From 55b2d0849d3ec9e45e4a4d9e480f5fa7977872a6 Mon Sep 17 00:00:00 2001
From: Olivier Chafik <ochafik@users.noreply.github.com>
Date: Thu, 6 Jun 2024 10:07:06 +0100
Subject: grammars: x{min,max} repetition operator (#6640)

* grammars: x{min,max} repetition operator + tweak +/*/? to avoid duplication of original over alternates

* grammars: handle `x{n}` and fix `x{n,n}`

* grammars: document new repetition operators

* grammars: uniform use of int for min & max

* grammars: refactor parser test

* grammar: parsing tests w/ natural pretty print of updated expectations

* grammars: much prettier print of expectations (+ TEST_GRAMMAR_PARSER_PRINT_ALL=1 to force all)

* grammars: improve test pretty print again

* grammars: pretty print rules and chars

* grammars: fix copy rule skipping

* grammars: disallow `a{,}` (not allowed in regexps)

* Update common/grammar-parser.cpp

Co-authored-by: Clint Herron <hanclinto@gmail.com>

* grammars: fix copy rule skipping (again) & display of expectations

* grammars: more test cases

* grammars: update reps parsing to bring ? / * / + closer to before

* json: use new GBNF repetitions{m,n} syntax

* grammars: update performance gotchas w/ repetition advice

* Update examples/json_schema_to_grammar.py

Co-authored-by: Clint Herron <hanclinto@gmail.com>

* Update examples/server/public/json-schema-to-grammar.mjs

Co-authored-by: Clint Herron <hanclinto@gmail.com>

* grammars: comment on rule repetitions

* grammars: ensure unambiguous number alternatives

* grammar: nit typo switched error msgs

* grammar: nit numbering in comment

* json: update numeric rule to be unambiguous

* Apply suggestions from code review

Co-authored-by: Clint Herron <hanclinto@gmail.com>

* Update examples/server/public/json-schema-to-grammar.mjs

Co-authored-by: Clint Herron <hanclinto@gmail.com>

* json: fix integral-part

* grammar: add repetition tests

---------

Co-authored-by: Clint Herron <hanclinto@gmail.com>
---
 tests/test-grammar-integration.cpp | 76 ++++++++++++++++++++++++++++++++++++++
 1 file changed, 76 insertions(+)

(limited to 'tests/test-grammar-integration.cpp')

diff --git a/tests/test-grammar-integration.cpp b/tests/test-grammar-integration.cpp
index 01c5bb27..9bdab05a 100644
--- a/tests/test-grammar-integration.cpp
+++ b/tests/test-grammar-integration.cpp
@@ -292,6 +292,82 @@ static void test_quantifiers() {
             "catyyy",
         }
     );
+    test_grammar(
+        "simple exact repetition",
+        // Grammar
+        R"""(
+            root ::= [ab]{4}
+        )""",
+        // Passing strings
+        {
+            "aaaa",
+            "bbbb",
+            "abab",
+        },
+        // Failing strings
+        {
+            "a",
+            "b",
+            "aaaaa",
+        }
+    );
+    test_grammar(
+        "simple min repetition",
+        // Grammar
+        R"""(
+            root ::= [ab]{4,}
+        )""",
+        // Passing strings
+        {
+            "aaaa",
+            "aaaaab",
+            "bbbb",
+            "ababab",
+        },
+        // Failing strings
+        {
+            "",
+            "aba",
+        }
+    );
+    test_grammar(
+        "simple max repetition",
+        // Grammar
+        R"""(
+            root ::= [ab]{0,4}
+        )""",
+        // Passing strings
+        {
+            "",
+            "a",
+            "aa",
+            "aaa",
+            "aaab",
+        },
+        // Failing strings
+        {
+            "aaaaa",
+        }
+    );
+    test_grammar(
+        "min / max repetition",
+        // Grammar
+        R"""(
+            root ::= ("0x" [A-F0-9]{2} " "?){3,5}
+        )""",
+        // Passing strings
+        {
+            "0xFF 0x12 0xAB",
+            "0xFF 0x12 0xAB 0x00 0x00",
+        },
+        // Failing strings
+        {
+            "",
+            "0xFF",
+            "0xFF 0x12",
+            "0xFF 0x12 0xAB 0x00 0x00 0x00",
+        }
+    );
 }
 
 static void test_failure_missing_root() {
-- 
cgit v1.2.3