commonmeta-py 0.118__py3-none-any.whl → 0.120__py3-none-any.whl

commonmeta/__init__.py

@@ -10,7 +10,7 @@ commonmeta-py is a Python library to convert scholarly metadata
 """
 
 __title__ = "commonmeta-py"
-__version__ = "0.118"
+__version__ = "0.120"
 __author__ = "Martin Fenner"
 __license__ = "MIT"
 

commonmeta/doi_utils.py

@@ -342,7 +342,6 @@ def is_rogue_scholar_doi(doi: str, ra: str = "crossref") -> bool:
 
 def generate_wordpress_doi(prefix: str, slug: str, guid: str) -> str:
     """Generate a DOI from a WordPress GUID and slug"""
-    import re
 
     if not prefix or not guid:
         return ""

commonmeta/file_utils.py

@@ -44,16 +44,6 @@ def download_file(url: str) -> bytes:
     resp = requests.get(url, stream=True)
     resp.raise_for_status()
     return resp.content
-    # # Progress bar
-    # total = int(resp.headers.get("content-length", 0))
-
-    # buf = io.BytesIO()
-    # with tqdm(total=total, unit="B", unit_scale=True, desc="downloading") as bar:
-    #     for chunk in resp.iter_content(chunk_size=8192):
-    #         if chunk:
-    #             buf.write(chunk)
-    #             bar.update(len(chunk))
-    # return buf.getvalue()
 
 
 def write_file(filename: str, output: bytes) -> None:

commonmeta/metadata.py

@@ -484,7 +484,7 @@ class MetadataList:
 
         if to == "crossref_xml":
             response = push_crossref_xml_list(
-                self, login_id=self.login_id, login_passwd=self.login_passwd
+                self, login_id=self.login_id, login_passwd=self.login_passwd, legacy_key=self.legacy_key
             )
             return response
         elif to == "datacite":

commonmeta/writers/crossref_xml_writer.py

@@ -1,6 +1,7 @@
 """Crossref XML writer for commonmeta-py"""
 
 import io
+import logging
 from datetime import datetime
 from time import time
 from typing import Optional
@@ -15,8 +16,11 @@ from requests_toolbelt.multipart.encoder import MultipartEncoder
 
 from ..base_utils import compact, parse_xml, unparse_xml, unparse_xml_list, wrap
 from ..constants import Commonmeta
-from ..doi_utils import doi_from_url, validate_doi
+from ..doi_utils import doi_from_url, is_rogue_scholar_doi, validate_doi
 from ..utils import validate_url
+from .inveniordm_writer import update_legacy_record
+
+logger = logging.getLogger(__name__)
 
 POSTED_CONTENT_TYPES = [
     "preprint",
@@ -342,20 +346,25 @@ def write_crossref_xml(metadata: Commonmeta) -> Optional[str]:
 
     data = convert_crossref_xml(metadata)
     if data is None:
+        logger.error(f"Could not convert metadata to Crossref XML: {metadata.id}")
         return None
+
+    # Use the marshmallow schema to dump the data
     schema = CrossrefXMLSchema()
     crossref_xml = schema.dump(data)
 
-    # Ensure the order of fields in the XML matches the expected order
+    # Ensure consistent field ordering through the defined mapping
     field_order = [MARSHMALLOW_MAP.get(k, k) for k in list(data.keys())]
     crossref_xml = {k: crossref_xml[k] for k in field_order if k in crossref_xml}
+
     # Convert to XML
     return unparse_xml(crossref_xml, dialect="crossref")
 
 
-def write_crossref_xml_list(metalist):
+def write_crossref_xml_list(metalist) -> Optional[str]:
     """Write crossref_xml list"""
     if metalist is None or not metalist.is_valid:
+        logger.error("Invalid metalist provided for Crossref XML generation")
         return None
 
     schema = CrossrefXMLSchema()
@@ -376,19 +385,21 @@ def write_crossref_xml_list(metalist):
     return unparse_xml_list(crossref_xml_list, dialect="crossref", head=head)
 
 
-def push_crossref_xml_list(metalist, login_id: str, login_passwd: str) -> bytes:
+def push_crossref_xml_list(metalist, login_id: str, login_passwd: str, legacy_key:str=None) -> bytes:
     """Push crossref_xml list to Crossref API, returns the API response."""
 
     input = write_crossref_xml_list(metalist)
+    if not input:
+        logger.error("Failed to generate XML for upload")
+        return "{}"
 
     # Convert string to bytes if necessary
     if isinstance(input, str):
         input = input.encode("utf-8")
 
-    # The filename displayed in the Crossref admin interface, using the current UNIX timestamp
+    # The filename displayed in the Crossref admin interface
     filename = f"{int(time())}"
 
-    # Create multipart form data
     multipart_data = MultipartEncoder(
         fields={
             "fname": (filename, io.BytesIO(input), "application/xml"),
@@ -398,38 +409,42 @@ def push_crossref_xml_list(metalist, login_id: str, login_passwd: str) -> bytes:
         }
     )
 
-    # Set up the request
     post_url = "https://doi.crossref.org/servlet/deposit"
     headers = {"Content-Type": multipart_data.content_type}
+    resp = requests.post(post_url, data=multipart_data, headers=headers, timeout=10)
+    resp.raise_for_status()
+
+    # Parse the response
+    response = parse_xml(resp.content)
+    status = py_.get(response, "html.body.h2")
+    if status != "SUCCESS":
+        # Handle error response
+        message = py_.get(response, "html.body.p")
+        logger.error(f"Crossref API error: {message}")
+        return "{}"
+
+    items = []
+    for item in metalist.items:
+        record = {
+                "doi": item.id,
+                "updated": datetime.now().isoformat("T", "seconds"),
+                "status": "submitted",
+            }
+
+        # update rogue-scholar legacy record if legacy_key is provided
+        if is_rogue_scholar_doi(item.id, ra="crossref") and legacy_key is not None:
+             record = update_legacy_record(record, legacy_key=legacy_key, field="doi")
+        items.append(record)
+
+    # Return JSON response
+    return json.dumps(items, option=json.OPT_INDENT_2)
+
+
+
 
-    try:
-        # Send the request
-        resp = requests.post(post_url, data=multipart_data, headers=headers, timeout=10)
-        resp.raise_for_status()
-
-        # Parse the response
-        response = parse_xml(resp.content)
-        status = py_.get(response, "html.body.h2")
-        if status == "SUCCESS":
-            items = []
-            for item in metalist.items:
-                items.append(
-                    {
-                        "doi": item.id,
-                        "updated": datetime.now().isoformat("T", "seconds"),
-                        "status": "submitted",
-                    }
-                )
 
-            # orjson has different options
-            return json.dumps(items, option=json.OPT_INDENT_2)
 
-        # if there is an error
-        message = py_.get(response, "html.body.p")
-        raise CrossrefError(f"Error uploading batch: {message}")
 
-    except requests.exceptions.RequestException as e:
-        raise CrossrefError(f"Error uploading batch: {str(e)}") from e
 
 
 def get_attributes(obj, **kwargs) -> dict:
@@ -539,15 +554,16 @@ def get_institution(obj) -> Optional[dict]:
 def get_titles(obj) -> Optional[dict]:
     """get titles"""
 
-    title = {}
+    titles = {}
     for t in wrap(py_.get(obj, "titles", [])):
         if isinstance(t, str):
-            title["title"] = t
+            titles["title"] = t
         elif isinstance(t, dict) and t.get("titleType", None) == "Subtitle":
-            title["subtitle"] = t.get("title", None)
-        elif isinstance(title, dict):
-            title["title"] = t.get("title", None)
-    return title
+            titles["subtitle"] = t.get("title", None)
+        elif isinstance(t, dict):
+            titles["title"] = t.get("title", None)
+
+    return titles if titles else None
 
 
 def get_contributors(obj) -> Optional[dict]:

commonmeta/writers/inveniordm_writer.py

@@ -3,7 +3,7 @@
 import logging
 import re
 from time import time
-from typing import Any, Dict, Optional, Tuple
+from typing import Dict, Optional
 from urllib.parse import urlparse
 
 import orjson as json
@@ -392,11 +392,11 @@ def push_inveniordm(
         host: str,
         token: str,
         legacy_key: str
-    ) -> Tuple[Dict[str, Any], Optional[Exception]]:
+    ) -> Dict:
     """Push record to InvenioRDM"""
 
     record = {}
-    input = write_inveniordm(metadata)
+    output = write_inveniordm(metadata)
 
     try:
         # Remove IsPartOf relation with InvenioRDM community identifier after storing it
@@ -439,10 +439,10 @@ def push_inveniordm(
             record = edit_published_record(record, host, token)
 
             # Update draft record
-            record = update_draft_record(record, host, token, input)
+            record = update_draft_record(record, host, token, output)
         else:
             # Create draft record
-            record = create_draft_record(record, host, token, input)
+            record = create_draft_record(record, host, token, output)
 
         # Publish draft record
         record = publish_draft_record(record, host, token)
@@ -484,7 +484,7 @@ def push_inveniordm(
 
         # optionally update rogue-scholar legacy record
         if host == "rogue-scholar.org" and legacy_key is not None:
-            record = update_legacy_record(record, legacy_key)
+            record = update_legacy_record(record, legacy_key=legacy_key, field="rid")
     except Exception as e:
         logger.error(f"Unexpected error in push_inveniordm: {str(e)}", exc_info=True, extra={
             "host": host,
@@ -525,7 +525,7 @@ def search_by_doi(doi, host, token) -> Optional[str]:
         return None
 
 
-def create_draft_record(record, host, token, input):
+def create_draft_record(record, host, token, output):
     """Create a new draft record in InvenioRDM"""
     headers = {
         "Authorization": f"Bearer {token}",
@@ -533,7 +533,7 @@ def create_draft_record(record, host, token, input):
     }
     try:
         response = requests.post(
-            f"https://{host}/api/records", headers=headers, json=input
+            f"https://{host}/api/records", headers=headers, json=output
         )
         if response.status_code == 429:
             record["status"] = "failed_rate_limited"
@@ -651,7 +651,7 @@ def add_record_to_community(record, host, token, community_id):
         return record
 
 
-def update_legacy_record(record, legacy_key: str):
+def update_legacy_record(record, legacy_key: str, field:str=None) -> dict:
     """Update corresponding record in Rogue Scholar legacy database."""
 
     legacy_host = "bosczcmeodcrajtcaddf.supabase.co"
@@ -662,7 +662,7 @@ def update_legacy_record(record, legacy_key: str):
             raise ValueError("no UUID provided")
 
         now = f"{int(time())}"
-        if record.get("id", None) is not None:
+        if field == "rid" and record.get("id", None) is not None:
             output = {
                 "rid": record.get("id"),
                 "indexed_at": now,

{commonmeta_py-0.118.dist-info → commonmeta_py-0.120.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: commonmeta-py
-Version: 0.118
+Version: 0.120
 Summary: Library for conversions to/from the Commonmeta scholarly metadata format
 Project-URL: Homepage, https://python.commonmeta.org
 Project-URL: Repository, https://github.com/front-matter/commonmeta-py
@@ -36,7 +36,6 @@ Requires-Dist: pyyaml>=5.4
 Requires-Dist: requests-toolbelt>=1.0.0
 Requires-Dist: requests>=2.31.0
 Requires-Dist: requests>=2.32.3
-Requires-Dist: setuptools>=70.3.0
 Requires-Dist: simplejson~=3.18
 Requires-Dist: types-beautifulsoup4<5,>=4.11
 Requires-Dist: types-dateparser~=1.1

