go/chroma
1
0
Fork 0
mirror of https://github.com/alecthomas/chroma.git synced 2025-10-30 23:57:49 +02:00
Code Issues Releases Activity

refactor: migrate a bunch more Go-based lexers to XML

Browse Source 
Also rename some existing XML lexers to their canonical XML name.
This commit is contained in:
Alec Thomas
2023-09-09 12:29:23 +10:00
parent 4dd2cbef84
commit 40542a6255
63 changed files with 2963 additions and 1343 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
.gitignore vendored
View File

@@ -22,3 +22,4 @@ _models/
_examples/
*.min.*
build/

4
Bitfile
View File

@@ -12,10 +12,10 @@ README.md: lexers/*.go lexers/*/*.xml table.py
implicit %{1}%{2}.min.%{3}: **/*.{css,js}
build: esbuild --bundle %{IN} --minify --outfile=%{OUT}
implicit %{1}: cmd/*
implicit build/%{1}: cmd/*
cd cmd/%{1}
inputs: cmd/%{1}/**/* **/*.go
build: go build -ldflags="-X 'main.version=%{VERSION}'" -o ../../%{1} .
build: go build -ldflags="-X 'main.version=%{VERSION}'" -o ../../build/%{1} .
#upload: chromad
# build:

202
_tools/pygments2chroma.py
View File

@@ -1,202 +0,0 @@
import functools
import importlib
import json
import os
import re
import sys
import types
import pystache
from pygments import lexer as pygments_lexer
from pygments.token import _TokenType
TEMPLATE = r'''
package {{package}}
import (
. "github.com/alecthomas/chroma/v2" // nolint
"github.com/alecthomas/chroma/v2/lexers/internal"
)
// {{upper_name}} lexer.
var {{upper_name}} = internal.Register(MustNewLazyLexer(
&Config{
Name: "{{name}}",
{{=<% %>=}}
Aliases: []string{<%#aliases%>"<%.%>", <%/aliases%>},
Filenames: []string{<%#filenames%>"<%.%>", <%/filenames%>},
MimeTypes: []string{<%#mimetypes%>"<%.%>", <%/mimetypes%>},
<%={{ }}=%>
{{#re_not_multiline}}
NotMultiline: true,
{{/re_not_multiline}}
{{#re_dotall}}
DotAll: true,
{{/re_dotall}}
{{#re_ignorecase}}
CaseInsensitive: true,
{{/re_ignorecase}}
},
func() Rules {
return Rules{
{{#tokens}}
"{{state}}": {
{{#rules}}
{{{.}}},
{{/rules}}
},
{{/tokens}}
}
},
))
'''
def go_regex(s):
return go_string(s)
def go_string(s):
if '`' not in s:
return '`' + s + '`'
return json.dumps(s)
def to_camel_case(snake_str):
components = snake_str.split('_')
return ''.join(x.title() for x in components)
def warning(message):
print('warning: ' + message, file=sys.stderr)
def resolve_emitter(emitter):
if isinstance(emitter, types.FunctionType):
if repr(emitter).startswith('<function bygroups.'):
args = emitter.__closure__[0].cell_contents
emitter = 'ByGroups(%s)' % ', '.join(resolve_emitter(e) for e in args)
elif repr(emitter).startswith('<function using.'):
args = emitter.__closure__[0].cell_contents
if isinstance(args, dict):
state = 'root'
if 'stack' in args:
state = args['stack'][1]
args.pop('stack')
assert args == {}, args
emitter = 'UsingSelf("%s")' % state
elif issubclass(args, pygments_lexer.Lexer):
name = args.__name__
if name.endswith('Lexer'):
name = name[:-5]
emitter = 'Using(%s)' % name
else:
raise ValueError('only support "using" with lexer classes, not %r' % args)
else:
warning('unsupported emitter function %r' % emitter)
emitter = '?? %r ??' % emitter
elif isinstance(emitter, _TokenType):
emitter = str(emitter).replace('.', '')[5:]
elif emitter is None:
# This generally only occurs when a lookahead/behind assertion is used, so we just allow it
# through.
return 'None'
else:
raise ValueError('unsupported emitter type %r' % emitter)
assert isinstance(emitter, str)
return emitter
def process_state_action(action):
if isinstance(action, tuple):
return functools.reduce(lambda a, b: a + b, (process_state_action(a) for a in action))
if action.startswith('#'):
action = action[1:]
if action== 'pop':
action = 'Pop(1)'
elif action.startswith('pop:'):
action = 'Pop(%s)' % action[4:]
elif action == 'push':
action = 'Push()'
elif action.startswith('push:'):
action = 'Push("%s")' % action[5:]
else:
raise ValueError('unsupported action %r' % (action,))
else:
action = 'Push("%s")' % action
return (action,)
def translate_rules(rules):
out = []
for rule in rules:
if isinstance(rule, tuple):
regex = rule[0]
if isinstance(regex, str):
regex = go_regex(regex)
elif isinstance(regex, pygments_lexer.words):
regex = 'Words(%s, %s, %s)' % (go_string(regex.prefix),
go_string(regex.suffix),
', '.join(go_string(w) for w in regex.words))
else:
raise ValueError('expected regex string but got %r' % regex)
emitter = resolve_emitter(rule[1])
if len(rule) == 2:
modifier = 'nil'
elif type(rule[2]) is str:
modifier = process_state_action(rule[2])[0]
elif isinstance(rule[2], pygments_lexer.combined):
modifier = 'Combined("%s")' % '", "'.join(rule[2])
elif type(rule[2]) is tuple:
modifier = 'Push("%s")' % '", "'.join(rule[2])
else:
raise ValueError('unsupported modifier %r' % (rule[2],))
out.append('{{{}, {}, {}}}'.format(regex, emitter, modifier))
elif isinstance(rule, pygments_lexer.include):
out.append('Include("{}")'.format(rule))
elif isinstance(rule, pygments_lexer.default):
out.append('Default({})'.format(', '.join(process_state_action(rule.state))))
else:
raise ValueError('unsupported rule %r' % (rule,))
return out
class TemplateView(object):
def __init__(self, **kwargs):
for key, value in kwargs.items():
setattr(self, key, value)
def re_not_multiline(self):
return not (self.regex_flags & re.MULTILINE)
def re_dotall(self):
return self.regex_flags & re.DOTALL
def re_ignorecase(self):
return self.regex_flags & re.IGNORECASE
def main():
package_name, symbol_name = sys.argv[1].rsplit(sep=".", maxsplit=1)
package = importlib.import_module(package_name)
lexer_cls = getattr(package, symbol_name)
assert issubclass(lexer_cls, pygments_lexer.RegexLexer), 'can only translate from RegexLexer'
print(pystache.render(TEMPLATE, TemplateView(
package=lexer_cls.name.lower()[0],
name=lexer_cls.name,
regex_flags=lexer_cls.flags,
upper_name=to_camel_case(re.sub(r'\W', '_', lexer_cls.name)),
aliases=lexer_cls.aliases,
filenames=lexer_cls.filenames,
mimetypes=lexer_cls.mimetypes,
tokens=[{'state': state, 'rules': translate_rules(rules)} for (state, rules) in lexer_cls.get_tokendefs().items()],
)))
if __name__ == '__main__':
main()

1
bin/.watchexec-1.23.0.pkg Symbolic link
View File

@@ -0,0 +1 @@
hermit

1
bin/watchexec Symbolic link
View File

@@ -0,0 +1 @@
.watchexec-1.23.0.pkg

5
cmd/chroma/main.go
View File

@@ -413,9 +413,10 @@ func dumpXMLLexerDefinitions(dir string) error {
// fmt.Println(name)
_, err = os.Stat(filename)
if err == nil {
return fmt.Errorf("%s already exists", filename)
fmt.Fprintf(os.Stderr, "warning: %s already exists\n", filename)
continue
}
err = ioutil.WriteFile(filename, data, 0600)
err = os.WriteFile(filename, data, 0600)
if err != nil {
return err
}

4
lexer.go
View File

@@ -69,8 +69,8 @@ type Config struct {
// AnalyseConfig defines the list of regexes analysers.
type AnalyseConfig struct {
Regexes []RegexConfig `xml:"regex,omitempty"`
// If true, the score is returned despite other matches.
Single bool `xml:"single,attr"`
// If true, the first matching score is returned.
First bool `xml:"first,attr"`
}
// RegexConfig defines a single regex pattern and its score in case of match.

17
lexers/bash.go
View File

@@ -1,17 +0,0 @@
package lexers
import (
"regexp"
)
// TODO(moorereason): can this be factored away?
var bashAnalyserRe = regexp.MustCompile(`(?m)^#!.*/bin/(?:env |)(?:bash|zsh|sh|ksh)`)
func init() { // nolint: gochecknoinits
Get("bash").SetAnalyser(func(text string) float32 {
if bashAnalyserRe.FindString(text) != "" {
return 1.0
}
return 0.0
})
}

62
lexers/chapel.go
View File

@@ -1,62 +0,0 @@
package lexers
import (
. "github.com/alecthomas/chroma/v2" // nolint
)
// Chapel lexer.
var Chapel = Register(MustNewLexer(
&Config{
Name: "Chapel",
Aliases: []string{"chapel", "chpl"},
Filenames: []string{"*.chpl"},
MimeTypes: []string{},
},
func() Rules {
return Rules{
"root": {
{`\n`, TextWhitespace, nil},
{`\s+`, TextWhitespace, nil},
{`\\\n`, Text, nil},
{`//(.*?)\n`, CommentSingle, nil},
{`/(\\\n)?[*](.|\n)*?[*](\\\n)?/`, CommentMultiline, nil},
{Words(``, `\b`, `config`, `const`, `in`, `inout`, `out`, `param`, `ref`, `type`, `var`), KeywordDeclaration, nil},
{Words(``, `\b`, `false`, `nil`, `none`, `true`), KeywordConstant, nil},
{Words(``, `\b`, `bool`, `bytes`, `complex`, `imag`, `int`, `locale`, `nothing`, `opaque`, `range`, `real`, `string`, `uint`, `void`), KeywordType, nil},
{Words(``, `\b`, `atomic`, `single`, `sync`, `borrowed`, `owned`, `shared`, `unmanaged`, `align`, `as`, `begin`, `break`, `by`, `catch`, `cobegin`, `coforall`, `continue`, `defer`, `delete`, `dmapped`, `do`, `domain`, `else`, `enum`, `except`, `export`, `extern`, `for`, `forall`, `foreach`, `forwarding`, `if`, `implements`, `import`, `index`, `init`, `inline`, `label`, `lambda`, `let`, `lifetime`, `local`, `new`, `noinit`, `on`, `only`, `otherwise`, `override`, `pragma`, `primitive`, `private`, `prototype`, `public`, `reduce`, `require`, `return`, `scan`, `select`, `serial`, `sparse`, `subdomain`, `then`, `this`, `throw`, `throws`, `try`, `use`, `when`, `where`, `while`, `with`, `yield`, `zip`), Keyword, nil},
{`(iter)(\s+)`, ByGroups(Keyword, TextWhitespace), Push("procname")},
{`(proc)(\s+)`, ByGroups(Keyword, TextWhitespace), Push("procname")},
{`(operator)(\s+)`, ByGroups(Keyword, TextWhitespace), Push("procname")},
{`(class|interface|module|record|union)(\s+)`, ByGroups(Keyword, TextWhitespace), Push("classname")},
{`\d+i`, LiteralNumber, nil},
{`\d+\.\d*([Ee][-+]\d+)?i`, LiteralNumber, nil},
{`\.\d+([Ee][-+]\d+)?i`, LiteralNumber, nil},
{`\d+[Ee][-+]\d+i`, LiteralNumber, nil},
{`(\d*\.\d+)([eE][+-]?[0-9]+)?i?`, LiteralNumberFloat, nil},
{`\d+[eE][+-]?[0-9]+i?`, LiteralNumberFloat, nil},
{`0[bB][01]+`, LiteralNumberBin, nil},
{`0[xX][0-9a-fA-F]+`, LiteralNumberHex, nil},
{`0[oO][0-7]+`, LiteralNumberOct, nil},
{`[0-9]+`, LiteralNumberInteger, nil},
{`"(\\\\|\\"|[^"])*"`, LiteralString, nil},
{`'(\\\\|\\'|[^'])*'`, LiteralString, nil},
{`(=|\+=|-=|\*=|/=|\*\*=|%=|&=|\|=|\^=|&&=|\|\|=|<<=|>>=|<=>|<~>|\.\.|by|#|\.\.\.|&&|\|\||!|&|\||\^|~|<<|>>|==|!=|<=|>=|<|>|[+\-*/%]|\*\*)`, Operator, nil},
{`[:;,.?()\[\]{}]`, Punctuation, nil},
{`[a-zA-Z_][\w$]*`, NameOther, nil},
},
"classname": {
{`[a-zA-Z_][\w$]*`, NameClass, Pop(1)},
},
"procname": {
{`([a-zA-Z_][.\w$]*|\~[a-zA-Z_][.\w$]*|[+*/!~%<>=&^|\-:]{1,2})`, NameFunction, Pop(1)},
{`\(`, Punctuation, Push("receivertype")},
{`\)+\.`, Punctuation, nil},
},
"receivertype": {
{Words(``, `\b`, `atomic`, `single`, `sync`, `borrowed`, `owned`, `shared`, `unmanaged`), Keyword, nil},
{Words(``, `\b`, `bool`, `bytes`, `complex`, `imag`, `int`, `locale`, `nothing`, `opaque`, `range`, `real`, `string`, `uint`, `void`), KeywordType, nil},
{`[^()]*`, NameOther, Pop(1)},
},
}
},
))

39
lexers/cheetah.go
View File

@@ -1,39 +0,0 @@
package lexers
import (
. "github.com/alecthomas/chroma/v2" // nolint
)
// Cheetah lexer.
var Cheetah = Register(MustNewLexer(
&Config{
Name: "Cheetah",
Aliases: []string{"cheetah", "spitfire"},
Filenames: []string{"*.tmpl", "*.spt"},
MimeTypes: []string{"application/x-cheetah", "application/x-spitfire"},
},
cheetahRules,
))
func cheetahRules() Rules {
return Rules{
"root": {
{`(##[^\n]*)$`, ByGroups(Comment), nil},
{`#[*](.|\n)*?[*]#`, Comment, nil},
{`#end[^#\n]*(?:#|$)`, CommentPreproc, nil},
{`#slurp$`, CommentPreproc, nil},
{`(#[a-zA-Z]+)([^#\n]*)(#|$)`, ByGroups(CommentPreproc, Using("Python"), CommentPreproc), nil},
{`(\$)([a-zA-Z_][\w.]*\w)`, ByGroups(CommentPreproc, Using("Python")), nil},
{`(\$\{!?)(.*?)(\})(?s)`, ByGroups(CommentPreproc, Using("Python"), CommentPreproc), nil},
{`(?sx)
(.+?) # anything, followed by:
(?:
(?=\#[#a-zA-Z]*) | # an eval comment
(?=\$[a-zA-Z_{]) | # a substitution
\Z # end of string
)
`, Other, nil},
{`\s+`, Text, nil},
},
}
}

70
lexers/cql.go
View File

@@ -1,70 +0,0 @@
package lexers
import (
. "github.com/alecthomas/chroma/v2" // nolint
)
// CassandraCQL lexer.
var CassandraCQL = Register(MustNewLexer(
&Config{
Name: "Cassandra CQL",
Aliases: []string{"cassandra", "cql"},
Filenames: []string{"*.cql"},
MimeTypes: []string{"text/x-cql"},
NotMultiline: true,
CaseInsensitive: true,
},
cassandraCQLRules,
))
func cassandraCQLRules() Rules {
return Rules{
"root": {
{`\s+`, TextWhitespace, nil},
{`(--|\/\/).*\n?`, CommentSingle, nil},
{`/\*`, CommentMultiline, Push("multiline-comments")},
{`(ascii|bigint|blob|boolean|counter|date|decimal|double|float|frozen|inet|int|list|map|set|smallint|text|time|timestamp|timeuuid|tinyint|tuple|uuid|varchar|varint)\b`, NameBuiltin, nil},
{Words(``, `\b`, `ADD`, `AGGREGATE`, `ALL`, `ALLOW`, `ALTER`, `AND`, `ANY`, `APPLY`, `AS`, `ASC`, `AUTHORIZE`, `BATCH`, `BEGIN`, `BY`, `CLUSTERING`, `COLUMNFAMILY`, `COMPACT`, `CONSISTENCY`, `COUNT`, `CREATE`, `CUSTOM`, `DELETE`, `DESC`, `DISTINCT`, `DROP`, `EACH_QUORUM`, `ENTRIES`, `EXISTS`, `FILTERING`, `FROM`, `FULL`, `GRANT`, `IF`, `IN`, `INDEX`, `INFINITY`, `INSERT`, `INTO`, `KEY`, `KEYS`, `KEYSPACE`, `KEYSPACES`, `LEVEL`, `LIMIT`, `LOCAL_ONE`, `LOCAL_QUORUM`, `MATERIALIZED`, `MODIFY`, `NAN`, `NORECURSIVE`, `NOSUPERUSER`, `NOT`, `OF`, `ON`, `ONE`, `ORDER`, `PARTITION`, `PASSWORD`, `PER`, `PERMISSION`, `PERMISSIONS`, `PRIMARY`, `QUORUM`, `RENAME`, `REVOKE`, `SCHEMA`, `SELECT`, `STATIC`, `STORAGE`, `SUPERUSER`, `TABLE`, `THREE`, `TO`, `TOKEN`, `TRUNCATE`, `TTL`, `TWO`, `TYPE`, `UNLOGGED`, `UPDATE`, `USE`, `USER`, `USERS`, `USING`, `VALUES`, `VIEW`, `WHERE`, `WITH`, `WRITETIME`, `REPLICATION`, `OR`, `REPLACE`, `FUNCTION`, `CALLED`, `INPUT`, `RETURNS`, `LANGUAGE`, `ROLE`, `ROLES`, `TRIGGER`, `DURABLE_WRITES`, `LOGIN`, `OPTIONS`, `LOGGED`, `SFUNC`, `STYPE`, `FINALFUNC`, `INITCOND`, `IS`, `CONTAINS`, `JSON`, `PAGING`, `OFF`), Keyword, nil},
{"[+*/<>=~!@#%^&|`?-]+", Operator, nil},
{
`(?s)(java|javascript)(\s+)(AS)(\s+)('|\$\$)(.*?)(\5)`,
UsingByGroup(1, 6,
NameBuiltin, TextWhitespace, Keyword, TextWhitespace,
LiteralStringHeredoc, LiteralStringHeredoc, LiteralStringHeredoc),
nil,
},
{`(true|false|null)\b`, KeywordConstant, nil},
{`0x[0-9a-f]+`, LiteralNumberHex, nil},
{`[0-9a-f]{8}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{12}`, LiteralNumberHex, nil},
{`\.[0-9]+(e[+-]?[0-9]+)?`, Error, nil},
{`-?[0-9]+(\.[0-9])?(e[+-]?[0-9]+)?`, LiteralNumberFloat, nil},
{`[0-9]+`, LiteralNumberInteger, nil},
{`'`, LiteralStringSingle, Push("string")},
{`"`, LiteralStringName, Push("quoted-ident")},
{`\$\$`, LiteralStringHeredoc, Push("dollar-string")},
{`[a-z_]\w*`, Name, nil},
{`:(['"]?)[a-z]\w*\b\1`, NameVariable, nil},
{`[;:()\[\]\{\},.]`, Punctuation, nil},
},
"multiline-comments": {
{`/\*`, CommentMultiline, Push("multiline-comments")},
{`\*/`, CommentMultiline, Pop(1)},
{`[^/*]+`, CommentMultiline, nil},
{`[/*]`, CommentMultiline, nil},
},
"string": {
{`[^']+`, LiteralStringSingle, nil},
{`''`, LiteralStringSingle, nil},
{`'`, LiteralStringSingle, Pop(1)},
},
"quoted-ident": {
{`[^"]+`, LiteralStringName, nil},
{`""`, LiteralStringName, nil},
{`"`, LiteralStringName, Pop(1)},
},
"dollar-string": {
{`[^\$]+`, LiteralStringHeredoc, nil},
{`\$\$`, LiteralStringHeredoc, Pop(1)},
},
}
}

32
lexers/docker.go
View File

@@ -1,32 +0,0 @@
package lexers
import (
. "github.com/alecthomas/chroma/v2" // nolint
)
// Docker lexer.
var Docker = Register(MustNewLexer(
&Config{
Name: "Docker",
Aliases: []string{"docker", "dockerfile"},
Filenames: []string{"Dockerfile", "Dockerfile.*", "*.docker"},
MimeTypes: []string{"text/x-dockerfile-config"},
CaseInsensitive: true,
},
dockerRules,
))
func dockerRules() Rules {
return Rules{
"root": {
{`#.*`, Comment, nil},
{`(ONBUILD)((?:\s*\\?\s*))`, ByGroups(Keyword, Using("Bash")), nil},
{`(HEALTHCHECK)(((?:\s*\\?\s*)--\w+=\w+(?:\s*\\?\s*))*)`, ByGroups(Keyword, Using("Bash")), nil},
{`(VOLUME|ENTRYPOINT|CMD|SHELL)((?:\s*\\?\s*))(\[.*?\])`, ByGroups(Keyword, Using("Bash"), Using("JSON")), nil},
{`(LABEL|ENV|ARG)((?:(?:\s*\\?\s*)\w+=\w+(?:\s*\\?\s*))*)`, ByGroups(Keyword, Using("Bash")), nil},
{`((?:FROM|MAINTAINER|EXPOSE|WORKDIR|USER|STOPSIGNAL)|VOLUME)\b(.*)`, ByGroups(Keyword, LiteralString), nil},
{`((?:RUN|CMD|ENTRYPOINT|ENV|ARG|LABEL|ADD|COPY))`, Keyword, nil},
{`(.*\\\n)*.+`, Using("Bash"), nil},
},
}
}

17
lexers/embedded/aql.xml → lexers/embedded/arangodb_aql.xml
View File

@@ -4,9 +4,9 @@
<alias>aql</alias>
<filename>*.aql</filename>
<mime_type>text/x-aql</mime_type>
<case_insensitive>true</case_insensitive>
<dot_all>true</dot_all>
<ensure_nl>true</ensure_nl>
<case_insensitive>true</case_insensitive>
</config>
<rules>
<state name="comments-and-whitespace">
@@ -37,10 +37,10 @@
<rule pattern="\\.">
<token type="LiteralStringDouble"/>
</rule>
<rule pattern="[^&quot;\\]+">
<rule pattern="[^&#34;\\]+">
<token type="LiteralStringDouble"/>
</rule>
<rule pattern="&quot;">
<rule pattern="&#34;">
<token type="LiteralStringDouble"/>
<pop depth="1"/>
</rule>
@@ -49,10 +49,10 @@
<rule pattern="\\.">
<token type="LiteralStringSingle"/>
</rule>
<rule pattern="[^'\\]+">
<rule pattern="[^&#39;\\]+">
<token type="LiteralStringSingle"/>
</rule>
<rule pattern="'">
<rule pattern="&#39;">
<token type="LiteralStringSingle"/>
<pop depth="1"/>
</rule>
@@ -155,15 +155,14 @@
<rule pattern="(?:to_bool|to_number|to_string|to_array|to_list|is_null|is_bool|is_number|is_string|is_array|is_list|is_object|is_document|is_datestring|typename|json_stringify|json_parse|concat|concat_separator|char_length|lower|upper|substring|substring_bytes|left|right|trim|reverse|contains|log|log2|log10|exp|exp2|sin|cos|tan|asin|acos|atan|atan2|radians|degrees|pi|regex_test|regex_replace|like|floor|ceil|round|abs|rand|sqrt|pow|length|count|min|max|average|avg|sum|product|median|variance_population|variance_sample|variance|percentile|bit_and|bit_or|bit_xor|bit_negate|bit_test|bit_popcount|bit_shift_left|bit_shift_right|bit_construct|bit_deconstruct|bit_to_string|bit_from_string|first|last|unique|outersection|interleave|in_range|jaccard|matches|merge|merge_recursive|has|attributes|keys|values|unset|unset_recursive|keep|keep_recursive|near|within|within_rectangle|is_in_polygon|distance|fulltext|stddev_sample|stddev_population|stddev|slice|nth|position|contains_array|translate|zip|call|apply|push|append|pop|shift|unshift|remove_value|remove_values|remove_nth|replace_nth|date_now|date_timestamp|date_iso8601|date_dayofweek|date_year|date_month|date_day|date_hour|date_minute|date_second|date_millisecond|date_dayofyear|date_isoweek|date_isoweekyear|date_leapyear|date_quarter|date_days_in_month|date_trunc|date_round|date_add|date_subtract|date_diff|date_compare|date_format|date_utctolocal|date_localtoutc|date_timezone|date_timezones|fail|passthru|v8|sleep|schema_get|schema_validate|shard_id|version|noopt|noeval|not_null|first_list|first_document|parse_identifier|current_user|current_database|collection_count|pregel_result|collections|document|decode_rev|range|union|union_distinct|minus|intersection|flatten|is_same_collection|check_document|ltrim|rtrim|find_first|find_last|split|substitute|ipv4_to_number|ipv4_from_number|is_ipv4|md5|sha1|sha256|sha512|crc32|fnv64|hash|random_token|to_base64|to_hex|encode_uri_component|soundex|assert|warn|is_key|sorted|sorted_unique|count_distinct|count_unique|levenshtein_distance|levenshtein_match|regex_matches|regex_split|ngram_match|ngram_similarity|ngram_positional_similarity|uuid|tokens|exists|starts_with|phrase|min_match|bm25|tfidf|boost|analyzer|offset_info|value|cosine_similarity|decay_exp|decay_gauss|decay_linear|l1_distance|l2_distance|minhash|minhash_count|minhash_error|minhash_match|geo_point|geo_multipoint|geo_polygon|geo_multipolygon|geo_linestring|geo_multilinestring|geo_contains|geo_intersects|geo_equals|geo_distance|geo_area|geo_in_range)(?=\s*\()">
<token type="NameFunction"/>
</rule>
<rule pattern="&quot;">
<rule pattern="&#34;">
<token type="LiteralStringDouble"/>
<push state="double-quote"/>
</rule>
<rule pattern="'">
<rule pattern="&#39;">
<token type="LiteralStringSingle"/>
<push state="single-quote"/>
</rule>
<!-- not part of the language but useful for highlighting query explain outputs -->
<rule pattern="#\d+\b">
<token type="NameLabel"/>
</rule>
@@ -172,4 +171,4 @@
</rule>
</state>
</rules>
</lexer>
</lexer>

3
lexers/embedded/bash.xml
View File

@@ -26,6 +26,9 @@
<filename>PKGBUILD</filename>
<mime_type>application/x-sh</mime_type>
<mime_type>application/x-shellscript</mime_type>
<analyse first="true" >
<regex pattern="(?m)^#!.*/bin/(?:env |)(?:bash|zsh|sh|ksh)" score="1.0" />
</analyse>
</config>
<rules>
<state name="data">

2
lexers/embedded/bashsession.xml → lexers/embedded/bash_session.xml
View File

@@ -10,7 +10,7 @@
</config>
<rules>
<state name="root">
<rule pattern="^((?:\[[^]]+@[^]]+\]\s?)?[#$%>])(\s*)(.*\n?)">
<rule pattern="^((?:\[[^]]+@[^]]+\]\s?)?[#$%&gt;])(\s*)(.*\n?)">
<bygroups>
<token type="GenericPrompt"/>
<token type="Text"/>

0
lexers/embedded/csharp.xml → lexers/embedded/c#.xml
View File

2
lexers/embedded/c++.xml
View File

@@ -19,7 +19,7 @@
<mime_type>text/x-c++hdr</mime_type>
<mime_type>text/x-c++src</mime_type>
<ensure_nl>true</ensure_nl>
<analyse single="true">
<analyse first="true">
<regex pattern="#include &lt;[a-z_]+>" score="0.2" />
<regex pattern="using namespace " score="0.4" />
</analyse>

2
lexers/embedded/c.xml
View File

@@ -11,7 +11,7 @@
<mime_type>image/x-xbitmap</mime_type>
<mime_type>image/x-xpixmap</mime_type>
<ensure_nl>true</ensure_nl>
<analyse single="true" >
<analyse first="true" >
<regex pattern="(?m)^\s*#include &lt;" score="0.1" />
<regex pattern="(?m)^\s*#ifn?def " score="0.1" />
</analyse>

137
lexers/embedded/cassandra_cql.xml Normal file
View File

@@ -0,0 +1,137 @@
<lexer>
<config>
<name>Cassandra CQL</name>
<alias>cassandra</alias>
<alias>cql</alias>
<filename>*.cql</filename>
<mime_type>text/x-cql</mime_type>
<case_insensitive>true</case_insensitive>
<not_multiline>true</not_multiline>
</config>
<rules>
<state name="string">
<rule pattern="[^&#39;]+">
<token type="LiteralStringSingle"/>
</rule>
<rule pattern="&#39;&#39;">
<token type="LiteralStringSingle"/>
</rule>
<rule pattern="&#39;">
<token type="LiteralStringSingle"/>
<pop depth="1"/>
</rule>
</state>
<state name="quoted-ident">
<rule pattern="[^&#34;]+">
<token type="LiteralStringName"/>
</rule>
<rule pattern="&#34;&#34;">
<token type="LiteralStringName"/>
</rule>
<rule pattern="&#34;">
<token type="LiteralStringName"/>
<pop depth="1"/>
</rule>
</state>
<state name="dollar-string">
<rule pattern="[^\$]+">
<token type="LiteralStringHeredoc"/>
</rule>
<rule pattern="\$\$">
<token type="LiteralStringHeredoc"/>
<pop depth="1"/>
</rule>
</state>
<state name="root">
<rule pattern="\s+">
<token type="TextWhitespace"/>
</rule>
<rule pattern="(--|\/\/).*\n?">
<token type="CommentSingle"/>
</rule>
<rule pattern="/\*">
<token type="CommentMultiline"/>
<push state="multiline-comments"/>
</rule>
<rule pattern="(ascii|bigint|blob|boolean|counter|date|decimal|double|float|frozen|inet|int|list|map|set|smallint|text|time|timestamp|timeuuid|tinyint|tuple|uuid|varchar|varint)\b">
<token type="NameBuiltin"/>
</rule>
<rule pattern="(DURABLE_WRITES|LOCAL_QUORUM|MATERIALIZED|COLUMNFAMILY|REPLICATION|NORECURSIVE|NOSUPERUSER|PERMISSIONS|EACH_QUORUM|CONSISTENCY|PERMISSION|CLUSTERING|WRITETIME|SUPERUSER|KEYSPACES|AUTHORIZE|LOCAL_ONE|AGGREGATE|FINALFUNC|PARTITION|FILTERING|UNLOGGED|CONTAINS|DISTINCT|FUNCTION|LANGUAGE|INFINITY|INITCOND|TRUNCATE|KEYSPACE|PASSWORD|REPLACE|OPTIONS|TRIGGER|STORAGE|ENTRIES|RETURNS|COMPACT|PRIMARY|EXISTS|STATIC|PAGING|UPDATE|CUSTOM|VALUES|INSERT|DELETE|MODIFY|CREATE|SELECT|SCHEMA|LOGGED|REVOKE|RENAME|QUORUM|CALLED|STYPE|ORDER|ALTER|BATCH|BEGIN|COUNT|ROLES|APPLY|WHERE|SFUNC|LEVEL|INPUT|LOGIN|INDEX|TABLE|THREE|ALLOW|TOKEN|LIMIT|USING|USERS|GRANT|FROM|KEYS|JSON|USER|INTO|ROLE|TYPE|VIEW|DESC|WITH|DROP|FULL|ASC|TTL|OFF|PER|KEY|USE|ADD|NAN|ONE|ALL|ANY|TWO|AND|NOT|AS|IN|IF|OF|IS|ON|TO|BY|OR)\b">
<token type="Keyword"/>
</rule>
<rule pattern="[+*/&lt;&gt;=~!@#%^&amp;|`?-]+">
<token type="Operator"/>
</rule>
<rule pattern="(?s)(java|javascript)(\s+)(AS)(\s+)(&#39;|\$\$)(.*?)(\5)">
<usingbygroup>
<sublexer_name_group>1</sublexer_name_group>
<code_group>6</code_group>
<emitters>
<token type="NameBuiltin"/>
<token type="TextWhitespace"/>
<token type="Keyword"/>
<token type="TextWhitespace"/>
<token type="LiteralStringHeredoc"/>
<token type="LiteralStringHeredoc"/>
<token type="LiteralStringHeredoc"/>
</emitters>
</usingbygroup>
</rule>
<rule pattern="(true|false|null)\b">
<token type="KeywordConstant"/>
</rule>
<rule pattern="0x[0-9a-f]+">
<token type="LiteralNumberHex"/>
</rule>
<rule pattern="[0-9a-f]{8}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{12}">
<token type="LiteralNumberHex"/>
</rule>
<rule pattern="\.[0-9]+(e[+-]?[0-9]+)?">
<token type="Error"/>
</rule>
<rule pattern="-?[0-9]+(\.[0-9])?(e[+-]?[0-9]+)?">
<token type="LiteralNumberFloat"/>
</rule>
<rule pattern="[0-9]+">
<token type="LiteralNumberInteger"/>
</rule>
<rule pattern="&#39;">
<token type="LiteralStringSingle"/>
<push state="string"/>
</rule>
<rule pattern="&#34;">
<token type="LiteralStringName"/>
<push state="quoted-ident"/>
</rule>
<rule pattern="\$\$">
<token type="LiteralStringHeredoc"/>
<push state="dollar-string"/>
</rule>
<rule pattern="[a-z_]\w*">
<token type="Name"/>
</rule>
<rule pattern=":([&#39;&#34;]?)[a-z]\w*\b\1">
<token type="NameVariable"/>
</rule>
<rule pattern="[;:()\[\]\{\},.]">
<token type="Punctuation"/>
</rule>
</state>
<state name="multiline-comments">
<rule pattern="/\*">
<token type="CommentMultiline"/>
<push state="multiline-comments"/>
</rule>
<rule pattern="\*/">
<token type="CommentMultiline"/>
<pop depth="1"/>
</rule>
<rule pattern="[^/*]+">
<token type="CommentMultiline"/>
</rule>
<rule pattern="[/*]">
<token type="CommentMultiline"/>
</rule>
</state>
</rules>
</lexer>

143
lexers/embedded/chapel.xml Normal file
View File

@@ -0,0 +1,143 @@
<lexer>
<config>
<name>Chapel</name>
<alias>chapel</alias>
<alias>chpl</alias>
<filename>*.chpl</filename>
</config>
<rules>
<state name="procname">
<rule pattern="([a-zA-Z_][.\w$]*|\~[a-zA-Z_][.\w$]*|[+*/!~%&lt;&gt;=&amp;^|\-:]{1,2})">
<token type="NameFunction"/>
<pop depth="1"/>
</rule>
<rule pattern="\(">
<token type="Punctuation"/>
<push state="receivertype"/>
</rule>
<rule pattern="\)+\.">
<token type="Punctuation"/>
</rule>
</state>
<state name="receivertype">
<rule pattern="(unmanaged|borrowed|atomic|single|shared|owned|sync)\b">
<token type="Keyword"/>
</rule>
<rule pattern="(complex|nothing|opaque|string|locale|bytes|range|imag|real|bool|uint|void|int)\b">
<token type="KeywordType"/>
</rule>
<rule pattern="[^()]*">
<token type="NameOther"/>
<pop depth="1"/>
</rule>
</state>
<state name="root">
<rule pattern="\n">
<token type="TextWhitespace"/>
</rule>
<rule pattern="\s+">
<token type="TextWhitespace"/>
</rule>
<rule pattern="\\\n">
<token type="Text"/>
</rule>
<rule pattern="//(.*?)\n">
<token type="CommentSingle"/>
</rule>
<rule pattern="/(\\\n)?[*](.|\n)*?[*](\\\n)?/">
<token type="CommentMultiline"/>
</rule>
<rule pattern="(config|const|inout|param|type|out|ref|var|in)\b">
<token type="KeywordDeclaration"/>
</rule>
<rule pattern="(false|none|true|nil)\b">
<token type="KeywordConstant"/>
</rule>
<rule pattern="(complex|nothing|opaque|string|locale|bytes|range|imag|real|bool|uint|void|int)\b">
<token type="KeywordType"/>
</rule>
<rule pattern="(implements|forwarding|prototype|otherwise|subdomain|primitive|unmanaged|override|borrowed|lifetime|coforall|continue|private|require|dmapped|cobegin|foreach|lambda|sparse|shared|domain|pragma|reduce|except|export|extern|throws|forall|delete|return|noinit|single|import|select|public|inline|serial|atomic|defer|break|local|index|throw|catch|label|begin|where|while|align|yield|owned|only|this|sync|with|scan|else|enum|init|when|then|let|for|try|use|new|zip|if|by|as|on|do)\b">
<token type="Keyword"/>
</rule>
<rule pattern="(iter)(\s+)">
<bygroups>
<token type="Keyword"/>
<token type="TextWhitespace"/>
</bygroups>
<push state="procname"/>
</rule>
<rule pattern="(proc)(\s+)">
<bygroups>
<token type="Keyword"/>
<token type="TextWhitespace"/>
</bygroups>
<push state="procname"/>
</rule>
<rule pattern="(operator)(\s+)">
<bygroups>
<token type="Keyword"/>
<token type="TextWhitespace"/>
</bygroups>
<push state="procname"/>
</rule>
<rule pattern="(class|interface|module|record|union)(\s+)">
<bygroups>
<token type="Keyword"/>
<token type="TextWhitespace"/>
</bygroups>
<push state="classname"/>
</rule>
<rule pattern="\d+i">
<token type="LiteralNumber"/>
</rule>
<rule pattern="\d+\.\d*([Ee][-+]\d+)?i">
<token type="LiteralNumber"/>
</rule>
<rule pattern="\.\d+([Ee][-+]\d+)?i">
<token type="LiteralNumber"/>
</rule>
<rule pattern="\d+[Ee][-+]\d+i">
<token type="LiteralNumber"/>
</rule>
<rule pattern="(\d*\.\d+)([eE][+-]?[0-9]+)?i?">
<token type="LiteralNumberFloat"/>
</rule>
<rule pattern="\d+[eE][+-]?[0-9]+i?">
<token type="LiteralNumberFloat"/>
</rule>
<rule pattern="0[bB][01]+">
<token type="LiteralNumberBin"/>
</rule>
<rule pattern="0[xX][0-9a-fA-F]+">
<token type="LiteralNumberHex"/>
</rule>
<rule pattern="0[oO][0-7]+">
<token type="LiteralNumberOct"/>
</rule>
<rule pattern="[0-9]+">
<token type="LiteralNumberInteger"/>
</rule>
<rule pattern="&#34;(\\\\|\\&#34;|[^&#34;])*&#34;">
<token type="LiteralString"/>
</rule>
<rule pattern="&#39;(\\\\|\\&#39;|[^&#39;])*&#39;">
<token type="LiteralString"/>
</rule>
<rule pattern="(=|\+=|-=|\*=|/=|\*\*=|%=|&amp;=|\|=|\^=|&amp;&amp;=|\|\|=|&lt;&lt;=|&gt;&gt;=|&lt;=&gt;|&lt;~&gt;|\.\.|by|#|\.\.\.|&amp;&amp;|\|\||!|&amp;|\||\^|~|&lt;&lt;|&gt;&gt;|==|!=|&lt;=|&gt;=|&lt;|&gt;|[+\-*/%]|\*\*)">
<token type="Operator"/>
</rule>
<rule pattern="[:;,.?()\[\]{}]">
<token type="Punctuation"/>
</rule>
<rule pattern="[a-zA-Z_][\w$]*">
<token type="NameOther"/>
</rule>
</state>
<state name="classname">
<rule pattern="[a-zA-Z_][\w$]*">
<token type="NameClass"/>
<pop depth="1"/>
</rule>
</state>
</rules>
</lexer>

55
lexers/embedded/cheetah.xml Normal file
View File

@@ -0,0 +1,55 @@
<lexer>
<config>
<name>Cheetah</name>
<alias>cheetah</alias>
<alias>spitfire</alias>
<filename>*.tmpl</filename>
<filename>*.spt</filename>
<mime_type>application/x-cheetah</mime_type>
<mime_type>application/x-spitfire</mime_type>
</config>
<rules>
<state name="root">
<rule pattern="(##[^\n]*)$">
<bygroups>
<token type="Comment"/>
</bygroups>
</rule>
<rule pattern="#[*](.|\n)*?[*]#">
<token type="Comment"/>
</rule>
<rule pattern="#end[^#\n]*(?:#|$)">
<token type="CommentPreproc"/>
</rule>
<rule pattern="#slurp$">
<token type="CommentPreproc"/>
</rule>
<rule pattern="(#[a-zA-Z]+)([^#\n]*)(#|$)">
<bygroups>
<token type="CommentPreproc"/>
<using lexer="Python"/>
<token type="CommentPreproc"/>
</bygroups>
</rule>
<rule pattern="(\$)([a-zA-Z_][\w.]*\w)">
<bygroups>
<token type="CommentPreproc"/>
<using lexer="Python"/>
</bygroups>
</rule>
<rule pattern="(\$\{!?)(.*?)(\})(?s)">
<bygroups>
<token type="CommentPreproc"/>
<using lexer="Python"/>
<token type="CommentPreproc"/>
</bygroups>
</rule>
<rule pattern="(?sx)&#xA; (.+?) # anything, followed by:&#xA; (?:&#xA; (?=\#[#a-zA-Z]*) | # an eval comment&#xA; (?=\$[a-zA-Z_{]) | # a substitution&#xA; \Z # end of string&#xA; )&#xA; ">
<token type="Other"/>
</rule>
<rule pattern="\s+">
<token type="Text"/>
</rule>
</state>
</rules>
</lexer>

56
lexers/embedded/docker.xml Normal file
View File

@@ -0,0 +1,56 @@
<lexer>
<config>
<name>Docker</name>
<alias>docker</alias>
<alias>dockerfile</alias>
<filename>Dockerfile</filename>
<filename>Dockerfile.*</filename>
<filename>*.docker</filename>
<mime_type>text/x-dockerfile-config</mime_type>
<case_insensitive>true</case_insensitive>
</config>
<rules>
<state name="root">
<rule pattern="#.*">
<token type="Comment"/>
</rule>
<rule pattern="(ONBUILD)((?:\s*\\?\s*))">
<bygroups>
<token type="Keyword"/>
<using lexer="Bash"/>
</bygroups>
</rule>
<rule pattern="(HEALTHCHECK)(((?:\s*\\?\s*)--\w+=\w+(?:\s*\\?\s*))*)">
<bygroups>
<token type="Keyword"/>
<using lexer="Bash"/>
</bygroups>
</rule>
<rule pattern="(VOLUME|ENTRYPOINT|CMD|SHELL)((?:\s*\\?\s*))(\[.*?\])">
<bygroups>
<token type="Keyword"/>
<using lexer="Bash"/>
<using lexer="JSON"/>
</bygroups>
</rule>
<rule pattern="(LABEL|ENV|ARG)((?:(?:\s*\\?\s*)\w+=\w+(?:\s*\\?\s*))*)">
<bygroups>
<token type="Keyword"/>
<using lexer="Bash"/>
</bygroups>
</rule>
<rule pattern="((?:FROM|MAINTAINER|EXPOSE|WORKDIR|USER|STOPSIGNAL)|VOLUME)\b(.*)">
<bygroups>
<token type="Keyword"/>
<token type="LiteralString"/>
</bygroups>
</rule>
<rule pattern="((?:RUN|CMD|ENTRYPOINT|ENV|ARG|LABEL|ADD|COPY))">
<token type="Keyword"/>
</rule>
<rule pattern="(.*\\\n)*.+">
<using lexer="Bash"/>
</rule>
</state>
</rules>
</lexer>

71
lexers/embedded/fortranfixed.xml Normal file
View File

@@ -0,0 +1,71 @@
<lexer>
<config>
<name>FortranFixed</name>
<alias>fortranfixed</alias>
<filename>*.f</filename>
<filename>*.F</filename>
<mime_type>text/x-fortran</mime_type>
<case_insensitive>true</case_insensitive>
<not_multiline>true</not_multiline>
</config>
<rules>
<state name="cont-char">
<rule pattern=" ">
<token type="TextWhitespace"/>
<push state="code"/>
</rule>
<rule pattern=".">
<token type="GenericStrong"/>
<push state="code"/>
</rule>
</state>
<state name="code">
<rule pattern="(.{66})(.*)(\n)">
<bygroups>
<using lexer="Fortran"/>
<token type="Comment"/>
<token type="TextWhitespace"/>
</bygroups>
<push state="root"/>
</rule>
<rule pattern="(.*)(!.*)(\n)">
<bygroups>
<using lexer="Fortran"/>
<token type="Comment"/>
<token type="TextWhitespace"/>
</bygroups>
<push state="root"/>
</rule>
<rule pattern="(.*)(\n)">
<bygroups>
<using lexer="Fortran"/>
<token type="TextWhitespace"/>
</bygroups>
<push state="root"/>
</rule>
<rule>
<mutators>
<push state="root"/>
</mutators>
</rule>
</state>
<state name="root">
<rule pattern="[C*].*\n">
<token type="Comment"/>
</rule>
<rule pattern="#.*\n">
<token type="CommentPreproc"/>
</rule>
<rule pattern=" {0,4}!.*\n">
<token type="Comment"/>
</rule>
<rule pattern="(.{5})">
<token type="NameLabel"/>
<push state="cont-char"/>
</rule>
<rule pattern=".*\n">
<using lexer="Fortran"/>
</rule>
</state>
</rules>
</lexer>

2
lexers/embedded/gdscript.xml
View File

@@ -7,7 +7,7 @@
<mime_type>text/x-gdscript</mime_type>
<mime_type>application/x-gdscript</mime_type>
<priority>0.1</priority>
<analyse single="true">
<analyse first="true">
<regex pattern="^@" score="0.4"/>
</analyse>
</config>

2
lexers/embedded/gdscript3.xml
View File

@@ -6,7 +6,7 @@
<filename>*.gd</filename>
<mime_type>text/x-gdscript</mime_type>
<mime_type>application/x-gdscript</mime_type>
<analyse single="true">
<analyse first="true">
<regex pattern="^export" score="0.1"/>
</analyse>
</config>

4
lexers/embedded/go_template.xml
View File

@@ -1,7 +1,7 @@
<lexer>
<config>
<name>Go HTML Template</name>
<alias>go-html-template</alias>
<name>Go Template</name>
<alias>go-template</alias>
</config>
<rules>
<state name="template">

159
lexers/embedded/html.xml Normal file
View File

@@ -0,0 +1,159 @@
<lexer>
<config>
<name>HTML</name>
<alias>html</alias>
<filename>*.html</filename>
<filename>*.htm</filename>
<filename>*.xhtml</filename>
<filename>*.xslt</filename>
<mime_type>text/html</mime_type>
<mime_type>application/xhtml+xml</mime_type>
<case_insensitive>true</case_insensitive>
<dot_all>true</dot_all>
<not_multiline>true</not_multiline>
</config>
<rules>
<state name="script-content">
<rule pattern="(&lt;)(\s*)(/)(\s*)(script)(\s*)(&gt;)">
<bygroups>
<token type="Punctuation"/>
<token type="Text"/>
<token type="Punctuation"/>
<token type="Text"/>
<token type="NameTag"/>
<token type="Text"/>
<token type="Punctuation"/>
</bygroups>
<pop depth="1"/>
</rule>
<rule pattern=".+?(?=&lt;\s*/\s*script\s*&gt;)">
<using lexer="Javascript"/>
</rule>
</state>
<state name="style-content">
<rule pattern="(&lt;)(\s*)(/)(\s*)(style)(\s*)(&gt;)">
<bygroups>
<token type="Punctuation"/>
<token type="Text"/>
<token type="Punctuation"/>
<token type="Text"/>
<token type="NameTag"/>
<token type="Text"/>
<token type="Punctuation"/>
</bygroups>
<pop depth="1"/>
</rule>
<rule pattern=".+?(?=&lt;\s*/\s*style\s*&gt;)">
<using lexer="CSS"/>
</rule>
</state>
<state name="attr">
<rule pattern="&#34;.*?&#34;">
<token type="LiteralString"/>
<pop depth="1"/>
</rule>
<rule pattern="&#39;.*?&#39;">
<token type="LiteralString"/>
<pop depth="1"/>
</rule>
<rule pattern="[^\s&gt;]+">
<token type="LiteralString"/>
<pop depth="1"/>
</rule>
</state>
<state name="root">
<rule pattern="[^&lt;&amp;]+">
<token type="Text"/>
</rule>
<rule pattern="&amp;\S*?;">
<token type="NameEntity"/>
</rule>
<rule pattern="\&lt;\!\[CDATA\[.*?\]\]\&gt;">
<token type="CommentPreproc"/>
</rule>
<rule pattern="&lt;!--">
<token type="Comment"/>
<push state="comment"/>
</rule>
<rule pattern="&lt;\?.*?\?&gt;">
<token type="CommentPreproc"/>
</rule>
<rule pattern="&lt;![^&gt;]*&gt;">
<token type="CommentPreproc"/>
</rule>
<rule pattern="(&lt;)(\s*)(script)(\s*)">
<bygroups>
<token type="Punctuation"/>
<token type="Text"/>
<token type="NameTag"/>
<token type="Text"/>
</bygroups>
<push state="script-content" state="tag"/>
</rule>
<rule pattern="(&lt;)(\s*)(style)(\s*)">
<bygroups>
<token type="Punctuation"/>
<token type="Text"/>
<token type="NameTag"/>
<token type="Text"/>
</bygroups>
<push state="style-content" state="tag"/>
</rule>
<rule pattern="(&lt;)(\s*)([\w:.-]+)">
<bygroups>
<token type="Punctuation"/>
<token type="Text"/>
<token type="NameTag"/>
</bygroups>
<push state="tag"/>
</rule>
<rule pattern="(&lt;)(\s*)(/)(\s*)([\w:.-]+)(\s*)(&gt;)">
<bygroups>
<token type="Punctuation"/>
<token type="Text"/>
<token type="Punctuation"/>
<token type="Text"/>
<token type="NameTag"/>
<token type="Text"/>
<token type="Punctuation"/>
</bygroups>
</rule>
</state>
<state name="comment">
<rule pattern="[^-]+">
<token type="Comment"/>
</rule>
<rule pattern="--&gt;">
<token type="Comment"/>
<pop depth="1"/>
</rule>
<rule pattern="-">
<token type="Comment"/>
</rule>
</state>
<state name="tag">
<rule pattern="\s+">
<token type="Text"/>
</rule>
<rule pattern="([\w:-]+\s*)(=)(\s*)">
<bygroups>
<token type="NameAttribute"/>
<token type="Operator"/>
<token type="Text"/>
</bygroups>
<push state="attr"/>
</rule>
<rule pattern="[\w:-]+">
<token type="NameAttribute"/>
</rule>
<rule pattern="(/?)(\s*)(&gt;)">
<bygroups>
<token type="Punctuation"/>
<token type="Text"/>
<token type="Punctuation"/>
</bygroups>
<pop depth="1"/>
</rule>
</state>
</rules>
</lexer>

0
lexers/embedded/lighttpd.xml → lexers/embedded/lighttpd_configuration_file.xml
View File

128
lexers/embedded/makefile.xml Normal file
View File

@@ -0,0 +1,128 @@
<lexer>
<config>
<name>Makefile</name>
<alias>make</alias>
<alias>makefile</alias>
<alias>mf</alias>
<alias>bsdmake</alias>
<filename>*.mak</filename>
<filename>*.mk</filename>
<filename>Makefile</filename>
<filename>makefile</filename>
<filename>Makefile.*</filename>
<filename>GNUmakefile</filename>
<filename>BSDmakefile</filename>
<mime_type>text/x-makefile</mime_type>
<ensure_nl>true</ensure_nl>
</config>
<rules>
<state name="root">
<rule pattern="^(?:[\t ]+.*\n|\n)+">
<using lexer="Bash"/>
</rule>
<rule pattern="\$[&lt;@$+%?|*]">
<token type="Keyword"/>
</rule>
<rule pattern="\s+">
<token type="Text"/>
</rule>
<rule pattern="#.*?\n">
<token type="Comment"/>
</rule>
<rule pattern="(export)(\s+)(?=[\w${}\t -]+\n)">
<bygroups>
<token type="Keyword"/>
<token type="Text"/>
</bygroups>
<push state="export"/>
</rule>
<rule pattern="export\s+">
<token type="Keyword"/>
</rule>
<rule pattern="([\w${}().-]+)(\s*)([!?:+]?=)([ \t]*)((?:.*\\\n)+|.*\n)">
<bygroups>
<token type="NameVariable"/>
<token type="Text"/>
<token type="Operator"/>
<token type="Text"/>
<using lexer="Bash"/>
</bygroups>
</rule>
<rule pattern="(?s)&#34;(\\\\|\\.|[^&#34;\\])*&#34;">
<token type="LiteralStringDouble"/>
</rule>
<rule pattern="(?s)&#39;(\\\\|\\.|[^&#39;\\])*&#39;">
<token type="LiteralStringSingle"/>
</rule>
<rule pattern="([^\n:]+)(:+)([ \t]*)">
<bygroups>
<token type="NameFunction"/>
<token type="Operator"/>
<token type="Text"/>
</bygroups>
<push state="block-header"/>
</rule>
<rule pattern="\$\(">
<token type="Keyword"/>
<push state="expansion"/>
</rule>
</state>
<state name="expansion">
<rule pattern="[^$a-zA-Z_()]+">
<token type="Text"/>
</rule>
<rule pattern="[a-zA-Z_]+">
<token type="NameVariable"/>
</rule>
<rule pattern="\$">
<token type="Keyword"/>
</rule>
<rule pattern="\(">
<token type="Keyword"/>
<push/>
</rule>
<rule pattern="\)">
<token type="Keyword"/>
<pop depth="1"/>
</rule>
</state>
<state name="export">
<rule pattern="[\w${}-]+">
<token type="NameVariable"/>
</rule>
<rule pattern="\n">
<token type="Text"/>
<pop depth="1"/>
</rule>
<rule pattern="\s+">
<token type="Text"/>
</rule>
</state>
<state name="block-header">
<rule pattern="[,|]">
<token type="Punctuation"/>
</rule>
<rule pattern="#.*?\n">
<token type="Comment"/>
<pop depth="1"/>
</rule>
<rule pattern="\\\n">
<token type="Text"/>
</rule>
<rule pattern="\$\(">
<token type="Keyword"/>
<push state="expansion"/>
</rule>
<rule pattern="[a-zA-Z_]+">
<token type="Name"/>
</rule>
<rule pattern="\n">
<token type="Text"/>
<pop depth="1"/>
</rule>
<rule pattern=".">
<token type="Text"/>
</rule>
</state>
</rules>
</lexer>

120
lexers/embedded/mako.xml Normal file
View File

@@ -0,0 +1,120 @@
<lexer>
<config>
<name>Mako</name>
<alias>mako</alias>
<filename>*.mao</filename>
<mime_type>application/x-mako</mime_type>
</config>
<rules>
<state name="root">
<rule pattern="(\s*)(%)(\s*end(?:\w+))(\n|\Z)">
<bygroups>
<token type="Text"/>
<token type="CommentPreproc"/>
<token type="Keyword"/>
<token type="Other"/>
</bygroups>
</rule>
<rule pattern="(\s*)(%)([^\n]*)(\n|\Z)">
<bygroups>
<token type="Text"/>
<token type="CommentPreproc"/>
<using lexer="Python"/>
<token type="Other"/>
</bygroups>
</rule>
<rule pattern="(\s*)(##[^\n]*)(\n|\Z)">
<bygroups>
<token type="Text"/>
<token type="CommentPreproc"/>
<token type="Other"/>
</bygroups>
</rule>
<rule pattern="(?s)&lt;%doc&gt;.*?&lt;/%doc&gt;">
<token type="CommentPreproc"/>
</rule>
<rule pattern="(&lt;%)([\w.:]+)">
<bygroups>
<token type="CommentPreproc"/>
<token type="NameBuiltin"/>
</bygroups>
<push state="tag"/>
</rule>
<rule pattern="(&lt;/%)([\w.:]+)(&gt;)">
<bygroups>
<token type="CommentPreproc"/>
<token type="NameBuiltin"/>
<token type="CommentPreproc"/>
</bygroups>
</rule>
<rule pattern="&lt;%(?=([\w.:]+))">
<token type="CommentPreproc"/>
<push state="ondeftags"/>
</rule>
<rule pattern="(&lt;%(?:!?))(.*?)(%&gt;)(?s)">
<bygroups>
<token type="CommentPreproc"/>
<using lexer="Python"/>
<token type="CommentPreproc"/>
</bygroups>
</rule>
<rule pattern="(\$\{)(.*?)(\})">
<bygroups>
<token type="CommentPreproc"/>
<using lexer="Python"/>
<token type="CommentPreproc"/>
</bygroups>
</rule>
<rule pattern="(?sx)&#xA; (.+?) # anything, followed by:&#xA; (?:&#xA; (?&lt;=\n)(?=%|\#\#) | # an eval or comment line&#xA; (?=\#\*) | # multiline comment&#xA; (?=&lt;/?%) | # a python block&#xA; # call start or end&#xA; (?=\$\{) | # a substitution&#xA; (?&lt;=\n)(?=\s*%) |&#xA; # - don&#39;t consume&#xA; (\\\n) | # an escaped newline&#xA; \Z # end of string&#xA; )&#xA; ">
<bygroups>
<token type="Other"/>
<token type="Operator"/>
</bygroups>
</rule>
<rule pattern="\s+">
<token type="Text"/>
</rule>
</state>
<state name="ondeftags">
<rule pattern="&lt;%">
<token type="CommentPreproc"/>
</rule>
<rule pattern="(?&lt;=&lt;%)(include|inherit|namespace|page)">
<token type="NameBuiltin"/>
</rule>
<rule>
<include state="tag"/>
</rule>
</state>
<state name="tag">
<rule pattern="((?:\w+)\s*=)(\s*)(&#34;.*?&#34;)">
<bygroups>
<token type="NameAttribute"/>
<token type="Text"/>
<token type="LiteralString"/>
</bygroups>
</rule>
<rule pattern="/?\s*&gt;">
<token type="CommentPreproc"/>
<pop depth="1"/>
</rule>
<rule pattern="\s+">
<token type="Text"/>
</rule>
</state>
<state name="attr">
<rule pattern="&#34;.*?&#34;">
<token type="LiteralString"/>
<pop depth="1"/>
</rule>
<rule pattern="&#39;.*?&#39;">
<token type="LiteralString"/>
<pop depth="1"/>
</rule>
<rule pattern="[^\s&gt;]+">
<token type="LiteralString"/>
<pop depth="1"/>
</rule>
</state>
</rules>
</lexer>

89
lexers/embedded/mason.xml Normal file
View File

@@ -0,0 +1,89 @@
<lexer>
<config>
<name>Mason</name>
<alias>mason</alias>
<filename>*.m</filename>
<filename>*.mhtml</filename>
<filename>*.mc</filename>
<filename>*.mi</filename>
<filename>autohandler</filename>
<filename>dhandler</filename>
<mime_type>application/x-mason</mime_type>
<priority>0.1</priority>
</config>
<rules>
<state name="root">
<rule pattern="\s+">
<token type="Text"/>
</rule>
<rule pattern="(&lt;%doc&gt;)(.*?)(&lt;/%doc&gt;)(?s)">
<bygroups>
<token type="NameTag"/>
<token type="CommentMultiline"/>
<token type="NameTag"/>
</bygroups>
</rule>
<rule pattern="(&lt;%(?:def|method))(\s*)(.*?)(&gt;)(.*?)(&lt;/%\2\s*&gt;)(?s)">
<bygroups>
<token type="NameTag"/>
<token type="Text"/>
<token type="NameFunction"/>
<token type="NameTag"/>
<usingself state="root"/>
<token type="NameTag"/>
</bygroups>
</rule>
<rule pattern="(&lt;%\w+)(.*?)(&gt;)(.*?)(&lt;/%\2\s*&gt;)(?s)">
<bygroups>
<token type="NameTag"/>
<token type="NameFunction"/>
<token type="NameTag"/>
<using lexer="Perl"/>
<token type="NameTag"/>
</bygroups>
</rule>
<rule pattern="(&lt;&amp;[^|])(.*?)(,.*?)?(&amp;&gt;)(?s)">
<bygroups>
<token type="NameTag"/>
<token type="NameFunction"/>
<using lexer="Perl"/>
<token type="NameTag"/>
</bygroups>
</rule>
<rule pattern="(&lt;&amp;\|)(.*?)(,.*?)?(&amp;&gt;)(?s)">
<bygroups>
<token type="NameTag"/>
<token type="NameFunction"/>
<using lexer="Perl"/>
<token type="NameTag"/>
</bygroups>
</rule>
<rule pattern="&lt;/&amp;&gt;">
<token type="NameTag"/>
</rule>
<rule pattern="(&lt;%!?)(.*?)(%&gt;)(?s)">
<bygroups>
<token type="NameTag"/>
<using lexer="Perl"/>
<token type="NameTag"/>
</bygroups>
</rule>
<rule pattern="(?&lt;=^)#[^\n]*(\n|\Z)">
<token type="Comment"/>
</rule>
<rule pattern="(?&lt;=^)(%)([^\n]*)(\n|\Z)">
<bygroups>
<token type="NameTag"/>
<using lexer="Perl"/>
<token type="Other"/>
</bygroups>
</rule>
<rule pattern="(?sx)&#xA; (.+?) # anything, followed by:&#xA; (?:&#xA; (?&lt;=\n)(?=[%#]) | # an eval or comment line&#xA; (?=&lt;/?[%&amp;]) | # a substitution or block or&#xA; # call start or end&#xA; # - don&#39;t consume&#xA; (\\\n) | # an escaped newline&#xA; \Z # end of string&#xA; )">
<bygroups>
<using lexer="HTML"/>
<token type="Operator"/>
</bygroups>
</rule>
</state>
</rules>
</lexer>

77
lexers/embedded/myghty.xml Normal file
View File

@@ -0,0 +1,77 @@
<lexer>
<config>
<name>Myghty</name>
<alias>myghty</alias>
<filename>*.myt</filename>
<filename>autodelegate</filename>
<mime_type>application/x-myghty</mime_type>
</config>
<rules>
<state name="root">
<rule pattern="\s+">
<token type="Text"/>
</rule>
<rule pattern="(&lt;%(?:def|method))(\s*)(.*?)(&gt;)(.*?)(&lt;/%\2\s*&gt;)(?s)">
<bygroups>
<token type="NameTag"/>
<token type="Text"/>
<token type="NameFunction"/>
<token type="NameTag"/>
<usingself state="root"/>
<token type="NameTag"/>
</bygroups>
</rule>
<rule pattern="(&lt;%\w+)(.*?)(&gt;)(.*?)(&lt;/%\2\s*&gt;)(?s)">
<bygroups>
<token type="NameTag"/>
<token type="NameFunction"/>
<token type="NameTag"/>
<using lexer="Python2"/>
<token type="NameTag"/>
</bygroups>
</rule>
<rule pattern="(&lt;&amp;[^|])(.*?)(,.*?)?(&amp;&gt;)">
<bygroups>
<token type="NameTag"/>
<token type="NameFunction"/>
<using lexer="Python2"/>
<token type="NameTag"/>
</bygroups>
</rule>
<rule pattern="(&lt;&amp;\|)(.*?)(,.*?)?(&amp;&gt;)(?s)">
<bygroups>
<token type="NameTag"/>
<token type="NameFunction"/>
<using lexer="Python2"/>
<token type="NameTag"/>
</bygroups>
</rule>
<rule pattern="&lt;/&amp;&gt;">
<token type="NameTag"/>
</rule>
<rule pattern="(&lt;%!?)(.*?)(%&gt;)(?s)">
<bygroups>
<token type="NameTag"/>
<using lexer="Python2"/>
<token type="NameTag"/>
</bygroups>
</rule>
<rule pattern="(?&lt;=^)#[^\n]*(\n|\Z)">
<token type="Comment"/>
</rule>
<rule pattern="(?&lt;=^)(%)([^\n]*)(\n|\Z)">
<bygroups>
<token type="NameTag"/>
<using lexer="Python2"/>
<token type="Other"/>
</bygroups>
</rule>
<rule pattern="(?sx)&#xA; (.+?) # anything, followed by:&#xA; (?:&#xA; (?&lt;=\n)(?=[%#]) | # an eval or comment line&#xA; (?=&lt;/?[%&amp;]) | # a substitution or block or&#xA; # call start or end&#xA; # - don&#39;t consume&#xA; (\\\n) | # an escaped newline&#xA; \Z # end of string&#xA; )">
<bygroups>
<token type="Other"/>
<token type="Operator"/>
</bygroups>
</rule>
</state>
</rules>
</lexer>

0
lexers/embedded/nginx.xml → lexers/embedded/nginx_configuration_file.xml
View File

101
lexers/embedded/openedge_abl.xml Normal file
View File

File diff suppressed because one or more lines are too long

329
lexers/embedded/org_mode.xml Normal file
View File

@@ -0,0 +1,329 @@
<lexer>
<config>
<name>Org Mode</name>
<alias>org</alias>
<alias>orgmode</alias>
<filename>*.org</filename>
<mime_type>text/org</mime_type>
</config>
<rules>
<state name="root">
<rule pattern="^# .*$">
<token type="Comment"/>
</rule>
<rule pattern="^(\*)( COMMENT)( .*)$">
<bygroups>
<token type="GenericHeading"/>
<token type="NameEntity"/>
<token type="GenericStrong"/>
</bygroups>
</rule>
<rule pattern="^(\*\*+)( COMMENT)( .*)$">
<bygroups>
<token type="GenericSubheading"/>
<token type="NameEntity"/>
<token type="Text"/>
</bygroups>
</rule>
<rule pattern="^(\*)( DONE)( .*)$">
<bygroups>
<token type="GenericHeading"/>
<token type="LiteralStringRegex"/>
<token type="GenericStrong"/>
</bygroups>
</rule>
<rule pattern="^(\*\*+)( DONE)( .*)$">
<bygroups>
<token type="GenericSubheading"/>
<token type="LiteralStringRegex"/>
<token type="Text"/>
</bygroups>
</rule>
<rule pattern="^(\*)( TODO)( .*)$">
<bygroups>
<token type="GenericHeading"/>
<token type="Error"/>
<token type="GenericStrong"/>
</bygroups>
</rule>
<rule pattern="^(\*\*+)( TODO)( .*)$">
<bygroups>
<token type="GenericSubheading"/>
<token type="Error"/>
<token type="Text"/>
</bygroups>
</rule>
<rule pattern="^(\*)( .+?)( :[a-zA-Z0-9_@:]+:)$">
<bygroups>
<token type="GenericHeading"/>
<token type="GenericStrong"/>
<token type="GenericEmph"/>
</bygroups>
</rule>
<rule pattern="^(\*)( .+)$">
<bygroups>
<token type="GenericHeading"/>
<token type="GenericStrong"/>
</bygroups>
</rule>
<rule pattern="^(\*\*+)( .+?)( :[a-zA-Z0-9_@:]+:)$">
<bygroups>
<token type="GenericSubheading"/>
<token type="Text"/>
<token type="GenericEmph"/>
</bygroups>
</rule>
<rule pattern="^(\*\*+)( .+)$">
<bygroups>
<token type="GenericSubheading"/>
<token type="Text"/>
</bygroups>
</rule>
<rule pattern="^( *)([+-] )(\[[ X]\])( .+)$">
<bygroups>
<token type="Text"/>
<token type="Keyword"/>
<token type="Keyword"/>
<usingself state="inline"/>
</bygroups>
</rule>
<rule pattern="^( +)(\* )(\[[ X]\])( .+)$">
<bygroups>
<token type="Text"/>
<token type="Keyword"/>
<token type="Keyword"/>
<usingself state="inline"/>
</bygroups>
</rule>
<rule pattern="^( *)([+-] )([^ \n]+ ::)( .+)$">
<bygroups>
<token type="Text"/>
<token type="Keyword"/>
<token type="Keyword"/>
<usingself state="inline"/>
</bygroups>
</rule>
<rule pattern="^( +)(\* )([^ \n]+ ::)( .+)$">
<bygroups>
<token type="Text"/>
<token type="Keyword"/>
<token type="Keyword"/>
<usingself state="inline"/>
</bygroups>
</rule>
<rule pattern="^( *)([+-] )(.+)$">
<bygroups>
<token type="Text"/>
<token type="Keyword"/>
<usingself state="inline"/>
</bygroups>
</rule>
<rule pattern="^( +)(\* )(.+)$">
<bygroups>
<token type="Text"/>
<token type="Keyword"/>
<usingself state="inline"/>
</bygroups>
</rule>
<rule pattern="^( *)([0-9]+[.)])( \[@[0-9]+\])( .+)$">
<bygroups>
<token type="Text"/>
<token type="Keyword"/>
<token type="GenericEmph"/>
<usingself state="inline"/>
</bygroups>
</rule>
<rule pattern="^( *)([0-9]+[.)])( .+)$">
<bygroups>
<token type="Text"/>
<token type="Keyword"/>
<usingself state="inline"/>
</bygroups>
</rule>
<rule pattern="(?i)^( *#\+begin: )([^ ]+)([\w\W]*?\n)([\w\W]*?)(^ *#\+end: *$)">
<bygroups>
<token type="Comment"/>
<token type="CommentSpecial"/>
<token type="Comment"/>
<usingself state="inline"/>
<token type="Comment"/>
</bygroups>
</rule>
<rule pattern="(?i)^( *#\+begin_comment *\n)([\w\W]*?)(^ *#\+end_comment *$)">
<bygroups>
<token type="Comment"/>
<token type="Comment"/>
<token type="Comment"/>
</bygroups>
</rule>
<rule pattern="(?i)^( *#\+begin_src )([^ \n]+)(.*?\n)([\w\W]*?)(^ *#\+end_src *$)">
<usingbygroup>
<sublexer_name_group>2</sublexer_name_group>
<code_group>4</code_group>
<emitters>
<token type="Comment"/>
<token type="CommentSpecial"/>
<token type="Comment"/>
<token type="Text"/>
<token type="Comment"/>
</emitters>
</usingbygroup>
</rule>
<rule pattern="(?i)^( *#\+begin_export )(\w+)( *\n)([\w\W]*?)(^ *#\+end_export *$)">
<usingbygroup>
<sublexer_name_group>2</sublexer_name_group>
<code_group>4</code_group>
<emitters>
<token type="Comment"/>
<token type="CommentSpecial"/>
<token type="Text"/>
<token type="Text"/>
<token type="Comment"/>
</emitters>
</usingbygroup>
</rule>
<rule pattern="(?i)^( *#\+begin_)(\w+)( *\n)([\w\W]*?)(^ *#\+end_\2)( *$)">
<bygroups>
<token type="Comment"/>
<token type="Comment"/>
<token type="Text"/>
<token type="Text"/>
<token type="Comment"/>
<token type="Text"/>
</bygroups>
</rule>
<rule pattern="^(#\+\w+)(:.*)$">
<bygroups>
<token type="CommentSpecial"/>
<token type="Comment"/>
</bygroups>
</rule>
<rule pattern="(?i)^( *:\w+: *\n)([\w\W]*?)(^ *:end: *$)">
<bygroups>
<token type="Comment"/>
<token type="CommentSpecial"/>
<token type="Comment"/>
</bygroups>
</rule>
<rule pattern="^(.*)(\\\\)$">
<bygroups>
<usingself state="inline"/>
<token type="Operator"/>
</bygroups>
</rule>
<rule pattern="(?i)^( *(?:DEADLINE|SCHEDULED): )(&lt;[^&lt;&gt;]+?&gt; *)$">
<bygroups>
<token type="Comment"/>
<token type="CommentSpecial"/>
</bygroups>
</rule>
<rule pattern="(?i)^( *CLOSED: )(\[[^][]+?\] *)$">
<bygroups>
<token type="Comment"/>
<token type="CommentSpecial"/>
</bygroups>
</rule>
<rule>
<include state="inline"/>
</rule>
</state>
<state name="inline">
<rule pattern="(\s)*(\*[^ \n*][^*]+?[^ \n*]\*)((?=\W|\n|$))">
<bygroups>
<token type="Text"/>
<token type="GenericStrong"/>
<token type="Text"/>
</bygroups>
</rule>
<rule pattern="(\s)*(/[^/]+?/)((?=\W|\n|$))">
<bygroups>
<token type="Text"/>
<token type="GenericEmph"/>
<token type="Text"/>
</bygroups>
</rule>
<rule pattern="(\s)*(=[^\n=]+?=)((?=\W|\n|$))">
<bygroups>
<token type="Text"/>
<token type="NameClass"/>
<token type="Text"/>
</bygroups>
</rule>
<rule pattern="(\s)*(~[^\n~]+?~)((?=\W|\n|$))">
<bygroups>
<token type="Text"/>
<token type="NameClass"/>
<token type="Text"/>
</bygroups>
</rule>
<rule pattern="(\s)*(\+[^+]+?\+)((?=\W|\n|$))">
<bygroups>
<token type="Text"/>
<token type="GenericDeleted"/>
<token type="Text"/>
</bygroups>
</rule>
<rule pattern="(\s)*(_[^_]+?_)((?=\W|\n|$))">
<bygroups>
<token type="Text"/>
<token type="GenericUnderline"/>
<token type="Text"/>
</bygroups>
</rule>
<rule pattern="(&lt;)([^&lt;&gt;]+?)(&gt;)">
<bygroups>
<token type="Text"/>
<token type="LiteralString"/>
<token type="Text"/>
</bygroups>
</rule>
<rule pattern="[{]{3}[^}]+[}]{3}">
<token type="NameBuiltin"/>
</rule>
<rule pattern="([^[])(\[fn:)([^]]+?)(\])([^]])">
<bygroups>
<token type="Text"/>
<token type="NameBuiltinPseudo"/>
<token type="LiteralString"/>
<token type="NameBuiltinPseudo"/>
<token type="Text"/>
</bygroups>
</rule>
<rule pattern="(\[\[)([^][]+?)(\]\[)([^][]+)(\]\])">
<bygroups>
<token type="Text"/>
<token type="NameAttribute"/>
<token type="Text"/>
<token type="NameTag"/>
<token type="Text"/>
</bygroups>
</rule>
<rule pattern="(\[\[)([^][]+?)(\]\])">
<bygroups>
<token type="Text"/>
<token type="NameAttribute"/>
<token type="Text"/>
</bygroups>
</rule>
<rule pattern="(&lt;&lt;)([^&lt;&gt;]+?)(&gt;&gt;)">
<bygroups>
<token type="Text"/>
<token type="NameAttribute"/>
<token type="Text"/>
</bygroups>
</rule>
<rule pattern="^( *)(\|[ -].*?[ -]\|)$">
<bygroups>
<token type="Text"/>
<token type="LiteralString"/>
</bygroups>
</rule>
<rule pattern="\n">
<token type="Text"/>
</rule>
<rule pattern=".">
<token type="Text"/>
</rule>
</state>
</rules>
</lexer>

21
lexers/embedded/plaintext.xml Normal file
View File

@@ -0,0 +1,21 @@
<lexer>
<config>
<name>plaintext</name>
<alias>text</alias>
<alias>plain</alias>
<alias>no-highlight</alias>
<filename>*.txt</filename>
<mime_type>text/plain</mime_type>
<priority>-1</priority>
</config>
<rules>
<state name="root">
<rule pattern=".+">
<token type="Text"/>
</rule>
<rule pattern="\n">
<token type="Text"/>
</rule>
</state>
</rules>
</lexer>

155
lexers/embedded/postgresql_sql_dialect.xml Normal file
View File

@@ -0,0 +1,155 @@
<lexer>
<config>
<name>PostgreSQL SQL dialect</name>
<alias>postgresql</alias>
<alias>postgres</alias>
<mime_type>text/x-postgresql</mime_type>
<case_insensitive>true</case_insensitive>
<not_multiline>true</not_multiline>
</config>
<rules>
<state name="root">
<rule pattern="\s+">
<token type="Text"/>
</rule>
<rule pattern="--.*\n?">
<token type="CommentSingle"/>
</rule>
<rule pattern="/\*">
<token type="CommentMultiline"/>
<push state="multiline-comments"/>
</rule>
<rule pattern="(bigint|bigserial|bit|bit\s+varying|bool|boolean|box|bytea|char|character|character\s+varying|cidr|circle|date|decimal|double\s+precision|float4|float8|inet|int|int2|int4|int8|integer|interval|json|jsonb|line|lseg|macaddr|money|numeric|path|pg_lsn|point|polygon|real|serial|serial2|serial4|serial8|smallint|smallserial|text|time|timestamp|timestamptz|timetz|tsquery|tsvector|txid_snapshot|uuid|varbit|varchar|with\s+time\s+zone|without\s+time\s+zone|xml|anyarray|anyelement|anyenum|anynonarray|anyrange|cstring|fdw_handler|internal|language_handler|opaque|record|void)\b">
<token type="NameBuiltin"/>
</rule>
<rule pattern="(?s)(DO)(\s+)(?:(LANGUAGE)?(\s+)(&#39;?)(\w+)?(&#39;?)(\s+))?(\$)([^$]*)(\$)(.*?)(\$)(\10)(\$)">
<usingbygroup>
<sublexer_name_group>6</sublexer_name_group>
<code_group>12</code_group>
<emitters>
<token type="Keyword"/>
<token type="Text"/>
<token type="Keyword"/>
<token type="Text"/>
<token type="LiteralStringSingle"/>
<token type="LiteralStringSingle"/>
<token type="LiteralStringSingle"/>
<token type="Text"/>
<token type="LiteralStringHeredoc"/>
<token type="LiteralStringHeredoc"/>
<token type="LiteralStringHeredoc"/>
<token type="LiteralStringHeredoc"/>
<token type="LiteralStringHeredoc"/>
<token type="LiteralStringHeredoc"/>
<token type="LiteralStringHeredoc"/>
</emitters>
</usingbygroup>
</rule>
<rule pattern="(CURRENT_TIMESTAMP|CHARACTERISTICS|CURRENT_CATALOG|CURRENT_SCHEMA|LOCALTIMESTAMP|CONFIGURATION|AUTHORIZATION|XMLATTRIBUTES|MATERIALIZED|SERIALIZABLE|CURRENT_DATE|XMLSERIALIZE|SESSION_USER|CURRENT_ROLE|CURRENT_USER|CONCURRENTLY|CURRENT_TIME|UNENCRYPTED|UNCOMMITTED|TRANSACTION|INSENSITIVE|CONSTRAINTS|ASSIGNMENT|ASYMMETRIC|DEALLOCATE|ORDINALITY|PRIVILEGES|DEFERRABLE|PROCEDURAL|CONVERSION|REFERENCES|WHITESPACE|TABLESPACE|CONSTRAINT|CONNECTION|STATISTICS|DELIMITERS|STANDALONE|DICTIONARY|REPEATABLE|CHECKPOINT|XMLELEMENT|LC_COLLATE|SYMMETRIC|PARTITION|SEQUENCES|FUNCTIONS|IMMEDIATE|IMMUTABLE|SAVEPOINT|EXTENSION|INCLUDING|RETURNING|COLLATION|INCREMENT|EXCLUSIVE|EXCLUDING|INITIALLY|COMMITTED|INTERSECT|STATEMENT|SUBSTRING|FOLLOWING|ISOLATION|TEMPORARY|ENCRYPTED|TIMESTAMP|RECURSIVE|LEAKPROOF|PROCEDURE|LOCALTIME|XMLFOREST|XMLEXISTS|AGGREGATE|ATTRIBUTE|UNBOUNDED|ASSERTION|XMLCONCAT|DELIMITER|CHARACTER|VALIDATOR|PRECISION|PRECEDING|LC_CTYPE|SECURITY|PREPARED|PASSWORD|VALIDATE|OVERLAPS|VARIADIC|DEFAULTS|VOLATILE|DEFERRED|OPERATOR|NATIONAL|UNLOGGED|UNLISTEN|TRAILING|BACKWARD|MAXVALUE|PRESERVE|DISTINCT|LOCATION|DOCUMENT|TRUNCATE|MINVALUE|POSITION|ABSOLUTE|XMLPARSE|LANGUAGE|ENCODING|CONTINUE|TEMPLATE|INTERVAL|CASCADED|DATABASE|RELATIVE|INHERITS|COMMENTS|SNAPSHOT|RESTRICT|COALESCE|IMPLICIT|ROLLBACK|EXTERNAL|REASSIGN|SMALLINT|IDENTITY|GREATEST|SEQUENCE|FUNCTION|DISCARD|CASCADE|DECIMAL|XMLROOT|FOREIGN|FORWARD|PARTIAL|PLACING|WRAPPER|WITHOUT|OVERLAY|DECLARE|PREPARE|GRANTED|CURRENT|DEFAULT|HANDLER|PRIMARY|OPTIONS|VERSION|VERBOSE|DEFINER|VARYING|ANALYSE|VARCHAR|EXTRACT|EXPLAIN|PROGRAM|RECHECK|EXECUTE|ANALYZE|INDEXES|INHERIT|EXCLUDE|CONTENT|REFRESH|REINDEX|NUMERIC|UNKNOWN|RELEASE|NOTNULL|INSTEAD|TRUSTED|INTEGER|NOTHING|COMMENT|TRIGGER|INVOKER|BETWEEN|REPLACE|REPLICA|RESTART|BOOLEAN|NATURAL|COLLATE|RETURNS|CLUSTER|LATERAL|STORAGE|DISABLE|LEADING|MAPPING|PASSING|SESSION|CATALOG|SIMILAR|SIMPLE|LISTEN|STABLE|SERVER|DOUBLE|DOMAIN|SELECT|SECOND|CALLED|SEARCH|SCROLL|STDOUT|MINUTE|SCHEMA|STRICT|REVOKE|SYSTEM|ENABLE|COLUMN|DELETE|TABLES|BINARY|BIGINT|ISNULL|BEFORE|RENAME|ESCAPE|NOTIFY|INSERT|NOWAIT|UNIQUE|NULLIF|COMMIT|UPDATE|OBJECT|VACUUM|INLINE|OFFSET|EXCEPT|EXISTS|VALUES|FAMILY|OPTION|HEADER|CREATE|HAVING|ALWAYS|WINDOW|CURSOR|WITHIN|GLOBAL|FILTER|POLICY|ACTION|PARSER|FREEZE|ACCESS|LOCAL|LEAST|OWNER|PLANS|OWNED|FORCE|XMLPI|CYCLE|ADMIN|OUTER|AFTER|ORDER|PRIOR|WRITE|CROSS|FIRST|GRANT|QUOTE|RANGE|FETCH|ALTER|WHERE|GROUP|VIEWS|ILIKE|FALSE|VALUE|INDEX|NULLS|VALID|INNER|USING|INOUT|UNTIL|RESET|NCHAR|NAMES|ARRAY|INPUT|MONTH|RIGHT|EVENT|UNION|TYPES|TREAT|BEGIN|CLOSE|LABEL|ABORT|MATCH|TABLE|CLASS|LARGE|CHECK|SYSID|CHAIN|FLOAT|STRIP|LIMIT|STDIN|SETOF|SHARE|CACHE|START|LEVEL|NAME|MOVE|SOME|LEFT|CAST|LIKE|DROP|SHOW|ZONE|EACH|ELSE|LAST|LOAD|YEAR|BOTH|CHAR|DATA|LOCK|DESC|FROM|TEMP|OVER|JOIN|TEXT|THEN|TIME|ALSO|FULL|WORK|RULE|ROWS|INTO|TRIM|TRUE|ENUM|ONLY|TYPE|WITH|READ|REAL|COST|MODE|ROLE|CASE|WHEN|COPY|NEXT|VIEW|USER|NONE|HOLD|NULL|HOUR|OIDS|BIT|ADD|SET|YES|FOR|AND|NOT|DAY|ANY|KEY|DEC|END|ASC|OFF|ROW|INT|REF|OUT|ALL|CSV|XML|ON|AT|NO|TO|AS|IN|DO|IS|IF|BY|OR|OF)\b">
<token type="Keyword"/>
</rule>
<rule pattern="[+*/&lt;&gt;=~!@#%^&amp;|`?-]+">
<token type="Operator"/>
</rule>
<rule pattern="::">
<token type="Operator"/>
</rule>
<rule pattern="\$\d+">
<token type="NameVariable"/>
</rule>
<rule pattern="([0-9]*\.[0-9]*|[0-9]+)(e[+-]?[0-9]+)?">
<token type="LiteralNumberFloat"/>
</rule>
<rule pattern="[0-9]+">
<token type="LiteralNumberInteger"/>
</rule>
<rule pattern="((?:E|U&amp;)?)(&#39;)">
<bygroups>
<token type="LiteralStringAffix"/>
<token type="LiteralStringSingle"/>
</bygroups>
<push state="string"/>
</rule>
<rule pattern="((?:U&amp;)?)(&#34;)">
<bygroups>
<token type="LiteralStringAffix"/>
<token type="LiteralStringName"/>
</bygroups>
<push state="quoted-ident"/>
</rule>
<rule pattern="(?s)(\$)([^$]*)(\$)(.*?)(\$)(\2)(\$)(\s+)(LANGUAGE)?(\s+)(&#39;?)(\w+)?(&#39;?)">
<usingbygroup>
<sublexer_name_group>12</sublexer_name_group>
<code_group>4</code_group>
<emitters>
<token type="LiteralStringHeredoc"/>
<token type="LiteralStringHeredoc"/>
<token type="LiteralStringHeredoc"/>
<token type="LiteralStringHeredoc"/>
<token type="LiteralStringHeredoc"/>
<token type="LiteralStringHeredoc"/>
<token type="LiteralStringHeredoc"/>
<token type="Text"/>
<token type="Keyword"/>
<token type="Text"/>
<token type="LiteralStringSingle"/>
<token type="LiteralStringSingle"/>
<token type="LiteralStringSingle"/>
</emitters>
</usingbygroup>
</rule>
<rule pattern="(?s)(\$)([^$]*)(\$)(.*?)(\$)(\2)(\$)">
<token type="LiteralStringHeredoc"/>
</rule>
<rule pattern="[a-z_]\w*">
<token type="Name"/>
</rule>
<rule pattern=":([&#39;&#34;]?)[a-z]\w*\b\1">
<token type="NameVariable"/>
</rule>
<rule pattern="[;:()\[\]{},.]">
<token type="Punctuation"/>
</rule>
</state>
<state name="multiline-comments">
<rule pattern="/\*">
<token type="CommentMultiline"/>
<push state="multiline-comments"/>
</rule>
<rule pattern="\*/">
<token type="CommentMultiline"/>
<pop depth="1"/>
</rule>
<rule pattern="[^/*]+">
<token type="CommentMultiline"/>
</rule>
<rule pattern="[/*]">
<token type="CommentMultiline"/>
</rule>
</state>
<state name="string">
<rule pattern="[^&#39;]+">
<token type="LiteralStringSingle"/>
</rule>
<rule pattern="&#39;&#39;">
<token type="LiteralStringSingle"/>
</rule>
<rule pattern="&#39;">
<token type="LiteralStringSingle"/>
<pop depth="1"/>
</rule>
</state>
<state name="quoted-ident">
<rule pattern="[^&#34;]+">
<token type="LiteralStringName"/>
</rule>
<rule pattern="&#34;&#34;">
<token type="LiteralStringName"/>
</rule>
<rule pattern="&#34;">
<token type="LiteralStringName"/>
<pop depth="1"/>
</rule>
</state>
</rules>
</lexer>

54
lexers/embedded/protobuf.xml → lexers/embedded/protocol_buffer.xml
View File

@@ -6,6 +6,33 @@
<filename>*.proto</filename>
</config>
<rules>
<state name="package">
<rule pattern="[a-zA-Z_]\w*">
<token type="NameNamespace"/>
<pop depth="1"/>
</rule>
<rule>
<pop depth="1"/>
</rule>
</state>
<state name="message">
<rule pattern="[a-zA-Z_]\w*">
<token type="NameClass"/>
<pop depth="1"/>
</rule>
<rule>
<pop depth="1"/>
</rule>
</state>
<state name="type">
<rule pattern="[a-zA-Z_]\w*">
<token type="Name"/>
<pop depth="1"/>
</rule>
<rule>
<pop depth="1"/>
</rule>
</state>
<state name="root">
<rule pattern="[ \t]+">
<token type="Text"/>
@@ -87,32 +114,5 @@
<token type="Name"/>
</rule>
</state>
<state name="package">
<rule pattern="[a-zA-Z_]\w*">
<token type="NameNamespace"/>
<pop depth="1"/>
</rule>
<rule>
<pop depth="1"/>
</rule>
</state>
<state name="message">
<rule pattern="[a-zA-Z_]\w*">
<token type="NameClass"/>
<pop depth="1"/>
</rule>
<rule>
<pop depth="1"/>
</rule>
</state>
<state name="type">
<rule pattern="[a-zA-Z_]\w*">
<token type="Name"/>
<pop depth="1"/>
</rule>
<rule>
<pop depth="1"/>
</rule>
</state>
</rules>
</lexer>

79
lexers/embedded/smarty.xml Normal file
View File

@@ -0,0 +1,79 @@
<lexer>
<config>
<name>Smarty</name>
<alias>smarty</alias>
<filename>*.tpl</filename>
<mime_type>application/x-smarty</mime_type>
<dot_all>true</dot_all>
</config>
<rules>
<state name="root">
<rule pattern="[^{]+">
<token type="Other"/>
</rule>
<rule pattern="(\{)(\*.*?\*)(\})">
<bygroups>
<token type="CommentPreproc"/>
<token type="Comment"/>
<token type="CommentPreproc"/>
</bygroups>
</rule>
<rule pattern="(\{php\})(.*?)(\{/php\})">
<bygroups>
<token type="CommentPreproc"/>
<using lexer="PHP"/>
<token type="CommentPreproc"/>
</bygroups>
</rule>
<rule pattern="(\{)(/?[a-zA-Z_]\w*)(\s*)">
<bygroups>
<token type="CommentPreproc"/>
<token type="NameFunction"/>
<token type="Text"/>
</bygroups>
<push state="smarty"/>
</rule>
<rule pattern="\{">
<token type="CommentPreproc"/>
<push state="smarty"/>
</rule>
</state>
<state name="smarty">
<rule pattern="\s+">
<token type="Text"/>
</rule>
<rule pattern="\{">
<token type="CommentPreproc"/>
<push/>
</rule>
<rule pattern="\}">
<token type="CommentPreproc"/>
<pop depth="1"/>
</rule>
<rule pattern="#[a-zA-Z_]\w*#">
<token type="NameVariable"/>
</rule>
<rule pattern="\$[a-zA-Z_]\w*(\.\w+)*">
<token type="NameVariable"/>
</rule>
<rule pattern="[~!%^&amp;*()+=|\[\]:;,.&lt;&gt;/?@-]">
<token type="Operator"/>
</rule>
<rule pattern="(true|false|null)\b">
<token type="KeywordConstant"/>
</rule>
<rule pattern="[0-9](\.[0-9]*)?(eE[+-][0-9])?[flFLdD]?|0[xX][0-9a-fA-F]+[Ll]?">
<token type="LiteralNumber"/>
</rule>
<rule pattern="&#34;(\\\\|\\&#34;|[^&#34;])*&#34;">
<token type="LiteralStringDouble"/>
</rule>
<rule pattern="&#39;(\\\\|\\&#39;|[^&#39;])*&#39;">
<token type="LiteralStringSingle"/>
</rule>
<rule pattern="[a-zA-Z_]\w*">
<token type="NameAttribute"/>
</rule>
</state>
</rules>
</lexer>

178
lexers/embedded/typoscript.xml Normal file
View File

@@ -0,0 +1,178 @@
<lexer>
<config>
<name>TypoScript</name>
<alias>typoscript</alias>
<filename>*.ts</filename>
<mime_type>text/x-typoscript</mime_type>
<dot_all>true</dot_all>
<priority>0.1</priority>
</config>
<rules>
<state name="whitespace">
<rule pattern="\s+">
<token type="Text"/>
</rule>
</state>
<state name="html">
<rule pattern="&lt;\S[^\n&gt;]*&gt;">
<using lexer="TypoScriptHTMLData"/>
</rule>
<rule pattern="&amp;[^;\n]*;">
<token type="LiteralString"/>
</rule>
<rule pattern="(_CSS_DEFAULT_STYLE)(\s*)(\()(?s)(.*(?=\n\)))">
<bygroups>
<token type="NameClass"/>
<token type="Text"/>
<token type="LiteralStringSymbol"/>
<using lexer="TypoScriptCSSData"/>
</bygroups>
</rule>
</state>
<state name="operator">
<rule pattern="[&lt;&gt;,:=.*%+|]">
<token type="Operator"/>
</rule>
</state>
<state name="structure">
<rule pattern="[{}()\[\]\\]">
<token type="LiteralStringSymbol"/>
</rule>
</state>
<state name="constant">
<rule pattern="(\{)(\$)((?:[\w\-]+\.)*)([\w\-]+)(\})">
<bygroups>
<token type="LiteralStringSymbol"/>
<token type="Operator"/>
<token type="NameConstant"/>
<token type="NameConstant"/>
<token type="LiteralStringSymbol"/>
</bygroups>
</rule>
<rule pattern="(\{)([\w\-]+)(\s*:\s*)([\w\-]+)(\})">
<bygroups>
<token type="LiteralStringSymbol"/>
<token type="NameConstant"/>
<token type="Operator"/>
<token type="NameConstant"/>
<token type="LiteralStringSymbol"/>
</bygroups>
</rule>
<rule pattern="(#[a-fA-F0-9]{6}\b|#[a-fA-F0-9]{3}\b)">
<token type="LiteralStringChar"/>
</rule>
</state>
<state name="comment">
<rule pattern="(?&lt;!(#|\&#39;|&#34;))(?:#(?!(?:[a-fA-F0-9]{6}|[a-fA-F0-9]{3}))[^\n#]+|//[^\n]*)">
<token type="Comment"/>
</rule>
<rule pattern="/\*(?:(?!\*/).)*\*/">
<token type="Comment"/>
</rule>
<rule pattern="(\s*#\s*\n)">
<token type="Comment"/>
</rule>
</state>
<state name="root">
<rule>
<include state="comment"/>
</rule>
<rule>
<include state="constant"/>
</rule>
<rule>
<include state="html"/>
</rule>
<rule>
<include state="label"/>
</rule>
<rule>
<include state="whitespace"/>
</rule>
<rule>
<include state="keywords"/>
</rule>
<rule>
<include state="punctuation"/>
</rule>
<rule>
<include state="operator"/>
</rule>
<rule>
<include state="structure"/>
</rule>
<rule>
<include state="literal"/>
</rule>
<rule>
<include state="other"/>
</rule>
</state>
<state name="literal">
<rule pattern="0x[0-9A-Fa-f]+t?">
<token type="LiteralNumberHex"/>
</rule>
<rule pattern="[0-9]+">
<token type="LiteralNumberInteger"/>
</rule>
<rule pattern="(###\w+###)">
<token type="NameConstant"/>
</rule>
</state>
<state name="label">
<rule pattern="(EXT|FILE|LLL):[^}\n&#34;]*">
<token type="LiteralString"/>
</rule>
<rule pattern="(?![^\w\-])([\w\-]+(?:/[\w\-]+)+/?)(\S*\n)">
<bygroups>
<token type="LiteralString"/>
<token type="LiteralString"/>
</bygroups>
</rule>
</state>
<state name="punctuation">
<rule pattern="[,.]">
<token type="Punctuation"/>
</rule>
</state>
<state name="other">
<rule pattern="[\w&#34;\-!/&amp;;]+">
<token type="Text"/>
</rule>
</state>
<state name="keywords">
<rule pattern="(\[)(?i)(browser|compatVersion|dayofmonth|dayofweek|dayofyear|device|ELSE|END|GLOBAL|globalString|globalVar|hostname|hour|IP|language|loginUser|loginuser|minute|month|page|PIDinRootline|PIDupinRootline|system|treeLevel|useragent|userFunc|usergroup|version)([^\]]*)(\])">
<bygroups>
<token type="LiteralStringSymbol"/>
<token type="NameConstant"/>
<token type="Text"/>
<token type="LiteralStringSymbol"/>
</bygroups>
</rule>
<rule pattern="(?=[\w\-])(HTMLparser|HTMLparser_tags|addParams|cache|encapsLines|filelink|if|imageLinkWrap|imgResource|makelinks|numRows|numberFormat|parseFunc|replacement|round|select|split|stdWrap|strPad|tableStyle|tags|textStyle|typolink)(?![\w\-])">
<token type="NameFunction"/>
</rule>
<rule pattern="(?:(=?\s*&lt;?\s+|^\s*))(cObj|field|config|content|constants|FEData|file|frameset|includeLibs|lib|page|plugin|register|resources|sitemap|sitetitle|styles|temp|tt_[^:.\s]*|types|xmlnews|INCLUDE_TYPOSCRIPT|_CSS_DEFAULT_STYLE|_DEFAULT_PI_VARS|_LOCAL_LANG)(?![\w\-])">
<bygroups>
<token type="Operator"/>
<token type="NameBuiltin"/>
</bygroups>
</rule>
<rule pattern="(?=[\w\-])(CASE|CLEARGIF|COA|COA_INT|COBJ_ARRAY|COLUMNS|CONTENT|CTABLE|EDITPANEL|FILE|FILES|FLUIDTEMPLATE|FORM|HMENU|HRULER|HTML|IMAGE|IMGTEXT|IMG_RESOURCE|LOAD_REGISTER|MEDIA|MULTIMEDIA|OTABLE|PAGE|QTOBJECT|RECORDS|RESTORE_REGISTER|SEARCHRESULT|SVG|SWFOBJECT|TEMPLATE|TEXT|USER|USER_INT)(?![\w\-])">
<token type="NameClass"/>
</rule>
<rule pattern="(?=[\w\-])(ACTIFSUBRO|ACTIFSUB|ACTRO|ACT|CURIFSUBRO|CURIFSUB|CURRO|CUR|IFSUBRO|IFSUB|NO|SPC|USERDEF1RO|USERDEF1|USERDEF2RO|USERDEF2|USRRO|USR)">
<token type="NameClass"/>
</rule>
<rule pattern="(?=[\w\-])(GMENU_FOLDOUT|GMENU_LAYERS|GMENU|IMGMENUITEM|IMGMENU|JSMENUITEM|JSMENU|TMENUITEM|TMENU_LAYERS|TMENU)">
<token type="NameClass"/>
</rule>
<rule pattern="(?=[\w\-])(PHP_SCRIPT(_EXT|_INT)?)">
<token type="NameClass"/>
</rule>
<rule pattern="(?=[\w\-])(userFunc)(?![\w\-])">
<token type="NameFunction"/>
</rule>
</state>
</rules>
</lexer>

355
lexers/embedded/v.xml Normal file
View File

@@ -0,0 +1,355 @@
<lexer>
<config>
<name>V</name>
<alias>v</alias>
<alias>vlang</alias>
<filename>*.v</filename>
<filename>*.vv</filename>
<filename>v.mod</filename>
<mime_type>text/x-v</mime_type>
<ensure_nl>true</ensure_nl>
</config>
<rules>
<state name="root">
<rule pattern="\n">
<token type="Text"/>
</rule>
<rule pattern="\s+">
<token type="Text"/>
</rule>
<rule pattern="\\\n">
<token type="Text"/>
</rule>
<rule pattern="(?&lt;=module\s+\w[^\n]*\s+)(//[^\n]+\n)+(?=\n)">
<token type="LiteralStringDoc"/>
</rule>
<rule pattern="(// *)(\w+)([^\n]+\n)(?=(?://[^\n]*\n)* *(?:pub +)?(?:fn|struct|union|type|interface|enum|const) +\2\b)">
<bygroups>
<token type="LiteralStringDoc"/>
<token type="GenericEmph"/>
<token type="LiteralStringDoc"/>
</bygroups>
<push state="string-doc"/>
</rule>
<rule pattern="//[^\n]*\n">
<token type="CommentSingle"/>
</rule>
<rule pattern="/\*(?:(?:/\*(?:.|\n)*?\*/)*|.|\n)*\*/">
<token type="CommentMultiline"/>
</rule>
<rule pattern="\b(import|module)\b">
<token type="KeywordNamespace"/>
</rule>
<rule pattern="\b(fn|struct|union|map|chan|type|interface|enum|const|mut|shared|pub|__global)\b">
<token type="KeywordDeclaration"/>
</rule>
<rule pattern="\?">
<token type="KeywordDeclaration"/>
</rule>
<rule pattern="(?&lt;=\)\s*)!">
<token type="KeywordDeclaration"/>
</rule>
<rule pattern="[ \t]*#include[^\n]+">
<using lexer="c"/>
</rule>
<rule pattern="[ \t]*#\w[^\n]*">
<token type="CommentPreproc"/>
</rule>
<rule pattern="(sql)(\s+)(\w+)(\s+)({)([^}]*?)(})">
<bygroups>
<token type="Keyword"/>
<token type="Text"/>
<token type="Name"/>
<token type="Text"/>
<token type="Punctuation"/>
<using lexer="sql"/>
<token type="Punctuation"/>
</bygroups>
</rule>
<rule pattern="\$(?=\w)">
<token type="Operator"/>
</rule>
<rule pattern="(?&lt;=\$)(?:embed_file|pkgconfig|tmpl|env|compile_error|compile_warn)">
<token type="NameBuiltin"/>
</rule>
<rule pattern="(asm)(\s+)(\w+)(\s*)({)([^}]*?)(})">
<bygroups>
<token type="Keyword"/>
<token type="Text"/>
<token type="KeywordType"/>
<token type="Text"/>
<token type="Punctuation"/>
<using lexer="nasm"/>
<token type="Punctuation"/>
</bygroups>
</rule>
<rule pattern="\b_(?:un)?likely_(?=\()">
<token type="NameFunctionMagic"/>
</rule>
<rule pattern="(?&lt;=\$if.+?(?:&amp;&amp;|\|\|)?)((no_segfault_handler|no_bounds_checking|little_endian|freestanding|no_backtrace|big_endian|cplusplus|dragonfly|prealloc|android|windows|no_main|solaris|darwin|clang|tinyc|glibc|mingw|haiku|macos|amd64|arm64|debug|linux|prod|msvc|test|hpux|mach|x32|x64|gcc|qnx|gnu|ios|mac|js))+">
<token type="NameBuiltin"/>
</rule>
<rule pattern="@(VMOD_FILE|VEXEROOT|VMODROOT|METHOD|STRUCT|COLUMN|VHASH|FILE|LINE|VEXE|MOD|FN)\b">
<token type="NameVariableMagic"/>
</rule>
<rule pattern="\b(?&lt;!@)(__offsetof|isreftype|continue|volatile|typeof|static|unsafe|return|assert|sizeof|atomic|select|match|break|defer|rlock|lock|else|goto|for|in|is|as|or|if|go)\b">
<token type="Keyword"/>
</rule>
<rule pattern="\b(?&lt;!@)(none|true|false|si_s_code|si_g32_code|si_g64_code)\b">
<token type="KeywordConstant"/>
</rule>
<rule pattern="\b(?&lt;!@)(vstring_literal_with_len|utf8_str_visible_length|get_str_intp_u64_format|get_str_intp_u32_format|utf32_decode_to_buffer|utf32_to_str_no_malloc|panic_optional_not_set|panic_result_not_set|contains_any_substr|strip_margin_custom|starts_with_capital|cstring_to_vstring|winapi_lasterr_str|c_error_number_str|panic_error_number|substr_with_check|string_from_wide2|sort_with_compare|trim_string_right|string_from_wide|sort_ignore_case|trim_string_left|reverse_in_place|split_into_lines|vstring_with_len|compare_strings|all_before_last|print_backtrace|repeat_to_depth|length_in_bytes|error_with_code|vstring_literal|gc_check_leaks|clone_to_depth|vcalloc_noscan|all_after_last|utf8_char_len|panic_lasterr|memdup_noscan|malloc_noscan|str_intp_rune|last_index_u8|utf8_to_utf32|flush_stderr|flush_stdout|str_intp_sub|replace_each|replace_once|vstrlen_char|utf8_getchar|str_intp_g64|contains_any|find_between|realloc_data|strip_margin|utf32_to_str|is_bin_digit|is_hex_digit|is_oct_digit|proc_pidpath|str_intp_g32|delete_many|delete_last|str_escaped|index_after|sort_by_len|str_intp_sq|starts_with|trim_space|last_index|parse_uint|is_capital|trim_right|join_lines|capitalize|all_before|after_char|match_glob|utf32_code|eq_epsilon|tos_clone|substr_ni|v_realloc|push_many|is_letter|split_nth|split_any|trim_left|index_any|ascii_str|parse_int|all_after|ends_with|is_title|contains|eprintln|is_space|index_u8|is_digit|vmemmove|byterune|is_alnum|pointers|grow_len|is_lower|grow_cap|str_intp|to_upper|hex_full|len_utf8|is_upper|try_push|to_lower|compare|vmemset|try_pop|vcalloc|reverse|vmemcmp|vstring|replace|ptr_str|strlong|to_wide|bytestr|f32_abs|f32_max|println|f32_min|f64_max|vmemcpy|vstrlen|prepend|vbytes|strsci|substr|string|insert|eprint|filter|delete|repeat|malloc|memdup|fields|before|reduce|string|isize|count|index|title|bytes|clone|usize|error|after|split|runes|print|panic|first|close|limit|isnil|bool|rune|tos3|u128|hex2|i128|hash|code|tos4|free|exit|keys|tos2|last|trim|strg|tos5|move|copy|drop|sort|dump|join|free|cap|int|any|all|any|len|map|pop|hex|f64|f32|u16|msg|i64|i16|u32|str|tos|u64|i8|u8)(?=\()">
<token type="NameBuiltin"/>
</rule>
<rule pattern="\b(?&lt;!@)(StrIntpCgenData|VAssertMetaInfo|StructAttribute|AttributeKind|FunctionData|StrIntpData|StrIntpType|MethodArgs|StrIntpMem|ArrayFlags|FieldData|SortedMap|ChanState|string|array|Error|map)\b">
<token type="NameBuiltin"/>
</rule>
<rule pattern="\b(?&lt;!@)(voidptr|string|error|isize|usize|i128|u128|bool|rune|int|f32|f64|i64|i16|u64|any|u32|u16|i8|u8)\b">
<token type="KeywordType"/>
</rule>
<rule pattern="\bit\b">
<token type="NameVariableMagic"/>
</rule>
<rule pattern="(?&lt;!fn\s+)(?&lt;=\w+\s+|^)\[(?=:if +)?(?=\w+)">
<token type="Punctuation"/>
<push state="attribute"/>
</rule>
<rule pattern="(&lt;&lt;=|&gt;&gt;=|&gt;&gt;&gt;=|&gt;&gt;&gt;|&lt;&lt;|&gt;&gt;|&lt;=|&gt;=|\^=|\+=|-=|\*=|/=|%=|&amp;=|\|=|&amp;&amp;|\|\||&lt;-|\+\+|--|==|!=|:=|\.\.\.|\.\.|[+\-*/%&amp;|^~=#@!])">
<token type="Operator"/>
</rule>
<rule pattern="[\d_]+(\.\d+e[+\-]?\d+|\.\d+|e[+\-]?\d+)">
<token type="LiteralNumberFloat"/>
</rule>
<rule pattern="\.\d+(e[+\-]?\d+)?">
<token type="LiteralNumberFloat"/>
</rule>
<rule pattern="0o[0-7_]+">
<token type="LiteralNumberOct"/>
</rule>
<rule pattern="0x[0-9a-fA-F_]+">
<token type="LiteralNumberHex"/>
</rule>
<rule pattern="0b[01_]+">
<token type="LiteralNumberBin"/>
</rule>
<rule pattern="(0|[1-9][0-9_]*)">
<token type="LiteralNumberInteger"/>
</rule>
<rule pattern="`">
<token type="LiteralStringChar"/>
<push state="char"/>
</rule>
<rule>
<include state="strings"/>
</rule>
<rule pattern="@?[A-Z]\w*">
<token type="NameClass"/>
</rule>
<rule pattern="(?&lt;=[^\W\d]\w*)(&lt;)([A-Z]\w*)(&gt;)">
<bygroups>
<token type="Punctuation"/>
<token type="NameClass"/>
<token type="Punctuation"/>
</bygroups>
</rule>
<rule pattern="@?[^\W\d]\w*(?=\()">
<token type="NameFunction"/>
</rule>
<rule pattern="(?&lt;=fn\s+)@?[^\W\d]\w*(?=\s*\()">
<token type="NameFunction"/>
</rule>
<rule pattern="(?&lt;=(?:continue|break|goto)\s+)\w+">
<token type="NameLabel"/>
</rule>
<rule pattern="\b[^\W\d]\w*(?=:(?:$|\s+for))">
<token type="NameLabel"/>
</rule>
<rule pattern="[&lt;&gt;()\[\]{}.,;:]">
<token type="Punctuation"/>
</rule>
<rule pattern="@?[^\W\d]\w*">
<token type="NameVariable"/>
</rule>
</state>
<state name="char">
<rule pattern="`">
<token type="LiteralStringChar"/>
<pop depth="1"/>
</rule>
<rule>
<include state="char-escape"/>
</rule>
<rule pattern="[^\\]">
<token type="LiteralStringChar"/>
</rule>
</state>
<state name="string-doc">
<rule pattern="(// *)(#+ [^\n]+)(\n)">
<bygroups>
<token type="LiteralStringDoc"/>
<token type="GenericHeading"/>
<token type="Text"/>
</bygroups>
</rule>
<rule pattern="// *([=_*~-])\1{2,}\n">
<token type="LiteralStringDelimiter"/>
</rule>
<rule pattern="//[^\n]*\n">
<token type="LiteralStringDoc"/>
</rule>
<rule>
<mutators>
<pop depth="1"/>
</mutators>
</rule>
</state>
<state name="string-curly-interpolation">
<rule pattern="}">
<token type="Punctuation"/>
<pop depth="1"/>
</rule>
<rule>
<include state="strings"/>
</rule>
<rule pattern="(:)( *?)([ 0&#39;#+-])?(?:(\.)?([0-9]+))?([fFgeEGxXobsd])?">
<bygroups>
<token type="Punctuation"/>
<token type="Text"/>
<token type="Operator"/>
<token type="Punctuation"/>
<token type="LiteralNumber"/>
<token type="LiteralStringAffix"/>
</bygroups>
</rule>
<rule pattern="[^}&#34;&#39;:]+">
<usingself state="root"/>
</rule>
</state>
<state name="attribute">
<rule pattern="\]">
<token type="Punctuation"/>
<pop depth="1"/>
</rule>
<rule pattern="&#39;">
<token type="Punctuation"/>
<push state="string-single"/>
</rule>
<rule pattern="&#34;">
<token type="Punctuation"/>
<push state="string-double"/>
</rule>
<rule pattern="[;:]">
<token type="Punctuation"/>
</rule>
<rule pattern="(?&lt;=\[)if\b">
<token type="Keyword"/>
</rule>
<rule pattern="\s+">
<token type="Text"/>
</rule>
<rule pattern="(?&lt;=: *)\w+">
<token type="LiteralString"/>
</rule>
<rule pattern="[^\W\d]\w*">
<token type="NameAttribute"/>
</rule>
</state>
<state name="strings">
<rule pattern="(c)?(&#34;)">
<bygroups>
<token type="LiteralStringAffix"/>
<token type="LiteralStringDouble"/>
</bygroups>
<push state="string-double"/>
</rule>
<rule pattern="(c)?(&#39;)">
<bygroups>
<token type="LiteralStringAffix"/>
<token type="LiteralStringSingle"/>
</bygroups>
<push state="string-single"/>
</rule>
<rule pattern="(r)(&#34;[^&#34;]+&#34;)">
<bygroups>
<token type="LiteralStringAffix"/>
<token type="LiteralString"/>
</bygroups>
</rule>
<rule pattern="(r)(&#39;[^&#39;]+&#39;)">
<bygroups>
<token type="LiteralStringAffix"/>
<token type="LiteralString"/>
</bygroups>
</rule>
</state>
<state name="string-double">
<rule pattern="&#34;">
<token type="LiteralStringDouble"/>
<pop depth="1"/>
</rule>
<rule>
<include state="char-escape"/>
</rule>
<rule pattern="(\$)((?!\\){)">
<bygroups>
<token type="Operator"/>
<token type="Punctuation"/>
</bygroups>
<push state="string-curly-interpolation"/>
</rule>
<rule pattern="\$">
<token type="Operator"/>
<push state="string-interpolation"/>
</rule>
<rule pattern="[^&#34;]+?">
<token type="LiteralStringDouble"/>
</rule>
</state>
<state name="string-single">
<rule pattern="&#39;">
<token type="LiteralStringSingle"/>
<pop depth="1"/>
</rule>
<rule>
<include state="char-escape"/>
</rule>
<rule pattern="(\$)((?!\\){)">
<bygroups>
<token type="Operator"/>
<token type="Punctuation"/>
</bygroups>
<push state="string-curly-interpolation"/>
</rule>
<rule pattern="\$">
<token type="Operator"/>
<push state="string-interpolation"/>
</rule>
<rule pattern="[^&#39;]+?">
<token type="LiteralStringSingle"/>
</rule>
</state>
<state name="char-escape">
<rule pattern="\\[`&#39;&#34;\\abfnrtv$]|\\x[0-9a-fA-F]{2}|\\[0-7]{1,3}|\\u[0-9a-fA-F]{4}|\\U[0-9a-fA-F]{8}">
<token type="LiteralStringEscape"/>
</rule>
</state>
<state name="string-interpolation">
<rule pattern="(\.)?(@)?(?:([^\W\d]\w*)(\()([^)]*)(\))|([^\W\d]\w*))">
<bygroups>
<token type="Punctuation"/>
<token type="Operator"/>
<token type="NameFunction"/>
<token type="Punctuation"/>
<usingself state="root"/>
<token type="Punctuation"/>
<token type="NameVariable"/>
</bygroups>
</rule>
<rule>
<mutators>
<pop depth="1"/>
</mutators>
</rule>
</state>
</rules>
</lexer>

365
lexers/embedded/v_shell.xml Normal file
View File

@@ -0,0 +1,365 @@
<lexer>
<config>
<name>V shell</name>
<alias>vsh</alias>
<alias>vshell</alias>
<filename>*.vsh</filename>
<mime_type>text/x-vsh</mime_type>
<ensure_nl>true</ensure_nl>
</config>
<rules>
<state name="attribute">
<rule pattern="\]">
<token type="Punctuation"/>
<pop depth="1"/>
</rule>
<rule pattern="&#39;">
<token type="Punctuation"/>
<push state="string-single"/>
</rule>
<rule pattern="&#34;">
<token type="Punctuation"/>
<push state="string-double"/>
</rule>
<rule pattern="[;:]">
<token type="Punctuation"/>
</rule>
<rule pattern="(?&lt;=\[)if\b">
<token type="Keyword"/>
</rule>
<rule pattern="\s+">
<token type="Text"/>
</rule>
<rule pattern="(?&lt;=: *)\w+">
<token type="LiteralString"/>
</rule>
<rule pattern="[^\W\d]\w*">
<token type="NameAttribute"/>
</rule>
</state>
<state name="string-double">
<rule pattern="&#34;">
<token type="LiteralStringDouble"/>
<pop depth="1"/>
</rule>
<rule>
<include state="char-escape"/>
</rule>
<rule pattern="(\$)((?!\\){)">
<bygroups>
<token type="Operator"/>
<token type="Punctuation"/>
</bygroups>
<push state="string-curly-interpolation"/>
</rule>
<rule pattern="\$">
<token type="Operator"/>
<push state="string-interpolation"/>
</rule>
<rule pattern="[^&#34;]+?">
<token type="LiteralStringDouble"/>
</rule>
</state>
<state name="char">
<rule pattern="`">
<token type="LiteralStringChar"/>
<pop depth="1"/>
</rule>
<rule>
<include state="char-escape"/>
</rule>
<rule pattern="[^\\]">
<token type="LiteralStringChar"/>
</rule>
</state>
<state name="string-doc">
<rule pattern="(// *)(#+ [^\n]+)(\n)">
<bygroups>
<token type="LiteralStringDoc"/>
<token type="GenericHeading"/>
<token type="Text"/>
</bygroups>
</rule>
<rule pattern="// *([=_*~-])\1{2,}\n">
<token type="LiteralStringDelimiter"/>
</rule>
<rule pattern="//[^\n]*\n">
<token type="LiteralStringDoc"/>
</rule>
<rule>
<mutators>
<pop depth="1"/>
</mutators>
</rule>
</state>
<state name="string-interpolation">
<rule pattern="(\.)?(@)?(?:([^\W\d]\w*)(\()([^)]*)(\))|([^\W\d]\w*))">
<bygroups>
<token type="Punctuation"/>
<token type="Operator"/>
<token type="NameFunction"/>
<token type="Punctuation"/>
<usingself state="root"/>
<token type="Punctuation"/>
<token type="NameVariable"/>
</bygroups>
</rule>
<rule>
<mutators>
<pop depth="1"/>
</mutators>
</rule>
</state>
<state name="string-curly-interpolation">
<rule pattern="}">
<token type="Punctuation"/>
<pop depth="1"/>
</rule>
<rule>
<include state="strings"/>
</rule>
<rule pattern="(:)( *?)([ 0&#39;#+-])?(?:(\.)?([0-9]+))?([fFgeEGxXobsd])?">
<bygroups>
<token type="Punctuation"/>
<token type="Text"/>
<token type="Operator"/>
<token type="Punctuation"/>
<token type="LiteralNumber"/>
<token type="LiteralStringAffix"/>
</bygroups>
</rule>
<rule pattern="[^}&#34;&#39;:]+">
<usingself state="root"/>
</rule>
</state>
<state name="root">
<rule pattern="^#![^\n]*\n">
<token type="CommentHashbang"/>
</rule>
<rule pattern="\b(path_delimiter|path_separator|wd_at_startup|max_path_len|sys_write|sys_close|sys_mkdir|sys_creat|sys_open|s_iflnk|s_irusr|s_ifdir|s_ixoth|s_isuid|s_isgid|s_isvtx|s_iwoth|s_iwusr|s_ixusr|s_irgrp|s_iwgrp|s_ixgrp|s_iroth|s_ifmt|args)\b">
<token type="NameConstant"/>
</rule>
<rule pattern="\b(ExecutableNotFoundError|FileNotOpenedError|SizeOfTypeIs0Error|ProcessState|SeekMode|Command|Process|Signal|Result|Uname|File)\b">
<token type="NameBuiltin"/>
</rule>
<rule pattern="\b(find_abs_path_of_executable|posix_set_permission_bit|read_bytes_into_newline|sigint_to_signal_name|exists_in_system_path|get_raw_lines_joined|expand_tilde_to_home|posix_get_error_msg|set_redirect_stdio|is_writable_folder|file_last_mod_unix|walk_with_context|resource_abs_path|debugger_present|write_file_array|join_path_single|execute_or_panic|get_lines_joined|set_environment|read_bytes_into|read_file_array|execute_or_exit|signal_continue|write_struct_at|read_struct_at|vmodules_paths|get_error_msg|signal_pgkill|read_into_ptr|read_bytes_at|existing_path|is_executable|get_raw_stdin|is_dir_empty|write_struct|vmodules_dir|stdout_slurp|write_raw_at|write_string|get_raw_line|stderr_slurp|signal_kill|stderr_read|signal_stop|quoted_path|stdin_write|stdout_read|open_append|new_process|args_before|read_struct|is_writable|is_readable|is_abs_path|read_raw_at|write_file|getenv_opt|args_after|read_lines|read_bytes|signal_opt|config_dir|last_error|executable|file_name|file_size|rmdir_all|write_raw|real_path|join_path|input_opt|norm_path|read_from|get_lines|loginname|read_file|cache_dir|mkdir_all|read_line|open_file|home_dir|hostname|fd_slurp|fd_close|mv_by_cp|open_uri|file_ext|walk_ext|unsetenv|write_to|fd_write|abs_path|read_raw|is_alive|get_line|truncate|temp_dir|set_args|geteuid|is_file|getppid|bitmask|is_atty|execute|symlink|environ|fd_read|is_link|writeln|getegid|user_os|is_dir|stdout|create|fileno|cp_all|system|getenv|vfopen|execve|getgid|stderr|getuid|execvp|exists|setenv|getpid|flush|getwd|input|stdin|mkdir|chdir|chmod|start|chown|rmdir|uname|write|close|utime|inode|wait|seek|base|fork|open|link|glob|read|tell|walk|msg|dir|run|log|cp|mv|rm|ls)(?=\()">
<token type="NameBuiltin"/>
</rule>
<rule pattern="\n">
<token type="Text"/>
</rule>
<rule pattern="\s+">
<token type="Text"/>
</rule>
<rule pattern="\\\n">
<token type="Text"/>
</rule>
<rule pattern="(?&lt;=module\s+\w[^\n]*\s+)(//[^\n]+\n)+(?=\n)">
<token type="LiteralStringDoc"/>
</rule>
<rule pattern="(// *)(\w+)([^\n]+\n)(?=(?://[^\n]*\n)* *(?:pub +)?(?:fn|struct|union|type|interface|enum|const) +\2\b)">
<bygroups>
<token type="LiteralStringDoc"/>
<token type="GenericEmph"/>
<token type="LiteralStringDoc"/>
</bygroups>
<push state="string-doc"/>
</rule>
<rule pattern="//[^\n]*\n">
<token type="CommentSingle"/>
</rule>
<rule pattern="/\*(?:(?:/\*(?:.|\n)*?\*/)*|.|\n)*\*/">
<token type="CommentMultiline"/>
</rule>
<rule pattern="\b(import|module)\b">
<token type="KeywordNamespace"/>
</rule>
<rule pattern="\b(fn|struct|union|map|chan|type|interface|enum|const|mut|shared|pub|__global)\b">
<token type="KeywordDeclaration"/>
</rule>
<rule pattern="\?">
<token type="KeywordDeclaration"/>
</rule>
<rule pattern="(?&lt;=\)\s*)!">
<token type="KeywordDeclaration"/>
</rule>
<rule pattern="[ \t]*#include[^\n]+">
<using lexer="c"/>
</rule>
<rule pattern="[ \t]*#\w[^\n]*">
<token type="CommentPreproc"/>
</rule>
<rule pattern="(sql)(\s+)(\w+)(\s+)({)([^}]*?)(})">
<bygroups>
<token type="Keyword"/>
<token type="Text"/>
<token type="Name"/>
<token type="Text"/>
<token type="Punctuation"/>
<using lexer="sql"/>
<token type="Punctuation"/>
</bygroups>
</rule>
<rule pattern="\$(?=\w)">
<token type="Operator"/>
</rule>
<rule pattern="(?&lt;=\$)(?:embed_file|pkgconfig|tmpl|env|compile_error|compile_warn)">
<token type="NameBuiltin"/>
</rule>
<rule pattern="(asm)(\s+)(\w+)(\s*)({)([^}]*?)(})">
<bygroups>
<token type="Keyword"/>
<token type="Text"/>
<token type="KeywordType"/>
<token type="Text"/>
<token type="Punctuation"/>
<using lexer="nasm"/>
<token type="Punctuation"/>
</bygroups>
</rule>
<rule pattern="\b_(?:un)?likely_(?=\()">
<token type="NameFunctionMagic"/>
</rule>
<rule pattern="(?&lt;=\$if.+?(?:&amp;&amp;|\|\|)?)((no_segfault_handler|no_bounds_checking|little_endian|freestanding|no_backtrace|big_endian|cplusplus|dragonfly|prealloc|android|windows|no_main|solaris|darwin|clang|tinyc|glibc|mingw|haiku|macos|amd64|arm64|debug|linux|prod|msvc|test|hpux|mach|x32|x64|gcc|qnx|gnu|ios|mac|js))+">
<token type="NameBuiltin"/>
</rule>
<rule pattern="@(VMOD_FILE|VEXEROOT|VMODROOT|METHOD|STRUCT|COLUMN|VHASH|FILE|LINE|VEXE|MOD|FN)\b">
<token type="NameVariableMagic"/>
</rule>
<rule pattern="\b(?&lt;!@)(__offsetof|isreftype|continue|volatile|typeof|static|unsafe|return|assert|sizeof|atomic|select|match|break|defer|rlock|lock|else|goto|for|in|is|as|or|if|go)\b">
<token type="Keyword"/>
</rule>
<rule pattern="\b(?&lt;!@)(none|true|false|si_s_code|si_g32_code|si_g64_code)\b">
<token type="KeywordConstant"/>
</rule>
<rule pattern="\b(?&lt;!@)(vstring_literal_with_len|utf8_str_visible_length|get_str_intp_u64_format|get_str_intp_u32_format|utf32_decode_to_buffer|utf32_to_str_no_malloc|panic_optional_not_set|panic_result_not_set|contains_any_substr|strip_margin_custom|starts_with_capital|cstring_to_vstring|winapi_lasterr_str|c_error_number_str|panic_error_number|substr_with_check|string_from_wide2|sort_with_compare|trim_string_right|string_from_wide|sort_ignore_case|trim_string_left|reverse_in_place|split_into_lines|vstring_with_len|compare_strings|all_before_last|print_backtrace|repeat_to_depth|length_in_bytes|error_with_code|vstring_literal|gc_check_leaks|clone_to_depth|vcalloc_noscan|all_after_last|utf8_char_len|panic_lasterr|memdup_noscan|malloc_noscan|str_intp_rune|last_index_u8|utf8_to_utf32|flush_stderr|flush_stdout|str_intp_sub|replace_each|replace_once|vstrlen_char|utf8_getchar|str_intp_g64|contains_any|find_between|realloc_data|strip_margin|utf32_to_str|is_bin_digit|is_hex_digit|is_oct_digit|proc_pidpath|str_intp_g32|delete_many|delete_last|str_escaped|index_after|sort_by_len|str_intp_sq|starts_with|trim_space|last_index|parse_uint|is_capital|trim_right|join_lines|capitalize|all_before|after_char|match_glob|utf32_code|eq_epsilon|tos_clone|substr_ni|v_realloc|push_many|is_letter|split_nth|split_any|trim_left|index_any|ascii_str|parse_int|all_after|ends_with|is_title|contains|eprintln|is_space|index_u8|is_digit|vmemmove|byterune|is_alnum|pointers|grow_len|is_lower|grow_cap|str_intp|to_upper|hex_full|len_utf8|is_upper|try_push|to_lower|compare|vmemset|try_pop|vcalloc|reverse|vmemcmp|vstring|replace|ptr_str|strlong|to_wide|bytestr|f32_abs|f32_max|println|f32_min|f64_max|vmemcpy|vstrlen|prepend|vbytes|strsci|substr|string|insert|eprint|filter|delete|repeat|malloc|memdup|fields|before|reduce|string|isize|count|index|title|bytes|clone|usize|error|after|split|runes|print|panic|first|close|limit|isnil|bool|rune|tos3|u128|hex2|i128|hash|code|tos4|free|exit|keys|tos2|last|trim|strg|tos5|move|copy|drop|sort|dump|join|free|cap|int|any|all|any|len|map|pop|hex|f64|f32|u16|msg|i64|i16|u32|str|tos|u64|i8|u8)(?=\()">
<token type="NameBuiltin"/>
</rule>
<rule pattern="\b(?&lt;!@)(StrIntpCgenData|VAssertMetaInfo|StructAttribute|AttributeKind|FunctionData|StrIntpData|StrIntpType|MethodArgs|StrIntpMem|ArrayFlags|FieldData|SortedMap|ChanState|string|array|Error|map)\b">
<token type="NameBuiltin"/>
</rule>
<rule pattern="\b(?&lt;!@)(voidptr|string|error|isize|usize|i128|u128|bool|rune|int|f32|f64|i64|i16|u64|any|u32|u16|i8|u8)\b">
<token type="KeywordType"/>
</rule>
<rule pattern="\bit\b">
<token type="NameVariableMagic"/>
</rule>
<rule pattern="(?&lt;!fn\s+)(?&lt;=\w+\s+|^)\[(?=:if +)?(?=\w+)">
<token type="Punctuation"/>
<push state="attribute"/>
</rule>
<rule pattern="(&lt;&lt;=|&gt;&gt;=|&gt;&gt;&gt;=|&gt;&gt;&gt;|&lt;&lt;|&gt;&gt;|&lt;=|&gt;=|\^=|\+=|-=|\*=|/=|%=|&amp;=|\|=|&amp;&amp;|\|\||&lt;-|\+\+|--|==|!=|:=|\.\.\.|\.\.|[+\-*/%&amp;|^~=#@!])">
<token type="Operator"/>
</rule>
<rule pattern="[\d_]+(\.\d+e[+\-]?\d+|\.\d+|e[+\-]?\d+)">
<token type="LiteralNumberFloat"/>
</rule>
<rule pattern="\.\d+(e[+\-]?\d+)?">
<token type="LiteralNumberFloat"/>
</rule>
<rule pattern="0o[0-7_]+">
<token type="LiteralNumberOct"/>
</rule>
<rule pattern="0x[0-9a-fA-F_]+">
<token type="LiteralNumberHex"/>
</rule>
<rule pattern="0b[01_]+">
<token type="LiteralNumberBin"/>
</rule>
<rule pattern="(0|[1-9][0-9_]*)">
<token type="LiteralNumberInteger"/>
</rule>
<rule pattern="`">
<token type="LiteralStringChar"/>
<push state="char"/>
</rule>
<rule>
<include state="strings"/>
</rule>
<rule pattern="@?[A-Z]\w*">
<token type="NameClass"/>
</rule>
<rule pattern="(?&lt;=[^\W\d]\w*)(&lt;)([A-Z]\w*)(&gt;)">
<bygroups>
<token type="Punctuation"/>
<token type="NameClass"/>
<token type="Punctuation"/>
</bygroups>
</rule>
<rule pattern="@?[^\W\d]\w*(?=\()">
<token type="NameFunction"/>
</rule>
<rule pattern="(?&lt;=fn\s+)@?[^\W\d]\w*(?=\s*\()">
<token type="NameFunction"/>
</rule>
<rule pattern="(?&lt;=(?:continue|break|goto)\s+)\w+">
<token type="NameLabel"/>
</rule>
<rule pattern="\b[^\W\d]\w*(?=:(?:$|\s+for))">
<token type="NameLabel"/>
</rule>
<rule pattern="[&lt;&gt;()\[\]{}.,;:]">
<token type="Punctuation"/>
</rule>
<rule pattern="@?[^\W\d]\w*">
<token type="NameVariable"/>
</rule>
</state>
<state name="strings">
<rule pattern="(c)?(&#34;)">
<bygroups>
<token type="LiteralStringAffix"/>
<token type="LiteralStringDouble"/>
</bygroups>
<push state="string-double"/>
</rule>
<rule pattern="(c)?(&#39;)">
<bygroups>
<token type="LiteralStringAffix"/>
<token type="LiteralStringSingle"/>
</bygroups>
<push state="string-single"/>
</rule>
<rule pattern="(r)(&#34;[^&#34;]+&#34;)">
<bygroups>
<token type="LiteralStringAffix"/>
<token type="LiteralString"/>
</bygroups>
</rule>
<rule pattern="(r)(&#39;[^&#39;]+&#39;)">
<bygroups>
<token type="LiteralStringAffix"/>
<token type="LiteralString"/>
</bygroups>
</rule>
</state>
<state name="string-single">
<rule pattern="&#39;">
<token type="LiteralStringSingle"/>
<pop depth="1"/>
</rule>
<rule>
<include state="char-escape"/>
</rule>
<rule pattern="(\$)((?!\\){)">
<bygroups>
<token type="Operator"/>
<token type="Punctuation"/>
</bygroups>
<push state="string-curly-interpolation"/>
</rule>
<rule pattern="\$">
<token type="Operator"/>
<push state="string-interpolation"/>
</rule>
<rule pattern="[^&#39;]+?">
<token type="LiteralStringSingle"/>
</rule>
</state>
<state name="char-escape">
<rule pattern="\\[`&#39;&#34;\\abfnrtv$]|\\x[0-9a-fA-F]{2}|\\[0-7]{1,3}|\\u[0-9a-fA-F]{4}|\\U[0-9a-fA-F]{8}">
<token type="LiteralStringEscape"/>
</rule>
</state>
</rules>
</lexer>

85
lexers/embedded/viml.xml Normal file
View File

@@ -0,0 +1,85 @@
<lexer>
<config>
<name>VimL</name>
<alias>vim</alias>
<filename>*.vim</filename>
<filename>.vimrc</filename>
<filename>.exrc</filename>
<filename>.gvimrc</filename>
<filename>_vimrc</filename>
<filename>_exrc</filename>
<filename>_gvimrc</filename>
<filename>vimrc</filename>
<filename>gvimrc</filename>
<mime_type>text/x-vim</mime_type>
</config>
<rules>
<state name="root">
<rule pattern="^([ \t:]*)(py(?:t(?:h(?:o(?:n)?)?)?)?)([ \t]*)(&lt;&lt;)([ \t]*)(.*)((?:\n|.)*)(\6)">
<bygroups>
<usingself state="root"/>
<token type="Keyword"/>
<token type="Text"/>
<token type="Operator"/>
<token type="Text"/>
<token type="Text"/>
<using lexer="Python"/>
<token type="Text"/>
</bygroups>
</rule>
<rule pattern="^([ \t:]*)(py(?:t(?:h(?:o(?:n)?)?)?)?)([ \t])(.*)">
<bygroups>
<usingself state="root"/>
<token type="Keyword"/>
<token type="Text"/>
<using lexer="Python"/>
</bygroups>
</rule>
<rule pattern="^\s*&#34;.*">
<token type="Comment"/>
</rule>
<rule pattern="[ \t]+">
<token type="Text"/>
</rule>
<rule pattern="/(\\\\|\\/|[^\n/])*/">
<token type="LiteralStringRegex"/>
</rule>
<rule pattern="&#34;(\\\\|\\&#34;|[^\n&#34;])*&#34;">
<token type="LiteralStringDouble"/>
</rule>
<rule pattern="&#39;(&#39;&#39;|[^\n&#39;])*&#39;">
<token type="LiteralStringSingle"/>
</rule>
<rule pattern="(?&lt;=\s)&#34;[^\-:.%#=*].*">
<token type="Comment"/>
</rule>
<rule pattern="-?\d+">
<token type="LiteralNumber"/>
</rule>
<rule pattern="#[0-9a-f]{6}">
<token type="LiteralNumberHex"/>
</rule>
<rule pattern="^:">
<token type="Punctuation"/>
</rule>
<rule pattern="[()&lt;&gt;+=!|,~-]">
<token type="Punctuation"/>
</rule>
<rule pattern="\b(let|if|else|endif|elseif|fun|function|endfunction|set|map|autocmd|filetype|hi(ghlight)?|execute|syntax|colorscheme)\b">
<token type="Keyword"/>
</rule>
<rule pattern="\b(NONE|bold|italic|underline|dark|light)\b">
<token type="NameBuiltin"/>
</rule>
<rule pattern="\b\w+\b">
<token type="NameOther"/>
</rule>
<rule pattern="\n">
<token type="Text"/>
</rule>
<rule pattern=".">
<token type="Text"/>
</rule>
</state>
</rules>
</lexer>

165
lexers/embedded/wgsl.xml → lexers/embedded/webgpu_shading_language.xml
View File

File diff suppressed because one or more lines are too long

36
lexers/embedded/z80.xml
View File

@@ -1,36 +0,0 @@
<lexer>
<config>
<name>Z80 Assembly</name>
<alias>z80</alias>
<filename>*.z80</filename>
<filename>*.asm</filename>
<case_insensitive>true</case_insensitive>
</config>
<rules>
<state name="root">
<rule pattern=";.*?$"><token type="CommentSingle"/></rule>
<rule pattern="^[.\w]+:"><token type="NameLabel"/></rule>
<rule pattern="((0x)|\$)[0-9a-fA-F]+"><token type="LiteralNumberHex"/></rule>
<rule pattern="[0-9][0-9a-fA-F]+h"><token type="LiteralNumberHex"/></rule>
<rule pattern="((0b)|%)[01]+"><token type="LiteralNumberBin"/></rule>
<rule pattern="-?[0-9]+"><token type="LiteralNumberInteger"/></rule>
<rule pattern="&quot;"><token type="LiteralString"/><push state="string"/></rule>
<rule pattern="&#x27;\\?.&#x27;"><token type="LiteralStringChar"/></rule>
<rule pattern="[,=()\\]"><token type="Punctuation"/></rule>
<rule pattern="^\s*#\w+"><token type="CommentPreproc"/></rule>
<rule pattern="\.(db|dw|end|org|byte|word|fill|block|addinstr|echo|error|list|nolist|equ|show|option|seek)"><token type="NameBuiltin"/></rule>
<rule pattern="(ex|exx|ld|ldd|lddr|ldi|ldir|pop|push|adc|add|cp|cpd|cpdr|cpi|cpir|cpl|daa|dec|inc|neg|sbc|sub|and|bit|ccf|or|res|scf|set|xor|rl|rla|rlc|rlca|rld|rr|rra|rrc|rrca|rrd|sla|sra|srl|call|djnz|jp|jr|ret|rst|nop|reti|retn|di|ei|halt|im|in|ind|indr|ini|inir|out|outd|otdr|outi|otir)"><token type="Keyword"/></rule>
<rule pattern="(z|nz|c|nc|po|pe|p|m)"><token type="Keyword"/></rule>
<rule pattern="[+-/*~\^&amp;|]"><token type="Operator"/></rule>
<rule pattern="\w+"><token type="Text"/></rule>
<rule pattern="\s+"><token type="Text"/></rule>
</state>
<state name="string">
<rule pattern="[^&quot;\\]+"><token type="LiteralString"/></rule>
<rule pattern="\\."><token type="LiteralStringEscape"/></rule>
<rule pattern="&quot;"><token type="LiteralString"/><pop depth="1"/></rule>
</state>
</rules>
</lexer>

74
lexers/embedded/z80_assembly.xml Normal file
View File

@@ -0,0 +1,74 @@
<lexer>
<config>
<name>Z80 Assembly</name>
<alias>z80</alias>
<filename>*.z80</filename>
<filename>*.asm</filename>
<case_insensitive>true</case_insensitive>
</config>
<rules>
<state name="string">
<rule pattern="[^&#34;\\]+">
<token type="LiteralString"/>
</rule>
<rule pattern="\\.">
<token type="LiteralStringEscape"/>
</rule>
<rule pattern="&#34;">
<token type="LiteralString"/>
<pop depth="1"/>
</rule>
</state>
<state name="root">
<rule pattern=";.*?$">
<token type="CommentSingle"/>
</rule>
<rule pattern="^[.\w]+:">
<token type="NameLabel"/>
</rule>
<rule pattern="((0x)|\$)[0-9a-fA-F]+">
<token type="LiteralNumberHex"/>
</rule>
<rule pattern="[0-9][0-9a-fA-F]+h">
<token type="LiteralNumberHex"/>
</rule>
<rule pattern="((0b)|%)[01]+">
<token type="LiteralNumberBin"/>
</rule>
<rule pattern="-?[0-9]+">
<token type="LiteralNumberInteger"/>
</rule>
<rule pattern="&#34;">
<token type="LiteralString"/>
<push state="string"/>
</rule>
<rule pattern="&#39;\\?.&#39;">
<token type="LiteralStringChar"/>
</rule>
<rule pattern="[,=()\\]">
<token type="Punctuation"/>
</rule>
<rule pattern="^\s*#\w+">
<token type="CommentPreproc"/>
</rule>
<rule pattern="\.(db|dw|end|org|byte|word|fill|block|addinstr|echo|error|list|nolist|equ|show|option|seek)">
<token type="NameBuiltin"/>
</rule>
<rule pattern="(ex|exx|ld|ldd|lddr|ldi|ldir|pop|push|adc|add|cp|cpd|cpdr|cpi|cpir|cpl|daa|dec|inc|neg|sbc|sub|and|bit|ccf|or|res|scf|set|xor|rl|rla|rlc|rlca|rld|rr|rra|rrc|rrca|rrd|sla|sra|srl|call|djnz|jp|jr|ret|rst|nop|reti|retn|di|ei|halt|im|in|ind|indr|ini|inir|out|outd|otdr|outi|otir)">
<token type="Keyword"/>
</rule>
<rule pattern="(z|nz|c|nc|po|pe|p|m)">
<token type="Keyword"/>
</rule>
<rule pattern="[+-/*~\^&amp;|]">
<token type="Operator"/>
</rule>
<rule pattern="\w+">
<token type="Text"/>
</rule>
<rule pattern="\s+">
<token type="Text"/>
</rule>
</state>
</rules>
</lexer>

38
lexers/fortran_fixed.go
View File

@@ -1,38 +0,0 @@
package lexers
import (
. "github.com/alecthomas/chroma/v2" // nolint
)
// FortranFixed lexer.
var FortranFixed = Register(MustNewLexer(
&Config{
Name: "FortranFixed",
Aliases: []string{"fortranfixed"},
Filenames: []string{"*.f", "*.F"},
MimeTypes: []string{"text/x-fortran"},
NotMultiline: true,
CaseInsensitive: true,
},
func() Rules {
return Rules{
"root": {
{`[C*].*\n`, Comment, nil},
{`#.*\n`, CommentPreproc, nil},
{` {0,4}!.*\n`, Comment, nil},
{`(.{5})`, NameLabel, Push("cont-char")},
{`.*\n`, Using("Fortran"), nil},
},
"cont-char": {
{` `, TextWhitespace, Push("code")},
{`.`, GenericStrong, Push("code")},
},
"code": {
{`(.{66})(.*)(\n)`, ByGroups(Using("Fortran"), Comment, TextWhitespace), Push("root")},
{`(.*)(!.*)(\n)`, ByGroups(Using("Fortran"), Comment, TextWhitespace), Push("root")},
{`(.*)(\n)`, ByGroups(Using("Fortran"), TextWhitespace), Push("root")},
Default(Push("root")),
},
}
},
))

56
lexers/html.go
View File

@@ -1,60 +1,8 @@
package lexers
import (
. "github.com/alecthomas/chroma/v2" // nolint
"github.com/alecthomas/chroma/v2"
)
// HTML lexer.
var HTML = Register(MustNewLexer(
&Config{
Name: "HTML",
Aliases: []string{"html"},
Filenames: []string{"*.html", "*.htm", "*.xhtml", "*.xslt"},
MimeTypes: []string{"text/html", "application/xhtml+xml"},
NotMultiline: true,
DotAll: true,
CaseInsensitive: true,
},
htmlRules,
))
func htmlRules() Rules {
return Rules{
"root": {
{`[^<&]+`, Text, nil},
{`&\S*?;`, NameEntity, nil},
{`\<\!\[CDATA\[.*?\]\]\>`, CommentPreproc, nil},
{`<!--`, Comment, Push("comment")},
{`<\?.*?\?>`, CommentPreproc, nil},
{`<![^>]*>`, CommentPreproc, nil},
{`(<)(\s*)(script)(\s*)`, ByGroups(Punctuation, Text, NameTag, Text), Push("script-content", "tag")},
{`(<)(\s*)(style)(\s*)`, ByGroups(Punctuation, Text, NameTag, Text), Push("style-content", "tag")},
{`(<)(\s*)([\w:.-]+)`, ByGroups(Punctuation, Text, NameTag), Push("tag")},
{`(<)(\s*)(/)(\s*)([\w:.-]+)(\s*)(>)`, ByGroups(Punctuation, Text, Punctuation, Text, NameTag, Text, Punctuation), nil},
},
"comment": {
{`[^-]+`, Comment, nil},
{`-->`, Comment, Pop(1)},
{`-`, Comment, nil},
},
"tag": {
{`\s+`, Text, nil},
{`([\w:-]+\s*)(=)(\s*)`, ByGroups(NameAttribute, Operator, Text), Push("attr")},
{`[\w:-]+`, NameAttribute, nil},
{`(/?)(\s*)(>)`, ByGroups(Punctuation, Text, Punctuation), Pop(1)},
},
"script-content": {
{`(<)(\s*)(/)(\s*)(script)(\s*)(>)`, ByGroups(Punctuation, Text, Punctuation, Text, NameTag, Text, Punctuation), Pop(1)},
{`.+?(?=<\s*/\s*script\s*>)`, Using("Javascript"), nil},
},
"style-content": {
{`(<)(\s*)(/)(\s*)(style)(\s*)(>)`, ByGroups(Punctuation, Text, Punctuation, Text, NameTag, Text, Punctuation), Pop(1)},
{`.+?(?=<\s*/\s*style\s*>)`, Using("CSS"), nil},
},
"attr": {
{`".*?"`, LiteralString, Pop(1)},
{`'.*?'`, LiteralString, Pop(1)},
{`[^\s>]+`, LiteralString, Pop(1)},
},
}
}
var HTML = chroma.MustNewXMLLexer(embedded, "embedded/html.xml")

56
lexers/make.go
View File

@@ -1,56 +0,0 @@
package lexers
import (
. "github.com/alecthomas/chroma/v2" // nolint
)
// Makefile lexer.
var Makefile = Register(MustNewLexer(
&Config{
Name: "Makefile",
Aliases: []string{"make", "makefile", "mf", "bsdmake"},
Filenames: []string{"*.mak", "*.mk", "Makefile", "makefile", "Makefile.*", "GNUmakefile", "BSDmakefile"},
MimeTypes: []string{"text/x-makefile"},
EnsureNL: true,
},
makefileRules,
))
func makefileRules() Rules {
return Rules{
"root": {
{`^(?:[\t ]+.*\n|\n)+`, Using("Bash"), nil},
{`\$[<@$+%?|*]`, Keyword, nil},
{`\s+`, Text, nil},
{`#.*?\n`, Comment, nil},
{`(export)(\s+)(?=[\w${}\t -]+\n)`, ByGroups(Keyword, Text), Push("export")},
{`export\s+`, Keyword, nil},
{`([\w${}().-]+)(\s*)([!?:+]?=)([ \t]*)((?:.*\\\n)+|.*\n)`, ByGroups(NameVariable, Text, Operator, Text, Using("Bash")), nil},
{`(?s)"(\\\\|\\.|[^"\\])*"`, LiteralStringDouble, nil},
{`(?s)'(\\\\|\\.|[^'\\])*'`, LiteralStringSingle, nil},
{`([^\n:]+)(:+)([ \t]*)`, ByGroups(NameFunction, Operator, Text), Push("block-header")},
{`\$\(`, Keyword, Push("expansion")},
},
"expansion": {
{`[^$a-zA-Z_()]+`, Text, nil},
{`[a-zA-Z_]+`, NameVariable, nil},
{`\$`, Keyword, nil},
{`\(`, Keyword, Push()},
{`\)`, Keyword, Pop(1)},
},
"export": {
{`[\w${}-]+`, NameVariable, nil},
{`\n`, Text, Pop(1)},
{`\s+`, Text, nil},
},
"block-header": {
{`[,|]`, Punctuation, nil},
{`#.*?\n`, Comment, Pop(1)},
{`\\\n`, Text, nil},
{`\$\(`, Keyword, Push("expansion")},
{`[a-zA-Z_]+`, Name, nil},
{`\n`, Text, Pop(1)},
{`.`, Text, nil},
},
}
}

62
lexers/mako.go
View File

@@ -1,62 +0,0 @@
package lexers
import (
. "github.com/alecthomas/chroma/v2" // nolint
)
// Mako lexer.
var Mako = Register(MustNewLexer(
&Config{
Name: "Mako",
Aliases: []string{"mako"},
Filenames: []string{"*.mao"},
MimeTypes: []string{"application/x-mako"},
},
makoRules,
))
func makoRules() Rules {
return Rules{
"root": {
{`(\s*)(%)(\s*end(?:\w+))(\n|\Z)`, ByGroups(Text, CommentPreproc, Keyword, Other), nil},
{`(\s*)(%)([^\n]*)(\n|\Z)`, ByGroups(Text, CommentPreproc, Using("Python"), Other), nil},
{`(\s*)(##[^\n]*)(\n|\Z)`, ByGroups(Text, CommentPreproc, Other), nil},
{`(?s)<%doc>.*?</%doc>`, CommentPreproc, nil},
{`(<%)([\w.:]+)`, ByGroups(CommentPreproc, NameBuiltin), Push("tag")},
{`(</%)([\w.:]+)(>)`, ByGroups(CommentPreproc, NameBuiltin, CommentPreproc), nil},
{`<%(?=([\w.:]+))`, CommentPreproc, Push("ondeftags")},
{`(<%(?:!?))(.*?)(%>)(?s)`, ByGroups(CommentPreproc, Using("Python"), CommentPreproc), nil},
{`(\$\{)(.*?)(\})`, ByGroups(CommentPreproc, Using("Python"), CommentPreproc), nil},
{`(?sx)
(.+?) # anything, followed by:
(?:
(?<=\n)(?=%|\#\#) | # an eval or comment line
(?=\#\*) | # multiline comment
(?=</?%) | # a python block
# call start or end
(?=\$\{) | # a substitution
(?<=\n)(?=\s*%) |
# - don't consume
(\\\n) | # an escaped newline
\Z # end of string
)
`, ByGroups(Other, Operator), nil},
{`\s+`, Text, nil},
},
"ondeftags": {
{`<%`, CommentPreproc, nil},
{`(?<=<%)(include|inherit|namespace|page)`, NameBuiltin, nil},
Include("tag"),
},
"tag": {
{`((?:\w+)\s*=)(\s*)(".*?")`, ByGroups(NameAttribute, Text, LiteralString), nil},
{`/?\s*>`, CommentPreproc, Pop(1)},
{`\s+`, Text, nil},
},
"attr": {
{`".*?"`, LiteralString, Pop(1)},
{`'.*?'`, LiteralString, Pop(1)},
{`[^\s>]+`, LiteralString, Pop(1)},
},
}
}

44
lexers/mason.go
View File

@@ -1,44 +0,0 @@
package lexers
import (
. "github.com/alecthomas/chroma/v2" // nolint
)
// Mason lexer.
var Mason = Register(MustNewLexer(
&Config{
Name: "Mason",
Aliases: []string{"mason"},
Filenames: []string{"*.m", "*.mhtml", "*.mc", "*.mi", "autohandler", "dhandler"},
MimeTypes: []string{"application/x-mason"},
Priority: 0.1,
},
masonRules,
))
func masonRules() Rules {
return Rules{
"root": {
{`\s+`, Text, nil},
{`(<%doc>)(.*?)(</%doc>)(?s)`, ByGroups(NameTag, CommentMultiline, NameTag), nil},
{`(<%(?:def|method))(\s*)(.*?)(>)(.*?)(</%\2\s*>)(?s)`, ByGroups(NameTag, Text, NameFunction, NameTag, UsingSelf("root"), NameTag), nil},
{`(<%\w+)(.*?)(>)(.*?)(</%\2\s*>)(?s)`, ByGroups(NameTag, NameFunction, NameTag, Using("Perl"), NameTag), nil},
{`(<&[^|])(.*?)(,.*?)?(&>)(?s)`, ByGroups(NameTag, NameFunction, Using("Perl"), NameTag), nil},
{`(<&\|)(.*?)(,.*?)?(&>)(?s)`, ByGroups(NameTag, NameFunction, Using("Perl"), NameTag), nil},
{`</&>`, NameTag, nil},
{`(<%!?)(.*?)(%>)(?s)`, ByGroups(NameTag, Using("Perl"), NameTag), nil},
{`(?<=^)#[^\n]*(\n|\Z)`, Comment, nil},
{`(?<=^)(%)([^\n]*)(\n|\Z)`, ByGroups(NameTag, Using("Perl"), Other), nil},
{`(?sx)
(.+?) # anything, followed by:
(?:
(?<=\n)(?=[%#]) | # an eval or comment line
(?=</?[%&]) | # a substitution or block or
# call start or end
# - don't consume
(\\\n) | # an escaped newline
\Z # end of string
)`, ByGroups(Using("HTML"), Operator), nil},
},
}
}

42
lexers/myghty.go
View File

@@ -1,42 +0,0 @@
package lexers
import (
. "github.com/alecthomas/chroma/v2" // nolint
)
// Myghty lexer.
var Myghty = Register(MustNewLexer(
&Config{
Name: "Myghty",
Aliases: []string{"myghty"},
Filenames: []string{"*.myt", "autodelegate"},
MimeTypes: []string{"application/x-myghty"},
},
myghtyRules,
))
func myghtyRules() Rules {
return Rules{
"root": {
{`\s+`, Text, nil},
{`(<%(?:def|method))(\s*)(.*?)(>)(.*?)(</%\2\s*>)(?s)`, ByGroups(NameTag, Text, NameFunction, NameTag, UsingSelf("root"), NameTag), nil},
{`(<%\w+)(.*?)(>)(.*?)(</%\2\s*>)(?s)`, ByGroups(NameTag, NameFunction, NameTag, Using("Python2"), NameTag), nil},
{`(<&[^|])(.*?)(,.*?)?(&>)`, ByGroups(NameTag, NameFunction, Using("Python2"), NameTag), nil},
{`(<&\|)(.*?)(,.*?)?(&>)(?s)`, ByGroups(NameTag, NameFunction, Using("Python2"), NameTag), nil},
{`</&>`, NameTag, nil},
{`(<%!?)(.*?)(%>)(?s)`, ByGroups(NameTag, Using("Python2"), NameTag), nil},
{`(?<=^)#[^\n]*(\n|\Z)`, Comment, nil},
{`(?<=^)(%)([^\n]*)(\n|\Z)`, ByGroups(NameTag, Using("Python2"), Other), nil},
{`(?sx)
(.+?) # anything, followed by:
(?:
(?<=\n)(?=[%#]) | # an eval or comment line
(?=</?[%&]) | # a substitution or block or
# call start or end
# - don't consume
(\\\n) | # an escaped newline
\Z # end of string
)`, ByGroups(Other, Operator), nil},
},
}
}

49
lexers/openedgeabl.go
View File

File diff suppressed because one or more lines are too long

99
lexers/org.go
View File

@@ -1,99 +0,0 @@
package lexers
import (
. "github.com/alecthomas/chroma/v2" // nolint
)
// Org mode lexer.
var Org = Register(MustNewLexer(
&Config{
Name: "Org Mode",
Aliases: []string{"org", "orgmode"},
Filenames: []string{"*.org"},
MimeTypes: []string{"text/org"}, // https://lists.gnu.org/r/emacs-orgmode/2017-09/msg00087.html
},
orgRules,
))
func orgRules() Rules {
return Rules{
"root": {
{`^# .*$`, Comment, nil},
// Headings
{`^(\*)( COMMENT)( .*)$`, ByGroups(GenericHeading, NameEntity, GenericStrong), nil},
{`^(\*\*+)( COMMENT)( .*)$`, ByGroups(GenericSubheading, NameEntity, Text), nil},
{`^(\*)( DONE)( .*)$`, ByGroups(GenericHeading, LiteralStringRegex, GenericStrong), nil},
{`^(\*\*+)( DONE)( .*)$`, ByGroups(GenericSubheading, LiteralStringRegex, Text), nil},
{`^(\*)( TODO)( .*)$`, ByGroups(GenericHeading, Error, GenericStrong), nil},
{`^(\*\*+)( TODO)( .*)$`, ByGroups(GenericSubheading, Error, Text), nil},
{`^(\*)( .+?)( :[a-zA-Z0-9_@:]+:)$`, ByGroups(GenericHeading, GenericStrong, GenericEmph), nil}, // Level 1 heading with tags
{`^(\*)( .+)$`, ByGroups(GenericHeading, GenericStrong), nil}, // // Level 1 heading with NO tags
{`^(\*\*+)( .+?)( :[a-zA-Z0-9_@:]+:)$`, ByGroups(GenericSubheading, Text, GenericEmph), nil}, // Level 2+ heading with tags
{`^(\*\*+)( .+)$`, ByGroups(GenericSubheading, Text), nil}, // Level 2+ heading with NO tags
// Checkbox lists
{`^( *)([+-] )(\[[ X]\])( .+)$`, ByGroups(Text, Keyword, Keyword, UsingSelf("inline")), nil},
{`^( +)(\* )(\[[ X]\])( .+)$`, ByGroups(Text, Keyword, Keyword, UsingSelf("inline")), nil},
// Definition lists
{`^( *)([+-] )([^ \n]+ ::)( .+)$`, ByGroups(Text, Keyword, Keyword, UsingSelf("inline")), nil},
{`^( +)(\* )([^ \n]+ ::)( .+)$`, ByGroups(Text, Keyword, Keyword, UsingSelf("inline")), nil},
// Unordered lists
{`^( *)([+-] )(.+)$`, ByGroups(Text, Keyword, UsingSelf("inline")), nil},
{`^( +)(\* )(.+)$`, ByGroups(Text, Keyword, UsingSelf("inline")), nil},
// Ordered lists
{`^( *)([0-9]+[.)])( \[@[0-9]+\])( .+)$`, ByGroups(Text, Keyword, GenericEmph, UsingSelf("inline")), nil},
{`^( *)([0-9]+[.)])( .+)$`, ByGroups(Text, Keyword, UsingSelf("inline")), nil},
// Dynamic Blocks
{`(?i)^( *#\+begin: )([^ ]+)([\w\W]*?\n)([\w\W]*?)(^ *#\+end: *$)`, ByGroups(Comment, CommentSpecial, Comment, UsingSelf("inline"), Comment), nil},
// Blocks
// - Comment Blocks
{`(?i)^( *#\+begin_comment *\n)([\w\W]*?)(^ *#\+end_comment *$)`, ByGroups(Comment, Comment, Comment), nil},
// - Src Blocks
{
`(?i)^( *#\+begin_src )([^ \n]+)(.*?\n)([\w\W]*?)(^ *#\+end_src *$)`,
UsingByGroup(2, 4, Comment, CommentSpecial, Comment, Text, Comment),
nil,
},
// - Export Blocks
{
`(?i)^( *#\+begin_export )(\w+)( *\n)([\w\W]*?)(^ *#\+end_export *$)`,
UsingByGroup(2, 4, Comment, CommentSpecial, Text, Text, Comment),
nil,
},
// - Org Special, Example, Verse, etc. Blocks
{`(?i)^( *#\+begin_)(\w+)( *\n)([\w\W]*?)(^ *#\+end_\2)( *$)`, ByGroups(Comment, Comment, Text, Text, Comment, Text), nil},
// Keywords
{`^(#\+\w+)(:.*)$`, ByGroups(CommentSpecial, Comment), nil}, // Other Org keywords like #+title
// Properties and Drawers
{`(?i)^( *:\w+: *\n)([\w\W]*?)(^ *:end: *$)`, ByGroups(Comment, CommentSpecial, Comment), nil},
// Line break operator
{`^(.*)(\\\\)$`, ByGroups(UsingSelf("inline"), Operator), nil},
// Deadline/Scheduled
{`(?i)^( *(?:DEADLINE|SCHEDULED): )(<[^<>]+?> *)$`, ByGroups(Comment, CommentSpecial), nil}, // DEADLINE/SCHEDULED: <datestamp>
// DONE state CLOSED
{`(?i)^( *CLOSED: )(\[[^][]+?\] *)$`, ByGroups(Comment, CommentSpecial), nil}, // CLOSED: [datestamp]
// All other lines
Include("inline"),
},
"inline": {
{`(\s)*(\*[^ \n*][^*]+?[^ \n*]\*)((?=\W|\n|$))`, ByGroups(Text, GenericStrong, Text), nil}, // Bold
{`(\s)*(/[^/]+?/)((?=\W|\n|$))`, ByGroups(Text, GenericEmph, Text), nil}, // Italic
{`(\s)*(=[^\n=]+?=)((?=\W|\n|$))`, ByGroups(Text, NameClass, Text), nil}, // Verbatim
{`(\s)*(~[^\n~]+?~)((?=\W|\n|$))`, ByGroups(Text, NameClass, Text), nil}, // Code
{`(\s)*(\+[^+]+?\+)((?=\W|\n|$))`, ByGroups(Text, GenericDeleted, Text), nil}, // Strikethrough
{`(\s)*(_[^_]+?_)((?=\W|\n|$))`, ByGroups(Text, GenericUnderline, Text), nil}, // Underline
{`(<)([^<>]+?)(>)`, ByGroups(Text, String, Text), nil}, // <datestamp>
{`[{]{3}[^}]+[}]{3}`, NameBuiltin, nil}, // {{{macro(foo,1)}}}
{`([^[])(\[fn:)([^]]+?)(\])([^]])`, ByGroups(Text, NameBuiltinPseudo, LiteralString, NameBuiltinPseudo, Text), nil}, // [fn:1]
// Links
{`(\[\[)([^][]+?)(\]\[)([^][]+)(\]\])`, ByGroups(Text, NameAttribute, Text, NameTag, Text), nil}, // [[link][descr]]
{`(\[\[)([^][]+?)(\]\])`, ByGroups(Text, NameAttribute, Text), nil}, // [[link]]
{`(<<)([^<>]+?)(>>)`, ByGroups(Text, NameAttribute, Text), nil}, // <<targetlink>>
// Tables
{`^( *)(\|[ -].*?[ -]\|)$`, ByGroups(Text, String), nil},
// Blank lines, newlines
{`\n`, Text, nil},
// Any other text
{`.`, Text, nil},
},
}
}

16
lexers/plaintext.go
View File

@@ -1,16 +0,0 @@
package lexers
import (
. "github.com/alecthomas/chroma/v2" // nolint
)
var Plaintext = Register(MustNewLexer(
&Config{
Name: "plaintext",
Aliases: []string{"text", "plain", "no-highlight"},
Filenames: []string{"*.txt"},
MimeTypes: []string{"text/plain"},
Priority: -1,
},
PlaintextRules,
))

77
lexers/postgres.go
View File

@@ -1,77 +0,0 @@
package lexers
import (
. "github.com/alecthomas/chroma/v2" // nolint
)
// Postgresql Sql Dialect lexer.
var PostgreSQL = Register(MustNewLexer(
&Config{
Name: "PostgreSQL SQL dialect",
Aliases: []string{"postgresql", "postgres"},
Filenames: []string{},
MimeTypes: []string{"text/x-postgresql"},
NotMultiline: true,
CaseInsensitive: true,
},
postgreSQLRules,
))
func postgreSQLRules() Rules {
return Rules{
"root": {
{`\s+`, Text, nil},
{`--.*\n?`, CommentSingle, nil},
{`/\*`, CommentMultiline, Push("multiline-comments")},
{`(bigint|bigserial|bit|bit\s+varying|bool|boolean|box|bytea|char|character|character\s+varying|cidr|circle|date|decimal|double\s+precision|float4|float8|inet|int|int2|int4|int8|integer|interval|json|jsonb|line|lseg|macaddr|money|numeric|path|pg_lsn|point|polygon|real|serial|serial2|serial4|serial8|smallint|smallserial|text|time|timestamp|timestamptz|timetz|tsquery|tsvector|txid_snapshot|uuid|varbit|varchar|with\s+time\s+zone|without\s+time\s+zone|xml|anyarray|anyelement|anyenum|anynonarray|anyrange|cstring|fdw_handler|internal|language_handler|opaque|record|void)\b`, NameBuiltin, nil},
{
`(?s)(DO)(\s+)(?:(LANGUAGE)?(\s+)('?)(\w+)?('?)(\s+))?(\$)([^$]*)(\$)(.*?)(\$)(\10)(\$)`,
UsingByGroup(6, 12,
Keyword, Text, Keyword, Text, // DO LANGUAGE
StringSingle, StringSingle, StringSingle, Text, // 'plpgsql'
StringHeredoc, StringHeredoc, StringHeredoc, // $tag$
StringHeredoc, // (code block)
StringHeredoc, StringHeredoc, StringHeredoc), // $tag$
nil,
},
{Words(``, `\b`, `ABORT`, `ABSOLUTE`, `ACCESS`, `ACTION`, `ADD`, `ADMIN`, `AFTER`, `AGGREGATE`, `ALL`, `ALSO`, `ALTER`, `ALWAYS`, `ANALYSE`, `ANALYZE`, `AND`, `ANY`, `ARRAY`, `AS`, `ASC`, `ASSERTION`, `ASSIGNMENT`, `ASYMMETRIC`, `AT`, `ATTRIBUTE`, `AUTHORIZATION`, `BACKWARD`, `BEFORE`, `BEGIN`, `BETWEEN`, `BIGINT`, `BINARY`, `BIT`, `BOOLEAN`, `BOTH`, `BY`, `CACHE`, `CALLED`, `CASCADE`, `CASCADED`, `CASE`, `CAST`, `CATALOG`, `CHAIN`, `CHAR`, `CHARACTER`, `CHARACTERISTICS`, `CHECK`, `CHECKPOINT`, `CLASS`, `CLOSE`, `CLUSTER`, `COALESCE`, `COLLATE`, `COLLATION`, `COLUMN`, `COMMENT`, `COMMENTS`, `COMMIT`, `COMMITTED`, `CONCURRENTLY`, `CONFIGURATION`, `CONNECTION`, `CONSTRAINT`, `CONSTRAINTS`, `CONTENT`, `CONTINUE`, `CONVERSION`, `COPY`, `COST`, `CREATE`, `CROSS`, `CSV`, `CURRENT`, `CURRENT_CATALOG`, `CURRENT_DATE`, `CURRENT_ROLE`, `CURRENT_SCHEMA`, `CURRENT_TIME`, `CURRENT_TIMESTAMP`, `CURRENT_USER`, `CURSOR`, `CYCLE`, `DATA`, `DATABASE`, `DAY`, `DEALLOCATE`, `DEC`, `DECIMAL`, `DECLARE`, `DEFAULT`, `DEFAULTS`, `DEFERRABLE`, `DEFERRED`, `DEFINER`, `DELETE`, `DELIMITER`, `DELIMITERS`, `DESC`, `DICTIONARY`, `DISABLE`, `DISCARD`, `DISTINCT`, `DO`, `DOCUMENT`, `DOMAIN`, `DOUBLE`, `DROP`, `EACH`, `ELSE`, `ENABLE`, `ENCODING`, `ENCRYPTED`, `END`, `ENUM`, `ESCAPE`, `EVENT`, `EXCEPT`, `EXCLUDE`, `EXCLUDING`, `EXCLUSIVE`, `EXECUTE`, `EXISTS`, `EXPLAIN`, `EXTENSION`, `EXTERNAL`, `EXTRACT`, `FALSE`, `FAMILY`, `FETCH`, `FILTER`, `FIRST`, `FLOAT`, `FOLLOWING`, `FOR`, `FORCE`, `FOREIGN`, `FORWARD`, `FREEZE`, `FROM`, `FULL`, `FUNCTION`, `FUNCTIONS`, `GLOBAL`, `GRANT`, `GRANTED`, `GREATEST`, `GROUP`, `HANDLER`, `HAVING`, `HEADER`, `HOLD`, `HOUR`, `IDENTITY`, `IF`, `ILIKE`, `IMMEDIATE`, `IMMUTABLE`, `IMPLICIT`, `IN`, `INCLUDING`, `INCREMENT`, `INDEX`, `INDEXES`, `INHERIT`, `INHERITS`, `INITIALLY`, `INLINE`, `INNER`, `INOUT`, `INPUT`, `INSENSITIVE`, `INSERT`, `INSTEAD`, `INT`, `INTEGER`, `INTERSECT`, `INTERVAL`, `INTO`, `INVOKER`, `IS`, `ISNULL`, `ISOLATION`, `JOIN`, `KEY`, `LABEL`, `LANGUAGE`, `LARGE`, `LAST`, `LATERAL`, `LC_COLLATE`, `LC_CTYPE`, `LEADING`, `LEAKPROOF`, `LEAST`, `LEFT`, `LEVEL`, `LIKE`, `LIMIT`, `LISTEN`, `LOAD`, `LOCAL`, `LOCALTIME`, `LOCALTIMESTAMP`, `LOCATION`, `LOCK`, `MAPPING`, `MATCH`, `MATERIALIZED`, `MAXVALUE`, `MINUTE`, `MINVALUE`, `MODE`, `MONTH`, `MOVE`, `NAME`, `NAMES`, `NATIONAL`, `NATURAL`, `NCHAR`, `NEXT`, `NO`, `NONE`, `NOT`, `NOTHING`, `NOTIFY`, `NOTNULL`, `NOWAIT`, `NULL`, `NULLIF`, `NULLS`, `NUMERIC`, `OBJECT`, `OF`, `OFF`, `OFFSET`, `OIDS`, `ON`, `ONLY`, `OPERATOR`, `OPTION`, `OPTIONS`, `OR`, `ORDER`, `ORDINALITY`, `OUT`, `OUTER`, `OVER`, `OVERLAPS`, `OVERLAY`, `OWNED`, `OWNER`, `PARSER`, `PARTIAL`, `PARTITION`, `PASSING`, `PASSWORD`, `PLACING`, `PLANS`, `POLICY`, `POSITION`, `PRECEDING`, `PRECISION`, `PREPARE`, `PREPARED`, `PRESERVE`, `PRIMARY`, `PRIOR`, `PRIVILEGES`, `PROCEDURAL`, `PROCEDURE`, `PROGRAM`, `QUOTE`, `RANGE`, `READ`, `REAL`, `REASSIGN`, `RECHECK`, `RECURSIVE`, `REF`, `REFERENCES`, `REFRESH`, `REINDEX`, `RELATIVE`, `RELEASE`, `RENAME`, `REPEATABLE`, `REPLACE`, `REPLICA`, `RESET`, `RESTART`, `RESTRICT`, `RETURNING`, `RETURNS`, `REVOKE`, `RIGHT`, `ROLE`, `ROLLBACK`, `ROW`, `ROWS`, `RULE`, `SAVEPOINT`, `SCHEMA`, `SCROLL`, `SEARCH`, `SECOND`, `SECURITY`, `SELECT`, `SEQUENCE`, `SEQUENCES`, `SERIALIZABLE`, `SERVER`, `SESSION`, `SESSION_USER`, `SET`, `SETOF`, `SHARE`, `SHOW`, `SIMILAR`, `SIMPLE`, `SMALLINT`, `SNAPSHOT`, `SOME`, `STABLE`, `STANDALONE`, `START`, `STATEMENT`, `STATISTICS`, `STDIN`, `STDOUT`, `STORAGE`, `STRICT`, `STRIP`, `SUBSTRING`, `SYMMETRIC`, `SYSID`, `SYSTEM`, `TABLE`, `TABLES`, `TABLESPACE`, `TEMP`, `TEMPLATE`, `TEMPORARY`, `TEXT`, `THEN`, `TIME`, `TIMESTAMP`, `TO`, `TRAILING`, `TRANSACTION`, `TREAT`, `TRIGGER`, `TRIM`, `TRUE`, `TRUNCATE`, `TRUSTED`, `TYPE`, `TYPES`, `UNBOUNDED`, `UNCOMMITTED`, `UNENCRYPTED`, `UNION`, `UNIQUE`, `UNKNOWN`, `UNLISTEN`, `UNLOGGED`, `UNTIL`, `UPDATE`, `USER`, `USING`, `VACUUM`, `VALID`, `VALIDATE`, `VALIDATOR`, `VALUE`, `VALUES`, `VARCHAR`, `VARIADIC`, `VARYING`, `VERBOSE`, `VERSION`, `VIEW`, `VIEWS`, `VOLATILE`, `WHEN`, `WHERE`, `WHITESPACE`, `WINDOW`, `WITH`, `WITHIN`, `WITHOUT`, `WORK`, `WRAPPER`, `WRITE`, `XML`, `XMLATTRIBUTES`, `XMLCONCAT`, `XMLELEMENT`, `XMLEXISTS`, `XMLFOREST`, `XMLPARSE`, `XMLPI`, `XMLROOT`, `XMLSERIALIZE`, `YEAR`, `YES`, `ZONE`), Keyword, nil},
{"[+*/<>=~!@#%^&|`?-]+", Operator, nil},
{`::`, Operator, nil},
{`\$\d+`, NameVariable, nil},
{`([0-9]*\.[0-9]*|[0-9]+)(e[+-]?[0-9]+)?`, LiteralNumberFloat, nil},
{`[0-9]+`, LiteralNumberInteger, nil},
{`((?:E|U&)?)(')`, ByGroups(LiteralStringAffix, LiteralStringSingle), Push("string")},
{`((?:U&)?)(")`, ByGroups(LiteralStringAffix, LiteralStringName), Push("quoted-ident")},
{
`(?s)(\$)([^$]*)(\$)(.*?)(\$)(\2)(\$)(\s+)(LANGUAGE)?(\s+)('?)(\w+)?('?)`,
UsingByGroup(12, 4,
StringHeredoc, StringHeredoc, StringHeredoc, // $tag$
StringHeredoc, // (code block)
StringHeredoc, StringHeredoc, StringHeredoc, // $tag$
Text, Keyword, Text, // <space> LANGUAGE <space>
StringSingle, StringSingle, StringSingle), // 'type'
nil,
},
{`(?s)(\$)([^$]*)(\$)(.*?)(\$)(\2)(\$)`, LiteralStringHeredoc, nil},
{`[a-z_]\w*`, Name, nil},
{`:(['"]?)[a-z]\w*\b\1`, NameVariable, nil},
{`[;:()\[\]{},.]`, Punctuation, nil},
},
"multiline-comments": {
{`/\*`, CommentMultiline, Push("multiline-comments")},
{`\*/`, CommentMultiline, Pop(1)},
{`[^/*]+`, CommentMultiline, nil},
{`[/*]`, CommentMultiline, nil},
},
"string": {
{`[^']+`, LiteralStringSingle, nil},
{`''`, LiteralStringSingle, nil},
{`'`, LiteralStringSingle, Pop(1)},
},
"quoted-ident": {
{`[^"]+`, LiteralStringName, nil},
{`""`, LiteralStringName, nil},
{`"`, LiteralStringName, Pop(1)},
},
}
}

