🐐 SCINDE

README.md

@@ -359,6 +359,11 @@ Returns an array of all non-overlapping matches of the regex `pattern` in `strin
 
 Replaces all non-overlapping matches of the regex `pattern` in `string` with `replacement`. All three arguments must be strings. The replacement string supports backreferences (`\1`, `\2`, etc.) to captured groups. Returns the resulting string. Raises an error if the pattern is invalid.
 
+### SCINDE
+`SCINDE(string, delimiter)`
+
+Splits `string` by `delimiter` and returns an array of substrings. Both arguments must be strings. If the delimiter is not found, returns a single-element array containing the original string. If the delimiter is an empty string, splits into individual characters.
+
 ## Modules
 Modules are additions to the base `CENTVRION` syntax. They add or change certain features. Modules are included in your code by having
 

centvrion/ast_nodes.py

@@ -1328,6 +1328,18 @@ class BuiltIn(Node):
         except re.error as e:
           raise CentvrionError(f"Invalid regex: {e}")
         return vtable, ValStr(result)
+      case "SCINDE":
+        string = params[0]
+        delimiter = params[1]
+        if not isinstance(string, ValStr) or not isinstance(delimiter, ValStr):
+          raise CentvrionError("SCINDE requires two strings")
+        s = string.value()
+        d = delimiter.value()
+        if d == "":
+          parts = [ValStr(c) for c in s]
+        else:
+          parts = [ValStr(p) for p in s.split(d)]
+        return vtable, ValList(parts)
       case "PETE":
         if "RETE" not in vtable["#modules"]:
           raise CentvrionError("Cannot use 'PETE' without module 'RETE'")

centvrion/compiler/emit_expr.py

@@ -303,6 +303,9 @@ def _emit_builtin(node, ctx):
     case "SVBSTITVE":
       lines.append(f"CentValue {tmp} = cent_svbstitve({param_vars[0]}, {param_vars[1]}, {param_vars[2]});")
 
+    case "SCINDE":
+      lines.append(f"CentValue {tmp} = cent_scinde({param_vars[0]}, {param_vars[1]});")
+
     case "PETE":
       if not ctx.has_module("RETE"):
         lines.append('cent_runtime_error("RETE module required for PETE");')

centvrion/compiler/runtime/cent_runtime.c

@@ -1015,6 +1015,40 @@ CentValue cent_svbstitve(CentValue pattern, CentValue replacement, CentValue tex
   return cent_str(result);
 }
 
+CentValue cent_scinde(CentValue str, CentValue delim) {
+  if (str.type != CENT_STR || delim.type != CENT_STR)
+    cent_type_error("'SCINDE' requires two strings");
+  const char *s = str.sval;
+  const char *d = delim.sval;
+  size_t dlen = strlen(d);
+  CentValue result = cent_list_new(8);
+  if (dlen == 0) {
+    /* empty delimiter: split into individual characters */
+    for (const char *p = s; *p; p++) {
+      char *buf = cent_arena_alloc(cent_arena, 2);
+      buf[0] = *p;
+      buf[1] = '\0';
+      cent_list_push(&result, cent_str(buf));
+    }
+    return result;
+  }
+  const char *cursor = s;
+  for (;;) {
+    const char *found = strstr(cursor, d);
+    if (!found) {
+      cent_list_push(&result, cent_str(cursor));
+      break;
+    }
+    size_t len = found - cursor;
+    char *buf = cent_arena_alloc(cent_arena, len + 1);
+    memcpy(buf, cursor, len);
+    buf[len] = '\0';
+    cent_list_push(&result, cent_str(buf));
+    cursor = found + dlen;
+  }
+  return result;
+}
+
 /* ------------------------------------------------------------------ */
 /* Networking (RETE)                                                    */
 /* ------------------------------------------------------------------ */

centvrion/compiler/runtime/cent_runtime.h

@@ -234,6 +234,7 @@ void      cent_scribe(CentValue path, CentValue content);       /* SCRIBE */
 void      cent_adivnge(CentValue path, CentValue content);      /* ADIVNGE */
 CentValue cent_qvaere(CentValue pattern, CentValue text);       /* QVAERE */
 CentValue cent_svbstitve(CentValue pattern, CentValue replacement, CentValue text); /* SVBSTITVE */
+CentValue cent_scinde(CentValue str, CentValue delim);            /* SCINDE */
 CentValue cent_pete(CentValue url);                             /* PETE */
 void      cent_petitvr(CentValue path, CentValue handler, CentScope scope); /* PETITVR */
 void      cent_avscvlta(CentValue port);                        /* AVSCVLTA */

centvrion/lexer.py

@@ -60,6 +60,7 @@ builtin_tokens = [("BUILTIN", i) for i in [
   "ADIVNGE",
   "QVAERE",
   "SVBSTITVE",
+  "SCINDE",
   "PETE",
   "PETITVR",
   "AVSCVLTA"

snippets/syntaxes/centvrion.sublime-syntax

@@ -70,7 +70,7 @@ contexts:
       scope: constant.language.centvrion
 
   builtins:
-    - match: '\b(ADIVNGE|AVDI_NVMERVS|AVDI|AVSCVLTA|CLAVES|DECIMATIO|DIC|DORMI|EVERRE|FORTVITVS_NVMERVS|FORTVITA_ELECTIO|LEGE|LONGITVDO|ORDINA|PETE|PETITVR|QVAERE|SCRIBE|SEMEN|SENATVS|SVBSTITVE|TYPVS)\b'
+    - match: '\b(ADIVNGE|AVDI_NVMERVS|AVDI|AVSCVLTA|CLAVES|DECIMATIO|DIC|DORMI|EVERRE|FORTVITVS_NVMERVS|FORTVITA_ELECTIO|LEGE|LONGITVDO|ORDINA|PETE|PETITVR|QVAERE|SCINDE|SCRIBE|SEMEN|SENATVS|SVBSTITVE|TYPVS)\b'
       scope: support.function.builtin.centvrion
 
   modules:

tests.py

@@ -638,6 +638,18 @@ builtin_tests = [
   ('SVBSTITVE("(a)(b)", "\\2\\1", "ab")', Program([], [ExpressionStatement(BuiltIn("SVBSTITVE", [String("(a)(b)"), String("\\2\\1"), String("ab")]))]), ValStr("ba")),
   # SVBSTITVE: backreference with unmatched group (ignored)
   ('SVBSTITVE("(a)(b)?", "\\1\\2", "a")', Program([], [ExpressionStatement(BuiltIn("SVBSTITVE", [String("(a)(b)?"), String("\\1\\2"), String("a")]))]), ValStr("a")),
+  # SCINDE: basic split
+  ('SCINDE("a,b,c", ",")', Program([], [ExpressionStatement(BuiltIn("SCINDE", [String("a,b,c"), String(",")]))]), ValList([ValStr("a"), ValStr("b"), ValStr("c")])),
+  # SCINDE: no match (delimiter not found)
+  ('SCINDE("abc", ",")', Program([], [ExpressionStatement(BuiltIn("SCINDE", [String("abc"), String(",")]))]), ValList([ValStr("abc")])),
+  # SCINDE: empty string
+  ('SCINDE("", ",")', Program([], [ExpressionStatement(BuiltIn("SCINDE", [String(""), String(",")]))]), ValList([ValStr("")])),
+  # SCINDE: multi-char delimiter
+  ('SCINDE("a::b::c", "::")', Program([], [ExpressionStatement(BuiltIn("SCINDE", [String("a::b::c"), String("::")]))]), ValList([ValStr("a"), ValStr("b"), ValStr("c")])),
+  # SCINDE: delimiter at edges
+  ('SCINDE(",a,", ",")', Program([], [ExpressionStatement(BuiltIn("SCINDE", [String(",a,"), String(",")]))]), ValList([ValStr(""), ValStr("a"), ValStr("")])),
+  # SCINDE: empty delimiter (split into chars)
+  ('SCINDE("abc", "")', Program([], [ExpressionStatement(BuiltIn("SCINDE", [String("abc"), String("")]))]), ValList([ValStr("a"), ValStr("b"), ValStr("c")])),
 ]
 
 class TestBuiltins(unittest.TestCase):
@@ -726,6 +738,8 @@ error_tests = [
   ('SVBSTITVE("a", I, "c")', CentvrionError),                                # SVBSTITVE requires strings, not int replacement
   ('SVBSTITVE("a", "b", I)', CentvrionError),                                # SVBSTITVE requires strings, not int text
   ('SVBSTITVE("[", "b", "c")', CentvrionError),                              # SVBSTITVE invalid regex
+  ('SCINDE(I, ",")', CentvrionError),                                         # SCINDE requires strings, not int
+  ('SCINDE("a", I)', CentvrionError),                                         # SCINDE requires strings, not int delimiter
   ('PETE("http://example.com")', CentvrionError),                             # RETE required for PETE
   ('CVM RETE\nPETE(I)', CentvrionError),                                      # PETE requires a string URL
   ('PETITVR("/", FVNCTIO (r) VT {\nREDI("hi")\n})', CentvrionError),           # RETE required for PETITVR

vscode-extension/syntaxes/cent.tmLanguage.json

@@ -65,7 +65,7 @@
 			"patterns": [
 				{
 					"name": "support.function.builtin.cent",
-					"match": "\\b(ADIVNGE|AVDI_NVMERVS|AVDI|AVSCVLTA|CLAVES|DECIMATIO|DIC|DORMI|EVERRE|FORTVITVS_NVMERVS|FORTVITA_ELECTIO|LEGE|LONGITVDO|ORDINA|PETE|PETITVR|QVAERE|SCRIBE|SEMEN|SENATVS|SVBSTITVE|TYPVS)\\b"
+					"match": "\\b(ADIVNGE|AVDI_NVMERVS|AVDI|AVSCVLTA|CLAVES|DECIMATIO|DIC|DORMI|EVERRE|FORTVITVS_NVMERVS|FORTVITA_ELECTIO|LEGE|LONGITVDO|ORDINA|PETE|PETITVR|QVAERE|SCINDE|SCRIBE|SEMEN|SENATVS|SVBSTITVE|TYPVS)\\b"
 				}
 			]
 		},