done with summary report extraction

utils/file_data_extraction.py

@@ -801,6 +801,64 @@ class ElmhurstSummaryReportExtractor:
 
         return wall_data
 
+    @staticmethod
+    def extract_conservatory(text):
+        """
+        Extracts conservatory data from the provided text.
+        The section is located between "5.0 Conservatory" and "7.0 Walls".
+
+        Args:
+            text (str): The full text of the Summary Report PDF.
+
+        Returns:
+            dict: A dictionary with conservatory details:
+                - "Conservatory Present"
+                - "Conservatory Separated"
+                - "Conservatory Floor Area"
+                - "Conservatory Double Glazed"
+                - "Conservatory Glazed Perimeter"
+                - "Heated Conservatory Height"
+        """
+
+        # Extract the section between "5.0 Conservatory" and "7.0 Walls"
+        conservatory_match = re.search(r"5\.0 Conservatory:(.*?)7\.0 Walls:", text, re.DOTALL)
+        if not conservatory_match:
+            logger.error("Failed to extract conservatory data.")
+            raise ValueError("Could not extract conservatory data.")
+
+        conservatory_text = conservatory_match.group(1)
+
+        # Check if conservatory is present
+        present_match = re.search(r"Is there a conservatory\?\s*(Yes|No)", conservatory_text, re.IGNORECASE)
+
+        if not present_match or present_match.group(1).strip().lower() == "no":
+            return {
+                "Conservatory Present": "No",
+                "Conservatory Separated": "",
+                "Conservatory Floor Area": 0,
+                "Conservatory Double Glazed": "",
+                "Conservatory Glazed Perimeter": 0,
+                "Heated Conservatory Height": "",
+            }
+
+        # If we get here, raise a temporary exception since we've not seen a case of this, so should make sure
+        # this is correct
+
+        separated_match = re.search(r"Is it thermally separated\?\s*(Yes|No)", conservatory_text, re.IGNORECASE)
+        floor_area_match = re.search(r"Floor Area \[m2\]\s*([\d.]+)", conservatory_text, re.IGNORECASE)
+        double_glazed_match = re.search(r"Double Glazed\s*(Yes|No)", conservatory_text, re.IGNORECASE)
+        glazed_perimeter_match = re.search(r"Glazed Perimeter \[m\]\s*([\d.]+)", conservatory_text, re.IGNORECASE)
+        height_match = re.search(r"Room Height\s*(.*?)(?=\n|$)", conservatory_text, re.IGNORECASE)
+
+        return {
+            "Conservatory Present": "Yes",
+            "Conservatory Separated": separated_match.group(1).strip() if separated_match else "",
+            "Conservatory Floor Area": float(floor_area_match.group(1)) if floor_area_match else 0,
+            "Conservatory Double Glazed": double_glazed_match.group(1).strip() if double_glazed_match else "",
+            "Conservatory Glazed Perimeter": float(glazed_perimeter_match.group(1)) if glazed_perimeter_match else 0,
+            "Heated Conservatory Height": height_match.group(1).strip() if height_match else "",
+        }
+
     def extract(self):
         """
         Extracts specific data from the provided PDF file.
@@ -810,11 +868,6 @@ class ElmhurstSummaryReportExtractor:
         - Address
         """
 
-        # Expected keys:
-        # dict_keys([
-        # 'Primary Heating', 'Secondary Heating', 'Building Parts', 'Roof Details', 'Wall Details', 'Conservatory',
-        # 'Water Heating Code'])
-
         data = {}
 
         with (open(self.file_path, "rb") as file):
@@ -904,6 +957,7 @@ class ElmhurstSummaryReportExtractor:
             data["Building Parts"] = self.extract_building_parts(text)
             data["Roof Details"] = self.extract_roof_details(text)
             data["Wall Details"] = self.extract_wall_details(text)
+            data["Conservatory"] = self.extract_conservatory(text)
 
             water_heating_code_match = re.search(r"Water Heating Code\s*(.*?)\n", text)
             if not water_heating_code_match:
@@ -911,15 +965,4 @@ class ElmhurstSummaryReportExtractor:
 
             data["Water Heating Code"] = water_heating_code_match.group(1).strip()
 
-            # Get the main building wall data
-            main_building_walls = [wall for wall in walls_data if "Main" in wall["Building Part"]][0]
-            data["Main Wall Type"] = main_building_walls["Wall Type"]
-            data["Main Wall Insulation"] = main_building_walls["Wall Insulation"]
-            data["Main Wall Dry-lining"] = main_building_walls["Wall Dry-lining"]
-            data["Main Wall Thickness"] = main_building_walls["Wall Thickness (mm)"]
-            data["Main Building Alternative Wall Type"] = main_building_walls["Alternative Wall Type"]
-            data["Main Building Alternative Wall Insulation"] = main_building_walls["Alternative Wall Insulation"]
-            data["Main Building Alternative Wall Dry-lining"] = main_building_walls["Alternative Wall Dry-lining"]
-            data["Main Building Alternative Wall Thickness"] = main_building_walls["Alternative Wall Thickness (mm)"]
-
         return data