pmacs3/mode/awk.py

import commands
import color, mode, tab
from lex import Grammar, PatternRule, RegionRule
from mode.python import StringGrammar2
from tab import StackTabber2

class RegexGrammar(Grammar):
    rules = [
        PatternRule(r'escaped', r'\\.'),
        PatternRule(r'data', r'[^\\/]+'),
    ]

class AwkGrammar(Grammar):
    rules = [
        PatternRule(r'comment', r'#.*\n$'),
        PatternRule(r'spaces', r' +'),
        RegionRule(r'awk_regex', r'/(?! )', RegexGrammar, r'/'),
        PatternRule(r'awk_global', r'(?:TEXTDOMAIN|SUBSEP|RLENGTH|RSTART|RT|RS|PROCINFO|ORS|OFS|OFMT|NR|NF|LINT|IGNORECASE|FS|FNR|FILENAME|FIELDWIDTHS|ERRNO|ENVIRON|CONVFMT|BINMODE|ARGV|ARGIND|ARGC)(?![a-zA-Z0-9_])'),
        PatternRule(r'delimiter', r'(?:[\{\}()\[\]?:;,]|=(?!=)|\+=|-=|\*=|/=|\%=|\^=)'),
        PatternRule(r'keyword', r'(?:BEGIN|END|if|else|while|do|for|break|continue|delete|exit)(?![a-zA-Z0-9_])'),
        PatternRule(r'builtin', r'(?:close|getline|nextfile|next|printf|print|system|fflush|atan2|cos|exp|int|log|rand|sin|sqrt|srand|asorti|asort|gensub|gsub|index|length|match|split|sprintf|strtonum|substr|sub|tolower|toupper|mktime|strftime|systime|and|compl|lshift|or|xor|rshift|bindtextdomain|dcgettext|dcngettext|function|extension)(?![a-zA-Z0-9_])'),

        PatternRule(r'awk_field', r'\$\d*'),

        PatternRule(r'number', r'-?0x[0-9A-Fa-f]+'),
        PatternRule(r'number', r'-?0[0-7]*'),
        PatternRule(r'number', r'-?[0-9]+\.?[0-9]*'),
        PatternRule(r'number', r'-?\.[0-9]+'),

        PatternRule(r'unop', r'!(?![=~])|--|\+\+'),
        PatternRule(r'binop', r'(?:&&|\|\||<=|>=|!=|!~|==|\^|%|[-~/+*<>])'),
        RegionRule(r'string', r'"', StringGrammar2, r'"'),
        PatternRule(r'awk_function', r'[a-zA-Z_][a-zA-Z0-9_]*(?=\()'),
        PatternRule(r'awk_identifier', r'[a-zA-Z_][a-zA-Z0-9_]*'),
        
        PatternRule(r'continuation', r'\\\n$'),
        PatternRule(r'eol', r'\n'),
    ]

class AwkTabber(StackTabber2):
    open_tokens    = {'delimiter': {'{': '}', '(': ')', '[': ']'}}
    close_tokens   = {'delimiter': {'}': '{', ')': '(', ']': '['}}
    control_tokens = {
        'keyword': {'if': 1, 'else': 1, 'while': 1, 'do': 1, 'for': 1},
    }
    end_at_eof    = True
    end_at_tokens = {}
    def _is_base(self, y):
        if y == 0:
            return True
        t = self._get_tokens(y)[0]
        if t.fqname() == 'awk_regex.start':
            return True
        elif t.name in ('awk_field', 'awk_global'):
            return True
        elif t.name == 'keyword' and t.string in ('BEGIN', 'END'):
            return True
        else:
            return False
    def _is_indent(self, t):
        return t.name == 'spaces'
    def _is_ignored(self, t):
        return t.name in ('spaces', 'eol', 'comment')


class Awk(mode.Fundamental):
    tabbercls   = AwkTabber
    modename   = 'awk'
    extensions = ['.awk']
    grammar    = AwkGrammar
    colors     = {
        'awk_global':      ('yellow', 'default', 'bold'),
        'awk_function':    ('magenta', 'default', 'bold'),
        'awk_field':       ('yellow', 'default', 'bold'),
        'awk_identifier':  ('yellow', 'default', 'bold'),
        'awk_regex.start': ('cyan', 'default', 'bold'),
        'awk_regex.null':  ('cyan', 'default', 'bold'),
        'awk_regex.data':  ('cyan', 'default', 'bold'),
        'awk_regex.end':   ('cyan', 'default', 'bold'),
    }

install = Awk.install