Difference between revisions of "Workdocumentation 2022-08-13"

From BITPlan ceur-ws Wiki
Jump to navigation Jump to search
 
(14 intermediate revisions by the same user not shown)
Line 1: Line 1:
 +
{{PageSequence|prev=Workdocumentation 2022-08-12|next=Workdocumentation 2022-08-15|category=Workdocumentation}}
 
= Participants =
 
= Participants =
 
* Beyza
 
* Beyza
 
* Wolfgang  
 
* Wolfgang  
 
= Agenda =
 
= Agenda =
 +
* CEUR-WS
 +
* Tools
 +
 
= CEUR-WS =  
 
= CEUR-WS =  
 
== pyCEURMake ==
 
== pyCEURMake ==
Line 9: Line 13:
 
git clone https://github.com/WolfgangFahl/pyCEURmake
 
git clone https://github.com/WolfgangFahl/pyCEURmake
 
</source>
 
</source>
 +
=== Indexparser ===
 +
* reads index.html to create volume dicts
 +
* VolumeManager then takes dicts to creates Volumes
 +
* VolumeManager.store() stores to Sqlite database
 +
<source lang='bash'>
 +
def testReadVolumePages(self):
 +
        '''
 +
        test reading the volume pages
 +
        '''
 +
        vm=VolumeManager()
 +
        vm.loadFromIndexHtml(force=False)
 +
        volumesByNumber, _duplicates = LOD.getLookup(vm.getList(), 'number')
 +
        debug=True
 +
        limit=len(volumesByNumber)+1
 +
        #limit=10
 +
        for number in range(1,limit):
 +
            volume=volumesByNumber[number]
 +
            volume.extractValuesFromVolumePage(debug=False,withPapers=False)
 +
            if debug and volume.valid:
 +
                print(f"{volume.url}:{volume.acronym}:{volume.desc}:{volume.h1}:{volume.title}")
 +
        withStore=False
 +
        if withStore:
 +
            vm.store()
 +
</source>
 +
 +
=== Database ===
 +
see https://github.com/coleifer/sqlite-web
 +
<source lang='bash'>
 +
sqlite_web ceurws.db
 +
</source>
 +
 
== gsimport/pyOnlineSpreadSheetEditing ==
 
== gsimport/pyOnlineSpreadSheetEditing ==
 
<source lang='bash'>
 
<source lang='bash'>
 
git clone  https://github.com/WolfgangFahl/pyOnlineSpreadSheetEditing
 
git clone  https://github.com/WolfgangFahl/pyOnlineSpreadSheetEditing
 
</source>
 
</source>
 +
* [https://docs.google.com/spreadsheets/d/1fTMUuXXq_7lJgUzwLntrg4GUQ-lmlXYhS-I1Fhwc9dQ/edit#gid=657550142 CEUR-WS Google Sheet for Wikidata import]
  
 
== Install Liclipse ==
 
== Install Liclipse ==
Line 25: Line 61:
 
<source lang='bash'>
 
<source lang='bash'>
 
curl -s http://ceur-ws.org > index.html
 
curl -s http://ceur-ws.org > index.html
 +
</source>
 +
== Series Examples ==
 +
* https://github.com/ceurws/lod/issues
 +
* [https://github.com/ceurws/lod/discussions/29 SePublica Example]
 +
* [https://github.com/ceurws/lod/discussions/27 IWSECO Example]
 +
 +
= Tools =
 +
== Wikibase Command line Tools (NPM/Javascript ==
 +
* https://github.com/maxlath/wikibase-cli
 +
<source lang='bash'>
 +
wd search "SePublica"
 +
Q30276418  Proceedings of the 2nd Workshop on Semantic Publishing
 +
</source>
 +
== Scholar script ==
 +
For result see {{Link|target=List of Scholars}}
 +
<source lang='bash'>
 +
#!/bin/bash
 +
# WF 2022-08-08
 +
# search for a scholar
 +
 +
wikidataProps() {
 +
cat << EOF
 +
item given_name P735 firstName
 +
item family_name P734 name
 +
url official_website P856 homepage
 +
id DBLP_author_ID P2456 dblpId
 +
id ORCID P496 orcid
 +
id LinkedIn personal profile ID P634 linkedInId
 +
id GND_ID P227 gndId
 +
id Google_Scholar_author_ID P1960 googleScholarUser
 +
EOF
 +
}
 +
smwScholar() {
 +
  local l_qid="$1"
 +
cat << EOF
 +
{{Scholar
 +
|wikiDataId=$l_qid
 +
EOF
 +
wikidataProps | while read line
 +
do
 +
  propType=$(echo $line | cut -f1 -d ' ')
 +
  propName=$(echo $line | cut -f2 -d ' ')
 +
  propId=$(echo $line | cut -f3 -d ' ')
 +
  propVar=$(echo $line | cut -f4 -d ' ')
 +
  #echo $propId
 +
  propValue=$(wd q --subject $l_qid -p $propId 2>&1)
 +
  if [ $? -eq 0 ]
 +
  then
 +
    case $propType in
 +
      'item')
 +
        propValue=$(wd label $propValue)
 +
      ;;
 +
    esac
 +
    echo "|$propVar=$propValue"
 +
  fi
 +
done
 +
cat << EOF
 +
}}
 +
EOF
 +
}
 +
name="$*"
 +
wd search "$name" | while read line
 +
do
 +
  echo $line
 +
  qid=$(echo $line | cut -f1 -d' ')
 +
  smwScholar "$qid"
 +
done
 
