def codepoint(x, c, chtxt):
cinf = c._cinf
if len(list(x.keys())) != 1: warn('Expected only one cp_value attribute')
cp_attr, cp_type = list(x.items())[0]
if cp_attr != 'cp_type': warn('Unexpected cp_value attribute', cp_attr)
if cp_type == 'ucs':
if int(x.text, 16) != jdb.uord(chtxt):
warn ("xml codepoint ucs value '%s' doesnt match character %s (0x%x)." \
% (x.text, chtxt, jdb.uord (chtxt)))
else:
cinf.append(
jdb.Cinf(kw=KW.CINF[Xml2db.CINF.get(cp_type, cp_type)].id,
value=x.text))
def chr(c):
fmt = []
a = []
fmt.append("Character %d:" % jdb.uord(c.chr))
if getattr(c, 'strokes', None): a.append("strokes: %d" % c.strokes)
if getattr(c, 'bushu', None): a.append("radical: %d" % c.strokes)
if getattr(c, 'freq', None): a.append("freq: %d" % c.freq)
if getattr(c, 'grade', None): a.append("grade: %d" % c.grade)
if getattr(c, 'jlpt', None): a.append("jlpt: %d" % c.jlpt)
if a: fmt.append(" " + ', '.join(a))
return fmt
def do_chr(elem, srcid, langs):
global Char
# Process a <character> element. The element has been
# parsed by the xml ElementTree parse and is in "elem".
# "lineno" is the source file line number.
chtxt = elem.find('literal').text
Char = chtxt # For warning messages created by warn().
c = jdb.Chr(chr=chtxt, _cinf=[])
e = jdb.Entr(src=srcid,
stat=KW.STAT_A,
seq=jdb.uord(chtxt),
unap=False,
chr=c,
_kanj=[jdb.Kanj(txt=chtxt)],
_rdng=[],
_sens=[],
_krslv=[])
for x in elem.findall('codepoint/cp_value'):
codepoint(x, c, chtxt)
for x in elem.findall('radical/rad_value'):
radical(x, c)
x = None
try:
x = (elem.find('misc/freq')).text
except:
pass
if x:
if c.freq is not None: warn('Duplicate "freq" element ignored: %s' % x)
else: c.freq = int(x)
x = None
try:
x = (elem.find('misc/grade')).text
except:
pass
if x:
if c.grade is not None:
warn('Duplicate "grade" element ignored: %s' % x)
else:
c.grade = int(x)
for n, x in enumerate(elem.findall('misc/stroke_count')):
strokes(x, n, c)
rn = '\u3001'.join([x.text for x in elem.findall('misc/rad_name')])
if rn: c.radname = rn
for x in elem.findall('reading_meaning'):
reading_meaning(x, e._rdng, e._sens, c._cinf, langs)
x = elem.find('dic_number')
if x is not None: dicnum(x, c._cinf)
x = elem.find('query_code')
if x is not None: qcode(x, c._cinf)
for x in elem.findall('misc/variant'):
e._krslv.append(variant(x))
x = elem.find('misc/jlpt')
if x is not None: jlptnum(x, c)
return e
def ucshex(s):
return ' '.join(["%0.4X" % jdb.uord(c) for c in s])