Added parameter to conversion from UTF-8 to locale, to return the number

of conversion failures.

diff --git a/doc/usage.html b/doc/usage.html
index 00003be0d0b4484dd762b1c4b4e7c0b174d1065f..5d36b89c44c46d6dcac2f5dde82ecaca5586b8be 100644 (file)
--- a/doc/usage.html
+++ b/doc/usage.html
@@ -452,7 +452,43 @@ All strings passed by the GEDCOM parser to the application are in UTF-8 encoding
 be able to display it.<br>
                     <br>
 The most common case is that the output character set is controlled by the <code>locale</code> mechanism (i.e. via the <code>LANG</code>, <code>LC_ALL</code> or <code>LC_CTYPE</code> environment variables), which also controls the <code>gettext</code>
- mechanism in the application. &nbsp;For this, the following steps need to
+ mechanism in the application. &nbsp;<br>
+                    <br>
+                    <br>
+
+
+                                                                        
+              
+                    The source distribution of <code>gedcom-parse</code> contains an example implementation (<code>utf8-locale.c</code> and <code>utf8-locale.h</code>
+ in the top directory).&nbsp; &nbsp;Feel free to use it in
+your source code (it is not part of the library, and it isn't installed anywhere,
+so you need to take over the source and header file in your application).
+&nbsp;<br>
+                    <br>
+
+Its interface is:<br>
+                    <blockquote><pre><code>char *<b>convert_utf8_to_locale</b> (char *input, int *conv_failures);<br>char *<b>convert_locale_to_utf8</b> (char *input);<br></code></pre></blockquote>
+
+Both functions return a pointer to a static buffer that is overwritten on
+each call. &nbsp;To function properly, the application must first set the
+locale using the <code>setlocale</code> function (the second step detailed below).
+&nbsp;All other steps given below, including setting up and closing down the conversion
+handles, are transparantly handled by the two functions. &nbsp;<br>
+                      <br>
+If you pass a pointer to an integer to the first function, it will be set
+to the number of conversion failures, i.e. characters that couldn't be converted;
+you can also just pass <code>NULL</code> if you are not interested (note that usually, the interesting information is just whether there <i>were</i>
+ conversion failures or not, which is then given by the integer being bigger
+than zero or not). &nbsp;The second function doesn't need this, because any
+locale can be converted to UTF-8.<br>
+                      <br>
+
+You can change the "?" that is output for characters that can't be converted
+to any string you want, using the following function before the conversion
+calls:<br>
+                      <blockquote><pre><code>void <b>convert_set_unknown</b> (const char *unknown);</code></pre></blockquote>
+                        <br>
+If you want to have your own functions for it instead of this example implementation, the following steps need to
 be taken by the application (more detailed info can be found in the info
 file of the GNU libc library in the "Generic Charset Conversion" section
 under "Character Set Handling" or online <a href="http://www.gnu.org/manual/glibc-2.2.3/html_chapter/libc_6.html#SEC99">here</a>):<br>
@@ -527,33 +563,10 @@ characters can't be represented in the target character set). &nbsp;The <code>ic
                                           <pre><code>iconv_close(iconv_handle);<br></code></pre>
                                           </blockquote>
                                           </blockquote>
-
-                                                                        
-              
-                    The source distribution of <code>gedcom-parse</code> contains an example implementation (<code>utf8-locale.c</code> and <code>utf8-locale.h</code>
- in the top directory) that grows the output buffer dynamically and outputs
-"?" for characters that can't be converted. &nbsp;Feel free to use it in
-your source code (it is not part of the library, and it isn't installed anywhere,
-so you need to take over the source and header file in your application).
-&nbsp;<br>
-                                          <br>
-Its interface is:<br>
-                                          <blockquote>
-                                            <pre><code>char *<b>convert_utf8_to_locale</b> (char *input);<br>char *<b>convert_locale_to_utf8</b> (char *input);<br></code></pre>
-                                            </blockquote>
-Both functions return a pointer to a static buffer that is overwritten on
-each call. &nbsp;To function properly, the application must first set the
-locale using the <code>setlocale</code> function (the second step above).
-&nbsp;All other steps, including setting up and closing down the conversion
-handles, are transparantly handled by the two functions.<br>
-                                            <br>
-You can change the "?" that is output for characters that can't be converted
-to any string you want, using the following function before the conversion
-calls:<br>
-                                            <blockquote>
-                                              <pre><code>void <b>convert_set_unknown</b> (const char *unknown);</code></pre>
-                                              </blockquote>
-                                              <hr width="100%" size="2">                           
+                                              The example implementation mentioned above grows the output buffer dynamically and outputs
+"?" for characters that can't be converted.<br>
+                                              <br>
+<hr width="100%" size="2">                           
                                    
                     <pre><font size="-1">$Id$<br>$Name$</font><br></pre>
                                                                  

diff --git a/standalone.c b/standalone.c
index 9c8dc15d2130188daf58d18bc945fa2b93036af0..a4d44774438f212f8475815a2c9cc2ff9df4e4b7 100644 (file)
--- a/standalone.c
+++ b/standalone.c
@@ -172,10 +172,11 @@ void default_cb(Gedcom_ctxt ctxt, int level, char *tag, char *raw_value,
                int tag_value)
 {
   char   *converted = NULL;
+  int    conv_fails;
   if (raw_value)
-    converted = convert_utf8_to_locale(raw_value);
-  output(0, "== %d %s (%d) %s (ctxt is %d)\n",
-        level, tag, tag_value, converted, (int)ctxt);
+    converted = convert_utf8_to_locale(raw_value, &conv_fails);
+  output(0, "== %d %s (%d) %s (ctxt is %d, conversion failures: %d)\n",
+        level, tag, tag_value, converted, (int)ctxt, conv_fails);
 }
 
 void subscribe_callbacks()

diff --git a/utf8-locale.c b/utf8-locale.c
index c89aa5c80417d182c49a53016c74b7c8f13bb29f..9946cc9c7e3ac38472e41820113c0b55fcca5a67 100644 (file)
--- a/utf8-locale.c
+++ b/utf8-locale.c
@@ -60,7 +60,7 @@ int open_conversion_contexts()
   }
 }
 
-char* convert_utf8_to_locale(char* input)
+char* convert_utf8_to_locale(char* input, int *conv_fails)
 {
   size_t insize  = strlen(input);
   size_t outsize;
@@ -73,6 +73,7 @@ char* convert_utf8_to_locale(char* input)
   assert(utf8_to_locale != (iconv_t) -1);
   /* make sure we start from an empty state */
   iconv(utf8_to_locale, NULL, NULL, NULL, NULL);
+  if (conv_fails != NULL) *conv_fails = 0;
   /* set up output buffer (empty it) */
   outptr  = outbuffer;
   outsize = outbufsize;
@@ -92,6 +93,7 @@ char* convert_utf8_to_locale(char* input)
     else if (errno == EILSEQ) {
       /* skip over character */
       const char* unkn_ptr = the_unknown;
+      if (conv_fails != NULL) (*conv_fails)++;
       if ((*inptr & 0x80) == 0) {
        /* an ASCII character, just skip one (this case is very improbable) */
        inptr++; insize--;

diff --git a/utf8-locale.h b/utf8-locale.h
index dec20efc8f3da4cffbeef3a0b37a7389f82e0d67..ffe974ba9b2edde400fad28a2fcc7a445279fd5d 100644 (file)
--- a/utf8-locale.h
+++ b/utf8-locale.h
@@ -17,7 +17,7 @@
 __BEGIN_DECLS
 
 void  convert_set_unknown(const char* unknown);
-char* convert_utf8_to_locale(char* input);
+char* convert_utf8_to_locale(char* input, int *conv_fails);
 char* convert_locale_to_utf8(char* input);
 
 __END_DECLS