Skip to content

bpo-46315: Use fopencookie() to avoid dup() in _PyTokenizer_FindEncodingFilename #32033

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.

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
merged 4 commits into from
Mar 22, 2022
Merged
Changes from all commits
Commits
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
40 changes: 34 additions & 6 deletions Parser/tokenizer.c
Original file line number Diff line number Diff line change
Expand Up @@ -2072,6 +2072,39 @@ _PyTokenizer_Get(struct tok_state *tok,
return result;
}

#if defined(__wasi__) || defined(__EMSCRIPTEN__)
// fdopen() with borrowed fd. WASI does not provide dup() and Emscripten's
// dup() emulation with open() is slow.
typedef union {
void *cookie;
int fd;
} borrowed;

static ssize_t
borrow_read(void *cookie, char *buf, size_t size)
{
borrowed b = {.cookie = cookie};
return read(b.fd, (void *)buf, size);
}

static FILE *
fdopen_borrow(int fd) {
// supports only reading. seek fails. close and write are no-ops.
cookie_io_functions_t io_cb = {borrow_read, NULL, NULL, NULL};
borrowed b = {.fd = fd};
return fopencookie(b.cookie, "r", io_cb);
}
#else
static FILE *
fdopen_borrow(int fd) {
fd = _Py_dup(fd);
if (fd < 0) {
return NULL;
}
return fdopen(fd, "r");
}
#endif

/* Get the encoding of a Python file. Check for the coding cookie and check if
the file starts with a BOM.

Expand All @@ -2091,12 +2124,7 @@ _PyTokenizer_FindEncodingFilename(int fd, PyObject *filename)
const char *p_end = NULL;
char *encoding = NULL;

fd = _Py_dup(fd);
if (fd < 0) {
return NULL;
}

fp = fdopen(fd, "r");
fp = fdopen_borrow(fd);
if (fp == NULL) {
return NULL;
}
Expand Down