GV

GeezerVison

The World Wide Web, restored to 800 pixels of glory.

Home|About|Gaming cabinet|Archives|How it works|Starter sites

On this site

  • Sign in
  • ActionsCI/CD and automation
  • CodespacesCloud development environments
  • All Features
  • Documentation
  • Training
  • Certifications
  • Build with Copilot
  • Customize Copilot
  • Integrations
  • Trending repos
  • GitHub Sponsors
  • Developer articles
  • Enterprises

This view

  • Original page
  • New address

GeezerVison is showing github.com — bpo-47256: re module, limit the maximum capturing group to 1,073,741,823, increasing the depth of backtracking. · Pull Request #32411 · python/cpython

bpo-47256: re module, limit the maximum capturing group to 1,073,741,823, increasing the depth of backtracking. #32411

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
serhiy-storchaka merged 5 commits into python:main from unknown repository Apr 18, 2022

Uh oh!

There was an error while loading. Please reload this page.
Merged

bpo-47256: re module, limit the maximum capturing group to 1,073,741,823, increasing the depth of backtracking. #32411

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
d13b037
1. limit the maximum capturing group to 1,073,741,823
wjssz Apr 16, 2022
8a38ca7
2. further reduce sizeof(SRE(match_context))
wjssz Apr 16, 2022
8cfcab9
3. MARK_(PUSH|POP) macros compute marks size only once
wjssz Apr 16, 2022
11c9ad3
4. remove variable i
wjssz Apr 16, 2022
f811dfc
Fix indentation
wjssz Apr 18, 2022
File filter
Filter by extension
Clear filters
Conversations
Failed to load comments.
Loading

Uh oh!

There was an error while loading. Please reload this page.
Jump to
Jump to file
Failed to load files.
Loading

Uh oh!

There was an error while loading. Please reload this page.
Diff view
Diff view

There are no files selected for viewing

2 changes: 2 additions & 0 deletions 2 Misc/NEWS.d/next/Library/2022-04-16-11-39-59.bpo-47256.1cygyd.rst
Show comments
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
:mod:`re` module, limit the maximum capturing group to 1,073,741,823 in
64-bit build, this increases the depth of backtracking.
12 changes: 6 additions & 6 deletions 12 Modules/_sre/sre.h
Show comments
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,10 +18,10 @@
#define SRE_CODE Py_UCS4
#if SIZEOF_SIZE_T > 4
# define SRE_MAXREPEAT (~(SRE_CODE)0)
# define SRE_MAXGROUPS ((~(SRE_CODE)0) / 2)
# define SRE_MAXGROUPS ((SRE_CODE)INT32_MAX / 2)
#else
# define SRE_MAXREPEAT ((SRE_CODE)PY_SSIZE_T_MAX)
# define SRE_MAXGROUPS ((SRE_CODE)PY_SSIZE_T_MAX / SIZEOF_SIZE_T / 2)
# define SRE_MAXGROUPS ((SRE_CODE)PY_SSIZE_T_MAX / SIZEOF_VOID_P / 2)
#endif

typedef struct {
Expand Down Expand Up @@ -73,12 +73,12 @@ typedef struct {
Py_ssize_t pos, endpos;
int isbytes;
int charsize; /* character size */
/* registers */
Py_ssize_t lastindex;
Py_ssize_t lastmark;
const void** mark;
int match_all;
int must_advance;
/* marks */
Comment thread
This conversation was marked as resolved.
Resolved

Uh oh!

