Last active
March 21, 2020 04:58
-
-
Save peta/5174284 to your computer and use it in GitHub Desktop.
Regex design pattern for Textmate language grammars. An absolutely cool feature of PCRE (even supported by Oniguruma) are named subexpression calls. Allowing for recursive matching while preserving (atomic) contexts at every recursion level in form of named match results. However, there is no light without shadow: When no multiline matches can b…
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| myPattern = { | |
| name = 'meta.spec.triples'; | |
| begin = '(?x) | |
| (?<subject> \g<iri> | \g<BlankNode> | \g<collection> ){0} | |
| (?<iri> \g<IRIREF> | \g<PrefixedName> ){0} | |
| (?<IRIREF> \< (?:[^\x00-\x20\<\>\\\"\{\}\|\^`] | (?:\\u[0-9A-Fa-f]{4}|\\U[0-9A-Fa-f]{8}))* \> ){0} | |
| (?<PrefixedName> \g<PNAME_LN> | \g<PNAME_NS> ){0} | |
| (?<PNAME_LN> (\g<PNAME_NS>) ( (?: [\p{L}\p{M}_] | [:0-9] | %[0-9A-Fa-f]{2} | [\\_~.\-!$&''\(\)*+,;=/?#@%] ) (?:(?:[\p{L}\p{M}_\-0-9\u00B7\u0300-\u036F\u203F-\u2040] | [:.] | %[0-9A-Fa-f]{2} | [\\_~.\-!$&''\(\)*+,;=/?#@%])* (?:[\p{L}\p{M}_\-0-9\u00B7\u0300-\u036F\u203F-\u2040] | : | %[0-9A-Fa-f]{2} | [\\_~.\-!$&''\(\)*+,;=/?#@%])) )? ){0} | |
| (?<PNAME_NS> (?: [\p{L}\p{M}] (?:(?:[\p{L}\p{M}_.\-0-9\u00B7\u0300-\u036F\u203F-\u2040])* [\p{L}\p{M}_\-0-9\u00B7\u0300-\u036F\u203F-\u2040] )? )? \: ){0} | |
| (?<BlankNode> \g<BLANK_NODE_LABEL> | \g<ANON> ){0} | |
| (?<BLANK_NODE_LABEL> _: ([\p{L}\p{M}_0-9]) ([\p{L}\p{M}_\-0-9\u00B7\u0300-\u036F\u203F-\u2040.]* [\p{L}\p{M}_\-0-9\u00B7\u0300-\u036F\u203F-\u2040])? ){0} | |
| (?<ANON> \[[\x20\x9\xD\xA]*\] ){0} | |
| (?<collection> \(\g<object>*\) ){0} | |
| (?<object> \g<iri> | \g<BlankNode> | \g<collection> | \g<blankNodePropertyList> | \g<literal> ){0} | |
| (?<blankNodePropertyList> \[\g<predicateObjectList>\] ){0} | |
| (?<predicateObjectList> \g<verb>\s+\g<objectList> (?:[ ]*;\s+\g<verb>\s+\g<objectList> )* ){0} | |
| (?<verb>\s\g<predicate>\s|\sa\s){0} | |
| (?<predicate> \g<iri> ){0} | |
| (?<objectList> \g<object> (?:,\s\g<object>)* ){0} | |
| (?<literal> "([^\x22\x5C\xA\xD] | \\[tbnrf"''] | (?:\\u[0-9A-Fa-f]{4}|\\U[0-9A-Fa-f]{8}))*" ){0} | |
| (?#Here starts the show) | |
| ^(?i)(?!@|\#|PREFIX|BASE)(?-i)(?:[ ]*)(\g<subject>)\b | |
| '; | |
| end = '(?x)(?#Here starts the show)'; | |
| captures = { | |
| ANON = { name = 'meta.tmp.ANON'; }; | |
| BlankNode = { name = 'meta.tmp.BlankNode'; }; | |
| IRIREF = { name = 'meta.tmp.IRIREF'; }; | |
| PNAME_LN = { name = 'meta.tmp.PNAME_LN'; }; | |
| PNAME_NS = { name = 'meta.tmp.PNAME_NS'; }; | |
| PrefixedName = { name = 'meta.tmp.PrefixedName'; }; | |
| blankNodePropertyList = { name = 'meta.tmp.blankNodePropertyList'; }; | |
| collection = { name = 'meta.tmp.collection'; }; | |
| iri = { name = 'meta.tmp.iri'; }; | |
| literal = { name = 'meta.tmp.literal'; }; | |
| object = { name = 'meta.tmp.object'; }; | |
| objectList = { name = 'meta.tmp.objectList'; }; | |
| predicate = { name = 'meta.tmp.predicate'; }; | |
| predicateObjectList = { name = 'meta.tmp.predicateObjectList'; }; | |
| subject = { name = 'meta.tmp.subject'; }; | |
| verb = { name = 'meta.tmp.verb'; }; | |
| }; | |
| } |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment