This is per reference of this question I raised on StackOverflow As per @Peter
Kluegl there is too much scope for code improvement.
So eagerly looking how can I improve this script
https://stackoverflow.com/questions/44351051/uima-ruta-out-of-memory-issue-in-spark-context
=========================================================
TYPESYSTEM EDMTypeSystem;
WORDLIST EnglishStopWordList = 'en/anchor/en_stopWords.txt';
WORDLIST FiltersList = 'en/anchor/AnchorFilters.txt';
DECLARE Filters, EnglishStopWords;
DECLARE Anchors, SpanStart,SpanClose;
DocumentAnnotation{-> ADDRETAINTYPE(MARKUP)};
DocumentAnnotation{-> MARKFAST(Filters, FiltersList)};
STRING MixCharacterRegex = "[0-9]+[a-zA-Z]+";
DocumentAnnotation{-> MARKFAST(EnglishStopWords, EnglishStopWordList,true)};
(SW | CW | CAP ) { -> MARK(Anchors, 1, 2)};
Anchors{CONTAINS(EnglishStopWords) -> UNMARK(Anchors)};
(SPECIAL{REGEXP("['\"-=()\\[\\]]")}| PM) (SW | CW | CAP )
(SPECIAL{REGEXP("['\"-=()\\[\\]]")}| PM) EnglishStopWords? { -> MARK(Anchors,
1, 4)};
(SPECIAL{REGEXP("['\"-=()\\[\\]]")}| PM)? (SW | CW | CAP )
(SPECIAL{REGEXP("['\"-=()\\[\\]]")}| PM) EnglishStopWords? { -> MARK(Anchors,
1, 4)};
(SPECIAL{REGEXP("['\"-=()\\[\\]]")}| PM) (SW | CW | CAP )
(SPECIAL{REGEXP("['\"-=()\\[\\]]")}| PM)? EnglishStopWords? { -> MARK(Anchors,
1, 4)};
(SW | CW | CAP ) (SPECIAL{REGEXP("['\"-=()\\[\\]]")}| PM) EnglishStopWords? {
-> MARK(Anchors, 1, 3)};
Anchors{CONTAINS(MARKUP) -> UNMARK(Anchors)};
MixCharacterRegex -> Anchors;
"<Value>" -> SpanStart;
"</Value>" -> SpanClose;
Anchors{-> CREATE(ExtractedData, "type" = "ANCHOR", "value" = Anchors)};
SpanStart Filters? SPACE? ExtractedData SPACE? Filters? SpanClose{->
GATHER(Data, 2, 6, "ExtractedData" = 4)};
=========================================================
