Merge pull request #59 from krishnasism/chore/remove-duplicate-functi…

…ons-and-refactor-krish19022024

hotpdf/hotpdf.py

@@ -252,15 +252,15 @@ def extract_text(
         )
         return extracted_text
 
-    def extract_page(
+    def extract_page_text(
         self,
-        page: int = 0,
+        page: int,
     ) -> str:
         """
         Extract text from a specified page.
 
         Args:
-            page (int): The page number. Defaults to 0.
+            page (int): The page number.
         Raises:
             ValueError: If the page number is invalid.
         Returns:

hotpdf/memory_map.py

@@ -32,34 +32,6 @@ def build_memory_map(self) -> None:
         """
         self.memory_map = SparseMatrix()
 
-    def text(self) -> str:
-        """
-        Get text of the memory map
-        Returns:
-            str: Text in the page of the pdf preserving the order of occurence.
-        """
-        memory_map_str = ""
-        for row in range(self.memory_map.rows):
-            for col in range(self.memory_map.columns):
-                memory_map_str += self.memory_map.get(row_idx=row, column_idx=col)
-            memory_map_str += "\n"
-        return memory_map_str
-
-    def display_memory_map(self, save: bool = False, filename: str = "memory_map.txt") -> None:
-        """
-        Display or save the memory map.
-
-        Args:
-            save (bool, optional): Whether to save to a file. Defaults to False.
-            filename (str, optional): The filename to save the map. Defaults to "memory_map.txt".
-        """
-        memory_map_str = self.text()
-        if save:
-            with open(filename, "w", encoding="utf-8") as file:
-                file.write(memory_map_str)
-        else:
-            print(memory_map_str)
-
     def __get_page_spans(self, page: ET.Element) -> Generator[ET.Element, None, None]:
         return page.iterfind(".//span")
 

tests/test_functions.py

@@ -1,4 +1,3 @@
-import os
 import shutil
 from unittest.mock import patch
 
@@ -52,16 +51,6 @@ def test_span_map_behaviours(valid_file_name):
     assert hot_pdf_object.pages[0].span_map.get_span(None) is None
 
 
-def test_memory_map_behaviour(valid_file_name):
-    hot_pdf_object = HotPdf()
-    with pytest.raises(Exception, match="list index out of range"):
-        hot_pdf_object.pages[0].text()
-    hot_pdf_object.load(valid_file_name, drop_duplicate_spans=False)
-    hot_pdf_object.pages[0].display_memory_map(save=True, filename="test.txt")
-    assert os.path.exists("test.txt")
-    os.remove("test.txt")
-
-
 def test_sparse_matrix_insert_and_get():
     matrix = SparseMatrix(3, 3)
     matrix.insert("A", 0, 0)
@@ -182,3 +171,10 @@ def test_intersect(bbox1, bbox2, expected):
 )
 def test_to_text(hot_characters, expected):
     assert to_text(hot_characters) == expected
+
+
+def test_invalid_page_number(valid_file_name):
+    hotpdf_object = HotPdf()
+    hotpdf_object.load(valid_file_name)
+    with pytest.raises(ValueError, match="Invalid page number"):
+        _ = hotpdf_object.extract_page_text(page=2)

tests/test_load.py

@@ -36,9 +36,9 @@ def test_load(valid_file_name):
 def test_full_text(valid_file_name):
     hot_pdf_object = HotPdf()
     hot_pdf_object.load(valid_file_name)
-    pages = hot_pdf_object.pages
+    text_first_page = hot_pdf_object.extract_page_text(page=0)
     # Not blank extraction
-    assert len(pages[0].text()) > 1000
+    assert len(text_first_page) > 500
 
 
 def test_pages_length(valid_file_name):
@@ -116,8 +116,8 @@ def test_non_existent_file_path(non_existent_file_name):
 def test_blank_pdf(blank_file_name):
     hot_pdf_object = HotPdf()
     hot_pdf_object.load(blank_file_name)
-    pages = hot_pdf_object.pages
-    assert all([len(page.text().strip("\n").strip()) == 0 for page in pages])
+    len_pages = len(hot_pdf_object.pages)
+    assert all([len(hot_pdf_object.extract_page_text(page=i).strip("\n").strip()) == 0 for i in range(len_pages)])
 
 
 def test_row_index_greater_than_rows_of_memory_map(valid_file_name):
@@ -165,13 +165,6 @@ def test_extract_invalid_coordinates(valid_file_name, coordinates):
         hot_pdf_object.extract_text(x0=coordinates[0], y0=coordinates[1], x1=coordinates[2], y1=coordinates[3])
 
 
-def test_display_memory_map(valid_file_name):
-    hot_pdf_object = HotPdf()
-    hot_pdf_object.load(valid_file_name)
-    pages = hot_pdf_object.pages
-    pages[0].display_memory_map(save=False, filename="test.txt")
-
-
 def test_get_spans(valid_file_name):
     INCOMPLETE_WORD = "EXPERIEN"
     NON_EXISTENT_WORD = "BLAH"