/usr/lib/python2.7/dist-packages/bibtexparser/customization.py is in python-bibtexparser 0.6.2-3.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 | #!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
A set of functions useful for customizing bibtex fields.
You can find inspiration from these functions to design yours.
Each of them takes a record and return the modified record.
"""
import itertools
import re
import logging
from .latexenc import unicode_to_latex, unicode_to_crappy_latex1, unicode_to_crappy_latex2, string_to_latex, protect_uppercase
logger = logging.getLogger(__name__)
__all__ = ['getnames', 'author', 'editor', 'journal', 'keyword', 'link',
'page_double_hyphen', 'doi', 'type', 'convert_to_unicode',
'homogeneize_latex_encoding']
def getnames(names):
"""Make people names as surname, firstnames
or surname, initials. Should eventually combine up the two.
:param names: a list of names
:type names: list
:returns: list -- Correctly formated names
"""
tidynames = []
for namestring in names:
namestring = namestring.strip()
if len(namestring) < 1:
continue
if ',' in namestring:
namesplit = namestring.split(',', 1)
last = namesplit[0].strip()
firsts = [i.strip() for i in namesplit[1].split()]
else:
namesplit = namestring.split()
last = namesplit.pop()
firsts = [i.replace('.', '. ').strip() for i in namesplit]
if last in ['jnr', 'jr', 'junior']:
last = firsts.pop()
for item in firsts:
if item in ['ben', 'van', 'der', 'de', 'la', 'le']:
last = firsts.pop() + ' ' + last
tidynames.append(last + ", " + ' '.join(firsts))
return tidynames
def author(record):
"""
Split author field into a list of "Name, Surname".
:param record: the record.
:type record: dict
:returns: dict -- the modified record.
"""
if "author" in record:
if record["author"]:
record["author"] = getnames([i.strip() for i in record["author"].replace('\n', ' ').split(" and ")])
else:
del record["author"]
return record
def editor(record):
"""
Turn the editor field into a dict composed of the original editor name
and a editor id (without coma or blank).
:param record: the record.
:type record: dict
:returns: dict -- the modified record.
"""
if "editor" in record:
if record["editor"]:
record["editor"] = getnames([i.strip() for i in record["editor"].replace('\n', ' ').split(" and ")])
# convert editor to object
record["editor"] = [{"name": i, "ID": i.replace(',', '').replace(' ', '').replace('.', '')} for i in record["editor"]]
else:
del record["editor"]
return record
def page_double_hyphen(record):
"""
Separate pages by a double hyphen (--).
:param record: the record.
:type record: dict
:returns: dict -- the modified record.
"""
if "pages" in record:
# hyphen, non-breaking hyphen, en dash, em dash, hyphen-minus, minus sign
separators = [u'‐', u'‑', u'–', u'—', u'-', u'−']
for separator in separators:
if separator in record["pages"]:
p = [i.strip().strip(separator) for i in record["pages"].split(separator)]
record["pages"] = p[0] + '--' + p[-1]
return record
def type(record):
"""
Put the type into lower case.
:param record: the record.
:type record: dict
:returns: dict -- the modified record.
"""
if "type" in record:
record["type"] = record["type"].lower()
return record
def journal(record):
"""
Turn the journal field into a dict composed of the original journal name
and a journal id (without coma or blank).
:param record: the record.
:type record: dict
:returns: dict -- the modified record.
"""
if "journal" in record:
# switch journal to object
if record["journal"]:
record["journal"] = {"name": record["journal"], "ID": record["journal"].replace(',', '').replace(' ', '').replace('.', '')}
return record
def keyword(record, sep=',|;'):
"""
Split keyword field into a list.
:param record: the record.
:type record: dict
:param sep: pattern used for the splitting regexp.
:type record: string, optional
:returns: dict -- the modified record.
"""
if "keyword" in record:
record["keyword"] = [i.strip() for i in re.split(sep, record["keyword"].replace('\n', ''))]
return record
def link(record):
"""
:param record: the record.
:type record: dict
:returns: dict -- the modified record.
"""
if "link" in record:
links = [i.strip().replace(" ", " ") for i in record["link"].split('\n')]
record['link'] = []
for link in links:
parts = link.split(" ")
linkobj = {"url": parts[0]}
if len(parts) > 1:
linkobj["anchor"] = parts[1]
if len(parts) > 2:
linkobj["format"] = parts[2]
if len(linkobj["url"]) > 0:
record["link"].append(linkobj)
return record
def doi(record):
"""
:param record: the record.
:type record: dict
:returns: dict -- the modified record.
"""
if 'doi' in record:
if 'link' not in record:
record['link'] = []
nodoi = True
for item in record['link']:
if 'doi' in item:
nodoi = False
if nodoi:
link = record['doi']
if link.startswith('10'):
link = 'http://dx.doi.org/' + link
record['link'].append({"url": link, "anchor": "doi"})
return record
def convert_to_unicode(record):
"""
Convert accent from latex to unicode style.
:param record: the record.
:type record: dict
:returns: dict -- the modified record.
"""
for val in record:
if '\\' in record[val] or '{' in record[val]:
for k, v in itertools.chain(unicode_to_crappy_latex1, unicode_to_latex):
if v in record[val]:
record[val] = record[val].replace(v, k)
# If there is still very crappy items
if '\\' in record[val]:
for k, v in unicode_to_crappy_latex2:
if v in record[val]:
parts = record[val].split(str(v))
for key, record[val] in enumerate(parts):
if key+1 < len(parts) and len(parts[key+1]) > 0:
# Change order to display accents
parts[key] = parts[key] + parts[key+1][0]
parts[key+1] = parts[key+1][1:]
record[val] = k.join(parts)
return record
def homogeneize_latex_encoding(record):
"""
Homogeneize the latex enconding style for bibtex
This function is experimental.
:param record: the record.
:type record: dict
:returns: dict -- the modified record.
"""
# First, we convert everything to unicode
record = convert_to_unicode(record)
# And then, we fall back
for val in record:
if val not in ('ID',):
logger.debug('Apply string_to_latex to: %s', val)
record[val] = string_to_latex(record[val])
if val == 'title':
logger.debug('Protect uppercase in title')
logger.debug('Before: %s', record[val])
record[val] = protect_uppercase(record[val])
logger.debug('After: %s', record[val])
return record
|