Merge branch 'next' into deprecations

CMakeLists.txt

@@ -3,6 +3,8 @@
 cmake_minimum_required (VERSION 2.8.7)
 
 set(LIB_NAME tidy)
+set(LIBTIDY_DESCRIPTION "${LIB_NAME} - HTML syntax checker")
+set(LIBTIDY_URL "http://www.html-tidy.org")
 
 project (${LIB_NAME})
 
@@ -203,7 +205,7 @@ if (NOT BIN_INSTALL_DIR)
 endif ()
 
 if (NOT INCLUDE_INSTALL_DIR)
-    set(INCLUDE_INSTALL_DIR include)
+    set(INCLUDE_INSTALL_DIR include/${LIB_NAME})
 endif ()
 
 # Always build the STATIC library
@@ -363,7 +365,7 @@ if (WIN32)
     set(CPACK_SOURCE_GENERATOR "ZIP")
     set(CPACK_WIX_UPGRADE_GUID "D809598A-B513-4752-B268-0BAC403B00E4")
 elseif ( ${CMAKE_SYSTEM_NAME} MATCHES "Darwin" )
-    set(CPACK_GENERATOR "PackageMake")
+    set(CPACK_GENERATOR "productbuild")
     set(CPACK_SOURCE_GENERATOR "TGZ")
 else ()
     set(CPACK_GENERATOR "DEB;RPM")
@@ -371,7 +373,7 @@ else ()
 endif ()
 
 set(CPACK_PACKAGE_NAME "${LIB_NAME}")
-set(CPACK_PACKAGE_DESCRIPTION_SUMMARY "${LIB_NAME} - HTML syntax checker")
+set(CPACK_PACKAGE_DESCRIPTION_SUMMARY "${LIBTIDY_DESCRIPTION}")
 set(CPACK_PACKAGE_VENDOR "HTML Tidy Advocacy Community Group")
 set(CPACK_PACKAGE_CONTACT "maintainer@htacg.org")
 
@@ -387,7 +389,7 @@ set(CPACK_RESOURCE_FILE_WELCOME "${CMAKE_CURRENT_SOURCE_DIR}/README/README.html"
 
 ## debian config
 set(CPACK_DEBIAN_PACKAGE_MAINTAINER ${CPACK_PACKAGE_CONTACT})
-set(CPACK_DEBIAN_PACKAGE_HOMEPAGE "http://www.html-tidy.org/")
+set(CPACK_DEBIAN_PACKAGE_HOMEPAGE ${LIBTIDY_URL})
 #set(CPACK_DEBIAN_PACKAGE_DEPENDS "libc")
 set(CPACK_DEBIAN_PACKAGE_SECTION "Libraries")
 set(CPACK_SOURCE_IGNORE_FILES
@@ -405,4 +407,15 @@ endif ()
 
 include(CPack)
 
+# pkg-config
+configure_file(
+    "${CMAKE_CURRENT_SOURCE_DIR}/${LIB_NAME}.pc.cmake.in"
+    "${CMAKE_CURRENT_BINARY_DIR}/${LIB_NAME}.pc"
+    @ONLY
+    )
+install(FILES
+    "${CMAKE_CURRENT_BINARY_DIR}/${LIB_NAME}.pc"
+    DESTINATION "${LIB_INSTALL_DIR}/pkgconfig"
+    )
+
 # eof

README/BUILD.md

@@ -40,6 +40,14 @@ If you do **not** need the tidy library built as a 'shared' (DLL) library, then
 
 See the `CMakeLists.txt` file for other CMake **options** offered.
 
+## Build the tidy packages
+
+  1. `cd build/cmake`
+
+  2. `cmake ../.. -DCMAKE_BUILD_TYPE=Release -DCMAKE_INSTALL_PREFIX=/usr`
+
+  3. Unix/OS X: `make package`
+
 ## Build PHP with the tidy-html5 library
 
 Due to API changes in the PHP source, `buffio.h` needs to be renamed to `tidybuffio.h` in the file `ext/tidy/tidy.c` in PHP's source.

build/cmake/.gitignore

@@ -30,5 +30,6 @@ _CPack_Packages/*
 tidy
 libtidy*
 tidy1.xsl
+tidy.pc
 *.vcproj
-
+.pkg

build/cmake/cmake-clean.txt

@@ -27,4 +27,4 @@ libtidy.so.5.0.0
 tidy.1
 _CPack_Packages
 tidy1.xsl
-
+tidy.pc

include/tidyenum.h

@@ -630,6 +630,7 @@ typedef enum
     TidyUpperCaseTags,           /**< Output tags in upper not lower case */
     TidyUseCustomTags,           /**< Enable Tidy to use autonomous custom tags */
     TidyVertSpace,               /**< degree to which markup is spread out vertically */
+    TidyWarnPropAttrs,           /**< Warns on proprietary attributes */
     TidyWord2000,                /**< Draconian cleaning for Word2000 */
     TidyWrapAsp,                 /**< Wrap within ASP pseudo elements */
     TidyWrapAttVals,             /**< Wrap within attribute values */

src/access.c

@@ -131,6 +131,49 @@ static void MetaDataPresent( TidyDocImpl* doc, Node* node );
 static void CheckEmbed( TidyDocImpl* doc, Node* node );
 static void CheckListUsage( TidyDocImpl* doc, Node* node );
 
+/*
+    IsFilePath attempts to determine whether or not the URI indicated
+    by path is a file rather than a TLD. For example, sample.com.au might
+    be confused with an audio file.
+*/
+static Bool IsFilePath( ctmbstr path )
+{
+    const char *p = path;
+    char c;
+    typedef enum states { initial, protocol_found, slash_found, file_found } states;
+    states state = initial;
+
+    while ( ( c = *p++ ) != 0 && state != file_found )
+    {
+        switch ( state )
+        {
+            case initial:
+                if ( c == ':' )
+                    state = protocol_found;
+                break;
+
+            case protocol_found:
+                if ( c =='/' )
+                    state = slash_found;
+                break;
+
+            case slash_found:
+                if ( c =='/' )
+                    state = protocol_found;
+                else
+                    state = file_found;
+                break;
+                
+            default:
+                break;
+        }
+        
+    }
+    
+    return state == file_found || state == initial;
+}
+
+
 /*
     GetFileExtension takes a path and returns the extension
     portion of the path (if any).
@@ -163,9 +206,10 @@ static void GetFileExtension( ctmbstr path, tmbchar *ext, uint maxExt )
 static Bool IsImage( ctmbstr iType )
 {
     uint i;
-
-    /* Get the file extension */
     tmbchar ext[20];
+
+    if ( !IsFilePath(iType) ) return 0;
+
     GetFileExtension( iType, ext, sizeof(ext) );
 
     /* Compare it to the array of known image file extensions */
@@ -190,6 +234,9 @@ static int IsSoundFile( ctmbstr sType )
 {
     uint i;
     tmbchar ext[ 20 ];
+
+    if ( !IsFilePath(sType) ) return 0;
+    
     GetFileExtension( sType, ext, sizeof(ext) );
     
     for (i = 0; i < N_AUDIO_EXTS; i++)
@@ -215,6 +262,9 @@ static Bool IsValidSrcExtension( ctmbstr sType )
 {
     uint i;
     tmbchar ext[20];
+    
+    if ( !IsFilePath(sType) ) return 0;
+    
     GetFileExtension( sType, ext, sizeof(ext) );
 
     for (i = 0; i < N_FRAME_EXTS; i++)
@@ -237,6 +287,9 @@ static Bool IsValidMediaExtension( ctmbstr sType )
 {
     uint i;
     tmbchar ext[20];
+
+    if ( !IsFilePath(sType) ) return 0;
+
     GetFileExtension( sType, ext, sizeof(ext) );
 
     for (i = 0; i < N_MEDIA_EXTS; i++)
@@ -2708,6 +2761,10 @@ static Bool CheckMetaData( TidyDocImpl* doc, Node* node, Bool HasMetaData )
                         TY_(ReportAccessError)( doc, node, REMOVE_AUTO_REDIRECT);
                     }
                 }
+                if (TY_(IsHTML5Mode)(doc) && attrIsCHARSET(av) && hasValue(av))
+                {
+                    ContainsAttr = yes;
+                }
             }
         
             if ( HasContent || HasHttpEquiv )
@@ -2787,10 +2844,18 @@ static void CheckDocType( TidyDocImpl* doc )
         if (DTnode && DTnode->end != 0)
         {
             ctmbstr word = textFromOneNode( doc, DTnode);
-            if ((strstr (word, "HTML PUBLIC") == NULL) &&
+            if (TY_(IsHTML5Mode)(doc))
-                (strstr (word, "html PUBLIC") == NULL))
+            {
+                if ((strstr(word, "HTML") == NULL) &&
+                    (strstr(word, "html") == NULL))
                     DTnode = NULL;
             }
+            else {
+                if ((strstr(word, "HTML PUBLIC") == NULL) &&
+                    (strstr(word, "html PUBLIC") == NULL))
+                    DTnode = NULL;
+            }
+        }
         if (!DTnode)
            TY_(ReportAccessError)( doc, &doc->root, DOCTYPE_MISSING);
     }

src/config.c

@@ -320,6 +320,7 @@ static const TidyOptionImpl option_defs[] =
     { TidyUpperCaseTags,           MU, "uppercase-tags",              BL, no,              ParseBool,         boolPicks       },
     { TidyUseCustomTags,           MU, "custom-tags",                 IN, TidyCustomNo,    ParseUseCustomTags,customTagsPicks }, /* 20170309 - Issue #119 */
     { TidyVertSpace,               PP, "vertical-space",              IN, no,              ParseAutoBool,     autoBoolPicks   }, /* #228 - tri option */
+    { TidyWarnPropAttrs,           MU, "warn-proprietary-attributes", BL, yes,             ParseBool,         boolPicks       },
     { TidyWord2000,                MU, "word-2000",                   BL, no,              ParseBool,         boolPicks       },
     { TidyWrapAsp,                 PP, "wrap-asp",                    BL, yes,             ParseBool,         boolPicks       },
     { TidyWrapAttVals,             PP, "wrap-attributes",             BL, no,              ParseBool,         boolPicks       },

src/gdoc.c

@@ -115,6 +115,11 @@ static void CleanNode( TidyDocImpl* doc, Node *node )
                 else if (nodeIsA(child) && !child->content)
                  {
                     AttVal *id = TY_(GetAttrByName)( child, "name" );
+                    /* Recent Google Docs is using "id" instead of "name" in
+                    ** the exported html.
+                    */
+                    if (!id)
+                        id = TY_(GetAttrByName)( child, "id" );
 
                     if (id)
                         TY_(RepairAttrValue)( doc, child->parent, "id", id->value );

