Page MenuHomePhabricator
Paste P6895

ref impl
ActivePublic
Actions

Authored by dcausse on Mar 23 2018, 5:43 PM.
Tags
None
Referenced Files
F16003832: ref impl
Mar 23 2018, 6:46 PM
F16003135: ref impl
Mar 23 2018, 5:43 PM
Subscribers
None
{
"empty: produce an empty tree": {
"query": "",
"expected": {
"query": "",
"rawQuery": "",
"root": {
"empty": {
"startOffset": 0,
"endOffset": 0
}
}
}
},
"empty: space only produce an empty tree": {
"query": "\t\u0000 \u3000\ufeff",
"expected": {
"query": "\t\u0000 \u3000\ufeff",
"rawQuery": "\t\u0000 \u3000\ufeff",
"root": {
"empty": {
"startOffset": 0,
"endOffset": 9
}
}
}
},
"words: single word": {
"query": "word",
"expected": {
"query": "word",
"rawQuery": "word",
"root": {
"words": {
"startOffset": 0,
"endOffset": 4,
"words": "word"
}
}
}
},
"words: parenthesis are simple words": {
"query": "Louise Michel (Anachiste)",
"expected": {
"query": "Louise Michel (Anachiste)",
"rawQuery": "Louise Michel (Anachiste)",
"root": {
"words": {
"startOffset": 0,
"endOffset": 25,
"words": "Louise Michel (Anachiste)"
}
}
}
},
"words: parenthesis cannot be used yet to group boolean": {
"query": "(word1 OR word2) AND (word3 OR word4)",
"expected": {
"query": "(word1 OR word2) AND (word3 OR word4)",
"rawQuery": "(word1 OR word2) AND (word3 OR word4)",
"root": {
"bool": {
"startOffset": 0,
"endOffset": 37,
"clauses": [
{
"SHOULD": {
"words": {
"startOffset": 0,
"endOffset": 6,
"words": "(word1"
}
},
"explicit": true
},
{
"MUST": {
"words": {
"startOffset": 10,
"endOffset": 16,
"words": "word2)"
}
},
"explicit": true
},
{
"SHOULD": {
"words": {
"startOffset": 21,
"endOffset": 27,
"words": "(word3"
}
},
"explicit": true
},
{
"SHOULD": {
"words": {
"startOffset": 31,
"endOffset": 37,
"words": "word4)"
}
},
"explicit": true
}
]
}
}
}
},
"words: multiple words are collapsed": {
"query": "word1 word2",
"expected": {
"query": "word1 word2",
"rawQuery": "word1 word2",
"root": {
"words": {
"startOffset": 0,
"endOffset": 11,
"words": "word1 word2"
}
}
}
},
"words: question mark stripping won't messup simple questions": {
"query": "how old is fred?",
"config": {
"CirrusSearchStripQuestionMarks": "all"
},
"expected": {
"query": "how old is fred ",
"rawQuery": "how old is fred?",
"queryCleanups": {
"stripped_qmark": true
},
"root": {
"words": {
"startOffset": 0,
"endOffset": 15,
"words": "how old is fred"
}
}
}
},
"words: expert users can bypass question mark stripping": {
"query": "201\\?",
"config": {
"CirrusSearchStripQuestionMarks": "all"
},
"expected": {
"query": "201?",
"rawQuery": "201\\?",
"queryCleanups": {
"stripped_qmark": true
},
"root": {
"wildcard": {
"startOffset": 0,
"endOffset": 4,
"wildcardquery": "201?"
}
}
}
},
"words: \\ can escape parsed operators": {
"query": "\\AND \\\" \\NOT \\!word word\\* word\\",
"expected": {
"query": "\\AND \\\" \\NOT \\!word word\\* word\\",
"rawQuery": "\\AND \\\" \\NOT \\!word word\\* word\\",
"root": {
"words": {
"startOffset": 0,
"endOffset": 32,
"words": "AND \" NOT !word word* word\\"
}
}
}
},
"words: tokenized on all unicode spaces and control chars": {
"query": "w1\t-w2\u3000-w3\ufeff-w4\u0000-w5",
"expected": {
"query": "w1\t-w2\u3000-w3\ufeff-w4\u0000-w5",
"rawQuery": "w1\t-w2\u3000-w3\ufeff-w4\u0000-w5",
"root": {
"bool": {
"startOffset": 0,
"endOffset": 22,
"clauses": [
{
"MUST": {
"words": {
"startOffset": 0,
"endOffset": 2,
"words": "w1"
}
},
"explicit": false
},
{
"MUST_NOT": {
"words": {
"startOffset": 4,
"endOffset": 6,
"words": "w2"
}
},
"explicit": false
},
{
"MUST_NOT": {
"words": {
"startOffset": 10,
"endOffset": 12,
"words": "w3"
}
},
"explicit": false
},
{
"MUST_NOT": {
"words": {
"startOffset": 16,
"endOffset": 18,
"words": "w4"
}
},
"explicit": false
},
{
"MUST_NOT": {
"words": {
"startOffset": 20,
"endOffset": 22,
"words": "w5"
}
},
"explicit": false
}
]
}
}
}
},
"negation prefix: a single word can be negated with !": {
"query": "!word1",
"expected": {
"query": "!word1",
"rawQuery": "!word1",
"root": {
"bool": {
"startOffset": 1,
"endOffset": 6,
"clauses": [
{
"MUST_NOT": {
"words": {
"startOffset": 1,
"endOffset": 6,
"words": "word1"
}
},
"explicit": false
}
]
}
}
}
},
"negation prefix: a single word can be negated with -": {
"query": "-word1",
"expected": {
"query": "-word1",
"rawQuery": "-word1",
"root": {
"bool": {
"startOffset": 1,
