🐐 Escape sequences

centvrion/ast_nodes.py

@@ -343,10 +343,15 @@ class String(Node):
     return f"String({self.value})"
 
   def print(self):
+    v = (self.value
+      .replace('\\', '\\\\')
+      .replace('\n', '\\n')
+      .replace('\t', '\\t')
+      .replace('\r', '\\r'))
     if self.quote == "'":
-      return f"'{self.value}'"
-    escaped = self.value.replace('{', '{{').replace('}', '}}')
-    return f'"{escaped}"'
+      return f"'{v}'"
+    v = v.replace('"', '\\"').replace('{', '{{').replace('}', '}}')
+    return f'"{v}"'
 
   def _eval(self, vtable):
     return vtable, ValStr(self.value)

centvrion/lexer.py

@@ -66,7 +66,7 @@ builtin_tokens = [("BUILTIN", i) for i in [
 ]]
 
 data_tokens = [
-  ("DATA_STRING", r"(\".*?\"|'.*?')"),
+  ("DATA_STRING", r'("(?:[^"\\]|\\.)*"|' + r"'(?:[^'\\]|\\.)*')"),
   ("DATA_FRACTION", r"([IVXLCDM][IVXLCDM_]*)?([S][S:.|]*|:[S:.|]+|\.[S:.|]*)"),
   ("DATA_NUMERAL", r"[IVXLCDM][IVXLCDM_]*")
 ]

centvrion/parser.py

@@ -7,19 +7,61 @@ from . import ast_nodes
 ALL_TOKENS = list(set([i[0] for i in all_tokens]))
 
 
+_ESCAPE_MAP = {
+  'n': '\n',
+  't': '\t',
+  'r': '\r',
+  '\\': '\\',
+  '"': '"',
+  "'": "'",
+}
+
+
+def _read_escape(s, i):
+  """Read a backslash escape at position i (the backslash). Returns (char, new_i)."""
+  if i + 1 >= len(s):
+    raise CentvrionError("Trailing backslash in string")
+  nxt = s[i + 1]
+  if nxt in _ESCAPE_MAP:
+    return _ESCAPE_MAP[nxt], i + 2
+  # unknown escapes pass through literally (e.g. \1 for regex backrefs)
+  return '\\' + nxt, i + 2
+
+
+def _unescape(s):
+  """Process escape sequences in a string with no interpolation."""
+  out = []
+  i = 0
+  while i < len(s):
+    if s[i] == '\\':
+      ch, i = _read_escape(s, i)
+      out.append(ch)
+    else:
+      out.append(s[i])
+      i += 1
+  return ''.join(out)
+
+
 def _parse_interpolated(raw_value):
   quote_char = raw_value[0]
   inner = raw_value[1:-1]
 
-  if quote_char == "'" or len(inner) == 0:
+  if len(inner) == 0:
     return ast_nodes.String(inner)
 
+  if quote_char == "'":
+    return ast_nodes.String(_unescape(inner))
+
   parts = []
   i = 0
   current = []
 
   while i < len(inner):
     ch = inner[i]
+    if ch == '\\':
+      c, i = _read_escape(inner, i)
+      current.append(c)
+      continue
     if ch == '{':
       if i + 1 < len(inner) and inner[i + 1] == '{':
         current.append('{')