Simplify definition of mathtext symbols.

anntzer · anntzer · commit 60e1ce51026c · 2022-05-01T13:19:57.000+02:00
Use a single regex that handles both single_symbol (a single character)
and symbol_name (`\knowntexsymbolname`), and also slightly simplify the
"end-of-symbol-name" regex.

This parsing element comes up extremely often, and removing one
indirection layers shaves off ~3-4% off drawing all the current mathtext
tests, i.e.
```
MPLBACKEND=agg python -c 'import time; from pylab import *; from matplotlib.tests.test_mathtext import math_tests; fig = figure(figsize=(3, 10)); fig.text(0, 0, "\n".join(filter(None, math_tests)), size=6); start = time.perf_counter(); [fig.canvas.draw() for _ in range(10)]; print((time.perf_counter() - start) / 10)'
```
diff --git a/lib/matplotlib/_mathtext.py b/lib/matplotlib/_mathtext.py
@@ -8,6 +8,7 @@
 import functools
 import logging
 import os
+import re
 import types
 import unicodedata
 
@@ -1710,15 +1711,13 @@ def set_names_and_parse_actions():
         p.float_literal  = Regex(r"[-+]?([0-9]+\.?[0-9]*|\.[0-9]+)")
         p.space          = oneOf(self._space_widths)("space")
 
-        p.single_symbol  = Regex(
-            r"([a-zA-Z0-9 +\-*/<>=:,.;!\?&'@()\[\]|%s])|(\\[%%${}\[\]_|])" %
-            "\U00000080-\U0001ffff"  # unicode range
-        )("sym")
         p.accentprefixed = "\\" + oneOf(self._accentprefixed)("sym")
-        p.symbol_name    = (
-            oneOf([rf"\{sym}" for sym in tex2uni])("sym")
-            + Regex("(?=[^A-Za-z]|$)").leaveWhitespace())
-        p.symbol         = (p.single_symbol | p.symbol_name).leaveWhitespace()
+        p.symbol         = Regex(
+            r"[a-zA-Z0-9 +\-*/<>=:,.;!\?&'@()\[\]|\U00000080-\U0001ffff]"
+            r"|\\[%${}\[\]_|]"
+            + r"|\\(?:{})(?![A-Za-z])".format(
+                "|".join(map(re.escape, tex2uni)))
+        )("sym").leaveWhitespace()
         p.unknown_symbol = Regex(r"\\[A-Za-z]*")("name")
 
         p.font           = "\\" + oneOf(self._fontnames)("font")
