jblite/jmdict_proto1.py

   1 import warnings
   2 from lxml import etree
   3
   4
   5 # lxml normalizes XML namespaces... so for xml:lang, we use the
   6 # following constant.
   7 XML_LANG = '{http://www.w3.org/XML/1998/namespace}lang'  # xml:lang
   8
   9
  10 def skip_elem(elem_name):
  11     warnings.warn("Encountered unsuppored element <%s>.  "
  12                   "<%s> elements will be skipped." % (elem_name, elem_name))
  13
  14 def main():
  15     parser = etree.XMLParser(resolve_entities=False)
  16     import sys
  17     with open(sys.argv[1]) as infile:
  18         et = etree.ElementTree(file=infile, parser=parser)
  19     root = et.getroot()
  20     for child in root.iterchildren():
  21         ent_seq = int(child.find('ent_seq').text)
  22         for k_ele in child.iterfind('k_ele'):
  23             blob = k_ele.find('keb').text
  24             #print u"k_ele.keb:", blob
  25             for ke_inf in k_ele.iterfind('ke_inf'):
  26                 info = ke_inf.text
  27                 #print u"k_ele.ke_inf:", info
  28             for ke_pri in k_ele.iterfind('ke_pri'):
  29                 priority = ke_pri.text
  30                 #print u"k_ele.ke_pri:", priority
  31         for r_ele in child.iterfind('r_ele'):
  32             blob = r_ele.find('reb').text
  33             #print u"r_ele.reb:", blob
  34             nokanji = True if r_ele.find('re_nokanji') is not None \
  35                       else False
  36             #print u"r_ele.nokanji:", nokanji
  37             for re_restr in r_ele.iterfind('re_restr'):
  38                 restr = re_restr.text
  39                 #print u"r_ele.re_restr:", restr
  40             for re_inf in r_ele.iterfind('re_inf'):
  41                 info = re_inf.text
  42                 #print u"r_ele.re_inf:", info
  43             for re_pri in r_ele.iterfind('re_pri'):
  44                 priority = re_pri.text
  45                 #print u"r_ele.re_pri:", priority
  46         info = child.find('info')
  47         if info is not None:
  48             for links in info.iterfind('links'):
  49                 tag = links.find('link_tag').text
  50                 desc = links.find('link_desc').text
  51                 uri = links.find('link_uri').text
  52                 # do something...
  53             for bibl in info.iterfind('bibl'):
  54                 tag = bibl.find('bib_tag')
  55                 txt = bibl.find('bib_txt')
  56                 tag = tag.text if tag is not None else None
  57                 txt = txt.text if txt is not None else None
  58                 # do something
  59             for etym in info.iterfind('etym'):
  60                 # Not yet supported: if we ever encounter, warn.
  61                 skip_elem('etym')
  62             for audit in info.iterfind('audit'):
  63                 upd_date = audit.find('upd_date').text
  64                 upd_detl = audit.find('upd_detl').text
  65                 # do something...
  66         for sense in child.iterfind('sense'):
  67             for stagk in sense.iterfind('stagk'):
  68                 text = stagk.text
  69                 # do something...
  70             for stagr in sense.iterfind('stagr'):
  71                 text = stagr.text
  72                 # do something...
  73             for pos in sense.iterfind('pos'):
  74                 text = pos.text  # entity, right...?
  75                 # do something...
  76             for xref in sense.iterfind('xref'):
  77                 text = xref.text  # text w/ special format; just store for now
  78                 # do something...
  79             for ant in sense.iterfind('ant'):
  80                 text = ant.text
  81                 # do something...
  82             for field in sense.iterfind('field'):
  83                 text = field.text
  84                 # do something...
  85             for misc in sense.iterfind('misc'):
  86                 text = misc.text
  87                 # do something...
  88             for s_inf in sense.iterfind('s_inf'):
  89                 text = s_inf.text
  90                 # do something...
  91             for lsource in sense.iterfind('lsource'):
  92                 text = lsource.text
  93                 lang = lsource.get(XML_LANG)
  94                 ltype = lsource.get('ls_type')
  95                 wasei = lsource.get('ls_wasei')
  96                 # do something...
  97             for dial in sense.iterfind('dial'):
  98                 text = dial.text
  99                 # do something...
 100             for gloss in sense.iterfind('gloss'):
 101                 lang = gloss.get(XML_LANG)
 102                 gender = gloss.get('g_gend')
 103                 text = gloss.text
 104                 # Do something...
 105                 for pri in gloss.iterfind('pri'):
 106                     # Not yet supported: if we ever encounter, warn.
 107                     skip_elem('pri')
 108             for example in sense.iterfind('example'):
 109                 text = example.text
 110
 111 if __name__ == "__main__":
 112     main()