def set_content(self, text):
metadata_dict = {}
package = find_or_empty_string(r"Package: (.*)", text)
title = find_or_empty_string(r"Title: (.*)", text)
self.source_preview["title"] = build_source_preview(
self.content_url, text, 'title', title)
metadata_dict["title"] = "{}: {}".format(package, title)
metadata_dict["author"] = self.find_authors(text)
if metadata_dict["author"] != "":
self.source_preview["author"] = build_author_source_preview(
self.content_url, text, 'author', metadata_dict["author"])
version = find_or_empty_string(r"Version: (.*)", text)
metadata_dict["note"] = "R package version {}".format(version)
metadata_dict["container-title"] = metadata_dict["note"]
published_date = find_or_empty_string(r"Date/Publication: (.*)", text)
if published_date:
year = published_date[0:4]
metadata_dict["year"] = year
metadata_dict["issued"] = {"date-parts": [[year]]}
self.source_preview["year"] = build_source_preview(
self.content_url, text, 'year', published_date)
metadata_dict["URL"] = "https://CRAN.R-project.org/package={}".format(
package)
metadata_dict["type"] = "Manual"
self.content = metadata_dict
def set_content_url(self, input):
# print "set_content_url", input
if input and "cran.r-project.org/web/packages" in input:
package_name = find_or_empty_string(
"cran.r-project.org/web/packages/(\w+\.?\w+)/?", input)
self.content_url = "https://cran.r-project.org/web/packages/{}".format(
package_name)
elif input and "cran.r-project.org/package=" in input.lower():
package_name = find_or_empty_string(
"cran.r-project.org/package=(.*)/?", input)
package_name = package_name.split("/")[0]
self.content_url = "https://cran.r-project.org/web/packages/{}".format(
package_name)
def set_content(self, input):
self.content = {}
input = strip_new_lines(input)
title = find_or_empty_string("<title.*?>(.+?)</title>", input)
if not title:
title = find_or_empty_string("<h1>(.+?)</h1>", input)
if not title:
title = find_or_empty_string("<h2>(.+?)</h2>", input)
self.content["type"] = "misc"
self.content["title"] = title.lstrip(" ").rstrip(" ")
self.content["URL"] = self.content_url
self.source_preview["title"] = build_source_preview(
self.content_url, input, 'title', title)
def extract_doi(self, text):
if text.startswith('https://zenodo.org/record/'):
text = get_webpage_text(text)
badge_doi = find_or_empty_string("://zenodo.org/badge/doi/(.+?).svg",
text)
if badge_doi:
return self.strip_junk_from_end_of_doi(badge_doi)
zenodo_doi = find_or_empty_string("10.5281/zenodo\.\d+", text)
if zenodo_doi:
return self.strip_junk_from_end_of_doi(zenodo_doi)
possible_dois = re.findall("10.\d{4,9}/[-._;()/:A-Z0-9+]+", text,
re.IGNORECASE | re.MULTILINE)
for doi in possible_dois:
if "10.5063/schema/codemeta-2.0" in doi.lower():
pass
else:
print("HERE I AM", doi)
return self.strip_junk_from_end_of_doi(doi)
def set_content(self, input):
if not "github.com" in input:
return
if input.startswith("http"):
url = "/".join(input.split("/", 5)[0:5])
else:
url = find_or_empty_string('\"(https?://github.com/.+?)\"', input)
url = url.replace("/issues", "")
url = url.replace("/new", "")
if 'sphinx' and 'theme' in url or url.endswith('.zip'):
url = None
if not url:
return
self.content = get_webpage_text(url)
self.content_url = url
def set_content(self, input):
if not "bitbucket.org" in input:
return
if input.startswith("http"):
url = "/".join(input.split("/", 5)[0:5])
url = url + '/src'
else:
url = find_or_empty_string(
'"(https?:\/\/bitbucket.org\/\w+\/\w+/?)"', input)
if not url:
return
else:
url = "/".join(url.split("/")[0:5])
url = url + '/src'
self.content = get_webpage_text(url)
self.content_url = url
def get_repo_api_url(github_url):
# remove /wiki
repo_api_url = github_url.replace("/wiki", "")
# strip trailing /
if repo_api_url.endswith("/"):
repo_api_url = repo_api_url[:-1]
# remove www
repo_api_url = repo_api_url.replace("http://www.", "http://")
repo_api_url = repo_api_url.replace("https://www.", "https://")
# switch to API URL
if "gist.github.com" in repo_api_url:
gist_id = find_or_empty_string("gist.github.com\/\w+\/(\w+|\d+)",
