From f141aa4d842a38d8133bdf9b586224333f5372be Mon Sep 17 00:00:00 2001
From: Khalim Conn-Kowlessar <kconnkowlessar@gmail.com>
Date: Thu, 28 Nov 2024 08:42:53 +0000
Subject: [PATCH] extracting windows

---
 utils/file_data_extraction.py | 71 ++++++++++++++++++++++++++++++-----
 1 file changed, 62 insertions(+), 9 deletions(-)

diff --git a/utils/file_data_extraction.py b/utils/file_data_extraction.py
index 2337ea9d..d444bff8 100644
--- a/utils/file_data_extraction.py
+++ b/utils/file_data_extraction.py
@@ -478,6 +478,59 @@ class ElmhurstSummaryReportExtractor:
     def __init__(self, file_path):
         self.file_path = file_path
 
+    @staticmethod
+    def extract_window_age_description(windows_text):
+        """
+        Extracts the most common window age description and its proportion.
+
+        Parameters:
+            windows_text (str): The text section containing window data.
+
+        Returns:
+            dict: A dictionary with the most common window age description and its proportion.
+        """
+        # Clean up windows_text by removing line breaks for better pattern matching
+        windows_text = windows_text.replace("\n", "")
+
+        # Define possible window age descriptions
+        window_descriptions = [
+            "Double post or during 2002",
+            "Double pre 2002",
+            "Double with unknown install date",
+            "Secondary glazing",
+            "Triple glazing",
+            "Single glazing",
+        ]
+
+        # Count occurrences of each description
+        description_counts = Counter()
+        for description in window_descriptions:
+            matches = re.findall(re.escape(description), windows_text)
+            description_counts[description] = len(matches)
+
+        if not description_counts or not sum(description_counts.values()):
+            raise ValueError("Failed to extract window data.")
+
+        # Determine the most common description and calculate its proportion
+        most_common_description, window_count = description_counts.most_common(1)[0]
+        window_proportion = window_count / sum(description_counts.values()) * 100
+
+        # Get the second most common and the proportion
+        if window_proportion == 100:
+            second_most_common_description = None
+            second_most_common_proportion = 0
+        else:
+            second_most_common_description, second_window_count = description_counts.most_common(2)[1]
+            second_most_common_proportion = second_window_count / sum(description_counts.values()) * 100
+
+        return {
+            "Window Age Description": most_common_description,
+            "Window Age Description Proportion (%)": window_proportion,
+            "Secondary Window Age Description": second_most_common_description,
+            "Secondary Window Age Description Proportion (%)": second_most_common_proportion,
+            "Number of Windows": sum(description_counts.values())
+        }
+
     def extract(self):
         """
         Extracts specific data from the provided PDF file.
@@ -488,8 +541,7 @@ class ElmhurstSummaryReportExtractor:
         """
 
         # Expected keys:
-        # dict_keys(['Total Number of Doors', 'Number of Insulated
-        # Doors', 'Number of Light Fittings', 'Number of LEL Fittings', 'Number of fittings needing LEL', 'Windows',
+        # dict_keys(['Windows',
         # 'Primary Heating', 'Secondary Heating', 'Building Parts', 'Roof Details', 'Wall Details', 'Conservatory',
         # 'Water Heating Code'])
 
@@ -569,10 +621,15 @@ class ElmhurstSummaryReportExtractor:
                 raise ValueError("Could not extract number of insulated doors")
             data["Number of Insulated Doors"] = int(insulated_doors_match.group(1))
 
+            # lighting
+            data["Number of Light Fittings"] = int(re.search(r"Total number of light fittings\s*(\d+)", text).group(1))
+            data["Number of LEL Fittings"] = int(re.search(r"Total number of L.E.L. fittings\s*(\d+)", text).group(1))
+            data["Number of fittings needing LEL"] = data["Number of Light Fittings"] - data["Number of LEL Fittings"]
+
             windows_section = re.search(r"Windows\s*(.*?)\s*Draught Proofing", text, re.DOTALL)
-            windows_text = windows_section.group(1)
-            window_data = extract_window_age_description(windows_text)
-            data.update(window_data)
+            if not windows_section:
+                raise ValueError("Failed to extract window data.")
+            data["Windows"] = self.extract_window_age_description(windows_section.group(1))
 
             # Extract heating system
             # Extract Primary Heating Data
@@ -636,10 +693,6 @@ class ElmhurstSummaryReportExtractor:
             dimensions = extract_building_parts_summary(text)
             data.update(dimensions)
 
-            data["Number of Light Fittings"] = int(re.search(r"Total number of light fittings\s*(\d+)", text).group(1))
-            data["Number of LEL Fittings"] = int(re.search(r"Total number of L.E.L. fittings\s*(\d+)", text).group(1))
-            data["Number of fittings needing LEL"] = data["Number of Light Fittings"] - data["Number of LEL Fittings"]
-
             extracted_roof_data = extract_roof_details_summary(text)
             main_roof_data = [roof for roof in extracted_roof_data if "Main" in roof["Building Part"]][0]
             data["Main Roof Type"] = main_roof_data["Roof Type"]