ipulse-shared-core-ftredge 2.55__py3-none-any.whl → 2.57__py3-none-any.whl

ipulse_shared_core_ftredge/utils_gcp_for_pipelines.py

@@ -0,0 +1,201 @@
+# pylint: disable=missing-module-docstring
+# pylint: disable=missing-function-docstring
+# pylint: disable=missing-class-docstring
+# pylint: disable=broad-exception-caught
+# pylint: disable=line-too-long
+# pylint: disable=unused-variable
+import json
+import os
+import time
+from ipulse_shared_core_ftredge.enums.enums_common_utils import LogLevel
+from .utils_custom_logs import ContextLog
+from ipulse_shared_core_ftredge.utils_pipelinemon import Pipelinemon
+
+############################################################################
+##################### SETTING UP LOGGER ##########################
+
+####DEPCREACATED: THIS APPROACH WAS GOOD, BUT ERRORS WERE NOT REPORTED TO ERROR REPORTING
+# logging.basicConfig(level=logging.INFO)
+# logging_client = google.cloud.logging.Client()
+# logging_client.setup_logging()
+###################################
+
+
+##### THIS APPROACH IS USED NOW ########
+ENV = os.getenv('ENV', 'LOCAL').strip("'")
+
+
+def write_json_to_gcs_in_pipeline( pipelinemon:Pipelinemon, storage_client, data, bucket_name, file_name,
+                      file_exists_if_starts_with_prefix:str=None, overwrite_if_exists:bool=False, increment_if_exists:bool=False,
+                      save_locally:bool=False, local_path=None,  max_retries:int=2, max_deletable_files:int=1):
+    """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 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.
+    """
+
+    with pipelinemon.context("write_json_to_gcs_in_pipeline"):
+        # GCS upload exception
+        gcs_upload_error = False
+        # Input validation
+        if overwrite_if_exists and increment_if_exists:
+            pipelinemon.add_log(ContextLog(LogLevel.ERROR_CUSTOM, subject="Param validation", description="Both 'overwrite_if_exists' and 'increment_if_exists' cannot be True simultaneously."))
+            gcs_upload_error=True
+        if not isinstance(data, (list, dict, str)):
+            pipelinemon.add_log(ContextLog(LogLevel.ERROR_CUSTOM,subject="Data validation", description="Unsupported data type. Data must be a list, dict, or str."))
+            gcs_upload_error=True
+        if max_deletable_files > 10:
+            pipelinemon.add_log(ContextLog(LogLevel.ERROR_CUSTOM,subject="max_deletable_files", description="max_deletable_files should be less than 10 for safety. For more use another method."))
+            gcs_upload_error=True
+
+        # Prepare data
+        if isinstance(data, (list, dict)):
+            data_str = json.dumps(data, indent=2)
+        else:
+            data_str = data
+
+        bucket = storage_client.bucket(bucket_name)
+        base_file_name, ext = os.path.splitext(file_name)
+        increment = 0
+        attempts = 0
+        success = False
+
+        # 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=[]
+
+        # Local file path
+        local_path_final = None
+
+        try:
+            upload_allowed = True
+            # --- Overwrite Logic ---
+            if overwrite_if_exists:
+                with pipelinemon.context("overwriting"):
+                    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:
+                            pipelinemon.add_log(ContextLog(LogLevel.NOTICE_ALREADY_EXISTS, subject=file_exists_if_starts_with_prefix, description=f"Prefix matched with {len(blobs_to_delete)} files in bucket {bucket_name}"))
+                            #### Ensuring to quit the operation if too many files are found
+                            raise Exception(f"Error: Attempt to delete {len(blobs_to_delete)} matched files, but limit is {max_deletable_files}.")
+                        if blobs_to_delete:
+                            gcs_file_already_exists = True
+                            pipelinemon.add_log(ContextLog(LogLevel.NOTICE_ALREADY_EXISTS, subject=file_exists_if_starts_with_prefix, description=f"Prefix matched with {len(blobs_to_delete)} files in bucket {bucket_name}"))
+                            for blob in blobs_to_delete:
+                                gcs_path_del = f"gs://{bucket_name}/{blob.name}"
+                                pipelinemon.add_system_impacted(f"delete: gcs_bucket_file: {gcs_path_del}")
+                                blob.delete()
+                                pipelinemon.add_log(ContextLog(LogLevel.INFO_REMOTE_DELETE_COMPLETE, subject= gcs_path_del, description="file deleted from GCS as part of overwrite, matched with prefix"))
+                                gcs_deleted_files.append(blob.name)
+                            gcs_file_overwritten = True
