MindsDB 25.2.2.1__py3-none-any.whl → 25.2.3.0__py3-none-any.whl

{MindsDB-25.2.2.1.dist-info → MindsDB-25.2.3.0.dist-info}/RECORD

@@ -1,4 +1,4 @@
-mindsdb/__about__.py,sha256=cXoHk72JCuA2YGQFO8tg_9d1m4nY9k7CitOwdgLfyKY,444
+mindsdb/__about__.py,sha256=uLW9FOsa76914MCeZsPLrQCq8Xx-uChOe89R4xgef8g,444
 mindsdb/__init__.py,sha256=fZopLiAYa9MzMZ0d48JgHc_LddfFKDzh7n_8icsjrVs,54
 mindsdb/__main__.py,sha256=VQ3RetGs34NhFRT9d76o5S3UpKxdr-G3c0138kz3f8Y,21435
 mindsdb/api/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -66,7 +66,7 @@ mindsdb/api/http/namespaces/analysis.py,sha256=Dp3izdLkG35cSAKNUPJfuGoFSRe34CzFP
 mindsdb/api/http/namespaces/auth.py,sha256=Qm1ZUBdbv_nTDzSQHdzXEosdpYCRzIa17k1yYErOeuk,5483
 mindsdb/api/http/namespaces/chatbots.py,sha256=9UBguchWd04wfYCrsNcFkkt0RCbg-eJcv79RIcJa5Zk,11738
 mindsdb/api/http/namespaces/config.py,sha256=msgxhD9pBnit1w7WD4OYWaq-YtgNCzraxN7ibAvcGcU,9880
-mindsdb/api/http/namespaces/databases.py,sha256=WlEBulLFPLtpQXGvnHR9a0r5nHGFhq44OgQPdu8TyxM,16016
+mindsdb/api/http/namespaces/databases.py,sha256=HAr2pvEuj3n2t1Wmxje0ZsSRxrY3sz9k_MGQ-yvgYWg,18570
 mindsdb/api/http/namespaces/default.py,sha256=r8PXn00Um2eyKB5e_Kj7fzk4e4LYH-JCzXCpxgJA2vY,4729
 mindsdb/api/http/namespaces/file.py,sha256=u6xYa_moAMb0UXWGkNtErGw9nk-FbloRuLHrLCANjoU,6644
 mindsdb/api/http/namespaces/handlers.py,sha256=zRWZvPOplwSAbKDKeQz93J38TsCQT89-GSlSug6Mtug,7911
@@ -607,11 +607,11 @@ mindsdb/integrations/handlers/faunadb_handler/tests/__init__.py,sha256=47DEQpj8H
 mindsdb/integrations/handlers/faunadb_handler/tests/test_faunadb_handler.py,sha256=JrgVIq6jucZjUCr8FpbC9ByJ3WdZGppZKHdovvFbNiw,1151
 mindsdb/integrations/handlers/file_handler/__about__.py,sha256=UavP5jJ_xWIaJ0oRsEANLulczZ0craaUb3XLfCSBmEc,331
 mindsdb/integrations/handlers/file_handler/__init__.py,sha256=46Hnm3ijRsYw95BkkBxHJK8k4h_2Te0j1W0r3-ptVCg,329
-mindsdb/integrations/handlers/file_handler/file_handler.py,sha256=r2EJh31dGygn6T6uiIDEQ1AStYeoExPOu-BF114kHmc,7638
+mindsdb/integrations/handlers/file_handler/file_handler.py,sha256=atOboSG8pcMwnHCsxTzT1vtr92LqYgCcMyqt3hjhO2w,7148
 mindsdb/integrations/handlers/file_handler/icon.svg,sha256=hsXEvUzrO7WQMOPC83LYQt-FW0wey9TCj5EwiIJwKwk,565
 mindsdb/integrations/handlers/file_handler/requirements.txt,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 mindsdb/integrations/handlers/file_handler/tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-mindsdb/integrations/handlers/file_handler/tests/test_file_handler.py,sha256=zc4QU4knxYLNVRq-kKKTwaJqquDeisLvw9DDnDzLuBY,11866
+mindsdb/integrations/handlers/file_handler/tests/test_file_handler.py,sha256=UubwfvgJFe7aSZxpzPGcJ32bvMUE72VnxUJB3RqmSZo,11743
 mindsdb/integrations/handlers/file_handler/tests/data/test.txt,sha256=SUG2Uw_Hmth51gyaCJyeyfAbFssHfsB3qWFcxBX_W1g,570
 mindsdb/integrations/handlers/financial_modeling_prep_handler/__about__.py,sha256=Dz6gPZVoxWJqMgte07pkMKtQq42u7qYtCiaxdHVgANw,392
 mindsdb/integrations/handlers/financial_modeling_prep_handler/__init__.py,sha256=AncBNXt6EECSYDNTlnkxkQ3_dfgEITMKaUUWjV-KSMY,537
@@ -1033,7 +1033,7 @@ mindsdb/integrations/handlers/ms_one_drive_handler/__init__.py,sha256=vraI6WlfpN
 mindsdb/integrations/handlers/ms_one_drive_handler/icon.svg,sha256=52dL1SJWSi44Z2hQUMEyyP8DUmhgUtjvsfN3HU2EBes,2430
 mindsdb/integrations/handlers/ms_one_drive_handler/ms_graph_api_one_drive_client.py,sha256=q3Qd-9bBYacurH_rV5cYpLUgrI0kvSHGSDoi_OnkeWY,3508
 mindsdb/integrations/handlers/ms_one_drive_handler/ms_one_drive_handler.py,sha256=8Xi8rKFWpEsDw5mzqgR7IW4wEbk-TBNqNqOj4350gL4,9333
-mindsdb/integrations/handlers/ms_one_drive_handler/ms_one_drive_tables.py,sha256=_Lq02LB_4swYjmxiWX6i-K4sUtpHuI7-Njhzy_LY2zA,2791
+mindsdb/integrations/handlers/ms_one_drive_handler/ms_one_drive_tables.py,sha256=rBD6sEli8XP-cxTogFu2J7ScO_WTw1gM-6gZm2P8lsc,2802
 mindsdb/integrations/handlers/ms_teams_handler/__about__.py,sha256=CqqxMr2iXyNXzPfcrMnDpK7u7gC6tmYPkOYR3KBXgQM,357
 mindsdb/integrations/handlers/ms_teams_handler/__init__.py,sha256=btEl5YvlZMkMn3NR6eChKtfT31OQY1LBEII1qJ4hf7g,518
 mindsdb/integrations/handlers/ms_teams_handler/icon.svg,sha256=pso2BBOFF2aiAw28W9lBPnvnVeNib21kvrqfZnO_C0M,3934
@@ -1530,7 +1530,7 @@ mindsdb/integrations/handlers/tidb_handler/tests/test_tidb_handler.py,sha256=2jW
 mindsdb/integrations/handlers/timegpt_handler/__about__.py,sha256=wBHyAM5O7yWVgUKBGJwRM6gpy8FUWzcBxL048e4yjhA,390
 mindsdb/integrations/handlers/timegpt_handler/__init__.py,sha256=lMvw91ghkXJj2RuXSi1om4KYc8xbNik3YwXcYA-Hld8,491
 mindsdb/integrations/handlers/timegpt_handler/icon.svg,sha256=CfkLqkeZTKSjsQMKTx_KqkCqXvnHRyAAa1DVs-R1qiA,590
-mindsdb/integrations/handlers/timegpt_handler/requirements.txt,sha256=vvCmrZlyKlVJH4KzFoegYd5NFsP6hjYaMTZo8MEQGlY,14
+mindsdb/integrations/handlers/timegpt_handler/requirements.txt,sha256=AfBYvR80CShVm2CPUOonQgDHgcTxApeX5OTKgfkjB-I,14
 mindsdb/integrations/handlers/timegpt_handler/timegpt_handler.py,sha256=rdAQhmGP_hqguShfHPNj5r5pBXZEla8A-4ErTQ0_LbY,9868
 mindsdb/integrations/handlers/timescaledb_handler/__about__.py,sha256=joUHMPBAiylB7Uc7sipeFVWlWDZ_wqVqyyy_MivkNFI,355
