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
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
|
/**
* Copyright (C) 2014 MongoDB Inc.
*
* This program is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License, version 3,
* as published by the Free Software Foundation.
*
* 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
* GNU Affero General Public License for more details.
*
* You should have received a copy of the GNU Affero General Public License
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*
* 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 GNU Affero General 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.
*/
#include "mongo/platform/basic.h"
#include "mongo/db/jsobj.h"
#include "mongo/db/pipeline/dependencies.h"
#include "mongo/db/pipeline/field_path.h"
#include "mongo/util/mongoutils/str.h"
namespace mongo {
using std::set;
using std::string;
using std::vector;
namespace str = mongoutils::str;
constexpr DepsTracker::MetadataAvailable DepsTracker::kAllGeoNearDataAvailable;
bool DepsTracker::_appendMetaProjections(BSONObjBuilder* projectionBuilder) const {
if (_needTextScore) {
projectionBuilder->append(Document::metaFieldTextScore,
BSON("$meta"
<< "textScore"));
}
if (_needSortKey) {
projectionBuilder->append(Document::metaFieldSortKey,
BSON("$meta"
<< "sortKey"));
}
if (_needGeoNearDistance) {
projectionBuilder->append(Document::metaFieldGeoNearDistance,
BSON("$meta"
<< "geoNearDistance"));
}
if (_needGeoNearPoint) {
projectionBuilder->append(Document::metaFieldGeoNearPoint,
BSON("$meta"
<< "geoNearPoint"));
}
return (_needTextScore || _needSortKey || _needGeoNearDistance || _needGeoNearPoint);
}
BSONObj DepsTracker::toProjection() const {
BSONObjBuilder bb;
const bool needsMetadata = _appendMetaProjections(&bb);
if (needWholeDocument) {
return bb.obj();
}
if (fields.empty()) {
if (needsMetadata) {
// We only need metadata, but there is no easy way to express this in the query
// projection language. We use $noFieldsNeeded with a meta-projection since this is an
// inclusion projection which will exclude all existing fields but add the metadata.
bb.append("_id", 0);
bb.append("$noFieldsNeeded", 1);
}
// We either need nothing (as we would if this was logically a count), or only the metadata.
return bb.obj();
}
bool needId = false;
string last;
for (set<string>::const_iterator it(fields.begin()), end(fields.end()); it != end; ++it) {
if (str::startsWith(*it, "_id") && (it->size() == 3 || (*it)[3] == '.')) {
// _id and subfields are handled specially due in part to SERVER-7502
needId = true;
continue;
}
if (!last.empty() && str::startsWith(*it, last)) {
// we are including a parent of *it so we don't need to include this field
// explicitly. In fact, due to SERVER-6527 if we included this field, the parent
// wouldn't be fully included. This logic relies on on set iterators going in
// lexicographic order so that a string is always directly before of all fields it
// prefixes.
continue;
}
last = *it + '.';
bb.append(*it, 1);
}
if (needId) // we are explicit either way
bb.append("_id", 1);
else
bb.append("_id", 0);
return bb.obj();
}
// ParsedDeps::_fields is a simple recursive look-up table. For each field:
// If the value has type==Bool, the whole field is needed
// If the value has type==Object, the fields in the subobject are needed
// All other fields should be missing which means not needed
boost::optional<ParsedDeps> DepsTracker::toParsedDeps() const {
MutableDocument md;
if (needWholeDocument || _needTextScore) {
// can't use ParsedDeps in this case
return boost::none;
}
string last;
for (set<string>::const_iterator it(fields.begin()), end(fields.end()); it != end; ++it) {
if (!last.empty() && str::startsWith(*it, last)) {
// we are including a parent of *it so we don't need to include this field
// explicitly. In fact, if we included this field, the parent wouldn't be fully
// included. This logic relies on on set iterators going in lexicographic order so
// that a string is always directly before of all fields it prefixes.
