From b7d08bc04a4296982fcef8b6b8a354a9e4e7afca Mon Sep 17 00:00:00 2001
From: Frank Tang <ftang@chromium.org>
Date: Sat, 1 Feb 2020 02:39:04 +0000
Subject: [PATCH] ICU-20958 Prevent SEGV_MAPERR in append

See #971
---
 icu4c/source/common/unistr.cpp          |  6 ++-
 icu4c/source/test/intltest/ustrtest.cpp | 62 +++++++++++++++++++++++++
 icu4c/source/test/intltest/ustrtest.h   |  1 +
 3 files changed, 68 insertions(+), 1 deletion(-)

diff --git a/icu4c/source/common/unistr.cpp b/icu4c/source/common/unistr.cpp
index 901bb3358ba..077b4d6ef20 100644
--- a/icu4c/source/common/unistr.cpp
+++ b/icu4c/source/common/unistr.cpp
@@ -1563,7 +1563,11 @@ UnicodeString::doAppend(const UChar *srcChars, int32_t srcStart, int32_t srcLeng
   }
 
   int32_t oldLength = length();
-  int32_t newLength = oldLength + srcLength;
+  int32_t newLength;
+  if (uprv_add32_overflow(oldLength, srcLength, &newLength)) {
+    setToBogus();
+    return *this;
+  }
 
   // Check for append onto ourself
   const UChar* oldArray = getArrayStart();
diff --git a/icu4c/source/test/intltest/ustrtest.cpp b/icu4c/source/test/intltest/ustrtest.cpp
index b6515ea813c..ad38bdf53a3 100644
--- a/icu4c/source/test/intltest/ustrtest.cpp
+++ b/icu4c/source/test/intltest/ustrtest.cpp
@@ -67,6 +67,7 @@ void UnicodeStringTest::runIndexedTest( int32_t index, UBool exec, const char* &
     TESTCASE_AUTO(TestWCharPointers);
     TESTCASE_AUTO(TestNullPointers);
     TESTCASE_AUTO(TestUnicodeStringInsertAppendToSelf);
+    TESTCASE_AUTO(TestLargeAppend);
     TESTCASE_AUTO_END;
 }
 
@@ -2310,3 +2311,64 @@ void UnicodeStringTest::TestUnicodeStringInsertAppendToSelf() {
     str.insert(2, sub);
     assertEquals("", u"abbcdcde", str);
 }
+
+void UnicodeStringTest::TestLargeAppend() {
+    if(quick) return;
+
+    IcuTestErrorCode status(*this, "TestLargeAppend");
+    // Make a large UnicodeString
+    int32_t len = 0xAFFFFFF;
+    UnicodeString str;
+    char16_t *buf = str.getBuffer(len);
+    // A fast way to set buffer to valid Unicode.
+    // 4E4E is a valid unicode character
+    uprv_memset(buf, 0x4e, len * 2);
+    str.releaseBuffer(len);
+    UnicodeString dest;
+    // Append it 16 times
+    // 0xAFFFFFF times 16 is 0xA4FFFFF1,
+    // which is greater than INT32_MAX, which is 0x7FFFFFFF.
+    int64_t total = 0;
+    for (int32_t i = 0; i < 16; i++) {
+        dest.append(str);
+        total += len;
+        if (total <= INT32_MAX) {
+            assertFalse("dest is not bogus", dest.isBogus());
+        } else {
+            assertTrue("dest should be bogus", dest.isBogus());
+        }
+    }
+    dest.remove();
+    total = 0;
+    for (int32_t i = 0; i < 16; i++) {
+        dest.append(str);
+        total += len;
+        if (total + len <= INT32_MAX) {
+            assertFalse("dest is not bogus", dest.isBogus());
+        } else if (total <= INT32_MAX) {
+            // Check that a string of exactly the maximum size works
+            UnicodeString str2;
+            int32_t remain = INT32_MAX - total;
+            char16_t *buf2 = str2.getBuffer(remain);
+            if (buf2 == nullptr) {
+                // if somehow memory allocation fail, return the test
+                return;
+            }
+            uprv_memset(buf2, 0x4e, remain * 2);
+            str2.releaseBuffer(remain);
+            dest.append(str2);
+            total += remain;
+            assertEquals("When a string of exactly the maximum size works", (int64_t)INT32_MAX, total);
+            assertEquals("When a string of exactly the maximum size works", INT32_MAX, dest.length());
+            assertFalse("dest is not bogus", dest.isBogus());
+
+            // Check that a string size+1 goes bogus
+            str2.truncate(1);
+            dest.append(str2);
+            total++;
+            assertTrue("dest should be bogus", dest.isBogus());
+        } else {
+            assertTrue("dest should be bogus", dest.isBogus());
+        }
+    }
+}
diff --git a/icu4c/source/test/intltest/ustrtest.h b/icu4c/source/test/intltest/ustrtest.h
index 218befdcc68..4a356a92c7a 100644
--- a/icu4c/source/test/intltest/ustrtest.h
+++ b/icu4c/source/test/intltest/ustrtest.h
@@ -97,6 +97,7 @@ class UnicodeStringTest: public IntlTest {
     void TestWCharPointers();
     void TestNullPointers();
     void TestUnicodeStringInsertAppendToSelf();
+    void TestLargeAppend();
 };
 
 #endif