repo_api_url)
repo_api_url = "https://api.github.com/gists/{}".format(gist_id)
else:
repo_api_url = repo_api_url.replace("github.com/",
"api.github.com/repos/")
return repo_api_url
def find_authors_method_2(text):
# format 'Author: Krzysztof Byrski [aut, cre], Przemyslaw Spurek [ctb]'
authors = []
raw_authors = find_or_empty_string("Author: (.*)", text)
roles = re.findall("\[\w+,?\s?\w+\,?\s?\w+]", raw_authors)
if roles:
for role in roles:
raw_authors = raw_authors.replace(role, '')
names = raw_authors.split(',')
if roles:
for name, role in zip(names, roles):
if 'aut' in role or 'cre' in role:
name = name.split('<')[0].strip() # remove email addresses
authors.append(author_name_as_dict(name))
else:
for name in names:
name = name.split('<')[0].strip() # remove email addresses
authors.append(author_name_as_dict(name))
return authors
def set_content(self, input):
data = json5.loads(input)
if "citation" in data:
data = data["citation"]
if data:
code_meta_exists = True
self.content = {}
if data.get("id"):
self.content["doi"] = find_or_empty_string(
"zenodo\.org\/record\/(\d+)", data["id"])
elif data.get("identifier"):
self.content["doi"] = clean_doi(data["identifier"],
code_meta_exists)
else:
self.content["doi"] = None
if self.content["doi"]:
doi_url = "https://doi.org/{}".format(self.content["doi"])
self.content["URL"] = doi_url
else:
if "codeRepository" in data:
self.content["URL"] = data["codeRepository"]
self.content["repo"] = data["codeRepository"]
elif "url" in data:
self.content["URL"] = data["url"]
self.content["repo"] = data["url"]
if "name" in data:
self.content["title"] = data["name"]
if "title" in data:
self.content["title"] = data["title"]
self.content["author"] = []
if "author" in data:
if type(data["author"]) is dict:
author = data["author"]
self.content["author"].append(
author_name_as_dict('{} {}'.format(author["givenName"],
author["familyName"])))
elif type(data["author"]) is list:
authors = data["author"]
for author in authors:
try:
self.content["author"].append(
author_name_as_dict('{} {}'.format(
author["givenName"], author["familyName"])))
except UnicodeEncodeError:
continue
if "agents" in data:
if isinstance(data["agents"], dict):
agents = [data["agents"]]
else:
agents = data["agents"]
for agent in agents:
self.content["author"].append(
author_name_as_dict(data["agents"]["name"]))
if "dateCreated" in data:
self.content["issued"] = {
"date-parts": [[data["dateCreated"][0:4]]]
}
if "version" in data:
self.content["version"] = data["version"]
self.content["type"] = "software"
def strip_dependencies(readme_text):
readme_text = strip_new_lines(readme_text)
dependencies = find_or_empty_string('# Dependencies #(.+)#?.+#?',
readme_text)
readme_text = readme_text.replace(dependencies, '')
return readme_text
def set_content(self, citentry_content):
self.content = {}
self.content["title"] = find_or_empty_string("title\s*=\s*\"(.*?)\"",
citentry_content)
self.content["URL"] = find_or_empty_string("url\s*=\s*\"(.*?)\"",
citentry_content)
self.content["volume"] = find_or_empty_string("volume\s*=\s*\"(.*?)\"",
citentry_content)
self.content["number"] = find_or_empty_string("number\s*=\s*\"(.*?)\"",
citentry_content)
self.content["pages"] = find_or_empty_string("pages\s*=\s*\"(.*?)\"",
citentry_content)
self.content["publisher"] = find_or_empty_string(
"publisher\s*=\s*\"(.*?)\"", citentry_content)
self.content["isbn"] = find_or_empty_string("isbn\s*=\s*\"(.*?)\"",
citentry_content)
self.content["container-title"] = find_or_empty_string(
"journal\s*=\s*\"(.*?)\"", citentry_content)
self.content["year"] = find_or_empty_string("year\s*=\s*\"(.*?)\"",
citentry_content)
if self.content["year"]:
self.content["issued"] = {"date-parts": [[self.content["year"]]]}
self.content["type"] = find_or_empty_string("entry\s*=\s*\"(.*?)\"",
citentry_content)
self.content["author"] = []
first_author = find_or_empty_string("author\s*=.*?\"(.*?)\"",
citentry_content)
if first_author:
self.content["author"].append(author_name_as_dict(first_author))