Python re 模块，X 实例源码
我们从Python开源项目中，提取了以下50个代码示例，用于说明如何使用re.X。
def get_client_ip(request):
access_route = get_access_route(request)
if len(access_route) == 1:
return access_route[0]
expression = """
(^(?!(?:[0-9]{1,3}\.){3}[0-9]{1,3}$).*$)| # will match non valid ipV4
(^127\.0\.0\.1)| # will match 127.0.0.1
(^10\.)| # will match 10.0.0.0 - 10.255.255.255 IP-s
(^172\.1[6-9]\.)| # will match 172.16.0.0 - 172.19.255.255 IP-s
(^172\.2[0-9]\.)| # will match 172.20.0.0 - 172.29.255.255 IP-s
(^172\.3[0-1]\.)| # will match 172.30.0.0 - 172.31.255.255 IP-s
(^192\.168\.) # will match 192.168.0.0 - 192.168.255.255 IP-s
"""
regex = re.compile(expression, re.X)
for ip in access_route:
if not ip:
# it's possible that the first value from X_FORWARDED_FOR
# will be null, so we need to pass that value
continue
if regex.search(ip):
continue
else:
return ip
def findHeadings(self, lines, struc):
linenum=len(lines)
level=struc[-1]
_h_re=re.compile(self.textparser._h_re_base % level, re.X | re.M)
hidx=[]
for ii in xrange(linenum):
if _h_re.match(lines[ii]):
hidx.append(ii)
hidx.append(linenum)
groups=[[hidx[ii],hidx[ii+1]] for ii in xrange(len(hidx)-1)]
result=[]
for ii in groups:
#--------Use heading line as container name--------
result.append(TextContainer(lines[ii[0]],struc,ii))
return result
def match_text(self):
match = self.match(r"""
(.*?) # anything, followed by:
(
(?<=\n)(?=[ \t]*(?=%|\#\#)) # an eval or line-based
# comment preceded by a
# consumed newline and whitespace
|
(?=\${) # an expression
|
(?=</?[%&]) # a substitution or block or call start or end
# - don't consume
|
(\\\r?\n) # an escaped newline - throw away
|
\Z # end of string
)""", re.X | re.S)
if match:
text = match.group(1)
if text:
self.append_node(parsetree.Text, text)
return True
else:
return False
def __init__(self, user, asset, role, login_type='ssh'):
self.username = user.username
self.asset_name = asset.hostname
self.ip = None
self.port = 22
self.ssh = None
self.channel = None
self.asset = asset
self.user = user
self.role = role
self.remote_ip = ''
self.login_type = login_type
self.vim_flag = False
self.vim_end_pattern = re.compile(r'\x1b\[\?1049', re.X)
self.vim_data = ''
self.stream = None
self.screen = None
self.__init_screen_stream()
def open(self):
logger.debug('Websocket: Open exec request')
role_name = self.get_argument('role', 'sb')
self.remote_ip = self.request.headers.get("X-Real-IP")
if not self.remote_ip:
self.remote_ip = self.request.remote_ip
logger.debug('Web????: ?????? %s' % role_name)
self.role = get_object(PermRole, name=role_name)
self.perm = get_group_user_perm(self.user)
roles = self.perm.get('role').keys()
if self.role not in roles:
self.write_message('No perm that role %s' % role_name)
self.close()
self.assets = self.perm.get('role').get(self.role).get('asset')
res = gen_resource({'user': self.user, 'asset': self.assets, 'role': self.role})
self.runner = MyRunner(res)
message = '??????: ' + ', '.join([asset.hostname for asset in self.assets])
self.__class__.clients.append(self)
self.write_message(message)
def _compile_patterns(self):
"""
Compiles the regexes based on the original implementation of the parser (``InventoryParser``)
and sets the to ``self.patterns``
"""
self.patterns['section'] = re.compile(
r'''^\[
([^:\]\s]+) # group name
(?::(\w+))? # optional tag name :
\]
\s* # ignore trailing whitespace
(?:\#.*)? # and/or a comment till the
$ # end of the line
''', re.X
)
self.patterns['groupname'] = re.compile(
r'''^
([^:\]\s]+)
\s* # ignore trailing whitespace
(?:\#.*)? # and/or a comment till the
$ # end of the line
''', re.X
)
def _do_code_blocks(self, text):
"""Process Markdown `<pre><code>` blocks."""
code_block_re = re.compile(r'''
(?:\n\n|\A\n?)
( # $1 = the code block -- one or more lines, starting with a space/tab
(?:
(?:[ ]{%d} | \t) # Lines must start with a tab or a tab-width of spaces
.*\n+
)+
)
((?=^[ ]{0,%d}\S)|\Z) # Lookahead for non-space at line-start, or end of doc
# Lookahead to make sure this block isn't already in a code block.
# Needed when syntax highlighting is being used.
(?![^<]*\</code\>)
''' % (self.tab_width, self.tab_width),
re.M | re.X)
return code_block_re.sub(self._code_block_sub, text)
def _xml_oneliner_re_from_tab_width(tab_width):
"""Standalone XML processing instruction regex."""
return re.compile(r"""
(?:
(?<=\n\n) # Starting after a blank line
| # or
\A\n? # the beginning of the doc
)
( # save in $1
[ ]{0,%d}
(?:
<\?\w+\b\s+.*?\?> # XML processing instruction
|
<\w+:\w+\b\s+.*?/> # namespaced single tag
)
[ \t]*
(?=\n{2,}|\Z) # followed by a blank line or end of document
)
""" % (tab_width - 1), re.X)
def _hr_tag_re_from_tab_width(tab_width):
return re.compile(r"""
(?:
(?<=\n\n) # Starting after a blank line
| # or
\A\n? # the beginning of the doc
)
( # save in \1
[ ]{0,%d}
<(hr) # start tag = \2
\b # word break
([^<>])*? #
/?> # the matching end tag
[ \t]*
(?=\n{2,}|\Z) # followed by a blank line or end of document
)
""" % (tab_width - 1), re.X)
def _do_code_blocks(self, text):
"""Process Markdown `<pre><code>` blocks."""
code_block_re = re.compile(r'''
(?:\n\n|\A\n?)
( # $1 = the code block -- one or more lines, starting with a space/tab
(?:
(?:[ ]{%d} | \t) # Lines must start with a tab or a tab-width of spaces
.*\n+
)+
)
((?=^[ ]{0,%d}\S)|\Z) # Lookahead for non-space at line-start, or end of doc
# Lookahead to make sure this block isn't already in a code block.
# Needed when syntax highlighting is being used.
(?![^<]*\</code\>)
''' % (self.tab_width, self.tab_width),
re.M | re.X)
return code_block_re.sub(self._code_block_sub, text)
def _xml_oneliner_re_from_tab_width(tab_width):
"""Standalone XML processing instruction regex."""
return re.compile(r"""
(?:
(?<=\n\n) # Starting after a blank line
| # or
\A\n? # the beginning of the doc
)
( # save in $1
[ ]{0,%d}
(?:
<\?\w+\b\s+.*?\?> # XML processing instruction
|
<\w+:\w+\b\s+.*?/> # namespaced single tag
)
[ \t]*
(?=\n{2,}|\Z) # followed by a blank line or end of document
)
""" % (tab_width - 1), re.X)
def _hr_tag_re_from_tab_width(tab_width):
return re.compile(r"""
(?:
(?<=\n\n) # Starting after a blank line
| # or
\A\n? # the beginning of the doc
)
( # save in \1
[ ]{0,%d}
<(hr) # start tag = \2
\b # word break
([^<>])*? #
/?> # the matching end tag
[ \t]*
(?=\n{2,}|\Z) # followed by a blank line or end of document
)
""" % (tab_width - 1), re.X)
def _do_code_blocks(self, text):
"""Process Markdown `<pre><code>` blocks."""
code_block_re = re.compile(r'''
(?:\n\n|\A\n?)
