about summary refs log tree commit diff
path: root/src/libexpr/lexer.l
blob: 3ac7ce723cb38e65bbfd5527739394f325193488 (plain) (blame)
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
%option reentrant bison-bridge bison-locations
%option noyywrap
%option never-interactive
%option stack
%option nodefault
%option nounput noyy_top_state


%x STRING
%x IND_STRING
%x INSIDE_DOLLAR_CURLY


%{
#include "nixexpr.hh"
#include "parser-tab.hh"

using namespace nix;

namespace nix {


static void initLoc(YYLTYPE * loc)
{
    loc->first_line = loc->last_line = 1;
    loc->first_column = loc->last_column = 1;
}


static void adjustLoc(YYLTYPE * loc, const char * s, size_t len)
{
    loc->first_line = loc->last_line;
    loc->first_column = loc->last_column;

    while (len--) {
       switch (*s++) {
       case '\r':
           if (*s == '\n') /* cr/lf */
               s++;
           /* fall through */
       case '\n':
           ++loc->last_line;
           loc->last_column = 1;
           break;
       default:
           ++loc->last_column;
       }
    }
}


static Expr * unescapeStr(SymbolTable & symbols, const char * s)
{
    string t;
    char c;
    while ((c = *s++)) {
        if (c == '\\') {
            assert(*s);
            c = *s++;
            if (c == 'n') t += '\n';
            else if (c == 'r') t += '\r';
            else if (c == 't') t += '\t';
            else t += c;
        }
        else if (c == '\r') {
            /* Normalise CR and CR/LF into LF. */
            t += '\n';
            if (*s == '\n') s++; /* cr/lf */
        }
        else t += c;
    }
    return new ExprString(symbols.create(t));
}


}

#define YY_USER_INIT initLoc(yylloc)
#define YY_USER_ACTION adjustLoc(yylloc, yytext, yyleng);

#define PUSH_STATE(state) yy_push_state(state, yyscanner)
#define POP_STATE() yy_pop_state(yyscanner)

%}


ID          [a-zA-Z\_][a-zA-Z0-9\_\'\-]*
INT         [0-9]+
FLOAT       (([1-9][0-9]*\.[0-9]*)|(0?\.[0-9]+))([Ee][+-]?[0-9]+)?
PATH        [a-zA-Z0-9\.\_\-\+]*(\/[a-zA-Z0-9\.\_\-\+]+)+
HPATH       \~(\/[a-zA-Z0-9\.\_\-\+]+)+
SPATH       \<[a-zA-Z0-9\.\_\-\+]+(\/[a-zA-Z0-9\.\_\-\+]+)*\>
URI         [a-zA-Z][a-zA-Z0-9\+\-\.]*\:[a-zA-Z0-9\%\/\?\:\@\&\=\+\$\,\-\_\.\!\~\*\']+


%%

<INITIAL,INSIDE_DOLLAR_CURLY>{


if          { return IF; }
then        { return THEN; }
else        { return ELSE; }
assert      { return ASSERT; }
with        { return WITH; }
let         { return LET; }
in          { return IN; }
rec         { return REC; }
inherit     { return INHERIT; }
or          { return OR_KW; }
\.\.\.      { return ELLIPSIS; }

\=\=        { return EQ; }
\!\=        { return NEQ; }
\<\=        { return LEQ; }
\>\=        { return GEQ; }
\&\&        { return AND; }
\|\|        { return OR; }
\-\>        { return IMPL; }
\/\/        { return UPDATE; }
\+\+        { return CONCAT; }

{ID}        { yylval->id = strdup(yytext); return ID; }
{INT}       { errno = 0;
              yylval->n = strtol(yytext, 0, 10);
              if (errno != 0)
                  throw ParseError(format("invalid integer ‘%1%’") % yytext);
              return INT;
            }
{FLOAT}     { errno = 0;
              yylval->nf = strtod(yytext, 0);
              if (errno != 0)
                  throw ParseError(format("invalid float ‘%1%’") % yytext);
              return FLOAT;
            }

\$\{        { PUSH_STATE(INSIDE_DOLLAR_CURLY); return DOLLAR_CURLY; }
}

\}                           { return '}'; }
<INSIDE_DOLLAR_CURLY>\}      { POP_STATE(); return '}'; }
\{                           { return '{'; }
<INSIDE_DOLLAR_CURLY>\{      { PUSH_STATE(INSIDE_DOLLAR_CURLY); return '{'; }

<INITIAL,INSIDE_DOLLAR_CURLY>\"          { PUSH_STATE(STRING); return '"'; }
<STRING>([^\$\"\\]|\$[^\{\"\\]|\\.|\$\\.)*\$/\" |
<STRING>([^\$\"\\]|\$[^\{\"\\]|\\.|\$\\.)+ {
              /* It is impossible to match strings ending with '$' with one
                 regex because trailing contexts are only valid at the end
                 of a rule. (A sane but undocumented limitation.) */
              yylval->e = unescapeStr(data->symbols, yytext);
              return STR;
            }
<STRING>\$\{  { PUSH_STATE(INSIDE_DOLLAR_CURLY); return DOLLAR_CURLY; }
<STRING>\"  { POP_STATE(); return '"'; }
<STRING>.   return yytext[0]; /* just in case: shouldn't be reached */

<INITIAL,INSIDE_DOLLAR_CURLY>\'\'(\ *\n)?     { PUSH_STATE(IND_STRING); return IND_STRING_OPEN; }
<IND_STRING>([^\$\']|\$[^\{\']|\'[^\'\$])+ {
                   yylval->e = new ExprIndStr(yytext);
                   return IND_STR;
                 }
<IND_STRING>\'\'\$ {
                   yylval->e = new ExprIndStr("$");
                   return IND_STR;
                 }
<IND_STRING>\'\'\' {
                   yylval->e = new ExprIndStr("''");
                   return IND_STR;
                 }
<IND_STRING>\'\'\\. {
                   yylval->e = unescapeStr(data->symbols, yytext + 2);
                   return IND_STR;
                 }
<IND_STRING>\$\{ { PUSH_STATE(INSIDE_DOLLAR_CURLY); return DOLLAR_CURLY; }
<IND_STRING>\'\' { POP_STATE(); return IND_STRING_CLOSE; }
<IND_STRING>\'   {
                   yylval->e = new ExprIndStr("'");
                   return IND_STR;
                 }
<IND_STRING>.    return yytext[0]; /* just in case: shouldn't be reached */

<INITIAL,INSIDE_DOLLAR_CURLY>{

{PATH}      { yylval->path = strdup(yytext); return PATH; }
{HPATH}     { yylval->path = strdup(yytext); return HPATH; }
{SPATH}     { yylval->path = strdup(yytext); return SPATH; }
{URI}       { yylval->uri = strdup(yytext); return URI; }

[ \t\r\n]+    /* eat up whitespace */
\#[^\r\n]*    /* single-line comments */
\/\*([^*]|\*+[^*/])*\*+\/  /* long comments */

.           return yytext[0];

}

<<EOF>> { data->atEnd = true; return 0; }

%%