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
|
/*-------------------------------------------------------------------------
*
* parser.c
* Main entry point/driver for PostgreSQL grammar
*
* This should match src/backend/parser/parser.c, except that we do not
* need to bother with re-entrant interfaces.
*
* Note: ECPG doesn't report error location like the backend does.
* This file will need work if we ever want it to.
*
*
* Portions Copyright (c) 1996-2022, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
*
* IDENTIFICATION
* src/interfaces/ecpg/preproc/parser.c
*
*-------------------------------------------------------------------------
*/
#include "postgres_fe.h"
#include "preproc_extern.h"
#include "preproc.h"
static bool have_lookahead; /* is lookahead info valid? */
static int lookahead_token; /* one-token lookahead */
static YYSTYPE lookahead_yylval; /* yylval for lookahead token */
static YYLTYPE lookahead_yylloc; /* yylloc for lookahead token */
static char *lookahead_yytext; /* start current token */
static bool check_uescapechar(unsigned char escape);
static bool ecpg_isspace(char ch);
/*
* Intermediate filter between parser and base lexer (base_yylex in scan.l).
*
* This filter is needed because in some cases the standard SQL grammar
* requires more than one token lookahead. We reduce these cases to one-token
* lookahead by replacing tokens here, in order to keep the grammar LALR(1).
*
* Using a filter is simpler than trying to recognize multiword tokens
* directly in scan.l, because we'd have to allow for comments between the
* words. Furthermore it's not clear how to do that without re-introducing
* scanner backtrack, which would cost more performance than this filter
* layer does.
*
* We also use this filter to convert UIDENT and USCONST sequences into
* plain IDENT and SCONST tokens. While that could be handled by additional
* productions in the main grammar, it's more efficient to do it like this.
*/
int
filtered_base_yylex(void)
{
int cur_token;
int next_token;
YYSTYPE cur_yylval;
YYLTYPE cur_yylloc;
char *cur_yytext;
/* Get next token --- we might already have it */
if (have_lookahead)
{
cur_token = lookahead_token;
base_yylval = lookahead_yylval;
base_yylloc = lookahead_yylloc;
base_yytext = lookahead_yytext;
have_lookahead = false;
}
else
cur_token = base_yylex();
/*
* If this token isn't one that requires lookahead, just return it.
*/
switch (cur_token)
{
case NOT:
case NULLS_P:
case WITH:
case UIDENT:
case USCONST:
break;
default:
return cur_token;
}
/* Save and restore lexer output variables around the call */
cur_yylval = base_yylval;
cur_yylloc = base_yylloc;
cur_yytext = base_yytext;
/* Get next token, saving outputs into lookahead variables */
next_token = base_yylex();
lookahead_token = next_token;
lookahead_yylval = base_yylval;
lookahead_yylloc = base_yylloc;
lookahead_yytext = base_yytext;
base_yylval = cur_yylval;
base_yylloc = cur_yylloc;
base_yytext = cur_yytext;
have_lookahead = true;
/* Replace cur_token if needed, based on lookahead */
switch (cur_token)
{
case NOT:
/* Replace NOT by NOT_LA if it's followed by BETWEEN, IN, etc */
switch (next_token)
{
case BETWEEN:
case IN_P:
case LIKE:
case ILIKE:
case SIMILAR:
cur_token = NOT_LA;
break;
}
break;
case NULLS_P:
/* Replace NULLS_P by NULLS_LA if it's followed by FIRST or LAST */
switch (next_token)
{
case FIRST_P:
case LAST_P:
cur_token = NULLS_LA;
break;
}
break;
case WITH:
/* Replace WITH by WITH_LA if it's followed by TIME or ORDINALITY */
switch (next_token)
{
case TIME:
case ORDINALITY:
cur_token = WITH_LA;
break;
}
break;
case UIDENT:
case USCONST:
/* Look ahead for UESCAPE */
if (next_token == UESCAPE)
{
/* Yup, so get third token, which had better be SCONST */
const char *escstr;
/*
* Again save and restore lexer output variables around the
* call
*/
cur_yylval = base_yylval;
cur_yylloc = base_yylloc;
cur_yytext = base_yytext;
/* Get third token */
next_token = base_yylex();
if (next_token != SCONST)
mmerror(PARSE_ERROR, ET_ERROR, "UESCAPE must be followed by a simple string literal");
/*
* Save and check escape string, which the scanner returns
* with quotes
*/
escstr = base_yylval.str;
if (strlen(escstr) != 3 || !check_uescapechar(escstr[1]))
mmerror(PARSE_ERROR, ET_ERROR, "invalid Unicode escape character");
base_yylval = cur_yylval;
base_yylloc = cur_yylloc;
base_yytext = cur_yytext;
/* Combine 3 tokens into 1 */
base_yylval.str = psprintf("%s UESCAPE %s", base_yylval.str, escstr);
/* Clear have_lookahead, thereby consuming all three tokens */
have_lookahead = false;
}
if (cur_token == UIDENT)
cur_token = IDENT;
else if (cur_token == USCONST)
cur_token = SCONST;
break;
}
return cur_token;
}
/*
* check_uescapechar() and ecpg_isspace() should match their equivalents
* in pgc.l.
*/
/* is 'escape' acceptable as Unicode escape character (UESCAPE syntax) ? */
static bool
check_uescapechar(unsigned char escape)
{
if (isxdigit(escape)
|| escape == '+'
|| escape == '\''
|| escape == '"'
|| ecpg_isspace(escape))
return false;
else
return true;
}
/*
* ecpg_isspace() --- return true if flex scanner considers char whitespace
*/
static bool
ecpg_isspace(char ch)
{
if (ch == ' ' ||
ch == '\t' ||
ch == '\n' ||
ch == '\r' ||
ch == '\f')
return true;
return false;
}
|
