commonmeta-py 0.73__tar.gz → 0.75__tar.gz

{commonmeta_py-0.73 → commonmeta_py-0.75}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: commonmeta-py
-Version: 0.73
+Version: 0.75
 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

{commonmeta_py-0.73 → commonmeta_py-0.75}/commonmeta/__init__.py

@@ -10,7 +10,7 @@ commonmeta-py is a Python library to convert scholarly metadata
 """
 
 __title__ = "commonmeta-py"
-__version__ = "0.73"
+__version__ = "0.75"
 __author__ = "Martin Fenner"
 __license__ = "MIT"
 

{commonmeta_py-0.73 → commonmeta_py-0.75}/commonmeta/constants.py

@@ -51,6 +51,7 @@ BIB_TO_CM_TRANSLATIONS = {
 
 CM_TO_BIB_TRANSLATIONS = {
     "Article": "article",
+    "BlogPost": "article",
     "Book": "book",
     "BookChapter": "inbook",
     "Dissertation": "phdthesis",
@@ -97,7 +98,7 @@ CSL_TO_CM_TRANSLATIONS = {
     "periodical": "Journal",
     "personal_communication": "PersonalCommunication",
     "post": "Post",
-    "post-weblog": "Article",
+    "post-weblog": "BlogPost",
     "regulation": "LegalDocument",
     "report": "Report",
     "review": "Review",
@@ -113,7 +114,7 @@ CSL_TO_CM_TRANSLATIONS = {
 
 CM_TO_CSL_TRANSLATIONS = {
     "Article": "article",
-    "JournalArticle": "article-journal",
+    "BlogPost": "post-weblog",
     "Book": "book",
     "BookChapter": "chapter",
     "Collection": "collection",
@@ -123,6 +124,7 @@ CM_TO_CSL_TRANSLATIONS = {
     "Event": "event",
     "Figure": "figure",
     "Image": "graphic",
+    "JournalArticle": "article-journal",
     "LegalDocument": "legal_case",
     "Manuscript": "manuscript",
     "Map": "map",
@@ -176,6 +178,7 @@ CR_TO_CM_TRANSLATIONS = {
 
 CM_TO_CR_TRANSLATIONS = {
     "Article": "PostedContent",
+    "BlogPost": "PostedContent",
     "BookChapter": "BookChapter",
     "BookSeries": "BookSeries",
     "Book": "Book",
@@ -200,7 +203,7 @@ CM_TO_CR_TRANSLATIONS = {
 # source: https://github.com/datacite/schema/blob/master/source/meta/kernel-4/include/datacite-resourceType-v4.xsd
 DC_TO_CM_TRANSLATIONS = {
     "Audiovisual": "Audiovisual",
-    "BlogPosting": "Article",
+    "BlogPosting": "BlogPost",
     "Book": "Book",
     "BookChapter": "BookChapter",
     "Collection": "Collection",
@@ -269,6 +272,7 @@ INVENIORDM_TO_CM_TRANSLATIONS = {
 
 CM_TO_INVENIORDM_TRANSLATIONS = {
     "Article": "publication-preprint",
+    "BlogPost": "publication-preprint",
     "Book": "book",
     "Dataset": "dataset",
     "Image": "image-other",
@@ -281,6 +285,7 @@ CM_TO_INVENIORDM_TRANSLATIONS = {
 CM_TO_DC_TRANSLATIONS = {
     "Article": "Preprint",
     "Audiovisual": "Audiovisual",
+    "BlogPost": "Preprint",
     "Book": "Book",
     "BookChapter": "BookChapter",
     "Collection": "Collection",
@@ -317,7 +322,7 @@ RIS_TO_CM_TRANSLATIONS = {
     "ANCIENT": "Text",
     "ART": "Text",
     "BILL": "Text",
-    "BLOG": "Text",
+    "BLOG": "BlogPost",
     "BOOK": "Book",
     "CASE": "Text",
     "CHAP": "BookChapter",
@@ -370,6 +375,7 @@ RIS_TO_CM_TRANSLATIONS = {
 CM_TO_RIS_TRANSLATIONS = {
     "Article": "JOUR",
     "Audiovisual": "VIDEO",
+    "BlogPost": "BLOG",
     "Book": "BOOK",
     "BookChapter": "CHAP",
     "Collection": "CTLG",
@@ -400,7 +406,7 @@ CM_TO_RIS_TRANSLATIONS = {
 
