honeymoose
/
OpenSearch
mirror of https://github.com/honeymoose/OpenSearch.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #20704 from johtani/remove_request_params_in_analyze_api 

Removing request parameters in _analyze API
This commit is contained in:
Jun Ohtani 2016-10-27 17:43:18 +09:00 committed by GitHub
parent c1a9833445 945fa499d2
commit a66c76eb44
18 changed files with 142 additions and 155 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

34
core/src/main/java/org/elasticsearch/rest/action/admin/indices/RestAnalyzeAction.java
View File

@ -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)) {
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);
}
}
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");

3
core/src/test/java/org/elasticsearch/rest/action/admin/indices/RestAnalyzeActionTests.java
View File

@ -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]"));
}
}

15
docs/plugins/analysis-icu.asciidoc
View File

@ -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>
}

58
docs/plugins/analysis-kuromoji.asciidoc
View File

@ -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

6
docs/plugins/analysis-phonetic.asciidoc
View File

@ -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

15
docs/reference/indices/analyze.asciidoc
View File

@ -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.

6
docs/reference/mapping/params/analyzer.asciidoc
View File

@ -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."
}
--------------------------------------------------

4
docs/reference/migration/migrate_6_0/rest.asciidoc
View File

@ -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.

26
plugins/analysis-icu/src/test/resources/rest-api-spec/test/analysis_icu/10_basic.yaml
View File

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

31
plugins/analysis-kuromoji/src/test/resources/rest-api-spec/test/analysis_kuromoji/10_basic.yaml
View File

@ -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
analyzer: kuromoji
body:
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
tokenizer: kuromoji_tokenizer
body:
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
tokenizer: kuromoji_tokenizer
filter: kuromoji_baseform
body:
text: 飲み
tokenizer: kuromoji_tokenizer
filter: [kuromoji_baseform]
- length: { tokens: 1 }
- match: { tokens.0.token: 飲む }
---
"Reading filter":
- do:
indices.analyze:
text: 寿司
tokenizer: kuromoji_tokenizer
filter: kuromoji_readingform
body:
text: 寿司
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
tokenizer: kuromoji_tokenizer
filter: kuromoji_stemmer
body:
text: サーバー
tokenizer: kuromoji_tokenizer
filter: [kuromoji_stemmer]
- length: { tokens: 1 }
- match: { tokens.0.token: サーバ }

5
plugins/analysis-phonetic/src/test/resources/rest-api-spec/test/analysis_phonetic/10_metaphone.yaml
View File

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

5
plugins/analysis-phonetic/src/test/resources/rest-api-spec/test/analysis_phonetic/20_double_metaphone.yaml
View File

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

5
plugins/analysis-phonetic/src/test/resources/rest-api-spec/test/analysis_phonetic/30_beider_morse.yaml
View File

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

5
plugins/analysis-phonetic/src/test/resources/rest-api-spec/test/analysis_phonetic/50_daitch_mokotoff.yaml
View File

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

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

@ -3,8 +3,9 @@
"Tokenizer":
- do:
indices.analyze:
text: 我购买了道具和服装。
tokenizer: smartcn_tokenizer
body:
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。
analyzer: smartcn
body:
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 }

12
plugins/analysis-stempel/src/test/resources/rest-api-spec/test/analysis_stempel/10_basic.yaml
View File

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

34
rest-api-spec/src/main/resources/rest-api-spec/api/indices.analyze.json
View File

@ -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"
}
}
}

23
rest-api-spec/src/main/resources/rest-api-spec/test/indices.analyze/10_analyze.yaml
View File

@ -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
text: Foo Bar
tokenizer: keyword
body:
filter: [lowercase]
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: