Menu
▾
▴
archive-access-cvs
|
From: <bra...@us...> - 2008-08-05 01:28:37
|
Revision: 2524
http://archive-access.svn.sourceforge.net/archive-access/?rev=2524&view=rev
Author: bradtofel
Date: 2008-08-05 01:28:47 +0000 (Tue, 05 Aug 2008)
Log Message:
-----------
BUGFIX (ACC-28): check that guessed charset is supported before attempting to use.
Modified Paths:
--------------
trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/replay/TextDocument.java
Modified: trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/replay/TextDocument.java
===================================================================
--- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/replay/TextDocument.java 2008-08-01 17:17:44 UTC (rev 2523)
+++ trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/replay/TextDocument.java 2008-08-05 01:28:47 UTC (rev 2524)
@@ -91,6 +91,9 @@
private boolean isCharsetSupported(String charsetName) {
// can you believe that this throws a runtime? Just asking if it's
// supported!!?! They coulda just said "no"...
+ if(charsetName == null) {
+ return false;
+ }
try {
return Charset.isSupported(charsetName);
} catch(IllegalCharsetNameException e) {
@@ -192,8 +195,10 @@
// (5)
detector.reset();
-
- return charsetName;
+ if(isCharsetSupported(charsetName)) {
+ return charsetName;
+ }
+ return null;
}
/**
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
|
From: <bra...@us...> - 2009-05-20 02:28:41
|
Revision: 2721
http://archive-access.svn.sourceforge.net/archive-access/?rev=2721&view=rev
Author: bradtofel
Date: 2009-05-20 02:28:33 +0000 (Wed, 20 May 2009)
Log Message:
-----------
FEATURE: Now compares chaset case-insensitive in meta tags and HTTP headers
FEATURE: exposed setResultBytes()
FEATURE: new insertAtStartOfDocument() method
FEATURE: now detects charset by: a) document META tag, b) byte-detection, c) HTTP header. before was c,b,a.
Modified Paths:
--------------
trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/replay/TextDocument.java
Modified: trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/replay/TextDocument.java
===================================================================
--- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/replay/TextDocument.java 2009-05-20 02:22:20 UTC (rev 2720)
+++ trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/replay/TextDocument.java 2009-05-20 02:28:33 UTC (rev 2721)
@@ -31,6 +31,7 @@
import java.nio.charset.Charset;
import java.nio.charset.IllegalCharsetNameException;
import java.text.ParseException;
+import java.util.Iterator;
import java.util.Map;
import javax.servlet.ServletException;
@@ -102,7 +103,9 @@
}
private String contentTypeToCharset(final String contentType) {
- int offset = contentType.indexOf(CHARSET_TOKEN);
+ int offset =
+ contentType.toUpperCase().indexOf(CHARSET_TOKEN.toUpperCase());
+
if (offset != -1) {
String cs = contentType.substring(offset + CHARSET_TOKEN.length());
if(isCharsetSupported(cs)) {
@@ -135,7 +138,16 @@
String charsetName = null;
Map<String,String> httpHeaders = resource.getHttpHeaders();
- String ctype = httpHeaders.get(HTTP_CONTENT_TYPE_HEADER);
+ Iterator<String> keys = httpHeaders.keySet().iterator();
+ String ctype = null;
+ while(keys.hasNext()) {
+ String headerKey = keys.next();
+ String keyCmp = headerKey.toUpperCase().trim();
+ if(keyCmp.equals(HTTP_CONTENT_TYPE_HEADER.toUpperCase())) {
+ ctype = httpHeaders.get(headerKey);
+ break;
+ }
+ }
if (ctype != null) {
charsetName = contentTypeToCharset(ctype);
}
@@ -212,11 +224,11 @@
*/
protected String guessCharset() throws IOException {
- String charSet = getCharsetFromMeta(resource);
+ String charSet = getCharsetFromHeaders(resource);
if(charSet == null) {
charSet = getCharsetFromBytes(resource);
if(charSet == null) {
- charSet = getCharsetFromHeaders(resource);
+ charSet = getCharsetFromMeta(resource);
if(charSet == null) {
charSet = "UTF-8";
}
@@ -365,6 +377,9 @@
* @throws UnsupportedEncodingException
*/
public byte[] getBytes() throws UnsupportedEncodingException {
+ if(resultBytes != null) {
+ return resultBytes;
+ }
if(sb == null) {
throw new IllegalStateException("No interal StringBuffer");
}
@@ -374,6 +389,10 @@
return resultBytes;
}
+ public void setResultBytes(byte[] resultBytes) {
+ this.resultBytes = resultBytes;
+ }
+
/**
* Write the contents of the page to the client.
*
@@ -396,6 +415,13 @@
/**
* @param toInsert
*/
+ public void insertAtStartOfDocument(String toInsert) {
+ sb.insert(0,toInsert);
+ }
+
+ /**
+ * @param toInsert
+ */
public void insertAtStartOfHead(String toInsert) {
int insertPoint = TagMagix.getEndOfFirstTag(sb,"head");
if (-1 == insertPoint) {
@@ -450,9 +476,6 @@
StringHttpServletResponseWrapper wrappedResponse =
new StringHttpServletResponseWrapper(httpResponse);
uiResults.forward(httpRequest, wrappedResponse, jspPath);
-// uiResults.storeInRequest(httpRequest,jspPath);
-// RequestDispatcher dispatcher = httpRequest.getRequestDispatcher(jspPath);
-// dispatcher.forward(httpRequest, wrappedResponse);
return wrappedResponse.getStringResponse();
}
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
|
From: <bra...@us...> - 2010-07-28 00:09:57
|
Revision: 3192
http://archive-access.svn.sourceforge.net/archive-access/?rev=3192&view=rev
Author: bradtofel
Date: 2010-07-28 00:09:51 +0000 (Wed, 28 Jul 2010)
Log Message:
-----------
Added method "addBase()" which just adds a <base href="X"> tag.
Modified Paths:
--------------
trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/replay/TextDocument.java
Modified: trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/replay/TextDocument.java
===================================================================
--- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/replay/TextDocument.java 2010-07-27 23:57:00 UTC (rev 3191)
+++ trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/replay/TextDocument.java 2010-07-28 00:09:51 UTC (rev 3192)
@@ -77,7 +77,20 @@
this.uriConverter = uriConverter;
}
+ public void addBase() {
+ // TODO: get url from Resource instead of SearchResult?
+ String pageUrl = result.getOriginalUrl();
+ String captureDate = result.getCaptureTimestamp();
+
+ String existingBaseHref = TagMagix.getBaseHref(sb);
+ if (existingBaseHref == null) {
+ insertAtStartOfHead("<base href=\"" + pageUrl + "\" />");
+ } else {
+ pageUrl = existingBaseHref;
+ }
+ }
+
/**
* Update URLs inside the page, so those URLs which must be correct at
* page load time resolve correctly to absolute URLs.
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
|
From: <ikr...@us...> - 2011-12-20 23:06:38
|
Revision: 3587
http://archive-access.svn.sourceforge.net/archive-access/?rev=3587&view=rev
Author: ikreymer
Date: 2011-12-20 23:06:32 +0000 (Tue, 20 Dec 2011)
Log Message:
-----------
BUGFIX: if the first char read from the InputStreamReader is a 0xFEFF BOM marker, remove it -- this implies the InputStreamReader is not interpreting it, and thus it should be removed from the content to avoid problems.
Modified Paths:
--------------
trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/replay/TextDocument.java
Modified: trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/replay/TextDocument.java
===================================================================
--- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/replay/TextDocument.java 2011-12-18 04:17:45 UTC (rev 3586)
+++ trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/replay/TextDocument.java 2011-12-20 23:06:32 UTC (rev 3587)
@@ -205,6 +205,13 @@
// slurp the whole thing into RAM:
sb = new StringBuilder(recordLength);
+
+ //Skip the UTF-8 BOM 0xFEFF
+ int firstChar = isr.read();
+ if ((firstChar != '\uFEFF') && (firstChar != -1)) {
+ sb.append(firstChar);
+ }
+
for (int r = -1; (r = isr.read(cbuffer, 0, C_BUFFER_SIZE)) != -1;) {
sb.append(cbuffer, 0, r);
}
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
|
From: <ikr...@us...> - 2011-12-24 00:46:49
|
Revision: 3589
http://archive-access.svn.sourceforge.net/archive-access/?rev=3589&view=rev
Author: ikreymer
Date: 2011-12-24 00:46:42 +0000 (Sat, 24 Dec 2011)
Log Message:
-----------
BUGFIX: Fix adding first character as a char not int!
Modified Paths:
--------------
trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/replay/TextDocument.java
Modified: trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/replay/TextDocument.java
===================================================================
--- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/replay/TextDocument.java 2011-12-21 20:55:11 UTC (rev 3588)
+++ trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/replay/TextDocument.java 2011-12-24 00:46:42 UTC (rev 3589)
@@ -209,7 +209,7 @@
//Skip the UTF-8 BOM 0xFEFF
int firstChar = isr.read();
if ((firstChar != '\uFEFF') && (firstChar != -1)) {
- sb.append(firstChar);
+ sb.append((char)firstChar);
}
for (int r = -1; (r = isr.read(cbuffer, 0, C_BUFFER_SIZE)) != -1;) {
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
×
Want the latest updates on software, tech news, and AI?
Get latest updates about software, tech news, and AI from SourceForge directly in your inbox once a month.
Thanks for helping keep SourceForge clean.
X