Merge pull request #20704 from johtani/remove_request_params_in_analyze_api

Removing request parameters in _analyze API

core/src/main/java/org/elasticsearch/rest/action/admin/indices/RestAnalyzeAction.java

@@ -22,13 +22,11 @@ import org.elasticsearch.action.admin.indices.analyze.AnalyzeRequest;
 import org.elasticsearch.client.node.NodeClient;
 import org.elasticsearch.common.ParseField;
 import org.elasticsearch.common.ParseFieldMatcher;
-import org.elasticsearch.common.Strings;
 import org.elasticsearch.common.bytes.BytesReference;
 import org.elasticsearch.common.inject.Inject;
 import org.elasticsearch.common.settings.Settings;
 import org.elasticsearch.common.xcontent.XContentHelper;
 import org.elasticsearch.common.xcontent.XContentParser;
-import org.elasticsearch.common.xcontent.XContentType;
 import org.elasticsearch.rest.BaseRestHandler;
 import org.elasticsearch.rest.RestController;
 import org.elasticsearch.rest.RestRequest;
@@ -67,42 +65,14 @@ public class RestAnalyzeAction extends BaseRestHandler {
     @Override
     public RestChannelConsumer prepareRequest(final RestRequest request, final NodeClient client) throws IOException {
 
-        String[] texts = request.paramAsStringArrayOrEmptyIfAll("text");
-
         AnalyzeRequest analyzeRequest = new AnalyzeRequest(request.param("index"));
-        analyzeRequest.text(texts);
-        analyzeRequest.analyzer(request.param("analyzer"));
-        analyzeRequest.field(request.param("field"));
-        final String tokenizer = request.param("tokenizer");
-        if (tokenizer != null) {
-            analyzeRequest.tokenizer(tokenizer);
-        }
-        for (String filter : request.paramAsStringArray("filter", Strings.EMPTY_ARRAY)) {
-            analyzeRequest.addTokenFilter(filter);
-        }
-        for (String charFilter : request.paramAsStringArray("char_filter", Strings.EMPTY_ARRAY)) {
-            analyzeRequest.addTokenFilter(charFilter);
-        }
-        analyzeRequest.explain(request.paramAsBoolean("explain", false));
-        analyzeRequest.attributes(request.paramAsStringArray("attributes", analyzeRequest.attributes()));
 
-        if (RestActions.hasBodyContent(request)) {
+        buildFromContent(RestActions.getRestContent(request), analyzeRequest, parseFieldMatcher);
-            XContentType type = RestActions.guessBodyContentType(request);
-            if (type == null) {
-                if (texts == null || texts.length == 0) {
-                    texts = new String[]{ RestActions.getRestContent(request).utf8ToString() };
-                    analyzeRequest.text(texts);
-                }
-            } else {
-                // NOTE: if rest request with xcontent body has request parameters, the parameters does not override xcontent values
-                buildFromContent(RestActions.getRestContent(request), analyzeRequest, parseFieldMatcher);
-            }
-        }
 
         return channel -> client.admin().indices().analyze(analyzeRequest, new RestToXContentListener<>(channel));
     }
 
-    public static void buildFromContent(BytesReference content, AnalyzeRequest analyzeRequest, ParseFieldMatcher parseFieldMatcher) {
+    static void buildFromContent(BytesReference content, AnalyzeRequest analyzeRequest, ParseFieldMatcher parseFieldMatcher) {
         try (XContentParser parser = XContentHelper.createParser(content)) {
             if (parser.nextToken() != XContentParser.Token.START_OBJECT) {
                 throw new IllegalArgumentException("Malformed content, must start with an object");

core/src/test/java/org/elasticsearch/rest/action/admin/indices/RestAnalyzeActionTests.java

@@ -118,7 +118,7 @@ public class RestAnalyzeActionTests extends ESTestCase {
         assertThat(e.getMessage(), startsWith("explain must be either 'true' or 'false'"));
     }
 
-    public void testDeprecatedParamException() throws Exception {
+    public void testDeprecatedParamIn2xException() throws Exception {
         IllegalArgumentException e = expectThrows(IllegalArgumentException.class,
             () -> RestAnalyzeAction.buildFromContent(
                 XContentFactory.jsonBuilder()
@@ -165,5 +165,4 @@ public class RestAnalyzeActionTests extends ESTestCase {
                 , new AnalyzeRequest("for test"), new ParseFieldMatcher(Settings.EMPTY)));
         assertThat(e.getMessage(), startsWith("Unknown parameter [token_filter]"));
     }
-
 }

docs/plugins/analysis-icu.asciidoc

@@ -164,7 +164,11 @@ PUT icu_sample
     }
 }
 
-POST icu_sample/_analyze?analyzer=my_analyzer&text=Elasticsearch. Wow!
+GET icu_sample/_analyze
+{
+  "analyzer": "my_analyzer",
+  "text": "Elasticsearch. Wow!"
+}
 --------------------------------------------------
 // CONSOLE
 
@@ -480,18 +484,21 @@ PUT icu_sample
   }
 }
 
-GET icu_sample/_analyze?analyzer=latin
+GET icu_sample/_analyze
 {
+  "analyzer": "latin",
   "text": "你好" <2>
 }
 
-GET icu_sample/_analyze?analyzer=latin
+GET icu_sample/_analyze
 {
+  "analyzer": "latin",
   "text": "здравствуйте" <3>
 }
 
-GET icu_sample/_analyze?analyzer=latin
+GET icu_sample/_analyze
 {
+  "analyzer": "latin",
   "text": "こんにちは" <4>
 }
 

docs/plugins/analysis-kuromoji.asciidoc

@@ -175,7 +175,11 @@ PUT kuromoji_sample
   }
 }
 
-POST kuromoji_sample/_analyze?analyzer=my_analyzer&text=東京スカイツリー
+GET kuromoji_sample/_analyze
+{
+  "analyzer": "my_analyzer",
+  "text": "東京スカイツリー"
+}
 --------------------------------------------------
 // CONSOLE
 
@@ -228,7 +232,11 @@ PUT kuromoji_sample
   }
 }
 
-POST kuromoji_sample/_analyze?analyzer=my_analyzer&text=飲み
+GET kuromoji_sample/_analyze
+{
+  "analyzer": "my_analyzer",
+  "text": "飲み"
+}
 --------------------------------------------------
 // CONSOLE
 
@@ -290,7 +298,11 @@ PUT kuromoji_sample
   }
 }
 
-POST kuromoji_sample/_analyze?analyzer=my_analyzer&text=寿司がおいしいね
+GET kuromoji_sample/_analyze
+{
+  "analyzer": "my_analyzer",
+  "text": "寿司がおいしいね"
+}
 --------------------------------------------------
 // CONSOLE
 
@@ -363,9 +375,17 @@ PUT kuromoji_sample
     }
 }
 
-POST kuromoji_sample/_analyze?analyzer=katakana_analyzer&text=寿司 <1>
+GET kuromoji_sample/_analyze
+{
+  "analyzer": "katakana_analyzer",
+  "text": "寿司" <1>
+}
 
-POST kuromoji_sample/_analyze?analyzer=romaji_analyzer&text=寿司 <2>
+GET kuromoji_sample/_analyze
+{
+  "analyzer": "romaji_analyzer",
+  "text": "寿司" <2>
+}
 --------------------------------------------------
 // CONSOLE
 
@@ -413,9 +433,17 @@ PUT kuromoji_sample
   }
 }
 
-POST kuromoji_sample/_analyze?analyzer=my_analyzer&text=コピー <1>
+GET kuromoji_sample/_analyze
+{
+  "analyzer": "my_analyzer",
+  "text": "コピー" <1>
+}
 
-POST kuromoji_sample/_analyze?analyzer=my_analyzer&text=サーバー <2>
+GET kuromoji_sample/_analyze
+{
+  "analyzer": "my_analyzer",
+  "text": "サーバー" <2>
+}
 --------------------------------------------------
 // CONSOLE
 
@@ -424,7 +452,7 @@ POST kuromoji_sample/_analyze?analyzer=my_analyzer&text=サーバー <2>
 
 
 [[analysis-kuromoji-stop]]
-===== `ja_stop` token filter
+==== `ja_stop` token filter
 
 The `ja_stop` token filter filters out Japanese stopwords (`_japanese_`), and
 any other custom stopwords specified by the user. This filter only supports
@@ -461,7 +489,11 @@ PUT kuromoji_sample
   }
 }
 
-POST kuromoji_sample/_analyze?analyzer=analyzer_with_ja_stop&text=ストップは消える
+GET kuromoji_sample/_analyze
+{
+  "analyzer": "analyzer_with_ja_stop",
+  "text": "ストップは消える"
+}
 --------------------------------------------------
 // CONSOLE
 
@@ -482,7 +514,7 @@ The above request returns:
 // TESTRESPONSE
 
 [[analysis-kuromoji-number]]
-===== `kuromoji_number` token filter
+==== `kuromoji_number` token filter
 
 The `kuromoji_number` token filter normalizes Japanese numbers (kansūji)
 to regular Arabic decimal numbers in half-width characters. For example:
@@ -507,7 +539,11 @@ PUT kuromoji_sample
   }
 }
 
-POST kuromoji_sample/_analyze?analyzer=my_analyzer&text=一〇〇〇
+GET kuromoji_sample/_analyze
+{
+  "analyzer": "my_analyzer",
+  "text": "一〇〇〇"
+}
 --------------------------------------------------
 // CONSOLE
 

docs/plugins/analysis-phonetic.asciidoc

@@ -82,7 +82,11 @@ PUT phonetic_sample
   }
 }
 
-POST phonetic_sample/_analyze?analyzer=my_analyzer&text=Joe Bloggs <1>
+GET phonetic_sample/_analyze
+{
+  "analyzer": "my_analyzer",
+  "text": "Joe Bloggs" <1>
+}
 --------------------------------------------------
 // CONSOLE
 

docs/reference/indices/analyze.asciidoc

@@ -100,21 +100,6 @@ curl -XGET 'localhost:9200/test/_analyze' -d '
 Will cause the analysis to happen based on the analyzer configured in the
 mapping for `obj1.field1` (and if not, the default index analyzer).
 
-All parameters can also supplied as request parameters. For example:
-
-[source,js]
---------------------------------------------------
-curl -XGET 'localhost:9200/_analyze?tokenizer=keyword&filter=lowercase&text=this+is+a+test'
---------------------------------------------------
-
-For backwards compatibility, we also accept the text parameter as the body of the request,
-provided it doesn't start with `{` :
-
-[source,js]
---------------------------------------------------
-curl -XGET 'localhost:9200/_analyze?tokenizer=keyword&filter=lowercase&char_filter=html_strip' -d 'this is a <b>test</b>'
---------------------------------------------------
-
 === Explain Analyze
 
 If you want to get more advanced details, set `explain` to `true` (defaults to `false`). It will output all token attributes for each token.

docs/reference/mapping/params/analyzer.asciidoc

@@ -60,13 +60,15 @@ PUT /my_index
   }
 }
 
-GET my_index/_analyze?field=text <3>
+GET my_index/_analyze <3>
 {
+  "field": "text",
   "text": "The quick Brown Foxes."
 }
 
-GET my_index/_analyze?field=text.english <4>
+GET my_index/_analyze <4>
 {
+  "field": "text.english",
   "text": "The quick Brown Foxes."
 }
 --------------------------------------------------

docs/reference/migration/migrate_6_0/rest.asciidoc

@@ -7,3 +7,7 @@ In previous versions of Elasticsearch, JSON documents were allowed to contain un
 This feature was removed in the 5.x series, but a backwards-compatibility layer was added via the
 system property `elasticsearch.json.allow_unquoted_field_names`. This backwards-compatibility layer
 has been removed in Elasticsearch 6.0.0.
+
+==== Analyze API changes
+
+The deprecated request parameters and plain text in request body has been removed. Define parameters in request body.

plugins/analysis-icu/src/test/resources/rest-api-spec/test/analysis_icu/10_basic.yaml

@@ -3,8 +3,9 @@
 "Tokenizer":
     - do:
         indices.analyze:
-          text:         Foo Bar
+          body:
-          tokenizer:    icu_tokenizer
+            text:         Foo Bar
+            tokenizer:    icu_tokenizer
     - length: { tokens: 2 }
     - match:  { tokens.0.token: Foo }
     - match:  { tokens.1.token: Bar }
@@ -12,26 +13,29 @@
 "Normalization filter":
     - do:
         indices.analyze:
-          filter:      icu_normalizer
+          body:
-          text:         Foo Bar Ruß
+            filter:       [icu_normalizer]
-          tokenizer:    keyword
+            text:         Foo Bar Ruß
+            tokenizer:    keyword
     - length: { tokens: 1 }
     - match:  { tokens.0.token: foo bar russ }
 ---
 "Normalization charfilter":
     - do:
         indices.analyze:
-          char_filter: icu_normalizer
+          body:
-          text:         Foo Bar Ruß
+            char_filter:  [icu_normalizer]
-          tokenizer:    keyword
+            text:         Foo Bar Ruß
+            tokenizer:    keyword
     - length: { tokens: 1 }
     - match:  { tokens.0.token: foo bar russ }
 ---
 "Folding filter":
     - do:
         indices.analyze:
-          filter:      icu_folding
+          body:
-          text:         Foo Bar résumé
+            filter:       [icu_folding]
-          tokenizer:    keyword
+            text:         Foo Bar résumé
+            tokenizer:    keyword
     - length: { tokens: 1 }
     - match:  { tokens.0.token: foo bar resume }

plugins/analysis-kuromoji/src/test/resources/rest-api-spec/test/analysis_kuromoji/10_basic.yaml

@@ -4,8 +4,9 @@
 "Analyzer":
     - do:
         indices.analyze:
-          text:         JR新宿駅の近くにビールを飲みに行こうか
+          body:
-          analyzer:     kuromoji
+            text:         JR新宿駅の近くにビールを飲みに行こうか
+            analyzer:     kuromoji
     - length: { tokens: 7 }
     - match:  { tokens.0.token: jr }
     - match:  { tokens.1.token: 新宿 }
@@ -18,8 +19,9 @@
 "Tokenizer":
     - do:
         indices.analyze:
-          text:         関西国際空港
+          body:
-          tokenizer:    kuromoji_tokenizer
+            text:         関西国際空港
+            tokenizer:    kuromoji_tokenizer
     - length: { tokens: 4 }
     - match:  { tokens.0.token: 関西 }
     - match:  { tokens.1.token: 関西国際空港 }
@@ -29,26 +31,29 @@
 "Baseform filter":
     - do:
         indices.analyze:
-          text:         飲み
+          body:
-          tokenizer:    kuromoji_tokenizer
+            text:         飲み
-          filter:      kuromoji_baseform
+            tokenizer:    kuromoji_tokenizer
+            filter:       [kuromoji_baseform]
     - length: { tokens: 1 }
     - match:  { tokens.0.token: 飲む }
 ---
 "Reading filter":
     - do:
         indices.analyze:
-          text:         寿司
+          body:
-          tokenizer:    kuromoji_tokenizer
+            text:         寿司
-          filter:      kuromoji_readingform
+            tokenizer:    kuromoji_tokenizer
+            filter:       [kuromoji_readingform]
     - length: { tokens: 1 }
     - match:  { tokens.0.token: スシ }
 ---
 "Stemming filter":
     - do:
         indices.analyze:
-          text:         サーバー
+          body:
-          tokenizer:    kuromoji_tokenizer
+            text:         サーバー
-          filter:      kuromoji_stemmer
+            tokenizer:    kuromoji_tokenizer
+            filter:       [kuromoji_stemmer]
     - length: { tokens: 1 }
     - match:  { tokens.0.token: サーバ }

plugins/analysis-phonetic/src/test/resources/rest-api-spec/test/analysis_phonetic/10_metaphone.yaml

@@ -22,8 +22,9 @@
     - do:
         indices.analyze:
             index: phonetic_sample
-            analyzer: my_analyzer
+            body:
-            text: Joe Bloggs
+                analyzer: my_analyzer
+                text: Joe Bloggs
 
     - length: { tokens: 4 }
     - match:  { tokens.0.token: J  }

plugins/analysis-phonetic/src/test/resources/rest-api-spec/test/analysis_phonetic/20_double_metaphone.yaml

@@ -22,8 +22,9 @@
     - do:
         indices.analyze:
             index: phonetic_sample
-            analyzer: my_analyzer
+            body:
-            text: supercalifragilisticexpialidocious
+                analyzer: my_analyzer
+                text: supercalifragilisticexpialidocious
 
     - length: { tokens: 1 }
     - match:  { tokens.0.token: SPRKLF }

plugins/analysis-phonetic/src/test/resources/rest-api-spec/test/analysis_phonetic/30_beider_morse.yaml

@@ -24,8 +24,9 @@
     - do:
         indices.analyze:
             index: phonetic_sample
-            analyzer: my_analyzer
+            body:
-            text: Szwarc
+                analyzer: my_analyzer
+                text: Szwarc
 
     - length: { tokens: 1 }
     - match:  { tokens.0.token: Svarts }

plugins/analysis-phonetic/src/test/resources/rest-api-spec/test/analysis_phonetic/50_daitch_mokotoff.yaml

@@ -21,8 +21,9 @@
     - do:
         indices.analyze:
             index: phonetic_sample
-            analyzer: my_analyzer
+            body:
-            text: Moskowitz
+                analyzer: my_analyzer
+                text: Moskowitz
 
     - length: { tokens: 1 }
     - match:  { tokens.0.token: "645740" }

plugins/analysis-smartcn/src/test/resources/rest-api-spec/test/analysis_smartcn/10_basic.yaml

