Menu
▾
▴
jtidy-cvs — JTidy mailing list for CVS commits
You can subscribe to this list here.
| 2000 |
Jan
|
Feb
|
Mar
|
Apr
|
May
|
Jun
|
Jul
|
Aug
|
Sep
|
Oct
|
Nov
(46) |
Dec
(1) |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2001 |
Jan
(1) |
Feb
|
Mar
(1) |
Apr
|
May
|
Jun
(1) |
Jul
(15) |
Aug
(24) |
Sep
(14) |
Oct
(2) |
Nov
(1) |
Dec
(18) |
| 2002 |
Jan
(12) |
Feb
(5) |
Mar
(3) |
Apr
(1) |
May
(1) |
Jun
(10) |
Jul
(3) |
Aug
(4) |
Sep
|
Oct
(1) |
Nov
|
Dec
(5) |
| 2003 |
Jan
(1) |
Feb
(1) |
Mar
|
Apr
(1) |
May
(2) |
Jun
(4) |
Jul
(2) |
Aug
(4) |
Sep
|
Oct
(1) |
Nov
(1) |
Dec
(1) |
| 2004 |
Jan
(141) |
Feb
(79) |
Mar
(85) |
Apr
(38) |
May
(1) |
Jun
|
Jul
(78) |
Aug
(223) |
Sep
(107) |
Oct
(158) |
Nov
(136) |
Dec
|
| 2005 |
Jan
(7) |
Feb
(4) |
Mar
|
Apr
(13) |
May
|
Jun
|
Jul
|
Aug
|
Sep
|
Oct
(1) |
Nov
(2) |
Dec
(3) |
| 2010 |
Jan
|
Feb
|
Mar
|
Apr
|
May
|
Jun
|
Jul
|
Aug
|
Sep
|
Oct
(2) |
Nov
(100) |
Dec
(22) |
|
From: <ad...@us...> - 2010-11-26 00:21:30
|
Revision: 1236
http://jtidy.svn.sourceforge.net/jtidy/?rev=1236&view=rev
Author: aditsu
Date: 2010-11-26 00:21:24 +0000 (Fri, 26 Nov 2010)
Log Message:
-----------
added setParent and setNext, with integrity checks
Modified Paths:
--------------
branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Node.java
Modified: branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Node.java
===================================================================
--- branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Node.java 2010-11-25 04:54:42 UTC (rev 1235)
+++ branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Node.java 2010-11-26 00:21:24 UTC (rev 1236)
@@ -485,43 +485,35 @@
* Insert a node into markup tree.
* @param node to insert
*/
- public void insertNodeAtStart(Node node)
- {
- node.parent = this;
+ public void insertNodeAtStart(final Node node) {
+ node.setParent(this);
- if (this.content == null)
- {
- this.last = node;
+ if (content == null) {
+ last = node;
}
- else
- {
- this.content.prev = node; // AQ added 13 Apr 2000
+ else {
+ content.prev = node; // AQ added 13 Apr 2000
}
-
- node.next = this.content;
+ node.setNext(content);
node.prev = null;
- this.content = node;
+ content = node;
}
/**
* Insert node into markup tree.
* @param node Node to insert
*/
- public void insertNodeAtEnd(Node node)
- {
- node.parent = this;
- node.prev = this.last;
-
- if (this.last != null)
- {
- this.last.next = node;
+ public void insertNodeAtEnd(final Node node) {
+ node.setParent(this);
+ node.prev = last;
+
+ if (last != null) {
+ last.setNext(node);
}
- else
- {
- this.content = node;
+ else {
+ content = node;
}
-
- this.last = node;
+ last = node;
}
/**
@@ -529,62 +521,48 @@
* @param element child node. Will be inserted as a child of element
* @param node parent node
*/
- public static void insertNodeAsParent(Node element, Node node)
- {
+ public static void insertNodeAsParent(final Node element, final Node node) {
node.content = element;
node.last = element;
- node.parent = element.parent;
- element.parent = node;
+ node.setParent(element.parent);
+ element.setParent(node);
- if (node.parent.content == element)
- {
+ if (node.parent.content == element) {
node.parent.content = node;
}
-
- if (node.parent.last == element)
- {
+ if (node.parent.last == element) {
node.parent.last = node;
}
-
node.prev = element.prev;
element.prev = null;
- if (node.prev != null)
- {
- node.prev.next = node;
+ if (node.prev != null) {
+ node.prev.setNext(node);
}
-
- node.next = element.next;
+ node.setNext(element.next);
element.next = null;
- if (node.next != null)
- {
+ if (node.next != null) {
node.next.prev = node;
}
}
/**
* Insert node into markup tree before element.
- * @param element child node. Will be insertedbefore element
+ * @param element child node. Will be inserted before element
* @param node following node
*/
- public static void insertNodeBeforeElement(Node element, Node node)
- {
- Node parent;
-
- parent = element.parent;
- node.parent = parent;
- node.next = element;
+ public static void insertNodeBeforeElement(Node element, Node node) {
+ Node parent = element.parent;
+ node.setParent(parent);
+ node.setNext(element);
node.prev = element.prev;
element.prev = node;
- if (node.prev != null)
- {
- node.prev.next = node;
+ if (node.prev != null) {
+ node.prev.setNext(node);
}
-
- if (parent != null && parent.content == element)
- {
+ if (parent != null && parent.content == element) {
parent.content = node;
}
}
@@ -593,29 +571,21 @@
* Insert node into markup tree after element.
* @param node new node to insert
*/
- public void insertNodeAfterElement(Node node)
- {
- Node parent;
+ public void insertNodeAfterElement(final Node node) {
+ node.setParent(parent);
- parent = this.parent;
- node.parent = parent;
-
// AQ - 13Jan2000 fix for parent == null
- if (parent != null && parent.last == this)
- {
+ if (parent != null && parent.last == this) {
parent.last = node;
}
- else
- {
- node.next = this.next;
+ else {
+ node.setNext(next);
// AQ - 13Jan2000 fix for node.next == null
- if (node.next != null)
- {
+ if (node.next != null) {
node.next.prev = node;
}
}
-
- this.next = node;
+ setNext(node);
node.prev = this;
}
@@ -918,30 +888,21 @@
* @param row Row node
* @param node Node which should be moved before the table
*/
- public static void moveBeforeTable(Node row, Node node)
- {
- Node table;
-
+ public static void moveBeforeTable(Node row, Node node) {
/* first find the table element */
- for (table = row.parent; table != null; table = table.parent)
- {
- if (table.is(TagId.TABLE))
- {
- if (table.parent.content == table)
- {
+ for (Node table = row.parent; table != null; table = table.parent) {
+ if (table.is(TagId.TABLE)) {
+ if (table.parent.content == table) {
table.parent.content = node;
}
-
node.prev = table.prev;
- node.next = table;
+ node.setNext(table);
table.prev = node;
- node.parent = table.parent;
+ node.setParent(table.parent);
- if (node.prev != null)
- {
- node.prev.next = node;
+ if (node.prev != null) {
+ node.prev.setNext(node);
}
-
break;
}
}
@@ -992,34 +953,24 @@
/**
* Extract this node and its children from a markup tree.
*/
- public void removeNode()
- {
- if (this.prev != null)
- {
- this.prev.next = this.next;
+ public void removeNode() {
+ if (prev != null) {
+ prev.setNext(next);
}
-
- if (this.next != null)
- {
- this.next.prev = this.prev;
+ if (next != null) {
+ next.prev = prev;
}
-
- if (this.parent != null)
- {
- if (this.parent.content == this)
- {
- this.parent.content = this.next;
+ if (parent != null) {
+ if (parent.content == this) {
+ parent.content = next;
}
-
- if (this.parent.last == this)
- {
- this.parent.last = this.prev;
+ if (parent.last == this) {
+ parent.last = prev;
}
}
-
- this.parent = null;
- this.prev = null;
- this.next = null;
+ parent = null;
+ prev = null;
+ next = null;
}
/**
@@ -1490,4 +1441,18 @@
}
return 0;
}
+
+ protected void setParent(final Node node) {
+ if (node == this) {
+ throw new IllegalArgumentException("Attempt to insert a node into itself");
+ }
+ parent = node;
+ }
+
+ protected void setNext(final Node node) {
+ if (node == this) {
+ throw new IllegalArgumentException("Attempt to insert a node as its own sibling");
+ }
+ next = node;
+ }
}
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
|
From: <ad...@us...> - 2010-11-25 04:54:49
|
Revision: 1235
http://jtidy.svn.sourceforge.net/jtidy/?rev=1235&view=rev
Author: aditsu
Date: 2010-11-25 04:54:42 +0000 (Thu, 25 Nov 2010)
Log Message:
-----------
fixed tests 1503897, 1590220-1 and 1590220-2 - updated unexpected tag handling in ParsePre - but results are questionable
Modified Paths:
--------------
branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/ParserImpl.java
Modified: branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/ParserImpl.java
===================================================================
--- branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/ParserImpl.java 2010-11-25 04:00:26 UTC (rev 1234)
+++ branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/ParserImpl.java 2010-11-25 04:54:42 UTC (rev 1235)
@@ -1975,13 +1975,33 @@
}
// strip unexpected tags
- if (!lexer.preContent(node))
- {
- Node newnode;
-
- lexer.report.warning(lexer, pre, node, ErrorCode.UNESCAPED_ELEMENT);
- newnode = Node.escapeTag(lexer, node);
- pre.insertNodeAtEnd(newnode);
+ if (!lexer.preContent(node)) {
+ if (node.type == NodeType.EndTag) {
+ if (lexer.exiled && (node.hasCM(Dict.CM_TABLE) || node.is(TagId.TABLE))) {
+ lexer.ungetToken();
+ Node.trimSpaces(lexer, pre);
+ return;
+ }
+ lexer.report.warning(lexer, pre, node, ErrorCode.DISCARDING_UNEXPECTED);
+ continue;
+ }
+ else if (node.hasCM(Dict.CM_TABLE | Dict.CM_ROW) || node.is(TagId.TABLE)) {
+ if (!lexer.exiled) {
+ /* No missing close warning if exiled. */
+ lexer.report.warning(lexer, pre, node, ErrorCode.MISSING_ENDTAG_BEFORE);
+ }
+ lexer.ungetToken();
+ return;
+ }
+
+ pre.insertNodeAfterElement(node);
+ lexer.report.warning(lexer, pre, node, ErrorCode.MISSING_ENDTAG_BEFORE);
+ parseTag(lexer, node, Lexer.IGNORE_WHITESPACE);
+
+ final Node newnode = lexer.inferredTag(TagId.PRE);
+ lexer.report.warning(lexer, pre, newnode, ErrorCode.INSERTING_TAG);
+ pre = newnode;
+ node.insertNodeAfterElement(pre);
continue;
}
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
|
From: <ad...@us...> - 2010-11-25 04:00:33
|
Revision: 1234
http://jtidy.svn.sourceforge.net/jtidy/?rev=1234&view=rev
Author: aditsu
Date: 2010-11-25 04:00:26 +0000 (Thu, 25 Nov 2010)
Log Message:
-----------
corrected node description for UNESCAPED_ELEMENT
Modified Paths:
--------------
branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Report.java
Modified: branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Report.java
===================================================================
--- branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Report.java 2010-11-24 02:39:29 UTC (rev 1233)
+++ branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Report.java 2010-11-25 04:00:26 UTC (rev 1234)
@@ -703,7 +703,7 @@
break;
case UNESCAPED_ELEMENT :
- messageLexer(lexer, Level.WARNING, code, getTagName(element));
+ messageLexer(lexer, Level.WARNING, code, nodedesc);
break;
case NOFRAMES_CONTENT :
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
|
From: <ad...@us...> - 2010-11-24 02:39:38
|
Revision: 1233
http://jtidy.svn.sourceforge.net/jtidy/?rev=1233&view=rev
Author: aditsu
Date: 2010-11-24 02:39:29 +0000 (Wed, 24 Nov 2010)
Log Message:
-----------
ported accessibility checks and messages - this fixes 5 tests
Modified Paths:
--------------
branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/AttVal.java
branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/ErrorCode.java
branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Lexer.java
branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Node.java
branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/ParserImpl.java
branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Report.java
branches/CodeUpdateAndJava5/src/main/resources/org/w3c/tidy/TidyMessages.properties
Added Paths:
-----------
branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/AccessErrorCode.java
branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Accessibility.java
branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/IErrorCode.java
Added: branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/AccessErrorCode.java
===================================================================
--- branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/AccessErrorCode.java (rev 0)
+++ branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/AccessErrorCode.java 2010-11-24 02:39:29 UTC (rev 1233)
@@ -0,0 +1,148 @@
+package org.w3c.tidy;
+
+/**
+ * Accessibility error codes (from access.h)
+ *
+ * @author aditsu
+ */
+public enum AccessErrorCode implements IErrorCode {
+ FIRST_ACCESS_ERR, /* must be first */
+
+/* [1.1.1.1] */ IMG_MISSING_ALT,
+/* [1.1.1.2] */ IMG_ALT_SUSPICIOUS_FILENAME,
+/* [1.1.1.3] */ IMG_ALT_SUSPICIOUS_FILE_SIZE,
+/* [1.1.1.4] */ IMG_ALT_SUSPICIOUS_PLACEHOLDER,
+/* [1.1.1.10] */ IMG_ALT_SUSPICIOUS_TOO_LONG,
+/* [1.1.1.11] */ IMG_MISSING_ALT_BULLET,
+/* [1.1.1.12] */ IMG_MISSING_ALT_H_RULE,
+/* [1.1.2.1] */ IMG_MISSING_LONGDESC_DLINK,
+/* [1.1.2.2] */ IMG_MISSING_DLINK,
+/* [1.1.2.3] */ IMG_MISSING_LONGDESC,
+/* [1.1.2.5] */ LONGDESC_NOT_REQUIRED,
+/* [1.1.3.1] */ IMG_BUTTON_MISSING_ALT,
+/* [1.1.4.1] */ APPLET_MISSING_ALT,
+/* [1.1.5.1] */ OBJECT_MISSING_ALT,
+/* [1.1.6.1] */ AUDIO_MISSING_TEXT_WAV,
+/* [1.1.6.2] */ AUDIO_MISSING_TEXT_AU,
+/* [1.1.6.3] */ AUDIO_MISSING_TEXT_AIFF,
+/* [1.1.6.4] */ AUDIO_MISSING_TEXT_SND,
+/* [1.1.6.5] */ AUDIO_MISSING_TEXT_RA,
+/* [1.1.6.6] */ AUDIO_MISSING_TEXT_RM,
+/* [1.1.8.1] */ FRAME_MISSING_LONGDESC,
+/* [1.1.9.1] */ AREA_MISSING_ALT,
+/* [1.1.10.1] */ SCRIPT_MISSING_NOSCRIPT,
+/* [1.1.12.1] */ ASCII_REQUIRES_DESCRIPTION,
+/* [1.2.1.1] */ IMG_MAP_SERVER_REQUIRES_TEXT_LINKS,
+/* [1.4.1.1] */ MULTIMEDIA_REQUIRES_TEXT,
+/* [1.5.1.1] */ IMG_MAP_CLIENT_MISSING_TEXT_LINKS,
+/* [2.1.1.1] */ INFORMATION_NOT_CONVEYED_IMAGE,
+/* [2.1.1.2] */ INFORMATION_NOT_CONVEYED_APPLET,
+/* [2.1.1.3] */ INFORMATION_NOT_CONVEYED_OBJECT,
+/* [2.1.1.4] */ INFORMATION_NOT_CONVEYED_SCRIPT,
+/* [2.1.1.5] */ INFORMATION_NOT_CONVEYED_INPUT,
+/* [2.2.1.1] */ COLOR_CONTRAST_TEXT,
+/* [2.2.1.2] */ COLOR_CONTRAST_LINK,
+/* [2.2.1.3] */ COLOR_CONTRAST_ACTIVE_LINK,
+/* [2.2.1.4] */ COLOR_CONTRAST_VISITED_LINK,
+/* [3.2.1.1] */ DOCTYPE_MISSING,
+/* [3.3.1.1] */ STYLE_SHEET_CONTROL_PRESENTATION,
+/* [3.5.1.1] */ HEADERS_IMPROPERLY_NESTED,
+/* [3.5.2.1] */ POTENTIAL_HEADER_BOLD,
+/* [3.5.2.2] */ POTENTIAL_HEADER_ITALICS,
+/* [3.5.2.3] */ POTENTIAL_HEADER_UNDERLINE,
+/* [3.5.3.1] */ HEADER_USED_FORMAT_TEXT,
+/* [3.6.1.1] */ LIST_USAGE_INVALID_UL,
+/* [3.6.1.2] */ LIST_USAGE_INVALID_OL,
+/* [3.6.1.4] */ LIST_USAGE_INVALID_LI,
+/* [4.1.1.1] */ INDICATE_CHANGES_IN_LANGUAGE,
+/* [4.3.1.1] */ LANGUAGE_NOT_IDENTIFIED,
+/* [4.3.1.1] */ LANGUAGE_INVALID,
+/* [5.1.2.1] */ DATA_TABLE_MISSING_HEADERS,
+/* [5.1.2.2] */ DATA_TABLE_MISSING_HEADERS_COLUMN,
+/* [5.1.2.3] */ DATA_TABLE_MISSING_HEADERS_ROW,
+/* [5.2.1.1] */ DATA_TABLE_REQUIRE_MARKUP_COLUMN_HEADERS,
+/* [5.2.1.2] */ DATA_TABLE_REQUIRE_MARKUP_ROW_HEADERS,
+/* [5.3.1.1] */ LAYOUT_TABLES_LINEARIZE_PROPERLY,
+/* [5.4.1.1] */ LAYOUT_TABLE_INVALID_MARKUP,
+/* [5.5.1.1] */ TABLE_MISSING_SUMMARY,
+/* [5.5.1.2] */ TABLE_SUMMARY_INVALID_NULL,
+/* [5.5.1.3] */ TABLE_SUMMARY_INVALID_SPACES,
+/* [5.5.1.6] */ TABLE_SUMMARY_INVALID_PLACEHOLDER,
+/* [5.5.2.1] */ TABLE_MISSING_CAPTION,
+/* [5.6.1.1] */ TABLE_MAY_REQUIRE_HEADER_ABBR,
+/* [5.6.1.2] */ TABLE_MAY_REQUIRE_HEADER_ABBR_NULL,
+/* [5.6.1.3] */ TABLE_MAY_REQUIRE_HEADER_ABBR_SPACES,
+/* [6.1.1.1] */ STYLESHEETS_REQUIRE_TESTING_LINK,
+/* [6.1.1.2] */ STYLESHEETS_REQUIRE_TESTING_STYLE_ELEMENT,
+/* [6.1.1.3] */ STYLESHEETS_REQUIRE_TESTING_STYLE_ATTR,
+/* [6.2.1.1] */ FRAME_SRC_INVALID,
+/* [6.2.2.1] */ TEXT_EQUIVALENTS_REQUIRE_UPDATING_APPLET,
+/* [6.2.2.2] */ TEXT_EQUIVALENTS_REQUIRE_UPDATING_SCRIPT,
+/* [6.2.2.3] */ TEXT_EQUIVALENTS_REQUIRE_UPDATING_OBJECT,
+/* [6.3.1.1] */ PROGRAMMATIC_OBJECTS_REQUIRE_TESTING_SCRIPT,
+/* [6.3.1.2] */ PROGRAMMATIC_OBJECTS_REQUIRE_TESTING_OBJECT,
+/* [6.3.1.3] */ PROGRAMMATIC_OBJECTS_REQUIRE_TESTING_EMBED,
+/* [6.3.1.4] */ PROGRAMMATIC_OBJECTS_REQUIRE_TESTING_APPLET,
+/* [6.5.1.1] */ FRAME_MISSING_NOFRAMES,
+/* [6.5.1.2] */ NOFRAMES_INVALID_NO_VALUE,
+/* [6.5.1.3] */ NOFRAMES_INVALID_CONTENT,
+/* [6.5.1.4] */ NOFRAMES_INVALID_LINK,
+/* [7.1.1.1] */ REMOVE_FLICKER_SCRIPT,
+/* [7.1.1.2] */ REMOVE_FLICKER_OBJECT,
+/* [7.1.1.3] */ REMOVE_FLICKER_EMBED,
+/* [7.1.1.4] */ REMOVE_FLICKER_APPLET,
+/* [7.1.1.5] */ REMOVE_FLICKER_ANIMATED_GIF,
+/* [7.2.1.1] */ REMOVE_BLINK_MARQUEE,
+/* [7.4.1.1] */ REMOVE_AUTO_REFRESH,
+/* [7.5.1.1] */ REMOVE_AUTO_REDIRECT,
+/* [8.1.1.1] */ ENSURE_PROGRAMMATIC_OBJECTS_ACCESSIBLE_SCRIPT,
+/* [8.1.1.2] */ ENSURE_PROGRAMMATIC_OBJECTS_ACCESSIBLE_OBJECT,
+/* [8.1.1.3] */ ENSURE_PROGRAMMATIC_OBJECTS_ACCESSIBLE_APPLET,
+/* [8.1.1.4] */ ENSURE_PROGRAMMATIC_OBJECTS_ACCESSIBLE_EMBED,
+/* [9.1.1.1] */ IMAGE_MAP_SERVER_SIDE_REQUIRES_CONVERSION,
+/* [9.3.1.1] */ SCRIPT_NOT_KEYBOARD_ACCESSIBLE_ON_MOUSE_DOWN,
+/* [9.3.1.2] */ SCRIPT_NOT_KEYBOARD_ACCESSIBLE_ON_MOUSE_UP,
+/* [9.3.1.3] */ SCRIPT_NOT_KEYBOARD_ACCESSIBLE_ON_CLICK,
+/* [9.3.1.4] */ SCRIPT_NOT_KEYBOARD_ACCESSIBLE_ON_MOUSE_OVER,
+/* [9.3.1.5] */ SCRIPT_NOT_KEYBOARD_ACCESSIBLE_ON_MOUSE_OUT,
+/* [9.3.1.6] */ SCRIPT_NOT_KEYBOARD_ACCESSIBLE_ON_MOUSE_MOVE,
+/* [10.1.1.1] */ NEW_WINDOWS_REQUIRE_WARNING_NEW,
+/* [10.1.1.2] */ NEW_WINDOWS_REQUIRE_WARNING_BLANK,
+/* [10.2.1.1] */ LABEL_NEEDS_REPOSITIONING_BEFORE_INPUT,
+/* [10.2.1.2] */ LABEL_NEEDS_REPOSITIONING_AFTER_INPUT,
+/* [10.4.1.1] */ FORM_CONTROL_REQUIRES_DEFAULT_TEXT,
+/* [10.4.1.2] */ FORM_CONTROL_DEFAULT_TEXT_INVALID_NULL,
+/* [10.4.1.3] */ FORM_CONTROL_DEFAULT_TEXT_INVALID_SPACES,
+/* [11.2.1.1] */ REPLACE_DEPRECATED_HTML_APPLET,
+/* [11.2.1.2] */ REPLACE_DEPRECATED_HTML_BASEFONT,
+/* [11.2.1.3] */ REPLACE_DEPRECATED_HTML_CENTER,
+/* [11.2.1.4] */ REPLACE_DEPRECATED_HTML_DIR,
+/* [11.2.1.5] */ REPLACE_DEPRECATED_HTML_FONT,
+/* [11.2.1.6] */ REPLACE_DEPRECATED_HTML_ISINDEX,
+/* [11.2.1.7] */ REPLACE_DEPRECATED_HTML_MENU,
+/* [11.2.1.8] */ REPLACE_DEPRECATED_HTML_S,
+/* [11.2.1.9] */ REPLACE_DEPRECATED_HTML_STRIKE,
+/* [11.2.1.10] */ REPLACE_DEPRECATED_HTML_U,
+/* [12.1.1.1] */ FRAME_MISSING_TITLE,
+/* [12.1.1.2] */ FRAME_TITLE_INVALID_NULL,
+/* [12.1.1.3] */ FRAME_TITLE_INVALID_SPACES,
+/* [12.4.1.1] */ ASSOCIATE_LABELS_EXPLICITLY,
+/* [12.4.1.2] */ ASSOCIATE_LABELS_EXPLICITLY_FOR,
+/* [12.4.1.3] */ ASSOCIATE_LABELS_EXPLICITLY_ID,
+/* [13.1.1.1] */ LINK_TEXT_NOT_MEANINGFUL,
+/* [13.1.1.2] */ LINK_TEXT_MISSING,
+/* [13.1.1.3] */ LINK_TEXT_TOO_LONG,
+/* [13.1.1.4] */ LINK_TEXT_NOT_MEANINGFUL_CLICK_HERE,
+/* [13.1.1.5] */ LINK_TEXT_NOT_MEANINGFUL_MORE,
+/* [13.1.1.6] */ LINK_TEXT_NOT_MEANINGFUL_FOLLOW_THIS,
+/* [13.2.1.1] */ METADATA_MISSING,
+/* [13.2.1.2] */ METADATA_MISSING_LINK,
+/* [13.2.1.3] */ METADATA_MISSING_REDIRECT_AUTOREFRESH,
+/* [13.10.1.1] */ SKIPOVER_ASCII_ART,
+
+ LAST_ACCESS_ERR; /* must be last */
+
+ public int code() {
+ return ordinal() + 1000;
+ }
+}
Added: branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Accessibility.java
===================================================================
--- branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Accessibility.java (rev 0)
+++ branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Accessibility.java 2010-11-24 02:39:29 UTC (rev 1233)
@@ -0,0 +1,2534 @@
+package org.w3c.tidy;
+
+/*********************************************************************
+* AccessibilityChecks
+*
+* Carries out processes for all accessibility checks. Traverses
+* through all the content within the tree and evaluates the tags for
+* accessibility.
+*
+* To perform the following checks, 'AccessibilityChecks' must be
+* called AFTER the tree structure has been formed.
+*
+* If, in the command prompt, there is no specification of which
+* accessibility priorities to check, no accessibility checks will be
+* performed. (ie. '1' for priority 1, '2' for priorities 1 and 2,
+* and '3') for priorities 1, 2 and 3.)
+*
+* Copyright University of Toronto
+* Programmed by: Mike Lam and Chris Ridpath
+* Modifications by : Terry Teague (TRT)
+*
+* Reference document: http://www.w3.org/TR/WAI-WEBCONTENT/
+*********************************************************************/
+
+
+public class Accessibility {
+
+// private static final int TEXTBUF_SIZE = 128;
+
+ /* List of possible image types */
+ private static final String imageExtensions[] = {".jpg", ".gif", ".tif", ".pct", ".pic", ".iff", ".dib",
+ ".tga", ".pcx", ".png", ".jpeg", ".tiff", ".bmp"};
+
+ /* List of possible sound file types */
+ private static final String soundExtensions[] = {".wav", ".au", ".aiff", ".snd", ".ra", ".rm"};
+
+ private static final AccessErrorCode soundExtErrCodes[] = {
+ AccessErrorCode.AUDIO_MISSING_TEXT_WAV,
+ AccessErrorCode.AUDIO_MISSING_TEXT_AU,
+ AccessErrorCode.AUDIO_MISSING_TEXT_AIFF,
+ AccessErrorCode.AUDIO_MISSING_TEXT_SND,
+ AccessErrorCode.AUDIO_MISSING_TEXT_RA,
+ AccessErrorCode.AUDIO_MISSING_TEXT_RM
+ };
+
+ /* List of possible media extensions */
+ private static final String mediaExtensions[] = {".mpg", ".mov", ".asx", ".avi", ".ivf", ".m1v", ".mmm", ".mp2v",
+ ".mpa", ".mpe", ".mpeg", ".ram", ".smi", ".smil", ".swf", ".wm", ".wma", ".wmv"};
+
+ /* List of possible frame sources */
+ private static final String frameExtensions[] = {".htm", ".html", ".shtm", ".shtml", ".cfm", ".cfml",
+ ".asp", ".cgi", ".pl", ".smil"};
+
+ /* List of possible colour values */
+ private static final int colorValues[][] = {
+ { 0, 0, 0},
+ {128, 128, 128},
+ {192, 192, 192},
+ {255, 255, 255},
+ {192, 0, 0},
+ {255, 0, 0},
+ {128, 0, 128},
+ {255, 0, 255},
+ { 0, 128, 0},
+ { 0, 255, 0},
+ {128, 128, 0},
+ {255, 255, 0},
+ { 0, 0, 128},
+ { 0, 0, 255},
+ { 0, 128, 128},
+ { 0, 255, 255}
+ };
+
+ /* These arrays are used to convert color names to their RGB values */
+ private static final String colorNames[] = { "black", "silver", "grey", "white", "maroon", "red", "purple",
+ "fuchsia", "green", "lime", "olive", "yellow", "navy", "blue", "teal", "aqua"};
+
+ /* gets set from Tidy variable AccessibilityCheckLevel */
+ private int level;
+
+ /* list of characters in the text nodes found within a container element */
+ private final StringBuilder textNode = new StringBuilder();
+
+ /* Number of frame elements found within a frameset */
+ private int numFrames;
+
+ /* Number of 'longdesc' attributes found within a frameset */
+ private int hasCheckedLongDesc;
+
+ private int checkedHeaders;
+ private int listElements;
+ private int otherListElements;
+
+ /* For 'USEMAP' identifier */
+ private boolean hasUseMap;
+ private boolean hasName;
+ private boolean hasMap;
+
+ /* For tracking nodes that are deleted from the original parse tree - TRT */
+ /* Node *access_tree; */
+
+ private boolean hasTH;
+ private boolean hasValidFor;
+ private boolean hasValidId;
+ private boolean hasValidRowHeaders;
+ private boolean hasValidColumnHeaders;
+ private boolean hasInvalidRowHeader;
+ private boolean hasInvalidColumnHeader;
+ private int forID;
+
+ /*
+ GetFileExtension takes a path and returns the extension
+ portion of the path (if any).
+ */
+
+ private static String getFileExtension(final String path) {
+ int i = path.length() - 1;
+
+ do {
+ if (path.charAt(i) == '/' || path.charAt(i) == '\\') {
+ return "";
+ }
+ else if (path.charAt(i) == '.') {
+ return path.substring(i);
+ }
+ } while (--i > 0);
+ return "";
+ }
+
+ /************************************************************************
+ * IsImage
+ *
+ * Checks if the given filename is an image file.
+ ************************************************************************/
+
+ private static boolean isImage(final String iType) {
+ /* Get the file extension */
+ final String ext = getFileExtension(iType);
+
+ /* Compare it to the array of known image file extensions */
+ for (String s : imageExtensions) {
+ if (ext.equalsIgnoreCase(s)) {
+ return true;
+ }
+ }
+ return false;
+ }
+
+
+ /***********************************************************************
+ * IsSoundFile
+ *
+ * Checks if the given filename is a sound file.
+ ***********************************************************************/
+
+ private static AccessErrorCode isSoundFile(final String sType) {
+ final String ext = getFileExtension(sType);
+
+ for (int i = 0; i < soundExtensions.length; i++) {
+ if (ext.equalsIgnoreCase(soundExtensions[i])) {
+ return soundExtErrCodes[i];
+ }
+ }
+ return null;
+ }
+
+
+ /***********************************************************************
+ * IsValidSrcExtension
+ *
+ * Checks if the 'SRC' value within the FRAME element is valid
+ * The 'SRC' extension must end in ".htm", ".html", ".shtm", ".shtml",
+ * ".cfm", ".cfml", ".asp", ".cgi", ".pl", or ".smil"
+ ***********************************************************************/
+
+ private static boolean isValidSrcExtension(final String sType) {
+ final String ext = getFileExtension(sType);
+
+ for (String s : frameExtensions) {
+ if (ext.equalsIgnoreCase(s)) {
+ return true;
+ }
+ }
+ return false;
+ }
+
+
+ /*********************************************************************
+ * IsValidMediaExtension
+ *
+ * Checks to warn the user that synchronized text equivalents are
+ * required if multimedia is used.
+ *********************************************************************/
+
+ private static boolean isValidMediaExtension(final String sType) {
+ final String ext = getFileExtension(sType);
+
+ for (String s : mediaExtensions) {
+ if (ext.equalsIgnoreCase(s)) {
+ return true;
+ }
+ }
+ return false;
+ }
+
+
+ /************************************************************************
+ * IsWhitespace
+ *
+ * Checks if the given string is all whitespace.
+ ************************************************************************/
+
+ private static boolean isWhitespace(final String pString) {
+ if (pString == null) {
+ return true;
+ }
+ for (int i = 0; i < pString.length(); ++i) {
+ final char c = pString.charAt(i);
+ if (!TidyUtils.isWhite(c)) {
+ return false;
+ }
+ }
+ return true;
+ }
+
+ private static boolean hasValue(final AttVal av) {
+ return av != null && !isWhitespace(av.value);
+ }
+
+ /***********************************************************************
+ * IsPlaceholderAlt
+ *
+ * Checks to see if there is an image and photo place holder contained
+ * in the ALT text.
+ ***********************************************************************/
+
+ private static boolean isPlaceholderAlt(final String txt) {
+ return txt.contains("image") || txt.contains("photo");
+ }
+
+
+ /***********************************************************************
+ * IsPlaceHolderObject
+ *
+ * Checks to see if there is an OBJECT place holder contained
+ * in the 'ALT' text.
+ ***********************************************************************/
+
+ private static boolean isPlaceHolderObject(final String txt) {
+ return txt.contains("object");
+ }
+
+
+ /**********************************************************
+ * EndsWithBytes
+ *
+ * Checks to see if the ALT text ends with 'bytes'
+ **********************************************************/
+
+ private static boolean endsWithBytes(final String txt) {
+ return txt.endsWith("bytes");
+ }
+
+
+ /*******************************************************
+ * textFromOneNode
+ *
+ * Returns a list of characters contained within one
+ * text node.
+ *******************************************************/
+
+ private String textFromOneNode(final Lexer lexer, final Node node) {
+ if (node != null) {
+ /* Copy contents of a text node */
+ return TidyUtils.getString(lexer.lexbuf, node.start, node.end - node.start);
+ }
+ return "";
+ }
+
+
+ /*********************************************************
+ * getTextNode
+ *
+ * Locates text nodes within a container element.
+ * Retrieves text that are found contained within
+ * text nodes, and concatenates the text.
+ *********************************************************/
+
+ private void getTextNode(final Lexer lexer, final Node node) {
+ if (node.isText()) {
+ /* Retrieves each character found within the text node */
+ textNode.append(TidyUtils.getString(lexer.lexbuf, node.start, node.end - node.start));
+ }
+ }
+
+
+ /**********************************************************
+ * getTextNodeClear
+ *
+ * Clears the current 'textNode' and reloads it with new
+ * text. The textNode must be cleared before use.
+ **********************************************************/
+
+ private String getTextNodeClear(final Lexer lexer, final Node node) {
+ /* Clears list */
+ textNode.setLength(0);
+
+ getTextNode(lexer, node.content);
+ return textNode.toString();
+ }
+
+ /**********************************************************
+ * LevelX_Enabled
+ *
+ * Tell whether access "X" is enabled.
+ **********************************************************/
+
+ private boolean level1Enabled() {
+ return level == 1 || level == 2 || level == 3;
+ }
+
+ private boolean level2Enabled() {
+ return level == 2 || level == 3;
+ }
+
+ private boolean level3Enabled() {
+ return level == 3;
+ }
+
+ /********************************************************
+ * CheckColorAvailable
+ *
+ * Verify that information conveyed with color is
+ * available without color.
+ ********************************************************/
+
+ private void checkColorAvailable(final Lexer lexer, final Node node) {
+ if (level1Enabled()) {
+ switch (node.getId()) {
+ case IMG:
+ lexer.report.accessWarning(lexer, node, AccessErrorCode.INFORMATION_NOT_CONVEYED_IMAGE);
+ break;
+ case APPLET:
+ lexer.report.accessWarning(lexer, node, AccessErrorCode.INFORMATION_NOT_CONVEYED_APPLET);
+ break;
+ case OBJECT:
+ lexer.report.accessWarning(lexer, node, AccessErrorCode.INFORMATION_NOT_CONVEYED_OBJECT);
+ break;
+ case SCRIPT:
+ lexer.report.accessWarning(lexer, node, AccessErrorCode.INFORMATION_NOT_CONVEYED_SCRIPT);
+ break;
+ case INPUT:
+ lexer.report.accessWarning(lexer, node, AccessErrorCode.INFORMATION_NOT_CONVEYED_INPUT);
+ break;
+ }
+ }
+ }
+
+ /*********************************************************************
+ * CheckColorContrast
+ *
+ * Checks elements for color contrast. Must have valid contrast for
+ * valid visibility.
+ *
+ * This logic is extremely fragile as it does not recognize
+ * the fact that color is inherited by many components and
+ * that BG and FG colors are often set separately. E.g. the
+ * background color may be set by for the body or a table
+ * or a cell. The foreground color may be set by any text
+ * element (p, h1, h2, input, textarea), either explicitly
+ * or by style. Ergo, this test will not handle most real
+ * world cases. It's a start, however.
+ *********************************************************************/
+
+ private void checkColorContrast(final Lexer lexer, final Node node) {
+ int rgbBG[] = {255,255,255}; /* Black text on white BG */
+
+ if (level3Enabled()) {
+ boolean gotBG = true;
+ AttVal av;
+
+ /* Check for 'BGCOLOR' first to compare with other color attributes */
+ for (av = node.attributes; av != null; av = av.next) {
+ if (av.is(AttrId.BGCOLOR)) {
+ if (hasValue(av)) {
+ gotBG = getRgb(av.value, rgbBG);
+ }
+ }
+ }
+ /*
+ Search for COLOR attributes to compare with background color
+ Must have valid colour contrast
+ */
+ for (av = node.attributes; gotBG && av != null; av = av.next) {
+ AccessErrorCode errcode = null;
+ switch (av.getId()) {
+ case TEXT:
+ errcode = AccessErrorCode.COLOR_CONTRAST_TEXT;
+ break;
+ case LINK:
+ errcode = AccessErrorCode.COLOR_CONTRAST_LINK;
+ break;
+ case ALINK:
+ errcode = AccessErrorCode.COLOR_CONTRAST_ACTIVE_LINK;
+ break;
+ case VLINK:
+ errcode = AccessErrorCode.COLOR_CONTRAST_VISITED_LINK;
+ break;
+ }
+ if (errcode != null && hasValue(av)) {
+ int rgbFG[] = {0, 0, 0}; /* Black text */
+
+ if (getRgb(av.value, rgbFG) && !compareColors(rgbBG, rgbFG)) {
+ lexer.report.accessWarning(lexer, node, errcode);
+ }
+ }
+ }
+ }
+ }
+
+
+ /**************************************************************
+ * CompareColors
+ *
+ * Compares two RGB colors for good contrast.
+ **************************************************************/
+ private static int minmax(final int i1, final int i2) {
+ return Math.max(i1, i2) - Math.min(i1, i2);
+ }
+
+ private static int brightness(final int rgb[]) {
+ return ((rgb[0] * 299) + (rgb[1] * 587) + (rgb[2] * 114)) / 1000;
+ }
+
+ private static boolean compareColors(final int rgbBG[], final int rgbFG[]) {
+ int brightBG = brightness(rgbBG);
+ int brightFG = brightness(rgbFG);
+
+ int diffBright = minmax(brightBG, brightFG);
+ int diffColor = minmax(rgbBG[0], rgbFG[0]) + minmax(rgbBG[1], rgbFG[1]) + minmax(rgbBG[2], rgbFG[2]);
+
+ return diffBright > 180 && diffColor > 500;
+ }
+
+
+ /*********************************************************************
+ * GetRgb
+ *
+ * Gets the red, green and blue values for this attribute for the
+ * background.
+ *
+ * Example: If attribute is BGCOLOR="#121005" then red = 18, green = 16,
+ * blue = 5.
+ *********************************************************************/
+
+ private static boolean getRgb(final String color, final int rgb[]) {
+ /* Check if we have a color name */
+ for (int x = 0; x < colorNames.length; x++) {
+ if (colorNames[x].contains(color)) {
+ rgb[0] = colorValues[x][0];
+ rgb[1] = colorValues[x][1];
+ rgb[2] = colorValues[x][2];
+ return true;
+ }
+ }
+ /*
+ No color name so must be hex values
+ Is this a number in hexadecimal format?
+ */
+ /* Must be 7 characters in the RGB value (including '#') */
+ if (color.length() == 7 && color.charAt(0) == '#') {
+ rgb[0] = (ctox(color.charAt(1)) * 16) + ctox(color.charAt(2));
+ rgb[1] = (ctox(color.charAt(3)) * 16) + ctox(color.charAt(4));
+ rgb[2] = (ctox(color.charAt(5)) * 16) + ctox(color.charAt(6));
+ return true;
+ }
+ return false;
+ }
+
+
+ /*******************************************************************
+ * ctox
+ *
+ * Converts a character to a number.
+ * Example: if given character is 'A' then returns 10.
+ *
+ * Returns the number that the character represents. Returns -1 if not a
+ * valid number.
+ *******************************************************************/
+
+ private static int ctox(final char ch) {
+ if (ch >= '0' && ch <= '9') {
+ return ch - '0';
+ }
+ else if (ch >= 'a' && ch <= 'f') {
+ return ch - 'a' + 10;
+ }
+ else if (ch >= 'A' && ch <= 'F') {
+ return ch - 'A' + 10;
+ }
+ return -1;
+ }
+
+
+ /***********************************************************
+ * CheckImage
+ *
+ * Checks all image attributes for specific elements to
+ * check for validity of the values contained within
+ * the attributes. An appropriate warning message is displayed
+ * to indicate the error.
+ ***********************************************************/
+
+ private void checkImage(final Lexer lexer, Node node) {
+ if (level1Enabled()) {
+ boolean hasAlt = false;
+ boolean hasIsMap = false;
+ boolean hasLongDesc = false;
+ boolean hasDLINK = false;
+ boolean hasValidHeight = false;
+ boolean hasValidWidthBullet = false;
+ boolean hasValidWidthHR = false;
+ boolean hasTriggeredMissingLongDesc = false;
+
+ /* Checks all image attributes for invalid values within attributes */
+ for (AttVal av = node.attributes; av != null; av = av.next) {
+ /*
+ Checks for valid ALT attribute.
+ The length of the alt text must be less than 150 characters
+ long.
+ */
+ if (av.is(AttrId.ALT)) {
+ if (av.value != null) {
+ if (av.value.length() < 150 && !isPlaceholderAlt(av.value) && !isPlaceHolderObject(av.value)
+ && !endsWithBytes(av.value) && !isImage(av.value)) {
+ hasAlt = true;
+ }
+ else if (av.value.length() > 150) {
+ hasAlt = true;
+ lexer.report.accessWarning(lexer, node, AccessErrorCode.IMG_ALT_SUSPICIOUS_TOO_LONG);
+ }
+ else if (isImage(av.value)) {
+ hasAlt = true;
+ lexer.report.accessWarning(lexer, node, AccessErrorCode.IMG_ALT_SUSPICIOUS_FILENAME);
+ }
+ else if (isPlaceholderAlt(av.value)) {
+ hasAlt = true;
+ lexer.report.accessWarning(lexer, node, AccessErrorCode.IMG_ALT_SUSPICIOUS_PLACEHOLDER);
+ }
+ else if (endsWithBytes(av.value)) {
+ hasAlt = true;
+ lexer.report.accessWarning(lexer, node, AccessErrorCode.IMG_ALT_SUSPICIOUS_FILE_SIZE);
+ }
+ }
+ }
+ /*
+ Checks for width values of 'bullets' and 'horizontal
+ rules' for validity.
+
+ Valid pixel width for 'bullets' must be < 30, and > 150 for
+ horizontal rules.
+ */
+ else if (av.is(AttrId.WIDTH)) {
+ /* Longdesc attribute needed if width attribute is not present. */
+ if (hasValue(av)) {
+ int width = Integer.parseInt(av.value);
+ if (width < 30) {
+ hasValidWidthBullet = true;
+ }
+ if (width > 150) {
+ hasValidWidthHR = true;
+ }
+ }
+ }
+ /*
+ Checks for height values of 'bullets' and horizontal
+ rules for validity.
+
+ Valid pixel height for 'bullets' and horizontal rules
+ must be < 30.
+ */
+ else if (av.is(AttrId.HEIGHT)) {
+ /* Longdesc attribute needed if height attribute not present. */
+ if (hasValue(av) && Integer.parseInt(av.value) < 30) {
+ hasValidHeight = true;
+ }
+ }
+ /*
+ Checks for longdesc and determines validity.
+ The length of the 'longdesc' must be > 1
+ */
+ else if (av.is(AttrId.LONGDESC)) {
+ if (hasValue(av) && av.value.length() > 1) {
+ hasLongDesc = true;
+ }
+ }
+ /*
+ Checks for 'USEMAP' attribute. Ensures that
+ text links are provided for client-side image maps
+ */
+ else if (av.is(AttrId.USEMAP)) {
+ if (hasValue(av)) {
+ hasUseMap = true;
+ }
+ }
+ else if (av.is(AttrId.ISMAP)) {
+ hasIsMap = true;
+ }
+ }
+
+ /*
+ Check to see if a dLINK is present. The ANCHOR element must
+ be present following the IMG element. The text found between
+ the ANCHOR tags must be < 6 characters long, and must contain
+ the letter 'd'.
+ */
+ if (node.next.is(TagId.A)) {
+ node = node.next;
+ /*
+ Node following the anchor must be a text node
+ for dLINK to exist
+ */
+ if (node.content != null && node.content.tag == null) {
+ /* Number of characters found within the text node */
+ String word = textFromOneNode(lexer, node.content);
+ if (word.equals("d") || word.equals("D")) {
+ hasDLINK = true;
+ }
+ }
+ }
+ /*
+ Special case check for dLINK. This will occur if there is
+ whitespace between the <img> and <a> elements. Ignores
+ whitespace and continues check for dLINK.
+ */
+ if (node.next != null && node.next.tag == null) {
+ node = node.next;
+
+ if (node.next.is(TagId.A)) {
+ node = node.next;
+ /*
+ Node following the ANCHOR must be a text node
+ for dLINK to exist
+ */
+ if (node.content != null && node.content.tag == null) {
+ /* Number of characters found within the text node */
+ String word = textFromOneNode(lexer, node.content);
+
+ if (word.equals("d") || word.equals("D")) {
+ hasDLINK = true;
+ }
+ }
+ }
+ }
+
+ if (!hasAlt) {
+ lexer.report.accessError(lexer, node, AccessErrorCode.IMG_MISSING_ALT);
+ }
+ if (!hasLongDesc && hasValidHeight && (hasValidWidthHR || hasValidWidthBullet)) {
+ hasTriggeredMissingLongDesc = true;
+ }
+ if (!hasTriggeredMissingLongDesc) {
+ if (hasDLINK && !hasLongDesc) {
+ lexer.report.accessWarning(lexer, node, AccessErrorCode.IMG_MISSING_LONGDESC);
+ }
+ if (hasLongDesc && !hasDLINK) {
+ lexer.report.accessWarning(lexer, node, AccessErrorCode.IMG_MISSING_DLINK);
+ }
+ if (!hasLongDesc && !hasDLINK) {
+ lexer.report.accessWarning(lexer, node, AccessErrorCode.IMG_MISSING_LONGDESC_DLINK);
+ }
+ }
+ if (hasIsMap) {
+ lexer.report.accessError(lexer, node, AccessErrorCode.IMAGE_MAP_SERVER_SIDE_REQUIRES_CONVERSION);
+ lexer.report.accessWarning(lexer, node, AccessErrorCode.IMG_MAP_SERVER_REQUIRES_TEXT_LINKS);
+ }
+ }
+ }
+
+
+ /***********************************************************
+ * CheckApplet
+ *
+ * Checks APPLET element to check for validity pertaining
+ * the 'ALT' attribute. An appropriate warning message is
+ * displayed to indicate the error. An appropriate warning
+ * message is displayed to indicate the error. If no 'ALT'
+ * text is present, then there must be alternate content
+ * within the APPLET element.
+ ***********************************************************/
+
+ private void checkApplet(final Lexer lexer, final Node node) {
+ if (level1Enabled()) {
+ boolean hasAlt = false;
+ boolean hasDescription = false;
+
+ /* Checks for attributes within the APPLET element */
+ for (AttVal av = node.attributes; av != null; av = av.next) {
+ /*
+ Checks for valid ALT attribute.
+ The length of the alt text must be > 4 characters in length
+ but must be < 150 characters long.
+ */
+ if (av.is(AttrId.ALT)) {
+ if (av.value != null) {
+ hasAlt = true;
+ }
+ }
+ }
+ if (!hasAlt) {
+ /* Must have alternate text representation for that element */
+ if (node.content != null) {
+ String word = null;
+
+ if (node.content.tag == null) {
+ word = textFromOneNode(lexer, node.content);
+ }
+ if (node.content.content != null && node.content.content.tag == null) {
+ word = textFromOneNode(lexer, node.content.content);
+ }
+ if (word != null && !isWhitespace(word)) {
+ hasDescription = true;
+ }
+ }
+ }
+ if (!hasDescription && !hasAlt) {
+ lexer.report.accessError(lexer, node, AccessErrorCode.APPLET_MISSING_ALT);
+ }
+ }
+ }
+
+
+ /*******************************************************************
+ * CheckObject
+ *
+ * Checks to verify whether the OBJECT element contains
+ * 'ALT' text, and to see that the sound file selected is
+ * of a valid sound file type. OBJECT must have an alternate text
+ * representation.
+ *******************************************************************/
+
+ private void checkObject(final Lexer lexer, final Node node) {
+ if (level1Enabled()) {
+ boolean hasAlt = false;
+ boolean hasDescription = false;
+
+ if (node.content != null) {
+ if (!node.content.isText()) {
+ Node tnode = node.content;
+
+ for (AttVal av = tnode.attributes; av != null; av = av.next) {
+ if (av.is(AttrId.ALT)) {
+ hasAlt = true;
+ break;
+ }
+ }
+ }
+
+ /* Must have alternate text representation for that element */
+ if (!hasAlt) {
+ String word = null;
+ if (node.content.isText()) {
+ word = textFromOneNode(lexer, node.content);
+ }
+ if (word == null && node.content.content.isText()) {
+ word = textFromOneNode(lexer, node.content.content);
+ }
+ if (word != null && !isWhitespace(word)) {
+ hasDescription = true;
+ }
+ }
+ }
+
+ if (!hasAlt && !hasDescription) {
+ lexer.report.accessError(lexer, node, AccessErrorCode.OBJECT_MISSING_ALT);
+ }
+ }
+ }
+
+
+ /***************************************************************
+ * CheckMissingStyleSheets
+ *
+ * Ensures that stylesheets are used to control the presentation.
+ ***************************************************************/
+
+ private static boolean checkMissingStyleSheets(final Node node) {
+ boolean sspresent = false;
+
+ for (Node content = node.content; !sspresent && content != null; content = content.next) {
+ sspresent = content.is(TagId.LINK) || content.is(TagId.STYLE) || content.is(TagId.FONT)
+ || content.is(TagId.BASEFONT);
+
+ for (AttVal av = content.attributes; !sspresent && av != null; av = av.next) {
+ sspresent = av.is(AttrId.STYLE) || av.is(AttrId.TEXT) || av.is(AttrId.VLINK) || av.is(AttrId.ALINK)
+ || av.is(AttrId.LINK);
+
+ if (!sspresent && av.is(AttrId.REL)) {
+ sspresent = av.valueIs("stylesheet");
+ }
+ }
+
+ if (!sspresent) {
+ sspresent = checkMissingStyleSheets(content);
+ }
+ }
+ return sspresent;
+ }
+
+
+ /*******************************************************************
+ * CheckFrame
+ *
+ * Checks if the URL is valid and to check if a 'LONGDESC' is needed
+ * within the FRAME element. If a 'LONGDESC' is needed, the value must
+ * be valid. The URL must end with the file extension, htm, or html.
+ * Also, checks to ensure that the 'SRC' and 'TITLE' values are valid.
+ *******************************************************************/
+
+ private void checkFrame(final Lexer lexer, final Node node) {
+ boolean hasTitle = false;
+ numFrames++;
+
+ if (level1Enabled()) {
+ /* Checks for attributes within the FRAME element */
+ for (AttVal av = node.attributes; av != null; av = av.next) {
+ /* Checks if 'LONGDESC' value is valid only if present */
+ if (av.is(AttrId.LONGDESC)) {
+ if (hasValue(av) && av.value.length() > 1) {
+ hasCheckedLongDesc++;
+ }
+ }
+
+ /* Checks for valid 'SRC' value within the frame element */
+ else if (av.is(AttrId.SRC)) {
+ if (hasValue(av) && !isValidSrcExtension(av.value)) {
+ lexer.report.accessError(lexer, node, AccessErrorCode.FRAME_SRC_INVALID);
+ }
+ }
+
+ /* Checks for valid 'TITLE' value within frame element */
+ else if (av.is(AttrId.TITLE)) {
+ if (hasValue(av)) {
+ hasTitle = true;
+ }
+ if (!hasTitle) {
+ if (av.value == null || av.value.length() == 0) {
+ hasTitle = true;
+ lexer.report.accessError(lexer, node, AccessErrorCode.FRAME_TITLE_INVALID_NULL);
+ }
+ else {
+ if (isWhitespace(av.value) && av.value.length() > 0) {
+ hasTitle = true;
+ lexer.report.accessError(lexer, node, AccessErrorCode.FRAME_TITLE_INVALID_SPACES);
+ }
+ }
+ }
+ }
+ }
+ if (!hasTitle) {
+ lexer.report.accessError(lexer, node, AccessErrorCode.FRAME_MISSING_TITLE);
+ }
+ if (numFrames == 3 && hasCheckedLongDesc < 3) {
+ numFrames = 0;
+ lexer.report.accessWarning(lexer, node, AccessErrorCode.FRAME_MISSING_LONGDESC);
+ }
+ }
+ }
+
+
+ /****************************************************************
+ * CheckIFrame
+ *
+ * Checks if 'SRC' value is valid. Must end in appropriate
+ * file extension.
+ ****************************************************************/
+
+ private void checkIFrame(final Lexer lexer, final Node node) {
+ if (level1Enabled()) {
+ /* Checks for valid 'SRC' value within the IFRAME element */
+ final AttVal av = node.getAttrById(AttrId.SRC);
+ if (hasValue(av)) {
+ if (!isValidSrcExtension(av.value)) {
+ lexer.report.accessError(lexer, node, AccessErrorCode.FRAME_SRC_INVALID);
+ }
+ }
+ }
+ }
+
+
+ /**********************************************************************
+ * CheckAnchorAccess
+ *
+ * Checks that the sound file is valid, and to ensure that
+ * text transcript is present describing the 'HREF' within the
+ * ANCHOR element. Also checks to see ensure that the 'TARGET' attribute
+ * (if it exists) is not null and does not contain '_new' or '_blank'.
+ **********************************************************************/
+
+ private void checkAnchorAccess(final Lexer lexer, final Node node) {
+ boolean hasDescription = false;
+ boolean hasTriggeredLink = false;
+
+ /* Checks for attributes within the ANCHOR element */
+ for (AttVal av = node.attributes; av != null; av = av.next) {
+ if (level1Enabled()) {
+ /* Must be of valid sound file type */
+ if (av.is(AttrId.HREF)) {
+ if (hasValue(av)) {
+ String ext = getFileExtension (av.value);
+
+ /* Checks to see if multimedia is used */
+ if (isValidMediaExtension(av.value)) {
+ lexer.report.accessError(lexer, node, AccessErrorCode.MULTIMEDIA_REQUIRES_TEXT);
+ }
+ /*
+ Checks for validity of sound file, and checks to see if
+ the file is described within the document, or by a link
+ that is present which gives the description.
+ */
+ if (ext.length() < 6 && ext.length() > 0) {
+ AccessErrorCode errcode = isSoundFile(av.value);
+ if (errcode != null) {
+ if (node.next != null) {
+ if (node.next.tag == null) {
+ String word = textFromOneNode(lexer, node.next);
+
+ /* Must contain at least one letter in the text */
+ if (!isWhitespace(word)) {
+ hasDescription = true;
+ }
+ }
+ }
+
+ /* Must contain text description of sound file */
+ if (!hasDescription) {
+ lexer.report.accessError(lexer, node, errcode);
+ }
+ }
+ }
+ }
+ }
+ }
+
+ if (level2Enabled()) {
+ /* Checks 'TARGET' attribute for validity if it exists */
+ if (av.is(AttrId.TARGET)) {
+ if (av.valueIs("_new")) {
+ lexer.report.accessWarning(lexer, node, AccessErrorCode.NEW_WINDOWS_REQUIRE_WARNING_NEW);
+ }
+ else if (av.valueIs("_blank")) {
+ lexer.report.accessWarning(lexer, node, AccessErrorCode.NEW_WINDOWS_REQUIRE_WARNING_BLANK);
+ }
+ }
+ }
+ }
+
+ if (level2Enabled()) {
+ if (node.content != null && node.content.tag == null) {
+ String word = textFromOneNode(lexer, node.content);
+ if (word != null && !isWhitespace(word)) {
+ if (word.equals("more")) {
+ hasTriggeredLink = true;
+ }
+ if (word.equals("click here")) {
+ lexer.report.accessWarning(lexer, node, AccessErrorCode.LINK_TEXT_NOT_MEANINGFUL_CLICK_HERE);
+ }
+ if (hasTriggeredLink == false) {
+ if (word.length() < 6) {
+ lexer.report.accessWarning(lexer, node, AccessErrorCode.LINK_TEXT_NOT_MEANINGFUL);
+ }
+ }
+ if (word.length() > 60) {
+ lexer.report.accessWarning(lexer, node, AccessErrorCode.LINK_TEXT_TOO_LONG);
+ }
+ }
+ }
+ if (node.content == null) {
+ lexer.report.accessWarning(lexer, node, AccessErrorCode.LINK_TEXT_MISSING);
+ }
+ }
+ }
+
+
+ /************************************************************
+ * CheckArea
+ *
+ * Checks attributes within the AREA element to
+ * determine if the 'ALT' text and 'HREF' values are valid.
+ * Also checks to see ensure that the 'TARGET' attribute
+ * (if it exists) is not null and does not contain '_new'
+ * or '_blank'.
+ ************************************************************/
+
+ private void checkArea(final Lexer lexer, final Node node) {
+ boolean hasAlt = false;
+
+ /* Checks all attributes within the AREA element */
+ for (AttVal av = node.attributes; av != null; av = av.next) {
+ if (level1Enabled()) {
+ /*
+ Checks for valid ALT attribute.
+ The length of the alt text must be > 4 characters long
+ but must be less than 150 characters long.
+ */
+ if (av.is(AttrId.ALT)) {
+ /* The check for validity */
+ if (av.value != null) {
+ hasAlt = true;
+ }
+ }
+ }
+
+ if (level2Enabled()) {
+ if (av.is(AttrId.TARGET)) {
+ if (av.valueIs("_new")) {
+ lexer.report.accessWarning(lexer, node, AccessErrorCode.NEW_WINDOWS_REQUIRE_WARNING_NEW);
+ }
+ else if (av.valueIs("_blank")) {
+ lexer.report.accessWarning(lexer, node, AccessErrorCode.NEW_WINDOWS_REQUIRE_WARNING_BLANK);
+ }
+ }
+ }
+ }
+
+ if (level1Enabled()) {
+ /* AREA must contain alt text */
+ if (!hasAlt) {
+ lexer.report.accessError(lexer, node, AccessErrorCode.AREA_MISSING_ALT);
+ }
+ }
+ }
+
+
+ /***************************************************
+ * CheckScript
+ *
+ * Checks the SCRIPT element to ensure that a
+ * NOSCRIPT section follows the SCRIPT.
+ ***************************************************/
+
+ private void checkScriptAcc(final Lexer lexer, final Node node) {
+ if (level1Enabled()) {
+ /* NOSCRIPT element must appear immediately following SCRIPT element */
+ if (node.next == null || !node.next.is(TagId.NOSCRIPT)) {
+ lexer.report.accessError(lexer, node, AccessErrorCode.SCRIPT_MISSING_NOSCRIPT);
+ }
+ }
+ }
+
+
+ /**********************************************************
+ * CheckRows
+ *
+ * Check to see that each table has a row of headers if
+ * a column of columns doesn't exist.
+ **********************************************************/
+
+ private void checkRows(final Lexer lexer, Node node) {
+ int numTR = 0;
+ int numValidTH = 0;
+ checkedHeaders++;
+
+ for (; node != null; node = node.next) {
+ numTR++;
+ if (node.content.is(TagId.TH)) {
+ hasTH = true;
+ if (node.content.content.isText()) {
+ String word = textFromOneNode(lexer, node.content.content);
+ if (!isWhitespace(word)) {
+ numValidTH++;
+ }
+ }
+ }
+ }
+ if (numTR == numValidTH) {
+ hasValidRowHeaders = true;
+ }
+ if (numTR >= 2 && numTR > numValidTH && numValidTH >= 2 && hasTH) {
+ hasInvalidRowHeader = true;
+ }
+ }
+
+
+ /**********************************************************
+ * CheckColumns
+ *
+ * Check to see that each table has a column of headers if
+ * a row of columns doesn't exist.
+ **********************************************************/
+
+ private void checkColumns(final Lexer lexer, final Node node) {
+ int numTH = 0;
+ boolean isMissingHeader = false;
+
+ checkedHeaders++;
+
+ /* Table must have row of headers if headers for columns don't exist */
+ if (node.content.is(TagId.TH)) {
+ hasTH = true;
+
+ for (Node tnode = node.content; tnode != null; tnode = tnode.next) {
+ if (tnode.is(TagId.TH)) {
+ if (tnode.content.isText()) {
+ String word = textFromOneNode(lexer, tnode.content);
+ if (!isWhitespace(word)) {
+ numTH++;
+ }
+ }
+ }
+ else {
+ isMissingHeader = true;
+ }
+ }
+ }
+
+ if (!isMissingHeader && numTH > 0) {
+ hasValidColumnHeaders = true;
+ }
+ if (isMissingHeader && numTH >= 2) {
+ hasInvalidColumnHeader = true;
+ }
+ }
+
+
+ /*****************************************************
+ * CheckTH
+ *
+ * Checks to see if the header provided for a table
+ * requires an abbreviation. (only required if the
+ * length of the header is greater than 15 characters)
+ *****************************************************/
+
+ private void checkTH(final Lexer lexer, final Node node) {
+ if (level3Enabled()) {
+ boolean hasAbbr = false;
+
+ /* Checks TH element for 'ABBR' attribute */
+ for (AttVal av = node.attributes; av != null; av = av.next) {
+ if (av.is(AttrId.ABBR)) {
+ /* Value must not be null and must be less than 15 characters */
+ if (av.value != null && !isWhitespace(av.value)) {
+ hasAbbr = true;
+ }
+ if (av.value == null || av.value.length() == 0) {
+ hasAbbr = true;
+ lexer.report.accessWarning(lexer, node, AccessErrorCode.TABLE_MAY_REQUIRE_HEADER_ABBR_NULL);
+ }
+ if (isWhitespace(av.value) && av.value.length() > 0) {
+ hasAbbr = true;
+ lexer.report.accessWarning(lexer, node, AccessErrorCode.TABLE_MAY_REQUIRE_HEADER_ABBR_SPACES);
+ }
+ }
+ }
+
+ /* If the header is greater than 15 characters, an abbreviation is needed */
+ final String word = textFromOneNode(lexer, node.content);
+
+ if (word != null && !isWhitespace(word)) {
+ /* Must have 'ABBR' attribute if header is > 15 characters */
+ if (word.length() > 15 && !hasAbbr) {
+ lexer.report.accessWarning(lexer, node, AccessErrorCode.TABLE_MAY_REQUIRE_HEADER_ABBR);
+ }
+ }
+ }
+ }
+
+
+ /*****************************************************************
+ * CheckMultiHeaders
+ *
+ * Layout tables should make sense when linearized.
+ * TABLE must contain at least one TH element.
+ * This technique applies only to tables used for layout purposes,
+ * not to data tables. Checks for column of multiple headers.
+ *****************************************************************/
+
+ private void checkMultiHeaders(final Lexer lexer, final Node node) {
+ if (level1Enabled()) {
+ boolean validColSpanRows = true;
+ boolean validColSpanColumns = true;
+
+ int flag = 0;
+
+ if (node.content != null) {
+ Node tnode = node.content;
+ /*
+ Checks for column of multiple headers found
+ within a data table.
+ */
+ while (tnode != null) {
+ if (tnode.is(TagId.TR)) {
+ if (tnode.content != null) {
+ Node temp = tnode.content;
+
+ /* The number of TH elements found within TR element */
+ if (flag == 0) {
+ while (temp != null) {
+ /*
+ Must contain at least one TH element
+ within in the TR element
+ */
+ if (temp.is(TagId.TH)) {
+ for (AttVal av = temp.attributes; av != null; av = av.next) {
+ if (av.is(AttrId.COLSPAN) && (Integer.parseInt(av.value) > 1)) {
+ validColSpanColumns = false;
+ }
+ if (av.is(AttrId.ROWSPAN) && (Integer.parseInt(av.value) > 1)) {
+ validColSpanRows = false;
+ }
+ }
+ }
+ temp = temp.next;
+ }
+ flag = 1;
+ }
+ }
+ }
+ tnode = tnode.next;
+ }
+ /* Displays HTML 4 Table Algorithm when multiple column of headers used */
+ if (!validColSpanRows) {
+ lexer.report.accessWarning(lexer, node, AccessErrorCode.DATA_TABLE_REQUIRE_MARKUP_ROW_HEADERS);
+ lexer.report.displayHTMLTableAlgorithm(lexer);
+ }
+ if (!validColSpanColumns) {
+ lexer.report.accessWarning(lexer, node, AccessErrorCode.DATA_TABLE_REQUIRE_MARKUP_COLUMN_HEADERS);
+ lexer.report.displayHTMLTableAlgorithm(lexer);
+ }
+ }
+ }
+ }
+
+
+ /****************************************************
+ * CheckTable
+ *
+ * Checks the TABLE element to ensure that the
+ * table is not missing any headers. Must have either
+ * a row or column of headers.
+ ****************************************************/
+
+ private void checkTable(final Lexer lexer, final Node node) {
+ int numTR = 0;
+ boolean hasSummary = false;
+ boolean hasCaption = false;
+
+ if (level3Enabled()) {
+ /* Table must have a 'SUMMARY' describing the purpose of the table */
+ for (AttVal av = node.attributes; av != null; av = av.next) {
+ if (av.is(AttrId.SUMMARY)) {
+ if (hasValue(av)) {
+ hasSummary = true;
+ if (av.contains("summary") && av.contains("table")) {
+ lexer.report.accessError(lexer, node, AccessErrorCode.TABLE_SUMMARY_INVALID_PLACEHOLDER);
+ }
+ }
+ if (av.value == null || av.value.length() == 0) {
+ hasSummary = true;
+ lexer.report.accessError(lexer, node, AccessErrorCode.TABLE_SUMMARY_INVALID_NULL);
+ }
+ else if (isWhitespace(av.value) && av.value.length() > 0) {
+ hasSummary = true;
+ lexer.report.accessError(lexer, node, AccessErrorCode.TABLE_SUMMARY_INVALID_SPACES);
+ }
+ }
+ }
+
+ /* TABLE must have content. */
+ if (node.content == null) {
+ lexer.report.accessError(lexer, node, AccessErrorCode.DATA_TABLE_MISSING_HEADERS);
+ return;
+ }
+ }
+
+ if (level1Enabled()) {
+ /* Checks for multiple headers */
+ checkMultiHeaders(lexer, node);
+ }
+
+ if (level2Enabled()) {
+ /* Table must have a CAPTION describing the purpose of the table */
+ if (node.content.is(TagId.CAPTION)) {
+ Node tnode = node.content;
+ String word = null;
+
+ if (tnode.content != null && tnode.content.tag == null) {
+ word = getTextNodeClear(lexer, tnode);
+ }
+ if (!isWhitespace(word)) {
+ hasCaption = true;
+ }
+ }
+ if (!hasCaption) {
+ lexer.report.accessError(lexer, node, AccessErrorCode.TABLE_MISSING_CAPTION);
+ }
+ }
+
+ if (node.content != null) {
+ if (node.content.is(TagId.CAPTION) && node.content.next != null && node.content.next.is(TagId.TR)) {
+ checkColumns(lexer, node.content.next);
+ }
+ else if (node.content.is(TagId.TR)) {
+ checkColumns(lexer, node.content);
+ }
+ }
+ if (!hasValidColumnHeaders) {
+ if (node.content != null) {
+ if (node.content.is(TagId.CAPTION) && node.content.next != null && node.content.next.is(TagId.TR)) {
+ checkRows(lexer, node.content.next);
+ }
+ else if (node.content.is(TagId.TR)) {
+ checkRows(lexer, node.content);
+ }
+ }
+ }
+
+ if (level3Enabled()) {
+ /* Suppress warning for missing 'SUMMARY for HTML 2.0 and HTML 3.2 */
+ if (!hasSummary) {
+ lexer.report.accessError(lexer, node, AccessErrorCode.TABLE_MISSING_SUMMARY);
+ }
+ }
+
+ if (level2Enabled()) {
+ if (node.content != null) {
+ Node temp = node.content;
+
+ while (temp != null) {
+ if (temp.is(TagId.TR)) {
+ numTR++;
+ }
+ temp = temp.next;
+ }
+
+ if (numTR == 1) {
+ lexer.report.accessWarning(lexer, node, AccessErrorCode.LAYOUT_TABLES_LINEARIZE_PROPERLY);
+ }
+ }
+ if (hasTH) {
+ lexer.report.accessWarning(lexer, node, AccessErrorCode.LAYOUT_TABLE_INVALID_MARKUP);
+ }
+ }
+
+ if (level1Enabled()) {
+ if (checkedHeaders == 2) {
+ if (!hasValidRowHeaders && !hasValidColumnHeaders && !hasInvalidRowHeader && !hasInvalidColumnHeader) {
+ lexer.report.accessError(lexer, node, AccessErrorCode.DATA_TABLE_MISSING_HEADERS);
+ }
+ if (!hasValidRowHeaders && hasInvalidRowHeader) {
+ lexer.report.accessError(lexer, node, AccessErrorCode.DATA_TABLE_MISSING_HEADERS_ROW);
+ }
+
+ if (!hasValidColumnHeaders && hasInvalidColumnHeader) {
+ lexer.report.accessError(lexer, node, AccessErrorCode.DATA_TABLE_MISSING_HEADERS_COLUMN);
+ }
+ }
+ }
+ }
+
+
+ /***************************************************
+ * CheckASCII
+ *
+ * Checks for valid text equivalents for XMP and PRE
+ * elements for ASCII art. Ensures that there is
+ * a skip over link to skip multi-lined ASCII art.
+ ***************************************************/
+
+ private void checkASCII(final Lexer lexer, final Node node) {
+ String skipOver = null;
+ boolean IsAscii = false;
+ int hasSkipOverLink = 0;
+
+ int newLines = -1;
+ char compareLetter;
+ int matchingCount = 0;
+
+ if (level1Enabled() && node.content != null) {
+ /*
+ Checks the text within the PRE and XMP tags to see if ascii
+ art is present
+ */
+ for (int i = node.content.start + 1; i < node.content.end; i++) {
+ matchingCount = 0;
+
+ /* Counts the number of lines of text */
+ if (lexer.lexbuf[i] == '\n') {
+ newLines++;
+ }
+ compareLetter = (char) lexer.lexbuf[i];
+
+ /* Counts consecutive character matches */
+ for (int x = i; x < i + 5; x++) {
+ if (lexer.lexbuf[x] == compareLetter) {
+ matchingCount++;
+ }
+ else {
+ break;
+ }
+ }
+
+ /* Must have at least 5 consecutive character matches */
+ if (matchingCount >= 5) {
+ break;
+ }
+ }
+ /*
+ Must have more than 6 lines of text OR 5 or more consecutive
+ letters that are the same for there to be ascii art
+ */
+ if (newLines >= 6 || matchingCount >= 5) {
+ IsAscii = true;
+ }
+
+ /* Checks for skip over link if ASCII art is present */
+ if (IsAscii) {
+ if (node.prev != null && node.prev.prev != null) {
+ final Node temp1 = node.prev.prev;
+
+ /* Checks for 'HREF' attribute */
+ for (AttVal av = temp1.attributes; av != null; av = av.next) {
+ if (av.is(AttrId.HREF) && hasValue(av)) {
+ skipOver = av.value;
+ hasSkipOverLink++;
+ }
+ }
+ }
+ }
+ }
+
+ if (level2Enabled()) {
+ /*
+ Checks for A element following PRE to ensure proper skipover link
+ only if there is an A element preceding PRE.
+ */
+ if (hasSkipOverLink == 1) {
+ if (node.next.is(TagId.A)) {
+ final Node temp2 = node.next;
+
+ /* Checks for 'NAME' attribute */
+ for (AttVal av = temp2.attributes; av != null; av = av.next) {
+ if (av.is(AttrId.NAME) && hasValue(av)) {
+ /*
+ Value within the 'HREF' attribute must be the same
+ as the value within the 'NAME' attribute for valid
+ skipover.
+ */
+ if (skipOver.contains(av.value)) {
+ hasSkipOverLink++;
+ }
+ }
+ }
+ }
+ }
+
+ if (IsAscii) {
+ lexer.report.accessError(lexer, node, AccessErrorCode.ASCII_REQUIRES_DESCRIPTION);
+ if (level3Enabled() && hasSkipOverLink < 2) {
+ lexer.report.accessError(lexer, node, AccessErrorCode.SKIPOVER_ASCII_ART);
+ }
+ }
+ }
+ }
+
+
+ /***********************************************************
+ * CheckFormControls
+ *
+ * <form> must have valid 'FOR' attribute, and <label> must
+ * have valid 'ID' attribute for valid form control.
+ ***********************************************************/
+
+ private void checkFormControls(final Lexer lexer, final Node node) {
+ if (!hasValidFor && hasValidId) {
+ lexer.report.accessError(lexer, node, AccessErrorCode.ASSOCIATE_LABELS_EXPLICITLY_FOR);
+ }
+ if (!hasValidId && hasValidFor) {
+ lexer.report.accessError(lexer, node, AccessErrorCode.ASSOCIATE_LABELS_EXPLICITLY_ID);
+ }
+ if (!hasValidId && !hasValidFor) {
+ lexer.report.accessError(lexer, node, AccessErrorCode.ASSOCIATE_LABELS_EXPLICITLY);
+ }
+ }
+
+
+ /************************************************************
+ * CheckLabel
+ *
+ * Check for valid 'FOR' attribute within the LABEL element
+ ************************************************************/
+
+ private void checkLabel(final Lexer lexer, final Node node) {
+ if (level2Enabled()) {
+ /* Checks for valid 'FOR' attribute */
+ final AttVal av = node.getAttrById(AttrId.FOR);
+ if (hasValue(av)) {
+ hasValidFor = true;
+ }
+ if (++forID == 2) {
+ forID = 0;
+ checkFormControls(lexer, node);
+ }
+ }
+ }
+
+
+ /************************************************************
+ * CheckInputLabel
+ *
+ * Checks for valid 'ID' attribute within the INPUT element.
+ * Checks to see if there is a LABEL directly before
+ * or after the INPUT element determined by the 'TYPE'.
+ * Each INPUT element must have a LABEL describing the form.
+ ************************************************************/
+
+ private void checkInputLabel(final Lexer lexer, final Node node) {
+ if (level2Enabled()) {
+ /* Checks attributes within the INPUT element */
+ for (AttVal av = node.attributes; av != null; av = av.next) {
+ /* Must have valid 'ID' value */
+ if (av.is(AttrId.ID) && hasValue(av)) {
+ hasValidId = true;
+ }
+ }
+ if (++forID == 2) {
+ forID = 0;
+ checkFormControls(lexer, node);
+ }
+ }
+ }
+
+
+ /***************************************************************
+ * CheckInputAttributes
+ *
+ * INPUT element must have a valid 'ALT' attribute if the
+ * 'VALUE' attribute is present.
+ ***************************************************************/
+
+ private void checkInputAttributes(final Lexer lexer, final Node node) {
+ boolean hasAlt = false;
+ boolean mustHaveAlt = false;
+
+ /* Checks attributes within the INPUT element */
+ for (AttVal av = node.attributes; av != null; av = av.next) {
+ /* 'VALUE' must be found if the 'TYPE' is 'text' or 'checkbox' */
+ if (av.is(AttrId.TYPE) && hasValue(av)) {
+ if (level1Enabled()) {
+ if (av.valueIs("image")) {
+ mustHaveAlt = true;
+ }
+ }
+ }
+ if (av.is(AttrId.ALT) && hasValue(av)) {
+ hasAlt = true;
+ }
+ }
+ if (mustHaveAlt && !hasAlt) {
+ lexer.report.accessError(lexer, node, AccessErrorCode.IMG_BUTTON_MISSING_ALT);
+ }
+ }
+
+
+ /***************************************************************
+ * CheckFrameSet
+ *
+ * Frameset must have valid NOFRAME section. Must contain some
+ * text but must not contain information telling user to update
+ * browsers,
+ ***************************************************************/
+
+ private void checkFrameSet(final Lexer lexer, final Node node) {
+ boolean hasNoFrames = false;
+
+ if (level1Enabled()) {
+ if ((lexer.badAccess & Report.INVALID_LINK_NOFRAMES) != 0) {
+ lexer.report.accessError(lexer, node, AccessErrorCode.NOFRAMES_INVALID_LINK);
+ lexer.badAccess &= ~Report.INVALID_LINK_NOFRAMES; /* emit only once */
+ }
+ for (Node temp = node.content; temp != null ; temp = temp.next) {
+ if (temp.is(TagId.NOFRAMES)) {
+ hasNoFrames = true;
+
+ if (temp.content != null && temp.content.content.is(TagId.P)) {
+ final Node para = temp.content.content;
+ if (para.content.isText()) {
+ final String word = textFromOneNode(lexer, para.content);
+ if (word != null && word.contains("browser")) {
+ lexer.report.accessError(lexer, para, AccessErrorCode.NOFRAMES_INVALID_CONTENT);
+ }
+ }
+ }
+ else if (temp.content == null) {
+ lexer.report.accessError(lexer, temp, AccessErrorCode.NOFRAMES_INVALID_NO_VALUE);
+ }
+ else if (temp.content != null && isWhitespace(textFromOneNode(lexer, temp.content))) {
+ lexer.report.accessError(lexer, temp, AccessErrorCode.NOFRAMES_INVALID_NO_VALUE);
+ }
+ }
+ }
+ if (!hasNoFrames) {
+ lexer.report.accessError(lexer, node, AccessErrorCode.FRAME_MISSING_NOFRAMES);
+ }
+ }
+ }
+
+
+ /***********************************************************
+ * CheckHeaderNesting
+ *
+ * Checks for heading increases and decreases. Headings must
+ * not increase by more than one header level, but may
+ * decrease at from any level to any level. Text within
+ * headers must not be more than 20 words in length.
+ ***********************************************************/
+
+ private void checkHeaderNesting(final Lexer lexer, final Node node) {
+ if (level2Enabled()) {
+ int numWords = 1;
+ boolean isValidIncrease = false;
+ boolean needsDescription = false;
+ /*
+ Text within header element cannot contain more than 20 words without
+ a separate description
+ */
+ if (node.content != null && node.content.tag == null) {
+ final String word = textFromOneNode(lexer, node.content);
+
+ for (int i = 0; i < word.length(); i++) {
+ if (word.charAt(i) == ' ') {
+ numWords++;
+ }
+ }
+ if (numWords > 20) {
+ needsDescription = true;
+ }
+ }
+
+ /* Header following must be same level or same plus 1 for
+ ** valid heading increase size. E.g. H1 . H1, H2. H3 . H3, H4
+ */
+ if (node.isHeader()) {
+ int level = node.getHeaderLevel();
+ isValidIncrease = true;
+
+ for (Node temp = node.next; temp != null; temp = temp.next) {
+ final int nested = temp.getHeaderLevel();
+ if (nested >= level) {
+ isValidIncrease = nested <= level + 1;
+ break;
+ }
+ }
+ }
+ if (!isValidIncrease) {
+ lexer.report.accessWarning(lexer, node, AccessErrorCode.HEADERS_IMPROPERLY_NESTED);
+ }
+ if (needsDescription) {
+ lexer.report.accessWarni...
[truncated message content] |
|
From: <ad...@us...> - 2010-11-23 12:41:31
|
Revision: 1232
http://jtidy.svn.sourceforge.net/jtidy/?rev=1232&view=rev
Author: aditsu
Date: 2010-11-23 12:41:24 +0000 (Tue, 23 Nov 2010)
Log Message:
-----------
fixed test 1359292 - corrected discarding of empty paragraphs, moved xmlns attribute handling to parseDocument, removed early returns from attrError (to update counts) and added a message about incomplete warning/error reporting
Modified Paths:
--------------
branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Clean.java
branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/ParserImpl.java
branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Report.java
branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/TagCheckImpl.java
branches/CodeUpdateAndJava5/src/main/resources/org/w3c/tidy/TidyMessages.properties
Modified: branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Clean.java
===================================================================
--- branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Clean.java 2010-11-23 04:24:37 UTC (rev 1231)
+++ branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Clean.java 2010-11-23 12:41:24 UTC (rev 1232)
@@ -2226,9 +2226,8 @@
}
// discard empty paragraphs
- if (node.content == null && node.is(TagId.P))
- {
- node = Node.discardElement(node);
+ if (node.content == null && node.is(TagId.P)) {
+ node = Node.trimEmptyElement(lexer, node);
continue;
}
Modified: branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/ParserImpl.java
===================================================================
--- branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/ParserImpl.java 2010-11-23 04:24:37 UTC (rev 1231)
+++ branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/ParserImpl.java 2010-11-23 12:41:24 UTC (rev 1232)
@@ -66,6 +66,10 @@
*/
public final class ParserImpl
{
+ /**
+ * xhtml namespace String.
+ */
+ private static final String XHTML_NAMESPACE = "http://www.w3.org/1999/xhtml";
/**
* parser for html.
@@ -3601,7 +3605,24 @@
lexer.report.warning(lexer, document, node, ErrorCode.DISCARDING_UNEXPECTED); // TODO?
continue;
}
+
+ if (node.type == NodeType.StartTag && node.is(TagId.HTML)) {
+ final AttVal xmlns = node.getAttrById(AttrId.XMLNS);
+ if (xmlns != null && xmlns.valueIs(XHTML_NAMESPACE)) {
+ final boolean htmlOut = lexer.configuration.isHtmlOut();
+ // Unless plain HTML is specified, output will be XHTML.
+ lexer.isvoyager = true;
+ lexer.configuration.setXHTML(!htmlOut);
+ lexer.configuration.setXmlOut(!htmlOut);
+ // adjust other config options, just as in Configuration
+ if (!htmlOut) {
+ lexer.configuration.setUpperCaseTags(false);
+ lexer.configuration.setUpperCaseAttrs(false);
+ }
+ }
+ }
+
if (node.type != NodeType.StartTag || !node.is(TagId.HTML))
{
lexer.ungetToken();
Modified: branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Report.java
===================================================================
--- branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Report.java 2010-11-23 04:24:37 UTC (rev 1231)
+++ branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Report.java 2010-11-23 12:41:24 UTC (rev 1232)
@@ -530,16 +530,6 @@
*/
public void attrError(Lexer lexer, Node node, AttVal attribute, ErrorCode code)
{
- if (lexer.errors > lexer.configuration.getShowErrors()) // keep quiet after <showErrors> errors
- {
- return;
- }
-
- if (!lexer.configuration.isShowWarnings()) // warnings
- {
- return;
- }
-
final String tagdesc = getTagName(node);
final String name = attribute == null || attribute.attribute == null ? "NULL" : attribute.attribute;
final String value = attribute == null || attribute.value == null ? "NULL" : attribute.value;
@@ -1052,18 +1042,13 @@
* @param errout PrintWriter
* @param lexer Lexer
*/
- public void reportNumWarnings(PrintWriter errout, Lexer lexer)
- {
- if (lexer.warnings > 0 || lexer.errors > 0)
- {
- printMessage(
- errout,
- Level.SUMMARY,
- "num_warnings",
- lexer.warnings, lexer.errors);
+ public void reportNumWarnings(PrintWriter errout, Lexer lexer) {
+ if (lexer.warnings > 0 || lexer.errors > 0) {
+ final int incomplete = lexer.errors > lexer.configuration.getShowErrors()
+ || !lexer.configuration.isShowWarnings() ? 1 : 0;
+ printMessage(errout, Level.SUMMARY, "num_warnings", lexer.warnings, lexer.errors, incomplete);
}
- else
- {
+ else {
printMessage(errout, Level.SUMMARY, "no_warnings");
}
}
Modified: branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/TagCheckImpl.java
===================================================================
--- branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/TagCheckImpl.java 2010-11-23 04:24:37 UTC (rev 1231)
+++ branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/TagCheckImpl.java 2010-11-23 12:41:24 UTC (rev 1232)
@@ -148,40 +148,11 @@
*/
public static class CheckHTML implements TagCheck
{
-
/**
- * xhtml namepace String.
- */
- private static final String XHTML_NAMESPACE = "http://www.w3.org/1999/xhtml";
-
- /**
* @see org.w3c.tidy.TagCheck#check(org.w3c.tidy.Lexer, org.w3c.tidy.Node)
*/
- public void check(Lexer lexer, Node node)
- {
-
- AttVal attval;
- AttVal xmlns;
-
- xmlns = node.getAttrByName("xmlns");
-
- if (xmlns != null && XHTML_NAMESPACE.equals(xmlns.value))
- {
- lexer.isvoyager = true;
- if (!lexer.configuration.isHtmlOut()) // Unless user has specified plain HTML output,
- {
- lexer.configuration.setXHTML(true); // output format will be XHTML.
- }
- // adjust other config options, just as in Configuration
- lexer.configuration.setXmlOut(true);
- lexer.configuration.setUpperCaseTags(false);
- lexer.configuration.setUpperCaseAttrs(false);
- }
-
- for (attval = node.attributes; attval != null; attval = attval.next)
- {
- attval.checkAttribute(lexer, node);
- }
+ public void check(Lexer lexer, Node node) {
+ node.checkAttributes(lexer);
}
}
Modified: branches/CodeUpdateAndJava5/src/main/resources/org/w3c/tidy/TidyMessages.properties
===================================================================
--- branches/CodeUpdateAndJava5/src/main/resources/org/w3c/tidy/TidyMessages.properties 2010-11-23 04:24:37 UTC (rev 1231)
+++ branches/CodeUpdateAndJava5/src/main/resources/org/w3c/tidy/TidyMessages.properties 2010-11-23 12:41:24 UTC (rev 1232)
@@ -86,7 +86,7 @@
no_warnings=No warnings or errors were found.\n
noframes_content={0} not inside ''noframes'' element
non_matching_endtag=replacing unexpected {0} by </{1}>
-num_warnings={0,choice,0#0 warnings|1#1 warning|1<{0,number,integer} warnings}, {1,choice,0#0 errors|1#1 error|2#{1,number,integer} errors} were found!\n
+num_warnings={0,choice,0#0 warnings|1#1 warning|1<{0,number,integer} warnings}, {1,choice,0#0 errors|1#1 error|2#{1,number,integer} errors} were found!{2,choice,0#|1# Not all warnings/errors were shown.}\n
obsolete_element=replacing obsolete element {0} by {1}
previous_location=<{0}> previously mentioned
proprietary_attr_value={0} proprietary attribute value "{1}"
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
|
From: <ad...@us...> - 2010-11-23 04:24:44
|
Revision: 1231
http://jtidy.svn.sourceforge.net/jtidy/?rev=1231&view=rev
Author: aditsu
Date: 2010-11-23 04:24:37 +0000 (Tue, 23 Nov 2010)
Log Message:
-----------
fixed tests 1067112 and 2085175 - corrected identification of word documents
Modified Paths:
--------------
branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Clean.java
Modified: branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Clean.java
===================================================================
--- branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Clean.java 2010-11-22 10:02:10 UTC (rev 1230)
+++ branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Clean.java 2010-11-23 04:24:37 UTC (rev 1231)
@@ -2145,8 +2145,7 @@
if (node.is(TagId.HTML))
{
// check that it's a Word 2000 document
- if ((node.getAttrByName("xmlns:o") == null))
- {
+ if (node.getAttrByName("xmlns:o") == null && !lexer.configuration.isMakeBare()) {
return;
}
lexer.configuration.tt.freeAttrs(node);
@@ -2357,8 +2356,7 @@
continue;
}
- if (!"generator".equals(attval.value))
- {
+ if (!attval.valueIs("generator")) {
continue;
}
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
|
From: <ad...@us...> - 2010-11-22 10:02:16
|
Revision: 1230
http://jtidy.svn.sourceforge.net/jtidy/?rev=1230&view=rev
Author: aditsu
Date: 2010-11-22 10:02:10 +0000 (Mon, 22 Nov 2010)
Log Message:
-----------
fixed test 1263391 - updated ParseInline to allow P within ADDRESS in transitional html versions
Modified Paths:
--------------
branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/ParserImpl.java
Modified: branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/ParserImpl.java
===================================================================
--- branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/ParserImpl.java 2010-11-22 09:09:53 UTC (rev 1229)
+++ branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/ParserImpl.java 2010-11-22 10:02:10 UTC (rev 1230)
@@ -1246,6 +1246,14 @@
continue;
}
+ /* <p> allowed within <address> in HTML 4.01 Transitional */
+ if (node.is(TagId.P) && node.type == NodeType.StartTag && element.is(TagId.ADDRESS)) {
+ lexer.constrainVersion(~VERS_HTML40_STRICT);
+ element.insertNodeAtEnd(node);
+ parseTag(lexer, node, mode);
+ continue;
+ }
+
// ignore unknown and PARAM tags
if (node.tag == null || node.is(TagId.PARAM))
{
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
|
From: <ad...@us...> - 2010-11-22 09:09:59
|
Revision: 1229
http://jtidy.svn.sourceforge.net/jtidy/?rev=1229&view=rev
Author: aditsu
Date: 2010-11-22 09:09:53 +0000 (Mon, 22 Nov 2010)
Log Message:
-----------
fixed test 1068087 - modified fontSize2Name to return null for empty strings, and added a special constant to deal with attribute values that wrongly end up empty in Tidy
Modified Paths:
--------------
branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/AttVal.java
branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Clean.java
branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Lexer.java
Modified: branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/AttVal.java
===================================================================
--- branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/AttVal.java 2010-11-21 22:14:51 UTC (rev 1228)
+++ branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/AttVal.java 2010-11-22 09:09:53 UTC (rev 1229)
@@ -66,6 +66,11 @@
*/
public class AttVal extends Object implements Cloneable
{
+ /**
+ * Special empty string object to mark strings that (wrongly) end up empty in Tidy (the C library);
+ * normally Tidy uses null for empty strings and checks values based on that
+ */
+ protected static final String EMPTY = new String();
/**
* next AttVal.
@@ -443,7 +448,7 @@
}
public boolean hasValue() {
- return value != null && value.length() > 0;
+ return value != null && value.length() > 0 || value == EMPTY;
}
public boolean valueIs(final String val) {
Modified: branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Clean.java
===================================================================
--- branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Clean.java 2010-11-21 22:14:51 UTC (rev 1228)
+++ branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Clean.java 2010-11-22 09:09:53 UTC (rev 1229)
@@ -828,13 +828,17 @@
String[] sizes = {"60%", "70%", "80%", null, "120%", "150%", "200%"};
String buf;
- if (size.length() > 0 && '0' <= size.charAt(0) && size.charAt(0) <= '6')
+ if (size.length() == 0) {
+ return null;
+ }
+
+ if ('0' <= size.charAt(0) && size.charAt(0) <= '6')
{
int n = size.charAt(0) - '0';
return sizes[n];
}
- if (size.length() > 0 && size.charAt(0) == '-')
+ if (size.charAt(0) == '-')
{
if (size.length() > 1 && '0' <= size.charAt(1) && size.charAt(1) <= '6')
{
Modified: branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Lexer.java
===================================================================
--- branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Lexer.java 2010-11-21 22:14:51 UTC (rev 1228)
+++ branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Lexer.java 2010-11-22 09:09:53 UTC (rev 1229)
@@ -3296,6 +3296,10 @@
// workaround to emulate broken Tidy behavior in compatibility mode
// invalid entity becomes character 0 that terminates the C string, see test 1062345
value = value.substring(0, x);
+ if (value.length() == 0) {
+ // use this special object to mark that the attribute is still considered to have a value
+ value = AttVal.EMPTY;
+ }
}
}
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
|
From: <ad...@us...> - 2010-11-21 22:14:57
|
Revision: 1228
http://jtidy.svn.sourceforge.net/jtidy/?rev=1228&view=rev
Author: aditsu
Date: 2010-11-21 22:14:51 +0000 (Sun, 21 Nov 2010)
Log Message:
-----------
fixed 1316307 and 3 others - updated parsing code to fix table processing
Modified Paths:
--------------
branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/ParserImpl.java
Modified: branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/ParserImpl.java
===================================================================
--- branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/ParserImpl.java 2010-11-21 21:39:44 UTC (rev 1227)
+++ branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/ParserImpl.java 2010-11-21 22:14:51 UTC (rev 1228)
@@ -1688,6 +1688,11 @@
lexer.report.warning(lexer, list, node, ErrorCode.MISSING_ENDTAG_BEFORE);
return;
}
+ /* In exiled mode, return so table processing can continue. */
+ else if (lexer.exiled && (node.hasCM(Dict.CM_TABLE | Dict.CM_ROWGRP | Dict.CM_ROW)
+ || node.is(TagId.TABLE))) {
+ return;
+ }
/* http://tidy.sf.net/issue/836462
If "list" is an unordered list, insert the next tag within
@@ -2369,6 +2374,10 @@
}
else if ((node.tag.model & Dict.CM_TABLE) != 0 || (node.tag.model & Dict.CM_ROW) != 0)
{
+ /* In exiled mode, return so table processing can continue. */
+ if (lexer.exiled) {
+ return;
+ }
node = lexer.inferredTag(TagId.TABLE);
}
else if ((element.tag.model & Dict.CM_OBJECT) != 0)
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
|
From: <ad...@us...> - 2010-11-21 21:39:50
|
Revision: 1227
http://jtidy.svn.sourceforge.net/jtidy/?rev=1227&view=rev
Author: aditsu
Date: 2010-11-21 21:39:44 +0000 (Sun, 21 Nov 2010)
Log Message:
-----------
fixed tests 1079820, 1168193, 1235296 - added more conditions when checking for nested emphasis in parseInline
Modified Paths:
--------------
branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/ParserImpl.java
Modified: branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/ParserImpl.java
===================================================================
--- branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/ParserImpl.java 2010-11-21 21:32:29 UTC (rev 1226)
+++ branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/ParserImpl.java 2010-11-21 21:39:44 UTC (rev 1227)
@@ -1171,7 +1171,10 @@
&& !node.is(TagId.FONT)
&& !node.is(TagId.BIG)
&& !node.is(TagId.SMALL)
- && !node.is(TagId.Q))
+ && !node.is(TagId.SUB)
+ && !node.is(TagId.SUP)
+ && !node.is(TagId.Q)
+ && !node.is(TagId.SPAN))
{
if (element.content != null && node.attributes == null
&& element.last.isText() && !lexer.textNodeEndWithSpace(element.last)) {
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
|
From: <ad...@us...> - 2010-11-21 21:32:36
|
Revision: 1226
http://jtidy.svn.sourceforge.net/jtidy/?rev=1226&view=rev
Author: aditsu
Date: 2010-11-21 21:32:29 +0000 (Sun, 21 Nov 2010)
Log Message:
-----------
fixed test 1069549 - fixed a tree integrity problem in nestedList
Modified Paths:
--------------
branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Clean.java
Modified: branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Clean.java
===================================================================
--- branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Clean.java 2010-11-21 21:00:53 UTC (rev 1225)
+++ branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Clean.java 2010-11-21 21:32:29 UTC (rev 1226)
@@ -1296,15 +1296,11 @@
node = list;
list = node.prev;
- list.next = node.next;
-
- if (list.next != null)
- {
- list.next.prev = list;
- }
-
child = list.last; /* <li> */
+ list.next = node.next;
+ fixNodeLinks(list);
+
node.parent = child;
node.next = null;
node.prev = child.last;
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
|
From: <ad...@us...> - 2010-11-21 21:00:59
|
Revision: 1225
http://jtidy.svn.sourceforge.net/jtidy/?rev=1225&view=rev
Author: aditsu
Date: 2010-11-21 21:00:53 +0000 (Sun, 21 Nov 2010)
Log Message:
-----------
fixed test 1333579 - updated ParseRow to parse inline/block elements (that were moved before the table) with excludeBlocks = false
Modified Paths:
--------------
branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/ParserImpl.java
Modified: branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/ParserImpl.java
===================================================================
--- branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/ParserImpl.java 2010-11-21 20:29:34 UTC (rev 1224)
+++ branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/ParserImpl.java 2010-11-21 21:00:53 UTC (rev 1225)
@@ -2945,6 +2945,8 @@
Node.moveBeforeTable(row, node);
lexer.report.warning(lexer, row, node, ErrorCode.TAG_NOT_ALLOWED_IN);
lexer.exiled = true;
+ excludeState = lexer.excludeBlocks;
+ lexer.excludeBlocks = false;
if (node.type != NodeType.TextNode)
{
@@ -2952,6 +2954,7 @@
}
lexer.exiled = false;
+ lexer.excludeBlocks = excludeState;
continue;
}
else if ((node.tag.model & Dict.CM_HEAD) != 0)
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
|
From: <ad...@us...> - 2010-11-21 20:29:40
|
Revision: 1224
http://jtidy.svn.sourceforge.net/jtidy/?rev=1224&view=rev
Author: aditsu
Date: 2010-11-21 20:29:34 +0000 (Sun, 21 Nov 2010)
Log Message:
-----------
fixed test 1410061 - removed thousands separator for line/column numbers
Modified Paths:
--------------
branches/CodeUpdateAndJava5/src/main/resources/org/w3c/tidy/TidyMessages.properties
Modified: branches/CodeUpdateAndJava5/src/main/resources/org/w3c/tidy/TidyMessages.properties
===================================================================
--- branches/CodeUpdateAndJava5/src/main/resources/org/w3c/tidy/TidyMessages.properties 2010-11-21 01:57:42 UTC (rev 1223)
+++ branches/CodeUpdateAndJava5/src/main/resources/org/w3c/tidy/TidyMessages.properties 2010-11-21 20:29:34 UTC (rev 1224)
@@ -63,7 +63,7 @@
invalid_xml_id={0} cannot copy name attribute to id
invaliduri_summary=URIs must be properly escaped, they must not contain unescaped\u000acharacters below U+0021 including the space character and not\u000aabove U+007E. Tidy escapes the URI for you as recommended by\u000aHTML 4.01 section B.2.1 and XML 1.0 section 4.2.2. Some user agents\u000ause another algorithm to escape such URIs and some server-sided\u000ascripts depend on that. If you want to depend on that, you must\u000aescape the URI by your own. For more information please refer to\u000ahttp://www.w3.org/International/O-URL-and-ident.html\n
joining_attribute={0} joining values of repeated attribute "{1}"
-line_column=line {0,number} column {1,number} -
+line_column=line {0,number,#} column {1,number,#} -
malformed_comment=adjacent hyphens within comment
malformed_doctype=discarding malformed <!DOCTYPE>
missing_attr_value={0} attribute "{1}" lacks value
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
|
From: <ad...@us...> - 2010-11-21 01:57:49
|
Revision: 1223
http://jtidy.svn.sourceforge.net/jtidy/?rev=1223&view=rev
Author: aditsu
Date: 2010-11-21 01:57:42 +0000 (Sun, 21 Nov 2010)
Log Message:
-----------
fixed test 1078345 - added encloseBodyText and encloseBlockText methods, and removed the old corresponding code
Modified Paths:
--------------
branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/ParserImpl.java
Modified: branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/ParserImpl.java
===================================================================
--- branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/ParserImpl.java 2010-11-21 01:14:22 UTC (rev 1222)
+++ branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/ParserImpl.java 2010-11-21 01:57:42 UTC (rev 1223)
@@ -803,18 +803,6 @@
continue;
}
- if (lexer.configuration.isEncloseBodyText() && !iswhitenode)
- {
- Node para;
-
- lexer.ungetToken();
- para = lexer.inferredTag(TagId.P);
- body.insertNodeAtEnd(para);
- parseTag(lexer, para, mode);
- mode = Lexer.MIXED_CONTENT;
- continue;
- }
-
// HTML2 and HTML4 strict doesn't allow text here
lexer.constrainVersion(~(VERS_HTML40_STRICT | VERS_HTML20));
@@ -2158,24 +2146,6 @@
// mixed content model permits text
if (node.type == NodeType.TextNode)
{
- boolean iswhitenode = false;
-
- if (node.type == NodeType.TextNode
- && node.end <= node.start + 1
- && lexer.lexbuf[node.start] == (byte) ' ')
- {
- iswhitenode = true;
- }
-
- if (lexer.configuration.isEncloseBlockText() && !iswhitenode)
- {
- lexer.ungetToken();
- node = lexer.inferredTag(TagId.P);
- element.insertNodeAtEnd(node);
- parseTag(lexer, node, Lexer.MIXED_CONTENT);
- continue;
- }
-
if (checkstack)
{
checkstack = false;
@@ -2423,17 +2393,6 @@
{
if (TidyUtils.toBoolean(node.tag.model & Dict.CM_INLINE))
{
- // DSR - 27Apr02 ensure we wrap anchors and other inline content
- // fgiust: commented out due to [1403105]: java.lang.StackOverflowError in Tidy.parseDOM()
- // if (lexer.configuration.encloseBlockText)
- // {
- // lexer.ungetToken();
- // node = lexer.inferredTag(TagId.P);
- // element.insertNodeAtEnd(node);
- // parseTag(lexer, node, Lexer.MIXED_CONTENT);
- // continue;
- // }
-
if (checkstack && !node.implicit)
{
checkstack = false;
@@ -3505,6 +3464,70 @@
}
}
+ private static boolean nodeCMIsOnlyInline(final Node node) {
+ return node.hasCM(Dict.CM_INLINE) && !node.hasCM(Dict.CM_BLOCK);
+ }
+
+ private static void encloseBodyText(final Lexer lexer) {
+ Node body = lexer.root.findBody();
+ if (body == null) {
+ return;
+ }
+ Node node = body.content;
+
+ while (node != null) {
+ if ((node.isText() && !node.isBlank(lexer)) ||
+ (node.isElement() && nodeCMIsOnlyInline(node))) {
+ Node p = lexer.inferredTag(TagId.P);
+ Node.insertNodeBeforeElement(node, p);
+ while (node != null && (!node.isElement() || nodeCMIsOnlyInline(node))) {
+ Node next = node.next;
+ node.removeNode();
+ p.insertNodeAtEnd(node);
+ node = next;
+ }
+ Node.trimSpaces(lexer, p);
+ continue;
+ }
+ node = node.next;
+ }
+ }
+
+ /* <form>, <blockquote> and <noscript> do not allow #PCDATA in
+ HTML 4.01 Strict (%block; model instead of %flow;).
+ When requested, text nodes in these elements are wrapped in <p>. */
+ private static void encloseBlockText(final Lexer lexer, Node node) {
+ while (node != null) {
+ Node next = node.next;
+
+ if (node.content != null) {
+ encloseBlockText(lexer, node.content);
+ }
+
+ if (!(node.is(TagId.FORM) || node.is(TagId.NOSCRIPT) ||
+ node.is(TagId.BLOCKQUOTE)) || node.content == null) {
+ node = next;
+ continue;
+ }
+ Node block = node.content;
+
+ if ((block.isText() && !block.isBlank(lexer)) ||
+ (block.isElement() && nodeCMIsOnlyInline(block))) {
+ Node p = lexer.inferredTag(TagId.P);
+ Node.insertNodeBeforeElement(block, p);
+ while (block != null && (!block.isElement() || nodeCMIsOnlyInline(block))) {
+ Node tempNext = block.next;
+ block.removeNode();
+ p.insertNodeAtEnd(block);
+ block = tempNext;
+ }
+ Node.trimSpaces(lexer, p);
+ continue;
+ }
+ node = next;
+ }
+ }
+
/**
* HTML is the top level element.
*/
@@ -3592,7 +3615,13 @@
attributeChecks(lexer, lexer.root);
dropEmptyElements(lexer, lexer.root);
cleanSpaces(lexer, lexer.root);
-
+
+ if (lexer.configuration.isEncloseBodyText()) {
+ encloseBodyText(lexer);
+ }
+ if (lexer.configuration.isEncloseBlockText()) {
+ encloseBlockText(lexer, lexer.root);
+ }
return document;
}
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
|
From: <ad...@us...> - 2010-11-21 01:14:32
|
Revision: 1222
http://jtidy.svn.sourceforge.net/jtidy/?rev=1222&view=rev
Author: aditsu
Date: 2010-11-21 01:14:22 +0000 (Sun, 21 Nov 2010)
Log Message:
-----------
fixed test 1266647 - updated comment parsing
Modified Paths:
--------------
branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Lexer.java
Modified: branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Lexer.java
===================================================================
--- branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Lexer.java 2010-11-21 00:40:56 UTC (rev 1221)
+++ branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Lexer.java 2010-11-21 01:14:22 UTC (rev 1222)
@@ -2114,8 +2114,7 @@
continue;
}
- end_comment : while (true)
- {
+ while (true) {
c = this.in.readChar();
if (c == '>')
@@ -2170,17 +2169,17 @@
this.lexbuf[this.lexsize - 2] = (byte) '=';
}
- addCharToLexer(c);
-
// if '-' then look for '>' to end the comment
- if (c != '-')
- {
- break end_comment;
+ if (c == '-') {
+ addCharToLexer(c);
}
-
+ else {
+ // otherwise continue to look for -->
+ this.lexbuf[this.lexsize - 1] = (byte) '=';
+ addCharToLexer(c);
+ break;
+ }
}
- // otherwise continue to look for -->
- this.lexbuf[this.lexsize - 2] = (byte) '=';
continue;
case LEX_DOCTYPE :
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
|
From: <ad...@us...> - 2010-11-21 00:41:02
|
Revision: 1221
http://jtidy.svn.sourceforge.net/jtidy/?rev=1221&view=rev
Author: aditsu
Date: 2010-11-21 00:40:56 +0000 (Sun, 21 Nov 2010)
Log Message:
-----------
fixed test 1231279 - updated ANCHOR_NOT_UNIQUE message
Modified Paths:
--------------
branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Report.java
branches/CodeUpdateAndJava5/src/main/resources/org/w3c/tidy/TidyMessages.properties
Modified: branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Report.java
===================================================================
--- branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Report.java 2010-11-21 00:02:57 UTC (rev 1220)
+++ branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Report.java 2010-11-21 00:40:56 UTC (rev 1221)
@@ -632,11 +632,7 @@
break;
case ANCHOR_NOT_UNIQUE :
- messageLexer(
- lexer,
- Level.WARNING,
- code,
- getTagName(node), attribute.value);
+ messageNode(lexer, Level.WARNING, node, code, tagdesc, value);
break;
case ENTITY_IN_ID :
Modified: branches/CodeUpdateAndJava5/src/main/resources/org/w3c/tidy/TidyMessages.properties
===================================================================
--- branches/CodeUpdateAndJava5/src/main/resources/org/w3c/tidy/TidyMessages.properties 2010-11-21 00:02:57 UTC (rev 1220)
+++ branches/CodeUpdateAndJava5/src/main/resources/org/w3c/tidy/TidyMessages.properties 2010-11-21 00:40:56 UTC (rev 1221)
@@ -1,4 +1,4 @@
-anchor_not_unique={0} Anchor "{1}" already defined
+anchor_not_unique={0} anchor "{1}" already defined
apos_undefined=named entity ' only defined in XML/XHTML
attr_value_not_lcase={0} attribute value "{1}" must be lower case for XHTML
# to be translated
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
|
From: <ad...@us...> - 2010-11-21 00:08:14
|
Revision: 1218
http://jtidy.svn.sourceforge.net/jtidy/?rev=1218&view=rev
Author: aditsu
Date: 2010-11-20 23:02:29 +0000 (Sat, 20 Nov 2010)
Log Message:
-----------
fixed test 1062345 - emulated (only in compatibility mode) broken Tidy behavior for invalid entities (and corrected it otherwise); updated repairDuplicateAttributes and JOINING_ATTRIBUTE message handling
Modified Paths:
--------------
branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Lexer.java
branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Node.java
branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Report.java
Modified: branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Lexer.java
===================================================================
--- branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Lexer.java 2010-11-20 21:37:31 UTC (rev 1217)
+++ branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Lexer.java 2010-11-20 23:02:29 UTC (rev 1218)
@@ -770,8 +770,11 @@
}
final Entity ent = EntityTable.getDefaultEntityTable().entityInfo(str, isXml);
- final boolean found = ent != null;
+ boolean found = ent != null;
int ch = found ? ent.getCode() : 0;
+ if (found && ch == 0 && !configuration.isTidyCompat()) {
+ found = false;
+ }
final int entver = found ? ent.getVersions() : isXml ? VERS_XML : VERS_PROPRIETARY;
// deal with unrecognized or invalid entities
@@ -3288,6 +3291,14 @@
}
value = parseValue(attribute, false, isempty, delim);
+ if (value != null) {
+ final int x = value.indexOf(0);
+ if (x >= 0 && configuration.isTidyCompat()) {
