Fix #39 also escape _ to -lowbar-

omwn · Oct 18, 2024 · 30404fc · 30404fc
1 parent 23fa3b3
commit 30404fc
Show file tree

Hide file tree

Showing 2 changed files with 3 additions and 2 deletions.
diff --git a/scripts/util.py b/scripts/util.py
@@ -29,7 +29,7 @@
     '\\': '-bsol-',
     ']': '-rsqb-',
     '^': '-Hat-',
-    '_': '_',            # keep, even though it's conflated with ' ' -> '_'
+    '_': '-lowbar-',
     '`': '-grave-',
     '{': '-lbrace-',
     '|': '-vert-',
@@ -46,7 +46,7 @@ def escape_lemma(lemma: str) -> str:
                 or '0' <= c <= '9'  # not in initial position
                 # or c == ':'  # drop this for xsd:id compatibility
                 # or c in '-'  # blocked for special purpose (see below)
-                or c in '_.·'  # _ is special-purpose, but accept
+                or c in '.·'
                 or 0xC0 <= codepoint <= 0xD6
                 or 0xD8 <= codepoint <= 0xF6
                 or 0xF8 <= codepoint <= 0x2FF

diff --git a/tests/test_util.py b/tests/test_util.py
@@ -8,3 +8,4 @@ def test_escape_lemma():
     assert escape_lemma("a:b:c") == "a-colon-b-colon-c"
     assert escape_lemma("a-b-c") == "a--b--c"
     assert escape_lemma("a´b´c") == "a-acute-b-acute-c"
+    assert escape_lemma("a_b_c") == "a-lowbar-b-lowbar-c"