Switch svg glyph references back to hex; merge tex & non-tex names.

anntzer · anntzer · commit 1fb0ace9eb01 · 2020-06-18T19:17:46.000+02:00
When embedding glyphs as paths in SVG files, each glyph has a name just so that we can link to them when actually placing the glyphs. Previously there were two different paths for non-usetex glyphs and usetex glyphs. - In a2287b1 I accidentally changed the number component of non-usetex names from hex to decimal (usetex was always using decimal); switch it back to hex as that's typically how glyph tables are listed anyways. Also switch the usetex case to hex for consistency. - Make non-usetex and usetex names use the same way to generate the name. The 2nd entry of ps_font_info typically matches postscript_name (but is only available for Type1 fonts, whereas postscript_name is defined for all fonts), but even if they donn't (see test_unicode_won), this doesn't matter as long as we are internally consistent... Also changed unicode_won test to actually parse the xml -- the regexp search seems quite slow locally, and anyways regex'ing xml is not necessarily a great idea :)
diff --git a/lib/matplotlib/tests/test_backend_svg.py b/lib/matplotlib/tests/test_backend_svg.py
@@ -118,9 +118,10 @@ def test_unicode_won():
         fig.savefig(fd, format='svg')
         buf = fd.getvalue().decode('ascii')
 
-    won_id = 'Computer_Modern_Sans_Serif-142'
-    assert re.search(r'<path d=(.|\s)*?id="{0}"/>'.format(won_id), buf)
-    assert re.search(r'<use[^/>]*? xlink:href="#{0}"/>'.format(won_id), buf)
+    won_id = 'SFSS3583-8e'
+    tree = xml.etree.ElementTree.fromstring(buf)
+    assert len(tree.findall(f'.//{{*}}path[@d][@id="{won_id}"]')) == 1
+    assert won_id in tree.findall(f'.//{{*}}use').attrib.values
 
 
 def test_svgnone_with_data_coordinates():
diff --git a/lib/matplotlib/textpath.py b/lib/matplotlib/textpath.py
@@ -41,15 +41,7 @@ def _get_char_id(self, font, ccode):
         """
         Return a unique id for the given font and character-code set.
         """
-        return urllib.parse.quote('{}-{}'.format(font.postscript_name, ccode))
-
-    def _get_char_id_ps(self, font, ccode):
-        """
-        Return a unique id for the given font and character-code set (for tex).
-        """
-        ps_name = font.get_ps_font_info()[2]
-        char_id = urllib.parse.quote('%s-%d' % (ps_name, ccode))
-        return char_id
+        return urllib.parse.quote(f"{font.postscript_name}-{ccode:x}")
 
     def get_text_width_height_descent(self, s, prop, ismath):
         if ismath == "TeX":
@@ -254,7 +246,7 @@ def get_glyphs_tex(self, prop, s, glyph_map=None,
         # characters into strings.
         for x1, y1, dvifont, glyph, width in page.text:
             font, enc = self._get_ps_font_and_encoding(dvifont.texname)
-            char_id = self._get_char_id_ps(font, glyph)
+            char_id = self._get_char_id(font, glyph)
 
             if char_id not in glyph_map:
                 font.clear()
