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
|
%%
%% %CopyrightBegin%
%%
%% Copyright Ericsson AB 2003-2016. 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%
%%
%% Description : Token scanner for XPATH grammar
%%%----------------------------------------------------------------------
%%%
%%% The XPATH grammar is a bit tricky, due to operator overloading.
%%% This version of the scanner is based on the XPATH spec:
%%% http://www.w3.org/TR/1999/REC-xpath-19991116 (XPATH version 1.0)
%%%
%%% Quote from the spec:
%%%
%%% "The following special tokenization rules must be applied in the order
%%% specified to disambiguate the ExprToken grammar:
%%%
%%% o If there is a preceding token and the preceding token is not one of
%%% @, ::. (, [, or an Operator, then a * must be recognized as a
%%% MultiplyOperator and an NCName must be recognized as an OperatorName
%%% o If the character following an NCName (possible after intervening
%%% ExprWhiteSpace) is (, then the token must be recognized as a NodeType
%%% or a FunctionName.
%%% o If the two characters following an NCName (possible after intervening
%%% ExprWhiteSpace) are ::, then the token must be recognized as an
%%% AxisName.
%%% o Otherwise, the token must not be recognized as a MultiplyOperator, an
%%% OperatorName, a NodeType, a FunctionName, or an AxisName."
%%%----------------------------------------------------------------------
-module(xmerl_xpath_scan).
%% main API
-export([tokens/1]).
%% exported helper functions
-export([scan_number/1]).
-include("xmerl.hrl").
-define(L, 1).
tokens(Str) ->
tokens(strip_ws(Str), []).
tokens([], Acc) ->
lists:reverse([{'$end', ?L, '$end'}|Acc]);
tokens(Str, Acc) ->
case scan_token(Str, Acc) of
{rescan, NewStr} ->
tokens(NewStr, Acc);
{Token, T} ->
tokens(strip_ws(T), [Token|Acc])
end.
%% Expr Tokens
scan_token("(" ++ T, _A) -> {{'(', ?L, '('}, T};
scan_token(")" ++ T, _A) -> {{')', ?L, ')'}, T};
scan_token("[" ++ T, _A) -> {{'[', ?L, '['}, T};
scan_token("]" ++ T, _A) -> {{']', ?L, ']'}, T};
scan_token(".." ++ T, _A) -> {rescan,"parent::node()" ++ T} ;
% {{'..',?L,'..'}, T};
scan_token("@" ++ T, _A) -> {rescan,"attribute::" ++ T};
% {{'@',?L,'@'},T};
scan_token("," ++ T, _A) -> {{',', ?L, ','}, T};
scan_token("::" ++ T, _A) -> {{'::', ?L, '::'}, T};
%% operators
scan_token("//" ++ T, _A) -> {rescan,"/descendant-or-self::node()/" ++ T};
% {{'//',?L,'//'},T};
scan_token("/" ++ T, _A) -> {{'/', ?L, '/'}, T};
scan_token("|" ++ T, _A) -> {{'|', ?L, '|'}, T};
scan_token("+" ++ T, _A) -> {{'+', ?L, '+'}, T};
scan_token("-" ++ T, _A) -> {{'-', ?L, '-'}, T};
scan_token("=" ++ T, _A) -> {{'=', ?L, '='}, T};
scan_token("!=" ++ T, _A) -> {{'!=', ?L, '!='}, T};
scan_token("<=" ++ T, _A) -> {{'<=', ?L, '<='}, T};
scan_token("<" ++ T, _A) -> {{'<', ?L, '<'}, T};
scan_token(">=" ++ T, _A) -> {{'>=', ?L, '>='}, T};
scan_token(">" ++ T, _A) -> {{'>', ?L, '>'}, T};
scan_token("*" ++ T, A) ->
Tok =
case A of
[{X,_,_}|_] ->
case special_token(X) of
false ->
{'*', ?L, '*'};
true ->
{'wildcard', ?L, 'wildcard'}
end;
_ ->
{'wildcard', ?L, 'wildcard'}
end,
{Tok, T};
%% numbers
scan_token(Str = [H|_], _A) when H >= $0, H =< $9 ->
scan_number(Str);
scan_token(Str = [$., H|_], A) when H >= $0, H =< $9 ->
scan_number(Str, A);
scan_token("." ++ T, _A) ->
% {{'.', ?L, '.'}, T};
{rescan, "self::node()" ++ T};
%% Variable Reference
scan_token([$$|T], _A) ->
{{Prefix, Local}, T1} = scan_name(T),
case Prefix of
[] ->
{{var_reference, ?L, list_to_atom(Local)}, T1};
_ ->
{{var_reference, ?L, list_to_atom(Prefix++":"++Local)}, T1}
end;
scan_token([H|T], _A) when H == $" ; H == $' ->
{Literal, T1} = scan_literal(T, H, []),
{{literal, ?L, Literal}, T1};
scan_token(T, A) ->
{{Prefix, Local}, T1} = scan_name(T),
case A of
[{X,_,_}|_] ->
case special_token(X) of
false ->
operator_name(Prefix, Local, T1);
true ->
other_name(Prefix, Local, strip_ws(T1))
end;
_ ->
other_name(Prefix, Local, T1)
end.
operator_name([], "and", T) -> {{'and', ?L, 'and'}, T};
operator_name([], "or", T) -> {{'or', ?L, 'or'}, T};
operator_name([], "mod", T) -> {{'mod', ?L, 'mod'}, T};
operator_name([], "div", T) -> {{'div', ?L, 'div'}, T}.
other_name(Prefix, [], "*" ++ T) ->
%% [37] NameTest ::= '*' | NCName ':' '*' | QName
{{prefix_test, ?L, Prefix}, T};
other_name(Prefix, Local, T = "(" ++ _) ->
node_type_or_function_name(Prefix, Local, T);
other_name(Prefix, Local, T = "::" ++ _) ->
axis(Prefix, Local, T);
other_name([], Local, T) ->
{{name, ?L, {list_to_atom(Local), [], Local}}, T};
other_name(Prefix, Local, T) ->
{{name, ?L, {list_to_atom(Prefix++":"++Local), Prefix, Local}}, T}.
