/
usr
/
lib
/
imh-scan
/
venv
/
lib
/
python3.13
/
site-packages
/
pygments
/
lexers
/
/usr/lib/imh-scan/venv/lib/python3.13/site-packages/pygments/lexers
mkdir
upload
Name
Size
Mode
Actions
__pycache__/
-
0755
rm
actionscript.py
11727
0644
edit
dl
rm
ada.py
5353
0644
edit
dl
rm
agile.py
896
0644
edit
dl
rm
algebra.py
9952
0644
edit
dl
rm
ambient.py
2605
0644
edit
dl
rm
amdgpu.py
1723
0644
edit
dl
rm
ampl.py
4176
0644
edit
dl
rm
apdlexer.py
30800
0644
edit
dl
rm
apl.py
3404
0644
edit
dl
rm
archetype.py
11538
0644
edit
dl
rm
arrow.py
3564
0644
edit
dl
rm
arturo.py
11414
0644
edit
dl
rm
asc.py
1693
0644
edit
dl
rm
asm.py
41967
0644
edit
dl
rm
asn1.py
4262
0644
edit
dl
rm
automation.py
19831
0644
edit
dl
rm
bare.py
3020
0644
edit
dl
rm
basic.py
27989
0644
edit
dl
rm
bdd.py
1641
0644
edit
dl
rm
berry.py
3209
0644
edit
dl
rm
bibtex.py
4811
0644
edit
dl
rm
blueprint.py
6188
0644
edit
dl
rm
boa.py
3921
0644
edit
dl
rm
bqn.py
3671
0644
edit
dl
rm
business.py
28345
0644
edit
dl
rm
capnproto.py
2174
0644
edit
dl
rm
carbon.py
3211
0644
edit
dl
rm
cddl.py
5076
0644
edit
dl
rm
chapel.py
5156
0644
edit
dl
rm
clean.py
6418
0644
edit
dl
rm
codeql.py
2576
0644
edit
dl
rm
comal.py
3179
0644
edit
dl
rm
compiled.py
1426
0644
edit
dl
rm
configs.py
50913
0644
edit
dl
rm
console.py
4180
0644
edit
dl
rm
cplint.py
1389
0644
edit
dl
rm
crystal.py
15754
0644
edit
dl
rm
csound.py
16998
0644
edit
dl
rm
css.py
25376
0644
edit
dl
rm
c_cpp.py
18059
0644
edit
dl
rm
c_like.py
32021
0644
edit
dl
rm
d.py
9920
0644
edit
dl
rm
dalvik.py
4606
0644
edit
dl
rm
data.py
27026
0644
edit
dl
rm
dax.py
8098
0644
edit
dl
rm
devicetree.py
4019
0644
edit
dl
rm
diff.py
5382
0644
edit
dl
rm
dns.py
3891
0644
edit
dl
rm
dotnet.py
39441
0644
edit
dl
rm
dsls.py
36746
0644
edit
dl
rm
dylan.py
10409
0644
edit
dl
rm
ecl.py
6371
0644
edit
dl
rm
eiffel.py
2690
0644
edit
dl
rm
elm.py
3152
0644
edit
dl
rm
elpi.py
6877
0644
edit
dl
rm
email.py
4804
0644
edit
dl
rm
erlang.py
19147
0644
edit
dl
rm
esoteric.py
10500
0644
edit
dl
rm
ezhil.py
3272
0644
edit
dl
rm
factor.py
19530
0644
edit
dl
rm
fantom.py
10231
0644
edit
dl
rm
felix.py
9655
0644
edit
dl
rm
fift.py
1644
0644
edit
dl
rm
floscript.py
2667
0644
edit
dl
rm
forth.py
7193
0644
edit
dl
rm
fortran.py
10382
0644
edit
dl
rm
foxpro.py
26295
0644
edit
dl
rm
freefem.py
26913
0644
edit
dl
rm
func.py
3700
0644
edit
dl
rm
functional.py
693
0644
edit
dl
rm
futhark.py
3743
0644
edit
dl
rm
gcodelexer.py
874
0644
edit
dl
rm
gdscript.py
7566
0644
edit
dl
rm
gleam.py
2392
0644
edit
dl
rm
go.py
3783
0644
edit
dl
rm
grammar_notation.py
8043
0644
edit
dl
rm
graph.py
4108
0644
edit
dl
rm
graphics.py
39145
0644
edit
dl
rm
graphql.py
5601
0644
edit
dl
rm
graphviz.py
1934
0644
edit
dl
rm
gsql.py
3990
0644
edit
dl
rm
hare.py
2649
0644
edit
dl
rm
haskell.py
33262
0644
edit
dl
rm
haxe.py
30974
0644
edit
dl
rm
hdl.py
22738
0644
edit
dl
rm
hexdump.py
3653
0644
edit
dl
rm
html.py
21977
0644
edit
dl
rm
idl.py
15449
0644
edit
dl
rm
igor.py
31633
0644
edit
dl
rm
inferno.py
3135
0644
edit
dl
rm
installers.py
14435
0644
edit
dl
rm
int_fiction.py
56544
0644
edit
dl
rm
iolang.py
1905
0644
edit
dl
rm
j.py
4853
0644
edit
dl
rm
javascript.py
63243
0644
edit
dl
rm
jmespath.py
2082
0644
edit
dl
rm
jslt.py
3700
0644
edit
dl
rm
json5.py
2502
0644
edit
dl
rm
jsonnet.py
5636
0644
edit
dl
rm
jsx.py
2693
0644
edit
dl
rm
julia.py
11710
0644
edit
dl
rm
jvm.py
72667
0644
edit
dl
rm
kuin.py
11405
0644
edit
dl
rm
kusto.py
3477
0644
edit
dl
rm
ldap.py
6551
0644
edit
dl
rm
lean.py
8570
0644
edit
dl
rm
lilypond.py
9752
0644
edit
dl
rm
lisp.py
157668
0644
edit
dl
rm
macaulay2.py
33366
0644
edit
dl
rm
make.py
7831
0644
edit
dl
rm
maple.py
7960
0644
edit
dl
rm
markup.py
65088
0644
edit
dl
rm
math.py
695
0644
edit
dl
rm
matlab.py
133027
0644
edit
dl
rm
maxima.py
2715
0644
edit
dl
rm
meson.py
4336
0644
edit
dl
rm
mime.py
7582
0644
edit
dl
rm
minecraft.py
13696
0644
edit
dl
rm
mips.py
4656
0644
edit
dl
rm
ml.py
35390
0644
edit
dl
rm
modeling.py
13683
0644
edit
dl
rm
modula2.py
53072
0644
edit
dl
rm
mojo.py
24233
0644
edit
dl
rm
monte.py
6289
0644
edit
dl
rm
mosel.py
9297
0644
edit
dl
rm
ncl.py
63999
0644
edit
dl
rm
nimrod.py
6413
0644
edit
dl
rm
nit.py
2725
0644
edit
dl
rm
nix.py
4421
0644
edit
dl
rm
numbair.py
1758
0644
edit
dl
rm
oberon.py
4210
0644
edit
dl
rm
objective.py
23297
0644
edit
dl
rm
ooc.py
3002
0644
edit
dl
rm
openscad.py
3700
0644
edit
dl
rm
other.py
1763
0644
edit
dl
rm
parasail.py
2719
0644
edit
dl
rm
parsers.py
26596
0644
edit
dl
rm
pascal.py
30989
0644
edit
dl
rm
pawn.py
8253
0644
edit
dl
rm
pddl.py
2989
0644
edit
dl
rm
perl.py
39192
0644
edit
dl
rm
phix.py
23249
0644
edit
dl
rm
php.py
13061
0644
edit
dl
rm
pointless.py
1974
0644
edit
dl
rm
pony.py
3279
0644
edit
dl
rm
praat.py
12676
0644
edit
dl
rm
procfile.py
1155
0644
edit
dl
rm
prolog.py
12866
0644
edit
dl
rm
promql.py
4738
0644
edit
dl
rm
prql.py
8747
0644
edit
dl
rm
ptx.py
4501
0644
edit
dl
rm
python.py
53805
0644
edit
dl
rm
q.py
6936
0644
edit
dl
rm
qlik.py
3693
0644
edit
dl
rm
qvt.py
6103
0644
edit
dl
rm
r.py
6474
0644
edit
dl
rm
rdf.py
16056
0644
edit
dl
rm
rebol.py
18259
0644
edit
dl
rm
rego.py
1748
0644
edit
dl
rm
resource.py
2927
0644
edit
dl
rm
ride.py
5035
0644
edit
dl
rm
rita.py
1127
0644
edit
dl
rm
rnc.py
1972
0644
edit
dl
rm
roboconf.py
2074
0644
edit
dl
rm
robotframework.py
18448
0644
edit
dl
rm
ruby.py
22753
0644
edit
dl
rm
rust.py
8260
0644
edit
dl
rm
sas.py
9456
0644
edit
dl
rm
savi.py
4878
0644
edit
dl
rm
scdoc.py
2524
0644
edit
dl
rm
scripting.py
81814
0644
edit
dl
rm
sgf.py
1985
0644
edit
dl
rm
shell.py
36381
0644
edit
dl
rm
sieve.py
2514
0644
edit
dl
rm
slash.py
8484
0644
edit
dl
rm
smalltalk.py
7204
0644
edit
dl
rm
smithy.py
2659
0644
edit
dl
rm
smv.py
2805
0644
edit
dl
rm
snobol.py
2778
0644
edit
dl
rm
solidity.py
3163
0644
edit
dl
rm
soong.py
2339
0644
edit
dl
rm
sophia.py
3376
0644
edit
dl
rm
special.py
3585
0644
edit
dl
rm
spice.py
2790
0644
edit
dl
rm
sql.py
41476
0644
edit
dl
rm
srcinfo.py
1746
0644
edit
dl
rm
stata.py
6415
0644
edit
dl
rm
supercollider.py
3697
0644
edit
dl
rm
tablegen.py
3987
0644
edit
dl
rm
tact.py
10809
0644
edit
dl
rm
tal.py
2904
0644
edit
dl
rm
tcl.py
5512
0644
edit
dl
rm
teal.py
3522
0644
edit
dl
rm
templates.py
75731
0644
edit
dl
rm
teraterm.py
9718
0644
edit
dl
rm
testing.py
10810
0644
edit
dl
rm
text.py
1068
0644
edit
dl
rm
textedit.py
7760
0644
edit
dl
rm
textfmts.py
15524
0644
edit
dl
rm
theorem.py
17855
0644
edit
dl
rm
thingsdb.py
6017
0644
edit
dl
rm
tlb.py
1450
0644
edit
dl
rm
tls.py
1540
0644
edit
dl
rm
tnt.py
10456
0644
edit
dl
rm
trafficscript.py
1506
0644
edit
dl
rm
typoscript.py
8332
0644
edit
dl
rm
typst.py
7167
0644
edit
dl
rm
ul4.py
10499
0644
edit
dl
rm
unicon.py
18625
0644
edit
dl
rm
urbi.py
6082
0644
edit
dl
rm
usd.py
3304
0644
edit
dl
rm
varnish.py
7473
0644
edit
dl
rm
verification.py
3934
0644
edit
dl
rm
verifpal.py
2661
0644
edit
dl
rm
vip.py
5711
0644
edit
dl
rm
vyper.py
5615
0644
edit
dl
rm
web.py
913
0644
edit
dl
rm
webassembly.py
5698
0644
edit
dl
rm
webidl.py
10516
0644
edit
dl
rm
webmisc.py
40564
0644
edit
dl
rm
wgsl.py
11880
0644
edit
dl
rm
whiley.py
4017
0644
edit
dl
rm
wowtoc.py
4076
0644
edit
dl
rm
wren.py
3229
0644
edit
dl
rm
x10.py
1943
0644
edit
dl
rm
xorg.py
925
0644
edit
dl
rm
yang.py
4499
0644
edit
dl
rm
yara.py
2427
0644
edit
dl
rm
zig.py
3976
0644
edit
dl
rm
_ada_builtins.py
1543
0644
edit
dl
rm
_asy_builtins.py
27287
0644
edit
dl
rm
_cl_builtins.py
13994
0644
edit
dl
rm
_cocoa_builtins.py
105173
0644
edit
dl
rm
_csound_builtins.py
18414
0644
edit
dl
rm
_css_builtins.py
12446
0644
edit
dl
rm
_googlesql_builtins.py
16132
0644
edit
dl
rm
_julia_builtins.py
11883
0644
edit
dl
rm
_lasso_builtins.py
134510
0644
edit
dl
rm
_lilypond_builtins.py
108094
0644
edit
dl
rm
_luau_builtins.py
955
0644
edit
dl
rm
_lua_builtins.py
8108
0644
edit
dl
rm
_mapping.py
70438
0644
edit
dl
rm
_mql_builtins.py
24713
0644
edit
dl
rm
_mysql_builtins.py
25838
0644
edit
dl
rm
_openedge_builtins.py
49398
0644
edit
dl
rm
_php_builtins.py
107922
0644
edit
dl
rm
_postgres_builtins.py
13343
0644
edit
dl
rm
_qlik_builtins.py
12595
0644
edit
dl
rm
_scheme_builtins.py
32564
0644
edit
dl
rm
_scilab_builtins.py
52411
0644
edit
dl
rm
_sourcemod_builtins.py
26777
0644
edit
dl
rm
_sql_builtins.py
6767
0644
edit
dl
rm
_stan_builtins.py
13445
0644
edit
dl
rm
_stata_builtins.py
27227
0644
edit
dl
rm
_tsql_builtins.py
15460
0644
edit
dl
rm
_usd_builtins.py
1658
0644
edit
dl
rm
_vbscript_builtins.py
4225
0644
edit
dl
rm
_vim_builtins.py
57066
0644
edit
dl
rm
__init__.py
12067
0644
edit
dl
rm
Edit:
/usr/lib/imh-scan/venv/lib/python3.13/site-packages/pygments/lexers/sql.py
(41476B)
""" pygments.lexers.sql ~~~~~~~~~~~~~~~~~~~ Lexers for various SQL dialects and related interactive sessions. Postgres specific lexers: `PostgresLexer` A SQL lexer for the PostgreSQL dialect. Differences w.r.t. the SQL lexer are: - keywords and data types list parsed from the PG docs (run the `_postgres_builtins` module to update them); - Content of $-strings parsed using a specific lexer, e.g. the content of a PL/Python function is parsed using the Python lexer; - parse PG specific constructs: E-strings, $-strings, U&-strings, different operators and punctuation. `PlPgsqlLexer` A lexer for the PL/pgSQL language. Adds a few specific construct on top of the PG SQL lexer (such as <<label>>). `PostgresConsoleLexer` A lexer to highlight an interactive psql session: - identifies the prompt and does its best to detect the end of command in multiline statement where not all the lines are prefixed by a prompt, telling them apart from the output; - highlights errors in the output and notification levels; - handles psql backslash commands. `PostgresExplainLexer` A lexer to highlight Postgres execution plan. The ``tests/examplefiles`` contains a few test files with data to be parsed by these lexers. :copyright: Copyright 2006-2025 by the Pygments team, see AUTHORS. :license: BSD, see LICENSE for details. """ import collections import re from pygments.lexer import Lexer, RegexLexer, do_insertions, bygroups, words from pygments.lexers import _googlesql_builtins from pygments.lexers import _mysql_builtins from pygments.lexers import _postgres_builtins from pygments.lexers import _sql_builtins from pygments.lexers import _tsql_builtins from pygments.lexers import get_lexer_by_name, ClassNotFound from pygments.token import Punctuation, Whitespace, Text, Comment, Operator, \ Keyword, Name, String, Number, Generic, Literal __all__ = ['GoogleSqlLexer', 'PostgresLexer', 'PlPgsqlLexer', 'PostgresConsoleLexer', 'PostgresExplainLexer', 'SqlLexer', 'TransactSqlLexer', 'MySqlLexer', 'SqliteConsoleLexer', 'RqlLexer'] line_re = re.compile('.*?\n') sqlite_prompt_re = re.compile(r'^(?:sqlite| ...)>(?= )') language_re = re.compile(r"\s+LANGUAGE\s+'?(\w+)'?", re.IGNORECASE) do_re = re.compile(r'\bDO\b', re.IGNORECASE) # Regular expressions for analyse_text() name_between_bracket_re = re.compile(r'\[[a-zA-Z_]\w*\]') name_between_backtick_re = re.compile(r'`[a-zA-Z_]\w*`') tsql_go_re = re.compile(r'\bgo\b', re.IGNORECASE) tsql_declare_re = re.compile(r'\bdeclare\s+@', re.IGNORECASE) tsql_variable_re = re.compile(r'@[a-zA-Z_]\w*\b') # Identifiers for analyse_text() googlesql_identifiers = ( _googlesql_builtins.functionnames + _googlesql_builtins.keywords + _googlesql_builtins.types) def language_callback(lexer, match): """Parse the content of a $-string using a lexer The lexer is chosen looking for a nearby LANGUAGE or assumed as plpgsql if inside a DO statement and no LANGUAGE has been found. """ lx = None m = language_re.match(lexer.text[match.end():match.end()+100]) if m is not None: lx = lexer._get_lexer(m.group(1)) else: m = list(language_re.finditer( lexer.text[max(0, match.start()-100):match.start()])) if m: lx = lexer._get_lexer(m[-1].group(1)) else: m = list(do_re.finditer( lexer.text[max(0, match.start()-25):match.start()])) if m: lx = lexer._get_lexer('plpgsql') # 1 = $, 2 = delimiter, 3 = $ yield (match.start(1), String, match.group(1)) yield (match.start(2), String.Delimiter, match.group(2)) yield (match.start(3), String, match.group(3)) # 4 = string contents if lx: yield from lx.get_tokens_unprocessed(match.group(4)) else: yield (match.start(4), String, match.group(4)) # 5 = $, 6 = delimiter, 7 = $ yield (match.start(5), String, match.group(5)) yield (match.start(6), String.Delimiter, match.group(6)) yield (match.start(7), String, match.group(7)) class PostgresBase: """Base class for Postgres-related lexers. This is implemented as a mixin to avoid the Lexer metaclass kicking in. this way the different lexer don't have a common Lexer ancestor. If they had, _tokens could be created on this ancestor and not updated for the other classes, resulting e.g. in PL/pgSQL parsed as SQL. This shortcoming seem to suggest that regexp lexers are not really subclassable. """ def get_tokens_unprocessed(self, text, *args): # Have a copy of the entire text to be used by `language_callback`. self.text = text yield from super().get_tokens_unprocessed(text, *args) def _get_lexer(self, lang): if lang.lower() == 'sql': return get_lexer_by_name('postgresql', **self.options) tries = [lang] if lang.startswith('pl'): tries.append(lang[2:]) if lang.endswith('u'): tries.append(lang[:-1]) if lang.startswith('pl') and lang.endswith('u'): tries.append(lang[2:-1]) for lx in tries: try: return get_lexer_by_name(lx, **self.options) except ClassNotFound: pass else: # TODO: better logging # print >>sys.stderr, "language not found:", lang return None class PostgresLexer(PostgresBase, RegexLexer): """ Lexer for the PostgreSQL dialect of SQL. """ name = 'PostgreSQL SQL dialect' aliases = ['postgresql', 'postgres'] mimetypes = ['text/x-postgresql'] url = 'https://www.postgresql.org' version_added = '1.5' flags = re.IGNORECASE tokens = { 'root': [ (r'\s+', Whitespace), (r'--.*\n?', Comment.Single), (r'/\*', Comment.Multiline, 'multiline-comments'), (r'(' + '|'.join(s.replace(" ", r"\s+") for s in _postgres_builtins.DATATYPES + _postgres_builtins.PSEUDO_TYPES) + r')\b', Name.Builtin), (words(_postgres_builtins.KEYWORDS, suffix=r'\b'), Keyword), (r'[+*/<>=~!@#%^&|`?-]+', Operator), (r'::', Operator), # cast (r'\$\d+', Name.Variable), (r'([0-9]*\.[0-9]*|[0-9]+)(e[+-]?[0-9]+)?', Number.Float), (r'[0-9]+', Number.Integer), (r"((?:E|U&)?)(')", bygroups(String.Affix, String.Single), 'string'), # quoted identifier (r'((?:U&)?)(")', bygroups(String.Affix, String.Name), 'quoted-ident'), (r'(?s)(\$)([^$]*)(\$)(.*?)(\$)(\2)(\$)', language_callback), (r'[a-z_]\w*', Name), # psql variable in SQL (r""":(['"]?)[a-z]\w*\b\1""", Name.Variable), (r'[;:()\[\]{},.]', Punctuation), ], 'multiline-comments': [ (r'/\*', Comment.Multiline, 'multiline-comments'), (r'\*/', Comment.Multiline, '#pop'), (r'[^/*]+', Comment.Multiline), (r'[/*]', Comment.Multiline) ], 'string': [ (r"[^']+", String.Single), (r"''", String.Single), (r"'", String.Single, '#pop'), ], 'quoted-ident': [ (r'[^"]+', String.Name), (r'""', String.Name), (r'"', String.Name, '#pop'), ], } class PlPgsqlLexer(PostgresBase, RegexLexer): """ Handle the extra syntax in Pl/pgSQL language. """ name = 'PL/pgSQL' aliases = ['plpgsql'] mimetypes = ['text/x-plpgsql'] url = 'https://www.postgresql.org/docs/current/plpgsql.html' version_added = '1.5' flags = re.IGNORECASE # FIXME: use inheritance tokens = {name: state[:] for (name, state) in PostgresLexer.tokens.items()} # extend the keywords list for i, pattern in enumerate(tokens['root']): if pattern[1] == Keyword: tokens['root'][i] = ( words(_postgres_builtins.KEYWORDS + _postgres_builtins.PLPGSQL_KEYWORDS, suffix=r'\b'), Keyword) del i break else: assert 0, "SQL keywords not found" # Add specific PL/pgSQL rules (before the SQL ones) tokens['root'][:0] = [ (r'\%[a-z]\w*\b', Name.Builtin), # actually, a datatype (r':=', Operator), (r'\<\<[a-z]\w*\>\>', Name.Label), (r'\#[a-z]\w*\b', Keyword.Pseudo), # #variable_conflict ] class PsqlRegexLexer(PostgresBase, RegexLexer): """ Extend the PostgresLexer adding support specific for psql commands. This is not a complete psql lexer yet as it lacks prompt support and output rendering. """ name = 'PostgreSQL console - regexp based lexer' aliases = [] # not public flags = re.IGNORECASE tokens = {name: state[:] for (name, state) in PostgresLexer.tokens.items()} tokens['root'].append( (r'\\[^\s]+', Keyword.Pseudo, 'psql-command')) tokens['psql-command'] = [ (r'\n', Text, 'root'), (r'\s+', Whitespace), (r'\\[^\s]+', Keyword.Pseudo), (r""":(['"]?)[a-z]\w*\b\1""", Name.Variable), (r"'(''|[^'])*'", String.Single), (r"`([^`])*`", String.Backtick), (r"[^\s]+", String.Symbol), ] re_prompt = re.compile(r'^(\S.*?)??[=\-\(\$\'\"][#>]') re_psql_command = re.compile(r'\s*\\') re_end_command = re.compile(r';\s*(--.*?)?$') re_psql_command = re.compile(r'(\s*)(\\.+?)(\s+)$') re_error = re.compile(r'(ERROR|FATAL):') re_message = re.compile( r'((?:DEBUG|INFO|NOTICE|WARNING|ERROR|' r'FATAL|HINT|DETAIL|CONTEXT|LINE [0-9]+):)(.*?\n)') class lookahead: """Wrap an iterator and allow pushing back an item.""" def __init__(self, x): self.iter = iter(x) self._nextitem = None def __iter__(self): return self def send(self, i): self._nextitem = i return i def __next__(self): if self._nextitem is not None: ni = self._nextitem self._nextitem = None return ni return next(self.iter) next = __next__ class PostgresConsoleLexer(Lexer): """ Lexer for psql sessions. """ name = 'PostgreSQL console (psql)' aliases = ['psql', 'postgresql-console', 'postgres-console'] mimetypes = ['text/x-postgresql-psql'] url = 'https://www.postgresql.org' version_added = '1.5' _example = "psql/psql_session.txt" def get_tokens_unprocessed(self, data): sql = PsqlRegexLexer(**self.options) lines = lookahead(line_re.findall(data)) # prompt-output cycle while 1: # consume the lines of the command: start with an optional prompt # and continue until the end of command is detected curcode = '' insertions = [] for line in lines: # Identify a shell prompt in case of psql commandline example if line.startswith('$') and not curcode: lexer = get_lexer_by_name('console', **self.options) yield from lexer.get_tokens_unprocessed(line) break # Identify a psql prompt mprompt = re_prompt.match(line) if mprompt is not None: insertions.append((len(curcode), [(0, Generic.Prompt, mprompt.group())])) curcode += line[len(mprompt.group()):] else: curcode += line # Check if this is the end of the command # TODO: better handle multiline comments at the end with # a lexer with an external state? if re_psql_command.match(curcode) \ or re_end_command.search(curcode): break # Emit the combined stream of command and prompt(s) yield from do_insertions(insertions, sql.get_tokens_unprocessed(curcode)) # Emit the output lines out_token = Generic.Output for line in lines: mprompt = re_prompt.match(line) if mprompt is not None: # push the line back to have it processed by the prompt lines.send(line) break mmsg = re_message.match(line) if mmsg is not None: if mmsg.group(1).startswith("ERROR") \ or mmsg.group(1).startswith("FATAL"): out_token = Generic.Error yield (mmsg.start(1), Generic.Strong, mmsg.group(1)) yield (mmsg.start(2), out_token, mmsg.group(2)) else: yield (0, out_token, line) else: return class PostgresExplainLexer(RegexLexer): """ Handle PostgreSQL EXPLAIN output """ name = 'PostgreSQL EXPLAIN dialect' aliases = ['postgres-explain'] filenames = ['*.explain'] mimetypes = ['text/x-postgresql-explain'] url = 'https://www.postgresql.org/docs/current/using-explain.html' version_added = '2.15' tokens = { 'root': [ (r'(:|\(|\)|ms|kB|->|\.\.|\,|\/)', Punctuation), (r'(\s+)', Whitespace), # This match estimated cost and effectively measured counters with ANALYZE # Then, we move to instrumentation state (r'(cost)(=?)', bygroups(Name.Class, Punctuation), 'instrumentation'), (r'(actual)( )(=?)', bygroups(Name.Class, Whitespace, Punctuation), 'instrumentation'), # Misc keywords (words(('actual', 'Memory Usage', 'Disk Usage', 'Memory', 'Buckets', 'Batches', 'originally', 'row', 'rows', 'Hits', 'Misses', 'Evictions', 'Overflows', 'Planned Partitions'), suffix=r'\b'), Comment.Single), (r'(hit|read|dirtied|written|write|time|calls)(=)', bygroups(Comment.Single, Operator)), (r'(shared|temp|local)', Keyword.Pseudo), # We move to sort state in order to emphasize specific keywords (especially disk access) (r'(Sort Method)(: )', bygroups(Comment.Preproc, Punctuation), 'sort'), # These keywords can be followed by an object, like a table (r'(Sort Key|Group Key|Presorted Key|Hash Key)(:)( )', bygroups(Comment.Preproc, Punctuation, Whitespace), 'object_name'), (r'(Cache Key|Cache Mode)(:)( )', bygroups(Comment, Punctuation, Whitespace), 'object_name'), # These keywords can be followed by a predicate (words(('Join Filter', 'Subplans Removed', 'Filter', 'Merge Cond', 'Hash Cond', 'Index Cond', 'Recheck Cond', 'Heap Blocks', 'TID Cond', 'Run Condition', 'Order By', 'Function Call', 'Table Function Call', 'Inner Unique', 'Params Evaluated', 'Single Copy', 'Sampling', 'One-Time Filter', 'Output', 'Relations', 'Remote SQL'), suffix=r'\b'), Comment.Preproc, 'predicate'), # Special keyword to handle ON CONFLICT (r'Conflict ', Comment.Preproc, 'conflict'), # Special keyword for InitPlan or SubPlan (r'(InitPlan|SubPlan)( )(\d+)( )', bygroups(Keyword, Whitespace, Number.Integer, Whitespace), 'init_plan'), (words(('Sort Method', 'Join Filter', 'Planning time', 'Planning Time', 'Execution time', 'Execution Time', 'Workers Planned', 'Workers Launched', 'Buffers', 'Planning', 'Worker', 'Query Identifier', 'Time', 'Full-sort Groups', 'Pre-sorted Groups'), suffix=r'\b'), Comment.Preproc), # Emphasize these keywords (words(('Rows Removed by Join Filter', 'Rows Removed by Filter', 'Rows Removed by Index Recheck', 'Heap Fetches', 'never executed'), suffix=r'\b'), Name.Exception), (r'(I/O Timings)(:)( )', bygroups(Name.Exception, Punctuation, Whitespace)), (words(_postgres_builtins.EXPLAIN_KEYWORDS, suffix=r'\b'), Keyword), # join keywords (r'((Right|Left|Full|Semi|Anti) Join)', Keyword.Type), (r'(Parallel |Async |Finalize |Partial )', Comment.Preproc), (r'Backward', Comment.Preproc), (r'(Intersect|Except|Hash)', Comment.Preproc), (r'(CTE)( )(\w*)?', bygroups(Comment, Whitespace, Name.Variable)), # Treat "on" and "using" as a punctuation (r'(on|using)', Punctuation, 'object_name'), # strings (r"'(''|[^'])*'", String.Single), # numbers (r'-?\d+\.\d+', Number.Float), (r'(-?\d+)', Number.Integer), # boolean (r'(true|false)', Name.Constant), # explain header (r'\s*QUERY PLAN\s*\n\s*-+', Comment.Single), # Settings (r'(Settings)(:)( )', bygroups(Comment.Preproc, Punctuation, Whitespace), 'setting'), # Handle JIT counters (r'(JIT|Functions|Options|Timing)(:)', bygroups(Comment.Preproc, Punctuation)), (r'(Inlining|Optimization|Expressions|Deforming|Generation|Emission|Total)', Keyword.Pseudo), # Handle Triggers counters (r'(Trigger)( )(\S*)(:)( )', bygroups(Comment.Preproc, Whitespace, Name.Variable, Punctuation, Whitespace)), ], 'expression': [ # matches any kind of parenthesized expression # the first opening paren is matched by the 'caller' (r'\(', Punctuation, '#push'), (r'\)', Punctuation, '#pop'), (r'(never executed)', Name.Exception), (r'[^)(]+', Comment), ], 'object_name': [ # This is a cost or analyze measure (r'(\(cost)(=?)', bygroups(Name.Class, Punctuation), 'instrumentation'), (r'(\(actual)( )(=?)', bygroups(Name.Class, Whitespace, Punctuation), 'instrumentation'), # if object_name is parenthesized, mark opening paren as # punctuation, call 'expression', and exit state (r'\(', Punctuation, 'expression'), (r'(on)', Punctuation), # matches possibly schema-qualified table and column names (r'\w+(\.\w+)*( USING \S+| \w+ USING \S+)', Name.Variable), (r'\"?\w+\"?(?:\.\"?\w+\"?)?', Name.Variable), (r'\'\S*\'', Name.Variable), # if we encounter a comma, another object is listed (r',\n', Punctuation, 'object_name'), (r',', Punctuation, 'object_name'), # special case: "*SELECT*" (r'"\*SELECT\*( \d+)?"(.\w+)?', Name.Variable), (r'"\*VALUES\*(_\d+)?"(.\w+)?', Name.Variable), (r'"ANY_subquery"', Name.Variable), # Variable $1 ... (r'\$\d+', Name.Variable), # cast (r'::\w+', Name.Variable), (r' +', Whitespace), (r'"', Punctuation), (r'\[\.\.\.\]', Punctuation), (r'\)', Punctuation, '#pop'), ], 'predicate': [ # if predicate is parenthesized, mark paren as punctuation (r'(\()([^\n]*)(\))', bygroups(Punctuation, Name.Variable, Punctuation), '#pop'), # otherwise color until newline (r'[^\n]*', Name.Variable, '#pop'), ], 'instrumentation': [ (r'=|\.\.', Punctuation), (r' +', Whitespace), (r'(rows|width|time|loops)', Name.Class), (r'\d+\.\d+', Number.Float), (r'(\d+)', Number.Integer), (r'\)', Punctuation, '#pop'), ], 'conflict': [ (r'(Resolution: )(\w+)', bygroups(Comment.Preproc, Name.Variable)), (r'(Arbiter \w+:)', Comment.Preproc, 'object_name'), (r'(Filter: )', Comment.Preproc, 'predicate'), ], 'setting': [ (r'([a-z_]*?)(\s*)(=)(\s*)(\'.*?\')', bygroups(Name.Attribute, Whitespace, Operator, Whitespace, String)), (r'\, ', Punctuation), ], 'init_plan': [ (r'\(', Punctuation), (r'returns \$\d+(,\$\d+)?', Name.Variable), (r'\)', Punctuation, '#pop'), ], 'sort': [ (r':|kB', Punctuation), (r'(quicksort|top-N|heapsort|Average|Memory|Peak)', Comment.Prepoc), (r'(external|merge|Disk|sort)', Name.Exception), (r'(\d+)', Number.Integer), (r' +', Whitespace), ], } class SqlLexer(RegexLexer): """ Lexer for Structured Query Language. Currently, this lexer does not recognize any special syntax except ANSI SQL. """ name = 'SQL' aliases = ['sql'] filenames = ['*.sql'] mimetypes = ['text/x-sql'] url = 'https://en.wikipedia.org/wiki/SQL' version_added = '' flags = re.IGNORECASE tokens = { 'root': [ (r'\s+', Whitespace), (r'--.*\n?', Comment.Single), (r'/\*', Comment.Multiline, 'multiline-comments'), (words(_sql_builtins.KEYWORDS, suffix=r'\b'), Keyword), (words(_sql_builtins.DATATYPES, suffix=r'\b'), Name.Builtin), (r'[+*/<>=~!@#%^&|`?-]', Operator), (r'[0-9]+', Number.Integer), # TODO: Backslash escapes? (r"'(''|[^'])*'", String.Single), (r'"(""|[^"])*"', String.Symbol), # not a real string literal in ANSI SQL (r'[a-z_][\w$]*', Name), # allow $s in strings for Oracle (r'[;:()\[\],.]', Punctuation) ], 'multiline-comments': [ (r'/\*', Comment.Multiline, 'multiline-comments'), (r'\*/', Comment.Multiline, '#pop'), (r'[^/*]+', Comment.Multiline), (r'[/*]', Comment.Multiline) ] } def analyse_text(self, text): return 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'] url = 'https://www.tsql.info' version_added = '' flags = re.IGNORECASE tokens = { 'root': [ (r'\s+', Whitespace), (r'--.*[$|\n]?', Comment.Single), (r'/\*', Comment.Multiline, 'multiline-comments'), (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), # Float variant 1, for example: 1., 1.e2, 1.2e3 (r'[0-9]+\.[0-9]*(e[+-]?[0-9]+)?', Number.Float), # Float variant 2, for example: .1, .1e2 (r'\.[0-9]+(e[+-]?[0-9]+)?', Number.Float), # Float variant 3, for example: 123e45 (r'[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), # names for temp tables and anything else (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) ] } def analyse_text(text): rating = 0 if tsql_declare_re.search(text): # Found T-SQL variable declaration. rating = 1.0 else: name_between_backtick_count = len( name_between_backtick_re.findall(text)) name_between_bracket_count = len( name_between_bracket_re.findall(text)) # We need to check if there are any names using # backticks or brackets, as otherwise both are 0 # and 0 >= 2 * 0, so we would always assume it's true dialect_name_count = name_between_backtick_count + name_between_bracket_count if dialect_name_count >= 1 and \ name_between_bracket_count >= 2 * name_between_backtick_count: # Found at least twice as many [name] as `name`. rating += 0.5 elif name_between_bracket_count > name_between_backtick_count: rating += 0.2 elif name_between_bracket_count > 0: rating += 0.1 if tsql_variable_re.search(text) is not None: rating += 0.1 if tsql_go_re.search(text) is not None: rating += 0.1 return rating class MySqlLexer(RegexLexer): """The Oracle MySQL lexer. This lexer does not attempt to maintain strict compatibility with MariaDB syntax or keywords. Although MySQL and MariaDB's common code history suggests there may be significant overlap between the two, compatibility between the two is not a target for this lexer. """ name = 'MySQL' aliases = ['mysql'] mimetypes = ['text/x-mysql'] url = 'https://www.mysql.com' version_added = '' flags = re.IGNORECASE tokens = { 'root': [ (r'\s+', Whitespace), # Comments (r'(?:#|--\s+).*', Comment.Single), (r'/\*\+', Comment.Special, 'optimizer-hints'), (r'/\*', Comment.Multiline, 'multiline-comment'), # Hexadecimal literals (r"x'([0-9a-f]{2})+'", Number.Hex), # MySQL requires paired hex characters in this form. (r'0x[0-9a-f]+', Number.Hex), # Binary literals (r"b'[01]+'", Number.Bin), (r'0b[01]+', Number.Bin), # Numeric literals (r'[0-9]+\.[0-9]*(e[+-]?[0-9]+)?', Number.Float), # Mandatory integer, optional fraction and exponent (r'[0-9]*\.[0-9]+(e[+-]?[0-9]+)?', Number.Float), # Mandatory fraction, optional integer and exponent (r'[0-9]+e[+-]?[0-9]+', Number.Float), # Exponents with integer significands are still floats (r'[0-9]+(?=[^0-9a-z$_\u0080-\uffff])', Number.Integer), # Integers that are not in a schema object name # Date literals (r"\{\s*d\s*(?P<quote>['\"])\s*\d{2}(\d{2})?.?\d{2}.?\d{2}\s*(?P=quote)\s*\}", Literal.Date), # Time literals (r"\{\s*t\s*(?P<quote>['\"])\s*(?:\d+\s+)?\d{1,2}.?\d{1,2}.?\d{1,2}(\.\d*)?\s*(?P=quote)\s*\}", Literal.Date), # Timestamp literals ( r"\{\s*ts\s*(?P<quote>['\"])\s*" r"\d{2}(?:\d{2})?.?\d{2}.?\d{2}" # Date part r"\s+" # Whitespace between date and time r"\d{1,2}.?\d{1,2}.?\d{1,2}(\.\d*)?" # Time part r"\s*(?P=quote)\s*\}", Literal.Date ), # String literals (r"'", String.Single, 'single-quoted-string'), (r'"', String.Double, 'double-quoted-string'), # Variables (r'@@(?:global\.|persist\.|persist_only\.|session\.)?[a-z_]+', Name.Variable), (r'@[a-z0-9_$.]+', Name.Variable), (r"@'", Name.Variable, 'single-quoted-variable'), (r'@"', Name.Variable, 'double-quoted-variable'), (r"@`", Name.Variable, 'backtick-quoted-variable'), (r'\?', Name.Variable), # For demonstrating prepared statements # Operators (r'[!%&*+/:<=>^|~-]+', Operator), # Exceptions; these words tokenize differently in different contexts. (r'\b(set)(?!\s*\()', Keyword), (r'\b(character)(\s+)(set)\b', bygroups(Keyword, Whitespace, Keyword)), # In all other known cases, "SET" is tokenized by MYSQL_DATATYPES. (words(_mysql_builtins.MYSQL_CONSTANTS, prefix=r'\b', suffix=r'\b'), Name.Constant), (words(_mysql_builtins.MYSQL_DATATYPES, prefix=r'\b', suffix=r'\b'), Keyword.Type), (words(_mysql_builtins.MYSQL_KEYWORDS, prefix=r'\b', suffix=r'\b'), Keyword), (words(_mysql_builtins.MYSQL_FUNCTIONS, prefix=r'\b', suffix=r'\b(\s*)(\()'), bygroups(Name.Function, Whitespace, Punctuation)), # Schema object names # # Note: Although the first regex supports unquoted all-numeric # identifiers, this will not be a problem in practice because # numeric literals have already been handled above. # ('[0-9a-z$_\u0080-\uffff]+', Name), (r'`', Name.Quoted, 'schema-object-name'), # Punctuation (r'[(),.;]', Punctuation), ], # Multiline comment substates # --------------------------- 'optimizer-hints': [ (r'[^*a-z]+', Comment.Special), (r'\*/', Comment.Special, '#pop'), (words(_mysql_builtins.MYSQL_OPTIMIZER_HINTS, suffix=r'\b'), Comment.Preproc), ('[a-z]+', Comment.Special), (r'\*', Comment.Special), ], 'multiline-comment': [ (r'[^*]+', Comment.Multiline), (r'\*/', Comment.Multiline, '#pop'), (r'\*', Comment.Multiline), ], # String substates # ---------------- 'single-quoted-string': [ (r"[^'\\]+", String.Single), (r"''", String.Escape), (r"""\\[0'"bnrtZ\\%_]""", String.Escape), (r"'", String.Single, '#pop'), ], 'double-quoted-string': [ (r'[^"\\]+', String.Double), (r'""', String.Escape), (r"""\\[0'"bnrtZ\\%_]""", String.Escape), (r'"', String.Double, '#pop'), ], # Variable substates # ------------------ 'single-quoted-variable': [ (r"[^']+", Name.Variable), (r"''", Name.Variable), (r"'", Name.Variable, '#pop'), ], 'double-quoted-variable': [ (r'[^"]+', Name.Variable), (r'""', Name.Variable), (r'"', Name.Variable, '#pop'), ], 'backtick-quoted-variable': [ (r'[^`]+', Name.Variable), (r'``', Name.Variable), (r'`', Name.Variable, '#pop'), ], # Schema object name substates # ---------------------------- # # "Name.Quoted" and "Name.Quoted.Escape" are non-standard but # formatters will style them as "Name" by default but add # additional styles based on the token name. This gives users # flexibility to add custom styles as desired. # 'schema-object-name': [ (r'[^`]+', Name.Quoted), (r'``', Name.Quoted.Escape), (r'`', Name.Quoted, '#pop'), ], } def analyse_text(text): rating = 0 name_between_backtick_count = len( name_between_backtick_re.findall(text)) name_between_bracket_count = len( name_between_bracket_re.findall(text)) # Same logic as above in the TSQL analysis dialect_name_count = name_between_backtick_count + name_between_bracket_count if dialect_name_count >= 1 and \ name_between_backtick_count >= 2 * name_between_bracket_count: # Found at least twice as many `name` as [name]. rating += 0.5 elif name_between_backtick_count > name_between_bracket_count: rating += 0.2 elif name_between_backtick_count > 0: rating += 0.1 return rating class GoogleSqlLexer(RegexLexer): """ GoogleSQL is Google's standard SQL dialect, formerly known as ZetaSQL. The list of keywords includes reserved words for future use. """ name = 'GoogleSQL' aliases = ['googlesql', 'zetasql'] filenames = ['*.googlesql', '*.googlesql.sql'] mimetypes = ['text/x-google-sql', 'text/x-google-sql-aux'] url = 'https://cloud.google.com/bigquery/googlesql' version_added = '2.19' flags = re.IGNORECASE tokens = { 'root': [ (r'\s+', Whitespace), # Comments (r'(?:#|--\s+).*', Comment.Single), (r'/\*', Comment.Multiline, 'multiline-comment'), # Hexadecimal literals (r"x'([0-9a-f]{2})+'", Number.Hex), (r'0x[0-9a-f]+', Number.Hex), # Binary literals (r"b'[01]+'", Number.Bin), (r'0b[01]+', Number.Bin), # Numeric literals (r'[0-9]+\.[0-9]*(e[+-]?[0-9]+)?', Number.Float), # Mandatory integer, optional fraction and exponent (r'[0-9]*\.[0-9]+(e[+-]?[0-9]+)?', Number.Float), # Mandatory fraction, optional integer and exponent (r'[0-9]+e[+-]?[0-9]+', Number.Float), # Exponents with integer significands are still floats (r'[0-9]+(?=[^0-9a-z$_\u0080-\uffff])', Number.Integer), # Integers that are not in a schema object name # Date literals (r"\{\s*d\s*(?P<quote>['\"])\s*\d{2}(\d{2})?.?\d{2}.?\d{2}\s*(?P=quote)\s*\}", Literal.Date), # Time literals (r"\{\s*t\s*(?P<quote>['\"])\s*(?:\d+\s+)?\d{1,2}.?\d{1,2}.?\d{1,2}(\.\d*)?\s*(?P=quote)\s*\}", Literal.Date), # Timestamp literals ( r"\{\s*ts\s*(?P<quote>['\"])\s*" r"\d{2}(?:\d{2})?.?\d{2}.?\d{2}" # Date part r"\s+" # Whitespace between date and time r"\d{1,2}.?\d{1,2}.?\d{1,2}(\.\d*)?" # Time part r"\s*(?P=quote)\s*\}", Literal.Date ), # String literals (r"'", String.Single, 'single-quoted-string'), (r'"', String.Double, 'double-quoted-string'), # Variables (r'@@(?:global\.|persist\.|persist_only\.|session\.)?[a-z_]+', Name.Variable), (r'@[a-z0-9_$.]+', Name.Variable), (r"@'", Name.Variable, 'single-quoted-variable'), (r'@"', Name.Variable, 'double-quoted-variable'), (r"@`", Name.Variable, 'backtick-quoted-variable'), (r'\?', Name.Variable), # For demonstrating prepared statements # Exceptions; these words tokenize differently in different contexts. (r'\b(set)(?!\s*\()', Keyword), (r'\b(character)(\s+)(set)\b', bygroups(Keyword, Whitespace, Keyword)), # Constants, types, keywords, functions, operators (words(_googlesql_builtins.constants, prefix=r'\b', suffix=r'\b'), Name.Constant), (words(_googlesql_builtins.types, prefix=r'\b', suffix=r'\b'), Keyword.Type), (words(_googlesql_builtins.keywords, prefix=r'\b', suffix=r'\b'), Keyword), (words(_googlesql_builtins.functionnames, prefix=r'\b', suffix=r'\b(\s*)(\()'), bygroups(Name.Function, Whitespace, Punctuation)), (words(_googlesql_builtins.operators, prefix=r'\b', suffix=r'\b'), Operator), # Schema object names # # Note: Although the first regex supports unquoted all-numeric # identifiers, this will not be a problem in practice because # numeric literals have already been handled above. # ('[0-9a-z$_\u0080-\uffff]+', Name), (r'`', Name.Quoted, 'schema-object-name'), # Punctuation (r'[(),.;]', Punctuation), ], # Multiline comment substates # --------------------------- 'multiline-comment': [ (r'[^*]+', Comment.Multiline), (r'\*/', Comment.Multiline, '#pop'), (r'\*', Comment.Multiline), ], # String substates # ---------------- 'single-quoted-string': [ (r"[^'\\]+", String.Single), (r"''", String.Escape), (r"""\\[0'"bnrtZ\\%_]""", String.Escape), (r"'", String.Single, '#pop'), ], 'double-quoted-string': [ (r'[^"\\]+', String.Double), (r'""', String.Escape), (r"""\\[0'"bnrtZ\\%_]""", String.Escape), (r'"', String.Double, '#pop'), ], # Variable substates # ------------------ 'single-quoted-variable': [ (r"[^']+", Name.Variable), (r"''", Name.Variable), (r"'", Name.Variable, '#pop'), ], 'double-quoted-variable': [ (r'[^"]+', Name.Variable), (r'""', Name.Variable), (r'"', Name.Variable, '#pop'), ], 'backtick-quoted-variable': [ (r'[^`]+', Name.Variable), (r'``', Name.Variable), (r'`', Name.Variable, '#pop'), ], # Schema object name substates # ---------------------------- # # "Name.Quoted" and "Name.Quoted.Escape" are non-standard but # formatters will style them as "Name" by default but add # additional styles based on the token name. This gives users # flexibility to add custom styles as desired. # 'schema-object-name': [ (r'[^`]+', Name.Quoted), (r'``', Name.Quoted.Escape), (r'`', Name.Quoted, '#pop'), ], } def analyse_text(text): tokens = collections.Counter(text.split()) return 0.001 * sum(count for t, count in tokens.items() if t in googlesql_identifiers) class SqliteConsoleLexer(Lexer): """ Lexer for example sessions using sqlite3. """ name = 'sqlite3con' aliases = ['sqlite3'] filenames = ['*.sqlite3-console'] mimetypes = ['text/x-sqlite3-console'] url = 'https://www.sqlite.org' version_added = '0.11' _example = "sqlite3/sqlite3.sqlite3-console" def get_tokens_unprocessed(self, data): sql = SqlLexer(**self.options) curcode = '' insertions = [] for match in line_re.finditer(data): line = match.group() prompt_match = sqlite_prompt_re.match(line) if prompt_match is not None: insertions.append((len(curcode), [(0, Generic.Prompt, line[:7])])) insertions.append((len(curcode), [(7, Whitespace, ' ')])) curcode += line[8:] else: if curcode: yield from do_insertions(insertions, sql.get_tokens_unprocessed(curcode)) curcode = '' insertions = [] if line.startswith('SQL error: '): yield (match.start(), Generic.Traceback, line) else: yield (match.start(), Generic.Output, line) if curcode: yield from do_insertions(insertions, sql.get_tokens_unprocessed(curcode)) class RqlLexer(RegexLexer): """ Lexer for Relation Query Language. """ name = 'RQL' url = 'http://www.logilab.org/project/rql' aliases = ['rql'] filenames = ['*.rql'] mimetypes = ['text/x-rql'] version_added = '2.0' flags = re.IGNORECASE tokens = { 'root': [ (r'\s+', Whitespace), (r'(DELETE|SET|INSERT|UNION|DISTINCT|WITH|WHERE|BEING|OR' r'|AND|NOT|GROUPBY|HAVING|ORDERBY|ASC|DESC|LIMIT|OFFSET' r'|TODAY|NOW|TRUE|FALSE|NULL|EXISTS)\b', Keyword), (r'[+*/<>=%-]', Operator), (r'(Any|is|instance_of|CWEType|CWRelation)\b', Name.Builtin), (r'[0-9]+', Number.Integer), (r'[A-Z_]\w*\??', Name), (r"'(''|[^'])*'", String.Single), (r'"(""|[^"])*"', String.Single), (r'[;:()\[\],.]', Punctuation) ], }
Save
cmd:
run