+ // workaround to emulate broken Tidy behavior in compatibility mode
+ // invalid entity becomes character 0 that terminates the C string, see test 1062345
+ value = value.substring(0, x);
+ }
+ }
if (attribute != null && isValidAttrName(attribute))
{
Modified: branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Node.java
===================================================================
--- branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Node.java 2010-11-20 21:37:31 UTC (rev 1217)
+++ branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Node.java 2010-11-20 23:02:29 UTC (rev 1218)
@@ -313,29 +313,25 @@
removeAttribute(first);
first = temp;
}
- else if ("style".equalsIgnoreCase(second.attribute) && lexer.configuration.isJoinStyles())
- {
+ else if (first.is(AttrId.STYLE) && lexer.configuration.isJoinStyles()) {
// concatenate styles
// this doesn't handle CSS comments and leading/trailing white-space very well see
// http://www.w3.org/TR/css-style-attr
- int end = first.value.length() - 1;
+ final int end = first.value.length();
- if (first.value.charAt(end) == ';')
- {
+ if (end > 0 && first.value.charAt(end - 1) == ';') {
// attribute ends with declaration seperator
first.value = first.value + " " + second.value;
}
- else if (first.value.charAt(end) == '}')
- {
+ else if (end > 0 && first.value.charAt(end - 1) == '}') {
// attribute ends with rule set
first.value = first.value + " { " + second.value + " }";
}
- else
- {
+ else {
// attribute ends with property value
- first.value = first.value + "; " + second.value;
+ first.value = first.value + (end > 0 ? "; " : "") + second.value;
}
temp = second.next;
Modified: branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Report.java
===================================================================
--- branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Report.java 2010-11-20 21:37:31 UTC (rev 1217)
+++ branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Report.java 2010-11-20 23:02:29 UTC (rev 1218)
@@ -551,7 +551,8 @@
break;
case INSERTING_ATTRIBUTE:
- case MISSING_ATTR_VALUE :
+ case MISSING_ATTR_VALUE:
+ case JOINING_ATTRIBUTE:
messageNode(lexer, Level.WARNING, node, code, tagdesc, name);
break;
@@ -642,14 +643,6 @@
messageLexer(lexer, Level.WARNING, code);
break;
- case JOINING_ATTRIBUTE :
- messageLexer(
- lexer,
- Level.WARNING,
- code,
- getTagName(node), attribute.attribute);
- break;
-
case UNEXPECTED_EQUALSIGN :
messageLexer(lexer, Level.WARNING, code, getTagName(node));
break;
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
|
From: <ad...@us...> - 2010-11-21 00:03:03
|
Revision: 1220
http://jtidy.svn.sourceforge.net/jtidy/?rev=1220&view=rev
Author: aditsu
Date: 2010-11-21 00:02:57 +0000 (Sun, 21 Nov 2010)
Log Message:
-----------
fixed test 1056910 - added a condition in nestedList
Modified Paths:
--------------
branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Clean.java
Modified: branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Clean.java
===================================================================
--- branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Clean.java 2010-11-20 23:57:13 UTC (rev 1219)
+++ branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Clean.java 2010-11-21 00:02:57 UTC (rev 1220)
@@ -1267,6 +1267,11 @@
{
return false;
}
+
+ /* check list has no peers */
+ if (list.next != null) {
+ return false;
+ }
pnode[0] = list; // Set node to resume iteration
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
|
From: <ad...@us...> - 2010-11-20 23:57:19
|
Revision: 1219
http://jtidy.svn.sourceforge.net/jtidy/?rev=1219&view=rev
Author: aditsu
Date: 2010-11-20 23:57:13 +0000 (Sat, 20 Nov 2010)
Log Message:
-----------
improved toString
Modified Paths:
--------------
branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Node.java
Modified: branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Node.java
===================================================================
--- branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Node.java 2010-11-20 23:02:29 UTC (rev 1218)
+++ branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Node.java 2010-11-20 23:57:13 UTC (rev 1219)
@@ -1202,59 +1202,48 @@
}
}
+ protected String toString(final String indent) {
+ final StringBuilder sb = new StringBuilder();
+ sb.append(type);
+ if (element != null) {
+ sb.append(':').append(element);
+ }
+ if (type == NodeType.TextNode || type == NodeType.CommentTag || type == NodeType.ProcInsTag) {
+ if (textarray != null && start <= end) {
+ sb.append(" \"");
+ sb.append(TidyUtils.getString(textarray, start, end - start));
+ sb.append('"');
+ }
+ else {
+ sb.append(" null");
+ }
+ }
+ for (AttVal av = attributes; av != null; av = av.next) {
+ sb.append(' ').append(av.attribute).append('=');
+ if (av.value == null) {
+ sb.append("null");
+ }
+ else {
+ sb.append('"').append(av.value).append('"');
+ }
+ }
+ if (content != null) {
+ sb.append("\n ").append(indent);
+ sb.append(content.toString(indent + ' '));
+ }
+ if (next != null) {
+ sb.append('\n').append(indent);
+ sb.append(next.toString(indent));
+ }
+ return sb.toString();
+ }
+
/**
* @see java.lang.Object#toString()
*/
@Override
- public String toString()
- {
- String s = "";
- Node n = this;
-
- while (n != null)
- {
- s += "[Node type=";
- s += n.type;
- s += ",element=";
- if (n.element != null)
- {
- s += n.element;
- }
- else
- {
- s += "null";
- }
- if (n.type == NodeType.TextNode || n.type == NodeType.CommentTag || n.type == NodeType.ProcInsTag)
- {
- s += ",text=";
- if (n.textarray != null && n.start <= n.end)
- {
- s += "\"";
- s += TidyUtils.getString(n.textarray, n.start, n.end - n.start);
- s += "\"";
- }
- else
- {
- s += "null";
- }
- }
- s += ",content=";
- if (n.content != null)
- {
- s += n.content.toString();
- }
- else
- {
- s += "null";
- }
- s += "]";
- if (n.next != null)
- {
- s += ",";
- }
- n = n.next;
- }
- return s;
+ public String toString() {
+ return toString("");
}
/**
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
|
From: <ad...@us...> - 2010-11-20 21:37:37
|
Revision: 1217
http://jtidy.svn.sourceforge.net/jtidy/?rev=1217&view=rev
Author: aditsu
Date: 2010-11-20 21:37:31 +0000 (Sat, 20 Nov 2010)
Log Message:
-----------
fixed test 1056023 - moved a return statement in ParseRowGroup
Modified Paths:
--------------
branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/ParserImpl.java
Modified: branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/ParserImpl.java
===================================================================
--- branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/ParserImpl.java 2010-11-20 21:26:27 UTC (rev 1216)
+++ branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/ParserImpl.java 2010-11-20 21:37:31 UTC (rev 1217)
@@ -2843,9 +2843,8 @@
if (node.type != NodeType.EndTag)
{
lexer.ungetToken();
+ return;
}
-
- return;
}
if (node.type == NodeType.EndTag)
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
|
From: <ad...@us...> - 2010-11-20 21:26:33
|
Revision: 1216
http://jtidy.svn.sourceforge.net/jtidy/?rev=1216&view=rev
Author: aditsu
Date: 2010-11-20 21:26:27 +0000 (Sat, 20 Nov 2010)
Log Message:
-----------
fixed test 1055398 - swapped "first" and "second" when joining styles in repairDuplicateAttributes
Modified Paths:
--------------
branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Node.java
Modified: branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Node.java
===================================================================
--- branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Node.java 2010-11-20 21:12:16 UTC (rev 1215)
+++ branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Node.java 2010-11-20 21:26:27 UTC (rev 1216)
@@ -320,40 +320,28 @@
// this doesn't handle CSS comments and leading/trailing white-space very well see
// http://www.w3.org/TR/css-style-attr
- int end = second.value.length() - 1;
+ int end = first.value.length() - 1;
- if (second.value.charAt(end) == ';')
+ if (first.value.charAt(end) == ';')
{
// attribute ends with declaration seperator
- second.value = second.value + " " + first.value;
+ first.value = first.value + " " + second.value;
}
- else if (second.value.charAt(end) == '}')
+ else if (first.value.charAt(end) == '}')
{
// attribute ends with rule set
- second.value = second.value + " { " + first.value + " }";
+ first.value = first.value + " { " + second.value + " }";
}
else
{
// attribute ends with property value
- second.value = second.value + "; " + first.value;
+ first.value = first.value + "; " + second.value;
}
- temp = first.next;
-
- if (temp.next == null)
- {
- second = null;
- }
- else
- {
- second = second.next;
- }
-
- lexer.report.attrError(lexer, this, first, ErrorCode.JOINING_ATTRIBUTE);
-
- removeAttribute(first);
- first = temp;
-
+ temp = second.next;
+ lexer.report.attrError(lexer, this, second, ErrorCode.JOINING_ATTRIBUTE);
+ removeAttribute(second);
+ second = temp;
}
else if (lexer.configuration.getDuplicateAttrs() == DupAttrModes.KeepLast)
{
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
|
From: <ad...@us...> - 2010-11-20 21:12:22
|
Revision: 1215
http://jtidy.svn.sourceforge.net/jtidy/?rev=1215&view=rev
Author: aditsu
Date: 2010-11-20 21:12:16 +0000 (Sat, 20 Nov 2010)
Log Message:
-----------
fixed test 500236 - modified parseValue to replace \n with space in certain cases
Modified Paths:
--------------
branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Lexer.java
Modified: branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Lexer.java
===================================================================
--- branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Lexer.java 2010-11-18 03:14:32 UTC (rev 1214)
+++ branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Lexer.java 2010-11-20 21:12:16 UTC (rev 1215)
@@ -3043,8 +3043,10 @@
addCharToLexer(c);
parseEntity((short) 0);
+ if (lexbuf[lexsize - 1] == '\n' && munge) {
+ changeChar((byte)' ');
+ }
continue;
-
}
// kludge for JavaScript attribute values with line continuations in string literals
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
|
From: <ad...@us...> - 2010-11-18 03:14:38
|
Revision: 1214
http://jtidy.svn.sourceforge.net/jtidy/?rev=1214&view=rev
Author: aditsu
Date: 2010-11-18 03:14:32 +0000 (Thu, 18 Nov 2010)
Log Message:
-----------
fixed tests 1004512, 1410061-1 and 1410061-2 - added a condition in font2Span
Modified Paths:
--------------
branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Clean.java
Modified: branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Clean.java
===================================================================
--- branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Clean.java 2010-11-18 02:59:21 UTC (rev 1213)
+++ branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Clean.java 2010-11-18 03:14:32 UTC (rev 1214)
@@ -1491,8 +1491,8 @@
}
// if FONT is only child of parent element then leave alone
- if (node.parent.content == node && node.next == null)
- {
+ // Do so only if blockStyle may be succesful.
+ if (node.parent.content == node && node.next == null && canApplyBlockStyle(node.parent)) {
return false;
}
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
|
From: <ad...@us...> - 2010-11-18 02:59:28
|
Revision: 1213
http://jtidy.svn.sourceforge.net/jtidy/?rev=1213&view=rev
Author: aditsu
Date: 2010-11-18 02:59:21 +0000 (Thu, 18 Nov 2010)
Log Message:
-----------
fixed tests 837023 and 1072528 - corrected MALFORMED_DOCTYPE message and level
Modified Paths:
--------------
branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Lexer.java
branches/CodeUpdateAndJava5/src/main/resources/org/w3c/tidy/TidyMessages.properties
Modified: branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Lexer.java
===================================================================
--- branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Lexer.java 2010-11-18 02:41:02 UTC (rev 1212)
+++ branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Lexer.java 2010-11-18 02:59:21 UTC (rev 1213)
@@ -3747,7 +3747,7 @@
AttrCheckImpl.URL.check(this, node, si);
}
if (node.element == null || !TidyUtils.isValidXMLID(node.element)) {
- report.error(this, null, null, ErrorCode.MALFORMED_DOCTYPE);
+ report.warning(this, null, null, ErrorCode.MALFORMED_DOCTYPE);
return null;
}
// #ifdef TIDY_STORE_ORIGINAL_TEXT
@@ -3816,7 +3816,7 @@
}
/* document type declaration not finished */
- report.error(this, null, null, ErrorCode.MALFORMED_DOCTYPE);
+ report.warning(this, null, null, ErrorCode.MALFORMED_DOCTYPE);
return null;
}
Modified: branches/CodeUpdateAndJava5/src/main/resources/org/w3c/tidy/TidyMessages.properties
===================================================================
--- branches/CodeUpdateAndJava5/src/main/resources/org/w3c/tidy/TidyMessages.properties 2010-11-18 02:41:02 UTC (rev 1212)
+++ branches/CodeUpdateAndJava5/src/main/resources/org/w3c/tidy/TidyMessages.properties 2010-11-18 02:59:21 UTC (rev 1213)
@@ -65,7 +65,7 @@
joining_attribute={0} joining values of repeated attribute "{1}"
line_column=line {0,number} column {1,number} -
malformed_comment=adjacent hyphens within comment
-malformed_doctype=expected "html PUBLIC" or "html SYSTEM"
+malformed_doctype=discarding malformed <!DOCTYPE>
missing_attr_value={0} attribute "{1}" lacks value
missing_attribute={0} lacks "{1}" attribute
missing_body=Can''t create slides - document is missing a body element.
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
|
From: <ad...@us...> - 2010-11-18 02:41:08
|
Revision: 1212
http://jtidy.svn.sourceforge.net/jtidy/?rev=1212&view=rev
Author: aditsu
Date: 2010-11-18 02:41:02 +0000 (Thu, 18 Nov 2010)
Log Message:
-----------
fixed test 660397 - added adjustCharEncoding, and removed inCharEncoding and outCharEncoding fields
Modified Paths:
--------------
branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Configuration.java
branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/ParsePropertyImpl.java
Modified: branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Configuration.java
===================================================================
--- branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Configuration.java 2010-11-18 01:41:14 UTC (rev 1211)
+++ branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/Configuration.java 2010-11-18 02:41:02 UTC (rev 1212)
@@ -303,16 +303,6 @@
private int definedTags;
/**
- * Input character encoding (defaults to "ISO8859_1").
- */
- private String inCharEncoding = "ISO8859_1";
-
- /**
- * Output character encoding (defaults to "ASCII").
- */
- private String outCharEncoding = "ASCII";
-
- /**
* Avoid mapping values > 127 to entities.
*/
private boolean rawOut;
@@ -399,6 +389,37 @@
}
}
+ /* ensure that char encodings are self consistent */
+ protected boolean adjustCharEncoding(final String encoding) {
+ final String enc = EncodingNameMapper.toJava(encoding);
+ String outenc = null;
+ String inenc = null;
+
+ if ("MacRoman".equals(enc) || "Cp1252".equals(enc) || "Cp858".equals(enc)
+ || "ISO8859_15".equals(enc)) {
+ inenc = enc;
+ outenc = "ASCII";
+ }
+ else if ("ASCII".equals(enc)) {
+ inenc = "ISO8859_1";
+ outenc = "ASCII";
+ }
+ for (String s : ENCODING_NAMES) {
+ if (s.equals(enc)) {
+ inenc = outenc = enc;
+ break;
+ }
+ }
+
+ if (inenc != null) {
+ set(Option.CharEncoding, enc);
+ set(Option.InCharEncoding, inenc);
+ set(Option.OutCharEncoding, outenc);
+ return true;
+ }
+ return false;
+ }
+
/**
* Ensure that config is self consistent.
*/
@@ -518,21 +539,18 @@
* Getter for <code>inCharEncodingName</code>.
* @return Returns the inCharEncodingName.
*/
- protected String getInCharEncodingName()
- {
- return this.inCharEncoding;
+ protected String getInCharEncodingName() {
+ return getString(Option.InCharEncoding);
}
/**
* Setter for <code>inCharEncodingName</code>.
* @param encoding The inCharEncodingName to set.
*/
- protected void setInCharEncodingName(String encoding)
- {
- String javaEncoding = EncodingNameMapper.toJava(encoding);
- if (javaEncoding != null)
- {
- this.inCharEncoding = javaEncoding;
+ protected void setInCharEncodingName(final String encoding) {
+ final String javaEncoding = EncodingNameMapper.toJava(encoding);
+ if (javaEncoding != null) {
+ set(Option.InCharEncoding, javaEncoding);
}
}
@@ -540,21 +558,18 @@
* Getter for <code>outCharEncodingName</code>.
* @return Returns the outCharEncodingName.
*/
- protected String getOutCharEncodingName()
- {
- return this.outCharEncoding;
+ protected String getOutCharEncodingName() {
+ return getString(Option.OutCharEncoding);
}
/**
* Setter for <code>outCharEncodingName</code>.
* @param encoding The outCharEncodingName to set.
*/
- protected void setOutCharEncodingName(String encoding)
- {
- String javaEncoding = EncodingNameMapper.toJava(encoding);
- if (javaEncoding != null)
- {
- this.outCharEncoding = javaEncoding;
+ protected void setOutCharEncodingName(final String encoding) {
+ final String javaEncoding = EncodingNameMapper.toJava(encoding);
+ if (javaEncoding != null) {
+ set(Option.OutCharEncoding, javaEncoding);
}
}
Modified: branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/ParsePropertyImpl.java
===================================================================
--- branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/ParsePropertyImpl.java 2010-11-18 01:41:14 UTC (rev 1211)
+++ branches/CodeUpdateAndJava5/src/main/java/org/w3c/tidy/ParsePropertyImpl.java 2010-11-18 02:41:02 UTC (rev 1212)
@@ -342,10 +342,8 @@
{
configuration.setOutCharEncodingName(value);
}
- else if ("char-encoding".equalsIgnoreCase(name))
- {
- configuration.setInCharEncodingName(value);
- configuration.setOutCharEncodingName(value);
+ else if ("char-encoding".equalsIgnoreCase(name)) {
+ configuration.adjustCharEncoding(value);
}
return null;
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
