def test_uri():
"""
test uri
"""
assert zh_ord('範例'.decode("utf8")) == 'p_7bc4_4f8b_v'
assert zh_chr('p_7bc4_4f8b_v') == '範例'
assert zh_chr(zh_ord('範例'.decode("utf8"))) == '範例'
def test_uri():
"""
test uri
"""
assert zh_ord('範例'.decode("utf8")) == 'p_7bc4_4f8b_v'
assert zh_ord('p_範例_v'.decode("utf8")) == 'p_70_5f_7bc4_4f8b_5f_76_v'
assert zh_chr('p_7bc4_4f8b_v') == '範例'
assert zh_chr(zh_ord('範例'.decode("utf8"))) == '範例'
def commandline():
"""zhpy, the python language in chinese
Accept options:
-i --input:
speficy the input source
-o --output:
speficy the output source
-p --python:
compile to python and run
-c --cmp:
input raw zhpy source and run
-e --encoding:
specify the encoding
--info:
zhpy information
-v --verbose:
show zhpy progress in detail
--tw:
convert python to twpy
--cn:
convert python to cnpy
help:
get information:
zhpy --info
interpreter usage:
zhpy [--tw | --cn]
command usage:
zhpy [-i | -p] input [-o] [output] [-e] [encoding] [-v]
::
$ zhpy input.py (.twpy, .cnpy) [arguments]
$ zhpy -i input.py (.twpy, .cnpy)
$ zhpy -i input.py -o output.py (.twpy, .cnpy)
$ zhpy -p input.py
script usage:
zhpy [-c] source [-e] [encoding] [-v]
convertor usage:
zhpy [--tw | --cn] input.py [-v]
::
$ zhpy --tw input.py [-v]
$ zhpy --cn input.py [-v]
"""
argv = sys.argv[1:]
os.chdir(os.getcwd())
source = None
target = None
encoding = None
raw_source = None
verbose = False
python = False
tw = False
cn = False
NonEnglish = False
# run as interpreter
if len(argv) == 0:
from interpreter import interpreter
import import_hook
display = os.getenv("LANG")
if display == None:
interpreter()
elif "zh_TW" in display:
interpreter('tw')
elif "zh_CN" in display:
interpreter('cn')
else:
interpreter()
sys.exit()
# run as script
# not accept any option
elif not argv[0].startswith('-'):
source = argv[0]
sys.argv = argv
# run as command
elif len(argv)==1:
if argv[0] == '--info':
from info import info
info()
sys.exit()
elif argv[0] == '-h' or argv[0] == '--help':
print commandline.__doc__
sys.exit()
# run as native interpreter
elif argv[0] == '--tw':
from interpreter import interpreter
import import_hook
interpreter('tw')
sys.exit()
elif argv[0] == '--cn':
from interpreter import interpreter
import import_hook
interpreter('cn')
sys.exit()
else:
print commandline.__doc__
sys.exit()
# accept "-c -e -v"
elif len(argv)>=2:
if argv[0] == '-c' or argv[0] == '--cmp':
raw_source = argv[1]
del(argv[:2])
if len(argv)>=2 and (argv[0] == '-e' or argv[0] == '--encoding'):
encoding = argv[1]
del(argv[:2])
if (len(argv)!=0) and (argv[0] == '-v' or \
argv[0] == '--verbose'):
verbose = True
# python to twpy
elif argv[0] == '--tw':
from pyzh import zh_chr, rev_annotator
rev_annotator()
source = argv[1]
filename = os.path.splitext(source)[0]
# remove extra .tw in filename
profix = os.path.splitext(filename)[-1]
if profix =='.tw':
filename = os.path.splitext(filename)[0]
del(argv[:2])
tw = True
target = "v_"+zh_chr(filename)+".twpy"
if (len(argv)!=0) and (argv[0] == '-v' or argv[0] == '--verbose'):
verbose = True
# python to cnpy
elif argv[0] == '--cn':
from pyzh import zh_chr, rev_annotator
rev_annotator()
source = argv[1]
filename = os.path.splitext(source)[0]
# remove extra .cn in filename
profix = os.path.splitext(filename)[-1]
if profix == '.cn':
filename = os.path.splitext(filename)[0]
del(argv[:2])
cn = True
target = "v_"+zh_chr(filename)+".cnpy"
if (len(argv)!=0) and (argv[0] == '-v' or argv[0] == '--verbose'):
verbose = True
# accept "-i -o -e -v" or "-p -e" or "-c -e -v"
elif argv[0] == '-i' or argv[0] == '--input':
source = argv[1]
del(argv[:2])
if (len(argv)!=0) and (argv[0] == '-v' or argv[0] == '--verbose'):
verbose = True
if len(argv)>=2 and (argv[0] == '-e' or argv[0] == '--encoding'):
encoding = argv[1]
del(argv[:2])
if (len(argv)!=0) and (argv[0] == '-v' or \
argv[0] == '--verbose'):
verbose = True
if len(argv)>=2 and (argv[0] == '-o' or argv[0] == '--output'):
target = argv[1]
del(argv[:2])
if len(argv)>=2 and (argv[0] == '-e' or \
argv[0] == '--encoding'):
encoding = argv[1]
del(argv[:2])
if (len(argv)!=0) and (argv[0] == '-v' or \
argv[0] == '--verbose'):
verbose = True
elif argv[0] == '-p' or argv[0] == '--python':
source = argv[1]
filename = os.path.splitext(source)[0]
# remove extra .tw in filename
profix = os.path.splitext(filename)[-1]
if (profix =='.tw') or (profix =='.cn'):
filename = os.path.splitext(filename)[0]
del(argv[:2])
# chinese filename to uri filename
for i in filename:
if i not in \
list('abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789_.'):
NonEnglish = True
print i, "file name is not in english"
break
if NonEnglish:
target = zh_ord(filename.decode('utf8'))+".py"
print "compile to python and run: %s"%(zh_ord(filename.decode('utf8'))+".py")
else:
target = "n_"+filename+".py"
print "compile to python and run: %s"%("n_"+filename+".py")
python = True
if (len(argv)!=0) and (argv[0] == '-v' or argv[0] == '--verbose'):
verbose = True
if len(argv)>=2 and (argv[0] == '-e' or argv[0] == '--encoding'):
encoding = argv[1]
del(argv[:2])
if (len(argv)!=0) and (argv[0] == '-v' or \
argv[0] == '--verbose'):
verbose = True
else:
print commandline.__doc__
sys.exit()
#convert
if raw_source:
if verbose:
print "run raw_source", raw_source
#annotator()
if encoding:
result = convertor(raw_source, verbose, encoding)
else:
result = convertor(raw_source, verbose)
zh_exec(result)
import import_hook
sys.exit()
if encoding:
print "encoding", encoding
if source:
if verbose:
print "input", source
# convertor
if(tw or cn):
if verbose:
print "convert python code to",
try:
from pyzh import rev_annotator, python_convertor
test = file(source, "r").read()
if tw:
print "twpy"
rev_annotator('tw', verbose)
result = python_convertor(test, lang='tw')
if cn:
print "cnpy"
rev_annotator('cn', verbose)
result = python_convertor(test, lang='cn')
except Exception, e:
print "zhpy Exception: you may input unproper source"
if verbose:
print e
sys.exit()
else:
try:
test = file(source, "r").read()
#annotator()
import import_hook
if encoding:
result = convertor(test, verbose, encoding)
else:
result = convertor(test, verbose)
except Exception, e:
print "zhpy Exception: you may input unproper source"
if verbose:
print e
sys.exit()
def commandline():
"""zhpy, the python language in chinese
Accept options:
-i --input:
speficy the input source
-o --output:
speficy the output source
-p --python:
compile to python and run
-c --cmp:
input raw zhpy source and run
-e --encoding:
specify the encoding
--info:
zhpy information
-v --verbose:
show zhpy progress in detail
--tw:
convert python to twpy
--cn:
convert python to cnpy
help:
get information:
zhpy --info
interpreter usage:
zhpy [--tw | --cn]
command usage:
zhpy [-i | -p] input [-o] [output] [-e] [encoding] [-v]
::
$ zhpy input.py (.twpy, .cnpy) [arguments]
$ zhpy -i input.py (.twpy, .cnpy)
$ zhpy -i input.py -o output.py (.twpy, .cnpy)
$ zhpy -p input.py
script usage:
zhpy [-c] source [-e] [encoding] [-v]
convertor usage:
zhpy [--tw | --cn] input.py [-v]
::
$ zhpy --tw input.py [-v]
$ zhpy --cn input.py [-v]
"""
argv = sys.argv[1:]
os.chdir(os.getcwd())
source = None
target = None
encoding = None
raw_source = None
verbose = False
python = False
tw = False
cn = False
NonEnglish = False
# run as interpreter
if len(argv) == 0:
from interpreter import interpreter
import zhimport
display = os.getenv("LANG")
if display == None:
interpreter()
elif "zh_TW" in display:
interpreter('tw')
elif "zh_CN" in display:
interpreter('cn')
else:
interpreter()
sys.exit()
# run as script
# not accept any option
elif not argv[0].startswith('-'):
source = argv[0]
sys.argv = argv
# run as command
elif len(argv) == 1:
if argv[0] == '--info':
from info import info
info()
sys.exit()
elif argv[0] == '-h' or argv[0] == '--help':
print commandline.__doc__
sys.exit()
# run as native interpreter
elif argv[0] == '--tw':
from interpreter import interpreter
import zhimport
interpreter('tw')
sys.exit()
elif argv[0] == '--cn':
from interpreter import interpreter
import zhimport
interpreter('cn')
sys.exit()
else:
print commandline.__doc__
sys.exit()
# accept "-c -e -v"
elif len(argv) >= 2:
if argv[0] == '-c' or argv[0] == '--cmp':
raw_source = argv[1]
del (argv[:2])
if len(argv) >= 2 and (argv[0] == '-e' or argv[0] == '--encoding'):
encoding = argv[1]
del (argv[:2])
if (len(argv)!=0) and (argv[0] == '-v' or \
argv[0] == '--verbose'):
verbose = True
# python to twpy
elif argv[0] == '--tw':
from pyzh import zh_chr, rev_annotator
rev_annotator()
source = argv[1]
filename = os.path.splitext(source)[0]
# remove extra .tw in filename
profix = os.path.splitext(filename)[-1]
if profix == '.tw':
filename = os.path.splitext(filename)[0]
del (argv[:2])
tw = True
target = "v_" + zh_chr(filename) + ".twpy"
if (len(argv) != 0) and (argv[0] == '-v'
or argv[0] == '--verbose'):
verbose = True
# python to cnpy
elif argv[0] == '--cn':
from pyzh import zh_chr, rev_annotator
rev_annotator()
source = argv[1]
filename = os.path.splitext(source)[0]
# remove extra .cn in filename
profix = os.path.splitext(filename)[-1]
if profix == '.cn':
filename = os.path.splitext(filename)[0]
del (argv[:2])
cn = True
target = "v_" + zh_chr(filename) + ".cnpy"
if (len(argv) != 0) and (argv[0] == '-v'
or argv[0] == '--verbose'):
verbose = True
# accept "-i -o -e -v" or "-p -e" or "-c -e -v"
elif argv[0] == '-i' or argv[0] == '--input':
source = argv[1]
del (argv[:2])
if (len(argv) != 0) and (argv[0] == '-v'
or argv[0] == '--verbose'):
verbose = True
if len(argv) >= 2 and (argv[0] == '-e' or argv[0] == '--encoding'):
encoding = argv[1]
del (argv[:2])
if (len(argv)!=0) and (argv[0] == '-v' or \
argv[0] == '--verbose'):
verbose = True
if len(argv) >= 2 and (argv[0] == '-o' or argv[0] == '--output'):
target = argv[1]
del (argv[:2])
if len(argv)>=2 and (argv[0] == '-e' or \
argv[0] == '--encoding'):
encoding = argv[1]
del (argv[:2])
if (len(argv)!=0) and (argv[0] == '-v' or \
argv[0] == '--verbose'):
verbose = True
elif argv[0] == '-p' or argv[0] == '--python':
source = argv[1]
filename = os.path.splitext(source)[0]
# remove extra .tw in filename
profix = os.path.splitext(filename)[-1]
if (profix == '.tw') or (profix == '.cn'):
filename = os.path.splitext(filename)[0]
del (argv[:2])
# chinese filename to uri filename
for i in filename:
if i not in \
list('abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789_.'):
NonEnglish = True
print i, "file name is not in english"
break
if NonEnglish:
target = zh_ord(filename.decode('utf8')) + ".py"
print "compile to python and run: %s" % (
zh_ord(filename.decode('utf8')) + ".py")
else:
target = "n_" + filename + ".py"
print "compile to python and run: %s" % ("n_" + filename +
".py")
python = True
if (len(argv) != 0) and (argv[0] == '-v'
or argv[0] == '--verbose'):
verbose = True
if len(argv) >= 2 and (argv[0] == '-e' or argv[0] == '--encoding'):
encoding = argv[1]
del (argv[:2])
if (len(argv)!=0) and (argv[0] == '-v' or \
argv[0] == '--verbose'):
verbose = True
else:
print commandline.__doc__
sys.exit()
#convert
if raw_source:
if verbose:
print "run raw_source", raw_source
annotator()
if encoding:
result = convertor(raw_source, verbose, encoding)
else:
result = convertor(raw_source, verbose)
zh_exec(result)
import zhimport
sys.exit()
if encoding:
print "encoding", encoding
if source:
if verbose:
print "input", source
# convertor
if (tw or cn):
if verbose:
print "convert python code to",
try:
from pyzh import rev_annotator, python_convertor
test = file(source, "r").read()
if tw:
print "twpy"
rev_annotator('tw', verbose)
result = python_convertor(test, lang='tw')
if cn:
print "cnpy"
rev_annotator('cn', verbose)
result = python_convertor(test, lang='cn')
except Exception, e:
print "zhpy Exception: you may input unproper source"
if verbose:
print e
sys.exit()
else:
try:
test = file(source, "r").read()
annotator()
import zhimport
if encoding:
result = convertor(test, verbose, encoding)
else:
result = convertor(test, verbose)
except Exception, e:
print "zhpy Exception: you may input unproper source"
if verbose:
print e
sys.exit()