1------------------------------------------------------------------------------
2--                                                                          --
3--                         GNAT COMPILER COMPONENTS                         --
4--                                                                          --
5--                          G N A T . R E G E X P                           --
6--                                                                          --
7--                                 S p e c                                  --
8--                                                                          --
9--           Copyright (C) 1998-2003 Ada Core Technologies, Inc.            --
10--                                                                          --
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 2,  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.  See the GNU General Public License --
17-- for  more details.  You should have  received  a copy of the GNU General --
18-- Public License  distributed with GNAT;  see file COPYING.  If not, write --
19-- to  the Free Software Foundation,  59 Temple Place - Suite 330,  Boston, --
20-- MA 02111-1307, USA.                                                      --
21--                                                                          --
22-- As a special exception,  if other files  instantiate  generics from this --
23-- unit, or you link  this unit with other files  to produce an executable, --
24-- this  unit  does not  by itself cause  the resulting  executable  to  be --
25-- covered  by the  GNU  General  Public  License.  This exception does not --
26-- however invalidate  any other reasons why  the executable file  might be --
27-- covered by the  GNU Public License.                                      --
28--                                                                          --
29-- GNAT was originally developed  by the GNAT team at  New York University. --
30-- Extensive contributions were provided by Ada Core Technologies Inc.      --
31--                                                                          --
32------------------------------------------------------------------------------
33
34--  Simple Regular expression matching
35
36--  This package provides a simple implementation of a regular expression
37--  pattern matching algorithm, using a subset of the syntax of regular
38--  expressions copied from familiar Unix style utilities.
39
40------------------------------------------------------------
41-- Summary of Pattern Matching Packages in GNAT Hierarchy --
42------------------------------------------------------------
43
44--  There are three related packages that perform pattern maching functions.
45--  the following is an outline of these packages, to help you determine
46--  which is best for your needs.
47
48--     GNAT.Regexp (files g-regexp.ads/g-regexp.adb)
49--       This is a simple package providing Unix-style regular expression
50--       matching with the restriction that it matches entire strings. It
51--       is particularly useful for file name matching, and in particular
52--       it provides "globbing patterns" that are useful in implementing
53--       unix or DOS style wild card matching for file names.
54
55--     GNAT.Regpat (files g-regpat.ads/g-regpat.adb)
56--       This is a more complete implementation of Unix-style regular
57--       expressions, copied from the original V7 style regular expression
58--       library written in C by Henry Spencer. It is functionally the
59--       same as this library, and uses the same internal data structures
60--       stored in a binary compatible manner.
61
62--     GNAT.Spitbol.Patterns (files g-spipat.ads/g-spipat.adb)
63--       This is a completely general patterm matching package based on the
64--       pattern language of SNOBOL4, as implemented in SPITBOL. The pattern
65--       language is modeled on context free grammars, with context sensitive
66--       extensions that provide full (type 0) computational capabilities.
67
68with Ada.Finalization;
69
70package GNAT.Regexp is
71
72   --  The regular expression must first be compiled, using the Compile
73   --  function, which creates a finite state matching table, allowing
74   --  very fast matching once the expression has been compiled.
75
76   --  The following is the form of a regular expression, expressed in Ada
77   --  reference manual style BNF is as follows
78
79   --     regexp ::= term
80
81   --     regexp ::= term | term          -- alternation (term or term ...)
82
83   --     term ::= item
84
85   --     term ::= item item ...          -- concatenation (item then item)
86
87   --     item ::= elmt                   -- match elmt
88   --     item ::= elmt *                 -- zero or more elmt's
89   --     item ::= elmt +                 -- one or more elmt's
90   --     item ::= elmt ?                 -- matches elmt or nothing
91
92   --     elmt ::= nchr                   -- matches given character
93   --     elmt ::= [nchr nchr ...]        -- matches any character listed
94   --     elmt ::= [^ nchr nchr ...]      -- matches any character not listed
95   --     elmt ::= [char - char]          -- matches chars in given range
96   --     elmt ::= .                      -- matches any single character
97   --     elmt ::= ( regexp )             -- parens used for grouping
98
99   --     char ::= any character, including special characters
100   --     nchr ::= any character except \()[].*+?^ or \char to match char
101   --     ... is used to indication repetition (one or more terms)
102
103   --  See also regexp(1) man page on Unix systems for further details
104
105   --  A second kind of regular expressions is provided. This one is more
106   --  like the wild card patterns used in file names by the Unix shell (or
107   --  DOS prompt) command lines. The grammar is the following:
108
109   --     regexp ::= term
110
111   --     term   ::= elmt
112
113   --     term   ::= elmt elmt ...     -- concatenation (elmt then elmt)
114   --     term   ::= *                 -- any string of 0 or more characters
115   --     term   ::= ?                 -- matches any character
116   --     term   ::= [char char ...]   -- matches any character listed
117   --     term   ::= [char - char]     -- matches any character in given range
118   --     term   ::= {elmt, elmt, ...} -- alternation (matches any of elmt)
119
120   --  Important note : This package was mainly intended to match regular
121   --  expressions against file names. The whole string has to match the
122   --  regular expression. If only a substring matches, then the function
123   --  Match will return False.
124
125   type Regexp is private;
126   --  Private type used to represent a regular expression
127
128   Error_In_Regexp : exception;
129   --  Exception raised when an error is found in the regular expression
130
131   function Compile
132     (Pattern        : String;
133      Glob           : Boolean := False;
134      Case_Sensitive : Boolean := True)
135      return           Regexp;
136   --  Compiles a regular expression S. If the syntax of the given
137   --  expression is invalid (does not match above grammar, Error_In_Regexp
138   --  is raised. If Glob is True, the pattern is considered as a 'globbing
139   --  pattern', that is a pattern as given by the second grammar above.
140   --  As a special case, if Pattern is the empty string it will always
141   --  match.
142
143   function Match (S : String; R : Regexp) return Boolean;
144   --  True if S matches R, otherwise False. Raises Constraint_Error if
145   --  R is an uninitialized regular expression value.
146
147private
148   type Regexp_Value;
149
150   type Regexp_Access is access Regexp_Value;
151
152   type Regexp is new Ada.Finalization.Controlled with record
153      R : Regexp_Access := null;
154   end record;
155
156   pragma Finalize_Storage_Only (Regexp);
157
158   procedure Finalize (R : in out Regexp);
159   --  Free the memory occupied by R
160
161   procedure Adjust (R : in out Regexp);
162   --  Called after an assignment (do a copy of the Regexp_Access.all)
163
164end GNAT.Regexp;
165