[svn] Improved --restrict-file-names to accept ",nocontrol".

doc/ChangeLog

@@ -1,3 +1,8 @@
+2003-09-17  Hrvoje Niksic  <hniksic@xemacs.org>
+
+	* wget.texi (Download Options): Explain new --restrict-file-names
+	semantics.
+
 2003-09-16  Hrvoje Niksic  <hniksic@xemacs.org>
 
 	* wget.texi: Set the man page title to a string more descriptive

doc/wget.texi

@@ -808,36 +808,39 @@ this option.
 
 @cindex file names, restrict
 @cindex Windows file names
-@itemx --restrict-file-names=none|unix|windows
+@itemx --restrict-file-names=@var{mode}
-Restrict characters that may occur in local file names created by Wget
+Change which characters found in remote URLs may show up in local file
-from remote URLs.  Characters that are considered @dfn{unsafe} under a
+names generated from those URLs.  Characters that are @dfn{restricted}
-set of restrictions are escaped, i.e. replaced with @samp{%XX}, where
+by this option are escaped, i.e. replaced with @samp{%HH}, where
-@samp{XX} is the hexadecimal code of the character.
+@samp{HH} is the hexadecimal number that corresponds to the restricted
+character.
 
-The default for this option depends on the operating system: on Unix and
+By default, Wget escapes the characters that are not valid as part of
-Unix-like OS'es, it defaults to ``unix''.  Under Windows and Cygwin, it
+file names on your operating system, as well as control characters that
-defaults to ``windows''.  Changing the default is useful when you are
+are typically unprintable.  This option is useful for changing these
-using a non-native partition, e.g. when downloading files to a Windows
+defaults, either because you are downloading to a non-native partition,
-partition mounted from Linux, or when using NFS-mounted or SMB-mounted
+or because you want to disable escaping of the control characters.
-Windows drives.
 
-When set to ``none'', the only characters that are quoted are those that
+When mode is set to ``unix'', Wget escapes the character @samp{/} and
-are impossible to get into a file name---the NUL character and @samp{/}.
+the control characters in the ranges 0--31 and 128--159.  This is the
-The control characters, newline, etc. are all placed into file names.
+default on Unix-like OS'es.
 
-When set to ``unix'', additional unsafe characters are those in the
+When mode is seto to ``windows'', Wget escapes the characters @samp{\},
-0--31 range and in the 128--159 range.  This is because those characters
+@samp{|}, @samp{/}, @samp{:}, @samp{?}, @samp{"}, @samp{*}, @samp{<},
-are typically not printable.
+@samp{>}, and the control characters in the ranges 0--31 and 128--159.
-
+In addition to this, Wget in Windows mode uses @samp{+} instead of
-When set to ``windows'', all of the above are quoted, along with
+@samp{:} to separate host and port in local file names, and uses
-@samp{\}, @samp{|}, @samp{:}, @samp{?}, @samp{"}, @samp{*}, @samp{<},
-and @samp{>}.  Additionally, Wget in Windows mode uses @samp{+} instead
-of @samp{:} to separate host and port in local file names, and uses
 @samp{@@} instead of @samp{?} to separate the query portion of the file
 name from the rest.  Therefore, a URL that would be saved as
 @samp{www.xemacs.org:4300/search.pl?input=blah} in Unix mode would be
 saved as @samp{www.xemacs.org+4300/search.pl@@input=blah} in Windows
-mode.
+mode.  This mode is the default on Windows.
+
+If you append @samp{,nocontrol} to the mode, as in
+@samp{unix,nocontrol}, escaping of the control characters is also
+switched off.  You can use @samp{--restrict-file-names=nocontrol} to
+turn off escaping of control characters without affecting the choice of
+the OS to use as file name restriction mode.
 @end table
 
 @node Directory Options, HTTP Options, Download Options, Invoking
@@ -2279,7 +2282,7 @@ Links}).
 If set to on, remove @sc{ftp} listings downloaded by Wget.  Setting it
 to off is the same as @samp{-nr}.
 
-@item restrict_file_names = off/unix/windows
+@item restrict_file_names = unix/windows
 Restrict the file names generated by Wget from URLs.  See
 @samp{--restrict-file-names} for a more detailed description.
 

src/ChangeLog

@@ -1,3 +1,14 @@
+2003-09-17  Hrvoje Niksic  <hniksic@xemacs.org>
+
+	* init.c (cmd_spec_restrict_file_names): Allow the OS setting to
+	be augmented by ",nocontrol" which means don't escape the control
+	characters, but otherwise keep OS settings.
+
+	* url.c (file_unsafe_char): Deleted.
+	(append_uri_pathel): Query filechr_table directly.
+	(filechr_table): Separated Unix, Windows, and control-unsafe
+	characters.
+
 2003-09-17  Hrvoje Niksic  <hniksic@xemacs.org>
 
 	* url.c (url_escape_1): New function.

src/init.c

@@ -189,7 +189,7 @@ static struct {
   { "reject",		&opt.rejects,		cmd_vector },
   { "relativeonly",	&opt.relative_only,	cmd_boolean },
   { "removelisting",	&opt.remove_listing,	cmd_boolean },
-  { "restrictfilenames", &opt.restrict_file_names, cmd_spec_restrict_file_names },
+  { "restrictfilenames", NULL,			cmd_spec_restrict_file_names },
   { "retrsymlinks",	&opt.retr_symlinks,	cmd_boolean },
   { "retryconnrefused",	&opt.retry_connrefused,	cmd_boolean },
   { "robots",		&opt.use_robots,	cmd_boolean },
@@ -286,10 +286,11 @@ defaults (void)
 
   /* The default for file name restriction defaults to the OS type. */
 #if !defined(WINDOWS) && !defined(__CYGWIN__)
-  opt.restrict_file_names = restrict_shell;
+  opt.restrict_files_os = restrict_unix;
 #else
-  opt.restrict_file_names = restrict_windows;
+  opt.restrict_files_os = restrict_windows;
 #endif
+  opt.restrict_files_ctrl = 1;
 }
 
 /* Return the user's home directory (strdup-ed), or NULL if none is
@@ -1020,20 +1021,41 @@ cmd_spec_recursive (const char *com, const char *val, void *closure)
 static int
 cmd_spec_restrict_file_names (const char *com, const char *val, void *closure)
 {
-  /* The currently accepted values are `none', `unix', and
+  int restrict_os = opt.restrict_files_os;
-     `windows'.  */
+  int restrict_ctrl = opt.restrict_files_ctrl;
-  if (0 == strcasecmp (val, "none"))
+
-    opt.restrict_file_names = restrict_none;
+  const char *end = strchr (val, ',');
-  else if (0 == strcasecmp (val, "unix"))
+  if (!end)
-    opt.restrict_file_names = restrict_shell;
+    end = val + strlen (val);
-  else if (0 == strcasecmp (val, "windows"))
+
-    opt.restrict_file_names = restrict_windows;
+#define VAL_IS(string_literal) BOUNDED_EQUAL (val, end, string_literal)
+
+  if (VAL_IS ("unix"))
+    restrict_os = restrict_unix;
+  else if (VAL_IS ("windows"))
+    restrict_os = restrict_windows;
+  else if (VAL_IS ("nocontrol"))
+    restrict_ctrl = 0;
   else
     {
+    err:
       fprintf (stderr, _("%s: %s: Invalid specification `%s'.\n"),
 	       exec_name, com, val);
       return 0;
     }
+
+#undef VAL_IS
+
+  if (*end)
+    {
+      if (!strcmp (end + 1, "nocontrol"))
+	restrict_ctrl = 0;
+      else
+	goto err;
+    }
+
+  opt.restrict_files_os = restrict_os;
+  opt.restrict_files_ctrl = restrict_ctrl;
   return 1;
 }
 

src/main.c

@@ -179,7 +179,7 @@ Download:\n\
        --bind-address=ADDRESS   bind to ADDRESS (hostname or IP) on local host.\n\
        --limit-rate=RATE        limit download rate to RATE.\n\
        --dns-cache=off          disable caching DNS lookups.\n\
-       --restrict-file-names=MODE restrict chars in file names to MODE.\n\
+       --restrict-file-names=OS restrict chars in file names to ones OS allows.\n\
 \n"), stdout);
   fputs (_("\
 Directories:\n\

src/options.h

@@ -186,10 +186,12 @@ struct options
   char *post_file_name;		/* File to post */
 
   enum {
-    restrict_none,
+    restrict_unix,
-    restrict_shell,
     restrict_windows
-  } restrict_file_names;	/* whether we restrict file name chars. */
+  } restrict_files_os;		/* file name restriction ruleset. */
+  int restrict_files_ctrl;	/* non-zero if control chars in URLs
+				   are restricted from appearing in
+				   generated file names. */
 };
 
 extern struct options opt;

src/url.c

@@ -1479,23 +1479,22 @@ append_char (char ch, struct growable *dest)
 }
 
 enum {
-  filechr_unsafe_always  = 1,	/* always unsafe, e.g. / or \0 */
+  filechr_not_unix    = 1,	/* unusable on Unix, / and \0 */
-  filechr_unsafe_shell   = 2,	/* unsafe for shell use, e.g. control chars */
+  filechr_not_windows = 2,	/* unusable on Windows, one of \|/<>?:*" */
-  filechr_unsafe_windows = 2,	/* disallowed on Windows file system */
+  filechr_control     = 4,	/* a control character, e.g. 0-31 */
 };
 
 #define FILE_CHAR_TEST(c, mask) (filechr_table[(unsigned char)(c)] & (mask))
 
 /* Shorthands for the table: */
-#define A filechr_unsafe_always
+#define U filechr_not_unix
-#define S filechr_unsafe_shell
+#define W filechr_not_windows
-#define W filechr_unsafe_windows
+#define C filechr_control
 
-/* Forbidden chars:
+#define UW U|W
+#define UWC U|W|C
 
-   always: \0, /
+/* Table of characters unsafe under various conditions (see above).
-   Unix shell: 0-31, 128-159
-   Windows:    \, |, /, <, >, ?, :
 
    Arguably we could also claim `%' to be unsafe, since we use it as
    the escape character.  If we ever want to be able to reliably
@@ -1504,12 +1503,12 @@ enum {
 
 const static unsigned char filechr_table[256] =
 {
-  A,  S,  S,  S,   S,  S,  S,  S,   /* NUL SOH STX ETX  EOT ENQ ACK BEL */
+UWC,  C,  C,  C,   C,  C,  C,  C,   /* NUL SOH STX ETX  EOT ENQ ACK BEL */
-  S,  S,  S,  S,   S,  S,  S,  S,   /* BS  HT  LF  VT   FF  CR  SO  SI  */
+  C,  C,  C,  C,   C,  C,  C,  C,   /* BS  HT  LF  VT   FF  CR  SO  SI  */
-  S,  S,  S,  S,   S,  S,  S,  S,   /* DLE DC1 DC2 DC3  DC4 NAK SYN ETB */
+  C,  C,  C,  C,   C,  C,  C,  C,   /* DLE DC1 DC2 DC3  DC4 NAK SYN ETB */
-  S,  S,  S,  S,   S,  S,  S,  S,   /* CAN EM  SUB ESC  FS  GS  RS  US  */
+  C,  C,  C,  C,   C,  C,  C,  C,   /* CAN EM  SUB ESC  FS  GS  RS  US  */
   0,  0,  W,  0,   0,  0,  0,  0,   /* SP  !   "   #    $   %   &   '   */
-  0,  0,  W,  0,   0,  0,  0,  A,   /* (   )   *   +    ,   -   .   /   */
+  0,  0,  W,  0,   0,  0,  0, UW,   /* (   )   *   +    ,   -   .   /   */
   0,  0,  0,  0,   0,  0,  0,  0,   /* 0   1   2   3    4   5   6   7   */
   0,  0,  W,  0,   W,  0,  W,  W,   /* 8   9   :   ;    <   =   >   ?   */
   0,  0,  0,  0,   0,  0,  0,  0,   /* @   A   B   C    D   E   F   G   */
@@ -1521,8 +1520,8 @@ const static unsigned char filechr_table[256] =
   0,  0,  0,  0,   0,  0,  0,  0,   /* p   q   r   s    t   u   v   w   */
   0,  0,  0,  0,   0,  0,  0,  0,   /* x   y   z   {    |   }   ~   DEL */
 
-  S, S, S, S,  S, S, S, S,  S, S, S, S,  S, S, S, S, /* 128-143 */
+  C, C, C, C,  C, C, C, C,  C, C, C, C,  C, C, C, C, /* 128-143 */
-  S, S, S, S,  S, S, S, S,  S, S, S, S,  S, S, S, S, /* 144-159 */
+  C, C, C, C,  C, C, C, C,  C, C, C, C,  C, C, C, C, /* 144-159 */
   0, 0, 0, 0,  0, 0, 0, 0,  0, 0, 0, 0,  0, 0, 0, 0,
   0, 0, 0, 0,  0, 0, 0, 0,  0, 0, 0, 0,  0, 0, 0, 0,
 
@@ -1532,30 +1531,16 @@ const static unsigned char filechr_table[256] =
   0, 0, 0, 0,  0, 0, 0, 0,  0, 0, 0, 0,  0, 0, 0, 0,
 };
 
-/* Return non-zero if character CH is unsafe for use in file or
-   directory name.  Called by append_uri_pathel. */
-
-static inline int
-file_unsafe_char (char ch, int restrict)
-{
-  int mask = filechr_unsafe_always;
-  if (restrict == restrict_shell)
-    mask |= filechr_unsafe_shell;
-  else if (restrict == restrict_windows)
-    mask |= (filechr_unsafe_shell | filechr_unsafe_windows);
-  return FILE_CHAR_TEST (ch, mask);
-}
-
 /* FN_PORT_SEP is the separator between host and port in file names
    for non-standard port numbers.  On Unix this is normally ':', as in
    "www.xemacs.org:4001/index.html".  Under Windows, we set it to +
    because Windows can't handle ':' in file names.  */
-#define FN_PORT_SEP  (opt.restrict_file_names != restrict_windows ? ':' : '+')
+#define FN_PORT_SEP  (opt.restrict_files_os != restrict_windows ? ':' : '+')
 
 /* FN_QUERY_SEP is the separator between the file name and the URL
    query, normally '?'.  Since Windows cannot handle '?' as part of
    file name, we use '@' instead there.  */
-#define FN_QUERY_SEP (opt.restrict_file_names != restrict_windows ? '?' : '@')
+#define FN_QUERY_SEP (opt.restrict_files_os != restrict_windows ? '?' : '@')
 
 /* Quote path element, characters in [b, e), as file name, and append
    the quoted string to DEST.  Each character is quoted as per
@@ -1570,12 +1555,13 @@ append_uri_pathel (const char *b, const char *e, struct growable *dest)
   const char *p;
   int quoted, outlen;
 
-  /* Currently restrict_for_windows is determined at compile time
+  int mask;
-     only.  But some users download files to Windows partitions; they
+  if (opt.restrict_files_os == restrict_unix)
-     should be able to say --windows-file-names so Wget escapes
+    mask = filechr_not_unix;
-     characters invalid on Windows.  Similar run-time restrictions for
+  else
-     other file systems can be implemented.  */
+    mask = filechr_not_windows;
-  const int restrict = opt.restrict_file_names;
+  if (opt.restrict_files_ctrl)
+    mask |= filechr_control;
 
   /* Copy [b, e) to PATHEL and URL-unescape it. */
   BOUNDED_TO_ALLOCA (b, e, pathel);
@@ -1586,7 +1572,7 @@ append_uri_pathel (const char *b, const char *e, struct growable *dest)
      add for file quoting. */
   quoted = 0;
   for (p = pathel; *p; p++)
-    if (file_unsafe_char (*p, restrict))
+    if (FILE_CHAR_TEST (*p, mask))
       ++quoted;
 
   /* p - pathel is the string length.  Each quoted char means two
@@ -1605,7 +1591,7 @@ append_uri_pathel (const char *b, const char *e, struct growable *dest)
       char *q = TAIL (dest);
       for (p = pathel; *p; p++)
 	{
-	  if (!file_unsafe_char (*p, restrict))
+	  if (!FILE_CHAR_TEST (*p, mask))
 	    *q++ = *p;
 	  else
 	    {