FazBrowse GitHub Viewer | Trending |
URL:
| Home
Tools: [Download Repo ZIP]   [Original HTTPS Page]

gh-101180: Fix a bug where iso2022_jp_3 and iso2022_jp_2004 codecs read out of bounds by moriyama · Pull Request #111695 · python/cpython · GitHub

/ cpython Public

gh-101180: Fix a bug where iso2022_jp_3 and iso2022_jp_2004 codecs read out of bounds #111695

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
corona10 merged 3 commits into from
Nov 6, 2023
+53 −3
Conversation 38 Commits 3 Checks 0 Files changed 3
Merged

gh-101180: Fix a bug where iso2022_jp_3 and iso2022_jp_2004 codecs read out of bounds #111695

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
13286d1
gh-101180: Fix a bug where iso2022_jp_3 and iso2022_jp_2004 codecs re…
moriyama Nov 3, 2023
ddff542
gh-101180: Add test for iso2022_jp_3 and iso2022_jp_2004 codecs
moriyama Nov 3, 2023
59e3e6f
gh-101180: Add NEWS
moriyama Nov 3, 2023
File filter

Filter by extension

Filter by extension .c  (1) .py  (1) .rst  (1) All 3 file types selected
Viewed files
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Unified
Split
Hide whitespace
Diff view
Unified
Split
Hide whitespace
46 changes: 46 additions & 0 deletions Lib/test/test_codecencodings_iso2022.py
Show comments
View file
Open in desktop
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode characters
Show hidden characters
Original file line number Diff line number Diff line change
Expand Up @@ -24,6 +24,52 @@ class Test_ISO2022_JP2(multibytecodec_support.TestBase, unittest.TestCase):
(b'ab\x1BNdef', 'replace', 'abdef'),
)

class Test_ISO2022_JP3(multibytecodec_support.TestBase, unittest.TestCase):
encoding = 'iso2022_jp_3'
tstring = multibytecodec_support.load_teststring('iso2022_jp')
codectests = COMMON_CODEC_TESTS + (
(b'ab\x1BNdef', 'replace', 'ab\x1BNdef'),
(b'\x1B$(O\x2E\x23\x1B(B', 'strict', '\u3402' ),
(b'\x1B$(O\x2E\x22\x1B(B', 'strict', '\U0002000B' ),
(b'\x1B$(O\x24\x77\x1B(B', 'strict', '\u304B\u309A'),
(b'\x1B$(P\x21\x22\x1B(B', 'strict', '\u4E02' ),
(b'\x1B$(P\x7E\x76\x1B(B', 'strict', '\U0002A6B2' ),
('\u3402', 'strict', b'\x1B$(O\x2E\x23\x1B(B'),
('\U0002000B', 'strict', b'\x1B$(O\x2E\x22\x1B(B'),
('\u304B\u309A', 'strict', b'\x1B$(O\x24\x77\x1B(B'),
('\u4E02', 'strict', b'\x1B$(P\x21\x22\x1B(B'),
('\U0002A6B2', 'strict', b'\x1B$(P\x7E\x76\x1B(B'),
(b'ab\x1B$(O\x2E\x21\x1B(Bdef', 'replace', 'ab\uFFFDdef'),
('ab\u4FF1def', 'replace', b'ab?def'),
)
xmlcharnametest = (
'\xAB\u211C\xBB = \u2329\u1234\u232A',
b'\x1B$(O\x29\x28\x1B(Bℜ\x1B$(O\x29\x32\x1B(B = ⟨ሴ⟩'
)

class Test_ISO2022_JP2004(multibytecodec_support.TestBase, unittest.TestCase):
encoding = 'iso2022_jp_2004'
tstring = multibytecodec_support.load_teststring('iso2022_jp')
codectests = COMMON_CODEC_TESTS + (
(b'ab\x1BNdef', 'replace', 'ab\x1BNdef'),
(b'\x1B$(Q\x2E\x23\x1B(B', 'strict', '\u3402' ),
(b'\x1B$(Q\x2E\x22\x1B(B', 'strict', '\U0002000B' ),
(b'\x1B$(Q\x24\x77\x1B(B', 'strict', '\u304B\u309A'),
(b'\x1B$(P\x21\x22\x1B(B', 'strict', '\u4E02' ),
(b'\x1B$(P\x7E\x76\x1B(B', 'strict', '\U0002A6B2' ),
('\u3402', 'strict', b'\x1B$(Q\x2E\x23\x1B(B'),
('\U0002000B', 'strict', b'\x1B$(Q\x2E\x22\x1B(B'),
('\u304B\u309A', 'strict', b'\x1B$(Q\x24\x77\x1B(B'),
('\u4E02', 'strict', b'\x1B$(P\x21\x22\x1B(B'),
('\U0002A6B2', 'strict', b'\x1B$(P\x7E\x76\x1B(B'),
(b'ab\x1B$(Q\x2E\x21\x1B(Bdef', 'replace', 'ab\u4FF1def'),
('ab\u4FF1def', 'replace', b'ab\x1B$(Q\x2E\x21\x1B(Bdef'),
)
xmlcharnametest = (
'\xAB\u211C\xBB = \u2329\u1234\u232A',
b'\x1B$(Q\x29\x28\x1B(Bℜ\x1B$(Q\x29\x32\x1B(B = ⟨ሴ⟩'
)

class Test_ISO2022_KR(multibytecodec_support.TestBase, unittest.TestCase):
encoding = 'iso2022_kr'
tstring = multibytecodec_support.load_teststring('iso2022_kr')
Expand Down
1 change: 1 addition & 0 deletions Misc/NEWS.d/next/Core and Builtins/2023-10-27-19-38-33.gh-issue-102388.vd5YUZ.rst
Show comments
View file
Open in desktop
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode characters
Show hidden characters
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
Fix a bug where ``iso2022_jp_3`` and ``iso2022_jp_2004`` codecs read out of bounds
9 changes: 6 additions & 3 deletions Modules/cjkcodecs/_codecs_iso2022.c
Show comments
View file
Open in desktop
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode characters
Show hidden characters
Original file line number Diff line number Diff line change
Expand Up @@ -207,8 +207,9 @@ ENCODER(iso2022)

encoded = MAP_UNMAPPABLE;
for (dsg = CONFIG_DESIGNATIONS; dsg->mark; dsg++) {
Py_UCS4 buf[2] = {c, 0};
Py_ssize_t length = 1;
encoded = dsg->encoder(codec, &c, &length);
encoded = dsg->encoder(codec, buf, &length);
if (encoded == MAP_MULTIPLE_AVAIL) {
/* this implementation won't work for pair
* of non-bmp characters. */
Expand All @@ -217,9 +218,11 @@ ENCODER(iso2022)
return MBERR_TOOFEW;
length = -1;
}
else
else {
buf[1] = INCHAR2;
length = 2;
encoded = dsg->encoder(codec, &c, &length);
}
encoded = dsg->encoder(codec, buf, &length);
if (encoded != MAP_UNMAPPABLE) {
insize = length;
break;
Expand Down
Back | FazBrowse Home | New Git URL