eyeprolog 1.2.4 → 1.2.5

package/conformance-report.md

@@ -11,7 +11,7 @@ This report summarizes the file-based conformance corpus under `test/conformance
 | builtins | 11 | 0 | 0 | 0 | 11 |
 | context | 11 | 0 | 0 | 0 | 11 |
 | control | 15 | 0 | 0 | 0 | 15 |
-| iso | 167 | 209 | 0 | 0 | 376 |
+| iso | 167 | 210 | 0 | 0 | 377 |
 | lists | 52 | 3 | 0 | 0 | 55 |
 | modules | 2 | 0 | 0 | 0 | 2 |
 | negation | 8 | 0 | 19 | 0 | 27 |
@@ -23,4 +23,4 @@ This report summarizes the file-based conformance corpus under `test/conformance
 | terms | 26 | 3 | 0 | 0 | 29 |
 | unification | 18 | 0 | 0 | 0 | 18 |
 | variables | 16 | 9 | 0 | 0 | 25 |
-| **Total** | **482** | **260** | **19** | **21** | **782** |
+| **Total** | **482** | **261** | **19** | **21** | **783** |

package/package.json

@@ -3,7 +3,7 @@
   "publishConfig": {
     "access": "public"
   },
-  "version": "1.2.4",
+  "version": "1.2.5",
   "description": "EyeProlog turns facts and rules into answers and proofs.",
   "type": "module",
   "main": "./index.js",

package/src/iso.js

@@ -1075,9 +1075,12 @@ function quotedEscapeEnd(source, index) {
     while (/^[0-9A-Fa-f]$/.test(source[cursor] ?? '')) cursor++;
     return source[cursor] === '\\' ? cursor : Math.max(index + 1, cursor - 1);
   }
-  if (/^[0-7]$/.test(escaped)) {
+  if (/^[0-9]$/.test(escaped)) {
     let cursor = index + 1;
-    while (/^[0-7]$/.test(source[cursor] ?? '')) cursor++;
+    // Scan all decimal digits here, including 8 and 9.  This scanner only
+    // locates the end of a candidate quoted escape; the parser remains
+    // authoritative and rejects non-octal digits.
+    while (/^[0-9]$/.test(source[cursor] ?? '')) cursor++;
     return source[cursor] === '\\' ? cursor : Math.max(index + 1, cursor - 1);
   }
 

package/src/parser.js

@@ -303,6 +303,10 @@ class Parser {
       if (this.take() !== '\\') throw new Error(`parse line ${line}: bad octal escape`);
       return String.fromCodePoint(Number.parseInt(digits, 8));
     }
+    // A backslash followed by a decimal digit is numeric-escape syntax, but
+    // ISO octal digits are limited to 0..7.  Do not reinterpret \8 or \9 as
+    // implementation-specific one-character escapes.
+    if (/^[0-9]$/.test(escaped)) throw new Error(`parse line ${line}: bad octal escape`);
     return escaped;
   }
   nextToken() {

package/src/repl.js

@@ -253,9 +253,12 @@ function quotedEscapeEnd(source, index) {
     while (/^[0-9A-Fa-f]$/.test(source[cursor] ?? '')) cursor++;
     return source[cursor] === '\\' ? cursor : Math.max(index + 1, cursor - 1);
   }
-  if (/^[0-7]$/.test(escaped)) {
+  if (/^[0-9]$/.test(escaped)) {
     let cursor = index + 1;
-    while (/^[0-7]$/.test(source[cursor] ?? '')) cursor++;
+    // Scan all decimal digits here, including 8 and 9.  This scanner only
+    // locates the end of a candidate quoted escape; the parser remains
+    // authoritative and rejects non-octal digits.
+    while (/^[0-9]$/.test(source[cursor] ?? '')) cursor++;
     return source[cursor] === '\\' ? cursor : Math.max(index + 1, cursor - 1);
   }
 

