summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorThomas Aglassinger <roskakori@users.sourceforge.net>2016-03-21 08:29:44 +0100
committerThomas Aglassinger <roskakori@users.sourceforge.net>2016-03-21 08:29:44 +0100
commit1d5aed09f1f7fcfa27c73d03ffc1a61e686658da (patch)
treee58d5ca42db23b95a639b942d46423d2c76d934d
parenta4a3df4ac8c645d890df8fc264733045108a3f53 (diff)
downloadpygments-1d5aed09f1f7fcfa27c73d03ffc1a61e686658da.tar.gz
Added lexer for Transact-SQL as used by Microsoft SQL Server and Sybase.
-rw-r--r--AUTHORS2
-rw-r--r--pygments/lexers/_mapping.py1
-rw-r--r--pygments/lexers/_tsql_builtins.py1006
-rw-r--r--pygments/lexers/sql.py57
-rw-r--r--tests/examplefiles/test_transact-sql.txt68
-rw-r--r--tests/test_sql.py76
6 files changed, 1207 insertions, 3 deletions
diff --git a/AUTHORS b/AUTHORS
index 204b4efe..2fc9a97e 100644
--- a/AUTHORS
+++ b/AUTHORS
@@ -7,7 +7,7 @@ Other contributors, listed alphabetically, are:
* Sam Aaron -- Ioke lexer
* Ali Afshar -- image formatter
-* Thomas Aglassinger -- Easytrieve, JCL and Rexx lexers
+* Thomas Aglassinger -- Easytrieve, JCL, Rexx and Transact-SQL lexers
* Muthiah Annamalai -- Ezhil lexer
* Kumar Appaiah -- Debian control lexer
* Andreas Amann -- AppleScript lexer
diff --git a/pygments/lexers/_mapping.py b/pygments/lexers/_mapping.py
index dba6d69a..e34adac2 100644
--- a/pygments/lexers/_mapping.py
+++ b/pygments/lexers/_mapping.py
@@ -393,6 +393,7 @@ LEXERS = {
'TextLexer': ('pygments.lexers.special', 'Text only', ('text',), ('*.txt',), ('text/plain',)),
'ThriftLexer': ('pygments.lexers.dsls', 'Thrift', ('thrift',), ('*.thrift',), ('application/x-thrift',)),
'TodotxtLexer': ('pygments.lexers.textfmts', 'Todotxt', ('todotxt',), ('todo.txt', '*.todotxt'), ('text/x-todo',)),
+ 'TransactSqlLexer': ('pygments.lexers.sql', 'Transact-SQL', ('tsql', 't-sql'), ('*.sql',), ('text/x-tsql',)),
'TreetopLexer': ('pygments.lexers.parsers', 'Treetop', ('treetop',), ('*.treetop', '*.tt'), ()),
'TurtleLexer': ('pygments.lexers.rdf', 'Turtle', ('turtle',), ('*.ttl',), ('text/turtle', 'application/x-turtle')),
'TwigHtmlLexer': ('pygments.lexers.templates', 'HTML+Twig', ('html+twig',), ('*.twig',), ('text/html+twig',)),
diff --git a/pygments/lexers/_tsql_builtins.py b/pygments/lexers/_tsql_builtins.py
new file mode 100644
index 00000000..7e2f4a3e
--- /dev/null
+++ b/pygments/lexers/_tsql_builtins.py
@@ -0,0 +1,1006 @@
+# -*- coding: utf-8 -*-
+"""
+ pygments.lexers._tsql_builtins
+ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+ This file contains the names of functions for Transact-SQL used by
+ ``pygments.lexers.sql.TransactSqlLexer. These lists describe SQL Server
+ 2012 and have been manually collected from:
+
+ * https://msdn.microsoft.com/en-us/library/ms189822.aspx
+ * https://msdn.microsoft.com/en-us/library/ms174318.aspx
+ * https://msdn.microsoft.com/en-us/library/ms187752.aspx
+
+ :copyright: Copyright 2006-2016 by the Pygments team, see AUTHORS.
+ :license: BSD, see LICENSE for details.
+"""
+
+OPERATORS = (
+ '!<',
+ '!=',
+ '!>',
+ '<',
+ '<=',
+ '<>',
+ '=',
+ '>',
+ '>=',
+ '+',
+ '+='
+ '-',
+ '-=',
+ '*',
+ '*=',
+ '/',
+ '/=',
+ '%',
+ '%=',
+ '&',
+ '&=',
+ '|',
+ '|=',
+ '^',
+ '^=',
+ '~',
+ '::',
+)
+
+OPERATOR_WORDS = (
+ 'all',
+ 'and',
+ 'any',
+ 'between',
+ 'except',
+ 'exists',
+ 'in',
+ 'intersect',
+ 'like',
+ 'not',
+ 'or',
+ 'some',
+ 'union',
+)
+
+_KEYWORDS_SERVER = (
+ 'add',
+ 'all',
+ 'alter',
+ 'and',
+ 'any',
+ 'as',
+ 'asc',
+ 'authorization',
+ 'backup',
+ 'begin',
+ 'between',
+ 'break',
+ 'browse',
+ 'bulk',
+ 'by',
+ 'cascade',
+ 'case',
+ 'catch',
+ 'check',
+ 'checkpoint',
+ 'close',
+ 'clustered',
+ 'coalesce',
+ 'collate',
+ 'column',
+ 'commit',
+ 'compute',
+ 'constraint',
+ 'contains',
+ 'containstable',
+ 'continue',
+ 'convert',
+ 'create',
+ 'cross',
+ 'current',
+ 'current_date',
+ 'current_time',
+ 'current_timestamp',
+ 'current_user',
+ 'cursor',
+ 'database',
+ 'dbcc',
+ 'deallocate',
+ 'declare',
+ 'default',
+ 'delete',
+ 'deny',
+ 'desc',
+ 'disk',
+ 'distinct',
+ 'distributed',
+ 'double',
+ 'drop',
+ 'dump',
+ 'else',
+ 'end',
+ 'errlvl',
+ 'escape',
+ 'except',
+ 'exec',
+ 'execute',
+ 'exists',
+ 'exit',
+ 'external',
+ 'fetch',
+ 'file',
+ 'fillfactor',
+ 'for',
+ 'foreign',
+ 'freetext',
+ 'freetexttable',
+ 'from',
+ 'full',
+ 'function',
+ 'goto',
+ 'grant',
+ 'group',
+ 'having',
+ 'holdlock',
+ 'identity',
+ 'identity_insert',
+ 'identitycol',
+ 'if',
+ 'in',
+ 'index',
+ 'inner',
+ 'insert',
+ 'intersect',
+ 'into',
+ 'is',
+ 'join',
+ 'key',
+ 'kill',
+ 'left',
+ 'like',
+ 'lineno',
+ 'load',
+ 'merge',
+ 'national',
+ 'nocheck',
+ 'nonclustered',
+ 'not',
+ 'null',
+ 'nullif',
+ 'of',
+ 'off',
+ 'offsets',
+ 'on',
+ 'open',
+ 'opendatasource',
+ 'openquery',
+ 'openrowset',
+ 'openxml',
+ 'option',
+ 'or',
+ 'order',
+ 'outer',
+ 'over',
+ 'percent',
+ 'pivot',
+ 'plan',
+ 'precision',
+ 'primary',
+ 'print',
+ 'proc',
+ 'procedure',
+ 'public',
+ 'raiserror',
+ 'read',
+ 'readtext',
+ 'reconfigure',
+ 'references',
+ 'replication',
+ 'restore',
+ 'restrict',
+ 'return',
+ 'revert',
+ 'revoke',
+ 'right',
+ 'rollback',
+ 'rowcount',
+ 'rowguidcol',
+ 'rule',
+ 'save',
+ 'schema',
+ 'securityaudit',
+ 'select',
+ 'semantickeyphrasetable',
+ 'semanticsimilaritydetailstable',
+ 'semanticsimilaritytable',
+ 'session_user',
+ 'set',
+ 'setuser',
+ 'shutdown',
+ 'some',
+ 'statistics',
+ 'system_user',
+ 'table',
+ 'tablesample',
+ 'textsize',
+ 'then',
+ 'throw',
+ 'to',
+ 'top',
+ 'tran',
+ 'transaction',
+ 'trigger',
+ 'truncate',
+ 'try',
+ 'try_convert',
+ 'tsequal',
+ 'union',
+ 'unique',
+ 'unpivot',
+ 'update',
+ 'updatetext',
+ 'use',
+ 'user',
+ 'values',
+ 'varying',
+ 'view',
+ 'waitfor',
+ 'when',
+ 'where',
+ 'while',
+ 'with',
+ 'within',
+ 'writetext',
+)
+
+_KEYWORDS_FUTURE = (
