Skip to content
GitLab
Explore
Sign in
Primary navigation
Search or go to…
Project
S
scripts pyDataverse
Manage
Activity
Members
Labels
Plan
Issues
Issue boards
Milestones
Wiki
Code
Merge requests
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Snippets
Build
Pipelines
Jobs
Pipeline schedules
Artifacts
Deploy
Releases
Package registry
Model registry
Operate
Environments
Terraform modules
Monitor
Incidents
Analyze
Value stream analytics
Contributor analytics
CI/CD analytics
Repository analytics
Model experiments
Help
Help
Support
GitLab documentation
Compare GitLab plans
Community forum
Contribute to GitLab
Provide feedback
Keyboard shortcuts
?
Snippets
Groups
Projects
Show more breadcrumbs
JOUNEAU Thomas
scripts pyDataverse
Commits
0268ee67
Commit
0268ee67
authored
3 years ago
by
JOUNEAU Thomas
Browse files
Options
Downloads
Patches
Plain Diff
Replace generate_citation.py
parent
95f94880
Branches
Branches containing commit
No related tags found
No related merge requests found
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
dorel_export_v0.2/generate_citation.py
+123
-103
123 additions, 103 deletions
dorel_export_v0.2/generate_citation.py
with
123 additions
and
103 deletions
dorel_export_v0.2/generate_citation.py
+
123
−
103
View file @
0268ee67
...
@@ -95,118 +95,138 @@ bibliography_list = []
...
@@ -95,118 +95,138 @@ bibliography_list = []
for
doi
,
metadata
in
complete_list
.
items
():
#
for
doi
,
metadata
in
complete_list
.
items
():
#
print
(
f
"
\n
{
doi
}
:
\n
"
)
# Retour du DOI. Décommenter pour débogage
print
(
f
"
\n
{
doi
}
:
\n
"
)
# Retour du DOI. Décommenter pour débogage
authors_list
=
[]
authors_list
=
[]
subjects_list
=
[]
subjects_list
=
[]
# On vérifie la présence de "latestVersion" dans metadata
metadata
=
metadata
[
0
]
# le dictionnaire étant enserré entre des crochets, on prend le premier et unique élément de cette "liste"
metadata
=
metadata
[
0
]
# le dictionnaire étant enserré entre des crochets, on prend le premier et unique élément de cette "liste"
# on récupère tout ce qu'on peut au niveau 1 de l'entrée et dans "latestVersion"
if
"
latestVersion
"
in
metadata
:
dataset_id
=
metadata
[
"
id
"
]
# print (dataset_id)
dataset_identifier
=
metadata
[
"
identifier
"
]
# ------------------------------------------------------------------------------
# mapping de champs seulement s'ils existent (tests avec if)
# on récupère tout ce qu'on peut au niveau 1 de l'entrée et dans "latestVersion"
if
"
persistentUrl
"
in
metadata
:
# ------------------------------------------------------------------------------
dataset_persistentUrl
=
metadata
[
"
persistentUrl
"
]
# print (dataset_persistentUrl)
dataset_id
=
metadata
[
"
id
"
]
elif
"
persistentUrl
"
not
in
metadata
:
# print (dataset_id)
dataset_persistentUrl
=
""
else
:
dataset_identifier
=
metadata
[
"
identifier
"
]
print
(
"
Vérifier la partie du code concernant le mapping de persistentUrl
"
)
# mapping de champs seulement s'ils existent (tests avec if)
if
"
persistentUrl
"
in
metadata
:
dataset_persistentUrl
=
metadata
[
"
persistentUrl
"
]
# print (dataset_persistentUrl)
elif
"
persistentUrl
"
not
in
metadata
:
dataset_persistentUrl
=
""
else
:
print
(
"
Vérifier la partie du code concernant le mapping de persistentUrl
"
)
if
"
publicationDate
"
in
metadata
:
dataset_publicationDate
=
metadata
[
"
publicationDate
"
]
# print (dataset_publicationDate)
elif
"
publicationDate
"
not
in
metadata
:
dataset_publicationDate
=
""
else
:
print
(
"
Vérifier la partie du code concernant le mapping de publicationDate
"
)
if
"
publisher
"
in
metadata
:
dataset_publisher
=
metadata
[
"
publisher
"
]
# print (dataset_publisher)
elif
"
publisher
"
not
in
metadata
:
dataset_publisher
=
""
else
:
print
(
"
Vérifier la partie du code concernant le mapping de publisher
"
)
dataset_yearofPublication
=
dataset_publicationDate
[
0
:
4
]
if
"
license
"
in
metadata
[
"
latestVersion
"
]
:
dataset_license
=
metadata
[
"
latestVersion
"
][
"
license
"
]
# print (dataset_license)
elif
"
license
"
not
in
metadata
[
"
latestVersion
"
]
:
dataset_license
=
""
else
:
print
(
"
Vérifier la partie du code concernant le mapping de license
"
)
if
"
versionNumber
"
in
metadata
[
"
latestVersion
"
]
:
dataset_versionNumber
=
metadata
[
"
latestVersion
"
][
"
versionNumber
"
]
# print (dataset_versionNumber)
elif
"
versionNumber
"
not
in
metadata
[
"
latestVersion
"
]
:
dataset_versionNumber
=
""
else
:
print
(
"
Vérifier la partie du code concernant le mapping de versionNumber
"
)
if
"
versionMinorNumber
"
in
metadata
[
"
latestVersion
"
]
:
dataset_versionMinorNumber
=
metadata
[
"
latestVersion
"
][
"
versionMinorNumber
"
]
# print (dataset_versionMinorNumber)
elif
"
versionMinorNumber
"
not
in
metadata
[
"
latestVersion
"
]
:
dataset_versionMinorNumber
=
"
0
"
else
:
print
(
"
Vérifier la partie du code concernant le mapping de versionMinorNumber
"
)
if
"
UNF
"
in
metadata
[
"
latestVersion
"
]
:
dataset_unf
=
metadata
[
"
latestVersion
"
][
"
UNF
"
]
# print (dataset_unf)
elif
"
UNF
"
not
in
metadata
[
"
latestVersion
"
]
:
dataset_unf
=
""
else
:
print
(
"
Vérifier la partie du code concernant le mapping de UNF
"
)
print
(
"
y
"
)
# ----------------------------------------------------------------
# Exploration des sous-blocs et récupération des champs répétables
# ----------------------------------------------------------------
fields
=
metadata
[
"
latestVersion
"
][
"
metadataBlocks
"
][
"
citation
"
][
"
fields
"
]
for
field
in
fields
:
# chaque champ est pris l'un après l'autre. field est un dictionnaire
# print (field)
# print (f"{field['typeName']} : {field['value']}")
typeName
=
field
[
'
typeName
'
]
# title = "" # on définit par avance l'ensemble des champs en leur attribuant une valeur vide
# authors = ""
# datasetContacts = ""
# dsDescriptions = ""
# subjects = ""
# keywords = ""
# languages = ""
# depositors = ""
# dateOfDeposit = ""
if
typeName
==
'
title
'
:
title
=
field
[
'
value
'
]
# champ unique
if
typeName
==
'
author
'
:
authors
=
field
[
'
value
'
]
# liste de dictionnaires donc chaque élément est un auteur
for
author
in
authors
:
authorName
=
author
[
"
authorName
"
][
"
value
"
]
authors_list
.
append
(
authorName
)
if
typeName
==
'
datasetContact
'
:
datasetContacts
=
field
[
'
value
'
]
# champ multiple
if
typeName
==
'
dsDescription
'
:
dsDescriptions
=
field
[
'
value
'
]
# champ multiple
if
typeName
==
'
subject
'
:
subjects
=
field
[
'
value
'
]
# champ multiple
if
typeName
==
'
language
'
:
languages
=
field
[
'
value
'
]
# liste
if
typeName
==
'
depositor
'
:
depositors
=
field
[
'
value
'
]
if
typeName
==
'
keyword
'
:
keywords
=
field
[
'
value
'
]
if
typeName
==
'
dateofDeposit
'
:
dateofDeposit
=
field
[
'
value
'
]
# Appel de la fonction de génération de citation
citation_current
=
citation_generation
(
cit_authors
=
authors_list
,
cit_title
=
title
,
cit_year
=
dataset_yearofPublication
,
cit_data_repository
=
dataset_publisher
,
cit_version_number
=
dataset_versionNumber
,
cit_version_minor_number
=
dataset_versionMinorNumber
,
cit_doi
=
doi
,
cit_unf
=
dataset_unf
)
print
(
citation_current
)
bibliography_list
.
append
(
citation_current
)
if
"
publicationDate
"
in
metadata
:
elif
"
latestVersion
"
not
in
metadata
:
dataset_publicationDate
=
metadata
[
"
publicationDate
"
]
print
(
"
Pas de version trouvée pour ce jeu de données. Pas d
'
export.
