def _glob_to_re(self, pattern):
"""Translate a shell-like glob pattern to a regular expression.
Return a string containing the regex. Differs from
'fnmatch.translate()' in that '*' does not match "special characters"
(which are platform-specific).
"""
pattern_re = fnmatch.translate(pattern)
# '?' and '*' in the glob pattern become '.' and '.*' in the RE, which
# IMHO is wrong -- '?' and '*' aren't supposed to match slash in Unix,
# and by extension they shouldn't match such "special characters" under
# any OS. So change all non-escaped dots in the RE to match any
# character except the special characters (currently: just os.sep).
sep = os.sep
if os.sep == '\\':
# we're using a regex to manipulate a regex, so we need
# to escape the backslash twice
sep = r'\\\\'
escaped = r'\1[^%s]' % sep
pattern_re = re.sub(r'((?<!\\)(\\\\)*)\.', escaped, pattern_re)
return pattern_re
python类translate()的实例源码
def __init__(
self, index_url="https://pypi.python.org/simple", hosts=('*',),
ca_bundle=None, verify_ssl=True, *args, **kw
):
Environment.__init__(self, *args, **kw)
self.index_url = index_url + "/" [:not index_url.endswith('/')]
self.scanned_urls = {}
self.fetched_urls = {}
self.package_pages = {}
self.allows = re.compile('|'.join(map(translate, hosts))).match
self.to_scan = []
use_ssl = (
verify_ssl
and ssl_support.is_available
and (ca_bundle or ssl_support.find_ca_bundle())
)
if use_ssl:
self.opener = ssl_support.opener_for(ca_bundle)
else:
self.opener = urllib.request.urlopen
def check_newline_eof():
includes = r'|'.join([fnmatch.translate(x)
for x in NEWLINE_EOF_INCLUDE_PATTERNS])
excludes = r'|'.join([fnmatch.translate(x)
for x in NEWLINE_EOF_EXCLUDE_PATTERNS])
return_code = 0
def has_newline_eof(path):
with open(path, 'r') as f:
data = f.read()
if data and data[-1] != '\n':
LOG.error('%s file error: no newline at end of file', path)
return False
return True
for root, dirs, files in os.walk(PROJECT_ROOT):
dirs[:] = [d for d in dirs if not re.match(excludes, d)]
for f in files:
if not re.match(excludes, f) and re.match(includes, f):
if not has_newline_eof(os.path.join(root, f)):
return_code = 1
return return_code
def keys(self, pattern='*'):
"""Emulate keys."""
import fnmatch
import re
# making sure the pattern is unicode/str.
try:
pattern = pattern.decode('utf-8')
# This throws an AttributeError in python 3, or an
# UnicodeEncodeError in python 2
except (AttributeError, UnicodeEncodeError):
pass
# Make regex out of glob styled pattern.
regex = fnmatch.translate(pattern)
regex = re.compile(regex)
# Find every key that matches the pattern
return [key for key in self.redis.keys() if regex.match(key.decode('utf-8'))]
def _glob_to_re(self, pattern):
"""Translate a shell-like glob pattern to a regular expression.
Return a string containing the regex. Differs from
'fnmatch.translate()' in that '*' does not match "special characters"
(which are platform-specific).
"""
pattern_re = fnmatch.translate(pattern)
# '?' and '*' in the glob pattern become '.' and '.*' in the RE, which
# IMHO is wrong -- '?' and '*' aren't supposed to match slash in Unix,
# and by extension they shouldn't match such "special characters" under
# any OS. So change all non-escaped dots in the RE to match any
# character except the special characters (currently: just os.sep).
sep = os.sep
if os.sep == '\\':
# we're using a regex to manipulate a regex, so we need
# to escape the backslash twice
sep = r'\\\\'
escaped = r'\1[^%s]' % sep
pattern_re = re.sub(r'((?<!\\)(\\\\)*)\.', escaped, pattern_re)
return pattern_re
def _glob_to_re(self, pattern):
"""Translate a shell-like glob pattern to a regular expression.
Return a string containing the regex. Differs from
'fnmatch.translate()' in that '*' does not match "special characters"
(which are platform-specific).
"""
pattern_re = fnmatch.translate(pattern)
# '?' and '*' in the glob pattern become '.' and '.*' in the RE, which
# IMHO is wrong -- '?' and '*' aren't supposed to match slash in Unix,
# and by extension they shouldn't match such "special characters" under
# any OS. So change all non-escaped dots in the RE to match any
# character except the special characters (currently: just os.sep).
sep = os.sep
if os.sep == '\\':
# we're using a regex to manipulate a regex, so we need
# to escape the backslash twice
sep = r'\\\\'
escaped = r'\1[^%s]' % sep
pattern_re = re.sub(r'((?<!\\)(\\\\)*)\.', escaped, pattern_re)
return pattern_re
def __init__(
self, index_url="https://pypi.python.org/simple", hosts=('*',),
ca_bundle=None, verify_ssl=True, *args, **kw
):
Environment.__init__(self, *args, **kw)
self.index_url = index_url + "/" [:not index_url.endswith('/')]
self.scanned_urls = {}
self.fetched_urls = {}
self.package_pages = {}
self.allows = re.compile('|'.join(map(translate, hosts))).match
self.to_scan = []
use_ssl = (
verify_ssl
and ssl_support.is_available
and (ca_bundle or ssl_support.find_ca_bundle())
)
if use_ssl:
self.opener = ssl_support.opener_for(ca_bundle)
else:
self.opener = urllib.request.urlopen
def _glob_to_re(self, pattern):
"""Translate a shell-like glob pattern to a regular expression.
Return a string containing the regex. Differs from
'fnmatch.translate()' in that '*' does not match "special characters"
(which are platform-specific).
"""
pattern_re = fnmatch.translate(pattern)
# '?' and '*' in the glob pattern become '.' and '.*' in the RE, which
# IMHO is wrong -- '?' and '*' aren't supposed to match slash in Unix,
# and by extension they shouldn't match such "special characters" under
# any OS. So change all non-escaped dots in the RE to match any
# character except the special characters (currently: just os.sep).
sep = os.sep
if os.sep == '\\':
# we're using a regex to manipulate a regex, so we need
# to escape the backslash twice
sep = r'\\\\'
escaped = r'\1[^%s]' % sep
pattern_re = re.sub(r'((?<!\\)(\\\\)*)\.', escaped, pattern_re)
return pattern_re
def __init__(
self, index_url="https://pypi.python.org/simple", hosts=('*',),
ca_bundle=None, verify_ssl=True, *args, **kw
):
Environment.__init__(self, *args, **kw)
self.index_url = index_url + "/" [:not index_url.endswith('/')]
self.scanned_urls = {}
self.fetched_urls = {}
self.package_pages = {}
self.allows = re.compile('|'.join(map(translate, hosts))).match
self.to_scan = []
use_ssl = (
verify_ssl
and ssl_support.is_available
and (ca_bundle or ssl_support.find_ca_bundle())
)
if use_ssl:
self.opener = ssl_support.opener_for(ca_bundle)
else:
self.opener = urllib.request.urlopen
def _glob_to_re(self, pattern):
"""Translate a shell-like glob pattern to a regular expression.
Return a string containing the regex. Differs from
'fnmatch.translate()' in that '*' does not match "special characters"
(which are platform-specific).
"""
pattern_re = fnmatch.translate(pattern)
# '?' and '*' in the glob pattern become '.' and '.*' in the RE, which
# IMHO is wrong -- '?' and '*' aren't supposed to match slash in Unix,
# and by extension they shouldn't match such "special characters" under
# any OS. So change all non-escaped dots in the RE to match any
# character except the special characters (currently: just os.sep).
sep = os.sep
if os.sep == '\\':
# we're using a regex to manipulate a regex, so we need
# to escape the backslash twice
sep = r'\\\\'
escaped = r'\1[^%s]' % sep
pattern_re = re.sub(r'((?<!\\)(\\\\)*)\.', escaped, pattern_re)
return pattern_re
def check_newline_eof():
includes = r'|'.join([fnmatch.translate(x)
for x in NEWLINE_EOF_INCLUDE_PATTERNS])
excludes = r'|'.join([fnmatch.translate(x)
for x in NEWLINE_EOF_EXCLUDE_PATTERNS])
return_code = 0
def has_newline_eof(path):
with open(path, 'r') as f:
data = f.read()
if data and data[-1] != '\n':
LOG.error('%s file error: no newline at end of file', path)
return False
return True
for root, dirs, files in os.walk(PROJECT_ROOT):
dirs[:] = [d for d in dirs if not re.match(excludes, d)]
for f in files:
if not re.match(excludes, f) and re.match(includes, f):
if not has_newline_eof(os.path.join(root, f)):
return_code = 1
return return_code
def _glob_to_re(self, pattern):
"""Translate a shell-like glob pattern to a regular expression.
Return a string containing the regex. Differs from
'fnmatch.translate()' in that '*' does not match "special characters"
(which are platform-specific).
"""
pattern_re = fnmatch.translate(pattern)
# '?' and '*' in the glob pattern become '.' and '.*' in the RE, which
# IMHO is wrong -- '?' and '*' aren't supposed to match slash in Unix,
# and by extension they shouldn't match such "special characters" under
# any OS. So change all non-escaped dots in the RE to match any
# character except the special characters (currently: just os.sep).
sep = os.sep
if os.sep == '\\':
# we're using a regex to manipulate a regex, so we need
# to escape the backslash twice
sep = r'\\\\'
escaped = r'\1[^%s]' % sep
pattern_re = re.sub(r'((?<!\\)(\\\\)*)\.', escaped, pattern_re)
return pattern_re
def __init__(
self, index_url="https://pypi.python.org/simple", hosts=('*',),
ca_bundle=None, verify_ssl=True, *args, **kw
):
Environment.__init__(self, *args, **kw)
self.index_url = index_url + "/" [:not index_url.endswith('/')]
self.scanned_urls = {}
self.fetched_urls = {}
self.package_pages = {}
self.allows = re.compile('|'.join(map(translate, hosts))).match
self.to_scan = []
use_ssl = (
verify_ssl
and ssl_support.is_available
and (ca_bundle or ssl_support.find_ca_bundle())
)
if use_ssl:
self.opener = ssl_support.opener_for(ca_bundle)
else:
self.opener = urllib.request.urlopen
def _glob_to_re(self, pattern):
"""Translate a shell-like glob pattern to a regular expression.
Return a string containing the regex. Differs from
'fnmatch.translate()' in that '*' does not match "special characters"
(which are platform-specific).
"""
pattern_re = fnmatch.translate(pattern)
# '?' and '*' in the glob pattern become '.' and '.*' in the RE, which
# IMHO is wrong -- '?' and '*' aren't supposed to match slash in Unix,
# and by extension they shouldn't match such "special characters" under
# any OS. So change all non-escaped dots in the RE to match any
# character except the special characters (currently: just os.sep).
sep = os.sep
if os.sep == '\\':
# we're using a regex to manipulate a regex, so we need
# to escape the backslash twice
sep = r'\\\\'
escaped = r'\1[^%s]' % sep
pattern_re = re.sub(r'((?<!\\)(\\\\)*)\.', escaped, pattern_re)
return pattern_re
def __init__(
self, index_url="https://pypi.python.org/simple", hosts=('*',),
ca_bundle=None, verify_ssl=True, *args, **kw
):
Environment.__init__(self, *args, **kw)
self.index_url = index_url + "/" [:not index_url.endswith('/')]
self.scanned_urls = {}
self.fetched_urls = {}
self.package_pages = {}
self.allows = re.compile('|'.join(map(translate, hosts))).match
self.to_scan = []
use_ssl = (
verify_ssl
and ssl_support.is_available
and (ca_bundle or ssl_support.find_ca_bundle())
)
if use_ssl:
self.opener = ssl_support.opener_for(ca_bundle)
else:
self.opener = urllib.request.urlopen
def _glob_to_re(self, pattern):
"""Translate a shell-like glob pattern to a regular expression.
Return a string containing the regex. Differs from
'fnmatch.translate()' in that '*' does not match "special characters"
(which are platform-specific).
"""
pattern_re = fnmatch.translate(pattern)
# '?' and '*' in the glob pattern become '.' and '.*' in the RE, which
# IMHO is wrong -- '?' and '*' aren't supposed to match slash in Unix,
# and by extension they shouldn't match such "special characters" under
# any OS. So change all non-escaped dots in the RE to match any
# character except the special characters (currently: just os.sep).
sep = os.sep
if os.sep == '\\':
# we're using a regex to manipulate a regex, so we need
# to escape the backslash twice
sep = r'\\\\'
escaped = r'\1[^%s]' % sep
pattern_re = re.sub(r'((?<!\\)(\\\\)*)\.', escaped, pattern_re)
return pattern_re
def _glob_to_re(self, pattern):
"""Translate a shell-like glob pattern to a regular expression.
Return a string containing the regex. Differs from
'fnmatch.translate()' in that '*' does not match "special characters"
(which are platform-specific).
"""
pattern_re = fnmatch.translate(pattern)
# '?' and '*' in the glob pattern become '.' and '.*' in the RE, which
# IMHO is wrong -- '?' and '*' aren't supposed to match slash in Unix,
# and by extension they shouldn't match such "special characters" under
# any OS. So change all non-escaped dots in the RE to match any
# character except the special characters (currently: just os.sep).
sep = os.sep
if os.sep == '\\':
# we're using a regex to manipulate a regex, so we need
# to escape the backslash twice
sep = r'\\\\'
escaped = r'\1[^%s]' % sep
pattern_re = re.sub(r'((?<!\\)(\\\\)*)\.', escaped, pattern_re)
return pattern_re
def __init__(
self, index_url="https://pypi.python.org/simple", hosts=('*',),
ca_bundle=None, verify_ssl=True, *args, **kw
):
Environment.__init__(self, *args, **kw)
self.index_url = index_url + "/" [:not index_url.endswith('/')]
self.scanned_urls = {}
self.fetched_urls = {}
self.package_pages = {}
self.allows = re.compile('|'.join(map(translate, hosts))).match
self.to_scan = []
use_ssl = (
verify_ssl
and ssl_support.is_available
and (ca_bundle or ssl_support.find_ca_bundle())
)
if use_ssl:
self.opener = ssl_support.opener_for(ca_bundle)
else:
self.opener = urllib.request.urlopen
def get_all_fastq_files(data_dir):
"""
recursively go down data_dir and get all fastq files
arguments:
data_dir -- the directory that has SampleSheet.csv in it
return list containing path for fastq files
"""
pattern = fn_translate("*.fastq.*")
fastq_files_path = path.join(data_dir, "Data", "Intensities", "BaseCalls")
try:
file_list = listdir(fastq_files_path)
fastq_file_list = [path.join(fastq_files_path, file)
for file in file_list if re.match(pattern, file)]
fastq_file_list.sort()
except OSError:
msg = "Invalid directory " + fastq_files_path
raise OSError(msg)
return fastq_file_list
def _glob_to_re(self, pattern):
"""Translate a shell-like glob pattern to a regular expression.
Return a string containing the regex. Differs from
'fnmatch.translate()' in that '*' does not match "special characters"
(which are platform-specific).
"""
pattern_re = fnmatch.translate(pattern)
# '?' and '*' in the glob pattern become '.' and '.*' in the RE, which
# IMHO is wrong -- '?' and '*' aren't supposed to match slash in Unix,
# and by extension they shouldn't match such "special characters" under
# any OS. So change all non-escaped dots in the RE to match any
# character except the special characters (currently: just os.sep).
sep = os.sep
if os.sep == '\\':
# we're using a regex to manipulate a regex, so we need
# to escape the backslash twice
sep = r'\\\\'
escaped = r'\1[^%s]' % sep
pattern_re = re.sub(r'((?<!\\)(\\\\)*)\.', escaped, pattern_re)
return pattern_re
