#489 language analyzer add ro de[WIP] (#536)

*  #489 language analyzer add ro de[WIP]

*  #489 language analyzer add[WIP]

*  import * to LocalDateTime

* format

src/main/resources/esclient.xml

@@ -26,6 +26,98 @@
 			<arg>"fess"</arg>
 			<arg>"ko/seunjeon.txt"</arg>
 		</postConstruct>
+		<postConstruct name="addConfigFile">
+			<arg>"fess"</arg>
+			<arg>"de/protwords.txt"</arg>
+		</postConstruct>
+		<postConstruct name="addConfigFile">
+			<arg>"fess"</arg>
+			<arg>"ar/protwords.txt"</arg>
+		</postConstruct>
+		<postConstruct name="addConfigFile">
+			<arg>"fess"</arg>
+			<arg>"ro/protwords.txt"</arg>
+		</postConstruct>
+		<postConstruct name="addConfigFile">
+			<arg>"fess"</arg>
+			<arg>"ca/protwords.txt"</arg>
+		</postConstruct>
+		<postConstruct name="addConfigFile">
+			<arg>"fess"</arg>
+			<arg>"cs/protwords.txt"</arg>
+		</postConstruct>
+		<postConstruct name="addConfigFile">
+			<arg>"fess"</arg>
+			<arg>"da/protwords.txt"</arg>
+		</postConstruct>
+		<postConstruct name="addConfigFile">
+			<arg>"fess"</arg>
+			<arg>"es/protwords.txt"</arg>
+		</postConstruct>
+		<postConstruct name="addConfigFile">
+			<arg>"fess"</arg>
+			<arg>"el/protwords.txt"</arg>
+		</postConstruct>
+		<postConstruct name="addConfigFile">
+			<arg>"fess"</arg>
+			<arg>"fa/protwords.txt"</arg>
+		</postConstruct>
+		<postConstruct name="addConfigFile">
+			<arg>"fess"</arg>
+			<arg>"fi/protwords.txt"</arg>
+		</postConstruct>
+		<postConstruct name="addConfigFile">
+			<arg>"fess"</arg>
+			<arg>"fr/protwords.txt"</arg>
+		</postConstruct>
+		<postConstruct name="addConfigFile">
+			<arg>"fess"</arg>
+			<arg>"hi/protwords.txt"</arg>
+		</postConstruct>
+		<postConstruct name="addConfigFile">
+			<arg>"fess"</arg>
+			<arg>"hu/protwords.txt"</arg>
+		</postConstruct>
+		<postConstruct name="addConfigFile">
+			<arg>"fess"</arg>
+			<arg>"id/protwords.txt"</arg>
+		</postConstruct>
+		<postConstruct name="addConfigFile">
+			<arg>"fess"</arg>
+			<arg>"it/protwords.txt"</arg>
+		</postConstruct>
+		<postConstruct name="addConfigFile">
+			<arg>"fess"</arg>
+			<arg>"lt/protwords.txt"</arg>
+		</postConstruct>
+		<postConstruct name="addConfigFile">
+			<arg>"fess"</arg>
+			<arg>"lv/protwords.txt"</arg>
+		</postConstruct>
+		<postConstruct name="addConfigFile">
+			<arg>"fess"</arg>
+			<arg>"nl/protwords.txt"</arg>
+		</postConstruct>
+		<postConstruct name="addConfigFile">
+			<arg>"fess"</arg>
+			<arg>"no/protwords.txt"</arg>
+		</postConstruct>
+		<postConstruct name="addConfigFile">
+			<arg>"fess"</arg>
+			<arg>"pt/protwords.txt"</arg>
+		</postConstruct>
+		<postConstruct name="addConfigFile">
+			<arg>"fess"</arg>
+			<arg>"ru/protwords.txt"</arg>
+		</postConstruct>
+		<postConstruct name="addConfigFile">
+			<arg>"fess"</arg>
+			<arg>"sv/protwords.txt"</arg>
+		</postConstruct>
+		<postConstruct name="addConfigFile">
+			<arg>"fess"</arg>
+			<arg>"tr/protwords.txt"</arg>
+		</postConstruct>
 		<!-- fess index -->
 		<postConstruct name="addIndexConfig">
 			<arg>"fess/doc"</arg>

src/main/resources/fess_indices/fess.json

@@ -11,6 +11,10 @@
           "type": "mapping",
           "mappings_path": "${fess.dictionary.path}ja/mapping.txt"
         },
+        "zero_width_spaces": {
+            "type":       "mapping",
+            "mappings": [ "\\u200C=> "]
+        },
         "removeall_filter": {
           "type": "pattern_replace",
           "pattern":"(.*)",
@@ -84,6 +88,317 @@
             "連体詞"
           ]
         },
+        "german_stop": {
+          "type":       "stop",
+          "stopwords":  "_german_"
+        },
+        "german_keywords": {
+          "type":       "keyword_marker",
+          "keywords_path": "${fess.dictionary.path}de/protwords.txt"
+        },
+        "german_stemmer": {
+          "type":       "stemmer",
+          "language":   "light_german"
+        },
+        "french_elision": {
+          "type":         "elision",
+          "articles_case": true,
+            "articles": [
+              "l", "m", "t", "qu", "n", "s",
+              "j", "d", "c", "jusqu", "quoiqu",
+              "lorsqu", "puisqu"
+            ]
+        },
+        "french_stop": {
+          "type":       "stop",
+          "stopwords":  "_french_"
+        },
+        "french_keywords": {
+          "type":       "keyword_marker",
+          "keywords_path": "${fess.dictionary.path}fr/protwords.txt"
+        },
+        "french_stemmer": {
+          "type":       "stemmer",
+          "language":   "light_french"
+        },
+        "italian_elision": {
+        "type":         "elision",
+            "articles": [
+                "c", "l", "all", "dall", "dell",
+                "nell", "sull", "coll", "pell",
+                "gl", "agl", "dagl", "degl", "negl",
+                "sugl", "un", "m", "t", "s", "v", "d"
+            ]
+        },
+        "italian_stop": {
+          "type":       "stop",
+          "stopwords":  "_italian_"
+        },
+        "italian_keywords": {
+          "type":       "keyword_marker",
+          "keywords_path": "${fess.dictionary.path}it/protwords.txt"
+        },
+        "italian_stemmer": {
+          "type":       "stemmer",
+          "language":   "light_italian"
+        },
+        "arabic_stop": {
+          "type":       "stop",
+          "stopwords":  "_arabic_"
+        },
+        "arabic_keywords": {
+          "type":       "keyword_marker",
+          "keywords_path": "${fess.dictionary.path}ar/protwords.txt"
+        },
+        "arabic_stemmer": {
+          "type":       "stemmer",
+          "language":   "arabic"
+        },
+        "romanian_stop": {
+          "type":       "stop",
+          "stopwords":  "_romanian_"
+        },
+        "romanian_keywords": {
+          "type":       "keyword_marker",
+          "keywords_path": "${fess.dictionary.path}ro/protwords.txt"
+        },
+        "romanian_stemmer": {
+          "type":       "stemmer",
+          "language":   "romanian"
+        },
+        "catalan_elision": {
+        "type":         "elision",
+            "articles": [ "d", "l", "m", "n", "s", "t"]
+        },
+        "catalan_stop": {
+          "type":       "stop",
+          "stopwords":  "_catalan_"
+        },
+        "catalan_keywords": {
+          "type":       "keyword_marker",
+          "keywords_path": "${fess.dictionary.path}ca/protwords.txt"
+        },
+        "catalan_stemmer": {
+          "type":       "stemmer",
+          "language":   "catalan"
+        },
+        "czech_stop": {
+          "type":       "stop",
+          "stopwords":  "_czech_"
+        },
+        "czech_keywords": {
+          "type":       "keyword_marker",
+          "keywords_path": "${fess.dictionary.path}cs/protwords.txt"
+        },
+        "czech_stemmer": {
+          "type":       "stemmer",
+          "language":   "czech"
+        },
+        "danish_stop": {
+          "type":       "stop",
+          "stopwords":  "_danish_"
+        },
+        "danish_keywords": {
+          "type":       "keyword_marker",
+          "keywords_path": "${fess.dictionary.path}da/protwords.txt"
+        },
+        "danish_stemmer": {
+          "type":       "stemmer",
+          "language":   "danish"
+        },
+        "spanish_stop": {
+          "type":       "stop",
+          "stopwords":  "_spanish_"
+        },
+        "spanish_keywords": {
+          "type":       "keyword_marker",
+          "keywords_path": "${fess.dictionary.path}es/protwords.txt"
+        },
+        "spanish_stemmer": {
+          "type":       "stemmer",
+          "language":   "light_spanish"
+        },
+        "greek_stop": {
+          "type":       "stop",
+          "stopwords":  "_greek_"
+        },
+        "greek_lowercase": {
+          "type":       "lowercase",
+          "language":   "greek"
+        },
+        "greek_keywords": {
+          "type":       "keyword_marker",
+          "keywords_path": "${fess.dictionary.path}el/protwords.txt"
+        },
+        "greek_stemmer": {
+          "type":       "stemmer",
+          "language":   "greek"
+        },
+        "persian_stop": {
+          "type":       "stop",
+          "stopwords":  "_persian_"
+        },
+        "finnish_stop": {
+          "type":       "stop",
+          "stopwords":  "_finnish_"
+        },
+        "finnish_keywords": {
+          "type":       "keyword_marker",
+          "keywords_path": "${fess.dictionary.path}fi/protwords.txt"
+        },
+        "finnish_stemmer": {
+          "type":       "stemmer",
+          "language":   "finnish"
+        },
+        "hindi_stop": {
+          "type":       "stop",
+          "stopwords":  "_hindi_"
+        },
+        "hindi_keywords": {
+          "type":       "keyword_marker",
+          "keywords_path": "${fess.dictionary.path}hi/protwords.txt"
+        },
+        "hindi_stemmer": {
+          "type":       "stemmer",
+          "language":   "hindi"
+        },
+        "hungarian_stop": {
+          "type":       "stop",
+          "stopwords":  "_hungarian_"
+        },
+        "hungarian_keywords": {
+          "type":       "keyword_marker",
+          "keywords_path": "${fess.dictionary.path}hu/protwords.txt"
+        },
+        "hungarian_stemmer": {
+          "type":       "stemmer",
+          "language":   "hungarian"
+        },
+        "indonesian_stop": {
+          "type":       "stop",
+          "stopwords":  "_indonesian_"
+        },
+        "indonesian_keywords": {
+          "type":       "keyword_marker",
+          "keywords_path": "${fess.dictionary.path}id/protwords.txt"
+        },
+        "indonesian_stemmer": {
+          "type":       "stemmer",
+          "language":   "indonesian"
+        },
+        "lithuanian_stop": {
+          "type":       "stop",
+          "stopwords":  "_lithuanian_"
+        },
+        "lithuanian_keywords": {
+          "type":       "keyword_marker",
+          "keywords_path": "${fess.dictionary.path}lt/protwords.txt"
+        },
+        "lithuanian_stemmer": {
+          "type":       "stemmer",
+          "language":   "lithuanian"
+        },
+        "latvian_stop": {
+          "type":       "stop",
+          "stopwords":  "_latvian_"
+        },
+        "latvian_keywords": {
+          "type":       "keyword_marker",
+          "keywords_path": "${fess.dictionary.path}lv/protwords.txt"
+        },
+        "latvian_stemmer": {
+          "type":       "stemmer",
+          "language":   "latvian"
+        },
+        "dutch_stop": {
+          "type":       "stop",
+          "stopwords":  "_dutch_"
+        },
+        "dutch_keywords": {
+          "type":       "keyword_marker",
+          "keywords_path": "${fess.dictionary.path}nl/protwords.txt"
+        },
+        "dutch_stemmer": {
+          "type":       "stemmer",
+          "language":   "dutch"
+        },
+        "dutch_override": {
+          "type":       "stemmer_override",
+          "rules": [
+            "fiets=>fiets",
+            "bromfiets=>bromfiets",
+            "ei=>eier",
+            "kind=>kinder"
+          ]
+        },
+        "norwegian_stop": {
+          "type":       "stop",
+          "stopwords":  "_norwegian_"
+        },
+        "norwegian_keywords": {
+          "type":       "keyword_marker",
+          "keywords_path": "${fess.dictionary.path}no/protwords.txt"
+        },
+        "norwegian_stemmer": {
+          "type":       "stemmer",
+          "language":   "norwegian"
+        },
+        "portuguese_stop": {
+          "type":       "stop",
+          "stopwords":  "_portuguese_"
+        },
+        "portuguese_keywords": {
+          "type":       "keyword_marker",
+          "keywords_path": "${fess.dictionary.path}pt/protwords.txt"
+        },
+        "portuguese_stemmer": {
+          "type":       "stemmer",
+          "language":   "light_portuguese"
+        },
+        "russian_stop": {
+          "type":       "stop",
