Implement the Pearson hash method.

3 files changed, 153 insertions, 0 deletions

diff --git a/src/common/Makefile.am b/src/common/Makefile.am
index fc313fb..2162d8c 100644
--- a/src/common/Makefile.am
+++ b/src/common/Makefile.am
@@ -21,6 +21,7 @@ libcommon_la_SOURCES =					\
 	net.h net.c							\
 	packed.h packed.c					\
 	pathname.h pathname.c				\
+	pearson.h pearson.c					\
 	shuffle.h shuffle.c					\
 	sort.h sort.c						\
 	sqlite.h sqlite.c					\
diff --git a/src/common/pearson.c b/src/common/pearson.c
new file mode 100644
index 0000000..5607a0c
--- /dev/null
+++ b/src/common/pearson.c
@@ -0,0 +1,106 @@
+
+/* Chrysalide - Outil d'analyse de fichiers binaires
+ * pearson.c - implémentaton du calcul rapide d'empreintes de chaînes
+ *
+ * Copyright (C) 2021 Cyrille Bagard
+ *
+ *  This file is part of Chrysalide.
+ *
+ *  Chrysalide is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 3 of the License, or
+ *  (at your option) any later version.
+ *
+ *  Chrysalide is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with Chrysalide.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+
+#include "pearson.h"
+
+
+#include <stddef.h>
+
+
+
+/* Permutations proposées */
+static const char _pearson_permutations[256] = {
+
+      1,  87,  49,  12, 176, 178, 102, 166, 121, 193,   6,  84, 249, 230,  44, 163,
+     14, 197, 213, 181, 161,  85, 218,  80,  64, 239,  24, 226, 236, 142,  38, 200,
+    110, 177, 104, 103, 141, 253, 255,  50,  77, 101,  81,  18,  45,  96,  31, 222,
+     25, 107, 190,  70,  86, 237, 240,  34,  72, 242,  20, 214, 244, 227, 149, 235,
+     97, 234,  57,  22,  60, 250,  82, 175, 208,   5, 127, 199, 111,  62, 135, 248,
+    174, 169, 211,  58,  66, 154, 106, 195, 245, 171,  17, 187, 182, 179,   0, 243,
+    132,  56, 148,  75, 128, 133, 158, 100, 130, 126,  91,  13, 153, 246, 216, 219,
+    119,  68, 223,  78,  83,  88, 201,  99, 122,  11,  92,  32, 136, 114,  52,  10,
+    138,  30,  48, 183, 156,  35,  61,  26, 143,  74, 251,  94, 129, 162,  63, 152,
+    170,   7, 115, 167, 241, 206,   3, 150,  55,  59, 151, 220,  90,  53,  23, 131,
+    125, 173,  15, 238,  79,  95,  89,  16, 105, 137, 225, 224, 217, 160,  37, 123,
+    118,  73,   2, 157,  46, 116,   9, 145, 134, 228, 207, 212, 202, 215,  69, 229,
+     27, 188,  67, 124, 168, 252,  42,   4,  29, 108,  21, 247,  19, 205,  39, 203,
+    233,  40, 186, 147, 198, 192, 155,  33, 164, 191,  98, 204, 165, 180, 117,  76,
+    140,  36, 210, 172,  41,  54, 159,   8, 185, 232, 113, 196, 231,  47, 146, 120,
+     51,  65,  28, 144, 254, 221,  93, 189, 194, 139, 112,  43,  71, 109, 184, 209
+
+};
+
+
+
+/******************************************************************************
+*                                                                             *
+*  Paramètres  : -                                                            *
+*                                                                             *
+*  Description : Fournit les permutations par défaut par Pearson.             *
+*                                                                             *
+*  Retour      : Table de valeurs utilisées par défaut.                       *
+*                                                                             *
+*  Remarques   : -                                                            *
+*                                                                             *
+******************************************************************************/
+
+const char *get_pearson_permutations(void)
+{
+    const char *result;                     /* Table à renvoyer            */
+
+    result = _pearson_permutations;
+
+    return result;
+
+}
+
+
+/******************************************************************************
+*                                                                             *
+*  Paramètres  : str = chaîne de caractères à traiter.                        *
+*                table = permutations à employer, NULL pour celles par défaut.*
+*                                                                             *
+*  Description : Détermine l'empreinte Pearson d'une chaîne de caractères.    *
+*                                                                             *
+*  Retour      : Valeur calculée.                                             *
+*                                                                             *
+*  Remarques   : -                                                            *
+*                                                                             *
+******************************************************************************/
+
+uint8_t pearson_hash(const char *str, const char *table)
+{
+    uint8_t result;                         /* Valeur à retourner          */
+    unsigned char *iter;                    /* Boucle de parcours          */
+
+    if (table == NULL)
+        table = _pearson_permutations;
+
+    result = 0;
+
+    for (iter = (unsigned char *)str; *iter; iter++)
+        result = table[result ^ (*iter)];
+
+    return result;
+
+}
diff --git a/src/common/pearson.h b/src/common/pearson.h
new file mode 100644
index 0000000..09f45cf
--- /dev/null
+++ b/src/common/pearson.h
@@ -0,0 +1,46 @@
+
+/* Chrysalide - Outil d'analyse de fichiers binaires
+ * pearson.h - prototypes pour l'implémentaton du calcul rapide d'empreintes de chaînes
+ *
+ * Copyright (C) 2021 Cyrille Bagard
+ *
+ *  This file is part of Chrysalide.
+ *
+ *  Chrysalide is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 3 of the License, or
+ *  (at your option) any later version.
+ *
+ *  Chrysalide is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with Chrysalide.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+
+#ifndef _COMMON_PEARSON_H
+#define _COMMON_PEARSON_H
+
+
+#include <stdint.h>
+
+
+/**
+ * Plus d'informations avec les liens suivants :
+ *  - https://en.wikipedia.org/wiki/Pearson_hashing
+ *  - https://web.archive.org/web/20120704025921/http://cs.mwsu.edu/~griffin/courses/2133/downloads/Spring11/p677-pearson.pdf
+ */
+
+
+/* Fournit les permutations par défaut par Pearson. */
+const char *get_pearson_permutations(void);
+
+/* Détermine l'empreinte Pearson d'une chaîne de caractères. */
+uint8_t pearson_hash(const char *, const char *);
+
+
+
+#endif  /* _COMMON_PEARSON_H */