17425918180

Committed 03 Sep 2025 07:11AM UTC coverage: 95.796% (-0.6%) from 96.378%

Build # 17425918180

Build Type

push

github

Committed by

PascalRepond

Commit Message

translations: extract messages

Co-Authored-by: Pascal Repond <pascal.repond@rero.ch>

Run Details

7816 of 8159 relevant lines covered (95.8%)

0.96 hits per line

Source File
Press 'n' to go to next uncovered line, 'b' for previous

41.51

/sonar/modules/documents/cli/documents.py

# Swiss Open Access Repository
# Copyright (C) 2021 RERO
#
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU Affero General Public License as published by
# the Free Software Foundation, version 3 of the License.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU Affero General Public License for more details.
#
# You should have received a copy of the GNU Affero General Public License
# along with this program.  If not, see <http://www.gnu.org/licenses/>.

"""Documents CLI commands."""

import json
from random import randint

import click
from flask.cli import with_appcontext
from invenio_db import db
from rero_invenio_files.pdf import PDFGenerator

from sonar.modules.documents.cli.rerodoc import rerodoc
from sonar.modules.documents.cli.urn import urn
from sonar.modules.documents.serializers.schemas.dc import DublinCoreSchema

from ..api import DocumentIndexer, DocumentRecord


@click.group()
def documents():
    """Commands for documents."""


documents.add_command(rerodoc)
documents.add_command(urn)


@click.group("documents")
def documents_fixtures():
    """Commands to import documents."""


def extract_metadata(record):
    """Extract metadata from record."""
    dc = DublinCoreSchema()
    data = {}
    if title := dc.get_title(record):
        data["title"] = title
    if authors := dc.get_contributors(record):
        data["authors"] = authors
    if summary := dc.get_descriptions(record):
        data["summary"] = summary[0]["value"]
    return data


@documents_fixtures.command("import")
@click.argument("file", type=click.File("r"))
@click.option("-m", "--maximum", type=int, default=None, help="Maximum number of documents to import.")
@with_appcontext
def import_documents(file, maximum=None):
    """Import documents from JSON file."""
    click.secho(f"Importing document from {file.name}")

    indexer = DocumentIndexer()
    n = 0
    data_documents = json.load(file)
    if maximum is not None:
        data_documents = data_documents[:maximum]
    with click.progressbar(data_documents, label="Loading documents...") as bar:
        for record in bar:
            try:
                # Register record to DB
                db_record = DocumentRecord.create(record)
                data = extract_metadata({"metadata": db_record})
                for i in range(1, randint(2, 5)):
                    pdf = PDFGenerator(data)
                    pdf.render()
                    db_record.add_file(pdf.output(), f"document_{i}.pdf", label="Document", type="file")

                db_record.commit()
                db.session.commit()

                indexer.index(db_record)
                n += 1
            except Exception as error:
                click.secho(
                    f"Document {record} could not be imported: {error}",
                    fg="red",
                )

    click.secho(f"{n} documents imported.", fg="green")

1	# Swiss Open Access Repository
2	# Copyright (C) 2021 RERO
3	#
4	# This program is free software: you can redistribute it and/or modify
5	# it under the terms of the GNU Affero General Public License as published by
6	# the Free Software Foundation, version 3 of the License.
7	#
8	# This program is distributed in the hope that it will be useful,
9	# but WITHOUT ANY WARRANTY; without even the implied warranty of
10	# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
11	# GNU Affero General Public License for more details.
12	#
13	# You should have received a copy of the GNU Affero General Public License
14	# along with this program. If not, see <http://www.gnu.org/licenses/>.
15
16	"""Documents CLI commands."""
17
18	import json	1✔
19	from random import randint	1✔
20
21	import click	1✔
22	from flask.cli import with_appcontext	1✔
23	from invenio_db import db	1✔
24	from rero_invenio_files.pdf import PDFGenerator	1✔
25
26	from sonar.modules.documents.cli.rerodoc import rerodoc	1✔
27	from sonar.modules.documents.cli.urn import urn	1✔
28	from sonar.modules.documents.serializers.schemas.dc import DublinCoreSchema	1✔
29
30	from ..api import DocumentIndexer, DocumentRecord	1✔
31
32
33	@click.group()	1✔
34	def documents():	1✔
35	"""Commands for documents."""
36
37
38	documents.add_command(rerodoc)	1✔
39	documents.add_command(urn)	1✔
40
41
42	@click.group("documents")	1✔
43	def documents_fixtures():	1✔
44	"""Commands to import documents."""
45
46
47	def extract_metadata(record):	1✔
48	"""Extract metadata from record."""
49	dc = DublinCoreSchema()	×
50	data = {}	×
51	if title := dc.get_title(record):	×
52	data["title"] = title	×
53	if authors := dc.get_contributors(record):	×
54	data["authors"] = authors	×
55	if summary := dc.get_descriptions(record):	×
56	data["summary"] = summary[0]["value"]	×
57	return data	×
58
59
60	@documents_fixtures.command("import")	1✔
61	@click.argument("file", type=click.File("r"))	1✔
62	@click.option("-m", "--maximum", type=int, default=None, help="Maximum number of documents to import.")	1✔
63	@with_appcontext	1✔
64	def import_documents(file, maximum=None):	1✔
65	"""Import documents from JSON file."""
66	click.secho(f"Importing document from {file.name}")	×
67
68	indexer = DocumentIndexer()	×
69	n = 0	×
70	data_documents = json.load(file)	×
71	if maximum is not None:	×
72	data_documents = data_documents[:maximum]	×
73	with click.progressbar(data_documents, label="Loading documents...") as bar:	×
74	for record in bar:	×
75	try:	×
76	# Register record to DB
77	db_record = DocumentRecord.create(record)	×
78	data = extract_metadata({"metadata": db_record})	×
79	for i in range(1, randint(2, 5)):	×
80	pdf = PDFGenerator(data)	×
81	pdf.render()	×
82	db_record.add_file(pdf.output(), f"document_{i}.pdf", label="Document", type="file")	×
83
84	db_record.commit()	×
85	db.session.commit()	×
86
87	indexer.index(db_record)	×
88	n += 1	×
89	except Exception as error:	×
90	click.secho(	×
91	f"Document {record} could not be imported: {error}",
92	fg="red",
93	)
94
95	click.secho(f"{n} documents imported.", fg="green")	×

rero / sonar / 17425918180

Source File Press 'n' to go to next uncovered line, 'b' for previous

Source File
Press 'n' to go to next uncovered line, 'b' for previous