mirror of
https://gitee.com/milvus-io/milvus.git
synced 2026-01-07 19:31:51 +08:00
issue: https://github.com/milvus-io/milvus/issues/27467 >My plan is as follows. >- [x] M1 Create collection with timestamptz field >- [x] M2 Insert timestamptz field data >- [x] M3 Retrieve timestamptz field data >- [x] M4 Implement handoff >- [x] M5 Implement compare operator >- [x] M6 Implement extract operator >- [x] M8 Support database/collection level default timezone >- [x] M7 Support STL-SORT index for datatype timestamptz --- The third PR of issue: https://github.com/milvus-io/milvus/issues/27467, which completes M5, M6, M7, M8 described above. ## M8 Default Timezone We will be able to use alter_collection() and alter_database() in a future Python SDK release to modify the default timezone at the collection or database level. For insert requests, the timezone will be resolved using the following order of precedence: String Literal-> Collection Default -> Database Default. For retrieval requests, the timezone will be resolved in this order: Query Parameters -> Collection Default -> Database Default. In both cases, the final fallback timezone is UTC. ## M5: Comparison Operators We can now use the following expression format to filter on the timestamptz field: - `timestamptz_field [+/- INTERVAL 'interval_string'] {comparison_op} ISO 'iso_string' ` - The interval_string follows the ISO 8601 duration format, for example: P1Y2M3DT1H2M3S. - The iso_string follows the ISO 8601 timestamp format, for example: 2025-01-03T00:00:00+08:00. - Example expressions: "tsz + INTERVAL 'P0D' != ISO '2025-01-03T00:00:00+08:00'" or "tsz != ISO '2025-01-03T00:00:00+08:00'". ## M6: Extract We will be able to extract sepecific time filed by kwargs in a future Python SDK release. The key is `time_fields`, and value should be one or more of "year, month, day, hour, minute, second, microsecond", seperated by comma or space. Then the result of each record would be an array of int64. ## M7: Indexing Support Expressions without interval arithmetic can be accelerated using an STL-SORT index. However, expressions that include interval arithmetic cannot be indexed. This is because the result of an interval calculation depends on the specific timestamp value. For example, adding one month to a date in February results in a different number of added days than adding one month to a date in March. --- After this PR, the input / output type of timestamptz would be iso string. Timestampz would be stored as timestamptz data, which is int64_t finally. > for more information, see https://en.wikipedia.org/wiki/ISO_8601 --------- Signed-off-by: xtx <xtianx@smail.nju.edu.cn>
170 lines
6.3 KiB
ANTLR
170 lines
6.3 KiB
ANTLR
grammar Plan;
|
|
|
|
expr:
|
|
Identifier (op1=(ADD | SUB) INTERVAL interval_string=StringLiteral)? op2=(LT | LE | GT | GE | EQ | NE) ISO compare_string=StringLiteral # TimestamptzCompare
|
|
| IntegerConstant # Integer
|
|
| FloatingConstant # Floating
|
|
| BooleanConstant # Boolean
|
|
| StringLiteral # String
|
|
| (Identifier|Meta) # Identifier
|
|
| JSONIdentifier # JSONIdentifier
|
|
| LBRACE Identifier RBRACE # TemplateVariable
|
|
| '(' expr ')' # Parens
|
|
| '[' expr (',' expr)* ','? ']' # Array
|
|
| EmptyArray # EmptyArray
|
|
| EXISTS expr # Exists
|
|
| expr LIKE StringLiteral # Like
|
|
| TEXTMATCH'('Identifier',' StringLiteral')' # TextMatch
|
|
| PHRASEMATCH'('Identifier',' StringLiteral (',' expr)? ')' # PhraseMatch
|
|
| RANDOMSAMPLE'(' expr ')' # RandomSample
|
|
| expr POW expr # Power
|
|
| op = (ADD | SUB | BNOT | NOT) expr # Unary
|
|
// | '(' typeName ')' expr # Cast
|
|
| expr op = (MUL | DIV | MOD) expr # MulDivMod
|
|
| expr op = (ADD | SUB) expr # AddSub
|
|
| expr op = (SHL | SHR) expr # Shift
|
|
| expr op = NOT? IN expr # Term
|
|
| (JSONContains | ArrayContains)'('expr',' expr')' # JSONContains
|
|
| (JSONContainsAll | ArrayContainsAll)'('expr',' expr')' # JSONContainsAll
|
|
| (JSONContainsAny | ArrayContainsAny)'('expr',' expr')' # JSONContainsAny
|
|
| ArrayLength'('(Identifier | JSONIdentifier)')' # ArrayLength
|
|
| Identifier '(' ( expr (',' expr )* ','? )? ')' # Call
|
|
| expr op1 = (LT | LE) (Identifier | JSONIdentifier) op2 = (LT | LE) expr # Range
|
|
| expr op1 = (GT | GE) (Identifier | JSONIdentifier) op2 = (GT | GE) expr # ReverseRange
|
|
| expr op = (LT | LE | GT | GE) expr # Relational
|
|
| expr op = (EQ | NE) expr # Equality
|
|
| expr BAND expr # BitAnd
|
|
| expr BXOR expr # BitXor
|
|
| expr BOR expr # BitOr
|
|
| expr AND expr # LogicalAnd
|
|
| expr OR expr # LogicalOr
|
|
| (Identifier | JSONIdentifier) ISNULL # IsNull
|
|
| (Identifier | JSONIdentifier) ISNOTNULL # IsNotNull;
|
|
|
|
// typeName: ty = (BOOL | INT8 | INT16 | INT32 | INT64 | FLOAT | DOUBLE);
|
|
|
|
// BOOL: 'bool';
|
|
// INT8: 'int8';
|
|
// INT16: 'int16';
|
|
// INT32: 'int32';
|
|
// INT64: 'int64';
|
|
// FLOAT: 'float';
|
|
// DOUBLE: 'double';
|
|
LBRACE: '{';
|
|
RBRACE: '}';
|
|
|
|
LT: '<';
|
|
LE: '<=';
|
|
GT: '>';
|
|
GE: '>=';
|
|
EQ: '==';
|
|
NE: '!=';
|
|
|
|
LIKE: 'like' | 'LIKE';
|
|
EXISTS: 'exists' | 'EXISTS';
|
|
TEXTMATCH: 'text_match'|'TEXT_MATCH';
|
|
PHRASEMATCH: 'phrase_match'|'PHRASE_MATCH';
|
|
RANDOMSAMPLE: 'random_sample' | 'RANDOM_SAMPLE';
|
|
INTERVAL: 'interval' | 'INTERVAL';
|
|
ISO: 'iso' | 'ISO';
|
|
|
|
ADD: '+';
|
|
SUB: '-';
|
|
MUL: '*';
|
|
DIV: '/';
|
|
MOD: '%';
|
|
POW: '**';
|
|
SHL: '<<';
|
|
SHR: '>>';
|
|
BAND: '&';
|
|
BOR: '|';
|
|
BXOR: '^';
|
|
|
|
AND: '&&' | 'and' | 'AND';
|
|
OR: '||' | 'or' | 'OR';
|
|
|
|
ISNULL: 'is null' | 'IS NULL';
|
|
ISNOTNULL: 'is not null' | 'IS NOT NULL';
|
|
|
|
BNOT: '~';
|
|
NOT: '!' | 'not' | 'NOT';
|
|
|
|
IN: 'in' | 'IN';
|
|
EmptyArray: '[' (Whitespace | Newline)* ']';
|
|
|
|
JSONContains: 'json_contains' | 'JSON_CONTAINS';
|
|
JSONContainsAll: 'json_contains_all' | 'JSON_CONTAINS_ALL';
|
|
JSONContainsAny: 'json_contains_any' | 'JSON_CONTAINS_ANY';
|
|
|
|
ArrayContains: 'array_contains' | 'ARRAY_CONTAINS';
|
|
ArrayContainsAll: 'array_contains_all' | 'ARRAY_CONTAINS_ALL';
|
|
ArrayContainsAny: 'array_contains_any' | 'ARRAY_CONTAINS_ANY';
|
|
ArrayLength: 'array_length' | 'ARRAY_LENGTH';
|
|
|
|
BooleanConstant: 'true' | 'True' | 'TRUE' | 'false' | 'False' | 'FALSE';
|
|
|
|
IntegerConstant:
|
|
DecimalConstant
|
|
| OctalConstant
|
|
| HexadecimalConstant
|
|
| BinaryConstant;
|
|
|
|
FloatingConstant:
|
|
DecimalFloatingConstant
|
|
| HexadecimalFloatingConstant;
|
|
|
|
Identifier: Nondigit (Nondigit | Digit)*;
|
|
Meta: '$meta';
|
|
|
|
StringLiteral: EncodingPrefix? ('"' DoubleSCharSequence? '"' | '\'' SingleSCharSequence? '\'');
|
|
JSONIdentifier: (Identifier | Meta)('[' (StringLiteral | DecimalConstant) ']')+;
|
|
|
|
fragment EncodingPrefix: 'u8' | 'u' | 'U' | 'L';
|
|
|
|
fragment DoubleSCharSequence: DoubleSChar+;
|
|
fragment SingleSCharSequence: SingleSChar+;
|
|
|
|
fragment DoubleSChar: ~["\\\r\n] | EscapeSequence | '\\\n' | '\\\r\n';
|
|
fragment SingleSChar: ~['\\\r\n] | EscapeSequence | '\\\n' | '\\\r\n';
|
|
fragment Nondigit: [a-zA-Z_];
|
|
fragment Digit: [0-9];
|
|
fragment BinaryConstant: '0' [bB] [0-1]+;
|
|
fragment DecimalConstant: NonzeroDigit Digit* | '0';
|
|
fragment OctalConstant: '0' OctalDigit*;
|
|
fragment HexadecimalConstant: '0' [xX] HexadecimalDigitSequence;
|
|
fragment NonzeroDigit: [1-9];
|
|
fragment OctalDigit: [0-7];
|
|
fragment HexadecimalDigit: [0-9a-fA-F];
|
|
fragment HexQuad:
|
|
HexadecimalDigit HexadecimalDigit HexadecimalDigit HexadecimalDigit;
|
|
fragment UniversalCharacterName:
|
|
'\\u' HexQuad
|
|
| '\\U' HexQuad HexQuad;
|
|
fragment DecimalFloatingConstant:
|
|
FractionalConstant ExponentPart?
|
|
| DigitSequence ExponentPart;
|
|
fragment HexadecimalFloatingConstant:
|
|
'0' [xX] (
|
|
HexadecimalFractionalConstant
|
|
| HexadecimalDigitSequence
|
|
) BinaryExponentPart;
|
|
fragment FractionalConstant:
|
|
DigitSequence? '.' DigitSequence
|
|
| DigitSequence '.';
|
|
fragment ExponentPart: [eE] [+-]? DigitSequence;
|
|
fragment DigitSequence: Digit+;
|
|
fragment HexadecimalFractionalConstant:
|
|
HexadecimalDigitSequence? '.' HexadecimalDigitSequence
|
|
| HexadecimalDigitSequence '.';
|
|
fragment HexadecimalDigitSequence: HexadecimalDigit+;
|
|
fragment BinaryExponentPart: [pP] [+-]? DigitSequence;
|
|
fragment EscapeSequence:
|
|
'\\' ['"?abfnrtv\\]
|
|
| '\\' OctalDigit OctalDigit? OctalDigit?
|
|
| '\\x' HexadecimalDigitSequence
|
|
| UniversalCharacterName;
|
|
|
|
Whitespace: [ \t]+ -> skip;
|
|
|
|
Newline: ( '\r' '\n'? | '\n') -> skip;
|