wizata-dsapi 2.1.0.dev5__tar.gz → 2.1.0.dev7__tar.gz

{wizata_dsapi-2.1.0.dev5 → wizata_dsapi-2.1.0.dev7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: wizata_dsapi
-Version: 2.1.0.dev5
+Version: 2.1.0.dev7
 Summary: Wizata Data Science Toolkit
 Author: Wizata S.A.
 Author-email: info@wizata.com

{wizata_dsapi-2.1.0.dev5 → wizata_dsapi-2.1.0.dev7}/wizata_dsapi/execution_log.py

@@ -79,7 +79,9 @@ class ExecutionLog(Dto):
             message=data.get("message"),
             messages=data.get("messages"),
             timestamp=int(data["timestamp"]) if "timestamp" in data and data["timestamp"] is not None else None,
-            level=data.get("level")
+            level=data.get("level"),
+            branch=data.get("branch"),
+            sha=data.get("sha"),
         )
 
     def __init__(self,
@@ -104,6 +106,8 @@ class ExecutionLog(Dto):
                  message: str = None,
                  messages: list = None,
                  level: str = None,
+                 branch: str = None,
+                 sha: str = None,
                  ):
 
         # labels
@@ -134,12 +138,18 @@ class ExecutionLog(Dto):
         self.edge_device_id = edge_device_id
         self.status = status
         self.level = level
+        # git branch this run TARGETS (which version to execute) — a label so
+        # runs are queryable per branch. None = default branch / non-git.
+        self.branch = branch
 
         # values
         if execution_id is None:
             execution_id = uuid.uuid4()
         self.execution_id = execution_id
         self.pipeline_image_id = pipeline_image_id
+        # resolved commit SHA the run executed — INFO only, from the branch HEAD
+        # (git) or the image id. Not a target.
+        self.sha = sha
         self.timestamp = timestamp
         self.started_date = started_date
         self.queued_date = queued_date
@@ -428,7 +438,8 @@ class ExecutionLog(Dto):
             "twin": self.get_twin_key(),
             "edgeDeviceId": self.edge_device_id,
             "status": self.status.value if hasattr(self.status, 'value') else self.status,
-            "level": self.level
+            "level": self.level,
+            "branch": self.branch,
         }
         return {k: v for k, v in labels.items() if v is not None}
 
@@ -443,6 +454,7 @@ class ExecutionLog(Dto):
             "executionTime": self.execution_time,
             "executionTriggerId": str(self.trigger_id) if self.trigger_id else None,
             "version": self.version,
+            "sha": self.sha,
             "message": self.message,
             "messages": self.messages or None
         }

{wizata_dsapi-2.1.0.dev5 → wizata_dsapi-2.1.0.dev7}/wizata_dsapi/scripts/common.py

@@ -323,10 +323,24 @@ def formula(context: wizata_dsapi.Context):
     expression = context.properties["expression"]
     result = context.properties.get("result", "result")
 
-    # Whitelist validation: strip everything we allow, flag any leftover token.
-    sanitized = expression
-    for col in sorted(df.columns, key=len, reverse=True):
-        sanitized = sanitized.replace(f"`{col}`", "").replace(col, "")
+    # Replace every column name (backticked or bare) with a safe placeholder
+    # identifier before evaluation. Column names can contain characters that
+    # are illegal in a Python/pandas eval expression — e.g. tag IDs like
+    # 'DE_AL_Ark1_1:04800F1?Value', whose numeric segment '04800' is otherwise
+    # parsed as a leading-zero integer literal and raises a SyntaxError
+    # (DEV-5912). Substituting the whole name atomically sidesteps this.
+    placeholders = {}  # placeholder -> real column name
+    substituted = expression
+    for i, col in enumerate(sorted(df.columns, key=len, reverse=True)):
+        placeholder = f"__wz_col_{i}__"
+        substituted = substituted.replace(f"`{col}`", placeholder).replace(col, placeholder)
+        placeholders[placeholder] = col
+
+    # Whitelist validation: strip placeholders + allowed functions, flag any
+    # leftover token as disallowed.
+    sanitized = substituted
+    for placeholder in placeholders:
+        sanitized = sanitized.replace(placeholder, "")
     for fn in _FORMULA_SAFE_FUNCTIONS:
         sanitized = sanitized.replace(fn, "")
     sanitized = re.sub(r"[\d\.\+\-\*/\%\(\)\s,\^]", "", sanitized)
@@ -337,7 +351,9 @@ def formula(context: wizata_dsapi.Context):
             f"{list(_FORMULA_SAFE_FUNCTIONS.keys())}"
         )
 
-    df[result] = df.eval(expression, local_dict=_FORMULA_SAFE_FUNCTIONS, engine="python")
+    # Evaluate against a frame whose columns are the safe placeholder names.
+    safe_df = df.rename(columns={real: ph for ph, real in placeholders.items()})
+    df[result] = safe_df.eval(substituted, local_dict=_FORMULA_SAFE_FUNCTIONS, engine="python")
     return df
 
 

wizata_dsapi-2.1.0.dev7/wizata_dsapi/version.py

@@ -0,0 +1 @@
+__version__ = "2.1.0.dev7"

{wizata_dsapi-2.1.0.dev5 → wizata_dsapi-2.1.0.dev7}/wizata_dsapi.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: wizata_dsapi
-Version: 2.1.0.dev5
+Version: 2.1.0.dev7
 Summary: Wizata Data Science Toolkit
 Author: Wizata S.A.
 Author-email: info@wizata.com

wizata_dsapi-2.1.0.dev5/wizata_dsapi/version.py

@@ -1 +0,0 @@
-__version__ = "2.1.0.dev5"