Use luatex in --luaonly mode to query kpsewhich.

anntzer · anntzer · commit 4775421aa7f7 · 2021-02-22T15:04:17.000+01:00
`luatex --luaonly` runs a *lua* interpreter with relevant tex libraries
available, which avoids both the overhead of repeatedly initializing
kpathsea (the old approach, very slow on macos and windows).  An
alternative approach would be to use `luatex` followed by `\directlua`
calls, but on windows it appears that one needs to use `lualatex` to get
a working interactive prompt, and just loading the latex format takes
seconds(!).

For the simple following benchmark:
```sh
python -c 'from pylab import *; mpl.use("pdf"); rcParams["text.usetex"] = True; plot(); savefig("test.pdf", backend="pdf")'
```
On a macos machine, this patch brings runtime from ~4.5s to ~2.5s.
On a windows machine, this patch brings runtime from ~6.5s to ~1.7s.

We also need to figure out how to best advertise this (do we emit a
warning suggesting to install luatex on windows and macos if luatex is
not present?).
diff --git a/lib/matplotlib/dviread.py b/lib/matplotlib/dviread.py
@@ -25,6 +25,7 @@
 from pathlib import Path
 import re
 import struct
+import subprocess
 import sys
 import textwrap
 
@@ -1040,6 +1041,28 @@ def _parse_enc(path):
             "Failed to parse {} as Postscript encoding".format(path))
 
 
+class _LuatexKpsewhich:
+    @lru_cache()  # A singleton.
+    def __new__(cls):
+        self = object.__new__(cls)
+        self._proc = self._new_proc()
+        return self
+
+    def _new_proc(self):
+        return subprocess.Popen(
+            ["luatex", "--luaonly",
+             str(cbook._get_data_path("kpsewhich.lua"))],
+            stdin=subprocess.PIPE, stdout=subprocess.PIPE)
+
+    def search(self, filename):
+        if self._proc.poll() is not None:  # Dead, restart it.
+            self._proc = self._new_proc()
+        self._proc.stdin.write(os.fsencode(filename) + b"\n")
+        self._proc.stdin.flush()
+        out = self._proc.stdout.readline().rstrip()
+        return "" if out == b"nil" else os.fsdecode(out)
+
+
 @lru_cache()
 def find_tex_file(filename, format=None):
     """
@@ -1072,6 +1095,14 @@ def find_tex_file(filename, format=None):
     if isinstance(format, bytes):
         format = format.decode('utf-8', errors='replace')
 
+    try:
+        lk = _LuatexKpsewhich()
+    except FileNotFoundError:
+        pass  # Fallback to directly calling kpsewhich, as below.
+    else:
+        return lk.search(
+            f"{filename}.{format}" if format is not None else filename)
+
     if os.name == 'nt':
         # On Windows only, kpathsea can use utf-8 for cmd args and output.
         # The `command_line_encoding` environment variable is set to force it
diff --git a/lib/matplotlib/mpl-data/kpsewhich.lua b/lib/matplotlib/mpl-data/kpsewhich.lua
@@ -0,0 +1,3 @@
+-- see dviread._LuatexKpsewhich
+kpse.set_program_name("tex")
+while true do print(kpse.lookup(io.read():gsub("\r", ""))) end

Original file line number	Diff line number	Diff line change
`@@ -0,0 +1,3 @@`
	`1`	`+-- see dviread._LuatexKpsewhich`
	`2`	`+kpse.set_program_name("tex")`
	`3`	`+while true do print(kpse.lookup(io.read():gsub("\r", ""))) end`