aboutsummaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorBryan Newbold <bnewbold@archive.org>2018-08-21 21:49:54 -0700
committerBryan Newbold <bnewbold@archive.org>2018-08-21 21:49:54 -0700
commitb628b7026ab8e7abf4beeaaad99d831b49578483 (patch)
treee7811391bf8ea5d6f1420f40ae544f198967b1f8
parentb4713502cfa2dbc9e47cf04cb6aef20faf1ad8af (diff)
downloadsandcrawler-b628b7026ab8e7abf4beeaaad99d831b49578483.tar.gz
sandcrawler-b628b7026ab8e7abf4beeaaad99d831b49578483.zip
expand slug-blacklist with results from prod GROBID/crossref match
-rw-r--r--scalding/src/main/resources/slug-blacklist.txt393
1 files changed, 393 insertions, 0 deletions
diff --git a/scalding/src/main/resources/slug-blacklist.txt b/scalding/src/main/resources/slug-blacklist.txt
index 7dc701f..6bc947b 100644
--- a/scalding/src/main/resources/slug-blacklist.txt
+++ b/scalding/src/main/resources/slug-blacklist.txt
@@ -32,3 +32,396 @@ reviewarticle
summary
title
name
+website
+technicalreport
+abstractsofaapaposterandpodiumpresentations
+affiliation
+authorindexforvolume81
+bookreviewssection
+links
+ll
+description
+indicegeneral
+genealogy
+summariesofkeyjournalarticles
+summer
+0
+jobdescription
+socialengineering
+approximation
+thetimes
+atribute
+components
+entscheidungsverzeichnis
+indexofauthorsandtitles
+inventions
+newlyelectedmembersofthecollege
+summaryofproceedings
+appointmentsandstaffchanges
+classes
+finalexam
+partone
+referenciasbibliograficas
+abstractsofthesesfromthescandinaviancountries
+acknowledgementsvii
+messagefromgeneralcochairs
+mm
+redaktorensforord
+109
+place
+computerscience
+medicinalchemistry
+homework
+sun
+dedicatoria
+outline
+affect
+section
+informationtoauthors
+theeditorsdesk
+entrevista
+thefirstauthorreplies
+councilminutes
+no
+furtherreadings
+printing
+glosario
+lucina
+mrsnews
+85
+bookofabstracts
+literaturrundschau
+thismonthin
+listedestableaux
+sommario
+specialsection
+revieweracknowledgement2013
+abstractnotsubmittedforonlinepublication
+essays
+tableofcontentsandprologue
+76
+callforarticles
+ataglance
+fichatecnica
+literacy
+theyearinreview
+print
+symptom
+66
+additionalresources
+unitednations
+meetingabstracts
+annualacknowledgementofmanuscriptreviewers
+specifications
+boardoftrustees
+timemanagement
+papers
+importantnotice
+annexa
+linearregression
+chaptertwo
+finalreport
+suggestedreadings
+essay
+copyrightform
+resumo
+bigdata
+chapter10
+publication
+changes
+presentacio
+ai
+materialsafetydatasheet
+home
+dearreaders
+acknowledgmentofreferees
+maintenance
+question
+listofpublications
+responsetothelettertotheeditor
+communiquedepresse
+58
+noii
+litteraturverzeichniss
+whatshappening
+chairmansopeningremarks
+editorscorrespondence
+award
+thebasics
+56
+conservation
+blood
+chapter7
+chaos
+citation
+memoranda
+figure3
+distribution
+regression
+synthese
+context
+editorialconsultants
+theoreticalbackground
+lecture
+electrophoresis
+editorspicks
+introductorycomments
+collaborateurs
+recensions
+personalandmiscellaneous
+issuesandevents
+theworldbank
+51
+reviewsanddescriptionsoftablesandbooks
+congratulations
+definition
+yourquestionsanswered
+chapterone
+missionstatement
+62
+newsandreviews
+decisionmaking
+41
+projectmanagement
+community
+metaanalysis
+magazin
+other
+linearalgebra
+online
+exercises
+languageteaching
+address
+radiology
+foreward
+heartfailure
+editoriale
+memorandum
+editorialinformation
+revieweracknowledgement
+safety
+21
+features
+aboutauthors
+messagefromtheprogramcochairs
+health
+security
+literaturecited
+meetingsandconferences
+messagefromthechairs
+feature
+meetingsofinterest
+introductiongenerale
+pressrelease
+lungcancer
+6
+7
+institutenews
+researchresearchers
+profile
+11
+5
+rehabilitation
+documents
+currentresearch
+4
+originalarticle
+committee
+endnotes
+chapter1
+originalarticles
+guidelinesforcontributors
+chapteroneintroduction
+aboutthecover
+membershipapplication
+awardsappointmentsannouncements
+materialsandmethods
+symposium
+abstractsofcommunications
+oralabstracts
+insidethisissue
+abreviations
+ear
+editorialstaff
+proceedings
+commentaries
+perspective
+agradecimientos
+iii
+glossaryofterms
+appendix1
+editorialeditorial
+interview
+fortherecord
+abstractwithdrawn
+highlightsfromthisissue
+materials
+keywords
+editorscomment
+editorscorner
+readersforum
+messagefromtheprogramchairs
+authorguidelines
+resumes
+reviewessay
+editorinchief
+8
+frequentlyaskedquestions
+aimsandscope
+abouttheeditors
+indice
+editorialstatement
+sommaire
+inthestudy
+listofreferees
+background
+bookreviewsandnotices
+articlesofsignificantinterestselectedfromthisissuebytheeditors
+fromthepresident
+panorama
+welcome
+history
+continuingeducation
+livresrecus
+acknowledgementtoreferees
+equipment
+coverimage
+1
+summaries
+positionsavailable
+y
+congresscalendar
+conferencereport
+upcomingevents
+posterpresentations
+editorsintroduction
+rezension
+appendixb
+2
+generalinformation
+theauthors
+notesandcomments
+subscriptions
+w
+listoffigures
+communication
+calendarofmeetings
+workscited
+n
+o
+d
+editorialcomments
+listofreviewers
+notitle
+editorschoice
+lettertotheeditors
+comments
+sumario
+editorialintroduction
+resenas
+introduccion
+classifieds
+tocorrespondents
+notesforcontributors
+forthcomingarticles
+bibliografia
+ii
+editorialsoftwaresurveysection
+listofparticipants
+advertisersindex
+generaldiscussion
+paperstoappearinforthcomingissues
+indexofauthors
+letterfromtheeditor
+chapter1introduction
+organizingcommittee
+noticeboard
+guideforauthors
+chapteri
+resources
+resume
+u
+p
+addendum
+impressum
+copyrightnotice
+r
+associationnews
+classified
+s
+l
+corrigenda
+presentacion
+instructionsforauthors
+resumen
+editorialnote
+comptesrendus
+response
+curriculumvitae
+obituaries
+meetings
+education
+e
+m
+a
+forthcomingevents
+reviewers
+abouttheauthors
+fromtheeditors
+i
+instructionstoauthors
+newproducts
+callforpapers
+blankpage
+apresentacao
+publishersnote
+newbooks
+corrections
+tabledesmatieres
+calendarofevents
+editorsnote
+shorternotices
+listofcontributors
+notesandnews
+editorialcomment
+newsandnotes
+comment
+inmemoriam
+presentation
+executivesummary
+guesteditorial
+avantpropos
+discussion
+glossary
+letters
+notes
+reply
+contributors
+acknowledgments
+fromtheeditor
+buchbesprechungen
+obituary
+inthisissue
+notesoncontributors
+conclusion
+einleitung
+inhalt
+bibliography
+titeleiinhaltsverzeichnis
+booksreceived
+calendar
+inhaltsverzeichnis
+corrigendum
+subjectindex
+errata
+frontmatter
+correction
+abstracts
+letterstotheeditor
+foreword
+tableofcontents
+authorindex
+index
+erratum
+editorialboard
+editorial