There was an error while loading. Please reload this page.
int lastmark;
int lastindex;
const void** mark;
/* dynamically allocated stuff */
char* data_stack;
size_t data_stack_size;
Expand Down
76 changes: 38 additions & 38 deletions 76 Modules/_sre/sre_lib.h
Show comments
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -450,20 +450,23 @@ do { \

#define MARK_PUSH(lastmark) \
do if (lastmark >= 0) { \
i = lastmark; /* ctx->lastmark may change if reallocated */ \
DATA_STACK_PUSH(state, state->mark, (i+1)*sizeof(void*)); \
size_t _marks_size = (lastmark+1) * sizeof(void*); \
DATA_STACK_PUSH(state, state->mark, _marks_size); \
} while (0)
#define MARK_POP(lastmark) \
do if (lastmark >= 0) { \
DATA_STACK_POP(state, state->mark, (lastmark+1)*sizeof(void*), 1); \
size_t _marks_size = (lastmark+1) * sizeof(void*); \
DATA_STACK_POP(state, state->mark, _marks_size, 1); \
} while (0)
#define MARK_POP_KEEP(lastmark) \
do if (lastmark >= 0) { \
DATA_STACK_POP(state, state->mark, (lastmark+1)*sizeof(void*), 0); \
size_t _marks_size = (lastmark+1) * sizeof(void*); \
DATA_STACK_POP(state, state->mark, _marks_size, 0); \
} while (0)
#define MARK_POP_DISCARD(lastmark) \
do if (lastmark >= 0) { \
DATA_STACK_POP_DISCARD(state, (lastmark+1)*sizeof(void*)); \
size_t _marks_size = (lastmark+1) * sizeof(void*); \
DATA_STACK_POP_DISCARD(state, _marks_size); \
} while (0)

#define JUMP_NONE 0
Expand All @@ -488,10 +491,10 @@ do { \
ctx->pattern = pattern; \
ctx->ptr = ptr; \
DATA_ALLOC(SRE(match_context), nextctx); \
nextctx->last_ctx_pos = ctx_pos; \
nextctx->jump = jumpvalue; \
nextctx->pattern = nextpattern; \
nextctx->toplevel = toplevel_; \
nextctx->jump = jumpvalue; \
nextctx->last_ctx_pos = ctx_pos; \
pattern = nextpattern; \
ctx_pos = alloc_pos; \
ctx = nextctx; \
Expand All @@ -507,18 +510,18 @@ do { \
DO_JUMPX(jumpvalue, jumplabel, nextpattern, 0)

typedef struct {
Py_ssize_t last_ctx_pos;
Py_ssize_t jump;
const SRE_CHAR* ptr;
const SRE_CODE* pattern;
Py_ssize_t count;
Py_ssize_t lastmark;
Py_ssize_t lastindex;
union {
SRE_CODE chr;
SRE_REPEAT* rep;
} u;
int lastmark;
int lastindex;
const SRE_CODE* pattern;
const SRE_CHAR* ptr;
int toplevel;
int jump;
Py_ssize_t last_ctx_pos;
} SRE(match_context);

#define MAYBE_CHECK_SIGNALS \
Expand Down Expand Up @@ -558,8 +561,8 @@ SRE(match)(SRE_STATE* state, const SRE_CODE* pattern, int toplevel)
{
const SRE_CHAR* end = (const SRE_CHAR *)state->end;
Py_ssize_t alloc_pos, ctx_pos = -1;
Py_ssize_t i, ret = 0;
Py_ssize_t jump;
Py_ssize_t ret = 0;
int jump;
unsigned int sigcount=0;

SRE(match_context)* ctx;
Expand Down Expand Up @@ -607,20 +610,22 @@ SRE(match)(SRE_STATE* state, const SRE_CODE* pattern, int toplevel)
/* <MARK> <gid> */
TRACE(("|%p|%p|MARK %d\n", pattern,
ptr, pattern[0]));
i = pattern[0];
if (i & 1)
state->lastindex = i/2 + 1;
if (i > state->lastmark) {
/* state->lastmark is the highest valid index in the
state->mark array. If it is increased by more than 1,
the intervening marks must be set to NULL to signal
that these marks have not been encountered. */
Py_ssize_t j = state->lastmark + 1;
while (j < i)
state->mark[j++] = NULL;
state->lastmark = i;
{
int i = pattern[0];
if (i & 1)
state->lastindex = i/2 + 1;
if (i > state->lastmark) {
/* state->lastmark is the highest valid index in the
state->mark array. If it is increased by more than 1,
the intervening marks must be set to NULL to signal
that these marks have not been encountered. */
int j = state->lastmark + 1;
while (j < i)
state->mark[j++] = NULL;
state->lastmark = i;
}
state->mark[i] = ptr;
}
state->mark[i] = ptr;
pattern++;
DISPATCH;

Expand Down Expand Up @@ -1373,9 +1378,8 @@ SRE(match)(SRE_STATE* state, const SRE_CODE* pattern, int toplevel)
/* match backreference */
TRACE(("|%p|%p|GROUPREF %d\n", pattern,
ptr, pattern[0]));
i = pattern[0];
{
Py_ssize_t groupref = i+i;
int groupref = pattern[0] * 2;
if (groupref >= state->lastmark) {
RETURN_FAILURE;
} else {
Expand All @@ -1398,9 +1402,8 @@ SRE(match)(SRE_STATE* state, const SRE_CODE* pattern, int toplevel)
/* match backreference */
TRACE(("|%p|%p|GROUPREF_IGNORE %d\n", pattern,
ptr, pattern[0]));
i = pattern[0];
{
Py_ssize_t groupref = i+i;
int groupref = pattern[0] * 2;
if (groupref >= state->lastmark) {
RETURN_FAILURE;
} else {
Expand All @@ -1424,9 +1427,8 @@ SRE(match)(SRE_STATE* state, const SRE_CODE* pattern, int toplevel)
/* match backreference */
TRACE(("|%p|%p|GROUPREF_UNI_IGNORE %d\n", pattern,
ptr, pattern[0]));
i = pattern[0];
{
Py_ssize_t groupref = i+i;
int groupref = pattern[0] * 2;
if (groupref >= state->lastmark) {
RETURN_FAILURE;
} else {
Expand All @@ -1450,9 +1452,8 @@ SRE(match)(SRE_STATE* state, const SRE_CODE* pattern, int toplevel)
/* match backreference */
TRACE(("|%p|%p|GROUPREF_LOC_IGNORE %d\n", pattern,
ptr, pattern[0]));
i = pattern[0];
{
Py_ssize_t groupref = i+i;
int groupref = pattern[0] * 2;
if (groupref >= state->lastmark) {
RETURN_FAILURE;
} else {
Expand All @@ -1476,9 +1477,8 @@ SRE(match)(SRE_STATE* state, const SRE_CODE* pattern, int toplevel)
TRACE(("|%p|%p|GROUPREF_EXISTS %d\n", pattern,
ptr, pattern[0]));
/* <GROUPREF_EXISTS> <group> <skip> codeyes <JUMP> codeno ... */
i = pattern[0];
{
Py_ssize_t groupref = i+i;
int groupref = pattern[0] * 2;
if (groupref >= state->lastmark) {
pattern += pattern[1];
DISPATCH;
Expand Down
Add this suggestion to a batch that can be applied as a single commit. This suggestion is invalid because no changes were made to the code. Suggestions cannot be applied while the pull request is closed. Suggestions cannot be applied while viewing a subset of changes. Only one suggestion per line can be applied in a batch. Add this suggestion to a batch that can be applied as a single commit. Applying suggestions on deleted lines is not supported. You must change the existing code in this line in order to create a valid suggestion. Outdated suggestions cannot be applied. This suggestion has been applied or marked resolved. Suggestions cannot be applied from pending reviews. Suggestions cannot be applied on multi-line comments. Suggestions cannot be applied while the pull request is queued to merge. Suggestion cannot be applied right now. Please check back later.
You are visitor 01402503 — GeezerVison does not store the pages you look up.
Best viewed with Netscape Navigator 4.7 or Internet Explorer 6 at 800×600. No cookies required.