def remove_compiled_regex(txt: str,
compiled_regex: re.compile,
substitute: str = ""):
"""
Search for the compiled regex in the txt and either replace it with the substitute or remove it
"""
entities = compiled_regex.findall(txt)
txt = compiled_regex.sub(substitute, txt)
return txt, entities
def load(string, required=None, callbacks=None):
"""Parse the given string. Raises a ParseError if any problems are
encountered, including if any field in required is not included. Callbacks
is a dictionary of functions, listed by field, with the signature (mapping,
line_number)."""
if callbacks is None:
callbacks = {}
lines = string.splitlines()
mapping = {}
#Skip blank lines at the beginning of the file
offset = 0
for offset, line in enumerate(lines):
if line and not line.isspace():
break
current_line, lines = lines[offset], lines[offset:]
current_line_number = offset
indent_size = get_indent(current_line)
comment = Regex(r"(?<!\\)#.*$")
line_numbers = {}
for line_number, indented_line in enumerate_with_offset(lines, offset + 1):
indent, line = indented_line[:indent_size], indented_line[indent_size:]
line = comment.sub("", line)
if indent and not indent.isspace():
raise ParseError("Unexpected unindent.", line_number,
indented_line)
if not line or line[0].isspace():
current_line += line
else:
field, value = pairify(current_line, current_line_number)
mapping[field] = value
line_numbers[field] = current_line_number
current_line = line
current_line_number = line_number
field, value = pairify(current_line, current_line_number)
mapping[field] = value
line_numbers[field] = current_line_number
if required is not None:
for field in required:
if field not in mapping:
raise ParseError("Required field \"%s\" missing." % field)
for field in callbacks.iterkeys():
line_number = line_numbers[field] if field in line_numbers else None
callbacks[field](mapping, line_number)
return mapping
#! /usr/bin/env python
# $ ./foo.py
# BEFORE: A \\" \\\" Z
# AFTER : A \\ \\\" Z
#
# BEFORE: A \\\" \\" Z
# AFTER : A \\\" \\ Z
from re import compile as Regex
def remove_first_group(m):
start = m.start(1) - m.start(0)
end = m.end(1) - m.start(0)
whole_match = m.group(0)
return whole_match[:start] + whole_match[end:]
unescaped_doublequote = Regex(r'(?<!\\)(?:\\\\)*(")')
for test in (
r'A \\" \\\" Z',
r'A \\\" \\" Z',
):
print 'BEFORE:', test
print 'AFTER :', unescaped_doublequote.sub(remove_first_group, test)
print
if oSwap4Blanks( sTest ) != ' ' * 82:
#
lProblems.append( 'getReplaceManyOldWithBlanksSwapper()' )
#
if ReplaceManyOldWithBlanks( sTest, ( digits, uppercase, lowercase ) ) != ' ' * 82:
#
lProblems.append( 'ReplaceManyOldWithBlanks()' )
#
if get_obsoleteGlobalReplaceWithSwapper( sTest, oSwap4Blanks ) != ' ' * 82:
#
lProblems.append( 'get_obsoleteGlobalReplaceWithSwapper()' )
#
#
oMatch = REcompile( 'l.+e' )
#
if oMatch.sub( getBlanksForReMatchObj,
'Mary had a little lamb.' ) != \
'Mary had a lamb.':
#
lProblems.append( 'getBlanksForReMatchObj()' )
#
#
sWhiteChars = '\n\t\rabc\r\t\n'
#
if getSpaceForWhiteAlsoStrip( sWhiteChars ) != 'abc' or \
getSpaceForWhiteAlsoStrip( sWhiteChars+sWhiteChars ) != 'abc abc':
#
lProblems.append( 'getSpaceForWhiteAlsoStrip()' )
#
#
if replaceLast( 'abcde0fghij0klmno0pqrst0uvwxy0z', '0', '8' ) != \
'abcde0fghij0klmno0pqrst0uvwxy8z':
#! /usr/bin/env python
# $ ./foo.py
# BEFORE: A \\" \\\" Z
# AFTER : A \\ \\\" Z
#
# BEFORE: A \\\" \\" Z
# AFTER : A \\\" \\ Z
from re import compile as Regex
def remove_first_group(m):
start = m.start(1) - m.start(0)
end = m.end(1) - m.start(0)
whole_match = m.group(0)
return whole_match[:start] + whole_match[end:]
unescaped_doublequote = Regex(r'(?<!\\)(?:\\\\)*(")')
for test in (
r'A \\" \\\" Z',
r'A \\\" \\" Z',
):
print 'BEFORE:', test
print 'AFTER :', unescaped_doublequote.sub(remove_first_group, test)
print
def remove_comments(lines):
"""Remove all lines containing a comment."""
comment_line = Regex("^\s*#.*$")
eol_comment = Regex(r"(?<!\\)#.*$")
return [eol_comment.sub("", line) for line in lines if not comment_line.match(line)]