Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

simplify grobid URL configuration #5

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

simplify grobid URL configuration #5

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 5 additions & 8 deletions article_dataset_builder/harvest.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -108,7 +108,7 @@ def _load_config(self, path='./config.json'):

# test if GROBID is up and running, except if we just want to download raw files
if self.apply_grobid:
the_url = _grobid_url(self.config['grobid_base'], self.config['grobid_port'])
the_url = _grobid_url(self.config['grobid_base'])
the_url += "isalive"
try:
r = requests.get(the_url)
Expand Down Expand Up @@ -449,7 +449,7 @@ def run_grobid(self, pdf_file, output=None, annotation_output=None):
)
}

the_url = _grobid_url(self.config['grobid_base'], self.config['grobid_port'])
the_url = _grobid_url(self.config['grobid_base'])
the_url += "processFulltextDocument"

# set the GROBID parameters
Expand Down Expand Up @@ -496,7 +496,7 @@ def run_grobid(self, pdf_file, output=None, annotation_output=None):
)
}

the_url = _grobid_url(self.config['grobid_base'], self.config['grobid_port'])
the_url = _grobid_url(self.config['grobid_base'])
the_url += "referenceAnnotations"

# set the GROBID parameters
Expand Down Expand Up @@ -1458,11 +1458,8 @@ def _biblio_glutton_url(biblio_glutton_url):
res = biblio_glutton_url[:-1]
return res+"/service/lookup?"

def _grobid_url(grobid_base, grobid_port):
the_url = 'http://'+grobid_base
if grobid_port is not None and len(grobid_port)>0:
the_url += ":"+grobid_port
the_url += "/api/"
def _grobid_url(grobid_url):
the_url = grobid_url + "/api/"
return the_url

def _download(url, filename):
Expand Down
3 changes: 1 addition & 2 deletions config.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,8 +14,7 @@
"biblio_glutton_base": "http://cloud.science-miner.com/glutton",
"crossref_base": "https://api.crossref.org",
"crossref_email": "",
"grobid_base": "localhost",
"grobid_port": "8070",
"grobid_base": "http://localhost:8070",
"cord19_elsevier_map_path": "resources/elsevier_covid_map_26-07-2021.csv.gz",
"cord19_elsevier_pdf_path": "",
"pub2tei_path": ""
Expand Down