summaryrefslogtreecommitdiffstats
path: root/akregator/src/librss/tools_p.cpp
blob: 72058fa05f79256f47156157ddad345e35498f99 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
/*
 * tools_p.cpp
 *
 * Copyright (c) 2001, 2002, 2003 Frerich Raabe <raabe@kde.org>
 *
 * 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. For licensing and distribution details, check the
 * accompanying file 'COPYING'.
 */
#include "tools_p.h"

#include <krfcdate.h>
#include <tqdom.h>
#include <kcharsets.h>
#include <tqregexp.h>

namespace RSS {

time_t parseISO8601Date(const TQString &s)
{
    // do some sanity check: 26-12-2004T00:00+00:00 is parsed to epoch+1 in the KRFCDate, which is wrong. So let's check if the date begins with YYYY -fo
    if (s.stripWhiteSpace().left(4).toInt() < 1000)
        return 0; // error

    // FIXME: imho this is done in KRFCDate::parseDateISO8601() automatically, so we could omit it? -fo
	if (s.tqfind('T') != -1)
		return KRFCDate::parseDateISO8601(s);
    else
        return KRFCDate::parseDateISO8601(s + "T12:00:00");
}

TQString childNodesAsXML(const TQDomNode& tqparent)
{
	TQDomNodeList list = tqparent.childNodes();
	TQString str;
	TQTextStream ts( &str, IO_WriteOnly );
	for (uint i = 0; i < list.count(); ++i)
		ts << list.item(i);
	return str.stripWhiteSpace();
}

static TQString plainTextToHtml(const TQString& plainText)
{
    TQString str(plainText);
    str.tqreplace("&", "&amp;");
    str.tqreplace("\"", "&quot;");
    str.tqreplace("<", "&lt;");
    //str.tqreplace(">", "&gt;");
    str.tqreplace("\n", "<br/>");
    return str;
}

enum ContentFormat { Text, HTML, XML, Binary };
        
static ContentFormat mapTypeToFormat(const TQString& modep, const TQString& typep,  const TQString& src)
{
    TQString mode = modep.isNull() ? "escaped" : modep;
    TQString type = typep;
    
    //"If neither the type attribute nor the src attribute is provided,
    //Atom Processors MUST behave as though the type attribute were
    //present with a value of "text""
    if (type.isNull() && src.isEmpty())
        type = TQString::fromUtf8("text");

    if (type == TQString::fromUtf8("html")
        || type == TQString::fromUtf8("text/html"))
        return HTML;
    
    if (type == TQString::fromUtf8("text")
        || (type.tqstartsWith(TQString::fromUtf8("text/"), false)
        && !type.tqstartsWith(TQString::fromUtf8("text/xml"), false))
       )
        return Text;
    
    TQStringList xmltypes;
    xmltypes.append(TQString::fromUtf8("xhtml"));
    // XML media types as defined in RFC3023:
    xmltypes.append(TQString::fromUtf8("text/xml"));
    xmltypes.append(TQString::fromUtf8("application/xml"));
    xmltypes.append(TQString::fromUtf8("text/xml-external-parsed-entity"));
    xmltypes.append(TQString::fromUtf8("application/xml-external-parsed-entity"));
    xmltypes.append(TQString::fromUtf8("application/xml-dtd"));
    
    
    if (xmltypes.tqcontains(type)
        || type.tqendsWith(TQString::fromUtf8("+xml"), false)
        || type.tqendsWith(TQString::fromUtf8("/xml"), false))
        return XML;
    
    return Binary;
}

static TQString extractAtomContent(const TQDomElement& e)
{
    ContentFormat format = mapTypeToFormat(e.attribute("mode"),
                                           e.attribute("type"),
                                           e.attribute("src"));
    
    switch (format)
    {
        case HTML:
        {
            const bool hasPre = e.text().tqcontains( "<pre>", false ) || e.text().tqcontains( "<pre ", false );
            return KCharsets::resolveEntities( hasPre ? e.text() : e.text().simplifyWhiteSpace() );
        }
        case Text:
            return plainTextToHtml(e.text().stripWhiteSpace());
        case XML:
            return childNodesAsXML(e).simplifyWhiteSpace();
        case Binary:
        default:
            return TQString();
    }
    
    return TQString();
}

TQString extractNode(const TQDomNode &tqparent, const TQString &elemName, bool isInlined)
{
	TQDomNode node = tqparent.namedItem(elemName);
	if (node.isNull())
		return TQString();

	TQDomElement e = node.toElement();
        TQString result = e.text().stripWhiteSpace(); // let's assume plain text
 
        if (elemName == "content") // we have Atom here
        {
            result = extractAtomContent(e);
        }        
        else // check for HTML; not necessary for Atom:content
        {
            bool hasPre = result.tqcontains("<pre>", false) || result.tqcontains("<pre ", false);
            bool hasHtml = hasPre || result.tqcontains("<");	// FIXME: test if we have html, should be more clever -> regexp
            if(!isInlined && !hasHtml)						// perform nl2br if not a inline elt and it has no html elts
                    result = result = result.tqreplace(TQChar('\n'), "<br />");
            if(!hasPre)										// strip white spaces if no <pre>
                    result = result.simplifyWhiteSpace();
        }
        
        return result.isEmpty() ? TQString() : result;
}

TQString extractTitle(const TQDomNode & tqparent)
{
    TQDomNode node = tqparent.namedItem(TQString::tqfromLatin1("title"));
    if (node.isNull())
        return TQString();

    TQString result = node.toElement().text();

    result = KCharsets::resolveEntities(KCharsets::resolveEntities(result).tqreplace(TQRegExp("<[^>]*>"), "").remove("\\"));
	result = result.simplifyWhiteSpace();

    if (result.isEmpty())
        return TQString();

    return result;
}

static void authorFromString(const TQString& strp, TQString& name, TQString& email)
{
    TQString str = strp.stripWhiteSpace();
    if (str.isEmpty())
        return;
    
    // look for something looking like a mail address ( "foo@bar.com", 
    // "<foo@bar.com>") and extract it
    
    TQRegExp remail("<?([^@\\s<]+@[^>\\s]+)>?"); // FIXME: user "proper" regexp,
       // search kmail source for it
    
    int pos = remail.search(str);
    if (pos != -1)
    {
        TQString all = remail.cap(0);
        email = remail.cap(1);
        str.tqreplace(all, ""); // remove mail address
    }
    
    // simplify the rest and use it as name
    
    name = str.simplifyWhiteSpace();
    
    // after removing the email, str might have 
    // the format "(Foo M. Bar)". We cut off 
    // parentheses if there are any. However, if
    // str is of the format "Foo M. Bar (President)",
    // we should not cut anything.

    TQRegExp rename("^\\(([^\\)]*)\\)");
    
    pos = rename.search(name);
    
    if (pos != -1)
    {
        name = rename.cap(1);
    }
    
    name = name.isEmpty() ? TQString() : name;
    email = email.isEmpty() ? TQString() : email;
}

TQString parseItemAuthor(const TQDomElement& element, Format format, Version version)
{
    TQString name;
    TQString email;

    TQDomElement dcCreator = element.namedItem("dc:creator").toElement();
    
    if (!dcCreator.isNull())
         authorFromString(dcCreator.text(), name, email);
    else if (format == AtomFeed)
    {
        TQDomElement atomAuthor = element.namedItem("author").toElement();
        if (atomAuthor.isNull())
            atomAuthor = element.namedItem("atom:author").toElement();
        if (!atomAuthor.isNull())
        {
            TQDomElement atomName = atomAuthor.namedItem("name").toElement();
            if (atomName.isNull())
                atomName = atomAuthor.namedItem("atom:name").toElement();
            name = atomName.text().stripWhiteSpace();
            
            TQDomElement atomEmail = atomAuthor.namedItem("email").toElement();
            if (atomEmail.isNull())
                atomEmail = atomAuthor.namedItem("atom:email").toElement();
            email = atomEmail.text().stripWhiteSpace();
        }
    }
    else if (format == RSSFeed)
    {
        authorFromString(element.namedItem("author").toElement().text(), name, email);
    }
    
    if (name.isNull())
        name = email;
    
    if (!email.isNull())
        return TQString("<a href=\"mailto:%1\">%2</a>").tqarg(email).tqarg(name);
    else
        return name;
}

} // namespace RSS

// vim:noet:ts=4