Merge branch 'develop' into echedey-ls/stable

CHANGELOG.md

@@ -2,6 +2,12 @@
 
 All notable changes to this project will be documented in this file. The format is based on [Keep a Changelog](http://keepachangelog.com/).
 
+## [0.10.4] - [Unreleased]
+
+### Fixed
+
+- Fix `Page.get_textmap` caching to allow for `extra_attrs=[...]`, by preconverting list kwargs to tuples. ([#1030](https://github.com/jsvine/pdfplumber/issues/1030))
+
 ## [0.10.3] - 2023-10-26
 
 ### Added

pdfplumber/page.py

@@ -167,6 +167,23 @@ class PDFPageAggregatorWithMarkedContent(PDFPageAggregator):
         self.tag_cur_item()
 
 
+def textmap_cacher(func: Callable[..., TextMap]) -> Callable[..., TextMap]:
+    """
+    Caches the kwargs to Page._get_textmap
+    and converts list kwargs (which would be unhashable) into tuples.
+    """
+
+    def new_func(**kwargs: Any) -> TextMap:
+        return lru_cache()(func)(
+            **{
+                key: (tuple(value) if isinstance(value, list) else value)
+                for key, value in kwargs.items()
+            }
+        )
+
+    return new_func
+
+
 class Page(Container):
     cached_properties: List[str] = Container.cached_properties + ["_layout"]
     is_original: bool = True
@@ -211,8 +228,8 @@ class Page(Container):
             )
         )
 
-        # https://rednafi.github.io/reflections/dont-wrap-instance-methods-with-functoolslru_cache-decorator-in-python.html
-        self.get_textmap = lru_cache()(self._get_textmap)
+        # https://rednafi.com/python/lru_cache_on_methods/
+        self.get_textmap = textmap_cacher(self._get_textmap)
 
     @property
     def width(self) -> T_num:
@@ -569,7 +586,7 @@ class DerivedPage(Page):
         self.page_obj = parent_page.page_obj
         self.page_number = parent_page.page_number
         self.flush_cache(Container.cached_properties)
-        self.get_textmap = lru_cache()(self._get_textmap)
+        self.get_textmap = textmap_cacher(self._get_textmap)
 
 
 def test_proposed_bbox(bbox: T_bbox, parent_bbox: T_bbox) -> None:

tests/test_utils.py

@@ -88,6 +88,27 @@ class Test(unittest.TestCase):
         assert words_rtl[1]["text"] == "baaabaaA/AAA"
         assert words_rtl[1]["direction"] == -1
 
+    def test_extra_attrs(self):
+        path = os.path.join(HERE, "pdfs/extra-attrs-example.pdf")
+        with pdfplumber.open(path) as pdf:
+            page = pdf.pages[0]
+            assert page.extract_text() == "BlackRedArial"
+            assert (
+                page.extract_text(extra_attrs=["non_stroking_color"])
+                == "Black RedArial"
+            )
+            assert page.extract_text(extra_attrs=["fontname"]) == "BlackRed Arial"
+            assert (
+                page.extract_text(extra_attrs=["non_stroking_color", "fontname"])
+                == "Black Red Arial"
+            )
+            # Should not error
+            assert page.extract_text(
+                layout=True,
+                use_text_flow=True,
+                extra_attrs=["non_stroking_color", "fontname"],
+            )
+
     def test_extract_words_punctuation(self):
         path = os.path.join(HERE, "pdfs/test-punkt.pdf")
         with pdfplumber.open(path) as pdf: