add wl-to-amslatex conversion table...

revise Differential symbol; allow two versions: \u1d451 | \uf74c

Author: rocky

mathics_scanner/characters.py

@@ -43,6 +43,9 @@
 _wl_to_ascii = _data.get("wl-to-ascii-dict", {})
 _wl_to_ascii_re = re.compile(_data.get("wl-to-ascii-re", ""))
 
+# AMS LaTeX replacements
+_wl_to_amstex = _data.get("wl-to-amstex", None)
+
 # Conversion from WL to unicode
 _wl_to_unicode = _data.get("wl-to-unicode-dict", {})
 _wl_to_unicode_re = re.compile(_data.get("wl-to-unicode-re", ""))

mathics_scanner/generate/build_tables.py

@@ -97,6 +97,13 @@ def compile_tables(data: dict) -> dict:
         if "esc-alias" in v
     }
 
+    # WL to AMS LaTeX characters
+    wl_to_amslatex = {
+        v["wl-unicode"]: v.get("amslatex")
+        for v in data.values()
+        if "amslatex" in v and "wl-unicode" in v
+    }
+
     # operator-to-unicode dictionary entry
     operator_to_precedence = {
         v["operator-name"]: v["precedence"]
@@ -188,6 +195,7 @@ def compile_tables(data: dict) -> dict:
         "unicode-to-wl-re": unicode_to_wl_re,
         "wl-to-ascii-dict": wl_to_ascii_dict,
         "wl-to-ascii-re": wl_to_ascii_re,
+        "wl-to-amslatex": wl_to_amslatex,
         "wl-to-unicode-dict": wl_to_unicode_dict,
         "wl-to-unicode-re": wl_to_unicode_re,
     }
@@ -207,6 +215,7 @@ def compile_tables(data: dict) -> dict:
     "unicode-to-operator",
     "unicode-to-wl-dict",
     "unicode-to-wl-re",
+    "wl-to-amslatex",
     "wl-to-ascii-dict",
     "wl-to-ascii-re",
     "wl-to-unicode-dict",

mathics_scanner/tokeniser.py

@@ -148,7 +148,7 @@
     ("ConjugateTranspose", r" \uf3c9 "),
     ("HermitianConjugate", r" \uf3ce "),
     ("Integral", r" \u222b "),
-    ("DifferentialD", r" \U0001D451 "),
+    ("DifferentialD", r" \u1d451 | \uf74c"),
     ("Del", r" \u2207 "),
     # uf520 is Wolfram custom, 25ab is standard unicode
     ("Square", r" \uf520 | \u25ab"),

test/test_tokeniser.py

@@ -125,10 +125,10 @@ def test_int_repeated():
 
 
 def test_integeral():
-    assert tokens("\u222B x \U0001D451 y") == [
+    assert tokens("\u222B x \uf74c y") == [
         Token("Integral", "\u222B", 0),
         Token("Symbol", "x", 2),
-        Token("DifferentialD", "\U0001D451", 4),
+        Token("DifferentialD", "\uf74c", 4),
         Token("Symbol", "y", 6),
     ]
 

test/test_translation_regressions.py

@@ -11,7 +11,7 @@ def check_translation_regression(c: str, expected_translation: str):
 
 
 def test_translation_regressions():
-    check_translation_regression("DifferentialD", "𝑑")
+    check_translation_regression("DifferentialD", "\U0001D451")
     check_translation_regression("PartialD", "\u2202")
     check_translation_regression("Uranus", "\u2645")
     check_translation_regression("WeierstrassP", "\u2118")