From: Joe Eli McIlvain <redacted>
Date: Wed, 16 Oct 2024 16:03:24 +0000 (-0700)
Subject: grammar : fix JSON Schema for string regex with top-level alt. (#9903)
X-Git-Tag: upstream/0.0.4488~559
X-Git-Url: https://git.djapps.eu/?a=commitdiff_plain;h=66c2c93082289325199ae1f773f3b0ab2e399a47;p=pkg%2Fggml%2Fsources%2Fllama.cpp

grammar : fix JSON Schema for string regex with top-level alt. (#9903)

Prior to this commit, using a JSON Schema containing a string
with `pattern` regular expression that uses top-level alternation
(e.g. `"pattern": "^A|B|C|D$"`) would result in invalid JSON
output from the constrained sampling grammar, because it
ended up creating a grammar rule like this for the string:

```
thing ::= "\"" "A" | "B" | "C" | "D" "\"" space
```

Note that this rule will only match a starting quote for the "A" case,
and will only match an ending quote for the "D" case,
so this rule will always produce invalid JSON when used for sampling
(that is, the JSON will always be lacking the starting quote,
the ending quote, or both).

This was fixed in a simple way by adding parentheses to the
generated rule (for all string pattern rules, to keep it simple),
such that the new generated rule looks like this (correct):

```
thing ::= "\"" ("A" | "B" | "C" | "D") "\"" space
```
---

diff --git a/common/json-schema-to-grammar.cpp b/common/json-schema-to-grammar.cpp
index 881eb49e..dadc18c8 100644
--- a/common/json-schema-to-grammar.cpp
+++ b/common/json-schema-to-grammar.cpp
@@ -611,7 +611,7 @@ private:
             }
             return join_seq();
         };
-        return _add_rule(name, "\"\\\"\" " + to_rule(transform()) + " \"\\\"\" space");
+        return _add_rule(name, "\"\\\"\" (" + to_rule(transform()) + ") \"\\\"\" space");
     }
 
     /*
diff --git a/examples/json_schema_to_grammar.py b/examples/json_schema_to_grammar.py
index a8779bf3..fc9f0097 100755
--- a/examples/json_schema_to_grammar.py
+++ b/examples/json_schema_to_grammar.py
@@ -540,7 +540,7 @@ class SchemaConverter:
         return self._add_rule(
             name,
             to_rule(transform()) if self._raw_pattern \
-                else "\"\\\"\" " + to_rule(transform()) + " \"\\\"\" space")
+                else "\"\\\"\" (" + to_rule(transform()) + ") \"\\\"\" space")
 
 
     def _resolve_ref(self, ref):
diff --git a/examples/server/public/json-schema-to-grammar.mjs b/examples/server/public/json-schema-to-grammar.mjs
index 7267f3f9..e67bb15c 100644
--- a/examples/server/public/json-schema-to-grammar.mjs
+++ b/examples/server/public/json-schema-to-grammar.mjs
@@ -529,7 +529,7 @@ export class SchemaConverter {
       return joinSeq();
     };
 
-    return this._addRule(name, "\"\\\"\" " + toRule(transform()) + " \"\\\"\" space")
+    return this._addRule(name, "\"\\\"\" (" + toRule(transform()) + ") \"\\\"\" space")
   }
 
   _notStrings(strings) {
diff --git a/tests/test-json-schema-to-grammar.cpp b/tests/test-json-schema-to-grammar.cpp
index 3a89598a..9d2db91f 100755
--- a/tests/test-json-schema-to-grammar.cpp
+++ b/tests/test-json-schema-to-grammar.cpp
@@ -696,7 +696,7 @@ static void test_all(const std::string & lang, std::function<void(const TestCase
             "pattern": "^abc?d*efg+(hij)?kl$"
         })""",
         R"""(
-            root ::= "\"" "ab" "c"? "d"* "ef" "g"+ ("hij")? "kl" "\"" space
+            root ::= "\"" ("ab" "c"? "d"* "ef" "g"+ ("hij")? "kl") "\"" space
             space ::= | " " | "\n" [ \t]{0,20}
         )"""
     });
@@ -709,7 +709,7 @@ static void test_all(const std::string & lang, std::function<void(const TestCase
             "pattern": "^\\[\\]\\{\\}\\(\\)\\|\\+\\*\\?$"
         })""",
         R"""(
-            root ::= "\"" "[]{}()|+*?" "\"" space
+            root ::= "\"" ("[]{}()|+*?") "\"" space
             space ::= | " " | "\n" [ \t]{0,20}
         )"""
     });
@@ -722,7 +722,20 @@ static void test_all(const std::string & lang, std::function<void(const TestCase
             "pattern": "^\"$"
         })""",
         R"""(
-            root ::= "\"" "\"" "\"" space
+            root ::= "\"" ("\"") "\"" space
+            space ::= | " " | "\n" [ \t]{0,20}
+        )"""
+    });
+
+    test({
+        SUCCESS,
+        "regexp with top-level alternation",
+        R"""({
+            "type": "string",
+            "pattern": "^A|B|C|D$"
+        })""",
+        R"""(
+            root ::= "\"" ("A" | "B" | "C" | "D") "\"" space
             space ::= | " " | "\n" [ \t]{0,20}
         )"""
     });
@@ -736,7 +749,7 @@ static void test_all(const std::string & lang, std::function<void(const TestCase
         })""",
         R"""(
             dot ::= [^\x0A\x0D]
-            root ::= "\"" ("(" root-1{1,3} ")")? root-1{3,3} "-" root-1{4,4} " " "a"{3,5} "nd" dot dot dot "\"" space
+            root ::= "\"" (("(" root-1{1,3} ")")? root-1{3,3} "-" root-1{4,4} " " "a"{3,5} "nd" dot dot dot) "\"" space
             root-1 ::= [0-9]
             space ::= | " " | "\n" [ \t]{0,20}
         )"""