 mindsdb/integrations/handlers/timescaledb_handler/__init__.py,sha256=ynMpLqCRlYomZEFEinXmtYYGr0DPIMQZ9HtsytOpe6c,497
@@ -1714,7 +1714,7 @@ mindsdb/integrations/utilities/datasets/dataset.py,sha256=HjxaMAPuos3HaMsVsAm3q-
 mindsdb/integrations/utilities/datasets/question_answering/fda_style_qa.csv,sha256=uEOevZwKVjtPScjDVvWfTl4VLvDrhL7D9_9DoRJu7ic,6906
 mindsdb/integrations/utilities/datasets/question_answering/squad_v2_val_100_sample.csv,sha256=erj_BGVabfxDFi9TbTXSJ-OiixHRYnDzoJUJcWWeeQY,104035
 mindsdb/integrations/utilities/files/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-mindsdb/integrations/utilities/files/file_reader.py,sha256=Qb43LJY-Kbe6kyL63OFQcpvCmzBPiwtXOcKxUarUJe0,9794
+mindsdb/integrations/utilities/files/file_reader.py,sha256=MwityIR28k3lrLQeVxOufRNlATHDMihedLtqB8YhuBQ,11219
 mindsdb/integrations/utilities/handlers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 mindsdb/integrations/utilities/handlers/api_utilities/__init__.py,sha256=zkvVb54zxtn4_NSwqCD-SVQG_5JI9EYRygb6EABQu7g,43
 mindsdb/integrations/utilities/handlers/api_utilities/microsoft/__init__.py,sha256=xmcg0gXVY4WUIazM-aCjXXFikFonS6hI05GbdEs5_I8,56
@@ -1788,7 +1788,7 @@ mindsdb/interfaces/database/log.py,sha256=tewoKWc-xvfbFC9RVaUUAjQGuRY__Lex8fbR_p
 mindsdb/interfaces/database/projects.py,sha256=0ZjcqpDf437FmRhUk4z8YJR3MaoxtwJH60uPusLbfPU,15077
 mindsdb/interfaces/database/views.py,sha256=CthbUly3OgOyFV8a-VRQwhjLh6I1LXbBUzMAcfu8USI,4404
 mindsdb/interfaces/file/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-mindsdb/interfaces/file/file_controller.py,sha256=9WgvdmPIHG-obJmYO9xVLKbW6tRZm_WkewSNdDR0yoU,4601
+mindsdb/interfaces/file/file_controller.py,sha256=ebe0hEZhOHbrMhVg84XW33Jl1jUeo2uARKGp_NWBkKY,8626
 mindsdb/interfaces/functions/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 mindsdb/interfaces/functions/controller.py,sha256=8kyWA8TnMsRDyIl2s3JcvdGYeww4_Qmf-jYq_wwOYH4,6057
 mindsdb/interfaces/jobs/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -1817,7 +1817,7 @@ mindsdb/interfaces/skills/custom/text2sql/__init__.py,sha256=47DEQpj8HBSa-_TImW-
 mindsdb/interfaces/skills/custom/text2sql/mindsdb_sql_tool.py,sha256=n7r08idG9Qaa0C41HokUf-w72yyACoINOFKGgtNVHLA,1375
 mindsdb/interfaces/skills/custom/text2sql/mindsdb_sql_toolkit.py,sha256=08WyJXYJ_hP7JYLvwaSWuJN6Q1PLgIAvh7bcgsV-0XU,7962
 mindsdb/interfaces/storage/__init__.py,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
-mindsdb/interfaces/storage/db.py,sha256=L-nXGVVkt4izM2VgORfCitLUg3xVup8nwLi7B9PyKCg,19351
+mindsdb/interfaces/storage/db.py,sha256=FDp3E1gqRUL9TJtEBii-g9o_Xdsj1ue7L0pJAwkTtsQ,19413
 mindsdb/interfaces/storage/fs.py,sha256=4Nyo-h23UtZc2nz_LWyVzboC_e1jlU58aph1_en8MdE,21155
 mindsdb/interfaces/storage/json.py,sha256=KdrmXfqVCNZ_anNpfyygcFQeywbdJMCMbaI3HFJic-U,2925
 mindsdb/interfaces/storage/model_fs.py,sha256=LQHyIs3wlOEpFHceAjziA7zuQKY3N-8gt9EuSYHO8zI,8267
@@ -1890,6 +1890,7 @@ mindsdb/migrations/versions/2024-11-19_0f89b523f346_agent_skills_parameters.py,s
 mindsdb/migrations/versions/2024-11-28_a8a3fac369e7_llm_log_json_in_out.py,sha256=1qQl720lynCbtcGqKIbFM0HCo81xIXqz0Hj3dWkH6UI,3174
 mindsdb/migrations/versions/2024-11-29_f6dc924079fa_predictor_training_metadata.py,sha256=nCnp-M3ljIEAO9XTc5mSURp2SX5Q8gE6kyJHp5J5vmo,1322
 mindsdb/migrations/versions/2025-01-15_c06c35f7e8e1_project_company.py,sha256=zJcBGdgBMlt9oI-SbB8C74w-jDf3ZMYlEuO2guwrfZw,1896
+mindsdb/migrations/versions/2025-02-09_4943359e354a_file_metadata.py,sha256=0-QqeVZECfpjKwe86PEwQ9dPgo6Pgmkp_213wTHYiPk,826
 mindsdb/migrations/versions/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 mindsdb/utilities/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 mindsdb/utilities/auth.py,sha256=6ycLJgXySghgFdzK6emxdStElzt5aOPafjDCRR_g_q0,2336
@@ -1929,9 +1930,9 @@ mindsdb/utilities/otel/metric_handlers/__init__.py,sha256=3jGsLt5KkdhqaAUUw8ALxE
 mindsdb/utilities/profiler/__init__.py,sha256=d4VXl80uSm1IotR-WwbBInPmLmACiK0AzxXGBA40I-0,251
 mindsdb/utilities/profiler/profiler.py,sha256=KCUtOupkbM_nCoof9MtiuhUzDGezx4a4NsBX6vGWbPA,3936
 mindsdb/utilities/render/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-mindsdb/utilities/render/sqlalchemy_render.py,sha256=-7iLVSXYcgta3p4Ihf2Si-D4aY2qFaD0b0Ea2wuqAHE,29816
-MindsDB-25.2.2.1.dist-info/LICENSE,sha256=ziqdjujs6WDn-9g3t0SISjHCBc2pLRht3gnRbQoXmIs,5804
-MindsDB-25.2.2.1.dist-info/METADATA,sha256=S1Hbsjgvm1aWQcrmBqYcJnawQIxhg2FjZR3MXXoLI08,42853
-MindsDB-25.2.2.1.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-MindsDB-25.2.2.1.dist-info/top_level.txt,sha256=10wPR96JDf3hM8aMP7Fz0lDlmClEP480zgXISJKr5jE,8
-MindsDB-25.2.2.1.dist-info/RECORD,,
+mindsdb/utilities/render/sqlalchemy_render.py,sha256=Z6bzVfQLqnMTYPJ9X4mZlFdrLmNwxM86yuvO_9TAsq4,30193
+MindsDB-25.2.3.0.dist-info/LICENSE,sha256=ziqdjujs6WDn-9g3t0SISjHCBc2pLRht3gnRbQoXmIs,5804
+MindsDB-25.2.3.0.dist-info/METADATA,sha256=lg683Nqs7NiKayjl8EL9yT4iLN-j059ktmL4Q5-eJWk,42861
+MindsDB-25.2.3.0.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
+MindsDB-25.2.3.0.dist-info/top_level.txt,sha256=10wPR96JDf3hM8aMP7Fz0lDlmClEP480zgXISJKr5jE,8
+MindsDB-25.2.3.0.dist-info/RECORD,,

