Part 1 - Add basic infra for 'add-meta-charset' option

include/tidyenum.h

@@ -172,6 +172,7 @@ typedef enum
   TidySkipNested,          /**< Skip nested tags in script and style CDATA */
   TidyStrictTagsAttr,      /**< Ensure tags and attributes match output HTML version */
   TidyEscapeScripts,       /**< Escape items that look like closing tags in script tags */
+  TidyMetaCharset,         /**< Adds/checks/fixes meta charset in the head, based on document type */
   N_TIDY_OPTIONS           /**< Must be last */
 } TidyOptionId;
 

src/config.c

@@ -324,6 +324,7 @@ static const TidyOptionImpl option_defs[] =
   { TidySkipNested,              MU, "skip-nested",                 BL, yes,             ParseBool,         boolPicks       }, /* 1642186 - Issue #65 */
   { TidyStrictTagsAttr,          MU, "strict-tags-attributes",      BL, no,              ParseBool,         boolPicks       }, /* 20160209 - Issue #350 */
   { TidyEscapeScripts,           PP, "escape-scripts",              BL, yes,             ParseBool,         boolPicks       }, /* 20160227 - Issue #348 */
+  { TidyMetaCharset,             MS, "add-meta-charset",            BL, yes,             ParseBool,         boolPicks       }, /* 20161004 - Issue #456 */
   { N_TIDY_OPTIONS,              XX, NULL,                          XY, 0,               NULL,              NULL            }
 };
 

src/language_en.h

@@ -2080,6 +2080,18 @@ static languageDefinition language_en = { whichPluralForm_en, {
         "This option causes items that look like closing tags, like <code>&lt;/g</code> to be escaped "
         "to <code>&lt;\\/g</code>. Set this option to 'no' if you do not want this."
     },
+    {/* Important notes for translators:
+        - Use only <code></code>, <var></var>, <em></em>, <strong></strong>, and
+          <br/>.
+        - Entities, tags, attributes, etc., should be enclosed in <code></code>.
+        - Option values should be enclosed in <var></var>.
+        - It's very important that <br/> be self-closing!
+        - The strings "Tidy" and "HTML Tidy" are the program name and must not
+          be translated. */
+      TidyMetaCharset,             0,
+        "This option adds a meta element and sets the charset attribute to the encoding of the document."
+        "Set this option to 'yes' if you want this."
+    },
 
     /********************************************************
      ** Console Application

src/lexer.c

@@ -1674,6 +1674,16 @@ Node *TY_(FindBody)( TidyDocImpl* doc )
     return node;
 }
 
+/* Check meta charset*/
+Bool TY_(TidyMetaCharset)( TidyDocImpl* doc )
+{
+    AttVal *attval;
+    Node *node;
+    Node *head = TY_(FindHEAD)( doc );
+    printf("hello");
+    return no;
+}
+
 /* add meta element for Tidy */
 Bool TY_(AddGenerator)( TidyDocImpl* doc )
 {

src/lexer.h

@@ -491,6 +491,9 @@ Node* TY_(FindXmlDecl)(TidyDocImpl* doc);
 /* Returns containing block element, if any */
 Node* TY_(FindContainer)( Node* node );
 
+/* Adds meta element and sets the charset */
+Bool TY_(TidyMetaCharset)( TidyDocImpl* doc );
+
 /* add meta element for Tidy */
 Bool TY_(AddGenerator)( TidyDocImpl* doc );
 

src/tidylib.c

@@ -1795,6 +1795,7 @@ int         tidyDocCleanAndRepair( TidyDocImpl* doc )
     Bool xhtmlOut = cfgBool( doc, TidyXhtmlOut );
     Bool xmlDecl  = cfgBool( doc, TidyXmlDecl );
     Bool tidyMark = cfgBool( doc, TidyMark );
+    Bool tidyMetaCharset = cfgBool( doc, TidyMetaCharset);
     Bool tidyXmlTags = cfgBool( doc, TidyXmlTags );
     Bool wantNameAttr = cfgBool( doc, TidyAnchorAsName );
     Bool mergeEmphasis = cfgBool( doc, TidyMergeEmphasis );
@@ -1898,6 +1899,9 @@ int         tidyDocCleanAndRepair( TidyDocImpl* doc )
 
         if (tidyMark )
             TY_(AddGenerator)(doc);
+
+        if (tidyMetaCharset)
+            TY_(TidyMetaCharset)(doc);
     }
 
     /* ensure presence of initial <?xml version="1.0"?> */