summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorph10 <ph10@6239d852-aaf2-0410-a92c-79f79f948069>2021-02-01 17:56:12 +0000
committerph10 <ph10@6239d852-aaf2-0410-a92c-79f79f948069>2021-02-01 17:56:12 +0000
commitca896b83b391bf6de7a7bf6e76da3bb02eb7001f (patch)
tree6bc9cef5b2712f45b2d329cbe68ada2035128ff3
parentd20ab1e7506ac54acb96f1f975f68d270687e706 (diff)
downloadpcre2-ca896b83b391bf6de7a7bf6e76da3bb02eb7001f.tar.gz
Fix some numerical checking bugs, Bugzilla 2690.
git-svn-id: svn://vcs.exim.org/pcre2/code/trunk@1295 6239d852-aaf2-0410-a92c-79f79f948069
-rw-r--r--ChangeLog9
-rw-r--r--src/pcre2_compile.c52
-rw-r--r--testdata/testinput19
-rw-r--r--testdata/testinput113
-rw-r--r--testdata/testinput22
-rw-r--r--testdata/testinput93
-rw-r--r--testdata/testoutput112
-rw-r--r--testdata/testoutput11-164
-rw-r--r--testdata/testoutput11-324
-rw-r--r--testdata/testoutput23
-rw-r--r--testdata/testoutput94
11 files changed, 83 insertions, 22 deletions
diff --git a/ChangeLog b/ChangeLog
index 3fd886a..2694119 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -16,6 +16,15 @@ but I have put in a check in order to get rid of the compiler error.
3. An alternative patch for CMakeLists.txt because 10.36 # 4 breaks CMake on
Windows. Patch from email@cs-ware.de fixes bugzilla #2688.
+4. Two bugs related to over-large numbers have been fixed so the behaviour is
+now the same as Perl.
+
+ (a) A pattern such as /\214748364/ gave an overflow error instead of being
+ treated as the octal number \214 followed by literal digits.
+
+ (b) A sequence such as {65536 that has no terminating } so is not a
+ quantifier was nevertheless complaining that a quantifier number was too big.
+
Version 10.36 04-December-2020
------------------------------
diff --git a/src/pcre2_compile.c b/src/pcre2_compile.c
index e811f12..4bd5be0 100644
--- a/src/pcre2_compile.c
+++ b/src/pcre2_compile.c
@@ -1398,32 +1398,47 @@ static BOOL
read_repeat_counts(PCRE2_SPTR *ptrptr, PCRE2_SPTR ptrend, uint32_t *minp,
uint32_t *maxp, int *errorcodeptr)
{
-PCRE2_SPTR p = *ptrptr;
+PCRE2_SPTR p;
BOOL yield = FALSE;
+BOOL had_comma = FALSE;
int32_t min = 0;
int32_t max = REPEAT_UNLIMITED; /* This value is larger than MAX_REPEAT_COUNT */
-/* NB read_number() initializes the error code to zero. The only error is for a
-number that is too big. */
+/* Check the syntax */
+*errorcodeptr = 0;
+for (p = *ptrptr;; p++)
+ {
+ uint32_t c;
+ if (p >= ptrend) return FALSE;
+ c = *p;
+ if (IS_DIGIT(c)) continue;
+ if (c == CHAR_RIGHT_CURLY_BRACKET) break;
+ if (c == CHAR_COMMA)
+ {
+ if (had_comma) return FALSE;
+ had_comma = TRUE;
+ }
+ else return FALSE;
+ }
+
+/* The only error from read_number() is for a number that is too big. */
+
+p = *ptrptr;
if (!read_number(&p, ptrend, -1, MAX_REPEAT_COUNT, ERR5, &min, errorcodeptr))
goto EXIT;
-if (p >= ptrend) goto EXIT;
-
if (*p == CHAR_RIGHT_CURLY_BRACKET)
{
p++;
max = min;
}
-
else
{
- if (*p++ != CHAR_COMMA || p >= ptrend) goto EXIT;
- if (*p != CHAR_RIGHT_CURLY_BRACKET)
+ if (*(++p) != CHAR_RIGHT_CURLY_BRACKET)
{
if (!read_number(&p, ptrend, -1, MAX_REPEAT_COUNT, ERR5, &max,
- errorcodeptr) || p >= ptrend || *p != CHAR_RIGHT_CURLY_BRACKET)
+ errorcodeptr))
goto EXIT;
if (max < min)
{
@@ -1438,11 +1453,10 @@ yield = TRUE;
if (minp != NULL) *minp = (uint32_t)min;
if (maxp != NULL) *maxp = (uint32_t)max;
-/* Update the pattern pointer on success, or after an error, but not when
-the result is "not a repeat quantifier". */
+/* Update the pattern pointer */
EXIT:
-if (yield || *errorcodeptr != 0) *ptrptr = p;
+*ptrptr = p;
return yield;
}
@@ -1776,19 +1790,23 @@ else
{
oldptr = ptr;
ptr--; /* Back to the digit */
- if (!read_number(&ptr, ptrend, -1, INT_MAX/10 - 1, ERR61, &s,
- errorcodeptr))
- break;
- /* \1 to \9 are always back references. \8x and \9x are too; \1x to \7x
+ /* As we know we are at a digit, the only possible error from
+ read_number() is a number that is too large to be a group number. In this
+ case we fall through handle this as not a group reference. If we have
+ read a small enough number, check for a back reference.
+
+ \1 to \9 are always back references. \8x and \9x are too; \1x to \7x
are octal escapes if there are not that many previous captures. */
- if (s < 10 || oldptr[-1] >= CHAR_8 || s <= (int)cb->bracount)
+ if (read_number(&ptr, ptrend, -1, INT_MAX/10 - 1, 0, &s, errorcodeptr) &&
+ (s < 10 || oldptr[-1] >= CHAR_8 || s <= (int)cb->bracount))
{
if (s > (int)MAX_GROUP_NUMBER) *errorcodeptr = ERR61;
else escape = -s; /* Indicates a back reference */
break;
}
+
ptr = oldptr; /* Put the pointer back and fall through */
}
diff --git a/testdata/testinput1 b/testdata/testinput1
index d4e42ba..bb4ddb7 100644
--- a/testdata/testinput1
+++ b/testdata/testinput1
@@ -6420,4 +6420,13 @@ ef) x/x,mark
/(?(DEFINE)(?<foo>bar))(?<![-a-z0-9])word/
word
+/a{1,2,3}b/
+ a{1,2,3}b
+
+/\214748364/
+ >\x{8c}748364<
+
+/a{65536/
+ >a{65536<
+
# End of testinput1
diff --git a/testdata/testinput11 b/testdata/testinput11
index 2d267d6..2bc8a25 100644
--- a/testdata/testinput11
+++ b/testdata/testinput11
@@ -368,4 +368,7 @@
abÿAz
ab\x{80000041}z
+/(?i:A{1,}\6666666666)/
+ A\x{1b6}6666666
+
# End of testinput11
diff --git a/testdata/testinput2 b/testdata/testinput2
index 3f9dd6d..87e3394 100644
--- a/testdata/testinput2
+++ b/testdata/testinput2
@@ -2189,8 +2189,6 @@
/a(*MARK)b/
-/(?i:A{1,}\6666666666)/
-
/\g6666666666/
/[\g6666666666]/B
diff --git a/testdata/testinput9 b/testdata/testinput9
index 7be4b15..4eb228a 100644
--- a/testdata/testinput9
+++ b/testdata/testinput9
@@ -260,4 +260,7 @@
/(*:*++++++++++++''''''''''''''''''''+''+++'+++x+++++++++++++++++++++++++++++++++++(++++++++++++++++++++:++++++%++:''''''''''''''''''''''''+++++++++++++++++++++++++++++++++++++++++++++++++++++-++++++++k+++++++''''+++'+++++++++++++++++++++++''''++++++++++++':Æ¿)/
+/(?i:A{1,}\6666666666)/
+ A\x{1b6}6666666
+
# End of testinput9
diff --git a/testdata/testoutput1 b/testdata/testoutput1
index 16c91d2..05b310b 100644
--- a/testdata/testoutput1
+++ b/testdata/testoutput1
@@ -10176,4 +10176,16 @@ No match
word
0: word
+/a{1,2,3}b/
+ a{1,2,3}b
+ 0: a{1,2,3}b
+
+/\214748364/
+ >\x{8c}748364<
+ 0: \x8c748364
+
+/a{65536/
+ >a{65536<
+ 0: a{65536
+
# End of testinput1
diff --git a/testdata/testoutput11-16 b/testdata/testoutput11-16
index 78bf7fb..8768785 100644
--- a/testdata/testoutput11-16
+++ b/testdata/testoutput11-16
@@ -661,4 +661,8 @@ Subject length lower bound = 1
abÿAz
ab\x{80000041}z
+/(?i:A{1,}\6666666666)/
+ A\x{1b6}6666666
+ 0: A\x{1b6}6666666
+
# End of testinput11
diff --git a/testdata/testoutput11-32 b/testdata/testoutput11-32
index 4b00384..2c95f61 100644
--- a/testdata/testoutput11-32
+++ b/testdata/testoutput11-32
@@ -667,4 +667,8 @@ Subject length lower bound = 1
ab\x{80000041}z
0: ab\x{80000041}z
+/(?i:A{1,}\6666666666)/
+ A\x{1b6}6666666
+ 0: A\x{1b6}6666666
+
# End of testinput11
diff --git a/testdata/testoutput2 b/testdata/testoutput2
index dc17011..4d8f65d 100644
--- a/testdata/testoutput2
+++ b/testdata/testoutput2
@@ -8374,9 +8374,6 @@ No match
/a(*MARK)b/
Failed: error 166 at offset 7: (*MARK) must have an argument
-/(?i:A{1,}\6666666666)/
-Failed: error 161 at offset 19: subpattern number is too big
-
/\g6666666666/
Failed: error 161 at offset 7: subpattern number is too big
diff --git a/testdata/testoutput9 b/testdata/testoutput9
index f98f276..1ec4317 100644
--- a/testdata/testoutput9
+++ b/testdata/testoutput9
@@ -367,4 +367,8 @@ Failed: error 134 at offset 14: character code point value in \x{} or \o{} is to
/(*:*++++++++++++''''''''''''''''''''+''+++'+++x+++++++++++++++++++++++++++++++++++(++++++++++++++++++++:++++++%++:''''''''''''''''''''''''+++++++++++++++++++++++++++++++++++++++++++++++++++++-++++++++k+++++++''''+++'+++++++++++++++++++++++''''++++++++++++':Æ¿)/
Failed: error 176 at offset 259: name is too long in (*MARK), (*PRUNE), (*SKIP), or (*THEN)
+/(?i:A{1,}\6666666666)/
+Failed: error 151 at offset 13: octal value is greater than \377 in 8-bit non-UTF-8 mode
+ A\x{1b6}6666666
+
# End of testinput9