@@ -3,8 +3,9 @@
 "Tokenizer":
     - do:
         indices.analyze:
-          text:         我购买了道具和服装。
+          body:
-          tokenizer:    smartcn_tokenizer
+            text:         我购买了道具和服装。
+            tokenizer:    smartcn_tokenizer
     - length: { tokens: 7 }
     - match:  { tokens.0.token: 我  }
     - match:  { tokens.1.token: 购买 }
@@ -17,8 +18,9 @@
 "Analyzer":
     - do:
         indices.analyze:
-          text:         我购买了道具和服装。
+          body:
-          analyzer:     smartcn
+            text:         我购买了道具和服装。
+            analyzer:     smartcn
     - length: { tokens: 6 }
     - match:  { tokens.0.token: 我  }
     - match:  { tokens.1.token: 购买 }

plugins/analysis-stempel/src/test/resources/rest-api-spec/test/analysis_stempel/10_basic.yaml

@@ -3,16 +3,18 @@
 "Stemmer":
     - do:
         indices.analyze:
-          text:         studenci
+          body:
-          tokenizer:    keyword
+            text:         studenci
-          filter:      polish_stem
+            tokenizer:    keyword
+            filter:       [polish_stem]
     - length: { tokens: 1 }
     - match:  { tokens.0.token: student  }
 ---
 "Analyzer":
     - do:
         indices.analyze:
-          text:         studenta był
+          body:
-          analyzer:     polish
+            text:         studenta był
+            analyzer:     polish
     - length: { tokens: 1 }
     - match:  { tokens.0.token: student  }

rest-api-spec/src/main/resources/rest-api-spec/api/indices.analyze.json

@@ -12,22 +12,6 @@
         }
       },
       "params": {
-        "analyzer": {
-          "type" : "string",
-          "description" : "The name of the analyzer to use"
-        },
-        "char_filter": {
-          "type" : "list",
-          "description" : "A comma-separated list of character filters to use for the analysis"
-        },
-        "field": {
-          "type" : "string",
-          "description" : "Use the analyzer configured for this field (instead of passing the analyzer name)"
-        },
-        "filter": {
-          "type" : "list",
-          "description" : "A comma-separated list of filters to use for the analysis"
-        },
         "index": {
           "type" : "string",
           "description" : "The name of the index to scope the operation"
@@ -36,22 +20,6 @@
           "type" : "boolean",
           "description" : "With `true`, specify that a local shard should be used if available, with `false`, use a random shard (default: true)"
         },
-        "text": {
-          "type" : "list",
-          "description" : "The text on which the analysis should be performed (when request body is not used)"
-        },
-        "tokenizer": {
-          "type" : "string",
-          "description" : "The name of the tokenizer to use for the analysis"
-        },
-        "explain": {
-          "type" : "boolean",
-          "description" : "With `true`, outputs more advanced details. (default: false)"
-        },
-        "attributes": {
-          "type" : "list",
-          "description" : "A comma-separated list of token attributes to output, this parameter works only with `explain=true`"
-        },
         "format": {
           "type": "enum",
           "options" : ["detailed","text"],
@@ -61,7 +29,7 @@
       }
     },
     "body": {
-      "description" : "The text on which the analysis should be performed"
+      "description" : "Define analyzer/tokenizer parameters and the text on which the analysis should be performed"
     }
   }
 }

rest-api-spec/src/main/resources/rest-api-spec/test/indices.analyze/10_analyze.yaml

@@ -8,7 +8,8 @@ setup:
 "Basic test":
     - do:
         indices.analyze:
-          text: Foo Bar
+          body:
+            text: Foo Bar
     - length: { tokens: 2 }
     - match:     { tokens.0.token: foo }
     - match:     { tokens.1.token: bar }
@@ -17,9 +18,10 @@ setup:
 "Tokenizer and filter":
     - do:
         indices.analyze:
-          filter:      lowercase
+          body:
-          text:         Foo Bar
+            filter:       [lowercase]
-          tokenizer:    keyword
+            text:         Foo Bar
+            tokenizer:    keyword
     - length: { tokens: 1 }
     - match:     { tokens.0.token: foo bar }
 
@@ -38,9 +40,10 @@ setup:
 
     - do:
         indices.analyze:
-          field: text
           index: test
-          text: Foo Bar!
+          body:
+            field: text
+            text: Foo Bar!
     - length: { tokens: 2 }
     - match:     { tokens.0.token: Foo }
     - match:     { tokens.1.token: Bar! }
@@ -52,14 +55,6 @@ setup:
     - length: {tokens: 1 }
     - match:     { tokens.0.token: foo bar }
 ---
-"Body params override query string":
-    - do:
-        indices.analyze:
-          text: Foo Bar
-          body: { "text": "Bar Foo", "filter": ["lowercase"], "tokenizer": keyword }
-    - length: {tokens: 1 }
-    - match:     { tokens.0.token: bar foo }
----
 "Array text":
     - do:
         indices.analyze: