ipulse-shared-core-ftredge 2.56__tar.gz → 2.57__tar.gz

{ipulse_shared_core_ftredge-2.56/src/ipulse_shared_core_ftredge.egg-info → ipulse_shared_core_ftredge-2.57}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ipulse_shared_core_ftredge
-Version: 2.56
+Version: 2.57
 Summary: Shared Core models and Logger util for the Pulse platform project. Using AI for financial advisory and investment management.
 Home-page: https://github.com/TheFutureEdge/ipulse_shared_core
 Author: Russlan Ramdowar

{ipulse_shared_core_ftredge-2.56 → ipulse_shared_core_ftredge-2.57}/setup.py

@@ -3,7 +3,7 @@ from setuptools import setup, find_packages
 
 setup(
     name='ipulse_shared_core_ftredge',
-    version='2.56',
+    version='2.57',
     package_dir={'': 'src'},  # Specify the source directory
     packages=find_packages(where='src'),  # Look for packages in 'src'
     install_requires=[

{ipulse_shared_core_ftredge-2.56 → ipulse_shared_core_ftredge-2.57}/src/ipulse_shared_core_ftredge/__init__.py

@@ -1,13 +1,18 @@
 from .models import (Organisation, UserAuth, UserProfile,
                      UserStatus, UserProfileUpdate, pulse_enums)
-from .utils_gcp import (setup_gcp_logger_and_error_report, 
-                        read_csv_from_gcs, read_json_from_gcs, 
-                        write_csv_to_gcs, write_json_to_gcs)
+
+
+from .utils_gcp import (setup_gcp_logger_and_error_report,
+                        read_csv_from_gcs, read_json_from_gcs,
+                        write_csv_to_gcs,write_json_to_gcs)
+from .utils_custom_logs import (ContextLog)
+from .utils_pipelinemon import ( Pipelinemon)
+from .utils_gcp_for_pipelines import (write_json_to_gcs_in_pipeline )
+
 from .utils_templates_and_schemas import (create_bigquery_schema_from_json,
                                           check_format_against_schema_template)
-from .utils_common import (ContextLog,  Pipelinemon)
 
-from .enums import (TargetLogs, LogLevel, Unit, Frequency,
+from .enums import (TargetLogs, LogStatus, LogLevel, Unit, Frequency,
                     Module, SubModule, BaseDataCategory,
                     FinCoreCategory, FincCoreSubCategory,
                     FinCoreRecordsCategory, ExchangeOrPublisher,

{ipulse_shared_core_ftredge-2.56 → ipulse_shared_core_ftredge-2.57}/src/ipulse_shared_core_ftredge/enums/__init__.py

@@ -4,6 +4,7 @@
 # pylint: disable=missing-class-docstring
 
 from .enums_common_utils import (LogLevel,
+                                 LogStatus,
                                 SystemsImpacted,
                                 TargetLogs,
                                 Unit,

{ipulse_shared_core_ftredge-2.56 → ipulse_shared_core_ftredge-2.57}/src/ipulse_shared_core_ftredge/enums/enums_common_utils.py

@@ -42,9 +42,15 @@ class LogLevel(Enum):
     DEBUG = 10  # Detailed debug information (for development/troubleshooting)
 
     INFO = 100
-    INFO_PERSISTNACE_COMPLETE= 101
-    INFO_UPDATE_COMPLETE = 102
-    INFO_DELETE_COMPLETE = 103
+    INFO_REMOTE_PERSISTNACE_COMPLETE= 101
+    INFO_REMOTE_UPDATE_COMPLETE = 102
+    INFO_REMOTE_DELETE_COMPLETE = 103
+
+    INFO_REMOTE_BULK_PERSISTNACE_COMPLETE= 111
+    INFO_REMOTE_BULK_UPDATE_COMPLETE = 112
+    INFO_REMOTE_BULK_DELETE_COMPLETE = 113
+
+    INFO_LOCAL_PERSISTNACE_COMPLETE = 121
 
     SUCCESS = 201
     SUCCESS_WITH_NOTICES = 211

{ipulse_shared_core_ftredge-2.56 → ipulse_shared_core_ftredge-2.57}/src/ipulse_shared_core_ftredge/models/user_profile.py

@@ -33,9 +33,9 @@ class UserProfile(BaseModel):
     provider_id: str   #User can Read only
     
     username: Optional[str] = None #User can Read and Edit
-    dob: Optional[date] = None #User can Read and Edit 
-    first_name: Optional[str] = None #User can Read and Edit 
-    last_name: Optional[str] = None #User can Read and Edit 
+    dob: Optional[date] = None #User can Read and Edit
+    first_name: Optional[str] = None #User can Read and Edit
+    last_name: Optional[str] = None #User can Read and Edit
     mobile: Optional[str] = None #User can Read and Edit
     class Config:
         extra = "forbid"

ipulse_shared_core_ftredge-2.57/src/ipulse_shared_core_ftredge/utils_custom_logs.py

@@ -0,0 +1,201 @@
+
+# pylint: disable=missing-module-docstring
+# pylint: disable=missing-function-docstring
+# pylint: disable=logging-fstring-interpolation
+# pylint: disable=line-too-long
+# pylint: disable=missing-class-docstring
+# pylint: disable=broad-exception-caught
+import traceback
+import json
+from datetime import datetime, timezone
+from typing import List
+from ipulse_shared_core_ftredge.enums.enums_common_utils import LogLevel, LogStatus
+
+
+class ContextLog:
+
+    def __init__(self, level: LogLevel, base_context: str = None, collector_id: str = None,
+                context: str = None, description: str = None,
+                e: Exception = None, e_type: str = None, e_message: str = None, e_traceback: str = None,
+                log_status: LogStatus = LogStatus.OPEN, subject: str = None, systems_impacted: List[str] = None,
+                ):
+
+        if e is not None:
+            e_type = type(e).__name__ if e_type is None else e_type
+            e_message = str(e) if e_message is None else e_message
+            e_traceback = traceback.format_exc() if e_traceback is None else e_traceback
+        elif e_traceback is None and (e_type or e_message):
+            e_traceback = traceback.format_exc()
+
+        self.level = level
+        self.subject = subject
+        self.description = description
+        self._base_context = base_context
+        self._context = context
+        self._systems_impacted = systems_impacted if systems_impacted else []
+        self.collector_id = collector_id
+        self.exception_type = e_type
+        self.exception_message = e_message
+        self.exception_traceback = e_traceback
+        self.log_status = log_status
+        self.timestamp = datetime.now(timezone.utc).isoformat()
+
+    @property
+    def base_context(self):
+        return self._base_context
+
+    @base_context.setter
+    def base_context(self, value):
+        self._base_context = value
+
+    @property
+    def context(self):
+        return self._context
+
+    @context.setter
+    def context(self, value):
+        self._context = value
+
+    @property
+    def systems_impacted(self):
+        return self._systems_impacted
+
+    @systems_impacted.setter
+    def systems_impacted(self, list_of_si: List[str]):
+        self._systems_impacted = list_of_si
+
+    def add_system_impacted(self, system_impacted: str):
+        if self._systems_impacted is None:
+            self._systems_impacted = []
+        self._systems_impacted.append(system_impacted)
+
+    def remove_system_impacted(self, system_impacted: str):
+        if self._systems_impacted is not None:
+            self._systems_impacted.remove(system_impacted)
+
+    def clear_systems_impacted(self):
+        self._systems_impacted = []
+
+    def _format_traceback(self, e_traceback, e_message, max_field_len:int, max_traceback_lines:int):
+        if not e_traceback or e_traceback == 'None\n':
+            return None
+
+        traceback_lines = e_traceback.splitlines()
+
+            # Check if the traceback is within the limits
+        if len(traceback_lines) <= max_traceback_lines and len(e_traceback) <= max_field_len:
+            return e_traceback
+
+        # Remove lines that are part of the exception message if they are present in traceback
+        message_lines = e_message.splitlines() if e_message else []
+        if message_lines:
+            for message_line in message_lines:
+                if message_line in traceback_lines:
+                    traceback_lines.remove(message_line)
+
+        # Filter out lines from third-party libraries (like site-packages)
+        filtered_lines = [line for line in traceback_lines if "site-packages" not in line]
+
+        # If filtering results in too few lines, revert to original traceback
+        if len(filtered_lines) < 2:
+            filtered_lines = traceback_lines
+
+        # Combine standalone bracket lines with previous or next lines
+        combined_lines = []
+        for line in filtered_lines:
+            if line.strip() in {"(", ")", "{", "}", "[", "]"} and combined_lines:
+                combined_lines[-1] += " " + line.strip()
+            else:
+                combined_lines.append(line)
+
+            # Ensure the number of lines doesn't exceed MAX_TRACEBACK_LINES
+        if len(combined_lines) > max_traceback_lines:
+            keep_lines_start = min(max_traceback_lines // 2, len(combined_lines))
+            keep_lines_end = min(max_traceback_lines // 2, len(combined_lines) - keep_lines_start)
+            combined_lines = (
+                combined_lines[:keep_lines_start] +
+                ['... (truncated) ...'] +
+                combined_lines[-keep_lines_end:]
+            )
+
+        formatted_traceback = '\n'.join(combined_lines)
+
+        # Ensure the total length doesn't exceed MAX_TRACEBACK_LENGTH
+        if len(formatted_traceback) > max_field_len:
+            truncated_length = max_field_len - len('... (truncated) ...')
+            half_truncated_length = truncated_length // 2
+            formatted_traceback = (
+                formatted_traceback[:half_truncated_length] +
+                '\n... (truncated) ...\n' +
+                formatted_traceback[-half_truncated_length:]
+            )
+        return formatted_traceback
+
+    def to_dict(self, max_field_len:int =10000, size_limit:float=256 * 1024 * 0.80,max_traceback_lines:int = 30):
+        size_limit = int(size_limit)  # Ensure size_limit is an integer
+
+        # Unified list of all fields
+        systems_impacted_str = f"{len(self.systems_impacted)} system(s): " + " ,,, ".join(self.systems_impacted) if self.systems_impacted else None
+        fields = [
+            ("log_status", str(self.log_status.name)),
+            ("level_code", self.level.value),
+            ("level_name", str(self.level.name)),
+            ("base_context", str(self.base_context)),
+            ("timestamp", str(self.timestamp)),
+            ("collector_id", str(self.collector_id)),
+            ("systems_impacted", systems_impacted_str),
+            ("context", str(self.context)),  # special sizing rules apply to it
+            ("subject", str(self.subject)),
+            ("description", str(self.description)),
+            ("exception_type", str(self.exception_type)),
+            ("exception_message", str(self.exception_message)),
+            ("exception_traceback", str(self._format_traceback(self.exception_traceback,self.exception_message, max_field_len, max_traceback_lines)))
+        ]
+
+        # Function to calculate the byte size of a JSON-encoded field
+        def field_size(key, value):
+            return len(json.dumps({key: value}).encode('utf-8'))
+
+        # Function to truncate a value based on its type
+        # Function to truncate a value based on its type
+        def truncate_value(value, max_size):
+            if isinstance(value, str):
+                half_size = max_size // 2
+                return value[:half_size] + '...' + value[-(max_size - half_size - 3):]
+            return value
+
+         # Ensure no field exceeds max_field_len
+        for i, (key, value) in enumerate(fields):
+            if isinstance(value, str) and len(value) > max_field_len:
+                fields[i] = (key, truncate_value(value, max_field_len))
+
+        # Ensure total size of the dict doesn't exceed size_limit
+        total_size = sum(field_size(key, value) for key, value in fields)
+        log_dict = {}
+        truncated = False
+
+        if total_size > size_limit:
+            truncated = True
+            remaining_size = size_limit
+            remaining_fields = len(fields)
+
+            for key, value in fields:
+                if remaining_fields > 0:
+                    max_size_per_field = remaining_size // remaining_fields
+                else:
+                    max_size_per_field = 0
+
+                field_sz = field_size(key, value)
+                if field_sz > max_size_per_field:
+                    value = truncate_value(value, max_size_per_field)
+                    field_sz = field_size(key, value)
+
+                log_dict[key] = value
+                remaining_size -= field_sz
+                remaining_fields -= 1
+        else:
+            log_dict = dict(fields)
+
+        log_dict['trunc'] = truncated
+
+        return log_dict

{ipulse_shared_core_ftredge-2.56 → ipulse_shared_core_ftredge-2.57}/src/ipulse_shared_core_ftredge/utils_gcp.py

@@ -14,7 +14,6 @@ import traceback
 from google.cloud import error_reporting, logging as cloud_logging
 from google.api_core.exceptions import NotFound
 
-
 ############################################################################
 ##################### SETTING UP LOGGER ##########################
 
@@ -124,15 +123,22 @@ def read_csv_from_gcs(bucket_name, file_name, storage_client, logger):
 
 
 
-def write_json_to_gcs(bucket_name, storage_client, data, file_name,
-                      save_locally=False, local_path=None, logger=None, max_retries=2,
-                      overwrite_if_exists=False, increment_if_exists=False):
+def write_json_to_gcs( storage_client, data, bucket_name, file_name,
+                      file_exists_if_starts_with_prefix=None, overwrite_if_exists=False, increment_if_exists=False,
+                      save_locally=False, local_path=None,  max_retries=2, max_deletable_files=1, logger=None):
     """Saves data to Google Cloud Storage and optionally locally.
-
-    This function attempts to upload data to GCS. If the upload fails after
-    retries and `save_locally` is True or `local_path` is provided, it attempts
-    to save the data locally.
-    It also tries to handle file name conflicts by overwriting or incrementing. If both are provided as Ture, an exception will be raised.
+    
+    This function attempts to upload data to GCS. 
+    - If the upload fails after retries and `save_locally` is True or `local_path` is provided, it attempts to save the data locally.
+    - It handles file name conflicts based on these rules:
+        - If `overwrite_if_exists` is True: 
+            - If `file_exists_if_contains_substr` is provided, ANY existing file containing the substring is deleted, and the new file is saved with the provided `file_name`.
+            - If `file_exists_if_contains_substr` is None, and a file with the exact `file_name` exists, it's overwritten.
+        - If `increment_if_exists` is True:
+            - If `file_exists_if_contains_substr` is provided, a new file with an incremented version is created ONLY if a file with the EXACT `file_name` exists.
+            - If `file_exists_if_contains_substr` is None, a new file with an incremented version is created if a file with the exact `file_name` exists. 
+            
+        -If both overwrite_if_exists and increment_if_exists are provided as Ture, an exception will be raised.
     """
 
     def log_message(message):
@@ -147,100 +153,141 @@ def write_json_to_gcs(bucket_name, storage_client, data, file_name,
         if logger:
             logger.warning(message)
 
-    attempts = 0
-    success = False
-    gcs_path = None
-    local_path_final = None
-    gcs_file_overwritten = False
-    gcs_file_already_exists = False
-    gcs_file_saved_with_increment = False
-    gcs_upload_exception = None  # Store potential GCS exception
-
-    # Check for conflicting options
+    # Input validation
     if overwrite_if_exists and increment_if_exists:
-        raise ValueError("When writing JSON to GCS, both overwrite and increment_if_exists cannot be True at the same time.")
+        raise ValueError("Both 'overwrite_if_exists' and 'increment_if_exists' cannot be True simultaneously.")
+    if not isinstance(data, (list, dict, str)):
+        raise ValueError("Unsupported data type. Data must be a list, dict, or str.")
+    if max_deletable_files > 10:
+        raise ValueError("max_deletable_files should be less than 10 for safety. For more use another method.")
 
+    # Prepare data
     if isinstance(data, (list, dict)):
         data_str = json.dumps(data, indent=2)
-    elif isinstance(data, str):
-        data_str = data
     else:
-        raise ValueError("Unsupported data type. It should be a list, dict, or str.")
+        data_str = data
 
     bucket = storage_client.bucket(bucket_name)
     base_file_name, ext = os.path.splitext(file_name)
     increment = 0
+    attempts = 0
+    success = False
 
-    while attempts < max_retries and not success:
-        try:
-            if increment_if_exists:
-                while bucket.blob(file_name).exists():
-                    gcs_file_already_exists = True
-                    increment += 1
-                    file_name = f"{base_file_name}_{increment}{ext}"
-                    gcs_file_saved_with_increment = True
-                    log_warning(f"File {file_name} already exists in bucket {bucket_name}. Writing with increment: {increment_if_exists}")
+    # GCS-related metadata
+    gcs_path = None
+    gcs_file_overwritten = False
+    gcs_file_already_exists = False
+    gcs_file_saved_with_increment = False
+    gcs_file_exists_checked_on_name = file_name
+    gcs_deleted_files=[]
+
+    # GCS upload exception
+    gcs_upload_exception = None
+
+     # Local file path
+    local_path_final = None
+
+    try:
+        # --- Overwrite Logic ---
+        if overwrite_if_exists:
+            if file_exists_if_starts_with_prefix:
+                gcs_file_exists_checked_on_name = file_exists_if_starts_with_prefix
+                blobs_to_delete = list(bucket.list_blobs(prefix=file_exists_if_starts_with_prefix))
+                if len(blobs_to_delete) > max_deletable_files:
+                    raise Exception(f"Error: Attempt to delete {len(blobs_to_delete)} matched files, but limit is {max_deletable_files}.")
+                if blobs_to_delete:
+                    log_message(f"Deleting files containing '{file_exists_if_starts_with_prefix}' for overwrite.")
+                    for blob in blobs_to_delete:
+                        blob.delete()
+                        gcs_deleted_files.append(blob.name)
+                        log_message(f"Deleted: gs://{bucket_name}/{blob.name}")
+                    gcs_file_overwritten = True
             else:
                 blob = bucket.blob(file_name)
-
-                # Check if the file exists
                 if blob.exists():
                     gcs_file_already_exists = True
                     gcs_path = f"gs://{bucket_name}/{file_name}"
-                    log_message(f"File {file_name} already exists in bucket {bucket_name}. Overwriting: {overwrite_if_exists}")
-                    if not overwrite_if_exists:
-                        log_warning(f"File {file_name} already exists and overwrite is set to False. Skipping save to GCS.")
-                        break
+                    log_message(f"File '{file_name}' already exists. Overwriting.")
+                    blob.delete()  # Delete the existing blob
+                    gcs_deleted_files.append(blob.name)
+                    gcs_file_overwritten = True
+
+        # --- Increment Logic ---
+        elif increment_if_exists:
+            gcs_file_exists_checked_on_name = file_name  # We only increment if the exact name exists
+            while bucket.blob(file_name).exists():
+                gcs_file_already_exists = True
+                increment += 1
+                file_name = f"{base_file_name}_v{increment}{ext}"
+                gcs_file_saved_with_increment = True
+                log_warning(f"File already exists. Using incremented name: {file_name}")
+
+        # --- GCS Upload ---
+        if overwrite_if_exists or increment_if_exists:  # Only upload if either overwrite or increment is True
+            while attempts < max_retries and not success:
+                try:
+                    blob = bucket.blob(file_name)  # Use the potentially updated file_name
+                    blob.upload_from_string(data_str, content_type='application/json')
+                    gcs_path = f"gs://{bucket_name}/{file_name}"
+                    log_message(f"Successfully saved file to GCS: {gcs_path}")
+                    success = True
+                except Exception as e:
+                    gcs_upload_exception=e
+                    attempts += 1
+                    if attempts < max_retries:
+                        log_warning(f"Attempt {attempts} to upload to GCS failed. Retrying...")
+                        time.sleep(2 ** attempts)
                     else:
-                        gcs_file_overwritten = True
-
-            blob.upload_from_string(data_str, content_type='application/json')
-            gcs_path = f"gs://{bucket_name}/{file_name}"
-            log_message(f"Successfully saved file to GCS {gcs_path}.")
-            success = True
-        except Exception as e:
-            gcs_upload_exception = e
-            attempts += 1
-            if attempts < max_retries:
-                time.sleep(2 ** attempts)
-            else:
-                log_error(f"Failed to write {file_name} to GCS bucket {bucket_name} after {max_retries} attempts: {e}")
+                        log_error(f"Failed to write '{file_name}' to GCS bucket '{bucket_name}' after {max_retries} attempts: {e}", exc_info=True)
+                        if save_locally or local_path:
+                            log_message(f"Attempting to save '{file_name}' locally due to GCS upload failure.")
+    except Exception as e:
+        log_error(f"Error during GCS operations: {e}", exc_info=True)
+        gcs_upload_exception = e
 
+    # --- Save Locally ---
+    write_out=False
     if not success or save_locally or local_path:
         try:
-            if not local_path:
-                local_path_final = os.path.join("/tmp", file_name)
-            else:
-                local_path_final = os.path.join(local_path, file_name)
+            local_path=local_path if local_path else "/tmp"
+            local_path_final = os.path.join(local_path, file_name)
 
             if os.path.exists(local_path_final):
                 if increment_if_exists:
                     increment = 0
                     while os.path.exists(local_path_final):
                         increment += 1
-                        local_path_final = os.path.join(local_path, f"{base_file_name}_{increment}{ext}")
-                elif not overwrite_if_exists:
-                    log_message(f"File {file_name} already exists locally at {local_path_final} and overwrite is set to False. Skipping save.")
-                    success = True
-                else:
+                        local_path_final = os.path.join(local_path, f"{base_file_name}_v{increment}{ext}")
+                    log_warning(f"Local file already exists. Using incremented name: {local_path_final}")
+                    write_out=True
+                elif overwrite_if_exists:
+                    write_out=True
                     log_message(f"File {file_name} already exists locally at {local_path_final}. Overwriting: {overwrite_if_exists}")
+                else:
+                    log_message(f"File {file_name} already exists locally at {local_path_final} and overwrite is set to False. Skipping save.")
+                    write_out=False
+            else:
+                write_out=True
 
-            if not success:
+            if write_out:
                 with open(local_path_final, 'w', encoding='utf-8') as f:
                     f.write(data_str)
-                log_message(f"Saved {file_name} locally at {local_path_final}. Overwritten: {overwrite_if_exists}")
-                success = True
+                    log_message(f"Saved {file_name} locally at {local_path_final}. Overwritten: {overwrite_if_exists}")
+
         except Exception as local_e:
             log_error(f"Failed to write {file_name} locally: {local_e}", exc_info=True)
 
     if gcs_upload_exception is not None:
         raise gcs_upload_exception  # Propagate without nesting
 
+    # --- Return Metadata ---
     return {
-        "gcs_path": gcs_path,
-        "local_path": local_path_final,
+        "gcs_path": gcs_path if success else None,  # Only set gcs_path if upload succeeded
+        "local_path": local_path_final if write_out else None,  # Only set local_path if saved locally
         "gcs_file_already_exists": gcs_file_already_exists,
+        "gcs_file_exists_checked_on_name":gcs_file_exists_checked_on_name ,
         "gcs_file_overwritten": gcs_file_overwritten,
+        "gcs_deleted_file_names": ",,,".join(gcs_deleted_files) if gcs_deleted_files else None,
         "gcs_file_saved_with_increment": gcs_file_saved_with_increment
     }