Current File : //opt/rh/rh-python35/root/lib64/python3.5/sre_parse.py
#
# Secret Labs' Regular Expression Engine
#
# convert re-style regular expression to sre pattern
#
# Copyright (c) 1998-2001 by Secret Labs AB. All rights reserved.
#
# See the sre.py file for information on usage and redistribution.
#
"""Internal support module for sre"""
# XXX: show string offset and offending character for all errors
from sre_constants import *
SPECIAL_CHARS = ".\\[{()*+?^$|"
REPEAT_CHARS = "*+?{"
DIGITS = frozenset("0123456789")
OCTDIGITS = frozenset("01234567")
HEXDIGITS = frozenset("0123456789abcdefABCDEF")
ASCIILETTERS = frozenset("abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ")
WHITESPACE = frozenset(" \t\n\r\v\f")
_REPEATCODES = frozenset({MIN_REPEAT, MAX_REPEAT})
_UNITCODES = frozenset({ANY, RANGE, IN, LITERAL, NOT_LITERAL, CATEGORY})
ESCAPES = {
r"\a": (LITERAL, ord("\a")),
r"\b": (LITERAL, ord("\b")),
r"\f": (LITERAL, ord("\f")),
r"\n": (LITERAL, ord("\n")),
r"\r": (LITERAL, ord("\r")),
r"\t": (LITERAL, ord("\t")),
r"\v": (LITERAL, ord("\v")),
r"\\": (LITERAL, ord("\\"))
}
CATEGORIES = {
r"\A": (AT, AT_BEGINNING_STRING), # start of string
r"\b": (AT, AT_BOUNDARY),
r"\B": (AT, AT_NON_BOUNDARY),
r"\d": (IN, [(CATEGORY, CATEGORY_DIGIT)]),
r"\D": (IN, [(CATEGORY, CATEGORY_NOT_DIGIT)]),
r"\s": (IN, [(CATEGORY, CATEGORY_SPACE)]),
r"\S": (IN, [(CATEGORY, CATEGORY_NOT_SPACE)]),
r"\w": (IN, [(CATEGORY, CATEGORY_WORD)]),
r"\W": (IN, [(CATEGORY, CATEGORY_NOT_WORD)]),
r"\Z": (AT, AT_END_STRING), # end of string
}
FLAGS = {
# standard flags
"i": SRE_FLAG_IGNORECASE,
"L": SRE_FLAG_LOCALE,
"m": SRE_FLAG_MULTILINE,
"s": SRE_FLAG_DOTALL,
"x": SRE_FLAG_VERBOSE,
# extensions
"a": SRE_FLAG_ASCII,
"t": SRE_FLAG_TEMPLATE,
"u": SRE_FLAG_UNICODE,
}
class Pattern:
# master pattern object. keeps track of global attributes
def __init__(self):
self.flags = 0
self.groupdict = {}
self.groupwidths = [None] # group 0
self.lookbehindgroups = None
@property
def groups(self):
return len(self.groupwidths)
def opengroup(self, name=None):
gid = self.groups
self.groupwidths.append(None)
if self.groups > MAXGROUPS:
raise error("too many groups")
if name is not None:
ogid = self.groupdict.get(name, None)
if ogid is not None:
raise error("redefinition of group name %r as group %d; "
"was group %d" % (name, gid, ogid))
self.groupdict[name] = gid
return gid
def closegroup(self, gid, p):
self.groupwidths[gid] = p.getwidth()
def checkgroup(self, gid):
return gid < self.groups and self.groupwidths[gid] is not None
def checklookbehindgroup(self, gid, source):
if self.lookbehindgroups is not None:
if not self.checkgroup(gid):
raise source.error('cannot refer to an open group')
if gid >= self.lookbehindgroups:
raise source.error('cannot refer to group defined in the same '
'lookbehind subpattern')
class SubPattern:
# a subpattern, in intermediate form
def __init__(self, pattern, data=None):
self.pattern = pattern
if data is None:
data = []
self.data = data
self.width = None
def dump(self, level=0):
nl = True
seqtypes = (tuple, list)
for op, av in self.data:
print(level*" " + str(op), end='')
if op is IN:
# member sublanguage
print()
for op, a in av:
print((level+1)*" " + str(op), a)
elif op is BRANCH:
print()
for i, a in enumerate(av[1]):
if i:
print(level*" " + "OR")
a.dump(level+1)
elif op is GROUPREF_EXISTS:
condgroup, item_yes, item_no = av
print('', condgroup)
item_yes.dump(level+1)
if item_no:
print(level*" " + "ELSE")
item_no.dump(level+1)
elif isinstance(av, seqtypes):
nl = False
for a in av:
if isinstance(a, SubPattern):
if not nl:
print()
a.dump(level+1)
nl = True
else:
if not nl:
print(' ', end='')
print(a, end='')
nl = False
if not nl:
print()
else:
print('', av)
def __repr__(self):
return repr(self.data)
def __len__(self):
return len(self.data)
def __delitem__(self, index):
del self.data[index]
def __getitem__(self, index):
if isinstance(index, slice):
return SubPattern(self.pattern, self.data[index])
return self.data[index]
def __setitem__(self, index, code):
self.data[index] = code
def insert(self, index, code):
self.data.insert(index, code)
def append(self, code):
self.data.append(code)
def getwidth(self):
# determine the width (min, max) for this subpattern
if self.width is not None:
return self.width
lo = hi = 0
for op, av in self.data:
if op is BRANCH:
i = MAXREPEAT - 1
j = 0
for av in av[1]:
l, h = av.getwidth()
i = min(i, l)
j = max(j, h)
lo = lo + i
hi = hi + j
elif op is CALL:
i, j = av.getwidth()
lo = lo + i
hi = hi + j
elif op is SUBPATTERN:
i, j = av[1].getwidth()
lo = lo + i
hi = hi + j
elif op in _REPEATCODES:
i, j = av[2].getwidth()
lo = lo + i * av[0]
hi = hi + j * av[1]
elif op in _UNITCODES:
lo = lo + 1
hi = hi + 1
elif op is GROUPREF:
i, j = self.pattern.groupwidths[av]
lo = lo + i
hi = hi + j
elif op is GROUPREF_EXISTS:
i, j = av[1].getwidth()
if av[2] is not None:
l, h = av[2].getwidth()
i = min(i, l)
j = max(j, h)
else:
i = 0
lo = lo + i
hi = hi + j
elif op is SUCCESS:
break
self.width = min(lo, MAXREPEAT - 1), min(hi, MAXREPEAT)
return self.width
class Tokenizer:
def __init__(self, string):
self.istext = isinstance(string, str)
self.string = string
if not self.istext:
string = str(string, 'latin1')
self.decoded_string = string
self.index = 0
self.next = None
self.__next()
def __next(self):
index = self.index
try:
char = self.decoded_string[index]
except IndexError:
self.next = None
return
if char == "\\":
index += 1
try:
char += self.decoded_string[index]
except IndexError:
raise error("bad escape (end of pattern)",
self.string, len(self.string) - 1) from None
self.index = index + 1
self.next = char
def match(self, char):
if char == self.next:
self.__next()
return True
return False
def get(self):
this = self.next
self.__next()
return this
def getwhile(self, n, charset):
result = ''
for _ in range(n):
c = self.next
if c not in charset:
break
result += c
self.__next()
return result
def getuntil(self, terminator):
result = ''
while True:
c = self.next
self.__next()
if c is None:
if not result:
raise self.error("missing group name")
raise self.error("missing %s, unterminated name" % terminator,
len(result))
if c == terminator:
if not result:
raise self.error("missing group name", 1)
break
result += c
return result
def tell(self):
return self.index - len(self.next or '')
def seek(self, index):
self.index = index
self.__next()
def error(self, msg, offset=0):
return error(msg, self.string, self.tell() - offset)
