def main(argv=None):
import argparse, sys
from seed.io.may_open import may_open_stdout, may_open_stdin
class Globals:
output_file_encoding = 'utf8'
input_file_encoding = 'utf8'
###################
parser = argparse.ArgumentParser(description='merge html <p>'
, epilog='''
<p></p> is the true seperator
"<p>abc</p> <p>def</p>" ==>> "<p>abcdef</p>"
''')
add_argument = parser.add_argument
add_argument('-i', '--input_file', type=str
, default=None
, help='the input file')
add_argument('-ie', '--input_encoding', type=str
, default = Globals.input_file_encoding
, help='the encoding of input file')
add_argument('-o', '--output_file', type=str
, default=None
, help='the output file')
add_argument('-oe', '--output_encoding', type=str
, default = Globals.output_file_encoding
, help='the encoding of output file')
args = parser.parse_args(argv)
with may_open_stdin(args.input_file, 'rt'
, encoding=args.input_encoding) as fin:
pseudo_htm = fin.read()
txt = merge_html_p(pseudo_htm)
if args.output_file is not None:
# try output_encoding
txt.encode(args.output_encoding)
with may_open_stdout(args.output_file, 'xt'
, encoding=args.output_encoding) as fout:
fout.write(txt)
#parser.exit(0)
return 0
##########
with may_open_stdout(args.output_file, 'xt'
, encoding=args.output_encoding) as fout\
, may_open_stdin(args.input_file, 'rt'
, encoding=args.input_encoding) as fin:
extract_fb_opf_items(fout, fin)
#parser.exit(0)
return 0
def main(args=None, /):
import argparse
from seed.io.may_open import may_open_stdin, may_open_stdout
parser = argparse.ArgumentParser(
description='factor_uint'
, epilog=''
, formatter_class=argparse.RawDescriptionHelpFormatter
)
parser.add_argument('--uint_le', type=int, required=True
, help='factor uint in [1..uint_le] only which coprime to [2..coprime_le]')
parser.add_argument('--coprime_le', type=int, required=True
, help='factor uint in [1..uint_le] only which coprime to [2..coprime_le]')
parser.add_argument('-o', '--output', type=str, default=None
, help='output file path')
parser.add_argument('-e', '--encoding', type=str
, default='utf8'
, help='output file encoding')
parser.add_argument('-f', '--force', action='store_true'
, default = False
, help='open mode for output file')
args = parser.parse_args(args)
encoding = args.encoding
omode = 'wt' if args.force else 'xt'
may_ofname = args.output
with may_open_stdout(may_ofname, omode, encoding=encoding) as fout:
show_factor_uint(fout=fout, uint_le=args.uint_le, coprime_le=args.coprime_le)
def main(args=None):
import argparse
from seed.io.may_open import may_open_stdout # may_open_stdin
from pprint import pprint
parser = argparse.ArgumentParser(
description=f'make max_cliques from simple_decomposed_chars3980'
, epilog=''
, formatter_class=argparse.RawDescriptionHelpFormatter
)
parser.add_argument('-o', '--output', type=str, default=None
, help='output file path')
parser.add_argument('-oe', '--output_encoding', type=str
, default='utf8'
, help='output file encoding')
parser.add_argument('-f', '--force', action='store_true'
, default = False
, help='open mode for output file')
args = parser.parse_args(args)
output_encoding = args.output_encoding
omode = 'wt' if args.force else 'xt'
var_name = 'doublesize2max_clique_srcs_dsts_pairs'
doublesize2max_clique_srcs_dsts_pairs = globals()[var_name]
may_ofname = args.output
if may_ofname is None:
may_ofname = this_folder / f'{var_name}.py'
with may_open_stdout(may_ofname, omode, encoding=output_encoding) as fout:
print(f'#{var_name} generated by {this_file_name}', file=fout);
print(f'{var_name} = \\', file=fout);
pprint(doublesize2max_clique_srcs_dsts_pairs, stream=fout)
def on_subcmd__cmp_branch_dir(sf, subcmd_name, parsed_args):
#see:[location4setting4the_two_kwargs]
#always_tribool_as_is_or_not_same_file
#bug:PP = _pairs__str2rpath
# see:str2rpath_encoding_pair
#
PP = tuple
kwargs4MkIsSameFile = dict(
always_tribool_as_is_or_not_same_file=ast.literal_eval(parsed_args.always_tribool_as_is_or_not_same_file)
, size_hash0_eq_as_same_file=parsed_args.size_hash0_eq_as_same_file
, mtime_eq_as_same_file=parsed_args.mtime_eq_as_same_file
, imay_max_size_threshold4cmp_content=parsed_args.imay_max_size_threshold4cmp_content
###########
, size_eq_as_same_file=False
, hash_eq_as_same_file=False
, mtime_ne_as_not_same_file=False
, _block_size=BLOCK_SIZE
)
kwargs4dir_cmp__relative = dict(
ignore_basename=None
, max_depth=None
)
(lhs_branch_idx4old, result_of_dir_cmp__relative) = type(sf)._main4subcmds.on_dir_cmp__relative(lhs_repository_extra_cache_root_dir_path=parsed_args.lhs_repository_extra_cache_root_dir_path, lhs_repository_root_dir_path=parsed_args.lhs_repository_root_dir_path, lhs_branch_name=parsed_args.lhs_branch_name, rhs_real_fsys_root_dir_path=parsed_args.rhs_real_fsys_root_dir_path, rhs_ignorefile_relative_path_encoding_pairs=PP(parsed_args.rhs_ignorefile_relative_path_encoding_pairs), kwargs4MkIsSameFile=kwargs4MkIsSameFile, kwargs4dir_cmp__relative=kwargs4dir_cmp__relative)
parsed_args.output
from seed.io.may_open import may_open_stdin, may_open_stdout
may_ofname = parsed_args.output
encoding = parsed_args.encoding
omode = 'wt' if parsed_args.force else 'xt'
with may_open_stdout(may_ofname, omode, encoding=encoding) as fout:
#see:[location4fmt_of_file4result_of_dir_cmp__relative__extended]
write__file4result_of_dir_cmp__relative__extended(fout, parsed_args.lhs_branch_name, lhs_branch_idx4old, PP(parsed_args.rhs_ignorefile_relative_path_encoding_pairs), result_of_dir_cmp__relative)
return
def main(args=None):
import argparse
from seed.io.may_open import may_open_stdout # may_open_stdin
from pprint import pprint
from pathlib import PurePath as Path
this_file = Path(__file__)
this_folder = this_file.parent
this_file_name = this_file.name
parser = argparse.ArgumentParser(
description=f'read “{Global.ifname}”',
epilog='',
formatter_class=argparse.RawDescriptionHelpFormatter)
parser.add_argument('-i',
'--input',
type=str,
default=None,
help='input file path')
parser.add_argument('-o',
'--output',
type=str,
default=None,
help='output file path')
parser.add_argument('-ie',
'--input_encoding',
type=str,
default=Global.iencoding,
help='input file encoding')
parser.add_argument('-oe',
'--output_encoding',
type=str,
default=Global.oencoding,
help='output file encoding')
parser.add_argument('-f',
'--force',
action='store_true',
default=False,
help='open mode for output file')
args = parser.parse_args(args)
input_encoding = args.input_encoding
output_encoding = args.output_encoding
omode = 'wt' if args.force else 'xt'
may_ifname = args.input
if may_ifname is None:
ifname = this_folder / Global.ifname
else:
ifname = may_ifname
with open(ifname, 'rt', encoding=input_encoding) as fin:
chars_3980 = read_中华字经(fin)
assert len(chars_3980) == Global.size
may_ofname = args.output
if may_ofname is None:
may_ofname = this_folder / Global.ofname
with may_open_stdout(may_ofname, omode, encoding=output_encoding) as fout:
print(f'#{Global.var_name} generated by {this_file_name}', file=fout)
print(f'{Global.var_name} = \\', file=fout)
pprint(chars_3980, stream=fout)
def main(argv=None):
import argparse
from seed.io.may_open import may_open_stdout
parser = argparse.ArgumentParser(
description='show the 8 trigrams'
)
parser.add_argument('-o', '--output', type=str, default = None
, help='output file path')
parser.add_argument('-e', '--encoding', type=str
, default='utf8'
, help='input/output file encoding')
parser.add_argument('-f', '--force', action='store_true'
, default = False
, help='open mode for output file')
parser.add_argument('-fun', '--output_fun_chars', action='store_true'
, default = False
, help='output fun_chars instead of grams')
args = parser.parse_args(argv)
encoding = args.encoding
omode = 'wt' if args.force else 'xt'
data = Data.fun_chars_data if args.output_fun_chars else Data.grams_data
may_ofname = args.output
with may_open_stdout(may_ofname, omode, encoding=encoding) as fout:
do_output(fout, data)
def main(args=None):
import argparse
from seed.io.may_open import may_open_stdin, may_open_stdout
parser = argparse.ArgumentParser(
description='make Windows special address link file',
epilog=f'spec_addr example: {windows_firewall_spec_addr__str!r}',
formatter_class=argparse.RawDescriptionHelpFormatter)
parser.add_argument('-a',
'--spec_addr',
type=str,
required=True,
help='spec_addr; for example, see epilog')
parser.add_argument('-o',
'--output',
type=str,
default=None,
help='output file path')
parser.add_argument('-f',
'--force',
action='store_true',
default=False,
help='open mode for output file')
args = parser.parse_args(args)
omode = 'wb' if args.force else 'xb'
lnk_file_bytes = mk_windows_spec_lnk(args.spec_addr)
may_ofname = args.output
with may_open_stdout(may_ofname, omode, encoding=None) as fout:
fout.write(lnk_file_bytes)
def main(args=None, /):
import argparse
from seed.io.may_open import may_open_stdin, may_open_stdout
parser = argparse.ArgumentParser(
description='python eval then hex then print'
, epilog=''
, formatter_class=argparse.RawDescriptionHelpFormatter
)
parser.add_argument('-i', '--input', type=str, nargs='*', default=[]
, help='input python expression')
parser.add_argument('-o', '--output', type=str, default=None
, help='output file path')
parser.add_argument('-e', '--encoding', type=str
, default='utf8'
, help='input/output file encoding')
parser.add_argument('-f', '--force', action='store_true'
, default = False
, help='open mode for output file')
args = parser.parse_args(args)
encoding = args.encoding
omode = 'wt' if args.force else 'xt'
#may_ifname = args.input
#with may_open_stdin(may_ifname, 'rt', encoding=encoding) as fin:
exprs = args.input
may_ofname = args.output
with may_open_stdout(may_ofname, omode, encoding=encoding) as fout:
for expr in exprs:
