Improve use of CharacterEncoding

mathics/builtin/atomic/strings.py

@@ -899,7 +899,20 @@ def eval_default(self, value, evaluation: Evaluation, options: dict):
     def eval_form(self, expr, form, evaluation: Evaluation, options: dict):
         "ToString[expr_, form_Symbol, OptionsPattern[ToString]]"
         encoding = options["System`CharacterEncoding"]
-        return eval_ToString(expr, form, encoding.value, evaluation)
+        if isinstance(encoding, String):
+            encoding_str = encoding.value
+            if encoding_str not in _encodings:
+                evaluation.message("$CharacterEncoding", "charcode", encoding)
+                encoding_str = evaluation.definitions.get_ownvalue(
+                    "System`$SystemCharacterEncoding"
+                ).value
+        else:
+            evaluation.message("$CharacterEncoding", "charcode", encoding)
+            encoding_str = evaluation.definitions.get_ownvalue(
+                "System`$SystemCharacterEncoding"
+            ).value
+
+        return eval_ToString(expr, form, encoding_str, evaluation)
 
 
 class Transliterate(Builtin):

mathics/eval/strings.py

@@ -23,8 +23,8 @@
 def eval_ToString(
     expr: BaseElement, form: Symbol, encoding: String, evaluation: Evaluation
 ) -> String:
-    boxes = format_element(expr, evaluation, form, encoding=encoding)
-    text = boxes.to_text(evaluation=evaluation)
+    boxes = format_element(expr, evaluation, form)
+    text = boxes.to_text(evaluation=evaluation, encoding=encoding)
     return String(text)
 
 

mathics/format/render/text.py

@@ -2,7 +2,6 @@
 """
 Mathics3 box rendering to plain text.
 """
-
 from mathics.builtin.box.graphics import GraphicsBox
 from mathics.builtin.box.graphics3d import Graphics3DBox
 from mathics.builtin.box.layout import (
@@ -34,6 +33,43 @@
 add_render_function(FormBox, convert_inner_box_field)
 
 
+# Map WMA encoding names to Python encoding names
+ENCODING_WMA_TO_PYTHON = {
+    "WindowsEastEurope": "cp1250",
+    "WindowsCyrillic": "cp1251",
+    "WindowsANSI": "cp1252",
+    "WindowsGreek": "cp1252",
+    "WindowsTurkish": "cp1254",
+}
+
+
+def encode_string_value(value: str, encoding: str):
+    """Convert an Unicode string `value` to the required `encoding`"""
+    if encoding == "ASCII":
+        # TODO: replace from a table from MathicsScanner
+        ascii_map = {
+            "⇒": "=>",
+            "↔": "<->",
+            "→": "->",
+            "⇾": "->",
+            "⇾": "->",
+            "⇴": "->",
+            "∫": r"\[Integral]",
+            "𝑑": r"\[DifferentialD]",
+            "⧦": r"\[Equivalent]",
+            "×": r" x ",
+        }
+        result = ""
+        for ch in value:
+            ch = ascii_map.get(ch, ch)
+            result += ch
+        return result
+
+    encoding = ENCODING_WMA_TO_PYTHON.get(encoding, encoding)
+    result = value.encode("utf-8").decode(encoding)
+    return result
+
+
 def fractionbox(box: FractionBox, **options) -> str:
     # Note: values set in `options` take precedence over `box_options`
     child_options = {**options, **box.box_options}
@@ -159,6 +195,9 @@ def string(s: String, **options) -> str:
     if value.startswith('"') and value.endswith('"'):  # nopep8
         if not show_string_characters:
             value = value[1:-1]
+
+    if "encoding" in options and options["encoding"] != "Unicode":
+        value = encode_string_value(value, options["encoding"])
     return value