+          "stopwords":  "_russian_"
+        },
+        "russian_keywords": {
+          "type":       "keyword_marker",
+          "keywords_path": "${fess.dictionary.path}ru/protwords.txt"
+        },
+        "russian_stemmer": {
+          "type":       "stemmer",
+          "language":   "russian"
+        },
+        "swedish_stop": {
+          "type":       "stop",
+          "stopwords":  "_swedish_"
+        },
+        "swedish_keywords": {
+          "type":       "keyword_marker",
+          "keywords_path": "${fess.dictionary.path}sv/protwords.txt"
+        },
+        "swedish_stemmer": {
+          "type":       "stemmer",
+          "language":   "swedish"
+        },
+        "thai_stop": {
+          "type":       "stop",
+          "stopwords":  "_thai_"
+        },
+        "turkish_stop": {
+          "type":       "stop",
+          "stopwords":  "_turkish_"
+        },
+        "turkish_lowercase": {
+          "type":       "lowercase",
+          "language":   "turkish"
+        },
+        "turkish_keywords": {
+          "type":       "keyword_marker",
+          "keywords_path": "${fess.dictionary.path}tr/protwords.txt"
+        },
+        "turkish_stemmer": {
+          "type":       "stemmer",
+          "language":   "turkish"
+        },
         "truncate10_filter" : {
           "type" : "truncate",
           "length" : 10
@@ -153,6 +468,276 @@
           "type": "custom",
           "tokenizer":"seunjeon_default_tokenizer"
         },
+        "german_analyzer": {
+          "type": "custom",
+          "tokenizer": "standard",
+          "filter": [
+            "truncate20_filter",
+            "lowercase",
+            "german_stop",
+            "german_normalization",
+            "german_stemmer"
+          ]
+        },
+        "french_analyzer": {
+          "type": "custom",
+          "tokenizer": "standard",
+          "filter": [
+            "truncate20_filter",
+            "french_elision",
+            "lowercase",
+            "french_stop",
+            "french_keywords",
+            "french_stemmer"
+          ]
+        },
+        "italian_analyzer": {
+          "type": "custom",
+          "tokenizer":  "standard",
+          "filter": [
+            "truncate20_filter",
+            "italian_elision",
+            "lowercase",
+            "italian_stop",
+            "italian_keywords",
+            "italian_stemmer"
+          ]
+        },
+        "arabic_analyzer": {
+          "type": "custom",
+          "tokenizer": "standard",
+          "filter": [
+            "truncate20_filter",
+            "lowercase",
+            "arabic_stop",
+            "arabic_normalization",
+            "arabic_keywords",
+            "arabic_stemmer"
+          ]
+        },
+        "romanian_analyzer": {
+          "type": "custom",
+          "tokenizer": "standard",
+          "filter": [
+            "truncate20_filter",
+            "lowercase",
+            "romanian_stop",
+            "romanian_stemmer"
+          ]
+        },
+        "catalan_analyzer": {
+          "type": "custom",
+          "tokenizer": "standard",
+          "filter": [
+            "truncate20_filter",
+            "catalan_elision",
+            "lowercase",
+            "catalan_stop",
+            "catalan_keywords",
+            "catalan_stemmer"
+          ]
+        },
+        "czech_analyzer": {
+          "type": "custom",
+          "tokenizer": "standard",
+          "filter": [
+            "truncate20_filter",
+            "lowercase",
+            "czech_stop",
+            "czech_keywords",
+            "czech_stemmer"
+          ]
+        },
+        "danish_analyzer": {
+          "type": "custom",
+          "tokenizer": "standard",
+          "filter": [
+            "truncate20_filter",
+            "lowercase",
+            "danish_stop",
+            "danish_keywords",
+            "danish_stemmer"
+          ]
+        },
+        "spanish_analyzer": {
+          "type": "custom",
+          "tokenizer": "standard",
+          "filter": [
+            "truncate20_filter",
+            "lowercase",
+            "spanish_stop",
+            "spanish_keywords",
+            "spanish_stemmer"
+          ]
+        },
+        "greek_analyzer": {
+          "type": "custom",
+          "tokenizer": "standard",
+          "filter": [
+            "truncate20_filter",
+            "greek_lowercase",
+            "greek_stop",
+            "greek_keywords",
