php-src/Zend/zend_virtual_cwd.h

376 lines
12 KiB
C
Raw Normal View History

/*
+----------------------------------------------------------------------+
2014-09-20 00:33:14 +08:00
| PHP Version 7 |
+----------------------------------------------------------------------+
2017-01-02 23:30:12 +08:00
| Copyright (c) 1997-2017 The PHP Group |
+----------------------------------------------------------------------+
2006-01-01 20:51:34 +08:00
| This source file is subject to version 3.01 of the PHP license, |
| that is bundled with this package in the file LICENSE, and is |
| available through the world-wide-web at the following url: |
2006-01-01 20:51:34 +08:00
| http://www.php.net/license/3_01.txt |
| If you did not receive a copy of the PHP license and are unable to |
| obtain it through the world-wide-web, please send a note to |
| license@php.net so we can mail you a copy immediately. |
+----------------------------------------------------------------------+
| Authors: Andi Gutmans <andi@zend.com> |
| Sascha Schumann <sascha@schumann.cx> |
2010-09-01 17:49:53 +08:00
| Pierre Joye <pierre@php.net> |
+----------------------------------------------------------------------+
*/
/* $Id$ */
#ifndef VIRTUAL_CWD_H
#define VIRTUAL_CWD_H
2001-08-05 09:34:40 +08:00
#include "TSRM.h"
#include "tsrm_config_common.h"
2000-09-04 02:58:46 +08:00
#include <sys/types.h>
#include <sys/stat.h>
#include <ctype.h>
#ifdef HAVE_UTIME_H
#include <utime.h>
#endif
#ifdef HAVE_STDARG_H
#include <stdarg.h>
#endif
2006-09-04 16:18:15 +08:00
#ifdef ZTS
#define VIRTUAL_DIR
#endif
#ifndef ZEND_WIN32
#include <unistd.h>
2006-09-04 16:18:15 +08:00
#else
#include <direct.h>
#endif
#if defined(__osf__) || defined(_AIX)
#include <errno.h>
#endif
#ifdef ZEND_WIN32
2000-09-04 02:47:35 +08:00
#include "readdir.h"
2000-09-04 12:18:38 +08:00
#include <sys/utime.h>
Fixed the UTF-8 and long path support in the streams on Windows. Since long the default PHP charset is UTF-8, however the Windows part is out of step with this important point. The current implementation in PHP doesn't technically permit to handle UTF-8 filepath and several other things. Till now, only the ANSI compatible APIs are being used. Here is more about it https://msdn.microsoft.com/en-us/library/windows/desktop/dd317752%28v=vs.85%29.aspx The patch fixes not only issues with multibyte filenames under incompatible codepages, but indirectly also issues with some other multibyte encodings like BIG5, Shift-JIS, etc. by providing a clean way to access filenames in UTF-8. Below is a small list of issues from the bug tracker, that are getting fixed: https://bugs.php.net/63401 https://bugs.php.net/41199 https://bugs.php.net/50203 https://bugs.php.net/71509 https://bugs.php.net/64699 https://bugs.php.net/64506 https://bugs.php.net/30195 https://bugs.php.net/65358 https://bugs.php.net/61315 https://bugs.php.net/70943 https://bugs.php.net/70903 https://bugs.php.net/63593 https://bugs.php.net/54977 https://bugs.php.net/54028 https://bugs.php.net/43148 https://bugs.php.net/30730 https://bugs.php.net/33350 https://bugs.php.net/35300 https://bugs.php.net/46990 https://bugs.php.net/61309 https://bugs.php.net/69333 https://bugs.php.net/45517 https://bugs.php.net/70551 https://bugs.php.net/50197 https://bugs.php.net/72200 https://bugs.php.net/37672 Yet more related tickets can for sure be found - on bugs.php.net, Stackoverflow and Github. Some of the bugs are pretty recent, some descend to early 2000th, but the user comments in there last even till today. Just for example, bug #30195 was opened in 2004, the latest comment in there was made in 2014. It is certain, that these bugs descend not only to pure PHP use cases, but get also redirected from the popular PHP based projects. Given the modern systems (and those supported by PHP) are always based on NTFS, there is no excuse to keep these issues unresolved. The internalization approach on Windows is in many ways different from UNIX and Linux, while it supports and is based on Unicode. It depends on the current system code page, APIs used and exact kind how the binary was compiled The locale doesn't affect the way Unicode or ANSI API work. PHP in particular is being compiled without _UNICODE defined and this is conditioned by the way we handle strings. Here is more about it https://msdn.microsoft.com/en-us/library/tsbaswba.aspx However, with any system code page ANSI functions automatically convert paths to UTF-16. Paths in some encodings incompatible with the current system code page, won't work correctly with ANSI APIs. PHP till now only uses the ANSI Windows APIs. For example, on a system with the current code page 1252, the paths in cp1252 are supported and transparently converted to UTF-16 by the ANSI functions. Once one wants to handle a filepath encoded with cp932 on that particular system, an ANSI or a POSIX compatible function used in PHP will produce an erroneous result. When trying to convert that cp932 path to UTF-8 and passing to the ANSI functions, an ANSI function would likely interpret the UTF-8 string as some string in the current code page and create a filepath that represents every single byte of the UTF-8 string. These behaviors are not only broken but also disregard the documented INI settings. This patch solves the issies with the multibyte paths on Windows by intelligently enforcing the usage of the Unicode aware APIs. For functions expect Unicode (fe CreateFileW, FindFirstFileW, etc.), arguments will be converted to UTF-16 wide chars. For functions returning Unicode aware data (fe GetCurrentDirectoryW, etc.), resulting wide string is converted back to char's depending on the current PHP charset settings, either to the current ANSI codepage (this is the behavior prior to this patch) or to UTF-8 (the default behavior). In a particular case, users might have to explicitly set internal_encoding or default_charset, if filenames in ANSI codepage are necessary. Current tests show no regressions and witness that this will be an exotic case, the current default UTF-8 encoding is compatible with any supported system. The dependency libraries are long switching to Unicode APIs, so some tests were also added for extensions not directly related to streams. At large, the patch brings over 150 related tests into the core. Those target and was run on various environments with European, Asian, etc. codepages. General PHP frameworks was tested and showed no regressions. The impact on the current C code base is low, the most places affected are the Windows only places in the three files tsrm_win32.c, zend_virtual_cwd.c and plain_wrapper.c. The actual implementation of the most of the wide char supporting functionality is in win32/ioutil.* and win32/codepage.*, several low level functionsare extended in place to avoid reimplementation for now. No performance impact was sighted. As previously mentioned, the ANSI APIs used prior the patch perform Unicode conversions internally. Using the Unicode APIs directly while doing custom conversions just retains the status quo. The ways to optimize it are open (fe. by implementing caching for the strings converted to wide variants). The long path implementation is user transparent. If a path exceeds the length of _MAX_PATH, it'll be automatically prefixed with \\?\. The MAXPATHLEN is set to 2048 bytes. Appreciation to Pierre Joye, Matt Ficken, @algo13 and others for tips, ideas and testing. Thanks.
2016-06-20 15:32:19 +08:00
#include "win32/ioutil.h"
2000-09-04 02:47:35 +08:00
/* mode_t isn't defined on Windows */
2000-11-01 02:05:28 +08:00
typedef unsigned short mode_t;
2000-10-04 00:36:32 +08:00
#define DEFAULT_SLASH '\\'
2001-07-16 21:31:22 +08:00
#define DEFAULT_DIR_SEPARATOR ';'
#define IS_SLASH(c) ((c) == '/' || (c) == '\\')
#define IS_SLASH_P(c) (*(c) == '/' || \
(*(c) == '\\' && !IsDBCSLeadByte(*(c-1))))
/* COPY_WHEN_ABSOLUTE is 2 under Win32 because by chance both regular absolute paths
in the file system and UNC paths need copying of two characters */
#define COPY_WHEN_ABSOLUTE(path) 2
2001-03-23 16:33:06 +08:00
#define IS_UNC_PATH(path, len) \
(len >= 2 && IS_SLASH(path[0]) && IS_SLASH(path[1]))
#define IS_ABSOLUTE_PATH(path, len) \
2014-10-02 19:50:46 +08:00
(len >= 2 && (/* is local */isalpha(path[0]) && path[1] == ':' || /* is UNC */IS_SLASH(path[0]) && IS_SLASH(path[1])))
#else
#ifdef HAVE_DIRENT_H
#include <dirent.h>
#endif
2000-10-04 00:36:32 +08:00
#define DEFAULT_SLASH '/'
2001-11-03 21:33:21 +08:00
#ifdef __riscos__
#define DEFAULT_DIR_SEPARATOR ';'
#else
#define DEFAULT_DIR_SEPARATOR ':'
#endif
#define IS_SLASH(c) ((c) == '/')
#define IS_SLASH_P(c) (*(c) == '/')
#endif
2000-10-04 00:36:32 +08:00
#ifndef COPY_WHEN_ABSOLUTE
#define COPY_WHEN_ABSOLUTE(path) 0
2000-10-04 00:36:32 +08:00
#endif
2010-09-13 17:08:42 +08:00
#ifndef IS_ABSOLUTE_PATH
#define IS_ABSOLUTE_PATH(path, len) \
(IS_SLASH(path[0]))
#endif
2000-09-04 02:47:35 +08:00
#ifdef TSRM_EXPORTS
#define CWD_EXPORTS
#endif
#ifdef ZEND_WIN32
# ifdef CWD_EXPORTS
# define CWD_API __declspec(dllexport)
# else
# define CWD_API __declspec(dllimport)
# endif
#elif defined(__GNUC__) && __GNUC__ >= 4
# define CWD_API __attribute__ ((visibility("default")))
#else
# define CWD_API
#endif
#ifdef ZEND_WIN32
CWD_API int php_sys_stat_ex(const char *path, zend_stat_t *buf, int lstat);
2010-09-01 17:49:53 +08:00
# define php_sys_stat(path, buf) php_sys_stat_ex(path, buf, 0)
# define php_sys_lstat(path, buf) php_sys_stat_ex(path, buf, 1)
CWD_API ssize_t php_sys_readlink(const char *link, char *target, size_t target_len);
#else
# define php_sys_stat stat
2010-09-01 17:49:53 +08:00
# define php_sys_lstat lstat
2010-09-10 22:01:44 +08:00
# ifdef HAVE_SYMLINK
# define php_sys_readlink(link, target, target_len) readlink(link, target, target_len)
# endif
#endif
typedef struct _cwd_state {
char *cwd;
size_t cwd_length;
} cwd_state;
typedef int (*verify_path_func)(const cwd_state *);
CWD_API void virtual_cwd_startup(void);
CWD_API void virtual_cwd_shutdown(void);
2014-12-14 06:06:14 +08:00
CWD_API int virtual_cwd_activate(void);
CWD_API int virtual_cwd_deactivate(void);
CWD_API char *virtual_getcwd_ex(size_t *length);
CWD_API char *virtual_getcwd(char *buf, size_t size);
CWD_API int virtual_chdir(const char *path);
CWD_API int virtual_chdir_file(const char *path, int (*p_chdir)(const char *path));
CWD_API int virtual_filepath(const char *path, char **filepath);
CWD_API int virtual_filepath_ex(const char *path, char **filepath, verify_path_func verify_path);
CWD_API char *virtual_realpath(const char *path, char *real_path);
CWD_API FILE *virtual_fopen(const char *path, const char *mode);
CWD_API int virtual_open(const char *path, int flags, ...);
CWD_API int virtual_creat(const char *path, mode_t mode);
CWD_API int virtual_rename(const char *oldname, const char *newname);
CWD_API int virtual_stat(const char *path, zend_stat_t *buf);
CWD_API int virtual_lstat(const char *path, zend_stat_t *buf);
CWD_API int virtual_unlink(const char *path);
CWD_API int virtual_mkdir(const char *pathname, mode_t mode);
CWD_API int virtual_rmdir(const char *pathname);
CWD_API DIR *virtual_opendir(const char *pathname);
CWD_API FILE *virtual_popen(const char *command, const char *type);
CWD_API int virtual_access(const char *pathname, int mode);
2002-10-04 09:04:00 +08:00
#if HAVE_UTIME
2014-12-14 06:06:14 +08:00
CWD_API int virtual_utime(const char *filename, struct utimbuf *buf);
#endif
2014-12-14 06:06:14 +08:00
CWD_API int virtual_chmod(const char *filename, mode_t mode);
#if !defined(ZEND_WIN32)
2014-12-14 06:06:14 +08:00
CWD_API int virtual_chown(const char *filename, uid_t owner, gid_t group, int link);
#endif
2010-09-13 17:08:42 +08:00
/* One of the following constants must be used as the last argument
2006-11-14 17:15:55 +08:00
in virtual_file_ex() call. */
#define CWD_EXPAND 0 /* expand "." and ".." but dont resolve symlinks */
#define CWD_FILEPATH 1 /* resolve symlinks if file is exist otherwise expand */
#define CWD_REALPATH 2 /* call realpath(), resolve symlinks. File must exist */
2006-11-13 23:13:20 +08:00
2014-12-14 06:06:14 +08:00
CWD_API int virtual_file_ex(cwd_state *state, const char *path, verify_path_func verify_path, int use_realpath);
2014-12-14 06:06:14 +08:00
CWD_API char *tsrm_realpath(const char *path, char *real_path);
#define REALPATH_CACHE_TTL (2*60) /* 2 minutes */
#define REALPATH_CACHE_SIZE 0 /* disabled while php.ini isn't loaded */
typedef struct _realpath_cache_bucket {
2014-08-26 01:24:55 +08:00
zend_ulong key;
char *path;
char *realpath;
struct _realpath_cache_bucket *next;
time_t expires;
uint16_t path_len;
uint16_t realpath_len;
uint8_t is_dir:1;
#ifdef ZEND_WIN32
uint8_t is_rvalid:1;
uint8_t is_readable:1;
uint8_t is_wvalid:1;
uint8_t is_writable:1;
#endif
} realpath_cache_bucket;
typedef struct _virtual_cwd_globals {
cwd_state cwd;
2014-08-26 01:24:55 +08:00
zend_long realpath_cache_size;
zend_long realpath_cache_size_limit;
zend_long realpath_cache_ttl;
realpath_cache_bucket *realpath_cache[1024];
} virtual_cwd_globals;
#ifdef ZTS
2014-09-26 00:48:27 +08:00
extern ts_rsrc_id cwd_globals_id;
# define CWDG(v) ZEND_TSRMG(cwd_globals_id, virtual_cwd_globals *, v)
#else
extern virtual_cwd_globals cwd_globals;
# define CWDG(v) (cwd_globals.v)
#endif
2014-12-14 06:06:14 +08:00
CWD_API void realpath_cache_clean(void);
CWD_API void realpath_cache_del(const char *path, size_t path_len);
CWD_API realpath_cache_bucket* realpath_cache_lookup(const char *path, size_t path_len, time_t t);
2014-12-14 06:06:14 +08:00
CWD_API zend_long realpath_cache_size(void);
CWD_API zend_long realpath_cache_max_buckets(void);
CWD_API realpath_cache_bucket** realpath_cache_get_buckets(void);
2017-08-14 06:44:19 +08:00
#ifdef CWD_EXPORTS
extern void virtual_cwd_main_cwd_init(uint8_t);
#endif
2000-09-04 12:18:38 +08:00
/* The actual macros to be used in programs using TSRM
* If the program defines VIRTUAL_DIR it will use the
2010-09-13 17:08:42 +08:00
* virtual_* functions
2000-09-04 12:18:38 +08:00
*/
#ifdef VIRTUAL_DIR
2014-12-14 06:06:14 +08:00
#define VCWD_GETCWD(buff, size) virtual_getcwd(buff, size)
#define VCWD_FOPEN(path, mode) virtual_fopen(path, mode)
2001-08-05 09:34:40 +08:00
/* Because open() has two modes, we have to macros to replace it */
2014-12-14 06:06:14 +08:00
#define VCWD_OPEN(path, flags) virtual_open(path, flags)
#define VCWD_OPEN_MODE(path, flags, mode) virtual_open(path, flags, mode)
#define VCWD_CREAT(path, mode) virtual_creat(path, mode)
#define VCWD_CHDIR(path) virtual_chdir(path)
#define VCWD_CHDIR_FILE(path) virtual_chdir_file(path, virtual_chdir)
#define VCWD_GETWD(buf)
2014-12-14 06:06:14 +08:00
#define VCWD_REALPATH(path, real_path) virtual_realpath(path, real_path)
#define VCWD_RENAME(oldname, newname) virtual_rename(oldname, newname)
#define VCWD_STAT(path, buff) virtual_stat(path, buff)
# define VCWD_LSTAT(path, buff) virtual_lstat(path, buff)
#define VCWD_UNLINK(path) virtual_unlink(path)
#define VCWD_MKDIR(pathname, mode) virtual_mkdir(pathname, mode)
#define VCWD_RMDIR(pathname) virtual_rmdir(pathname)
#define VCWD_OPENDIR(pathname) virtual_opendir(pathname)
#define VCWD_POPEN(command, type) virtual_popen(command, type)
#define VCWD_ACCESS(pathname, mode) virtual_access(pathname, mode)
2000-09-04 12:18:38 +08:00
#if HAVE_UTIME
2014-12-14 06:06:14 +08:00
#define VCWD_UTIME(path, time) virtual_utime(path, time)
2000-09-04 12:18:38 +08:00
#endif
2014-12-14 06:06:14 +08:00
#define VCWD_CHMOD(path, mode) virtual_chmod(path, mode)
#if !defined(ZEND_WIN32)
2014-12-14 06:06:14 +08:00
#define VCWD_CHOWN(path, owner, group) virtual_chown(path, owner, group, 0)
#if HAVE_LCHOWN
2014-12-14 06:06:14 +08:00
#define VCWD_LCHOWN(path, owner, group) virtual_chown(path, owner, group, 1)
2000-09-04 12:18:38 +08:00
#endif
#endif
2000-09-04 12:18:38 +08:00
#else
#define VCWD_CREAT(path, mode) creat(path, mode)
/* rename on windows will fail if newname already exists.
MoveFileEx has to be used */
#if defined(ZEND_WIN32)
Fixed the UTF-8 and long path support in the streams on Windows. Since long the default PHP charset is UTF-8, however the Windows part is out of step with this important point. The current implementation in PHP doesn't technically permit to handle UTF-8 filepath and several other things. Till now, only the ANSI compatible APIs are being used. Here is more about it https://msdn.microsoft.com/en-us/library/windows/desktop/dd317752%28v=vs.85%29.aspx The patch fixes not only issues with multibyte filenames under incompatible codepages, but indirectly also issues with some other multibyte encodings like BIG5, Shift-JIS, etc. by providing a clean way to access filenames in UTF-8. Below is a small list of issues from the bug tracker, that are getting fixed: https://bugs.php.net/63401 https://bugs.php.net/41199 https://bugs.php.net/50203 https://bugs.php.net/71509 https://bugs.php.net/64699 https://bugs.php.net/64506 https://bugs.php.net/30195 https://bugs.php.net/65358 https://bugs.php.net/61315 https://bugs.php.net/70943 https://bugs.php.net/70903 https://bugs.php.net/63593 https://bugs.php.net/54977 https://bugs.php.net/54028 https://bugs.php.net/43148 https://bugs.php.net/30730 https://bugs.php.net/33350 https://bugs.php.net/35300 https://bugs.php.net/46990 https://bugs.php.net/61309 https://bugs.php.net/69333 https://bugs.php.net/45517 https://bugs.php.net/70551 https://bugs.php.net/50197 https://bugs.php.net/72200 https://bugs.php.net/37672 Yet more related tickets can for sure be found - on bugs.php.net, Stackoverflow and Github. Some of the bugs are pretty recent, some descend to early 2000th, but the user comments in there last even till today. Just for example, bug #30195 was opened in 2004, the latest comment in there was made in 2014. It is certain, that these bugs descend not only to pure PHP use cases, but get also redirected from the popular PHP based projects. Given the modern systems (and those supported by PHP) are always based on NTFS, there is no excuse to keep these issues unresolved. The internalization approach on Windows is in many ways different from UNIX and Linux, while it supports and is based on Unicode. It depends on the current system code page, APIs used and exact kind how the binary was compiled The locale doesn't affect the way Unicode or ANSI API work. PHP in particular is being compiled without _UNICODE defined and this is conditioned by the way we handle strings. Here is more about it https://msdn.microsoft.com/en-us/library/tsbaswba.aspx However, with any system code page ANSI functions automatically convert paths to UTF-16. Paths in some encodings incompatible with the current system code page, won't work correctly with ANSI APIs. PHP till now only uses the ANSI Windows APIs. For example, on a system with the current code page 1252, the paths in cp1252 are supported and transparently converted to UTF-16 by the ANSI functions. Once one wants to handle a filepath encoded with cp932 on that particular system, an ANSI or a POSIX compatible function used in PHP will produce an erroneous result. When trying to convert that cp932 path to UTF-8 and passing to the ANSI functions, an ANSI function would likely interpret the UTF-8 string as some string in the current code page and create a filepath that represents every single byte of the UTF-8 string. These behaviors are not only broken but also disregard the documented INI settings. This patch solves the issies with the multibyte paths on Windows by intelligently enforcing the usage of the Unicode aware APIs. For functions expect Unicode (fe CreateFileW, FindFirstFileW, etc.), arguments will be converted to UTF-16 wide chars. For functions returning Unicode aware data (fe GetCurrentDirectoryW, etc.), resulting wide string is converted back to char's depending on the current PHP charset settings, either to the current ANSI codepage (this is the behavior prior to this patch) or to UTF-8 (the default behavior). In a particular case, users might have to explicitly set internal_encoding or default_charset, if filenames in ANSI codepage are necessary. Current tests show no regressions and witness that this will be an exotic case, the current default UTF-8 encoding is compatible with any supported system. The dependency libraries are long switching to Unicode APIs, so some tests were also added for extensions not directly related to streams. At large, the patch brings over 150 related tests into the core. Those target and was run on various environments with European, Asian, etc. codepages. General PHP frameworks was tested and showed no regressions. The impact on the current C code base is low, the most places affected are the Windows only places in the three files tsrm_win32.c, zend_virtual_cwd.c and plain_wrapper.c. The actual implementation of the most of the wide char supporting functionality is in win32/ioutil.* and win32/codepage.*, several low level functionsare extended in place to avoid reimplementation for now. No performance impact was sighted. As previously mentioned, the ANSI APIs used prior the patch perform Unicode conversions internally. Using the Unicode APIs directly while doing custom conversions just retains the status quo. The ways to optimize it are open (fe. by implementing caching for the strings converted to wide variants). The long path implementation is user transparent. If a path exceeds the length of _MAX_PATH, it'll be automatically prefixed with \\?\. The MAXPATHLEN is set to 2048 bytes. Appreciation to Pierre Joye, Matt Ficken, @algo13 and others for tips, ideas and testing. Thanks.
2016-06-20 15:32:19 +08:00
#define VCWD_FOPEN(path, mode) php_win32_ioutil_fopen(path, mode)
#define VCWD_OPEN(path, flags) php_win32_ioutil_open(path, flags)
#define VCWD_OPEN_MODE(path, flags, mode) php_win32_ioutil_open(path, flags, mode)
# define VCWD_RENAME(oldname, newname) php_win32_ioutil_rename(oldname, newname)
#define VCWD_MKDIR(pathname, mode) php_win32_ioutil_mkdir(pathname, mode)
#define VCWD_RMDIR(pathname) php_win32_ioutil_rmdir(pathname)
#define VCWD_UNLINK(path) php_win32_ioutil_unlink(path)
#define VCWD_CHDIR(path) php_win32_ioutil_chdir(path)
#define VCWD_ACCESS(pathname, mode) tsrm_win32_access(pathname, mode)
#define VCWD_GETCWD(buff, size) php_win32_ioutil_getcwd(buff, size)
#define VCWD_CHMOD(path, mode) php_win32_ioutil_chmod(path, mode)
#else
Fixed the UTF-8 and long path support in the streams on Windows. Since long the default PHP charset is UTF-8, however the Windows part is out of step with this important point. The current implementation in PHP doesn't technically permit to handle UTF-8 filepath and several other things. Till now, only the ANSI compatible APIs are being used. Here is more about it https://msdn.microsoft.com/en-us/library/windows/desktop/dd317752%28v=vs.85%29.aspx The patch fixes not only issues with multibyte filenames under incompatible codepages, but indirectly also issues with some other multibyte encodings like BIG5, Shift-JIS, etc. by providing a clean way to access filenames in UTF-8. Below is a small list of issues from the bug tracker, that are getting fixed: https://bugs.php.net/63401 https://bugs.php.net/41199 https://bugs.php.net/50203 https://bugs.php.net/71509 https://bugs.php.net/64699 https://bugs.php.net/64506 https://bugs.php.net/30195 https://bugs.php.net/65358 https://bugs.php.net/61315 https://bugs.php.net/70943 https://bugs.php.net/70903 https://bugs.php.net/63593 https://bugs.php.net/54977 https://bugs.php.net/54028 https://bugs.php.net/43148 https://bugs.php.net/30730 https://bugs.php.net/33350 https://bugs.php.net/35300 https://bugs.php.net/46990 https://bugs.php.net/61309 https://bugs.php.net/69333 https://bugs.php.net/45517 https://bugs.php.net/70551 https://bugs.php.net/50197 https://bugs.php.net/72200 https://bugs.php.net/37672 Yet more related tickets can for sure be found - on bugs.php.net, Stackoverflow and Github. Some of the bugs are pretty recent, some descend to early 2000th, but the user comments in there last even till today. Just for example, bug #30195 was opened in 2004, the latest comment in there was made in 2014. It is certain, that these bugs descend not only to pure PHP use cases, but get also redirected from the popular PHP based projects. Given the modern systems (and those supported by PHP) are always based on NTFS, there is no excuse to keep these issues unresolved. The internalization approach on Windows is in many ways different from UNIX and Linux, while it supports and is based on Unicode. It depends on the current system code page, APIs used and exact kind how the binary was compiled The locale doesn't affect the way Unicode or ANSI API work. PHP in particular is being compiled without _UNICODE defined and this is conditioned by the way we handle strings. Here is more about it https://msdn.microsoft.com/en-us/library/tsbaswba.aspx However, with any system code page ANSI functions automatically convert paths to UTF-16. Paths in some encodings incompatible with the current system code page, won't work correctly with ANSI APIs. PHP till now only uses the ANSI Windows APIs. For example, on a system with the current code page 1252, the paths in cp1252 are supported and transparently converted to UTF-16 by the ANSI functions. Once one wants to handle a filepath encoded with cp932 on that particular system, an ANSI or a POSIX compatible function used in PHP will produce an erroneous result. When trying to convert that cp932 path to UTF-8 and passing to the ANSI functions, an ANSI function would likely interpret the UTF-8 string as some string in the current code page and create a filepath that represents every single byte of the UTF-8 string. These behaviors are not only broken but also disregard the documented INI settings. This patch solves the issies with the multibyte paths on Windows by intelligently enforcing the usage of the Unicode aware APIs. For functions expect Unicode (fe CreateFileW, FindFirstFileW, etc.), arguments will be converted to UTF-16 wide chars. For functions returning Unicode aware data (fe GetCurrentDirectoryW, etc.), resulting wide string is converted back to char's depending on the current PHP charset settings, either to the current ANSI codepage (this is the behavior prior to this patch) or to UTF-8 (the default behavior). In a particular case, users might have to explicitly set internal_encoding or default_charset, if filenames in ANSI codepage are necessary. Current tests show no regressions and witness that this will be an exotic case, the current default UTF-8 encoding is compatible with any supported system. The dependency libraries are long switching to Unicode APIs, so some tests were also added for extensions not directly related to streams. At large, the patch brings over 150 related tests into the core. Those target and was run on various environments with European, Asian, etc. codepages. General PHP frameworks was tested and showed no regressions. The impact on the current C code base is low, the most places affected are the Windows only places in the three files tsrm_win32.c, zend_virtual_cwd.c and plain_wrapper.c. The actual implementation of the most of the wide char supporting functionality is in win32/ioutil.* and win32/codepage.*, several low level functionsare extended in place to avoid reimplementation for now. No performance impact was sighted. As previously mentioned, the ANSI APIs used prior the patch perform Unicode conversions internally. Using the Unicode APIs directly while doing custom conversions just retains the status quo. The ways to optimize it are open (fe. by implementing caching for the strings converted to wide variants). The long path implementation is user transparent. If a path exceeds the length of _MAX_PATH, it'll be automatically prefixed with \\?\. The MAXPATHLEN is set to 2048 bytes. Appreciation to Pierre Joye, Matt Ficken, @algo13 and others for tips, ideas and testing. Thanks.
2016-06-20 15:32:19 +08:00
#define VCWD_FOPEN(path, mode) fopen(path, mode)
#define VCWD_OPEN(path, flags) open(path, flags)
#define VCWD_OPEN_MODE(path, flags, mode) open(path, flags, mode)
# define VCWD_RENAME(oldname, newname) rename(oldname, newname)
Fixed the UTF-8 and long path support in the streams on Windows. Since long the default PHP charset is UTF-8, however the Windows part is out of step with this important point. The current implementation in PHP doesn't technically permit to handle UTF-8 filepath and several other things. Till now, only the ANSI compatible APIs are being used. Here is more about it https://msdn.microsoft.com/en-us/library/windows/desktop/dd317752%28v=vs.85%29.aspx The patch fixes not only issues with multibyte filenames under incompatible codepages, but indirectly also issues with some other multibyte encodings like BIG5, Shift-JIS, etc. by providing a clean way to access filenames in UTF-8. Below is a small list of issues from the bug tracker, that are getting fixed: https://bugs.php.net/63401 https://bugs.php.net/41199 https://bugs.php.net/50203 https://bugs.php.net/71509 https://bugs.php.net/64699 https://bugs.php.net/64506 https://bugs.php.net/30195 https://bugs.php.net/65358 https://bugs.php.net/61315 https://bugs.php.net/70943 https://bugs.php.net/70903 https://bugs.php.net/63593 https://bugs.php.net/54977 https://bugs.php.net/54028 https://bugs.php.net/43148 https://bugs.php.net/30730 https://bugs.php.net/33350 https://bugs.php.net/35300 https://bugs.php.net/46990 https://bugs.php.net/61309 https://bugs.php.net/69333 https://bugs.php.net/45517 https://bugs.php.net/70551 https://bugs.php.net/50197 https://bugs.php.net/72200 https://bugs.php.net/37672 Yet more related tickets can for sure be found - on bugs.php.net, Stackoverflow and Github. Some of the bugs are pretty recent, some descend to early 2000th, but the user comments in there last even till today. Just for example, bug #30195 was opened in 2004, the latest comment in there was made in 2014. It is certain, that these bugs descend not only to pure PHP use cases, but get also redirected from the popular PHP based projects. Given the modern systems (and those supported by PHP) are always based on NTFS, there is no excuse to keep these issues unresolved. The internalization approach on Windows is in many ways different from UNIX and Linux, while it supports and is based on Unicode. It depends on the current system code page, APIs used and exact kind how the binary was compiled The locale doesn't affect the way Unicode or ANSI API work. PHP in particular is being compiled without _UNICODE defined and this is conditioned by the way we handle strings. Here is more about it https://msdn.microsoft.com/en-us/library/tsbaswba.aspx However, with any system code page ANSI functions automatically convert paths to UTF-16. Paths in some encodings incompatible with the current system code page, won't work correctly with ANSI APIs. PHP till now only uses the ANSI Windows APIs. For example, on a system with the current code page 1252, the paths in cp1252 are supported and transparently converted to UTF-16 by the ANSI functions. Once one wants to handle a filepath encoded with cp932 on that particular system, an ANSI or a POSIX compatible function used in PHP will produce an erroneous result. When trying to convert that cp932 path to UTF-8 and passing to the ANSI functions, an ANSI function would likely interpret the UTF-8 string as some string in the current code page and create a filepath that represents every single byte of the UTF-8 string. These behaviors are not only broken but also disregard the documented INI settings. This patch solves the issies with the multibyte paths on Windows by intelligently enforcing the usage of the Unicode aware APIs. For functions expect Unicode (fe CreateFileW, FindFirstFileW, etc.), arguments will be converted to UTF-16 wide chars. For functions returning Unicode aware data (fe GetCurrentDirectoryW, etc.), resulting wide string is converted back to char's depending on the current PHP charset settings, either to the current ANSI codepage (this is the behavior prior to this patch) or to UTF-8 (the default behavior). In a particular case, users might have to explicitly set internal_encoding or default_charset, if filenames in ANSI codepage are necessary. Current tests show no regressions and witness that this will be an exotic case, the current default UTF-8 encoding is compatible with any supported system. The dependency libraries are long switching to Unicode APIs, so some tests were also added for extensions not directly related to streams. At large, the patch brings over 150 related tests into the core. Those target and was run on various environments with European, Asian, etc. codepages. General PHP frameworks was tested and showed no regressions. The impact on the current C code base is low, the most places affected are the Windows only places in the three files tsrm_win32.c, zend_virtual_cwd.c and plain_wrapper.c. The actual implementation of the most of the wide char supporting functionality is in win32/ioutil.* and win32/codepage.*, several low level functionsare extended in place to avoid reimplementation for now. No performance impact was sighted. As previously mentioned, the ANSI APIs used prior the patch perform Unicode conversions internally. Using the Unicode APIs directly while doing custom conversions just retains the status quo. The ways to optimize it are open (fe. by implementing caching for the strings converted to wide variants). The long path implementation is user transparent. If a path exceeds the length of _MAX_PATH, it'll be automatically prefixed with \\?\. The MAXPATHLEN is set to 2048 bytes. Appreciation to Pierre Joye, Matt Ficken, @algo13 and others for tips, ideas and testing. Thanks.
2016-06-20 15:32:19 +08:00
#define VCWD_MKDIR(pathname, mode) mkdir(pathname, mode)
#define VCWD_RMDIR(pathname) rmdir(pathname)
#define VCWD_UNLINK(path) unlink(path)
#define VCWD_CHDIR(path) chdir(path)
Fixed the UTF-8 and long path support in the streams on Windows. Since long the default PHP charset is UTF-8, however the Windows part is out of step with this important point. The current implementation in PHP doesn't technically permit to handle UTF-8 filepath and several other things. Till now, only the ANSI compatible APIs are being used. Here is more about it https://msdn.microsoft.com/en-us/library/windows/desktop/dd317752%28v=vs.85%29.aspx The patch fixes not only issues with multibyte filenames under incompatible codepages, but indirectly also issues with some other multibyte encodings like BIG5, Shift-JIS, etc. by providing a clean way to access filenames in UTF-8. Below is a small list of issues from the bug tracker, that are getting fixed: https://bugs.php.net/63401 https://bugs.php.net/41199 https://bugs.php.net/50203 https://bugs.php.net/71509 https://bugs.php.net/64699 https://bugs.php.net/64506 https://bugs.php.net/30195 https://bugs.php.net/65358 https://bugs.php.net/61315 https://bugs.php.net/70943 https://bugs.php.net/70903 https://bugs.php.net/63593 https://bugs.php.net/54977 https://bugs.php.net/54028 https://bugs.php.net/43148 https://bugs.php.net/30730 https://bugs.php.net/33350 https://bugs.php.net/35300 https://bugs.php.net/46990 https://bugs.php.net/61309 https://bugs.php.net/69333 https://bugs.php.net/45517 https://bugs.php.net/70551 https://bugs.php.net/50197 https://bugs.php.net/72200 https://bugs.php.net/37672 Yet more related tickets can for sure be found - on bugs.php.net, Stackoverflow and Github. Some of the bugs are pretty recent, some descend to early 2000th, but the user comments in there last even till today. Just for example, bug #30195 was opened in 2004, the latest comment in there was made in 2014. It is certain, that these bugs descend not only to pure PHP use cases, but get also redirected from the popular PHP based projects. Given the modern systems (and those supported by PHP) are always based on NTFS, there is no excuse to keep these issues unresolved. The internalization approach on Windows is in many ways different from UNIX and Linux, while it supports and is based on Unicode. It depends on the current system code page, APIs used and exact kind how the binary was compiled The locale doesn't affect the way Unicode or ANSI API work. PHP in particular is being compiled without _UNICODE defined and this is conditioned by the way we handle strings. Here is more about it https://msdn.microsoft.com/en-us/library/tsbaswba.aspx However, with any system code page ANSI functions automatically convert paths to UTF-16. Paths in some encodings incompatible with the current system code page, won't work correctly with ANSI APIs. PHP till now only uses the ANSI Windows APIs. For example, on a system with the current code page 1252, the paths in cp1252 are supported and transparently converted to UTF-16 by the ANSI functions. Once one wants to handle a filepath encoded with cp932 on that particular system, an ANSI or a POSIX compatible function used in PHP will produce an erroneous result. When trying to convert that cp932 path to UTF-8 and passing to the ANSI functions, an ANSI function would likely interpret the UTF-8 string as some string in the current code page and create a filepath that represents every single byte of the UTF-8 string. These behaviors are not only broken but also disregard the documented INI settings. This patch solves the issies with the multibyte paths on Windows by intelligently enforcing the usage of the Unicode aware APIs. For functions expect Unicode (fe CreateFileW, FindFirstFileW, etc.), arguments will be converted to UTF-16 wide chars. For functions returning Unicode aware data (fe GetCurrentDirectoryW, etc.), resulting wide string is converted back to char's depending on the current PHP charset settings, either to the current ANSI codepage (this is the behavior prior to this patch) or to UTF-8 (the default behavior). In a particular case, users might have to explicitly set internal_encoding or default_charset, if filenames in ANSI codepage are necessary. Current tests show no regressions and witness that this will be an exotic case, the current default UTF-8 encoding is compatible with any supported system. The dependency libraries are long switching to Unicode APIs, so some tests were also added for extensions not directly related to streams. At large, the patch brings over 150 related tests into the core. Those target and was run on various environments with European, Asian, etc. codepages. General PHP frameworks was tested and showed no regressions. The impact on the current C code base is low, the most places affected are the Windows only places in the three files tsrm_win32.c, zend_virtual_cwd.c and plain_wrapper.c. The actual implementation of the most of the wide char supporting functionality is in win32/ioutil.* and win32/codepage.*, several low level functionsare extended in place to avoid reimplementation for now. No performance impact was sighted. As previously mentioned, the ANSI APIs used prior the patch perform Unicode conversions internally. Using the Unicode APIs directly while doing custom conversions just retains the status quo. The ways to optimize it are open (fe. by implementing caching for the strings converted to wide variants). The long path implementation is user transparent. If a path exceeds the length of _MAX_PATH, it'll be automatically prefixed with \\?\. The MAXPATHLEN is set to 2048 bytes. Appreciation to Pierre Joye, Matt Ficken, @algo13 and others for tips, ideas and testing. Thanks.
2016-06-20 15:32:19 +08:00
#define VCWD_ACCESS(pathname, mode) access(pathname, mode)
#define VCWD_GETCWD(buff, size) getcwd(buff, size)
#define VCWD_CHMOD(path, mode) chmod(path, mode)
#endif
#define VCWD_CHDIR_FILE(path) virtual_chdir_file(path, chdir)
#define VCWD_GETWD(buf) getwd(buf)
#define VCWD_STAT(path, buff) php_sys_stat(path, buff)
#define VCWD_LSTAT(path, buff) lstat(path, buff)
#define VCWD_OPENDIR(pathname) opendir(pathname)
#define VCWD_POPEN(command, type) popen(command, type)
2001-08-05 09:34:40 +08:00
2014-12-14 06:06:14 +08:00
#define VCWD_REALPATH(path, real_path) tsrm_realpath(path, real_path)
2001-08-05 09:34:40 +08:00
2000-09-04 12:18:38 +08:00
#if HAVE_UTIME
# ifdef ZEND_WIN32
# define VCWD_UTIME(path, time) win32_utime(path, time)
# else
# define VCWD_UTIME(path, time) utime(path, time)
# endif
2000-09-04 12:18:38 +08:00
#endif
#if !defined(ZEND_WIN32)
2001-08-05 09:34:40 +08:00
#define VCWD_CHOWN(path, owner, group) chown(path, owner, group)
#if HAVE_LCHOWN
#define VCWD_LCHOWN(path, owner, group) lchown(path, owner, group)
2000-09-04 12:18:38 +08:00
#endif
#endif
2000-09-04 12:18:38 +08:00
#endif
/* Global stat declarations */
#ifndef _S_IFDIR
#define _S_IFDIR S_IFDIR
#endif
#ifndef _S_IFREG
#define _S_IFREG S_IFREG
#endif
2015-05-26 00:07:47 +08:00
#ifndef S_IFLNK
2016-12-22 09:17:55 +08:00
#define _IFLNK 0120000 /* symbolic link */
#define S_IFLNK _IFLNK
2015-05-26 00:07:47 +08:00
#endif
#ifndef S_ISDIR
#define S_ISDIR(mode) (((mode)&S_IFMT) == S_IFDIR)
#endif
#ifndef S_ISREG
#define S_ISREG(mode) (((mode)&S_IFMT) == S_IFREG)
#endif
#ifndef S_ISLNK
#define S_ISLNK(mode) (((mode)&S_IFMT) == S_IFLNK)
#endif
#ifndef S_IXROOT
#define S_IXROOT ( S_IXUSR | S_IXGRP | S_IXOTH )
#endif
2016-12-22 09:17:55 +08:00
/* XXX should be _S_IFIFO? */
#ifndef S_IFIFO
#define _IFIFO 0010000 /* fifo */
#define S_IFIFO _IFIFO
#endif
#ifndef S_IFBLK
#define _IFBLK 0060000 /* block special */
#define S_IFBLK _IFBLK
#endif
#endif /* VIRTUAL_CWD_H */
2017-07-05 00:12:45 +08:00
/*
* Local variables:
* tab-width: 4
* c-basic-offset: 4
* indent-tabs-mode: t
* End:
* vim600: sw=4 ts=4 fdm=marker
* vim<600: sw=4 ts=4
*/