From f0ac2727815787c8288fda60b553549d4b3821ed Mon Sep 17 00:00:00 2001 From: ale <ale@incal.net> Date: Mon, 5 Dec 2022 20:53:53 +0000 Subject: [PATCH] Remove back-reference patterns --- gen-ignores.py | 2 +- ignore_patterns.go | 5 ----- 2 files changed, 1 insertion(+), 6 deletions(-) diff --git a/gen-ignores.py b/gen-ignores.py index abf9b96..e0dae51 100755 --- a/gen-ignores.py +++ b/gen-ignores.py @@ -20,7 +20,7 @@ for fn in glob.glob(os.path.join(archivebot_ignore_path, '*.json')): with open(fn) as fd: print('\n\t// %s' % os.path.basename(fn)) for p in json.load(fd)['patterns']: - if '\\\\1' in p or '(?!' in p: + if re.search(r'\\[0-9]', p) or '(?!' in p: # RE2 does not support backreferences or other # fancy PCRE constructs. This excludes <10 # patterns from the ignore list. diff --git a/ignore_patterns.go b/ignore_patterns.go index 4c38ff6..319b294 100644 --- a/ignore_patterns.go +++ b/ignore_patterns.go @@ -79,7 +79,6 @@ var defaultIgnorePatterns = []string{ "[\\?&]undo(after)?=\\d+", "^https?://a\\.wikia-beacon\\.com/__track/", "^https?://beacon\\.wikia-services\\.com/__track/", - "([\\?&]title=|/)Special:(PrefixIndex|WhatLinksHere|Contributions|ListFiles|ListUsers)/.*/\\2/", "/User_talk:.+/User_talk:", "/User_blog:.+/User_blog:", "/User:.+/User:", @@ -135,7 +134,6 @@ var defaultIgnorePatterns = []string{ "[\\?&]undo(after)?=\\d+", "^https?://a\\.wikia-beacon\\.com/__track/", "^https?://beacon\\.wikia-services\\.com/__track/", - "([\\?&]title=|/)Spezial:(Pr%C3%A4fixindex|(Linkliste|Verweisliste)|Beitr%C3%A4ge|(Dateien|Dateiliste)|(Benutzer|Benutzerliste))/.*/\\2/", "/Benutzer_Diskussion:.+/Benutzer_Diskussion:", "/User_blog:.+/User_blog:", "/Benutzer:.+/Benutzer:", @@ -478,7 +476,6 @@ var defaultIgnorePatterns = []string{ "[\\?&]undo(after)?=\\d+", "^https?://a\\.wikia-beacon\\.com/__track/", "^https?://beacon\\.wikia-services\\.com/__track/", - "([\\?&]title=|/)Especial:((P%C3%A1ginasPorPrefijo|P%C3%A1ginas_por_prefijo)|(LoQueEnlazaAqu%C3%AD|Lo_que_enlaza_aqu%C3%AD)|Contribuciones|(ListaIm%C3%A1genes|Lista_de_im%C3%A1genes)|(ListaUsuarios|Lista_de_usuarios))/.*/\\2/", "/Usuario_discusi%C3%B3n:.+/Usuario_discusi%C3%B3n:", "/User_blog:.+/User_blog:", "/Usuario:.+/Usuario:", @@ -601,7 +598,6 @@ var defaultIgnorePatterns = []string{ "SESSION_ID=", "showcal\\.php", "site=guestbook.+type=(?:ASC|DESC)", - "/sites/all/(sites|modules|libraries|scripts|themes)/.+/\\1", "Souprava=.+Souprava=.+", "Special:Whatlinkshere", "start-index=-\\d+", @@ -768,7 +764,6 @@ var defaultIgnorePatterns = []string{ "[\\?&]undo(after)?=\\d+", "^https?://a\\.wikia-beacon\\.com/__track/", "^https?://beacon\\.wikia-services\\.com/__track/", - "([\\?&]title=|/)Sp%C3%A9cial:((Index|Pr%C3%A9fixes|Prefixes)|(Pages_li%C3%A9es|PagesLi%C3%A9es|Pages_liees|PagesLiees)|Contributions|(Liste_des_fichiers|ListeDesFichiers|Liste_des_images|ListeDesImages)|(Liste_des_utilisateurs|ListeDesUtilisateurs|Utilisateurs))/.*/\\2/", "/Discussion_utilisateur:.+/Discussion_utilisateur:", "/User_blog:.+/User_blog:", "/Utilisateur:.+/Utilisateur:", -- GitLab