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
|
#include <Rinternals.h>
// A macro similar to SET_STRING_ELT, it assumes a string vector protected with
// PROTECT_WITH_INDEX, will automatically grow it if needed.
#define SET_STRING_ELT2(X, I, VAL, P_IDX) { \
R_xlen_t len = Rf_xlength(X); \
R_xlen_t i = I; \
if (i >= len) { \
len *= 2; \
REPROTECT(X = Rf_lengthgets(X, len), P_IDX); \
} \
SET_STRING_ELT(X, i, VAL); \
}
Rboolean str_is_ASCII(const char *str) {
const char *p;
for(p = str; *p; p++) {
if((unsigned int)*p > 0x7F) return FALSE;
}
return TRUE;
}
// Break template text into character vector. The first element element of the
// resulting vector is HTML, the next is R code, and they continue alternating.
// [[export]]
SEXP template_dfa(SEXP x_sxp) {
typedef enum {
html,
code,
html_oneOpenBracket,
code_oneCloseBracket,
code_string1,
code_string1_backslash,
code_string2,
code_string2_backslash,
code_backtick,
code_backtick_backslash,
code_percentOp,
code_comment,
code_comment_oneCloseBracket
} State;
if (Rf_xlength(x_sxp) != 1) {
Rf_error("Input HTML must be a character vector of length 1");
}
SEXP input_sxp = STRING_ELT(x_sxp, 0);
if (!(Rf_getCharCE(input_sxp) == CE_UTF8 || str_is_ASCII(CHAR(input_sxp)))) {
Rf_warning("Input HTML must have a UTF-8 encoding");
}
SEXP str;
SEXP pieces = Rf_allocVector(STRSXP, 10);
R_xlen_t pieces_num = 0;
PROTECT_INDEX pieces_idx;
PROTECT_WITH_INDEX(pieces, &pieces_idx);
const char* input = CHAR(input_sxp);
int pieceStartIdx = 0;
R_xlen_t len = Rf_xlength(input_sxp);
char c;
State state = html;
for (R_xlen_t i=0; i < len; i++) {
c = input[i];
switch (state) {
case html:
switch (c) {
case '{':
state = html_oneOpenBracket; break;
}
break;
case html_oneOpenBracket:
switch (c) {
case '{':
state = code;
str = PROTECT(Rf_mkCharLenCE(input + pieceStartIdx, i - pieceStartIdx - 1, CE_UTF8));
SET_STRING_ELT2(pieces, pieces_num++, str, pieces_idx);
UNPROTECT(1);
pieceStartIdx = i + 1;
break;
default:
state = html;
}
break;
case code:
switch (c) {
case '}':
state = code_oneCloseBracket; break;
case '\'':
state = code_string1; break;
case '"':
state = code_string2; break;
case '`':
state = code_backtick; break;
case '%':
state = code_percentOp; break;
case '#':
state = code_comment; break;
}
break;
case code_oneCloseBracket:
switch (c) {
case '}':
state = html;
str = PROTECT(Rf_mkCharLenCE(input + pieceStartIdx, i - pieceStartIdx - 1, CE_UTF8));
SET_STRING_ELT2(pieces, pieces_num++, str, pieces_idx);
UNPROTECT(1);
pieceStartIdx = i + 1;
break;
default: state = code;
}
break;
case code_string1:
switch (c) {
case '\\':
state = code_string1_backslash; break;
case '\'':
state = code; break;
}
break;
case code_string1_backslash:
state = code_string1;
break;
case code_string2:
switch (c) {
case '\\':
state = code_string2_backslash; break;
case '\"':
state = code; break;
}
break;
case code_string2_backslash:
state = code_string2;
break;
case code_backtick:
switch (c) {
case '\\':
state = code_backtick_backslash; break;
case '`':
state = code; break;
}
break;
case code_backtick_backslash:
state = code_backtick;
break;
case code_percentOp:
switch (c) {
case '%':
state = code; break;
}
break;
case code_comment:
switch (c) {
case '}':
state = code_comment_oneCloseBracket; break;
case '\n':
state = code; break;
}
break;
case code_comment_oneCloseBracket:
switch (c) {
case '}':
state = html;
str = PROTECT(Rf_mkCharLenCE(input + pieceStartIdx, i - pieceStartIdx - 1, CE_UTF8));
SET_STRING_ELT2(pieces, pieces_num++, str, pieces_idx);
UNPROTECT(1);
pieceStartIdx = i + 1;
break;
default:
state = code;
}
break;
}
}
if (!(state == html || state == html_oneOpenBracket)) {
Rf_error("HTML template did not end in html state (missing closing \"}}\").");
}
// Add ending HTML piece
str = PROTECT(Rf_mkCharLenCE(input + pieceStartIdx, len - pieceStartIdx, CE_UTF8));
SET_STRING_ELT2(pieces, pieces_num++, str, pieces_idx);
UNPROTECT(1);
if (pieces_num < Rf_xlength(pieces)) {
// Using SETLENGTH and SET_TRUELENGTH in this way allows us to resize the
// vector without an extra copy.
SETLENGTH(pieces, pieces_num);
SET_TRUELENGTH(pieces, pieces_num);
}
UNPROTECT(1);
return pieces;
}
|