def norm_author(record):
""" Transforms the author field into an ordered list of last names
Args:
record (Dict[str]): record containing an author field
Returns:
str: normalized author names
Examples:
>>> records = [{'author': 'Siegfried Fischbacher and Uwe Ludwig Horn'},
... {'author': 'Fischbacher, S. and Horn, U.'},
... {'author': 'Fischbacher, Siegfried and Horn, Uwe '
... 'Ludwig'}
... ]
>>> [norm_author(rec) for rec in records]
['Fischbacher Horn', 'Fischbacher Horn', 'Fischbacher Horn']
>>> norm_author({'author': 'François Augiéras'})
'Augieras'
>>> norm_author({'author': 'Avraham (Abraham), Uri and '
... 'Ihoda (Haim Judah), Jaime'})
'Avraham Ihoda'
"""
authors = record['author'].split(' and ')
authors = bc.getnames(authors) # Correct "Name, Surname"-format
authors = [a.split(',')[0] for a in authors]
authors = list(map(_norm_author, authors))
authors.sort()
return ' '.join(authors)
def test_getnames(self):
names = ['Foo Bar',
'Foo B. Bar',
'F. B. Bar',
'F.B. Bar',
'F. Bar',
'Jean de Savigny',
'Jean la Tour',
'Jean le Tour',
'Mike ben Akar',
#'Jean de la Tour',
#'Johannes Diderik van der Waals',
]
result = getnames(names)
expected = ['Bar, Foo',
'Bar, Foo B.',
'Bar, F. B.',
'Bar, F. B.',
'Bar, F.',
'de Savigny, Jean',
'la Tour, Jean',
'le Tour, Jean',
'ben Akar, Mike',
#'de la Tour, Jean',
#'van der Waals, Johannes Diderik',
]
self.assertEqual(result, expected)
def test_getnames(self):
names = [
'Foo Bar',
'Foo B. Bar',
'F. B. Bar',
'F.B. Bar',
'F. Bar',
'Jean de Savigny',
'Jean la Tour',
'Jean le Tour',
'Mike ben Akar',
#'Jean de la Tour',
#'Johannes Diderik van der Waals',
]
result = getnames(names)
expected = [
'Bar, Foo',
'Bar, Foo B.',
'Bar, F. B.',
'Bar, F. B.',
'Bar, F.',
'de Savigny, Jean',
'la Tour, Jean',
'le Tour, Jean',
'ben Akar, Mike',
#'de la Tour, Jean',
#'van der Waals, Johannes Diderik',
]
self.assertEqual(result, expected)
def customizations(record):
for n in ["author", "editor"]:
if n in record:
a = [i for i in record[n].replace("\n", " ").split(", ")]
b = [i.split(" and ") for i in a]
c = [item for sublist in b for item in sublist]
d = [i.strip() for i in c]
record[n] = getnames(d)
return record
def customizations(record):
for n in ['author', 'editor']:
if n in record:
a = [i for i in record[n].replace('\n', ' ').split(', ')]
b = [i.split(" and ") for i in a]
c = [item for sublist in b for item in sublist]
d = [i.strip() for i in c]
record[n] = getnames(d)
return record
def get_names(self):
"""
Get a list of names from the reference.
.. code-block:: python
>>> with open("bib/1968_chow.bib", "r") as fh:
... _citation = bibtexparser.load(fh)
>>> db = Reference(_citation)
>>> print(db.get_names())
['Friedman, Nir', 'Geiger, Dan', 'Goldszmidt, Moises']
"""
return getnames([
i.strip()
for i in self.db["author"].replace("\n", " ").split(" and ")
])
def editor(record):
"""
Split editor field into a list of "Name, Surname".
:param record: the record.
:type record: dict
"""
if "editor" in record:
if record["editor"]:
record["editor"] = customization.getnames([
i.strip()
for i in record["editor"].replace("\n", " ").split(" and ")
])
else:
del record["editor"]
return record
def btex_custom(self, record):
r = convert_to_unicode(record)
if "pages" in record: # fix -- -> –
if "-" in record["pages"]:
p = [i.strip().strip('-') for i in record["pages"].split("-")]
record["pages"] = p[0] + u'–' + p[-1]
authors = r.get('author')
if not authors:
authors = r.get('editor', 'Anon.')
_authors = getnames(authors.split(" and "))
_and_surnames = self.and_authors(
[s.split(",")[0].strip() for s in _authors])
r['author'] = self.and_authors(_authors)
r['surnames'] = _and_surnames
r['author_year'] = _and_surnames + u" " + r['year']
r['unique_suffix'] = self.unique_suffix(r['author_year'])
r['author_year'] += r['unique_suffix']
r['title'] = r['title'] # .replace("{", "").replace("}","")
return r
def btex_custom(self, record):
r = convert_to_unicode(record)
if "pages" in record: # fix -- -> –
if "-" in record["pages"]:
p = [i.strip().strip('-') for i in record["pages"].split("-")]
record["pages"] = p[0] + u'–' + p[-1]
authors = r.get('author')
if not authors:
authors = r.get('editor', 'Anon.')
_authors = getnames(authors.split(" and "))
_and_surnames = self.and_authors(
[s.split(",")[0].strip() for s in _authors])
r['author'] = self.and_authors(_authors)
r['surnames'] = _and_surnames
r['author_year'] = _and_surnames + u" " + r.get('year', '')
r['unique_suffix'] = self.unique_suffix(r['author_year'])
r['author_year'] += r['unique_suffix']
r['title'] = r['title'] # .replace("{", "").replace("}","")
return r
def custom(record):
try:
record = c.convert_to_unicode(record)
except TypeError as e:
logging.warning("Unicode Error on: {}".format(record['ID']))
record['error'] = 'unicode'
try:
#add md5 of associated files
files = [add_slash_if_necessary(y) for x in record['file'].split(';') for y in x.split(':') if bool(y.strip()) and y.strip().lower() != 'pdf']
file_set = set(files)
if not 'hashes' in record:
hashes = [file_to_hash(x) for x in file_set]
record['hashes'] = ";".join(hashes)
#regularize format of files list
record['file'] = ";".join(file_set)
except Exception as e:
logging.warning("File Error: {} : {}".format(record['ID'], e.args[0]))
record['error'] = 'file'
#todo: if file is not in the library common prefix, move it there
#look for year, then first surname, then copy in, making dir if necessary
if file_set:
for x in file_set:
try:
current_path = realpath(x)
common = commonpath([current_path, args.library])
if common != args.library:
logging.info("Found file outside library: {}".format(current_path))
logging.info("Common: {}".format(common))
#get the author and year
year = record['year']
authors = c.getnames([i.strip() for i in record["author"].replace('\n', ' ').split(" and ")])
authors_split = [c.splitname(a) for a in authors]
author_surnames = [a['last'][0] for a in authors_split]
new_path = join(args.library, year, ", ".join(author_surnames))
logging.info("New Path: {}".format(new_path))
#create directory if necessary
#copy file
full_new_path = join(new_path, split(current_path)[1])
logging.info("Copying file")
logging.info("From: {}".format(current_path))
logging.info("To: {}".format(full_new_path))
response = input("Enter to confirm: ")
if response == "":
logging.info("Proceeding")
if not exists(new_path):
mkdir(new_path)
if exists(full_new_path):
raise Exception("File already exists")
copyfile(x, full_new_path)
file_set.remove(x)
file_set.add(full_new_path)
record['file'] = ";".join(file_set)
except Exception as e:
logging.info("Issue copying file for: {}".format(x))
logging.info(e)
record['error'] = 'file_copy'
#regularize keywords
try:
keywords = set()
if 'tags' not in record:
if 'keywords' in record:
keywords.update([x.strip() for x in record['keywords'].split(',')])
del record['keywords']
if 'mendeley-tags' in record:
keywords.update([x.strip() for x in record['mendeley-tags'].split(',')])
del record['mendeley-tags']
record['tags'] = ",".join(keywords)
except Error as e:
logging.warning("Tag Error: {}".format(record['ID']))
record['error'] = 'tag'
# record = c.type(record)
# record = c.author(record)
# record = c.editor(record)
# record = c.journal(record)
# record = c.keyword(record)
# record = c.link(record)
# record = c.doi(record)
# record['p_authors'] = []
# if 'author' in record:
# record['p_authors'] = [c.splitname(x, False) for x in record['author']]
return record
def test_getnames_braces(self):
names = ['A. {Delgado de Molina}', 'M. Vign{\\\'e}']
result = getnames(names)
expected = ['Delgado de Molina, A.', 'Vigné, M.']
self.assertEqual(result, expected)
def test_getnames_braces(self):
names = ['A. {Delgado de Molina}', 'M. Vign{\\\'e}']
result = getnames(names)
expected = ['Delgado de Molina, A.', 'Vigné, M.']
self.assertEqual(result, expected)
def test_getnames_add_double_dot(self):
names = ['FG Bar', 'CQ Lux']
result = getnames(names)
expected = [['F. G.', 'Bar'], ['C. Q.', 'Lux']]
self.assertEqual(result, expected)
def test_getnames_add_single_dot(self):
names = ['F Bar', 'C Lux']
result = getnames(names)
expected = [['F.', 'Bar'], ['C.', 'Lux']]
self.assertEqual(result, expected)