commonmeta-py 0.118__py3-none-any.whl → 0.119__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- commonmeta/__init__.py +1 -1
- commonmeta/doi_utils.py +0 -1
- commonmeta/file_utils.py +0 -10
- commonmeta/writers/crossref_xml_writer.py +43 -38
- commonmeta/writers/inveniordm_writer.py +7 -7
- {commonmeta_py-0.118.dist-info → commonmeta_py-0.119.dist-info}/METADATA +2 -2
- {commonmeta_py-0.118.dist-info → commonmeta_py-0.119.dist-info}/RECORD +10 -10
- {commonmeta_py-0.118.dist-info → commonmeta_py-0.119.dist-info}/WHEEL +0 -0
- {commonmeta_py-0.118.dist-info → commonmeta_py-0.119.dist-info}/entry_points.txt +0 -0
- {commonmeta_py-0.118.dist-info → commonmeta_py-0.119.dist-info}/licenses/LICENSE +0 -0
commonmeta/__init__.py
CHANGED
commonmeta/doi_utils.py
CHANGED
@@ -342,7 +342,6 @@ def is_rogue_scholar_doi(doi: str, ra: str = "crossref") -> bool:
|
|
342
342
|
|
343
343
|
def generate_wordpress_doi(prefix: str, slug: str, guid: str) -> str:
|
344
344
|
"""Generate a DOI from a WordPress GUID and slug"""
|
345
|
-
import re
|
346
345
|
|
347
346
|
if not prefix or not guid:
|
348
347
|
return ""
|
commonmeta/file_utils.py
CHANGED
@@ -44,16 +44,6 @@ def download_file(url: str) -> bytes:
|
|
44
44
|
resp = requests.get(url, stream=True)
|
45
45
|
resp.raise_for_status()
|
46
46
|
return resp.content
|
47
|
-
# # Progress bar
|
48
|
-
# total = int(resp.headers.get("content-length", 0))
|
49
|
-
|
50
|
-
# buf = io.BytesIO()
|
51
|
-
# with tqdm(total=total, unit="B", unit_scale=True, desc="downloading") as bar:
|
52
|
-
# for chunk in resp.iter_content(chunk_size=8192):
|
53
|
-
# if chunk:
|
54
|
-
# buf.write(chunk)
|
55
|
-
# bar.update(len(chunk))
|
56
|
-
# return buf.getvalue()
|
57
47
|
|
58
48
|
|
59
49
|
def write_file(filename: str, output: bytes) -> None:
|
@@ -1,6 +1,7 @@
|
|
1
1
|
"""Crossref XML writer for commonmeta-py"""
|
2
2
|
|
3
3
|
import io
|
4
|
+
import logging
|
4
5
|
from datetime import datetime
|
5
6
|
from time import time
|
6
7
|
from typing import Optional
|
@@ -18,6 +19,8 @@ from ..constants import Commonmeta
|
|
18
19
|
from ..doi_utils import doi_from_url, validate_doi
|
19
20
|
from ..utils import validate_url
|
20
21
|
|
22
|
+
logger = logging.getLogger(__name__)
|
23
|
+
|
21
24
|
POSTED_CONTENT_TYPES = [
|
22
25
|
"preprint",
|
23
26
|
"working_paper",
|
@@ -342,20 +345,25 @@ def write_crossref_xml(metadata: Commonmeta) -> Optional[str]:
|
|
342
345
|
|
343
346
|
data = convert_crossref_xml(metadata)
|
344
347
|
if data is None:
|
348
|
+
logger.error(f"Could not convert metadata to Crossref XML: {metadata.id}")
|
345
349
|
return None
|
350
|
+
|
351
|
+
# Use the marshmallow schema to dump the data
|
346
352
|
schema = CrossrefXMLSchema()
|
347
353
|
crossref_xml = schema.dump(data)
|
348
354
|
|
349
|
-
# Ensure
|
355
|
+
# Ensure consistent field ordering through the defined mapping
|
350
356
|
field_order = [MARSHMALLOW_MAP.get(k, k) for k in list(data.keys())]
|
351
357
|
crossref_xml = {k: crossref_xml[k] for k in field_order if k in crossref_xml}
|
358
|
+
|
352
359
|
# Convert to XML
|
353
360
|
return unparse_xml(crossref_xml, dialect="crossref")
|
354
361
|
|
355
362
|
|
356
|
-
def write_crossref_xml_list(metalist):
|
363
|
+
def write_crossref_xml_list(metalist) -> Optional[str]:
|
357
364
|
"""Write crossref_xml list"""
|
358
365
|
if metalist is None or not metalist.is_valid:
|
366
|
+
logger.error("Invalid metalist provided for Crossref XML generation")
|
359
367
|
return None
|
360
368
|
|
361
369
|
schema = CrossrefXMLSchema()
|
@@ -380,15 +388,17 @@ def push_crossref_xml_list(metalist, login_id: str, login_passwd: str) -> bytes:
|
|
380
388
|
"""Push crossref_xml list to Crossref API, returns the API response."""
|
381
389
|
|
382
390
|
input = write_crossref_xml_list(metalist)
|
391
|
+
if not input:
|
392
|
+
logger.error("Failed to generate XML for upload")
|
393
|
+
return "{}"
|
383
394
|
|
384
395
|
# Convert string to bytes if necessary
|
385
396
|
if isinstance(input, str):
|
386
397
|
input = input.encode("utf-8")
|
387
398
|
|
388
|
-
# The filename displayed in the Crossref admin interface
|
399
|
+
# The filename displayed in the Crossref admin interface
|
389
400
|
filename = f"{int(time())}"
|
390
401
|
|
391
|
-
# Create multipart form data
|
392
402
|
multipart_data = MultipartEncoder(
|
393
403
|
fields={
|
394
404
|
"fname": (filename, io.BytesIO(input), "application/xml"),
|
@@ -398,38 +408,32 @@ def push_crossref_xml_list(metalist, login_id: str, login_passwd: str) -> bytes:
|
|
398
408
|
}
|
399
409
|
)
|
400
410
|
|
401
|
-
# Set up the request
|
402
411
|
post_url = "https://doi.crossref.org/servlet/deposit"
|
403
412
|
headers = {"Content-Type": multipart_data.content_type}
|
413
|
+
resp = requests.post(post_url, data=multipart_data, headers=headers, timeout=10)
|
414
|
+
resp.raise_for_status()
|
415
|
+
|
416
|
+
# Parse the response
|
417
|
+
response = parse_xml(resp.content)
|
418
|
+
status = py_.get(response, "html.body.h2")
|
419
|
+
if status == "SUCCESS":
|
420
|
+
items = []
|
421
|
+
for item in metalist.items:
|
422
|
+
items.append(
|
423
|
+
{
|
424
|
+
"doi": item.id,
|
425
|
+
"updated": datetime.now().isoformat("T", "seconds"),
|
426
|
+
"status": "submitted",
|
427
|
+
}
|
428
|
+
)
|
404
429
|
|
405
|
-
|
406
|
-
|
407
|
-
resp = requests.post(post_url, data=multipart_data, headers=headers, timeout=10)
|
408
|
-
resp.raise_for_status()
|
409
|
-
|
410
|
-
# Parse the response
|
411
|
-
response = parse_xml(resp.content)
|
412
|
-
status = py_.get(response, "html.body.h2")
|
413
|
-
if status == "SUCCESS":
|
414
|
-
items = []
|
415
|
-
for item in metalist.items:
|
416
|
-
items.append(
|
417
|
-
{
|
418
|
-
"doi": item.id,
|
419
|
-
"updated": datetime.now().isoformat("T", "seconds"),
|
420
|
-
"status": "submitted",
|
421
|
-
}
|
422
|
-
)
|
423
|
-
|
424
|
-
# orjson has different options
|
425
|
-
return json.dumps(items, option=json.OPT_INDENT_2)
|
426
|
-
|
427
|
-
# if there is an error
|
428
|
-
message = py_.get(response, "html.body.p")
|
429
|
-
raise CrossrefError(f"Error uploading batch: {message}")
|
430
|
+
# Return JSON response
|
431
|
+
return json.dumps(items, option=json.OPT_INDENT_2)
|
430
432
|
|
431
|
-
|
432
|
-
|
433
|
+
# Handle error response
|
434
|
+
message = py_.get(response, "html.body.p")
|
435
|
+
logger.error(f"Crossref API error: {message}")
|
436
|
+
return "{}"
|
433
437
|
|
434
438
|
|
435
439
|
def get_attributes(obj, **kwargs) -> dict:
|
@@ -539,15 +543,16 @@ def get_institution(obj) -> Optional[dict]:
|
|
539
543
|
def get_titles(obj) -> Optional[dict]:
|
540
544
|
"""get titles"""
|
541
545
|
|
542
|
-
|
546
|
+
titles = {}
|
543
547
|
for t in wrap(py_.get(obj, "titles", [])):
|
544
548
|
if isinstance(t, str):
|
545
|
-
|
549
|
+
titles["title"] = t
|
546
