Last active
January 14, 2022 02:22
-
-
Save alexandrehuat/6d3263f73ccae87d0107977978316c02 to your computer and use it in GitHub Desktop.
Mendeley-exported BibTeX cleaner
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import sys | |
import re | |
from collections import Counter | |
import bibtexparser as bp | |
# ============================================================================== | |
# Process | |
# ============================================================================== | |
MONTH_INT = {"jan": 1, "feb": 2, "mar": 3, "apr": 4, "may": 5, "jun": 6, "jul": 7, "aug": 8, "sep": 9, "oct": 10, "nov": 11, "dec": 12} | |
def mapchain(funcs, iterable): | |
if funcs: | |
return mapchain(funcs[1:], map(funcs[0], iterable)) | |
else: | |
return iterable | |
def rm_fields(entry, fields=["abstract", "keywords", "annote", "url"]): | |
for f in fields: | |
entry.pop(f, None) | |
return entry | |
def rm_httpsdoi(entry): | |
try: | |
entry["doi"] = entry["doi"].replace("https://doi.org/", '') | |
except KeyError: | |
pass | |
return entry | |
def correct_pages(entry): | |
try: | |
if "--" not in entry["pages"]: | |
entry["pages"] = entry["pages"].replace("-", "--") | |
entry["pages"] = entry["pages"].replace(" -- ", "--") | |
except KeyError: | |
pass | |
return entry | |
def correct_title(entry): | |
""" | |
Remove end point if it exists. Escape '&'. | |
""" | |
try: | |
if entry["title"][-1] == '.': | |
entry["title"] = entry["title"][:-1] | |
elif entry["title"][-2:] == '.}': | |
entry["title"] = entry["title"][:-2] + '}' | |
entry["title"] = entry["title"].replace('&', "\&") | |
except KeyError: | |
pass | |
return entry | |
def rm_escape_codes(word): | |
_word = word.replace('{', '').replace('}', '').replace("\i", '').replace("\j", '') | |
codes = "`'^" + '"' + "H~ckl=b.druvto" | |
for code in codes: | |
_word = _word.replace("\{}".format(code), '') | |
return _word | |
def _alias_sort_key(entry): | |
return "{:04}{:02}{:02}{}".format(int(entry.get("year", 9999)), | |
int(entry.get("month", 99)), | |
int(entry.get("day", 99)), | |
entry.get("title", 10 * 'z')) | |
def format_aliases_authyear(entries): | |
aliascount = Counter() | |
for entry in sorted(entries, key=_alias_sort_key): | |
name = rm_escape_codes(''.join(entry["author"].split(" and ")[0].split(", ")[0].split(' '))) | |
name = name[0].upper() + name[1:] | |
entry["ID"] = name + entry["year"] | |
aliascount.update([entry["ID"]]) | |
if aliascount[entry["ID"]] > 1: | |
entry["ID"] += chr(ord('a') + aliascount[entry["ID"]] - 2) | |
return entries | |
def month2num(entry): | |
try: | |
for k, v in MONTH_INT.items(): | |
if k in entry["month"]: | |
entry["month"] = str(v) | |
break | |
except KeyError: | |
pass | |
return entry | |
def correct_issn(entry): | |
try: | |
r = re.search("\w\w\w\w-?\w\w\w\w", entry["issn"]) | |
if r: | |
entry["issn"] = entry["issn"][r.start():r.end()] | |
if '-' not in entry["issn"]: | |
entry["issn"] = '-'.join((entry["issn"][:4], entry["issn"][4:])) | |
except KeyError: | |
pass | |
return entry | |
# ============================================================================== | |
# Tests | |
# ============================================================================== | |
def strfentry(entry): | |
return '\n'.join(reversed(["{:16}{}".format(k, v) | |
for k, v in entry.items()])) | |
def print_fail(message, entry, fatal=True): | |
print("ERROR:" if fatal else "WARNING:", message) | |
print("Entry:", 80 * '-', strfentry(entry), 80 * '-', sep='\n') | |
def test_rm_fields(entry, fields=["abstract", "keywords", "annote", "url"]): | |
for f in fields: | |
if f in entry.keys(): | |
print_fail("Field '{}' not removed.".format(f), entry) | |
return False | |
return True | |
def test_month2num(entry): | |
try: | |
if not 1 <= int(entry["month"]) <= 12: | |
print_fail("month is out of range [1, 12].", entry) | |
return False | |
except KeyError: | |
pass | |
except ValueError: | |
print_fail("month is not an integer.", entry) | |
return False | |
return True | |
def test_no_title_endp(entry): | |
try: | |
if '.' in entry["title"][-2:]: | |
print_fail("Title has an end punct.", entry) | |
return False | |
except KeyError: | |
pass | |
return True | |
def test_issn(entry): | |
try: | |
if not re.match("\w\w\w\w-\w\w\w\w$", entry["issn"]): | |
print_fail("Non-standard ISSN format.", entry, fatal=False) | |
except KeyError: | |
pass | |
return True | |
# ============================================================================== | |
# Main | |
# ============================================================================== | |
if __name__ == "__main__": | |
if len(sys.argv) != 3: | |
print("ERROR: Wrong number of arguments.") | |
print("Usage: python3 mendeley_bibtex_cleaner.py input_file.bib output_file.bib") | |
else: | |
input_file, output_file = sys.argv[1:3] | |
# Read | |
with open(input_file) as f: | |
db = bp.load(f) | |
# Clean | |
db.entries = list(mapchain([rm_fields, | |
month2num, | |
rm_httpsdoi, | |
correct_pages, | |
correct_title, | |
correct_issn], db.entries)) | |
db.entries = format_aliases_authyear(db.entries) | |
# Test cleaning | |
success = True | |
for e in db.entries: | |
success &= all([test_rm_fields(e), | |
test_month2num(e), | |
test_no_title_endp(e), | |
test_issn(e)]) | |
# Write | |
if success: | |
with open(output_file, 'w') as f: | |
bp.dump(db, f) | |
print("Cleaning successful.") | |
else: | |
print(20 * "*~%^" + "\nCleaning failed. No file was output.") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Usage
Suggested alias to be added in your .bashrc or .zshrc :
Requirements
Install on Linux (systemwide)