Update PrefixQuery, MatchQuery, ConstantScoreQuery and FuzzyQuery (opensearch-project#249)

lucy66hw · web-flow · commit 61fcd2b1ca05 · 2025-10-01T19:01:51.000-04:00
* Update PrefixQuery, MatchQuery, ConstantScoreQuery and FuzzyQuery

Signed-off-by: xil &lt;fridalu66@gmail.com&gt;

* update

Signed-off-by: xil &lt;fridalu66@gmail.com&gt;

---------

Signed-off-by: xil &lt;fridalu66@gmail.com&gt;
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -6,6 +6,7 @@ Inspired from [Keep a Changelog](https://keepachangelog.com/en/1.0.0/)
 ### Added
 
 ### Changed
+- update `PrefixQuery`, `MatchQuery`, `ConstantScoreQuery` and `FuzzyQuery`  ([#249](https://github.com/opensearch-project/opensearch-protobufs/pull/249))
 
 ### Removed
 
diff --git a/protos/schemas/common.proto b/protos/schemas/common.proto
@@ -439,7 +439,7 @@ message QueryContainer {
     WildcardQuery wildcard = 15;
 
     // Use the match query for full-text search on a specific document field. If you run a match query on a text field, the match query analyzes the provided search string and returns documents that match any of the string's terms. If you run a match query on an exact-value field, it returns documents that match the exact value. The preferred way to search exact-value fields is to use a filter because, unlike a query, a filter is cached.
-    MatchQueryTypeless match = 16;
+    MatchQuery match = 16;
 
     // The match_bool_prefix query analyzes the provided search string and creates a Boolean query from the string's terms. It uses every term except the last term as a whole word for matching. The last term is used as a prefix. The match_bool_prefix query returns documents that contain either the whole-word terms or terms that start with the prefix term, in any order.
     MatchBoolPrefixQuery match_bool_prefix = 17;
@@ -1315,89 +1315,37 @@ message KnnQueryRescore {
   }
 }
 
