aboutsummaryrefslogblamecommitdiffstats
path: root/lib/inets/src/inets_app/inets_regexp.erl
blob: fc1608bc5af89fa5e51d72d44eb98a37f81dbcf9 (plain) (tree)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414





























































































































































































































































































































































































































                                                                              
%%
%% %CopyrightBegin%
%% 
%% Copyright Ericsson AB 2009. All Rights Reserved.
%% 
%% Licensed under the Apache License, Version 2.0 (the "License");
%% you may not use this file except in compliance with the License.
%% You may obtain a copy of the License at
%%
%%     http://www.apache.org/licenses/LICENSE-2.0
%%
%% Unless required by applicable law or agreed to in writing, software
%% distributed under the License is distributed on an "AS IS" BASIS,
%% WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
%% See the License for the specific language governing permissions and
%% limitations under the License.
%% 
%% %CopyrightEnd%
%%

-module(inets_regexp).

-export([parse/1, match/2, first_match/2, split/2, sub/3, gsub/3]).


%%%=========================================================================
%%%  API
%%%=========================================================================

%% parse(RegExp) -> {ok, RE} | {error, E}.
%% Parse the regexp described in the string RegExp.

parse(S) ->
    case (catch reg(S)) of
	{R, []} -> 
	    {ok, R};
	{_R, [C|_]} -> 
	    {error, {illegal, [C]}};
	{error, E} -> 
	    {error, E}
    end.


%% Find the longest match of RegExp in String.

match(S, RegExp) when is_list(RegExp) ->
    case parse(RegExp) of
	{ok,RE} -> match(S, RE);
	{error,E} -> {error,E}
    end;
match(S, RE) ->
    case match(RE, S, 1, 0, -1) of
	{Start,Len} when Len >= 0 ->
	    {match, Start, Len};
	{_Start,_Len} -> 
	    nomatch
    end.

%% Find the first match of RegExp in String.

first_match(S, RegExp) when is_list(RegExp) ->
    case parse(RegExp) of
	{ok, RE} -> 
	    first_match(S, RE);
	{error, E} -> 
	    {error, E}
    end;
first_match(S, RE) ->
    case first_match(RE, S, 1) of
	{Start,Len} when Len >= 0 ->
	    {match, Start,Len};
	nomatch -> 
	    nomatch
    end.

first_match(RE, S, St) when S =/= [] ->
    case re_apply(S, St, RE) of
	{match, P, _Rest} -> 
	    {St, P-St};
	nomatch -> 
	    first_match(RE, tl(S), St+1)
    end;
first_match(_RE, [], _St) -> 
    nomatch.


match(RE, S, St, Pos, L) ->
    case first_match(RE, S, St) of
	{St1, L1} ->
	    Nst = St1 + 1,
	    if L1 > L -> 
		    match(RE, lists:nthtail(Nst-St, S), Nst, St1, L1);
	       true -> 
		    match(RE, lists:nthtail(Nst-St, S), Nst, Pos, L)
	    end;
	nomatch -> 
	    {Pos, L}
    end.


%% Split a string into substrings where the RegExp describes the
%% field seperator. The RegExp " " is specially treated.

split(String, " ") ->				%This is really special
    {ok, RE} = parse("[ \t]+"),
    case split_apply(String, RE, true) of
	[[]|Ss] -> 
	    {ok,Ss};
	Ss -> 
	    {ok,Ss}
    end;
split(String, RegExp) when is_list(RegExp) ->
    case parse(RegExp) of
	{ok, RE} -> 
	    {ok, split_apply(String, RE, false)};
	{error, E} -> 
	    {error,E}
    end;
split(String, RE) -> 
    {ok, split_apply(String, RE, false)}.


%% Substitute the first match of the regular expression RegExp 
%% with the string Replace in String. Accept pre-parsed regular
%% expressions.

sub(String, RegExp, Rep) when is_list(RegExp) ->
    case parse(RegExp) of
	{ok, RE} -> 
	    sub(String, RE, Rep);
	{error, E} -> 
	    {error, E}
    end;
sub(String, RE, Rep) ->
    Ss = sub_match(String, RE, 1),
    {ok, sub_repl(Ss, Rep, String, 1), length(Ss)}.


%% Substitute every match of the regular expression RegExp with 
%% the string New in String. Accept pre-parsed regular expressions.

gsub(String, RegExp, Rep) when is_list(RegExp) ->
    case parse(RegExp) of
	{ok, RE} -> 
	    gsub(String, RE, Rep);
	{error, E} -> 
	    {error, E}
    end;
gsub(String, RE, Rep) ->
    Ss = matches(String, RE, 1),
    {ok, sub_repl(Ss, Rep, String, 1), length(Ss)}.


%%%========================================================================
%%% Internal functions
%%%========================================================================

%% This is the regular expression grammar used. It is equivalent to the
%% one used in AWK, except that we allow ^ $ to be used anywhere and fail
%% in the matching.
%%
%% reg -> reg1 : '$1'.
%% reg1 -> reg1 "|" reg2 : {'or','$1','$2'}.
%% reg1 -> reg2 : '$1'.
%% reg2 -> reg2 reg3 : {concat,'$1','$2'}.
%% reg2 -> reg3 : '$1'.
%% reg3 -> reg3 "*" : {kclosure,'$1'}.
%% reg3 -> reg3 "+" : {pclosure,'$1'}.
%% reg3 -> reg3 "?" : {optional,'$1'}.
%% reg3 -> reg4 : '$1'.
%% reg4 -> "(" reg ")" : '$2'.
%% reg4 -> "\\" char : '$2'.
%% reg4 -> "^" : bos.
%% reg4 -> "$" : eos.
%% reg4 -> "." : char.
%% reg4 -> "[" class "]" : {char_class,char_class('$2')}
%% reg4 -> "[" "^" class "]" : {comp_class,char_class('$3')}
%% reg4 -> "\"" chars "\"" : char_string('$2')
%% reg4 -> char : '$1'.
%% reg4 -> empty : epsilon.
%%  The grammar of the current regular expressions. The actual parser
%%  is a recursive descent implementation of the grammar.

reg(S) -> reg1(S).

%% reg1 -> reg2 reg1'
%% reg1' -> "|" reg2
%% reg1' -> empty

reg1(S0) ->
    {L,S1} = reg2(S0),
    reg1p(S1, L).

reg1p([$||S0], L) ->
    {R,S1} = reg2(S0),
    reg1p(S1, {'or',L,R});
reg1p(S, L) -> {L,S}.

%% reg2 -> reg3 reg2'
%% reg2' -> reg3
%% reg2' -> empty

reg2(S0) ->
    {L,S1} = reg3(S0),
    reg2p(S1, L).

reg2p([C|S0], L) when (C =/= $|) andalso (C =/= $)) ->
    {R,S1} = reg3([C|S0]),
    reg2p(S1, {concat,L,R});
reg2p(S, L) -> {L,S}.

%% reg3 -> reg4 reg3'
%% reg3' -> "*" reg3'
%% reg3' -> "+" reg3'
%% reg3' -> "?" reg3'
%% reg3' -> empty

reg3(S0) ->
    {L,S1} = reg4(S0),
    reg3p(S1, L).

reg3p([$*|S], L) -> reg3p(S, {kclosure,L});
reg3p([$+|S], L) -> reg3p(S, {pclosure,L});
reg3p([$?|S], L) -> reg3p(S, {optional,L});
reg3p(S, L) -> {L,S}.

reg4([$(|S0]) ->
    case reg(S0) of
	{R,[$)|S1]} -> {R,S1};
	{_R,_S} -> throw({error,{unterminated,"("}})
    end;
reg4([$\\,O1,O2,O3|S]) 
  when ((O1 >= $0) andalso 
	(O1 =< $7) andalso 
	(O2 >= $0) andalso 
	(O2 =< $7) andalso 
	(O3 >= $0) andalso 
	(O3 =< $7)) ->
    {(O1*8 + O2)*8 + O3 - 73*$0,S};
reg4([$\\,C|S]) -> 
    {escape_char(C),S};
reg4([$\\]) -> 
    throw({error, {unterminated,"\\"}});
reg4([$^|S]) -> 
    {bos,S};
reg4([$$|S]) -> 
    {eos,S};
reg4([$.|S]) -> 
    {{comp_class,"\n"},S};
reg4("[^" ++ S0) ->
    case char_class(S0) of
	{Cc,[$]|S1]} -> {{comp_class,Cc},S1};
	{_Cc,_S} -> throw({error,{unterminated,"["}})
    end;
reg4([$[|S0]) ->
    case char_class(S0) of
	{Cc,[$]|S1]} -> {{char_class,Cc},S1};
	{_Cc,_S1} -> throw({error,{unterminated,"["}})
    end;
reg4([C|S]) 
  when (C =/= $*) andalso (C =/= $+) andalso (C =/= $?) andalso (C =/= $]) -> 
    {C, S};
reg4([C|_S]) -> 
    throw({error,{illegal,[C]}});
reg4([]) -> 
    {epsilon,[]}.

escape_char($n) -> $\n;				%\n = LF
escape_char($r) -> $\r;				%\r = CR
escape_char($t) -> $\t;				%\t = TAB
escape_char($v) -> $\v;				%\v = VT
escape_char($b) -> $\b;				%\b = BS
escape_char($f) -> $\f;				%\f = FF
escape_char($e) -> $\e;				%\e = ESC
escape_char($s) -> $\s;				%\s = SPACE
escape_char($d) -> $\d;				%\d = DEL
escape_char(C) -> C.

char_class([$]|S]) -> char_class(S, [$]]);
char_class(S) -> char_class(S, []).

char($\\, [O1,O2,O3|S]) when
  O1 >= $0, O1 =< $7, O2 >= $0, O2 =< $7, O3 >= $0, O3 =< $7 ->
    {(O1*8 + O2)*8 + O3 - 73*$0,S};
char($\\, [C|S]) -> {escape_char(C),S};
char(C, S) -> {C,S}.

char_class([C1|S0], Cc) when C1 =/= $] ->
    case char(C1, S0) of
	{Cf,[$-,C2|S1]} when C2 =/= $] ->
	    case char(C2, S1) of
		{Cl,S2} when Cf < Cl -> char_class(S2, [{Cf,Cl}|Cc]); 
		{Cl,_S2} -> throw({error,{char_class,[Cf,$-,Cl]}})
	    end;
	{C,S1} -> char_class(S1, [C|Cc])
    end;
char_class(S, Cc) -> {Cc,S}.


%% re_apply(String, StartPos, RegExp) -> re_app_res().
%%
%%  Apply the (parse of the) regular expression RegExp to String.  If
%%  there is a match return the position of the remaining string and
%%  the string if else return 'nomatch'. BestMatch specifies if we want
%%  the longest match, or just a match.
%%
%%  StartPos should be the real start position as it is used to decide
%%  if we ae at the beginning of the string.
%%
%%  Pass two functions to re_apply_or so it can decide, on the basis
%%  of BestMatch, whether to just any take any match or try both to
%%  find the longest. This is slower but saves duplicatng code.

re_apply(S, St, RE) -> re_apply(RE, [], S, St).

re_apply(epsilon, More, S, P) ->		%This always matches
    re_apply_more(More, S, P);
re_apply({'or',RE1,RE2}, More, S, P) ->
    re_apply_or(re_apply(RE1, More, S, P),
		re_apply(RE2, More, S, P));
re_apply({concat,RE1,RE2}, More, S0, P) ->
    re_apply(RE1, [RE2|More], S0, P);
re_apply({kclosure,CE}, More, S, P) ->
    %% Be careful with the recursion, explicitly do one call before
    %% looping.
    re_apply_or(re_apply_more(More, S, P),
		re_apply(CE, [{kclosure,CE}|More], S, P));
re_apply({pclosure,CE}, More, S, P) ->
    re_apply(CE, [{kclosure,CE}|More], S, P);
re_apply({optional,CE}, More, S, P) ->
    re_apply_or(re_apply_more(More, S, P),
		re_apply(CE, More, S, P));
re_apply(bos, More, S, 1) -> re_apply_more(More, S, 1);
re_apply(eos, More, [$\n|S], P) -> re_apply_more(More, S, P);
re_apply(eos, More, [], P) -> re_apply_more(More, [], P);
re_apply({char_class,Cc}, More, [C|S], P) ->
    case in_char_class(C, Cc) of
	true -> re_apply_more(More, S, P+1);
	false -> nomatch
    end;
re_apply({comp_class,Cc}, More, [C|S], P) ->
    case in_char_class(C, Cc) of
	true -> nomatch;
	false -> re_apply_more(More, S, P+1)
    end;
re_apply(C, More, [C|S], P) when is_integer(C) ->
    re_apply_more(More, S, P+1);
re_apply(_RE, _More, _S, _P) -> nomatch.

%% re_apply_more([RegExp], String, Length) -> re_app_res().

re_apply_more([RE|More], S, P) -> re_apply(RE, More, S, P);
re_apply_more([], S, P) -> {match,P,S}.

%% in_char_class(Char, Class) -> bool().

in_char_class(C, [{C1,C2}|_Cc]) when C >= C1, C =< C2 -> true;
in_char_class(C, [C|_Cc]) -> true;
in_char_class(C, [_|Cc]) -> in_char_class(C, Cc);
in_char_class(_C, []) -> false.

%% re_apply_or(Match1, Match2) -> re_app_res().
%%  If we want the best match then choose the longest match, else just
%%  choose one by trying sequentially.

re_apply_or({match,P1,S1},   {match,P2,_S2}) when P1 >= P2 -> {match,P1,S1};
re_apply_or({match,_P1,_S1}, {match,P2,S2}) -> {match,P2,S2};
re_apply_or(nomatch, R2) -> R2;
re_apply_or(R1, nomatch) -> R1.


matches(S, RE, St) ->
    case first_match(RE, S, St) of
	{St1,0} -> 
	    [{St1,0}|matches(string:substr(S, St1+2-St), RE, St1+1)];
	{St1,L1} -> 
	    [{St1,L1}|matches(string:substr(S, St1+L1+1-St), RE, St1+L1)];
	nomatch -> 
	    []
    end.

sub_match(S, RE, St) ->
    case first_match(RE, S, St) of
	{St1,L1} -> [{St1,L1}];
	nomatch -> []
    end.

sub_repl([{St,L}|Ss], Rep, S, Pos) ->
    Rs = sub_repl(Ss, Rep, S, St+L),
    string:substr(S, Pos, St-Pos) ++ 
	sub_repl(Rep, string:substr(S, St, L), Rs);
sub_repl([], _Rep, S, Pos) -> 
    string:substr(S, Pos).

sub_repl([$&|Rep], M, Rest) -> M ++ sub_repl(Rep, M, Rest);
sub_repl("\\&" ++ Rep, M, Rest) -> [$&|sub_repl(Rep, M, Rest)];
sub_repl([C|Rep], M, Rest) -> [C|sub_repl(Rep, M, Rest)];
sub_repl([], _M, Rest) -> Rest.

split_apply(S, RE, Trim) -> split_apply(S, 1, RE, Trim, []).

split_apply([], _P, _RE, true, []) -> 
    [];
split_apply([], _P, _RE, _T, Sub) -> 
    [lists:reverse(Sub)];
split_apply(S, P, RE, T, Sub) ->
    case re_apply(S, P, RE) of
	{match,P,_Rest} ->
	    split_apply(tl(S), P+1, RE, T, [hd(S)|Sub]);
	{match,P1,Rest} ->
	    [lists:reverse(Sub)|split_apply(Rest, P1, RE, T, [])];
	nomatch ->
	    split_apply(tl(S), P+1, RE, T, [hd(S)|Sub])
    end.