EBernhardson has uploaded a new change for review. ( 
https://gerrit.wikimedia.org/r/346336 )

Change subject: Add fixtures for ukrainian analysis config
......................................................................

Add fixtures for ukrainian analysis config

It looks like ukrainian was missed when building up the analysis
chain fixtures. Add it in to ease reviewing future changes to
analysis chains.

Change-Id: I41e2519fa16f7a3fbbf21e23df306c174b18c3e5
---
M tests/unit/Maintenance/AnalysisConfigBuilderTest.php
A tests/unit/fixtures/languageAnalysis/uk.config
A tests/unit/fixtures/languageAnalysis/uk.expected
3 files changed, 267 insertions(+), 0 deletions(-)


  git pull ssh://gerrit.wikimedia.org:29418/mediawiki/extensions/CirrusSearch 
refs/changes/36/346336/1

diff --git a/tests/unit/Maintenance/AnalysisConfigBuilderTest.php 
b/tests/unit/Maintenance/AnalysisConfigBuilderTest.php
index e6f0aa9..3672cb7 100644
--- a/tests/unit/Maintenance/AnalysisConfigBuilderTest.php
+++ b/tests/unit/Maintenance/AnalysisConfigBuilderTest.php
@@ -395,6 +395,7 @@
                $plugins = [
                        'analysis-stempel', 'analysis-kuromoji',
                        'analysis-smartcn', 'elasticsearch-analysis-hebrew',
+                       'analysis-ukrainian',
                ];
                $builder = new AnalysisConfigBuilder( $langCode, $plugins, 
$config );
                if ( is_string( $expected ) ) {
diff --git a/tests/unit/fixtures/languageAnalysis/uk.config 
b/tests/unit/fixtures/languageAnalysis/uk.config
new file mode 100644
index 0000000..0967ef4
--- /dev/null
+++ b/tests/unit/fixtures/languageAnalysis/uk.config
@@ -0,0 +1 @@
+{}
diff --git a/tests/unit/fixtures/languageAnalysis/uk.expected 
b/tests/unit/fixtures/languageAnalysis/uk.expected
new file mode 100644
index 0000000..4e8f843
--- /dev/null
+++ b/tests/unit/fixtures/languageAnalysis/uk.expected
@@ -0,0 +1,265 @@
+{
+    "analyzer": {
+        "text": {
+            "type": "ukrainian",
+            "char_filter": [
+                "word_break_helper"
+            ]
+        },
+        "text_search": {
+            "type": "ukrainian",
+            "char_filter": [
+                "word_break_helper"
+            ]
+        },
+        "plain": {
+            "type": "custom",
+            "tokenizer": "standard",
+            "filter": [
+                "lowercase"
+            ],
+            "char_filter": [
+                "word_break_helper"
+            ]
+        },
+        "plain_search": {
+            "type": "custom",
+            "tokenizer": "standard",
+            "filter": [
+                "lowercase"
+            ],
+            "char_filter": [
+                "word_break_helper"
+            ]
+        },
+        "short_text": {
+            "type": "custom",
+            "tokenizer": "whitespace",
+            "filter": [
+                "lowercase",
+                "aggressive_splitting",
+                "asciifolding_preserve",
+                "dedup_asciifolding"
+            ]
+        },
+        "short_text_search": {
+            "type": "custom",
+            "tokenizer": "whitespace",
+            "filter": [
+                "lowercase",
+                "aggressive_splitting"
+            ]
+        },
+        "source_text_plain": {
+            "type": "custom",
+            "tokenizer": "standard",
+            "filter": [
+                "lowercase"
+            ],
+            "char_filter": [
+                "word_break_helper_source_text"
+            ]
+        },
+        "source_text_plain_search": {
+            "type": "custom",
+            "tokenizer": "standard",
+            "filter": [
+                "lowercase"
+            ],
+            "char_filter": [
+                "word_break_helper_source_text"
+            ]
+        },
+        "suggest": {
+            "type": "custom",
+            "tokenizer": "standard",
+            "filter": [
+                "lowercase",
+                "suggest_shingle"
+            ]
+        },
+        "suggest_search": {
+            "type": "custom",
+            "tokenizer": "standard",
+            "filter": [
+                "lowercase",
+                "suggest_shingle",
+                "limit_30"
+            ]
+        },
+        "suggest_reverse": {
+            "type": "custom",
+            "tokenizer": "standard",
+            "filter": [
+                "lowercase",
+                "suggest_shingle",
+                "reverse"
+            ]
+        },
+        "token_reverse": {
+            "type": "custom",
+            "tokenizer": "no_splitting",
+            "filter": [
+                "reverse"
+            ]
+        },
+        "near_match": {
