1
  2
  3
  4
  5
  6
  7
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
"""
    pygments.lexers.ecl
    ~~~~~~~~~~~~~~~~~~~

    Lexers for the ECL language.

    :copyright: Copyright 2006-2022 by the Pygments team, see AUTHORS.
    :license: BSD, see LICENSE for details.
"""

import re

from pygments.lexer import RegexLexer, include, bygroups, words
from pygments.token import Comment, Operator, Keyword, Name, String, \
    Number, Punctuation, Whitespace

__all__ = ['ECLLexer']


class ECLLexer(RegexLexer):
    """
    Lexer for the declarative big-data ECL language.

    .. versionadded:: 1.5
    """

    name = 'ECL'
    url = 'https://hpccsystems.com/training/documentation/ecl-language-reference/html'
    aliases = ['ecl']
    filenames = ['*.ecl']
    mimetypes = ['application/x-ecl']

    flags = re.IGNORECASE | re.MULTILINE

    tokens = {
        'root': [
            include('whitespace'),
            include('statements'),
        ],
        'whitespace': [
            (r'\s+', Whitespace),
            (r'\/\/.*', Comment.Single),
            (r'/(\\\n)?\*(.|\n)*?\*(\\\n)?/', Comment.Multiline),
        ],
        'statements': [
            include('types'),
            include('keywords'),
            include('functions'),
            include('hash'),
            (r'"', String, 'string'),
            (r'\'', String, 'string'),
            (r'(\d+\.\d*|\.\d+|\d+)e[+-]?\d+[lu]*', Number.Float),
            (r'(\d+\.\d*|\.\d+|\d+f)f?', Number.Float),
            (r'0x[0-9a-f]+[lu]*', Number.Hex),
            (r'0[0-7]+[lu]*', Number.Oct),
            (r'\d+[lu]*', Number.Integer),
            (r'[~!%^&*+=|?:<>/-]+', Operator),
            (r'[{}()\[\],.;]', Punctuation),
            (r'[a-z_]\w*', Name),
        ],
        'hash': [
            (r'^#.*$', Comment.Preproc),
        ],
        'types': [
            (r'(RECORD|END)\D', Keyword.Declaration),
            (r'((?:ASCII|BIG_ENDIAN|BOOLEAN|DATA|DECIMAL|EBCDIC|INTEGER|PATTERN|'
             r'QSTRING|REAL|RECORD|RULE|SET OF|STRING|TOKEN|UDECIMAL|UNICODE|'
             r'UNSIGNED|VARSTRING|VARUNICODE)\d*)(\s+)',
             bygroups(Keyword.Type, Whitespace)),
        ],
        'keywords': [
            (words((
                'APPLY', 'ASSERT', 'BUILD', 'BUILDINDEX', 'EVALUATE', 'FAIL',
                'KEYDIFF', 'KEYPATCH', 'LOADXML', 'NOTHOR', 'NOTIFY', 'OUTPUT',
                'PARALLEL', 'SEQUENTIAL', 'SOAPCALL', 'CHECKPOINT', 'DEPRECATED',
                'FAILCODE', 'FAILMESSAGE', 'FAILURE', 'GLOBAL', 'INDEPENDENT',
                'ONWARNING', 'PERSIST', 'PRIORITY', 'RECOVERY', 'STORED', 'SUCCESS',
                'WAIT', 'WHEN'), suffix=r'\b'),
             Keyword.Reserved),
            # These are classed differently, check later
            (words((
                'ALL', 'AND', 'ANY', 'AS', 'ATMOST', 'BEFORE', 'BEGINC++', 'BEST',
                'BETWEEN', 'CASE', 'CONST', 'COUNTER', 'CSV', 'DESCEND', 'ENCRYPT',
                'ENDC++', 'ENDMACRO', 'EXCEPT', 'EXCLUSIVE', 'EXPIRE', 'EXPORT',
                'EXTEND', 'FALSE', 'FEW', 'FIRST', 'FLAT', 'FULL', 'FUNCTION',
                'GROUP', 'HEADER', 'HEADING', 'HOLE', 'IFBLOCK', 'IMPORT', 'IN',
                'JOINED', 'KEEP', 'KEYED', 'LAST', 'LEFT', 'LIMIT', 'LOAD', 'LOCAL',
                'LOCALE', 'LOOKUP', 'MACRO', 'MANY', 'MAXCOUNT', 'MAXLENGTH',
                'MIN SKEW', 'MODULE', 'INTERFACE', 'NAMED', 'NOCASE', 'NOROOT',
                'NOSCAN', 'NOSORT', 'NOT', 'OF', 'ONLY', 'OPT', 'OR', 'OUTER',
                'OVERWRITE', 'PACKED', 'PARTITION', 'PENALTY', 'PHYSICALLENGTH',
                'PIPE', 'QUOTE', 'RELATIONSHIP', 'REPEAT', 'RETURN', 'RIGHT',
                'SCAN', 'SELF', 'SEPARATOR', 'SERVICE', 'SHARED', 'SKEW', 'SKIP',
                'SQL', 'STORE', 'TERMINATOR', 'THOR', 'THRESHOLD', 'TOKEN',
                'TRANSFORM', 'TRIM', 'TRUE', 'TYPE', 'UNICODEORDER', 'UNSORTED',
                'VALIDATE', 'VIRTUAL', 'WHOLE', 'WILD', 'WITHIN', 'XML', 'XPATH',
                '__COMPRESSED__'), suffix=r'\b'),
             Keyword.Reserved),
        ],
        'functions': [
            (words((
                'ABS', 'ACOS', 'ALLNODES', 'ASCII', 'ASIN', 'ASSTRING', 'ATAN',
                'ATAN2', 'AVE', 'CASE', 'CHOOSE', 'CHOOSEN', 'CHOOSESETS',
                'CLUSTERSIZE', 'COMBINE', 'CORRELATION', 'COS', 'COSH', 'COUNT',
                'COVARIANCE', 'CRON', 'DATASET', 'DEDUP', 'DEFINE', 'DENORMALIZE',
                'DISTRIBUTE', 'DISTRIBUTED', 'DISTRIBUTION', 'EBCDIC', 'ENTH',
                'ERROR', 'EVALUATE', 'EVENT', 'EVENTEXTRA', 'EVENTNAME', 'EXISTS',
                'EXP', 'FAILCODE', 'FAILMESSAGE', 'FETCH', 'FROMUNICODE',
                'GETISVALID', 'GLOBAL', 'GRAPH', 'GROUP', 'HASH', 'HASH32',
                'HASH64', 'HASHCRC', 'HASHMD5', 'HAVING', 'IF', 'INDEX',
                'INTFORMAT', 'ISVALID', 'ITERATE', 'JOIN', 'KEYUNICODE', 'LENGTH',
                'LIBRARY', 'LIMIT', 'LN', 'LOCAL', 'LOG', 'LOOP', 'MAP', 'MATCHED',
                'MATCHLENGTH', 'MATCHPOSITION', 'MATCHTEXT', 'MATCHUNICODE', 'MAX',
                'MERGE', 'MERGEJOIN', 'MIN', 'NOLOCAL', 'NONEMPTY', 'NORMALIZE',
                'PARSE', 'PIPE', 'POWER', 'PRELOAD', 'PROCESS', 'PROJECT', 'PULL',
                'RANDOM', 'RANGE', 'RANK', 'RANKED', 'REALFORMAT', 'RECORDOF',
                'REGEXFIND', 'REGEXREPLACE', 'REGROUP', 'REJECTED', 'ROLLUP',
                'ROUND', 'ROUNDUP', 'ROW', 'ROWDIFF', 'SAMPLE', 'SET', 'SIN',
                'SINH', 'SIZEOF', 'SOAPCALL', 'SORT', 'SORTED', 'SQRT', 'STEPPED',
                'STORED', 'SUM', 'TABLE', 'TAN', 'TANH', 'THISNODE', 'TOPN',
                'TOUNICODE', 'TRANSFER', 'TRIM', 'TRUNCATE', 'TYPEOF', 'UNGROUP',
                'UNICODEORDER', 'VARIANCE', 'WHICH', 'WORKUNIT', 'XMLDECODE',
                'XMLENCODE', 'XMLTEXT', 'XMLUNICODE'), suffix=r'\b'),
             Name.Function),
        ],
        'string': [
            (r'"', String, '#pop'),
            (r'\'', String, '#pop'),
            (r'[^"\']+', String),
        ],
    }

    def analyse_text(text):
        """This is very difficult to guess relative to other business languages.
        -> in conjunction with BEGIN/END seems relatively rare though."""
        result = 0

        if '->' in text:
            result += 0.01
        if 'BEGIN' in text:
            result += 0.01
        if 'END' in text:
            result += 0.01

        return result