Added DataLinguist

README.md

 # Major Project Handcrafted
 
 The one made by hand, not the one made using ML
+
+
+
+
+
+## Attribution
+
+
+[DataLinguist v0.2.171](https://github.com/simongray/datalinguist)
+
+DataLinguist is a Clojure wrapper for the Natural Language Processing behemoth,
+[Stanford CoreNLP](https://github.com/stanfordnlp/CoreNLP). The goal of the project is to support an NLP workflow in a data-oriented style,
+integrating relevant Clojure protocols and libraries.
+
+Manning, Christopher D., Mihai Surdeanu, John Bauer, Jenny Finkel, Steven J. Bethard, and David McClosky. 2014.
+The Stanford CoreNLP Natural Language Processing Toolkit In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pp. 55-60.
+[[pdf](http://nlp.stanford.edu/pubs/StanfordCoreNlp2014.pdf)] [[bib](http://nlp.stanford.edu/pubs/StanfordCoreNlp2014.bib)]

project.clj

@@ -12,6 +12,10 @@
                     [:role "developer"]
                     [:role "maintainer"]]])
   :dependencies [[org.clojure/clojure "1.11.1"]
+                 ;; DataLinguist
+                 [dk.simongray/datalinguist "0.2.171"]
+                 [edu.stanford.nlp/stanford-corenlp "4.4.0" :classifier "models"]
+                 [edu.stanford.nlp/stanford-corenlp "4.4.0" :classifier "models-english"]
                  ;; tools.namespace
                  [org.clojure/tools.namespace "1.3.0"]
                  ;; java.data

src/poalses/jonathan/dialect/dialect_nlp.clj

+(ns poalses.jonathan.dialect.dialect-nlp
+  (:require [clojure.datafy :refer [datafy]]
+           [dk.simongray.datalinguist :as dl]
+           [dk.simongray.datalinguist.triple :refer [triple->datalog]])
+  (:import [edu.stanford.nlp.coref CorefCoreAnnotations$CorefChainAnnotation]))
+
+
+(def example
+  "Great work, thanks for doing this!
+  Having had no previous experience with NLP libraries, I was wondering why I couldn’t get your examples to work. Then I realized that I had to download CoreNLP first from https://stanfordnlp.github.io/CoreNLP/ and add stanford-corenlp-4.4.0/* to the classpath. Everything worked fine after that.
+  Is this what you are supposed to do? It wasn’t mentioned in the readme, so I was wondering if I did something wrong here or if it is more obvious to people who have already worked with CoreNLP.")
+
+(def nlp
+  (dl/->pipeline {:annotators ["truecase"
+                               "quote"
+                               "entitymentions"
+                               "parse"
+                               "depparse"
+                               "lemma"
+                               "coref"
+                               "openie"
+                               "ner"]
+                  :quote      {:extractUnclosedQuotes "true"}}))
+
+(def annotated-example
+  (delay (nlp example)))
+
+(def sentences
+  (delay (dl/sentences @annotated-example)))
+
+(defn show-sentences []
+  (clojure.pprint/pprint (map dl/mentions @sentences)))
+
+
+(comment
+  ;; Test every annotator in the pipeline
+  (map dl/true-case @sentences)
+  (map dl/quotations @sentences)
+  (map dl/mentions @sentences)
+  (map dl/constituency-tree @sentences)
+  (map dl/dependency-graph @sentences)
+  (map dl/lemma @sentences)
+  (map dl/mentions @sentences)
+  (->> (mapcat dl/triples @sentences) (map triple->datalog))
+  (dl/annotation CorefCoreAnnotations$CorefChainAnnotation @annotated-example)
+
+  (show-sentences)
+
+  ;; Datafy the annotations. Retrieves direct annotations for every sentence.
+  ;; Keep in mind that `dl/recur-datafy` currently doesn't work in this instance
+  ;; and will possibly be removed in a future update:
+  ;;   https://github.com/simongray/datalinguist/issues/13
+  (map datafy @sentences)
+  #_.)
\ No newline at end of file

src/poalses/jonathan/dialect/main.clj

@@ -3,6 +3,7 @@
   {:author "Jonathan Poalses"}
   (:require [clojure.string :as string]
             [clojure.tools.cli :as cli]
+            [poalses.jonathan.dialect.dialect-nlp :as nlp]
             [taoensso.timbre :as log])
   (:gen-class))
 
@@ -70,6 +71,7 @@
       (let [shutdown-trigger (promise)
             _bye-testing-hack (future (Thread/sleep 6000) (deliver shutdown-trigger true))]
         (log/info "Dialect Detector started up.")
+        (nlp/show-sentences)
         @shutdown-trigger
         (log/info "Dialect Detector shutting down..."))
       (catch Exception e
@@ -84,11 +86,53 @@
 ;;==============================================================================
 (comment
 
+  (def test-vector [122 "blah blah blah" "more" 777])
 
+  test-vector
+
+  (count test-vector)
+
+  (def test-list '(122 "blah blah blah" "more" 777))
+
+  test-list
+
+  (count test-list)
+
+  (conj test-vector (first test-list))
+
+  (conj test-vector (vec test-list))
+
+  (take 21 (cycle test-vector))
+
+  (into test-vector (vec (take 15 (repeatedly #(rand-int 10000)))))
+
+
+  (def another-vector
+    (delay [18746 "gjhsdfgh" 5857 58923]))
+
+  another-vector
+
+  @another-vector
+
+
+
+
+
+
+
+  (into test-vector test-list)
+
+  (conj test-vector 42)
+
+  [test-list]
+
+  (vec test-list)
+
+  (conj test-list 42)
 
   *e)
 ;
-; HissyBots REPL Service.
+; Dialect Detector.
 ;
-; Copyright (c) 2023, Hissycode Ltd. All rights reserved.
+; Copyright (c) 2023, Jonathan Poalses.
 ;