From d7757d423e285ae0c112407d1dcc60191aa0b4bd Mon Sep 17 00:00:00 2001 From: oehhar Date: Thu, 30 Jan 2014 11:02:51 +0000 Subject: win/tclWinChan.c Tcl_InitNotifier: Bug [2413550] Avoid reopening of serial channels which causes issues with Bluetooth virtual com. Patch by Rolf Schroedter. --- ChangeLog | 6 +++ win/tclWinChan.c | 151 ++++++++++++++++++++++++++++++++++++++++++++++++++++- win/tclWinInt.h | 2 +- win/tclWinSerial.c | 25 +++++---- 4 files changed, 171 insertions(+), 13 deletions(-) diff --git a/ChangeLog b/ChangeLog index fd8c7c7..aec77d9 100644 --- a/ChangeLog +++ b/ChangeLog @@ -7,6 +7,12 @@ this log file. You may still find useful things in it, but the Timeline is a better first place to look now. ============================================================================ +2014-01-30 Harald Oehlmann + + * win/tclWinChan.c Tcl_InitNotifier: Bug [2413550] + Avoid reopening of serial channels which causes issues with + Bluetooth virtual com. Patch by Rolf Schroedter. + 2013-08-30 Don Porter * generic/tcl.h: Bump to 8.5.15 for release. diff --git a/win/tclWinChan.c b/win/tclWinChan.c index 89d898f..19e3655 100644 --- a/win/tclWinChan.c +++ b/win/tclWinChan.c @@ -95,7 +95,7 @@ static void FileThreadActionProc(ClientData instanceData, static int FileTruncateProc(ClientData instanceData, Tcl_WideInt length); static DWORD FileGetType(HANDLE handle); - +static int NativeIsComPort(CONST TCHAR *nativeName); /* * This structure describes the channel type structure for file based IO. */ @@ -904,6 +904,33 @@ TclpOpenFileChannel( } /* + * [2413550] Avoid double-open of serial ports on Windows + * Special handling for Windows serial ports by a "name-hint" + * to directly open it with the OVERLAPPED flag set. + */ + + if( NativeIsComPort(nativeName) ) { + + handle = TclWinSerialOpen(INVALID_HANDLE_VALUE, nativeName, accessMode); + if (handle == INVALID_HANDLE_VALUE) { + TclWinConvertError(GetLastError()); + if (interp != (Tcl_Interp *) NULL) { + Tcl_AppendResult(interp, "couldn't open serial \"", + TclGetString(pathPtr), "\": ", + Tcl_PosixError(interp), NULL); + } + return NULL; + } + + /* + * For natively named Windows serial ports we are done. + */ + channel = TclWinOpenSerialChannel(handle, channelName, + channelPermissions); + + return channel; + } + /* * Set up the file sharing mode. We want to allow simultaneous access. */ @@ -935,11 +962,15 @@ TclpOpenFileChannel( switch (FileGetType(handle)) { case FILE_TYPE_SERIAL: /* + * Natively named serial ports "com1-9", "\\\\.\\comXX" are + * already done with the code above. + * Here we handle all other serial port names. + * * Reopen channel for OVERLAPPED operation. Normally this shouldn't * fail, because the channel exists. */ - handle = TclWinSerialReopen(handle, nativeName, accessMode); + handle = TclWinSerialOpen(handle, nativeName, accessMode); if (handle == INVALID_HANDLE_VALUE) { TclWinConvertError(GetLastError()); if (interp != (Tcl_Interp *) NULL) { @@ -1476,6 +1507,122 @@ FileGetType( return type; } + /* + *---------------------------------------------------------------------- + * + * NativeIsComPort -- + * + * Determines if a path refers to a Windows serial port. + * A simple and efficient solution is to use a "name hint" to detect + * COM ports by their filename instead of resorting to a syscall + * to detect serialness after the fact. + * The following patterns cover common serial port names: + * COM[1-9]:? + * //./COM[0-9]+ + * \\.\COM[0-9]+ + * + * Results: + * 1 = serial port, 0 = not. + * + *---------------------------------------------------------------------- + */ + +static int +NativeIsComPort( + const TCHAR *nativePath) /* Path of file to access, native encoding. */ +{ + /* + * Use wide-char or plain character case-insensitive comparison + */ + if (tclWinProcs->useWide) { + const WCHAR *p = (const WCHAR *) nativePath; + int i, len = wcslen(p); + + /* + * 1. Look for com[1-9]:? + */ + + if ( (len >= 4) && (len <= 5) + && (_wcsnicmp(p, L"com", 3) == 0) ) { + /* + * The 4th character must be a digit 1..9 optionally followed by a ":" + */ + + if ( (p[3] < L'1') || (p[3] > L'9') ) { + return 0; + } + if ( (len == 5) && (p[4] != L':') ) { + return 0; + } + return 1; + } + + /* + * 2. Look for //./com[0-9]+ or \\.\com[0-9]+ + */ + + if ( (len >= 8) && ( + (_wcsnicmp(p, L"//./com", 7) == 0) + || (_wcsnicmp(p, L"\\\\.\\com", 7) == 0) ) ) + { + /* + * Charaters 8..end must be a digits 0..9 + */ + + for ( i=7; i '9') ) { + return 0; + } + } + return 1; + } + + } else { + const char *p = (const char *) nativePath; + int i, len = strlen(p); + + /* + * 1. Look for com[1-9]:? + */ + + if ( (len >= 4) && (len <= 5) + && (strnicmp(p, "com", 3) == 0) ) { + /* + * The 4th character must be a digit 1..9 optionally followed by a ":" + */ + + if ( (p[3] < '1') || (p[3] > '9') ) { + return 0; + } + if ( (len == 5) && (p[4] != ':') ) { + return 0; + } + return 1; + } + + /* + * 2. Look for //./com[0-9]+ or \\.\com[0-9]+ + */ + + if ( (len >= 8) && ( + (strnicmp(p, "//./com", 7) == 0) + || (strnicmp(p, "\\\\.\\com", 7) == 0) ) ) + { + /* + * Charaters 8..end must be a digits 0..9 + */ + + for ( i=7; i '9') ) { + return 0; + } + } + return 1; + } + } + return 0; +} + /* * Local Variables: * mode: c diff --git a/win/tclWinInt.h b/win/tclWinInt.h index 3d5e275..ccf48bb 100644 --- a/win/tclWinInt.h +++ b/win/tclWinInt.h @@ -187,7 +187,7 @@ MODULE_SCOPE Tcl_Channel TclWinOpenFileChannel(HANDLE handle, char *channelName, MODULE_SCOPE Tcl_Channel TclWinOpenSerialChannel(HANDLE handle, char *channelName, int permissions); MODULE_SCOPE void TclWinResetInterfaceEncodings(); -MODULE_SCOPE HANDLE TclWinSerialReopen(HANDLE handle, CONST TCHAR *name, +MODULE_SCOPE HANDLE TclWinSerialOpen(HANDLE handle, CONST TCHAR *name, DWORD access); MODULE_SCOPE int TclWinSymLinkCopyDirectory(CONST TCHAR* LinkOriginal, CONST TCHAR* LinkCopy); diff --git a/win/tclWinSerial.c b/win/tclWinSerial.c index d5244ac..312a2f8 100644 --- a/win/tclWinSerial.c +++ b/win/tclWinSerial.c @@ -1410,23 +1410,22 @@ SerialWriterThread( /* *---------------------------------------------------------------------- * - * TclWinSerialReopen -- + * TclWinSerialOpen -- * - * Reopens the serial port with the OVERLAPPED FLAG set + * Opens or Reopens the serial port with the OVERLAPPED FLAG set * * Results: - * Returns the new handle, or INVALID_HANDLE_VALUE. Normally there - * shouldn't be any error, because the same channel has previously been - * succeesfully opened. + * Returns the new handle, or INVALID_HANDLE_VALUE. + * I an existing channel is specified it is closed and reopened. * * Side effects: - * May close the original handle + * May close/reopen the original handle * *---------------------------------------------------------------------- */ HANDLE -TclWinSerialReopen( +TclWinSerialOpen( HANDLE handle, CONST TCHAR *name, DWORD access) @@ -1434,16 +1433,22 @@ TclWinSerialReopen( SerialInit(); /* + * If an open channel is specified, close it + */ + + if ( handle != INVALID_HANDLE_VALUE && CloseHandle(handle) == FALSE) { + return INVALID_HANDLE_VALUE; + } + + /* * Multithreaded I/O needs the overlapped flag set otherwise * ClearCommError blocks under Windows NT/2000 until serial output is * finished */ - if (CloseHandle(handle) == FALSE) { - return INVALID_HANDLE_VALUE; - } handle = (*tclWinProcs->createFileProc)(name, access, 0, 0, OPEN_EXISTING, FILE_FLAG_OVERLAPPED, 0); + return handle; } -- cgit v0.12 From 38e56569f541a17fd0445bc3619d66e985e823db Mon Sep 17 00:00:00 2001 From: oehhar Date: Tue, 11 Feb 2014 08:53:33 +0000 Subject: Changed position of flag evaluation as proposed by Phil Hoffman --- win/tclWinChan.c | 36 ++++++++++++++++++------------------ 1 file changed, 18 insertions(+), 18 deletions(-) diff --git a/win/tclWinChan.c b/win/tclWinChan.c index 19e3655..6d480a8 100644 --- a/win/tclWinChan.c +++ b/win/tclWinChan.c @@ -886,24 +886,6 @@ TclpOpenFileChannel( } /* - * If the file is being created, get the file attributes from the - * permissions argument, else use the existing file attributes. - */ - - if (mode & O_CREAT) { - if (permissions & S_IWRITE) { - flags = FILE_ATTRIBUTE_NORMAL; - } else { - flags = FILE_ATTRIBUTE_READONLY; - } - } else { - flags = (*tclWinProcs->getFileAttributesProc)(nativeName); - if (flags == 0xFFFFFFFF) { - flags = 0; - } - } - - /* * [2413550] Avoid double-open of serial ports on Windows * Special handling for Windows serial ports by a "name-hint" * to directly open it with the OVERLAPPED flag set. @@ -931,6 +913,24 @@ TclpOpenFileChannel( return channel; } /* + * If the file is being created, get the file attributes from the + * permissions argument, else use the existing file attributes. + */ + + if (mode & O_CREAT) { + if (permissions & S_IWRITE) { + flags = FILE_ATTRIBUTE_NORMAL; + } else { + flags = FILE_ATTRIBUTE_READONLY; + } + } else { + flags = (*tclWinProcs->getFileAttributesProc)(nativeName); + if (flags == 0xFFFFFFFF) { + flags = 0; + } + } + + /* * Set up the file sharing mode. We want to allow simultaneous access. */ -- cgit v0.12 From eb24399a17b85fad292fe5137bb9ea641f8b7896 Mon Sep 17 00:00:00 2001 From: dkf Date: Sun, 23 Feb 2014 13:07:36 +0000 Subject: [3597178]: Improve documentation of what's going on with encodings --- doc/encoding.n | 34 +++++++++++++++++++++++++++------- doc/string.n | 28 ++++++++++++++++++++++++---- 2 files changed, 51 insertions(+), 11 deletions(-) diff --git a/doc/encoding.n b/doc/encoding.n index be1dc3f..5782199 100644 --- a/doc/encoding.n +++ b/doc/encoding.n @@ -14,10 +14,21 @@ encoding \- Manipulate encodings .BE .SH INTRODUCTION .PP -Strings in Tcl are encoded using 16-bit Unicode characters. Different -operating system interfaces or applications may generate strings in -other encodings such as Shift-JIS. The \fBencoding\fR command helps -to bridge the gap between Unicode and these other formats. +Strings in Tcl are logically a sequence of 16-bit Unicode characters. +These strings are represented in memory as a sequence of bytes that +may be in one of several encodings: modified UTF\-8 (which uses 1 to 3 +bytes per character), 16-bit +.QW Unicode +(which uses 2 bytes per character, with an endianness that is +dependent on the host architecture), and binary (which uses a single +byte per character but only handles a restricted range of characters). +Tcl does not guarantee to always use the same encoding for the same +string. +.PP +Different operating system interfaces or applications may generate +strings in other encodings such as Shift\-JIS. The \fBencoding\fR +command helps to bridge the gap between Unicode and these other +formats. .SH DESCRIPTION .PP Performs one of several encoding related operations, depending on @@ -37,8 +48,9 @@ system encoding is used. Convert \fIstring\fR from Unicode to the specified \fIencoding\fR. The result is a sequence of bytes that represents the converted string. Each byte is stored in the lower 8-bits of a Unicode -character. If \fIencoding\fR is not specified, the current -system encoding is used. +character (indeed, the resulting string is a binary string as far as +Tcl is concerned, at least initially). If \fIencoding\fR is not +specified, the current system encoding is used. .TP \fBencoding dirs\fR ?\fIdirectoryList\fR? . @@ -56,6 +68,11 @@ searchable directory, that element is ignored. . Returns a list containing the names of all of the encodings that are currently available. +The encodings +.QW utf-8 +and +.QW iso8859-1 +are guaranteed to be present in the list. .TP \fBencoding system\fR ?\fIencoding\fR? . @@ -73,7 +90,7 @@ However, because the \fBsource\fR command always reads files using the current system encoding, Tcl will only source such files correctly when the encoding used to write the file is the same. This tends not to be true in an internationalized setting. For example, if such a -file was sourced in North America (where the ISO8859-1 is normally +file was sourced in North America (where the ISO8859\-1 is normally used), each byte in the file would be treated as a separate character that maps to the 00 page in Unicode. The resulting Tcl strings will not contain the expected Japanese characters. Instead, they will @@ -93,3 +110,6 @@ which is the Hiragana letter HA. Tcl_GetEncoding(3) .SH KEYWORDS encoding, unicode +.\" Local Variables: +.\" mode: nroff +.\" End: diff --git a/doc/string.n b/doc/string.n index 76005fc..163abdd 100644 --- a/doc/string.n +++ b/doc/string.n @@ -343,10 +343,13 @@ misleading. \fBstring bytelength \fIstring\fR . Returns a decimal string giving the number of bytes used to represent -\fIstring\fR in memory. Because UTF\-8 uses one to three bytes to -represent Unicode characters, the byte length will not be the same as -the character length in general. The cases where a script cares about -the byte length are rare. +\fIstring\fR in memory when encoded as Tcl's internal modified UTF\-8; +Tcl may use other encodings for \fIstring\fR as well, and does not +guarantee to only use a single encoding for a particular \fIstring\fR. +Because UTF\-8 uses a variable number of bytes to represent Unicode +characters, the byte length will not be the same as the character +length in general. The cases where a script cares about the byte +length are rare. .RS .PP In almost all cases, you should use the @@ -354,10 +357,27 @@ In almost all cases, you should use the Tcl byte array value). Refer to the \fBTcl_NumUtfChars\fR manual entry for more details on the UTF\-8 representation. .PP +Formally, the \fBstring bytelength\fR operation returns the content of +the \fIlength\fR field of the \fBTcl_Obj\fR structure, after calling +\fBTcl_GetString\fR to ensure that the \fIbytes\fR field is populated. +This is highly unlikely to be useful to Tcl scripts, as Tcl's internal +encoding is not strict UTF\-8, but rather a modified CESU\-8 with a +denormalized NUL (identical to that used in a number of places by +Java's serialization mechanism) to enable basic processing with +non-Unicode-aware C functions. As this representation should only +ever be used by Tcl's implementation, the number of bytes used to +store the representation is of very low value (except to C extension +code, which has direct access for the purpose of memory management, +etc.) +.PP \fICompatibility note:\fR it is likely that this subcommand will be withdrawn in a future version of Tcl. It is better to use the \fBencoding convertto\fR command to convert a string to a known encoding and then apply \fBstring length\fR to that. +.PP +.CS +\fBstring length\fR [encoding convertto utf-8 $theString] +.CE .RE .TP \fBstring wordend \fIstring charIndex\fR -- cgit v0.12