bib2html.py

   1 #!/usr/bin/env python3
   2 """Creates a webpage with all entries of a .bib file"""
   3
   4 __version__ = "1.1"
   5
   6 __author__ = "Stefan Huber"
   7 __email__ = "shuber@sthu.org"
   8 __copyright__ = "Copyright 2013, Stefan Huber"
   9
  10 __license__ = "MIT"
  11
  12 # Permission is hereby granted, free of charge, to any person
  13 # obtaining a copy of this software and associated documentation
  14 # files (the "Software"), to deal in the Software without
  15 # restriction, including without limitation the rights to use,
  16 # copy, modify, merge, publish, distribute, sublicense, and/or sell
  17 # copies of the Software, and to permit persons to whom the
  18 # Software is furnished to do so, subject to the following
  19 # conditions:
  20 #
  21 # The above copyright notice and this permission notice shall be
  22 # included in all copies or substantial portions of the Software.
  23 #
  24 # THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
  25 # EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
  26 # OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
  27 # NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
  28 # HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
  29 # WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
  30 # FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
  31 # OTHER DEALINGS IN THE SOFTWARE.
  32
  33
  34 import os, sys, getopt, re
  35 import dateutil.parser
  36
  37
  38 def format_latex(text):
  39     # Get rid of matching dollar signs
  40     text = re.sub(r'\$([^\$]*)\$', r'\1', text)
  41
  42     # Replace text
  43     subst = {
  44         '\\"a': 'ä',
  45         '\\"o': 'ö',
  46         '\\"u': 'u',
  47         '\mathcal': '',
  48         '{': '',
  49         '}': '',
  50         '\\': '',
  51         '~': ' ',
  52         '---': '–',
  53         '--': '–',
  54     }
  55
  56     for a, b in subst.items():
  57         text = text.replace(a, b)
  58
  59     return text
  60
  61 def format_field_span(type, value):
  62     return "<span class=bibentry_" + type + ">" + format_latex(value) + "</span>"
  63
  64 def format_field(bibentry, field, pre='', post=''):
  65     if field in bibentry.fields:
  66         if bibentry.fields[field] != "":
  67             return format_field_span(field, pre + bibentry.fields[field] + post)
  68     return ""
  69
  70 def format_author(a):
  71     return  ' '.join(' '.join(p) for p in (a.first_names, a.middle_names, a.prelast_names, a.last_names, a.lineage_names) if p)
  72
  73 def format_authors(entry):
  74     return ", ".join([format_author(a) for a in entry.persons['author']])
  75
  76
  77 def format_details_article(entry):
  78
  79     where = format_field(entry, 'journal')
  80
  81     line = []
  82     line.append(format_field(entry, 'pages', pre='pp. '))
  83     line.append(format_field(entry, 'volume', pre='vol. ') + \
  84             format_field(entry, 'number', pre='(', post=')'))
  85     line.append(format_field(entry, 'month', post=' ') + \
  86             format_field(entry, 'year'))
  87     line.append(format_field(entry, 'note'))
  88
  89     line = filter(lambda l: l != "", line)
  90     return [where, ", ".join(line)]
  91
  92 def format_details_inproceedings(entry):
  93     where = format_field(entry, 'booktitle')
  94
  95     line = []
  96     line.append(format_field(entry, 'pages', pre='pp. '))
  97     line.append(format_field(entry, 'address'))
  98     line.append(format_field(entry, 'month', post=' ') + \
  99             format_field(entry, 'year'))
 100     line.append(format_field(entry, 'isbn', pre='ISBN '))
 101     line.append(format_field(entry, 'note'))
 102
 103     line = filter(lambda l: l != "", line)
 104     return [where, ", ".join(line)]
 105
 106 def format_details_incollection(entry):
 107     where = format_field(entry, 'booktitle')
 108
 109     line = []
 110     line.append(format_field(entry, 'publisher'))
 111     line.append(format_field(entry, 'pages', pre='pp. '))
 112     line.append(format_field(entry, 'address'))
 113     line.append(format_field(entry, 'month', post=' ') + \
 114             format_field(entry, 'year'))
 115     line.append(format_field(entry, 'isbn', pre='ISBN '))
 116     line.append(format_field(entry, 'note'))
 117
 118     line = filter(lambda l: l != "", line)
 119     return [where, ", ".join(line)]
 120
 121 def format_details_thesis(entry):
 122     line = []
 123     line.append(format_field(entry, 'school'))
 124     line.append(format_field(entry, 'month', post=' ') + \
 125             format_field(entry, 'year'))
 126     line.append(format_field(entry, 'note'))
 127
 128     line = filter(lambda l: l != "", line)
 129     return [", ".join(line)]
 130
 131 def format_details_book(entry):
 132     line = []
 133     line.append(format_field(entry, 'publisher'))
 134     line.append(format_field(entry, 'isbn', pre='ISBN '))
 135     line.append(format_field(entry, 'month', post=' ') + \
 136             format_field(entry, 'year'))
 137     line.append(format_field(entry, 'note'))
 138
 139     line = filter(lambda l: l != "", line)
 140     return [", ".join(line)]
 141
 142 def format_details_patent(entry):
 143     line = []
 144     line.append(format_field(entry, 'number', pre='Pat. '))
 145     line.append(format_field(entry, 'month', post=' ') + \
 146             format_field(entry, 'year'))
 147     line.append(format_field(entry, 'note'))
 148
 149     line = filter(lambda l: l != "", line)
 150     return [", ".join(line)]
 151
 152 def format_links(entry):
 153     doi = format_field(entry, 'doi', pre='<a href="http://dx.doi.org/', post='">[DOI]</a>')
 154     webpdf = format_field(entry, 'webpdf', pre='<a href="', post='">[PDF]</a>')
 155     weblink = format_field(entry, 'weblink', pre='<a href="', post='">[link]</a>')
 156     url = format_field(entry, 'url', pre='<a href="', post='">[url]</a>')
 157     webslides = format_field(entry, 'webslides', pre='<a href="', post='">[slides]</a>')
 158     weberrata = format_field(entry, 'weberrata', pre='<a href="',
 159             post='">[errata]</a>')
 160     return " ".join([doi, webpdf, weblink, url, webslides, weberrata])
 161
 162 def format_entry(entry):
 163     lines = []
 164     lines.append(format_field(entry, 'title', pre="<b>", post="</b>"))
 165     lines.append(format_field_span('author', format_authors(entry)))
 166
 167     if entry.type=='article':
 168         lines.extend(format_details_article(entry))
 169     elif entry.type=='inproceedings':
 170         lines.extend(format_details_inproceedings(entry))
 171     elif entry.type=='incollection':
 172         lines.extend(format_details_incollection(entry))
 173     elif entry.type=='book':
 174         lines.extend(format_details_book(entry))
 175     elif entry.type=='patent':
 176         lines.extend(format_details_patent(entry))
 177     elif entry.type in ['mastersthesis', 'phdthesis']:
 178         lines.extend(format_details_thesis(entry))
 179     else:
 180         lines.append("Unknown type <b>'" + entry.type + "'</b>")
 181
 182     lines.append(format_field(entry, 'webnote'))
 183     lines.append(format_links(entry))
 184
 185     lines = filter(lambda l: l != "", lines)
 186     return "<br/>\n".join(lines)
 187
 188
 189 def entryDateSortKey(p):
 190     k, e = p
 191
 192     if 'date' in e.fields:
 193         return e.fields['date']
 194
 195     month2num = { 'jan' : '01', 'feb' : '02', 'mar' : '03', \
 196             'apr' : '04', 'may' : '05', 'jun' : '06', \
 197             'jul' : '07', 'aug' : '08', 'sep' : '09', \
 198             'oct' : '10', 'nov' : '11', 'dec' : '12'}
 199
 200     if not 'month' in e.fields:
 201         return e.fields['year']
 202
 203     month = e.fields['month'].lower()[0:3]
 204     if month in month2num:
 205         month = month2num[month]
 206     else:
 207         month = ""
 208
 209     return e.fields['year'] + "-" + month
 210
 211
 212 def entryGetYear(e):
 213     if 'year' in e.fields:
 214         return e.fields['year']
 215
 216     if 'date' in e.fields:
 217         dt = dateutil.parser.isoparse(e.fields['date'])
 218         return str(dt.year)
 219
 220     return None
 221
 222
 223 def usage():
 224     """Print usage text of this program"""
 225
 226     print("""Usage:
 227   {0} -i FILE
 228   {0} -h
 229
 230 OPTIONS:
 231   -h       print this text
 232   -i       .bib file
 233 """.format(sys.argv[0]))
 234
 235 if __name__ == "__main__":
 236
 237     bibfile = None
 238
 239     try:
 240         opts, args = getopt.getopt(sys.argv[1:], "hi:")
 241
 242         for opt, arg in opts:
 243             if opt == "-h":
 244                 usage()
 245                 sys.exit(os.EX_OK)
 246             elif opt == "-i":
 247                 bibfile = arg
 248             else:
 249                 print("Unknown option '", opt, "'.")
 250
 251     except getopt.GetoptError as e:
 252         print("Error parsing arguments:", e)
 253         usage()
 254
 255     if bibfile == None:
 256         print("You need to specify a bibfile")
 257         usage()
 258         sys.exit(os.EX_USAGE)
 259
 260
 261     from pybtex.database.input import bibtex
 262     parser = bibtex.Parser()
 263
 264     from pybtex.style.formatting.unsrt import Style
 265
 266     bib_data = parser.parse_file(bibfile)
 267     entries = bib_data.entries
 268
 269     years = list(set([entryGetYear(e) for e in entries.values()]))
 270     years.sort(reverse=True)
 271
 272     for year in years:
 273
 274         print("<h2>" + year + "</h2>")
 275
 276         iteritems = list(entries.items())
 277         iteritems.sort(key=entryDateSortKey, reverse=True)
 278         for key, entry in iteritems:
 279
 280             if entryGetYear(entry) != year:
 281                 continue
 282
 283             print("<div class=bibentry>")
 284             print("<a class=bibentry_key id={}>[{}]</a><br/><span class=bibentry_type>{}</span><br/>".format(key, key, entry.type))
 285             e = format_entry(entry)
 286             print(e)
 287
 288             print("</div>\n")