mindsdb/__about__.py

@@ -1,6 +1,6 @@
 __title__ = 'MindsDB'
 __package_name__ = 'mindsdb'
-__version__ = '25.2.2.1'
+__version__ = '25.2.3.0'
 __description__ = "MindsDB's AI SQL Server enables developers to build AI tools that need access to real-time data to perform their tasks"
 __email__ = "jorge@mindsdb.com"
 __author__ = 'MindsDB Inc'

mindsdb/api/http/namespaces/databases.py

@@ -1,6 +1,9 @@
+from http import HTTPStatus
+import tempfile
 import time
 from typing import Dict
-from http import HTTPStatus
+from pathlib import Path
+import shutil
 from sqlalchemy.exc import NoResultFound
 
 from flask import request
@@ -94,6 +97,71 @@ class DatabasesResource(Resource):
         return new_integration, HTTPStatus.CREATED
 
 
+@ns_conf.route('/status')
+class DatabasesStatusResource(Resource):
+    @ns_conf.doc('check_database_connection_status')
+    @api_endpoint_metrics('POST', '/databases/status')
+    def post(self):
+        '''Check the connection parameters for a database'''
+        data = {}
+        if request.content_type == 'application/json':
+            data.update(request.json or {})
+        elif request.content_type.startswith('multipart/form-data'):
+            data.update(request.form or {})
+
+        if 'engine' not in data:
+            return http_error(
+                HTTPStatus.BAD_REQUEST, 'Wrong argument',
+                'Missing "engine" field for database'
+            )
+
+        engine = data['engine']
+        parameters = data
+        del parameters['engine']
+
+        files = request.files
+        temp_dir = None
+        if files is not None and len(files) > 0:
+            temp_dir = tempfile.mkdtemp(prefix='integration_files_')
+            for key, file in files.items():
+                temp_dir_path = Path(temp_dir)
+                file_name = Path(file.filename)
+                file_path = temp_dir_path.joinpath(file_name).resolve()
+                if temp_dir_path not in file_path.parents:
+                    raise Exception(f'Can not save file at path: {file_path}')
+                file.save(file_path)
+                parameters[key] = str(file_path)
+
+        session = SessionController()
+
+        try:
+            handler = session.integration_controller.create_tmp_handler("test_connection", engine, parameters)
+            status = handler.check_connection()
+        except ImportError as import_error:
+            status = HandlerStatusResponse(success=False, error_message=str(import_error))
+        except Exception as unknown_error:
+            status = HandlerStatusResponse(success=False, error_message=str(unknown_error))
+        finally:
+            if temp_dir is not None:
+                shutil.rmtree(temp_dir)
+
+        if not status.success:
+            if hasattr(status, 'redirect_url') and isinstance(status, str):
+                return {
+                    "status": "redirect_required",
+                    "redirect_url": status.redirect_url,
+                    "detail": status.error_message
+                }, HTTPStatus.OK
+            return {
+                "status": "connection_error",
+                "detail": status.error_message
+            }, HTTPStatus.OK
+
+        return {
+            "status": "success",
+        }, HTTPStatus.OK
+
+
 @ns_conf.route('/<database_name>')
 class DatabaseResource(Resource):
     @ns_conf.doc('get_database')

mindsdb/integrations/handlers/file_handler/file_handler.py

@@ -1,11 +1,10 @@
 import os
 import shutil
 import tempfile
-from pathlib import Path
 
 import pandas as pd
 from mindsdb_sql_parser import parse_sql
-from mindsdb_sql_parser.ast import CreateTable, DropTables, Insert, Select
+from mindsdb_sql_parser.ast import CreateTable, DropTables, Insert, Select, Identifier
 from mindsdb_sql_parser.ast.base import ASTNode
 
 from mindsdb.api.executor.utilities.sql import query_df
@@ -15,8 +14,6 @@ from mindsdb.integrations.libs.response import HandlerResponse as Response
 from mindsdb.integrations.libs.response import HandlerStatusResponse as StatusResponse
 from mindsdb.utilities import log
 
-from mindsdb.integrations.utilities.files.file_reader import FileReader
-
 
 logger = log.getLogger(__name__)
 
@@ -63,6 +60,18 @@ class FileHandler(DatabaseHandler):
     def check_connection(self) -> StatusResponse:
         return StatusResponse(True)
 
+    def _get_table_page_names(self, table: Identifier):
+        table_name_parts = table.parts
+
+        # Check if it's a multi-part name (e.g., `file_name.sheet_name`)
+        if len(table_name_parts) > 1:
+            table_name = table_name_parts[-2]
+            page_name = table_name_parts[-1]  # Get the sheet name
+        else:
+            table_name = table_name_parts[-1]
+            page_name = None
+        return table_name, page_name
+
     def query(self, query: ASTNode) -> Response:
         if type(query) is DropTables:
             for table_identifier in query.tables:
@@ -84,7 +93,7 @@ class FileHandler(DatabaseHandler):
                     )
             return Response(RESPONSE_TYPE.OK)
 
-        if type(query) is CreateTable:
+        if isinstance(query, CreateTable):
             # Check if the table already exists or if the table name contains more than one namespace
             existing_files = self.file_controller.get_files_names()
 
