gh-116741: Upgrade libexpat to 2.6.2 (#117296)

Upgrade libexpat to 2.6.2

Author: sethmlarson

Misc/NEWS.d/next/Security/2024-03-27-13-50-02.gh-issue-116741.ZoGryG.rst

@@ -0,0 +1 @@
+Update bundled libexpat to 2.6.2

Misc/sbom.spdx.json

@@ -18,6 +18,7 @@
    Copyright (c) 2022      Thijs Schreijer <thijs@thijsschreijer.nl>
    Copyright (c) 2023      Hanno Böck <hanno@gentoo.org>
    Copyright (c) 2023      Sony Corporation / Snild Dolkow <snild@sony.com>
+   Copyright (c) 2024      Taichi Haradaguchi <20001722@ymail.ne.jp>
    Licensed under the MIT license:
 
    Permission is  hereby granted,  free of charge,  to any  person obtaining
@@ -1042,7 +1043,7 @@ typedef struct {
 XMLPARSEAPI(const XML_Feature *)
 XML_GetFeatureList(void);
 
-#if XML_GE == 1
+#if defined(XML_DTD) || (defined(XML_GE) && XML_GE == 1)
 /* Added in Expat 2.4.0 for XML_DTD defined and
  * added in Expat 2.6.0 for XML_GE == 1. */
 XMLPARSEAPI(XML_Bool)
@@ -1065,7 +1066,7 @@ XML_SetReparseDeferralEnabled(XML_Parser parser, XML_Bool enabled);
 */
 #define XML_MAJOR_VERSION 2
 #define XML_MINOR_VERSION 6
-#define XML_MICRO_VERSION 0
+#define XML_MICRO_VERSION 2
 
 #ifdef __cplusplus
 }

Modules/expat/expat.h

@@ -28,10 +28,11 @@
    Copyright (c) 2002-2003 Fred L. Drake, Jr. <fdrake@users.sourceforge.net>
    Copyright (c) 2002-2006 Karl Waclawek <karl@waclawek.net>
    Copyright (c) 2003      Greg Stein <gstein@users.sourceforge.net>
-   Copyright (c) 2016-2023 Sebastian Pipping <sebastian@pipping.org>
+   Copyright (c) 2016-2024 Sebastian Pipping <sebastian@pipping.org>
    Copyright (c) 2018      Yury Gribov <tetra2005@gmail.com>
    Copyright (c) 2019      David Loffredo <loffredo@steptools.com>
-   Copyright (c) 2023      Sony Corporation / Snild Dolkow <snild@sony.com>
+   Copyright (c) 2023-2024 Sony Corporation / Snild Dolkow <snild@sony.com>
+   Copyright (c) 2024      Taichi Haradaguchi <20001722@ymail.ne.jp>
    Licensed under the MIT license:
 
    Permission is  hereby granted,  free of charge,  to any  person obtaining
@@ -155,14 +156,20 @@ extern "C" {
 void _INTERNAL_trim_to_complete_utf8_characters(const char *from,
                                                 const char **fromLimRef);
 
-#if XML_GE == 1
+#if defined(XML_GE) && XML_GE == 1
 unsigned long long testingAccountingGetCountBytesDirect(XML_Parser parser);
 unsigned long long testingAccountingGetCountBytesIndirect(XML_Parser parser);
 const char *unsignedCharToPrintable(unsigned char c);
 #endif
 
-extern XML_Bool g_reparseDeferralEnabledDefault; // written ONLY in runtests.c
-extern unsigned int g_parseAttempts;             // used for testing only
+extern
+#if ! defined(XML_TESTING)
+    const
+#endif
+    XML_Bool g_reparseDeferralEnabledDefault; // written ONLY in runtests.c
+#if defined(XML_TESTING)
+extern unsigned int g_bytesScanned; // used for testing only
+#endif
 
 #ifdef __cplusplus
 }

Modules/expat/internal.h

@@ -1,4 +1,4 @@
-/* 628e24d4966bedbd4800f6ed128d06d29703765b4bce12d3b7f099f90f842fc9 (2.6.0+)
+/* 2a14271ad4d35e82bde8ba210b4edb7998794bcbae54deab114046a300f9639a (2.6.2+)
                             __  __            _
                          ___\ \/ /_ __   __ _| |_
                         / _ \\  /| '_ \ / _` | __|
@@ -38,7 +38,7 @@
    Copyright (c) 2022      Jann Horn <jannh@google.com>
    Copyright (c) 2022      Sean McBride <sean@rogue-research.com>
    Copyright (c) 2023      Owain Davies <owaind@bath.edu>
-   Copyright (c) 2023      Sony Corporation / Snild Dolkow <snild@sony.com>
+   Copyright (c) 2023-2024 Sony Corporation / Snild Dolkow <snild@sony.com>
    Licensed under the MIT license:
 
    Permission is  hereby granted,  free of charge,  to any  person obtaining
@@ -210,7 +210,7 @@ typedef char ICHAR;
 #endif
 
 /* Round up n to be a multiple of sz, where sz is a power of 2. */
-#define ROUND_UP(n, sz) (((n) + ((sz)-1)) & ~((sz)-1))
+#define ROUND_UP(n, sz) (((n) + ((sz) - 1)) & ~((sz) - 1))
 
 /* Do safe (NULL-aware) pointer arithmetic */
 #define EXPAT_SAFE_PTR_DIFF(p, q) (((p) && (q)) ? ((p) - (q)) : 0)
@@ -248,7 +248,7 @@ static void copy_salt_to_sipkey(XML_Parser parser, struct sipkey *key);
    it odd, since odd numbers are always relative prime to a power of 2.
 */
 #define SECOND_HASH(hash, mask, power)                                         \
-  ((((hash) & ~(mask)) >> ((power)-1)) & ((mask) >> 2))
+  ((((hash) & ~(mask)) >> ((power) - 1)) & ((mask) >> 2))
 #define PROBE_STEP(hash, mask, power)                                          \
   ((unsigned char)((SECOND_HASH(hash, mask, power)) | 1))
 
@@ -629,8 +629,14 @@ static unsigned long getDebugLevel(const char *variableName,
        ? 0                                                                     \
        : ((*((pool)->ptr)++ = c), 1))
 
-XML_Bool g_reparseDeferralEnabledDefault = XML_TRUE; // write ONLY in runtests.c
-unsigned int g_parseAttempts = 0;                    // used for testing only
+#if ! defined(XML_TESTING)
+const
+#endif
+    XML_Bool g_reparseDeferralEnabledDefault
+    = XML_TRUE; // write ONLY in runtests.c
+#if defined(XML_TESTING)
+unsigned int g_bytesScanned = 0; // used for testing only
+#endif
 
 struct XML_ParserStruct {
   /* The first member must be m_userData so that the XML_GetUserData
@@ -1017,7 +1023,9 @@ callProcessor(XML_Parser parser, const char *start, const char *end,
       return XML_ERROR_NONE;
     }
   }
-  g_parseAttempts += 1;
+#if defined(XML_TESTING)
+  g_bytesScanned += (unsigned)have_now;
+#endif
   const enum XML_Error ret = parser->m_processor(parser, start, end, endPtr);
   if (ret == XML_ERROR_NONE) {
     // if we consumed nothing, remember what we had on this parse attempt.
@@ -6232,7 +6240,7 @@ storeEntityValue(XML_Parser parser, const ENCODING *enc,
           dtd->keepProcessing = dtd->standalone;
           goto endEntityValue;
         }
-        if (entity->open) {
+        if (entity->open || (entity == parser->m_declEntity)) {
           if (enc == parser->m_encoding)
             parser->m_eventPtr = entityTextPtr;
           result = XML_ERROR_RECURSIVE_ENTITY_REF;
@@ -7779,14 +7787,18 @@ copyString(const XML_Char *s, const XML_Memory_Handling_Suite *memsuite) {
 
 static float
 accountingGetCurrentAmplification(XML_Parser rootParser) {
+  //                                          1.........1.........12 => 22
+  const size_t lenOfShortestInclude = sizeof("<!ENTITY a SYSTEM 'b'>") - 1;
   const XmlBigCount countBytesOutput
       = rootParser->m_accounting.countBytesDirect
         + rootParser->m_accounting.countBytesIndirect;
   const float amplificationFactor
       = rootParser->m_accounting.countBytesDirect
             ? (countBytesOutput
                / (float)(rootParser->m_accounting.countBytesDirect))
-            : 1.0f;
+            : ((lenOfShortestInclude
+                + rootParser->m_accounting.countBytesIndirect)
+               / (float)lenOfShortestInclude);
   assert(! rootParser->m_parentParser);
   return amplificationFactor;
 }