</source>
 
</source>

Latest revision as of 04:56, 18 August 2022

Participants

  • Beyza
  • Wolfgang

Agenda

  • CEUR-WS
  • Tools

CEUR-WS

pyCEURMake

git clone https://github.com/WolfgangFahl/pyCEURmake

Indexparser

  • reads index.html to create volume dicts
  • VolumeManager then takes dicts to creates Volumes
  • VolumeManager.store() stores to Sqlite database
def testReadVolumePages(self):
        '''
        test reading the volume pages
        '''
        vm=VolumeManager()
        vm.loadFromIndexHtml(force=False)
        volumesByNumber, _duplicates = LOD.getLookup(vm.getList(), 'number')
        debug=True
        limit=len(volumesByNumber)+1
        #limit=10
        for number in range(1,limit):
            volume=volumesByNumber[number]
            volume.extractValuesFromVolumePage(debug=False,withPapers=False)
            if debug and volume.valid:
                print(f"{volume.url}:{volume.acronym}:{volume.desc}:{volume.h1}:{volume.title}")
        withStore=False
        if withStore:
            vm.store()

Database

see https://github.com/coleifer/sqlite-web 

sqlite_web ceurws.db

gsimport/pyOnlineSpreadSheetEditing

git clone  https://github.com/WolfgangFahl/pyOnlineSpreadSheetEditing

Install Liclipse

Python installation

Get a copy of index.html

curl -s http://ceur-ws.org > index.html

Series Examples

Tools

Wikibase Command line Tools (NPM/Javascript

wd search "SePublica"
Q30276418  Proceedings of the 2nd Workshop on Semantic Publishing

Scholar script

For result see List of Scholars 

#!/bin/bash
# WF 2022-08-08
# search for a scholar

wikidataProps() {
cat << EOF
item given_name P735 firstName
item family_name P734 name
url official_website P856 homepage
id DBLP_author_ID P2456 dblpId
id ORCID P496 orcid
id LinkedIn personal profile ID P634 linkedInId
id GND_ID P227 gndId
id Google_Scholar_author_ID P1960 googleScholarUser
EOF
}
smwScholar() {
  local l_qid="$1"
cat << EOF
{{Scholar
|wikiDataId=$l_qid
EOF
wikidataProps | while read line
do
  propType=$(echo $line | cut -f1 -d ' ')
  propName=$(echo $line | cut -f2 -d ' ')
  propId=$(echo $line | cut -f3 -d ' ')
  propVar=$(echo $line | cut -f4 -d ' ')
  #echo $propId
  propValue=$(wd q --subject $l_qid -p $propId 2>&1)
  if [ $? -eq 0 ]
  then
    case $propType in
      'item')
         propValue=$(wd label $propValue)
      ;;
    esac
    echo "|$propVar=$propValue"
  fi
done
cat << EOF
}}
EOF
}
name="$*"
wd search "$name" | while read line
do
  echo $line
  qid=$(echo $line | cut -f1 -d' ')
  smwScholar "$qid"
done
Retrieved from "http://ceur-ws.bitplan.com/index.php?title=Workdocumentation_2022-08-13&oldid=708"