def getStrokeOrd(fin, kl):
"""
Trying for awareness of glyph locale
in lookup.
"""
from cjklib.characterlookup import CharacterLookup
for i in kl:
if i in cedict.simplified: cjk = CharacterLookup('C')
elif i in cedict.traditional: cjk = CharacterLookup('T')
else: cjk = CharacterLookup('J')
j = cjk.getStrokeOrder(i)
fin.append(u'• ' + u' '.join(j))
return fin
def auxSOrd(i):
"""
Try to get stroke decomposition
if subcomponent decomposition fails.
"""
from cjklib.characterlookup import CharacterLookup
if i in cedict.simplified: cjk = CharacterLookup('C')
elif i in cedict.traditional: cjk = CharacterLookup('T')
else: cjk = CharacterLookup('J')
try:
j = cjk.getStrokeOrder(i)
except:
return u'[x]'
return u' '.join(j)
def mandarinToPinyin(mandarinChar):
cjk = CharacterLookup('C')
textPinYinList = cjk.getReadingForCharacter(mandarinChar,
'Pinyin',
toneMarkType='none')
if len(textPinYinList) > 1:
print "converted syllable {} has {} parts".format(
textPinYinList, len(textPinYinList))
pinyin = textPinYinList[
0] # take only first variant of pinyin interpretations
return pinyin
def tokenize(input, output):
try:
text = open(input, 'r').readlines()
except IOError:
print "IOError: could not open", input
sys.exit()
cjk = CharacterLookup('T')
out = open(output, 'w')
for line in text:
line = line.decode('utf-8')
new_line = ""
for char in line:
pinyin = cjk.getReadingForCharacter(char, 'Pinyin')
if pinyin:
new_line += char
new_line += '\n'
out.write(new_line.encode('utf-8'))
out.close()
def to_pinyin(filename):
try:
input = open(filename, 'r').readlines()
except IOError:
print "IOError: could not open", filename
sys.exit()
cjk = CharacterLookup('T')
input = [u'我喜歡他']
for line in input:
#line = line.decode('utf-8')
new_line = ""
for char in line:
pinyin = cjk.getReadingForCharacter(char, 'Pinyin')
if pinyin:
print [unidecode(x) for x in pinyin]
simplified = unidecode(pinyin[0])
new_line += simplified + char + " "
line = new_line
print line
import requests
import codecs
import gevent
from gevent import monkey
monkey.patch_all()
from bs4 import BeautifulSoup
# 汉字拼音识别
from pypinyin import pinyin, lazy_pinyin, Style
# 笔划数识别
from cjklib.characterlookup import CharacterLookup
cjk = CharacterLookup('C')
# 汉字偏旁识别
from lib.component import *
reload(sys)
sys.setdefaultencoding("utf-8")
# 代理配置
proxies = {}
class BabyName():
def __init__(self,
config={},
name_dict={},
def _characterLookup(cls):
if not hasattr(cls, '_cjk'):
cls._cjk = CharacterLookup('T', 'Unicode')
return cls._cjk
def getCharacters(self):
cjk = CharacterLookup('T', self.title)
return ' '.join(cjk.getDomainCharacterIterator())
def __init__(self):
self._cjk = CharacterLookup('T', 'Unicode')
self.characterIterator = self._cjk.getDomainCharacterIterator()
self.curChar = None
self.glyphQueue = []
def __init__(self, options, args):
self._locale = options.locale
self._characterDomain = options.characterDomain
self._cjk = CharacterLookup(self._locale, self._characterDomain)
def __init__(self, variant='T'):
self.characterLookup = CharacterLookup('T')
self.variant = variant
def main():
cjk = CharacterLookup('T')
cjkSimplified = CharacterLookup('C')
fileEntryCount = 0
databaseMissingEntryCount = 0
noEntryCount = 0
wrongEquivalentCount = 0
seenRadicalFormIndices = set()
seenRadicalVariantIndices = set()
for line in sys.stdin:
line = line.decode(default_encoding)
if re.match(r'\s*#', line) or re.match(r'\s+$', line):
continue
else:
fileEntryCount = fileEntryCount + 1
matchObj = re.match(r"(\d{1,3})('?);\s+([1234567890ABCDEF]{4,5});" \
+ r"\s+([1234567890ABCDEF]{4,5})\s*$", line)
if matchObj:
index, variant, radicalCP, equivalentCP = matchObj.groups()
radicalIdx = int(index)
radicalForm = chr(int(radicalCP, 16))
equivalentForm = chr(int(equivalentCP, 16))
if variant:
seenRadicalVariantIndices.add(radicalIdx)
else:
seenRadicalFormIndices.add(radicalIdx)
# check radicalForm
if not variant:
targetForms = set([cjk.getKangxiRadicalForm(radicalIdx)])
else:
targetForms = set()
# add simplified form, if different
simplifiedForm = cjkSimplified.getKangxiRadicalForm(
radicalIdx)
if simplifiedForm != cjk.getKangxiRadicalForm(radicalIdx):
targetForms.add(simplifiedForm)
# add simplified variant
targetForms.update(
set(cjkSimplified.getKangxiRadicalVariantForms(
radicalIdx)) \
- set(cjk.getKangxiRadicalVariantForms(radicalIdx)))
if radicalForm not in targetForms:
# cjklib is missing something
print(("No entry for radical form '%s' with index %d%s"
% (radicalForm, radicalIdx, variant))\
.encode(default_encoding))
databaseMissingEntryCount += 1
if targetForms - set([radicalForm]):
# CJKRadicals.txt is missing something
for form in targetForms - set([radicalForm]):
print(("Database entry '%s' with radical index %d%s" \
% (form, radicalIdx, variant) \
+ " not included in table")\
.encode(default_encoding))
noEntryCount += 1
# check equivalentForm
libraryEquivalentForm \
= cjk.getRadicalFormEquivalentCharacter(radicalForm)
if libraryEquivalentForm != equivalentForm:
print(("Equivalent radical form '%s' with index %d%s"
% (libraryEquivalentForm, radicalIdx, variant) \
+ " not backed by table: '%s'" % equivalentForm)\
.encode(default_encoding))
wrongEquivalentCount += 1
else:
print(("error reading line: '" + line + "'")\
.encode(default_encoding))
for radicalIdx in set(range(1, 215)) - seenRadicalFormIndices:
print(("No table entry for radical index %d" % radicalIdx)\
.encode(default_encoding))
noEntryCount += 1
for radicalIdx in set(range(1, 215)) - seenRadicalVariantIndices:
simplifiedForms = set()
# add simplified form, if different
simplifiedForm = cjkSimplified.getKangxiRadicalForm(
radicalIdx)
if simplifiedForm != cjk.getKangxiRadicalForm(radicalIdx):
simplifiedForms.add(simplifiedForm)
# add simplified variant
simplifiedForms.update(
set(cjkSimplified.getKangxiRadicalVariantForms(
radicalIdx)) \
- set(cjk.getKangxiRadicalVariantForms(radicalIdx)))
for form in simplifiedForms:
print(("No table entry for simplified radical %s with index %d'"
% (form, radicalIdx)).encode(default_encoding))
noEntryCount += 1
for radicalIdx in range(1, 215):
otherVariants = set(cjk.getKangxiRadicalVariantForms(radicalIdx)) \
- set(cjkSimplified.getKangxiRadicalVariantForms(radicalIdx))
for form in otherVariants:
print(("No table entry for variant %s with index %d'"
% (form, radicalIdx)).encode(default_encoding))
noEntryCount += 1
print("Total %d entries" % fileEntryCount \
+ ", %d missing from cjklib" % databaseMissingEntryCount \
+ ", %d mismatches in equivalent forms" % wrongEquivalentCount \
+ ", not found in source list: %d" % noEntryCount)
