jenkins-bot has submitted this change and it was merged. ( https://gerrit.wikimedia.org/r/371942 )
Change subject: Add subpageof keyword
......................................................................
Add subpageof keyword
It's a specialized version of the prefix keywork to find subpages.
It does not have the limitation of prefix:
- non-greedy
- does not try to handle namespace
- search on redirects
NOTE: The keyword is subpageof, but could be changed to something else.
(feel free to amend the patch).
If reusing the prefix elastic field is not sufficient we'll have to dig
into more dedicated field.
Bug: T159321
Change-Id: Ic1489b00b6179d60d662cd6645d54ba3428343d9
---
M autoload.php
A includes/Query/SubPageOf.php
M includes/Searcher.php
A tests/unit/fixtures/searchText/subpageof_001.default.expected
A tests/unit/fixtures/searchText/subpageof_001.fullyfeatured-interwiki.expected
A tests/unit/fixtures/searchText/subpageof_001.fullyfeatured.expected
A tests/unit/fixtures/searchText/subpageof_001.query
7 files changed, 1,392 insertions(+), 0 deletions(-)
Approvals:
Smalyshev: Looks good to me, but someone else must approve
Cindy-the-browser-test-bot: Looks good to me, but someone else must approve
EBernhardson: Looks good to me, approved
jenkins-bot: Verified
Thiemo Mättig (WMDE): Looks good to me, but someone else must approve
diff --git a/autoload.php b/autoload.php
index 6b8cdda..2e72740 100644
--- a/autoload.php
+++ b/autoload.php
@@ -135,6 +135,7 @@
'CirrusSearch\\Query\\RegexInSourceFeature' => __DIR__ .
'/includes/Query/RegexInSourceFeature.php',
'CirrusSearch\\Query\\SimpleInSourceFeature' => __DIR__ .
'/includes/Query/SimpleInSourceFeature.php',
'CirrusSearch\\Query\\SimpleKeywordFeature' => __DIR__ .
'/includes/Query/SimpleKeywordFeature.php',
+ 'CirrusSearch\\Query\\SubPageOfFeature' => __DIR__ .
'/includes/Query/SubPageOf.php',
'CirrusSearch\\RequestLog' => __DIR__ . '/includes/RequestLog.php',
'CirrusSearch\\RequestLogger' => __DIR__ .
'/includes/RequestLogger.php',
'CirrusSearch\\RescoreProfiles' => __DIR__ .
'/profiles/RescoreProfiles.php',
diff --git a/includes/Query/SubPageOf.php b/includes/Query/SubPageOf.php
new file mode 100644
index 0000000..04fdf4c
--- /dev/null
+++ b/includes/Query/SubPageOf.php
@@ -0,0 +1,44 @@
+<?php
+
+namespace CirrusSearch\Query;
+
+use CirrusSearch\Search\Filters;
+use CirrusSearch\Search\SearchContext;
+
+/**
+ * subpagesof, find subpages of a given page
+ * uses the prefix field, very similar to the prefix except
+ * that it enforces a trailing / and is not a greedy keyword
+ */
+class SubPageOfFeature extends SimpleKeywordFeature {
+ /**
+ * @return string[]
+ */
+ protected function getKeywords() {
+ return [ 'subpageof' ];
+ }
+
+ /**
+ * @param SearchContext $context
+ * @param string $key The keyword
+ * @param string $value The value attached to the keyword with quotes
stripped
+ * @param string $quotedValue The original value in the search string,
including quotes if used
+ * @param bool $negated Is the search negated? Not used to generate the
returned AbstractQuery,
+ * that will be negated as necessary. Used for any other
building/context necessary.
+ * @return array Two element array, first an AbstractQuery or null to
apply to the
+ * query. Second a boolean indicating if the quotedValue should be
kept in the search
+ * string.
+ */
+ protected function doApply( SearchContext $context, $key, $value,
$quotedValue, $negated ) {
+ if ( empty( $value ) ) {
+ return [ null, false ];
+ }
+ if ( substr( $value, -1 ) != '/' ) {
+ $value .= '/';
+ }
+ $query = new \Elastica\Query\MultiMatch();
+ $query->setFields( [ 'title.prefix', 'redirect.title.prefix' ]
);
+ $query->setQuery( $value );
+ return [ $query, false ];
+ }
+}
diff --git a/includes/Searcher.php b/includes/Searcher.php
index 766cb38..74d69cb 100644
--- a/includes/Searcher.php
+++ b/includes/Searcher.php
@@ -351,6 +351,8 @@
new Query\FileNumericFeature(),
// Content model feature
new Query\ContentModelFeature(),
+ // subpageof keyword
+ new Query\SubPageOfFeature(),
];
$extraFeatures = [];
diff --git a/tests/unit/fixtures/searchText/subpageof_001.default.expected
b/tests/unit/fixtures/searchText/subpageof_001.default.expected
new file mode 100644
index 0000000..2fd4d6c
--- /dev/null
+++ b/tests/unit/fixtures/searchText/subpageof_001.default.expected
@@ -0,0 +1,220 @@
+{
+ "description": "full_text search for 'subpageof:\"parent page\"'",
+ "options": {
+ "search_type": "dfs_query_then_fetch",
+ "timeout": "20s"
+ },
+ "params": {
+ "search_type": "dfs_query_then_fetch",
+ "timeout": "20s"
+ },
+ "query": {
+ "_source": [
+ "namespace",
+ "namespace_text",
+ "redirect.*",
+ "text_bytes",
+ "timestamp",
+ "title",
+ "wiki"
+ ],
+ "highlight": {
+ "fields": {
+ "auxiliary_text": {
+ "fragment_size": 150,
+ "fragmenter": "scan",
+ "matched_fields": [
+ "auxiliary_text",
+ "auxiliary_text.plain"
+ ],
+ "number_of_fragments": 1,
+ "options": {
+ "boost_before": {
+ "20": 2,
+ "50": 1.8,
+ "200": 1.5,
+ "1000": 1.2
+ },
+ "max_fragments_scored": 5000,
+ "skip_if_last_matched": true,
+ "top_scoring": true
+ },
+ "type": "experimental"
+ },
+ "category": {
+ "fragmenter": "none",
+ "matched_fields": [
+ "category",
+ "category.plain"
+ ],
+ "number_of_fragments": 1,
+ "options": {
+ "skip_if_last_matched": true
+ },
+ "order": "score",
+ "type": "experimental"
+ },
+ "heading": {
+ "fragmenter": "none",
+ "matched_fields": [
+ "heading",
+ "heading.plain"
+ ],
+ "number_of_fragments": 1,
+ "options": {
+ "skip_if_last_matched": true
+ },
+ "order": "score",
+ "type": "experimental"
+ },
+ "redirect.title": {
+ "fragmenter": "none",
+ "matched_fields": [
+ "redirect.title",
+ "redirect.title.plain"
+ ],
+ "number_of_fragments": 1,
+ "options": {
+ "skip_if_last_matched": true
+ },
+ "order": "score",
+ "type": "experimental"
+ },
+ "text": {
+ "fragment_size": 150,
+ "fragmenter": "scan",
+ "matched_fields": [
+ "text",
+ "text.plain"
+ ],
+ "no_match_size": 150,
+ "number_of_fragments": 1,
+ "options": {
+ "boost_before": {
+ "20": 2,
+ "50": 1.8,
+ "200": 1.5,
+ "1000": 1.2
+ },
+ "max_fragments_scored": 5000,
+ "top_scoring": true
+ },
+ "type": "experimental"
+ },
+ "title": {
+ "fragmenter": "none",
+ "matched_fields": [
+ "title",
+ "title.plain"
+ ],
+ "number_of_fragments": 1,
+ "type": "experimental"
+ }
+ },
+ "post_tags": [
+ "<\/span>"
+ ],
+ "pre_tags": [
+ "<span class=\"searchmatch\">"
+ ]
+ },
+ "query": {
+ "bool": {
+ "filter": [
+ {
+ "bool": {
+ "must": [