+            "greek_stemmer"
+          ]
+        },
+        "persian_analyzer": {
+          "type": "custom",
+          "tokenizer": "standard",
+          "char_filter": [ "zero_width_spaces" ],
+          "filter": [
+            "truncate20_filter",
+            "lowercase",
+            "arabic_normalization",
+            "persian_normalization",
+            "persian_stop"
+          ]
+        },
+        "finnish_analyzer": {
+          "type": "custom",
+          "tokenizer":  "standard",
+          "filter": [
+            "truncate20_filter",
+            "lowercase",
+            "finnish_stop",
+            "finnish_keywords",
+            "finnish_stemmer"
+          ]
+        },
+        "hindi_analyzer": {
+          "type": "custom",
+          "tokenizer": "standard",
+          "filter": [
+            "truncate20_filter",
+            "lowercase",
+            "indic_normalization",
+            "hindi_normalization",
+            "hindi_stop",
+            "hindi_keywords",
+            "hindi_stemmer"
+          ]
+        },
+        "hungarian_analyzer": {
+          "type": "custom",
+          "tokenizer":  "standard",
+          "filter": [
+            "truncate20_filter",
+            "lowercase",
+            "hungarian_stop",
+            "hungarian_keywords",
+            "hungarian_stemmer"
+          ]
+        },
+        "indonesian_analyzer": {
+          "type": "custom",
+          "tokenizer":  "standard",
+          "filter": [
+            "truncate20_filter",
+            "lowercase",
+            "indonesian_stop",
+            "indonesian_keywords",
+            "indonesian_stemmer"
+          ]
+        },
+        "lithuanian_analyzer": {
+          "type": "custom",
+          "tokenizer":  "standard",
+          "filter": [
+            "truncate20_filter",
+            "lowercase",
+            "lithuanian_stop",
+            "lithuanian_keywords",
+            "lithuanian_stemmer"
+          ]
+        },
+        "latvian_analyzer": {
+          "type": "custom",
+          "tokenizer": "standard",
+          "filter": [
+            "truncate20_filter",
+            "lowercase",
+            "latvian_stop",
+            "latvian_keywords",
+            "latvian_stemmer"
+          ]
+        },
+        "dutch_analyzer": {
+          "type": "custom",
+          "tokenizer": "standard",
+          "filter": [
+            "truncate20_filter",
+            "lowercase",
+            "dutch_stop",
+            "dutch_keywords",
+            "dutch_override",
+            "dutch_stemmer"
+          ]
+        },
+        "norwegian_analyzer": {
+          "type": "custom",
+          "tokenizer": "standard",
+          "filter": [
+            "truncate20_filter",
+            "lowercase",
+            "norwegian_stop",
+            "norwegian_keywords",
+            "norwegian_stemmer"
+          ]
+        },
+        "portuguese_analyzer": {
+          "type": "custom",
+          "tokenizer": "standard",
+          "filter": [
+            "truncate20_filter",
+            "lowercase",
+            "portuguese_stop",
+            "portuguese_keywords",
+            "portuguese_stemmer"
+          ]
+        },
+        "russian_analyzer": {
+          "type": "custom",
+          "tokenizer":  "standard",
+          "filter": [
+            "truncate20_filter",
+            "lowercase",
+            "russian_stop",
+            "russian_keywords",
+            "russian_stemmer"
+          ]
+        },
+        "swedish_analyzer": {
+          "type": "custom",
+          "tokenizer": "standard",
+          "filter": [
+            "truncate20_filter",
+            "lowercase",
+            "swedish_stop",
+            "swedish_keywords",
+            "swedish_stemmer"
+          ]
+        },
+        "thai_analyzer": {
+          "type": "custom",
+          "tokenizer": "thai",
+          "filter": [
+            "truncate20_filter",
+            "lowercase",
+            "thai_stop"
+          ]
+        },
+        "turkish_analyzer": {
+          "type": "custom",
+          "tokenizer": "standard",
+          "filter": [
+            "truncate20_filter",
+            "apostrophe",
+            "turkish_lowercase",
+            "turkish_stop",
+            "turkish_keywords",
+            "turkish_stemmer"
+          ]
+        },
         "empty_analyzer": {
           "type": "custom",
           "tokenizer": "standard",