continue;
}
last = *it + '.';
md.setNestedField(*it, Value(true));
}
return ParsedDeps(md.freeze());
}
bool DepsTracker::getNeedsMetadata(MetadataType type) const {
switch (type) {
case MetadataType::TEXT_SCORE:
return _needTextScore;
case MetadataType::SORT_KEY:
return _needSortKey;
case MetadataType::GEO_NEAR_DISTANCE:
return _needGeoNearDistance;
case MetadataType::GEO_NEAR_POINT:
return _needGeoNearPoint;
}
MONGO_UNREACHABLE;
}
bool DepsTracker::isMetadataAvailable(MetadataType type) const {
switch (type) {
case MetadataType::TEXT_SCORE:
return _metadataAvailable & MetadataAvailable::kTextScore;
case MetadataType::SORT_KEY:
MONGO_UNREACHABLE;
case MetadataType::GEO_NEAR_DISTANCE:
return _metadataAvailable & MetadataAvailable::kGeoNearDistance;
case MetadataType::GEO_NEAR_POINT:
return _metadataAvailable & MetadataAvailable::kGeoNearPoint;
}
MONGO_UNREACHABLE;
}
void DepsTracker::setNeedsMetadata(MetadataType type, bool required) {
switch (type) {
case MetadataType::TEXT_SCORE:
uassert(40218,
"pipeline requires text score metadata, but there is no text score available",
!required || isMetadataAvailable(type));
_needTextScore = required;
return;
case MetadataType::SORT_KEY:
invariant(required || !_needSortKey);
_needSortKey = required;
return;
case MetadataType::GEO_NEAR_DISTANCE:
uassert(50860,
"pipeline requires $geoNear distance metadata, but it is not available",
!required || isMetadataAvailable(type));
invariant(required || !_needGeoNearDistance);
_needGeoNearDistance = required;
return;
case MetadataType::GEO_NEAR_POINT:
uassert(50859,
"pipeline requires $geoNear point metadata, but it is not available",
!required || isMetadataAvailable(type));
invariant(required || !_needGeoNearPoint);
_needGeoNearPoint = required;
return;
}
MONGO_UNREACHABLE;
}
std::vector<DepsTracker::MetadataType> DepsTracker::getAllRequiredMetadataTypes() const {
std::vector<MetadataType> reqs;
if (_needTextScore) {
reqs.push_back(MetadataType::TEXT_SCORE);
}
if (_needSortKey) {
reqs.push_back(MetadataType::SORT_KEY);
}
if (_needGeoNearDistance) {
reqs.push_back(MetadataType::GEO_NEAR_DISTANCE);
}
if (_needGeoNearPoint) {
reqs.push_back(MetadataType::GEO_NEAR_POINT);
}
return reqs;
}
namespace {
// Mutually recursive with arrayHelper
Document documentHelper(const BSONObj& bson, const Document& neededFields, int nFieldsNeeded = -1);
// Handles array-typed values for ParsedDeps::extractFields
Value arrayHelper(const BSONObj& bson, const Document& neededFields) {
BSONObjIterator it(bson);
vector<Value> values;
while (it.more()) {
BSONElement bsonElement(it.next());
if (bsonElement.type() == Object) {
Document sub = documentHelper(bsonElement.embeddedObject(), neededFields);
values.push_back(Value(sub));
}
if (bsonElement.type() == Array) {
values.push_back(arrayHelper(bsonElement.embeddedObject(), neededFields));
}
}
return Value(std::move(values));
}
// Handles object-typed values including the top-level for ParsedDeps::extractFields
Document documentHelper(const BSONObj& bson, const Document& neededFields, int nFieldsNeeded) {
// We cache the number of top level fields, so don't need to re-compute it every time. For
// sub-documents, just scan for the number of fields.
if (nFieldsNeeded == -1) {
nFieldsNeeded = neededFields.size();
}
MutableDocument md(nFieldsNeeded);
BSONObjIterator it(bson);
while (it.more() && nFieldsNeeded > 0) {
auto bsonElement = it.next();
StringData fieldName = bsonElement.fieldNameStringData();
Value isNeeded = neededFields[fieldName];
if (isNeeded.missing())
continue;
--nFieldsNeeded; // Found a needed field.
if (isNeeded.getType() == Bool) {
md.addField(fieldName, Value(bsonElement));
} else {
dassert(isNeeded.getType() == Object);
if (bsonElement.type() == BSONType::Object) {
md.addField(
fieldName,
Value(documentHelper(bsonElement.embeddedObject(), isNeeded.getDocument())));
} else if (bsonElement.type() == BSONType::Array) {
md.addField(fieldName,
arrayHelper(bsonElement.embeddedObject(), isNeeded.getDocument()));
}
}
}
return md.freeze();
}
} // namespace
Document ParsedDeps::extractFields(const BSONObj& input) const {
return documentHelper(input, _fields, _nFields);
}
}
|