550
|
elif isinstance(t, dict) and t.get("titleType", None) == "Subtitle":
|
547
|
-
|
548
|
-
elif isinstance(
|
549
|
-
|
550
|
-
|
551
|
+
titles["subtitle"] = t.get("title", None)
|
552
|
+
elif isinstance(t, dict):
|
553
|
+
titles["title"] = t.get("title", None)
|
554
|
+
|
555
|
+
return titles if titles else None
|
551
556
|
|
552
557
|
|
553
558
|
def get_contributors(obj) -> Optional[dict]:
|
@@ -3,7 +3,7 @@
|
|
3
3
|
import logging
|
4
4
|
import re
|
5
5
|
from time import time
|
6
|
-
from typing import
|
6
|
+
from typing import Dict, Optional
|
7
7
|
from urllib.parse import urlparse
|
8
8
|
|
9
9
|
import orjson as json
|
@@ -392,11 +392,11 @@ def push_inveniordm(
|
|
392
392
|
host: str,
|
393
393
|
token: str,
|
394
394
|
legacy_key: str
|
395
|
-
) ->
|
395
|
+
) -> Dict:
|
396
396
|
"""Push record to InvenioRDM"""
|
397
397
|
|
398
398
|
record = {}
|
399
|
-
|
399
|
+
output = write_inveniordm(metadata)
|
400
400
|
|
401
401
|
try:
|
402
402
|
# Remove IsPartOf relation with InvenioRDM community identifier after storing it
|
@@ -439,10 +439,10 @@ def push_inveniordm(
|
|
439
439
|
record = edit_published_record(record, host, token)
|
440
440
|
|
441
441
|
# Update draft record
|
442
|
-
record = update_draft_record(record, host, token,
|
442
|
+
record = update_draft_record(record, host, token, output)
|
443
443
|
else:
|
444
444
|
# Create draft record
|
445
|
-
record = create_draft_record(record, host, token,
|
445
|
+
record = create_draft_record(record, host, token, output)
|
446
446
|
|
447
447
|
# Publish draft record
|
448
448
|
record = publish_draft_record(record, host, token)
|
@@ -525,7 +525,7 @@ def search_by_doi(doi, host, token) -> Optional[str]:
|
|
525
525
|
return None
|
526
526
|
|
527
527
|
|
528
|
-
def create_draft_record(record, host, token,
|
528
|
+
def create_draft_record(record, host, token, output):
|
529
529
|
"""Create a new draft record in InvenioRDM"""
|
530
530
|
headers = {
|
531
531
|
"Authorization": f"Bearer {token}",
|
@@ -533,7 +533,7 @@ def create_draft_record(record, host, token, input):
|
|
533
533
|
}
|
534
534
|
try:
|
535
535
|
response = requests.post(
|
536
|
-
f"https://{host}/api/records", headers=headers, json=
|
536
|
+
f"https://{host}/api/records", headers=headers, json=output
|
537
537
|
)
|
538
538
|
if response.status_code == 429:
|
539
539
|
record["status"] = "failed_rate_limited"
|
@@ -1,6 +1,6 @@
|
|
1
1
|
Metadata-Version: 2.4
|
2
2
|
Name: commonmeta-py
|
3
|
-
Version: 0.
|
3
|
+
Version: 0.119
|
4
4
|
Summary: Library for conversions to/from the Commonmeta scholarly metadata format
|
5
5
|
Project-URL: Homepage, https://python.commonmeta.org
|
6
6
|
Project-URL: Repository, https://github.com/front-matter/commonmeta-py
|
@@ -36,7 +36,7 @@ Requires-Dist: pyyaml>=5.4
|
|
36
36
|
Requires-Dist: requests-toolbelt>=1.0.0
|
37
37
|
Requires-Dist: requests>=2.31.0
|
38
38
|
Requires-Dist: requests>=2.32.3
|
39
|
-
Requires-Dist: setuptools
|
39
|
+
Requires-Dist: setuptools<81,>=70.3.0
|
40
40
|
Requires-Dist: simplejson~=3.18
|
41
41
|
Requires-Dist: types-beautifulsoup4<5,>=4.11
|
42
42
|
Requires-Dist: types-dateparser~=1.1
|
@@ -1,12 +1,12 @@
|
|
1
|
-
commonmeta/__init__.py,sha256=
|
1
|
+
commonmeta/__init__.py,sha256=V-Y0A2HSjqUF0gh_o1M-VRLMSbZAFWTSfKunBeX02UE,2098
|
2
2
|
commonmeta/api_utils.py,sha256=y5KLfIOWOjde7LXZ36u-eneQJ-Q53yXUZg3hWpCBS2E,2685
|
3
3
|
commonmeta/author_utils.py,sha256=3lYW5s1rOUWNTKs1FP6XLfEUY3yCLOe_3L_VdJTDMp0,8585
|
4
4
|
commonmeta/base_utils.py,sha256=-MGy9q2uTiJEkPWQUYOJMdq-3tRpNnvBwlLjvllQ5g8,11164
|
5
5
|
commonmeta/cli.py,sha256=pdBpBosLNq3RS9buO-Voqawc9Ay1eSt-xP5O97iOft4,8480
|
6
6
|
commonmeta/constants.py,sha256=wSTEUiHeRdXLwjXEQD9AU2hxFyEKi5OTX2iHOKO6nF0,19844
|
7
7
|
commonmeta/date_utils.py,sha256=H2cCobX0JREIUOT_cCigGd3MG7prGiQpXk1m4ZNrFwU,6318
|
8
|
-
commonmeta/doi_utils.py,sha256=
|
9
|
-
commonmeta/file_utils.py,sha256=
|
8
|
+
commonmeta/doi_utils.py,sha256=cOogLatKg6qea2jgMd3yLALSTfaTNUgr-IkBXIK4xZw,11498
|
9
|
+
commonmeta/file_utils.py,sha256=eFYDWyR8Gr722nvFmp542hCm-TGmO_q4ciZ85IPHpjA,2893
|
10
10
|
commonmeta/metadata.py,sha256=U9uYOkKAdgqLiQwQKXMXjrAFvO6avMWp9heJG4cNAAY,18893
|
11
11
|
commonmeta/schema_utils.py,sha256=WGpmMj9cfNMg_55hhgwY9qpO0A1HSvTLQC2equjBftI,1770
|
12
12
|
commonmeta/translators.py,sha256=CBMK4jrXRmGZiAhCh6wsJjhbDJWbcsda8UvXFXxccAw,1363
|
@@ -77,14 +77,14 @@ commonmeta/writers/__init__.py,sha256=47-snms6xBHkoEXKYV1DBtH1npAtlVtvY29Z4Zr45q
|
|
77
77
|
commonmeta/writers/bibtex_writer.py,sha256=doAdyl1NEp60mPkHPo3GMH8B-HA6MzLAdlyNsIecTzU,4972
|
78
78
|
commonmeta/writers/citation_writer.py,sha256=qs_4X3BjrSqHexmJFPvPDTp0mRIqzb0F70_Wuc7S9x0,2343
|
79
79
|
commonmeta/writers/commonmeta_writer.py,sha256=QpfyhG__7o_XpsOTCPWxGymO7YKwZi2LQh8Zic44bdc,1365
|
80
|
-
commonmeta/writers/crossref_xml_writer.py,sha256=
|
80
|
+
commonmeta/writers/crossref_xml_writer.py,sha256=1zEln2yJwcY62jFde5X-6BHWfnKOqadRRjx5z8Nt5CY,33540
|
81
81
|
commonmeta/writers/csl_writer.py,sha256=4gDYs1EzK4_L2UIRTfs25wgHmYRwdRP2zmfxF9387oU,2779
|
82
82
|
commonmeta/writers/datacite_writer.py,sha256=bcinpwhq7XnVthKHH8-sdXA34dSlvFH4ImYH768iaQU,6428
|
83
|
-
commonmeta/writers/inveniordm_writer.py,sha256=
|
83
|
+
commonmeta/writers/inveniordm_writer.py,sha256=mmCCxNi1OVSALeWdw-1g0ZzB84GGOcH3r7va3Abj9W4,25672
|
84
84
|
commonmeta/writers/ris_writer.py,sha256=3SdyEvMRaPRP1SV1MB-MXBlunE7x6og7RF1zuWtetPc,2094
|
85
85
|
commonmeta/writers/schema_org_writer.py,sha256=s18_x0ReXwAGBoEAwp2q-HCgFQ-h5qRg6JyAlqCoSFE,5871
|
86
|
-
commonmeta_py-0.
|
87
|
-
commonmeta_py-0.
|
88
|
-
commonmeta_py-0.
|
89
|
-
commonmeta_py-0.
|
90
|
-
commonmeta_py-0.
|
86
|
+
commonmeta_py-0.119.dist-info/METADATA,sha256=Jq7ojg3cdi-sxDsoujwL8SzWLGzulwv9rFIZole3yJ4,7656
|
87
|
+
commonmeta_py-0.119.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
|
88
|
+
commonmeta_py-0.119.dist-info/entry_points.txt,sha256=U4w4BoRuS3rN5t5Y-uYSyOeU5Lh_VRVMS9OIDzIgw4w,50
|
89
|
+
commonmeta_py-0.119.dist-info/licenses/LICENSE,sha256=wsIvxF9Q9GC9vA_s79zTWP3BkXJdfUNRmALlU8GbW1s,1074
|
90
|
+
commonmeta_py-0.119.dist-info/RECORD,,
|
File without changes
|
File without changes
|
File without changes
|