Merge pull request #66 from krishnasism/chore/use-yield-instead-of-di…

…rect-return-sparsematrix-krish-20012024

Use yield in SparseMatrix items function + remove lru_cache

hotpdf/hotpdf.py

@@ -298,6 +298,5 @@ def extract_spans_text(
         extracted_text: list[str] = []
 
         for span in spans:
-            # TODO: This will be span.to_text() in the next release
             extracted_text.append(span.to_text())
         return "".join(extracted_text)

hotpdf/memory_map.py

@@ -1,7 +1,6 @@
 import math
 import xml.etree.ElementTree as ET
 from collections.abc import Generator
-from functools import lru_cache
 from hashlib import md5
 
 from .data.classes import HotCharacter, PageResult
@@ -103,7 +102,6 @@ def load_memory_map(self, page: ET.Element, drop_duplicate_spans: bool = True) -
         self.width = self.memory_map.columns
         self.height = self.memory_map.rows
 
-    @lru_cache  # noqa: B019
     def extract_text_from_bbox(self, x0: int, x1: int, y0: int, y1: int) -> str:
         """Extract text within a specified bounding box.
 
@@ -128,7 +126,6 @@ def extract_text_from_bbox(self, x0: int, x1: int, y0: int, y1: int) -> str:
 
         return extracted_text
 
-    @lru_cache  # noqa: B019
     def find_text(self, query: str) -> tuple[list[str], PageResult]:
         """Find text within the memory map.
 

hotpdf/span_map.py

@@ -24,7 +24,7 @@ def __setitem__(self, span_id: Union[str, None], hot_character: HotCharacter) ->
         self.insert(span_id, hot_character)
 
     def items(self) -> Iterable[tuple[str, Span]]:
-        return self.span_map.items()
+        yield from self.span_map.items()
 
     def insert(self, span_id: Union[str, None], hot_character: HotCharacter) -> None:
         if not span_id: