Mercurial Repositories > eric / file comparison
comparison: ThirdParty/Pygments/pygments/lexers/_postgres_builtins.py
ThirdParty/Pygments/pygments/lexers/_postgres_builtins.py
- changeset 1705
- b0fbc9300f2b
- child 2426
- da76c71624de
equal
deleted
inserted
replaced
| 1704:02ae6c55b35b | 1705:b0fbc9300f2b |
|---|---|
| 1 """ | |
| 2 pygments.lexers._postgres_builtins | |
| 3 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ | |
| 4 | |
| 5 Self-updating data files for PostgreSQL lexer. | |
| 6 | |
| 7 :copyright: Copyright 2006-2012 by the Pygments team, see AUTHORS. | |
| 8 :license: BSD, see LICENSE for details. | |
| 9 """ | |
| 10 | |
| 11 import re | |
| 12 import urllib.request, urllib.parse, urllib.error | |
| 13 | |
| 14 # One man's constant is another man's variable. | |
| 15 SOURCE_URL = 'https://github.com/postgres/postgres/raw/master' | |
| 16 KEYWORDS_URL = SOURCE_URL + '/doc/src/sgml/keywords.sgml' | |
| 17 DATATYPES_URL = SOURCE_URL + '/doc/src/sgml/datatype.sgml' | |
| 18 | |
| 19 def update_myself(): | |
| 20 data_file = list(fetch(DATATYPES_URL)) | |
| 21 datatypes = parse_datatypes(data_file) | |
| 22 pseudos = parse_pseudos(data_file) | |
| 23 | |
| 24 keywords = parse_keywords(fetch(KEYWORDS_URL)) | |
| 25 update_consts(__file__, 'DATATYPES', datatypes) | |
| 26 update_consts(__file__, 'PSEUDO_TYPES', pseudos) | |
| 27 update_consts(__file__, 'KEYWORDS', keywords) | |
| 28 | |
| 29 def parse_keywords(f): | |
| 30 kw = [] | |
| 31 for m in re.finditer( | |
| 32 r'\s*<entry><token>([^<]+)</token></entry>\s*' | |
| 33 r'<entry>([^<]+)</entry>', f.read()): | |
| 34 kw.append(m.group(1)) | |
| 35 | |
| 36 if not kw: | |
| 37 raise ValueError('no keyword found') | |
| 38 | |
| 39 kw.sort() | |
| 40 return kw | |
| 41 | |
| 42 def parse_datatypes(f): | |
| 43 dt = set() | |
| 44 re_entry = re.compile('\s*<entry><type>([^<]+)</type></entry>') | |
| 45 for line in f: | |
| 46 if '<sect1' in line: | |
| 47 break | |
| 48 if '<entry><type>' not in line: | |
| 49 continue | |
| 50 | |
| 51 # Parse a string such as | |
| 52 # time [ (<replaceable>p</replaceable>) ] [ without time zone ] | |
| 53 # into types "time" and "without time zone" | |
| 54 | |
| 55 # remove all the tags | |
| 56 line = re.sub("<replaceable>[^<]+</replaceable>", "", line) | |
| 57 line = re.sub("<[^>]+>", "", line) | |
| 58 | |
| 59 # Drop the parts containing braces | |
| 60 for tmp in [ t for tmp in line.split('[') for t in tmp.split(']') if "(" not in t ]: | |
| 61 for t in tmp.split(','): | |
| 62 t = t.strip() | |
| 63 if not t: continue | |
| 64 dt.add(" ".join(t.split())) | |
| 65 | |
| 66 dt = list(dt) | |
| 67 dt.sort() | |
| 68 return dt | |
| 69 | |
| 70 def parse_pseudos(f): | |
| 71 dt = [] | |
| 72 re_start = re.compile(r'\s*<table id="datatype-pseudotypes-table">') | |
