chore:enhance pagination handling for search results

Refactor pagination to use Django Paginator for improved reliability. The context is now updated with pagination details and results are consistently aggregated across all pages for accurate representation.

orp/orp_search/public_gateway.py

@@ -1,12 +1,16 @@
 import logging
 
+from typing import Tuple
+
 import pandas as pd
 import requests  # type: ignore
 
 from jinja2 import Template
 from orp_search.config import SearchDocumentConfig
 from orp_search.dummy_data import get_construction_data_as_dataframe
 
+from django.core.paginator import InvalidPage, Paginator
+
 logger = logging.getLogger(__name__)
 
 
@@ -35,20 +39,40 @@ def _build_like_conditions(self, field, terms):
         """
         return " OR ".join([f"{field} LIKE '%{term}%'" for term in terms])
 
-    def paginate_results(self, config: SearchDocumentConfig, results):
+    def paginate_results(
+        self, config: SearchDocumentConfig, results, context
+    ) -> Tuple[dict, Paginator]:
         """
-        Paginates the search results.
+        Paginates the given search results based on the provided configuration.
 
-        Args:
-            results (list): The search results to paginate.
+        Arguments:
+         config (SearchDocumentConfig): Configuration parameters for search,
+                                        including pagination limits.
+         results: A collection of search results to be paginated.
+         context: A dictionary containing context data which will be updated
+                  with pagination details.
 
         Returns:
-            list: The paginated search results.
-            count: Total number of pages from results
+         A tuple containing:
+          - Updated context dictionary with pagination information.
+          - Paginator instance used for paginating the results.
+
+        The context dictionary is updated with the following keys:
+         is_paginated: A boolean indicating if the results span multiple pages.
+         reports: The paginated results for the current page.
+         paginator: The Paginator instance.
+         page_obj: The current page of results.
         """
-        start = (config.offset - 1) * config.limit
-        end = start + config.limit
-        return results[start:end]
+        paginator = Paginator(results, config.limit)
+        try:
+            paginated_reports = paginator.page(config.offset)
+        except InvalidPage:
+            paginated_reports = paginator.page(1)
+        context["is_paginated"] = paginator.num_pages > 1
+        context["reports"] = paginated_reports
+        context["paginator"] = paginator
+        context["page_obj"] = paginated_reports
+        return context, paginator
 
     def calculate_total_pages(self, config, results_count):
         """
@@ -61,6 +85,7 @@ def calculate_total_pages(self, config, results_count):
         Returns:
             int: The total number of pages.
         """
+
         if config.limit <= 0:
             raise ValueError("limit must be greater than 0")
         return (results_count + config.limit - 1) // config.limit

orp/orp_search/views.py

@@ -174,32 +174,40 @@ def search(request: HttpRequest) -> HttpResponse:
     # on the landing page.
 
     if search_results:
-        paginated_search_results = public_gateway.paginate_results(
-            config, search_results
-        )
-        logger.info(
-            "paginated search results after paginate: %s",
-            paginated_search_results,
+        context, paginator = public_gateway.paginate_results(
+            config, search_results, context
         )
 
+        # Initialize a list to hold all results from all pages
+        paginated_search_results = []
+
+        # Iterate over each page
+        for page_num in paginator.page_range:
+            # Get the page
+            page = paginator.page(page_num)
+            # Add the objects of the current page to the aggregate list
+
+            for result in page.object_list:
+                paginated_search_results.append(
+                    {
+                        "id": result["id"],
+                        "title": result["title"],
+                        "publisher": result["publisher"],
+                        "description": (
+                            result["description"][:100] + "..."
+                            if len(result["description"]) > 100
+                            else result["description"]
+                        ),
+                        "date_issued": result["date_issued"],
+                        "date_modified": result["date_modified"],
+                        "document_type": result["type"],
+                        "regulatory_topics": result["regulatory_topics"].split(
+                            "\n"
+                        ),
+                    }
+                )
+
         # We can use the following code to filter the search_results list:
-        paginated_search_results = [
-            {
-                "id": result["id"],
-                "title": result["title"],
-                "publisher": result["publisher"],
-                "description": (
-                    result["description"][:100] + "..."
-                    if len(result["description"]) > 100
-                    else result["description"]
-                ),
-                "date_issued": result["date_issued"],
-                "date_modified": result["date_modified"],
-                "document_type": result["type"],
-                "regulatory_topics": result["regulatory_topics"].split("\n"),
-            }
-            for result in paginated_search_results
-        ]
         context["results_count"] = len(paginated_search_results)
     else:
         paginated_search_results = []