diff options
Diffstat (limited to 'Python/fileutils.c')
| -rw-r--r-- | Python/fileutils.c | 101 |
1 files changed, 76 insertions, 25 deletions
diff --git a/Python/fileutils.c b/Python/fileutils.c index 7d08e0726a..5c66ecf0b5 100644 --- a/Python/fileutils.c +++ b/Python/fileutils.c @@ -1,10 +1,12 @@ #include "Python.h" +#include "osdefs.h" +#include <locale.h> + #ifdef MS_WINDOWS # include <windows.h> #endif #ifdef HAVE_LANGINFO_H -#include <locale.h> #include <langinfo.h> #endif @@ -12,6 +14,36 @@ extern wchar_t* _Py_DecodeUTF8_surrogateescape(const char *s, Py_ssize_t size); #endif +PyObject * +_Py_device_encoding(int fd) +{ +#if defined(MS_WINDOWS) || defined(MS_WIN64) + UINT cp; +#endif + if (!_PyVerify_fd(fd) || !isatty(fd)) { + Py_RETURN_NONE; + } +#if defined(MS_WINDOWS) || defined(MS_WIN64) + if (fd == 0) + cp = GetConsoleCP(); + else if (fd == 1 || fd == 2) + cp = GetConsoleOutputCP(); + else + cp = 0; + /* GetConsoleCP() and GetConsoleOutputCP() return 0 if the application + has no console */ + if (cp != 0) + return PyUnicode_FromFormat("cp%u", (unsigned int)cp); +#elif defined(CODESET) + { + char *codeset = nl_langinfo(CODESET); + if (codeset != NULL && codeset[0] != 0) + return PyUnicode_FromString(codeset); + } +#endif + Py_RETURN_NONE; +} + #if !defined(__APPLE__) && !defined(MS_WINDOWS) extern int _Py_normalize_encoding(const char *, char *, size_t); @@ -203,7 +235,9 @@ decode_ascii_surrogateescape(const char *arg, size_t *size) Return a pointer to a newly allocated wide character string (use PyMem_Free() to free the memory) and write the number of written wide characters excluding the null character into *size if size is not NULL, or - NULL on error (conversion or memory allocation error). + NULL on error (decoding or memory allocation error). If size is not NULL, + *size is set to (size_t)-1 on memory error and (size_t)-2 on decoding + error. Conversion errors should never happen, unless there is a bug in the C library. */ @@ -302,8 +336,9 @@ _Py_char2wchar(const char* arg, size_t *size) since we provide everything that we have - unless there is a bug in the C library, or I misunderstood how mbrtowc works. */ - fprintf(stderr, "unexpected mbrtowc result -2\n"); PyMem_Free(res); + if (size != NULL) + *size = (size_t)-2; return NULL; } if (converted == (size_t)-1) { @@ -339,7 +374,8 @@ _Py_char2wchar(const char* arg, size_t *size) #endif /* HAVE_MBRTOWC */ return res; oom: - fprintf(stderr, "out of memory\n"); + if (size != NULL) + *size = (size_t)-1; return NULL; #endif /* __APPLE__ */ } @@ -351,10 +387,10 @@ oom: This function is the reverse of _Py_char2wchar(). Return a pointer to a newly allocated byte string (use PyMem_Free() to free - the memory), or NULL on conversion or memory allocation error. + the memory), or NULL on encoding or memory allocation error. If error_pos is not NULL: *error_pos is the index of the invalid character - on conversion error, or (size_t)-1 otherwise. */ + on encoding error, or (size_t)-1 otherwise. */ char* _Py_wchar2char(const wchar_t *text, size_t *error_pos) { @@ -367,9 +403,7 @@ _Py_wchar2char(const wchar_t *text, size_t *error_pos) if (unicode == NULL) return NULL; - bytes = PyUnicode_EncodeUTF8(PyUnicode_AS_UNICODE(unicode), - PyUnicode_GET_SIZE(unicode), - "surrogateescape"); + bytes = _PyUnicode_AsUTF8String(unicode, "surrogateescape"); Py_DECREF(unicode); if (bytes == NULL) { PyErr_Clear(); @@ -493,8 +527,8 @@ _Py_wstat(const wchar_t* path, struct stat *buf) /* Call _wstat() on Windows, or encode the path to the filesystem encoding and call stat() otherwise. Only fill st_mode attribute on Windows. - Return 0 on success, -1 on _wstat() / stat() error or (if PyErr_Occurred()) - unicode error. */ + Return 0 on success, -1 on _wstat() / stat() error, -2 if an exception was + raised. */ int _Py_stat(PyObject *path, struct stat *statbuf) @@ -502,8 +536,12 @@ _Py_stat(PyObject *path, struct stat *statbuf) #ifdef MS_WINDOWS int err; struct _stat wstatbuf; + wchar_t *wpath; - err = _wstat(PyUnicode_AS_UNICODE(path), &wstatbuf); + wpath = PyUnicode_AsUnicode(path); + if (wpath == NULL) + return -2; + err = _wstat(wpath, &wstatbuf); if (!err) statbuf->st_mode = wstatbuf.st_mode; return err; @@ -511,7 +549,7 @@ _Py_stat(PyObject *path, struct stat *statbuf) int ret; PyObject *bytes = PyUnicode_EncodeFSDefault(path); if (bytes == NULL) - return -1; + return -2; ret = stat(PyBytes_AS_STRING(bytes), statbuf); Py_DECREF(bytes); return ret; @@ -557,18 +595,29 @@ FILE* _Py_fopen(PyObject *path, const char *mode) { #ifdef MS_WINDOWS + wchar_t *wpath; wchar_t wmode[10]; int usize; + if (!PyUnicode_Check(path)) { + PyErr_Format(PyExc_TypeError, + "str file path expected under Windows, got %R", + Py_TYPE(path)); + return NULL; + } + wpath = PyUnicode_AsUnicode(path); + if (wpath == NULL) + return NULL; + usize = MultiByteToWideChar(CP_ACP, 0, mode, -1, wmode, sizeof(wmode)); if (usize == 0) return NULL; - return _wfopen(PyUnicode_AS_UNICODE(path), wmode); + return _wfopen(wpath, wmode); #else FILE *f; - PyObject *bytes = PyUnicode_EncodeFSDefault(path); - if (bytes == NULL) + PyObject *bytes; + if (!PyUnicode_FSConverter(path, &bytes)) return NULL; f = fopen(PyBytes_AS_STRING(bytes), mode); Py_DECREF(bytes); @@ -579,13 +628,13 @@ _Py_fopen(PyObject *path, const char *mode) #ifdef HAVE_READLINK /* Read value of symbolic link. Encode the path to the locale encoding, decode - the result from the locale encoding. */ + the result from the locale encoding. Return -1 on error. */ int _Py_wreadlink(const wchar_t *path, wchar_t *buf, size_t bufsiz) { char *cpath; - char cbuf[PATH_MAX]; + char cbuf[MAXPATHLEN]; wchar_t *wbuf; int res; size_t r1; @@ -595,11 +644,11 @@ _Py_wreadlink(const wchar_t *path, wchar_t *buf, size_t bufsiz) errno = EINVAL; return -1; } - res = (int)readlink(cpath, cbuf, PATH_MAX); + res = (int)readlink(cpath, cbuf, Py_ARRAY_LENGTH(cbuf)); PyMem_Free(cpath); if (res == -1) return -1; - if (res == PATH_MAX) { + if (res == Py_ARRAY_LENGTH(cbuf)) { errno = EINVAL; return -1; } @@ -623,14 +672,15 @@ _Py_wreadlink(const wchar_t *path, wchar_t *buf, size_t bufsiz) #ifdef HAVE_REALPATH /* Return the canonicalized absolute pathname. Encode path to the locale - encoding, decode the result from the locale encoding. */ + encoding, decode the result from the locale encoding. + Return NULL on error. */ wchar_t* _Py_wrealpath(const wchar_t *path, wchar_t *resolved_path, size_t resolved_path_size) { char *cpath; - char cresolved_path[PATH_MAX]; + char cresolved_path[MAXPATHLEN]; wchar_t *wresolved_path; char *res; size_t r; @@ -661,7 +711,8 @@ _Py_wrealpath(const wchar_t *path, #endif /* Get the current directory. size is the buffer size in wide characters - including the null character. Decode the path from the locale encoding. */ + including the null character. Decode the path from the locale encoding. + Return NULL on error. */ wchar_t* _Py_wgetcwd(wchar_t *buf, size_t size) @@ -669,11 +720,11 @@ _Py_wgetcwd(wchar_t *buf, size_t size) #ifdef MS_WINDOWS return _wgetcwd(buf, size); #else - char fname[PATH_MAX]; + char fname[MAXPATHLEN]; wchar_t *wname; size_t len; - if (getcwd(fname, PATH_MAX) == NULL) + if (getcwd(fname, Py_ARRAY_LENGTH(fname)) == NULL) return NULL; wname = _Py_char2wchar(fname, &len); if (wname == NULL) |