eval_then_show(expr, fout=fout)
def main(argv=None):
import argparse
from seed.io.may_open import may_open_stdin, may_open_stdout
parser = argparse.ArgumentParser(
description='extract first content_div of article on 360doc.com'
)
parser.add_argument('-e', '--encoding', type=str, default='utf8', help='input/output file encoding')
parser.add_argument('-i', '--input', type=str, default = None
, help='input file path')
parser.add_argument('-o', '--output', type=str, default = None
, help='output file path')
parser.add_argument('-f', '--force', action='store_true'
, default = False
, help='open mode for output file')
parser.add_argument('-url', '--url', type=str, default = None
, help='input webpage url')
args = parser.parse_args(argv)
encoding = args.encoding
omode = 'wt' if args.force else 'xt'
if args.input is not None and args.url is not None:
raise ValueError('input both file and url at same time')
if args.url is not None:
with open_webpage(args.url) as fin:
content_div = extract_360doc_com(fin)
else:
may_ifname = args.input
try:
# open as text file
with may_open_stdin(may_ifname, 'rt', encoding=encoding) as fin:
content_div = extract_360doc_com(fin)
except UnicodeError:
assert may_ifname is not None
ifname = may_ifname
# open as binary file
with open(ifname, 'rb') as fin:
content_div = extract_360doc_com(fin)
if 0:
print(len(content_div))
print(repr(content_div[5216:]))
for i in range(len(content_div)):
if ord(content_div[i]) > 0x7f:
print(i)
print(repr(content_div[i:]))
break
return
may_ofname = args.output
with may_open_stdout(may_ofname, omode, encoding=encoding) as fout:
fout.write(content_div)
parser.exit(0)
return 0
def main(argv=None):
import argparse
from seed.io.may_open import may_open_stdin, may_open_stdout
encodingI = 'ascii'
encodingO = 'utf8'
parser = argparse.ArgumentParser(
description='simple encrypt ascii text'
, epilog=r'only " " and "\n" are allowed, other control/whitespace should not occur in input text'
#, formatter_class=argparse.RawDescriptionHelpFormatter
)
#parser.add_argument('-e', '--encoding', type=str, default='utf8', help='input/output file encoding')
parser.add_argument('cmd', type=str, choices='encrypt decrypt'.split()
, help='encrypt/decrypt - treat input as cleartext/ciphertext')
parser.add_argument('psw', type=str
, help='password: regex = [0-9a-f]*')
parser.add_argument('-i', '--input', type=str, default = None
, help='input file path')
parser.add_argument('-o', '--output', type=str, default = None
, help='output file path')
parser.add_argument('-f', '--force', action='store_true'
, default = False
, help='open mode for output file')
args = parser.parse_args(argv)
psw = args.psw
if not all(ch in aCrypt.char2idxP for ch in psw): raise TypeError
omode = 'wt' if args.force else 'xt'
does_encrypt = args.cmd == 'encrypt'
iencoding = encodingI if does_encrypt else encodingO
oencoding = encodingO if does_encrypt else encodingI
may_ifname = args.input
with may_open_stdin(may_ifname, 'rt', encoding=iencoding) as fin:
input_text = ''.join(fin)
if does_encrypt:
message = input_text
ciphertext = aCrypt.encrypt(psw, message)
output_text = ciphertext
else:
ciphertext = input_text
message = aCrypt.decrypt(psw, ciphertext)
output_text = message
may_ofname = args.output
with may_open_stdout(may_ofname, omode, encoding=oencoding) as fout:
fout.write(output_text)
parser.exit(0)
return 0
def main(args=None):
import argparse
from seed.io.may_open import may_open_stdin, may_open_stdout
choices = [
ls笔顺码字符范围__closed_rngs, cmp3, prepare_for_汉字粗拆分, prepare_for_2汉字粗拆分2
]
choices = [f.__name__ for f in choices]
parser = argparse.ArgumentParser(
description="汉字相关字符范围",
epilog="",
formatter_class=argparse.RawDescriptionHelpFormatter)
r"""
parser.add_argument('-i', '--input', type=str, default=None
, help='input file path')
#"""
parser.add_argument(
'-do',
'--do',
type=str,
required=True #, default=None
,
choices=choices,
help='input file path')
parser.add_argument('-o',
'--output',
type=str,
default=None,
help='output file path')
parser.add_argument('-e',
'--encoding',
type=str,
default='utf8',
help='input/output file encoding')
parser.add_argument('-f',
'--force',
action='store_true',
default=False,
help='open mode for output file')
args = parser.parse_args(args)
encoding = args.encoding
omode = 'wt' if args.force else 'xt'
do = args.do
f = globals()[do]
r"""
may_ifname = args.input
with may_open_stdin(may_ifname, 'rt', encoding=encoding) as fin:
#"""
may_ofname = args.output
with may_open_stdout(may_ofname, omode, encoding=encoding) as fout:
f(fout=fout)
def on_subcmd__get_branch_size(sf, subcmd_name, parsed_args):
lhs_branch_sz = type(sf)._main4subcmds.on_get_branch_size(lhs_repository_extra_cache_root_dir_path=parsed_args.lhs_repository_extra_cache_root_dir_path, lhs_repository_root_dir_path=parsed_args.lhs_repository_root_dir_path, lhs_branch_name=parsed_args.lhs_branch_name)
#print(lhs_branch_sz)
parsed_args.output
from seed.io.may_open import may_open_stdin, may_open_stdout
may_ofname = parsed_args.output
encoding = parsed_args.encoding
omode = 'wt' if parsed_args.force else 'xt'
with may_open_stdout(may_ofname, omode, encoding=encoding) as fout:
print(lhs_branch_sz, file=fout)
return
def main(argv=None):
import argparse, sys
parser = argparse.ArgumentParser(
description='translate characters from lower to upper case')
parser.add_argument('-i',
'--input',
type=str,
default=None,
help='input file name')
parser.add_argument('-o',
'--output',
type=str,
default=None,
help='output file name')
parser.add_argument('-e',
'--encoding',
type=str,
default='utf8',
help='encoding of input/output file')
parser.add_argument('-f',
'--force',
action='store_true',
default=False,
help='open mode for output file')
parser.add_argument(
'-s',
'--sep',
type=str,
default=None,
help='seperator string of output file which has 2 columes')
parser.add_argument('-u',
'--upper',
action='store_true',
default=False,
help='lower2upper instead of upper2lower')
args = parser.parse_args(argv)
encoding = args.encoding
omode = 'wt' if args.force else 'xt'
may_ifname = args.input
may_ofname = args.output
with may_open_stdin(may_ifname, 'rt', encoding=encoding, newline='')\
as fin\
, may_open_stdout(may_ofname, omode, encoding=encoding, newline='')\
as fout:
lower_file(fout, fin, upper=args.upper, sep=args.sep)
parser.exit(0)
return 0
def main(argv=None):
import argparse
import sys
parser = argparse.ArgumentParser(
description='convert torrent file to dict'
, epilog=epilog_str
, formatter_class=argparse.RawDescriptionHelpFormatter
)
parser.add_argument('input', type=str
, help='path to the input torrent file')
parser.add_argument('-ie', '--input_encoding', type=str
, default='utf8'
, help='encoding to strings in input file')
parser.add_argument('-pp', '--pretty_print', action='store_true'
, default=False
, help='pretty print output')
parser.add_argument('-o', '--output', type=str
, default=None
, help='output file path')
parser.add_argument('-oe', '--output_encoding', type=str
, default='utf8'
, help='output file encoding')
parser.add_argument('--mode', choices='exclusive append overwrite'.split()
, default='exclusive'
, help='mode for open output file')
args = parser.parse_args()
iencoding = args.input_encoding
result = parse_torrent(args.input, encoding=iencoding)
#print_err('piece length =', result['info']['piece length'])
#print_err('len(pieces) =', len(result['info']['pieces']))
if args.pretty_print:
# pprint
def xprint(obj, *, file):
pprint(obj, stream=file)
else:
# print
def xprint(obj, *, file):
print(obj, file=file)
oencoding = args.output_encoding
mode = {'exclusive':'x', 'append':'a', 'overwrite':'w'}[args.mode]
with may_open_stdout(args.output, mode+'t', encoding=oencoding) as fout:
xprint(result, file=fout)
parser.exit(0)
return 0
def main(args=None):
import argparse
from seed.io.may_open import may_open_stdin, may_open_stdout
parser = argparse.ArgumentParser(
description='invert bytes of file',
epilog='',
formatter_class=argparse.RawDescriptionHelpFormatter)
parser.add_argument('-i',
'--input',
type=str,
default=None,
help='input file path')
parser.add_argument('-o',
'--output',
type=str,
default=None,
help='output file path')
parser.add_argument('-f',
'--force',
action='store_true',
default=False,
help='open mode for output file')
parser.add_argument(
'-a',
'--auto_name_output',
action='store_true',
default=False,
help='add/remove ".inv" to input fname for output fname')
args = parser.parse_args(args)
omode = 'wb' if args.force else 'xb'
may_ifname = args.input
may_ofname = args.output
if (args.auto_name_output and may_ofname is None
and may_ifname is not None):
ext = '.inv'
if may_ifname.endswith(ext):
#bug:may_ofname = may_ifname[-len(ext):]
may_ofname = may_ifname[:-len(ext)]
else:
may_ofname = may_ifname + ext
with may_open_stdin(may_ifname, 'rb', encoding=None) as fin:
with may_open_stdout(may_ofname, omode, encoding=None) as fout:
while 1:
bs = fin.read(BLOCK_SIZE)
if not bs: break
bs = bs.translate(TABLE)
fout.write(bs)
def main(sf):
bs4_ops = sf._ops
oprint = sf.oprint
#with open(sf.may_ofname, sf.omode, encoding=sf.oencoding) as fout:
with may_open_stdout(sf.may_ofname, sf.omode, encoding=sf.oencoding) as fout:
sf.fout = fout
for idx, (usrdata, path) in enumerate(sf.iter_usrdata_htmlpath_pairs()):
html_fname = Path(path)
if sf.pre_break(idx, usrdata, html_fname): break
if sf.skip(idx, usrdata, html_fname): continue
html_doc = html_fname.read_text(encoding=sf.iencoding)
bs4_obj = bs4_ops.建(html_doc, markup_lang=MarkupLang.HTML)
sf.output(bs4_ops, bs4_obj, idx, usrdata, html_fname)
if sf.post_break(idx, usrdata, html_fname): break
def main(argv=None):
import argparse
import sys
parser = argparse.ArgumentParser(
description='sort and unique chars in text.')
