[Faxpp-devel] SF.net SVN: faxpp: [23] trunk/faxpp

[<jp...@us...>]

Revision: 23
          http://faxpp.svn.sourceforge.net/faxpp/?rev=23&view=rev
Author:   jpcs
Date:     2007-08-20 15:46:46 -0700 (Mon, 20 Aug 2007)

Log Message:
-----------
Fixed a bug that was causing all strings to be copied.

Tweaked the UTF-8 tokenizer states so that Latin1 could also use them.

Fixed column counting, and line counting for "\r\n" at a buffer
boundary.

Modified Paths:
--------------
    trunk/faxpp/configure
    trunk/faxpp/configure.in
    trunk/faxpp/src/tokenizer_states.c
    trunk/faxpp/src/tokenizer_states.h
    trunk/faxpp/src/xml_tokenizer.c

Modified: trunk/faxpp/configure
===================================================================
--- trunk/faxpp/configure	2007-08-20 00:17:50 UTC (rev 22)
+++ trunk/faxpp/configure	2007-08-20 22:46:46 UTC (rev 23)
@@ -20600,7 +20600,97 @@
 
 
 
+{ echo "$as_me:$LINENO: checking for working memcmp" >&5
+echo $ECHO_N "checking for working memcmp... $ECHO_C" >&6; }
+if test "${ac_cv_func_memcmp_working+set}" = set; then
+  echo $ECHO_N "(cached) $ECHO_C" >&6
+else
+  if test "$cross_compiling" = yes; then
+  ac_cv_func_memcmp_working=no
+else
+  cat >conftest.$ac_ext <<_ACEOF
+/* confdefs.h.  */
+_ACEOF
+cat confdefs.h >>conftest.$ac_ext
+cat >>conftest.$ac_ext <<_ACEOF
+/* end confdefs.h.  */
+$ac_includes_default
+int
+main ()
+{
 
+  /* Some versions of memcmp are not 8-bit clean.  */
+  char c0 = '\100', c1 = '\200', c2 = '\201';
+  if (memcmp(&c0, &c2, 1) >= 0 || memcmp(&c1, &c2, 1) >= 0)
+    return 1;
+
+  /* The Next x86 OpenStep bug shows up only when comparing 16 bytes
+     or more and with at least one buffer not starting on a 4-byte boundary.
+     William Lewis provided this test program.   */
+  {
+    char foo[21];
+    char bar[21];
+    int i;
+    for (i = 0; i < 4; i++)
+      {
+	char *a = foo + i;
+	char *b = bar + i;
+	strcpy (a, "--------01111111");
+	strcpy (b, "--------10000000");
+	if (memcmp (a, b, 16) >= 0)
+	  return 1;
+      }
+    return 0;
+  }
+
+  ;
+  return 0;
+}
+_ACEOF
+rm -f conftest$ac_exeext
+if { (ac_try="$ac_link"
+case "(($ac_try" in
+  *\"* | *\`* | *\\*) ac_try_echo=\$ac_try;;
+  *) ac_try_echo=$ac_try;;
+esac
+eval "echo \"\$as_me:$LINENO: $ac_try_echo\"") >&5
+  (eval "$ac_link") 2>&5
+  ac_status=$?
+  echo "$as_me:$LINENO: \$? = $ac_status" >&5
+  (exit $ac_status); } && { ac_try='./conftest$ac_exeext'
+  { (case "(($ac_try" in
+  *\"* | *\`* | *\\*) ac_try_echo=\$ac_try;;
+  *) ac_try_echo=$ac_try;;
+esac
+eval "echo \"\$as_me:$LINENO: $ac_try_echo\"") >&5
+  (eval "$ac_try") 2>&5
+  ac_status=$?
+  echo "$as_me:$LINENO: \$? = $ac_status" >&5
+  (exit $ac_status); }; }; then
+  ac_cv_func_memcmp_working=yes
+else
+  echo "$as_me: program exited with status $ac_status" >&5
+echo "$as_me: failed program was:" >&5
+sed 's/^/| /' conftest.$ac_ext >&5
+
+( exit $ac_status )
+ac_cv_func_memcmp_working=no
+fi
+rm -f core *.core core.conftest.* gmon.out bb.out conftest$ac_exeext conftest.$ac_objext conftest.$ac_ext
+fi
+
+
+fi
+{ echo "$as_me:$LINENO: result: $ac_cv_func_memcmp_working" >&5
+echo "${ECHO_T}$ac_cv_func_memcmp_working" >&6; }
+test $ac_cv_func_memcmp_working = no && case " $LIBOBJS " in
+  *" memcmp.$ac_objext "* ) ;;
+  *) LIBOBJS="$LIBOBJS memcmp.$ac_objext"
+ ;;
+esac
+
+
+
 for ac_header in stdlib.h
 do
 as_ac_Header=`echo "ac_cv_header_$ac_header" | $as_tr_sh`

Modified: trunk/faxpp/configure.in
===================================================================
--- trunk/faxpp/configure.in	2007-08-20 00:17:50 UTC (rev 22)
+++ trunk/faxpp/configure.in	2007-08-20 22:46:46 UTC (rev 23)
@@ -62,6 +62,7 @@
 
 # Checks for library functions.
 AC_FUNC_MALLOC
+AC_FUNC_MEMCMP
 AC_FUNC_REALLOC
 AC_CHECK_FUNCS([gettimeofday memmove memset strerror])
 

Modified: trunk/faxpp/src/tokenizer_states.c
===================================================================
--- trunk/faxpp/src/tokenizer_states.c	2007-08-20 00:17:50 UTC (rev 22)
+++ trunk/faxpp/src/tokenizer_states.c	2007-08-20 22:46:46 UTC (rev 23)
@@ -655,7 +655,7 @@
   /* Check if it really was a one byte char */ \
   if(env->current_char >= 0x80) { \
     /* Decode properly */ \
-    env->char_len = FAXPP_utf8_decode(env->position, env->buffer_end, &env->current_char); \
+    env->char_len = (env)->decode(env->position, env->buffer_end, &env->current_char); \
     switch((env)->char_len) { \
     case TRANSCODE_PREMATURE_END_OF_BUFFER: \
       return PREMATURE_END_OF_BUFFER; \

Modified: trunk/faxpp/src/tokenizer_states.h
===================================================================
--- trunk/faxpp/src/tokenizer_states.h	2007-08-20 00:17:50 UTC (rev 22)
+++ trunk/faxpp/src/tokenizer_states.h	2007-08-20 22:46:46 UTC (rev 23)
@@ -280,12 +280,13 @@
     if(err != 0) return err; \
   } \
 \
+  (env)->column += 1; \
   (env)->position += (env)->char_len; \
 }
 
 #define token_start_position(env) \
 { \
-  if((env)->encode) { \
+  if((env)->do_encode) { \
     FAXPP_reset_buffer(&(env)->token_buffer); \
     (env)->token.value.ptr = (env)->token_buffer.cursor; \
   } else { \
@@ -353,25 +354,28 @@
 }
 
 #define LINE_ENDINGS \
-  case '\n': \
   case '\r': { \
     Char32 next_char; \
-    if((env)->current_char == '\r' && \
-       (env)->decode((env)->position + (env)->char_len, (env)->buffer_end, &next_char) \
-       != TRANSCODE_PREMATURE_END_OF_BUFFER && next_char == '\n') { \
-      (env)->column += 1; \
-    } else { \
-      (env)->line += 1; \
-      (env)->column = 0; \
+    if((env)->decode((env)->position + (env)->char_len, (env)->buffer_end, &next_char) \
+       == TRANSCODE_PREMATURE_END_OF_BUFFER) { \
+      if(!(env)->buffer_done) return PREMATURE_END_OF_BUFFER; \
+      goto LINE_ENDINGS_INC; \
     } \
-  }
+    else if(next_char != '\n') goto LINE_ENDINGS_INC; \
+    goto LINE_ENDINGS_END; \
+  } \
+  case '\n': \
+LINE_ENDINGS_INC: \
+    (env)->line += 1; \
+    (env)->column = (unsigned int)-1; \
+LINE_ENDINGS_END:
 
 /*
  * [3]     S    ::=    (#x20 | #x9 | #xD | #xA)+
  */
 #define WHITESPACE \
   LINE_ENDINGS \
-  case '\t':\
+  case '\t': \
   case ' '
 
 #endif

Modified: trunk/faxpp/src/xml_tokenizer.c
===================================================================
--- trunk/faxpp/src/xml_tokenizer.c	2007-08-20 00:17:50 UTC (rev 22)
+++ trunk/faxpp/src/xml_tokenizer.c	2007-08-20 22:46:46 UTC (rev 23)
@@ -275,6 +275,8 @@
 void
 FAXPP_set_tokenizer_decode(FAXPP_Tokenizer *tokenizer, FAXPP_DecodeFunction decode)
 {
+  tokenizer->do_encode = 1;
+
   if(decode == FAXPP_utf16_native_decode ||
 #ifdef WORDS_BIGENDIAN
      decode == FAXPP_utf16_be_decode
@@ -299,6 +301,13 @@
     tokenizer->start_element_name_state = utf8_start_element_name_state;
     tokenizer->element_content_state = utf8_element_content_state;
   }
+  else if(decode == FAXPP_iso_8859_1_decode) {
+    tokenizer->decode = FAXPP_iso_8859_1_decode;
+
+    // Latin1 can use the UTF-8 states, since the first 128 values are the same as UTF-8
+    tokenizer->start_element_name_state = utf8_start_element_name_state;
+    tokenizer->element_content_state = utf8_element_content_state;
+  }
   else if(decode == FAXPP_ucs4_native_decode ||
 #ifdef WORDS_BIGENDIAN
      decode == FAXPP_ucs4_be_decode


This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.