You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

83 lines
2.9 KiB

/*
* This file is part of the MicroPython project, http://micropython.org/
*
* 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.
*/
#ifndef MICROPY_INCLUDED_PY_QSTR_H
#define MICROPY_INCLUDED_PY_QSTR_H
#include "py/mpconfig.h"
#include "py/misc.h"
// See qstrdefs.h for a list of qstr's that are available as constants.
// Reference them as MP_QSTR_xxxx.
//
// Note: it would be possible to define MP_QSTR_xxx as qstr_from_str_static("xxx")
// for qstrs that are referenced this way, but you don't want to have them in ROM.
// first entry in enum will be MP_QSTRnull=0, which indicates invalid/no qstr
enum {
#ifndef NO_QSTR
#define QDEF(id, str) id,
#include "genhdr/qstrdefs.generated.h"
#undef QDEF
#endif
MP_QSTRnumber_of, // no underscore so it can't clash with any of the above
};
typedef size_t qstr;
typedef struct _qstr_pool_t {
struct _qstr_pool_t *prev;
size_t total_prev_len;
size_t alloc;
size_t len;
const byte *qstrs[];
} qstr_pool_t;
#define QSTR_FROM_STR_STATIC(s) (qstr_from_strn((s), strlen(s)))
#define QSTR_TOTAL() (MP_STATE_VM(last_pool)->total_prev_len + MP_STATE_VM(last_pool)->len)
void qstr_init(void);
mp_uint_t qstr_compute_hash(const byte *data, size_t len);
qstr qstr_find_strn(const char *str, size_t str_len); // returns MP_QSTRnull if not found
qstr qstr_from_str(const char *str);
qstr qstr_from_strn(const char *str, size_t len);
mp_uint_t qstr_hash(qstr q);
const char *qstr_str(qstr q);
size_t qstr_len(qstr q);
const byte *qstr_data(qstr q, size_t *len);
void qstr_pool_info(size_t *n_pool, size_t *n_qstr, size_t *n_str_data_bytes, size_t *n_total_bytes);
void qstr_dump_data(void);
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.
5 years ago
#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
#endif // MICROPY_INCLUDED_PY_QSTR_H