texcleanup: adding option --re-sub

tests/test_cli_texcleanup.py

@@ -0,0 +1,17 @@
+import texplain
+
+
+def test_regex(tmp_path):
+    text = r"""
+This is some {\it italic text} that needes formatting.
+    """
+
+    formatted = r"""
+This is some \emph{italic text} that needes formatting.
+    """
+
+    fpath = tmp_path / "test.tex"
+    fpath.write_text(text.strip())
+
+    texplain.texcleanup(["--re-sub", r"{\\it\s+(.*)}", r"\\emph{\1}", str(fpath)])
+    assert fpath.read_text().strip() == formatted.strip()

texplain/__init__.py

@@ -2751,6 +2751,15 @@ def _texcleanup_parser():
         help="Fix non-LaTeX quotation marks: \"...\" -> ``...''",
     )
 
+    parser.add_argument(
+        "--re-sub",
+        nargs=2,
+        type=str,
+        action="append",
+        metavar=("pattern", "repl"),
+        help="Apply ``re.sub(pattern, repl, text)``.",
+    )
+
     parser.add_argument("-v", "--version", action="version", version=version)
     parser.add_argument("files", nargs="+", type=str, help="TeX file(s) (changed in-place).")
 
@@ -2798,6 +2807,9 @@ def texcleanup(args: list[str]):
         if args.fix_quotes:
             tex.fix_quotes()
 
+        for pattern, repl in args.re_sub:
+            tex.main = re.sub(pattern, repl, tex.main)
+
         if tex.changed():
             with open(file, "w") as file:
                 file.write(str(tex))