1 /* ****************************************************************** 2 hist : Histogram functions 3 part of Finite State Entropy project 4 Copyright (C) 2013-present, Yann Collet. 5 6 BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php) 7 8 Redistribution and use in source and binary forms, with or without 9 modification, are permitted provided that the following conditions are 10 met: 11 12 * Redistributions of source code must retain the above copyright 13 notice, this list of conditions and the following disclaimer. 14 * Redistributions in binary form must reproduce the above 15 copyright notice, this list of conditions and the following disclaimer 16 in the documentation and/or other materials provided with the 17 distribution. 18 19 THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS 20 "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT 21 LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR 22 A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT 23 OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, 24 SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT 25 LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, 26 DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY 27 THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT 28 (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE 29 OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. 30 31 You can contact the author at : 32 - FSE source repository : https://github.com/Cyan4973/FiniteStateEntropy 33 - Public forum : https://groups.google.com/forum/#!forum/lz4c 34 ****************************************************************** */ 35 36 /* --- dependencies --- */ 37 #include <stddef.h> /* size_t */ 38 39 40 /* --- simple histogram functions --- */ 41 42 /*! HIST_count(): 43 * Provides the precise count of each byte within a table 'count'. 44 * 'count' is a table of unsigned int, of minimum size (*maxSymbolValuePtr+1). 45 * Updates *maxSymbolValuePtr with actual largest symbol value detected. 46 * @return : count of the most frequent symbol (which isn't identified). 47 * or an error code, which can be tested using HIST_isError(). 48 * note : if return == srcSize, there is only one symbol. 49 */ 50 size_t HIST_count(unsigned* count, unsigned* maxSymbolValuePtr, 51 const void* src, size_t srcSize); 52 53 unsigned HIST_isError(size_t code); /**< tells if a return value is an error code */ 54 55 56 /* --- advanced histogram functions --- */ 57 58 #define HIST_WKSP_SIZE_U32 1024 59 #define HIST_WKSP_SIZE (HIST_WKSP_SIZE_U32 * sizeof(unsigned)) 60 /** HIST_count_wksp() : 61 * Same as HIST_count(), but using an externally provided scratch buffer. 62 * Benefit is this function will use very little stack space. 63 * `workSpace` is a writable buffer which must be 4-bytes aligned, 64 * `workSpaceSize` must be >= HIST_WKSP_SIZE 65 */ 66 size_t HIST_count_wksp(unsigned* count, unsigned* maxSymbolValuePtr, 67 const void* src, size_t srcSize, 68 void* workSpace, size_t workSpaceSize); 69 70 /** HIST_countFast() : 71 * same as HIST_count(), but blindly trusts that all byte values within src are <= *maxSymbolValuePtr. 72 * This function is unsafe, and will segfault if any value within `src` is `> *maxSymbolValuePtr` 73 */ 74 size_t HIST_countFast(unsigned* count, unsigned* maxSymbolValuePtr, 75 const void* src, size_t srcSize); 76 77 /** HIST_countFast_wksp() : 78 * Same as HIST_countFast(), but using an externally provided scratch buffer. 79 * `workSpace` is a writable buffer which must be 4-bytes aligned, 80 * `workSpaceSize` must be >= HIST_WKSP_SIZE 81 */ 82 size_t HIST_countFast_wksp(unsigned* count, unsigned* maxSymbolValuePtr, 83 const void* src, size_t srcSize, 84 void* workSpace, size_t workSpaceSize); 85 86 /*! HIST_count_simple() : 87 * Same as HIST_countFast(), this function is unsafe, 88 * and will segfault if any value within `src` is `> *maxSymbolValuePtr`. 89 * It is also a bit slower for large inputs. 90 * However, it does not need any additional memory (not even on stack). 91 * @return : count of the most frequent symbol. 92 * Note this function doesn't produce any error (i.e. it must succeed). 93 */ 94 unsigned HIST_count_simple(unsigned* count, unsigned* maxSymbolValuePtr, 95 const void* src, size_t srcSize); 96