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 | package Torello.HTML.Tools.NewsSite;
import Torello.HTML.HTMLNode;
import Torello.HTML.TextNode;
import Torello.HTML.Util;
import java.util.Vector;
import java.net.URL;
import java.util.regex.Pattern;
class Usual_pattern
{
public static ArticleGet generate(
final Pattern startPattern,
final Pattern endPattern
)
{
// *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** ***
// FAIL-FAST: Check user-input for possible errors BEFORE building the Lambda-Function.
// *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** ***
if (startPattern == null) throw new NullPointerException
("Null has been passed to parameter 'startPattern', but this is not allowed here.");
if (endPattern == null) throw new NullPointerException
("Null has been passed to parameter 'endPattern', but this is not allowed here.");
// *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** ***
// Build the instance, using a lambda-expression
// *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** ***
return (URL url, Vector<HTMLNode> page) ->
{
// This exception-check is done on every invokation of this Lambda-Function.
// It is merely checking that these inputs are not-null, and page is of non-zero size.
// ArticleGetException is a compile-time, checked exception. It is important to halt
// News-Site Scrape Progress when "Empty News-Page Data" is being passed here.
// NOTE: This would imply an internal-error with class Download has occured.
ArticleGetException.check(url, page);
int start = -1;
int end = -1;
HTMLNode n = null;
while (start++ < page.size())
if ((n = page.elementAt(start)) instanceof TextNode)
if (startPattern.matcher(n.str).find())
break;
while (end++ < page.size())
if ((n = page.elementAt(end)) instanceof TextNode)
if (endPattern.matcher(n.str).find())
break;
// These error-checks are used to deduce whether the "Article Get" was successful.
// When this exception is thrown, it means that the user-specified means of "Retrieving
// an Article Body" FAILED. In this case it is because the start or end regex failed to
// match.
if (start == page.size()) throw new ArticleGetException(
"Start Pattern [" + startPattern.toString() + "], was not found on the HTML " +
"page."
);
if (end == page.size()) throw new ArticleGetException
("End Pattern [" + endPattern.toString() + "], was not found on the HTML page.");
return Util.cloneRange(page, start, end + 1);
};
}
}
|