Fix to set color space from color convenience ops (#794)

Section 4.5 of the PDF reference says: "Color values are interpreted
according to the current color space, another parameter of the graphics
state. A PDF content stream first selects a color space by invoking the
CS operator (for the stroking color) or the cs operator (for the
non-stroking color). It then selects color values within that color
space with the SC operator (stroking) or the sc operator (nonstroking).
There are also convenience operators—G, g, RG, rg, K, and k—that select
both a color space and a color value within it in a single step."

Previously, those convenience operators did *not* set the color space.
This commit, following on filed issue #779, fixes this. It also adds a
test to demonstrate that, at least for the do_rg method, the fix works
as intended.

CHANGELOG.md

@@ -18,6 +18,7 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
 - `TypeError` when getting default width of font ([#720](https://github.com/pdfminer/pdfminer.six/issues/720))
 - Installing typing-extensions on Python 3.6 and 3.7 ([#775](https://github.com/pdfminer/pdfminer.six/pull/775))
 - `TypeError` in cmapdb.py when parsing null characters ([#768](https://github.com/pdfminer/pdfminer.six/pull/768))
+- Color "convenience operators" now (per spec) also set color space ([#779](https://github.com/pdfminer/pdfminer.six/issues/779))
 
 ### Deprecated
 

pdfminer/pdfinterp.py

@@ -652,21 +652,25 @@ class PDFPageInterpreter:
     def do_G(self, gray: PDFStackT) -> None:
         """Set gray level for stroking operations"""
         self.graphicstate.scolor = cast(float, gray)
+        self.scs = self.csmap["DeviceGray"]
         return
 
     def do_g(self, gray: PDFStackT) -> None:
         """Set gray level for nonstroking operations"""
         self.graphicstate.ncolor = cast(float, gray)
+        self.ncs = self.csmap["DeviceGray"]
         return
 
     def do_RG(self, r: PDFStackT, g: PDFStackT, b: PDFStackT) -> None:
         """Set RGB color for stroking operations"""
         self.graphicstate.scolor = (cast(float, r), cast(float, g), cast(float, b))
+        self.scs = self.csmap["DeviceRGB"]
         return
 
     def do_rg(self, r: PDFStackT, g: PDFStackT, b: PDFStackT) -> None:
         """Set RGB color for nonstroking operations"""
         self.graphicstate.ncolor = (cast(float, r), cast(float, g), cast(float, b))
+        self.ncs = self.csmap["DeviceRGB"]
         return
 
     def do_K(self, c: PDFStackT, m: PDFStackT, y: PDFStackT, k: PDFStackT) -> None:
@@ -677,6 +681,7 @@ class PDFPageInterpreter:
             cast(float, y),
             cast(float, k),
         )
+        self.scs = self.csmap["DeviceCMYK"]
         return
 
     def do_k(self, c: PDFStackT, m: PDFStackT, y: PDFStackT, k: PDFStackT) -> None:
@@ -687,6 +692,7 @@ class PDFPageInterpreter:
             cast(float, y),
             cast(float, k),
         )
+        self.ncs = self.csmap["DeviceCMYK"]
         return
 
     def do_SCN(self) -> None:

tests/test_converter.py

@@ -1,9 +1,10 @@
 import io
 from tempfile import TemporaryFile
 
+from helpers import absolute_sample_path
 from pdfminer.converter import PDFLayoutAnalyzer, PDFConverter
 from pdfminer.high_level import extract_pages
-from pdfminer.layout import LTContainer, LTRect, LTLine, LTCurve
+from pdfminer.layout import LTChar, LTContainer, LTRect, LTLine, LTCurve
 from pdfminer.pdfinterp import PDFGraphicState
 
 
@@ -225,6 +226,31 @@ class TestPaintPath:
         assert len(analyzer.cur_item._objs) == 0
 
 
+def get_chars(el):
+    if isinstance(el, LTContainer):
+        for item in el:
+            yield from get_chars(item)
+    elif isinstance(el, LTChar):
+        yield el
+    else:
+        pass
+
+
+class TestColorSpace:
+    def test_do_rg(self):
+        path = absolute_sample_path("contrib/issue-00352-hash-twos-complement.pdf")
+        for page in extract_pages(path):
+            for char in get_chars(page):
+                cs = char.ncs.name
+                color = char.graphicstate.ncolor
+                if cs == "DeviceGray":
+                    assert isinstance(color, (float, int))
+                elif cs == "DeviceRGB":
+                    assert len(color) == 3
+                elif cs == "DeviceCMYK":
+                    assert len(color) == 4
+
+
 class TestBinaryDetector:
     def test_stringio(self):
         assert not PDFConverter._is_binary_stream(io.StringIO())