bib2html.py

   1 #!/usr/bin/env python2
   2 """Creates a webpage with all entries of a .bib file"""
   3
   4 __version__ = "1.0"
   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
  35
  36
  37 def format_latex(text):
  38     return text.replace('{', '').replace('}', '').replace('\\', '')
  39
  40 def format_field_span(type, value):
  41     return "<span class=bibentry_" + type + ">" + format_latex(value) + "</span>"
  42
  43 def format_field(bibentry, field, pre='', post=''):
  44     if field in bibentry.fields:
  45         if bibentry.fields[field] != "":
  46             return format_field_span(field, pre + bibentry.fields[field] + post)
  47     return ""
  48
  49 def format_author(a):
  50     return  ' '.join(' '.join(p) for p in (a.first(), a.middle(), a.prelast(), a.last(), a.lineage()) if p)
  51
  52 def format_authors(entry):
  53     return ", ".join([format_author(a) for a in entry.persons['author']])
  54
  55
  56 def format_details_article(entry):
  57
  58     where = format_field(entry, 'journal')
  59
  60     line = []
  61     line.append(format_field(entry, 'pages', pre='pp. '))
  62     line.append(format_field(entry, 'volume', pre='vol. ') + \
  63             format_field(entry, 'number', pre='(', post=')'))
  64     line.append(format_field(entry, 'month', post=' ') + \
  65             format_field(entry, 'year'))
  66     line = filter(lambda l: l != "", line)
  67
  68     return [where, ", ".join(line)]
  69
  70 def format_details_inproceedings(entry):
  71     where = format_field(entry, 'booktitle')
  72
  73     line = []
  74     line.append(format_field(entry, 'pages', pre='pp. '))
  75     line.append(format_field(entry, 'address'))
  76     line.append(format_field(entry, 'month', post=' ') + \
  77             format_field(entry, 'year'))
  78     line = filter(lambda l: l != "", line)
  79     return [where, ", ".join(line)]
  80
  81 def format_details_thesis(entry):
  82     line = []
  83     line.append(format_field(entry, 'school'))
  84     line.append(format_field(entry, 'month', post=' ') + \
  85             format_field(entry, 'year'))
  86     line = filter(lambda l: l != "", line)
  87     return [", ".join(line)]
  88
  89 def format_details_book(entry):
  90     line = []
  91     line.append(format_field(entry, 'publisher'))
  92     line.append(format_field(entry, 'isbn', pre='ISBN '))
  93     line.append(format_field(entry, 'month', post=' ') + \
  94             format_field(entry, 'year'))
  95     line = filter(lambda l: l != "", line)
  96     return [", ".join(line)]
  97
  98 def format_links(entry):
  99     doi = format_field(entry, 'doi', pre='<a href="http://dx.doi.org/', post='">[DOI]</a>')
 100     webpdf = format_field(entry, 'webpdf', pre='<a href="', post='">[PDF]</a>')
 101     weblink = format_field(entry, 'weblink', pre='<a href="', post='">[link]</a>')
 102     webslides = format_field(entry, 'webslides', pre='<a href="', post='">[slides]</a>')
 103     weberrata = format_field(entry, 'weberrata', pre='<a href="',
 104             post='">[errata]</a>')
 105     return " ".join([doi, webpdf, weblink, webslides, weberrata])
 106
 107 def format_entry(entry):
 108     lines = []
 109     lines.append(format_field(entry, 'title', pre="<b>", post="</b>"))
 110     lines.append(format_field_span('author', format_authors(entry)))
 111
 112     if entry.type=='article':
 113         lines.extend(format_details_article(entry))
 114     elif entry.type=='inproceedings':
 115         lines.extend(format_details_inproceedings(entry))
 116     elif entry.type=='book':
 117         lines.extend(format_details_book(entry))
 118     elif entry.type in ['mastersthesis', 'phdthesis']:
 119         lines.extend(format_details_thesis(entry))
 120     else:
 121         lines.append("Unknown type <b>'" + entry.type + "'</b>")
 122
 123     lines.append(format_field(entry, 'webnote'))
 124     lines.append(format_links(entry))
 125
 126     lines = filter(lambda l: l != "", lines)
 127     return "<br/>\n".join(lines)
 128
 129
 130 def entryCompareDate(p1, p2):
 131     k1, e1 = p1
 132     k2, e2 = p2
 133
 134
 135     def toStr(e):
 136         month2num = { 'jan' : '01', 'feb' : '02', 'mar' : '03', \
 137                 'apr' : '04', 'may' : '05', 'jun' : '06', \
 138                 'jul' : '07', 'aug' : '08', 'sep' : '09', \
 139                 'oct' : '10', 'nov' : '11', 'dec' : '12'}
 140         month = e.fields['month'].lower()[0:3]
 141         if month in month2num:
 142             month = month2num[month]
 143         else:
 144             month = ""
 145         return e.fields['year'] + "-" + month
 146
 147     return cmp(toStr(e1), toStr(e2))
 148
 149
 150 def usage():
 151     """Print usage text of this program"""
 152
 153     print("""Usage:
 154   {0} -i FILE
 155   {0} -h
 156
 157 OPTIONS:
 158   -h       print this text
 159   -i       .bib file
 160 """.format(sys.argv[0]))
 161
 162 if __name__ == "__main__":
 163
 164     bibfile = None
 165
 166     try:
 167         opts, args = getopt.getopt(sys.argv[1:], "hi:")
 168
 169         for opt, arg in opts:
 170             if opt == "-h":
 171                 usage()
 172                 sys.exit(os.EX_OK)
 173             elif opt == "-i":
 174                 bibfile = arg
 175             else:
 176                 print("Unknown option '", opt, "'.")
 177
 178     except getopt.GetoptError as e:
 179         print("Error parsing arguments:", e)
 180         usage()
 181
 182     if bibfile == None:
 183         print("You need to specify a bibfile")
 184         usage()
 185         sys.exit(os.EX_USAGE)
 186
 187
 188     from pybtex.database.input import bibtex
 189     parser = bibtex.Parser()
 190
 191     from pybtex.style.formatting.unsrt import Style
 192
 193     bib_data = parser.parse_file(bibfile)
 194     entries = bib_data.entries
 195
 196     years = list(set([ b.fields['year'] for b in entries.values() ]))
 197     years.sort(reverse=True)
 198
 199     for year in years:
 200
 201         print("<h2>" + year + "</h2>")
 202
 203         iteritems = list(entries.iteritems())
 204         iteritems.sort(cmp=entryCompareDate, reverse=True)
 205         for key, entry in iteritems:
 206
 207             if entry.fields['year'] != year:
 208                 continue
 209
 210             print("<div class=bibentry>")
 211             print("<a class=bibentry_key id=" + key + ">[" + key + "]</a><br/>")
 212
 213             print(format_entry(entry).encode('utf8'))
 214
 215             print("</div>\n")
 216