"endOffset": 6,
"clauses": [
{
"MUST_NOT": {
"words": {
"startOffset": 1,
"endOffset": 6,
"words": "word1"
}
},
"explicit": false
}
]
}
}
}
},
"negation prefix: - won't split words": {
"query": "foo-bar",
"expected": {
"query": "foo-bar",
"rawQuery": "foo-bar",
"root": {
"words": {
"startOffset": 0,
"endOffset": 7,
"words": "foo-bar"
}
}
}
},
"negation prefix: ! won't split words": {
"query": "foo!bar",
"expected": {
"query": "foo!bar",
"rawQuery": "foo!bar",
"root": {
"words": {
"startOffset": 0,
"endOffset": 7,
"words": "foo!bar"
}
}
}
},
"negation prefix: a single word can be explicitily negated with NOT": {
"query": "NOT word1",
"expected": {
"query": "NOT word1",
"rawQuery": "NOT word1",
"root": {
"bool": {
"startOffset": 4,
"endOffset": 9,
"clauses": [
{
"MUST_NOT": {
"words": {
"startOffset": 4,
"endOffset": 9,
"words": "word1"
}
},
"explicit": true
}
]
}
}
}
},
"negation prefix: words are not collapsed when one is negated": {
"query": "word0 !word1 word1",
"expected": {
"query": "word0 !word1 word1",
"rawQuery": "word0 !word1 word1",
"root": {
"bool": {
"startOffset": 0,
"endOffset": 18,
"clauses": [
{
"MUST": {
"words": {
"startOffset": 0,
"endOffset": 5,
"words": "word0"
}
},
"explicit": false
},
{
"MUST_NOT": {
"words": {
"startOffset": 7,
"endOffset": 12,
"words": "word1"
}
},
"explicit": false
},
{
"MUST": {
"words": {
"startOffset": 13,
"endOffset": 18,
"words": "word1"
}
},
"explicit": false
}
]
}
}
}
},
"negation prefix: ! negation is ignored on non letters": {
"query": "!@word1",
"expected": {
"query": "!@word1",
"rawQuery": "!@word1",
"root": {
"words": {
"startOffset": 0,
"endOffset": 7,
"words": "!@word1"
}
}
}
},
"negation prefix: - negation is ignored on non letters": {
"query": "-@word1",
"expected": {
"query": "-@word1",
"rawQuery": "-@word1",
"root": {
"words": {
"startOffset": 0,
"endOffset": 7,
"words": "-@word1"
}
}
}
},
"negation: NOT negation is not ignored on non letters": {
"query": "NOT @word1",
"expected": {
"query": "NOT @word1",
"rawQuery": "NOT @word1",
"root": {
"bool": {
"startOffset": 4,
"endOffset": 10,
"clauses": [
{
"MUST_NOT": {
"words": {
"startOffset": 4,
"endOffset": 10,
"words": "@word1"
}
},
"explicit": true
}
]
}
}
}
},
"bool: simple AND between words with AND": {
"query": "word1 AND word2",
"expected": {
"query": "word1 AND word2",
"rawQuery": "word1 AND word2",
"root": {
"bool": {
"startOffset": 0,
"endOffset": 15,
"clauses": [
{
"MUST": {
"words": {
"startOffset": 0,
"endOffset": 5,
"words": "word1"
}
},
"explicit": true
},
{
"MUST": {
"words": {
"startOffset": 10,
"endOffset": 15,
"words": "word2"
}
},
"explicit": true
}
]
}
}
}
},
"bool: simple AND between words with &&": {
"query": "word1 && word2",
"expected": {
"query": "word1 && word2",
"rawQuery": "word1 && word2",
"root": {
"bool": {
"startOffset": 0,
"endOffset": 14,
"clauses": [
{
"MUST": {
"words": {
"startOffset": 0,
"endOffset": 5,
"words": "word1"
}
},
"explicit": true
},
{
"MUST": {
"words": {
"startOffset": 9,
"endOffset": 14,
"words": "word2"
}
},
"explicit": true
}
]
}
}
}
},
"bool: simple OR between words with OR": {
"query": "word1 OR word2",
"expected": {
"query": "word1 OR word2",
"rawQuery": "word1 OR word2",
"root": {
"bool": {
"startOffset": 0,
"endOffset": 14,
"clauses": [
{
"SHOULD": {
"words": {
"startOffset": 0,
"endOffset": 5,
"words": "word1"
}
},
"explicit": true
},
{
"SHOULD": {
"words": {
"startOffset": 9,
"endOffset": 14,
"words": "word2"
}
},
"explicit": true
}
]
}
}
}
},
"bool: simple OR between words with ||": {
"query": "word1 || word2",
"expected": {
"query": "word1 || word2",
"rawQuery": "word1 || word2",
"root": {
"bool": {
"startOffset": 0,
"endOffset": 14,
"clauses": [
{
"SHOULD": {
"words": {
"startOffset": 0,
"endOffset": 5,
"words": "word1"
}
},
"explicit": true
},
{
"SHOULD": {
"words": {
"startOffset": 9,
"endOffset": 14,
"words": "word2"
}
},
"explicit": true
}
]
}
}
}
},
"bool: backward order precedence MUST:word1 SHOULD:word2 SHOULD:word3": {
"query": "word1 AND word2 OR word3",
"expected": {
"query": "word1 AND word2 OR word3",
"rawQuery": "word1 AND word2 OR word3",
"root": {
"bool": {
"startOffset": 0,
"endOffset": 24,
"clauses": [
{
"MUST": {
"words": {
"startOffset": 0,
"endOffset": 5,
"words": "word1"
}
},
"explicit": true
},
{
"SHOULD": {
"words": {
