Removed option for SUPPORT_ASIAN_ENCODINGS, and regen'd strings.

CMakeLists.txt

@@ -228,7 +228,6 @@ endif ()
 # Macro Values
 #   These additional macros are set in Tidy's source code.
 #------------------------------------------------------------------------
-add_definitions ( -DSUPPORT_ASIAN_ENCODINGS=1 )
 add_definitions ( -DSUPPORT_ACCESSIBILITY_CHECKS=1 )
 add_definitions ( -DLIBTIDY_VERSION="${LIBTIDY_VERSION}" )
 add_definitions ( -DRELEASE_DATE="${tidy_YEAR}/${tidy_MONTH}/${tidy_DAY}" )

console/tidy.c

@@ -379,10 +379,8 @@ static const CmdOptDesc cmdopt_defs[] =  {
     { CmdOptCharEnc,   "-utf16le",               TC_OPT_UTF16LE,  0,             NULL },
     { CmdOptCharEnc,   "-utf16be",               TC_OPT_UTF16BE,  0,             NULL },
     { CmdOptCharEnc,   "-utf16",                 TC_OPT_UTF16,    0,             NULL },
-#if SUPPORT_ASIAN_ENCODINGS /* #431953 - RJ */
     { CmdOptCharEnc,   "-big5",                  TC_OPT_BIG5,     0,             NULL },
     { CmdOptCharEnc,   "-shiftjis",              TC_OPT_SHIFTJIS, 0,             NULL },
-#endif
     { CmdOptMisc,      "-version",               TC_OPT_VERSION,  0,             NULL,  "-v" },
     { CmdOptMisc,      "-help",                  TC_OPT_HELP,     0,             NULL,  "-h", "-?" },
     { CmdOptMisc,      "-help-config",           TC_OPT_HELPCFG,  0,             NULL },
@@ -2145,11 +2143,8 @@ int main( int argc, char** argv )
                      strcasecmp(arg, "utf16le") == 0  ||
                      strcasecmp(arg, "utf16be") == 0  ||
                      strcasecmp(arg, "utf16") == 0    ||
-                     
-#if SUPPORT_ASIAN_ENCODINGS
                      strcasecmp(arg, "shiftjis") == 0 ||
                      strcasecmp(arg, "big5") == 0     ||
-#endif
                      strcasecmp(arg, "mac") == 0      ||
                      strcasecmp(arg, "win1252") == 0  ||
                      strcasecmp(arg, "ibm858") == 0 )

include/tidyenum.h

@@ -603,11 +603,7 @@ typedef enum
     TidyMergeEmphasis,           /**< Merge nested B and I elements */
     TidyMergeSpans,              /**< Merge multiple SPANs */
     TidyMetaCharset,             /**< Adds/checks/fixes meta charset in the head, based on document type */
-#if SUPPORT_ASIAN_ENCODINGS
     TidyNCR,                     /**< Allow numeric character references */
-#else
-    TidyNCRNotUsed,              /**< This option is not compiled in */
-#endif
     TidyNewline,                 /**< Output line ending (default to platform) */
     TidyNumEntities,             /**< Use numeric entities */
     TidyOmitOptionalTags,        /**< Suppress optional start tags and end tags */
@@ -618,11 +614,7 @@ typedef enum
     TidyPreserveEntities,        /**< Preserve entities */
     TidyPreTags,                 /**< Declared pre tags */
     TidyPriorityAttributes,      /**< Attributes to place first in an element */
-#if SUPPORT_ASIAN_ENCODINGS
     TidyPunctWrap,               /**< consider punctuation and breaking spaces for wrapping */
-#else
-    TidyPunctWrapNotUsed,        /**< This option is not compiled in */
-#endif
     TidyQuiet,                   /**< No 'Parsing X', guessed DTD or summary */
     TidyQuoteAmpersand,          /**< Output naked ampersand as &amp; */
     TidyQuoteMarks,              /**< Output " marks as &quot; */
@@ -755,11 +747,8 @@ typedef enum
     TidyEncUtf16le,
     TidyEncUtf16be,
     TidyEncUtf16,
-
-#if SUPPORT_ASIAN_ENCODINGS
     TidyEncBig5,
     TidyEncShiftjis
-#endif
 } TidyEncodingOptions;
 
 

include/tidyplatform.h

@@ -77,11 +77,6 @@ extern "C" {
  * Optional Tidy features support
  *===========================================================================*/
 
-/* Enable/disable support for Big5 and Shift_JIS character encodings */
-#ifndef SUPPORT_ASIAN_ENCODINGS
-#  define SUPPORT_ASIAN_ENCODINGS 1
-#endif
-
 /* Enable/disable support for additional accessibility checks */
 #ifndef SUPPORT_ACCESSIBILITY_CHECKS
 #  define SUPPORT_ACCESSIBILITY_CHECKS 1

localize/translations/language_en_gb.po

@@ -5,7 +5,7 @@ msgstr ""
 "Plural-Forms: nplurals=2; plural=n != 1;\n"
 "X-Generator: HTML Tidy poconvert.rb\n"
 "Project-Id-Version: \n"
-"PO-Revision-Date: 2017-10-03 12:22:47\n"
+"PO-Revision-Date: 2017-10-03 12:37:01\n"
 "Last-Translator: jderry\n"
 "Language-Team: \n"
 

localize/translations/language_es.po

@@ -5,7 +5,7 @@ msgstr ""
 "Plural-Forms: nplurals=2; plural=n != 1;\n"
 "X-Generator: HTML Tidy poconvert.rb\n"
 "Project-Id-Version: \n"
-"PO-Revision-Date: 2017-10-03 12:22:47\n"
+"PO-Revision-Date: 2017-10-03 12:37:01\n"
 "Last-Translator: jderry\n"
 "Language-Team: \n"
 

localize/translations/language_es_mx.po

@@ -5,7 +5,7 @@ msgstr ""
 "Plural-Forms: nplurals=2; plural=n != 1;\n"
 "X-Generator: HTML Tidy poconvert.rb\n"
 "Project-Id-Version: \n"
-"PO-Revision-Date: 2017-10-03 12:22:47\n"
+"PO-Revision-Date: 2017-10-03 12:37:01\n"
 "Last-Translator: jderry\n"
 "Language-Team: \n"
 

localize/translations/language_fr.po

@@ -5,7 +5,7 @@ msgstr ""
 "Plural-Forms: nplurals=2; plural=(n > 1);\n"
 "X-Generator: HTML Tidy poconvert.rb\n"
 "Project-Id-Version: \n"
-"PO-Revision-Date: 2017-10-03 12:22:47\n"
+"PO-Revision-Date: 2017-10-03 12:37:01\n"
 "Last-Translator: jderry\n"
 "Language-Team: \n"
 

localize/translations/language_pt_br.po

@@ -5,7 +5,7 @@ msgstr ""
 "Plural-Forms: nplurals=2; plural=(n > 1);\n"
 "X-Generator: HTML Tidy poconvert.rb\n"
 "Project-Id-Version: \n"
-"PO-Revision-Date: 2017-10-03 12:22:47\n"
+"PO-Revision-Date: 2017-10-03 12:37:01\n"
 "Last-Translator: jderry\n"
 "Language-Team: \n"
 

localize/translations/language_zh_cn.po

@@ -5,7 +5,7 @@ msgstr ""
 "Plural-Forms: nplurals=1; plural=0;\n"
 "X-Generator: HTML Tidy poconvert.rb\n"
 "Project-Id-Version: \n"
-"PO-Revision-Date: 2017-10-03 12:22:47\n"
+"PO-Revision-Date: 2017-10-03 12:37:01\n"
 "Last-Translator: jderry\n"
 "Language-Team: \n"
 

localize/translations/tidy.pot

@@ -5,7 +5,7 @@ msgstr ""
 "Plural-Forms: nplurals=2; plural=n != 1;\n"
 "X-Generator: HTML Tidy poconvert.rb\n"
 "Project-Id-Version: \n"
-"POT-Creation-Date: 2017-10-03 12:22:47\n"
+"POT-Creation-Date: 2017-10-03 12:37:01\n"
 "Last-Translator: jderry\n"
 "Language-Team: \n"
 

src/config.c

@@ -94,12 +94,8 @@ static PickListItems charEncPicks = {
     { "utf16le",  TidyEncUtf16le,  { "utf16le",  NULL } },
     { "utf16be",  TidyEncUtf16be,  { "utf16be",  NULL } },
     { "utf16",    TidyEncUtf16,    { "utf16",    NULL } },
-
-#if SUPPORT_ASIAN_ENCODINGS
     { "big5",     TidyEncBig5,     { "big5",     NULL } },
     { "shiftjis", TidyEncShiftjis, { "shiftjis", NULL } },
-#endif
-
     { NULL }
 };
 
@@ -263,9 +259,7 @@ static const TidyOptionImpl option_defs[] =
     { TidyMergeEmphasis,           MU, "merge-emphasis",              BL, yes,             ParsePickList,     &boolPicks          },
     { TidyMergeSpans,              MU, "merge-spans",                 IN, TidyAutoState,   ParsePickList,     &autoBoolPicks      },
     { TidyMetaCharset,             MS, "add-meta-charset",            BL, no,              ParsePickList,     &boolPicks          }, /* 20161004 - Issue #456 */
-#if SUPPORT_ASIAN_ENCODINGS
     { TidyNCR,                     MU, "ncr",                         BL, yes,             ParsePickList,     &boolPicks          },
-#endif
     { TidyNewline,                 CE, "newline",                     IN, DLF,             ParsePickList,     &newlinePicks       },
     { TidyNumEntities,             MU, "numeric-entities",            BL, no,              ParsePickList,     &boolPicks          },
     { TidyOmitOptionalTags,        MU, "omit-optional-tags",          BL, no,              ParsePickList,     &boolPicks          },
@@ -276,9 +270,7 @@ static const TidyOptionImpl option_defs[] =
     { TidyPreserveEntities,        MU, "preserve-entities",           BL, no,              ParsePickList,     &boolPicks          },
     { TidyPreTags,                 MU, "new-pre-tags",                ST, 0,               ParseTagNames,     NULL                },
     { TidyPriorityAttributes,      MU, "priority-attributes",         ST, 0,               ParseList,         NULL                },
-#if SUPPORT_ASIAN_ENCODINGS
     { TidyPunctWrap,               PP, "punctuation-wrap",            BL, no,              ParsePickList,     &boolPicks          },
-#endif
     { TidyQuiet,                   MS, "quiet",                       BL, no,              ParsePickList,     &boolPicks          },
     { TidyQuoteAmpersand,          MU, "quote-ampersand",             BL, yes,             ParsePickList,     &boolPicks          },
     { TidyQuoteMarks,              MU, "quote-marks",                 BL, no,              ParsePickList,     &boolPicks          },
@@ -995,11 +987,8 @@ Bool  TY_(AdjustCharEncoding)( TidyDocImpl* doc, int encoding )
     case UTF16LE:
     case UTF16BE:
     case UTF16:
-
-#if SUPPORT_ASIAN_ENCODINGS
     case SHIFTJIS:
     case BIG5:
-#endif
         inenc = outenc = encoding;
         break;
     }

src/language_en.h

@@ -835,7 +835,6 @@ static languageDefinition language_en = { whichPluralForm_en, {
         "<br/>"
         "The algorithm is identical to the one used by <code>merge-divs</code>. "
     },
-#if SUPPORT_ASIAN_ENCODINGS
     {/* Important notes for translators:
         - Use only <code></code>, <var></var>, <em></em>, <strong></strong>, and
           <br/>.
@@ -847,7 +846,6 @@ static languageDefinition language_en = { whichPluralForm_en, {
       TidyNCR,                      0,
         "This option specifies if Tidy should allow numeric character references. "
     },
-#endif
     {/* Important notes for translators:
       - Use only <code></code>, <var></var>, <em></em>, <strong></strong>, and
       <br/>.
@@ -1024,7 +1022,6 @@ static languageDefinition language_en = { whichPluralForm_en, {
         "<br/>"
         "This option takes a space or comma separated list of attribute names. "
     },
-#if SUPPORT_ASIAN_ENCODINGS
     {/* Important notes for translators:
       - Use only <code></code>, <var></var>, <em></em>, <strong></strong>, and
       <br/>.
@@ -1037,7 +1034,6 @@ static languageDefinition language_en = { whichPluralForm_en, {
         "This option specifies if Tidy should line wrap after some Unicode or "
         "Chinese punctuation characters. "
     },
-#endif
     {/* Important notes for translators:
       - Use only <code></code>, <var></var>, <em></em>, <strong></strong>, and
       <br/>.

src/language_en_gb.h

@@ -1,4 +1,4 @@
-#ifndef language_en_gb_h
+#ifndef language_en_gb_h
 #define language_en_gb_h
 /*
  * language_en_gb.h
@@ -28,7 +28,7 @@
  *
  * Orginating PO file metadata:
  *   PO_LAST_TRANSLATOR=jderry
- *   PO_REVISION_DATE=2017-08-28 10:04:30
+ *   PO_REVISION_DATE=2017-10-03 12:37:01
  */
 
 #ifdef _MSC_VER

src/language_es.h

@@ -1,4 +1,4 @@
-#ifndef language_es_h
+#ifndef language_es_h
 #define language_es_h
 /*
  * language_es.h
@@ -28,7 +28,7 @@
  *
  * Orginating PO file metadata:
  *   PO_LAST_TRANSLATOR=jderry
- *   PO_REVISION_DATE=2017-05-13 21:04:45
+ *   PO_REVISION_DATE=2017-10-03 12:37:01
  */
 
 #ifdef _MSC_VER
@@ -68,11 +68,7 @@ static languageDefinition language_es = { whichPluralForm_es, {
         "code>). Si se establece en <code>yes</code>, entonces etiquetas existentes serán reemplazados "
         "con CSS <code>&lt;style&gt;</code> y estructural markup según corresponda. "
     },
-
-#if SUPPORT_ASIAN_ENCODINGS
     { TidyNCR,                0, "Esta opción especifica si Tidy debe permitir referencias de caracteres numéricos. "   },
-#endif /* SUPPORT_ASIAN_ENCODINGS */
-
     { TEXT_GENERAL_INFO_PLEA, 0,        
         "\n"
         "¿Le gustaría ver Tidy en un español correcto? Por favor considere \n"

src/language_es_mx.h

@@ -1,4 +1,4 @@
-#ifndef language_es_mx_h
+#ifndef language_es_mx_h
 #define language_es_mx_h
 /*
  * language_es_mx.h
@@ -28,7 +28,7 @@
  *
  * Orginating PO file metadata:
  *   PO_LAST_TRANSLATOR=jderry
- *   PO_REVISION_DATE=2017-05-13 21:04:45
+ *   PO_REVISION_DATE=2017-10-03 12:37:01
  */
 
 #ifdef _MSC_VER

src/language_fr.h

@@ -28,7 +28,7 @@
  *
  * Orginating PO file metadata:
  *   PO_LAST_TRANSLATOR=jderry
- *   PO_REVISION_DATE=2017-10-03 12:22:47
+ *   PO_REVISION_DATE=2017-10-03 12:37:01
  */
 
 #ifdef _MSC_VER
@@ -319,11 +319,7 @@ static languageDefinition language_fr = { whichPluralForm_fr, {
         "imbriqués, comme suit : <code>&lt;span&gt;&lt;span&gt;...&lt;/span&gt;&lt;/span&gt;</code>. <br/"
         ">L'algorithme est le même que celui de <code>merge-divs</code>. "
     },
-
-#if SUPPORT_ASIAN_ENCODINGS
     { TidyNCR,                                       0, "Cette option précise si Tidy doit autoriser les références numériques de caractères. "                  },
-#endif /* SUPPORT_ASIAN_ENCODINGS */
-
     { TidyNewline,                                   0,        
         "La valeur par défaut est appropriée à la plateforme d'exécution de Tidy. <br/>Généralement "
         "<var>CRLF</var> sur PC-DOS, Windows et OS/2; <var>CR</var> sur Classic Mac OS; et <var>LF</var> "
@@ -381,14 +377,10 @@ static languageDefinition language_fr = { whichPluralForm_fr, {
         "inconnues. <br/>Notez que vous ne pouvez encore ajouter de nouveaux éléments CDATA. <br/>Cette "
         "option est ignorée avec le mode XML. "
     },
-
-#if SUPPORT_ASIAN_ENCODINGS
     { TidyPunctWrap,                                 0,        
         "Cette option précise si Tidy doit passer à la ligne après certains caractères de ponctuation "
         "Unicode ou chinois."
     },
-#endif /* SUPPORT_ASIAN_ENCODINGS */
-
     { TidyQuiet,                                     0,        
         "Cette option précise si Tidy doit afficher le résumé du nombre des erreurs et avertissements, ou "
         "les messages de bienvenue et d'information."

src/language_pt_br.h

@@ -1,4 +1,4 @@
-#ifndef language_pt_br_h
+#ifndef language_pt_br_h
 #define language_pt_br_h
 /*
  * language_pt_br.h
@@ -27,8 +27,8 @@
  * Template Created by Jim Derry on 01/14/2016.
  *
  * Orginating PO file metadata:
- *   PO_LAST_TRANSLATOR=Rafael Fontenelle <rafaelff@gnome.org>
+ *   PO_LAST_TRANSLATOR=jderry
- *   PO_REVISION_DATE=2017-09-21 00:07-0200
+ *   PO_REVISION_DATE=2017-10-03 12:37:01
  */
 
 #ifdef _MSC_VER
@@ -361,14 +361,10 @@ static languageDefinition language_pt_br = { whichPluralForm_pt_br, {
         "<code>&lt;span&gt;&lt;span&gt;...&lt;/span&gt;&lt;/span&gt;</code>. <br/>O "
         "algoritmo é idêntico àquele usado por <code>merge-divs</code>. "
     },
-
-#if SUPPORT_ASIAN_ENCODINGS
     { TidyNCR,                                       0,        
         "Esta opção especifica se o Tidy deve permitir referências de caracteres "
         "numéricos. "
     },
-#endif /* SUPPORT_ASIAN_ENCODINGS */
-
     { TidyNewline,                                   0,        
         "O padrão é apropriado para a plataforma atual. <br/>Geralmente, CRLF no PC-"
         "DOS, Windows e OS/2; CR no Mac OS Clássico; e LF nos demais (Linux, Mac OS X "
@@ -436,14 +432,10 @@ static languageDefinition language_pt_br = { whichPluralForm_pt_br, {
         "que você ainda não pode adicionar novos elementos CDATA. <br/>Esta opção é "
         "ignorada no modo XML. "
     },
-
-#if SUPPORT_ASIAN_ENCODINGS
     { TidyPunctWrap,                                 0,        
         "Essa opção especifica se o Tidy deve quebrar linha após alguns Unicode ou "
         "caracteres de pontuação chineses. "
     },
-#endif /* SUPPORT_ASIAN_ENCODINGS */
-
     { TidyQuiet,                                     0,        
         "Essa opção especifica se o Tidy deve emitir o resumo dos números de erros e "
         "avisos, ou as mensagens de boas-vidas ou informacionais. "

src/language_zh_cn.h

@@ -28,7 +28,7 @@
  *
  * Orginating PO file metadata:
  *   PO_LAST_TRANSLATOR=jderry
- *   PO_REVISION_DATE=2017-10-03 12:22:47
+ *   PO_REVISION_DATE=2017-10-03 12:37:01
  */
 
 #ifdef _MSC_VER

src/lexer.c

@@ -1215,15 +1215,14 @@ static void ParseEntity( TidyDocImpl* doc, GetTokenMode mode )
 
         if (charRead == 1 && c == '#')
         {
-#if SUPPORT_ASIAN_ENCODINGS
+            if ( !cfgBool(doc, TidyNCR) ||
-            if ( !cfgBool(doc, TidyNCR) || 
                  cfg(doc, TidyInCharEncoding) == BIG5 ||
                  cfg(doc, TidyInCharEncoding) == SHIFTJIS )
             {
                 TY_(UngetChar)('#', doc->docIn);
                 return;
             }
-#endif
+
             TY_(AddCharToLexer)( lexer, c );
             entState = ENT_numdec;
             continue;

src/pprint.c

@@ -69,7 +69,6 @@ void TY_(PPrintSpaces)(void)
     indent_char = ' ';
 }
 
-#if SUPPORT_ASIAN_ENCODINGS
 /* #431953 - start RJ Wraplen adjusted for smooth international ride */
 
 typedef enum
@@ -287,7 +286,6 @@ static WrapPoint Big5WrapPoint(tchar c)
     return NoWrapPoint;
 }
 
-#endif /* SUPPORT_ASIAN_ENCODINGS */
 
 static void InitIndent( TidyIndent* ind )
 {
@@ -888,8 +886,6 @@ static void PPrintChar( TidyDocImpl* doc, uint c, uint mode )
         }
     }
 
-#if SUPPORT_ASIAN_ENCODINGS
-
     /* #431953 - start RJ */
     /* Handle encoding-specific issues */
     switch ( outenc )
@@ -930,22 +926,6 @@ static void PPrintChar( TidyDocImpl* doc, uint c, uint mode )
         AddChar( pprint, c );
         return;
     }
-    /* #431953 - end RJ */
-
-#else /* SUPPORT_ASIAN_ENCODINGS */
-
-    /* otherwise ISO 2022 characters are passed raw */
-    if (
-#ifndef NO_NATIVE_ISO2022_SUPPORT
-        outenc == ISO2022 ||
-#endif
-        outenc == RAW )
-    {
-        AddChar( pprint, c );
-        return;
-    }
-
-#endif /* SUPPORT_ASIAN_ENCODINGS */
 
     /* don't map latin-1 chars to entities */
     if ( outenc == LATIN1 )

src/pprint.h

@@ -60,7 +60,7 @@ typedef struct _TidyPrintImpl
 } TidyPrintImpl;
 
 
-#if 0 && SUPPORT_ASIAN_ENCODINGS
+#if 0
 /* #431953 - start RJ Wraplen adjusted for smooth international ride */
 uint CWrapLen( TidyDocImpl* doc, uint ind );
 #endif

src/streamio.c

@@ -395,11 +395,8 @@ uint TY_(ReadChar)( StreamIn *in )
          || in->encoding == ISO2022
 #endif
          || in->encoding == UTF8
-
-#if SUPPORT_ASIAN_ENCODINGS
          || in->encoding == SHIFTJIS /* #431953 - RJ */
          || in->encoding == BIG5     /* #431953 - RJ */
-#endif
            )
         {
             in->curcol++;
@@ -710,8 +707,6 @@ void TY_(WriteChar)( uint c, StreamOut* out )
             }
         }
     }
-
-#if SUPPORT_ASIAN_ENCODINGS
     else if (out->encoding == BIG5 || out->encoding == SHIFTJIS)
     {
         if (c < 128)
@@ -722,8 +717,6 @@ void TY_(WriteChar)( uint c, StreamOut* out )
             ch = c & 0xFF; PutByte(ch, out); 
         }
     }
-#endif
-
     else
         PutByte( c, out );
 }
@@ -1243,7 +1236,6 @@ static uint ReadCharFromStream( StreamIn* in )
         return n;
     }
     
-#if SUPPORT_ASIAN_ENCODINGS
     /*
        This section is suitable for any "multibyte" variable-width 
        character encoding in which a one-byte code is less than
@@ -1273,7 +1265,6 @@ static uint ReadCharFromStream( StreamIn* in )
             return n;
         }
     }
-#endif
 
 #ifdef TIDY_WIN32_MLANG_SUPPORT
     else if (in->encoding > WIN32MLANG)
@@ -1322,10 +1313,8 @@ static struct _enc2iana
   { UTF16LE,  "utf-16",       "utf16le" },
   { UTF16BE,  "utf-16",       "utf16be" },
   { UTF16,    "utf-16",       "utf16"   },
-#if SUPPORT_ASIAN_ENCODINGS
   { BIG5,     "big5",         "big5"    },
   { SHIFTJIS, "shift_jis",    "shiftjis"},
-#endif
 #ifndef NO_NATIVE_ISO2022_SUPPORT
   { ISO2022,  NULL,           "iso2022" },
 #endif

src/streamio.h

@@ -157,18 +157,8 @@ int TY_(GetCharEncodingFromOptName)(ctmbstr charenc);
 #define UTF16LE     9
 #define UTF16BE     10
 #define UTF16       11
-
-/* Note that Big5 and SHIFTJIS are not converted to ISO 10646 codepoints
-** (i.e., to Unicode) before being recoded into UTF-8. This may be
-** confusing: usually UTF-8 implies ISO10646 codepoints.
-*/
-#if SUPPORT_ASIAN_ENCODINGS
 #define BIG5        12
 #define SHIFTJIS    13
-#else
-#define BIG5        9
-#define SHIFTJIS    10
-#endif
 
 #ifdef TIDY_WIN32_MLANG_SUPPORT
 /* hack: windows code page numbers start at 37 */