Dfa module

pyproject.toml

@@ -23,6 +23,8 @@ dependencies = [
   "rstr",
   "exrex",
   "joblib",
+  #"automata-lib",
+  "automata-lib @ git+https://github.com/StefanosChaliasos/automata.git@add-support-for-charclass"
 ]
 
 [project.optional-dependencies]
@@ -33,9 +35,8 @@ dev = [
 
 [tool.ruff]
 line-length = 88
-target-version = "py38"
-lint.select = ["E", "F", "W"]
-lint.extend-select = ["I"]
+target-version = "py312"
+lint.select = ["E", "F", "W", "I"]
 lint.ignore = ["F401", "E501"]
 
 [tool.ruff.format]

scripts/lint_and_tests.py

@@ -23,7 +23,7 @@ def run_formatter() -> int:
 
 def run_tests() -> int:
     """Placeholder for future test execution."""
-    print("Running Tests (Placeholder)...")
+    print("Running Tests...")
     return run_command("pytest")
 
 

src/zkregex_fuzzer/chars.py

@@ -0,0 +1,15 @@
+import string
+
+
+def create_range(start_char: str, end_char: str) -> set[str]:
+    """
+    Create a set of characters from start_char to end_char.
+    """
+    return {chr(i) for i in range(ord(start_char), ord(end_char) + 1)}
+
+
+LATIN_EXT_CHARS = create_range("¡", "ƿ")
+GREEK_CHARS = create_range("Ͱ", "Ͽ")
+CYRILLIC_CHARS = create_range("Ѐ", "ӿ")
+ASCII_CHARS = set(string.printable)
+ALL_CHARS = ASCII_CHARS.union(LATIN_EXT_CHARS).union(GREEK_CHARS).union(CYRILLIC_CHARS)

src/zkregex_fuzzer/cli.py

@@ -9,7 +9,7 @@
 from pathlib import Path
 
 from zkregex_fuzzer.configs import GENERATORS, TARGETS, VALID_INPUT_GENERATORS
-from zkregex_fuzzer.fuzzer import fuzz_with_database, fuzz_with_grammar
+from zkregex_fuzzer.fuzzer import fuzz_with_database, fuzz_with_dfa, fuzz_with_grammar
 from zkregex_fuzzer.grammar import REGEX_GRAMMAR
 from zkregex_fuzzer.harness import HarnessStatus
 from zkregex_fuzzer.logger import logger
@@ -240,6 +240,14 @@ def do_fuzz(args):
             inputs_num=args.inputs_num,
             kwargs=kwargs,
         )
+    elif args.fuzzer == "dfa":
+        fuzz_with_dfa(
+            target_implementation=args.target,
+            oracle_params=(args.oracle == "valid", args.valid_input_generator),
+            regex_num=args.regex_num,
+            inputs_num=args.inputs_num,
+            kwargs=kwargs,
+        )
 
 
 def do_reproduce(args):

src/zkregex_fuzzer/configs.py

@@ -1,7 +1,16 @@
 from zkregex_fuzzer.grammar import REGEX_GRAMMAR
-from zkregex_fuzzer.regexgen import DatabaseRegexGenerator, GrammarRegexGenerator
+from zkregex_fuzzer.regexgen import (
+    DatabaseRegexGenerator,
+    DFARegexGenerator,
+    GrammarRegexGenerator,
+)
 from zkregex_fuzzer.runner import CircomRunner, NoirRunner, PythonReRunner
-from zkregex_fuzzer.vinpgen import ExrexGenerator, GrammarBasedGenerator, RstrGenerator
+from zkregex_fuzzer.vinpgen import (
+    DFAWalkerGenerator,
+    ExrexGenerator,
+    GrammarBasedGenerator,
+    RstrGenerator,
+)
 
 TARGETS = {
     "circom": CircomRunner,
@@ -17,9 +26,11 @@
     "grammar": GrammarBasedGenerator,
     "rstr": RstrGenerator,
     "exrex": ExrexGenerator,
+    "dfa": DFAWalkerGenerator,
 }
 
 GENERATORS = {
     "grammar": GrammarRegexGenerator,
     "database": DatabaseRegexGenerator,
+    "dfa": DFARegexGenerator,
 }