src/language_en.h

@@ -1167,10 +1167,10 @@ static languageDefinition language_en = { whichPluralForm_en, {
       be translated. */
         TidyStrictTagsAttr,           0,
         "This options ensures that tags and attributes are applicable for the "
-        "version of HTML that Tidy outputs. When set to <var>yes</var> (the "
+        "version of HTML that Tidy outputs. When set to <var>yes</var> and the "
-        "default) and the output document type is a strict doctype, then Tidy "
+        "output document type is a strict doctype, then Tidy will report "
-        "will report errors. If the output document type is a loose or "
+        "errors. If the output document type is a loose or transitional "
-        "transitional doctype, then Tidy will report warnings. "
+        "doctype, then Tidy will report warnings. "
         "<br/>"
         "Additionally if <code>drop-proprietary-attributes</code> is enabled, "
         "then not applicable attributes will be dropped, too. "
@@ -1261,6 +1261,17 @@ static languageDefinition language_en = { whichPluralForm_en, {
         "If set to <var>auto</var> Tidy will eliminate nearly all newline "
         "characters."
     },
+    {/* 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. */
+        TidyWarnPropAttrs,            0,
+        "This option specifies if Tidy should warn on proprietary attributes."
+    },
     {/* Important notes for translators:
       - Use only <code></code>, <var></var>, <em></em>, <strong></strong>, and
       <br/>.
@@ -1600,14 +1611,6 @@ static languageDefinition language_en = { whichPluralForm_en, {
         "        search stops for the current direction.\n"
         "        TD cells that set the axis attribute are also treated as header cells.\n"
     },
-    {/* This console output should be limited to 78 characters per line. */
-      TEXT_WINDOWS_CHARS,           0,
-        "Characters codes for the Microsoft Windows fonts in the range\n"
-        "128 - 159 may not be recognized on other platforms. You are\n"
-        "instead recommended to use named entities, e.g. &trade; rather\n"
-        "than Windows character code 153 (0x2122 in Unicode). Note that\n"
-        "as of February 1998 few browsers support the new entities.\n"
-    },
     {/* This console output should be limited to 78 characters per line.
         - %s represents a string-encoding name which may be localized in your language. */
       TEXT_VENDOR_CHARS,            0,

src/message.c

@@ -757,13 +757,6 @@ void TY_(ErrorSummary)( TidyDocImpl* doc )
 
     if (doc->badChars)
     {
-#if 0
-        if ( doc->badChars & WINDOWS_CHARS )
-        {
-            message = TY_(tidyMessageCreate)( doc, TEXT_WINDOWS_CHARS, TidyDialogueDoc);
-            messagePos(message);
-        }
-#endif
         if (doc->badChars & BC_VENDOR_SPECIFIC_CHARS)
         {
             message = TY_(tidyMessageCreate)( doc, TEXT_VENDOR_CHARS, TidyDialogueDoc, encnam);

src/tags.c

@@ -184,7 +184,7 @@ static Dict tag_defs[] =
   { TidyTag_BLOCKQUOTE, "blockquote", VERS_ELEM_BLOCKQUOTE, &TY_(W3CAttrsFor_BLOCKQUOTE)[0], (CM_BLOCK),                                    TY_(ParseBlock),    NULL           },
   { TidyTag_BODY,       "body",       VERS_ELEM_BODY,       &TY_(W3CAttrsFor_BODY)[0],       (CM_HTML|CM_OPT|CM_OMITST),                    TY_(ParseBody),     NULL           },
   { TidyTag_BR,         "br",         VERS_ELEM_BR,         &TY_(W3CAttrsFor_BR)[0],         (CM_INLINE|CM_EMPTY),                          TY_(ParseEmpty),    NULL           },
-  { TidyTag_BUTTON,     "button",     VERS_ELEM_BUTTON,     &TY_(W3CAttrsFor_BUTTON)[0],     (CM_INLINE),                                   TY_(ParseBlock),    NULL           },
+  { TidyTag_BUTTON,     "button",     VERS_ELEM_BUTTON,     &TY_(W3CAttrsFor_BUTTON)[0],     (CM_INLINE),                                   TY_(ParseInline),   NULL           },
   { TidyTag_CAPTION,    "caption",    VERS_ELEM_CAPTION,    &TY_(W3CAttrsFor_CAPTION)[0],    (CM_TABLE),                                    TY_(ParseBlock),    CheckCaption   },
   { TidyTag_CENTER,     "center",     VERS_ELEM_CENTER,     &TY_(W3CAttrsFor_CENTER)[0],     (CM_BLOCK),                                    TY_(ParseBlock),    NULL           },
   { TidyTag_CITE,       "cite",       VERS_ELEM_CITE,       &TY_(W3CAttrsFor_CITE)[0],       (CM_INLINE),                                   TY_(ParseInline),   NULL           },
@@ -773,9 +773,6 @@ void TY_(AdjustTags)( TidyDocImpl *doc )
     {
         np->parser = TY_(ParseInline);
         np->model  = CM_INLINE;
-#if ELEMENT_HASH_LOOKUP
-        tagsEmptyHash( doc, tags );
-#endif
     }
 
 /*\
@@ -787,9 +784,6 @@ void TY_(AdjustTags)( TidyDocImpl *doc )
     if (np)
     {
         np->parser = TY_(ParseInline);
-#if ELEMENT_HASH_LOOKUP
-        tagsEmptyHash( doc, tags );
-#endif
     }
 
 /*\
@@ -801,10 +795,24 @@ void TY_(AdjustTags)( TidyDocImpl *doc )
     if (np)
     {
         np->model |= CM_HEAD; /* add back allowed in head */
-#if ELEMENT_HASH_LOOKUP
-        tagsEmptyHash( doc, tags );
-#endif
     }
+
+/*\
+ * Issue #461
+ * TidyTag_BUTTON is a block in HTML4,
+ * whereas it is inline in HTML5
+\*/
+    np = (Dict *)TY_(LookupTagDef)(TidyTag_BUTTON);
+    if (np)
+    {
+        np->parser = TY_(ParseBlock);
+    }
+
+#if ELEMENT_HASH_LOOKUP
+    tagsEmptyHash(doc, tags); /* not sure this is really required, but to be sure */
+#endif
+    doc->HTML5Mode = no;   /* set *NOT* HTML5 mode */
+
 }
 
 Bool TY_(IsHTML5Mode)( TidyDocImpl *doc )
@@ -839,6 +847,16 @@ void TY_(ResetTags)( TidyDocImpl *doc )
     {
         np->model = (CM_OBJECT|CM_IMG|CM_INLINE|CM_PARAM); /* reset */
     }
+    /*\
+     * Issue #461
+     * TidyTag_BUTTON reset to inline in HTML5
+    \*/
+    np = (Dict *)TY_(LookupTagDef)(TidyTag_BUTTON);
+    if (np)
+    {
+        np->parser = TY_(ParseInline);
+    }
+
 #if ELEMENT_HASH_LOOKUP
     tagsEmptyHash( doc, tags ); /* not sure this is really required, but to be sure */
 #endif
@@ -858,7 +876,6 @@ void TY_(FreeTags)( TidyDocImpl* doc )
     /* get rid of dangling tag references */
     TidyClearMemory( tags, sizeof(TidyTagImpl) );
 
-    doc->HTML5Mode = no;    /* reset html5 mode == legacy html4 mode */
 }
 
 

src/tidylib.c

@@ -1823,7 +1823,10 @@ void TY_(CheckHTMLTagsAttribsVersions)( TidyDocImpl* doc, Node* node )
                 attrIsMismatched = check_versions ? TY_(AttributeIsMismatched)(node, attval, doc) : no;
                 /* Let the PROPRIETARY_ATTRIBUTE warning have precedence. */
                 if ( attrIsProprietary )
+                {
+                    if ( cfgBool(doc, TidyWarnPropAttrs) )
                         TY_(ReportAttrError)(doc, node, attval, PROPRIETARY_ATTRIBUTE);
+                }
                 else if ( attrIsMismatched )
                 {
                     TY_(ReportAttrError)(doc, node, attval, attrReportType);

tidy.pc.cmake.in

@@ -0,0 +1,11 @@
+prefix=@CMAKE_INSTALL_PREFIX@
+exec_prefix=${prefix}
+libdir=${exec_prefix}/@LIB_INSTALL_DIR@
+includedir=${prefix}/@INCLUDE_INSTALL_DIR@
+
+Name: @LIB_NAME@
+Description: @LIBTIDY_DESCRIPTION@
+URL: @LIBTIDY_URL@
+Version: @LIBTIDY_VERSION@
+Libs: -L${libdir} -l@LIB_NAME@
+Cflags: -I${includedir}

version.txt

@@ -1,2 +1,2 @@
-5.5.13
+5.5.18
-2017.03.31
+2017.05.06