"startOffset": 10,
"endOffset": 15,
"words": "word2"
}
},
"explicit": true
},
{
"SHOULD": {
"words": {
"startOffset": 19,
"endOffset": 24,
"words": "word3"
}
},
"explicit": true
}
]
}
}
}
},
"bool: backward order precedence SHOULD:word1 MUST:word2 MUST:word3": {
"query": "word1 OR word2 AND word3",
"expected": {
"query": "word1 OR word2 AND word3",
"rawQuery": "word1 OR word2 AND word3",
"root": {
"bool": {
"startOffset": 0,
"endOffset": 24,
"clauses": [
{
"SHOULD": {
"words": {
"startOffset": 0,
"endOffset": 5,
"words": "word1"
}
},
"explicit": true
},
{
"MUST": {
"words": {
"startOffset": 9,
"endOffset": 14,
"words": "word2"
}
},
"explicit": true
},
{
"MUST": {
"words": {
"startOffset": 19,
"endOffset": 24,
"words": "word3"
}
},
"explicit": true
}
]
}
}
}
},
"bool & negation: AND NOT is comprehensive": {
"query": "word1 AND NOT word2",
"expected": {
"query": "word1 AND NOT word2",
"rawQuery": "word1 AND NOT word2",
"root": {
"bool": {
"startOffset": 0,
"endOffset": 19,
"clauses": [
{
"MUST": {
"words": {
"startOffset": 0,
"endOffset": 5,
"words": "word1"
}
},
"explicit": true
},
{
"MUST_NOT": {
"words": {
"startOffset": 14,
"endOffset": 19,
"words": "word2"
}
},
"explicit": true
}
]
}
}
}
},
"bool & negation: OR NOT is obscure in search bool (SHOULD_NOT does not exist)": {
"query": "word1 OR NOT word2",
"expected": {
"query": "word1 OR NOT word2",
"rawQuery": "word1 OR NOT word2",
"root": {
"bool": {
"startOffset": 0,
"endOffset": 18,
"clauses": [
{
"SHOULD": {
"words": {
"startOffset": 0,
"endOffset": 5,
"words": "word1"
}
},
"explicit": true
},
{
"MUST_NOT": {
"words": {
"startOffset": 13,
"endOffset": 18,
"words": "word2"
}
},
"explicit": true
}
]
}
}
}
},
"phrase: simple phrase": {
"query": "\"word1 word2\"",
"expected": {
"query": "\"word1 word2\"",
"rawQuery": "\"word1 word2\"",
"root": {
"phrase": {
"startOffset": 0,
"endOffset": 13,
"phrase": "word1 word2",
"slop": -1,
"stem": false,
"unbalanced": false
}
}
}
},
"phrase: phrase can include uninterepreted negation prefix": {
"query": "\"!happy\" \"-happy\" happy",
"expected": {
"query": "\"!happy\" \"-happy\" happy",
"rawQuery": "\"!happy\" \"-happy\" happy",
"root": {
"bool": {
"startOffset": 0,
"endOffset": 23,
"clauses": [
{
"MUST": {
"phrase": {
"startOffset": 0,
"endOffset": 8,
"phrase": "!happy",
"slop": -1,
"stem": false,
"unbalanced": false
}
},
"explicit": false
},
{
"MUST": {
"phrase": {
"startOffset": 9,
"endOffset": 17,
"phrase": "-happy",
"slop": -1,
"stem": false,
"unbalanced": false
}
},
"explicit": false
},
{
"MUST": {
"words": {
"startOffset": 18,
"endOffset": 23,
"words": "happy"
}
},
"explicit": false
}
]
}
}
}
},
"phrase: simple phrase on stems": {
"query": "\"word1 word2\"~",
"expected": {
"query": "\"word1 word2\"~",
"rawQuery": "\"word1 word2\"~",
"root": {
"phrase": {
"startOffset": 0,
"endOffset": 14,
"phrase": "word1 word2",
"slop": -1,
"stem": true,
"unbalanced": false
}
}
}
},
"phrase: simple phrase with 0 slop": {
"query": "\"word1 word2\"~0",
"expected": {
"query": "\"word1 word2\"~0",
"rawQuery": "\"word1 word2\"~0",
"root": {
"phrase": {
"startOffset": 0,
"endOffset": 15,
"phrase": "word1 word2",
"slop": 0,
"stem": false,
"unbalanced": false
}
}
}
},
"phrase: simple phrase with 1 slop": {
"query": "\"word1 word2\"~1",
"expected": {
"query": "\"word1 word2\"~1",
"rawQuery": "\"word1 word2\"~1",
"root": {
"phrase": {
"startOffset": 0,
"endOffset": 15,
"phrase": "word1 word2",
"slop": 1,
"stem": false,
"unbalanced": false
}
}
}
},
"phrase: simple phrase on stems with 0 slop": {
"query": "\"word1 word2\"~0~",
"expected": {
"query": "\"word1 word2\"~0~",
"rawQuery": "\"word1 word2\"~0~",
"root": {
"phrase": {
"startOffset": 0,
"endOffset": 16,
"phrase": "word1 word2",
"slop": 0,
"stem": true,
"unbalanced": false
}
}
}
},
"phrase: simple phrase on stems with 1 slop": {
"query": "\"word1 word2\"~1~",
"expected": {
"query": "\"word1 word2\"~1~",
"rawQuery": "\"word1 word2\"~1~",
"root": {
"phrase": {
"startOffset": 0,
"endOffset": 16,
"phrase": "word1 word2",
"slop": 1,
"stem": true,
"unbalanced": false
}
}
}
},
"phrase prefix: simple phrase prefix": {
"query": "\"word1 word2*\"",
"expected": {
"query": "\"word1 word2*\"",
"rawQuery": "\"word1 word2*\"",
"root": {
"phrase_prefix": {
"startOffset": 0,
"endOffset": 14,
"phrase": "word1 word2"
}
}
}
},
"phrase prefix: phrase prefix does not support stem": {
"query": "\"word1 word2*\"~",
"expected": {
"query": "\"word1 word2*\"~",
"rawQuery": "\"word1 word2*\"~",
"root": {
"phrase": {
"startOffset": 0,
"endOffset": 15,
"phrase": "word1 word2*",
"slop": -1,
"stem": true,
"unbalanced": false
}
}
}
},
"phrase prefix: phrase prefix does not support stem & slop": {
"query": "\"word1 word2*\"~1~",
"expected": {
"query": "\"word1 word2*\"~1~",
"rawQuery": "\"word1 word2*\"~1~",
"root": {
"phrase": {
"startOffset": 0,
"endOffset": 17,
"phrase": "word1 word2*",
"slop": 1,
"stem": true,
"unbalanced": false
}
}
}
},
"phrase prefix: phrase prefix does not support slop": {
"query": "\"word1 word2*\"~2",
"expected": {
"query": "\"word1 word2*\"~2",
"rawQuery": "\"word1 word2*\"~2",
"root": {
"phrase": {
"startOffset": 0,
"endOffset": 16,
"phrase": "word1 word2*",
"slop": 2,
"stem": false,
"unbalanced": false
}
}
}
},
"phrase and words: words can be callapsed to phrase begining and ending": {
"query": "foo\"bar\"baz",
"expected": {
"query": "foo\"bar\"baz",
"rawQuery": "foo\"bar\"baz",
"root": {
"bool": {
"startOffset": 0,
"endOffset": 11,
"clauses": [
{
"MUST": {
"words": {
"startOffset": 0,
"endOffset": 3,
"words": "foo"
}
},
"explicit": false
},
{
"MUST": {
"phrase": {
"startOffset": 3,
"endOffset": 8,
"phrase": "bar",
"slop": -1,
"stem": false,
"unbalanced": false
}
},
"explicit": false
},
{
"MUST": {
"words": {
"startOffset": 8,
"endOffset": 11,
"words": "baz"
}
},
"explicit": false
}
]
}
}
}
},
"phrase and words: hebrew has special quirks for gershayim": {
"query": "foo\"b",
"config": {
"LanguageCode": "he"
},
"expected": {
"query": "foo\\\"b",
"rawQuery": "foo\"b",
"queryCleanups": {
"gershayim_quirks": true
},
"root": {
"words": {
"startOffset": 0,
"endOffset": 6,
"words": "foo\"b"
}
}
}
},
"bool and phrase: boolean within phrase are not interpreted": {
"query": "\"foo AND NOT bar OR baz\"",
"expected": {
"query": "\"foo AND NOT bar OR baz\"",
"rawQuery": "\"foo AND NOT bar OR baz\"",
"root": {
"phrase": {
"startOffset": 0,
"endOffset": 24,
"phrase": "foo AND NOT bar OR baz",
"slop": -1,
"stem": false,
"unbalanced": false
}
}
}
},
"bool and phrase: boolean operator can be collapsed with phrase like words (debatable)": {
"query": "foo OR\"bar baz\"OR buz",
"expected": {
"query": "foo OR\"bar baz\"OR buz",
"rawQuery": "foo OR\"bar baz\"OR buz",
"root": {
"bool": {
"startOffset": 0,
"endOffset": 21,
"clauses": [
{
"SHOULD": {
"words": {
"startOffset": 0,
"endOffset": 3,
"words": "foo"
}
},
"explicit": true
},
{
"SHOULD": {
"phrase": {
"startOffset": 6,
"endOffset": 15,
"phrase": "bar baz",
"slop": -1,
"stem": false,
"unbalanced": false
}
},
"explicit": true
},
{
"SHOULD": {
"words": {
"startOffset": 18,
"endOffset": 21,
"words": "buz"
}
},
"explicit": true
}
]
}
}
}
},
"boolean: bool operators cannot be collapsed with negation prefix": {
"query": "foo AND-bar NOT!baz",
"expected": {
"query": "foo AND-bar NOT!baz",
"rawQuery": "foo AND-bar NOT!baz",
"root": {
"words": {
"startOffset": 0,
"endOffset": 19,
"words": "foo AND-bar NOT!baz"
}
}
}
},
"fuzzy: simple fuzzy word": {
"query": "word~",
"expected": {
"query": "word~",
"rawQuery": "word~",
"root": {
"words": {
"startOffset": 0,
"endOffset": 5,
"words": "word~"
}
}
}
},
"fuzzy: fuzzy word with explicit distance": {
"query": "word~0 2word~1 word~2",
"expected": {
"query": "word~0 2word~1 word~2",
"rawQuery": "word~0 2word~1 word~2",
"root": {
"bool": {
"startOffset": 0,
"endOffset": 21,
"clauses": [
{
"MUST": {
"fuzzy": {
"startOffset": 0,
"endOffset": 6,
"word": "word",
"fuzziness": 1
}
},
"explicit": false
},
{
"MUST": {
"fuzzy": {
"startOffset": 7,
"endOffset": 14,
"word": "2word",
"fuzziness": 1
}
},
"explicit": false
},
{
"MUST": {
"fuzzy": {
"startOffset": 15,
"endOffset": 21,
"word": "word",
"fuzziness": 1
}
},
"explicit": false
}
]
}
}
}
},
"fuzzy: fuzzy markup is ignored on non letters\/numbers and invalid distance": {
"query": "w@rd~ w-ord~1 word~.9 word~a ~",
"expected": {
"query": "w@rd~ w-ord~1 word~.9 word~a ~",
"rawQuery": "w@rd~ w-ord~1 word~.9 word~a ~",
"root": {
"words": {
"startOffset": 0,
"endOffset": 30,
"words": "w@rd~ w-ord~1 word~.9 word~a ~"
}
}
}
},
"prefix: only letters and numbers are allowed": {
"query": "1* 1w** @notaprefix*",
"expected": {
"query": "1* 1w** @notaprefix*",
"rawQuery": "1* 1w** @notaprefix*",
"root": {
"bool": {
"startOffset": 0,
"endOffset": 20,
"clauses": [
{
"MUST": {
"prefix": [
{
"startOffset": 0,
"endOffset": 2,
"prefix": "1"
}
]
},
"explicit": false
},
{
"MUST": {
"prefix": [
{
"startOffset": 3,
"endOffset": 7,
"prefix": "1w"
}
]
},
"explicit": false
},
{
"MUST": {
"words": {
"startOffset": 8,
"endOffset": 20,
"words": "@notaprefix*"
}
},
"explicit": false
}
]
}
}
}
},
"wildcard (leading allowed): only letters and numbers (3 non contiguous wildcard max)": {
"query": "*w* *1?2*3 *@not*a*wildcard no?*awildcard",
"config": {
"CirrusSearchStripQuestionMarks": "none",
"CirrusSearchAllowLeadingWildcard": true
},
"expected": {
"query": "*w* *1?2*3 *@not*a*wildcard no?*awildcard",
"rawQuery": "*w* *1?2*3 *@not*a*wildcard no?*awildcard",
"root": {
"bool": {
"startOffset": 0,
"endOffset": 41,
"clauses": [
{
"MUST": {
"wildcard": {
"startOffset": 0,
"endOffset": 3,
"wildcardquery": "*w*"
}
},
"explicit": false
},
{
"MUST": {
"wildcard": {
"startOffset": 4,
"endOffset": 10,
"wildcardquery": "*1?2*3"
}
},
"explicit": false
},
{
"MUST": {
"words": {
"startOffset": 11,
"endOffset": 27,
"words": "*@not*a*wildcard"
}
},
"explicit": false
},
{
"MUST": {
"wildcard": {
"startOffset": 28,
"endOffset": 41,
"wildcardquery": "no?*awildcard"
}
},
"explicit": false
}
]
}
}
}
},
"wildcard (leading not allowed): only letters and numbers (3 wildcard max)": {
"query": "*w* *1?2*3 1*2*3*4* *@not*a*wildcard",
"config": {
"CirrusSearchStripQuestionMarks": "none",
"CirrusSearchAllowLeadingWildcard": false
},
"expected": {
"query": "*w* *1?2*3 1*2*3*4* *@not*a*wildcard",
"rawQuery": "*w* *1?2*3 1*2*3*4* *@not*a*wildcard",
"root": {
"words": {
"startOffset": 0,
"endOffset": 36,
"words": "*w* *1?2*3 1*2*3*4* *@not*a*wildcard"
}
}
}
},
"keyword headings: is parsed if at the beginning (incl leading spaces)": {
"query": " local:word",
"expected": {
"query": " local:word",
"rawQuery": " local:word",
"root": {
"bool": {
"startOffset": 2,
"endOffset": 12,
"clauses": [
{
"MUST": {
"keyword": {
"startOffset": 2,
"endOffset": 8,
"keyword": "CirrusSearch\\Query\\LocalFeature",
"key": "local",
"value": "",
"quotedValue": "",
"delimiter": "",
"suffix": ""
}
},
"explicit": false
},
{
"MUST": {
"words": {
"startOffset": 8,
"endOffset": 12,
"words": "word"
}
},
"explicit": false
}
]
}
}
}
},
"keyword headings: is parsed if at the beginning": {
"query": "local:word",
"expected": {
"query": "local:word",
"rawQuery": "local:word",
"root": {
"bool": {
"startOffset": 0,
"endOffset": 10,
"clauses": [
{
"MUST": {
"keyword": {
"startOffset": 0,
"endOffset": 6,
"keyword": "CirrusSearch\\Query\\LocalFeature",
"key": "local",
"value": "",
"quotedValue": "",
"delimiter": "",
"suffix": ""
}
},
"explicit": false
},
{
"MUST": {
"words": {
"startOffset": 6,
"endOffset": 10,
"words": "word"
}
},
"explicit": false
}
]
}
}
}
},
"keyword value: valued keywords can accept a space": {
"query": "intitle: word",
"expected": {
"query": "intitle: word",
"rawQuery": "intitle: word",
"root": {
"keyword": {
"startOffset": 0,
"endOffset": 13,
"keyword": "CirrusSearch\\Query\\InTitleFeature",
"key": "intitle",
"value": "word",
"quotedValue": "word",
"delimiter": "",
"suffix": ""
}
}
}
},
"keyword value: valued keywords are ignored if no value is provided": {
"query": "intitle: ",
"expected": {
"query": "intitle: ",
"rawQuery": "intitle: ",
"root": {
"words": {
"startOffset": 0,
"endOffset": 8,
"words": "intitle:"
}
}
}
},
"keyword unvalued: some non heading keywords accepts no value": {
"query": "foo prefer-recent:",
"expected": {
"query": "foo prefer-recent:",
"rawQuery": "foo prefer-recent:",
"root": {
"bool": {
"startOffset": 0,
"endOffset": 18,
"clauses": [
{
"MUST": {
"words": {
"startOffset": 0,
"endOffset": 3,
"words": "foo"
}
},
"explicit": false
},
{
"MUST": {
"keyword": {
"startOffset": 4,
"endOffset": 18,
"keyword": "CirrusSearch\\Query\\PreferRecentFeature",
"key": "prefer-recent",
"value": "",
"quotedValue": "",
"delimiter": "",
"suffix": ""
}
},
"explicit": false
}
]
}
}
}
},
"keyword greedy: greedy keywords eat no matter what is written after them": {
"query": "prefix:test intitle:test",
"expected": {
"query": "prefix:test intitle:test",
"rawQuery": "prefix:test intitle:test",