src/main/resources/fess_indices/fess/ar/protwords.txt

@@ -0,0 +1,3 @@
+مرحباا
+عالم
+بحث

src/main/resources/fess_indices/fess/ca/protwords.txt

@@ -0,0 +1,3 @@
+Hola
+món
+recerca

src/main/resources/fess_indices/fess/cs/protwords.txt

@@ -0,0 +1,3 @@
+Haló
+svět
+vyhledávání

src/main/resources/fess_indices/fess/da/protwords.txt

@@ -0,0 +1,3 @@
+Hej
+verden
+Søg

src/main/resources/fess_indices/fess/de/protwords.txt

@@ -0,0 +1,3 @@
+Hallo
+Welt
+Suche

src/main/resources/fess_indices/fess/doc.json

@@ -12,7 +12,7 @@
           "match": "*_ar",
           "mapping": {
             "type": "string",
-            "analyzer": "empty_analyzer"
+            "analyzer": "arabic_analyzer"
           }
         }
       },
@@ -21,7 +21,7 @@
           "match": "*_bg",
           "mapping": {
             "type": "string",
-            "analyzer": "empty_analyzer"
+            "analyzer": "bulgarian_analyzer"
           }
         }
       },
@@ -39,7 +39,7 @@
           "match": "*_ca",
           "mapping": {
             "type": "string",
-            "analyzer": "empty_analyzer"
+            "analyzer": "catalan_analyzer"
           }
         }
       },
@@ -48,7 +48,7 @@
           "match": "*_cs",
           "mapping": {
             "type": "string",
-            "analyzer": "empty_analyzer"
+            "analyzer": "czech_analyzer"
           }
         }
       },
@@ -57,7 +57,7 @@
           "match": "*_da",
           "mapping": {
             "type": "string",
-            "analyzer": "empty_analyzer"
+            "analyzer": "danish_analyzer"
           }
         }
       },
@@ -66,7 +66,7 @@
           "match": "*_de",
           "mapping": {
             "type": "string",
-            "analyzer": "empty_analyzer"
+            "analyzer": "german_analyzer"
           }
         }
       },
@@ -75,7 +75,7 @@
           "match": "*_el",
           "mapping": {
             "type": "string",
-            "analyzer": "empty_analyzer"
+            "analyzer": "greek_analyzer"
           }
         }
       },
@@ -93,7 +93,7 @@
           "match": "*_es",
           "mapping": {
             "type": "string",
-            "analyzer": "empty_analyzer"
+            "analyzer": "spanish_analyzer"
           }
         }
       },
@@ -111,7 +111,7 @@
           "match": "*_fa",
           "mapping": {
             "type": "string",
-            "analyzer": "empty_analyzer"
+            "analyzer": "persian_analyzer"
           }
         }
       },
@@ -120,7 +120,7 @@
           "match": "*_fi",
           "mapping": {
             "type": "string",
-            "analyzer": "empty_analyzer"
+            "analyzer": "finnish_analyzer"
           }
         }
       },
@@ -129,7 +129,7 @@
           "match": "*_fr",
           "mapping": {
             "type": "string",
-            "analyzer": "empty_analyzer"
+            "analyzer": "french_analyzer"
           }
         }
       },
@@ -174,7 +174,7 @@
           "match": "*_hu",
           "mapping": {
             "type": "string",
-            "analyzer": "empty_analyzer"
+            "analyzer": "hungarian_analyzer"
           }
         }
       },
@@ -183,7 +183,7 @@
           "match": "*_id",
           "mapping": {
             "type": "string",
-            "analyzer": "empty_analyzer"
+            "analyzer": "indonesian_analyzer"
           }
         }
       },
@@ -192,7 +192,7 @@
           "match": "*_it",
           "mapping": {
             "type": "string",
-            "analyzer": "empty_analyzer"
+            "analyzer": "italian_analyzer"
           }
         }
       },
@@ -219,7 +219,7 @@
           "match": "*_lt",
           "mapping": {
             "type": "string",
-            "analyzer": "empty_analyzer"
+            "analyzer": "lithuanian_analyzer"
           }
         }
       },
@@ -228,7 +228,7 @@
           "match": "*_lv",
           "mapping": {
             "type": "string",
-            "analyzer": "empty_analyzer"
+            "analyzer": "latvian_analyzer"
           }
         }
       },
@@ -255,7 +255,7 @@
           "match": "*_nl",
           "mapping": {
             "type": "string",
-            "analyzer": "empty_analyzer"
+            "analyzer": "dutch_analyzer"
           }
         }
       },
@@ -264,7 +264,7 @@
           "match": "*_no",
           "mapping": {
             "type": "string",
-            "analyzer": "empty_analyzer"
+            "analyzer": "norwegian_analyzer"
           }
         }
       },
@@ -291,7 +291,7 @@
           "match": "*_pt",
           "mapping": {
             "type": "string",
-            "analyzer": "empty_analyzer"
+            "analyzer": "portuguese_analyzer"
           }
         }
       },
@@ -300,7 +300,7 @@
           "match": "*_ro",
           "mapping": {
             "type": "string",
-            "analyzer": "empty_analyzer"
+            "analyzer": "romanian_analyzer"
           }
         }
       },
@@ -309,7 +309,7 @@
           "match": "*_ru",
           "mapping": {
             "type": "string",
-            "analyzer": "empty_analyzer"
+            "analyzer": "russian_analyzer"
           }
         }
       },
@@ -336,7 +336,7 @@
           "match": "*_sv",
           "mapping": {
             "type": "string",
-            "analyzer": "empty_analyzer"
+            "analyzer": "swedish_analyzer"
           }
         }
       },
@@ -363,7 +363,7 @@
           "match": "*_th",
           "mapping": {
             "type": "string",
-            "analyzer": "empty_analyzer"
+            "analyzer": "thai_analyzer"
           }
         }
       },
@@ -381,7 +381,7 @@
           "match": "*_tr",
           "mapping": {
             "type": "string",
-            "analyzer": "empty_analyzer"
+            "analyzer": "turkish_analyzer"
           }
         }
       },

