Skip to content

Commit

Permalink
Revert "Merge pull request #1692 from CentreForDigitalHumanities/feat…
Browse files Browse the repository at this point in the history
…ure/gallica"

This reverts commit a9cec96, reversing
changes made to bb5d3f1.
  • Loading branch information
lukavdplas committed Nov 15, 2024
1 parent a9cec96 commit bc3194a
Show file tree
Hide file tree
Showing 13 changed files with 17 additions and 495 deletions.
17 changes: 0 additions & 17 deletions backend/addcorpus/python_corpora/corpus.py
Original file line number Diff line number Diff line change
Expand Up @@ -79,23 +79,6 @@ def category(self):
'''
raise NotImplementedError('CorpusDefinition missing category')

'''
Directory where source data is located
If neither `data_directory` nor `data_url` is set to valid paths, this corpus cannot be indexed
'''
data_directory = None

'''
URL where source data is located
If neither `data_directory` nor `data_url` is set to valid paths, this corpus cannot be indexed
'''
data_url = None

'''
If connecting to the data URL requires and API key, it needs to be set here
'''
data_api_key = None

@property
def es_index(self):
'''
Expand Down
27 changes: 10 additions & 17 deletions backend/addcorpus/validation/indexing.py
Original file line number Diff line number Diff line change
@@ -1,9 +1,9 @@
'''
This module defines functions to check if a corpus is ready for indexing.
'''
import os
import requests

import warnings
import os

from addcorpus.validation.creation import primary_mapping_type

Expand Down Expand Up @@ -87,19 +87,12 @@ def validate_has_data_directory(corpus):
return

config = corpus.configuration
if not config.data_directory and not config.data_url:
raise CorpusNotIndexableError('Missing data directory or url')

if corpus.data_dircetory and not os.path.isdir(config.data_directory):
raise CorpusNotIndexableError('Configured data directory does not exist.')
if not config.data_directory:
raise CorpusNotIndexableError(
'Missing data directory'
)

if corpus.data_url:
headers = {}
if corpus.data_api_key:
headers = {"Authorization": f"Token {corpus.data_api_key}"}
try:
requests.get(corpus.data_url, headers=headers)
except ConnectionError:
raise CorpusNotIndexableError(
'Cannot connect to the configured data url. Do you need to provide an API key?'
)
if not os.path.isdir(config.data_directory):
raise CorpusNotIndexableError(
'Configured data directory does not exist.'
)
35 changes: 0 additions & 35 deletions backend/corpora/gallica/conftest.py

This file was deleted.

55 changes: 0 additions & 55 deletions backend/corpora/gallica/figaro.py

This file was deleted.

162 changes: 0 additions & 162 deletions backend/corpora/gallica/gallica.py

This file was deleted.

Binary file removed backend/corpora/gallica/images/figaro.jpg
Binary file not shown.
Empty file.
4 changes: 0 additions & 4 deletions backend/corpora/gallica/tests/data/figaro/Issues.xml

This file was deleted.

62 changes: 0 additions & 62 deletions backend/corpora/gallica/tests/data/figaro/OAIRecord.xml

This file was deleted.

2 changes: 0 additions & 2 deletions backend/corpora/gallica/tests/data/figaro/RoughText.html

This file was deleted.

Loading

0 comments on commit bc3194a

Please sign in to comment.