+                    else:
+                        blob = bucket.blob(file_name)
+                        if blob.exists():
+                            gcs_file_already_exists = True
+                            pipelinemon.add_log(ContextLog(LogLevel.NOTICE_ALREADY_EXISTS, subject=file_name, description=f"Exact name matched with existing file in bucket {bucket_name}"))
+                            gcs_path_del = f"gs://{bucket_name}/{file_name}"
+                            pipelinemon.add_system_impacted(f"delete: gcs_bucket_file: {gcs_path_del}")
+                            blob.delete()  # Delete the existing blob
+                            pipelinemon.add_log(ContextLog(LogLevel.INFO_REMOTE_DELETE_COMPLETE, subject= gcs_path_del, description="file deleted from GCS as part of overwrite, matched with exact name"))
+                            gcs_deleted_files.append(blob.name)
+                            gcs_file_overwritten = True
+
+            # --- Increment Logic ---
+            elif increment_if_exists:
+                with pipelinemon.context("incrementing"):
+                    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
+                    if increment>0:
+                        pipelinemon.add_log(ContextLog(LogLevel.NOTICE_ALREADY_EXISTS, subject=file_name, description=f"File saved with incremented version in {bucket_name}"))
+
+             # --- Check for Conflicts (Including Prefix) ---
+            else:
+                if file_exists_if_starts_with_prefix:
+                    blobs_matched = list(bucket.list_blobs(prefix=file_exists_if_starts_with_prefix))
+                    if blobs_matched:
+                        upload_allowed = False
+                        pipelinemon.add_log(ContextLog(LogLevel.NOTICE_ALREADY_EXISTS, subject=file_exists_if_starts_with_prefix, description=f"Prefix matched with {len(blobs_matched)} existing files in bucket {bucket_name}."))
+                    elif bucket.blob(file_name).exists():
+                        pipelinemon.add_log(ContextLog(LogLevel.NOTICE_ALREADY_EXISTS, subject=file_name, description=f"Exact name matched with existing file in bucket {bucket_name}."))
+                        upload_allowed = False
+
+            # --- GCS Upload ---
+            if overwrite_if_exists or increment_if_exists or upload_allowed:
+                with pipelinemon.context("uploading"):
+                    while attempts < max_retries and not success:
+                        try:
+                            gcs_path = f"gs://{bucket_name}/{file_name}"
+                            blob = bucket.blob(file_name)  # Use the potentially updated file_name
+                            pipelinemon.add_system_impacted(f"upload: gcs_bucket_file: {gcs_path}")
+                            blob.upload_from_string(data_str, content_type='application/json')
+                            pipelinemon.add_log(ContextLog(LogLevel.INFO_REMOTE_PERSISTNACE_COMPLETE, subject= gcs_path, description="file uploaded to GCS"))
+                            success = True
+                        except Exception as e:
+                            attempts += 1
+                            if attempts < max_retries:
+                                time.sleep(2 ** attempts)
+                            else:
+                                pipelinemon.add_log(ContextLog(LogLevel.ERROR_EXCEPTION, e=e))
+                                gcs_upload_error = True
+
+        except Exception as e:
+            pipelinemon.add_log(ContextLog(LogLevel.ERROR_EXCEPTION, e=e))
+            gcs_upload_error = True
+
+        # --- Save Locally ---
+        ###### Not logging the local save operation in pipeline, as it is not a critical operation
+        write_out=False
+        if not success or gcs_upload_error or save_locally or local_path:
+            try:
+                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}_v{increment}{ext}")
+                        write_out=True
+                    elif overwrite_if_exists:
+                        write_out=True
+                    else:
+                        write_out=False
+                else:
+                    write_out=True
+
+                if write_out:
+                    with open(local_path_final, 'w', encoding='utf-8') as f:
+                        f.write(data_str)
+
+            except Exception as local_e:
+                pipelinemon.add_log(ContextLog(LogLevel.WARNING_FIX_RECOMMENDED, e=local_e, description="Failed to write to local file"))
+
+        # --- Return Metadata ---
+        return {
+            "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
+        }

ipulse_shared_core_ftredge/{utils_common.py → utils_pipelinemon.py}

@@ -3,213 +3,26 @@
 # pylint: disable=logging-fstring-interpolation
 # pylint: disable=line-too-long
 # pylint: disable=missing-class-docstring
-import traceback
+# pylint: disable=broad-exception-caught
 import json
 import uuid
 from datetime import datetime, timezone
 from contextlib import contextmanager
 from typing import List
 from google.cloud import logging as cloudlogging
-from ipulse_shared_core_ftredge.enums.enums_common_utils import TargetLogs, LogLevel, LogStatus
+from ipulse_shared_core_ftredge.enums.enums_common_utils import TargetLogs, LogLevel
 from ipulse_shared_core_ftredge.utils_gcp import write_json_to_gcs
+from ipulse_shared_core_ftredge.utils_custom_logs import ContextLog
 
 
-# ["data_import","data_quality", "data_processing","data_general","data_persistance","metadata_quality", "metadata_processing", "metadata_persistance","metadata_general"]
-
-class ContextLog:
-    MAX_TRACEBACK_LINES = 24  # Define the maximum number of traceback lines to include
-    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
-                ):
-        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.collector_id = collector_id
-        self.exception_type = e_type
-        self.exception_message = e_message
-        self.exception_traceback = self._format_traceback(e_traceback,e_message)
-        self.log_status = log_status
-        self.timestamp = datetime.now(timezone.utc).isoformat()
-
-    def _format_traceback(self, e_traceback, e_message):
-        if not e_traceback or e_traceback == 'None\n':
-            return None
-
-        traceback_lines = e_traceback.splitlines()
-
-        # 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)
-
-        # Determine the number of lines to keep from the start and end
-        keep_lines_start = min(self.MAX_TRACEBACK_LINES // 2, len(combined_lines))
-        keep_lines_end = min(self.MAX_TRACEBACK_LINES // 2, len(combined_lines) - keep_lines_start)
-
-        if len(combined_lines) > self.MAX_TRACEBACK_LINES:
-            # Include the first few and last few lines, and an indicator of truncation
-            formatted_traceback = '\n'.join(
-                combined_lines[:keep_lines_start] + 
-                ['... (truncated) ...'] + 
-                combined_lines[-keep_lines_end:]
-            )
-        else:
-            formatted_traceback = '\n'.join(combined_lines)
-
-        return formatted_traceback
-
-    @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
-
-
-    def to_dict(self, size_limit=256 * 1024 * 0.80):
-        size_limit = int(size_limit)  # Ensure size_limit is an integer
-
-        # Define the priority order of the fields
-        priority_fields = [
-            ("base_context", self.base_context),
-            ("level_code", self.level.value),
-            ("level_name", self.level.name),
-            ("log_status", self.log_status.value),
-            ("collector_id", self.collector_id),
-            ("timestamp", self.timestamp),
-        ]
-
-        # Additional fields to be truncated if necessary. Shorter fields are truncated first so that remaining size can increase for longer fields.
-        additional_fields = [
-            ("subject", self.subject),
-            ("description", self.description),
-            ("exception_type", self.exception_type),
-            ("exception_message", self.exception_message),
-            ("context", self.context),  # special sizing rules apply to it
-            ("exception_traceback", self.exception_traceback)
-        ]
-
-        all_fields = priority_fields + additional_fields
-        non_zero_fields = [(key, value) for key, value in all_fields if value is not None]
-
-        total_size = 0
-        truncated = False  # Flag to indicate if truncation happened
-
-        # 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
-        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):]
-            elif isinstance(value, (list, tuple)):
-                half_size = max_size // 2
-                return list(value[:half_size]) + ['...'] + list(value[-(max_size - half_size - 1):])
-            elif isinstance(value, set):
-                truncated_set = set(list(value)[:max_size // 2]) | set(list(value)[-(max_size // 2):])
-                return truncated_set
-            elif isinstance(value, dict):
-                truncated_dict = {k: truncate_value(v, max_size // len(value)) for k, v in list(value.items())}
-                return truncated_dict
-            else:
-                return value
-
-        # Calculate the initial total size
-        for key, value in non_zero_fields:
-            total_size += field_size(key, value)
-
-        log_dict = {}
-        # Check if total size exceeds the size limit
-        if total_size > size_limit:
-            truncated = True  # Set the truncation flag
-            # Calculate max size per field based on all non-zero fields
-            max_size_per_field = size_limit // len(non_zero_fields)
-
-            # Reset total_size to recompute with truncation
-            total_size = 0
-
-            # Add priority fields first with possible truncation
-            for key, value in priority_fields:
-                if value is not None:
-                    truncated_value = value
-                    if isinstance(value, (str, list, tuple, set, dict)) and field_size(key, value) > max_size_per_field:
-                        truncated_value = truncate_value(value, max_size_per_field)
-                    log_dict[key] = truncated_value
-                    total_size += field_size(key, truncated_value)
-                else:
-                    log_dict[key] = value
-
-            # Calculate remaining size for additional fields
-            remaining_size = size_limit - total_size
-
-            # Handle remaining additional fields
-            non_zero_additional_fields = [field for field in additional_fields[1:] if field[1]]
-            remaining_field_size = remaining_size // len(non_zero_additional_fields) if non_zero_additional_fields else 0
-
-            for key, value in additional_fields[1:]:
-                if value is not None:
-                    if field_size(key, value) > remaining_field_size:
-                        truncated_value = truncate_value(value, remaining_field_size)
-                    else:
-                        truncated_value = value
-                    log_dict[key] = truncated_value
-                    remaining_size -= field_size(key, truncated_value)
-                else:
-                    log_dict[key] = value
-        else:
-            log_dict = dict(all_fields)
-
-        # Add trunc flag to the log dictionary
-        log_dict['trunc'] = truncated
-
-        return log_dict
-
 class Pipelinemon:
     ERROR_START_CODE = LogLevel.ERROR.value
     WARNING_START_CODE = LogLevel.WARNING.value
     NOTICE_START_CODE = LogLevel.NOTICE.value
     SUCCESS_START_CODE = LogLevel.SUCCESS.value
+    INFO_START_CODE = LogLevel.INFO.value
 
-    def __init__(self, base_context: str, target_logs: TargetLogs = TargetLogs.MIXED, logger_name=None):
+    def __init__(self, base_context: str, target_logs: TargetLogs = TargetLogs.MIXED, logger_name=None, max_log_field_size:int =10000, max_log_dict_size:float=256 * 1024 * 0.80, max_log_traceback_lines:int = 30):
         self._id = str(uuid.uuid4())
         self._logs = []
         self._early_stop = False
@@ -217,11 +30,16 @@ class Pipelinemon:
         self._warnings_count = 0
         self._notices_count = 0
         self._successes_count = 0
-        self._level_counts = {level.name: 0 for level in LogLevel}
+        self._infos_count = 0
+        self._systems_impacted = []
+        self._by_level_counts = {level.name: 0 for level in LogLevel}
         self._base_context = base_context
         self._context_stack = []
         self._target_logs = target_logs.value
         self._logger = self._initialize_logger(logger_name)
+        self._max_log_field_size = max_log_field_size
+        self._max_log_dict_size = max_log_dict_size
+        self._max_log_traceback_lines = max_log_traceback_lines
 
     def _initialize_logger(self, logger_name):
         if logger_name:
@@ -256,6 +74,46 @@ class Pipelinemon:
     def id(self):
         return self._id
 
+    @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 clear_systems_impacted(self):
+        self._systems_impacted = []
+
+    @property
+    def max_log_dict_size(self):
+        return self._max_log_dict_size
+
+    @max_log_dict_size.setter
+    def max_log_dict_size(self, value):
+        self._max_log_dict_size = value
+
+    @property
+    def max_log_field_size(self):
+        return self._max_log_field_size
+
+    @max_log_field_size.setter
+    def max_log_field_size(self, value):
+        self._max_log_field_size = value
+
+    @property
+    def max_log_traceback_lines(self):
+        return self._max_log_traceback_lines
+
+    @max_log_traceback_lines.setter
+    def max_log_traceback_lines(self, value):
+        self._max_log_traceback_lines = value
+
     @property
     def early_stop(self):
         return self._early_stop
@@ -265,24 +123,23 @@ class Pipelinemon:
         if create_error_log:
             if pop_context:
                 self.pop_context()
-            self.add_log(ContextLog(level=LogLevel.ERROR,
+            self.add_log(ContextLog(level=LogLevel.ERROR_PIPELINE_THRESHOLD_REACHED,
                                     subject="EARLY_STOP",
                                     description=f"Total MAX_ERRORS_TOLERANCE of {max_errors_tolerance} has been reached."))
 
     def reset_early_stop(self):
         self._early_stop = False
 
-    def get_early_stop(self):
-        return self._early_stop
 
-    def add_log(self, log: ContextLog):
+    def add_log(self, log: ContextLog ):
         if (self._target_logs == TargetLogs.SUCCESSES and log.level >=self.NOTICE_START_CODE) or \
            (self._target_logs == TargetLogs.WARNINGS_AND_ERRORS and log.level.value < self.WARNING_START_CODE):
             raise ValueError(f"Invalid log level {log.level.name} for Pipelinemon target logs setup: {self._target_logs}")
         log.base_context = self.base_context
         log.context = self.current_context
         log.collector_id = self.id
-        log_dict = log.to_dict()
+        log.systems_impacted = self.systems_impacted
+        log_dict = log.to_dict(max_field_len=self.max_log_field_size, size_limit=self.max_log_dict_size, max_traceback_lines=self.max_log_traceback_lines)
         self._logs.append(log_dict)
         self._update_counts(log_dict)
 
@@ -306,7 +163,8 @@ class Pipelinemon:
         self._warnings_count = 0
         self._notices_count = 0
         self._successes_count = 0
-        self._level_counts = {level.name: 0 for level in LogLevel}
+        self._infos_count = 0
+        self._by_level_counts = {level.name: 0 for level in LogLevel}
 
     def clear_logs(self):
         self._logs = []
@@ -344,11 +202,20 @@ class Pipelinemon:
     def count_successes(self):
         return self._successes_count
 
+    def count_successes_with_notice(self):
+        return self.count_logs_by_level(LogLevel.SUCCESS_WITH_NOTICES)
+
+    def count_successes_no_notice(self):
+        return self.count_logs_by_level(LogLevel.SUCCESS)
+
+    def count_infos(self):
+        return self._infos_count
+
     def count_all_logs(self):
         return len(self._logs)
 
     def count_logs_by_level(self, level: LogLevel):
-        return self._level_counts.get(level.name, 0)
+        return self._by_level_counts.get(level.name, 0)
 
     def _count_logs(self, context_substring: str, exact_match=False, level_code_min=None, level_code_max=None):
         return sum(
@@ -400,7 +267,13 @@ class Pipelinemon:
     def count_successes_for_current_and_nested_contexts(self):
         return self._count_logs(self.current_context, level_code_min=self.SUCCESS_START_CODE, level_code_max=self.NOTICE_START_CODE-1)
 
-    def export_logs_to_gcs_file(self, bucket_name, storage_client, file_prefix=None, file_name=None, top_level_context=None, save_locally=False, local_path=None, logger=None, max_retries=2):
+    def count_infos_for_current_context(self):
+        return self._count_logs(self.current_context, exact_match=True, level_code_min=self.INFO_START_CODE, level_code_max=self.SUCCESS_START_CODE-1)
+
+    def count_infos_for_current_and_nested_contexts(self):
+        return self._count_logs(self.current_context, level_code_min=self.INFO_START_CODE, level_code_max=self.SUCCESS_START_CODE-1)
+
+    def export_logs_to_gcs_file(self, bucket_name, storage_client, file_prefix=None, file_name=None, top_level_context=None, save_locally=False, overwrite_if_exists=False, increment_if_exists=True, local_path=None, logger=None, max_retries=2):
         def log_message(message):
             if logger:
                 logger.info(message)
@@ -429,9 +302,11 @@ class Pipelinemon:
                 local_path=local_path,
                 logger=logger,
                 max_retries=max_retries,
-                overwrite_if_exists=False
+                overwrite_if_exists=overwrite_if_exists,
+                increment_if_exists=increment_if_exists
+
             )
-            log_message(f"{file_prefix} successfully saved (overwritten={result.get('gcs_file_overwritten')}) to GCS at {result.get('gcs_path')} and locally at {result.get('local_path')}.")
+            log_message(f"{file_prefix} successfully saved (overwritten={result.get('gcs_file_overwritten')}, incremented={result.get('gcs_file_saved_with_increment')}) to GCS at {result.get('gcs_path')} and locally at {result.get('local_path')}.")
         except Exception as e:
             log_error(f"Failed at export_logs_to_gcs_file for {file_prefix} for file {file_name} to bucket {bucket_name}: {type(e).__name__} - {str(e)}")
 
@@ -469,7 +344,9 @@ class Pipelinemon:
                 self._notices_count -= 1
             elif self.SUCCESS_START_CODE <= level_code < self.NOTICE_START_CODE:
                 self._successes_count -= 1
-            self._level_counts[level_name] -= 1
+            elif self.INFO_START_CODE <= level_code < self.SUCCESS_START_CODE:
+                self._infos_count -= 1
+            self._by_level_counts[level_name] -= 1
         else:
             if level_code >= self.ERROR_START_CODE:
                 self._errors_count += 1
@@ -479,4 +356,7 @@ class Pipelinemon:
                 self._notices_count += 1
             elif self.SUCCESS_START_CODE <= level_code < self.NOTICE_START_CODE:
                 self._successes_count += 1
-            self._level_counts[level_name] += 1
+            elif self.INFO_START_CODE <= level_code < self.SUCCESS_START_CODE:
+                self._infos_count += 1
+            self._by_level_counts[level_name] += 1
+

ipulse_shared_core_ftredge/utils_templates_and_schemas.py

@@ -6,7 +6,7 @@
 import datetime
 from google.cloud import bigquery
 from ipulse_shared_core_ftredge.enums.enums_common_utils import LogLevel
-from ipulse_shared_core_ftredge.utils_common import ContextLog
+from ipulse_shared_core_ftredge.utils_custom_logs import ContextLog
 
 
 def create_bigquery_schema_from_json(json_schema):
@@ -59,16 +59,14 @@ def check_format_against_schema_template(data_to_check, schema, dt_ts_to_str=Tru
                     checked_data[field_name] = value
 
             elif mode == "REQUIRED":
-                warning = ContextLog(level=LogLevel.WARNING,
+                warnings_or_error.append(ContextLog(level=LogLevel.WARNING,
                                               subject=field_name,
-                                              description=f"Required field '{field_name}' is missing in the updates.")
-                warnings_or_error.append(warning)
+                                              description=f"Required field '{field_name}' is missing in the updates."))
 
     except Exception as e:
-        error_log = ContextLog(level=LogLevel.ERROR_EXCEPTION_REDO,
+        warnings_or_error.append(ContextLog(level=LogLevel.ERROR_EXCEPTION,
                                subject=data_to_check,
-                               description=f"An error occurred during update check: {str(e)}")
-        warnings_or_error.append(error_log)
+                               description=f"An error occurred during update check: {str(e)}"))
 
     return checked_data, warnings_or_error
 
@@ -144,11 +142,11 @@ def handle_type_conversion(field_type, field_name, value):
         try:
             return float(value), None
         except ValueError:
-            return None, ContextLog(level=LogLevel.WARNING_FIX_REQUIRED, 
+            return None, ContextLog(level=LogLevel.WARNING_FIX_REQUIRED,
                                                 subject=field_name,
                                                 description=f"Expected FLOAT, but got  {value} of type {type(value).__name__}.")
     if field_type == "BOOL" and not isinstance(value, bool):
-        return bool(value), ContextLog(level=LogLevel.WARNING_REVIEW_RECOMMENDED, 
+        return bool(value), ContextLog(level=LogLevel.WARNING_REVIEW_RECOMMENDED,
                                                 subject=field_name,
                                                 description=f"Expected BOOL, but got  {value}. Converting as {bool(value)}.")
 

{ipulse_shared_core_ftredge-2.55.dist-info → ipulse_shared_core_ftredge-2.57.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ipulse_shared_core_ftredge
-Version: 2.55
+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