+ 'absolute',
+ 'action',
+ 'admin',
+ 'after',
+ 'aggregate',
+ 'alias',
+ 'allocate',
+ 'are',
+ 'array',
+ 'asensitive',
+ 'assertion',
+ 'asymmetric',
+ 'at',
+ 'atomic',
+ 'before',
+ 'binary',
+ 'bit',
+ 'blob',
+ 'boolean',
+ 'both',
+ 'breadth',
+ 'call',
+ 'called',
+ 'cardinality',
+ 'cascaded',
+ 'cast',
+ 'catalog',
+ 'char',
+ 'character',
+ 'class',
+ 'clob',
+ 'collation',
+ 'collect',
+ 'completion',
+ 'condition',
+ 'connect',
+ 'connection',
+ 'constraints',
+ 'constructor',
+ 'corr',
+ 'corresponding',
+ 'covar_pop',
+ 'covar_samp',
+ 'cube',
+ 'cume_dist',
+ 'current_catalog',
+ 'current_default_transform_group',
+ 'current_path',
+ 'current_role',
+ 'current_schema',
+ 'current_transform_group_for_type',
+ 'cycle',
+ 'data',
+ 'date',
+ 'day',
+ 'dec',
+ 'decimal',
+ 'deferrable',
+ 'deferred',
+ 'depth',
+ 'deref',
+ 'describe',
+ 'descriptor',
+ 'destroy',
+ 'destructor',
+ 'deterministic',
+ 'diagnostics',
+ 'dictionary',
+ 'disconnect',
+ 'domain',
+ 'dynamic',
+ 'each',
+ 'element',
+ 'end-exec',
+ 'equals',
+ 'every',
+ 'exception',
+ 'false',
+ 'filter',
+ 'first',
+ 'float',
+ 'found',
+ 'free',
+ 'fulltexttable',
+ 'fusion',
+ 'general',
+ 'get',
+ 'global',
+ 'go',
+ 'grouping',
+ 'hold',
+ 'host',
+ 'hour',
+ 'ignore',
+ 'immediate',
+ 'indicator',
+ 'initialize',
+ 'initially',
+ 'inout',
+ 'input',
+ 'int',
+ 'integer',
+ 'intersection',
+ 'interval',
+ 'isolation',
+ 'iterate',
+ 'language',
+ 'large',
+ 'last',
+ 'lateral',
+ 'leading',
+ 'less',
+ 'level',
+ 'like_regex',
+ 'limit',
+ 'ln',
+ 'local',
+ 'localtime',
+ 'localtimestamp',
+ 'locator',
+ 'map',
+ 'match',
+ 'member',
+ 'method',
+ 'minute',
+ 'mod',
+ 'modifies',
+ 'modify',
+ 'module',
+ 'month',
+ 'multiset',
+ 'names',
+ 'natural',
+ 'nchar',
+ 'nclob',
+ 'new',
+ 'next',
+ 'no',
+ 'none',
+ 'normalize',
+ 'numeric',
+ 'object',
+ 'occurrences_regex',
+ 'old',
+ 'only',
+ 'operation',
+ 'ordinality',
+ 'out',
+ 'output',
+ 'overlay',
+ 'pad',
+ 'parameter',
+ 'parameters',
+ 'partial',
+ 'partition',
+ 'path',
+ 'percent_rank',
+ 'percentile_cont',
+ 'percentile_disc',
+ 'position_regex',
+ 'postfix',
+ 'prefix',
+ 'preorder',
+ 'prepare',
+ 'preserve',
+ 'prior',
+ 'privileges',
+ 'range',
+ 'reads',
+ 'real',
+ 'recursive',
+ 'ref',
+ 'referencing',
+ 'regr_avgx',
+ 'regr_avgy',
+ 'regr_count',
+ 'regr_intercept',
+ 'regr_r2',
+ 'regr_slope',
+ 'regr_sxx',
+ 'regr_sxy',
+ 'regr_syy',
+ 'relative',
+ 'release',
+ 'result',
+ 'returns',
+ 'role',
+ 'rollup',
+ 'routine',
+ 'row',
+ 'rows',
+ 'savepoint',
+ 'scope',
+ 'scroll',
+ 'search',
+ 'second',
+ 'section',
+ 'sensitive',
+ 'sequence',
+ 'session',
+ 'sets',
+ 'similar',
+ 'size',
+ 'smallint',
+ 'space',
+ 'specific',
+ 'specifictype',
+ 'sql',
+ 'sqlexception',
+ 'sqlstate',
+ 'sqlwarning',
+ 'start',
+ 'state',
+ 'statement',
+ 'static',
+ 'stddev_pop',
+ 'stddev_samp',
+ 'structure',
+ 'submultiset',
+ 'substring_regex',
+ 'symmetric',
+ 'system',
+ 'temporary',
+ 'terminate',
+ 'than',
+ 'time',
+ 'timestamp',
+ 'timezone_hour',
+ 'timezone_minute',
+ 'trailing',
+ 'translate_regex',
+ 'translation',
+ 'treat',
+ 'true',
+ 'uescape',
+ 'under',
+ 'unknown',
+ 'unnest',
+ 'usage',
+ 'using',
+ 'value',
+ 'var_pop',
+ 'var_samp',
+ 'varchar',
+ 'variable',
+ 'whenever',
+ 'width_bucket',
+ 'window',
+ 'within',
+ 'without',
+ 'work',
+ 'write',
+ 'xmlagg',
+ 'xmlattributes',
+ 'xmlbinary',
+ 'xmlcast',
+ 'xmlcomment',
+ 'xmlconcat',
+ 'xmldocument',
+ 'xmlelement',
+ 'xmlexists',
+ 'xmlforest',
+ 'xmliterate',
+ 'xmlnamespaces',
+ 'xmlparse',
+ 'xmlpi',
+ 'xmlquery',
+ 'xmlserialize',
+ 'xmltable',
+ 'xmltext',
+ 'xmlvalidate',
+ 'year',
+ 'zone',
+)
+
+_KEYWORDS_ODBC = (
+ 'absolute',
+ 'action',
+ 'ada',
+ 'add',
+ 'all',
+ 'allocate',
+ 'alter',
+ 'and',
+ 'any',
+ 'are',
+ 'as',
+ 'asc',
+ 'assertion',
+ 'at',
+ 'authorization',
+ 'avg',
+ 'begin',
+ 'between',
+ 'bit',
+ 'bit_length',
+ 'both',
+ 'by',
+ 'cascade',
+ 'cascaded',
+ 'case',
+ 'cast',
+ 'catalog',
+ 'char',
+ 'char_length',
+ 'character',
+ 'character_length',
+ 'check',
+ 'close',
+ 'coalesce',
+ 'collate',
+ 'collation',
+ 'column',
+ 'commit',
+ 'connect',
+ 'connection',
+ 'constraint',
+ 'constraints',
+ 'continue',
+ 'convert',
+ 'corresponding',
+ 'count',
+ 'create',
+ 'cross',
+ 'current',
+ 'current_date',
+ 'current_time',
+ 'current_timestamp',
+ 'current_user',
+ 'cursor',
+ 'date',
+ 'day',
+ 'deallocate',
+ 'dec',
+ 'decimal',
+ 'declare',
+ 'default',
+ 'deferrable',
+ 'deferred',
+ 'delete',
+ 'desc',
+ 'describe',
+ 'descriptor',
+ 'diagnostics',
+ 'disconnect',
+ 'distinct',
+ 'domain',
+ 'double',
+ 'drop',
+ 'else',
+ 'end',
+ 'end-exec',
+ 'escape',
+ 'except',
+ 'exception',
+ 'exec',
+ 'execute',
+ 'exists',
+ 'external',
+ 'extract',
+ 'false',
+ 'fetch',
+ 'first',
+ 'float',
+ 'for',
+ 'foreign',
+ 'fortran',
+ 'found',
+ 'from',
+ 'full',
+ 'get',
+ 'global',
+ 'go',
+ 'goto',
+ 'grant',
+ 'group',
+ 'having',
+ 'hour',
+ 'identity',
+ 'immediate',
+ 'in',
+ 'include',
+ 'index',
+ 'indicator',
+ 'initially',
+ 'inner',
+ 'input',
+ 'insensitive',
+ 'insert',
+ 'int',
+ 'integer',
+ 'intersect',
+ 'interval',
+ 'into',
+ 'is',
+ 'isolation',
+ 'join',
+ 'key',
+ 'language',
+ 'last',
+ 'leading',
+ 'left',
+ 'level',
+ 'like',
+ 'local',
+ 'lower',
+ 'match',
+ 'max',
+ 'min',
+ 'minute',
+ 'module',
+ 'month',
+ 'names',
+ 'national',
+ 'natural',
+ 'nchar',
+ 'next',
+ 'no',
+ 'none',
+ 'not',
+ 'null',
+ 'nullif',
+ 'numeric',
+ 'octet_length',
+ 'of',
+ 'on',
+ 'only',
+ 'open',
+ 'option',
+ 'or',
+ 'order',
+ 'outer',
+ 'output',
+ 'overlaps',
+ 'pad',
+ 'partial',
+ 'pascal',
+ 'position',
+ 'precision',
+ 'prepare',
+ 'preserve',
+ 'primary',
+ 'prior',
+ 'privileges',
+ 'procedure',
+ 'public',
+ 'read',
+ 'real',
+ 'references',
+ 'relative',
+ 'restrict',
+ 'revoke',
+ 'right',
+ 'rollback',
+ 'rows',
+ 'schema',
+ 'scroll',
+ 'second',
+ 'section',
+ 'select',
+ 'session',
+ 'session_user',
+ 'set',
+ 'size',
+ 'smallint',
+ 'some',
+ 'space',
+ 'sql',
+ 'sqlca',
+ 'sqlcode',
+ 'sqlerror',
+ 'sqlstate',
+ 'sqlwarning',
+ 'substring',
+ 'sum',
+ 'system_user',
+ 'table',
+ 'temporary',
+ 'then',
+ 'time',
+ 'timestamp',
+ 'timezone_hour',
+ 'timezone_minute',
+ 'to',
+ 'trailing',
+ 'transaction',
+ 'translate',
+ 'translation',
+ 'trim',
+ 'true',
+ 'union',
+ 'unique',
+ 'unknown',
+ 'update',
+ 'upper',
+ 'usage',
+ 'user',
+ 'using',
+ 'value',
+ 'values',
+ 'varchar',
+ 'varying',
+ 'view',
+ 'when',
+ 'whenever',
+ 'where',
+ 'with',
+ 'work',
+ 'write',
+ 'year',
+ 'zone',
+)
+
+KEYWORDS = sorted(set(_KEYWORDS_FUTURE + _KEYWORDS_ODBC + _KEYWORDS_SERVER))
+
+TYPES = (
+ 'bigint',
+ 'binary',
+ 'bit',
+ 'char',
+ 'cursor',
+ 'date',
+ 'datetime',
+ 'datetime2',
+ 'datetimeoffset',
+ 'decimal',
+ 'float',
+ 'hierarchyid',
+ 'image',
+ 'int',
+ 'money',
+ 'nchar',
+ 'ntext',
+ 'numeric',
+ 'nvarchar',
+ 'real',
+ 'smalldatetime',
+ 'smallint',
+ 'smallmoney',
+ 'sql_variant',
+ 'table',
+ 'text',
+ 'time',
+ 'timestamp',
+ 'tinyint',
+ 'uniqueidentifier',
+ 'varbinary',
+ 'varchar',
+ 'xml',
+)
+
+FUNCTIONS = (
+ '$partition',
+ 'abs',
+ 'acos',
+ 'app_name',
+ 'applock_mode',
+ 'applock_test',
+ 'ascii',
+ 'asin',
+ 'assemblyproperty',
+ 'atan',
+ 'atn2',
+ 'avg',
+ 'binary_checksum',
+ 'cast',
+ 'ceiling',
+ 'certencoded',
+ 'certprivatekey',
+ 'char',
+ 'charindex',
+ 'checksum',
+ 'checksum_agg',
+ 'choose',
+ 'col_length',
+ 'col_name',
+ 'columnproperty',
+ 'compress',
+ 'concat',
+ 'connectionproperty',
+ 'context_info',
+ 'convert',
+ 'cos',
+ 'cot',
+ 'count',
+ 'count_big',
+ 'current_request_id',
+ 'current_timestamp',
+ 'current_transaction_id',
+ 'current_user',
+ 'cursor_status',
+ 'database_principal_id',
+ 'databasepropertyex',
+ 'dateadd',
+ 'datediff',
+ 'datediff_big',
+ 'datefromparts',
+ 'datename',
+ 'datepart',
+ 'datetime2fromparts',
+ 'datetimefromparts',
+ 'datetimeoffsetfromparts',
+ 'day',
+ 'db_id',
+ 'db_name',
+ 'decompress',
+ 'degrees',
+ 'dense_rank',
+ 'difference',
+ 'eomonth',
+ 'error_line',
+ 'error_message',
+ 'error_number',
+ 'error_procedure',
+ 'error_severity',
+ 'error_state',
+ 'exp',
+ 'file_id',
+ 'file_idex',
+ 'file_name',
+ 'filegroup_id',
+ 'filegroup_name',
+ 'filegroupproperty',
+ 'fileproperty',
+ 'floor',
+ 'format',
+ 'formatmessage',
+ 'fulltextcatalogproperty',
+ 'fulltextserviceproperty',
+ 'get_filestream_transaction_context',
+ 'getansinull',
+ 'getdate',
+ 'getutcdate',
+ 'grouping',
