1 ------------------------------------------------------------------------------
3 -- GNAT COMPILER COMPONENTS --
5 -- G N A T . P E R F E C T _ H A S H _ G E N E R A T O R S --
9 -- Copyright (C) 2002-2024, AdaCore --
11 -- GNAT is free software; you can redistribute it and/or modify it under --
12 -- terms of the GNU General Public License as published by the Free Soft- --
13 -- ware Foundation; either version 3, or (at your option) any later ver- --
14 -- sion. GNAT is distributed in the hope that it will be useful, but WITH- --
15 -- OUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY --
16 -- or FITNESS FOR A PARTICULAR PURPOSE. --
18 -- As a special exception under Section 7 of GPL version 3, you are granted --
19 -- additional permissions described in the GCC Runtime Library Exception, --
20 -- version 3.1, as published by the Free Software Foundation. --
22 -- You should have received a copy of the GNU General Public License and --
23 -- a copy of the GCC Runtime Library Exception along with this program; --
24 -- see the files COPYING3 and COPYING.RUNTIME respectively. If not, see --
25 -- <http://www.gnu.org/licenses/>. --
27 -- GNAT was originally developed by the GNAT team at New York University. --
28 -- Extensive contributions were provided by Ada Core Technologies Inc. --
30 ------------------------------------------------------------------------------
32 -- This package provides a generator of static minimal perfect hash functions.
33 -- To understand what a perfect hash function is, we define several notions.
34 -- These definitions are inspired from the following paper:
36 -- Zbigniew J. Czech, George Havas, and Bohdan S. Majewski ``An Optimal
37 -- Algorithm for Generating Minimal Perfect Hash Functions'', Information
38 -- Processing Letters, 43(1992) pp.257-264, Oct.1992
40 -- Let W be a set of m words. A hash function h is a function that maps the
41 -- set of words W into some given interval I of integers [0, k-1], where k is
42 -- an integer, usually k >= m. h (w) where w is a word in W computes an
43 -- address or an integer from I for the storage or the retrieval of that
44 -- item. The storage area used to store items is known as a hash table. Words
45 -- for which the same address is computed are called synonyms. Due to the
46 -- existence of synonyms a situation called collision may arise in which two
47 -- items w1 and w2 have the same address. Several schemes for resolving
48 -- collisions are known. A perfect hash function is an injection from the word
49 -- set W to the integer interval I with k >= m. If k = m, then h is a minimal
50 -- perfect hash function. A hash function is order preserving if it puts
51 -- entries into the hash table in a prespecified order.
53 -- A minimal perfect hash function is defined by two properties:
55 -- Since no collisions occur each item can be retrieved from the table in
56 -- *one* probe. This represents the "perfect" property.
58 -- The hash table size corresponds to the exact size of W and *no larger*.
59 -- This represents the "minimal" property.
61 -- The functions generated by this package require the words to be known in
62 -- advance (they are "static" hash functions). The hash functions are also
63 -- order preserving. If w2 is inserted after w1 in the generator, then h (w1)
64 -- < h (w2). These hashing functions are convenient for use with realtime
67 with System
.Perfect_Hash_Generators
;
69 package GNAT
.Perfect_Hash_Generators
is
71 package SPHG
renames System
.Perfect_Hash_Generators
;
73 Default_K_To_V
: constant Float := 2.05;
74 -- Default ratio for the algorithm. When K is the number of keys, V =
75 -- (K_To_V) * K is the size of the main table of the hash function. To
76 -- converge, the algorithm requires K_To_V to be strictly greater than 2.0.
78 Default_Pkg_Name
: constant String := "Perfect_Hash";
79 -- Default package name in which the hash function is defined
81 Default_Position
: constant String := "";
82 -- The generator allows selection of the character positions used in the
83 -- hash function. By default, all positions are selected.
85 Default_Tries
: constant Positive := 20;
86 -- This algorithm may not succeed to find a possible mapping on the first
87 -- try and may have to iterate a number of times. This constant bounds the
90 type Optimization
is new SPHG
.Optimization
;
91 -- Optimize either the memory space or the execution time. Note: in
92 -- practice, the optimization mode has little effect on speed. The tables
93 -- are somewhat smaller with Memory_Space.
95 Verbose
: Boolean renames SPHG
.Verbose
;
96 -- Output the status of the algorithm. For instance, the tables, the random
97 -- graph (edges, vertices) and selected char positions are output between
102 K_To_V
: Float := Default_K_To_V
;
103 Optim
: Optimization
:= Memory_Space
;
104 Tries
: Positive := Default_Tries
);
105 -- Initialize the generator and its internal structures. Set the ratio of
106 -- vertices over keys in the random graphs. This value has to be greater
107 -- than 2.0 in order for the algorithm to succeed. The word set is not
108 -- modified (in particular when it is already set). For instance, it is
109 -- possible to run several times the generator with different settings on
112 -- A classical way of doing is to Insert all the words and then to invoke
113 -- Initialize and Compute. If this fails to find a perfect hash function,
114 -- invoke Initialize again with other configuration parameters (probably
115 -- with a greater K_To_V ratio). Once successful, invoke Produce and then
119 -- Deallocate the internal structures and the words table
121 procedure Insert
(Value
: String);
122 -- Insert a new word into the table. ASCII.NUL characters are not allowed.
124 Too_Many_Tries
: exception renames SPHG
.Too_Many_Tries
;
125 -- Raised after Tries unsuccessful runs
127 procedure Compute
(Position
: String := Default_Position
);
128 -- Compute the hash function. Position allows the definition of selection
129 -- of character positions used in the word hash function. Positions can be
130 -- separated by commas and ranges like x-y may be used. Character '$'
131 -- represents the final character of a word. With an empty position, the
132 -- generator automatically produces positions to reduce the memory usage.
133 -- Raise Too_Many_Tries if the algorithm does not succeed within Tries
134 -- attempts (see Initialize).
137 (Pkg_Name
: String := Default_Pkg_Name
;
138 Use_Stdout
: Boolean := False);
139 -- Generate the hash function package Pkg_Name. This package includes the
140 -- minimal perfect Hash function. The output is normally placed in the
141 -- current directory, in files X.ads and X.adb, where X is the standard
142 -- GNAT file name for a package named Pkg_Name. If Use_Stdout is True, the
143 -- output goes to standard output, and no files are written.
145 end GNAT
.Perfect_Hash_Generators
;