Directly loop through characters from the source string instead of
using a StringReader. Dropped character entity encoding, since this limits us to western encoding and should not be necessary because browsers usually default to western encoding.
This commit is contained in:
parent
7a6b473e22
commit
4f28990143
1 changed files with 94 additions and 134 deletions
|
@ -124,60 +124,60 @@ public final class HtmlEncoder {
|
|||
/**
|
||||
*
|
||||
*/
|
||||
public final static String encode (String what) {
|
||||
public final static String encode (String str) {
|
||||
// try to make stringbuffer large enough from the start
|
||||
StringBuffer ret = new StringBuffer (Math.round (what.length()*1.4f));
|
||||
encode (what, ret);
|
||||
StringBuffer ret = new StringBuffer (Math.round (str.length()*1.4f));
|
||||
encode (str, ret);
|
||||
return ret.toString();
|
||||
}
|
||||
|
||||
/**
|
||||
*
|
||||
*/
|
||||
public final static void encode (String what, StringBuffer ret) {
|
||||
if (what == null || what.length() == 0) {
|
||||
public final static void encode (String str, StringBuffer ret) {
|
||||
if (str == null)
|
||||
return;
|
||||
}
|
||||
|
||||
StringReader in = new StringReader (what);
|
||||
int c;
|
||||
int l = str.length();
|
||||
|
||||
boolean closeTag=false, readTag=false, tagOpen=false;
|
||||
// the difference between swallowOneNewline and ignoreNewline is that swallowOneNewline is just effective once (for the next newline)
|
||||
boolean ignoreNewline = false;
|
||||
boolean ignoreNewline = false;
|
||||
boolean swallowOneNewline = false;
|
||||
StringBuffer tag = new StringBuffer ();
|
||||
try {
|
||||
while ((c = in.read()) != -1) {
|
||||
if (readTag) {
|
||||
if (Character.isLetterOrDigit ((char) c))
|
||||
tag.append ((char) c);
|
||||
else if ('/' == c)
|
||||
closeTag = true;
|
||||
else {
|
||||
String t = tag.toString ();
|
||||
// set ignoreNewline on some tags, depending on wheather they're
|
||||
// being opened or closed.
|
||||
// what's going on here? we switch newline encoding on inside some tags, for
|
||||
// others we switch it on when they're closed
|
||||
if ("td".equalsIgnoreCase (t) || "th".equalsIgnoreCase (t) || "li".equalsIgnoreCase (t)) {
|
||||
ignoreNewline = closeTag;
|
||||
swallowOneNewline = true;
|
||||
} else if ("table".equalsIgnoreCase (t) || "ul".equalsIgnoreCase (t) || "ol".equalsIgnoreCase (t) || "pre".equalsIgnoreCase (t)) {
|
||||
ignoreNewline = !closeTag;
|
||||
swallowOneNewline = true;
|
||||
} else if ("p".equalsIgnoreCase (t)) {
|
||||
swallowOneNewline = true;
|
||||
}
|
||||
|
||||
readTag = false;
|
||||
closeTag = false;
|
||||
tag.setLength (0);
|
||||
}
|
||||
} // if (readTag)
|
||||
for (int i=0; i<l; i++) {
|
||||
char c = str.charAt (i);
|
||||
if (readTag) {
|
||||
if (Character.isLetterOrDigit (c))
|
||||
tag.append (c);
|
||||
else if ('/' == c)
|
||||
closeTag = true;
|
||||
else {
|
||||
String t = tag.toString ();
|
||||
// set ignoreNewline on some tags, depending on wheather they're
|
||||
// being opened or closed.