+ {
+ "multi_match": {
+ "fields": [
+ "redirect.title.prefix",
+ "title.prefix"
+ ],
+ "query": "parent page\/"
+ }
+ },
+ {
+ "terms": {
+ "namespace": [
+ 0,
+ 1,
+ 2,
+ 3
+ ]
+ }
+ }
+ ]
+ }
+ }
+ ],
+ "must": [
+ {
+ "match_all": []
+ }
+ ]
+ }
+ },
+ "rescore": [
+ {
+ "query": {
+ "query_weight": 1,
+ "rescore_query": {
+ "function_score": {
+ "functions": [
+ {
+ "field_value_factor": {
+ "field": "incoming_links",
+ "missing": 0,
+ "modifier": "log2p"
+ }
+ },
+ {
+ "filter": {
+ "terms": {
+ "namespace": [
+ 1
+ ]
+ }
+ },
+ "weight": "0.25"
+ },
+ {
+ "filter": {
+ "terms": {
+ "namespace": [
+ 2
+ ]
+ }
+ },
+ "weight": "0.05"
+ },
+ {
+ "filter": {
+ "terms": {
+ "namespace": [
+ 3
+ ]
+ }
+ },
+ "weight": "0.0125"
+ }
+ ]
+ }
+ },
+ "rescore_query_weight": 1,
+ "score_mode": "multiply"
+ },
+ "window_size": 8192
+ }
+ ],
+ "size": 20,
+ "stats": [
+ "filter_only",
+ "full_text",
+ "subpageof"
+ ],
+ "stored_fields": [
+ "text.word_count"
+ ]
+ }
+}
\ No newline at end of file
diff --git
a/tests/unit/fixtures/searchText/subpageof_001.fullyfeatured-interwiki.expected
b/tests/unit/fixtures/searchText/subpageof_001.fullyfeatured-interwiki.expected
new file mode 100644
index 0000000..8afab83
--- /dev/null
+++
b/tests/unit/fixtures/searchText/subpageof_001.fullyfeatured-interwiki.expected
@@ -0,0 +1,902 @@
+[
+ {
+ "description": "full_text search for 'subpageof:\"parent page\"'",
+ "options": {
+ "search_type": "dfs_query_then_fetch",
+ "timeout": "20s"
+ },
+ "params": {
+ "search_type": "dfs_query_then_fetch",
+ "timeout": "20s"
+ },
+ "path": "itwikibooks\/page\/_search",
+ "query": {
+ "_source": [
+ "namespace",
+ "namespace_text",
+ "redirect.*",
+ "text_bytes",
+ "timestamp",
+ "title",
+ "wiki"
+ ],
+ "highlight": {
+ "fields": {
+ "auxiliary_text": {
+ "fragment_size": 150,
+ "fragmenter": "scan",
+ "matched_fields": [
+ "auxiliary_text",
+ "auxiliary_text.plain"
+ ],
+ "number_of_fragments": 1,
+ "options": {
+ "boost_before": {
+ "20": 2,
+ "50": 1.8,
+ "200": 1.5,
+ "1000": 1.2
+ },
+ "max_fragments_scored": 5000,
+ "skip_if_last_matched": true,
+ "top_scoring": true
+ },
+ "type": "experimental"
+ },
+ "category": {
+ "fragmenter": "none",
+ "matched_fields": [
+ "category",
+ "category.plain"
+ ],
+ "number_of_fragments": 1,
+ "options": {
+ "skip_if_last_matched": true
+ },
+ "order": "score",
+ "type": "experimental"
+ },
+ "heading": {
+ "fragmenter": "none",
+ "matched_fields": [
+ "heading",
+ "heading.plain"
+ ],
+ "number_of_fragments": 1,
+ "options": {
+ "skip_if_last_matched": true
+ },
+ "order": "score",
+ "type": "experimental"
+ },
+ "redirect.title": {
+ "fragmenter": "none",
+ "matched_fields": [
+ "redirect.title",
+ "redirect.title.plain"
+ ],
+ "number_of_fragments": 1,
+ "options": {
+ "skip_if_last_matched": true
+ },
+ "order": "score",
+ "type": "experimental"
+ },
+ "text": {
+ "fragment_size": 150,
+ "fragmenter": "scan",
+ "matched_fields": [
+ "text",
+ "text.plain"
+ ],
+ "no_match_size": 150,
+ "number_of_fragments": 1,
+ "options": {
+ "boost_before": {
+ "20": 2,
+ "50": 1.8,
+ "200": 1.5,
+ "1000": 1.2
+ },
+ "max_fragments_scored": 5000,
+ "top_scoring": true
+ },
+ "type": "experimental"
+ },
+ "title": {
+ "fragmenter": "none",
+ "matched_fields": [
+ "title",
+ "title.plain"
+ ],
+ "number_of_fragments": 1,
+ "type": "experimental"
+ }
+ },
+ "post_tags": [
+ "<\/span>"
+ ],
+ "pre_tags": [
+ "<span class=\"searchmatch\">"
+ ]
+ },
+ "query": {
+ "bool": {
+ "filter": [
+ {
+ "bool": {
+ "must": [
+ {
+ "multi_match": {
+ "fields": [
+ "redirect.title.prefix",
+ "title.prefix"
+ ],
+ "query": "parent page\/"
+ }
+ },
+ {
+ "terms": {
+ "namespace": [
+ 0,
+ 1,
+ 2,
+ 3
+ ]
+ }
+ }
+ ]
+ }
+ }
+ ],
+ "must": [
+ {
+ "match_all": []
+ }
+ ]
+ }
+ },
+ "rescore": [
+ {
+ "query": {
+ "query_weight": 1,
+ "rescore_query": {
+ "function_score": {
+ "functions": [
+ {
+ "field_value_factor": {
+ "field": "incoming_links",
+ "missing": 0,
+ "modifier": "log2p"
+ }
+ },
+ {
+ "filter": {
+ "terms": {
+ "namespace": [
+ 1
+ ]
+ }
+ },
+ "weight": "0.25"
+ },
+ {
+ "filter": {
+ "terms": {
+ "namespace": [
+ 2
+ ]
+ }
+ },
+ "weight": "0.05"
+ },
+ {
+ "filter": {
+ "terms": {
+ "namespace": [
+ 3
+ ]
+ }
+ },
+ "weight": "0.0125"
+ }
+ ]
+ }
+ },
+ "rescore_query_weight": 1,
+ "score_mode": "multiply"
+ },
+ "window_size": 8192
+ }
+ ],
+ "size": 5,
+ "stats": [
+ "filter_only",
+ "full_text",
+ "subpageof"
+ ],
+ "stored_fields": [
+ "text.word_count"
+ ]
+ }
+ },
+ {
+ "description": "full_text search for 'subpageof:\"parent page\"'",
+ "options": {
+ "search_type": "dfs_query_then_fetch",
+ "timeout": "20s"
+ },
+ "params": {
+ "search_type": "dfs_query_then_fetch",
+ "timeout": "20s"
+ },
+ "path": "itwikivoyage\/page\/_search",
+ "query": {
+ "_source": [
+ "namespace",
+ "namespace_text",
+ "redirect.*",
+ "text_bytes",
+ "timestamp",
+ "title",
+ "wiki"
+ ],
+ "highlight": {
+ "fields": {
+ "auxiliary_text": {
+ "fragment_size": 150,
+ "fragmenter": "scan",
+ "matched_fields": [
+ "auxiliary_text",
+ "auxiliary_text.plain"
+ ],
+ "number_of_fragments": 1,
+ "options": {
+ "boost_before": {
+ "20": 2,
+ "50": 1.8,
+ "200": 1.5,
+ "1000": 1.2
+ },
+ "max_fragments_scored": 5000,
+ "skip_if_last_matched": true,
+ "top_scoring": true
+ },
+ "type": "experimental"
+ },
+ "category": {
+ "fragmenter": "none",
+ "matched_fields": [
+ "category",
+ "category.plain"
+ ],
+ "number_of_fragments": 1,
+ "options": {
+ "skip_if_last_matched": true
+ },
+ "order": "score",
+ "type": "experimental"
+ },
+ "heading": {
+ "fragmenter": "none",
+ "matched_fields": [
+ "heading",
+ "heading.plain"
+ ],
+ "number_of_fragments": 1,
+ "options": {
+ "skip_if_last_matched": true
+ },
+ "order": "score",
+ "type": "experimental"
+ },
+ "redirect.title": {
+ "fragmenter": "none",
+ "matched_fields": [
+ "redirect.title",
+ "redirect.title.plain"
+ ],
+ "number_of_fragments": 1,
+ "options": {
+ "skip_if_last_matched": true
+ },
+ "order": "score",
+ "type": "experimental"
+ },
+ "text": {
+ "fragment_size": 150,
+ "fragmenter": "scan",
+ "matched_fields": [
+ "text",
+ "text.plain"
+ ],
+ "no_match_size": 150,
+ "number_of_fragments": 1,
+ "options": {
+ "boost_before": {
+ "20": 2,
+ "50": 1.8,
+ "200": 1.5,
+ "1000": 1.2
+ },
+ "max_fragments_scored": 5000,
+ "top_scoring": true
+ },
+ "type": "experimental"
+ },
+ "title": {
+ "fragmenter": "none",
+ "matched_fields": [
+ "title",
+ "title.plain"
+ ],
+ "number_of_fragments": 1,
+ "type": "experimental"
+ }
+ },
+ "post_tags": [
+ "<\/span>"
+ ],
+ "pre_tags": [
+ "<span class=\"searchmatch\">"
+ ]
+ },
+ "query": {
+ "bool": {
+ "filter": [
+ {
+ "bool": {
+ "must": [
+ {
+ "multi_match": {
+ "fields": [
+ "redirect.title.prefix",
+ "title.prefix"
+ ],
+ "query": "parent page\/"
+ }
+ },
+ {
+ "terms": {
+ "namespace": [
+ 0,
+ 1,
+ 2,
+ 3
+ ]
+ }
+ }
+ ]
+ }
+ }
+ ],
+ "must": [
+ {
+ "match_all": []
+ }
+ ]
+ }
+ },
+ "rescore": [
+ {
+ "query": {
+ "query_weight": 1,
+ "rescore_query": {
+ "function_score": {
+ "functions": [
+ {
+ "filter": {
+ "terms": {
+ "namespace": [
+ 1
+ ]
+ }
+ },
+ "weight": "0.25"
+ },
+ {
+ "filter": {
+ "terms": {
+ "namespace": [
+ 2
+ ]
+ }
+ },
+ "weight": "0.05"
+ },
+ {
+ "filter": {
+ "terms": {
+ "namespace": [
+ 3
+ ]
+ }
+ },
+ "weight": "0.0125"
+ }
+ ]
+ }
+ },
+ "rescore_query_weight": 1,
+ "score_mode": "multiply"
+ },
+ "window_size": 8192
+ },
+ {
+ "query": {
+ "query_weight": 1,
+ "rescore_query": {
+ "function_score": {
+ "functions": [
+ {
+ "script_score": {
+ "script": {
+ "inline":
"pow(doc['incoming_links'].value , 0.7) \/ ( pow(doc['incoming_links'].value,
0.7) + pow(30,0.7))",
+ "lang": "expression"
+ }
+ },
+ "weight": 13
+ }
+ ]
+ }
+ },
+ "rescore_query_weight": 1,
+ "score_mode": "total"
+ },
+ "window_size": 8192
+ }
+ ],
+ "size": 5,
+ "stats": [
+ "filter_only",
+ "full_text",
+ "subpageof"
+ ],
+ "stored_fields": [
+ "text.word_count"
+ ]
+ }
+ },
+ {
+ "description": "full_text search for 'subpageof:\"parent page\"'",
+ "options": {
+ "search_type": "dfs_query_then_fetch",
+ "timeout": "20s"
+ },
+ "params": {
+ "search_type": "dfs_query_then_fetch",
+ "timeout": "20s"
+ },
+ "path": "itwiktionary\/page\/_search",
+ "query": {
+ "_source": [
+ "namespace",
+ "namespace_text",
+ "redirect.*",
+ "text_bytes",
+ "timestamp",
+ "title",
+ "wiki"
+ ],
+ "highlight": {
+ "fields": {
+ "auxiliary_text": {
+ "fragment_size": 150,
+ "fragmenter": "scan",
+ "matched_fields": [
+ "auxiliary_text",
+ "auxiliary_text.plain"
+ ],
+ "number_of_fragments": 1,
+ "options": {
+ "boost_before": {
+ "20": 2,
+ "50": 1.8,
+ "200": 1.5,
+ "1000": 1.2
+ },
+ "max_fragments_scored": 5000,
+ "skip_if_last_matched": true,
+ "top_scoring": true
+ },
+ "type": "experimental"
+ },
+ "category": {
+ "fragmenter": "none",
+ "matched_fields": [
+ "category",
+ "category.plain"
+ ],
+ "number_of_fragments": 1,
+ "options": {
+ "skip_if_last_matched": true
+ },
+ "order": "score",
+ "type": "experimental"
+ },
+ "heading": {
+ "fragmenter": "none",
+ "matched_fields": [
+ "heading",
+ "heading.plain"
+ ],
+ "number_of_fragments": 1,
+ "options": {
+ "skip_if_last_matched": true
+ },
+ "order": "score",
+ "type": "experimental"
+ },
+ "redirect.title": {
+ "fragmenter": "none",
+ "matched_fields": [
+ "redirect.title",
+ "redirect.title.plain"
+ ],
+ "number_of_fragments": 1,
+ "options": {
+ "skip_if_last_matched": true
+ },
+ "order": "score",
+ "type": "experimental"
+ },
+ "text": {
+ "fragment_size": 150,
+ "fragmenter": "scan",
+ "matched_fields": [
+ "text",
+ "text.plain"
+ ],
+ "no_match_size": 150,
+ "number_of_fragments": 1,
+ "options": {
+ "boost_before": {
+ "20": 2,
+ "50": 1.8,
+ "200": 1.5,
+ "1000": 1.2
+ },
+ "max_fragments_scored": 5000,
+ "top_scoring": true
+ },
+ "type": "experimental"
+ },
+ "title": {
+ "fragmenter": "none",
+ "matched_fields": [
+ "title",
+ "title.plain"
+ ],
+ "number_of_fragments": 1,
+ "type": "experimental"
+ }
+ },
+ "post_tags": [
+ "<\/span>"
+ ],
+ "pre_tags": [
+ "<span class=\"searchmatch\">"
+ ]
+ },
+ "query": {
+ "bool": {
+ "filter": [
+ {
+ "bool": {
+ "must": [
+ {
+ "multi_match": {
+ "fields": [
+ "redirect.title.prefix",
+ "title.prefix"
+ ],
+ "query": "parent page\/"
+ }
+ },
+ {
+ "terms": {
+ "namespace": [
+ 0,
+ 1,
+ 2,
+ 3
+ ]
+ }
+ }
+ ]
+ }
+ }
+ ],
+ "must": [
+ {
+ "match_all": []
+ }
+ ]
+ }
+ },
+ "rescore": [
+ {
+ "query": {
+ "query_weight": 1,
+ "rescore_query": {
+ "function_score": {
+ "functions": [
+ {
+ "field_value_factor": {
+ "field": "incoming_links",
+ "missing": 0,
+ "modifier": "log2p"
+ }
+ },
+ {
+ "filter": {
+ "terms": {
+ "namespace": [
+ 1
+ ]
+ }
+ },
+ "weight": "0.25"
+ },
+ {
+ "filter": {
+ "terms": {
+ "namespace": [
+ 2
+ ]
+ }
+ },
+ "weight": "0.05"
+ },
+ {
+ "filter": {
+ "terms": {
+ "namespace": [
+ 3
+ ]
+ }
+ },
+ "weight": "0.0125"
+ }
+ ]
+ }
+ },
+ "rescore_query_weight": 1,
+ "score_mode": "multiply"
+ },
+ "window_size": 8192
+ }
+ ],
+ "size": 5,
+ "stats": [
+ "filter_only",
+ "full_text",
+ "subpageof"
+ ],
+ "stored_fields": [
+ "text.word_count"
+ ]
+ }
+ },
+ {
+ "description": "full_text search for 'subpageof:\"parent page\"'",
+ "options": {
+ "search_type": "dfs_query_then_fetch",
+ "timeout": "20s"
+ },
+ "params": {
+ "search_type": "dfs_query_then_fetch",
+ "timeout": "20s"
+ },
+ "path": "wiki\/page\/_search",
+ "query": {
+ "_source": [
+ "namespace",
+ "namespace_text",
+ "redirect.*",
+ "text_bytes",
+ "timestamp",
+ "title",
+ "wiki"
+ ],
+ "highlight": {
+ "fields": {
+ "auxiliary_text": {
+ "fragment_size": 150,
+ "fragmenter": "scan",
+ "matched_fields": [
+ "auxiliary_text",
+ "auxiliary_text.plain"
+ ],
+ "number_of_fragments": 1,
+ "options": {
+ "boost_before": {
+ "20": 2,
+ "50": 1.8,
+ "200": 1.5,
+ "1000": 1.2
+ },
+ "max_fragments_scored": 5000,
+ "skip_if_last_matched": true,
+ "top_scoring": true
+ },
+ "type": "experimental"
+ },
+ "category": {
+ "fragmenter": "none",
+ "matched_fields": [
+ "category",
+ "category.plain"
+ ],
+ "number_of_fragments": 1,
+ "options": {
+ "skip_if_last_matched": true
+ },
+ "order": "score",
+ "type": "experimental"
+ },
+ "heading": {
+ "fragmenter": "none",
+ "matched_fields": [
+ "heading",
+ "heading.plain"
+ ],
+ "number_of_fragments": 1,
+ "options": {
+ "skip_if_last_matched": true
+ },
+ "order": "score",
+ "type": "experimental"
+ },
+ "redirect.title": {
+ "fragmenter": "none",
+ "matched_fields": [
+ "redirect.title",
+ "redirect.title.plain"
+ ],
+ "number_of_fragments": 1,
+ "options": {
+ "skip_if_last_matched": true
+ },
+ "order": "score",
