jchris (owner)

Revisions

gist: 3212 Download_button fork
public
Public Clone URL: git://gist.github.com/3212.git
Embed All Files: show embed
json_grammer.yrl #
raw 
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

Nonterminals array element elements object members member.

 
Terminals '{' '}' '[' ']' string ',' ':' integer float true false null.

 
Rootsymbol element.

 
object -> '{' members '}' : {obj, '$2'}.

object -> '{' '}' : {obj, []}.

% object -> '{' member '}' : {'$2'}. % results in a shift/reduce conflict...

 
members -> member ',' members : ['$1' | '$3'].

members -> member : ['$1'].

 
member -> string ':' element : {element(3, '$1'),'$3'}.

 
array -> '[' elements ']' : list_to_tuple('$2').

 
elements -> element ',' elements : ['$1' | '$3'].

elements -> element : ['$1'].

elements -> '$empty' : [].

 
element -> string : element(3, '$1').

element -> array : '$1'.

element -> object : '$1'.

element -> integer : element(3, '$1').

element -> float : element(3, '$1').

element -> true : element(1, '$1').

element -> false : element(1, '$1').

element -> null : element(1, '$1').
json_lex2.xrl #
raw 
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

Definitions.

 
ST = [^"]

L = [A-Za-z]

WS  = ([\000-\s]|%.*)

D = [0-9]

H = [0-9a-fA-F]

 
Rules.

 
{   : {token, {'{', TokenLine}}.

}   : {token, {'}', TokenLine}}.

 
\[   : {token, {'[', TokenLine}}.

\]   : {token, {']', TokenLine}}.

 
\-?{D}+\.{D}+((E|e)(\+|\-)?{D}+)? : {token,{float,TokenLine,list_to_float(TokenChars)}}.

\-?{D}+(E|e)(\+|\-)?{D}+ : {token,{float,TokenLine,whole_float(TokenChars)}}.

\-?{D}+		:	{token,{integer,TokenLine,list_to_integer(TokenChars)}}.

 
% "[^"\\]*(\\[^u][^"\\]*)*"  : {token,{string,TokenLine,strip(unicode_string(TokenChars),TokenLen)}}.

"[^"\\]*(\\.[^"\\]*)*"  : {token,{string,TokenLine,parse_string(strip(TokenChars,TokenLen))}}.

 
 
% \\u{H}{H}{H}{H} : {token, {unicode, TokenLine,TokenChars}}.

 
true : {token,{'true', TokenLine}}.

false : {token,{'false', TokenLine}}.

null : {token,{'null', TokenLine}}.

 
: : {token, {':', TokenLine}}.

, : {token, {',', TokenLine}}.

 
{WS}+       :   skip_token.

 
Erlang code.

% "

 
-define(LOG(Name, Value), 

        io:format("{~p:~p}: ~p -> ~s~n", [?MODULE, ?LINE, Name, Value])).

-define(PLOG(Name, Value), 

        io:format("{~p:~p}: ~p -> ~p~n", [?MODULE, ?LINE, Name, Value])).

 
strip(TokenChars,TokenLen) -> lists:sublist(TokenChars, 2, TokenLen - 2).

 
whole_float(TokenChars) ->

  {ok, NowFloat, 1 } = regexp:sub(TokenChars,"e",".0e"),

  list_to_float(NowFloat).

 
unescape([$\\,$\"|Cs]) -> [$\"|unescape(Cs)];

unescape([$\\,$\\|Cs]) -> [$\\|unescape(Cs)];

unescape([$\\,$/|Cs]) -> [$/|unescape(Cs)];

unescape([$\\,$b|Cs]) -> [$\b|unescape(Cs)];

unescape([$\\,$f|Cs]) -> [$\f|unescape(Cs)];

unescape([$\\,$n|Cs]) -> [$\n|unescape(Cs)];

unescape([$\\,$r|Cs]) -> [$\r|unescape(Cs)];

unescape([$\\,$t|Cs]) -> [$\t|unescape(Cs)];

unescape([$\\,$u,C0,C1,C2,C3|Cs]) ->

    C = dehex(C0) bor

	(dehex(C1) bsl 4) bor

	(dehex(C2) bsl 8) bor

	(dehex(C3) bsl 12),

    [C|unescape(Cs)];

unescape([C|Cs]) -> [C|unescape(Cs)];

unescape([]) -> [].

 
dehex(C) when C >= $0, C =< $9 -> C - $0;

dehex(C) when C >= $a, C =< $f -> C - $a + 10;

dehex(C) when C >= $A, C =< $F -> C - $A + 10.

 
parse_string(StringChars) -> 

    unescape(StringChars).