parser.add_argument('-e',
'--encoding',
type=str,
default='utf8',
help='input/output file encoding')
parser.add_argument('-f',
'--force',
action='store_true',
default=False,
help='open mode for output file')
parser.add_argument('-i',
'--input',
type=str,
help='path to the input novel text file')
parser.add_argument('-o',
'--output',
type=str,
help='path to the output file')
parser.add_argument('-u',
'--repr_as_unicode',
action='store_true',
default=False,
help='output char in format \\UXXXXXXXX')
args = parser.parse_args(argv)
encoding = args.encoding
omode = 'wt' if args.force else 'xt'
may_ifname = args.input
with may_open_stdin(may_ifname, 'rt', encoding=encoding) as fin:
#all_chars = file2unique_sorted_char_string(fin)
all_chars = file2all_char_set(fin)
#txt = chars2sorted_char_string(all_chars)
s = chars2sorted_char_string(all_chars)
if args.repr_as_unicode:
s = repr_string_as_unicode(s)
may_ofname = args.output
with may_open_stdout(may_ofname, omode, encoding=encoding) as fout:
print(s, file=fout)
def main(argv=None):
import argparse
from seed.io.may_open import may_open_stdin, may_open_stdout
parser = argparse.ArgumentParser(
description='parse pythoncoded_rules_in_str',
epilog=example_doc,
formatter_class=argparse.RawDescriptionHelpFormatter)
parser.add_argument('-i',
'--input',
type=str,
default=None,
help='input file path')
parser.add_argument('-o',
'--output',
type=str,
default=None,
help='output file path')
parser.add_argument('-e',
'--encoding',
type=str,
default='utf8',
help='input/output file encoding')
parser.add_argument('-f',
'--force',
action='store_true',
default=False,
help='open mode for output file')
args = parser.parse_args(argv)
encoding = args.encoding
omode = 'wt' if args.force else 'xt'
may_ifname = args.input
with may_open_stdin(may_ifname, 'rt', encoding=encoding) as fin:
pythoncoded_rules_in_str = fin.read()
python_code_str_ex = parse_ex(pythoncoded_rules_in_str,
name2count=None,
the_input_parameter_name='p',
with_class_keyword=False)
head_str, tail_str, name2count = python_code_str_ex
may_ofname = args.output
with may_open_stdout(may_ofname, omode, encoding=encoding) as fout:
fout.write(head_str)
fout.write(tail_str)
def main(argv=None):
import argparse, sys
from seed.io.may_open import may_open_stdout, may_open_stdin
class Globals:
output_file_encoding = 'utf8'
input_file_encoding = 'utf8'
###################
parser = argparse.ArgumentParser(description='extract epub/OPS/fb.opf',
epilog='''
extract epub/OPS/fb.opf::manifest.item.href
where item["media-type"]=="application/xhtml+xml"
''')
add_argument = parser.add_argument
add_argument('-i',
'--input_file',
type=str,
default=None,
help='the input file')
add_argument('-ie',
'--input_encoding',
type=str,
default=Globals.input_file_encoding,
help='the encoding of input file')
add_argument('-o',
'--output_file',
type=str,
default=None,
help='the output file')
add_argument('-oe',
'--output_encoding',
type=str,
default=Globals.output_file_encoding,
help='the encoding of output file')
args = parser.parse_args(argv)
with may_open_stdout(args.output_file, 'xt'
, encoding=args.output_encoding) as fout\
, may_open_stdin(args.input_file, 'rt'
, encoding=args.input_encoding) as fin:
extract_fb_opf_items(fout, fin)
#parser.exit(0)
return 0
def main(args=None, /):
import argparse
from seed.io.may_open import may_open_stdin, may_open_stdout
parser = argparse.ArgumentParser(
description='简繁对称字-middle-parse',
epilog='',
formatter_class=argparse.RawDescriptionHelpFormatter)
parser.add_argument('-i',
'--input',
type=str,
default=None,
help='input file path')
parser.add_argument('-o',
'--output',
type=str,
default=None,
help='output file path')
parser.add_argument('-e',
'--encoding',
type=str,
default='utf8',
help='input/output file encoding')
parser.add_argument('-f',
'--force',
action='store_true',
default=False,
help='open mode for output file')
args = parser.parse_args(args)
encoding = args.encoding
omode = 'wt' if args.force else 'xt'
may_ifname = args.input
with may_open_stdin(may_ifname, 'rt', encoding=encoding) as fin:
s = parser4pseudo_symmetric_hz_from_completed_chars_3980(fin)
may_ofname = args.output
with may_open_stdout(may_ofname, omode, encoding=encoding) as fout:
print(
f'###parser4pseudo_symmetric_hz_from_completed_chars_3980:total={len(s)}###',
file=fout)
print(s, file=fout)
def main(args=None):
import argparse
from seed.io.may_open import may_open_stdout # may_open_stdin
from pprint import pprint
from pathlib import PurePath as Path
this_file = Path(__file__)
this_folder = this_file.parent
this_file_name = this_file.name
parser = argparse.ArgumentParser(
description=
f'make sm2ym_num_graph__for_good_hanzis from sm2ym2num2good_hanzis',
epilog='',
formatter_class=argparse.RawDescriptionHelpFormatter)
parser.add_argument('-o',
'--output',
type=str,
default=None,
help='output file path')
parser.add_argument('-oe',
'--output_encoding',
type=str,
default='utf8',
help='output file encoding')
parser.add_argument('-f',
'--force',
action='store_true',
default=False,
help='open mode for output file')
args = parser.parse_args(args)
output_encoding = args.output_encoding
omode = 'wt' if args.force else 'xt'
var_name = 'sm2ym_num_graph__for_good_hanzis'
sm2ym_num_graph = globals()[var_name]
may_ofname = args.output
if may_ofname is None:
may_ofname = this_folder / f'{var_name}.py'
with may_open_stdout(may_ofname, omode, encoding=output_encoding) as fout:
print(f'#{var_name} generated by {this_file_name}', file=fout)
print(f'{var_name} = \\', file=fout)
pprint(sm2ym_num_graph, stream=fout)
def main(argv=None):
import argparse, sys
parser = argparse.ArgumentParser(
description='merge lines into paragraph for novel text')
parser.add_argument('-i',
'--input',
type=str,
default=None,
help='input file name')
parser.add_argument('-o',
'--output',
type=str,
default=None,
help='output file name')
parser.add_argument('-e',
'--encoding',
type=str,
default='utf8',
help='encoding of input/output file')
parser.add_argument('-f',
'--force',
action='store_true',
default=False,
help='open mode for output file')
args = parser.parse_args(argv)
encoding = args.encoding
omode = 'wt' if args.force else 'xt'
may_ifname = args.input
with may_open_stdin(may_ifname, 'rt', encoding=encoding) as fin:
case_line_pairs = novel_merge_lines_into_paragraph__pattern(
GlobalArgsExample.not_merge_pattern,
GlobalArgsExample.transparent_pattern,
GlobalArgsExample.case_pattern_pairs, iter(fin))
case_line_pairs = list(case_line_pairs)
#print(case_line_pairs)
may_ofname = args.output
with may_open_stdout(may_ofname, omode, encoding=encoding) as fout:
for line in merge_case_line_pairs(case_line_pairs):
print(line, file=fout)
def main(argv=None):
import argparse
from seed.io.may_open import may_open_stdin, may_open_stdout
parser = argparse.ArgumentParser(
description='simple encape text to html'
, epilog=r'''only "<>&" and "\"\'" if quote=True will be escaped.'''
#, formatter_class=argparse.RawDescriptionHelpFormatter
)
parser.add_argument('-e', '--encoding', type=str, default='utf8', help='input/output file encoding')
parser.add_argument('-i', '--input', type=str, default = None
, help='input file path')
parser.add_argument('-o', '--output', type=str, default = None
, help='output file path')
parser.add_argument('-f', '--force', action='store_true'
, default = False
, help='open mode for output file')
parser.add_argument('-q', '--quote', action='store_true'
, default = False
, help=r'''escape "\"\'" too; otherwise only "<>&" be escaped''')
args = parser.parse_args(argv)
encoding = args.encoding
omode = 'wt' if args.force else 'xt'
may_ifname = args.input
with may_open_stdin(may_ifname, 'rt', encoding=encoding) as fin:
input_text = ''.join(fin)
output_text = escape(input_text, args.quote)
may_ofname = args.output
with may_open_stdout(may_ofname, omode, encoding=encoding) as fout:
fout.write(output_text)
parser.exit(0)
return 0
def main(argv=None):
'''
'''
import argparse, sys
parser = argparse.ArgumentParser(description='list paths')
add_argument = parser.add_argument
add_argument('glob_patterns',
type=str,
nargs='+',
metavar='GLOB_PATTERN',
help='glob_patterns for list paths')
add_argument('-r',
'--recursive',
action='store_true',
default=False,
help='recursive search')
add_argument('-o',
'--output_file',
type=str,
default=None,
help='the output file')
add_argument('-oe',
'--output_encoding',
type=str,
default=Globals.output_file_encoding,
help='the encoding of output file')
args = parser.parse_args(argv)
with may_open_stdout(args.output_file, 'xt',
encoding=args.output_encoding) as fout:
for glob_pattern in args.glob_patterns:
for path in iglob(glob_pattern, recursive=args.recursive):
print(path, file=fout)
#parser.exit()
return
def main(args=None):
import argparse
from seed.io.may_open import may_open_stdin, may_open_stdout
parser = argparse.ArgumentParser(
description='format html/xml by well indent'
, epilog=''
, formatter_class=argparse.RawDescriptionHelpFormatter
)
parser.add_argument('-i', '--input', type=str, default=None
, help='input file path')
parser.add_argument('-o', '--output', type=str, default=None
, help='output file path')
parser.add_argument('-e', '--encoding', type=str
, default='utf8'
, help='input/output file encoding')
parser.add_argument('-f', '--force', action='store_true'
, default = False
, help='open mode for output file')