@@ -96,13 +105,13 @@ class FileHandler(DatabaseHandler):
 
             table_name = query.name.parts[-1]
             if table_name in existing_files:
-                return Response(
-                    RESPONSE_TYPE.ERROR,
-                    error_message=f"Table '{table_name}' already exists",
-                )
-
-            if query.is_replace:
-                self.file_controller.delete_file(table_name)
+                if query.is_replace:
+                    self.file_controller.delete_file(table_name)
+                else:
+                    return Response(
+                        RESPONSE_TYPE.ERROR,
+                        error_message=f"Table '{table_name}' already exists",
+                    )
 
             temp_dir_path = tempfile.mkdtemp(prefix="mindsdb_file_")
 
@@ -126,31 +135,19 @@ class FileHandler(DatabaseHandler):
 
             return Response(RESPONSE_TYPE.OK)
 
-        elif type(query) is Select:
-            table_name_parts = query.from_table.parts
-            table_name = table_name_parts[-1]
-
-            # Check if it's a multi-part name (e.g., `files.file_name.sheet_name`)
-            if len(table_name_parts) > 1:
-                table_name = table_name_parts[-2]
-                sheet_name = table_name_parts[-1]  # Get the sheet name
-            else:
-                sheet_name = None
-            file_path = self.file_controller.get_file_path(table_name)
+        elif isinstance(query, Select):
+            table_name, page_name = self._get_table_page_names(query.from_table)
 
-            df = self.handle_source(file_path, sheet_name=sheet_name)
+            df = self.file_controller.get_file_data(table_name, page_name)
 
             # Process the SELECT query
             result_df = query_df(df, query)
             return Response(RESPONSE_TYPE.TABLE, data_frame=result_df)
 
-        elif type(query) is Insert:
-            table_name = query.table.parts[-1]
-            file_path = self.file_controller.get_file_path(table_name)
+        elif isinstance(query, Insert):
+            table_name, page_name = self._get_table_page_names(query.table)
 
-            file_reader = FileReader(path=file_path)
-
-            df = file_reader.to_df()
+            df = self.file_controller.get_file_data(table_name, page_name)
 
             # Create a new dataframe with the values from the query
             new_df = pd.DataFrame(query.values, columns=[col.name for col in query.columns])
@@ -158,10 +155,7 @@ class FileHandler(DatabaseHandler):
             # Concatenate the new dataframe with the existing one
             df = pd.concat([df, new_df], ignore_index=True)
 
-            # Write the concatenated data to the file based on its format
-            format = Path(file_path).suffix.strip(".").lower()
-            write_method = getattr(df, f"to_{format}")
-            write_method(file_path, index=False)
+            self.file_controller.set_file_data(table_name, df, page_name=page_name)
 
             return Response(RESPONSE_TYPE.OK)
 
@@ -175,18 +169,6 @@ class FileHandler(DatabaseHandler):
         ast = self.parser(query)
         return self.query(ast)
 
-    @staticmethod
-    def handle_source(file_path, **kwargs):
-        file_reader = FileReader(path=file_path)
-
-        df = file_reader.to_df(**kwargs)
-
-        header = df.columns.values.tolist()
-
-        df.columns = [key.strip() for key in header]
-        df = df.applymap(clean_cell)
-        return df
-
     def get_tables(self) -> Response:
         """
         List all files

mindsdb/integrations/handlers/file_handler/tests/test_file_handler.py

@@ -64,6 +64,12 @@ class MockFileController:
     def save_file(self, name, file_path, file_name=None):
         return True
 
+    def get_file_data(self, name, page_name=None):
+        return pandas.DataFrame(test_file_content[1:], columns=test_file_content[0])
+
+    def set_file_data(self, name, df, page_name=None):
+        return True
+
 
 def curr_dir():
     return os.path.dirname(os.path.realpath(__file__))
@@ -296,18 +302,9 @@ def test_handle_source(file_path, expected_columns):
 
     # using different methods to create reader
     for reader in get_reader(file_path):
-        df = reader.to_df()
+        df = reader.get_page_content()
         assert isinstance(df, pandas.DataFrame)
 
-        if reader.get_format() == 'xlsx':
-
-            assert df.columns.tolist() == test_excel_sheet_content[0]
-            assert len(df) == len(test_excel_sheet_content) - 1
-            assert df.values.tolist() == test_excel_sheet_content[1:]
-            sheet_name = test_excel_sheet_content[1][0]
-
-            df = reader.to_df(sheet_name=sheet_name)
-
         assert df.columns.tolist() == expected_columns
 