 SO_TO_CM_TRANSLATIONS = {
     "Article": "Article",
-    "BlogPosting": "Article",
+    "BlogPosting": "BlogPost",
     "Book": "Book",
     "BookChapter": "BookChapter",
     "CreativeWork": "Other",
@@ -439,6 +445,7 @@ OG_TO_SO_TRANSLATIONS = {
 CM_TO_SO_TRANSLATIONS = {
     "Article": "Article",
     "Audiovisual": "CreativeWork",
+    "BlogPost": "BlogPosting",
     "Book": "Book",
     "BookChapter": "BookChapter",
     "Collection": "CreativeWork",

{commonmeta_py-0.73 → commonmeta_py-0.75}/commonmeta/crossref_utils.py

@@ -36,13 +36,13 @@ def generate_crossref_xml(metadata: Commonmeta) -> Optional[str]:
 
 def insert_crossref_work(metadata, xml):
     """Insert crossref work"""
-    if metadata.type not in ["JournalArticle", "Article"]:
+    if metadata.type not in ["JournalArticle", "Article", "BlogPost"]:
         return xml
     if doi_from_url(metadata.id) is None or metadata.url is None:
         return xml
     if metadata.type == "JournalArticle":
         xml = insert_journal(metadata, xml)
-    elif metadata.type == "Article":
+    elif metadata.type in ["Article", "BlogPost"]:
         xml = insert_posted_content(metadata, xml)
 
 

{commonmeta_py-0.73 → commonmeta_py-0.75}/commonmeta/readers/crossref_reader.py

@@ -83,7 +83,8 @@ def read_crossref(data: Optional[dict], **kwargs) -> Commonmeta:
     url = normalize_url(py_.get(meta, "resource.primary.URL"))
     titles = get_titles(meta)
     publisher = compact({"name": meta.get("publisher", None)})
-
+    if _type == "Article" and py_.get(publisher, "name") == "Front Matter":
+        _type = "BlogPost"
     date = compact(
         {
             "published": py_.get(meta, "issued.date-time")

{commonmeta_py-0.73 → commonmeta_py-0.75}/commonmeta/readers/crossref_xml_reader.py

@@ -158,6 +158,9 @@ def read_crossref_xml(data: dict, **kwargs) -> Commonmeta:
         or py_.get(bibmeta, "doi_data.doi")
     )
     _type = CR_TO_CM_TRANSLATIONS.get(resource_type, "Other")
+    if _type == "Article" and py_.get(publisher, "name") == "Front Matter":
+        _type = "BlogPost"
+
     url = parse_attributes(py_.get(bibmeta, "doi_data.resource"))
     url = normalize_url(url)
     titles = crossref_titles(bibmeta)

{commonmeta_py-0.73 → commonmeta_py-0.75}/commonmeta/readers/inveniordm_reader.py

@@ -57,6 +57,9 @@ def read_inveniordm(data: dict, **kwargs) -> Commonmeta:
     publisher = meta.get("publisher", None) or py_.get(meta, "metadata.publisher")
     if publisher:
         publisher = {"name": publisher}
+    if _type == "Article" and py_.get(publisher, "name") == "Front Matter":
+        _type = "BlogPost"
+
     title = py_.get(meta, "metadata.title")
     titles = [{"title": sanitize(title)}] if title else None
     additional_titles = py_.get(meta, "metadata.additional_titles")

{commonmeta_py-0.73 → commonmeta_py-0.75}/commonmeta/readers/json_feed_reader.py

@@ -54,7 +54,7 @@ def read_json_feed_item(data: Optional[dict], **kwargs) -> Commonmeta:
     ):
         url = normalize_url(meta.get("archive_url", None))
     _id = normalize_doi(read_options.get("doi", None) or meta.get("doi", None)) or url
-    _type = "Article"
+    _type = "BlogPost"
 
     # optionally generate a DOI if missing but a DOI prefix is provided
     prefix = read_options.get("prefix", None) or py_.get(meta, "blog.prefix", None)

{commonmeta_py-0.73 → commonmeta_py-0.75}/commonmeta/readers/schema_org_reader.py

@@ -216,7 +216,7 @@ def read_schema_org(data: Optional[dict], **kwargs) -> Commonmeta:
                 "lastPage": meta.get("pageEnd", None),
             }
         )
-    elif _type == "Article":
+    elif _type in ["Article", "BlogPost"]:
         issn = py_.get(meta, "isPartOf.issn")
         container_url = py_.get(meta, "publisher.url")
         container = compact(

{commonmeta_py-0.73 → commonmeta_py-0.75}/commonmeta/resources/commonmeta_v0.15.json

@@ -533,6 +533,7 @@
       "enum": [
         "Article",
         "Audiovisual",
+        "BlogPost",
         "BookChapter",
         "BookPart",
         "BookSection",

{commonmeta_py-0.73 → commonmeta_py-0.75}/commonmeta/utils.py

@@ -1116,16 +1116,33 @@ 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)
+    match = re.search(
+        r"((?:doi|DOI):\s?([\w.,@?^=%&:\/~+#-]*[\w@?^=%&\/~+#-]))", string
+    )
     if match is None:
         return None
     return doi_as_url(match.group(2))
 
-    
+
+def replace_curie(string: Optional[str]) -> Optional[str]:
+    """Replace CURIE with DOI expressed as URL"""
+    if string is None:
+        return None
+    match = re.sub(
+        r"((?:doi|DOI):\s?([\w.,@?^=%&:\/~+#-]*[\w@?^=%&\/~+#-]))", r'https://doi.org/\2', string
+    )
+    if match is None:
+        return None
+    return match
+
+
 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)
+    match = re.search(
+        r"((?:http|https):\/\/(?:[\w_-]+(?:(?:\.[\w_-]+)+))(?:[\w.,@?^=%&:\/~+#-]*[\w@?^=%&\/~+#-]))",
+        string,
+    )
     if match is None:
         return None
     return normalize_url(match.group(1))
@@ -1134,7 +1151,10 @@ def extract_url(string: str) -> list:
 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)
+    urls = re.findall(
+        r"((?:http|https):\/\/(?:[\w_-]+(?:(?:\.[\w_-]+)+))(?:[\w.,@?^=%&:\/~+#-]*[\w@?^=%&\/~+#-]))",
+        string,
+    )
     return py_.uniq(urls)
 
 

{commonmeta_py-0.73 → commonmeta_py-0.75}/commonmeta/writers/datacite_writer.py

@@ -47,6 +47,8 @@ def write_datacite(metadata: Commonmeta) -> Optional[Union[str, dict]]:
 
     resource__typegeneral = CM_TO_DC_TRANSLATIONS.get(metadata.type, "Other")
     resource_type = CM_TO_CR_TRANSLATIONS.get(metadata.type, "Other")
+    if metadata.type == "BlogPost":
+        resource_type = "BlogPost"
     if resource__typegeneral == resource_type or resource__typegeneral in [
         "Dataset",
         "JournalArticle",

{commonmeta_py-0.73 → commonmeta_py-0.75}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "commonmeta-py"
-version = "0.73"
+version = "0.75"
 description = "Library for conversions to/from the Commonmeta scholarly metadata format"
 authors = [{ name = "Martin Fenner", email = "martin@front-matter.io" }]
 requires-python = ">=3.9,<4.0"