From 6408941b625115ce0f4fb44fab30dc5b2150de39 Mon Sep 17 00:00:00 2001
From: psaesha <saesha.parekh@gmail.com>
Date: Wed, 24 Jun 2026 14:49:17 +0530
Subject: [PATCH] no of entries for file formats other than csv

---
 api/types/type_resource.py | 32 ++++++++++++++++++++++-------
 api/utils/data_indexing.py | 41 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 66 insertions(+), 7 deletions(-)

diff --git a/api/types/type_resource.py b/api/types/type_resource.py
index 20532023..cd6d09c3 100644
--- a/api/types/type_resource.py
+++ b/api/types/type_resource.py
@@ -20,7 +20,13 @@
 from api.types.type_preview_data import PreviewData
 from api.types.type_prompt_resource_details import TypePromptResourceDetails
 from api.types.type_resource_metadata import TypeResourceMetadata
-from api.utils.data_indexing import get_preview_data, get_row_count
+from api.utils.data_indexing import (
+    FILE_COUNT_FORMATS,
+    INDEXED_FORMATS,
+    get_entry_count_from_file,
+    get_preview_data,
+    get_row_count,
+)
 from api.utils.graphql_telemetry import trace_resolver
 
 logger = structlog.get_logger(__name__)
@@ -177,14 +183,26 @@ def no_of_entries(self) -> int:
             if not file_details:
                 return 0
 
-            if not hasattr(file_details, "format") or file_details.format.lower() != "csv":
+            if not hasattr(file_details, "format"):
                 return 0
 
-            try:
-                return get_row_count(self)  # type: ignore
-            except Exception as row_count_error:
-                logger.error(f"Error in get_row_count: {str(row_count_error)}")
-                return 0
+            fmt = file_details.format.lower()
+
+            if fmt in INDEXED_FORMATS:
+                try:
+                    return get_row_count(self)  # type: ignore
+                except Exception as row_count_error:
+                    logger.error(f"Error in get_row_count: {str(row_count_error)}")
+                    return 0
+
+            if fmt in FILE_COUNT_FORMATS:
+                try:
+                    return get_entry_count_from_file(self)  # type: ignore
+                except Exception as file_count_error:
+                    logger.error(f"Error in get_entry_count_from_file: {str(file_count_error)}")
+                    return 0
+
+            return 0
         except Exception as e:
             logger.error(f"Error getting number of entries: {str(e)}")
             return 0
diff --git a/api/utils/data_indexing.py b/api/utils/data_indexing.py
index 8e817b88..8d56da54 100644
--- a/api/utils/data_indexing.py
+++ b/api/utils/data_indexing.py
@@ -16,6 +16,11 @@
 # Use a separate database for data tables
 DATA_DB = "data_db"  # This should match the connection name in settings.py
 
+# Formats indexed into ResourceDataTable (queryable via get_row_count)
+INDEXED_FORMATS = {"csv", "xls", "xlsx", "ods", "parquet", "feather", "json", "tsv"}
+# Formats counted by parsing the file directly (not indexed into DB)
+FILE_COUNT_FORMATS = {"yml", "yaml", "xml"}
+
 # Allowed comparison operators for column-based filtering on indexed data.
 # Maps operator suffix -> (sql_template_with_{ph}_placeholder, value_transformer)
 _FILTER_OPERATORS: Dict[str, Tuple[str, Any]] = {
@@ -397,6 +402,42 @@ def get_row_count(resource: Resource) -> int:
         return 0
 
 
+def get_entry_count_from_file(resource: Resource) -> int:
+    """Count entries in yml/yaml/xml files by parsing the file directly."""
+    try:
+        file_details = getattr(resource, "resourcefiledetails", None)
+        if not file_details:
+            return 0
+
+        fmt = file_details.format.lower()
+        filepath = file_details.file.path
+
+        if fmt in ("yml", "yaml"):
+            import yaml
+
+            with open(filepath, "r") as f:
+                data = yaml.safe_load(f)
+            if isinstance(data, list):
+                return len(data)
+            if isinstance(data, dict):
+                for v in data.values():
+                    if isinstance(v, list):
+                        return len(v)
+                return len(data)
+            return 0
+
+        if fmt == "xml":
+            import xml.etree.ElementTree as ET
+
+            root = ET.parse(filepath).getroot()
+            return len(list(root))
+
+        return 0
+    except Exception as e:
+        logger.error(f"Error counting entries from file for resource {resource.id}: {str(e)}")
+        return 0
+
+
 def get_preview_data(resource: Resource) -> Optional[PreviewData]:
     try:
         if not resource.preview_enabled: