make-glossary

   1 #!/usr/bin/python3
   2
   3 from lxml import etree
   4 from lxml.etree import tostring
   5
   6 tree = etree.parse('mekanikk-1999/meksme-utf8.xml')
   7 root = tree.getroot()
   8
   9 #print(root)
  10 #print(tostring(tree))
  11
  12 cols = (
  13     'topic', 'sme', 'desc-sme', 'desc-nb', 'nb', 'sv', 'fi', 'en', 'is',
  14     'unknown',
  15 )
  16
  17 resultset = root.find("{http://www.filemaker.com/fmpxmlresult}RESULTSET")
  18
  19 words = []
  20 for row in resultset.getchildren():
  21     d = {}
  22     index = 0
  23     for col in row.findall("{http://www.filemaker.com/fmpxmlresult}COL"):
  24         t = col.getchildren()[0].text
  25         if t:
  26             import re
  27             t = re.sub(r'\s+', ' ', t)
  28             d[cols[index]] = t
  29         index += 1
  30     #print(d)
  31     words.append(d)
  32
  33 def make_glossary(lang):
  34     print(".. glossary::")
  35     print()
  36
  37     def langsort(e):
  38         if lang in e:
  39             return e[lang]
  40         else:
  41             return e['sme']
  42     for e in sorted(words, key=langsort):
  43         if lang in e and 'desc-%s' % lang in e:
  44             if 'topic' not in e:
  45                 e['topic'] = 'n/a'
  46             #print(e)
  47             print("  %s [%s]\n     %s" % (e[lang], e['topic'], e['desc-%s' % lang]))
  48             print()
  49         else:
  50             # ERROR / missing definition
  51             pass
  52
  53 print("Nordsamisk")
  54 print("==========")
  55 print()
  56 make_glossary(lang='sme')
  57
  58 print("Norsk")
  59 print("=====")
  60 print()
  61 make_glossary(lang='nb')
  62
  63 #print("Engelsk")
  64 #print("=====")
  65 #print()
  66 #make_glossary(lang='en')