luxorasap 0.1.38__tar.gz → 0.1.39__tar.gz

{luxorasap-0.1.38 → luxorasap-0.1.39}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: luxorasap
-Version: 0.1.38
+Version: 0.1.39
 Summary: Toolbox da Luxor para ingestão, análise e automação de dados financeiros.
 Author-email: Luxor Group <backoffice@luxor.com.br>
 License: Proprietary – All rights reserved

{luxorasap-0.1.38 → luxorasap-0.1.39}/pyproject.toml

@@ -10,7 +10,7 @@ build-backend = "setuptools.build_meta"
 #############################
 [project]
 name            = "luxorasap"
-version = "0.1.38"
+version = "0.1.39"
 description     = "Toolbox da Luxor para ingestão, análise e automação de dados financeiros."
 readme          = "README.md"
 requires-python = ">=3.9"
@@ -78,7 +78,7 @@ exclude = ["tests*"]
 # bumpver (sem-ver)
 #############################
 [tool.bumpver]
-current_version = "0.1.38"
+current_version = "0.1.39"
 version_pattern = "MAJOR.MINOR.PATCH"
 
 # regex explícito – obrigatório no bumpver 2024+

{luxorasap-0.1.38 → luxorasap-0.1.39}/src/luxorasap/__init__.py

@@ -13,7 +13,7 @@ from types import ModuleType
 try:
     __version__: str = metadata.version(__name__)
 except metadata.PackageNotFoundError:  # editable install
-    __version__ = "0.1.38"
+    __version__ = "0.1.39"
 
 # ─── Lazy loader ─────────────────────────────────────────────────
 def __getattr__(name: str) -> ModuleType:

{luxorasap-0.1.38 → luxorasap-0.1.39}/src/luxorasap/datareader/core.py

@@ -24,12 +24,15 @@ load_dotenv()
 #@logger.catch
 class LuxorQuery:
 
-    def __init__(self, update_mode="optimized", is_develop_mode=False, tables_path=None, 
-                 blob_directory='enriched/parquet', adls_connection_string:str=None, container_name="luxorasap"):
+    # Criando construtor com docstring detalhada
+    def __init__(self, blob_directory='enriched/parquet', adls_connection_string:str=None, 
+                 container_name="luxorasap"):
         """
-            update_mode: 
-                'standard' - Carrega todas as tabelas disponiveis
-                'optimized' - Carrega apenas as tabelas utilizadas sob demanda
+        Classe para consulta de dados da Luxor.
+        Args:
+            blob_directory (str, optional): Diretório no blob onde estão as tabelas. Defaults to 'enriched/parquet'.
+            adls_connection_string (str, optional): String de conexão com o ADLS. Se None, usa variável de ambiente. Defaults to None.
+            container_name (str, optional): Nome do container no blob. Defaults to "luxorasap".
         """
             
         self.blob_client = BlobParquetClient(adls_connection_string=adls_connection_string,
@@ -38,10 +41,8 @@ class LuxorQuery:
 
         
         self.modified_tables = []
-        self.is_develop_mode = is_develop_mode
         
-
-        self.tables_path = tables_path
+        
         #if tables_path is None:
         #    self.tables_path = self.__set_tables_path()
 
@@ -54,8 +55,6 @@ class LuxorQuery:
         self.lipi_manga_incorp_date = dt.date(2022,12,9)
         
 
-        self.update_modes_name = {"standard" : 0, "optimized" : 1}
-        self.update_mode = self.update_modes_name[update_mode]
         self.update() # Nessa 1° exec. vai inicializar os dicionarios acima
 
 

{luxorasap-0.1.38 → luxorasap-0.1.39}/src/luxorasap/ingest/cloud/__init__.py

@@ -4,7 +4,7 @@ import pandas as pd
 import datetime as dt
 import numpy as np
 
-from luxorasap.utils.storage import BlobParquetClient
+from luxorasap.utils.storage import BlobParquetClient, BlobExcelClient, BlobPickleClient
 from luxorasap.utils.dataframe import prep_for_save, astype_str_inplace
 from luxorasap.datareader import LuxorQuery
 
@@ -12,6 +12,8 @@ from luxorasap.datareader import LuxorQuery
 __all__ = ["save_table", "incremental_load"]
 
 _client = BlobParquetClient()   # instância única para o módulo
+_client_excel = None
+_client_pickle = None
 
 
 # ────────────────────────────────────────────────────────────────
@@ -23,7 +25,8 @@ def save_table(
     index_name: str = "index",
     normalize_columns: bool = True,
     directory: str = "enriched/parquet",
-    override=False
+    override=False,
+    format='parquet'
 ):
     """Salva DataFrame como Parquet em ADLS (sobrescrevendo)."""
     
@@ -43,9 +46,27 @@ def save_table(
     
     df = prep_for_save(df, index=index, index_name=index_name, normalize=normalize_columns)
     
-    #_client.write_df(df.astype(str), f"{directory}/{table_name}.parquet")
-    astype_str_inplace(df)
-    _client.write_df(df, f"{directory}/{table_name}.parquet")
+    if format == 'parquet':
+        #_client.write_df(df.astype(str), f"{directory}/{table_name}.parquet")
+        astype_str_inplace(df)
+        _client.write_df(df, f"{directory}/{table_name}.parquet")
+    
+    elif format == 'excel':
+        global _client_excel
+        if _client_excel is None:
+            _client_excel = BlobExcelClient()
+        if index:
+            df = df.reset_index().rename(columns={"index": index_name})
+        _client_excel.write_excel(df, f"{directory}/{table_name}.xlsx")
+    
+    elif format == 'pickle':
+        global _client_pickle
+        if _client_pickle is None:
+            _client_pickle = BlobPickleClient()
+        _client_pickle.write_pickle(df, f"{directory}/{table_name}.pkl")
+    
+    else:
+        raise ValueError(f"Formato '{format}' não suportado. Use 'parquet', 'excel' ou 'pickle'.")
 
 
 

luxorasap-0.1.39/src/luxorasap/utils/storage/__init__.py

@@ -0,0 +1,2 @@
+from .blob import BlobParquetClient, BlobPickleClient, BlobExcelClient, delete_blob, list_blob_files
+__all__ = ["BlobParquetClient", "BlobPickleClient", "BlobExcelClient", "delete_blob", "list_blob_files"]

luxorasap-0.1.39/src/luxorasap/utils/storage/blob.py

@@ -0,0 +1,263 @@
+import io, os
+from pathlib import PurePosixPath
+from datetime import timezone
+import pandas as pd
+import pyarrow as pa, pyarrow.parquet as pq
+import pickle
+import re
+
+from azure.storage.blob import BlobServiceClient
+from azure.core.exceptions import ResourceNotFoundError
+
+from ..dataframe import read_bytes
+
+
+class BlobParquetClient:
+    """Leitura/gravacao de Parquet em Azure Blob – stateless & reutilizável."""
+
+    def __init__(self, container: str = "luxorasap", adls_connection_string: str = None):
+        if adls_connection_string is None:
+            adls_connection_string = os.getenv('AZURE_STORAGE_CONNECTION_STRING')
+
+        if adls_connection_string is None:
+            raise RuntimeError("AZURE_STORAGE_CONNECTION_STRING not set")
+        self._svc = BlobServiceClient.from_connection_string(adls_connection_string)
+        self._container = container
+
+    # ---------- API pública ----------
+    def read_df(self, blob_path: str) -> (pd.DataFrame, bool):
+        buf = io.BytesIO()
+        try:
+            self._blob(blob_path).download_blob().readinto(buf)
+            return (
+                read_bytes(buf.getvalue(), filename=PurePosixPath(blob_path).name),
+                True,
+            )
+        except Exception:
+            return None, False
+            
+
+    def write_df(self, df, blob_path: str):
+        
+        blob = self._blob(blob_path)
+        table = pa.Table.from_pandas(df)
+        buf = io.BytesIO()
+        pq.write_table(table, buf)
+        buf.seek(0)
+        blob.upload_blob(buf, overwrite=True)
+            
+        
+    def get_df_update_time(self, blob_path: str) -> float:
+        try:
+            properties = self._blob(blob_path).get_blob_properties()
+            return properties['last_modified'].replace(tzinfo=timezone.utc).timestamp()
+        except Exception:
+            return 0.0
+    
+    
+    def exists_df(self, blob_path: str) -> bool:
+        try:
+            self._blob(blob_path).get_blob_properties()
+            return True
+        except Exception:
+            return False
+
+
+    def list_blob_files(self, blob_path: str, ends_with: str = None) -> list:
+        """
+        Lista os arquivos em um diretório do blob storage.
+
+        Args:
+            blob_path (str): O caminho do diretório no blob storage.
+            ends_with (str, optional): Filtra os arquivos que terminam com esta string.(Ex.: '.parquet')
+
+        Returns:
+            list: Uma lista de nomes de blob.
+            
+        """
+        try:
+            container_client = self._svc.get_container_client(self._container)
+            blob_list = container_client.list_blobs(name_starts_with=blob_path)
+            if ends_with:
+                return [blob.name for blob in blob_list if blob.name.endswith(ends_with)]
+            return [blob.name for blob in blob_list]
+        except Exception:
+            return []
+            
+
+    def table_exists(self, table_path: str) -> bool:
+        """
+            Checa se uma tabela existe no blob storage.
+        """
+        return self.exists_df(table_path)
+    
+    
+    # ---------- interno --------------
+    def _blob(self, path: str):
+        path = str(PurePosixPath(path))
+        return self._svc.get_blob_client(self._container, path)
+    
+
+class BlobPickleClient:
+    def __init__(self, *, adls_connection_string: str = None, container: str = "luxorasap"):
+        if adls_connection_string is None:
+            adls_connection_string = os.getenv("AZURE_STORAGE_CONNECTION_STRING")
+            
+        if adls_connection_string is None:
+            raise RuntimeError("AZURE_STORAGE_CONNECTION_STRING not set")
+        
+        self._svc = BlobServiceClient.from_connection_string(adls_connection_string)
+        self._container = self._svc.get_container_client(container)
+
+
+    def write_pickle(self, obj, blob_name: str):
+        """Salva objeto Python (ex: DataFrame) como pickle no blob"""
+        buf = io.BytesIO()
+        pickle.dump(obj, buf)
+        buf.seek(0)
+        self._container.upload_blob(name=blob_name, data=buf, overwrite=True)
+
+
+    def read_pickle(self, blob_name: str):
+        """Lê pickle do blob e retorna objeto Python"""
+        downloader = self._container.download_blob(blob_name)
+        buf = io.BytesIO(downloader.readall())
+        return pickle.load(buf)
+
+
+    def exists(self, blob_name: str) -> bool:
+        return self._container.get_blob_client(blob_name).exists()
+    
+    
+
+class BlobExcelClient:
+    def __init__(self, *, adls_connection_string: str = None, container: str = "luxorasap"):
+        if adls_connection_string is None:
+            adls_connection_string = os.getenv("AZURE_STORAGE_CONNECTION_STRING")
+        
+        if adls_connection_string is None:
+            raise RuntimeError("AZURE_STORAGE_CONNECTION_STRING not set")
+            
+        self._svc = BlobServiceClient.from_connection_string(adls_connection_string)
+        self._container = self._svc.get_container_client(container)
+
+
+    def write_excel(self, df: pd.DataFrame, blob_name: str, **kwargs):
+        """
+        Salva um DataFrame como arquivo Excel no blob.
+
+        Args:
+            df (pd.DataFrame): DataFrame a ser salvo
+            blob_name (str): caminho/nome do blob (ex: "reports/test.xlsx")
+            **kwargs: argumentos extras para `DataFrame.to_excel`
+        """
+        buf = io.BytesIO()
+        df.to_excel(buf, index=False, engine="openpyxl", **kwargs)
+        buf.seek(0)
+        self._container.upload_blob(name=blob_name, data=buf, overwrite=True)
+
+
+    def read_excel(self, blob_name: str, **kwargs) -> pd.DataFrame:
+        """
+        Lê um arquivo Excel do blob e retorna um DataFrame.
+
+        Args:
+            blob_name (str): caminho/nome do blob (ex: "reports/test.xlsx")
+            **kwargs: argumentos extras para `pd.read_excel`
+
+        Returns:
+            pd.DataFrame
+        """
+        downloader = self._container.download_blob(blob_name)
+        buf = io.BytesIO(downloader.readall())
+        return pd.read_excel(buf, engine="openpyxl", **kwargs)
+
+    def exists(self, blob_name: str) -> bool:
+        return self._container.get_blob_client(blob_name).exists()
+    
+ 
+    
+def list_blob_files(blob_path: str, container="luxorasap", ends_with: str = None, adls_connection_string: str = None) -> list:
+    """
+    Lista os arquivos em um diretório do blob storage.
+
+    Args:
+        blob_path (str): O caminho do diretório no blob storage.
+        ends_with (str, optional): Filtra os arquivos que terminam com esta string.(Ex.: '.parquet')
+
+    Returns:
+        list: Uma lista de nomes de blob.
+        
+    """
+    
+    if adls_connection_string is None:
+        adls_connection_string = os.getenv("AZURE_STORAGE_CONNECTION_STRING")
+    if adls_connection_string is None:
+        raise RuntimeError("AZURE_STORAGE_CONNECTION_STRING not set")
+    
+    try:
+        svc  = BlobServiceClient.from_connection_string(adls_connection_string)
+        container_client = svc.get_container_client(container)
+        blob_list = container_client.list_blobs(name_starts_with=blob_path)
+        if ends_with:
+            return [blob.name for blob in blob_list if blob.name.endswith(ends_with)]
+        return [blob.name for blob in blob_list]
+    except Exception:
+        return []
+        
+
+def delete_blob(
+    blob_name: str,
+    *,
+    adls_connection_string: str | None = None,
+    container: str = "luxorasap",
+    include_snapshots: bool = False,
+) -> None:
+    """
+    Exclui com segurança APENAS um arquivo (blob) exato do Azure Blob Storage.
+
+    Regras de segurança:
+      - Recusa nomes que terminem com "/" (prefixos de diretório virtual).
+      - Recusa curingas/shell globs (*, ?, []), para evitar exclusões indevidas.
+      - Verifica a existência do blob exato antes de remover.
+
+    Args:
+        blob_name: Caminho EXATO do blob (ex.: "enriched/parquet/tabela.parquet").
+        adls_connection_string: Se None, lê de AZURE_STORAGE_CONNECTION_STRING.
+        container: Nome do container.
+        include_snapshots: Se True, apaga snapshots vinculados ao blob.
+
+    Raises:
+        ValueError: Se o nome parecer um diretório/prefixo ou contiver curingas.
+        FileNotFoundError: Se o blob exato não existir.
+        RuntimeError: Se a conexão com o Azure não estiver configurada.
+    """
+    if adls_connection_string is None:
+        adls_connection_string = os.getenv("AZURE_STORAGE_CONNECTION_STRING")
+    if adls_connection_string is None:
+        raise RuntimeError("AZURE_STORAGE_CONNECTION_STRING not set")
+    
+    # 1) Bloqueios contra “diretórios” e curingas
+    if blob_name.endswith("/"):
+        raise ValueError("Nome termina com '/': recusa exclusão de diretórios/prefixos.")
+    if re.search(r"[\*\?\[\]]", blob_name):
+        raise ValueError("Curingas encontrados no nome do blob. Informe um arquivo exato.")
+
+    svc = BlobServiceClient.from_connection_string(adls_connection_string)
+    container_client = svc.get_container_client(container)
+    blob_client = container_client.get_blob_client(blob_name)
+
+    # 2) Checa existência do blob exato
+    try:
+        blob_client.get_blob_properties()
+    except ResourceNotFoundError:
+        raise FileNotFoundError(f"Blob não encontrado: {blob_name}")
+
+    # 3) Exclui apenas o alvo exato
+    delete_kwargs = {}
+    if include_snapshots:
+        delete_kwargs["delete_snapshots"] = "include"
+
+    blob_client.delete_blob(**delete_kwargs)
+
+    

{luxorasap-0.1.38 → luxorasap-0.1.39}/src/luxorasap.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: luxorasap
-Version: 0.1.38
+Version: 0.1.39
 Summary: Toolbox da Luxor para ingestão, análise e automação de dados financeiros.
 Author-email: Luxor Group <backoffice@luxor.com.br>
 License: Proprietary – All rights reserved

luxorasap-0.1.38/src/luxorasap/utils/storage/__init__.py

@@ -1,2 +0,0 @@
-from .blob import BlobParquetClient, BlobPickleClient
-__all__ = ["BlobParquetClient", "BlobPickleClient"]

luxorasap-0.1.38/src/luxorasap/utils/storage/blob.py

@@ -1,124 +0,0 @@
-import io, os
-from pathlib import PurePosixPath
-from datetime import timezone
-import pandas as pd
-import pyarrow as pa, pyarrow.parquet as pq
-from azure.storage.blob import BlobServiceClient
-import pickle
-
-from ..dataframe import read_bytes
-
-
-class BlobParquetClient:
-    """Leitura/gravacao de Parquet em Azure Blob – stateless & reutilizável."""
-
-    def __init__(self, container: str = "luxorasap", adls_connection_string: str = None):
-        if adls_connection_string is None:
-            adls_connection_string = os.getenv('AZURE_STORAGE_CONNECTION_STRING')
-
-        if adls_connection_string is None:
-            raise RuntimeError("AZURE_STORAGE_CONNECTION_STRING not set")
-        self._svc = BlobServiceClient.from_connection_string(adls_connection_string)
-        self._container = container
-
-    # ---------- API pública ----------
-    def read_df(self, blob_path: str) -> (pd.DataFrame, bool):
-        buf = io.BytesIO()
-        try:
-            self._blob(blob_path).download_blob().readinto(buf)
-            return (
-                read_bytes(buf.getvalue(), filename=PurePosixPath(blob_path).name),
-                True,
-            )
-        except Exception:
-            return None, False
-            
-
-    def write_df(self, df, blob_path: str):
-        
-        blob = self._blob(blob_path)
-        table = pa.Table.from_pandas(df)
-        buf = io.BytesIO()
-        pq.write_table(table, buf)
-        buf.seek(0)
-        blob.upload_blob(buf, overwrite=True)
-            
-        
-    def get_df_update_time(self, blob_path: str) -> float:
-        try:
-            properties = self._blob(blob_path).get_blob_properties()
-            return properties['last_modified'].replace(tzinfo=timezone.utc).timestamp()
-        except Exception:
-            return 0.0
-    
-    
-    def exists_df(self, blob_path: str) -> bool:
-        try:
-            self._blob(blob_path).get_blob_properties()
-            return True
-        except Exception:
-            return False
-
-
-    def list_blob_files(self, blob_path: str, ends_with: str = None) -> list:
-        """
-        Lista os arquivos em um diretório do blob storage.
-
-        Args:
-            blob_path (str): O caminho do diretório no blob storage.
-            ends_with (str, optional): Filtra os arquivos que terminam com esta string.(Ex.: '.parquet')
-
-        Returns:
-            list: Uma lista de nomes de blob.
-            
-        """
-        try:
-            container_client = self._svc.get_container_client(self._container)
-            blob_list = container_client.list_blobs(name_starts_with=blob_path)
-            if ends_with:
-                return [blob.name for blob in blob_list if blob.name.endswith(ends_with)]
-            return [blob.name for blob in blob_list]
-        except Exception:
-            return []
-            
-
-    def table_exists(self, table_path: str) -> bool:
-        """
-            Checa se uma tabela existe no blob storage.
-        """
-        return self.exists_df(table_path)
-    
-    
-    # ---------- interno --------------
-    def _blob(self, path: str):
-        path = str(PurePosixPath(path))
-        return self._svc.get_blob_client(self._container, path)
-    
-
-class BlobPickleClient:
-    def __init__(self, *, adls_connection_string: str = None, container: str = "luxorasap"):
-        if adls_connection_string is None:
-            adls_connection_string = os.getenv("AZURE_STORAGE_CONNECTION_STRING")
-            
-        if adls_connection_string is None:
-            raise RuntimeError("AZURE_STORAGE_CONNECTION_STRING not set")
-        
-        self.blob_service_client = BlobServiceClient.from_connection_string(adls_connection_string)
-        self.container_client = self.blob_service_client.get_container_client(container)
-
-    def write_pickle(self, obj, blob_name: str):
-        """Salva objeto Python (ex: DataFrame) como pickle no blob"""
-        buf = io.BytesIO()
-        pickle.dump(obj, buf)
-        buf.seek(0)
-        self.container_client.upload_blob(name=blob_name, data=buf, overwrite=True)
-
-    def read_pickle(self, blob_name: str):
-        """Lê pickle do blob e retorna objeto Python"""
-        downloader = self.container_client.download_blob(blob_name)
-        buf = io.BytesIO(downloader.readall())
-        return pickle.load(buf)
-
-    def exists(self, blob_name: str) -> bool:
-        return self.container_client.get_blob_client(blob_name).exists()
-