[libcxx-commits] [PATCH] D62453: Regex backreference [3/3] Validate backreferences in the constructor.

[Mark de Wever via Phabricator via libcxx-commits]

Mordante created this revision.
Mordante added a reviewer: mclow.lists.
Herald added subscribers: libcxx-commits, christof.
Herald added a project: libc++.

This patch enables throwing exceptions for invalid backreferences 
in the constructor when using the basic or grep grammar.

This fixes bug 34297.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D62453

Files:
  libcxx/include/regex
  libcxx/test/std/re/re.regex/re.regex.construct/bad_backref.pass.cpp


Index: libcxx/test/std/re/re.regex/re.regex.construct/bad_backref.pass.cpp
===================================================================
--- libcxx/test/std/re/re.regex/re.regex.construct/bad_backref.pass.cpp
+++ libcxx/test/std/re/re.regex/re.regex.construct/bad_backref.pass.cpp
@@ -18,11 +18,11 @@
 #include <cassert>
 #include "test_macros.h"
 
-static bool error_badbackref_thrown(const char *pat)
+static bool error_badbackref_thrown(const char *pat, std::regex::flag_type f = std::regex_constants::ECMAScript)
 {
     bool result = false;
     try {
-        std::regex re(pat);
+        std::regex re(pat, f);
     } catch (const std::regex_error &ex) {
         result = (ex.code() == std::regex_constants::error_backref);
     }
@@ -41,6 +41,16 @@
     const char *pat1 = "a(b)c\\1234";
     std::regex re(pat1, pat1 + 7); // extra chars after the end.
     }
+//  https://bugs.llvm.org/show_bug.cgi?id=34297
+    assert(error_badbackref_thrown("(cat)\\1", std::regex::basic));
+    assert(error_badbackref_thrown("\\(cat\\)\\1", std::regex::basic) == false);
+    assert(error_badbackref_thrown("(cat)\\1", std::regex::extended) == false);
+    assert(error_badbackref_thrown("\\(cat\\)\\1", std::regex::extended));
+    assert(error_badbackref_thrown("(cat)\\1", std::regex::grep));
+    assert(error_badbackref_thrown("\\(cat\\)\\1", std::regex::grep) == false);
+    assert(error_badbackref_thrown("(cat)\\1", std::regex::egrep) == false);
+    assert(error_badbackref_thrown("\\(cat\\)\\1", std::regex::egrep));
+
 
   return 0;
 }
Index: libcxx/include/regex
===================================================================
--- libcxx/include/regex
+++ libcxx/include/regex
@@ -3422,9 +3422,11 @@
         {
             if (*__first == '\\')
             { 
-                int __val = __traits_.value(*__temp, 10);
+                unsigned __val = __traits_.value(*__temp, 10);
                 if (__val >= 1 && __val <= 9)
                 {
+                    if (__val > mark_count())
+                        __throw_regex_error<regex_constants::error_backref>();
                     __push_back_ref(__val);
                     __first = ++__temp;
                 }


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D62453.201418.patch
Type: text/x-patch
Size: 2205 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/libcxx-commits/attachments/20190525/f6540605/attachment.bin>