commonmeta-py 0.62__py3-none-any.whl → 0.65__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__ = "0.62"
+__version__ = "0.65"
 __author__ = "Martin Fenner"
 __license__ = "MIT"
 
@@ -94,4 +94,5 @@ from .doi_utils import (
     normalize_doi,
     validate_doi,
     validate_prefix,
+    is_rogue_scholar_doi,
 )

commonmeta/constants.py

@@ -408,11 +408,32 @@ SO_TO_CM_TRANSLATIONS = {
     "DigitalDocument": "Document",
     "Dissertation": "Dissertation",
     "Instrument": "Instrument",
+    "MusicRecording": "Audiovisual",
+    "MusicAlbum": "Audiovisual",
     "NewsArticle": "Article",
     "Legislation": "LegalDocument",
+    "ProfilePage": "WebPage",
     "Report": "Report",
     "ScholarlyArticle": "JournalArticle",
     "SoftwareSourceCode": "Software",
+    "Video": "Audiovisual",
+    "WebSite": "WebPage",
+}
+
+# OpenGraph to schema.org mapping
+OG_TO_SO_TRANSLATIONS = {
+    "music.song": "MusicRecording",
+    "music.album": "MusicAlbum",
+    "music.playlist": "MusicPlaylist",
+    "music.radio_station": "RadioStation",
+    "video.movie": "Video",
+    "video.episode": "Video",
+    "video.tv_show": "Video",
+    "video.other": "Video",
+    "article": "Article",
+    "book": "Book",
+    "profile": "ProfilePage",
+    "website": "WebSite",
 }
 
 CM_TO_SO_TRANSLATIONS = {

commonmeta/readers/schema_org_reader.py

@@ -36,6 +36,7 @@ from ..constants import (
     SO_TO_CM_TRANSLATIONS,
     SO_TO_DC_RELATION_TYPES,
     SO_TO_DC_REVERSE_RELATION_TYPES,
+    OG_TO_SO_TRANSLATIONS,
     Commonmeta,
 )
 
@@ -59,7 +60,6 @@ def get_schema_org(pid: str, **kwargs) -> dict:
             "via": "schema_org",
             "errors": [str(error)],
         }
-
     if response.status_code >= 400:
         if response.status_code in [404, 410]:
             state = "not_found"
@@ -105,7 +105,7 @@ def get_schema_org(pid: str, **kwargs) -> dict:
 
     # load html meta tags
     data = get_html_meta(soup)
-
+    print(data)
     # load site-specific metadata
     data |= web_translator(soup, url)
 
@@ -119,6 +119,7 @@ def get_schema_org(pid: str, **kwargs) -> dict:
         None,
     )
     if json_ld is not None:
+        print(json_ld)
         data |= json_ld
 
     # if @id is a DOI, get metadata from Crossref or DataCite
@@ -136,7 +137,7 @@ def get_schema_org(pid: str, **kwargs) -> dict:
     # author and creator are synonyms
     if data.get("author", None) is None and data.get("creator", None) is not None:
         data["author"] = data["creator"]
-
+    print(data)
     return data | {"via": "schema_org", "state": "findable"}
 
 
@@ -412,11 +413,13 @@ def get_html_meta(soup):
         data["@id"] = normalize_id(pid)
 
     _type = (
-        soup.select_one("meta[property='og:type']")
-        or soup.select_one("meta[name='dc.type']")
+        soup.select_one("meta[name='dc.type']")
         or soup.select_one("meta[name='DC.type']")
     )
     data["@type"] = _type["content"].capitalize() if _type else None
+    if _type is None:
+        _type = soup.select_one("meta[property='og:type']")
+        data["@type"] = OG_TO_SO_TRANSLATIONS.get(_type["content"]) if _type else None
 
     url = soup.select_one("meta[property='og:url']") or soup.select_one(
         "meta[name='twitter:url']"
@@ -431,6 +434,7 @@ def get_html_meta(soup):
         or soup.select_one("meta[name='DC.title']")
         or soup.select_one("meta[property='og:title']")
         or soup.select_one("meta[name='twitter:title']")
+        or soup.select_one("meta[name='title']")
     )
     data["name"] = title["content"] if title else None
 
@@ -441,6 +445,7 @@ def get_html_meta(soup):
         "meta[name='dc.description']"
         or soup.select_one("meta[property='og:description']")
         or soup.select_one("meta[name='twitter:description']")
+        or soup.select_one("meta[name='description']")
     )
     data["description"] = description["content"] if description else None
 

commonmeta/utils.py

@@ -1096,22 +1096,48 @@ def from_curie(id: Optional[str]) -> Optional[str]:
     if id is None:
         return None
     _type = id.split(":")[0]
-    if _type == "DOI":
+    if _type.upper() == "DOI":
         return doi_as_url(id.split(":")[1])
-    elif _type == "ROR":
+    elif _type.upper() == "ROR":
         return "https://ror.org/" + id.split(":")[1]
-    elif _type == "ISNI":
+    elif _type.upper() == "ISNI":
         return "https://isni.org/isni/" + id.split(":")[1]
-    elif _type == "ORCID":
+    elif _type.upper() == "ORCID":
         return normalize_orcid(id.split(":")[1])
-    elif _type == "URL":
+    elif _type.upper() == "URL":
         return normalize_url(id.split(":")[1])
-    elif _type == "JDP":
+    elif _type.upper() == "JDP":
         return id.split(":")[1]
     # TODO: resolvable url for other identifier types
     return None
 
 
+def extract_curie(string: Optional[str]) -> Optional[str]:
+    """Extract CURIE"""
+    if string is None:
+        return None
+    match = re.search(r"((?:doi|DOI):\s?([\w.,@?^=%&:\/~+#-]*[\w@?^=%&\/~+#-]))", string)
+    if match is None:
+        return None
+    return doi_as_url(match.group(2))
+
+    
+def extract_url(string: str) -> list:
+    """Extract urls from string, including markdown and html."""
+
+    match = re.search(r"((?:http|https):\/\/(?:[\w_-]+(?:(?:\.[\w_-]+)+))(?:[\w.,@?^=%&:\/~+#-]*[\w@?^=%&\/~+#-]))", string)
+    if match is None:
+        return None
+    return normalize_url(match.group(1))
+
+
+def extract_urls(string: str) -> list:
+    """Extract urls from string, including markdown and html."""
+
+    urls = re.findall(r"((?:http|https):\/\/(?:[\w_-]+(?:(?:\.[\w_-]+)+))(?:[\w.,@?^=%&:\/~+#-]*[\w@?^=%&\/~+#-]))", string)
+    return py_.uniq(urls)
+
+
 def issn_as_url(issn: str) -> Optional[str]:
     """ISSN as URL"""
     if normalize_issn(issn) is None:

commonmeta/writers/inveniordm_writer.py

@@ -257,7 +257,8 @@ def to_inveniordm_reference(reference: dict) -> dict:
         identifier = reference.get("id", None)
         scheme = "url"
     else:
-        return None
+        identifier = None
+        scheme = None
 
     if reference.get("unstructured", None) is None:
         # use title as unstructured reference

{commonmeta_py-0.62.dist-info → commonmeta_py-0.65.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: commonmeta-py
-Version: 0.62
+Version: 0.65
 Summary: Library for conversions to/from the Commonmeta scholarly metadata format
 Home-page: https://python.commonmeta.org
 License: MIT

{commonmeta_py-0.62.dist-info → commonmeta_py-0.65.dist-info}/RECORD

@@ -1,9 +1,9 @@
-commonmeta/__init__.py,sha256=t2QRGjR73eSP55rlkljDk1Rckce3LCX8TSKrmZzNbh4,1795
+commonmeta/__init__.py,sha256=LqrBGNgQuAGQiRF9HrhX5iHHu14t44M7nTTOYmg4Rmc,1821
 commonmeta/api_utils.py,sha256=-ZHGVZZhJqnjnsLtp4-PoeHYbDqL0cQme7W70BEjo4U,2677
 commonmeta/author_utils.py,sha256=zBIPTgP5n7Zx57xomJ2h7x0dvC0AV8gJ2gPoYeDy5Lo,8348
 commonmeta/base_utils.py,sha256=AsUElA5kT2fw_Osy7Uaj2F6MKeq9yB7d5f2V-h2lh7c,3750
 commonmeta/cli.py,sha256=sOI9BJTePnljVcXcZ95N7TKXDT283XpjUaak7bMnbr0,6076
-commonmeta/constants.py,sha256=VfjXLkwoV4A5uztH3vgDJ_qrt7PaWGO6QtHbAt4r03c,17501
+commonmeta/constants.py,sha256=AFm8gSo4WGnTdJOm1SOGLK602BctcQbaWU_tKCkgn_4,18087
 commonmeta/crossref_utils.py,sha256=qJlTZtfKR2shAXQDm8VBYUujKFkTtZTUz19GuMUANaI,22198
 commonmeta/date_utils.py,sha256=rJRV4YmWKQWU__iAV8www3cqwaefC0iRKyHwvxrr_XY,6316
 commonmeta/doi_utils.py,sha256=xlYQq-qkqhz07CLKpL_WfxZBT8maXgB9-TvQHlL2ZoY,9266
@@ -22,7 +22,7 @@ commonmeta/readers/inveniordm_reader.py,sha256=jzv0rXzT8OCdPD_MShBXTnlwD-F9tpTX7
 commonmeta/readers/json_feed_reader.py,sha256=ctlASyxByjXDVgREzdeYOCZezn9aFFv3yKogDFd8WNs,14174
 commonmeta/readers/kbase_reader.py,sha256=ehKXQsJyPCtaq2FmBxNb2Jb5Nktpx8pNscpmEM6N0A4,6763
 commonmeta/readers/ris_reader.py,sha256=v6qOd-i2OcMTEFy5RGd3MlYthJcYSU6yzmZ5yHDzmII,3677
-commonmeta/readers/schema_org_reader.py,sha256=xyWzO2XAWlI2pYVl2EbVRsUmfiWXEwP64CHRBQNRN-M,16835
+commonmeta/readers/schema_org_reader.py,sha256=udvRBeEnsyRmy5UOIk523f7x08RRLvxqTCMMS736oFs,17132
 commonmeta/resources/cff_v1.2.0.json,sha256=MpfjDYgX7fN9PLiG54ISZ2uu9WItNqfh-yaRuTf6Ptg,46691
 commonmeta/resources/commonmeta_v0.12.json,sha256=HUSNReXh2JN3Q6YWSt7CE69js8dh50OlpMYGTyU98oU,16762
 commonmeta/resources/commonmeta_v0.13.json,sha256=2-WSZGijR13zVu97S_YHXr-cyeLW7hzHXYMlr6nIjdw,15787
@@ -58,7 +58,7 @@ commonmeta/resources/styles/modern-language-association.csl,sha256=HI2iU4krze1aH
 commonmeta/resources/styles/vancouver.csl,sha256=lun3_i2oTilgsANk4LjFao2UDPQlGj_hgFgKAWC_DF8,12878
 commonmeta/schema_utils.py,sha256=gg3l1jd_lFtRkQlO1DYGMVbC10nEmVTN4AWacxC4AAE,915
 commonmeta/translators.py,sha256=RpGJtKNLjmz41VREZDY7KyyE2eXOi8j7m-da4jHmknI,1362
-commonmeta/utils.py,sha256=0ky8xyDQWVND5nJWApPgyVhbjXdPPzfpx4fJpX9ivyw,43674
+commonmeta/utils.py,sha256=lIH7VejIn_gReLsuXsAZxE-RiMCRGECA_6aPrhGsBFc,44596
 commonmeta/writers/__init__.py,sha256=47-snms6xBHkoEXKYV1DBtH1npAtlVtvY29Z4Zr45qI,45
 commonmeta/writers/bibtex_writer.py,sha256=s3hIJIgWvSG7TAriZMRQEAyuitw6ebwWSI1YcYFQ-do,4971
 commonmeta/writers/citation_writer.py,sha256=RjaNh9EALxq6gfODLRWVJxGxPArGd6ZiHUlkYnCT6MA,2355
@@ -66,11 +66,11 @@ commonmeta/writers/commonmeta_writer.py,sha256=2qlttCfYpGhfVjrYkjzbIra7AywssRLT3
 commonmeta/writers/crossref_xml_writer.py,sha256=0Ds494RnXfdfjWw5CLX1kwV2zP7gqffdVqO-X74Uc6c,492
 commonmeta/writers/csl_writer.py,sha256=6N-93R1emcOsZrUTIhPBVd_Fv1C8Z5EAFYI0mYjoYaY,2797
 commonmeta/writers/datacite_writer.py,sha256=G7Lr0aZ4sAEdbfXe3dG4Y6AyGUKA9UWr_iiaQRDnV24,6233
-commonmeta/writers/inveniordm_writer.py,sha256=oVcXdHYtuugbfDgKO8JwTRXmP7AK2U96uK4YF0eKXAY,11399
+commonmeta/writers/inveniordm_writer.py,sha256=YXLfiMkWDMMd7ZlOzhp0zNieQFfHKZ4m5FQLIl_XuWI,11427
 commonmeta/writers/ris_writer.py,sha256=AcnCszS3WY9lF594NbFBtLylsA8ownnYp_XLQJ84Ios,2093
 commonmeta/writers/schema_org_writer.py,sha256=5j002uCNLdlScZMNQmPjodcVWqaBh2z38zL1H4lo2hY,5741
-commonmeta_py-0.62.dist-info/LICENSE,sha256=746hEF2wZCKkcckk5-_DcBLtHewfaEMS4iXTlA1PVwk,1074
-commonmeta_py-0.62.dist-info/METADATA,sha256=3amCMEJUFi6F88HR4wPmrBww-8VL49HgBs0LamBOsqo,8279
-commonmeta_py-0.62.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
-commonmeta_py-0.62.dist-info/entry_points.txt,sha256=vbcDw3_2lMTKdcAL2VUF4DRYRpKuzXVYLMCdgKVf88U,49
-commonmeta_py-0.62.dist-info/RECORD,,
+commonmeta_py-0.65.dist-info/LICENSE,sha256=746hEF2wZCKkcckk5-_DcBLtHewfaEMS4iXTlA1PVwk,1074
+commonmeta_py-0.65.dist-info/METADATA,sha256=th0VmBY3Kk5evcQrUOk55lTyqjeZ6CEuXnvumG_Duvc,8279
+commonmeta_py-0.65.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
+commonmeta_py-0.65.dist-info/entry_points.txt,sha256=vbcDw3_2lMTKdcAL2VUF4DRYRpKuzXVYLMCdgKVf88U,49
+commonmeta_py-0.65.dist-info/RECORD,,