Skip to content
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

Jump to bottom

Fixing problems with Wikipedia dump template #3

Open
wants to merge 3 commits into
base: master
Choose a base branch
from
Open

Fixing problems with Wikipedia dump template #3

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
d96a321
fix: replace <text xml:space="preserve"> for a pattern matching <tex…
ragnarok85 Jul 19, 2020
7711ad8
Update ExtractContextualToken.java
Julio-Noe Sep 16, 2020
a52e2f6
Fixing problems with updated template from Wikipedia dumps files
ragnarok85 Mar 15, 2021
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
4 changes: 3 additions & 1 deletion src/main/java/com/diffbot/wikistatsextractor/extractors/ExtractContextualToken.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -455,7 +455,9 @@ public static void extractContextualToken(String path_to_dump, String tmp_folder
String line = br.readLine();
while (line != null) {
String[] split = Util.fastSplit(line);
redirections.put(split[0], split[1]);
//old: redirections.put(split[0], split[1]), sometimes length was 0
if(split.length > 1)
redirections.put(split[0], split[1]);
line = br.readLine();
}
br.close();
Expand Down
17 changes: 15 additions & 2 deletions src/main/java/com/diffbot/wikistatsextractor/util/Util.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,6 +6,8 @@
import java.net.URLDecoder;
import java.net.URLEncoder;
import java.util.*;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

/** some Utils methods */
public class Util {
Expand Down Expand Up @@ -44,10 +46,21 @@ public static List<String> getCleanTextFromPage(String page, boolean ignore_list
}

/** go to the index of the text */
int index_text = page.indexOf("<text xml:space=\"preserve\">");
String patternStr = "<text.*xml:space=\"preserve\">";
Pattern patternIndex = Pattern.compile(patternStr);
Matcher matcherIndex = patternIndex.matcher(page);
//old pattern version: int index_text = page.indexOf("<text xml:space=\"preserve\">");
int index_text = -1;
String preserve = "";
if(matcherIndex.find()) {
index_text = matcherIndex.start();
preserve = page.substring(index_text,matcherIndex.end());
//System.out.println(preserve + "...");
}
if (index_text == -1)
return null;
index_text += "<text xml:space=\"preserve\">".length();
//index_text += "<text xml:space=\"preserve\">".length();
index_text += preserve.length();

/** locate the end */
int end_text = page.indexOf("</text>");
Expand Down