Wikipedia:Bots/Requests for approval/MetsBot 12


 * The following discussion is an archived debate. Please do not modify it. Subsequent comments should be made in a new section. The result of the discussion was Symbol keep vote.svg Approved.

MetsBot
Operator: Mets501

Automatic or Manually Assisted: Automatic but every edit will be checked

Programming Language(s): AWB with C# module

Function Summary: ame exact task as Bots/Requests for approval/EBot Task2

Edit period(s) (e.g. Continuous, daily, one time run): one time run

Edit rate requested: 10 edits per minute

Already has a bot flag (Y/N): Y

Function Details: User:E withdrew his request to run this task, so I'm taking it over.

Discussion
Actually, if I could just get approval for any of this sort of template parameter-updating that would be great. — M ETS 501 (talk) 03:27, 24 August 2007 (UTC)
 * The prior withdrawal was that AWB would not be able to accomplish this task, has that been resolved? —  xaosflux  Talk 04:31, 24 August 2007 (UTC)
 * I'm actually not really using AWB for the article processing, just for the list-making and article-saving. I'm using C# regexes for the processing.  I'll have some sample diffs in a second. — M ETS 501 (talk) 04:44, 24 August 2007 (UTC)

I went ahead and did a little trial: check it out here. — M ETS 501 (talk) 05:26, 24 August 2007 (UTC)
 * Give it 50 more edits, report back and I can approve. Thanks for taking this over, didn't really have much time on my hands. — E  talkbots 06:22, 24 August 2007 (UTC)
 * OK, trial done. Here's the article-text-processing source code, if anyone's curious:

{{hide|Code| char[] trimchars = { '|', ' ', '_' }; Match m1 = Regex.Match(ArticleText, @"band_name *= ?(.*?)\r\n"); string strName = m1.Groups[1].Value.Trim(trimchars);

Match m2 = Regex.Match(ArticleText, @"image *= ?\[\[ ?[Ii]mage:(.*?)( ?\| ?([0-9]*) ?px ?)?\|?\]\](\r\n| ?\|)"); string strImg = m2.Groups[1].Value.Trim(trimchars); string strImg_size = m2.Groups[3].Value.Trim(trimchars);

if (strImg == "") {               Match m2a = Regex.Match(ArticleText, @"(image|Img) *= ?(.*?)\r\n"); strImg = m2a.Groups[2].Value.Trim(trimchars); }

if (strImg_size == "") {               Match m2b = Regex.Match(ArticleText, @"image_size *= ?(.*?)(px)?\r\n"); strImg_size = m2b.Groups[1].Value.Trim(trimchars); }

Match m3 = Regex.Match(ArticleText, @"caption *= ?(.*?)\r\n"); string strImg_capt = m3.Groups[1].Value.Trim(trimchars);

if (strImg.Contains("|")) {               Match m2c = Regex.Match(strImg, @"(.*?) ?\| ?([0-9]*) ?px ?\|([^\|]*)"); strImg = m2c.Groups[1].Value.Trim(trimchars); strImg_size = m2c.Groups[2].Value.Trim(trimchars); if (strImg_capt == "") strImg_capt = m2c.Groups[3].Value.Trim(trimchars); }

Match m4 = Regex.Match(ArticleText, @"origin *= ?(.*?)\r\n"); string strOrigin = m4.Groups[1].Value.Trim(trimchars);

Match m5 = Regex.Match(ArticleText, @"years_active *= ?(.*?)\r\n"); string strYears_active = m5.Groups[1].Value.Trim(trimchars);

Match m6 = Regex.Match(ArticleText, @"music_genre *= ?(.*?)\r\n"); string strGenre = m6.Groups[1].Value.Trim(trimchars);

Match m7 = Regex.Match(ArticleText, @"record_label *= ?(.*?)\r\n"); string strLabel = m7.Groups[1].Value.Trim(trimchars);

Match m8 = Regex.Match(ArticleText, @"current_members *= ?(.*?)\r\n"); string strCurrent_members = m8.Groups[1].Value.Trim(trimchars);

Match m9 = Regex.Match(ArticleText, @"past_members *= ?(.*?)\r\n"); string strPast_members = m9.Groups[1].Value.Trim(trimchars);

Match m10 = Regex.Match(ArticleText, @"website *= ?(.*?)\r\n"); string strURL = m10.Groups[1].Value.Trim(trimchars);

if (strOrigin == "") {               Match m11 = Regex.Match(ArticleText, @"country *= ?(.*?)\r\n"); strOrigin = m11.Groups[1].Value.Trim(trimchars); }

string OldArticleText = ArticleText;

Match Testing = Regex.Match(ArticleText, @"{{[Ii]nfobox[_ ][Bb]and[^{]*?}}"); if (!Testing.Success) ArticleText = Regex.Replace(ArticleText, @"{{[Ii]nfobox[_ ][Bb]and.*?(music_genre|record_label|current_members).*?}}", "{{Infobox musical artist \r\n| Name               = " + strName + "\r\n| Img                 = " + strImg + "\r\n| Img_capt            = " + strImg_capt + "\r\n| Img_size            = " + strImg_size + "\r\n| Landscape           = \r\n| Background          = group_or_band\r\n| Alias               = \r\n| Origin              = " + strOrigin + "\r\n| Genre               = " + strGenre + "\r\n| Years_active        = " + strYears_active + "\r\n| Label               = " + strLabel + "\r\n| Associated_acts     = \r\n| URL                 = " + strURL + "\r\n| Current_members     = " + strCurrent_members + "\r\n| Past_members        = " + strPast_members + "\r\n| Notable_instruments = \r\n}}", RegexOptions.Singleline); else ArticleText = Regex.Replace(ArticleText, @"{{[Ii]nfobox[_ ][Bb]and.*?}}", "{{Infobox musical artist \r\n| Name               = " + strName + "\r\n| Img                 = " + strImg + "\r\n| Img_capt            = " + strImg_capt + "\r\n| Img_size            = " + strImg_size + "\r\n| Landscape           = \r\n| Background          = group_or_band\r\n| Alias               = \r\n| Origin              = " + strOrigin + "\r\n| Genre               = " + strGenre + "\r\n| Years_active        = " + strYears_active + "\r\n| Label               = " + strLabel + "\r\n| Associated_acts     = \r\n| URL                 = " + strURL + "\r\n| Current_members     = " + strCurrent_members + "\r\n| Past_members        = " + strPast_members + "\r\n| Notable_instruments = \r\n}}", RegexOptions.Singleline);

if (ArticleText == OldArticleText) Skip = true;

return ArticleText; }}
 * I'm searching for a good way of matching an entire template with a regex reliably (even if there is a template inside one of the template parameters. Anyone? — M ETS 501 (talk) 13:29, 24 August 2007 (UTC)
 * - As per usual ;) Reedy Boy 20:08, 24 August 2007 (UTC)


 * The above discussion is preserved as an archive of the debate. Please do not modify it. Subsequent comments should be made in a new section.