|
||||
// what's going on here? we switch newline encoding on inside some tags, for
|
||||
// others we switch it on when they're closed
|
||||
if ("td".equalsIgnoreCase (t) || "th".equalsIgnoreCase (t) || "li".equalsIgnoreCase (t)) {
|
||||
ignoreNewline = closeTag;
|
||||
swallowOneNewline = true;
|
||||
} else if ("table".equalsIgnoreCase (t) || "ul".equalsIgnoreCase (t) || "ol".equalsIgnoreCase (t) || "pre".equalsIgnoreCase (t)) {
|
||||
ignoreNewline = !closeTag;
|
||||
swallowOneNewline = true;
|
||||
} else if ("p".equalsIgnoreCase (t)) {
|
||||
swallowOneNewline = true;
|
||||
}
|
||||
|
||||
switch (c) {
|
||||
readTag = false;
|
||||
closeTag = false;
|
||||
tag.setLength (0);
|
||||
}
|
||||
} // if (readTag)
|
||||
|
||||
switch (c) {
|
||||
// case '&':
|
||||
// ret.append ("&");
|
||||
// ret.append ("&");
|
||||
// break;
|
||||
case '\n':
|
||||
ret.append ('\n');
|
||||
|
@ -197,28 +197,28 @@ public final class HtmlEncoder {
|
|||
ret.append ('>');
|
||||
break;
|
||||
default:
|
||||
if (c < 160)
|
||||
ret.append ((char) c);
|
||||
ret.append (c);
|
||||
// if (c < 160)
|
||||
// ret.append ((char) c);
|
||||
// else if (c >= 160 && c <= 255)
|
||||
// ret.append (convertor.get(new Integer(c)));
|
||||
else {
|
||||
ret.append ("&#");
|
||||
ret.append (c);
|
||||
ret.append (";");
|
||||
}
|
||||
if (!tagOpen && !Character.isWhitespace ((char)c))
|
||||
// else {
|
||||
// ret.append ("&#");
|
||||
// ret.append (c);
|
||||
// ret.append (";");
|
||||
// }
|
||||
if (!tagOpen && !Character.isWhitespace (c))
|
||||
swallowOneNewline = false;
|
||||
}
|
||||
}
|
||||
} catch (IOException e) {}
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
*
|
||||
*/
|
||||
public final static String encodeFormValue (String what) {
|
||||
StringBuffer ret = new StringBuffer (Math.round (what.length()*1.4f));
|
||||
encodeAll (what, ret, false);
|
||||
public final static String encodeFormValue (String str) {
|
||||
StringBuffer ret = new StringBuffer (Math.round (str.length()*1.2f));
|
||||
encodeAll (str, ret, false);
|
||||
return ret.toString();
|
||||
}
|
||||
|
||||
|
@ -226,17 +226,17 @@ public final class HtmlEncoder {
|
|||
/**
|
||||
*
|
||||
*/
|
||||
public final static String encodeAll (String what) {
|
||||
StringBuffer ret = new StringBuffer (Math.round (what.length()*1.4f));
|
||||
encodeAll (what, ret, true);
|
||||
public final static String encodeAll (String str) {
|
||||
StringBuffer ret = new StringBuffer (Math.round (str.length()*1.2f));
|
||||
encodeAll (str, ret, true);
|
||||
return ret.toString();
|
||||
}
|
||||
|
||||
/**
|
||||
*
|
||||
*/
|
||||
public final static String encodeAll (String what, StringBuffer ret) {
|
||||
encodeAll (what, ret, true);
|
||||
public final static String encodeAll (String str, StringBuffer ret) {
|
||||
encodeAll (str, ret, true);
|
||||
return ret.toString();
|
||||
}
|
||||
|
||||
|
@ -244,116 +244,76 @@ public final class HtmlEncoder {
|
|||
/**
|
||||
*
|
||||
*/
|
||||
public final static void encodeAll (String what, StringBuffer ret, boolean encodeNewline) {
|
||||
if (what == null || what.length() == 0) {
|
||||
public final static void encodeAll (String str, StringBuffer ret, boolean encodeNewline) {
|
||||
if (str == null)
|
||||
return;
|
||||
}
|
||||
|
||||
StringReader in = new StringReader (what);
|
||||
int c;
|
||||
try {
|
||||
while ((c = in.read()) != -1) {
|
||||
switch (c) {
|
||||
case '<' :
|
||||
int l = str.length();
|
||||
for (int i=0; i<l; i++) {
|
||||
char c = str.charAt (i);
|
||||
switch (c) {
|
||||
case '<' :
|
||||
ret.append ("<");
|
||||
break;
|
||||
case '>':
|
||||
case '>':
|
||||
ret.append (">");
|
||||
break;
|
||||
case '&':
|
||||
case '&':
|
||||
ret.append ("&");
|
||||
break;
|
||||
case '"':
|
||||
case '"':
|
||||
ret.append (""");
|
||||
break;
|
||||
case '\n':
|
||||
case '\n':
|
||||
ret.append ('\n');
|
||||
if (encodeNewline) {
|
||||
ret.append ("<br>");
|
||||
}
|
||||
break;
|
||||
default:
|
||||
if (c < 160)
|
||||
ret.append ((char) c);
|
||||
default:
|
||||
ret.append (c);
|
||||
// if (c < 160)
|
||||
// ret.append ((char) c);
|
||||
// else if (c >= 160 && c <= 255)
|
||||
// ret.append (convertor.get(new Integer(c)));
|
||||
else {
|
||||
ret.append ("&#");
|
||||
ret.append (c);
|
||||
ret.append (";");
|
||||
}
|
||||
}
|
||||
// else {
|
||||
// ret.append ("&#");
|
||||
// ret.append (c);
|
||||
// ret.append (";");
|
||||
// }
|
||||
}
|
||||
} catch (IOException e) {}
|
||||
}
|
||||
|
||||
public final static String encodeSoft (String what) {
|
||||
StringBuffer ret = new StringBuffer (Math.round (what.length()*1.4f));
|
||||
encodeSoft (what, ret);
|
||||
return ret.toString();
|
||||
}
|
||||
|
||||
public final static void encodeSoft (String what, StringBuffer ret) {
|
||||
if (what == null || what.length() == 0) {
|
||||
return;
|
||||
}
|
||||
|
||||
StringReader in = new StringReader (what);
|
||||
int c;
|
||||
try {
|
||||
while ((c = in.read()) != -1) {
|
||||
switch (c) {
|
||||
case 128: // Euro-Symbol. This is for missing Unicode support in TowerJ.
|
||||
ret.append ("€");
|
||||
break;
|
||||
default:
|
||||
if (c < 160)
|
||||
ret.append ((char) c);
|
||||
// else if (c >= 160 && c <= 255)
|
||||
// ret.append (convertor.get(new Integer(c)));
|
||||
else {
|
||||
ret.append ("&#");
|
||||
ret.append (c);
|
||||
ret.append (";");
|
||||
}
|
||||
}
|
||||
}
|
||||
} catch (IOException e) {}
|
||||
}
|
||||
|
||||
|
||||
public final static String encodeXml (String what) {
|
||||
StringBuffer ret = new StringBuffer (Math.round (what.length()*1.4f));
|
||||
encodeXml (what, ret);
|
||||
public final static String encodeXml (String str) {
|
||||
StringBuffer ret = new StringBuffer (Math.round (str.length()*1.2f));
|
||||
encodeXml (str, ret);
|
||||
return ret.toString();
|
||||
}
|
||||
|
||||
public final static void encodeXml (String what, StringBuffer ret) {
|
||||
if (what == null || what.length() == 0) {
|
||||
public final static void encodeXml (String str, StringBuffer ret) {
|
||||
if (str == null)
|
||||
return;
|
||||
}
|
||||
|
||||
StringReader in = new StringReader (what);
|
||||
int c;
|
||||
try {
|
||||
while ((c = in.read()) != -1) {
|
||||
switch (c) {
|
||||
case '<' :
|
||||
int l = str.length();
|
||||
for (int i=0; i<l; i++) {
|
||||
char c = str.charAt (i);
|
||||
switch (c) {
|
||||
case '<' :
|
||||
ret.append ("<");
|
||||
break;
|
||||
case '>':
|
||||
case '>':
|
||||
ret.append (">");
|
||||
break;
|
||||
case '&':
|
||||
case '&':
|
||||
ret.append ("&");
|
||||
break;
|
||||
default:
|
||||
ret.append ((char) c);
|
||||
}
|
||||
default:
|
||||
ret.append (c);
|
||||
}
|
||||
} catch (IOException e) {}
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
|
||||
}
|
||||
} // end of class
|
||||
|
|
Loading…
Add table
Reference in a new issue