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
|
/**
* Copyright (C) 2020-present MongoDB, Inc.
*
* This program is free software: you can redistribute it and/or modify
* it under the terms of the Server Side Public License, version 1,
* as published by MongoDB, Inc.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* Server Side Public License for more details.
*
* You should have received a copy of the Server Side Public License
* along with this program. If not, see
* <http://www.mongodb.com/licensing/server-side-public-license>.
*
* As a special exception, the copyright holders give permission to link the
* code of portions of this program with the OpenSSL library under certain
* conditions as described in each individual source file and distribute
* linked combinations including the program with the OpenSSL library. You
* must comply with the Server Side Public License in all respects for
* all of the code used other than as permitted herein. If you modify file(s)
* with this exception, you may extend this exception to your version of the
* file(s), but you are not obligated to do so. If you do not wish to do so,
* delete this exception statement from your version. If you delete this
* exception statement from all source files in the program, then also delete
* it in the license file.
*/
//
// This is a grammar file to describe the syntax of the aggregation pipeline language. It is
// ingested by GNU Bison (https://www.gnu.org/software/bison/) to generate native C++ parser code
// based on the rules provided here.
//
// To manually generate the parser files, run
// 'bison pipeline_grammar.yy -o pipeline_parser_gen.cpp'.
//
%require "3.5"
%language "c++"
// Generate header for tokens to be included from lexer.
%defines
// Tell Bison to generate make_* methods for tokens.
%define api.token.constructor
// The mapping of scanner token ID to Bison's internal symbol enum is consistent.
%define api.token.raw
// Instead of specifying a %union directive of possible semantic types, allow Bison to build a sort
// of std::variant structure. This allows symbol declaration with '%type <C++ type> symbol'.
%define api.value.type variant
%define parse.assert
%define api.namespace {mongo}
%define api.parser.class {PipelineParserGen}
// Track locations of symbols.
%locations
%define api.location.file "location_gen.h"
// Header only.
%code requires {
#include "mongo/db/cst/c_node.h"
#include "mongo/db/cst/key_fieldname.h"
#include "mongo/stdx/variant.h"
// Forward declare any parameters needed for lexing/parsing.
namespace mongo {
class BSONLexer;
}
#ifdef _MSC_VER
// warning C4065: switch statement contains 'default' but no 'case' labels.
#pragma warning (disable : 4065)
#endif
}
// Cpp only.
%code {
#include "mongo/db/cst/bson_lexer.h"
namespace mongo {
// Mandatory error function.
void PipelineParserGen::error (const PipelineParserGen::location_type& loc,
const std::string& msg) {
uasserted(ErrorCodes::FailedToParse, str::stream() << msg <<
" at location " <<
loc.begin.line << ":" << loc.begin.column <<
" of input BSON. Lexer produced token of type " <<
lexer[loc.begin.column].type_get() << "." );
}
} // namespace mongo
}
// Parsing parameters, funneled through yyparse() to yylex().
%param {BSONLexer& lexer}
// yyparse() parameter only.
%parse-param {CNode* cst}
//
// Token definitions.
//
%token
START_OBJECT
END_OBJECT
START_ARRAY
END_ARRAY
// Reserve pipeline stage names.
STAGE_INHIBIT_OPTIMIZATION
STAGE_UNION_WITH
// $unionWith arguments.
COLL_ARG
PIPELINE_ARG
END_OF_FILE 0 "EOF"
;
%token <std::string> STRING
%token <int> NUMBER_INT
%token <long long> NUMBER_LONG
%token <double> NUMBER_DOUBLE
%token <bool> BOOL
//
// Semantic values (aka the C++ types produced by the actions).
//
%nterm <CNode> stageList stage inhibitOptimization unionWith
//
// Grammar rules
//
%%
// Entry point to pipeline parsing.
pipeline: START_ARRAY stageList END_ARRAY {
*cst = std::move($stageList);
};
stageList[result]:
%empty { }
| START_OBJECT stage END_OBJECT stageList[stagesArg] {
$result = CNode{CNode::ArrayChildren{$stage}};
}
;
// Special rule to hint to the lexer that the next set of tokens should be sorted. Note that the
// sort order is not lexicographical, but rather based on the enum generated from the %token list
// above.
START_ORDERED_OBJECT: { lexer.sortObjTokens(); } START_OBJECT;
stage:
inhibitOptimization | unionWith
;
inhibitOptimization:
STAGE_INHIBIT_OPTIMIZATION START_OBJECT END_OBJECT {
$inhibitOptimization =
CNode{CNode::ObjectChildren{std::pair{KeyFieldname::inhibitOptimization, CNode::noopLeaf()}}};
};
unionWith:
STAGE_UNION_WITH START_ORDERED_OBJECT COLL_ARG STRING PIPELINE_ARG NUMBER_DOUBLE END_OBJECT {
auto coll = CNode{UserString($STRING)};
auto pipeline = CNode{UserDouble($NUMBER_DOUBLE)};
$unionWith = CNode{CNode::ObjectChildren{std::pair{KeyFieldname::unionWith,
CNode{CNode::ObjectChildren{
{KeyFieldname::collArg, std::move(coll)},
{KeyFieldname::pipelineArg, std::move(pipeline)}
}}}}};
};
%%
|
