extracting dimensions from epr

etl/customers/stonewater/Wave 3 Preparation.py

@@ -16,6 +16,7 @@ def extract_summary_report(pdf_path):
     - Fuel Bill
     - Address
     """
+    blah
     data = {
         "Address": None,
         "Postcode": None,
@@ -56,8 +57,8 @@ def extract_summary_report(pdf_path):
         data["Number of Storeys"] = int(storeys_match.group(1))
 
         # Extract Carbon Emissions
-        carbon_match = re.search(r"Emissions \(t/year\):\s*([\d.]+)\s*tonnes", text)
-        data["Carbon Emissions (t/year)"] = float(carbon_match.group(1))
+        # carbon_match = re.search(r"Emissions \(t/year\):\s*([\d.]+)\s*tonnes", text)
+        # data["Carbon Emissions (t/year)"] = float(carbon_match.group(1))
 
         # Extract Fuel Bill
         fuel_bill_match = re.search(r"Fuel Bill:\s*£(\d+)", text)
@@ -204,6 +205,69 @@ def extract_window_age_description(windows_text):
     }
 
 
+def extract_building_parts_epr(text):
+    """
+    Extracts building parts and associated dimensions from the provided PDF file.
+    Each building part (main and extensions) includes floor area, room height, perimeter, and party wall length.
+    """
+    data = []
+
+    # Pattern to locate each "Building part" section
+    building_part_pattern = re.compile(
+        r"Construction details: Building part: (.*?)\nFloor Area \[m2\] Room Height \[m\] Perimeter \[m\] Party "
+        r"Wall Length \[m\]\n(.*?)(?=Construction details|Data inputs|$)",
+        re.DOTALL
+    )
+
+    # Extract each building part
+    for match in building_part_pattern.finditer(text):
+        part_name = match.group(1).strip()
+        # Clean up building part name to keep only the descriptor (e.g., "Main" or "1st Extension")
+        cleaned_part_name = re.sub(r" - built in.*", "", part_name)
+
+        floor_data = match.group(2)
+
+        # Pattern to match each floor's measurements
+        floor_pattern = re.compile(
+            r"(Lowest floor|First floor)\s+([\d.]+)\s+([\d.]+)\s+([\d.]+)\s+([\d.]+)"
+        )
+
+        # Extract floor details for each building part
+        for floor_match in floor_pattern.finditer(floor_data):
+            floor_level = floor_match.group(1)
+            floor_area = float(floor_match.group(2))
+            room_height = float(floor_match.group(3))
+            perimeter = float(floor_match.group(4))
+            party_wall_length = float(floor_match.group(5))
+
+            # Append to data
+            data.append({
+                "Building Part": cleaned_part_name,
+                "Floor Level": floor_level,
+                "Floor Area (m2)": floor_area,
+                "Room Height (m)": room_height,
+                "Perimeter (m)": perimeter,
+                "Party Wall Length (m)": party_wall_length
+            })
+
+    # We now extract out the aggregated data
+
+    main_building = [part for part in data if "Main" in part["Building Part"]]
+    first_extension = [part for part in data if "1st Extension" in part["Building Part"]]
+    dimensions = {
+        "Total Floor Area (m2)": sum([part["Floor Area (m2)"] for part in data]),
+        "Total Ground Floor Area": sum(
+            [part["Floor Area (m2)"] for part in data if "Lowest floor" in part["Floor Level"]]
+        ),
+        "RIR Floor Area": 0,
+        "Main Building Wall Area (m2)": sum([x["Perimeter (m)"] * x["Room Height (m)"] for x in main_building]),
+        "First Extension Wall Area (m2)": sum(
+            [x["Perimeter (m)"] * x["Room Height (m)"] for x in first_extension]) if first_extension else 0,
+    }
+
+    return dimensions
+
+
 def extract_epr(pdf_path):
     """
     Extracts specific data from an Energy Report (EPR) PDF file.
@@ -212,6 +276,7 @@ def extract_epr(pdf_path):
         "Address": None,
         "Postcode": None,
         "Current SAP Rating": None,
+        "Primary Energy Use (kWh/yr)": None,
         "Primary Energy Use Intensity (kWh/m2/yr)": None,
         "Number of Storeys": None,
         "Fuel Bill": None,
@@ -232,6 +297,11 @@ def extract_epr(pdf_path):
         "Existing Secondary Heating % of Heat": None,
         "Secondary Heating Code": None,
         "Water Heating Code": None,
+        'Total Floor Area (m2)': None,
+        'Total Ground Floor Area': None,
+        'RIR Floor Area': None,
+        'Main Building Wall Area (m2)': None,
+        'First Extension Wall Area (m2)': None
     }
 
     with open(pdf_path, "rb") as file:
@@ -336,6 +406,9 @@ def extract_epr(pdf_path):
             window_data = extract_window_age_description(windows_text)
             data.update(window_data)
 
+        building_parts = extract_building_parts_epr(text)
+        data.update(building_parts)
+
     return data
 
 
@@ -465,7 +538,7 @@ def main():
                 if summary_data:
                     summary_data = {
                         "survey_folder": survey_folder,
-                        **summary_data
+                        **summary_data,
                     }
                     extracted_data.append(summary_data)
                     continue
@@ -474,11 +547,12 @@ def main():
                 continue
 
         # If no retrofit folder or it was empty, check files in survey_folder
+
         summary_data = extract_retrofit_pdfs(data_folder_path=survey_folder_path)
         if summary_data:
             summary_data = {
                 "survey_folder": survey_folder,
-                **summary_data
+                **summary_data,
             }
             extracted_data.append(summary_data)