common : fix json schema with '\' in literals (#17307)

* Fix json schema with '\' in literals

* Add "literal string with escapes" test

diff --git a/common/json-schema-to-grammar.cpp b/common/json-schema-to-grammar.cpp
index e64dc059f31f7b91412f944de2e95f38320ca060..c8421e1e826375f89f81e8de8d605d0d56c0d73b 100644 (file)
--- a/common/json-schema-to-grammar.cpp
+++ b/common/json-schema-to-grammar.cpp
@@ -268,10 +268,10 @@ static bool is_reserved_name(const std::string & name) {
 }
 
 std::regex INVALID_RULE_CHARS_RE("[^a-zA-Z0-9-]+");
-std::regex GRAMMAR_LITERAL_ESCAPE_RE("[\r\n\"]");
+std::regex GRAMMAR_LITERAL_ESCAPE_RE("[\r\n\"\\\\]");
 std::regex GRAMMAR_RANGE_LITERAL_ESCAPE_RE("[\r\n\"\\]\\-\\\\]");
 std::unordered_map<char, std::string> GRAMMAR_LITERAL_ESCAPES = {
-    {'\r', "\\r"}, {'\n', "\\n"}, {'"', "\\\""}, {'-', "\\-"}, {']', "\\]"}
+    {'\r', "\\r"}, {'\n', "\\n"}, {'"', "\\\""}, {'-', "\\-"}, {']', "\\]"}, {'\\', "\\\\"}
 };
 
 std::unordered_set<char> NON_LITERAL_SET = {'|', '.', '(', ')', '[', ']', '{', '}', '*', '+', '?'};

diff --git a/examples/json_schema_to_grammar.py b/examples/json_schema_to_grammar.py
index 26989157fe6b6a7e9a9b1447e717313280c1443c..886dd3d81ec3dba23e1095f5643ca3ea0877097f 100755 (executable)
--- a/examples/json_schema_to_grammar.py
+++ b/examples/json_schema_to_grammar.py
@@ -231,9 +231,9 @@ DOT = '[^\\x0A\\x0D]'
 RESERVED_NAMES = set(["root", "dot", *PRIMITIVE_RULES.keys(), *STRING_FORMAT_RULES.keys()])
 
 INVALID_RULE_CHARS_RE = re.compile(r'[^a-zA-Z0-9-]+')
-GRAMMAR_LITERAL_ESCAPE_RE = re.compile(r'[\r\n"]')
+GRAMMAR_LITERAL_ESCAPE_RE = re.compile(r'[\r\n"\\]')
 GRAMMAR_RANGE_LITERAL_ESCAPE_RE = re.compile(r'[\r\n"\]\-\\]')
-GRAMMAR_LITERAL_ESCAPES = {'\r': '\\r', '\n': '\\n', '"': '\\"', '-': '\\-', ']': '\\]'}
+GRAMMAR_LITERAL_ESCAPES = {'\r': '\\r', '\n': '\\n', '"': '\\"', '-': '\\-', ']': '\\]', '\\': '\\\\'}
 
 NON_LITERAL_SET = set('|.()[]{}*+?')
 ESCAPED_IN_REGEXPS_BUT_NOT_IN_LITERALS = set('^$.[]()|{}*+?')

diff --git a/tests/test-json-schema-to-grammar.cpp b/tests/test-json-schema-to-grammar.cpp
index 8a55bc54ae4667fe9668e1d432c0d1f9ff1b6239..1e568219d21e9cea9a75a3ba93711c41fcf87d82 100755 (executable)
--- a/tests/test-json-schema-to-grammar.cpp
+++ b/tests/test-json-schema-to-grammar.cpp
@@ -1339,6 +1339,32 @@ static void test_all(const std::string & lang, std::function<void(const TestCase
             space ::= | " " | "\n"{1,2} [ \t]{0,20}
         )"""
     });
+
+    test({
+        SUCCESS,
+        "literal string with escapes",
+        R"""({
+            "properties": {
+                "code": {
+                    "const": " \r \n \" \\ ",
+                    "description": "Generated code",
+                    "title": "Code",
+                    "type": "string"
+                }
+            },
+            "required": [
+                "code"
+            ],
+            "title": "DecoderResponse",
+            "type": "object"
+        })""",
+        R"""(
+            code ::= "\" \\r \\n \\\" \\\\ \"" space
+            code-kv ::= "\"code\"" space ":" space code
+            root ::= "{" space code-kv "}" space
+            space ::= | " " | "\n"{1,2} [ \t]{0,20}
+        )"""
+    });
 }
 
 int main() {

diff --git a/tools/server/public_legacy/json-schema-to-grammar.mjs b/tools/server/public_legacy/json-schema-to-grammar.mjs
index 1d9dc5105eee91e4e646cfc116dbfb887da5c2cb..38576c45fa071b0889025104f434cf94f18c68a9 100644 (file)
--- a/tools/server/public_legacy/json-schema-to-grammar.mjs
+++ b/tools/server/public_legacy/json-schema-to-grammar.mjs
@@ -257,9 +257,9 @@ const STRING_FORMAT_RULES = {
 const RESERVED_NAMES = {'root': true, ...PRIMITIVE_RULES, ...STRING_FORMAT_RULES};
 
 const INVALID_RULE_CHARS_RE = /[^\dA-Za-z-]+/g;
-const GRAMMAR_LITERAL_ESCAPE_RE = /[\n\r"]/g;
+const GRAMMAR_LITERAL_ESCAPE_RE = /[\n\r"\\]/g;
 const GRAMMAR_RANGE_LITERAL_ESCAPE_RE = /[\n\r"\]\-\\]/g;
-const GRAMMAR_LITERAL_ESCAPES = { '\r': '\\r', '\n': '\\n', '"': '\\"', '-': '\\-', ']': '\\]' };
+const GRAMMAR_LITERAL_ESCAPES = { '\r': '\\r', '\n': '\\n', '"': '\\"', '-': '\\-', ']': '\\]', '\\': '\\\\' };
 
 const NON_LITERAL_SET = new Set('|.()[]{}*+?');
 const ESCAPED_IN_REGEXPS_BUT_NOT_IN_LITERALS = new Set('^$.[]()|{}*+?');