Re: bzip2 1.0.7 released

[Mark Wielaard <mark@klomp.org>]

[-- Attachment #1: Type: text/plain, Size: 299 bytes --]

On Fri, 2019-06-28 at 13:10 +0200, Mark Wielaard wrote:
> That seems good. The attached patch does this and makes it possible
> to decode the problematic bz2 file.

The patch was correct, but I misspelled Julian's last name in the
commit message... embarrassing. Sorry. Fixed in the attached.

[-- Attachment #2: 0001-Be-more-liberal-in-the-number-of-selectors-we-accept.patch --]
[-- Type: text/x-patch, Size: 3871 bytes --]

From d970bad3371761555d249374e70012bba705ed73 Mon Sep 17 00:00:00 2001
From: Mark Wielaard <mark@klomp.org>
Date: Fri, 28 Jun 2019 12:38:41 +0200
Subject: [PATCH] Be more liberal in the number of selectors we accept when
 decoding.

As proposed by Julian Seward:

* split BZ_MAX_SELECTORS into two different values:

  - BZ_MAX_SELECTORS_ENC = (2 + (900000 / BZ_G_SIZE)) [= 18002], the max
    number of selectors that bzip2 can create ("encode")

  - BZ_MAX_SELECTORS_DEC = BZ_MAX_SELECTORS_ENC + 6 [= 18008], the max
    number of selectors that we'll accept during decoding, and add a
    comment explaining that the difference is due to buggy lbzip2/whatever
    creating more than BZ_MAX_SELECTORS_ENC

* use BZ_MAX_SELECTORS_ENC to dimension the arrays in struct EState

* use BZ_MAX_SELECTORS_DEC to dimension the arrays in struct DState,
  and for the new decompress.c range check

* change the compress.c assertion

  AssertH( nSelectors < 32768 &&
           nSelectors <= (2 + (900000 / BZ_G_SIZE)),
           3003 );

  to actually mention BZ_MAX_SELECTORS_ENC directly, instead of
  (2 + (900000 / BZ_G_SIZE)), [which is embarrassingly lame]
---
 bzlib_private.h | 15 ++++++++++-----
 compress.c      |  2 +-
 decompress.c    |  2 +-
 3 files changed, 12 insertions(+), 7 deletions(-)

diff --git a/bzlib_private.h b/bzlib_private.h
index 7975552..6208ba1 100644
--- a/bzlib_private.h
+++ b/bzlib_private.h
@@ -122,7 +122,12 @@ extern void bz_internal_error ( int errcode );
 #define BZ_G_SIZE   50
 #define BZ_N_ITERS  4
 
-#define BZ_MAX_SELECTORS (2 + (900000 / BZ_G_SIZE))
+/* The max number of selectors that bzip2 can create ("encode") [= 18002] */
+#define BZ_MAX_SELECTORS_ENC (2 + (900000 / BZ_G_SIZE))
+/* The max number of selectors that bzip2 accept during decoding [= 18008]
+   This is larger than BZ_MAX_SELECTORS_ENC because some implementations,
+   might round up the number of selectors to a factor of 8. */
+#define BZ_MAX_SELECTORS_DEC (BZ_MAX_SELECTORS_ENC + 6)
 
 
 
@@ -253,8 +258,8 @@ typedef
       /* stuff for coding the MTF values */
       Int32    nMTF;
       Int32    mtfFreq    [BZ_MAX_ALPHA_SIZE];
-      UChar    selector   [BZ_MAX_SELECTORS];
-      UChar    selectorMtf[BZ_MAX_SELECTORS];
+      UChar    selector   [BZ_MAX_SELECTORS_ENC];
+      UChar    selectorMtf[BZ_MAX_SELECTORS_ENC];
 
       UChar    len     [BZ_N_GROUPS][BZ_MAX_ALPHA_SIZE];
       Int32    code    [BZ_N_GROUPS][BZ_MAX_ALPHA_SIZE];
@@ -399,8 +404,8 @@ typedef
       /* for decoding the MTF values */
       UChar    mtfa   [MTFA_SIZE];
       Int32    mtfbase[256 / MTFL_SIZE];
-      UChar    selector   [BZ_MAX_SELECTORS];
-      UChar    selectorMtf[BZ_MAX_SELECTORS];
+      UChar    selector   [BZ_MAX_SELECTORS_DEC];
+      UChar    selectorMtf[BZ_MAX_SELECTORS_DEC];
       UChar    len  [BZ_N_GROUPS][BZ_MAX_ALPHA_SIZE];
 
       Int32    limit  [BZ_N_GROUPS][BZ_MAX_ALPHA_SIZE];
diff --git a/compress.c b/compress.c
index 237620d..9b660f8 100644
--- a/compress.c
+++ b/compress.c
@@ -454,7 +454,7 @@ void sendMTFValues ( EState* s )
 
    AssertH( nGroups < 8, 3002 );
    AssertH( nSelectors < 32768 &&
-            nSelectors <= (2 + (900000 / BZ_G_SIZE)),
+            nSelectors <= BZ_MAX_SELECTORS_ENC,
             3003 );
 
 
diff --git a/decompress.c b/decompress.c
index 20ce493..d24a052 100644
--- a/decompress.c
+++ b/decompress.c
@@ -287,7 +287,7 @@ Int32 BZ2_decompress ( DState* s )
       GET_BITS(BZ_X_SELECTOR_1, nGroups, 3);
       if (nGroups < 2 || nGroups > BZ_N_GROUPS) RETURN(BZ_DATA_ERROR);
       GET_BITS(BZ_X_SELECTOR_2, nSelectors, 15);
-      if (nSelectors < 1 || nSelectors > BZ_MAX_SELECTORS) RETURN(BZ_DATA_ERROR);
+      if (nSelectors < 1 || nSelectors > BZ_MAX_SELECTORS_DEC) RETURN(BZ_DATA_ERROR);
       for (i = 0; i < nSelectors; i++) {
          j = 0;
          while (True) {
-- 
1.8.3.1