Skip to content

StringIndexOutOfBoundsException in patternCSSExtract #57

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
sebastian-nagel wants to merge 1 commit into from
Closed

StringIndexOutOfBoundsException in patternCSSExtract #57

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
31 changes: 10 additions & 21 deletions src/main/java/org/archive/resource/html/ExtractingParseObserver.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,7 +23,7 @@ public class ExtractingParseObserver implements ParseObserver {
protected static String cssUrlPatString =
"url\\s*\\(\\s*([\\\\\"']*.+?[\\\\\"']*)\\s*\\)";
protected static String cssImportNoUrlPatString =
"@import\\s+(('[^']+')|(\"[^\"]+\")|(\\('[^']+'\\))|(\\(\"[^\"]+\"\\))|(\\([^)]+\\))|([a-z0-9_.:/\\\\-]+))\\s*;";
"@import\\s+((?:'[^']+')|(?:\"[^\"]+\")|(?:\\('[^']+'\\))|(?:\\(\"[^\"]+\"\\))|(?:\\([^)]+\\))|(?:[a-z0-9_.:/\\\\-]+))\\s*;";

protected static Pattern cssImportNoUrlPattern = Pattern
.compile(cssImportNoUrlPatString);
Expand Down Expand Up @@ -372,36 +372,25 @@ private void patternCSSExtract(HTMLMetaData data, Pattern pattern, String conten
Matcher m = pattern.matcher(content);
int idx = 0;
int contentLen = content.length();
while((idx < contentLen) && m.find(idx)) {
while((idx < contentLen) && m.find()) {
idx = m.end();
String url = m.group(1);
int origUrlLength = url.length();
int urlStart = m.start(1);
int urlEnd = m.end(1);
idx = urlEnd;
if(url.length() < 2) {
continue;
}
if ((url.charAt(0) == '(')
&& (url.charAt(origUrlLength-1) == ')')) {
url = url.substring(1, origUrlLength - 1);
urlStart += 1;
origUrlLength -= 2;
&& (url.charAt(url.length()-1) == ')')) {
url = url.substring(1, url.length() - 1);
}
if (url.charAt(0) == '"') {
url = url.substring(1, origUrlLength - 1);
urlStart += 1;
} else if (url.charAt(0) == '\'') {
url = url.substring(1, origUrlLength - 1);
urlStart += 1;
if (url.charAt(0) == '"' || url.charAt(0) == '\'') {
url = url.substring(1, url.length() - 1);
} else if (url.charAt(0) == '\\') {
if(url.length() == 2)
if(url.length() <= 4) {
continue;
url = url.substring(2, origUrlLength - 2);
urlStart += 2;
}
url = url.substring(2, url.length() - 2);
}
int urlLength = url.length();
data.addHref("path","STYLE/#text","href",url);
idx += urlLength;
}
}
}
3 changes: 2 additions & 1 deletion src/test/java/org/archive/resource/html/ExtractingParseObserverTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,8 @@ public void testHandleStyleNodeExceptions() throws Exception {
"url (' ')",
"url('\")",
"url(')",
"url('\"')"
"url('\"')",
"url('\\\"\"')"
};
boolean except = false;
HTMLMetaData md = new HTMLMetaData(new MetaData());
Expand Down