+ "type": "experimental"
+ },
+ "text": {
+ "fragment_size": 150,
+ "fragmenter": "scan",
+ "matched_fields": [
+ "text",
+ "text.plain"
+ ],
+ "no_match_size": 150,
+ "number_of_fragments": 1,
+ "options": {
+ "boost_before": {
+ "20": 2,
+ "50": 1.8,
+ "200": 1.5,
+ "1000": 1.2
+ },
+ "max_fragments_scored": 5000,
+ "top_scoring": true
+ },
+ "type": "experimental"
+ },
+ "title": {
+ "fragmenter": "none",
+ "matched_fields": [
+ "title",
+ "title.plain"
+ ],
+ "number_of_fragments": 1,
+ "type": "experimental"
+ }
+ },
+ "post_tags": [
+ "<\/span>"
+ ],
+ "pre_tags": [
+ "<span class=\"searchmatch\">"
+ ]
+ },
+ "query": {
+ "bool": {
+ "filter": [
+ {
+ "bool": {
+ "must": [
+ {
+ "multi_match": {
+ "fields": [
+ "redirect.title.prefix",
+ "title.prefix"
+ ],
+ "query": "parent page\/"
+ }
+ },
+ {
+ "terms": {
+ "namespace": [
+ 0,
+ 1,
+ 2,
+ 3
+ ]
+ }
+ }
+ ]
+ }
+ }
+ ],
+ "must": [
+ {
+ "match_all": []
+ }
+ ]
+ }
+ },
+ "rescore": [
+ {
+ "query": {
+ "query_weight": 1,
+ "rescore_query": {
+ "function_score": {
+ "functions": [
+ {
+ "field_value_factor": {
+ "field": "incoming_links",
+ "missing": 0,
+ "modifier": "log2p"
+ }
+ },
+ {
+ "filter": {
+ "terms": {
+ "namespace": [
+ 1
+ ]
+ }
+ },
+ "weight": "0.25"
+ },
+ {
+ "filter": {
+ "terms": {
+ "namespace": [
+ 2
+ ]
+ }
+ },
+ "weight": "0.05"
+ },
+ {
+ "filter": {
+ "terms": {
+ "namespace": [
+ 3
+ ]
+ }
+ },
+ "weight": "0.0125"
+ }
+ ]
+ }
+ },
+ "rescore_query_weight": 1,
+ "score_mode": "multiply"
+ },
+ "window_size": 8192
+ }
+ ],
+ "size": 20,
+ "stats": [
+ "filter_only",
+ "full_text",
+ "subpageof"
+ ],
+ "stored_fields": [
+ "text.word_count"
+ ]
+ }
+ }
+]
\ No newline at end of file
diff --git
a/tests/unit/fixtures/searchText/subpageof_001.fullyfeatured.expected
b/tests/unit/fixtures/searchText/subpageof_001.fullyfeatured.expected
new file mode 100644
index 0000000..2fd4d6c
--- /dev/null
+++ b/tests/unit/fixtures/searchText/subpageof_001.fullyfeatured.expected
@@ -0,0 +1,220 @@
+{
+ "description": "full_text search for 'subpageof:\"parent page\"'",
+ "options": {
+ "search_type": "dfs_query_then_fetch",
+ "timeout": "20s"
+ },
+ "params": {
+ "search_type": "dfs_query_then_fetch",
+ "timeout": "20s"
+ },
+ "query": {
+ "_source": [
+ "namespace",
+ "namespace_text",
+ "redirect.*",
+ "text_bytes",
+ "timestamp",
+ "title",
+ "wiki"
+ ],
+ "highlight": {
+ "fields": {
+ "auxiliary_text": {
+ "fragment_size": 150,
+ "fragmenter": "scan",
+ "matched_fields": [
+ "auxiliary_text",
+ "auxiliary_text.plain"
+ ],
+ "number_of_fragments": 1,
+ "options": {
+ "boost_before": {
+ "20": 2,
+ "50": 1.8,
+ "200": 1.5,
+ "1000": 1.2
+ },
+ "max_fragments_scored": 5000,
+ "skip_if_last_matched": true,
+ "top_scoring": true
+ },
+ "type": "experimental"
+ },
+ "category": {
+ "fragmenter": "none",
+ "matched_fields": [
+ "category",
+ "category.plain"
+ ],
+ "number_of_fragments": 1,
+ "options": {
+ "skip_if_last_matched": true
+ },
+ "order": "score",
+ "type": "experimental"
+ },
+ "heading": {
+ "fragmenter": "none",
+ "matched_fields": [
+ "heading",
+ "heading.plain"
+ ],
+ "number_of_fragments": 1,
+ "options": {
+ "skip_if_last_matched": true
+ },
+ "order": "score",
+ "type": "experimental"
+ },
+ "redirect.title": {
+ "fragmenter": "none",
+ "matched_fields": [
+ "redirect.title",
+ "redirect.title.plain"
+ ],
+ "number_of_fragments": 1,
+ "options": {
+ "skip_if_last_matched": true
+ },
+ "order": "score",
+ "type": "experimental"
+ },
+ "text": {
+ "fragment_size": 150,
+ "fragmenter": "scan",
+ "matched_fields": [
+ "text",
+ "text.plain"
+ ],
+ "no_match_size": 150,
+ "number_of_fragments": 1,
+ "options": {
+ "boost_before": {
+ "20": 2,
+ "50": 1.8,
+ "200": 1.5,
+ "1000": 1.2
+ },
+ "max_fragments_scored": 5000,
+ "top_scoring": true
+ },
+ "type": "experimental"
+ },
+ "title": {
+ "fragmenter": "none",
+ "matched_fields": [
+ "title",
+ "title.plain"
+ ],
+ "number_of_fragments": 1,
+ "type": "experimental"
+ }
+ },
+ "post_tags": [
+ "<\/span>"
+ ],
+ "pre_tags": [
+ "<span class=\"searchmatch\">"
+ ]
+ },
+ "query": {
+ "bool": {
+ "filter": [
+ {
+ "bool": {
+ "must": [
+ {
+ "multi_match": {
+ "fields": [
+ "redirect.title.prefix",
+ "title.prefix"
+ ],
+ "query": "parent page\/"
+ }
+ },
+ {
+ "terms": {
+ "namespace": [
+ 0,
+ 1,
+ 2,
+ 3
+ ]
+ }
+ }
+ ]
+ }
+ }
+ ],
+ "must": [
+ {
+ "match_all": []
+ }
+ ]
+ }
+ },
+ "rescore": [
+ {
+ "query": {
+ "query_weight": 1,
+ "rescore_query": {
+ "function_score": {
+ "functions": [
+ {
+ "field_value_factor": {
+ "field": "incoming_links",
+ "missing": 0,
+ "modifier": "log2p"
+ }
+ },
+ {
+ "filter": {
+ "terms": {
+ "namespace": [
+ 1
+ ]
+ }
+ },
+ "weight": "0.25"
+ },
+ {
+ "filter": {
+ "terms": {
+ "namespace": [
+ 2
+ ]
+ }
+ },
+ "weight": "0.05"
+ },
+ {
+ "filter": {
+ "terms": {
+ "namespace": [
+ 3
+ ]
+ }
+ },
+ "weight": "0.0125"
+ }
+ ]
+ }
+ },
+ "rescore_query_weight": 1,
+ "score_mode": "multiply"
+ },
+ "window_size": 8192
+ }
+ ],
+ "size": 20,
+ "stats": [
+ "filter_only",
+ "full_text",
+ "subpageof"
+ ],
+ "stored_fields": [
+ "text.word_count"
+ ]
+ }
+}
\ No newline at end of file
diff --git a/tests/unit/fixtures/searchText/subpageof_001.query
b/tests/unit/fixtures/searchText/subpageof_001.query
new file mode 100644
index 0000000..54b8de2
--- /dev/null
+++ b/tests/unit/fixtures/searchText/subpageof_001.query
@@ -0,0 +1,3 @@
+{
+ "query": "subpageof:\"parent page\""
+}
--
To view, visit https://gerrit.wikimedia.org/r/371942
To unsubscribe, visit https://gerrit.wikimedia.org/r/settings
Gerrit-MessageType: merged
Gerrit-Change-Id: Ic1489b00b6179d60d662cd6645d54ba3428343d9
Gerrit-PatchSet: 1
Gerrit-Project: mediawiki/extensions/CirrusSearch
Gerrit-Branch: master
Gerrit-Owner: DCausse <dcau...@wikimedia.org>
Gerrit-Reviewer: Cindy-the-browser-test-bot <bernhardsone...@gmail.com>
Gerrit-Reviewer: DCausse <dcau...@wikimedia.org>
Gerrit-Reviewer: EBernhardson <ebernhard...@wikimedia.org>
Gerrit-Reviewer: Smalyshev <smalys...@wikimedia.org>
Gerrit-Reviewer: Thiemo Mättig (WMDE) <thiemo.maet...@wikimedia.de>
Gerrit-Reviewer: jenkins-bot <>
_______________________________________________
MediaWiki-commits mailing list
MediaWiki-commits@lists.wikimedia.org
https://lists.wikimedia.org/mailman/listinfo/mediawiki-commits