parser.add_argument('-iw', '--indent_width', type=int
, default = 1
, help='the number of indent spaces for children')
args = parser.parse_args(args)
encoding = args.encoding
omode = 'wt' if args.force else 'xt'
may_ifname = args.input
with may_open_stdin(may_ifname, 'rt', encoding=encoding) as fin:
soup = BeautifulSoup(fin, 'lxml')
txt = soup.prettify()
txt = replace_indent_spaces(args.indent_width, txt)
may_ofname = args.output
with may_open_stdout(may_ofname, omode, encoding=encoding) as fout:
fout.write(txt)
def main(args=None, /):
import argparse
from seed.io.may_open import may_open_stdin, may_open_stdout
parser = argparse.ArgumentParser(
description='繁简字信息相关',
epilog='',
formatter_class=argparse.RawDescriptionHelpFormatter)
parser.add_argument('case',
type=str,
choices=sorted(main_routines.keys()),
help='choose one main_routine')
parser.add_argument('-o',
'--output',
type=str,
default=None,
help='output file path')
parser.add_argument('-e',
'--encoding',
type=str,
default='utf8',
help='input/output file encoding')
parser.add_argument('-f',
'--force',
action='store_true',
default=False,
help='open mode for output file')
args = parser.parse_args(args)
encoding = args.encoding
omode = 'wt' if args.force else 'xt'
main_routine = main_routines[args.case]
may_ofname = args.output
with may_open_stdout(may_ofname, omode, encoding=encoding) as fout:
main_routine(fout)
parser.add_argument('-o', '--output', type=str, default=None
, help='output file path')
parser.add_argument('-oe', '--output_encoding', type=str
, default='utf8'
, help='output file encoding')
parser.add_argument('-f', '--force', action='store_true'
, default = False
, help='open mode for output file')
args = parser.parse_args(args)
oencoding = args.output_encoding
omode = 'wt' if args.force else 'xt'
nm = args.name4target
case = args.post_process
post_process = case2post_process[case]
xxx = case2name2xxx[case][nm]
may_ofname = args.output
with may_open_stdout(may_ofname, omode, encoding=oencoding) as fout:
post_process(nm, xxx, fout=fout)
if __name__ == "__main__":
main()
def main(argv=None):
'''
'''
import argparse, sys
parser = argparse.ArgumentParser(description='extract info from files',
allow_abbrev=False,
epilog='''
NOTE:
extract_data_cmd -oe gbk -o ./1+2.txt -ie ascii -i ./paths.txt nn_ns.filedir._extractor_example.main --encoding=utf8
where:
-ie ascii
the encoding of input file which contains paths to files from which data were extracted.
arg of this program
--encodinga utf8
the encoding of all files from which data were extracted.
arg of nn_ns.filedir._extractor_example
glob_cmd ./*.html | line_filter_cmd chapter(\d+)\.html --group_names 1 --INT_GROUP | sort_lines_cmd --line_type=KEY_LINE | extract_data_cmd -oe gbk -o ./1+2.txt nn_ns.filedir._extractor_example.main --encoding=utf8
''')
add_argument = parser.add_argument
add_argument('extractor',
type=str,
help='fullname of a python function: e.g. math.log2')
add_argument('-i',
'--input_file',
type=str,
default=None,
help='the input file which contains paths')
add_argument('-ie',
'--input_encoding',
type=str,
default=Globals.input_file_encoding,
help='the encoding of input file')
add_argument('-o',
'--output_file',
type=str,
default=None,
help='the output file')
add_argument('-oe',
'--output_encoding',
type=str,
default=Globals.output_file_encoding,
help='the encoding of output file')
args, unknown_args = parser.parse_known_args(argv)
_args, _kwargs = parse_unknown_args(unknown_args)
_kwargs = dict(_kwargs)
extractor_qname = args.extractor
extractor = import_object(extractor_qname)
# extractor :: (fout, input_fname, **kwargs) -> None
with may_open_stdout(args.output_file, 'xt'
, encoding=args.output_encoding) as fout\
, may_open_stdin(args.input_file, 'rt'
, encoding=args.input_encoding) as fin:
for line in fin:
if line[-1:] == '\n':
line = line[:-1]
path = line
extractor(fout, path, *_args, **_kwargs)
#parser.exit()
return
def main(argv=None):
import argparse
from seed.io.may_open import may_open_stdin, may_open_stdout
parser = argparse.ArgumentParser(
description='extract text on ctext.org or ctext.cn')
parser.add_argument('-e',
'--encoding',
type=str,
default='utf8',
help='input/output file encoding')
parser.add_argument('-i',
'--input',
type=str,
default=None,
help='input file path')
parser.add_argument('-o',
'--output',
type=str,
default=None,
help='output file path')
parser.add_argument('-f',
'--force',
action='store_true',
default=False,
help='open mode for output file')
parser.add_argument('--append',
action='store_true',
default=False,
help='open mode for output file')
parser.add_argument('-V',
'--verbose',
action='store_true',
default=False,
help='show path/url that opened')
parser.add_argument('-url',
'--url',
type=str,
default=None,
help='input webpage url')
parser.add_argument(
'-rng',
'--range',
type=int,
default=None,
nargs=2,
help='input webpage url range (first, last); {url}/{i} for i in range')
parser.add_argument(
'-ifmt',
'--index_format',
type=str,
default='{}',
help='index python format for webpage url; base_url/{fmt}')
parser.add_argument('--timeout',
type=int,
default=10,
help='timeout for urllib')
parser.add_argument('--time_sep',
type=int,
default=1,
help='time space between two downloads')
parser.add_argument('--without_book_title',
action='store_true',
default=False,
help='not show book_title')
parser.add_argument(
'--book_title_at',
type=str,
default=None,
help='extended url for book_title; {base_url}{book_title_at}')
args = parser.parse_args(argv)
encoding = args.encoding
omode = 'wt' if args.force else 'xt'
if args.append:
omode = 'at'
if args.input is not None and args.url is not None:
raise ValueError('input both file and url at same time')
if args.url is not None:
if args.range is None:
title, txt = extract_ctext_org__url(args.url,
verbose=args.verbose,
timeout=args.timeout)
may_book_title = None
begin = 0
result = (may_book_title, begin, [(title, txt)])
else:
first, last = args.range
begin, end = first, last + 1
rng = range(begin, end)
base_url = args.url
index_format = args.index_format
it = iter_extract_ctext_org__url_rng(base_url,
rng,
index_format,
verbose=args.verbose,
timeout=args.timeout,
time_sep=args.time_sep)
if args.without_book_title:
may_book_title = None
else:
if args.book_title_at is None:
book_title_url = base_url
else:
book_title_url = f'{base_url}{args.book_title_at}'
book_title, _ = extract_ctext_org__url(book_title_url,
verbose=args.verbose,
timeout=args.timeout)
may_book_title = book_title
begin = begin
#result = (may_book_title, begin, list(it))
result = (may_book_title, begin, iter(it))
else:
may_ifname = args.input
try:
# open as text file
with may_open_stdin(may_ifname, 'rt', encoding=encoding) as fin:
title, txt = extract_ctext_org(fin,
verbose=args.verbose,
timeout=args.timeout)
except UnicodeError:
assert may_ifname is not None
ifname = may_ifname
# open as binary file
with open(ifname, 'rb') as fin:
title, txt = extract_ctext_org(fin,
verbose=args.verbose,
timeout=args.timeout)
may_book_title = None
begin = 0
result = (may_book_title, begin, [(title, txt)])
#result :: (may_book_title, begin, [(title, txt)])
may_ofname = args.output
with may_open_stdout(may_ofname, omode, encoding=encoding) as fout:
def fprint(*args, **kwargs):
print(*args, file=fout, **kwargs)
may_book_title, begin, title_txt_pairs = result
if not args.without_book_title:
fprint(f'[book]:{may_book_title}')
for i, (title, txt) in enumerate(title_txt_pairs, begin):
fprint(f'[chapter{i}]:{title}')
fprint(txt)
parser.exit(0)
return 0
def main(args=None):
import argparse
from seed.io.may_open import may_open_stdin, may_open_stdout
#import skimage.io as image_io
import imageio as image_io
read_image = image_io.imread
del image_io
parser = argparse.ArgumentParser(
description='convert grey_image to binary_image',
epilog='',
formatter_class=argparse.RawDescriptionHelpFormatter)
parser.add_argument('-i',
'--input',
type=str,
required=True,
help='input file path')
parser.add_argument('-o',
'--output',
type=str,
default=None,
help='output file path')
parser.add_argument('-f',
'--force',
action='store_true',
default=False,
help='open mode for output file')
parser.add_argument('-F',
'--flip',
action='store_true',
default=False,
help='flip final binary_image')
parser.add_argument('-G',
'--as_grey',
action='store_true',
default=False,
help='convert color_image to grey_image first')
parser.add_argument(
'-T',
'--threshold_coeff',
type=float,
required=True,
nargs=3,
help='threshold_coeff A B C; threshold = A*min+B*mean+C+max')
'''
parser.add_argument('-out_txt', '--output_as_text', action='store_true'
, default = False
, help='output binary_image as text')
'''
args = parser.parse_args(args)
encoding = None
omode = 'wb' if args.force else 'xb'
ifname = args.input
image = read_image(ifname, as_gray=args.as_grey)
if not is_grey_image(image): raise Exception('not grey_image')
grey_image = image
A, B, C = args.threshold_coeff
threshold = A * grey_image.min() + B * grey_image.mean(
) + C * grey_image.max()
binary_image = grey_image2binary_image(grey_image,
threshold,
negative=args.flip)
text_grey_image = binary_image2text_grey_image(binary_image)
may_ofname = args.output
with may_open_stdout(may_ofname, omode, encoding=encoding) as fout:
for byte_row in grey_image2iter_byte_rows(text_grey_image):
fout.write(byte_row)
fout.write(b'\n')
