Merge pull request #782 from interscript/feat/parg-complete

fix: .parg gate to 283/285 — alias-stop guard and 4-hex \U escapes

Author: ronaldtse

isc.artifact.json

@@ -62,7 +62,10 @@ module Primitives
               str('"').as(:dquote) |
               str("\\").as(:backslash) |
               (str("u") >> match(/[0-9a-fA-F]/).repeat(4, 4).as(:unicode)) |
-              (str("U") >> match(/[0-9a-fA-F]/).repeat(8, 8).as(:unicode))
+              # The corpus converter emits \U with 4 hex digits too
+              # (gki-bel "\U040E") — accept 4..8, don't be stricter than
+              # the corpus.
+              (str("U") >> match(/[0-9a-fA-F]/).repeat(4, 8).as(:unicode))
             )
           end
 

lib/interscript/isc/grammar/concerns/primitives.rb

@@ -38,7 +38,7 @@ grammar InterscriptIsc version "0.1.0" {
   esc_dq = "\"" as dquote
   esc_bs = "\\" as backslash
   esc_uni4 = "u" (4hexd) as unicode
-  esc_uni8 = "U" (8hexd) as unicode
+  esc_uni8 = "U" (4*8hexd) as unicode
   escape_sequence = "\\" (esc_nl / esc_cr / esc_tab / esc_dq / esc_bs / esc_uni4 / esc_uni8)
 
   raw_run = 1*(!("\\" / "\"") chr)
@@ -129,8 +129,9 @@ grammar InterscriptIsc version "0.1.0" {
 
   item_atom_start = "\"" / "'" / ident_first
   cont_stop = "to" / "before" / "after" / "not_before" / "not_after" / "}"
+  alias_decl_stop = identifier [ws] "="
   item_atom = quoted_string / none_lit / zw_primitive / any_char_lit / any_ctor / capture_ctor / maybe_ctor / some_ctor / fn_lit / capture_reference / alias_reference
-  item = (item_atom 0*(item_sep !cont_stop &item_atom_start item_atom)) as concatenation
+  item = (item_atom 0*(item_sep !cont_stop !(alias_decl_stop) &item_atom_start item_atom)) as concatenation
 
   # -- rules and stages ---------------------------------------------------