Do not interpret characters that cannot be parsed in octal as int (#176)

ref: https://yaml.org/type/int.html https://yaml.org/type/float.html
kislyuk · Oct 25, 2023 · d4faa16 · d4faa16
1 parent ee87412
commit d4faa16
Show file tree

Hide file tree

Showing 2 changed files with 23 additions and 2 deletions.
diff --git a/test/test.py b/test/test.py
@@ -317,6 +317,7 @@ def test_yaml_1_2(self):
 
     def test_yaml_1_1_octals(self):
         self.assertEqual(self.run_yq("on: -012345", ["-y", "."]), "'on': -5349\n")
+        self.assertEqual(self.run_yq("on: -012349", ["-y", "."]), "'on': -012349\n")
 
     @unittest.expectedFailure
     def test_yaml_1_2_octals(self):

diff --git a/yq/loader.py b/yq/loader.py
@@ -87,13 +87,33 @@
         },
         {
             "tag": "tag:yaml.org,2002:int",
-            "regexp": re.compile(r"^(?:|0o[0-7]+|[-+]?(?:[0-9]+)|0x[0-9a-fA-F]+)$", re.X),
+            "regexp": re.compile(
+                r"""^(?:
+                # [-+]?0b[0-1_]+ # (base 2)
+                 [-+]?0[0-7]+ # (base 8)
+                |[-+]?0o[0-7]+ # (base 8)
+                |[-+]?(0|[1-9][0-9]*) # (base 10)
+                # |[-+]?0[0-7_]+ # (base 8)
+                # |[-+]?0o[0-7_]+ # (base 8)
+                # |[-+]?(0|[1-9][0-9_]*) # (base 10)
+                # |[-+]?0x[0-9a-fA-F_]+ # (base 16)
+                # |[-+]?[1-9][0-9_]*(:[0-5]?[0-9])+ # (base 60)
+                )$""",
+                re.X
+            ),
             "start_chars": list("-+0123456789"),
         },
         {
             "tag": "tag:yaml.org,2002:float",
             "regexp": re.compile(
-                r"^(?:[-+]?(?:\.[0-9]+|[0-9]+(\.[0-9]*)?)(?:[eE][-+]?[0-9]+)?|[-+]?\.(?:inf|Inf|INF)|\.(?:nan|NaN|NAN))$",  # noqa
+                r"""^(?:
+                 [-+]?([0-9][0-9]*)?\.[0-9.]*([eE][-+][0-9]+)? (base 10)
+                |[-+]?[0-9][0-9]*(:[0-5]?[0-9])+\.[0-9]* (base 60)
+                # |[-+]?([0-9][0-9_]*)?\.[0-9.]*([eE][-+][0-9]+)? (base 10)
+                # |[-+]?[0-9][0-9_]*(:[0-5]?[0-9])+\.[0-9_]* (base 60)
+                |[-+]?\.(inf|Inf|INF) # (infinity)
+                |\.(nan|NaN|NAN) # (not a number)
+                )$""",
                 re.X,
             ),
             "start_chars": list("-+0123456789."),