Python ply.lex.lexer() Examples

The following are 30 code examples of ply.lex.lexer(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module ply.lex , or try the search function .
Example #1
Source File: yacc.py    From SublimeKSP with GNU General Public License v3.0 6 votes vote down vote up 
def parse(self,input=None,lexer=None,debug=0,tracking=0,tokenfunc=None):
        if debug or yaccdevel:
            if isinstance(debug,int):
                debug = PlyLogger(sys.stderr)
            return self.parsedebug(input,lexer,debug,tracking,tokenfunc)
        elif tracking:
            return self.parseopt(input,lexer,debug,tracking,tokenfunc)
        else:
            return self.parseopt_notrack(input,lexer,debug,tracking,tokenfunc)
        

    # !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
    # parsedebug().
    #
    # This is the debugging enabled version of parse().  All changes made to the
    # parsing engine should be made here.   For the non-debugging version,
    # copy this code to a method parseopt() and delete all of the sections
    # enclosed in:
    #
    #      #--! DEBUG
    #      statements
    #      #--! DEBUG
    #
    # !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
Example #2
Source File: cpp.py    From misp42splunk with GNU Lesser General Public License v3.0 6 votes vote down vote up 
def __init__(self,lexer=None):
        if lexer is None:
            lexer = lex.lexer
        self.lexer = lexer
        self.macros = { }
        self.path = []
        self.temp_path = []

        # Probe the lexer for selected tokens
        self.lexprobe()

        tm = time.localtime()
        self.define("__DATE__ \"%s\"" % time.strftime("%b %d %Y",tm))
        self.define("__TIME__ \"%s\"" % time.strftime("%H:%M:%S",tm))
        self.parser = None

    # -----------------------------------------------------------------------------
    # tokenize()
    #
    # Utility function. Given a string of text, tokenize into a list of tokens
    # -----------------------------------------------------------------------------
Example #3
Source File: yacc.py    From oss-ftp with MIT License 6 votes vote down vote up 
def parse(self,input=None,lexer=None,debug=0,tracking=0,tokenfunc=None):
        if debug or yaccdevel:
            if isinstance(debug,int):
                debug = PlyLogger(sys.stderr)
            return self.parsedebug(input,lexer,debug,tracking,tokenfunc)
        elif tracking:
            return self.parseopt(input,lexer,debug,tracking,tokenfunc)
        else:
            return self.parseopt_notrack(input,lexer,debug,tracking,tokenfunc)
        

    # !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
    # parsedebug().
    #
    # This is the debugging enabled version of parse().  All changes made to the
    # parsing engine should be made here.   For the non-debugging version,
    # copy this code to a method parseopt() and delete all of the sections
    # enclosed in:
    #
    #      #--! DEBUG
    #      statements
    #      #--! DEBUG
    #
    # !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
Example #4
Source File: cpp.py    From SwiftKitten with MIT License 6 votes vote down vote up 
def __init__(self,lexer=None):
        if lexer is None:
            lexer = lex.lexer
        self.lexer = lexer
        self.macros = { }
        self.path = []
        self.temp_path = []

        # Probe the lexer for selected tokens
        self.lexprobe()

        tm = time.localtime()
        self.define("__DATE__ \"%s\"" % time.strftime("%b %d %Y",tm))
        self.define("__TIME__ \"%s\"" % time.strftime("%H:%M:%S",tm))
        self.parser = None

    # -----------------------------------------------------------------------------
    # tokenize()
    #
    # Utility function. Given a string of text, tokenize into a list of tokens
    # -----------------------------------------------------------------------------
Example #5
Source File: cpp.py    From oss-ftp with MIT License 6 votes vote down vote up 
def __init__(self,lexer=None):
        if lexer is None:
            lexer = lex.lexer
        self.lexer = lexer
        self.macros = { }
        self.path = []
        self.temp_path = []

        # Probe the lexer for selected tokens
        self.lexprobe()

        tm = time.localtime()
        self.define("__DATE__ \"%s\"" % time.strftime("%b %d %Y",tm))
        self.define("__TIME__ \"%s\"" % time.strftime("%H:%M:%S",tm))
        self.parser = None

    # -----------------------------------------------------------------------------
    # tokenize()
    #
    # Utility function. Given a string of text, tokenize into a list of tokens
    # -----------------------------------------------------------------------------
Example #6
Source File: yacc.py    From SwiftKitten with MIT License 6 votes vote down vote up 
def parse(self,input=None,lexer=None,debug=0,tracking=0,tokenfunc=None):
        if debug or yaccdevel:
            if isinstance(debug,int):
                debug = PlyLogger(sys.stderr)
            return self.parsedebug(input,lexer,debug,tracking,tokenfunc)
        elif tracking:
            return self.parseopt(input,lexer,debug,tracking,tokenfunc)
        else:
            return self.parseopt_notrack(input,lexer,debug,tracking,tokenfunc)
        

