informatica-python 1.5.1__tar.gz → 1.5.2__tar.gz

{informatica_python-1.5.1 → informatica_python-1.5.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: informatica-python
-Version: 1.5.1
+Version: 1.5.2
 Summary: Convert Informatica PowerCenter workflow XML to Python/PySpark code
 Author: Nick
 License: MIT

{informatica_python-1.5.1 → informatica_python-1.5.2}/informatica_python/__init__.py

@@ -7,7 +7,7 @@ Licensed under the MIT License.
 
 from informatica_python.converter import InformaticaConverter
 
-__version__ = "1.5.1"
+__version__ = "1.5.2"
 __author__ = "Nick"
 __license__ = "MIT"
 __all__ = ["InformaticaConverter"]

{informatica_python-1.5.1 → informatica_python-1.5.2}/informatica_python/converter.py

@@ -90,6 +90,10 @@ class InformaticaConverter:
     def _convert_folder(self, folder: FolderDef, output_dir: str,
                         output_zip: Optional[str] = None,
                         param_file: Optional[str] = None) -> str:
+        if param_file:
+            from informatica_python.utils.expression_converter import parse_param_file
+            parse_param_file(param_file)
+
         files = {}
 
         files["helper_functions.py"] = generate_helper_functions(folder, self.data_lib)

{informatica_python-1.5.1 → informatica_python-1.5.2}/informatica_python/utils/expression_converter.py

@@ -295,8 +295,8 @@ def _vectorize_value(val, df_var="df"):
     return val
 
 
-def _vectorize_condition(cond, df_var="df"):
-    c = cond.strip()
+def _vectorize_simple(part, df_var):
+    c = part.strip()
 
     c = re.sub(r'\bISNULL\s*\(\s*([A-Za-z_]\w*)\s*\)',
                lambda m: f'{df_var}["{m.group(1)}"].isna()', c, flags=re.IGNORECASE)
@@ -305,9 +305,6 @@ def _vectorize_condition(cond, df_var="df"):
     c = re.sub(r'\b([A-Za-z_]\w*)\s*IS\s+NULL\b',
                lambda m: f'{df_var}["{m.group(1)}"].isna()', c, flags=re.IGNORECASE)
 
-    c = re.sub(r'\bAND\b', ' & ', c, flags=re.IGNORECASE)
-    c = re.sub(r'\bOR\b', ' | ', c, flags=re.IGNORECASE)
-    c = re.sub(r'\bNOT\s+', ' ~', c, flags=re.IGNORECASE)
     c = re.sub(r'<>', '!=', c)
     c = re.sub(r'(?<![<>!=])=(?!=)', '==', c)
 
@@ -322,6 +319,45 @@ def _vectorize_condition(cond, df_var="df"):
     return c
 
 
+def _vectorize_condition(cond, df_var="df"):
+    c = cond.strip()
+
+    tokens = re.split(r'\b(AND|OR)\b', c, flags=re.IGNORECASE)
+
+    parts = []
+    ops = []
+    for tok in tokens:
+        stripped = tok.strip()
+        if stripped.upper() in ('AND', 'OR'):
+            ops.append('&' if stripped.upper() == 'AND' else '|')
+        elif stripped:
+            parts.append(stripped)
+
+    if not parts:
+        return "True"
+
+    vectorized = []
+    for part in parts:
+        negate = False
+        inner = part.strip()
+        if re.match(r'^NOT\s+', inner, flags=re.IGNORECASE):
+            negate = True
+            inner = re.sub(r'^NOT\s+', '', inner, flags=re.IGNORECASE).strip()
+        v = _vectorize_simple(inner, df_var)
+        if negate:
+            v = f"~({v})"
+        vectorized.append(v)
+
+    if len(vectorized) == 1:
+        return vectorized[0]
+
+    result_parts = [f"({vectorized[0]})"]
+    for i, op in enumerate(ops):
+        result_parts.append(f" {op} ")
+        result_parts.append(f"({vectorized[i + 1]})")
+    return "".join(result_parts)
+
+
 def convert_filter_expression(expr):
     if not expr or not expr.strip():
         return "True"

{informatica_python-1.5.1 → informatica_python-1.5.2}/informatica_python.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: informatica-python
-Version: 1.5.1
+Version: 1.5.2
 Summary: Convert Informatica PowerCenter workflow XML to Python/PySpark code
 Author: Nick
 License: MIT

{informatica_python-1.5.1 → informatica_python-1.5.2}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "informatica-python"
-version = "1.5.1"
+version = "1.5.2"
 description = "Convert Informatica PowerCenter workflow XML to Python/PySpark code"
 readme = "README.md"
 license = {text = "MIT"}

{informatica_python-1.5.1 → informatica_python-1.5.2}/tests/test_integration.py

@@ -210,10 +210,18 @@ class TestFilterVectorized:
         assert 'df["A"]' in result
         assert 'df["B"]' in result
         assert "AND" not in result
+        assert "(df[" in result
 
     def test_or_condition(self):
         result = convert_filter_vectorized("STATUS = 'A' OR STATUS = 'B'", "df")
         assert "|" in result
+        assert "(df[" in result
+
+    def test_not_condition(self):
+        result = convert_filter_vectorized("NOT A = 1", "df")
+        assert "~(" in result
+        assert 'df["A"]' in result
+        assert "==" in result
 
     def test_is_null_filter(self):
         result = convert_filter_vectorized("NAME IS NULL", "df_src")
@@ -232,6 +240,7 @@ class TestFilterVectorized:
         result = convert_expression_vectorized("IIF(A > 1 AND B < 2, 1, 0)", "df")
         assert "np.where" in result
         assert "&" in result
+        assert "(" in result
 
 
 class TestLibAdapters: