def del_comment(soql):
result = soql
if soql:
# TODO
# soql = soql.strip().replace('\t', ' ').replace('\r\n', ' ').replace('\n', ' ')
soql = soql.strip().replace('\t', ' ')
# delete // comment
result1, number = re.subn("//.*", "", soql)
# delete /**/ comment
result, number = re.subn("/\*([\s|\S]*?)\*/", "", result1, flags=re.M)
result = result.strip()
# show_in_panel(result)
return result
# get sobject name from soql
python类subn()的实例源码
def pre_process(dates):
# \u5e74\u6708\u65e5
# dates = [re.subn(r'[\u4e00-\u5e73]|[\u5e75-\u6707]', '', tm)[0] for tm in dates]
# dates = [re.subn(r'[\u6709-\u65e4]|[\u65e6-\u9fa5]', '', tm)[0] for tm in dates]
# ???
dates = dates[:int(len(dates) / 2)]
# ?????100??
dates = [d for d in dates if 100 > len(d) > 0]
# ????????
dates = [d.replace('\n', ' ').replace('\t', ' ').replace('\b', ' ').replace(' ', ' ') for d in dates]
# ????????????????
new_dates = []
for v in dates:
v = re.sub('\A\s*', '', v)
v = re.sub('\s*\Z', '', v)
v = re.sub('\s+', ' ', v)
new_dates.append(v)
# ???????????????????????
shorter_dates = []
for v in new_dates:
ffdi = find_first_digit_index(v)
if ffdi:
shorter_dates.append(v[ffdi-1:])
return shorter_dates
def _rename_schema(self, schema):
""" Rename a schema name and return new name
Args:
schema (str): schema nae
Returns:
str
"""
try:
return self._schema_new_names[schema]
except KeyError:
new_name = schema
for pattern, repl in self.schema_rename.items():
new_name, subs_made = re.subn(pattern, repl, schema)
if subs_made:
break
self._schema_new_names[schema] = new_name
return new_name
def _rename_table(self, schema, table):
""" Rename a table and rereturn new name
Args:
schema (str): schema name (the new one)
table (str): table name
Returns:
str
"""
try:
return self._table_new_names[(schema, table)]
except KeyError:
new_name = table
_rules = self.table_rename.get(schema, {})
for pattern, repl in _rules.items():
new_name, subs_made = re.subn(pattern, repl, table)
if subs_made:
break
self._table_new_names[(schema, table)] = new_name
return new_name
def resolve_reference_ucp(cls, design_uri):
"""Retrieve artifacts from a UCP service endpoint.
Return a byte array of the response content. Assumes Keystone
authentication required.
:param design_uri: Tuple as returned by urllib.parse for the design reference
"""
ks_sess = KeystoneUtils.get_session()
(new_scheme, foo) = re.subn('^[^+]+\+', '', design_uri.scheme)
url = urllib.parse.urlunparse((new_scheme, design_uri.netloc, design_uri.path,
design_uri.params, design_uri.query, design_uri.fragment))
logger = logging.getLogger(__name__)
logger.debug("Calling Keystone session for url %s" % str(url))
resp = ks_sess.get(url)
if resp.status_code >= 400:
raise errors.InvalidDesignReference(
"Received error code for reference %s: %s - %s" % (url, str(resp.status_code), resp.text))
return resp.content
def apply(self, sed):
_, repl, count, printit, _, write, filename = self.args
# managing ampersand is done when converting to python format
# manage empty regexp
regexp = sed.cache_regexp(self.regexp)
success, sed.PS = regexp.subn(repl, sed.PS, count=count)
sed.subst_successful = sed.subst_successful or success
if success:
if printit:
sed.printline(sed.PS)
if write:
sed.write_subst_file(filename, sed.PS)
return self.next
def normalize(word):
'''
Perform fuzzy search normalization (collapse commonly confused sounds
so search is resilient to misspellings of Alutiiq words).
>>> normalize('tuumiaqlluku')
'tumiaklluku'
>>> normalize("Wiiwaq")
'uiuak'
>>> normalize("estui'isuun")
'stuisun'
'''
word = re.subn(r'(?<!n)g', 'r', word)[0]
word = re.subn(r'[A-QS-Z]', lambda m: m.group().lower(), word)[0]
word = (word.replace('q', 'k')
.replace('y', 'i')
.replace('w', 'u')
.replace('e', '')
.replace("'", ''))
for vowel in 'aiu':
word = re.sub(vowel + '+', vowel, word)
return word
def find_substring_ignore_special_chars(s, substr):
s = s.upper()
substr = substr.upper()
clean_s, dummy_subs_in_s = re.subn('[^A-Z0-9]', '', s)
clean_substr, dummy_subs_in_substr = re.subn('[^A-Z0-9]', '', substr)
startIndex = clean_s.find(clean_substr)
if startIndex != -1:
i = 0
real_index = 0
re_alphanum = re.compile('[A-Z0-9]')
for real_index, char in enumerate(s):
if re_alphanum.match(char):
i += 1
if i > startIndex:
break
return real_index
else:
return -1
def search_and_replace_date(lines, newdate):
pattern = gpar.date_assign_re % gpar.datevar
repl = gpar.date_repl_re % newdate
log.debug('search_and_replace_date: pattern: %s', pattern)
log.debug('search_and_replace_date: replace: %s', repl)
for ln, line in enumerate(lines):
newline, n = re.subn(pattern, repl, line)
if n:
if line != newline:
# pattern matched and line changed
log.debug('found pattern: %s', line[:-1])
log.debug(' replacement: %s', newline[:-1])
lines[ln] = newline
return True
else:
# pattern matched, but not changed
return False
return False
def logReSubn(subnExpr, preComment, postComment, errorMsg='') -> str:
"""
Takes in the result of a re.subn call, subnExpr, and
logs preComment to stdout, then logs postComment and specifies the
number of subs.
Prints errorMsg in case of 0 subs.
Returns the string from subnExpr with replacements made.
"""
out = subnExpr[0]
subs = subnExpr[1]
print(preComment)
print(str(subs) + ' ' + postComment)
if (subs == 0 and errorMsg != ''):
print(errorMsg)
return out
def subn(self, repl, string, count=0):
if (isinstance(repl, SourcedString) or
isinstance(string, SourcedString)):
result = ''
pos = 0
n = 0
for match in self.pattern.finditer(string):
result += string[pos:match.start()]
result += repl
pos = match.end()
n += 1
if count and n==count: break
result += string[pos:]
return result, n
else:
return self.pattern.subn(repl, string, count)
def patch_re_module():
"""
Modify the standard ``re`` module by installing new versions of
the functions ``re.compile``, ``re.sub``, and ``re.subn``,
causing regular expression substitutions to return
``SourcedStrings`` when called with ``SourcedStrings``
arguments.
Use this function only if necessary: it potentially affects
all Python modules that use regular expressions!
"""
def new_re_sub(pattern, repl, string, count=0):
return re.compile(pattern).sub(repl, string, count)
def new_re_subn(pattern, repl, string, count=0):
return re.compile(pattern).subn(repl, string, count)
re.compile = SourcedStringRegexp
re.sub = new_re_sub
re.subn = new_re_subn
def subn(self, repl, string, count=0):
if (isinstance(repl, SourcedString) or
isinstance(string, SourcedString)):
result = ''
pos = 0
n = 0
for match in self.pattern.finditer(string):
result += string[pos:match.start()]
result += repl
pos = match.end()
n += 1
if count and n==count: break
result += string[pos:]
return result, n
else:
return self.pattern.subn(repl, string, count)
def patch_re_module():
"""
Modify the standard ``re`` module by installing new versions of
the functions ``re.compile``, ``re.sub``, and ``re.subn``,
causing regular expression substitutions to return
``SourcedStrings`` when called with ``SourcedStrings``
arguments.
Use this function only if necessary: it potentially affects
all Python modules that use regular expressions!
"""
def new_re_sub(pattern, repl, string, count=0):
return re.compile(pattern).sub(repl, string, count)
def new_re_subn(pattern, repl, string, count=0):
return re.compile(pattern).subn(repl, string, count)
re.compile = SourcedStringRegexp
re.sub = new_re_sub
re.subn = new_re_subn
def _unescape_entities(xml_text):
"""
Strips tags of the form <text:span ...> from inside Jinja elements
and unescapes HTML codes for >, <, & and "
"""
unescape_rules = {
r'(?is)({([{%])[^%}]*?)(</?text:s.*?>)(.*?[%}]})': r'\1 \4',
r'(?is)({([{%])[^%}]*?)(>)(.*?[%}]})' : r'\1>\4',
r'(?is)({([{%])[^%}]*?)(<)(.*?[%}]})' : r'\1<\4',
r'(?is)({([{%])[^%}]*?)(&)(.*?[%}]})' : r'\1&\4',
r'(?is)({([{%])[^%}]*?)(")(.*?[%}]})' : r'\1"\4',
}
for regexp, replacement in unescape_rules.items():
subs_made = True
while subs_made:
xml_text, subs_made = re.subn(regexp, replacement, xml_text)
return xml_text
def datetime_parsing(text, base_date=datetime.now()):
"""
Extract datetime objects from a string of text.
"""
matches = []
found_array = []
# Find the position in the string
for expression, function in regex:
for match in expression.finditer(text):
matches.append((match.group(), function(match, base_date), match.span()))
# Wrap the matched text with TAG element to prevent nested selections
for match, value, spans in matches:
subn = re.subn(
'(?!<TAG[^>]*?>)' + match + '(?![^<]*?</TAG>)', '<TAG>' + match + '</TAG>', text
)
text = subn[0]
is_substituted = subn[1]
if is_substituted != 0:
found_array.append((match, value, spans))
# To preserve order of the match, sort based on the start position
return sorted(found_array, key=lambda match: match and match[2][0])
def getTextFromSoup(htmlsoup):
#print(htmlsoup)
text = str(htmlsoup)
imgurls = []
imgs = htmlsoup.find_all('img')
#print_list(imgs)
for img in imgs:
imgurls.append('http://acm.hdu.edu.cn%s' % img['src'])
#print(htmlsoup)
if len(imgurls) != 0:
for url in imgurls:
text, number = re.subn(r'<img.+?>', r'' % url, text)
#print(text)
text, number = re.subn(r'<br>', '\n', text)
text, number = re.subn(r'<.+?>', '', text)
return text
#print(text)
#print(seh.group())
#print_list(imgurls)
# res = htmlsoup.replace('<br/>', '\r\n')
# result, number = re.subn('<.+?>', '', res)
# print(result)
# print(number)
def translate_enumeration(types, enum, constructor):
name = enum["name"]
name = rename_enumeration(name)
types[name] = this = {"type":constructor, "ctype":"i32"}
this["constants"] = constants = {}
# turns out the "expand" was insufficient nearly everywhere.
prefix = "^VK_"
for cell in split_case(name):
prefix += "(" + cell.upper() + "_)?"
for tag in enum:
if tag.name == "enum":
name_ = re.subn(prefix, "", tag["name"])[0]
if "bitpos" in tag.attrs:
value = 1 << int(tag["bitpos"])
elif tag["value"].startswith("0x"):
value = int(tag["value"], 16)
else:
value = int(tag["value"])
constants[name_] = value
return name
def translate_enumeration(enum, constructor):
name = enum["name"]
name = rename_enumeration(name)
print "{0} = {1}({0!r}, {{".format(name, constructor)
# turns out the "expand" was insufficient nearly everywhere.
prefix = "^VK_"
for cell in split_case(name):
prefix += "(" + cell.upper() + "_)?"
for tag in enum:
if tag.name == "enum":
name_ = re.subn(prefix, "", tag["name"])[0]
if "bitpos" in tag.attrs:
value = "1 << " + tag["bitpos"]
else:
value = tag["value"]
print " {!r:<50}: {!s},".format(name_, value)
print "})"
return name
def fix_unpair_tag(text, tag, count_selfclosing=True):
"""
Fix self-closing unpair tags and return (new_text, replacements_count) tuple.
tag parameter must contains only name of the tag, for example, "br" for <br>.
If self-closing tags are correct, set count_selfclosing param to False.
self-closing still will be corrected in the name of unification, but those
replacements will not be counted.
Used in 2nd error.
"""
correct_tag = "<{}>".format(tag)
all_tags = r"<[/\\ ]*{}[/\\ ]*>".format(tag)
if count_selfclosing:
correct = count_ignore_case(text, correct_tag)
else:
correct = len(re.findall(r"<{}\s*/?>".format(tag), text))
(text, fixed) = re.subn(all_tags, correct_tag, text, flags=re.I)
return (text, fixed - correct)
def fix_pair_tag(text, tag, recursive=False):
"""
Fix self-closing pair tags and return (new_text, replacements_count) tuple.
tag parameter must contains only name of the tag, for example, "b" for <b>.
recursive flag must be True if nested tags are correct. The default value is False.
Checks tag balance: if something going wrong, function willn't change anything.
Used in 2nd error.
"""
old_text = text
correct_tag = "</{}>".format(tag)
(text, fixed1) = re.subn(r"<[ ]*{}[ ]*[/\\]>".format(tag), correct_tag, text, flags=re.I)
(text, fixed2) = re.subn(r"<\\[ ]*{}[ ]*>".format(tag), correct_tag, text, flags=re.I)
if check_tag_balance(text, tag, recursive):
return (text, fixed1 + fixed2)
else:
return (old_text, 0)
def error_002_invalid_tags(text):
"""Fix the error and return (new_text, replacements_count) tuple."""
(text, fixed_br) = fix_unpair_tag(text, "br", count_selfclosing=False)
(text, fixed_hr) = fix_unpair_tag(text, "hr", count_selfclosing=False)
fixed_total = fixed_br + fixed_hr
(text, fixed_clear) = re.subn(r"<br clear=\"?(left|right)\"?\s*/?>", "{{clear|\\1}}", text)
(text, fixed_clear_all) = re.subn(r"<br clear=\"?(?:all|both)\"?\s*/?>", "{{clear}}", text)
fixed_total += fixed_clear + fixed_clear_all
(text, fixed_small) = fix_pair_tag(text, "small")
(text, fixed_center) = fix_pair_tag(text, "center")
(text, fixed_div) = fix_pair_tag(text, "div", recursive=True)
(text, fixed_span) = fix_pair_tag(text, "span", recursive=True)
fixed_total += fixed_small + fixed_center + fixed_div + fixed_span
return (text, fixed_total)
def error_068_interwiki_link(text):
"""
Fix links to Special:BookSearch and direct links, written like interwiki
ones. For example, for ruwiki fixes [[:ru:Example|Something]].
Return (new_text, replacements_count) tuple.
"""
def _check_link(match_obj):
"""Check if founded link is a link to a file or a category and insert extra ":" if so."""
link = match_obj.group(2).lstrip().lower()
if re.search(r"^" + IMAGE, link) is None and re.search(r"^" + CATEGORY, link) is None:
return match_obj.group(1) + match_obj.group(2)
else:
return match_obj.group(1) + ":" + match_obj.group(2)
# bot will not fix links without a pipe: manual control needed
(text, direct) = re.subn(r"(\[\[):{}:([^|\[\]\n]+\|[^|\[\]\n]+\]\])".format(LANG_CODE),
_check_link, text, flags=re.I)
(text, books) = re.subn(r"\[\[:..:Special:BookSources/\d+X?\|(ISBN [0-9\-X]+)\]\]",
"\\1", text, flags=re.I)
return (text, direct + books)
def error_086_ext_link_two_brackets(text):
"""Fix some cases and return (new_text, replacements_count) tuple."""
# case: [[http://youtube.com/|YouTube]]
def _process_link(match_obj):
"""Deals with founded wiki-link."""
link = match_obj.group(1)
name = match_obj.group(2)
if "wikipedia.org" in link.lower():
link = re.sub(" ", "_", link)
else:
link = re.sub(" ", "%20", link)
return "[" + link + " " + name + "]"
exp1 = r"\[\[(https?://[^|\[\]\n]+)\|([^|\[\]\n]+)\]\]"
(text, count1) = re.subn(exp1, _process_link, text, flags=re.I)
# case: [[http://youtube.com YouTube]]
exp2 = r"\[(\[https?://[^\[\]\n]+\])\]"
(text, count2) = re.subn(exp2, "\\1", text, flags=re.I)
return (text, count1 + count2)
def error_104_quote_marks_in_refs(text):
"""Fix the error and return (new_text, replacements_count) tuple."""
count3 = 0
def quote_ref(match):
"""Quote ref name if it's neccessary."""
#pylint: disable=undefined-variable
nonlocal count3
name = match.group(2)
if re.search(r"group\s*=", name):
return match.group(0)
if "\"" in name or re.match(r"^'.*'$", name):
# ref is already quotetd (all is ok) or has a quote (dangerous to fix)
return match.group(0)
if re.search(r"['/\\=?#\s]", name):
count3 += 1
return match.group(1) + "\"" + name + "\"" + match.group(3)
return match.group(0)
(text, count1) = re.subn(r"(<ref\s+name\s*=\s*\"[^\">]+?)(\s*/?>)", "\\1\"\\2", text)
(text, count2) = re.subn(r"(<ref\s+name\s*=\s*)([^\">]+?\"\s*/?>)", "\\1\"\\2", text)
text = re.sub(r"(<ref\s+name\s*=\s*)(.*?)(\s*/?>)", quote_ref, text)
return (text, count1 + count2 + count3)
def modify_start_url(self, start_url):
"""
Given a SAML redirect URL, parse it and change the ID to
a consistent value, so the request is always identical.
"""
# Parse the SAML Request URL to get the XML being sent to TestShib
url_parts = urlparse(start_url)
query = dict((k, v[0]) for (k, v) in
parse_qs(url_parts.query).items())
xml = OneLogin_Saml2_Utils.decode_base64_and_inflate(
query['SAMLRequest']
)
# Modify the XML:
xml = xml.decode()
xml, changed = re.subn(r'ID="[^"]+"', 'ID="TEST_ID"', xml)
self.assertEqual(changed, 1)
# Update the URL to use the modified query string:
query['SAMLRequest'] = OneLogin_Saml2_Utils.deflate_and_base64_encode(
xml
)
url_parts = list(url_parts)
url_parts[4] = urlencode(query)
return urlunparse(url_parts)
def removebackspaces(text):
backspace_or_eol = r'(.\010)|(\033\[K)'
n = 1
while n > 0:
text, n = re.subn(backspace_or_eol, '', text, 1)
return text
def load(self, name, model, alias_list=None):
param_dict = self._load(name)
if alias_list:
new_dict = {}
for key, value in param_dict.items():
for src, dst in alias_list:
if not key.startswith(src):
continue
print(key)
if isinstance(dst, widgets.Widget):
dst = dst.prefix()
key, _ = re.subn('^{}'.format(src), dst, key)
new_dict[key] = value
param_dict = new_dict
model.parameters = param_dict
def checksum(line):
line, n = re.subn('-', '1', line) # replace dashes with 1's
line, n = re.subn('[^\d]', '', line) # remove non-digit chars
# compare with last digit with sum modulo 10
digits = [int(x) for x in line[:-1]]
return int(line[-1]) == sum(digits) % 10
def stamp_source(base_dir, version, dry_run=False):
"""update version string in passlib dist"""
path = os.path.join(base_dir, "passlib", "__init__.py")
with open(path) as fh:
input = fh.read()
output, count = re.subn('(?m)^__version__\s*=.*$',
'__version__ = ' + repr(version),
input)
assert count == 1, "failed to replace version string"
if not dry_run:
os.unlink(path) # sdist likes to use hardlinks
with open(path, "w") as fh:
fh.write(output)