| 73 re_entry = re.compile(r'\s*<entry><type>([^<]+)</></entry>') | |
| 74 re_end = re.compile(r'\s*</table>') | |
| 75 | |
| 76 f = iter(f) | |
| 77 for line in f: | |
| 78 if re_start.match(line) is not None: | |
| 79 break | |
| 80 else: | |
| 81 raise ValueError('pseudo datatypes table not found') | |
| 82 | |
| 83 for line in f: | |
| 84 m = re_entry.match(line) | |
| 85 if m is not None: | |
| 86 dt.append(m.group(1)) | |
| 87 | |
| 88 if re_end.match(line) is not None: | |
| 89 break | |
| 90 else: | |
| 91 raise ValueError('end of pseudo datatypes table not found') | |
| 92 | |
| 93 if not dt: | |
| 94 raise ValueError('pseudo datatypes not found') | |
| 95 | |
| 96 return dt | |
| 97 | |
| 98 def fetch(url): | |
| 99 return urllib.request.urlopen(url) | |
| 100 | |
| 101 def update_consts(filename, constname, content): | |
| 102 f = open(filename) | |
| 103 lines = f.readlines() | |
| 104 f.close() | |
| 105 | |
| 106 # Line to start/end inserting | |
| 107 re_start = re.compile(r'^%s\s*=\s*\[\s*$' % constname) | |
| 108 re_end = re.compile(r'^\s*\]\s*$') | |
| 109 start = [ n for n, l in enumerate(lines) if re_start.match(l) ] | |
| 110 if not start: | |
| 111 raise ValueError("couldn't find line containing '%s = ['" % constname) | |
| 112 if len(start) > 1: | |
| 113 raise ValueError("too many lines containing '%s = ['" % constname) | |
| 114 start = start[0] + 1 | |
| 115 | |
| 116 end = [ n for n, l in enumerate(lines) if n >= start and re_end.match(l) ] | |
| 117 if not end: | |
| 118 raise ValueError("couldn't find line containing ']' after %s " % constname) | |
| 119 end = end[0] | |
| 120 | |
| 121 # Pack the new content in lines not too long | |
| 122 content = [repr(item) for item in content ] | |
| 123 new_lines = [[]] | |
| 124 for item in content: | |
| 125 if sum(map(len, new_lines[-1])) + 2 * len(new_lines[-1]) + len(item) + 4 > 75: | |
| 126 new_lines.append([]) | |
| 127 new_lines[-1].append(item) | |
| 128 | |
| 129 lines[start:end] = [ " %s,\n" % ", ".join(items) for items in new_lines ] | |
| 130 | |
| 131 f = open(filename, 'w') | |
| 132 f.write(''.join(lines)) | |
| 133 f.close() | |
| 134 | |
| 135 | |
| 136 # Autogenerated: please edit them if you like wasting your time. | |
| 137 | |
| 138 KEYWORDS = [ | |
| 139 'ABORT', 'ABSOLUTE', 'ACCESS', 'ACTION', 'ADD', 'ADMIN', 'AFTER', | |
| 140 'AGGREGATE', 'ALL', 'ALSO', 'ALTER', 'ALWAYS', 'ANALYSE', 'ANALYZE', | |
| 141 'AND', 'ANY', 'ARRAY', 'AS', 'ASC', 'ASSERTION', 'ASSIGNMENT', | |
| 142 'ASYMMETRIC', 'AT', 'ATTRIBUTE', 'AUTHORIZATION', 'BACKWARD', 'BEFORE', | |
| 143 'BEGIN', 'BETWEEN', 'BIGINT', 'BINARY', 'BIT', 'BOOLEAN', 'BOTH', 'BY', | |
| 144 'CACHE', 'CALLED', 'CASCADE', 'CASCADED', 'CASE', 'CAST', 'CATALOG', | |
| 145 'CHAIN', 'CHAR', 'CHARACTER', 'CHARACTERISTICS', 'CHECK', 'CHECKPOINT', | |
| 146 'CLASS', 'CLOSE', 'CLUSTER', 'COALESCE', 'COLLATE', 'COLLATION', | |
| 147 'COLUMN', 'COMMENT', 'COMMENTS', 'COMMIT', 'COMMITTED', 'CONCURRENTLY', | |
| 148 'CONFIGURATION', 'CONNECTION', 'CONSTRAINT', 'CONSTRAINTS', 'CONTENT', | |
| 149 'CONTINUE', 'CONVERSION', 'COPY', 'COST', 'CREATE', 'CROSS', 'CSV', | |
| 150 'CURRENT', 'CURRENT_CATALOG', 'CURRENT_DATE', 'CURRENT_ROLE', | |
| 151 'CURRENT_SCHEMA', 'CURRENT_TIME', 'CURRENT_TIMESTAMP', 'CURRENT_USER', | |
| 152 'CURSOR', 'CYCLE', 'DATA', 'DATABASE', 'DAY', 'DEALLOCATE', 'DEC', | |
| 153 'DECIMAL', 'DECLARE', 'DEFAULT', 'DEFAULTS', 'DEFERRABLE', 'DEFERRED', | |
| 154 'DEFINER', 'DELETE', 'DELIMITER', 'DELIMITERS', 'DESC', 'DICTIONARY', | |
| 155 'DISABLE', 'DISCARD', 'DISTINCT', 'DO', 'DOCUMENT', 'DOMAIN', 'DOUBLE', | |
| 156 'DROP', 'EACH', 'ELSE', 'ENABLE', 'ENCODING', 'ENCRYPTED', 'END', | |
| 157 'ENUM', 'ESCAPE', 'EXCEPT', 'EXCLUDE', 'EXCLUDING', 'EXCLUSIVE', | |
| 158 'EXECUTE', 'EXISTS', 'EXPLAIN', 'EXTENSION', 'EXTERNAL', 'EXTRACT', | |
| 159 'FALSE', 'FAMILY', 'FETCH', 'FIRST', 'FLOAT', 'FOLLOWING', 'FOR', | |
| 160 'FORCE', 'FOREIGN', 'FORWARD', 'FREEZE', 'FROM', 'FULL', 'FUNCTION', | |
| 161 'FUNCTIONS', 'GLOBAL', 'GRANT', 'GRANTED', 'GREATEST', 'GROUP', | |
| 162 'HANDLER', 'HAVING', 'HEADER', 'HOLD', 'HOUR', 'IDENTITY', 'IF', | |
| 163 'ILIKE', 'IMMEDIATE', 'IMMUTABLE', 'IMPLICIT', 'IN', 'INCLUDING', | |
| 164 'INCREMENT', 'INDEX', 'INDEXES', 'INHERIT', 'INHERITS', 'INITIALLY', | |
| 165 'INLINE', 'INNER', 'INOUT', 'INPUT', 'INSENSITIVE', 'INSERT', 'INSTEAD', | |
| 166 'INT', 'INTEGER', 'INTERSECT', 'INTERVAL', 'INTO', 'INVOKER', 'IS', | |
| 167 'ISNULL', 'ISOLATION', 'JOIN', 'KEY', 'LABEL', 'LANGUAGE', 'LARGE', | |
| 168 'LAST', 'LC_COLLATE', 'LC_CTYPE', 'LEADING', 'LEAST', 'LEFT', 'LEVEL', | |
| 169 'LIKE', 'LIMIT', 'LISTEN', 'LOAD', 'LOCAL', 'LOCALTIME', | |
| 170 'LOCALTIMESTAMP', 'LOCATION', 'LOCK', 'MAPPING', 'MATCH', 'MAXVALUE', | |
| 171 'MINUTE', 'MINVALUE', 'MODE', 'MONTH', 'MOVE', 'NAME', 'NAMES', | |
| 172 'NATIONAL', 'NATURAL', 'NCHAR', 'NEXT', 'NO', 'NONE', 'NOT', 'NOTHING', | |
| 173 'NOTIFY', 'NOTNULL', 'NOWAIT', 'NULL', 'NULLIF', 'NULLS', 'NUMERIC', | |
| 174 'OBJECT', 'OF', 'OFF', 'OFFSET', 'OIDS', 'ON', 'ONLY', 'OPERATOR', | |
| 175 'OPTION', 'OPTIONS', 'OR', 'ORDER', 'OUT', 'OUTER', 'OVER', 'OVERLAPS', | |
| 176 'OVERLAY', 'OWNED', 'OWNER', 'PARSER', 'PARTIAL', 'PARTITION', | |
| 177 'PASSING', 'PASSWORD', 'PLACING', 'PLANS', 'POSITION', 'PRECEDING', | |
| 178 'PRECISION', 'PREPARE', 'PREPARED', 'PRESERVE', 'PRIMARY', 'PRIOR', | |
| 179 'PRIVILEGES', 'PROCEDURAL', 'PROCEDURE', 'QUOTE', 'RANGE', 'READ', | |
| 180 'REAL', 'REASSIGN', 'RECHECK', 'RECURSIVE', 'REF', 'REFERENCES', | |
| 181 'REINDEX', 'RELATIVE', 'RELEASE', 'RENAME', 'REPEATABLE', 'REPLACE', | |
| 182 'REPLICA', 'RESET', 'RESTART', 'RESTRICT', 'RETURNING', 'RETURNS', | |
| 183 'REVOKE', 'RIGHT', 'ROLE', 'ROLLBACK', 'ROW', 'ROWS', 'RULE', | |
| 184 'SAVEPOINT', 'SCHEMA', 'SCROLL', 'SEARCH', 'SECOND', 'SECURITY', | |
| 185 'SELECT', 'SEQUENCE', 'SEQUENCES', 'SERIALIZABLE', 'SERVER', 'SESSION', | |
| 186 'SESSION_USER', 'SET', 'SETOF', 'SHARE', 'SHOW', 'SIMILAR', 'SIMPLE', | |
| 187 'SMALLINT', 'SOME', 'STABLE', 'STANDALONE', 'START', 'STATEMENT', | |
| 188 'STATISTICS', 'STDIN', 'STDOUT', 'STORAGE', 'STRICT', 'STRIP', | |
| 189 'SUBSTRING', 'SYMMETRIC', 'SYSID', 'SYSTEM', 'TABLE', 'TABLES', | |
| 190 'TABLESPACE', 'TEMP', 'TEMPLATE', 'TEMPORARY', 'TEXT', 'THEN', 'TIME', | |
| 191 'TIMESTAMP', 'TO', 'TRAILING', 'TRANSACTION', 'TREAT', 'TRIGGER', | |
| 192 'TRIM', 'TRUE', 'TRUNCATE', 'TRUSTED', 'TYPE', 'UNBOUNDED', | |
| 193 'UNCOMMITTED', 'UNENCRYPTED', 'UNION', 'UNIQUE', 'UNKNOWN', 'UNLISTEN', | |
| 194 'UNLOGGED', 'UNTIL', 'UPDATE', 'USER', 'USING', 'VACUUM', 'VALID', | |
| 195 'VALIDATE', 'VALIDATOR', 'VALUE', 'VALUES', 'VARCHAR', 'VARIADIC', | |
| 196 'VARYING', 'VERBOSE', 'VERSION', 'VIEW', 'VOLATILE', 'WHEN', 'WHERE', | |
| 197 'WHITESPACE', 'WINDOW', 'WITH', 'WITHOUT', 'WORK', 'WRAPPER', 'WRITE', | |
| 198 'XML', 'XMLATTRIBUTES', 'XMLCONCAT', 'XMLELEMENT', 'XMLEXISTS', | |
| 199 'XMLFOREST', 'XMLPARSE', 'XMLPI', 'XMLROOT', 'XMLSERIALIZE', 'YEAR', | |
| 200 'YES', 'ZONE', | |
| 201 ] | |
| 202 | |
| 203 DATATYPES = [ | |
| 204 'bigint', 'bigserial', 'bit', 'bit varying', 'bool', 'boolean', 'box', | |
| 205 'bytea', 'char', 'character', 'character varying', 'cidr', 'circle', | |
| 206 'date', 'decimal', 'double precision', 'float4', 'float8', 'inet', | |
| 207 'int', 'int2', 'int4', 'int8', 'integer', 'interval', 'line', 'lseg', | |
| 208 'macaddr', 'money', 'numeric', 'path', 'point', 'polygon', 'real', | |
| 209 'serial', 'serial4', 'serial8', 'smallint', 'text', 'time', 'timestamp', | |
| 210 'timestamptz', 'timetz', 'tsquery', 'tsvector', 'txid_snapshot', 'uuid', | |
| 211 'varbit', 'varchar', 'with time zone', 'without time zone', 'xml', | |
| 212 ] | |
| 213 | |
| 214 PSEUDO_TYPES = [ | |
| 215 'any', 'anyarray', 'anyelement', 'anyenum', 'anynonarray', 'cstring', | |
| 216 'internal', 'language_handler', 'fdw_handler', 'record', 'trigger', | |
| 217 'void', 'opaque', | |
| 218 ] | |
| 219 | |
| 220 # Remove 'trigger' from types | |
| 221 PSEUDO_TYPES = sorted(set(PSEUDO_TYPES) - set(map(str.lower, KEYWORDS))) | |
| 222 | |
| 223 PLPGSQL_KEYWORDS = [ | |
| 224 'ALIAS', 'CONSTANT', 'DIAGNOSTICS', 'ELSIF', 'EXCEPTION', 'EXIT', | |
| 225 'FOREACH', 'GET', 'LOOP', 'NOTICE', 'OPEN', 'PERFORM', 'QUERY', 'RAISE', | |
| 226 'RETURN', 'REVERSE', 'SQLSTATE', 'WHILE', | |
| 227 ] | |
| 228 | |
| 229 if __name__ == '__main__': | |
| 230 update_myself() | |
| 231 |
