ewah / ewah_io.con commit Merge branch 'jc/denoise-rm-to-resolve' (5e9d978)
   1/**
   2 * Copyright 2013, GitHub, Inc
   3 * Copyright 2009-2013, Daniel Lemire, Cliff Moon,
   4 *      David McIntosh, Robert Becho, Google Inc. and Veronika Zenz
   5 *
   6 * This program is free software; you can redistribute it and/or
   7 * modify it under the terms of the GNU General Public License
   8 * as published by the Free Software Foundation; either version 2
   9 * of the License, or (at your option) any later version.
  10 *
  11 * This program is distributed in the hope that it will be useful,
  12 * but WITHOUT ANY WARRANTY; without even the implied warranty of
  13 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  14 * GNU General Public License for more details.
  15 *
  16 * You should have received a copy of the GNU General Public License
  17 * along with this program; if not, see <http://www.gnu.org/licenses/>.
  18 */
  19#include "git-compat-util.h"
  20#include "ewok.h"
  21#include "strbuf.h"
  22
  23int ewah_serialize_to(struct ewah_bitmap *self,
  24                      int (*write_fun)(void *, const void *, size_t),
  25                      void *data)
  26{
  27        size_t i;
  28        eword_t dump[2048];
  29        const size_t words_per_dump = sizeof(dump) / sizeof(eword_t);
  30        uint32_t bitsize, word_count, rlw_pos;
  31
  32        const eword_t *buffer;
  33        size_t words_left;
  34
  35        /* 32 bit -- bit size for the map */
  36        bitsize =  htonl((uint32_t)self->bit_size);
  37        if (write_fun(data, &bitsize, 4) != 4)
  38                return -1;
  39
  40        /** 32 bit -- number of compressed 64-bit words */
  41        word_count =  htonl((uint32_t)self->buffer_size);
  42        if (write_fun(data, &word_count, 4) != 4)
  43                return -1;
  44
  45        /** 64 bit x N -- compressed words */
  46        buffer = self->buffer;
  47        words_left = self->buffer_size;
  48
  49        while (words_left >= words_per_dump) {
  50                for (i = 0; i < words_per_dump; ++i, ++buffer)
  51                        dump[i] = htonll(*buffer);
  52
  53                if (write_fun(data, dump, sizeof(dump)) != sizeof(dump))
  54                        return -1;
  55
  56                words_left -= words_per_dump;
  57        }
  58
  59        if (words_left) {
  60                for (i = 0; i < words_left; ++i, ++buffer)
  61                        dump[i] = htonll(*buffer);
  62
  63                if (write_fun(data, dump, words_left * 8) != words_left * 8)
  64                        return -1;
  65        }
  66
  67        /** 32 bit -- position for the RLW */
  68        rlw_pos = (uint8_t*)self->rlw - (uint8_t *)self->buffer;
  69        rlw_pos = htonl(rlw_pos / sizeof(eword_t));
  70
  71        if (write_fun(data, &rlw_pos, 4) != 4)
  72                return -1;
  73
  74        return (3 * 4) + (self->buffer_size * 8);
  75}
  76
  77static int write_strbuf(void *user_data, const void *data, size_t len)
  78{
  79        struct strbuf *sb = user_data;
  80        strbuf_add(sb, data, len);
  81        return len;
  82}
  83
  84int ewah_serialize_strbuf(struct ewah_bitmap *self, struct strbuf *sb)
  85{
  86        return ewah_serialize_to(self, write_strbuf, sb);
  87}
  88
  89ssize_t ewah_read_mmap(struct ewah_bitmap *self, const void *map, size_t len)
  90{
  91        const uint8_t *ptr = map;
  92        size_t data_len;
  93        size_t i;
  94
  95        if (len < sizeof(uint32_t))
  96                return error("corrupt ewah bitmap: eof before bit size");
  97        self->bit_size = get_be32(ptr);
  98        ptr += sizeof(uint32_t);
  99        len -= sizeof(uint32_t);
 100
 101        if (len < sizeof(uint32_t))
 102                return error("corrupt ewah bitmap: eof before length");
 103        self->buffer_size = self->alloc_size = get_be32(ptr);
 104        ptr += sizeof(uint32_t);
 105        len -= sizeof(uint32_t);
 106
 107        REALLOC_ARRAY(self->buffer, self->alloc_size);
 108
 109        /*
 110         * Copy the raw data for the bitmap as a whole chunk;
 111         * if we're in a little-endian platform, we'll perform
 112         * the endianness conversion in a separate pass to ensure
 113         * we're loading 8-byte aligned words.
 114         */
 115        data_len = st_mult(self->buffer_size, sizeof(eword_t));
 116        if (len < data_len)
 117                return error("corrupt ewah bitmap: eof in data "
 118                             "(%"PRIuMAX" bytes short)",
 119                             (uintmax_t)(data_len - len));
 120        memcpy(self->buffer, ptr, data_len);
 121        ptr += data_len;
 122        len -= data_len;
 123
 124        for (i = 0; i < self->buffer_size; ++i)
 125                self->buffer[i] = ntohll(self->buffer[i]);
 126
 127        if (len < sizeof(uint32_t))
 128                return error("corrupt ewah bitmap: eof before rlw");
 129        self->rlw = self->buffer + get_be32(ptr);
 130        ptr += sizeof(uint32_t);
 131        len -= sizeof(uint32_t);
 132
 133        return ptr - (const uint8_t *)map;
 134}