"
)
# print (dataset_publicationDate)
elif
"
publicationDate
"
not
in
metadata
:
dataset_publicationDate
=
""
else
:
print
(
"
Vérifier la partie du code concernant le mapping de publicationDate
"
)
dataset_yearofPublication
=
dataset_publicationDate
[
0
:
4
]
if
"
license
"
in
metadata
[
"
latestVersion
"
]
:
dataset_license
=
metadata
[
"
latestVersion
"
][
"
license
"
]
# print (dataset_license)
elif
"
license
"
not
in
metadata
[
"
latestVersion
"
]
:
dataset_license
=
""
else
:
print
(
"
Vérifier la partie du code concernant le mapping de license
"
)
if
"
publisher
"
in
metadata
:
dataset_publisher
=
metadata
[
"
publisher
"
]
# print (dataset_publisher)
elif
"
publisher
"
not
in
metadata
:
dataset_publisher
=
""
else
:
print
(
"
Vérifier la partie du code concernant le mapping de publisher
"
)
if
"
versionNumber
"
in
metadata
[
"
latestVersion
"
]
:
dataset_versionNumber
=
metadata
[
"
latestVersion
"
][
"
versionNumber
"
]
# print (dataset_versionNumber)
elif
"
versionNumber
"
not
in
metadata
[
"
latestVersion
"
]
:
dataset_versionNumber
=
""
else
:
print
(
"
Vérifier la partie du code concernant le mapping de versionNumber
"
)
if
"
versionMinorNumber
"
in
metadata
[
"
latestVersion
"
]
:
dataset_versionMinorNumber
=
metadata
[
"
latestVersion
"
][
"
versionMinorNumber
"
]
# print (dataset_versionMinorNumber)
elif
"
versionMinorNumber
"
not
in
metadata
[
"
latestVersion
"
]
:
dataset_versionMinorNumber
=
"
0
"
else
:
print
(
"
Vérifier la partie du code concernant le mapping de versionMinorNumber
"
)
if
"
UNF
"
in
metadata
[
"
latestVersion
"
]
:
dataset_unf
=
metadata
[
"
latestVersion
"
][
"
UNF
"
]
# print (dataset_unf)
elif
"
UNF
"
not
in
metadata
[
"
latestVersion
"
]
:
dataset_unf
=
""
else
:
else
:
print
(
"
Vérifier la partie du code concernant le mapping de UNF
"
)
print
(
"
Problème d
'
exception sur le test de présence de latestVersion, corriger le code.
"
)
fields
=
metadata
[
"
latestVersion
"
][
"
metadataBlocks
"
][
"
citation
"
][
"
fields
"
]
for
field
in
fields
:
# chaque champ est pris l'un après l'autre. field est un dictionnaire
# print (field)
# print (f"{field['typeName']} : {field['value']}")
typeName
=
field
[
'
typeName
'
]
# title = "" # on définit par avance l'ensemble des champs en leur attribuant une valeur vide
# authors = ""
# datasetContacts = ""
# dsDescriptions = ""
# subjects = ""
# keywords = ""
# languages = ""
# depositors = ""
# dateOfDeposit = ""
if
typeName
==
'
title
'
:
title
=
field
[
'
value
'
]
# champ unique
if
typeName
==
'
author
'
:
authors
=
field
[
'
value
'
]
# liste de dictionnaires donc chaque élément est un auteur
for
author
in
authors
:
authorName
=
author
[
"
authorName
"
][
"
value
"
]
authors_list
.
append
(
authorName
)
if
typeName
==
'
datasetContact
'
:
datasetContacts
=
field
[
'
value
'
]
# champ multiple
if
typeName
==
'
dsDescription
'
:
dsDescriptions
=
field
[
'
value
'
]
# champ multiple
if
typeName
==
'
subject
'
:
subjects
=
field
[
'
value
'
]
# champ multiple
if
typeName
==
'
language
'
:
languages
=
field
[
'
value
'
]
# liste
if
typeName
==
'
depositor
'
:
depositors
=
field
[
'
value
'
]
if
typeName
==
'
keyword
'
:
keywords
=
field
[
'
value
'
]
if
typeName
==
'
dateofDeposit
'
:
dateofDeposit
=
field
[
'
value
'
]
# Appel de la fonction de génération de citation
citation_current
=
citation_generation
(
cit_authors
=
authors_list
,
cit_title
=
title
,
cit_year
=
dataset_yearofPublication
,
cit_data_repository
=
dataset_publisher
,
cit_version_number
=
dataset_versionNumber
,
cit_version_minor_number
=
dataset_versionMinorNumber
,
cit_doi
=
doi
,
cit_unf
=
dataset_unf
)
print
(
citation_current
)
bibliography_list
.
append
(
citation_current
)
# -------------------------------------
# -------------------------------------
# Génération de la bibliographie finale
# Génération de la bibliographie finale
...
...
This diff is collapsed.
Click to expand it.
Preview
0%
Loading
Try again
or
attach a new file
.
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Save comment
Cancel
Please
register
or
sign in
to comment