tellaro-query-language 0.1.8__tar.gz → 0.2.0__tar.gz

{tellaro_query_language-0.1.8 → tellaro_query_language-0.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: tellaro-query-language
-Version: 0.1.8
+Version: 0.2.0
 Summary: A flexible, human-friendly query language for searching and filtering structured data
 Home-page: https://github.com/tellaro/tellaro-query-language
 License: MIT

{tellaro_query_language-0.1.8 → tellaro_query_language-0.2.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "tellaro-query-language"
-version = "0.1.8"
+version = "0.2.0"
 description = "A flexible, human-friendly query language for searching and filtering structured data"
 authors = ["Justin Henderson <justin@tellaro.io>"]
 license = "MIT"

{tellaro_query_language-0.1.8 → tellaro_query_language-0.2.0}/src/tql/core.py

@@ -450,7 +450,8 @@ class TQL:
         index: Optional[str] = None,
         query: Optional[str] = None,
         size: int = 500,
-        from_: int = 0,
+        search_after: Optional[List[Any]] = None,
+        sort: Optional[List[Dict[str, Any]]] = None,
         timestamp_field: str = "@timestamp",
         time_range: Optional[Dict[str, str]] = None,
         scan_all: bool = False,
@@ -468,7 +469,8 @@ class TQL:
             index: Index name to search
             query: The TQL query string
             size: Number of results to return (default: 500)
-            from_: Starting offset for pagination (default: 0)
+            search_after: Values from previous result's sort field for pagination
+            sort: Sort order specification (e.g., [{"@timestamp": "desc"}, {"_id": "asc"}])
             timestamp_field: Field name for timestamp filtering (default: "@timestamp")
             time_range: Optional time range dict with 'gte' and/or 'lte' keys
             scan_all: If True, use scroll API to retrieve all matching documents
@@ -480,6 +482,7 @@ class TQL:
             Dictionary containing:
             - results: List of processed results
             - total: Total number of matching documents
+            - sort_values: Sort values of the last document (for search_after pagination)
             - post_processing_applied: Whether post-processing was applied
             - health_status: Query health status
             - health_reasons: List of health issues
@@ -503,6 +506,24 @@ class TQL:
         # Remove parameters that the new implementation doesn't understand
         filtered_kwargs = {k: v for k, v in kwargs.items() if k not in ["save_enrichment", "opensearch_client"]}
 
+        # Check for backward compatibility - if from_ is in kwargs, it's old usage
+        if "from_" in kwargs:
+            # Old style pagination - convert to search_after with default sort
+            from_ = kwargs.pop("from_")
+            if from_ > 0 and not sort:
+                # Need a sort for proper pagination
+                sort = [{"_id": "asc"}]
+            # Note: We can't directly convert from_ to search_after without previous results
+            # This is a limitation of moving to search_after
+            if from_ > 0:
+                import warnings
+
+                warnings.warn(
+                    "from_ parameter is deprecated. Use search_after with sort for efficient pagination.",
+                    DeprecationWarning,
+                    stacklevel=2,
+                )
+
         # Add the supported parameters
         filtered_kwargs.update(
             {
@@ -511,6 +532,8 @@ class TQL:
                 "scan_all": scan_all,
                 "scroll_size": scroll_size,
                 "scroll_timeout": scroll_timeout,
+                "search_after": search_after,
+                "sort": sort,
             }
         )
 
@@ -519,7 +542,7 @@ class TQL:
             filtered_kwargs["client"] = opensearch_client
 
         # Execute using new implementation
-        results = self.opensearch_ops.execute_opensearch(query, index=index, size=size, from_=from_, **filtered_kwargs)
+        results = self.opensearch_ops.execute_opensearch(query, index=index, size=size, **filtered_kwargs)
 
         # Convert to old format if needed
         if isinstance(results, list):

{tellaro_query_language-0.1.8 → tellaro_query_language-0.2.0}/src/tql/core_components/opensearch_operations.py