-message MatchQueryTypeless {
-  string field = 1;
-  oneof match_query_typeless {
-    // Standard match query for performing a full-text search, including options for fuzzy matching.
-    MatchQuery match_query = 2;
-    // Simplified match query syntax by combining the <field> and query parameters
-    ObjectMap object_map = 3;
-  }
-}
-
 message MatchQuery {
-
+  // [required] Specifies the field against which to run a search query
+  string field = 1;
+  // [required] The query string to use for search.
+  FieldValue query = 2;
   // [optional] Floating point number used to decrease or increase the relevance scores of the query. Boost values are relative to the default value of 1.0. A boost value between 0 and 1.0 decreases the relevance score. A value greater than 1.0 increases the relevance score.
-  optional float boost = 1;
-
+  optional float boost = 3;
   // [optional] Query name for query tagging.
-  optional string x_name = 2;
-
-  // [optional]
-  // The analyzer used to tokenize the query string text.
-  // Default is the index-time analyzer specified for the default_field. If no analyzer is specified for the default_field, the analyzer is the default analyzer for the index.
-  string analyzer = 3;
-
-  // [optional]
-  // Specifies whether to create a match phrase query automatically for multi-term synonyms.
-  // For example, if you specify ba,batting average as synonyms and search for ba, OpenSearch searches for ba OR "batting average" (if this option is true) or ba OR (batting AND average) (if this option is false).
-  // Default is true.
-  bool auto_generate_synonyms_phrase_query = 4;
-
-  // [x-deprecated]
-  float cutoff_frequency = 5;
-
-  // [optional]
-  // The number of character edits (insertions, deletions, substitutions, or transpositions) that it takes to change one word to another when determining whether a term matched a value.
-  // For example, the distance between wined and wind is 1. Valid values are non-negative integers or AUTO.
-  // The default, AUTO, chooses a value based on the length of each term and is a good choice for most use cases.
-  Fuzziness fuzziness = 6;
-
-  // [optional]
-  // Determines how OpenSearch rewrites the query.
-  // Default is constant_score.
-  MultiTermQueryRewrite fuzzy_rewrite = 7;
-  // [optional]
-  // Setting fuzzy_transpositions to true (default) adds swaps of adjacent characters to the insert, delete, and substitute operations of the fuzziness option.
-  // For example, the distance between wind and wnid is 1 if fuzzy_transpositions is true (swap “n” and “i”) and 2 if it is false (delete “n”, insert “n”). If fuzzy_transpositions is false, rewind and wnid have the same distance (2) from wind, despite the more human-centric opinion that wnid is an obvious typo.
-  // The default(true) is a good choice for most use cases.
-  bool fuzzy_transpositions = 8;
-
-  // [optional]
-  // Setting lenient to true ignores data type mismatches between the query and the document field.
-  // For example, a query string of "8.2" could match a field of type float.
-  // Default is false.
-  bool lenient = 9;
-
-  // [optional]
-  // The maximum number of terms to which the query can expand. Fuzzy queries “expand to” a number of matching terms that are within the distance specified in fuzziness. Then OpenSearch tries to match those terms.
-  // Default is 50.
-  int32 max_expansions = 10;
-
-  // [optional]
-  // If the query string contains multiple search terms and you use the or operator, the number of terms that need to match for the document to be considered a match.
-  // For example, if minimum_should_match is 2, wind often rising does not match The Wind Rises. If minimum_should_match is 1, it matches.
-  MinimumShouldMatch minimum_should_match = 11;
-
-  // [optional]
-  // If the query string contains multiple search terms, whether all terms need to match (AND) or only one term needs to match (OR) for a document to be considered a match.
-  // Default is OR.
-  Operator operator = 12;
-
-  // [optional]
-  // The number of leading characters that are not considered in fuzziness.
-  // Default is 0.
-  int32 prefix_length = 13;
-  // [required]
-  // The query string to use for search.
-  FieldValue query = 14;
-
-  // [optional]
-  // In some cases, the analyzer removes all terms from a query string.
-  // For example, the stop analyzer removes all terms from the string an but this. In those cases, zero_terms_query specifies whether to match no documents (none) or all documents (all). Valid values are none and all.
-  // Default is none.
-  ZeroTermsQuery zero_terms_query = 15;
-
+  optional string x_name = 4;
+  // [optional] The analyzer used to tokenize the query string text. Default is the index-time analyzer specified for the default_field. If no analyzer is specified for the default_field, the analyzer is the default analyzer for the index.
+  optional string analyzer = 5;
+  // [optional] Specifies whether to create a match phrase query automatically for multi-term synonyms. For example, if you specify ba,batting average as synonyms and search for ba, OpenSearch searches for ba OR "batting average" (if this option is true) or ba OR (batting AND average) (if this option is false).
+  optional bool auto_generate_synonyms_phrase_query = 6;
+  // [optional] The number of character edits (insertions, deletions, substitutions, or transpositions) that it takes to change one word to another when determining whether a term matched a value. For example, the distance between wined and wind is 1. Valid values are non-negative integers or AUTO.
+  optional Fuzziness fuzziness = 7;
+  // [optional] Determines how OpenSearch rewrites the query. Default is constant_score.
+  optional MultiTermQueryRewrite fuzzy_rewrite = 8;
+  // [optional] Setting fuzzy_transpositions to true (default) adds swaps of adjacent characters to the insert, delete, and substitute operations of the fuzziness option. For example, the distance between wind and wnid is 1 if fuzzy_transpositions is true (swap “n” and “i”) and 2 if it is false (delete “n”, insert “n”). If fuzzy_transpositions is false, rewind and wnid have the same distance (2) from wind, despite the more human-centric opinion that wnid is an obvious typo. The default(true) is a good choice for most use cases.
+  optional bool fuzzy_transpositions = 9;
+  // [optional] Setting lenient to true ignores data type mismatches between the query and the document field. For example, a query string of "8.2" could match a field of type float. Default is false.
+  optional bool lenient = 10;
+  // [optional] The maximum number of terms to which the query can expand. Fuzzy queries “expand to” a number of matching terms that are within the distance specified in fuzziness. Then OpenSearch tries to match those terms. Default is 50.
+  optional int32 max_expansions = 11;
+  // [optional] If the query string contains multiple search terms and you use the or operator, the number of terms that need to match for the document to be considered a match. For example, if minimum_should_match is 2, wind often rising does not match The Wind Rises. If minimum_should_match is 1, it matches.
+  optional MinimumShouldMatch minimum_should_match = 12;
+  // [optional] If the query string contains multiple search terms, whether all terms need to match (AND) or only one term needs to match (OR) for a document to be considered a match. Default is OR.
+  optional Operator operator = 13;
+  // [optional] The number of leading characters that are not considered in fuzziness. Default is 0.
+  optional int32 prefix_length = 14;
+  // [optional] In some cases, the analyzer removes all terms from a query string. For example, the stop analyzer removes all terms from the string an but this. In those cases, zero_terms_query specifies whether to match no documents (none) or all documents (all). Valid values are none and all. Default is none.
+  optional ZeroTermsQuery zero_terms_query = 15;
 }
 
 message Query {
@@ -1465,15 +1413,12 @@ message BoostingQuery {
 }
 
 message ConstantScoreQuery {
-
+  // [required] The filter query that a document must match to be returned in the results.
+  QueryContainer filter = 1;
   // [optional] Floating point number used to decrease or increase the relevance scores of the query. Boost values are relative to the default value of 1.0. A boost value between 0 and 1.0 decreases the relevance score. A value greater than 1.0 increases the relevance score.
-  optional float boost = 1;
-
+  optional float boost = 2;
   // [optional] Query name for query tagging.
-  optional string x_name = 2;
-
-  QueryContainer filter = 3;
-
+  optional string x_name = 3;
 }
 
 message DisMaxQuery {
@@ -1738,26 +1683,16 @@ message IntervalsContainer {
 message PrefixQuery {
   // [required] Specifies the field against which to run a search query
   string field = 1;
-
+  // [required] The term to search for in the field specified in <field>.
+  string value = 2;
   // [optional] Floating point number used to decrease or increase the relevance scores of the query. Boost values are relative to the default value of 1.0. A boost value between 0 and 1.0 decreases the relevance score. A value greater than 1.0 increases the relevance score.
-  optional float boost = 2;
-
+  optional float boost = 3;
   // [optional] Query name for query tagging.
-  optional string x_name = 3;
-
-  // [optional]
-  // Determines how OpenSearch rewrites the query.
-  // Default is constant_score.
-  MultiTermQueryRewrite rewrite = 4;
-
-  // [required]
-  // The term to search for in the field specified in <field>.
-  string value = 5;
-
-  // [optional]
-  // Allows ASCII case insensitive matching of the value with the indexed field values when set to `true`. Default is `false` which means the case sensitivity of matching depends on the underlying field's mapping.
-  bool case_insensitive = 6;
-
+  optional string x_name = 4;
+  // [optional] Determines how OpenSearch rewrites the query. Default is constant_score.
+  optional MultiTermQueryRewrite rewrite = 5;
+  // [optional] Allows ASCII case insensitive matching of the value with the indexed field values when set to `true`. Default is `false` which means the case sensitivity of matching depends on the underlying field's mapping.
+  optional bool case_insensitive = 6;
 }
 
 message TermsLookupFieldStringArrayMap {
@@ -2121,35 +2056,22 @@ message RegexpQuery {
 message FuzzyQuery {
   // [required] Specifies the field against which to run a search query
   string field = 1;
-
+  // [required] Term you wish to find in the provided <field>.
+  FieldValue value = 2;
   // [optional] Floating point number used to decrease or increase the relevance scores of the query. Boost values are relative to the default value of 1.0. A boost value between 0 and 1.0 decreases the relevance score. A value greater than 1.0 increases the relevance score.
-  optional float boost = 2;
-
+  optional float boost = 3;
   // [optional] Query name for query tagging.
-  optional string x_name = 3;
-
-  // [optional]
-  // The maximum number of terms to which the query can expand. Fuzzy queries "expand to" a number of matching terms that are within the distance specified in fuzziness. Then OpenSearch tries to match those terms. Default is 50.
-  int32 max_expansions = 4;
-
-  // [optional]
-  // The number of leading characters that are not considered in fuzziness. Default is 0.
-  int32 prefix_length = 5;
-
-  // [optional]
-  // Determines how OpenSearch rewrites the query.
-  // Default is constant_score.
-  MultiTermQueryRewrite rewrite = 6;
-  // [optional]
-  // Specifies whether to allow transpositions of two adjacent characters (ab to ba) as edits. Default is true.
-  bool transpositions = 7;
-  // [optional]
-  // The number of character edits (insert, delete, substitute) needed to change one word to another when determining whether a term matched a value.
-  Fuzziness fuzziness = 8;
-
-  // [required]
-  // Term you wish to find in the provided <field>.
-  FieldValue value = 9;
+  optional string x_name = 4;
+  // [optional] The maximum number of terms to which the query can expand. Fuzzy queries "expand to" a number of matching terms that are within the distance specified in fuzziness. Then OpenSearch tries to match those terms. Default is 50.
+  optional int32 max_expansions = 5;
+  // [optional] The number of leading characters that are not considered in fuzziness. Default is 0.
+  optional int32 prefix_length = 6;
+  // [optional] Determines how OpenSearch rewrites the query. Default is constant_score.
+  optional MultiTermQueryRewrite rewrite = 7;
+  // [optional] Specifies whether to allow transpositions of two adjacent characters (ab to ba) as edits. Default is true.
+  optional bool transpositions = 8;
+  // [optional] The number of character edits (insert, delete, substitute) needed to change one word to another when determining whether a term matched a value.
+  optional Fuzziness fuzziness = 9;
 }
 