( # $1 = the code block -- one or more lines, starting with a space/tab
(?:
(?:[ ]{%d} | \t) # Lines must start with a tab or a tab-width of spaces
.*\n+
)+
)
((?=^[ ]{0,%d}\S)|\Z) # Lookahead for non-space at line-start, or end of doc
# Lookahead to make sure this block isn't already in a code block.
# Needed when syntax highlighting is being used.
(?![^<]*\</code\>)
''' % (self.tab_width, self.tab_width),
re.M | re.X)
return code_block_re.sub(self._code_block_sub, text)
def _xml_oneliner_re_from_tab_width(tab_width):
"""Standalone XML processing instruction regex."""
return re.compile(r"""
(?:
(?<=\n\n) # Starting after a blank line
| # or
\A\n? # the beginning of the doc
)
( # save in $1
[ ]{0,%d}
(?:
<\?\w+\b\s+.*?\?> # XML processing instruction
|
<\w+:\w+\b\s+.*?/> # namespaced single tag
)
[ \t]*
(?=\n{2,}|\Z) # followed by a blank line or end of document
)
""" % (tab_width - 1), re.X)
def _hr_tag_re_from_tab_width(tab_width):
return re.compile(r"""
(?:
(?<=\n\n) # Starting after a blank line
| # or
\A\n? # the beginning of the doc
)
( # save in \1
[ ]{0,%d}
<(hr) # start tag = \2
\b # word break
([^<>])*? #
/?> # the matching end tag
[ \t]*
(?=\n{2,}|\Z) # followed by a blank line or end of document
)
""" % (tab_width - 1), re.X)
def match_text(self):
match = self.match(r"""
(.*?) # anything, followed by:
(
(?<=\n)(?=[ \t]*(?=%|\#\#)) # an eval or line-based
# comment preceded by a
# consumed newline and whitespace
|
(?=\${) # an expression
|
(?=</?[%&]) # a substitution or block or call start or end
# - don't consume
|
(\\\r?\n) # an escaped newline - throw away
|
\Z # end of string
)""", re.X | re.S)
if match:
text = match.group(1)
if text:
self.append_node(parsetree.Text, text)
return True
else:
return False
def __init__(self, stream):
"""Initialise Loader."""
try:
self._root = os.path.split(stream.name)[0]
except AttributeError:
self._root = os.path.curdir
super().__init__(stream)
self.add_implicit_resolver(
u'tag:yaml.org,2002:float',
re.compile(u'''^(?:
[-+]?(?:[0-9][0-9_]*)\\.[0-9_]*(?:[eE][-+]?[0-9]+)?
|[-+]?(?:[0-9][0-9_]*)(?:[eE][-+]?[0-9]+)
|\\.[0-9_]+(?:[eE][-+][0-9]+)?
|[-+]?[0-9][0-9_]*(?::[0-5]?[0-9])+\\.[0-9_]*
|[-+]?\\.(?:inf|Inf|INF)
|\\.(?:nan|NaN|NAN))$''', re.X),
list(u'-+0123456789.'))
self.filenames = [os.path.abspath(stream.name)]
def _xml_oneliner_re_from_tab_width(tab_width):
"""Standalone XML processing instruction regex."""
return re.compile(r"""
(?:
(?<=\n\n) # Starting after a blank line
| # or
\A\n? # the beginning of the doc
)
( # save in $1
[ ]{0,%d}
(?:
<\?\w+\b\s+.*?\?> # XML processing instruction
|
<\w+:\w+\b\s+.*?/> # namespaced single tag
)
[ \t]*
(?=\n{2,}|\Z) # followed by a blank line or end of document
)
""" % (tab_width - 1), re.X)
def _hr_tag_re_from_tab_width(tab_width):
return re.compile(r"""
(?:
(?<=\n\n) # Starting after a blank line
| # or
\A\n? # the beginning of the doc
)
( # save in \1
[ ]{0,%d}
<(hr) # start tag = \2
\b # word break
([^<>])*? #
/?> # the matching end tag
[ \t]*
(?=\n{2,}|\Z) # followed by a blank line or end of document
)
""" % (tab_width - 1), re.X)
def __init__(self, user, asset, role, login_type='ssh'):
self.username = user.username
self.asset_name = asset.hostname
self.ip = None
self.port = 22
self.ssh = None
self.channel = None
self.asset = asset
self.user = user
self.role = role
self.remote_ip = ''
self.login_type = login_type
self.vim_flag = False
self.vim_end_pattern = re.compile(r'\x1b\[\?1049', re.X)
self.vim_data = ''
self.stream = None
self.screen = None
self.__init_screen_stream()
def open(self):
logger.debug('Websocket: Open exec request')
role_name = self.get_argument('role', 'sb')
self.remote_ip = self.request.headers.get("X-Real-IP")
if not self.remote_ip:
self.remote_ip = self.request.remote_ip
logger.debug('Web????: ?????? %s' % role_name)
self.role = get_object(PermRole, name=role_name)
self.perm = get_group_user_perm(self.user)
roles = self.perm.get('role').keys()
if self.role not in roles:
self.write_message('No perm that role %s' % role_name)
self.close()
self.assets = self.perm.get('role').get(self.role).get('asset')
res = gen_resource({'user': self.user, 'asset': self.assets, 'role': self.role})
self.runner = MyRunner(res)
message = '??????: ' + ', '.join([asset.hostname for asset in self.assets])
self.__class__.clients.append(self)
self.write_message(message)
def _xml_oneliner_re_from_tab_width(tab_width):
"""Standalone XML processing instruction regex."""
return re.compile(r"""
(?:
(?<=\n\n) # Starting after a blank line
| # or
\A\n? # the beginning of the doc
)
( # save in $1
[ ]{0,%d}
(?:
<\?\w+\b\s+.*?\?> # XML processing instruction
|
<\w+:\w+\b\s+.*?/> # namespaced single tag
)
[ \t]*
(?=\n{2,}|\Z) # followed by a blank line or end of document
)
""" % (tab_width - 1), re.X)
def _hr_tag_re_from_tab_width(tab_width):
return re.compile(r"""
(?:
(?<=\n\n) # Starting after a blank line
| # or
\A\n? # the beginning of the doc
)
( # save in \1
[ ]{0,%d}
<(hr) # start tag = \2
\b # word break
([^<>])*? #
/?> # the matching end tag
[ \t]*
(?=\n{2,}|\Z) # followed by a blank line or end of document
)
""" % (tab_width - 1), re.X)
def match_text(self):
match = self.match(r"""
(.*?) # anything, followed by:
(
(?<=\n)(?=[ \t]*(?=%|\#\#)) # an eval or line-based
# comment preceded by a
# consumed newline and whitespace
|
(?=\${) # an expression
|
(?=</?[%&]) # a substitution or block or call start or end
# - don't consume
|
(\\\r?\n) # an escaped newline - throw away
|
\Z # end of string
)""", re.X | re.S)
if match:
text = match.group(1)
if text:
self.append_node(parsetree.Text, text)
return True
else:
return False
def _xml_oneliner_re_from_tab_width(tab_width):
"""Standalone XML processing instruction regex."""
return re.compile(r"""
(?:
(?<=\n\n) # Starting after a blank line
| # or
\A\n? # the beginning of the doc
)
( # save in $1
[ ]{0,%d}
(?:
<\?\w+\b\s+.*?\?> # XML processing instruction
|
<\w+:\w+\b\s+.*?/> # namespaced single tag
)
[ \t]*
(?=\n{2,}|\Z) # followed by a blank line or end of document
)
""" % (tab_width - 1), re.X)
def _hr_tag_re_from_tab_width(tab_width):
return re.compile(r"""
(?:
(?<=\n\n) # Starting after a blank line
| # or
\A\n? # the beginning of the doc
)
( # save in \1
[ ]{0,%d}
<(hr) # start tag = \2
\b # word break
([^<>])*? #
/?> # the matching end tag
[ \t]*
(?=\n{2,}|\Z) # followed by a blank line or end of document
)
""" % (tab_width - 1), re.X)
def _parse_rfc1738_args(url):
pattern = re.compile(r'''
(?P<name>[\w\+]+)://
(?:
(?P<username>[^:/]*)
(?::(?P<password>.*))?
@)?
(?:
(?:
\[(?P<ipv6host>[^/]+)\] |
(?P<ipv4host>[^/:]+)
)?
(?::(?P<port>[^/]*))?
)?
(?:/(?P<database>.*))?
''', re.X)
m = pattern.match(url)
if m is not None:
components = m.groupdict()
ipv6 = components.pop('ipv6host')
ipv4 = components.pop('ipv4host')
components['host'] = ipv4 or ipv6
return components
else:
raise ValueError('wrong url format')
def match_text(self):
match = self.match(r"""
(.*?) # anything, followed by:
(
(?<=\n)(?=[ \t]*(?=%|\#\#)) # an eval or line-based
# comment preceded by a
# consumed newline and whitespace
|
(?=\${) # an expression
|
(?=</?[%&]) # a substitution or block or call start or end
# - don't consume
|
(\\\r?\n) # an escaped newline - throw away
|
\Z # end of string
)""", re.X | re.S)
if match:
text = match.group(1)
if text:
self.append_node(parsetree.Text, text)
return True
else:
return False
def match_text(self):
match = self.match(r"""
(.*?) # anything, followed by:
(
(?<=\n)(?=[ \t]*(?=%|\#\#)) # an eval or line-based
# comment preceded by a
# consumed newline and whitespace
|
(?=\${) # an expression
|
(?=</?[%&]) # a substitution or block or call start or end
# - don't consume
|
(\\\r?\n) # an escaped newline - throw away
|
\Z # end of string
)""", re.X | re.S)
if match:
text = match.group(1)
if text:
self.append_node(parsetree.Text, text)
return True
else:
return False
def match_text(self):
match = self.match(r"""
(.*?) # anything, followed by:
(
(?<=\n)(?=[ \t]*(?=%|\#\#)) # an eval or line-based
# comment preceded by a
# consumed newline and whitespace
|
(?=\${) # an expression
|
(?=</?[%&]) # a substitution or block or call start or end
# - don't consume
|
(\\\r?\n) # an escaped newline - throw away
|
\Z # end of string
)""", re.X | re.S)
if match:
text = match.group(1)
if text:
self.append_node(parsetree.Text, text)
return True
else:
return False
def _do_code_blocks(self, text):
"""Process Markdown `<pre><code>` blocks."""
code_block_re = re.compile(r'''
(?:\n\n|\A\n?)
( # $1 = the code block -- one or more lines, starting with a space/tab
(?:
(?:[ ]{%d} | \t) # Lines must start with a tab or a tab-width of spaces
.*\n+
)+
)
((?=^[ ]{0,%d}\S)|\Z) # Lookahead for non-space at line-start, or end of doc
# Lookahead to make sure this block isn't already in a code block.
# Needed when syntax highlighting is being used.
(?![^<]*\</code\>)
''' % (self.tab_width, self.tab_width),
re.M | re.X)
return code_block_re.sub(self._code_block_sub, text)
def _xml_oneliner_re_from_tab_width(tab_width):
"""Standalone XML processing instruction regex."""
return re.compile(r"""
(?:
(?<=\n\n) # Starting after a blank line
| # or
\A\n? # the beginning of the doc
)
( # save in $1
[ ]{0,%d}
(?:
<\?\w+\b\s+.*?\?> # XML processing instruction
|
<\w+:\w+\b\s+.*?/> # namespaced single tag
)
[ \t]*
(?=\n{2,}|\Z) # followed by a blank line or end of document
)
""" % (tab_width - 1), re.X)
def _hr_tag_re_from_tab_width(tab_width):
return re.compile(r"""
(?:
(?<=\n\n) # Starting after a blank line
| # or
\A\n? # the beginning of the doc
)
( # save in \1
[ ]{0,%d}
<(hr) # start tag = \2
\b # word break
([^<>])*? #
/?> # the matching end tag
[ \t]*
(?=\n{2,}|\Z) # followed by a blank line or end of document
)
""" % (tab_width - 1), re.X)
def match_text(self):
match = self.match(r"""
(.*?) # anything, followed by:
(
(?<=\n)(?=[ \t]*(?=%|\#\#)) # an eval or line-based
# comment preceded by a
# consumed newline and whitespace
|
(?=\${) # an expression
|
(?=</?[%&]) # a substitution or block or call start or end
# - don't consume
|
(\\\r?\n) # an escaped newline - throw away
|
\Z # end of string
)""", re.X | re.S)
if match:
text = match.group(1)
if text:
self.append_node(parsetree.Text, text)
return True
else:
return False
def _do_code_blocks(self, text):
"""Process Markdown `<pre><code>` blocks."""