%% node types
node_type_or_function_name([], "comment", T) ->
{{node_type, ?L, comment}, T};
node_type_or_function_name([], "text", T) ->
{{node_type, ?L, text}, T};
node_type_or_function_name([], "processing-instruction", T) ->
{{'processing-instruction', ?L, 'processing-instruction'}, T};
node_type_or_function_name([], "node", T) ->
{{node_type, ?L, node}, T};
node_type_or_function_name(Prefix, Local, T) ->
{{function_name, ?L, list_to_atom(Prefix ++ Local)}, T}.
%% axis names
axis([], "ancestor-or-self", T) -> {{axis, ?L, ancestor_or_self}, T};
axis([], "ancestor", T) -> {{axis, ?L, ancestor}, T};
axis([], "attribute", T) -> {{axis, ?L, attribute}, T};
axis([], "child", T) -> {{axis, ?L, child}, T};
axis([], "descendant-or-self", T) -> {{axis, ?L, descendant_or_self}, T};
axis([], "descendant", T) -> {{axis, ?L, descendant}, T};
axis([], "following-sibling", T) -> {{axis, ?L, following_sibling}, T};
axis([], "following", T) -> {{axis, ?L, following}, T};
axis([], "namespace", T) -> {{axis, ?L, namespace}, T};
axis([], "parent", T) -> {{axis, ?L, parent}, T};
axis([], "preceding-sibling", T) -> {{axis, ?L, preceding_sibling}, T};
axis([], "preceding", T) -> {{axis, ?L, preceding}, T};
axis([], "self", T) -> {{axis, ?L, self}, T}.
scan_literal([H|T], H, Acc) ->
{lists:reverse(Acc), T};
scan_literal([H|T], Delim, Acc) ->
scan_literal(T, Delim, [H|Acc]).
scan_name([H1, H2 | T]) when H1 == $: ; H1 == $_ ->
if ?whitespace(H2) ->
exit({invalid_name, [H1, H2, '...']});
true ->
scan_prefix(T, [H2, H1])
end;
scan_name([H|T]) ->
case xmerl_lib:is_letter(H) of
true ->
scan_prefix(T, [H]);
false ->
exit({invalid_name, lists:sublist([H|T], 1, 6)})
end;
scan_name(Str) ->
exit({invalid_name, lists:sublist(Str, 1, 6)}).
scan_prefix([], Acc) ->
{{[], lists:reverse(Acc)}, []};
scan_prefix(Str = [H|_], Acc) when ?whitespace(H) ->
{{[], lists:reverse(Acc)}, Str};
scan_prefix(T = "::" ++ _, Acc) ->
%% This is the next token
{{[], lists:reverse(Acc)}, T};
scan_prefix(":" ++ T, Acc) ->
{LocalPart, T1} = scan_local_part(T, []),
Prefix = lists:reverse(Acc),
{{Prefix, LocalPart}, T1};
scan_prefix(Str = [H|T], Acc) ->
case xmerl_lib:is_namechar(H) of
true ->
scan_prefix(T, [H|Acc]);
false ->
{{[], lists:reverse(Acc)}, Str}
end.
scan_local_part([], Acc) ->
{lists:reverse(Acc), []};
scan_local_part(Str = [H|_], Acc) when ?whitespace(H) ->
{lists:reverse(Acc), Str};
scan_local_part(Str = [H|T], Acc) ->
case xmerl_lib:is_namechar(H) of
true ->
scan_local_part(T, [H|Acc]);
false ->
{lists:reverse(Acc), Str}
end.
scan_number(T) ->
scan_number(T, []).
scan_number([], Acc) ->
{{number, ?L, list_to_integer(lists:reverse(Acc))}, []};
scan_number("." ++ T, []) ->
{Digits, T1} = scan_digits(T, ".0"),
Number = list_to_float(Digits),
{{number, ?L, Number}, T1};
scan_number("." ++ T, Acc) ->
{Digits, T1} = scan_digits(T, "." ++ Acc),
Number = list_to_float(Digits),
{{number, ?L, Number}, T1};
scan_number([H|T], Acc) when H >= $0, H =< $9 ->
scan_number(T, [H|Acc]);
scan_number(T, Acc) ->
{{number, ?L, list_to_integer(lists:reverse(Acc))}, T}.
scan_digits([], Acc) ->
{lists:reverse(Acc), []};
scan_digits([H|T], Acc) when H >= $0, H =< $9 ->
scan_digits(T, [H|Acc]);
scan_digits(T, Acc) ->
{lists:reverse(Acc), T}.
strip_ws([H|T]) when ?whitespace(H) ->
strip_ws(T);
strip_ws(T) ->
T.
%% special_token('@') -> true;
special_token('::') -> true;
special_token(',') -> true;
special_token('(') -> true;
special_token('[') -> true;
special_token('/') -> true;
%% special_token('//') -> true;
special_token('|') -> true;
special_token('+') -> true;
special_token('-') -> true;
special_token('=') -> true;
special_token('!=') -> true;
special_token('<') -> true;
special_token('<=') -> true;
special_token('>') -> true;
special_token('>=') -> true;
special_token('and') -> true;
special_token('or') -> true;
special_token('mod') -> true;
special_token('div') -> true;
special_token(_) -> false.
|