# The following three functions are not used in this module anymore, but we keep
# them here (with DeprecationWarnings) for backwards compatibility.
def isident(char):
import warnings
warnings.warn('sre_parse.isident() will be removed in 3.5',
DeprecationWarning, stacklevel=2)
return "a" <= char <= "z" or "A" <= char <= "Z" or char == "_"
def isdigit(char):
import warnings
warnings.warn('sre_parse.isdigit() will be removed in 3.5',
DeprecationWarning, stacklevel=2)
return "0" <= char <= "9"
def isname(name):
import warnings
warnings.warn('sre_parse.isname() will be removed in 3.5',
DeprecationWarning, stacklevel=2)
# check that group name is a valid string
if not isident(name[0]):
return False
for char in name[1:]:
if not isident(char) and not isdigit(char):
return False
return True
def _class_escape(source, escape):
# handle escape code inside character class
code = ESCAPES.get(escape)
if code:
return code
code = CATEGORIES.get(escape)
if code and code[0] is IN:
return code
try:
c = escape[1:2]
if c == "x":
# hexadecimal escape (exactly two digits)
escape += source.getwhile(2, HEXDIGITS)
if len(escape) != 4:
raise source.error("incomplete escape %s" % escape, len(escape))
return LITERAL, int(escape[2:], 16)
elif c == "u" and source.istext:
# unicode escape (exactly four digits)
escape += source.getwhile(4, HEXDIGITS)
if len(escape) != 6:
raise source.error("incomplete escape %s" % escape, len(escape))
return LITERAL, int(escape[2:], 16)
elif c == "U" and source.istext:
# unicode escape (exactly eight digits)
escape += source.getwhile(8, HEXDIGITS)
if len(escape) != 10:
raise source.error("incomplete escape %s" % escape, len(escape))
c = int(escape[2:], 16)
chr(c) # raise ValueError for invalid code
return LITERAL, c
elif c in OCTDIGITS:
# octal escape (up to three digits)
escape += source.getwhile(2, OCTDIGITS)
c = int(escape[1:], 8)
if c > 0o377:
raise source.error('octal escape value %s outside of '
'range 0-0o377' % escape, len(escape))
return LITERAL, c
elif c in DIGITS:
raise ValueError
if len(escape) == 2:
if c in ASCIILETTERS:
import warnings
warnings.warn('bad escape %s' % escape,
DeprecationWarning, stacklevel=8)
return LITERAL, ord(escape[1])
except ValueError:
pass
raise source.error("bad escape %s" % escape, len(escape))
def _escape(source, escape, state):
# handle escape code in expression
code = CATEGORIES.get(escape)
if code:
return code
code = ESCAPES.get(escape)
if code:
return code
try:
c = escape[1:2]
if c == "x":
# hexadecimal escape
escape += source.getwhile(2, HEXDIGITS)
if len(escape) != 4:
raise source.error("incomplete escape %s" % escape, len(escape))
return LITERAL, int(escape[2:], 16)
elif c == "u" and source.istext:
# unicode escape (exactly four digits)
escape += source.getwhile(4, HEXDIGITS)
if len(escape) != 6:
raise source.error("incomplete escape %s" % escape, len(escape))
return LITERAL, int(escape[2:], 16)
elif c == "U" and source.istext:
# unicode escape (exactly eight digits)
escape += source.getwhile(8, HEXDIGITS)
if len(escape) != 10:
raise source.error("incomplete escape %s" % escape, len(escape))
c = int(escape[2:], 16)
chr(c) # raise ValueError for invalid code
return LITERAL, c
elif c == "0":
# octal escape
escape += source.getwhile(2, OCTDIGITS)
return LITERAL, int(escape[1:], 8)
elif c in DIGITS:
# octal escape *or* decimal group reference (sigh)
if source.next in DIGITS:
escape += source.get()
if (escape[1] in OCTDIGITS and escape[2] in OCTDIGITS and
source.next in OCTDIGITS):
# got three octal digits; this is an octal escape
escape += source.get()
c = int(escape[1:], 8)
if c > 0o377:
raise source.error('octal escape value %s outside of '
'range 0-0o377' % escape,
len(escape))
return LITERAL, c
# not an octal escape, so this is a group reference
group = int(escape[1:])
if group < state.groups:
if not state.checkgroup(group):
raise source.error("cannot refer to an open group",
len(escape))
state.checklookbehindgroup(group, source)
return GROUPREF, group
raise source.error("invalid group reference", len(escape))
if len(escape) == 2:
if c in ASCIILETTERS:
import warnings
warnings.warn('bad escape %s' % escape,
DeprecationWarning, stacklevel=8)
return LITERAL, ord(escape[1])
except ValueError:
pass
raise source.error("bad escape %s" % escape, len(escape))
def _parse_sub(source, state, nested=True):
# parse an alternation: a|b|c
items = []
itemsappend = items.append
sourcematch = source.match
start = source.tell()
while True:
itemsappend(_parse(source, state))
if not sourcematch("|"):
break
if len(items) == 1:
return items[0]
subpattern = SubPattern(state)
subpatternappend = subpattern.append
# check if all items share a common prefix
while True:
prefix = None
for item in items:
if not item:
break
if prefix is None:
prefix = item[0]
elif item[0] != prefix:
break
else:
# all subitems start with a common "prefix".
# move it out of the branch
for item in items:
del item[0]
subpatternappend(prefix)
continue # check next one
break
# check if the branch can be replaced by a character set
for item in items:
if len(item) != 1 or item[0][0] is not LITERAL:
break
else:
# we can store this as a character set instead of a
# branch (the compiler may optimize this even more)
subpatternappend((IN, [item[0] for item in items]))
return subpattern
subpattern.append((BRANCH, (None, items)))
return subpattern
def _parse_sub_cond(source, state, condgroup):
item_yes = _parse(source, state)
if source.match("|"):
item_no = _parse(source, state)
if source.next == "|":
raise source.error("conditional backref with more than two branches")
else:
item_no = None
subpattern = SubPattern(state)
subpattern.append((GROUPREF_EXISTS, (condgroup, item_yes, item_no)))
return subpattern
def _parse(source, state):
# parse a simple pattern
subpattern = SubPattern(state)
# precompute constants into local variables
subpatternappend = subpattern.append
sourceget = source.get
sourcematch = source.match
_len = len
_ord = ord
verbose = state.flags & SRE_FLAG_VERBOSE
while True:
this = source.next
if this is None:
break # end of pattern
if this in "|)":
break # end of subpattern
sourceget()
if verbose:
# skip whitespace and comments
if this in WHITESPACE:
continue
if this == "#":
while True:
this = sourceget()
if this is None or this == "\n":
break
continue
if this[0] == "\\":
code = _escape(source, this, state)
subpatternappend(code)
elif this not in SPECIAL_CHARS:
subpatternappend((LITERAL, _ord(this)))
elif this == "[":
here = source.tell() - 1
# character set
set = []
setappend = set.append
## if sourcematch(":"):
## pass # handle character classes
if sourcematch("^"):
setappend((NEGATE, None))
# check remaining characters
start = set[:]
while True:
this = sourceget()
if this is None:
raise source.error("unterminated character set",
source.tell() - here)
if this == "]" and set != start:
break
elif this[0] == "\\":
code1 = _class_escape(source, this)
else:
code1 = LITERAL, _ord(this)
if sourcematch("-"):
# potential range
that = sourceget()
if that is None:
raise source.error("unterminated character set",
source.tell() - here)
if that == "]":
if code1[0] is IN:
code1 = code1[1][0]
setappend(code1)
setappend((LITERAL, _ord("-")))
break
if that[0] == "\\":
code2 = _class_escape(source, that)
else:
code2 = LITERAL, _ord(that)
if code1[0] != LITERAL or code2[0] != LITERAL:
msg = "bad character range %s-%s" % (this, that)
raise source.error(msg, len(this) + 1 + len(that))
lo = code1[1]
hi = code2[1]
if hi < lo:
msg = "bad character range %s-%s" % (this, that)
raise source.error(msg, len(this) + 1 + len(that))
setappend((RANGE, (lo, hi)))
else:
if code1[0] is IN:
code1 = code1[1][0]
setappend(code1)
# XXX: <fl> should move set optimization to compiler!
if _len(set)==1 and set[0][0] is LITERAL:
subpatternappend(set[0]) # optimization
elif _len(set)==2 and set[0][0] is NEGATE and set[1][0] is LITERAL:
subpatternappend((NOT_LITERAL, set[1][1])) # optimization
else:
# XXX: <fl> should add charmap optimization here
subpatternappend((IN, set))
elif this in REPEAT_CHARS:
# repeat previous item
here = source.tell()
if this == "?":
min, max = 0, 1
elif this == "*":
min, max = 0, MAXREPEAT
elif this == "+":
min, max = 1, MAXREPEAT
elif this == "{":
if source.next == "}":
subpatternappend((LITERAL, _ord(this)))
continue
min, max = 0, MAXREPEAT
lo = hi = ""
while source.next in DIGITS:
lo += sourceget()
if sourcematch(","):
while source.next in DIGITS:
hi += sourceget()
else:
hi = lo
if not sourcematch("}"):
subpatternappend((LITERAL, _ord(this)))
source.seek(here)
continue
if lo:
min = int(lo)
if min >= MAXREPEAT:
raise OverflowError("the repetition number is too large")
if hi:
max = int(hi)
if max >= MAXREPEAT:
raise OverflowError("the repetition number is too large")
if max < min:
raise source.error("min repeat greater than max repeat",
source.tell() - here)
else:
raise AssertionError("unsupported quantifier %r" % (char,))
# figure out which item to repeat
if subpattern:
item = subpattern[-1:]
else:
item = None
if not item or (_len(item) == 1 and item[0][0] is AT):
raise source.error("nothing to repeat",
source.tell() - here + len(this))
if item[0][0] in _REPEATCODES:
raise source.error("multiple repeat",
source.tell() - here + len(this))
if sourcematch("?"):
subpattern[-1] = (MIN_REPEAT, (min, max, item))
else:
subpattern[-1] = (MAX_REPEAT, (min, max, item))
elif this == ".":
subpatternappend((ANY, None))
elif this == "(":
start = source.tell() - 1
group = True
name = None
condgroup = None
if sourcematch("?"):
# options
char = sourceget()
if char is None:
raise source.error("unexpected end of pattern")
if char == "P":
# python extensions
if sourcematch("<"):
# named group: skip forward to end of name
name = source.getuntil(">")
if not name.isidentifier():
msg = "bad character in group name %r" % name
raise source.error(msg, len(name) + 1)
elif sourcematch("="):
# named backreference
name = source.getuntil(")")
if not name.isidentifier():
msg = "bad character in group name %r" % name
raise source.error(msg, len(name) + 1)
gid = state.groupdict.get(name)
if gid is None:
msg = "unknown group name %r" % name
raise source.error(msg, len(name) + 1)
if not state.checkgroup(gid):
raise source.error("cannot refer to an open group",
len(name) + 1)
state.checklookbehindgroup(gid, source)
subpatternappend((GROUPREF, gid))
continue
else:
char = sourceget()
if char is None:
raise source.error("unexpected end of pattern")
raise source.error("unknown extension ?P" + char,
len(char) + 2)
elif char == ":":
# non-capturing group
group = None
elif char == "#":
# comment
while True:
if source.next is None:
raise source.error("missing ), unterminated comment",
source.tell() - start)
if sourceget() == ")":
break
continue
elif char in "=!<":
# lookahead assertions
dir = 1
if char == "<":
char = sourceget()
if char is None:
raise source.error("unexpected end of pattern")
if char not in "=!":
raise source.error("unknown extension ?<" + char,
len(char) + 2)
dir = -1 # lookbehind
lookbehindgroups = state.lookbehindgroups
if lookbehindgroups is None:
state.lookbehindgroups = state.groups
p = _parse_sub(source, state)
if dir < 0:
if lookbehindgroups is None:
state.lookbehindgroups = None
if not sourcematch(")"):
raise source.error("missing ), unterminated subpattern",
source.tell() - start)
if char == "=":
subpatternappend((ASSERT, (dir, p)))
else:
subpatternappend((ASSERT_NOT, (dir, p)))
continue
elif char == "(":
# conditional backreference group
condname = source.getuntil(")")
group = None
if condname.isidentifier():
condgroup = state.groupdict.get(condname)
if condgroup is None:
msg = "unknown group name %r" % condname
raise source.error(msg, len(condname) + 1)
else:
try:
condgroup = int(condname)
if condgroup < 0:
raise ValueError
except ValueError:
msg = "bad character in group name %r" % condname
raise source.error(msg, len(condname) + 1) from None
if not condgroup:
raise source.error("bad group number",
len(condname) + 1)
if condgroup >= MAXGROUPS:
raise source.error("invalid group reference",
len(condname) + 1)
state.checklookbehindgroup(condgroup, source)
elif char in FLAGS:
# flags
while True:
state.flags |= FLAGS[char]
char = sourceget()
if char is None:
raise source.error("missing )")
if char == ")":
break
if char not in FLAGS:
raise source.error("unknown flag", len(char))
verbose = state.flags & SRE_FLAG_VERBOSE
continue
else:
raise source.error("unknown extension ?" + char,
len(char) + 1)
# parse group contents
if group is not None:
try:
group = state.opengroup(name)
except error as err:
raise source.error(err.msg, len(name) + 1) from None
if condgroup:
p = _parse_sub_cond(source, state, condgroup)
else:
p = _parse_sub(source, state)
if not source.match(")"):
raise source.error("missing ), unterminated subpattern",
source.tell() - start)
if group is not None:
state.closegroup(group, p)
subpatternappend((SUBPATTERN, (group, p)))
elif this == "^":
subpatternappend((AT, AT_BEGINNING))
elif this == "$":
subpattern.append((AT, AT_END))
else:
raise AssertionError("unsupported special character %r" % (char,))
return subpattern
def fix_flags(src, flags):
# Check and fix flags according to the type of pattern (str or bytes)
if isinstance(src, str):
if flags & SRE_FLAG_LOCALE:
import warnings
warnings.warn("LOCALE flag with a str pattern is deprecated. "
"Will be an error in 3.6",
DeprecationWarning, stacklevel=6)
if not flags & SRE_FLAG_ASCII:
flags |= SRE_FLAG_UNICODE
elif flags & SRE_FLAG_UNICODE:
raise ValueError("ASCII and UNICODE flags are incompatible")
else:
if flags & SRE_FLAG_UNICODE:
raise ValueError("cannot use UNICODE flag with a bytes pattern")
if flags & SRE_FLAG_LOCALE and flags & SRE_FLAG_ASCII:
import warnings
warnings.warn("ASCII and LOCALE flags are incompatible. "
"Will be an error in 3.6",
DeprecationWarning, stacklevel=6)
return flags
def parse(str, flags=0, pattern=None):
# parse 're' pattern into list of (opcode, argument) tuples
source = Tokenizer(str)
if pattern is None:
pattern = Pattern()
pattern.flags = flags
pattern.str = str
p = _parse_sub(source, pattern, 0)
p.pattern.flags = fix_flags(str, p.pattern.flags)
if source.next is not None:
assert source.next == ")"
raise source.error("unbalanced parenthesis")
if flags & SRE_FLAG_DEBUG:
p.dump()
if not (flags & SRE_FLAG_VERBOSE) and p.pattern.flags & SRE_FLAG_VERBOSE:
# the VERBOSE flag was switched on inside the pattern. to be
# on the safe side, we'll parse the whole thing again...
return parse(str, p.pattern.flags)
return p
def parse_template(source, pattern):
# parse 're' replacement string into list of literals and
# group references
s = Tokenizer(source)
sget = s.get
groups = []
literals = []
literal = []
lappend = literal.append
def addgroup(index):
if literal:
literals.append(''.join(literal))
del literal[:]
groups.append((len(literals), index))
literals.append(None)
groupindex = pattern.groupindex
while True:
this = sget()
if this is None:
break # end of replacement string
if this[0] == "\\":
# group
c = this[1]
if c == "g":
name = ""
if not s.match("<"):
raise s.error("missing <")
name = s.getuntil(">")
if name.isidentifier():
try:
index = groupindex[name]
except KeyError:
raise IndexError("unknown group name %r" % name)
else:
try:
index = int(name)
if index < 0:
raise ValueError
except ValueError:
raise s.error("bad character in group name %r" % name,
len(name) + 1) from None
if index >= MAXGROUPS:
raise s.error("invalid group reference",
len(name) + 1)
addgroup(index)
elif c == "0":
if s.next in OCTDIGITS:
this += sget()
if s.next in OCTDIGITS:
this += sget()
lappend(chr(int(this[1:], 8) & 0xff))
elif c in DIGITS:
isoctal = False
if s.next in DIGITS:
this += sget()
if (c in OCTDIGITS and this[2] in OCTDIGITS and
s.next in OCTDIGITS):
this += sget()
isoctal = True
c = int(this[1:], 8)
if c > 0o377:
raise s.error('octal escape value %s outside of '
'range 0-0o377' % this, len(this))
lappend(chr(c))
if not isoctal:
addgroup(int(this[1:]))
else:
try:
this = chr(ESCAPES[this][1])
except KeyError:
if c in ASCIILETTERS:
import warnings
warnings.warn('bad escape %s' % this,
DeprecationWarning, stacklevel=4)
lappend(this)
else:
lappend(this)
if literal:
literals.append(''.join(literal))
if not isinstance(source, str):
# The tokenizer implicitly decodes bytes objects as latin-1, we must
# therefore re-encode the final representation.
literals = [None if s is None else s.encode('latin-1') for s in literals]
return groups, literals
def expand_template(template, match):
g = match.group
empty = match.string[:0]
groups, literals = template
literals = literals[:]
try:
for index, group in groups:
literals[index] = g(group) or empty
except IndexError:
raise error("invalid group reference")
return empty.join(literals)
Rosenblum TV: Video training, virtual workshops, classes, tutorials
RE-INVENTING THE TELEVISION NEWS BUSINESS*
A revolution in video storytelling
Creating entirely new & cost-effective production methods
From the world leaders in video production training and the creators of Character Driven Storytelling™
*and every other business that uses video
WHAT WE DO
Over the past 35 years, we have designed, built or restructured some of the most powerful news and journalism companies in the world.
We replace the traditional TV news ‘crew’ with one highly trained journalist, working alone with nothing but an iPhone.
No more TV news ‘crews’, no editors and no field producers.
This is television news done the way newspaper journalism is done – one reporter with their electronic pad and pencil.
In doing this, we can cut the cost of production by as much as 75% while increasing ratings and audience engagement.
In the place of conventional TV news ‘packages’ – ie, reporter stand up, interview, b-roll, man on the street, we marry great journalism with Netflix and Hollywood storytelling.
It’s a combination that works.
We have taken most of our clients to #1 in their respective markets.
And it’s not just for news. Any company, any profit, any NGO and anyone else who is online needs to tell their story in compelling yet cost-effective video. We can teach you to do that. Either in person or virtually.
EXAMPLES OF WHAT WE CAN TEACH YOUR STAFF TO PRODUCE
ITAY HOD
Itay Hod, MMJ with KPIX/CBS in San Francisco, took the 5-Day Intensive Video Storytelling Bootcamp in 2018.
Because he works alone, with only an iPhone, he was able to embed himself with a homeless family.
Here’s the story he produced in a one-day turn.
KIET DO
Kiet Do, an MMJ with KPIX/CBS in San Francisco, took the 5-Day Intensive Video Storytelling Bootcamp in 2021.
Here is a story he produced, all on his own, with only an iPhone and in a one-day turn.
TAYLOR SCHAUB
Taylor Schaub, an MMJ with Spectrum News 1 in LA, took the 5-Day Intensive Video Storytelling Bootcamp in 2023.
Here is a story he turned in only one day, using only an iPhone. It was the first video story he ever did and it was nominated for an Emmy.
THE BOOTCAMP
How do we convert stations and whole networks to working in this way?
Since 1988, we have run intensive 5-Day Video Storytelling Bootcamps
We have done these all over the world.
These are hands-on bootcamps, and participants learn an entirely new way of creating TV news stories.
-We shoot at a 3:1 ratio or lower, so turnaround times are fast.
-We go directly from camera to timelilne and edit – no written scripts. We work in the medium of pictures and sound.
-We are entirely character-driven.
-We are driven by pictures and real events.
-We are focused almost entirely on ’the viewer experience’.
Since 1988, more than 70,000 journalists around the world have taken our bootcamps, either in person on virtualy.
We have started to work with CBS News, bringing our ideas of character-driven storytelling to one of the most successful and biggest networks in the United States. Since beginning to work with them ratings have climbed and more importantly, audience engagement is through the ceiling.
We started New York Times Television in 1990 and it was the first paper to be brought into the world of TV. It quickly became one of the most successful non-fiction production companies in the United States. The series and documentaries we produced won many awards including multiple Emmys.
We have been working with the BBC since the year 2000 helping to convert their national news network to our visual storytelling technique. Most recently we have trained teams from their sports, documentaries, and comedy divisions to make character-driven stories using only smartphones.
For the past five years we have worked with Spectrum News to introduce and train their journalists on visual, character driven storytelling using smartphones helping to create a different kind of local news for their network of 24-Hour News Stations across the United States.
In 2006, we were approached by the United Nations. Rather than rely on news outlets, it would be much easier to train the field operatives to produce their own stories. We spent two years working with the UN, training more than 100 of their staff in bootcamps in Geneva and Nairobi.
We trained 50 print reporters at the paper to shoot and tell their own stories, in conjunction with their print work. We built a TV newsroom in their existing print newsroom – you could not ask for a better set and they began to live stream their stories in conjunction with their print work.
We spent two years with McGraw Hill, training more than 150 of their staffers, making them completely video literate. McGraw/Hill media properties we transit included Business Week, Aviation Week, (what was the name of the architecture magazine), and JD Power and Associates.
In 1990, we were approached by The Voice of America, the official broadcasting agency for the United States Government. When we met with VOA, they were only a short wave radio broadcaster, but working with them, we took them into television, launching VOA-TV.
British based Oyster Yachts makes some of the finest yachts in the world. Like every other company, they had to find a way to feed the never-ending video demands of social media – sites like Instagram and TikTok. We trained the Oyster staff to tell their own stories, using only iPhones.
We were approached by SEPA, the Scottish Environmental Protection Agency because they had to continually find a way to ‘feed the media beast’. The result was that SEPA was able to tell their own stories, whenever they wanted, and at almost no additional cost.
Michael Rosenblum has been writing about the media since 1988. His work and ideas have appeared in The Guardian, The Huffington Post, Ilkeston Life and many other publications.
He has been blogging regularly for the past 35 years on this subject. Having taught media studies at Columbia University, NYU and now the University of Oxford, he is considered an expert on this subject.
Continue reading this post or look back at previous posts.