code_block_re = re.compile(r'''
(?:\n\n|\A\n?)
( # $1 = the code block -- one or more lines, starting with a space/tab
(?:
(?:[ ]{%d} | \t) # Lines must start with a tab or a tab-width of spaces
.*\n+
)+
)
((?=^[ ]{0,%d}\S)|\Z) # Lookahead for non-space at line-start, or end of doc
# Lookahead to make sure this block isn't already in a code block.
# Needed when syntax highlighting is being used.
(?![^<]*\</code\>)
''' % (self.tab_width, self.tab_width),
re.M | re.X)
return code_block_re.sub(self._code_block_sub, text)
def _xml_oneliner_re_from_tab_width(tab_width):
"""Standalone XML processing instruction regex."""
return re.compile(r"""
(?:
(?<=\n\n) # Starting after a blank line
| # or
\A\n? # the beginning of the doc
)
( # save in $1
[ ]{0,%d}
(?:
<\?\w+\b\s+.*?\?> # XML processing instruction
|
<\w+:\w+\b\s+.*?/> # namespaced single tag
)
[ \t]*
(?=\n{2,}|\Z) # followed by a blank line or end of document
)
""" % (tab_width - 1), re.X)
def _hr_tag_re_from_tab_width(tab_width):
return re.compile(r"""
(?:
(?<=\n\n) # Starting after a blank line
| # or
\A\n? # the beginning of the doc
)
( # save in \1
[ ]{0,%d}
<(hr) # start tag = \2
\b # word break
([^<>])*? #
/?> # the matching end tag
[ \t]*
(?=\n{2,}|\Z) # followed by a blank line or end of document
)
""" % (tab_width - 1), re.X)
def _do_code_blocks(self, text):
"""Process Markdown `<pre><code>` blocks."""
code_block_re = re.compile(r'''
(?:\n\n|\A\n?)
( # $1 = the code block -- one or more lines, starting with a space/tab
(?:
(?:[ ]{%d} | \t) # Lines must start with a tab or a tab-width of spaces
.*\n+
)+
)
((?=^[ ]{0,%d}\S)|\Z) # Lookahead for non-space at line-start, or end of doc
# Lookahead to make sure this block isn't already in a code block.
# Needed when syntax highlighting is being used.
(?![^<]*\</code\>)
''' % (self.tab_width, self.tab_width),
re.M | re.X)
return code_block_re.sub(self._code_block_sub, text)
def _xml_oneliner_re_from_tab_width(tab_width):
"""Standalone XML processing instruction regex."""
return re.compile(r"""
(?:
(?<=\n\n) # Starting after a blank line
| # or
\A\n? # the beginning of the doc
)
( # save in $1
[ ]{0,%d}
(?:
<\?\w+\b\s+.*?\?> # XML processing instruction
|
<\w+:\w+\b\s+.*?/> # namespaced single tag
)
[ \t]*
(?=\n{2,}|\Z) # followed by a blank line or end of document
)
""" % (tab_width - 1), re.X)
def _hr_tag_re_from_tab_width(tab_width):
return re.compile(r"""
(?:
(?<=\n\n) # Starting after a blank line
| # or
\A\n? # the beginning of the doc
)
( # save in \1
[ ]{0,%d}
<(hr) # start tag = \2
\b # word break
([^<>])*? #
/?> # the matching end tag
[ \t]*
(?=\n{2,}|\Z) # followed by a blank line or end of document
)
""" % (tab_width - 1), re.X)
def __init__(self, user, asset, role, login_type='ssh'):
self.username = user.username
self.asset_name = asset.hostname
self.ip = None
self.port = 22
self.ssh = None
self.channel = None
self.asset = asset
self.user = user
self.role = role
self.remote_ip = ''
self.login_type = login_type
self.vim_flag = False
self.vim_end_pattern = re.compile(r'\x1b\[\?1049', re.X)
self.vim_data = ''
self.stream = None
self.screen = None
self.__init_screen_stream()
def open(self):
logger.debug('Websocket: Open exec request')
role_name = self.get_argument('role', 'sb')
self.remote_ip = self.request.headers.get("X-Real-IP")
if not self.remote_ip:
self.remote_ip = self.request.remote_ip
logger.debug('Web????: ?????? %s' % role_name)
self.role = get_object(PermRole, name=role_name)
self.perm = get_group_user_perm(self.user)
roles = self.perm.get('role').keys()
if self.role not in roles:
self.write_message('No perm that role %s' % role_name)
self.close()
self.assets = self.perm.get('role').get(self.role).get('asset')
res = gen_resource({'user': self.user, 'asset': self.assets, 'role': self.role})
self.runner = MyRunner(res)
message = '??????: ' + ', '.join([asset.hostname for asset in self.assets])
self.__class__.clients.append(self)
self.write_message(message)
def match_text(self):
match = self.match(r"""
(.*?) # anything, followed by:
(
(?<=\n)(?=[ \t]*(?=%|\#\#)) # an eval or line-based
# comment preceded by a
# consumed newline and whitespace
|
(?=\${) # an expression
|
(?=</?[%&]) # a substitution or block or call start or end
# - don't consume
|
(\\\r?\n) # an escaped newline - throw away
|
\Z # end of string
)""", re.X | re.S)
if match:
text = match.group(1)
if text:
self.append_node(parsetree.Text, text)
return True
else:
return False
def match_text(self):
match = self.match(r"""
(.*?) # anything, followed by:
(
(?<=\n)(?=[ \t]*(?=%|\#\#)) # an eval or line-based
# comment preceded by a
# consumed newline and whitespace
|
(?=\${) # an expression
|
(?=</?[%&]) # a substitution or block or call start or end
# - don't consume
|
(\\\r?\n) # an escaped newline - throw away
|
\Z # end of string
)""", re.X | re.S)
if match:
text = match.group(1)
if text:
self.append_node(parsetree.Text, text)
return True
else:
return False
def _do_code_blocks(self, text):
"""Process Markdown `<pre><code>` blocks."""
code_block_re = re.compile(r'''
(?:\n\n|\A\n?)
( # $1 = the code block -- one or more lines, starting with a space/tab
(?:
(?:[ ]{%d} | \t) # Lines must start with a tab or a tab-width of spaces
.*\n+
)+
)
((?=^[ ]{0,%d}\S)|\Z) # Lookahead for non-space at line-start, or end of doc
# Lookahead to make sure this block isn't already in a code block.
# Needed when syntax highlighting is being used.
(?![^<]*\</code\>)
''' % (self.tab_width, self.tab_width),
re.M | re.X)
return code_block_re.sub(self._code_block_sub, text)
def _xml_oneliner_re_from_tab_width(tab_width):
"""Standalone XML processing instruction regex."""
return re.compile(r"""
(?:
(?<=\n\n) # Starting after a blank line
| # or
\A\n? # the beginning of the doc
)
( # save in $1
[ ]{0,%d}
(?:
<\?\w+\b\s+.*?\?> # XML processing instruction
|
<\w+:\w+\b\s+.*?/> # namespaced single tag
)
[ \t]*
(?=\n{2,}|\Z) # followed by a blank line or end of document
)
""" % (tab_width - 1), re.X)
def _hr_tag_re_from_tab_width(tab_width):
return re.compile(r"""
(?:
(?<=\n\n) # Starting after a blank line
| # or
\A\n? # the beginning of the doc
)
( # save in \1
[ ]{0,%d}
<(hr) # start tag = \2
\b # word break
([^<>])*? #
/?> # the matching end tag
[ \t]*
(?=\n{2,}|\Z) # followed by a blank line or end of document
)
""" % (tab_width - 1), re.X)
def defSyntax(self):
'''Define re patterns according to syntax.'''
#------------------REGEX patterns------------------
if self.syntax=='markdown':
self._img_re=re.compile('^(.*)!\\[(.+?)\\]\\((.+?)\\)', re.M | re.L)
self._h_re_base = r'''
(^(.+)[ \t]*\n(=+|-+)[ \t]*\n+)
|
(^(\#{%s}) # \1 = string of #'s
[ \t]*
(.+?) # \2 = Header text
[ \t]*
(?<!\\) # ensure not an escaped trailing '#'
\#* # optional closing #'s (not counted)
\n+
)
'''
self._all_h_re=re.compile(self._h_re_base %'1,6', re.X | re.M)
elif self.syntax=='zim':
self._img_re=re.compile('^(.*)\\{\\{(.+?)\\}\\}(.*)$', re.M | re.L)
self._h_re_base = r'''
^(\={%s}) # \1 = string of ='s
[ \t]*
(.+?) # \2 = Header text
[ \t]*
\1
\n+
'''
self._all_h_re=re.compile(self._h_re_base %'1,6', re.X | re.M)
else:
raise Exception("Unknown syntax %s" %self.syntax)
return
def createNoteBook(title,geeknote=None,verbose=True):
#-------------------Trunc title-------------------
title=title.strip()
title=truncStr(title,MAX_NOTEBOOK_TITLE_LEN)
#-------Make sure title doesnt start with #-------
tp=textparse.TextParser('markdown')
_h_re=re.compile(tp._h_re_base %'1,', re.X | re.M)
m=_h_re.match(title)
if m:
title=m.group(6)
#---------------------Connect---------------------
if geeknote is None:
geeknote=GeekNoteConnector()
geeknote.connectToEvertone()
#-----------------Check if exists-----------------
notebooks=geeknote.getEvernote().findNotebooks()
out.preloader.stop()
if not isinstance(title,unicode):
title=unicode(title,'utf8')
notebooks=[unicode(ii.name,'utf8') for ii in notebooks]
if title in notebooks:
out.successMessage('Notebook already exists.')
return 0
else:
out.preloader.setMessage("Creating notebook...")
result = geeknote.getEvernote().createNotebook(name=title)
if result:
out.successMessage("Notebook has been successfully created.")
return 0
else:
out.failureMessage("Error while the process "
"of creating the notebook.")
return tools.exitErr()
def createNote(title,content,tags,notebook,geeknote=None,\
skipnotebook=False):
#-------------------Trunc texts-------------------
notebook=notebook.strip()
notebook=truncStr(notebook,MAX_NOTEBOOK_TITLE_LEN)
title=title.strip()
title=truncStr(title,MAX_NOTE_TITLE_LEN)
#-------Make sure title doesnt start with #-------
tp=textparse.TextParser('markdown')
_h_re=re.compile(tp._h_re_base %'1,', re.X | re.M)
m=_h_re.match(title)
if m:
title=m.group(6)
m=_h_re.match(notebook)
if m:
notebook=m.group(6)
if tags is not None and len(tags.split(','))>=MAX_NOTE_TAGS:
tags=u','.join(tags.split(',')[:MAX_NOTE_TAGS])
#---------------------Connect---------------------
if geeknote is None:
geeknote=GeekNoteConnector()
geeknote.connectToEvertone()
#-----------------Create notebook-----------------
if not skipnotebook:
result=createNoteBook(notebook,geeknote)
if skipnotebook or result==0:
#----------------------Write----------------------
inputdata=geeknote._parseInput(title,content,tags,notebook,None)
out.preloader.setMessage('Creating note...')
result=bool(geeknote.getEvernote().createNote(**inputdata))
if result:
out.successMessage("Note has been successfully saved.")
else:
out.failureMessage("Error while saving the note.")