peng - set the default fragment size to 100

Signed-off-by: Jialiang Liang <jiallian@amazon.com>

Author: RyanL1997

integ-test/src/test/resources/expectedOutput/calcite/explain_highlight_single_term.yaml

@@ -5,4 +5,4 @@ calcite:
         LogicalHighlight(highlightConfig=[[Holmes]])
           CalciteLogicalIndexScan(table=[[OpenSearch, opensearch-sql_test_index_account]])
   physical: |
-    CalciteEnumerableIndexScan(table=[[OpenSearch, opensearch-sql_test_index_account]], PushDownContext=[[HIGHLIGHT->[Holmes], PROJECT->[account_number, firstname, address, balance, gender, city, employer, state, age, email, lastname, _highlight], LIMIT->10000], OpenSearchRequestBuilder(sourceBuilder={"from":0,"size":10000,"timeout":"1m","_source":{"includes":["account_number","firstname","address","balance","gender","city","employer","state","age","email","lastname"],"excludes":[]},"highlight":{"fragment_size":2147483647,"fields":{"Holmes":{}}}}, requestedTotalSize=10000, pageSize=null, startFrom=0)])
+    CalciteEnumerableIndexScan(table=[[OpenSearch, opensearch-sql_test_index_account]], PushDownContext=[[HIGHLIGHT->[Holmes], PROJECT->[account_number, firstname, address, balance, gender, city, employer, state, age, email, lastname, _highlight], LIMIT->10000], OpenSearchRequestBuilder(sourceBuilder={"from":0,"size":10000,"timeout":"1m","_source":{"includes":["account_number","firstname","address","balance","gender","city","employer","state","age","email","lastname"],"excludes":[]},"highlight":{"fields":{"Holmes":{}}}}, requestedTotalSize=10000, pageSize=null, startFrom=0)])

integ-test/src/test/resources/expectedOutput/calcite/explain_highlight_wildcard.yaml

@@ -5,4 +5,4 @@ calcite:
         LogicalHighlight(highlightConfig=[[*]])
           CalciteLogicalIndexScan(table=[[OpenSearch, opensearch-sql_test_index_account]])
   physical: |
-    CalciteEnumerableIndexScan(table=[[OpenSearch, opensearch-sql_test_index_account]], PushDownContext=[[HIGHLIGHT->[*], PROJECT->[account_number, firstname, address, balance, gender, city, employer, state, age, email, lastname, _highlight], LIMIT->10000], OpenSearchRequestBuilder(sourceBuilder={"from":0,"size":10000,"timeout":"1m","_source":{"includes":["account_number","firstname","address","balance","gender","city","employer","state","age","email","lastname"],"excludes":[]},"highlight":{"fragment_size":2147483647,"fields":{"*":{}}}}, requestedTotalSize=10000, pageSize=null, startFrom=0)])
+    CalciteEnumerableIndexScan(table=[[OpenSearch, opensearch-sql_test_index_account]], PushDownContext=[[HIGHLIGHT->[*], PROJECT->[account_number, firstname, address, balance, gender, city, employer, state, age, email, lastname, _highlight], LIMIT->10000], OpenSearchRequestBuilder(sourceBuilder={"from":0,"size":10000,"timeout":"1m","_source":{"includes":["account_number","firstname","address","balance","gender","city","employer","state","age","email","lastname"],"excludes":[]},"highlight":{"fields":{"*":{}}}}, requestedTotalSize=10000, pageSize=null, startFrom=0)])

integ-test/src/test/resources/expectedOutput/calcite/explain_highlight_with_filter.yaml

@@ -6,4 +6,4 @@ calcite:
           LogicalHighlight(highlightConfig=[[*]])
             CalciteLogicalIndexScan(table=[[OpenSearch, opensearch-sql_test_index_account]])
   physical: |
-    CalciteEnumerableIndexScan(table=[[OpenSearch, opensearch-sql_test_index_account]], PushDownContext=[[HIGHLIGHT->[*], FILTER->>($8, 30), PROJECT->[firstname, age, _highlight], LIMIT->10000], OpenSearchRequestBuilder(sourceBuilder={"from":0,"size":10000,"timeout":"1m","query":{"range":{"age":{"from":30,"to":null,"include_lower":false,"include_upper":true,"boost":1.0}}},"_source":{"includes":["firstname","age"],"excludes":[]},"highlight":{"fragment_size":2147483647,"fields":{"*":{}}}}, requestedTotalSize=10000, pageSize=null, startFrom=0)])
+    CalciteEnumerableIndexScan(table=[[OpenSearch, opensearch-sql_test_index_account]], PushDownContext=[[HIGHLIGHT->[*], FILTER->>($8, 30), PROJECT->[firstname, age, _highlight], LIMIT->10000], OpenSearchRequestBuilder(sourceBuilder={"from":0,"size":10000,"timeout":"1m","query":{"range":{"age":{"from":30,"to":null,"include_lower":false,"include_upper":true,"boost":1.0}}},"_source":{"includes":["firstname","age"],"excludes":[]},"highlight":{"fields":{"*":{}}}}, requestedTotalSize=10000, pageSize=null, startFrom=0)])

integ-test/src/test/resources/expectedOutput/calcite_no_pushdown/explain_highlight_single_term.yaml

@@ -7,4 +7,4 @@ calcite:
   physical: |
     EnumerableLimit(fetch=[10000])
       EnumerableCalc(expr#0..17=[{inputs}], proj#0..10=[{exprs}], _highlight=[$t17])
-        CalciteEnumerableIndexScan(table=[[OpenSearch, opensearch-sql_test_index_account]], PushDownContext=[[HIGHLIGHT->[Holmes]], OpenSearchRequestBuilder(sourceBuilder={"from":0,"timeout":"1m","highlight":{"fragment_size":2147483647,"fields":{"Holmes":{}}}}, requestedTotalSize=2147483647, pageSize=null, startFrom=0)])
+        CalciteEnumerableIndexScan(table=[[OpenSearch, opensearch-sql_test_index_account]], PushDownContext=[[HIGHLIGHT->[Holmes]], OpenSearchRequestBuilder(sourceBuilder={"from":0,"timeout":"1m","highlight":{"fields":{"Holmes":{}}}}, requestedTotalSize=2147483647, pageSize=null, startFrom=0)])

integ-test/src/test/resources/expectedOutput/calcite_no_pushdown/explain_highlight_wildcard.yaml

@@ -7,4 +7,4 @@ calcite:
   physical: |
     EnumerableLimit(fetch=[10000])
       EnumerableCalc(expr#0..17=[{inputs}], proj#0..10=[{exprs}], _highlight=[$t17])
-        CalciteEnumerableIndexScan(table=[[OpenSearch, opensearch-sql_test_index_account]], PushDownContext=[[HIGHLIGHT->[*]], OpenSearchRequestBuilder(sourceBuilder={"from":0,"timeout":"1m","highlight":{"fragment_size":2147483647,"fields":{"*":{}}}}, requestedTotalSize=2147483647, pageSize=null, startFrom=0)])
+        CalciteEnumerableIndexScan(table=[[OpenSearch, opensearch-sql_test_index_account]], PushDownContext=[[HIGHLIGHT->[*]], OpenSearchRequestBuilder(sourceBuilder={"from":0,"timeout":"1m","highlight":{"fields":{"*":{}}}}, requestedTotalSize=2147483647, pageSize=null, startFrom=0)])

integ-test/src/test/resources/expectedOutput/calcite_no_pushdown/explain_highlight_with_filter.yaml

@@ -8,4 +8,4 @@ calcite:
   physical: |
     EnumerableLimit(fetch=[10000])
       EnumerableCalc(expr#0..17=[{inputs}], expr#18=[30], expr#19=[>($t8, $t18)], firstname=[$t1], age=[$t8], _highlight=[$t17], $condition=[$t19])
-        CalciteEnumerableIndexScan(table=[[OpenSearch, opensearch-sql_test_index_account]], PushDownContext=[[HIGHLIGHT->[*]], OpenSearchRequestBuilder(sourceBuilder={"from":0,"timeout":"1m","highlight":{"fragment_size":2147483647,"fields":{"*":{}}}}, requestedTotalSize=2147483647, pageSize=null, startFrom=0)])
+        CalciteEnumerableIndexScan(table=[[OpenSearch, opensearch-sql_test_index_account]], PushDownContext=[[HIGHLIGHT->[*]], OpenSearchRequestBuilder(sourceBuilder={"from":0,"timeout":"1m","highlight":{"fields":{"*":{}}}}, requestedTotalSize=2147483647, pageSize=null, startFrom=0)])

opensearch/src/main/java/org/opensearch/sql/opensearch/storage/scan/AbstractCalciteIndexScan.java

@@ -520,11 +520,10 @@ protected static void applyHighlightPushDown(
       hb.postTags(highlightConfig.postTags().toArray(new String[0]));
     }
 
-    // Apply fragment_size (default to Integer.MAX_VALUE when not specified)
-    hb.fragmentSize(
-        highlightConfig.fragmentSize() != null
-            ? highlightConfig.fragmentSize()
-            : Integer.MAX_VALUE);
+    // Apply fragment_size only when explicitly specified; otherwise let OpenSearch use its default
+    if (highlightConfig.fragmentSize() != null) {
+      hb.fragmentSize(highlightConfig.fragmentSize());
+    }
 
     requestBuilder.getSourceBuilder().highlighter(hb);
   }