adding file detection for elmhurst project handover

etl/lodgement/app.py

@@ -98,7 +98,8 @@ def handler():
         "osmosis condition report": OsmosisConditionReportParser,
         "elmhurst evidence report": None,
         "full sap xml": FullSapParser,
-        "pulse air permeability": file_extraction_tools.PulseAirPermeabilityExtractor
+        "pulse air permeability": file_extraction_tools.PulseAirPermeabilityExtractor,
+        "elmhurst project handover": file_extraction_tools.ElmhurstProjectHandoverExtractor,
     }
 
     extracted = []
@@ -159,6 +160,32 @@ def handler():
 
                 extracted_contents[report_type] = file_extractor(filepath).extract()
 
+        lodgement_folder = os.path.join(
+            property_folder_path, [f for f in subfolders if "TrustMark Lodgement" in f][0]
+        )
+        # Within the lodgement folder, we want the required documents sub-folder
+        lodgement_subfolders = [
+            file for file in os.listdir(lodgement_folder) if os.path.isdir(os.path.join(lodgement_folder, file))
+        ]
+        required_documents_folder = os.path.join(
+            lodgement_folder, [f for f in lodgement_subfolders if "required documents" in f.lower()][0]
+        )
+        # List the contents
+        required_documents_contents = [
+            file for file in os.listdir(required_documents_folder) if
+            os.path.isfile(os.path.join(required_documents_folder, file))
+        ]
+
+        # There are only a few file types we actually want to process in here for the moment
+        for filename in required_documents_contents:
+            filepath = os.path.join(required_documents_folder, filename)
+            if file_extraction_tools.is_pdf(filepath):
+                report_type = file_extraction_tools.detect_pdf_report_type(pdf_path=filepath)
+                if report_type != "elmhurst project handover":
+                    continue
+                blah
+                file_extractor = extractors[report_type]
+
         output_row_data = output_template.copy()
 
         # dict_keys([ 'City/County', 'District/Town',

utils/file_data_extraction.py

@@ -50,6 +50,13 @@ def is_pulse_air_permeability(text):
     return text.startswith("Air Permeability Test Report @O PULSE")
 
 
+def is_elmhurst_project_handover(text):
+    """
+    Determines if the provided text indicates that the PDF is an Elmhurst Project Handover Report.
+    """
+    return "Retrofit_Project_Handover" in text or "Retrofit Project Handover" in text
+
+
 def detect_pdf_report_type(pdf_path):
     """
     Detects the type of report based on content or filename.
@@ -78,6 +85,8 @@ def detect_pdf_report_type(pdf_path):
         return "elmhurst evidence report"
     elif is_pulse_air_permeability(first_page_text):
         return "pulse air permeability"
+    elif is_elmhurst_project_handover(first_page_text):
+        return "elmhurst project handover"
 
     return None
 
@@ -1057,3 +1066,15 @@ class PulseAirPermeabilityExtractor:
         }
 
         return data
+
+
+class ElmhurstProjectHandoverExtractor:
+    """
+    A utility class for extracting specific data from The Elmhurst Project Handover document
+    """
+
+    def __init__(self, file_path):
+        self.file_path = file_path
+
+    def extract(self):
+        pass