commons-metrics 0.0.16__py3-none-any.whl → 0.0.18__py3-none-any.whl

commons_metrics/__init__.py

@@ -6,4 +6,4 @@ from .github_api_client import GitHubAPIClient
 from .azure_devops_client import AzureDevOpsClient
 
 __all__ = ['Util', 'DatabaseConnection', 'ComponentRepository', 'UpdateDesignSystemComponents', 'GitHubAPIClient', 'AzureDevOpsClient']
-__version__ = '0.0.16'
+__version__ = '0.0.18'

commons_metrics/cache_manager.py

@@ -0,0 +1,71 @@
+import requests
+import urllib3
+
+from lib.commons_metrics.commons_metrics.s3_file_manager import S3FileManager
+
+urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
+
+
+def load_cache_or_fetch(path: str, fetch_fn, clear_cache: bool = False):
+    """
+    Load data from a JSON cache stored in S3 using S3FileManager,
+    or fetch the data and update the cache.
+
+    Args:
+        path (str): Cache key relative to "cache/", e.g. "logs/123.json"
+        fetch_fn (Callable): Function returning JSON-serializable data
+        clear_cache (bool): If True, delete existing cache before fetching
+    Returns:
+        Any: Cached or freshly fetched data
+    """
+    s3 = S3FileManager()
+    key = f"cache/{path}"
+    if clear_cache:
+        try:
+            s3.s3.delete_object(Bucket=s3.bucket, Key=key)
+        except Exception:
+            pass
+    data = s3.load_json(key)
+
+    if data:
+        return data
+
+    data = fetch_fn()
+    s3.save_json(data, key)
+
+    return data
+
+
+def get_data_from_api(url: str, headers: dict, auth_api) -> list:
+    """
+    Sends a GET request to the specified API and returns the JSON response if successful.
+
+    Args:
+        url (str): The API endpoint URL.
+        headers (dict): HTTP headers for the request.
+        auth_api: Authentication object for the request.
+    Returns:
+        list or dict: JSON response from the API if successful, otherwise an empty list.
+    """
+    response = requests.get(url, headers=headers, auth=auth_api, verify=False)
+    if response.ok:
+        return response.json()
+    return []
+
+
+def post_data_to_api(url: str, headers: dict, body: dict, auth_api) -> list:
+    """
+    Sends a POST request to the specified API with the given body and returns the JSON response if successful.
+
+    Args:
+        url (str): The API endpoint URL.
+        headers (dict): HTTP headers for the request.
+        body (dict): Data to send in the POST request.
+        auth_api: Authentication object for the request.
+    Returns:
+        list or dict: JSON response from the API if successful, otherwise an empty list.
+    """
+    response = requests.post(url, headers=headers, auth=auth_api, data=body, verify=False)
+    if response.ok:
+        return response.json()
+    return []

commons_metrics/connection_database.py

@@ -0,0 +1,18 @@
+from lib.commons_metrics.commons_metrics import DatabaseConnection, Util, ComponentRepository
+
+
+def get_connection_database_from_secret(secret_name: str, logger: str, aws_region: str) -> ComponentRepository:
+    """
+    Retrieve connection database from AWS secrets manager
+    """
+    secret_json = Util.get_secret_aws(secret_name, logger, aws_region)
+    db_connection = DatabaseConnection()
+    db_connection.connect({
+        'host': secret_json["host"],
+        'port': secret_json["port"],
+        'dbname': secret_json["dbname"],
+        'username': secret_json["username"],
+        'password': secret_json["password"]
+    })
+
+    return ComponentRepository(db_connection)

commons_metrics/date_utils.py

@@ -0,0 +1,66 @@
+from datetime import datetime
+from typing import List, Dict
+
+from dateutil import parser
+
+
+def parse_datetime(date_str: str) -> datetime:
+    """
+    Converts a string in ISO 8601 format to a datetime object.
+    If the string is empty or None, it returns the current date and time with the time zone.
+
+    Args:
+        date_str(str): Date in ISO 8601 format (e.g., "2025-12-02T10:00:00+00:00").
+    Returns:
+        datetime: Datetime object corresponding to the string, or the current date if empty.
+    """
+    if not date_str:
+        return datetime.now().astimezone()
+    return parser.isoparse(date_str)
+
+
+def get_hours_difference_from_strings(start_date: str, end_date: str) -> float:
+    """
+    Calculate the difference in hours between two dates given as ISO 8601 strings.
+
+    Args:
+        start_date(str): Start date in ISO 8601 format.
+        end_date(str): End date in ISO 8601 format.
+    Returns:
+        float: Difference in hours (can be negative if end_date < start_date).
+    """
+    start = parse_datetime(start_date)
+    end = parse_datetime(end_date)
+    return get_hours_difference(start, end)
+
+
+def get_hours_difference(start_date: datetime, end_date: datetime) -> float:
+    """
+    Calculate the difference in hours between two datetime objects.
+
+    Args:
+        start_date(datetime): Start date.
+        end_date(datetime): End date.
+    Returns:
+        float: Difference in hours (can be negative if end_date < start_date).
+    """
+    return (end_date - start_date).total_seconds() / 3600
+
+
+def sort_by_date(list_dicts: List[Dict], date_attribute_name: str) -> List[Dict]:
+    """
+    Sorts a list of dictionaries by a specified date attribute in descending order.
+    The method uses the `parse_datetime` function to convert date strings into datetime objects
+    for accurate sorting.
+
+    Args:
+        list_dicts (List[Dict]): A list of dictionaries containing date attributes.
+        date_attribute_name (str): The key name of the date attribute in each dictionary.
+    Returns:
+        List[Dict]: A new list of dictionaries sorted by the given date attribute in descending order.
+    """
+    return sorted(
+        list_dicts,
+        key=lambda x: parse_datetime(x.get(date_attribute_name)),
+        reverse=True
+    )

commons_metrics/s3_file_manager.py

@@ -0,0 +1,104 @@
+import os
+import json
+import sys
+from typing import List
+import boto3
+from awsglue.utils import getResolvedOptions
+from botocore.exceptions import ClientError
+
+args = getResolvedOptions(sys.argv, ['bucket', 'aws_region'])
+
+class S3FileManager:
+    def __init__(self):
+        self.bucket = args['bucket']
+        if not self.bucket:
+            raise ValueError("Environment variable BUCKET is required")
+
+        region = args['aws_region']
+
+        client_params = {
+            "service_name": "s3",
+            "region_name": region,
+        }
+
+        self.s3 = boto3.client(**client_params)
+
+
+    def load_json(self, key: str) -> dict:
+        """
+        Loads JSON data from a file.
+
+        Args:
+            key (str): Key or Path to the JSON file.
+        Returns:
+            dict: Parsed JSON data as a dictionary.
+                  Returns an empty dictionary if the file does not exist,
+                  if the JSON is invalid, or if an unexpected error occurs.
+        """
+        try:
+            response = self.s3.get_object(Bucket=self.bucket, Key=key)
+            content = response["Body"].read().decode("utf-8")
+            return json.loads(content)
+        except ClientError as e:
+            pass
+        except json.JSONDecodeError:
+            print(f"[ERROR] Invalid JSON in S3 object: {key}")
+        except Exception as e:
+            print(f"[ERROR] Unexpected error: {e}")
+        return {}
+
+
+    def save_json(self, data: dict, key: str) -> None:
+        """
+        Saves a dictionary as a JSON file at the specified key or path.
+        Creates directories if they do not exist.
+
+        Args:
+            data (dict): Data to save.
+            key (str): Key or Path where the JSON file will be stored.
+        """
+        try:
+            self.s3.put_object(
+                Bucket=self.bucket,
+                Key=key,
+                Body=json.dumps(data, ensure_ascii=False, indent=4),
+                ContentType="application/json",
+            )
+        except Exception as e:
+            print(f"[ERROR] Saving JSON to S3: {e}")
+
+
+    def list_files(self, prefix: str, extension: str = ".json") -> List[str]:
+        """
+        Return a sorted list of files in the given folder that match the provided extension.
+        This function:
+          - Collects files pattern: `*{extension}`.
+          - Sorts results in ascending order by filename (lexicographic).
+          - Returns an empty list when no files match.
+        Parameters
+            prefix: str
+                Absolute or relative path to the target folder.
+            extension : str, optional
+                File extension to match (default: ".json"). The value is appended directly to
+                the glob pattern `*{extension}`; for reliable matching use a leading dot,
+                e.g., ".json", ".txt".
+        Returns
+            List[pathlib.Path]
+                A list of `Path` objects representing matching files. If the folder does not
+                exist or no files match, returns an empty list.
+        """
+        try:
+            response = self.s3.list_objects_v2(Bucket=self.bucket, Prefix=prefix)
+
+            if "Contents" not in response:
+                return []
+
+            return sorted(
+                obj["Key"]
+                for obj in response["Contents"]
+                if obj["Key"].endswith(extension)
+            )
+
+        except Exception as e:
+            print(f"[ERROR] Listing files in S3: {e}")
+            return []

commons_metrics/text_simplifier.py

@@ -0,0 +1,48 @@
+import html
+import json
+import re
+
+
+def compact_data(data: dict) -> str:
+    """
+    Removes keys with empty values (None, "", [], {}) from a dictionary
+    and returns a compact JSON string without unnecessary spaces.
+
+    Args:
+        data(dict): Original dictionary.
+    Returns:
+        str: Compact JSON representation of the filtered dictionary.
+    """
+    data = {k: v for k, v in data.items() if v not in (None, "", [], {})}
+    return json.dumps(data, separators=(",", ":"))
+
+def clear_text(text: str) -> str:
+    """
+    Cleans text by removing HTML tags, Markdown links,
+    decoding HTML characters, removing escaped quotes, and
+    normalizing spaces.
+
+    Args:
+        text (str): Original text.
+    Returns:
+        str: Cleaned and simplified text.
+    """
+    if not text:
+        return ""
+
+    # Remove HTML tags
+    text = re.sub(r'<[^>]+>', '', text)
+
+    # Replace Markdown links [Text](URLxt
+    text = re.sub(r'\[([^\]]+)\]\([^)]+\)', r'\1', text)
+
+    # Decode HTML characters (&nbsp;, &lt;, etc.)
+    text = html.unescape(text)
+
+    # Remove escaped quotes
+    text = text.replace('\\"', '"').replace("\\'", "'")
+
+    # Remove line breaks, tabs, and multiple spaces
+    text = re.sub(r'\s+', ' ', text).strip()
+
+    return text

commons_metrics/variable_finder.py

@@ -0,0 +1,187 @@
+import re
+
+from typing import Optional
+
+
+def extract_issue_number(pr_body: str):
+    """
+    Extracts an issue number from a pull request body text.
+    Looks for a pattern like '#123' preceded by whitespace.
+
+    Args:
+        pr_body (str): The pull request body text.
+    Returns:
+        Optional[int]: The extracted issue number as an integer, or None if not found.
+    """
+    match = re.search(r"\s+#(\d+)", pr_body or "", re.IGNORECASE)
+    return int(match.group(1)) if match else None
+
+
+def get_code(text: str) -> Optional[str]:
+    """
+    Extracts a code matching the pattern 'AW1234567' or 'NU1234567' from a string.
+    The code consists of two uppercase letters followed by seven digits.
+
+    Args:
+        text (str): The input string.
+    Returns:
+        Optional[str]: The extracted code or None if not found.
+    """
+    for tok in text.split('_'):
+        if re.fullmatch(r'[A-Z]{2}\d{7}', tok):
+            return tok
+    return None
+
+
+def get_component_name(text: str) -> Optional[str]:
+    """
+    Extracts a component name from a string based on underscore-separated parts.
+    If the last part is 'dxp', returns the two preceding parts joined by underscore.
+    Otherwise, returns the last two parts.
+
+    Args:
+        text (str): The input string.
+    Returns:
+        Optional[str]: The component name or None if not enough parts.
+    """
+    parts = [p for p in text.strip('_').split('_') if p]
+    if len(parts) >= 2:
+        if parts[-1].lower() == "dxp":
+            return f"{parts[-3]}_{parts[-2]}"
+        return '_'.join(parts[-2:])
+    return None
+
+
+def get_component_name_from_image(image: str, release_name: str) -> Optional[str]:
+    """
+    Extracts the component name from an image string.
+    If extraction fails, falls back to using release_name.
+
+    Args:
+        image (str): The image string (e.g., 'repo/component:tag').
+        release_name (str): The fallback release name.
+    Returns:
+        Optional[str]: The component name.
+    """
+    try:
+        tag = image.split('/')[-1]
+        repository_name = tag.split(':')[0]
+        return repository_name
+    except Exception:
+        return get_component_name(release_name)
+
+
+def collect_all_variables(json_data, txt_variable_groups):
+    """
+    Collects all variables from a nested JSON structure.
+    Searches for keys named 'variables' and merges them into a single dictionary.
+
+    Args:
+        json_data (dict or list): The JSON data.
+        txt_variable_groups (str): The key name for variable groups.
+    Returns:
+        dict: A dictionary of all variables found.
+    """
+    all_variables = {}
+
+    def loop_through_json(data):
+        if isinstance(data, dict):
+            for key, value in data.items():
+                if key == 'variables':
+                    all_variables.update(value)
+                elif key == txt_variable_groups:
+                    if isinstance(value, list):
+                        for group in value:
+                            if isinstance(group, dict) and 'variables' in group:
+                                all_variables.update(group['variables'])
+                else:
+                    loop_through_json(value)
+        elif isinstance(data, list):
+            for item in data:
+                loop_through_json(item)
+
+    loop_through_json(json_data)
+    return all_variables
+
+
+def resolve_value(value: str, all_variables: dict, visited=None) -> str:
+    """
+    Resolves variable references in a string recursively.
+    Variables are referenced using the format $(VAR_NAME).
+
+    Args:
+        value (str): The string containing variable references.
+        all_variables (dict): Dictionary of variables and their values.
+        visited (set): Set of visited variables to detect cycles.
+    Returns:
+        str: The resolved string with all references replaced.
+    """
+    if visited is None:
+        visited = set()
+
+    pattern = re.compile(r'\$\(([^)]+)\)')
+    while True:
+        matches = pattern.findall(value)
+        if not matches:
+            break
+        for match in matches:
+            if match in visited:
+                return f'$(CYCLE:{match})'
+            visited.add(match)
+            replacement = all_variables.get(match, {}).get('value', '')
+            resolved = resolve_value(replacement, all_variables, visited.copy())
+            value = value.replace(f'$({match})', resolved)
+    return value
+
+
+def search_in_json(search_value: str, search_type: str, json_data, is_json_from_azure: bool = False) -> Optional[str]:
+    """
+    Searches for a variable in a nested JSON structure by key or value.
+    Resolves references if found.
+
+    Args:
+        search_value (str): The value to search for.
+        search_type (str): 'clave' to search by key, 'valor' to search by value.
+        json_data (dict or list): The JSON data.
+        is_json_from_azure (bool): Whether the JSON is from Azure (changes key names).
+    Returns:
+        Optional[str]: The resolved value if found, otherwise None.
+    """
+    txt_variable_groups = 'variableGroups' if is_json_from_azure else 'variable_groups'
+    search_value = search_value.lower()
+    all_variables = collect_all_variables(json_data, txt_variable_groups)
+
+    result_search = all_variables.get(search_value, {}).get('value', '')
+    if result_search and '$(' not in result_search:
+        return result_search
+
+    def recursive_search(data):
+        if isinstance(data, dict):
+            for key, value in data.items():
+                if key in ['variables', txt_variable_groups]:
+                    if isinstance(value, dict):
+                        for var_key, var_value in value.items():
+                            if search_type == 'clave' and search_value == var_key.lower():
+                                return resolve_value(var_value.get('value', ''), all_variables)
+                            elif search_type == 'valor' and search_value == var_value.get('value', '').lower():
+                                return resolve_value(var_value.get('value', ''), all_variables)
+                    elif isinstance(value, list):
+                        for item in value:
+                            if isinstance(item, dict) and 'variables' in item:
+                                for var_key, var_value in item['variables'].items():
+                                    if search_type == 'clave' and search_value == var_key.lower():
+                                        return resolve_value(var_value.get('value', ''), all_variables)
+                                    elif search_type == 'valor' and search_value == var_value.get('value', '').lower():
+                                        return resolve_value(var_value.get('value', ''), all_variables)
+                else:
+                    result = recursive_search(value)
+                    if result:
+                        return result
+        elif isinstance(data, list):
+            for item in data:
+                result = recursive_search(item)
+                if result:
+                    return result
+        return None
+
+    return recursive_search(json_data)

{commons_metrics-0.0.16.dist-info → commons_metrics-0.0.18.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: commons_metrics
-Version: 0.0.16
+Version: 0.0.18
 Summary: A simple library for basic statistical calculations
 Author: Bancolombia
 Author-email: omar.david.pino@email.com

