[3.13] gh-127971: fix off-by-one read beyond the end of a string during search (...

(cherry picked from commit 85ec3b3b503ffd5b7e45f8b3fa2cec0c10e4bef0)

diff --git a/Lib/test/string_tests.py b/Lib/test/string_tests.py
index 9bb0ce7bb57f8bb418c562424e0fb56ea17c21eb..8dcfa98f85b0754ec94bf8a1cf74d1892191ab08 100644 (file)
--- a/Lib/test/string_tests.py
+++ b/Lib/test/string_tests.py
@@ -767,6 +767,15 @@ class BaseTest:
         self.checkraises(TypeError, 'hello', 'replace', 42, 'h')
         self.checkraises(TypeError, 'hello', 'replace', 'h', 42)
 
+    def test_replacement_on_buffer_boundary(self):
+        # gh-127971: Check we don't read past the end of the buffer when a
+        # potential match misses on the last character.
+        any_3_nonblank_codepoints = '!!!'
+        seven_codepoints = any_3_nonblank_codepoints + ' ' + any_3_nonblank_codepoints
+        a = (' ' * 243) + seven_codepoints + (' ' * 7)
+        b = ' ' * 6 + chr(256)
+        a.replace(seven_codepoints, b)
+
     def test_replace_uses_two_way_maxcount(self):
         # Test that maxcount works in _two_way_count in fastsearch.h
         A, B = "A"*1000, "B"*1000

diff --git a/Misc/NEWS.d/next/Core and Builtins/2025-04-16-12-01-13.gh-issue-127971.pMDOQ0.rst b/Misc/NEWS.d/next/Core and Builtins/2025-04-16-12-01-13.gh-issue-127971.pMDOQ0.rst
new file mode 100644 (file)
index 0000000..ced7a9c
--- /dev/null
+++ b/Misc/NEWS.d/next/Core and Builtins/2025-04-16-12-01-13.gh-issue-127971.pMDOQ0.rst
@@ -0,0 +1 @@
+Fix off-by-one read beyond the end of a string in string search.

diff --git a/Objects/stringlib/fastsearch.h b/Objects/stringlib/fastsearch.h
index 257b7bd6788ad248a08f2e85bdb7ac3b0d0e34b2..513250c08be104e74aa5e22b6b58f5e730a47fe5 100644 (file)
--- a/Objects/stringlib/fastsearch.h
+++ b/Objects/stringlib/fastsearch.h
@@ -588,7 +588,7 @@ STRINGLIB(default_find)(const STRINGLIB_CHAR* s, Py_ssize_t n,
                 continue;
             }
             /* miss: check if next character is part of pattern */
-            if (!STRINGLIB_BLOOM(mask, ss[i+1])) {
+            if (i + 1 <= w && !STRINGLIB_BLOOM(mask, ss[i+1])) {
                 i = i + m;
             }
             else {
@@ -597,7 +597,7 @@ STRINGLIB(default_find)(const STRINGLIB_CHAR* s, Py_ssize_t n,
         }
         else {
             /* skip: check if next character is part of pattern */
-            if (!STRINGLIB_BLOOM(mask, ss[i+1])) {
+            if (i + 1 <= w && !STRINGLIB_BLOOM(mask, ss[i+1])) {
                 i = i + m;
             }
         }
@@ -661,7 +661,7 @@ STRINGLIB(adaptive_find)(const STRINGLIB_CHAR* s, Py_ssize_t n,
                 }
             }
             /* miss: check if next character is part of pattern */
-            if (!STRINGLIB_BLOOM(mask, ss[i+1])) {
+            if (i + 1 <= w && !STRINGLIB_BLOOM(mask, ss[i+1])) {
                 i = i + m;
             }
             else {
@@ -670,7 +670,7 @@ STRINGLIB(adaptive_find)(const STRINGLIB_CHAR* s, Py_ssize_t n,
         }
         else {
             /* skip: check if next character is part of pattern */
-            if (!STRINGLIB_BLOOM(mask, ss[i+1])) {
+            if (i + 1 <= w && !STRINGLIB_BLOOM(mask, ss[i+1])) {
                 i = i + m;
             }
         }