{commonmeta_py-0.118.dist-info → commonmeta_py-0.120.dist-info}/RECORD

@@ -1,13 +1,13 @@
-commonmeta/__init__.py,sha256=RbBIG26IxRjdvGzHH77sogy-rtAEHC51It7TQ6wPjS0,2098
+commonmeta/__init__.py,sha256=rWmoYjzULmmEdcjXnYZxNQk0qJ2tGwxTycmYxXoH65A,2098
 commonmeta/api_utils.py,sha256=y5KLfIOWOjde7LXZ36u-eneQJ-Q53yXUZg3hWpCBS2E,2685
 commonmeta/author_utils.py,sha256=3lYW5s1rOUWNTKs1FP6XLfEUY3yCLOe_3L_VdJTDMp0,8585
 commonmeta/base_utils.py,sha256=-MGy9q2uTiJEkPWQUYOJMdq-3tRpNnvBwlLjvllQ5g8,11164
 commonmeta/cli.py,sha256=pdBpBosLNq3RS9buO-Voqawc9Ay1eSt-xP5O97iOft4,8480
 commonmeta/constants.py,sha256=wSTEUiHeRdXLwjXEQD9AU2hxFyEKi5OTX2iHOKO6nF0,19844
 commonmeta/date_utils.py,sha256=H2cCobX0JREIUOT_cCigGd3MG7prGiQpXk1m4ZNrFwU,6318
-commonmeta/doi_utils.py,sha256=kS9wBoZQHvV-fqFoW9j-_aN_7Kj1I6sQdqnqK3Nno0M,11512
-commonmeta/file_utils.py,sha256=tGvXxScjh-PPo5YvLDyk4sqwY5Q50N0zAmBHVaUOLeU,3268
-commonmeta/metadata.py,sha256=U9uYOkKAdgqLiQwQKXMXjrAFvO6avMWp9heJG4cNAAY,18893
+commonmeta/doi_utils.py,sha256=cOogLatKg6qea2jgMd3yLALSTfaTNUgr-IkBXIK4xZw,11498
+commonmeta/file_utils.py,sha256=eFYDWyR8Gr722nvFmp542hCm-TGmO_q4ciZ85IPHpjA,2893
+commonmeta/metadata.py,sha256=m9UtE95t9awrlo9w9qZtwF7Y9sRfABpA5JKUZdyz5b4,18921
 commonmeta/schema_utils.py,sha256=WGpmMj9cfNMg_55hhgwY9qpO0A1HSvTLQC2equjBftI,1770
 commonmeta/translators.py,sha256=CBMK4jrXRmGZiAhCh6wsJjhbDJWbcsda8UvXFXxccAw,1363
 commonmeta/utils.py,sha256=pJnh3EzOU1E2nutnAZsopY_NsUX6zYmxoj5bIYqqWvE,50574
@@ -77,14 +77,14 @@ commonmeta/writers/__init__.py,sha256=47-snms6xBHkoEXKYV1DBtH1npAtlVtvY29Z4Zr45q
 commonmeta/writers/bibtex_writer.py,sha256=doAdyl1NEp60mPkHPo3GMH8B-HA6MzLAdlyNsIecTzU,4972
 commonmeta/writers/citation_writer.py,sha256=qs_4X3BjrSqHexmJFPvPDTp0mRIqzb0F70_Wuc7S9x0,2343
 commonmeta/writers/commonmeta_writer.py,sha256=QpfyhG__7o_XpsOTCPWxGymO7YKwZi2LQh8Zic44bdc,1365
-commonmeta/writers/crossref_xml_writer.py,sha256=d-Rb2Vd_g3UW8GM4APIT7fivSQ5GMssZ6Ubi3OykHaw,33479
+commonmeta/writers/crossref_xml_writer.py,sha256=Z5vhtWH-uz5WcBz1W_KOxyrvB5OQ2nTixV6EOhjOBnc,33859
 commonmeta/writers/csl_writer.py,sha256=4gDYs1EzK4_L2UIRTfs25wgHmYRwdRP2zmfxF9387oU,2779
 commonmeta/writers/datacite_writer.py,sha256=bcinpwhq7XnVthKHH8-sdXA34dSlvFH4ImYH768iaQU,6428
-commonmeta/writers/inveniordm_writer.py,sha256=el4Eapa9HHg1ceddHb9rd4d1MAsM1ZBZ1F4jQUV8mbI,25717
+commonmeta/writers/inveniordm_writer.py,sha256=eLllddYulFqg8qfRIScpYpnAJ82NCHXotCFJb09mHX8,25739
 commonmeta/writers/ris_writer.py,sha256=3SdyEvMRaPRP1SV1MB-MXBlunE7x6og7RF1zuWtetPc,2094
 commonmeta/writers/schema_org_writer.py,sha256=s18_x0ReXwAGBoEAwp2q-HCgFQ-h5qRg6JyAlqCoSFE,5871
-commonmeta_py-0.118.dist-info/METADATA,sha256=BD1a2ouuh4hYizCty5tBGQuQM3m6LWVf1zfmTQwnFPU,7652
-commonmeta_py-0.118.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-commonmeta_py-0.118.dist-info/entry_points.txt,sha256=U4w4BoRuS3rN5t5Y-uYSyOeU5Lh_VRVMS9OIDzIgw4w,50
-commonmeta_py-0.118.dist-info/licenses/LICENSE,sha256=wsIvxF9Q9GC9vA_s79zTWP3BkXJdfUNRmALlU8GbW1s,1074
-commonmeta_py-0.118.dist-info/RECORD,,
+commonmeta_py-0.120.dist-info/METADATA,sha256=BxKd_hZcarnoQQUklRQ0leX_vAUu3hxYP1KGSTpH89E,7618
+commonmeta_py-0.120.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+commonmeta_py-0.120.dist-info/entry_points.txt,sha256=U4w4BoRuS3rN5t5Y-uYSyOeU5Lh_VRVMS9OIDzIgw4w,50
+commonmeta_py-0.120.dist-info/licenses/LICENSE,sha256=wsIvxF9Q9GC9vA_s79zTWP3BkXJdfUNRmALlU8GbW1s,1074
+commonmeta_py-0.120.dist-info/RECORD,,