@@ -141,7 +141,7 @@ class OpenSearchOperations:
         query: str,
         index: Optional[str] = None,
         size: int = 10000,
-        from_: int = 0,
+        search_after: Optional[List[Any]] = None,
         sort: Optional[List[Dict[str, Any]]] = None,
         source_includes: Optional[List[str]] = None,
         source_excludes: Optional[List[str]] = None,
@@ -175,8 +175,8 @@ class OpenSearchOperations:
             query: TQL query string
             index: OpenSearch index name (uses environment variable if not provided)
             size: Maximum number of results to return (default: 10000)
-            from_: Offset for pagination (default: 0)
-            sort: List of sort specifications
+            search_after: Values from previous result for pagination
+            sort: List of sort specifications (required for search_after)
             source_includes: Fields to include in response
             source_excludes: Fields to exclude from response
             track_total_hits: Whether to track total hit count
@@ -322,11 +322,13 @@ class OpenSearchOperations:
             else:
                 search_body["query"] = time_filter
 
-        search_body.update({"size": size, "from": from_, "track_total_hits": track_total_hits})
+        search_body.update({"size": size, "track_total_hits": track_total_hits})
 
         # Add optional parameters
         if sort:
             search_body["sort"] = sort
+        if search_after:
+            search_body["search_after"] = search_after
         if source_includes or source_excludes:
             search_body["_source"] = {}
             if source_includes:
@@ -705,11 +707,16 @@ class OpenSearchOperations:
         if not scan_all:
             result["pagination"] = {
                 "size": size,
-                "from": from_,
                 "total": opensearch_total,
-                "has_more": opensearch_total > (from_ + len(results)),
+                "has_more": len(hits) == size,  # If we got a full page, there might be more
             }
 
+            # Add sort values from the last hit for search_after pagination
+            if hits and sort:
+                last_hit = hits[-1]
+                if "sort" in last_hit:
+                    result["sort_values"] = last_hit["sort"]
+
         return result
 
     def _docs_match(self, doc1: Dict[str, Any], doc2: Dict[str, Any]) -> bool:

{tellaro_query_language-0.1.8 → tellaro_query_language-0.2.0}/src/tql/evaluator.py

@@ -81,7 +81,10 @@ class TQLEvaluator:
         if isinstance(node, dict):
             node_type = node.get("type")
 
-            if node_type == "comparison":
+            if node_type == "match_all":
+                # Empty query matches all records
+                return True
+            elif node_type == "comparison":
                 return self._evaluate_comparison(node, record, field_mappings)
             elif node_type == "logical_op":
                 return self._evaluate_logical_op(node, record, field_mappings)

{tellaro_query_language-0.1.8 → tellaro_query_language-0.2.0}/src/tql/opensearch_components/lucene_converter.py

@@ -31,7 +31,10 @@ class LuceneConverter:
         if isinstance(node, dict):
             node_type = node.get("type")
 
-            if node_type == "comparison":
+            if node_type == "match_all":
+                # Empty query matches all documents in Lucene
+                return "*:*"
+            elif node_type == "comparison":
                 return self._convert_comparison_to_lucene(node)
             elif node_type == "logical_op":
                 return self._convert_logical_op_to_lucene(node)

{tellaro_query_language-0.1.8 → tellaro_query_language-0.2.0}/src/tql/opensearch_components/query_converter.py

@@ -27,7 +27,10 @@ class QueryConverter:
         if isinstance(node, dict):
             node_type = node.get("type")
 
-            if node_type == "comparison":
+            if node_type == "match_all":
+                # Empty query matches all documents
+                return {"match_all": {}}
+            elif node_type == "comparison":
                 return self._convert_comparison(node)
             elif node_type == "logical_op":
                 return self._convert_logical_op(node)

{tellaro_query_language-0.1.8 → tellaro_query_language-0.2.0}/src/tql/parser.py

@@ -43,6 +43,11 @@ class TQLParser:
         Raises:
             TQLParseError: If the query has invalid syntax
         """
+        # Handle empty or whitespace-only queries
+        if not query or not query.strip():
+            # Return a special AST that matches all records
+            return {"type": "match_all"}
+
         try:
             # Parse the query
             parsed_result = self.grammar.tql_expr.parseString(query, parseAll=True)