def _abbrev_word(cls, word):
new_word = word
if not word in cls.keep:
new_word = word
for entry in cls.abbrev_map:
if cls._startswith(word, entry):
new_word = cls.abbrev_map[entry]
break
if new_word in cls.upper:
new_word = new_word.upper()
elif new_word in cls.lower:
new_word = new_word.lower()
else:
new_word = capitalize_word(new_word)
new_word = cls._add_period(new_word)
return new_word
def abbreviate(cls, journal):
journal = journal.lower()
for entry in cls.special:
journal = journal.replace(entry, cls.special[entry])
words = journal.replace("-"," ").strip().split()
if len(words) == 1: #don't abbreivate
title = capitalize_word(words[0])
return cls.final_process(title)
str_arr = []
for word in words:
if word in cls.erase:
continue
str_arr.append(cls._abbrev_word(word))
text = " ".join(str_arr)
return cls.final_process(text)
def process_authors(entries):
authors = []
for entry in entries:
if len(entry) == 1: #hmm, chinese name
entry = map(lambda x: x.strip(), entry[0].split())
last, first = entry[:2]
#check to see if we have stupidness
first_first = first.split()[0]
match = re.compile("[A-Z]{2}").search(first_first)
if match: #I f*****g hate you papers
initials = []
for entry in first_first:
initials.append(entry)
first = " ".join(initials)
else:
first = clean_line(first)
#capitalize last name
last = capitalize_word(last)
name = "%s, %s" % (last, first)
authors.append(name)
return authors
def capitalize_word(cls, word):
for delim in "/", "-":
if delim in word and not word[-1] == delim:
return cls.capitalize_hyphenated_word(word, delim)
else:
return capitalize_word(word)