package/src/write.js

@@ -22,6 +22,7 @@ function quoteAtom(name) {
   for (const ch of name) {
     if (ch === "'") out += "''";
     else if (ch === '\\') out += '\\\\';
+    else if (ch === '\x00') out += '\\0\\';
     else if (ch === '\x07') out += '\\a';
     else if (ch === '\b') out += '\\b';
     else if (ch === '\r') out += '\\r';
@@ -59,6 +60,7 @@ function writeString(value) {
   let out = '"';
   for (const ch of value) {
     if (ch === '"' || ch === '\\') out += `\\${ch}`;
+    else if (ch === '\x00') out += '\\0\\';
     else if (ch === '\x07') out += '\\a';
     else if (ch === '\b') out += '\\b';
     else if (ch === '\r') out += '\\r';

package/test/conformance/ISO-MATRIX.md

@@ -8,7 +8,7 @@ compliance audit and the remaining work before a full conformance claim.
 
 | Standard area | Implementation | Representative executable coverage |
 | --- | --- | --- |
-| Clause 6 lexical and term syntax | tokenizer, operator parser, lists, curly terms, quotes, numeric syntax, comments | `scryer_lexical_terms`, `lexical_and_curly_terms`, `double_quoted_lists`, `corrigendum1_double_quote_operator`, `wg17_syntax_high_risk`, syntax error cases |
+| Clause 6 lexical and term syntax | tokenizer, operator parser, lists, curly terms, quotes, numeric syntax, comments | `scryer_lexical_terms`, `lexical_and_curly_terms`, `double_quoted_lists`, `corrigendum1_double_quote_operator`, `wg17_syntax_high_risk`, `wg17_invalid_octal_escape`, syntax error cases |
 | Clause 7 term order and unification | finite-tree unification, identity, standard order, errors | `unification_control_information`, `swipl_occurs_check`, `term_modes_and_ordering`, `logtalk_compare_standard_order` |
 | Clause 7 control and exceptions | call, cut, conjunction, disjunction, if-then-else, catch and throw | `cut_control`, `control_and_terms`, `exceptions_and_flags`, `corrigenda_catch_callability`, `throw_copies_ball` |
 | 8.2-8.5 term predicates | unification, Corrigendum 2 tests, comparison, sorting, creation and decomposition | `corrigenda_term_predicates`, `corrigenda_sort_keysort`, `logtalk_arg_unification`, `logtalk_univ`, associated error cases |

package/test/conformance/README.md

@@ -102,7 +102,7 @@ Selected cases are adapted from the ISO and standard-core suites of Logtalk,
 Scryer Prolog, Trealla Prolog, and SWI-Prolog. Their upstream identifiers and licenses
 are recorded in [THIRD_PARTY.md](THIRD_PARTY.md).
 
-The corpus has 376 cases in `iso/` and 782 file-based conformance cases in
+The corpus has 377 cases in `iso/` and 783 file-based conformance cases in
 total. The generated `conformance-report.md` is the authoritative source for
 current category totals. Together with regression, documentation-sync, API,
 example, and book-example checks, `npm test` is the release gate.

package/test/conformance/cases/iso/wg17_syntax_high_risk.pl

@@ -1,6 +1,6 @@
 % High-risk ISO syntax/write regressions, independently derived from
 % ISO/IEC 13211-1 clauses 6.3, 6.4 and 7.10 and cross-checked against the
-% public WG17 conformity-testing syntax cases (#1, #14-15, #28-31, #33-34).
+% public WG17 conformity-testing syntax cases (#1, #14-15, #28-31, #33-34, #301).
 
