com.itextpdf.styledxmlparser.jsoup.helper.StringUtil Maven / Gradle / Ivy
Go to download
Show more of this group Show more artifacts with this name
Show all versions of styled-xml-parser Show documentation
Show all versions of styled-xml-parser Show documentation
Styled XML parser is used by iText7 modules to parse HTML and XML
/*
This file is part of the iText (R) project.
Copyright (c) 1998-2019 iText Group NV
Authors: iText Software.
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU Affero General Public License version 3
as published by the Free Software Foundation with the addition of the
following permission added to Section 15 as permitted in Section 7(a):
FOR ANY PART OF THE COVERED WORK IN WHICH THE COPYRIGHT IS OWNED BY
ITEXT GROUP. ITEXT GROUP DISCLAIMS THE WARRANTY OF NON INFRINGEMENT
OF THIRD PARTY RIGHTS
This program is distributed in the hope that it will be useful, but
WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
or FITNESS FOR A PARTICULAR PURPOSE.
See the GNU Affero General Public License for more details.
You should have received a copy of the GNU Affero General Public License
along with this program; if not, see http://www.gnu.org/licenses or write to
the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
Boston, MA, 02110-1301 USA, or download the license from the following URL:
http://itextpdf.com/terms-of-use/
The interactive user interfaces in modified source and object code versions
of this program must display Appropriate Legal Notices, as required under
Section 5 of the GNU Affero General Public License.
In accordance with Section 7(b) of the GNU Affero General Public License,
a covered work must retain the producer line in every PDF that is created
or manipulated using iText.
You can be released from the requirements of the license by purchasing
a commercial license. Buying such a license is mandatory as soon as you
develop commercial activities involving the iText software without
disclosing the source code of your own applications.
These activities include: offering paid services to customers as an ASP,
serving PDFs on the fly in a web application, shipping iText with a closed
source product.
For more information, please contact iText Software Corp. at this
address: [email protected]
*/
package com.itextpdf.styledxmlparser.jsoup.helper;
import java.net.MalformedURLException;
import java.net.URL;
import java.util.Arrays;
import java.util.Collection;
import java.util.Iterator;
/**
* A minimal String utility class. Designed for internal jsoup use only.
*/
public final class StringUtil {
// memoised padding up to 10
private static final String[] padding = {"", " ", " ", " ", " ", " ", " ", " ", " ", " ", " "};
/**
* Join a collection of strings by a seperator
* @param strings collection of string objects
* @param sep string to place between strings
* @return joined string
*/
public static String join(Collection strings, String sep) {
return join(strings.iterator(), sep);
}
/**
* Join a collection of strings by a seperator
* @param strings iterator of string objects
* @param sep string to place between strings
* @return joined string
*/
public static String join(Iterator strings, String sep) {
if (!strings.hasNext())
return "";
String start = strings.next().toString();
if (!strings.hasNext()) // only one, avoid builder
return start;
StringBuilder sb = new StringBuilder(64).append(start);
while (strings.hasNext()) {
sb.append(sep);
sb.append(strings.next());
}
return sb.toString();
}
/**
* Returns space padding
* @param width amount of padding desired
* @return string of spaces * width
*/
public static String padding(int width) {
if (width < 0)
throw new IllegalArgumentException("width must be > 0");
if (width < padding.length)
return padding[width];
char[] out = new char[width];
for (int i = 0; i < width; i++)
out[i] = ' ';
return String.valueOf(out);
}
/**
* Tests if a string is blank: null, emtpy, or only whitespace (" ", \r\n, \t, etc)
* @param string string to test
* @return if string is blank
*/
public static boolean isBlank(String string) {
if (string == null || string.length() == 0)
return true;
int l = string.length();
for (int i = 0; i < l; i++) {
if (!StringUtil.isWhitespace(string.codePointAt(i)))
return false;
}
return true;
}
/**
* Tests if a string is numeric, i.e. contains only digit characters
* @param string string to test
* @return true if only digit chars, false if empty or null or contains non-digit chrs
*/
public static boolean isNumeric(String string) {
if (string == null || string.length() == 0)
return false;
int l = string.length();
for (int i = 0; i < l; i++) {
if (!Character.isDigit(string.codePointAt(i)))
return false;
}
return true;
}
/**
* Tests if a code point is "whitespace" as defined in the HTML spec.
* @param c code point to test
* @return true if code point is whitespace, false otherwise
*/
public static boolean isWhitespace(int c){
return c == ' ' || c == '\t' || c == '\n' || c == '\f' || c == '\r';
}
/**
* Normalise the whitespace within this string; multiple spaces collapse to a single, and all whitespace characters
* (e.g. newline, tab) convert to a simple space
* @param string content to normalise
* @return normalised string
*/
public static String normaliseWhitespace(String string) {
StringBuilder sb = new StringBuilder(string.length());
appendNormalisedWhitespace(sb, string, false);
return sb.toString();
}
/**
* After normalizing the whitespace within a string, appends it to a string builder.
* @param accum builder to append to
* @param string string to normalize whitespace within
* @param stripLeading set to true if you wish to remove any leading whitespace
*/
public static void appendNormalisedWhitespace(StringBuilder accum, String string, boolean stripLeading) {
boolean lastWasWhite = false;
boolean reachedNonWhite = false;
int len = string.length();
int c;
for (int i = 0; i < len; i+= Character.charCount(c)) {
c = string.codePointAt(i);
if (isWhitespace(c)) {
if ((stripLeading && !reachedNonWhite) || lastWasWhite)
continue;
accum.append(' ');
lastWasWhite = true;
}
else {
accum.appendCodePoint(c);
lastWasWhite = false;
reachedNonWhite = true;
}
}
}
public static boolean in(String needle, String... haystack) {
for (String hay : haystack) {
if (hay.equals(needle))
return true;
}
return false;
}
public static boolean inSorted(String needle, String[] haystack) {
return Arrays.binarySearch(haystack, needle) >= 0;
}
/**
* Create a new absolute URL, from a provided existing absolute URL and a relative URL component.
* @param base the existing absolulte base URL
* @param relUrl the relative URL to resolve. (If it's already absolute, it will be returned)
* @return the resolved absolute URL
* @throws MalformedURLException if an error occurred generating the URL
*/
public static URL resolve(URL base, String relUrl) throws MalformedURLException {
// workaround: java resolves '//path/file + ?foo' to '//path/?foo', not '//path/file?foo' as desired
if (relUrl.startsWith("?"))
relUrl = base.getPath() + relUrl;
// workaround: //example.com + ./foo = //example.com/./foo, not //example.com/foo
if (relUrl.indexOf('.') == 0 && base.getFile().indexOf('/') != 0) {
base = new URL(base.getProtocol(), base.getHost(), base.getPort(), "/" + base.getFile());
}
return new URL(base, relUrl);
}
/**
* Create a new absolute URL, from a provided existing absolute URL and a relative URL component.
* @param baseUrl the existing absolute base URL
* @param relUrl the relative URL to resolve. (If it's already absolute, it will be returned)
* @return an absolute URL if one was able to be generated, or the empty string if not
*/
public static String resolve(final String baseUrl, final String relUrl) {
URL base;
try {
try {
base = new URL(baseUrl);
} catch (MalformedURLException e) {
// the base is unsuitable, but the attribute/rel may be abs on its own, so try that
URL abs = new URL(relUrl);
return abs.toExternalForm();
}
return resolve(base, relUrl).toExternalForm();
} catch (MalformedURLException e) {
return "";
}
}
}