Upgrade pdfminer.six from 20250327 to 20250506

... and adjust color handling accordingly.

CHANGELOG.md

@@ -2,6 +2,14 @@
 
 All notable changes to this project will be documented in this file. The format is based on [Keep a Changelog](http://keepachangelog.com/).
 
+## [0.11.7] - [Unreleased]
+
+### Changed
+- Upgrade `pdfminer.six` from `20250327` to `20250506`
+
+### Removed
+- Remove `stroking_pattern` and `non_stroking_pattern` object attributes
+
 ## [0.11.6] - 2025-03-27
 ### Changed
 - Upgrade `pdfminer.six` from `20231228` to `20250327` ([3fcb493](https://github.com/jsvine/pdfplumber/commit/3fcb493) + [12a73a2](https://github.com/jsvine/pdfplumber/commit/12a73a2))
@@ -13,7 +21,7 @@ All notable changes to this project will be documented in this file. The format
 - Catch exceptions from pdfminer and malformed PDFs ([43ccc5b](https://github.com/jsvine/pdfplumber/commit/43ccc5b))
 - More broadly handle RecursionError ([748ff31](https://github.com/jsvine/pdfplumber/commit/748ff31))
 
-## Removed
+### Removed
 - Remove test_issue_1089 ([#1263](https://github.com/jsvine/pdfplumber/issues/1263) + [7e28e76](https://github.com/jsvine/pdfplumber/commit/7e28e76))
 
 ## [0.11.5] - 2025-01-01

pdfplumber/page.py

@@ -100,29 +100,6 @@ def fix_fontname_bytes(fontname: bytes) -> str:
     return str(prefix)[2:-1] + suffix_new
 
 
-def separate_pattern(
-    color: Tuple[Any, ...]
-) -> Tuple[Optional[Tuple[Union[float, int], ...]], Optional[str]]:
-    if isinstance(color[-1], PSLiteral):
-        return (color[:-1] or None), decode_text(color[-1].name)
-    else:
-        return color, None
-
-
-def normalize_color(
-    color: Any,
-) -> Tuple[Optional[Tuple[Union[float, int], ...]], Optional[str]]:
-    if color is None:
-        return (None, None)
-    elif isinstance(color, tuple):
-        tuplefied = color
-    elif isinstance(color, list):
-        tuplefied = tuple(color)
-    else:
-        tuplefied = (color,)
-    return separate_pattern(tuplefied)
-
-
 def tuplify_list_kwargs(kwargs: Dict[str, Any]) -> Dict[str, Any]:
     return {
         key: (tuple(value) if isinstance(value, list) else value)
@@ -395,13 +372,6 @@ class Page(Container):
             if hasattr(obj, cs):
                 attr[cs] = resolve_and_decode(getattr(obj, cs).name)
 
-        for color_attr, pattern_attr in [
-            ("stroking_color", "stroking_pattern"),
-            ("non_stroking_color", "non_stroking_pattern"),
-        ]:
-            if color_attr in attr:
-                attr[color_attr], attr[pattern_attr] = normalize_color(attr[color_attr])
-
         if isinstance(obj, (LTChar, LTTextContainer)):
             text = obj.get_text()
             attr["text"] = (
@@ -415,11 +385,11 @@ class Page(Container):
             # directly expose .stroking_color and .non_stroking_color
             # for LTChar objects (unlike, e.g., LTRect objects).
             gs = obj.graphicstate
-            attr["stroking_color"], attr["stroking_pattern"] = normalize_color(
-                gs.scolor
+            attr["stroking_color"] = (
+                gs.scolor if isinstance(gs.scolor, tuple) else (gs.scolor,)
             )
-            attr["non_stroking_color"], attr["non_stroking_pattern"] = normalize_color(
-                gs.ncolor
+            attr["non_stroking_color"] = (
+                gs.ncolor if isinstance(gs.ncolor, tuple) else (gs.ncolor,)
             )
 
             # Handle (rare) byte-encoded fontnames

requirements.txt

@@ -1,3 +1,3 @@
-pdfminer.six==20250327
+pdfminer.six==20250506
 Pillow>=9.1
 pypdfium2>=4.18.0

tests/test_convert.py

@@ -177,8 +177,9 @@ class Test(unittest.TestCase):
         c = self.pdf.to_csv(precision=3)
         assert c.split("\r\n")[9] == (
             "char,1,45.83,58.826,656.82,674.82,117.18,117.18,135.18,12.996,"
-            '18.0,12.996,,,,,,,TimesNewRomanPSMT,,,"(1, 0, 0, 1, 45.83, 660.69)"'
-            ',,,DeviceRGB,"(0, 0, 0)",,,,18.0,,,,,,,Y,,1,'
+            "18.0,12.996,,,,,,,TimesNewRomanPSMT,,,"
+            '"(1.0, 0.0, 0.0, 1.0, 45.83, 660.69)"'
+            ',,,DeviceRGB,"(0.0, 0.0, 0.0)",,,18.0,,,,"(0,)",,Y,,1,'
         )
 
         io = StringIO()
@@ -244,8 +245,9 @@ class Test(unittest.TestCase):
 
         assert res.decode("utf-8").split("\r\n")[9] == (
             "char,1,45.83,58.826,656.82,674.82,117.18,117.18,135.18,12.996,"
-            '18.0,12.996,,,,,,,TimesNewRomanPSMT,,,"(1, 0, 0, 1, 45.83, 660.69)"'
-            ',,,DeviceRGB,"(0, 0, 0)",,,,18.0,,,,,,,Y,,1,'
+            "18.0,12.996,,,,,,,TimesNewRomanPSMT,,,"
+            '"(1.0, 0.0, 0.0, 1.0, 45.83, 660.69)"'
+            ',,,DeviceRGB,"(0.0, 0.0, 0.0)",,,18.0,,,,"(0,)",,Y,,1,'
         )
 
     def test_cli_csv_exclude(self):
@@ -263,15 +265,13 @@ class Test(unittest.TestCase):
                 "matrix",
                 "mcid",
                 "ncs",
-                "non_stroking_pattern",
-                "stroking_pattern",
             ]
         )
 
         assert res.decode("utf-8").split("\r\n")[9] == (
             "char,1,45.83,58.826,656.82,674.82,117.18,117.18,135.18,12.996,"
             "18.0,12.996,,,,,,,TimesNewRomanPSMT,"
-            ',,,"(0, 0, 0)",,,18.0,,,,,,Y,,1,'
+            ',,,"(0.0, 0.0, 0.0)",,,18.0,,,,"(0,)",,Y,,1,'
         )
 
     def test_cli_csv_include(self):