    # !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
    # parsedebug().
    #
    # This is the debugging enabled version of parse().  All changes made to the
    # parsing engine should be made here.   For the non-debugging version,
    # copy this code to a method parseopt() and delete all of the sections
    # enclosed in:
    #
    #      #--! DEBUG
    #      statements
    #      #--! DEBUG
    #
    # !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
Example #7
Source File: cpp.py    From SublimeKSP with GNU General Public License v3.0 6 votes vote down vote up 
def __init__(self,lexer=None):
        if lexer is None:
            lexer = lex.lexer
        self.lexer = lexer
        self.macros = { }
        self.path = []
        self.temp_path = []

        # Probe the lexer for selected tokens
        self.lexprobe()

        tm = time.localtime()
        self.define("__DATE__ \"%s\"" % time.strftime("%b %d %Y",tm))
        self.define("__TIME__ \"%s\"" % time.strftime("%H:%M:%S",tm))
        self.parser = None

    # -----------------------------------------------------------------------------
    # tokenize()
    #
    # Utility function. Given a string of text, tokenize into a list of tokens
    # -----------------------------------------------------------------------------
Example #8
Source File: cpp.py    From rfmt with Apache License 2.0 5 votes vote down vote up 
def t_CPP_WS(t):
    r'\s+'
    t.lexer.lineno += t.value.count("\n")
    return t
Example #9
Source File: cpp.py    From learn_python3_spider with MIT License 5 votes vote down vote up 
def t_error(t):
    t.type = t.value[0]
    t.value = t.value[0]
    t.lexer.skip(1)
    return t
Example #10
Source File: yacc.py    From SublimeKSP with GNU General Public License v3.0 5 votes vote down vote up 
def __init__(self,s,stack=None):
        self.slice = s
        self.stack = stack
        self.lexer = None
        self.parser= None
Example #11
Source File: cpp.py    From learn_python3_spider with MIT License 5 votes vote down vote up 
def t_CPP_COMMENT1(t):
    r'(/\*(.|\n)*?\*/)'
    ncr = t.value.count("\n")
    t.lexer.lineno += ncr
    # replace with one space or a number of '\n'
    t.type = 'CPP_WS'; t.value = '\n' * ncr if ncr else ' '
    return t

# Line comment
Example #12
Source File: cpp.py    From learn_python3_spider with MIT License 5 votes vote down vote up 
def t_CPP_WS(t):
    r'\s+'
    t.lexer.lineno += t.value.count("\n")
    return t
Example #13
Source File: cpp.py    From retdec-regression-tests-framework with MIT License 5 votes vote down vote up 
def group_lines(self,input):
        lex = self.lexer.clone()
        lines = [x.rstrip() for x in input.splitlines()]
        for i in xrange(len(lines)):
            j = i+1
            while lines[i].endswith('\\') and (j < len(lines)):
                lines[i] = lines[i][:-1]+lines[j]
                lines[j] = ""
                j += 1

        input = "\n".join(lines)
        lex.input(input)
        lex.lineno = 1

        current_line = []
        while True:
            tok = lex.token()
            if not tok:
                break
            current_line.append(tok)
            if tok.type in self.t_WS and '\n' in tok.value:
                yield current_line
                current_line = []

        if current_line:
            yield current_line

    # ----------------------------------------------------------------------
    # tokenstrip()
    # 
    # Remove leading/trailing whitespace tokens from a token list
    # ----------------------------------------------------------------------
Example #14
Source File: cpp.py    From retdec-regression-tests-framework with MIT License 5 votes vote down vote up 
def error(self,file,line,msg):
        print("%s:%d %s" % (file,line,msg))

    # ----------------------------------------------------------------------
    # lexprobe()
    #
    # This method probes the preprocessor lexer object to discover
    # the token types of symbols that are important to the preprocessor.
    # If this works right, the preprocessor will simply "work"
    # with any suitable lexer regardless of how tokens have been named.
    # ----------------------------------------------------------------------
Example #15
Source File: cpp.py    From retdec-regression-tests-framework with MIT License 5 votes vote down vote up 
def tokenize(self,text):
        tokens = []
        self.lexer.input(text)
        while True:
            tok = self.lexer.token()
            if not tok: break
            tokens.append(tok)
        return tokens

    # ---------------------------------------------------------------------
    # error()
    #
    # Report a preprocessor error/warning of some kind
    # ----------------------------------------------------------------------
Example #16
Source File: cpp.py    From learn_python3_spider with MIT License 5 votes vote down vote up 
def t_CPP_STRING(t):
    r'\"([^\\\n]|(\\(.|\n)))*?\"'
    t.lexer.lineno += t.value.count("\n")
    return t

# Character constant 'c' or L'c'
Example #17
Source File: cpp.py    From rfmt with Apache License 2.0 5 votes vote down vote up 
def t_CPP_CHAR(t):
    r'(L)?\'([^\\\n]|(\\(.|\n)))*?\''
    t.lexer.lineno += t.value.count("\n")
    return t

# Comment
Example #18
Source File: cpp.py    From Safejumper-for-Desktop with GNU General Public License v2.0 5 votes vote down vote up 
def t_error(t):
    t.type = t.value[0]
    t.value = t.value[0]
    t.lexer.skip(1)
    return t
Example #19
Source File: cpp.py    From rfmt with Apache License 2.0 5 votes vote down vote up 
def t_CPP_STRING(t):
    r'\"([^\\\n]|(\\(.|\n)))*?\"'
    t.lexer.lineno += t.value.count("\n")
    return t

# Character constant 'c' or L'c'
Example #20
Source File: cpp.py    From SwiftKitten with MIT License 5 votes vote down vote up 
def error(self,file,line,msg):
        print("%s:%d %s" % (file,line,msg))

    # ----------------------------------------------------------------------
    # lexprobe()
    #
    # This method probes the preprocessor lexer object to discover
    # the token types of symbols that are important to the preprocessor.
    # If this works right, the preprocessor will simply "work"
    # with any suitable lexer regardless of how tokens have been named.
    # ----------------------------------------------------------------------
Example #21
Source File: cpp.py    From SwiftKitten with MIT License 5 votes vote down vote up 
def tokenize(self,text):
        tokens = []
        self.lexer.input(text)
        while True:
            tok = self.lexer.token()
            if not tok: break
            tokens.append(tok)
        return tokens

    # ---------------------------------------------------------------------
    # error()
    #
    # Report a preprocessor error/warning of some kind
    # ----------------------------------------------------------------------
Example #22
Source File: cpp.py    From learn_python3_spider with MIT License 5 votes vote down vote up 
def tokenize(self,text):
        tokens = []
        self.lexer.input(text)
        while True:
            tok = self.lexer.token()
            if not tok: break
            tokens.append(tok)
        return tokens

    # ---------------------------------------------------------------------
    # error()
    #
    # Report a preprocessor error/warning of some kind
    # ----------------------------------------------------------------------
Example #23
Source File: cpp.py    From Safejumper-for-Desktop with GNU General Public License v2.0 5 votes vote down vote up 
def tokenize(self,text):
        tokens = []
        self.lexer.input(text)
        while True:
            tok = self.lexer.token()
            if not tok: break
            tokens.append(tok)
        return tokens

    # ---------------------------------------------------------------------
    # error()
    #
    # Report a preprocessor error/warning of some kind
    # ----------------------------------------------------------------------
Example #24
Source File: cpp.py    From SwiftKitten with MIT License 5 votes vote down vote up 
def t_error(t):
    t.type = t.value[0]
    t.value = t.value[0]
    t.lexer.skip(1)
    return t
Example #25
Source File: cpp.py    From SwiftKitten with MIT License 5 votes vote down vote up 
def t_CPP_CHAR(t):
    r'(L)?\'([^\\\n]|(\\(.|\n)))*?\''
    t.lexer.lineno += t.value.count("\n")
    return t

# Comment
Example #26
Source File: cpp.py    From SwiftKitten with MIT License 5 votes vote down vote up 
def t_CPP_STRING(t):
    r'\"([^\\\n]|(\\(.|\n)))*?\"'
    t.lexer.lineno += t.value.count("\n")
    return t

# Character constant 'c' or L'c'
Example #27
Source File: cpp.py    From Safejumper-for-Desktop with GNU General Public License v2.0 5 votes vote down vote up 
def error(self,file,line,msg):
        print("%s:%d %s" % (file,line,msg))

    # ----------------------------------------------------------------------
    # lexprobe()
    #
    # This method probes the preprocessor lexer object to discover
    # the token types of symbols that are important to the preprocessor.
    # If this works right, the preprocessor will simply "work"
    # with any suitable lexer regardless of how tokens have been named.
    # ----------------------------------------------------------------------
Example #28
Source File: cpp.py    From SwiftKitten with MIT License 5 votes vote down vote up 
def t_CPP_WS(t):
    r'\s+'
    t.lexer.lineno += t.value.count("\n")
    return t
Example #29
Source File: cpp.py    From Safejumper-for-Desktop with GNU General Public License v2.0 5 votes vote down vote up 
def group_lines(self,input):
        lex = self.lexer.clone()
        lines = [x.rstrip() for x in input.splitlines()]
        for i in xrange(len(lines)):
            j = i+1
            while lines[i].endswith('\\') and (j < len(lines)):
                lines[i] = lines[i][:-1]+lines[j]
                lines[j] = ""
                j += 1

        input = "\n".join(lines)
        lex.input(input)
        lex.lineno = 1

        current_line = []
        while True:
            tok = lex.token()
            if not tok:
                break
            current_line.append(tok)
            if tok.type in self.t_WS and '\n' in tok.value:
                yield current_line
                current_line = []

        if current_line:
            yield current_line

    # ----------------------------------------------------------------------
    # tokenstrip()
    # 
    # Remove leading/trailing whitespace tokens from a token list
    # ----------------------------------------------------------------------
Example #30
Source File: yacc.py    From SwiftKitten with MIT License 5 votes vote down vote up 
def __init__(self,s,stack=None):
        self.slice = s
        self.stack = stack
        self.lexer = None
        self.parser= None