+ 'grouping_id',
+ 'has_perms_by_name',
+ 'host_id',
+ 'host_name',
+ 'iif',
+ 'index_col',
+ 'indexkey_property',
+ 'indexproperty',
+ 'is_member',
+ 'is_rolemember',
+ 'is_srvrolemember',
+ 'isdate',
+ 'isjson',
+ 'isnull',
+ 'isnumeric',
+ 'json_modify',
+ 'json_query',
+ 'json_value',
+ 'left',
+ 'len',
+ 'log',
+ 'log10',
+ 'lower',
+ 'ltrim',
+ 'max',
+ 'min',
+ 'min_active_rowversion',
+ 'month',
+ 'nchar',
+ 'newid',
+ 'newsequentialid',
+ 'ntile',
+ 'object_definition',
+ 'object_id',
+ 'object_name',
+ 'object_schema_name',
+ 'objectproperty',
+ 'objectpropertyex',
+ 'opendatasource',
+ 'openjson',
+ 'openquery',
+ 'openrowset',
+ 'openxml',
+ 'original_db_name',
+ 'original_login',
+ 'parse',
+ 'parsename',
+ 'patindex',
+ 'permissions',
+ 'pi',
+ 'power',
+ 'pwdcompare',
+ 'pwdencrypt',
+ 'quotename',
+ 'radians',
+ 'rand',
+ 'rank',
+ 'replace',
+ 'replicate',
+ 'reverse',
+ 'right',
+ 'round',
+ 'row_number',
+ 'rowcount_big',
+ 'rtrim',
+ 'schema_id',
+ 'schema_name',
+ 'scope_identity',
+ 'serverproperty',
+ 'session_context',
+ 'session_user',
+ 'sign',
+ 'sin',
+ 'smalldatetimefromparts',
+ 'soundex',
+ 'sp_helplanguage',
+ 'space',
+ 'sqrt',
+ 'square',
+ 'stats_date',
+ 'stdev',
+ 'stdevp',
+ 'str',
+ 'string_escape',
+ 'string_split',
+ 'stuff',
+ 'substring',
+ 'sum',
+ 'suser_id',
+ 'suser_name',
+ 'suser_sid',
+ 'suser_sname',
+ 'switchoffset',
+ 'sysdatetime',
+ 'sysdatetimeoffset',
+ 'system_user',
+ 'sysutcdatetime',
+ 'tan',
+ 'textptr',
+ 'textvalid',
+ 'timefromparts',
+ 'todatetimeoffset',
+ 'try_cast',
+ 'try_convert',
+ 'try_parse',
+ 'type_id',
+ 'type_name',
+ 'typeproperty',
+ 'unicode',
+ 'upper',
+ 'user_id',
+ 'user_name',
+ 'var',
+ 'varp',
+ 'xact_state',
+ 'year',
+)
diff --git a/pygments/lexers/sql.py b/pygments/lexers/sql.py
index 7c06226b..f6539c36 100644
--- a/pygments/lexers/sql.py
+++ b/pygments/lexers/sql.py
@@ -41,17 +41,19 @@
import re
from pygments.lexer import Lexer, RegexLexer, do_insertions, bygroups, words
-from pygments.token import Punctuation, \
+from pygments.token import Punctuation, Whitespace, Error, \
Text, Comment, Operator, Keyword, Name, String, Number, Generic
from pygments.lexers import get_lexer_by_name, ClassNotFound
from pygments.util import iteritems
from pygments.lexers._postgres_builtins import KEYWORDS, DATATYPES, \
PSEUDO_TYPES, PLPGSQL_KEYWORDS
+from pygments.lexers import _tsql_builtins
__all__ = ['PostgresLexer', 'PlPgsqlLexer', 'PostgresConsoleLexer',
- 'SqlLexer', 'MySqlLexer', 'SqliteConsoleLexer', 'RqlLexer']
+ 'SqlLexer', 'TransactSqlLexer', 'MySqlLexer',
+ 'SqliteConsoleLexer', 'RqlLexer']
line_re = re.compile('.*?\n')
@@ -479,6 +481,57 @@ class SqlLexer(RegexLexer):
}
+class TransactSqlLexer(RegexLexer):
+ """
+ Transact-SQL (T-SQL) is Microsoft's and Sybase's proprietary extension to
+ SQL.