42
lexers/smarty.go
View File

@@ -1,42 +0,0 @@
package lexers
import (
. "github.com/alecthomas/chroma/v2" // nolint
)
// Smarty lexer.
var Smarty = Register(MustNewLexer(
&Config{
Name: "Smarty",
Aliases: []string{"smarty"},
Filenames: []string{"*.tpl"},
MimeTypes: []string{"application/x-smarty"},
DotAll: true,
},
smartyRules,
))
func smartyRules() Rules {
return Rules{
"root": {
{`[^{]+`, Other, nil},
{`(\{)(\*.*?\*)(\})`, ByGroups(CommentPreproc, Comment, CommentPreproc), nil},
{`(\{php\})(.*?)(\{/php\})`, ByGroups(CommentPreproc, Using("PHP"), CommentPreproc), nil},
{`(\{)(/?[a-zA-Z_]\w*)(\s*)`, ByGroups(CommentPreproc, NameFunction, Text), Push("smarty")},
{`\{`, CommentPreproc, Push("smarty")},
},
"smarty": {
{`\s+`, Text, nil},
{`\{`, CommentPreproc, Push()},
{`\}`, CommentPreproc, Pop(1)},
{`#[a-zA-Z_]\w*#`, NameVariable, nil},
{`\$[a-zA-Z_]\w*(\.\w+)*`, NameVariable, nil},
{`[~!%^&*()+=|\[\]:;,.<>/?@-]`, Operator, nil},
{`(true|false|null)\b`, KeywordConstant, nil},
{`[0-9](\.[0-9]*)?(eE[+-][0-9])?[flFLdD]?|0[xX][0-9a-fA-F]+[Ll]?`, LiteralNumber, nil},
{`"(\\\\|\\"|[^"])*"`, LiteralStringDouble, nil},
{`'(\\\\|\\'|[^'])*'`, LiteralStringSingle, nil},
{`[a-zA-Z_]\w*`, NameAttribute, nil},
},
}
}

3
lexers/testdata/analysis/bash.actual vendored Normal file
View File

@@ -0,0 +1,3 @@
#!/bin/bash
echo "This is a bash script"

1
lexers/testdata/analysis/bash.expected vendored Normal file
View File

@@ -0,0 +1 @@
1.0

173
lexers/v.go
View File

@@ -1,173 +0,0 @@
package lexers
import (
"strings"
. "github.com/alecthomas/chroma/v2" // nolint
)
// V lexer.
var V = Register(MustNewLexer(
&Config{
Name: "V",
Aliases: []string{"v", "vlang"},
Filenames: []string{"*.v", "*.vv", "v.mod"},
MimeTypes: []string{"text/x-v"},
EnsureNL: true,
},
vRules,
).SetAnalyser(func(text string) float32 {
if strings.Contains(text, "import ") && strings.Contains(text, "module ") {
return 0.2
}
if strings.Contains(text, "module ") {
return 0.1
}
return 0.0
}))
const (
namePattern = `[^\W\d]\w*`
typeNamePattern = `[A-Z]\w*`
multiLineCommentPattern = `/\*(?:.|\n)*?\*/`
)
func vRules() Rules {
return Rules{
"root": {
{`\n`, Text, nil},
{`\s+`, Text, nil},
{`\\\n`, Text, nil},
{`(?<=module\s+\w[^\n]*\s+)(//[^\n]+\n)+(?=\n)`, StringDoc, nil},
{`(// *)(\w+)([^\n]+\n)(?=(?://[^\n]*\n)* *(?:pub +)?(?:fn|struct|union|type|interface|enum|const) +\2\b)`, ByGroups(StringDoc, GenericEmph, StringDoc), Push(`string-doc`)},
{`//[^\n]*\n`, CommentSingle, nil},
{`/\*(?:(?:` + multiLineCommentPattern + `)*|.|\n)*\*/`, CommentMultiline, nil},
{`\b(import|module)\b`, KeywordNamespace, nil},
{`\b(fn|struct|union|map|chan|type|interface|enum|const|mut|shared|pub|__global)\b`, KeywordDeclaration, nil},
{`\?`, KeywordDeclaration, nil},
{`(?<=\)\s*)!`, KeywordDeclaration, nil},
{`[ \t]*#include[^\n]+`, Using(`c`), nil},
{`[ \t]*#\w[^\n]*`, CommentPreproc, nil},
{`(sql)(\s+)(\w+)(\s+)({)([^}]*?)(})`, ByGroups(Keyword, Text, Name, Text, Punctuation, Using(`sql`), Punctuation), nil},
{`\$(?=\w)`, Operator, nil},
{`(?<=\$)(?:embed_file|pkgconfig|tmpl|env|compile_error|compile_warn)`, NameBuiltin, nil},
{`(asm)(\s+)(\w+)(\s*)({)([^}]*?)(})`, ByGroups(Keyword, Text, KeywordType, Text, Punctuation, Using(`nasm`), Punctuation), nil},
{`\b_(?:un)?likely_(?=\()`, NameFunctionMagic, nil},
{`(?<=\$if.+?(?:&&|\|\|)?)(` + Words(``, ``, `windows`, `linux`, `macos`, `mac`, `darwin`, `ios`, `android`, `mach`, `dragonfly`, `gnu`, `hpux`, `haiku`, `qnx`, `solaris`, `gcc`, `tinyc`, `clang`, `mingw`, `msvc`, `cplusplus`, `amd64`, `arm64`, `x64`, `x32`, `little_endian`, `big_endian`, `debug`, `prod`, `test`, `js`, `glibc`, `prealloc`, `no_bounds_checking`, `freestanding`, `no_segfault_handler`, `no_backtrace`, `no_main`) + `)+`, NameBuiltin, nil},
{`@` + Words(``, `\b`, `FN`, `METHOD`, `MOD`, `STRUCT`, `FILE`, `LINE`, `COLUMN`, `VEXE`, `VEXEROOT`, `VHASH`, `VMOD_FILE`, `VMODROOT`), NameVariableMagic, nil},
{Words(`\b(?<!@)`, `\b`, `break`, `select`, `match`, `defer`, `go`, `goto`, `else`, `if`, `continue`, `for`, `return`, `assert`, `or`, `as`, `atomic`, `isreftype`, `is`, `in`, `lock`, `rlock`, `sizeof`, `typeof`, `unsafe`, `volatile`, `static`, `__offsetof`), Keyword, nil},
{`\b(?<!@)(none|true|false|si_s_code|si_g32_code|si_g64_code)\b`, KeywordConstant, nil},
{Words(`\b(?<!@)`, `(?=\()`, `u8`, `u16`, `u32`, `u64`, `u128`, `int`, `i8`, `i16`, `i64`, `i128`, `f32`, `f64`, `rune`, `string`, `bool`, `usize`, `isize`, `any`, `error`, `print`, `println`, `dump`, `panic`, `eprint`, `eprintln`, `copy`, `close`, `len`, `map`, `filter`, `cap`, `delete`, `delete_many`, `delete_last`, `c_error_number_str`, `compare_strings`, `cstring_to_vstring`, `error_with_code`, `exit`, `f32_abs`, `f32_max`, `f32_min`, `f64_max`, `flush_stderr`, `flush_stdout`, `free`, `gc_check_leaks`, `get_str_intp_u32_format`, `get_str_intp_u64_format`, `isnil`, `malloc`, `malloc_noscan`, `memdup`, `memdup_noscan`, `panic_error_number`, `panic_lasterr`, `panic_optional_not_set`, `panic_result_not_set`, `print_backtrace`, `proc_pidpath`, `ptr_str`, `realloc_data`, `str_intp`, `str_intp_g32`, `str_intp_g64`, `str_intp_rune`, `str_intp_sq`, `str_intp_sub`, `string_from_wide`, `string_from_wide2`, `tos`, `tos2`, `tos3`, `tos4`, `tos5`, `tos_clone`, `utf32_decode_to_buffer`, `utf32_to_str`, `utf32_to_str_no_malloc`, `utf8_char_len`, `utf8_getchar`, `utf8_str_visible_length`, `v_realloc`, `vcalloc`, `vcalloc_noscan`, `vmemcmp`, `vmemcpy`, `vmemmove`, `vmemset`, `vstrlen`, `vstrlen_char`, `winapi_lasterr_str`, `reduce`, `string`, `join`, `free`, `join_lines`, `sort_by_len`, `sort_ignore_case`, `str`, `byterune`, `bytestr`, `clone`, `hex`, `utf8_to_utf32`, `vbytes`, `vstring`, `vstring_literal`, `vstring_literal_with_len`, `vstring_with_len`, `try_pop`, `try_push`, `strg`, `strsci`, `strlong`, `eq_epsilon`, `hex_full`, `hex2`, `msg`, `code`, `repeat`, `bytes`, `length_in_bytes`, `ascii_str`, `is_alnum`, `is_bin_digit`, `is_capital`, `is_digit`, `is_hex_digit`, `is_letter`, `is_oct_digit`, `is_space`, `str_escaped`, `repeat_to_depth`, `insert`, `prepend`, `trim`, `drop`, `first`, `last`, `pop`, `clone_to_depth`, `push_many`, `reverse_in_place`, `reverse`, `any`, `all`, `sort`, `sort_with_compare`, `contains`, `index`, `grow_cap`, `grow_len`, `pointers`, `move`, `keys`, `after`, `after_char`, `all_after`, `all_after_last`, `all_before`, `all_before_last`, `before`, `capitalize`, `compare`, `contains_any`, `contains_any_substr`, `count`, `ends_with`, `fields`, `find_between`, `hash`, `index_after`, `index_any`, `index_u8`, `is_lower`, `is_title`, `is_upper`, `last_index`, `last_index_u8`, `len_utf8`, `limit`, `match_glob`, `parse_int`, `parse_uint`, `replace`, `replace_each`, `replace_once`, `runes`, `split`, `split_any`, `split_into_lines`, `split_nth`, `starts_with`, `starts_with_capital`, `strip_margin`, `strip_margin_custom`, `substr`, `substr_ni`, `substr_with_check`, `title`, `to_lower`, `to_upper`, `to_wide`, `trim_left`, `trim_right`, `trim_space`, `trim_string_left`, `trim_string_right`, `utf32_code`), NameBuiltin, nil},
{Words(`\b(?<!@)`, `\b`, `ArrayFlags`, `AttributeKind`, `ChanState`, `StrIntpType`, `array`, `Error`, `FieldData`, `FunctionData`, `map`, `MethodArgs`, `SortedMap`, `string`, `StrIntpCgenData`, `StrIntpData`, `StrIntpMem`, `StructAttribute`, `VAssertMetaInfo`), NameBuiltin, nil},
{Words(`\b(?<!@)`, `\b`, `u8`, `u16`, `u32`, `u64`, `u128`, `int`, `i8`, `i16`, `i64`, `i128`, `f32`, `f64`, `rune`, `string`, `bool`, `usize`, `isize`, `any`, `error`, `voidptr`), KeywordType, nil},
{`\bit\b`, NameVariableMagic, nil},
{`(?<!fn\s+)(?<=\w+\s+|^)\[(?=:if +)?(?=\w+)`, Punctuation, Push(`attribute`)},
{`(<<=|>>=|>>>=|>>>|<<|>>|<=|>=|\^=|\+=|-=|\*=|/=|%=|&=|\|=|&&|\|\||<-|\+\+|--|==|!=|:=|\.\.\.|\.\.|[+\-*/%&|^~=#@!])`, Operator, nil},
{`[\d_]+(\.\d+e[+\-]?\d+|\.\d+|e[+\-]?\d+)`, LiteralNumberFloat, nil},
{`\.\d+(e[+\-]?\d+)?`, LiteralNumberFloat, nil},
{`0o[0-7_]+`, LiteralNumberOct, nil},
{`0x[0-9a-fA-F_]+`, LiteralNumberHex, nil},
{`0b[01_]+`, LiteralNumberBin, nil},
{`(0|[1-9][0-9_]*)`, LiteralNumberInteger, nil},
{"`", StringChar, Push(`char`)},
Include(`strings`),
{`@?` + typeNamePattern, NameClass, nil},
{`(?<=` + namePattern + `)(<)(` + typeNamePattern + `)(>)`, ByGroups(Punctuation, NameClass, Punctuation), nil},
{`@?` + namePattern + `(?=\()`, NameFunction, nil},
{`(?<=fn\s+)@?` + namePattern + `(?=\s*\()`, NameFunction, nil},
{`(?<=(?:continue|break|goto)\s+)\w+`, NameLabel, nil},
{`\b` + namePattern + `(?=:(?:$|\s+for))`, NameLabel, nil},
{`[<>()\[\]{}.,;:]`, Punctuation, nil},
{`@?` + namePattern, NameVariable, nil},
},
"strings": {
{`(c)?(")`, ByGroups(StringAffix, StringDouble), Push(`string-double`)},
{`(c)?(')`, ByGroups(StringAffix, StringSingle), Push(`string-single`)},
{`(r)("[^"]+")`, ByGroups(StringAffix, String), nil},
{`(r)('[^']+')`, ByGroups(StringAffix, String), nil},
},
"string-double": {
{`"`, StringDouble, Pop(1)},
Include(`char-escape`),
{`(\$)((?!\\){)`, ByGroups(Operator, Punctuation), Push(`string-curly-interpolation`)},
{`\$`, Operator, Push(`string-interpolation`)},
{`[^"]+?`, StringDouble, nil},
},
"string-single": {
{`'`, StringSingle, Pop(1)},
Include(`char-escape`),
{`(\$)((?!\\){)`, ByGroups(Operator, Punctuation), Push(`string-curly-interpolation`)},
{`\$`, Operator, Push(`string-interpolation`)},
{`[^']+?`, StringSingle, nil},
},
"char": {
{"`", StringChar, Pop(1)},
Include(`char-escape`),
{`[^\\]`, StringChar, nil},
},
"char-escape": {
{"\\\\[`'\"\\\\abfnrtv$]|\\\\x[0-9a-fA-F]{2}|\\\\[0-7]{1,3}|\\\\u[0-9a-fA-F]{4}|\\\\U[0-9a-fA-F]{8}", StringEscape, nil},
},
"string-doc": {
{`(// *)(#+ [^\n]+)(\n)`, ByGroups(StringDoc, GenericHeading, Text), nil},
{`// *([=_*~-])\1{2,}\n`, StringDelimiter, nil},
{`//[^\n]*\n`, StringDoc, nil},
Default(Pop(1)),
},
"string-interpolation": {
{`(\.)?(@)?(?:(` + namePattern + `)(\()([^)]*)(\))|(` + namePattern + `))`, ByGroups(Punctuation, Operator, NameFunction, Punctuation, UsingSelf(`root`), Punctuation, NameVariable), nil},
Default(Pop(1)),
},
"string-curly-interpolation": {
{`}`, Punctuation, Pop(1)},
Include(`strings`),
{`(:)( *?)([ 0'#+-])?(?:(\.)?([0-9]+))?([fFgeEGxXobsd])?`, ByGroups(Punctuation, Text, Operator, Punctuation, Number, StringAffix), nil},
{`[^}"':]+`, UsingSelf(`root`), nil},
},
"attribute": {
{`\]`, Punctuation, Pop(1)},
{`'`, Punctuation, Push(`string-single`)},
{`"`, Punctuation, Push(`string-double`)},
{`[;:]`, Punctuation, nil},
{`(?<=\[)if\b`, Keyword, nil},
{`\s+`, Text, nil},
{`(?<=: *)\w+`, String, nil},
{namePattern, NameAttribute, nil},
},
}
}
// V shell lexer.
var VSH = Register(MustNewLexer(
&Config{
Name: "V shell",
Aliases: []string{"vsh", "vshell"},
Filenames: []string{"*.vsh"},
MimeTypes: []string{"text/x-vsh"},
EnsureNL: true,
},
vshRules,
).SetAnalyser(func(text string) float32 {
firstLine := strings.Split(text, "\n")[0]
if strings.Contains(firstLine, "#!/usr/bin/env") && strings.Contains(firstLine, "v run") {
return 1.0
}
if strings.Contains(firstLine, "#!/") && strings.Contains(firstLine, "/v run") {
return 1.0
}
return 0.0
}))
func vshRules() Rules {
vshRules := vRules()
vshRoot := []Rule{
{`^#![^\n]*\n`, CommentHashbang, nil},
{Words(`\b`, `\b`, `args`, `max_path_len`, `wd_at_startup`, `sys_write`, `sys_open`, `sys_close`, `sys_mkdir`, `sys_creat`, `path_separator`, `path_delimiter`, `s_ifmt`, `s_ifdir`, `s_iflnk`, `s_isuid`, `s_isgid`, `s_isvtx`, `s_irusr`, `s_iwusr`, `s_ixusr`, `s_irgrp`, `s_iwgrp`, `s_ixgrp`, `s_iroth`, `s_iwoth`, `s_ixoth`), NameConstant, nil},
{Words(`\b`, `\b`, `ProcessState`, `SeekMode`, `Signal`, `Command`, `ExecutableNotFoundError`, `File`, `FileNotOpenedError`, `Process`, `Result`, `SizeOfTypeIs0Error`, `Uname`), NameBuiltin, nil},
{Words(`\b`, `(?=\()`, `abs_path`, `args_after`, `args_before`, `base`, `cache_dir`, `chdir`, `chmod`, `chown`, `config_dir`, `cp`, `cp_all`, `create`, `debugger_present`, `dir`, `environ`, `executable`, `execute`, `execute_or_exit`, `execute_or_panic`, `execve`, `execvp`, `existing_path`, `exists`, `exists_in_system_path`, `expand_tilde_to_home`, `fd_close`, `fd_read`, `fd_slurp`, `fd_write`, `file_ext`, `file_last_mod_unix`, `file_name`, `file_size`, `fileno`, `find_abs_path_of_executable`, `flush`, `fork`, `get_error_msg`, `get_line`, `get_lines`, `get_lines_joined`, `get_raw_line`, `get_raw_lines_joined`, `get_raw_stdin`, `getegid`, `getenv`, `getenv_opt`, `geteuid`, `getgid`, `getpid`, `getppid`, `getuid`, `getwd`, `glob`, `home_dir`, `hostname`, `inode`, `input`, `input_opt`, `is_abs_path`, `is_atty`, `is_dir`, `is_dir_empty`, `is_executable`, `is_file`, `is_link`, `is_readable`, `is_writable`, `is_writable_folder`, `join_path`, `join_path_single`, `last_error`, `link`, `log`, `loginname`, `ls`, `mkdir`, `mkdir_all`, `mv`, `mv_by_cp`, `new_process`, `norm_path`, `open`, `open_append`, `open_file`, `open_uri`, `posix_get_error_msg`, `posix_set_permission_bit`, `quoted_path`, `read_bytes`, `read_file`, `read_file_array`, `read_lines`, `real_path`, `resource_abs_path`, `rm`, `rmdir`, `rmdir_all`, `setenv`, `sigint_to_signal_name`, `signal_opt`, `stderr`, `stdin`, `stdout`, `symlink`, `system`, `temp_dir`, `truncate`, `uname`, `unsetenv`, `user_os`, `utime`, `vfopen`, `vmodules_dir`, `vmodules_paths`, `wait`, `walk`, `walk_ext`, `walk_with_context`, `write_file`, `write_file_array`, `bitmask`, `close`, `read_line`, `start`, `msg`, `read`, `read_bytes_at`, `read_bytes_into`, `read_bytes_into_newline`, `read_from`, `read_into_ptr`, `read_raw`, `read_raw_at`, `read_struct`, `read_struct_at`, `seek`, `tell`, `write`, `write_raw`, `write_raw_at`, `write_string`, `write_struct`, `write_struct_at`, `write_to`, `writeln`, `is_alive`, `run`, `set_args`, `set_environment`, `set_redirect_stdio`, `signal_continue`, `signal_kill`, `signal_pgkill`, `signal_stop`, `stderr_read`, `stderr_slurp`, `stdin_write`, `stdout_read`, `stdout_slurp`), NameBuiltin, nil},
}
vshRules[`root`] = append(vshRoot, vshRules[`root`]...)
return vshRules
}

40
lexers/vim.go
View File

@@ -1,40 +0,0 @@
package lexers
import (
. "github.com/alecthomas/chroma/v2" // nolint
)
// Viml lexer.
var Viml = Register(MustNewLexer(
&Config{
Name: "VimL",
Aliases: []string{"vim"},
Filenames: []string{"*.vim", ".vimrc", ".exrc", ".gvimrc", "_vimrc", "_exrc", "_gvimrc", "vimrc", "gvimrc"},
MimeTypes: []string{"text/x-vim"},
},
vimlRules,
))
func vimlRules() Rules {
return Rules{
"root": {
{`^([ \t:]*)(py(?:t(?:h(?:o(?:n)?)?)?)?)([ \t]*)(<<)([ \t]*)(.*)((?:\n|.)*)(\6)`, ByGroups(UsingSelf("root"), Keyword, Text, Operator, Text, Text, Using("Python"), Text), nil},
{`^([ \t:]*)(py(?:t(?:h(?:o(?:n)?)?)?)?)([ \t])(.*)`, ByGroups(UsingSelf("root"), Keyword, Text, Using("Python")), nil},
{`^\s*".*`, Comment, nil},
{`[ \t]+`, Text, nil},
{`/(\\\\|\\/|[^\n/])*/`, LiteralStringRegex, nil},
{`"(\\\\|\\"|[^\n"])*"`, LiteralStringDouble, nil},
{`'(''|[^\n'])*'`, LiteralStringSingle, nil},
{`(?<=\s)"[^\-:.%#=*].*`, Comment, nil},
{`-?\d+`, LiteralNumber, nil},
{`#[0-9a-f]{6}`, LiteralNumberHex, nil},
{`^:`, Punctuation, nil},
{`[()<>+=!|,~-]`, Punctuation, nil},
{`\b(let|if|else|endif|elseif|fun|function|endfunction|set|map|autocmd|filetype|hi(ghlight)?|execute|syntax|colorscheme)\b`, Keyword, nil},
{`\b(NONE|bold|italic|underline|dark|light)\b`, NameBuiltin, nil},
{`\b\w+\b`, NameOther, nil},
{`\n`, Text, nil},
{`.`, Text, nil},
},
}
}

2
mutators.go
View File

@@ -69,7 +69,7 @@ func (m *multiMutator) MarshalXML(e *xml.Encoder, start xml.StartElement) error
return e.EncodeToken(xml.EndElement{Name: name})
}
func (m *multiMutator) MutatorKind() string { return "multiple" }
func (m *multiMutator) MutatorKind() string { return "mutators" }
func (m *multiMutator) Mutate(state *LexerState) error {
for _, modifier := range m.Mutators {

2
serialise.go
View File

@@ -168,7 +168,7 @@ func NewXMLLexer(from fs.FS, path string) (*RegexLexer, error) {
return 0
}
if ok && config.Analyse.Single {
if ok && config.Analyse.First {
return float32(math.Min(float64(ra.score), 1.0))
}