"root": {
"keyword": {
"startOffset": 0,
"endOffset": 24,
"keyword": "CirrusSearch\\Query\\PrefixFeature",
"key": "prefix",
"value": "test intitle:test",
"quotedValue": "test intitle:test",
"delimiter": "",
"suffix": ""
}
}
}
},
"keyword greedy headings: greedy headings keywords eat no matter what is written after them": {
"query": "morelike: prefix:test intitle:test",
"expected": {
"query": "morelike: prefix:test intitle:test",
"rawQuery": "morelike: prefix:test intitle:test",
"root": {
"keyword": {
"startOffset": 0,
"endOffset": 34,
"keyword": "CirrusSearch\\Query\\MoreLikeFeature",
"key": "morelike",
"value": "prefix:test intitle:test",
"quotedValue": "prefix:test intitle:test",
"delimiter": "",
"suffix": ""
}
}
}
},
"keyword greedy headings: greedy headings keywords are ignored when not at the begining": {
"query": "foo morelike:baz",
"expected": {
"query": "foo morelike:baz",
"rawQuery": "foo morelike:baz",
"root": {
"words": {
"startOffset": 0,
"endOffset": 16,
"words": "foo morelike:baz"
}
}
}
},
"keyword headings: heading is not parsed when in the middle": {
"query": "word local:word",
"expected": {
"query": "word local:word",
"rawQuery": "word local:word",
"root": {
"words": {
"startOffset": 0,
"endOffset": 15,
"words": "word local:word"
}
}
}
},
"keyword : normal keyword can appear at the begining or after a space": {
"query": "intitle:foo word intitle:bar",
"expected": {
"query": "intitle:foo word intitle:bar",
"rawQuery": "intitle:foo word intitle:bar",
"root": {
"bool": {
"startOffset": 0,
"endOffset": 28,
"clauses": [
{
"MUST": {
"keyword": {
"startOffset": 0,
"endOffset": 11,
"keyword": "CirrusSearch\\Query\\InTitleFeature",
"key": "intitle",
"value": "foo",
"quotedValue": "foo",
"delimiter": "",
"suffix": ""
}
},
"explicit": false
},
{
"MUST": {
"words": {
"startOffset": 12,
"endOffset": 16,
"words": "word"
}
},
"explicit": false
},
{
"MUST": {
"keyword": {
"startOffset": 17,
"endOffset": 28,
"keyword": "CirrusSearch\\Query\\InTitleFeature",
"key": "intitle",
"value": "bar",
"quotedValue": "bar",
"delimiter": "",
"suffix": ""
}
},
"explicit": false
}
]
}
}
}
},
"keyword : normal usually accept a quoted value": {
"query": "intitle:\"foo \"bar baz\"",
"expected": {
"query": "intitle:\"foo \"bar baz\"",
"rawQuery": "intitle:\"foo \"bar baz\"",
"warnings": [
{
"msg": "cirrus-parse-error-unbalanced-phrase",
"start": 21
}
],
"root": {
"bool": {
"startOffset": 0,
"endOffset": 22,
"clauses": [
{
"MUST": {
"keyword": {
"startOffset": 0,
"endOffset": 14,
"keyword": "CirrusSearch\\Query\\InTitleFeature",
"key": "intitle",
"value": "foo ",
"quotedValue": "\"foo \"",
"delimiter": "\"",
"suffix": ""
}
},
"explicit": false
},
{
"MUST": {
"words": {
"startOffset": 14,
"endOffset": 21,
"words": "bar baz"
}
},
"explicit": false
},
{
"MUST": {
"phrase": {
"startOffset": 21,
"endOffset": 22,
"phrase": "",
"slop": -1,
"stem": false,
"unbalanced": true
}
},
"explicit": false
}
]
}
}
}
},
"keyword : regex is triggered with a \/ and accepts an optional suffix ": {
"query": "intitle:\/[a-z]\/ insource:\/<\\\/a>[^ ]\/i",
"expected": {
"query": "intitle:\/[a-z]\/ insource:\/<\\\/a>[^ ]\/i",
"rawQuery": "intitle:\/[a-z]\/ insource:\/<\\\/a>[^ ]\/i",
"root": {
"bool": {
"startOffset": 0,
"endOffset": 37,
"clauses": [
{
"MUST": {
"keyword": {
"startOffset": 0,
"endOffset": 15,
"keyword": "CirrusSearch\\Query\\InTitleFeature",
"key": "intitle",
"value": "[a-z]",
"quotedValue": "\/[a-z]\/",
"delimiter": "\/",
"suffix": ""
}
},
"explicit": false
},
{
"MUST": {
"keyword": {
"startOffset": 16,
"endOffset": 37,
"keyword": "CirrusSearch\\Query\\InSourceFeature",
"key": "insource",
"value": "<\/a>[^ ]",
"quotedValue": "\/<\\\/a>[^ ]\/",
"delimiter": "\/",
"suffix": "i"
}
},
"explicit": false
}
]
}
}
}
},
"keyword : normal keyword can not appear anywhere": {
"query": "\"intitle:bar\"",
"expected": {
"query": "\"intitle:bar\"",
"rawQuery": "\"intitle:bar\"",
"root": {
"phrase": {
"startOffset": 0,
"endOffset": 13,
"phrase": "intitle:bar",
"slop": -1,
"stem": false,
"unbalanced": false
}
}
}
},
"keyword : normal keyword can not appear anywhere unlike normal words": {
"query": "\"foo bar\"intitle:bar",
"expected": {
"query": "\"foo bar\"intitle:bar",
"rawQuery": "\"foo bar\"intitle:bar",
"root": {
"bool": {
"startOffset": 0,
