aboutsummaryrefslogtreecommitdiffstats
path: root/scalding/src/main
diff options
context:
space:
mode:
authorBryan Newbold <bnewbold@archive.org>2018-08-23 17:16:46 -0700
committerBryan Newbold <bnewbold@archive.org>2018-08-23 17:16:46 -0700
commit1f0e447cfb4c739a9a39b9af27a0c86d2d46bc7e (patch)
tree79521535044f052aab243fd826e6aa1e06fe6943 /scalding/src/main
parent103c3aeff74d7f820f40d0a77e9d85ade8cb555c (diff)
downloadsandcrawler-1f0e447cfb4c739a9a39b9af27a0c86d2d46bc7e.tar.gz
sandcrawler-1f0e447cfb4c739a9a39b9af27a0c86d2d46bc7e.zip
additions to slug blacklist
Diffstat (limited to 'scalding/src/main')
-rw-r--r--scalding/src/main/resources/slug-blacklist.txt797
1 files changed, 414 insertions, 383 deletions
diff --git a/scalding/src/main/resources/slug-blacklist.txt b/scalding/src/main/resources/slug-blacklist.txt
index 6bc947b..ad3dc1d 100644
--- a/scalding/src/main/resources/slug-blacklist.txt
+++ b/scalding/src/main/resources/slug-blacklist.txt
@@ -1,427 +1,458 @@
abbreviations
+abbreviationsandacronyms
+aboutauthors
+abouttheauthor
+abouttheauthors
+aboutthecover
+abouttheeditors
+abreviations
abstract
+abstractnotsubmittedforonlinepublication
+abstracts
+abstractsofaapaposterandpodiumpresentations
+abstractsofcommunications
+abstractsofthesesfromthescandinaviancountries
+abstractwithdrawn
+acknowledgement
acknowledgements
+acknowledgementsvii
+acknowledgementtoreferees
+acknowledgment
+acknowledgmentofreferees
+acknowledgments
+addendum
+additionalresources
+address
+advertisersindex
+affect
+affiliation
+agenda
+agradecimientos
+aimsandscope
+annexa
+annualacknowledgementofmanuscriptreviewers
+appendices
+appendix1
+appendixa
+appendixb
+appointmentsandstaffchanges
+approximation
+apresentacao
article
+articles
+articlesofsignificantinterestselectedfromthisissuebytheeditors
+associationnews
+ataglance
+atribute
+authorguidelines
+authorindex
+authorindexforvolume81
authorreply
+authors
authorsreply
+authorsresponse
+avantpropos
+award
+awardsappointmentsannouncements
+backcover
+background
+bibliografia
+bibliography
+bigdata
+blankpage
+blood
+boardoftrustees
+bookofabstracts
bookreview
bookreviews
+bookreviewsandnotices
+bookreviewssection
+booksreceived
+buchbesprechungen
+bulletin
+calendar
+calendarofevents
+calendarofmeetings
+callforarticles
+callforpapers
casereport
+casereports
+chairmansopeningremarks
+changes
+chaos
+chapter1
+chapter10
+chapter1introduction
+chapter7
+chapteri
+chapterone
+chapteroneintroduction
+chaptertwo
+citation
+classes
+classified
+classifieds
+collaborateurs
+comment
+commentaries
commentary
commentaryon
commenton
+comments
commentto
+committee
+communication
+communications
+communicationstotheeditor
+communiquedepresse
+community
+components
+comptesrendus
+computerscience
+conclusion
+conclusions
+conferencereport
+congratulations
+congresscalendar
+conservation
+content
contents
+context
+continuingeducation
+continuingmedicaleducation
+contributors
+copyright
+copyrightform
+copyrightnotice
+correction
+corrections
correspondence
+corrigenda
+corrigendum
+councilminutes
+cover
+coverimage
+currentresearch
+curriculumvitae
+danksagung
+dearreaders
+decisionmaking
dedication
+dedicatoria
+definition
+description
+discussion
+distribution
+documents
+ear
+editorial
editorialadvisoryboard
+editorialboard
+editorialcomment
+editorialcomments
+editorialconsultants
+editoriale
+editorialeditorial
+editorialinformation
+editorialintroduction
+editorialnote
+editorials
+editorialsoftwaresurveysection
+editorialstaff
+editorialstatement
+editorinchief
+editors
+editorschoice
+editorscomment
+editorscorner
+editorscorrespondence
+editorsintroduction
+editorsnote
+editorspicks
+editorspreface
+education
+einfuhrung
+einleitung
+electrophoresis
+employment
+endnotes
+entrevista
+entscheidungsverzeichnis
+epilogue
+equipment
+errata
+erratum
+essay
+essays
+executivesummary
+exercises
+extendedabstracts
+feature
+features
+fichatecnica
+figure3
+finalexam
+finalreport
focus
+foreward
+foreword
+forthcomingarticles
+forthcomingevents
+fortherecord
+forum
+frequentlyaskedquestions
+fromtheeditor
+fromtheeditors
+fromthepresident
+frontmatter
+furtherreadings
+genealogy
+generaldiscussion
+generalinformation
+generalintroduction
+germany
+glosario
+glossary
+glossaryofterms
+guesteditorial
+guideforauthors
+guidelinesforcontributors
+health
+heartfailure
+highlights
+highlightsfromthisissue
+history
+home
+homework
hypothesis
+iii
+importantnotice
+impressum
inbrief
+index
+indexofauthors
+indexofauthorsandtitles
+indice
+indicegeneral
+informationforauthors
+informationtoauthors
+inhalt
+inhaltsverzeichnis
+inmemoriam
+inreply
+insidethisissue
+institutenews
+instructionsforauthors
+instructionstoauthors
+interview
+inthestudy
+inthisissue
+introduccion
introduction
+introductiongenerale
introductiontotheissue
+introductorycomments
+inventions
+invitedcommentary
+issuesandevents
+jobdescription
+keywords
+languageteaching
+lecture
+letter
+letterfromtheeditor
+letters
+letterstotheeditor
lettertotheeditor
-listofabbreviations
-note
-overview
-preface
-references
-results
-review
-reviewarticle
-summary
-title
-name
-website
-technicalreport
-abstractsofaapaposterandpodiumpresentations
-affiliation
-authorindexforvolume81
-bookreviewssection
+lettertotheeditors
+linearalgebra
+linearregression
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
+listofabbreviations
+listofcontributors
+listoffigures
+listofparticipants
listofpublications
-responsetothelettertotheeditor
-communiquedepresse
-58
-noii
+listofreferees
+listofreviewers
+listoftables
+literacy
+literature
+literaturecited
+literaturrundschau
litteraturverzeichniss
-whatshappening
-chairmansopeningremarks
-editorscorrespondence
-award
-thebasics
-56
-conservation
-blood
-chapter7
-chaos
-citation
+livresrecus
+lucina
+lungcancer
+magazin
+maintenance
+materials
+materialsafetydatasheet
+materialsandmethods
+medicinalchemistry
+meetingabstracts
+meetings
+meetingsandconferences
+meetingsofinterest
+membershipapplication
memoranda
-figure3
-distribution
-regression
-synthese
-context
-editorialconsultants
-theoreticalbackground
-lecture
-electrophoresis
-editorspicks
-introductorycomments
-collaborateurs
-recensions
-personalandmiscellaneous
-issuesandevents
-theworldbank
-51
-reviewsanddescriptionsoftablesandbooks
-congratulations
-definition
-yourquestionsanswered
-chapterone
+memorandum
+messagefromgeneralcochairs
+messagefromthechairs
+messagefromtheprogramchairs
+messagefromtheprogramcochairs
+metaanalysis
missionstatement
-62
+motivation
+mrsnews
+name
+newbooks
+newlyelectedmembersofthecollege
+newproducts
+news
+newsandnotes
newsandreviews
-decisionmaking
-41
-projectmanagement
-community
-metaanalysis
-magazin
-other
-linearalgebra
+newsandviews
+newsviews
+noii
+note
+notes
+notesandcomments
+notesandnews
+notesforcontributors
+notesoncontributors
+notice
+noticeboard
+notitle
+notitleavailable
+obituaries
+obituary
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
+openaccess
+oralabstracts
+oralpresentations
+organizingcommittee
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
+other
+outline
+overview
panorama
-welcome
-history
-continuingeducation
-livresrecus
-acknowledgementtoreferees
-equipment
-coverimage
-1
-summaries
+papers
+paperstoappearinforthcomingissues
+partone
+personalandmiscellaneous
+perspective
+perspectives
+place
positionsavailable
-y
-congresscalendar
-conferencereport
-upcomingevents
+poster
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
+postscript
+preface
+preliminarymaterial
+presentacio
+presentacion
+presentation
+pressrelease
+print
+printing
+proceedings
+profile
+programcommittee
+projectmanagement
+publication
+publichealth
+publishersnote
+question
+radiology
+readersforum
+recensions
+recentpublications
+redaktorensforord
+references
+referenciasbibliograficas
+regression
+rehabilitation
+rejoinder
+remerciements
+reply
+replybyauthors
+researchresearchers
resenas
-introduccion
-classifieds
-tocorrespondents
-notesforcontributors
-forthcomingarticles
-bibliografia
-ii
-editorialsoftwaresurveysection
-listofparticipants
-advertisersindex
-generaldiscussion
-paperstoappearinforthcomingissues
-indexofauthors
-letterfromtheeditor
-chapter1introduction
-organizingcommittee
-noticeboard
-guideforauthors
-chapteri
resources
+response
+responsetothelettertotheeditor
+results
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
+resumes
+resumo
+review
+reviewarticle
+revieweracknowledgement
+revieweracknowledgement2013
reviewers
-abouttheauthors
-fromtheeditors
-i
-instructionstoauthors
-newproducts
-callforpapers
-blankpage
-apresentacao
-publishersnote
-newbooks
-corrections
-tabledesmatieres
-calendarofevents
-editorsnote
+reviewessay
+reviews
+reviewsanddescriptionsoftablesandbooks
+rezension
+safety
+section
+security
+selectedbibliography
+shortcommunication
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
+socialengineering
+sommaire
+sommario
+specialsection
+specifications
subjectindex
-errata
-frontmatter
-correction
-abstracts
-letterstotheeditor
-foreword
+subscriptions
+suggestedreadings
+sumario
+summaries
+summariesofkeyjournalarticles
+summary
+summaryofproceedings
+summer
+sun
+supplementarymaterial
+symposium
+symptom
+synthese
+tabledesmatieres
tableofcontents
-authorindex
-index
-erratum
-editorialboard
-editorial
+tableofcontentsandprologue
+technicalreport
+theauthors
+thebasics
+theeditorsdesk
+thefirstauthorreplies
+thelancet
+theoreticalbackground
+thetimes
+theworldbank
+theyearinreview
+thismonthin
+timemanagement
+titeleiinhaltsverzeichnis
+title
+titlepage
+titlepagei
+tocorrespondents
+totheeditor
+unitedkingdom
+unitednations
+unitedstates
+upcomingevents
+vorwort
+website
+welcome
+whatshappening
+whatsnew
+workscited
+yourquestionsanswered
+zusammenfassung