New function quotearg_alloc. Treat { } = as special sometimes.

Work around bug in multibyte handling in older shells.

diff --git a/ChangeLog b/ChangeLog
index 3e06d3f166f3d0030a91512440b46d9b5430b686..62b65c36035b1caf30ba19985e2df38ba4a8de6f 100644 (file)
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,15 @@
+2004-02-05  Paul Eggert  <eggert@twinsun.com>
+
+       Add comments and code, prompted by suggestions from Bruno Haible
+       for sh-quote.
+       * quotearg.h (quotearg_alloc): New decl.  Improve the comments
+       describing the enum quoting_style values.
+       * quotearg.c (quotearg_alloc): New function.
+       (quotearg_buffer_restyled): Treat lone { and } as special.
+       Treat = as special.  Work around bug with older shells
+       that "see" a '\' that is really the 2nd byte of a multibyte char.
+       Quote empty string with shell_quoting_style.
+
 2004-02-03  Bruno Haible  <bruno@clisp.org>
 
        * modules/pipe: New file.

diff --git a/lib/quotearg.c b/lib/quotearg.c
index c695646f13ec247187b0404c04835f6f0479976e..fe747fb0b91e6e97ecb3b19e720146938a60e8b8 100644 (file)
--- a/lib/quotearg.c
+++ b/lib/quotearg.c
@@ -1,5 +1,7 @@
 /* quotearg.c - quote arguments for output
-   Copyright (C) 1998, 1999, 2000, 2001, 2002 Free Software Foundation, Inc.
+
+   Copyright (C) 1998, 1999, 2000, 2001, 2002, 2004 Free Software
+   Foundation, Inc.
 
    This program is free software; you can redistribute it and/or modify
    it under the terms of the GNU General Public License as published by
@@ -174,7 +176,7 @@ gettext_quote (char const *msgid, enum quoting_style s)
    size of the output, not counting the terminating null.
    If BUFFERSIZE is too small to store the output string, return the
    value that would have been returned had BUFFERSIZE been large enough.
-   If ARGSIZE is -1, use the string length of the argument for ARGSIZE.
+   If ARGSIZE is SIZE_MAX, use the string length of the argument for ARGSIZE.
 
    This function acts like quotearg_buffer (BUFFER, BUFFERSIZE, ARG,
    ARGSIZE, O), except it uses QUOTING_STYLE instead of the quoting
@@ -326,6 +328,10 @@ quotearg_buffer_restyled (char *buffer, size_t buffersize,
            }
          break;
 
+       case '{': case '}': /* sometimes special if isolated */
+         if (! (argsize == SIZE_MAX ? arg[1] == '\0' : argsize == 1))
+           break;
+         /* Fall through.  */
        case '#': case '~':
          if (i != 0)
            break;
@@ -334,7 +340,9 @@ quotearg_buffer_restyled (char *buffer, size_t buffersize,
        case '!': /* special in bash */
        case '"': case '$': case '&':
        case '(': case ')': case '*': case ';':
-       case '<': case '>': case '[':
+       case '<':
+       case '=': /* sometimes special in 0th or (with "set -k") later args */
+       case '>': case '[':
        case '^': /* special in old /bin/sh, e.g. SunOS 4.1.4 */
        case '`': case '|':
          /* A shell special character.  In theory, '$' and '`' could
@@ -364,7 +372,7 @@ quotearg_buffer_restyled (char *buffer, size_t buffersize,
 
        case '%': case '+': case ',': case '-': case '.': case '/':
        case '0': case '1': case '2': case '3': case '4': case '5':
-       case '6': case '7': case '8': case '9': case ':': case '=':
+       case '6': case '7': case '8': case '9': case ':':
        case 'A': case 'B': case 'C': case 'D': case 'E': case 'F':
        case 'G': case 'H': case 'I': case 'J': case 'K': case 'L':
        case 'M': case 'N': case 'O': case 'P': case 'Q': case 'R':
@@ -374,7 +382,6 @@ quotearg_buffer_restyled (char *buffer, size_t buffersize,
        case 'i': case 'j': case 'k': case 'l': case 'm': case 'n':
        case 'o': case 'p': case 'q': case 'r': case 's': case 't':
        case 'u': case 'v': case 'w': case 'x': case 'y': case 'z':
-       case '{': case '}':
          /* These characters don't cause problems, no matter what the
             quoting style is.  They cannot start multibyte sequences.  */
          break;
@@ -427,6 +434,22 @@ quotearg_buffer_restyled (char *buffer, size_t buffersize,
                      }
                    else
                      {
+                       /* Work around a bug with older shells that "see" a '\'
+                          that is really the 2nd byte of a multibyte character.
+                          In practice the problem is limited to ASCII
+                          chars >= '@' that are shell special chars.  */
+                       if ('[' == 0x5b && quoting_style == shell_quoting_style)
+                         {
+                           size_t j;
+                           for (j = 1; j < bytes; j++)
+                             switch (arg[i + m + j])
+                               {
+                               case '[': case '\\': case '^':
+                               case '`': case '|':
+                                 goto use_shell_always_quoting_style;
+                               }
+                         }
+                           
                        if (! iswprint (w))
                          printable = 0;
                        m += bytes;
@@ -472,6 +495,9 @@ quotearg_buffer_restyled (char *buffer, size_t buffersize,
       STORE (c);
     }
 
+  if (i == 0 && quoting_style == shell_quoting_style)
+    goto use_shell_always_quoting_style;
+
   if (quote_string)
     for (; *quote_string; quote_string++)
       STORE (*quote_string);
@@ -492,7 +518,8 @@ quotearg_buffer_restyled (char *buffer, size_t buffersize,
    size of the output, not counting the terminating null.
    If BUFFERSIZE is too small to store the output string, return the
    value that would have been returned had BUFFERSIZE been large enough.
-   If ARGSIZE is -1, use the string length of the argument for ARGSIZE.  */
+   If ARGSIZE is SIZE_MAX, use the string length of the argument for
+   ARGSIZE.  */
 size_t
 quotearg_buffer (char *buffer, size_t buffersize,
                 char const *arg, size_t argsize,
@@ -506,8 +533,23 @@ quotearg_buffer (char *buffer, size_t buffersize,
   return r;
 }
 
+/* Like quotearg_buffer (..., ARG, ARGSIZE, O), except return newly
+   allocated storage containing the quoted string.  */
+char *
+quotearg_alloc (char const *arg, size_t argsize,
+               struct quoting_options const *o)
+{
+  int e = errno;
+  size_t bufsize = quotearg_buffer (0, 0, arg, argsize, o) + 1;
+  char *buf = xmalloc (bufsize);
+  quotearg_buffer (buf, bufsize, arg, argsize, o);
+  errno = e;
+  return buf;
+}
+
 /* Use storage slot N to return a quoted version of argument ARG.
-   ARG is of size ARGSIZE, but if that is -1, ARG is a null-terminated string.
+   ARG is of size ARGSIZE, but if that is SIZE_MAX, ARG is a
+   null-terminated string.
    OPTIONS specifies the quoting options.
    The returned value points to static storage that can be
    reused by the next call to this function with the same value of N.

diff --git a/lib/quotearg.h b/lib/quotearg.h
index efc933173dcb3674d1a88d1ac2314d77ef187b97..2bbf38d92a14d74ea5248ba66480cfc2bf6d1354 100644 (file)
--- a/lib/quotearg.h
+++ b/lib/quotearg.h
@@ -1,6 +1,6 @@
 /* quotearg.h - quote arguments for output
 
-   Copyright (C) 1998, 1999, 2000, 2001, 2002 Free Software
+   Copyright (C) 1998, 1999, 2000, 2001, 2002, 2004 Free Software
    Foundation, Inc.
 
    This program is free software; you can redistribute it and/or modify
@@ -27,13 +27,31 @@
 /* Basic quoting styles.  */
 enum quoting_style
   {
-    literal_quoting_style,     /* --quoting-style=literal */
-    shell_quoting_style,       /* --quoting-style=shell */
-    shell_always_quoting_style,        /* --quoting-style=shell-always */
-    c_quoting_style,           /* --quoting-style=c */
-    escape_quoting_style,      /* --quoting-style=escape */
-    locale_quoting_style,      /* --quoting-style=locale */
-    clocale_quoting_style      /* --quoting-style=clocale */
+    /* Output names as-is (ls --quoting-style=literal).  */
+    literal_quoting_style,
+    
+    /* Quote names for the shell if they contain shell metacharacters
+       or would cause ambiguous output (ls --quoting-style=shell).  */
+    shell_quoting_style,
+
+    /* Quote names for the shell, even if they would normally not
+       require quoting (ls --quoting-style=shell-always).  */
+    shell_always_quoting_style,
+
+    /* Quote names as for a C language string (ls --quoting-style=c).  */
+    c_quoting_style,
+
+    /* Like c_quoting_style except omit the surrounding double-quote
+       characters (ls --quoting-style=escape).  */
+    escape_quoting_style,
+
+    /* Like clocale_quoting_style, but quote `like this' instead of
+       "like this" in the default C locale (ls --quoting-style=locale).  */
+    locale_quoting_style,
+
+    /* Like c_quoting_style except use quotation marks appropriate for
+       the locale (ls --quoting-style=clocale).  */
+    clocale_quoting_style
   };
 
 /* For now, --quoting-style=literal is the default, but this may change.  */
@@ -81,6 +99,11 @@ size_t quotearg_buffer (char *buffer, size_t buffersize,
                        char const *arg, size_t argsize,
                        struct quoting_options const *o);
 
+/* Like quotearg_buffer, except return the result in a newly allocated
+   buffer.  It is the caller's responsibility to free the result.  */
+char *quotearg_alloc (char const *arg, size_t argsize,
+                     struct quoting_options const *o);
+
 /* Use storage slot N to return a quoted version of the string ARG.
    Use the default quoting options.
    The returned value points to static storage that can be