"endOffset": 20,
"clauses": [
{
"MUST": {
"phrase": {
"startOffset": 0,
"endOffset": 9,
"phrase": "foo bar",
"slop": -1,
"stem": false,
"unbalanced": false
}
},
"explicit": false
},
{
"MUST": {
"words": {
"startOffset": 9,
"endOffset": 20,
"words": "intitle:bar"
}
},
"explicit": false
}
]
}
}
}
},
"keyword & negation prefix: normal keyword can be negated with - but not with ! (debatable)": {
"query": "-intitle:bar !intitle:bar",
"expected": {
"query": "-intitle:bar !intitle:bar",
"rawQuery": "-intitle:bar !intitle:bar",
"root": {
"bool": {
"startOffset": 1,
"endOffset": 25,
"clauses": [
{
"MUST_NOT": {
"keyword": {
"startOffset": 1,
"endOffset": 12,
"keyword": "CirrusSearch\\Query\\InTitleFeature",
"key": "intitle",
"value": "bar",
"quotedValue": "bar",
"delimiter": "",
"suffix": ""
}
},
"explicit": false
},
{
"MUST_NOT": {
"words": {
"startOffset": 14,
"endOffset": 25,
"words": "intitle:bar"
}
},
"explicit": false
}
]
}
}
}
},
"keywords & bool: follows normal boolean logic": {
"query": "intitle:foo AND intitle:bar OR intitle:baz OR NOT intitle:buz",
"expected": {
"query": "intitle:foo AND intitle:bar OR intitle:baz OR NOT intitle:buz",
"rawQuery": "intitle:foo AND intitle:bar OR intitle:baz OR NOT intitle:buz",
"root": {
"bool": {
"startOffset": 0,
"endOffset": 61,
"clauses": [
{
"MUST": {
"keyword": {
"startOffset": 0,
"endOffset": 11,
"keyword": "CirrusSearch\\Query\\InTitleFeature",
"key": "intitle",
"value": "foo",
"quotedValue": "foo",
"delimiter": "",
"suffix": ""
}
},
"explicit": true
},
{
"SHOULD": {
"keyword": {
"startOffset": 16,
"endOffset": 27,
"keyword": "CirrusSearch\\Query\\InTitleFeature",
"key": "intitle",
"value": "bar",
"quotedValue": "bar",
"delimiter": "",
"suffix": ""
}
},
"explicit": true
},
{
"SHOULD": {
"keyword": {
"startOffset": 31,
"endOffset": 42,
"keyword": "CirrusSearch\\Query\\InTitleFeature",
"key": "intitle",
"value": "baz",
"quotedValue": "baz",
"delimiter": "",
"suffix": ""
}
},
"explicit": true
},
{
"MUST_NOT": {
"keyword": {
"startOffset": 50,
"endOffset": 61,
"keyword": "CirrusSearch\\Query\\InTitleFeature",
"key": "intitle",
"value": "buz",
"quotedValue": "buz",
"delimiter": "",
"suffix": ""
}
},
"explicit": true
}
]
}
}
}
},
"keywords precedence: keywords take precedence over everything else": {
"query": "\" intitle:test \"",
"expected": {
"query": "\" intitle:test \"",
"rawQuery": "\" intitle:test \"",
"warnings": [
{
"msg": "cirrus-parse-error-unbalanced-phrase",
"start": 0
},
{
"msg": "cirrus-parse-error-unbalanced-phrase",
"start": 15
}
],
"root": {
"bool": {
"startOffset": 0,
"endOffset": 16,
"clauses": [
{
"MUST": {
"phrase": {
"startOffset": 0,
"endOffset": 2,
"phrase": " ",
"slop": -1,
"stem": false,
"unbalanced": true
}
},
"explicit": false
},
{
"MUST": {
"keyword": {
"startOffset": 2,
"endOffset": 14,
"keyword": "CirrusSearch\\Query\\InTitleFeature",
"key": "intitle",
"value": "test",
"quotedValue": "test",
"delimiter": "",
"suffix": ""
}
},
"explicit": false
},
{
"MUST": {
"phrase": {
"startOffset": 15,
"endOffset": 16,
"phrase": "",
"slop": -1,
"stem": false,
"unbalanced": true
}
},
"explicit": false
}
]
}
}
}
},
"fixups: unexpected bool operator is eaten as a word and produduce a warning": {
"query": "foo AND AND bar",
"expected": {
"query": "foo AND AND bar",
"rawQuery": "foo AND AND bar",
"warnings": [
{
"msg": "cirrus-parse-error-unexpected-token",
"start": 8,
"expected": [
"NOT",
"QUERY"
],
"actual": "AND"
}
],
"root": {
"bool": {
"startOffset": 0,
"endOffset": 15,
"clauses": [
{
"MUST": {
"words": {
"startOffset": 0,
"endOffset": 3,
"words": "foo"
}
},
"explicit": false
},
{
"MUST": {
"words": {
"startOffset": 8,
"endOffset": 15,
"words": "AND bar"
}
},
"explicit": true
}
]
}
}
}
},
"fixups: unexpected bool operator after NOT is eaten as a word and produduce a warning": {
"query": "foo NOT AND bar",
"expected": {
"query": "foo NOT AND bar",
"rawQuery": "foo NOT AND bar",
"warnings": [
{
"msg": "cirrus-parse-error-unexpected-token",
"start": 8,
"expected": [
"QUERY"
],
"actual": "AND"
}
],
"root": {
"bool": {
"startOffset": 0,
"endOffset": 15,
"clauses": [
{
"MUST": {
"words": {
"startOffset": 0,
"endOffset": 3,
"words": "foo"
}
},
"explicit": false
},
{
"MUST": {
"words": {
"startOffset": 8,
"endOffset": 15,
"words": "AND bar"
}
},
"explicit": false
}
]
}
}
}
},
"fixups: double explicit NOT is eaten as a word and produduce a warning": {
"query": "foo NOT NOT bar",
"expected": {
"query": "foo NOT NOT bar",
"rawQuery": "foo NOT NOT bar",
"warnings": [
{
"msg": "cirrus-parse-error-unexpected-token",
"start": 8,
"expected": [
"QUERY"
],
"actual": "NOT"
}
],
"root": {
"bool": {
"startOffset": 0,
"endOffset": 15,
"clauses": [
{
"MUST": {
"words": {
"startOffset": 0,
"endOffset": 3,
"words": "foo"
}
},
"explicit": false
},
{
"MUST": {
"words": {
"startOffset": 8,
"endOffset": 15,
"words": "NOT bar"
}
},
"explicit": false
}
]
}
}
}
},
"fixups: double negation with negation prefix is ignored and produduce a warning (debatable)": {
"query": "foo NOT -bar",
"expected": {
"query": "foo NOT -bar",
"rawQuery": "foo NOT -bar",
"warnings": [
{
"msg": "cirrus-parse-error-double-negation",
"start": 8
}
],
"root": {
"bool": {
"startOffset": 0,
"endOffset": 12,
"clauses": [
{
"MUST": {
"words": {
"startOffset": 0,
"endOffset": 3,
"words": "foo"
}
},
"explicit": false
},
{
"MUST": {
"words": {
"startOffset": 9,
"endOffset": 12,
"words": "bar"
}
},
"explicit": false
}
]
}
}
}
},
"fixups: OR at eof is eaten as a word and produduce a warning": {
"query": "foo OR ",
"expected": {
"query": "foo OR ",
"rawQuery": "foo OR ",
"warnings": [
{
"msg": "cirrus-parse-error-unexpected-eof",
"start": 7,
"expected": [
"NOT",
"QUERY"
],
"actual": "EOF"
}
],
"root": {
"words": {
"startOffset": 0,
"endOffset": 6,
"words": "foo OR"
}
}
}
},
"fixups: NOT at eof is eaten as a word and produduce a warning": {
"query": "foo NOT ",
"expected": {
"query": "foo NOT ",
"rawQuery": "foo NOT ",
"warnings": [
{
"msg": "cirrus-parse-error-unexpected-eof",
"start": 8,
"expected": [
"QUERY"
],
"actual": "EOF"
}
],
"root": {
"words": {
"startOffset": 0,
"endOffset": 7,
"words": "foo NOT"
}
}
}
},
"fixups: leading boolean operator is eaten as a word and produce a warning": {
"query": "AND foo",
"expected": {
"query": "AND foo",
"rawQuery": "AND foo",
"warnings": [
{
"msg": "cirrus-parse-error-unexpected-token",
"start": 0,
"expected": [
"NOT",
"QUERY"
],
"actual": "AND"
}
],
"root": {
"words": {
"startOffset": 0,
"endOffset": 7,
"words": "AND foo"
}
}
}
},
"fixups: unbalanced phrase are identified and produce a warning": {
"query": "foo \"bar ",
"expected": {
"query": "foo \"bar ",
"rawQuery": "foo \"bar ",
"warnings": [
{
"msg": "cirrus-parse-error-unbalanced-phrase",
"start": 4
}
],
"root": {
"bool": {
"startOffset": 0,
"endOffset": 9,
"clauses": [
{
"MUST": {
"words": {
"startOffset": 0,
"endOffset": 3,
"words": "foo"
}
},
"explicit": false
},
{
"MUST": {
"phrase": {
"startOffset": 4,
"endOffset": 9,
"phrase": "bar ",
"slop": -1,
"stem": false,
"unbalanced": true
}
},
"explicit": false
}
]
}
}
}
},
"fixups: query made of bool operator may read one bool out of 2 properly and produce a warning (debatable)": {
"query": "AND && OR OR AND && ||",
"expected": {
"query": "AND && OR OR AND && ||",
"rawQuery": "AND && OR OR AND && ||",
"warnings": [
{
"msg": "cirrus-parse-error-unexpected-token",
"start": 0,
"expected": [
"NOT",
"QUERY"
],
"actual": "AND"
},
{
"msg": "cirrus-parse-error-unexpected-token",
"start": 7,
"expected": [
"NOT",
"QUERY"
],
"actual": "OR"
},
{
"msg": "cirrus-parse-error-unexpected-token",
"start": 13,
"expected": [
"NOT",
"QUERY"
],
"actual": "AND"
},
{
"msg": "cirrus-parse-error-unexpected-token",
"start": 20,
"expected": [
"NOT",
"QUERY"
],
"actual": "OR"
}
],
"root": {
"bool": {
"startOffset": 0,
"endOffset": 22,
"clauses": [
{
"MUST": {
"words": {
"startOffset": 0,
"endOffset": 3,
"words": "AND"
}
},
"explicit": false
},
{
"MUST": {
"words": {
"startOffset": 7,
"endOffset": 9,
"words": "OR"
}
},
"explicit": false
},
{
"MUST": {
"words": {
"startOffset": 13,
"endOffset": 16,
"words": "AND"
}
},
"explicit": false
},
{
"MUST": {
"words": {
"startOffset": 20,
"endOffset": 22,
"words": "||"
}
},
"explicit": true
}
]
}
}
}
}
}
Content licensed under Creative Commons Attribution-ShareAlike (CC BY-SA) 4.0 unless otherwise noted; code licensed under GNU General Public License (GPL) 2.0 or later and other open source licenses. By using this site, you agree to the Terms of Use, Privacy Policy, and Code of Conduct. · Wikimedia Foundation · Privacy Policy · Code of Conduct · Terms of Use · Disclaimer · CC-BY-SA · GPL