 %% goal: wg17_numeric_escape
 wg17_numeric_escape :-
@@ -24,3 +24,7 @@ wg17_operator_precedence :-
 %% goal: wg17_canonical_list
 wg17_canonical_list :-
     write_canonical([a]), nl.
+
+%% goal: wg17_zero_character_escape
+wg17_zero_character_escape :-
+    writeq('\0\'), nl.

package/test/conformance/errors/iso/wg17_invalid_octal_escape.pl

@@ -0,0 +1 @@
+'\8\'.

package/test/conformance/expected/iso/wg17_syntax_high_risk.pl

@@ -11,3 +11,5 @@ a :- b, c
 wg17_operator_precedence.
 '.'(a,[])
 wg17_canonical_list.
+'\0\'
+wg17_zero_character_escape.

package/test/conformance/expected-errors/iso/wg17_invalid_octal_escape.txt

@@ -0,0 +1 @@
+parse line 1: bad octal escape

package/test/run-regression.mjs

@@ -671,6 +671,31 @@ c4 ?- call((!;1)).
         assertEqual(result.stderr, '', 'stderr');
       },
     },
+    {
+      name: 'writeq preserves the NUL character with an ISO octal escape',
+      run: () => {
+        const result = runCli([], {
+          input: "writeq('\\0\\').\nhalt.\n",
+        });
+        assertEqual(result.status, 0, 'exit status');
+        assertEqual(result.stdout, "?- '\\0\\'   true.\n?- ", 'stdout');
+        assertEqual(result.stderr, '', 'stderr');
+      },
+    },
+    {
+      name: 'REPL rejects non-octal numeric escapes without waiting for continuation',
+      run: () => {
+        const result = runCli([], {
+          input: "'\\8\\'.\nhalt.\n",
+        });
+        assertEqual(result.status, 0, 'exit status');
+        assertEqual(result.stdout,
+          '?-    parse line 1: bad octal escape.\n' +
+          '?- ',
+          'stdout');
+        assertEqual(result.stderr, '', 'stderr');
+      },
+    },
     {
       name: 'REPL read predicates consume following interactive term input',
       run: () => {
@@ -1312,6 +1337,16 @@ c4 ?- call((!;1)).
           "answer('\\a').\n",
           'read/1 user_input numeric escape',
         );
+
+        const invalidOctal = String.fromCharCode(39, 92, 56, 92, 39, 46);
+        assertEqual(
+          run('answer(T) :- catch(read(T), E, T=E).\n', {
+            goal: 'answer(T)',
+            ioOptions: { input: invalidOctal },
+          }).stdout,
+          'answer(error(syntax_error(read_term), eyeprolog)).\n',
+          'read/1 rejects non-octal numeric escape',
+        );
       },
     },
     {

package/the-art-of-eyeprolog.md

@@ -5279,7 +5279,10 @@ message("café").
 Inside a quoted atom, a single quote is doubled: `'don''t'`. Quoted characters
 support the ISO symbolic control escapes such as `\a`, `\n`, and `\t`, and numeric
 octal or hexadecimal escapes are terminated by a backslash; for example, `'\7\'`
-and `'\x7\'` both denote the alert character. Double-quoted lists use the same
+and `'\x7\'` both denote the alert character. The NUL character, when present in
+the processor character set, is written readably as `'\0\'`; digits `8` and `9`
+are not octal digits, so forms such as `'\8\'` are syntax errors rather than
+continuation input. Double-quoted lists use the same
 quoted-character escapes. Whitespace is insignificant
 between tokens, and a `%` comment continues to the end of its line. Doubling
 the active delimiter is also accepted inside either quoted form, so `""`
@@ -6946,7 +6949,7 @@ precedence still need one-by-one closure. `test/conformance/ISO-MATRIX.md`
 maps language families to representative executable cases.
 
 The complete suite must pass before release. The file-based conformance corpus
-contains 782 cases, including 376 focused ISO
+contains 783 cases, including 377 focused ISO
 cases derived from the success, failure, mode, and error behavior in
 ISO/IEC 13211-1 clauses 7 and 8, Part 2 modules, and Part 3 grammar rules.
 Separate exact-output suites check 189 normal