jcs.org
an experiment in making a cocoa webkit browser manageable under X11
1//
2// NSString+HTML.h
3// MWFeedParser
4//
5// Copyright (c) 2010 Michael Waterfall
6//
7// Permission is hereby granted, free of charge, to any person obtaining a copy
8// of this software and associated documentation files (the "Software"), to deal
9// in the Software without restriction, including without limitation the rights
10// to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
11// copies of the Software, and to permit persons to whom the Software is
12// furnished to do so, subject to the following conditions:
13//
14// 1. The above copyright notice and this permission notice shall be included
15// in all copies or substantial portions of the Software.
16//
17// 2. This Software cannot be used to archive or collect data such as (but not
18// limited to) that of events, news, experiences and activities, for the
19// purpose of any concept relating to diary/journal keeping.
20//
21// THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
22// IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
23// FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
24// AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
25// LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
26// OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
27// THE SOFTWARE.
28//
29
30#import <Foundation/Foundation.h>
31
32// Dependant upon GTMNSString+HTML
33
34@interface NSString (HTML)
35
36// Strips HTML tags & comments, removes extra whitespace and decodes HTML character entities.
37- (NSString *)stringByConvertingHTMLToPlainText;
38
39// Decode all HTML entities using GTM.
40- (NSString *)stringByDecodingHTMLEntities;
41
42// Encode all HTML entities using GTM.
43- (NSString *)stringByEncodingHTMLEntities;
44
45// Minimal unicode encoding will only cover characters from table
46// A.2.2 of http://www.w3.org/TR/xhtml1/dtds.html#a_dtd_Special_characters
47// which is what you want for a unicode encoded webpage.
48- (NSString *)stringByEncodingHTMLEntities:(BOOL)isUnicode;
49
50// Replace newlines with <br /> tags.
51- (NSString *)stringWithNewLinesAsBRs;
52
53// Remove newlines and white space from string.
54- (NSString *)stringByRemovingNewLinesAndWhitespace;
55
56// Wrap plain URLs in <a href="..." class="linkified">...</a>
57// - Ignores URLs inside tags (any URL beginning with =")
58// - HTTP & HTTPS schemes only
59// - Only works in iOS 4+ as we use NSRegularExpression (returns self if not supported so be careful with NSMutableStrings)
60// - Expression: (?<!=")\b((http|https):\/\/[\w\-_]+(\.[\w\-_]+)+([\w\-\.,@?^=%&:/~\+#]*[\w\-\@?^=%&/~\+#])?)
61// - Adapted from http://regexlib.com/REDetails.aspx?regexp_id=96
62- (NSString *)stringByLinkifyingURLs;
63
64// DEPRECIATED - Please use NSString stringByConvertingHTMLToPlainText
65- (NSString *)stringByStrippingTags __attribute__((deprecated));
66
67@end