 message Fuzziness{
@@ -2387,36 +2309,39 @@ message MultiMatchQuery {
   // [optional] Determines how OpenSearch rewrites the query. Valid values are constant_score, scoring_boolean, constant_score_boolean, top_terms_N, top_terms_boost_N, and top_terms_blended_freqs_N. If the fuzziness parameter is not 0, the query uses a fuzzy_rewrite method of top_terms_blended_freqs_${max_expansions} by default. Default is constant_score.
   optional string fuzzy_rewrite = 7;
 
+  // [optional] The number of character edits (insert, delete, substitute) that it takes to change one word to another when determining whether a term matched a value.
+  optional Fuzziness fuzziness = 8;
+
   // [optional] Setting fuzzy_transpositions to true (default) adds swaps of adjacent characters to the insert, delete, and substitute operations of the fuzziness option. For example, the distance between wind and wnid is 1 if fuzzy_transpositions is true (swap “n” and “i”) and 2 if it is false (delete “n”, insert “n”). If fuzzy_transpositions is false, rewind and wnid have the same distance (2) from wind, despite the more human-centric opinion that wnid is an obvious typo. The default is a good choice for most use cases.
-  optional bool fuzzy_transpositions = 8;
+  optional bool fuzzy_transpositions = 9;
 
   // [optional] Setting lenient to true ignores data type mismatches between the query and the document field. For example, a query string of "8.2" could match a field of type float. Default is false.
-  optional bool lenient = 9;
+  optional bool lenient = 10;
 
   // [optional] The maximum number of terms to which the query can expand. Fuzzy queries “expand to” a number of matching terms that are within the distance specified in fuzziness. Then OpenSearch tries to match those terms. Default is 50.
-  optional int32 max_expansions = 10;
+  optional int32 max_expansions = 11;
 
   // [optional] If the query string contains multiple search terms and you use the or operator, the number of terms that need to match for the document to be considered a match. For example, if minimum_should_match is 2, wind often rising does not match The Wind Rises. If minimum_should_match is 1, it matches. For details, see Minimum should match.
 
-  optional MinimumShouldMatch minimum_should_match = 11;
+  optional MinimumShouldMatch minimum_should_match = 12;
 
   // [optional] If the query string contains multiple search terms, whether all terms need to match (AND) or only one term needs to match (OR) for a document to be considered a match. Valid values are: 1) OR: The string to be is interpreted as to OR be. 2) AND: The string to be is interpreted as to AND be. Default is OR.
-  optional Operator operator = 12;
+  optional Operator operator = 13;
 
   // [optional] The number of leading characters that are not considered in fuzziness. Default is 0.
-  optional int32 prefix_length = 13;
+  optional int32 prefix_length = 14;
 
   // [optional] Controls the degree to which words in a query can be misordered and still be considered a match. From the Lucene documentation: “The number of other words permitted between words in query phrase. For example, to switch the order of two words requires two moves (the first move places the words atop one another), so to permit reorderings of phrases, the slop must be at least two. A value of zero requires an exact match.” Supported for phrase and phrase_prefix query types.
-  optional int32 slop = 14;
+  optional int32 slop = 15;
 
   // [optional] A factor between 0 and 1.0 that is used to give more weight to documents that match multiple query clauses. For more information, see The tie_breaker parameter`.
-  optional float tie_breaker = 15;
+  optional float tie_breaker = 16;
 
   // [optional] The multi-match query type. Valid values are best_fields, most_fields, cross_fields, phrase, phrase_prefix, bool_prefix. Default is best_fields.
-  optional TextQueryType type = 16;
+  optional TextQueryType type = 17;
 
   // [optional] In some cases, the analyzer removes all terms from a query string. For example, the stop analyzer removes all terms from the string an but this. In those cases, zero_terms_query specifies whether to match no documents (none) or all documents (all). Valid values are none and all. Default is none.
-  optional ZeroTermsQuery zero_terms_query = 17;
+  optional ZeroTermsQuery zero_terms_query = 18;
 }
 
 message FieldValueFactorScoreFunction {
