Merge remote-tracking branch 'origin/keep-tabs' into complete_callbacks

include/tidyenum.h

@@ -604,6 +604,7 @@ typedef enum
     TidyJoinClasses,             /**< Join multiple class attributes */
     TidyJoinStyles,              /**< Join multiple style attributes */
     TidyKeepFileTimes,           /**< If yes last modied time is preserved */
+    TidyKeepTabs,                /**< If yes keep input source tabs */
     TidyLiteralAttribs,          /**< If true attributes may use newlines */
     TidyLogicalEmphasis,         /**< Replace i by em and b by strong */
     TidyLowerLiterals,           /**< Folds known attribute values to lower case */

src/config.c

@@ -214,6 +214,7 @@ static const TidyOptionImpl option_defs[] =
     { TidyJoinClasses,             MX, "join-classes",                BL, no,              ParsePickList,     &boolPicks          },
     { TidyJoinStyles,              MX, "join-styles",                 BL, yes,             ParsePickList,     &boolPicks          },
     { TidyKeepFileTimes,           IO, "keep-time",                   BL, no,              ParsePickList,     &boolPicks          },
+    { TidyKeepTabs,                PP, "keep-tabs",                   BL, no,              ParsePickList,     &boolPicks          }, /* 20171103 - Issue #403 */
     { TidyLiteralAttribs,          MR, "literal-attributes",          BL, no,              ParsePickList,     &boolPicks          },
     { TidyLogicalEmphasis,         MC, "logical-emphasis",            BL, no,              ParsePickList,     &boolPicks          },
     { TidyLowerLiterals,           MR, "lower-literals",              BL, yes,             ParsePickList,     &boolPicks          },

src/language_en.h

@@ -699,6 +699,27 @@ static languageDefinition language_en = { whichPluralForm_en, {
         "<br/>"
         "Note this feature is not supported on some platforms. "
     },
+    {/* 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. */
+        TidyKeepTabs,            0,
+        "With the default <var>no</var> Tidy will replace all source tabs, with spaces, "
+        "controlled by the option <code>tab-size</code>, and the current line offset. "
+        "Of course, except in the special blocks/elements enumerated below, this will later "
+        "be reduced to just one space. "
+        "<br/>"
+        "If set <var>yes</var> this option specifies Tidy should keep certain tabs "
+        "found in the source, but only "
+        "in preformatted blocks like <code>&lt;pre&gt;</code>, and other CDATA elements like "
+        "<code>&lt;script&gt;</code>, <code>&lt;style&gt;<code>, and other pseudo elements like "
+        "<code>&lt;?php ... ?&gt;</code>. As always, all other tabs, or sequences of tabs, in "
+        "the source will continue to be replaced with a space. "
+    },
     {/* Important notes for translators:
       - Use only <code></code>, <var></var>, <em></em>, <strong></strong>, and
       <br/>.

src/lexer.c

@@ -63,6 +63,9 @@ static tmbstr get_text_string(Lexer* lexer, Node *node)
             if (c == '\n') {
                 buffer[i++] = '\\';
                 buffer[i++] = 'n';
+            } else if (c == '\t') {
+                buffer[i++] = '\\';
+                buffer[i++] = 't';
             } else if ( c == ' ' ) {
                 if (!insp)
                     buffer[i++] = c;
@@ -84,6 +87,9 @@ static tmbstr get_text_string(Lexer* lexer, Node *node)
             if (c == '\n') {
                 buffer[i++] = '\\';
                 buffer[i++] = 'n';
+            } else if (c == '\t') {
+                buffer[i++] = '\\';
+                buffer[i++] = 't';
             } else if ( c == ' ' ) {
                 if (!insp)
                     buffer[i++] = c;
@@ -116,6 +122,9 @@ static tmbstr get_text_string(Lexer* lexer, Node *node)
             if (c == '\n') {
                 buffer[i++] = '\\';
                 buffer[i++] = 'n';
+            } else if (c == '\t') {
+                buffer[i++] = '\\';
+                buffer[i++] = 't';
             } else if ( c == ' ' ) {
                 if (!insp)
                     buffer[i++] = c;

src/streamio.c

@@ -239,7 +239,6 @@ static void RestoreLastPos( StreamIn *in )
 uint TY_(ReadChar)( StreamIn *in )
 {
     uint c = EndOfStream;
-    uint tabsize = cfg( in->doc, TidyTabSize );
 
     if ( in->pushed )
         return PopChar( in );
@@ -269,11 +268,15 @@ uint TY_(ReadChar)( StreamIn *in )
 
         if (c == '\t')
         {
+            Bool keeptabs = cfg( in->doc, TidyKeepTabs );
+            in->curcol++;
+            if (!keeptabs) {
+                uint tabsize = cfg(in->doc, TidyTabSize);
                 in->tabs = tabsize > 0 ?
                     tabsize - ((in->curcol - 1) % tabsize) - 1
                     : 0;
-            in->curcol++;
                 c = ' ';
+            }
             break;
         }