这是indexloc提供的服务，不要输入任何密码
Skip to content

improve url matching regex #1237

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

Merged
merged 1 commit into from
Sep 8, 2019
Merged

improve url matching regex #1237

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
73 changes: 70 additions & 3 deletions app/src/main/java/com/termux/app/TermuxActivity.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -654,19 +654,86 @@ public boolean onCreateOptionsMenu(Menu menu) {
}

static LinkedHashSet<CharSequence> extractUrls(String text) {
// Pattern for recognizing a URL, based off RFC 3986
// http://stackoverflow.com/questions/5713558/detect-and-extract-url-from-a-string

StringBuilder regex_sb = new StringBuilder();

regex_sb.append("("); // Begin first matching group.
regex_sb.append("(?:"); // Begin scheme group.
regex_sb.append("dav|"); // The DAV proto.
regex_sb.append("dict|"); // The DICT proto.
regex_sb.append("dns|"); // The DNS proto.
regex_sb.append("file|"); // File path.
regex_sb.append("finger|"); // The Finger proto.
regex_sb.append("ftp(?:s?)|"); // The FTP proto.
regex_sb.append("git|"); // The Git proto.
regex_sb.append("gopher|"); // The Gopher proto.
regex_sb.append("http(?:s?)|"); // The HTTP proto.
regex_sb.append("imap(?:s?)|"); // The IMAP proto.
regex_sb.append("irc(?:[6s]?)|"); // The IRC proto.
regex_sb.append("ip[fn]s|"); // The IPFS proto.
regex_sb.append("ldap(?:s?)|"); // The LDAP proto.
regex_sb.append("pop3(?:s?)|"); // The POP3 proto.
regex_sb.append("redis(?:s?)|"); // The Redis proto.
regex_sb.append("rsync|"); // The Rsync proto.
regex_sb.append("rtsp(?:[su]?)|"); // The RTSP proto.
regex_sb.append("sftp|"); // The SFTP proto.
regex_sb.append("smb(?:s?)|"); // The SAMBA proto.
regex_sb.append("smtp(?:s?)|"); // The SMTP proto.
regex_sb.append("svn(?:(?:\\+ssh)?)|"); // The Subversion proto.
regex_sb.append("tcp|"); // The TCP proto.
regex_sb.append("telnet|"); // The Telnet proto.
regex_sb.append("tftp|"); // The TFTP proto.
regex_sb.append("udp|"); // The UDP proto.
regex_sb.append("vnc|"); // The VNC proto.
regex_sb.append("ws(?:s?)"); // The Websocket proto.
regex_sb.append(")://"); // End scheme group.
regex_sb.append(")"); // End first matching group.


// Begin second matching group.
regex_sb.append("(");

// User name and/or password in format 'user:pass@'.
regex_sb.append("(?:\\S+(?::\\S*)?@)?");

// Begin host group.
regex_sb.append("(?:");

// IP address (from http://www.regular-expressions.info/examples.html).
regex_sb.append("(?:(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)\\.){3}(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)|");

// Host name or domain.
regex_sb.append("(?:(?:[a-z\\u00a1-\\uffff0-9]-*)*[a-z\\u00a1-\\uffff0-9]+)(?:(?:\\.(?:[a-z\\u00a1-\\uffff0-9]-*)*[a-z\\u00a1-\\uffff0-9]+)*(?:\\.(?:[a-z\\u00a1-\\uffff]{2,})))?|");

// Just path. Used in case of 'file://' scheme.
regex_sb.append("/(?:(?:[a-z\\u00a1-\\uffff0-9]-*)*[a-z\\u00a1-\\uffff0-9]+)");

// End host group.
regex_sb.append(")");

// Port number.
regex_sb.append("(?::\\d{1,5})?");

// Resource path with optional query string.
regex_sb.append("(?:/[a-zA-Z0-9:@%\\-._~!$&()*+,;=?/]*)?");

// End second matching group.
regex_sb.append(")");

final Pattern urlPattern = Pattern.compile(
"(?:^|[\\W])((ht|f)tp(s?)://|www\\.)" + "(([\\w\\-]+\\.)+?([\\w\\-.~]+/?)*" + "[\\p{Alnum}.,%_=?&#\\-+()\\[\\]*$~@!:/{};']*)",
regex_sb.toString(),
Pattern.CASE_INSENSITIVE | Pattern.MULTILINE | Pattern.DOTALL);

LinkedHashSet<CharSequence> urlSet = new LinkedHashSet<>();
Matcher matcher = urlPattern.matcher(text);

while (matcher.find()) {
int matchStart = matcher.start(1);
int matchEnd = matcher.end();
String url = text.substring(matchStart, matchEnd);
urlSet.add(url);
}

return urlSet;
}

Expand Down