed that the common-word compression gets better
results. This is before counting the increased cost of the Huffman
decoder. This might be slightly counter-intuitive, but this data is
extremely repetitive at a word-level, and the byte-level entropy coder
can't quite exploit that as efficiently. Ideally one would combine both
approaches, but for now the common-word approach is the one that is used.
For additional comparison, the size of the raw data compressed with gzip
and zlib is calculated, as a sort of proxy for a lower entropy bound. With
this scheme we come within 15% on stm32, and 30% on bare-arm (i.e. we use
x% more bytes than the data compressed with gzip -- not counting the code
overhead of a decoder, and how this would be hypothetically implemented).
The feature is disabled by default and can be enabled by setting
MICROPY_ROM_TEXT_COMPRESSION at the Makefile-level.
2019-09-26 08:19:29 -04:00
|
|
|
#if MICROPY_ROM_TEXT_COMPRESSION
|
|
|
|
void mp_decompress_rom_string(byte *dst, mp_rom_error_text_t src);
|
|
|
|
#define MP_IS_COMPRESSED_ROM_STRING(s) (*(byte *)(s) == 0xff)
|
|
|
|
#endif
|
|
|
|
|
all: Unify header guard usage.
The code conventions suggest using header guards, but do not define how
those should look like and instead point to existing files. However, not
all existing files follow the same scheme, sometimes omitting header guards
altogether, sometimes using non-standard names, making it easy to
accidentally pick a "wrong" example.
This commit ensures that all header files of the MicroPython project (that
were not simply copied from somewhere else) follow the same pattern, that
was already present in the majority of files, especially in the py folder.
The rules are as follows.
Naming convention:
* start with the words MICROPY_INCLUDED
* contain the full path to the file
* replace special characters with _
In addition, there are no empty lines before #ifndef, between #ifndef and
one empty line before #endif. #endif is followed by a comment containing
the name of the guard macro.
py/grammar.h cannot use header guards by design, since it has to be
included multiple times in a single C file. Several other files also do not
need header guards as they are only used internally and guaranteed to be
included only once:
* MICROPY_MPHALPORT_H
* mpconfigboard.h
* mpconfigport.h
* mpthreadport.h
* pin_defs_*.h
* qstrdefs*.h
2017-06-29 17:14:58 -04:00
|
|
|
#endif // MICROPY_INCLUDED_PY_QSTR_H
|