kubernetes-watch 0.1.8__tar.gz → 0.1.10__tar.gz

{kubernetes_watch-0.1.8 → kubernetes_watch-0.1.10}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: kubernetes-watch
-Version: 0.1.8
+Version: 0.1.10
 Summary: 
 Author: bmotevalli
 Author-email: b.motevalli@gmail.com
@@ -81,6 +81,14 @@ workflow:
       inputsArgType: arg
       conditional:
         tasks: ["Task_B"]
+
+    - name: Task_external
+      module: <module_external_path>
+      plugin_path: <path_to_module>
+      task: <func_name>
+      inputsArgType: arg
+      conditional:
+        tasks: ["Task_B"]
 ```
 
 
@@ -88,6 +96,10 @@ workflow:
 
 **module**: all modules are located in 'modules' directory in kube_watch. This is where you can extend the library and add new tasks / modules. Below modules, there are submodules such as providers, clusters, and logic. Within each of this submodules, specific modules are defined. For example: providers.aws contains a series of tasks related to AWS. In this case, <module_path> = providers.aws. To add new tasks, add a new module with a similar pattern and refer the path in your task block. 
 
+**plugin_path**: you can add new funtions outside the library without needing to modify this library. If plugin_path is defined, the
+library assumes you are referring to a module outside the library (e.g. in your app or workflow). The plugin_path is path to your
+py script (the folder). Then, provide your script name as module and function name as task.
+
 **task**: task is simply the name function that you put in the <module_path>. i.e. as you define a function in a module, you can simply start to use it in your manifests.
 
 **inputArgType**: arg | dict | list: if the task functions accept known-fixed number of parameters, then use arg. 

{kubernetes_watch-0.1.8 → kubernetes_watch-0.1.10}/README.md

@@ -58,6 +58,14 @@ workflow:
       inputsArgType: arg
       conditional:
         tasks: ["Task_B"]
+
+    - name: Task_external
+      module: <module_external_path>
+      plugin_path: <path_to_module>
+      task: <func_name>
+      inputsArgType: arg
+      conditional:
+        tasks: ["Task_B"]
 ```
 
 
@@ -65,6 +73,10 @@ workflow:
 
 **module**: all modules are located in 'modules' directory in kube_watch. This is where you can extend the library and add new tasks / modules. Below modules, there are submodules such as providers, clusters, and logic. Within each of this submodules, specific modules are defined. For example: providers.aws contains a series of tasks related to AWS. In this case, <module_path> = providers.aws. To add new tasks, add a new module with a similar pattern and refer the path in your task block. 
 
+**plugin_path**: you can add new funtions outside the library without needing to modify this library. If plugin_path is defined, the
+library assumes you are referring to a module outside the library (e.g. in your app or workflow). The plugin_path is path to your
+py script (the folder). Then, provide your script name as module and function name as task.
+
 **task**: task is simply the name function that you put in the <module_path>. i.e. as you define a function in a module, you can simply start to use it in your manifests.
 
 **inputArgType**: arg | dict | list: if the task functions accept known-fixed number of parameters, then use arg. 

kubernetes_watch-0.1.10/kube_watch/modules/logic/checks.py

@@ -0,0 +1,15 @@
+from prefect import get_run_logger
+logger = get_run_logger()
+
+def dicts_has_diff(dict_a, dict_b):
+    return dict_a != dict_b
+
+
+def remove_keys(d, keys):
+    return {k: v for k, v in d.items() if k not in keys}
+
+
+def print_data(data, indicator = None):
+    if indicator:
+        logger.info(indicator)    
+    logger.info(data)

{kubernetes_watch-0.1.8 → kubernetes_watch-0.1.10}/kube_watch/modules/logic/merge.py

@@ -1,6 +1,6 @@
 from typing import Any, List, Dict
 from kube_watch.enums.logic import Operations
-
+from copy import deepcopy
 
 def merge_logical_outputs(inp_dict: Dict):
     if 'operation' not in inp_dict.keys():
@@ -25,7 +25,8 @@ def partial_dict_update(orig_data, new_data):
     This function is used when some key value pairs in orig_data should
     be updated from new_data.
     """
+    orig_data_copy = deepcopy(orig_data)
     for k, v in new_data.items():
-        orig_data[k] = v
+        orig_data_copy[k] = v
 
-    return orig_data
+    return orig_data_copy

kubernetes_watch-0.1.10/kube_watch/modules/providers/git.py

@@ -0,0 +1,109 @@
+import os
+import shutil
+import subprocess
+import tempfile
+from pathlib import Path
+
+from prefect import get_run_logger
+
+logger = get_run_logger()
+
+
+def clone_pat_repo(git_pat, git_url, clone_base_path):
+    """ Clone a Git repository using a Personal Access Token (PAT) for authentication."""
+    # Retrieve environment variables
+    access_token = git_pat # os.environ.get('GIT_PAT')
+    repo_url = git_url # os.environ.get('GIT_URL')
+    
+    if not access_token or not repo_url:
+        raise ValueError("Environment variables GIT_PAT or GIT_URL are not set")
+
+    # Correctly format the URL with the PAT
+    if 'https://' in repo_url:
+        # Splitting the URL and inserting the PAT
+        parts = repo_url.split('https://', 1)
+        repo_url = f'https://{access_token}@{parts[1]}'
+    else:
+        raise ValueError("URL must begin with https:// for PAT authentication")
+
+    # Directory where the repo will be cloned
+    repo_path = os.path.join(clone_base_path, 'manifest-repo')
+
+    # Clone the repository
+    if not os.path.exists(repo_path):
+        logger.info(f"Cloning repository into {repo_path}")
+        repo = Repo.clone_from(repo_url, repo_path)
+        logger.info("Repository cloned successfully.")
+    else:
+        logger.info(f"Repository already exists at {repo_path}")
+
+
+def clone_ssh_repo(
+    git_url: str,
+    clone_base_path: str,
+    repo_dir_name: str = "manifest-repo",
+    depth: int = 1,
+    ssh_key_env: str = "GIT_SSH_PRIVATE_KEY",
+    known_hosts_env: str = "GIT_SSH_KNOWN_HOSTS",
+) -> Path:
+    """
+    Clone/update a repo via SSH using key + known_hosts from env vars.
+    - GIT_SSH_PRIVATE_KEY: full private key (BEGIN/END ...)
+    - GIT_SSH_KNOWN_HOSTS: lines from `ssh-keyscan github.com`
+    """
+    if not git_url.startswith("git@"):
+        raise ValueError("git_url must be an SSH URL like 'git@github.com:org/repo.git'")
+
+    priv_key = os.environ.get(ssh_key_env)
+    kh_data  = os.environ.get(known_hosts_env)
+    if not priv_key:
+        raise ValueError(f"Missing env var {ssh_key_env}")
+    if not kh_data:
+        raise ValueError(f"Missing env var {known_hosts_env}")
+
+    base = Path(clone_base_path).expanduser().resolve()
+    base.mkdir(parents=True, exist_ok=True)
+    repo_path = base / repo_dir_name
+
+    tmpdir = Path(tempfile.mkdtemp(prefix="git_ssh_"))
+    key_path = tmpdir / "id_rsa"
+    kh_path  = tmpdir / "known_hosts"
+
+    try:
+        key_path.write_text(priv_key, encoding="utf-8")
+        kh_path.write_text(kh_data, encoding="utf-8")
+        try:
+            os.chmod(key_path, 0o600)
+        except PermissionError:
+            pass  # ignore on platforms where chmod doesn't apply
+
+        # Note: no StrictModes here
+        ssh_cmd = (
+            f"ssh -i {key_path} -o IdentitiesOnly=yes "
+            f"-o UserKnownHostsFile={kh_path} "
+            f"-o StrictHostKeyChecking=yes"
+        )
+
+        env = os.environ.copy()
+        env["GIT_SSH_COMMAND"] = ssh_cmd
+
+        if not repo_path.exists():
+            cmd = ["git", "clone"]
+            if depth and depth > 0:
+                cmd += ["--depth", str(depth)]
+            cmd += [git_url, str(repo_path)]
+            subprocess.check_call(cmd, env=env)
+        else:
+            if not (repo_path / ".git").exists():
+                raise RuntimeError(f"Path exists but is not a git repo: {repo_path}")
+            subprocess.check_call(["git", "remote", "set-url", "origin", git_url], cwd=repo_path, env=env)
+            subprocess.check_call(["git", "fetch", "--all", "--prune"], cwd=repo_path, env=env)
+            subprocess.check_call(["git", "pull", "--ff-only", "origin"], cwd=repo_path, env=env)
+
+        return repo_path
+
+    finally:
+        try:
+            shutil.rmtree(tmpdir)
+        except Exception:
+            pass

{kubernetes_watch-0.1.8 → kubernetes_watch-0.1.10}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "kubernetes-watch"
-version = "0.1.8"
+version = "0.1.10"
 description = ""
 authors = ["bmotevalli <b.motevalli@gmail.com>"]
 packages = [{include = "kube_watch"}]

kubernetes_watch-0.1.8/kube_watch/modules/logic/checks.py

@@ -1,8 +0,0 @@
-
-
-def dicts_has_diff(dict_a, dict_b):
-    return dict_a != dict_b
-
-
-def remove_keys(d, keys):
-    return {k: v for k, v in d.items() if k not in keys}

kubernetes_watch-0.1.8/kube_watch/modules/providers/git.py

@@ -1,33 +0,0 @@
-import os
-from git import Repo
-
-from prefect import get_run_logger
-
-logger = get_run_logger()
-
-def clone_repo(git_pat, git_url, clone_base_path):
-    # Retrieve environment variables
-    access_token = git_pat # os.environ.get('GIT_PAT')
-    repo_url = git_url # os.environ.get('GIT_URL')
-    
-    if not access_token or not repo_url:
-        raise ValueError("Environment variables GIT_PAT or GIT_URL are not set")
-
-    # Correctly format the URL with the PAT
-    if 'https://' in repo_url:
-        # Splitting the URL and inserting the PAT
-        parts = repo_url.split('https://', 1)
-        repo_url = f'https://{access_token}@{parts[1]}'
-    else:
-        raise ValueError("URL must begin with https:// for PAT authentication")
-
-    # Directory where the repo will be cloned
-    repo_path = os.path.join(clone_base_path, 'manifest-repo')
-
-    # Clone the repository
-    if not os.path.exists(repo_path):
-        logger.info(f"Cloning repository into {repo_path}")
-        repo = Repo.clone_from(repo_url, repo_path)
-        logger.info("Repository cloned successfully.")
-    else:
-        logger.info(f"Repository already exists at {repo_path}")