Skip to content

Add _ENCODE_FILE_EXISTING variable #4

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

Closed
sabi789 wants to merge 1 commit into from
Closed

Add _ENCODE_FILE_EXISTING variable #4

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
22 changes: 22 additions & 0 deletions man/zoslib.1
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,8 +21,30 @@ New files are created with encoding IBM-1047 and tagged IBM-1047.

.TP
.B _ENCODE_FILE_NEW=BINARY

.TP
.B _ENCODE_FILE_NEW=UTF-8
Copy link
Copy Markdown

@augmentcode augmentcode Bot May 12, 2026 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

man/zoslib.1:26: This .TP starts a new term immediately after _ENCODE_FILE_NEW=BINARY, which leaves the BINARY option with no description and makes the “tagged as BINARY” paragraph apply to the UTF-8 entry instead.

Severity: medium

Fix This in Augment

🤖 Was this useful? React with 👍 or 👎, or 🚀 if it prevented an incident/outage.

New files are created with encoding UTF-8 and tagged UTF-8.


New files are created without translation and are tagged as BINARY.

.TP
.B _ENCODE_FILE_EXISTING=ISO8859-1
(Default) Existing files are opened with encoding ISO8859-1.

.TP
.B _ENCODE_FILE_EXISTING=IBM-1047
Existing files are opened with encoding IBM-1047.

.TP
.B _ENCODE_FILE_EXISTING=BINARY
Existing files are opened without translation as BINARY.

.TP
.B _ENCODE_FILE_EXISTING=UTF-8
Existing files are opened with encoding UTF-8.

.TP
.B __UNTAGGED_READ_MODE=AUTO
(default) for handling of reading untagged files or files tagged with CCSID 1047 and txtflag turned off, up to 4k of datawill be read and checked, if it is found to be in CCSID 1047, data is converted
Expand Down
18 changes: 18 additions & 0 deletions src/zos-io.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -761,6 +761,20 @@ int __tag_new_file(int fd) {
return __chgfdccsid(fd, ccsid);
}

int __tag_existing_file(int fd) {
char* encode_file_existing = getenv("_ENCODE_FILE_EXISTING");

if (!encode_file_existing) {
return 0;
}

if (strcmp(encode_file_existing, "BINARY") == 0) {
return __setfdbinary(fd);
}

return __chgfdcodeset(fd, encode_file_existing);
}

int __chgfdcodeset(int fd, char* codeset) {
unsigned short ccsid = __toCcsid(codeset);
if (!ccsid)
Expand Down Expand Up @@ -877,6 +891,8 @@ int __open_ascii(const char *filename, int opts, ...) {
}
// Enable auto-conversion of untagged files
else if (S_ISREG(sb.st_mode)) {
__tag_existing_file(fd);
Copy link
Copy Markdown

@augmentcode augmentcode Bot May 12, 2026 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

src/zos-io.cc:894: The return value from __tag_existing_file(fd) is ignored and errno is reset unconditionally, so failures (e.g., invalid _ENCODE_FILE_EXISTING or a failing tag operation) can be silently dropped while still returning a usable fd.

Severity: medium

Other Locations
  • src/zos-io.cc:939

Fix This in Augment

🤖 Was this useful? React with 👍 or 👎, or 🚀 if it prevented an incident/outage.

errno = old_errno;
struct file_tag *t = &sb.st_tag;
if (t->ft_txtflag == 0 && (t->ft_ccsid == 0 || t->ft_ccsid == 1047) &&
(opts & O_RDONLY) != 0) {
Expand Down Expand Up @@ -920,6 +936,8 @@ FILE *__fopen_ascii(const char *filename, const char *mode) {
}
// Enable auto-conversion of untagged files
else if (S_ISREG(sb.st_mode)) {
__tag_existing_file(fd);
errno = old_errno;
struct file_tag *t = &sb.st_tag;
if (t->ft_txtflag == 0 && (t->ft_ccsid == 0 || t->ft_ccsid == 1047) &&
strcmp(mode, "r") == 0) {
Expand Down
60 changes: 60 additions & 0 deletions test/test-clib-override.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -179,6 +179,66 @@ TEST_F(CLIBOverrides, open) {
EXPECT_EQ(__getfdccsid(fd), 0x10000 + 819);
memset(buff2, 1, sizeof(buff));
read(fd, buff2, sizeof(buff));

// Delete and re-open temp_path _ENCODE_FILE_NEW=UTF-8
setenv("_ENCODE_FILE_NEW", "UTF-8", 1);
remove(temp_path);
fd = open(temp_path, O_CREAT | O_WRONLY, 0777);
EXPECT_EQ(__getfdccsid(fd), 0x10000 + 1208);
write(fd, buff, sizeof(buff));
close(fd);

fd = open(temp_path, O_RDONLY);
Copy link
Copy Markdown

@augmentcode augmentcode Bot May 12, 2026 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

test/test-clib-override.cc:191: This fd isn’t closed before remove(temp_path) and reassigning fd, which can leak a descriptor and make the subsequent remove() behavior platform-dependent. It also means the final close(fd) later in the test may double-close or close the wrong descriptor.

Severity: medium

Fix This in Augment

🤖 Was this useful? React with 👍 or 👎, or 🚀 if it prevented an incident/outage.

EXPECT_EQ(__getfdccsid(fd), 0x10000 + 1208);
memset(buff2, 1, sizeof(buff));
read(fd, buff2, sizeof(buff));
EXPECT_EQ(strcmp(buff, buff2), 0);

// Test _ENCODE_FILE_EXISTING with IBM-1047
unsetenv("_ENCODE_FILE_NEW");
remove(temp_path);
fd = open(temp_path, O_CREAT | O_WRONLY, 0777);
write(fd, buff, sizeof(buff));
close(fd);

setenv("_ENCODE_FILE_EXISTING", "IBM-1047", 1);
fd = open(temp_path, O_RDONLY);
EXPECT_EQ(__getfdccsid(fd), 0x10000 + 1047);
memset(buff2, 1, sizeof(buff));
read(fd, buff2, sizeof(buff));
EXPECT_EQ(strcmp(buff, buff2), 0);
close(fd);

// Test _ENCODE_FILE_EXISTING with BINARY
setenv("_ENCODE_FILE_EXISTING", "BINARY", 1);
fd = open(temp_path, O_RDONLY);
EXPECT_EQ(__getfdccsid(fd), 65535);
memset(buff2, 1, sizeof(buff));
read(fd, buff2, sizeof(buff));
EXPECT_EQ(strcmp(buff, buff2), 0);
close(fd);

// Test _ENCODE_FILE_EXISTING with ISO8859-1
setenv("_ENCODE_FILE_EXISTING", "ISO8859-1", 1);
fd = open(temp_path, O_RDONLY);
EXPECT_EQ(__getfdccsid(fd), 0x10000 + 819);
memset(buff2, 1, sizeof(buff));
read(fd, buff2, sizeof(buff));
EXPECT_EQ(strcmp(buff, buff2), 0);
close(fd);

// Test _ENCODE_FILE_EXISTING with UTF-8
setenv("_ENCODE_FILE_EXISTING", "UTF-8", 1);
fd = open(temp_path, O_RDONLY);
EXPECT_EQ(__getfdccsid(fd), 0x10000 + 1208);
memset(buff2, 1, sizeof(buff));
read(fd, buff2, sizeof(buff));
EXPECT_EQ(strcmp(buff, buff2), 0);
close(fd);

unsetenv("_ENCODE_FILE_EXISTING");


EXPECT_EQ(strcmp(buff, buff2), 0);
free(buff2);
close(fd);
Expand Down
Loading