commons_metrics-0.0.18.dist-info/RECORD

@@ -0,0 +1,19 @@
+commons_metrics/__init__.py,sha256=zLT4kmogcGARPf9DuuBv_r72fwAdvy5ff9y3CNAOnyk,434
+commons_metrics/azure_devops_client.py,sha256=sD130ggzZWUsNqkBVNrLH80_AN00CxQ4preP9sBdzHM,16778
+commons_metrics/cache_manager.py,sha256=ARZBqUCGzpNeQuU2ixd8gu_kqW4PYujnN8Ve9EdIG00,2249
+commons_metrics/commons_repos_client.py,sha256=SYIe1fFXM3qlc_G154AmorHScPS3rTsztKqxy3dD28w,4150
+commons_metrics/connection_database.py,sha256=JvmEuhnnaE3MyQJfN4nXZzVuXB-hfWUAbJq4DEKVtO8,680
+commons_metrics/database.py,sha256=570TtLZ9psNzvIp75UFLYph34cKVEz6eGJgxXyRyjW4,1285
+commons_metrics/date_utils.py,sha256=owKtefTWQ6zT-a3ssurPlphjfjGyxtwrZ_EuFkrPhf0,2265
+commons_metrics/github_api_client.py,sha256=yPLsqn_KvQDIXcNp7Ma8qQwWy8svpXNLpDX69vwL9BU,11465
+commons_metrics/repositories.py,sha256=4hSA51Ft1qcZvHtNta_QKSkHIe78JmsVlKcihzkBcb4,9476
+commons_metrics/s3_file_manager.py,sha256=qyviGsLKuNWeEPtHpITfbL62RmPeuf5CZTzHBnAUS_U,3489
+commons_metrics/text_simplifier.py,sha256=U0oVy2tpOOin5MbfK-9R3euy2P_SkR0b8chto-qy0_M,1257
+commons_metrics/update_design_components.py,sha256=QpY0GCCCMjdYOZ7b8oNigU9iTpiGx91CYsyWwN8WVDA,7660
+commons_metrics/util.py,sha256=98zuynalXumQRh-BB0Bcjyoh6vS2BTOUM8tVgr7iS9Q,1225
+commons_metrics/variable_finder.py,sha256=fTy4njbvZcwBgRDc3MbKejUJkgJS2Mj1ByzRtvS9uV8,7101
+commons_metrics-0.0.18.dist-info/licenses/LICENSE,sha256=jsHZ2Sh1wCL74HC25pDDGXCyQ0xgsTAy62FvEnehKIg,1067
+commons_metrics-0.0.18.dist-info/METADATA,sha256=bRiZoXClNrqzTcwgjQI9ozHnd5mLofczOH9lv3Xk4AE,402
+commons_metrics-0.0.18.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+commons_metrics-0.0.18.dist-info/top_level.txt,sha256=lheUN-3OKdU3A8Tg8Y-1IEB_9i_vVRA0g_FOiUsTQz8,16
+commons_metrics-0.0.18.dist-info/RECORD,,

commons_metrics-0.0.16.dist-info/RECORD

@@ -1,13 +0,0 @@
-commons_metrics/__init__.py,sha256=Ka0Uux56IH7Uikg7fh2aAUVRgJl82pulWscsWfi-LO4,434
-commons_metrics/azure_devops_client.py,sha256=sD130ggzZWUsNqkBVNrLH80_AN00CxQ4preP9sBdzHM,16778
-commons_metrics/commons_repos_client.py,sha256=SYIe1fFXM3qlc_G154AmorHScPS3rTsztKqxy3dD28w,4150
-commons_metrics/database.py,sha256=570TtLZ9psNzvIp75UFLYph34cKVEz6eGJgxXyRyjW4,1285
-commons_metrics/github_api_client.py,sha256=yPLsqn_KvQDIXcNp7Ma8qQwWy8svpXNLpDX69vwL9BU,11465
-commons_metrics/repositories.py,sha256=4hSA51Ft1qcZvHtNta_QKSkHIe78JmsVlKcihzkBcb4,9476
-commons_metrics/update_design_components.py,sha256=QpY0GCCCMjdYOZ7b8oNigU9iTpiGx91CYsyWwN8WVDA,7660
-commons_metrics/util.py,sha256=98zuynalXumQRh-BB0Bcjyoh6vS2BTOUM8tVgr7iS9Q,1225
-commons_metrics-0.0.16.dist-info/licenses/LICENSE,sha256=jsHZ2Sh1wCL74HC25pDDGXCyQ0xgsTAy62FvEnehKIg,1067
-commons_metrics-0.0.16.dist-info/METADATA,sha256=AoaNTjvaQG_q_tS7icKlYlFIZEuAn8aeL0-mERjZEOk,402
-commons_metrics-0.0.16.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-commons_metrics-0.0.16.dist-info/top_level.txt,sha256=lheUN-3OKdU3A8Tg8Y-1IEB_9i_vVRA0g_FOiUsTQz8,16
-commons_metrics-0.0.16.dist-info/RECORD,,