         # The pdf and txt files have some different content
@@ -336,7 +333,7 @@ def test_tsv():
     assert reader.get_format() == 'csv'
     assert reader.parameters['delimiter'] == '\t'
 
-    df = reader.to_df()
+    df = reader.get_page_content()
     assert len(df.columns) == 2
 
 

mindsdb/integrations/handlers/ms_one_drive_handler/ms_one_drive_tables.py

@@ -87,4 +87,4 @@ class FileTable(APIResource):
 
         reader = FileReader(file=BytesIO(file_content), name=table_name)
 
-        return reader.to_df()
+        return reader.get_page_content()

mindsdb/integrations/handlers/timegpt_handler/requirements.txt

@@ -1 +1 @@
-nixtla==0.5.0
+nixtla==0.6.6

mindsdb/integrations/utilities/files/file_reader.py

@@ -4,6 +4,7 @@ import csv
 from io import BytesIO, StringIO, IOBase
 from pathlib import Path
 import codecs
+from typing import List
 
 import filetype
 import pandas as pd
@@ -65,6 +66,7 @@ def decode(file_obj: IOBase) -> StringIO:
 class FormatDetector:
 
     supported_formats = ['parquet', 'csv', 'xlsx', 'pdf', 'json', 'txt']
+    multipage_formats = ['xlsx']
 
     def __init__(
         self,
@@ -200,16 +202,62 @@ class FormatDetector:
 
 class FileReader(FormatDetector):
 
-    def to_df(self, **kwargs) -> pd.DataFrame:
+    def _get_fnc(self):
         format = self.get_format()
-
         func = getattr(self, f'read_{format}', None)
         if func is None:
             raise FileDetectError(f'Unsupported format: {format}')
+        return func
+
+    def get_pages(self, **kwargs) -> List[str]:
+        """
+            Get list of tables in file
+        """
+        format = self.get_format()
+        if format not in self.multipage_formats:
+            # only one table
+            return ['main']
+
+        func = self._get_fnc()
+        self.file_obj.seek(0)
 
+        return [
+            name for name, _ in
+            func(self.file_obj, only_names=True, **kwargs)
+        ]
+
+    def get_contents(self, **kwargs):
+        """
+            Get all info(pages with content) from file as dict: {tablename, content}
+        """
+        func = self._get_fnc()
         self.file_obj.seek(0)
-        kwargs.update(self.parameters)
-        return func(self.file_obj, name=self.name, **kwargs)
+
+        format = self.get_format()
+        if format not in self.multipage_formats:
+            # only one table
+            return {'main': func(self.file_obj, name=self.name, **kwargs)}
+
+        return {
+            name: df
+            for name, df in
+            func(self.file_obj, **kwargs)
+        }
+
+    def get_page_content(self, page_name: str = None, **kwargs) -> pd.DataFrame:
+        """
+            Get content of a single table
+        """
+        func = self._get_fnc()
+        self.file_obj.seek(0)
+
+        format = self.get_format()
+        if format not in self.multipage_formats:
+            # only one table
+            return func(self.file_obj, name=self.name, **kwargs)
+
+        for _, df in func(self.file_obj, name=self.name, page_name=page_name, **kwargs):
+            return df
 
     @staticmethod
     def _get_csv_dialect(buffer, delimiter=None) -> csv.Dialect:
@@ -304,14 +352,18 @@ class FileReader(FormatDetector):
         return pd.read_parquet(file_obj)
 
     @staticmethod
-    def read_xlsx(file_obj: BytesIO, sheet_name=None, **kwargs) -> pd.DataFrame:
-
-        file_obj.seek(0)
+    def read_xlsx(file_obj: BytesIO, page_name=None, only_names=False, **kwargs):
         with pd.ExcelFile(file_obj) as xls:
-            if sheet_name is None:
-                # No sheet specified: Return list of sheets
-                sheet_list = xls.sheet_names
-                return pd.DataFrame(sheet_list, columns=["Sheet_Name"])
-            else:
-                # Specific sheet requested: Load that sheet
-                return pd.read_excel(xls, sheet_name=sheet_name)
+
+            if page_name is not None:
+                # return specific page
+                yield page_name, pd.read_excel(xls, sheet_name=page_name)
+
+            for page_name in xls.sheet_names:
+
+                if only_names:
+                    # extract only pages names
+                    df = None
+                else:
+                    df = pd.read_excel(xls, sheet_name=page_name)
+                yield page_name, df