gh-114014: Update `fractions.Fraction()`'s rational parsing regex (#114015)

Fix a bug in the regex used for parsing a string input to the `fractions.Fraction` constructor. That bug led to an inconsistent exception message being given for some inputs.

---------

Co-authored-by: blurb-it[bot] <43283697+blurb-it[bot]@users.noreply.github.com>
Co-authored-by: Mark Dickinson <dickinsm@gmail.com>

diff --git a/Lib/fractions.py b/Lib/fractions.py
index 6532d5d54e3c351fe29ea74c135c7cd0b7dc9433..389ab386b6a8a4d4d0c0179c3a4cca7feeaa0f39 100644 (file)
--- a/Lib/fractions.py
+++ b/Lib/fractions.py
@@ -55,17 +55,17 @@ def _hash_algorithm(numerator, denominator):
     return -2 if result == -1 else result
 
 _RATIONAL_FORMAT = re.compile(r"""
-    \A\s*                                 # optional whitespace at the start,
-    (?P<sign>[-+]?)                       # an optional sign, then
-    (?=\d|\.\d)                           # lookahead for digit or .digit
-    (?P<num>\d*|\d+(_\d+)*)               # numerator (possibly empty)
-    (?:                                   # followed by
-       (?:\s*/\s*(?P<denom>\d+(_\d+)*))?  # an optional denominator
-    |                                     # or
-       (?:\.(?P<decimal>d*|\d+(_\d+)*))?  # an optional fractional part
-       (?:E(?P<exp>[-+]?\d+(_\d+)*))?     # and optional exponent
+    \A\s*                                  # optional whitespace at the start,
+    (?P<sign>[-+]?)                        # an optional sign, then
+    (?=\d|\.\d)                            # lookahead for digit or .digit
+    (?P<num>\d*|\d+(_\d+)*)                # numerator (possibly empty)
+    (?:                                    # followed by
+       (?:\s*/\s*(?P<denom>\d+(_\d+)*))?   # an optional denominator
+    |                                      # or
+       (?:\.(?P<decimal>\d*|\d+(_\d+)*))?  # an optional fractional part
+       (?:E(?P<exp>[-+]?\d+(_\d+)*))?      # and optional exponent
     )
-    \s*\Z                                 # and optional whitespace to finish
+    \s*\Z                                  # and optional whitespace to finish
 """, re.VERBOSE | re.IGNORECASE)
 
 

diff --git a/Lib/test/test_fractions.py b/Lib/test/test_fractions.py
index 84779526ce0eb071a9b2ac18485de0d8e9e0cb2b..af3cb214ab0ac11474dd4b709f59ed2abc3dbcb1 100644 (file)
--- a/Lib/test/test_fractions.py
+++ b/Lib/test/test_fractions.py
@@ -261,6 +261,30 @@ class FractionTest(unittest.TestCase):
         self.assertRaisesMessage(
             ValueError, "Invalid literal for Fraction: '1.1e+1__1'",
             F, "1.1e+1__1")
+        self.assertRaisesMessage(
+            ValueError, "Invalid literal for Fraction: '123.dd'",
+            F, "123.dd")
+        self.assertRaisesMessage(
+            ValueError, "Invalid literal for Fraction: '123.5_dd'",
+            F, "123.5_dd")
+        self.assertRaisesMessage(
+            ValueError, "Invalid literal for Fraction: 'dd.5'",
+            F, "dd.5")
+        self.assertRaisesMessage(
+            ValueError, "Invalid literal for Fraction: '7_dd'",
+            F, "7_dd")
+        self.assertRaisesMessage(
+            ValueError, "Invalid literal for Fraction: '1/dd'",
+            F, "1/dd")
+        self.assertRaisesMessage(
+            ValueError, "Invalid literal for Fraction: '1/123_dd'",
+            F, "1/123_dd")
+        self.assertRaisesMessage(
+            ValueError, "Invalid literal for Fraction: '789edd'",
+            F, "789edd")
+        self.assertRaisesMessage(
+            ValueError, "Invalid literal for Fraction: '789e2_dd'",
+            F, "789e2_dd")
         # Test catastrophic backtracking.
         val = "9"*50 + "_"
         self.assertRaisesMessage(

diff --git a/Misc/NEWS.d/next/Library/2024-01-13-11-34-29.gh-issue-114014.WRHifN.rst b/Misc/NEWS.d/next/Library/2024-01-13-11-34-29.gh-issue-114014.WRHifN.rst
new file mode 100644 (file)
index 0000000..a6630d7
--- /dev/null
+++ b/Misc/NEWS.d/next/Library/2024-01-13-11-34-29.gh-issue-114014.WRHifN.rst
@@ -0,0 +1 @@
+Fixed a bug in :class:`fractions.Fraction` where an invalid string using ``d`` in the decimals part creates a different error compared to other invalid letters/characters. Patch by Jeremiah Gabriel Pascual.