Merge pull request matplotlib#30512 from QuLogic/pdf-text-subsets

pdf: Improve text with characters outside embedded font limits

Author: QuLogic

doc/api/next_api_changes/deprecations/30512-ES.rst

@@ -0,0 +1,3 @@
+``PdfFile.multi_byte_charprocs``
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+... is deprecated with no replacement.

doc/release/next_whats_new/pdf_fonts.rst

@@ -0,0 +1,10 @@
+Improved font embedding in PDF
+------------------------------
+
+Both Type 3 and Type 42 fonts (see :ref:`fonts` for more details) are now
+embedded into PDFs without limitation. Fonts may be split into multiple
+embedded subsets in order to satisfy format limits. Additionally, a corrected
+Unicode mapping is added for each.
+
+This means that *all* text should now be selectable and copyable in PDF viewers
+that support doing so.

lib/matplotlib/backends/_backend_pdf_ps.py

@@ -205,6 +205,25 @@ def track_glyph(
         self.used.setdefault((font.fname, subset), {})[subset_charcode] = glyph
         return (subset, subset_charcode)
 
+    def subset_to_unicode(self, index: int,
+                          charcode: CharacterCodeType) -> CharacterCodeType:
+        """
+        Map a subset index and character code to a Unicode character code.
+
+        Parameters
+        ----------
+        index : int
+            The subset index within a font.
+        charcode : CharacterCodeType
+            The character code within a subset to map back.
+
+        Returns
+        -------
+        CharacterCodeType
+            The Unicode character code corresponding to the subsetted one.
+        """
+        return index * self.subset_size + charcode
+
 
 class RendererPDFPSBase(RendererBase):
     # The following attributes must be defined by the subclasses: