commonmeta-py 0.105__py3-none-any.whl → 0.107__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__ = "0.105"
+__version__ = "0.107"
 __author__ = "Martin Fenner"
 __license__ = "MIT"
 
@@ -31,6 +31,18 @@ from .base_utils import (
     unwrap,
     wrap,
 )
+from .crossref_utils import (
+    CrossrefBadRequestError,
+    CrossrefError,
+    CrossrefForbiddenError,
+    CrossrefNoContentError,
+    CrossrefNotFoundError,
+    CrossrefRequestError,
+    CrossrefServerError,
+    CrossrefUnauthorizedError,
+    HttpError,
+    generate_crossref_xml,
+)
 from .date_utils import (
     get_date_from_crossref_parts,
     get_date_from_date_parts,

commonmeta/api_utils.py

@@ -1,12 +1,13 @@
 """API Utils module for commonmeta-py"""
 
-from typing import Optional
 from datetime import datetime as date
-import httpx
-from furl import furl
+from typing import Optional
+
 import jwt
+import requests
+from furl import furl
 
-from .doi_utils import validate_doi, doi_as_url
+from .doi_utils import doi_as_url, validate_doi
 from .readers.json_feed_reader import get_json_feed_item_uuid
 
 
@@ -52,7 +53,7 @@ def update_ghost_post_via_api(
     f = furl(url)
     slug = f.path.segments[-1]
     ghost_url = f"{api_url}/ghost/api/admin/posts/slug/{slug}/"
-    response = httpx.get(ghost_url, headers=headers, timeout=10)
+    response = requests.get(ghost_url, headers=headers, timeout=10)
     if response.status_code != 200:
         return {"error": "Error fetching post"}
     ghost_post = response.json().get("posts")[0]
@@ -67,7 +68,7 @@ def update_ghost_post_via_api(
     ghost_url = f"{api_url}/ghost/api/admin/posts/{guid}/"
 
     json = {"posts": [{"canonical_url": doi, "updated_at": updated_at}]}
-    response = httpx.put(
+    response = requests.put(
         ghost_url,
         headers=headers,
         json=json,

commonmeta/author_utils.py

@@ -2,23 +2,23 @@
 
 import re
 from typing import List
+
+from furl import furl
 from nameparser import HumanName
 from pydash import py_
-from furl import furl
 
+from .base_utils import compact, parse_attributes, presence, wrap
+from .constants import (
+    COMMONMETA_CONTRIBUTOR_ROLES,
+)
 from .utils import (
-    normalize_orcid,
+    format_name_identifier,
     normalize_id,
-    normalize_ror,
     normalize_isni,
-    format_name_identifier,
-    validate_ror,
+    normalize_orcid,
+    normalize_ror,
     validate_orcid,
-)
-from .base_utils import parse_attributes, wrap, presence, compact
-
-from .constants import (
-    COMMONMETA_CONTRIBUTOR_ROLES,
+    validate_ror,
 )
 
 

commonmeta/base_utils.py

@@ -1,11 +1,12 @@
 """Base utilities for commonmeta-py"""
 
 import html
-from os import path
 import re
-import xmltodict
+from os import path
 from typing import Optional, Union
+
 import nh3
+import xmltodict
 
 
 def wrap(item) -> list:

commonmeta/crossref_utils.py

@@ -231,7 +231,6 @@ def insert_citation_list(metadata, xml):
 
     citation_list = etree.SubElement(xml, "citation_list")
     for i, ref in enumerate(metadata.references):
-        print(i)
         if ref.get("id", None) is None:
             continue
         citation = etree.SubElement(
@@ -581,3 +580,83 @@ def generate_crossref_xml_list(metalist) -> Optional[str]:
         doctype='<?xml version="1.0" encoding="UTF-8"?>',
         pretty_print=True,
     )
+
+
+"""Errors for the Crossref XML API.
+
+Error responses will be converted into an exception from this module.
+"""
+
+
+class HttpError(Exception):
+    """Exception raised when a connection problem happens."""
+
+
+class CrossrefError(Exception):
+    """Exception raised when the server returns a known HTTP error code.
+
+    Known HTTP error codes include:
+
+    * 204 No Content
+    * 400 Bad Request
+    * 401 Unauthorized
+    * 403 Forbidden
+    * 404 Not Found
+    * 410 Gone (deleted)
+    """
+
+    @staticmethod
+    def factory(err_code, *args):
+        """Create exceptions through a Factory based on the HTTP error code."""
+        if err_code == 204:
+            return CrossrefNoContentError(*args)
+        elif err_code == 400:
+            return CrossrefBadRequestError(*args)
+        elif err_code == 401:
+            return CrossrefUnauthorizedError(*args)
+        elif err_code == 403:
+            return CrossrefForbiddenError(*args)
+        elif err_code == 404:
+            return CrossrefNotFoundError(*args)
+        else:
+            return CrossrefServerError(*args)
+
+
+class CrossrefServerError(CrossrefError):
+    """An internal server error happened on the Crossref end. Try later.
+
+    Base class for all 5XX-related HTTP error codes.
+    """
+
+
+class CrossrefRequestError(CrossrefError):
+    """A Crossref request error. You made an invalid request.
+
+    Base class for all 4XX-related HTTP error codes as well as 204.
+    """
+
+
+class CrossrefNoContentError(CrossrefRequestError):
+    """DOI is known to Crossref, but not resolvable.
+
+    This might be due to handle's latency.
+    """
+
+
+class CrossrefBadRequestError(CrossrefRequestError):
+    """Bad request error.
+
+    Bad requests can include e.g. invalid XML, wrong domain, wrong prefix.
+    """
+
+
+class CrossrefUnauthorizedError(CrossrefRequestError):
+    """Bad username or password."""
+
+
+class CrossrefForbiddenError(CrossrefRequestError):
+    """Login problem, record belongs to another party or quota exceeded."""
+
+
+class CrossrefNotFoundError(CrossrefRequestError):
+    """DOI does not exist in the database."""

commonmeta/date_utils.py

@@ -3,10 +3,11 @@
 import datetime
 from datetime import datetime as dt
 from typing import Optional, Union
+
 import dateparser
-from edtf import parse_edtf, DateAndTime, Date
-from edtf.parser.edtf_exceptions import EDTFParseException
 import pydash as py_
+from edtf import Date, DateAndTime, parse_edtf
+from edtf.parser.edtf_exceptions import EDTFParseException
 
 from .base_utils import compact
 

commonmeta/doi_utils.py

@@ -4,7 +4,7 @@ import re
 from typing import Optional
 
 import base32_lib as base32
-import httpx
+import requests
 from furl import furl
 
 from .base_utils import compact
@@ -94,7 +94,7 @@ def short_doi_as_doi(doi: Optional[str]) -> Optional[str]:
     doi_url = doi_as_url(doi)
     if doi_url is None:
         return None
-    response = httpx.head(doi_url, timeout=10)
+    response = requests.head(doi_url, timeout=10)
     if response.status_code != 301:
         return doi_url
     return response.headers.get("Location")
@@ -137,7 +137,7 @@ def get_doi_ra(doi) -> Optional[str]:
     prefix = validate_prefix(doi)
     if prefix is None:
         return None
-    response = httpx.get("https://doi.org/ra/" + prefix, timeout=10)
+    response = requests.get("https://doi.org/ra/" + prefix, timeout=10)
     if response.status_code != 200:
         return None
     return response.json()[0].get("RA", None)
@@ -170,7 +170,7 @@ def decode_doi(doi: str, checksum: bool = True) -> int:
 
 def get_crossref_member(member_id) -> Optional[dict]:
     """Return the Crossref member for a given member_id"""
-    response = httpx.get("https://api.crossref.org/members/" + member_id, timeout=10)
+    response = requests.get("https://api.crossref.org/members/" + member_id, timeout=10)
     if response.status_code != 200:
         return None
     data = response.json().get("message", None)

commonmeta/readers/cff_reader.py

@@ -2,26 +2,27 @@
 
 from typing import Optional
 from urllib.parse import urlparse
-import httpx
+
+import requests
 import yaml
 
+from ..base_utils import compact, parse_attributes, presence, sanitize, wrap
+from ..constants import Commonmeta
+from ..date_utils import get_iso8601_date
 from ..utils import (
-    normalize_id,
-    name_to_fos,
     dict_to_spdx,
-    normalize_orcid,
     github_as_cff_url,
     github_as_repo_url,
+    name_to_fos,
+    normalize_id,
+    normalize_orcid,
 )
-from ..base_utils import compact, wrap, presence, sanitize, parse_attributes
-from ..date_utils import get_iso8601_date
-from ..constants import Commonmeta
 
 
 def get_cff(pid: str, **kwargs) -> dict:
     """get_cff"""
     url = github_as_cff_url(pid)
-    response = httpx.get(url, timeout=10, **kwargs)
+    response = requests.get(url, timeout=10, **kwargs)
     if response.status_code != 200:
         return {"state": "not_found"}
     text = response.text

commonmeta/readers/codemeta_reader.py

@@ -1,30 +1,31 @@
 """codemeta reader for commonmeta-py"""
 
-from typing import Optional
 from collections import defaultdict
-import httpx
+from typing import Optional
+
+import requests
 
+from ..author_utils import get_authors
+from ..base_utils import compact, presence, sanitize, wrap
+from ..constants import (
+    SO_TO_CM_TRANSLATIONS,
+    Commonmeta,
+)
 from ..utils import (
-    normalize_id,
-    from_schema_org_creators,
-    name_to_fos,
     dict_to_spdx,
+    doi_from_url,
+    from_schema_org_creators,
     github_as_codemeta_url,
     github_as_repo_url,
-    doi_from_url,
-)
-from ..base_utils import wrap, presence, compact, sanitize
-from ..author_utils import get_authors
-from ..constants import (
-    Commonmeta,
-    SO_TO_CM_TRANSLATIONS,
+    name_to_fos,
+    normalize_id,
 )
 
 
 def get_codemeta(pid: str, **kwargs) -> dict:
     """get_codemeta"""
     url = str(github_as_codemeta_url(pid))
-    response = httpx.get(url, timeout=10, **kwargs)
+    response = requests.get(url, timeout=10, **kwargs)
     if response.status_code != 200:
         return {"state": "not_found"}
     data = response.json()

commonmeta/readers/crossref_reader.py

@@ -2,8 +2,9 @@
 
 from typing import Optional
 
-import httpx
+import requests
 from pydash import py_
+from requests.exceptions import ConnectionError, ReadTimeout
 
 from ..author_utils import get_authors
 from ..base_utils import compact, parse_attributes, presence, sanitize, wrap
@@ -34,7 +35,7 @@ from ..utils import (
 def get_crossref_list(query: dict, **kwargs) -> list[dict]:
     """get_crossref list from Crossref API."""
     url = crossref_api_query_url(query, **kwargs)
-    response = httpx.get(url, timeout=30, **kwargs)
+    response = requests.get(url, timeout=30, **kwargs)
     if response.status_code != 200:
         return []
     return response.json().get("message", {}).get("items", [])
@@ -46,7 +47,7 @@ def get_crossref(pid: str, **kwargs) -> dict:
     if doi is None:
         return {"state": "not_found"}
     url = crossref_api_url(doi)
-    response = httpx.get(url, timeout=10, **kwargs)
+    response = requests.get(url, timeout=10, **kwargs)
     if response.status_code != 200:
         return {"state": "not_found"}
     return response.json().get("message", {}) | {"via": "crossref"}
@@ -402,11 +403,11 @@ def get_random_crossref_id(number: int = 1, **kwargs) -> list:
     number = 20 if number > 20 else number
     url = crossref_api_sample_url(number, **kwargs)
     try:
-        response = httpx.get(url, timeout=10)
+        response = requests.get(url, timeout=10)
         if response.status_code != 200:
             return []
 
         items = py_.get(response.json(), "message.items")
         return [i.get("DOI") for i in items]
-    except (httpx.ReadTimeout, httpx.ConnectError):
+    except (ReadTimeout, ConnectionError):
         return []

commonmeta/readers/crossref_xml_reader.py

@@ -1,34 +1,35 @@
 """crossref_xml reader for commonmeta-py"""
 
-from typing import Optional
 from collections import defaultdict
-import httpx
+from typing import Optional
+
+import requests
 from pydash import py_
 
-from ..utils import (
-    doi_from_url,
-    dict_to_spdx,
-    from_crossref_xml,
-    normalize_cc_url,
-    normalize_issn,
-    normalize_url,
-)
+from ..author_utils import get_authors
 from ..base_utils import (
     compact,
-    wrap,
-    presence,
-    sanitize,
     parse_attributes,
     parse_xml,
+    presence,
+    sanitize,
+    wrap,
 )
-from ..author_utils import get_authors
-from ..date_utils import get_date_from_crossref_parts, get_iso8601_date
-from ..doi_utils import get_doi_ra, crossref_xml_api_url, normalize_doi
 from ..constants import (
-    Commonmeta,
+    CR_TO_CM_CONTAINER_TRANSLATIONS,
     CR_TO_CM_TRANSLATIONS,
     CROSSREF_CONTAINER_TYPES,
-    CR_TO_CM_CONTAINER_TRANSLATIONS,
+    Commonmeta,
+)
+from ..date_utils import get_date_from_crossref_parts, get_iso8601_date
+from ..doi_utils import crossref_xml_api_url, get_doi_ra, normalize_doi
+from ..utils import (
+    dict_to_spdx,
+    doi_from_url,
+    from_crossref_xml,
+    normalize_cc_url,
+    normalize_issn,
+    normalize_url,
 )
 
 
@@ -38,7 +39,7 @@ def get_crossref_xml(pid: str, **kwargs) -> dict:
     if doi is None:
         return {"state": "not_found"}
     url = crossref_xml_api_url(doi)
-    response = httpx.get(
+    response = requests.get(
         url, headers={"Accept": "text/xml;charset=utf-8"}, timeout=10, **kwargs
     )
     if response.status_code != 200:

commonmeta/readers/datacite_reader.py

@@ -3,8 +3,9 @@
 from collections import defaultdict
 from typing import Optional
 
-import httpx
+import requests
 from pydash import py_
+from requests.exceptions import ReadTimeout
 
 from ..author_utils import get_authors
 from ..base_utils import compact, presence, wrap
@@ -36,11 +37,11 @@ def get_datacite(pid: str, **kwargs) -> dict:
         return {"state": "not_found"}
     url = datacite_api_url(doi)
     try:
-        response = httpx.get(url, timeout=10, **kwargs)
+        response = requests.get(url, timeout=10, **kwargs)
         if response.status_code != 200:
             return {"state": "not_found"}
         return py_.get(response.json(), "data.attributes", {}) | {"via": "datacite"}
-    except httpx.ReadTimeout:
+    except ReadTimeout:
         return {"state": "timeout"}
 
 
@@ -381,11 +382,11 @@ def get_random_datacite_id(number: int = 1) -> list:
     number = 20 if number > 20 else number
     url = datacite_api_sample_url(number)
     try:
-        response = httpx.get(url, timeout=60)
+        response = requests.get(url, timeout=60)
         if response.status_code != 200:
             return []
 
         items = py_.get(response.json(), "data")
         return [i.get("id") for i in items]
-    except httpx.ReadTimeout:
+    except ReadTimeout:
         return []

commonmeta/readers/datacite_xml_reader.py

@@ -1,15 +1,16 @@
 """datacite_xml reader for Commonmeta"""
 
 from collections import defaultdict
-import httpx
+
+import requests
 from pydash import py_
 
-from ..base_utils import compact, wrap, presence, sanitize, parse_attributes
 from ..author_utils import get_authors
-from ..date_utils import strip_milliseconds, normalize_date_dict
-from ..doi_utils import doi_from_url, doi_as_url, datacite_api_url, normalize_doi
-from ..utils import normalize_url, normalize_cc_url, dict_to_spdx
+from ..base_utils import compact, parse_attributes, presence, sanitize, wrap
 from ..constants import DC_TO_CM_TRANSLATIONS, Commonmeta
+from ..date_utils import normalize_date_dict, strip_milliseconds
+from ..doi_utils import datacite_api_url, doi_as_url, doi_from_url, normalize_doi
+from ..utils import dict_to_spdx, normalize_cc_url, normalize_url
 
 
 def get_datacite_xml(pid: str, **kwargs) -> dict:
@@ -18,7 +19,7 @@ def get_datacite_xml(pid: str, **kwargs) -> dict:
     if doi is None:
         return {"state": "not_found"}
     url = datacite_api_url(doi)
-    response = httpx.get(url, timeout=10, **kwargs)
+    response = requests.get(url, timeout=10, **kwargs)
     if response.status_code != 200:
         return {"state": "not_found"}
     return py_.get(response.json(), "data.attributes", {}) | {"via": "datacite_xml"}

commonmeta/readers/inveniordm_reader.py

@@ -1,27 +1,27 @@
 """InvenioRDM reader for Commonmeta"""
 
-import httpx
-from pydash import py_
+import requests
 from furl import furl
+from pydash import py_
 
+from ..author_utils import get_authors
+from ..base_utils import compact, presence, sanitize, wrap
+from ..constants import (
+    COMMONMETA_RELATION_TYPES,
+    INVENIORDM_TO_CM_TRANSLATIONS,
+    Commonmeta,
+)
+from ..date_utils import strip_milliseconds
+from ..doi_utils import doi_as_url, doi_from_url
 from ..utils import (
-    normalize_url,
-    normalize_doi,
     dict_to_spdx,
-    name_to_fos,
     from_inveniordm,
     get_language,
+    name_to_fos,
+    normalize_doi,
+    normalize_url,
     validate_ror,
 )
-from ..base_utils import compact, wrap, presence, sanitize
-from ..author_utils import get_authors
-from ..date_utils import strip_milliseconds
-from ..doi_utils import doi_as_url, doi_from_url
-from ..constants import (
-    INVENIORDM_TO_CM_TRANSLATIONS,
-    COMMONMETA_RELATION_TYPES,
-    Commonmeta,
-)
 
 
 def get_inveniordm(pid: str, **kwargs) -> dict:
@@ -29,7 +29,7 @@ def get_inveniordm(pid: str, **kwargs) -> dict:
     if pid is None:
         return {"state": "not_found"}
     url = normalize_url(pid)
-    response = httpx.get(url, timeout=10, follow_redirects=True, **kwargs)
+    response = requests.get(url, timeout=10, allow_redirects=True, **kwargs)
     if response.status_code != 200:
         return {"state": "not_found"}
     return response.json()
@@ -63,7 +63,6 @@ def read_inveniordm(data: dict, **kwargs) -> Commonmeta:
 
     title = py_.get(meta, "metadata.title")
     titles = [{"title": sanitize(title)}] if title else None
-    additional_titles = py_.get(meta, "metadata.additional_titles")
     # if additional_titles:
     #     titles += [{"title": sanitize("bla")} for i in wrap(additional_titles)]
 

commonmeta/readers/json_feed_reader.py

@@ -1,33 +1,34 @@
 """JSON Feed reader for commonmeta-py"""
 
 from typing import Optional
-import httpx
-from pydash import py_
+
+import requests
 from furl import furl
+from pydash import py_
 
+from ..author_utils import get_authors
+from ..base_utils import parse_attributes, presence, sanitize
+from ..constants import Commonmeta
+from ..date_utils import get_date_from_unix_timestamp
+from ..doi_utils import (
+    doi_from_url,
+    encode_doi,
+    is_rogue_scholar_doi,
+    normalize_doi,
+    validate_doi,
+    validate_prefix,
+)
 from ..utils import (
     compact,
-    normalize_url,
-    from_json_feed,
-    wrap,
     dict_to_spdx,
+    from_json_feed,
+    issn_as_url,
     name_to_fos,
+    normalize_url,
     validate_ror,
     validate_url,
-    issn_as_url,
-)
-from ..author_utils import get_authors
-from ..base_utils import presence, sanitize, parse_attributes
-from ..date_utils import get_date_from_unix_timestamp
-from ..doi_utils import (
-    normalize_doi,
-    validate_prefix,
-    validate_doi,
-    doi_from_url,
-    is_rogue_scholar_doi,
-    encode_doi,
+    wrap,
 )
-from ..constants import Commonmeta
 
 
 def get_json_feed_item(pid: str, **kwargs) -> dict:
@@ -35,7 +36,7 @@ def get_json_feed_item(pid: str, **kwargs) -> dict:
     if pid is None:
         return {"state": "not_found"}
     url = normalize_url(pid)
-    response = httpx.get(url, timeout=10, follow_redirects=True, **kwargs)
+    response = requests.get(url, timeout=10, allow_redirects=True, **kwargs)
     if response.status_code != 200:
         return {"state": "not_found"}
     return response.json() | {"via": "json_feed_item"}
@@ -255,7 +256,9 @@ def get_funding_references(meta: Optional[dict]) -> Optional[list]:
         elif len(urls) == 2 and validate_ror(urls[0]):
             f = furl(urls[0])
             _id = f.path.segments[-1]
-            response = httpx.get(f"https://api.ror.org/organizations/{_id}", timeout=10)
+            response = requests.get(
+                f"https://api.ror.org/organizations/{_id}", timeout=10
+            )
             ror = response.json()
             funder_name = ror.get("name", None)
             funder_identifier = urls[0]
@@ -398,7 +401,7 @@ def get_json_feed_item_uuid(id: str):
     if id is None:
         return None
     url = f"https://api.rogue-scholar.org/posts/{id}"
-    response = httpx.get(url, timeout=10)
+    response = requests.get(url, timeout=10)
     if response.status_code != 200:
         return response.json()
     post = response.json()
@@ -426,7 +429,7 @@ def get_json_feed_blog_slug(id: str):
     if id is None:
         return None
     url = f"https://api.rogue-scholar.org/posts/{id}"
-    response = httpx.get(url, timeout=10)
+    response = requests.get(url, timeout=10)
     if response.status_code != 200:
         return response.json()
     post = response.json()