+
+ The list of keywords includes ODBC and keywords reserved for future use..
+ """
+
+ name = 'Transact-SQL'
+ aliases = ['tsql', 't-sql']
+ filenames = ['*.sql']
+ mimetypes = ['text/x-tsql']
+
+ flags = re.IGNORECASE | re.UNICODE
+ tokens = {
+ 'root': [
+ (r'\s+', Whitespace),
+ (r'--.*?\n', Comment.Single),
+ (r'/\*', Comment.Multiline, 'multiline-comments'),
+ (r'(-=|-)', Operator), # HACK: For some reason these operators do not work as part of OPERATORS.
+ (words(_tsql_builtins.OPERATORS), Operator),
+ (words(_tsql_builtins.OPERATOR_WORDS, suffix=r'\b'), Operator.Word),
+ (words(_tsql_builtins.TYPES, suffix=r'\b'), Name.Class),
+ (words(_tsql_builtins.FUNCTIONS, suffix=r'\b'), Name.Function),
+ (r'(goto)(\s+)(\w+\b)', bygroups(Keyword, Whitespace, Name.Label)),
+ (words(_tsql_builtins.KEYWORDS, suffix=r'\b'), Keyword),
+ (r'(\[)([^]]+)(\])', bygroups(Operator, Name, Operator)),
+ (r'0x[0-9a-f]+', Number.Hex),
+ (r'[0-9]*\.?[0-9]+(e[+-]?[0-9]+)?', Number.Float),
+ (r'[0-9]+', Number.Integer),
+ (r"'(''|[^'])*'", String.Single),
+ (r'"(""|[^"])*"', String.Symbol),
+ (r'[;(),.]', Punctuation),
+ # Below we use \w even for the first "real" character because
+ # tokens starting with a digit have already been recognized
+ # as Number above.
+ (r'@@\w+', Name.Builtin),
+ (r'@\w+', Name.Variable),
+ (r'(\w+)(:)', bygroups(Name.Label, Punctuation)),
+ (r'#?#?\w+', Name),
+ (r'\?', Name.Variable.Magic), # Parameter for prepared statements
+ ],
+ 'multiline-comments': [
+ (r'/\*', Comment.Multiline, 'multiline-comments'),
+ (r'\*/', Comment.Multiline, '#pop'),
+ (r'[^/*]+', Comment.Multiline),
+ (r'[/*]', Comment.Multiline)
+ ]
+ }
+
+
class MySqlLexer(RegexLexer):
"""
Special lexer for MySQL.
diff --git a/tests/examplefiles/test_transact-sql.txt b/tests/examplefiles/test_transact-sql.txt
new file mode 100644
index 00000000..90e06c34
--- /dev/null
+++ b/tests/examplefiles/test_transact-sql.txt
@@ -0,0 +1,68 @@
+-- Example Transact-SQL file.
+--
+-- We cannot use "*.sql" as file suffix because then the automatic tests for
+-- the ANSI SQL lexer would attempt to read it and in turn detect errors in
+-- it which would cause a test case to fail.
+
+-- Single line comment
+/* A comment
+ * spawning two lines. */
+ /* An indented comment
+ * spawning multiple
+ * lines. */
+/* A /* nested */ comment. */
+
+select
+ left(emp.firstname, 1) + '.' + [emp.surname] as "Name",
+ dep.name as [Department]
+into
+ #temp_employee
+from
+ employee as emp
+ inner join department as dep on
+ dep.ident_code = emp.department_id
+where
+ emp.date_of_birth >= '1990-01-01';
+go
+
+declare @TextToFind nvarchar(100) = N'some
+text across
+multiple lines';
+
+set @TextToFind = 'hello' + ' world';
+set @TextTiFind += '!';
+
+delete from
+ [server].[database].[schema].[table]
+where
+ [Text] = @TextToFind and author Not LIKE '%some%';
+
+goto overthere;
+overthere:
+
+select
+ 123 as "int 1",
+ +123 as "int 2",
+ -123 as "int 3",
+ 0x20 as "hex int",
+ 123.45 as "float 1",
+ -1.23e45 as "float 2"
+ +1.23E+45 as "float 3",
+ -1.23e-45 as "float 4";
+
+Select @@Error, $PARTITion.RangePF1(10);
+
+select top 3 Ähnliches from Müll;
+
+-- Example transaction
+BEGIN TRAN
+
+BEGIN TRY
+ INSERT INTO #temp_employe(Name, Department) VALUES ('L. Miller', 'Sales')
+ iNsErT inTO #temp_employe(Name, Department) VaLuEs ('M. Webster', 'Helpdesk')
+ COMMIT TRAN
+END TRY
+BEGIN CATCH
+ print 'cannot perform transaction; rolling back';
+ ROLLBACK TRAN
+END CATCH
diff --git a/tests/test_sql.py b/tests/test_sql.py
new file mode 100644
index 00000000..37a81ff8
--- /dev/null
+++ b/tests/test_sql.py
@@ -0,0 +1,76 @@
+# -*- coding: utf-8 -*-
+"""
+ Pygments SQL lexers tests
+ ~~~~~~~~~~~~~~~~~~~~~~~~~
+
+ :copyright: Copyright 2006-2016 by the Pygments team, see AUTHORS.
+ :license: BSD, see LICENSE for details.
+"""
+import io
+import os.path
+import unittest
+
+from pygments.lexers.sql import TransactSqlLexer
+from pygments.token import Comment, Error, Name, Number, Whitespace
+
+
+class TransactSqlLexerTest(unittest.TestCase):
+
+ def setUp(self):
+ self.lexer = TransactSqlLexer()
+
+ def _assertAreTokensOfType(self, examples, expected_token_type):
+ for test_number, example in enumerate(examples.split(), 1):
+ token_count = 0
+ for token_type, token_value in self.lexer.get_tokens(example):
+ if token_type != Whitespace:
+ token_count += 1
+ self.assertEqual(
+ token_type, expected_token_type,
+ 'token_type #%d for %s is be %s but must be %s' %
+ (test_number, token_value, token_type, expected_token_type))
+ self.assertEqual(
+ token_count, 1,
+ '%s must yield exactly 1 token instead of %d' %
+ (example, token_count))
+
+ def _assertTokensMatch(self, text, expected_tokens_without_trailing_newline):
+ actual_tokens = tuple(self.lexer.get_tokens(text))
+ if (len(actual_tokens) >= 1) and (actual_tokens[-1] == (Whitespace, '\n')):
+ actual_tokens = tuple(actual_tokens[:-1])
+ self.assertEqual(
+ expected_tokens_without_trailing_newline, actual_tokens,
+ 'text must yield expected tokens: %s' % text)
+
+ def test_can_lex_float(self):
+ self._assertAreTokensOfType(
+ '1.2 1.2e3 1.2e+3 1.2e-3 1e2', Number.Float)
+ self._assertTokensMatch(
+ '1e2.1e2',
+ ((Number.Float, '1e2'), (Number.Float, '.1e2'))
+ )
+
+ def test_can_lex_names(self):
+ self._assertAreTokensOfType(
+ u'thingy thingy123 _thingy _ _123 Ähnliches Müll #temp1 ##temp2', Name)
+
+ def test_can_lex_comments(self):
+ self._assertTokensMatch('--\n', ((Comment.Single, '--\n'),))
+ self._assertTokensMatch('/**/', (
+ (Comment.Multiline, '/*'), (Comment.Multiline, '*/')
+ ))
+ self._assertTokensMatch('/*/**/*/', (
+ (Comment.Multiline, '/*'),
+ (Comment.Multiline, '/*'),
+ (Comment.Multiline, '*/'),
+ (Comment.Multiline, '*/'),
+ ))
+
+ def test_can_lex_example_file(self):
+ tests_path = os.path.dirname(__file__)
+ example_path = os.path.join(tests_path, 'examplefiles', 'test_transact-sql.txt')
+
+ with io.open(example_path, 'r', encoding='utf-8') as example_file:
+ example_code = example_file.read()
+ for token_type, token_value in self.lexer.get_tokens(example_code):
+ self.assertNotEqual(Error, token_type, 'token_value=%r' % token_value)