# Each plugin needs a description so the driver can advertise the details # to the users on the site plugin { # Integer version number for the plugin code. When this number is incremented, # CiteULike may reparse all existing articles with the new code. version {1} # The name of the plugin, as displayed on the "CiteULike supports..." page name {ACL Anthology} # The link the front page of this service url {http://www.aclweb.org/anthology/} # Any additional information which needs to be displayed to the user. # E.g. "Experimental support" blurb {} # Your name author {Karl-Michael Schneider} # Your email address email {karlmicha@gmail.com} # Language you wrote the plugin in language {python} # Regular expression to match URLs that the plugin is # *potentially* interested in. Any URL matching this regexp # will cause your parser to be invoked. Currently, this will # require fork()ing a process, so you should try to reduce the number # of false positives by making your regexp as restrictive as possible. # # If it is not possible to determine whether or not your plugin is # interested purely on the basis of the URL, you will have a chance # to refine this decision in your code. For now, try to make a reasonable # approximation - like, check for URLs on the right hostname # # Note: Some universities provide mirrors of commericial publishers' sites # with different hostnames, so you should provide some leeway in your # regexp if that applies to you. regexp {^http://(?:(?:www\.)?aclweb\.org/anthology(?:-new)?|acl\.ldc\.upenn\.edu|ucrel\.lancs\.ac\.uk/acl|acl\.eldoc\.ub\.rug\.nl/mirror|www\.cs\.mu\.oz\.au/acl)/[A-Z]/[A-Z]\d{2}/[A-Z]\d{2}-\d+(?:\.bib|\.pdf)?$} } # # Linkout formatting # # CiteULike doesn't store URLs for articles. # Instead it stores the raw ingredients required to build the dynamically. # Each plugin is required to define a small procedure which does this formatting # See the HOWTO file for more details. # # The variables following variables are defined for your use # in the function: type ikey_1 ckey_1 ikey_2 ckey_2 # format_linkout ACLANT { return [list "ACL Anthology (BibTeX)" \ "http://www.aclweb.org/anthology-new/${ckey_1}.bib" \ "ACL Anthology (PDF)" \ "http://www.aclweb.org/anthology-new/${ckey_1}.pdf" \ ] } # # TESTS # # Each plugin MUST provide a set of tests. The motivation behind this is # that web scraping code is inherently fragile, and is likely to break whenever # the provider decides to redisign their site. CiteULike will periodically # run tests to see if anything has broken. # Please provide as comprehensive a set of tests as possible. # If you ever fix a bug in the parser, it is highly recommended that # you add the offending page as a test case. test {http://www.aclweb.org/anthology-new/P/P07/P07-1001.bib} { formatted_url {{ACL Anthology (BibTeX)} http://www.aclweb.org/anthology-new/P/P07/P07-1001.bib} formatted_url {{ACL Anthology (PDF)} http://www.aclweb.org/anthology-new/P/P07/P07-1001.pdf} linkout {ACLANT {} P/P07/P07-1001 {} {}} abstract {} title {Guiding Statistical Word Alignment Models With Prior Knowledge} title_secondary {Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics} author {Deng Yonggang Y {Yonggang Deng}} author {Gao Yuqing Y {Yuqing Gao}} start_page 1 end_page 8 address {Prague, Czech Republic} publisher {Association for Computational Linguistics} type INCONF year 2007 month June url http://www.aclweb.org/anthology/P/P07/P07-1001 status ok } test {http://www.aclweb.org/anthology/N/N06/N06-1012} { formatted_url {{ACL Anthology (BibTeX)} http://www.aclweb.org/anthology-new/N/N06/N06-1012.bib} formatted_url {{ACL Anthology (PDF)} http://www.aclweb.org/anthology-new/N/N06/N06-1012.pdf} linkout {ACLANT {} N/N06/N06-1012 {} {}} abstract {} title {Reducing Weight Undertraining in Structured Discriminative Learning} title_secondary {Proceedings of the Human Language Technology Conference of the NAACL, Main Conference} author {Sutton Charles C {Charles Sutton}} author {Sindelar Michael M {Michael Sindelar}} author {Mccallum Andrew A {Andrew McCallum}} start_page 89 end_page 95 address {New York City, USA} publisher {Association for Computational Linguistics} type INCONF year 2006 month June url http://www.aclweb.org/anthology/N/N06/N06-1012 status ok } test {http://www.aclweb.org/anthology-new/W/W04/W04-0110.pdf} { formatted_url {{ACL Anthology (BibTeX)} http://www.aclweb.org/anthology-new/W/W04/W04-0110.bib} formatted_url {{ACL Anthology (PDF)} http://www.aclweb.org/anthology-new/W/W04/W04-0110.pdf} linkout {ACLANT {} W/W04/W04-0110 {} {}} abstract {} title {Segment Predictability as a Cue in Word Segmentation: Application to Modern Greek} title_secondary {Proceedings of the Seventh Meeting of the ACL Special Interest Group in Computational Phonology} author {Rytting Anton AC {C. Anton Rytting}} start_page 78 end_page 85 address {Barcelona, Spain} publisher {Association for Computational Linguistics} type INCONF year 2004 month July status ok }