Re: using libmagic in Emacs?

[joakim@verona.se]

[-- Attachment #1: Type: text/plain, Size: 1651 bytes --]

New filemagic patch mostly fixing Eli:s concerns.


Eli Zaretskii <eliz@gnu.org> writes:
>> +DEFUN ("libmagic-file-internal", Flibmagic_file_internal, Slibmagic_file_internal, 1,1,0,
>> +       doc: /* Return (MIME_TYPE MIME_ENCODING DESCRIPTION) for FILENAME_OR_BUFFER.
>> +Return nil on error. */)


Renamed entry point to libmagic-file-internal since its meant to be
of internal usage for a lisp wrapper, yet to be written. Should that be
a new file BTW?

> This doc string "needs work"(TM).  Please use the doc string of
> visited-file-name as an example.

I worked on this

>
>> +  (filename_or_buffer)
>> +     Lisp_Object filename_or_buffer;
>
> Using a `_' in an argument is un-Lisp'y (IMO).

Ok.

> You need to encode file names before you pass them to C APIs.  Use
> ENCODE_FILE to do that; see file-attributes for an example of how this
> is done.

Ok.

>> +  if (rvs == NULL) goto libmagic_error;
>> +  Lisp_Object file_mime = intern (rvs);
>
> You cannot declare variables in the middle of a block: Emacs does not
> require a C99 compiler yet and need to support C90 or even older
> compilers, which will reject this code.

I'm habing trouble remembering not to use c99. Is there some convenient
compiler flag to force lower versions? Fixed the errors I saw.


> Is file_encoding supposed to be a valid encoding, one of those for
> which Emacs has a coding-system?  If so, perhaps you should make sure
> you indeed return a valid coding-system or its alias, or otherwise
> tell in the doc string that it's not guaranteed to be valid (so that
> the caller should validate it before using).

I described a bit more in the doc string. Ok?



[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #2: filemagic3.patch --]
[-- Type: text/x-patch, Size: 5892 bytes --]

diff --git a/configure.in b/configure.in
index f4096db..49a3f15 100644
--- a/configure.in
+++ b/configure.in
@@ -137,6 +137,8 @@ OPTION_DEFAULT_ON([xft],[don't use XFT for anti aliased fonts])
 OPTION_DEFAULT_ON([libotf],[don't use libotf for OpenType font support])
 OPTION_DEFAULT_ON([m17n-flt],[don't use m17n-flt for text shaping])
 
+OPTION_DEFAULT_ON([libmagic],[don't compile with libmagic support])
+
 OPTION_DEFAULT_ON([toolkit-scroll-bars],[don't use Motif or Xaw3d scroll bars])
 OPTION_DEFAULT_ON([xaw3d],[don't use Xaw3d])
 OPTION_DEFAULT_ON([xim],[don't use X11 XIM])
@@ -2223,6 +2225,19 @@ if test x"$ac_cv_func_alloca_works" != xyes; then
    AC_MSG_ERROR( [a system implementation of alloca is required] )
 fi
 
+
+HAVE_LIBMAGIC=no
+if test "${with_libmagic}" != "no"; then
+  #libmagic support
+  AC_CHECK_HEADERS(magic.h, [  AC_CHECK_LIB(magic,magic_open,HAVE_LIBMAGIC=yes) ])
+fi
+
+if test "${HAVE_LIBMAGIC}" = "yes"; then
+  LIBMAGIC=-lmagic
+  AC_SUBST(LIBMAGIC)
+  AC_DEFINE(HAVE_LIBMAGIC, 1, [Define to 1 if using libmagic.])  
+fi
+
 # fmod, logb, and frexp are found in -lm on most systems.
 # On HPUX 9.01, -lm does not contain logb, so check for sqrt.
 AC_CHECK_LIB(m, sqrt)
@@ -2954,6 +2969,7 @@ echo "  Does Emacs use -lpng?                                   ${HAVE_PNG}"
 echo "  Does Emacs use -lrsvg-2?                                ${HAVE_RSVG}"
 echo "  Does Emacs use -lgpm?                                   ${HAVE_GPM}"
 echo "  Does Emacs use -ldbus?                                  ${HAVE_DBUS}"
+echo "  Does Emacs use -lmagic?                                 ${HAVE_LIBMAGIC}"
 
 echo "  Does Emacs use -lfreetype?                              ${HAVE_FREETYPE}"
 echo "  Does Emacs use -lm17n-flt?                              ${HAVE_M17N_FLT}"
diff --git a/src/Makefile.in b/src/Makefile.in
index 425cf98..33d1a14 100644
--- a/src/Makefile.in
+++ b/src/Makefile.in
@@ -420,6 +420,7 @@ LIBX= $(LIBXMENU) LD_SWITCH_X_SITE
 #endif /* not HAVE_LIBRESOLV */
 
 LIBSOUND= @LIBSOUND@
+LIBMAGIC= @LIBMAGIC@
 CFLAGS_SOUND= @CFLAGS_SOUND@
 
 RSVG_LIBS= @RSVG_LIBS@
@@ -878,7 +879,7 @@ SOME_MACHINE_LISP = ../lisp/mouse.elc \
    duplicated symbols.  If the standard libraries were compiled
    with GCC, we might need gnulib again after them.  */
 
-LIBES = $(LOADLIBES) $(LIBS) $(LIBX) $(LIBSOUND) $(RSVG_LIBS) $(DBUS_LIBS) \
+LIBES = $(LOADLIBES) $(LIBS) $(LIBX) $(LIBSOUND) $(LIBMAGIC) $(RSVG_LIBS) $(DBUS_LIBS) \
    LIBGPM LIBRESOLV LIBS_SYSTEM LIBS_MACHINE LIBS_TERMCAP \
    LIBS_DEBUG $(GETLOADAVG_LIBS) \
    @FREETYPE_LIBS@ @FONTCONFIG_LIBS@ @LIBOTF_LIBS@ @M17N_FLT_LIBS@ \
diff --git a/src/fileio.c b/src/fileio.c
index 3702d4c..cbb0461 100644
--- a/src/fileio.c
+++ b/src/fileio.c
@@ -205,6 +205,10 @@ Lisp_Object Vdirectory_sep_char;
 int write_region_inhibit_fsync;
 #endif
 
+#ifdef HAVE_LIBMAGIC
+#include <magic.h>
+#endif
+
 /* Non-zero means call move-file-to-trash in Fdelete_file or
    Fdelete_directory.  */
 int delete_by_moving_to_trash;
@@ -2997,6 +3001,77 @@ DEFUN ("unix-sync", Funix_sync, Sunix_sync, 0, 0, "",
 
 #endif /* HAVE_SYNC */
 
+#ifdef HAVE_LIBMAGIC
+DEFUN ("libmagic-file-internal", Flibmagic_file_internal, Slibmagic_file_internal, 1,1,0,
+       doc: /* Return (MIME-TYPE MIME-ENCODING DESCRIPTION) for
+FILENAME-OR-BUFFER using libmagic.  If FILENAME-OR-BUFFER is a file,
+return information about the file. If FILENAME-OR-BUFFER is a buffer,
+return information about the file of the buffer.  MIME-TYPE and
+MIME-ENCODING are the mime type and mime encoding as determined by
+libmagic.  DESCRIPTION is the human readable descripton offered by
+libmagic for the file.
+
+The default libmagic database is used, and the quality of information
+given depends on your version of that database. Often the mime type is
+less exact than the description.
+
+ */)
+  (filename_or_buffer)
+     Lisp_Object filename_or_buffer;
+{
+  CHECK_STRING_OR_BUFFER (filename_or_buffer);
+  magic_t cookie=NULL;
+  char* f = NULL;
+  const char* rvs;
+  Lisp_Object file_freetext;
+  Lisp_Object rv;
+  Lisp_Object file_mime;
+  Lisp_Object file_encoding;  
+
+  Lisp_Object filename, absname, encoded_absname;
+  struct gcpro gcpro1;
+  
+  GCPRO1 (f);
+
+  if (STRINGP (filename_or_buffer))
+    filename = filename_or_buffer;
+  if (BUFFERP (filename_or_buffer))
+    filename = XBUFFER (filename_or_buffer)->filename;
+  absname = Fexpand_file_name (filename, current_buffer->directory);
+  f = SDATA(ENCODE_FILE (absname));
+
+  cookie = magic_open (MAGIC_ERROR);
+  if (cookie == NULL) goto libmagic_error;  
+  magic_load (cookie, NULL); /* load default database */
+
+  magic_setflags (cookie, MAGIC_MIME_TYPE | MAGIC_ERROR);  
+  rvs = magic_file (cookie, f);
+  if (rvs == NULL) goto libmagic_error;
+  file_mime = intern (rvs);
+
+  magic_setflags (cookie, MAGIC_MIME_ENCODING | MAGIC_ERROR);
+  rvs=magic_file (cookie, f);
+  if (rvs == NULL) goto libmagic_error;
+  file_encoding = intern(rvs);  
+
+  magic_setflags (cookie, MAGIC_NONE | MAGIC_ERROR);
+  rvs=magic_file (cookie, f);
+  if (rvs == NULL) goto libmagic_error;
+
+  file_freetext = build_string (rvs);
+  rv = Fcons (file_mime, Fcons (file_encoding, Fcons (file_freetext, Qnil)));
+  
+  magic_close (cookie);
+  UNGCPRO;
+  return rv;
+ libmagic_error:
+  if (cookie != NULL) magic_close (cookie);  
+  report_file_error("Libmagic error",Qnil);
+  UNGCPRO;
+  return Qnil;
+}
+#endif
+
 DEFUN ("file-newer-than-file-p", Ffile_newer_than_file_p, Sfile_newer_than_file_p, 2, 2, 0,
        doc: /* Return t if file FILE1 is newer than file FILE2.
 If FILE1 does not exist, the answer is nil;
@@ -5781,6 +5856,9 @@ When non-nil, the function `move-file-to-trash' will be used by
 #ifdef HAVE_SYNC
   defsubr (&Sunix_sync);
 #endif
+#ifdef HAVE_LIBMAGIC
+    defsubr (&Slibmagic_file_internal);
+#endif
 }
 
 /* arch-tag: 64ba3fd7-f844-4fb2-ba4b-427eb928786c

[-- Attachment #3: Type: text/plain, Size: 19 bytes --]


-- 
Joakim Verona