src/main/resources/fess_indices/fess/el/protwords.txt

@@ -0,0 +1,3 @@
+Γεια σας
+κόσμος
+έρευνα

src/main/resources/fess_indices/fess/es/protwords.txt

@@ -0,0 +1,3 @@
+¡Hola
+mundo
+búsqueda

src/main/resources/fess_indices/fess/fa/protwords.txt

@@ -0,0 +1,3 @@
+سلام
+جهان
+جستجو

src/main/resources/fess_indices/fess/fi/protwords.txt

@@ -0,0 +1,3 @@
+Hei
+maailma
+haku

src/main/resources/fess_indices/fess/fr/protwords.txt

@@ -0,0 +1,3 @@
+Bonjour
+monde
+recherche

src/main/resources/fess_indices/fess/hi/protwords.txt

@@ -0,0 +1,3 @@
+नमस्ते
+दुनिया
+खोज

src/main/resources/fess_indices/fess/hu/protwords.txt

@@ -0,0 +1,3 @@
+Helló
+világ
+keresés

src/main/resources/fess_indices/fess/id/protwords.txt

@@ -0,0 +1,3 @@
+halo
+dunia
+pencarian

src/main/resources/fess_indices/fess/it/protwords.txt

@@ -0,0 +1,3 @@
+Ciao
+mondo
+ricerca

src/main/resources/fess_indices/fess/lt/protwords.txt

@@ -0,0 +1,3 @@
+Sveiki
+pasaulis
+paieška

src/main/resources/fess_indices/fess/lv/protwords.txt

@@ -0,0 +1,3 @@
+sveiki
+pasaule
+meklēšana

src/main/resources/fess_indices/fess/nl/protwords.txt

@@ -0,0 +1,3 @@
+hallo
+wereld
+zoeken

src/main/resources/fess_indices/fess/no/protwords.txt

@@ -0,0 +1,3 @@
+Hallo
+verden
+Søk

src/main/resources/fess_indices/fess/pt/protwords.txt

@@ -0,0 +1,3 @@
+Olá
+mundo
+pesquisa

src/main/resources/fess_indices/fess/ro/protwords.txt

@@ -0,0 +1,3 @@
+Alo
+lume
+căutare

src/main/resources/fess_indices/fess/ru/protwords.txt

@@ -0,0 +1,3 @@
+привет
+мир
+поиск

src/main/resources/fess_indices/fess/sv/protwords.txt

@@ -0,0 +1,3 @@
+Hallå
+material
+sök

src/main/resources/fess_indices/fess/th/protwords.txt

@@ -0,0 +1,3 @@
+สวัสดี
+โลก
+ค้นหา

src/main/resources/fess_indices/fess/tr/protwords.txt

@@ -0,0 +1,3 @@
+Merhaba
+Dünya
+arama