+            "type": "custom",
+            "tokenizer": "no_splitting",
+            "filter": [
+                "lowercase"
+            ],
+            "char_filter": [
+                "near_space_flattener"
+            ]
+        },
+        "near_match_asciifolding": {
+            "type": "custom",
+            "tokenizer": "no_splitting",
+            "filter": [
+                "truncate_keyword",
+                "lowercase",
+                "asciifolding"
+            ],
+            "char_filter": [
+                "near_space_flattener"
+            ]
+        },
+        "prefix": {
+            "type": "custom",
+            "tokenizer": "prefix",
+            "filter": [
+                "lowercase"
+            ],
+            "char_filter": [
+                "near_space_flattener"
+            ]
+        },
+        "prefix_asciifolding": {
+            "type": "custom",
+            "tokenizer": "prefix",
+            "filter": [
+                "lowercase",
+                "asciifolding"
+            ],
+            "char_filter": [
+                "near_space_flattener"
+            ]
+        },
+        "word_prefix": {
+            "type": "custom",
+            "tokenizer": "standard",
+            "filter": [
+                "lowercase",
+                "prefix_ngram_filter"
+            ]
+        },
+        "keyword": {
+            "type": "custom",
+            "tokenizer": "no_splitting",
+            "filter": [
+                "truncate_keyword"
+            ]
+        },
+        "lowercase_keyword": {
+            "type": "custom",
+            "tokenizer": "no_splitting",
+            "filter": [
+                "truncate_keyword",
+                "lowercase"
+            ]
+        },
+        "trigram": {
+            "type": "custom",
+            "tokenizer": "trigram",
+            "filter": [
+                "lowercase"
+            ]
+        }
+    },
+    "filter": {
+        "suggest_shingle": {
+            "type": "shingle",
+            "min_shingle_size": 2,
+            "max_shingle_size": 3,
+            "output_unigrams": true
+        },
+        "limit_30": {
+            "type": "limit",
+            "max_token_count": 30
+        },
+        "lowercase": {
+            "type": "lowercase"
+        },
+        "aggressive_splitting": {
+            "type": "word_delimiter",
+            "stem_english_possessive": false,
+            "preserve_original": false
+        },
+        "prefix_ngram_filter": {
+            "type": "edgeNGram",
+            "max_gram": 255
+        },
+        "asciifolding": {
+            "type": "asciifolding",
+            "preserve_original": false
+        },
+        "asciifolding_preserve": {
+            "type": "asciifolding",
+            "preserve_original": true
+        },
+        "truncate_keyword": {
+            "type": "truncate",
+            "length": 5000
+        },
+        "dedup_asciifolding": {
+            "type": "unique",
+            "only_on_same_position": true
+        }
+    },
+    "tokenizer": {
+        "prefix": {
+            "type": "edgeNGram",
+            "max_gram": 255
+        },
+        "no_splitting": {
+            "type": "keyword"
+        },
+        "trigram": {
+            "type": "nGram",
+            "min_gram": 3,
+            "max_gram": 3
+        }
+    },
+    "char_filter": {
+        "near_space_flattener": {
+            "type": "mapping",
+            "mappings": [
+                "'=>\\u0020",
+                "\\u2019=>\\u0020",
+                "\\u02BC=>\\u0020",
+                "_=>\\u0020",
+                "-=>\\u0020"
+            ]
+        },
+        "word_break_helper": {
+            "type": "mapping",
+            "mappings": [
+                "_=>\\u0020",
+                ".=>\\u0020",
+                "(=>\\u0020",
+                ")=>\\u0020"
+            ]
+        },
+        "word_break_helper_source_text": {
+            "type": "mapping",
+            "mappings": [
+                "_=>\\u0020",
+                ".=>\\u0020",
+                "(=>\\u0020",
+                ")=>\\u0020",
+                ":=>\\u0020"
+            ]
+        }
+    }
+}
\ No newline at end of file

-- 
To view, visit https://gerrit.wikimedia.org/r/346336
To unsubscribe, visit https://gerrit.wikimedia.org/r/settings

Gerrit-MessageType: newchange
Gerrit-Change-Id: I41e2519fa16f7a3fbbf21e23df306c174b18c3e5
Gerrit-PatchSet: 1
Gerrit-Project: mediawiki/extensions/CirrusSearch
Gerrit-Branch: master
Gerrit-Owner: EBernhardson <[email protected]>

_______________________________________________
MediaWiki-commits mailing list
[email protected]
https://lists.wikimedia.org/mailman/listinfo/mediawiki-commits

Reply via email to