wink-nlp - npm Package Compare versions

Comparing version 1.12.3 to 1.13.0

.nyc_output/processinfo/index.json

@@ -1,1 +0,1 @@
-{"processes":{"ecaabe35-e24e-4d7b-931f-1f56d35101ff":{"parent":null,"children":[]}},"files":{"/Users/neilsbohr/dev/winkjs/wink-nlp/src/wink-nlp.js":["ecaabe35-e24e-4d7b-931f-1f56d35101ff"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/dd-wrapper.js":["ecaabe35-e24e-4d7b-931f-1f56d35101ff"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/constants.js":["ecaabe35-e24e-4d7b-931f-1f56d35101ff"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/doc-v2.js":["ecaabe35-e24e-4d7b-931f-1f56d35101ff"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/contained-entities.js":["ecaabe35-e24e-4d7b-931f-1f56d35101ff"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/locate.js":["ecaabe35-e24e-4d7b-931f-1f56d35101ff"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/get-parent-item.js":["ecaabe35-e24e-4d7b-931f-1f56d35101ff"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/search.js":["ecaabe35-e24e-4d7b-931f-1f56d35101ff"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/col-get-item.js":["ecaabe35-e24e-4d7b-931f-1f56d35101ff"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/sel-get-item.js":["ecaabe35-e24e-4d7b-931f-1f56d35101ff"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/col-each.js":["ecaabe35-e24e-4d7b-931f-1f56d35101ff"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/sel-each.js":["ecaabe35-e24e-4d7b-931f-1f56d35101ff"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/col-filter.js":["ecaabe35-e24e-4d7b-931f-1f56d35101ff"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/sel-filter.js":["ecaabe35-e24e-4d7b-931f-1f56d35101ff"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/itm-token-out.js":["ecaabe35-e24e-4d7b-931f-1f56d35101ff"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/its.js":["ecaabe35-e24e-4d7b-931f-1f56d35101ff"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/sort4FT.js":["ecaabe35-e24e-4d7b-931f-1f56d35101ff"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/allowed.js":["ecaabe35-e24e-4d7b-931f-1f56d35101ff"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/as.js":["ecaabe35-e24e-4d7b-931f-1f56d35101ff"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/contained-markings.js":["ecaabe35-e24e-4d7b-931f-1f56d35101ff"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/col-tokens-out.js":["ecaabe35-e24e-4d7b-931f-1f56d35101ff"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/sel-tokens-out.js":["ecaabe35-e24e-4d7b-931f-1f56d35101ff"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/itm-entity-out.js":["ecaabe35-e24e-4d7b-931f-1f56d35101ff"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/col-entities-out.js":["ecaabe35-e24e-4d7b-931f-1f56d35101ff"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/sel-entities-out.js":["ecaabe35-e24e-4d7b-931f-1f56d35101ff"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/itm-sentence-out.js":["ecaabe35-e24e-4d7b-931f-1f56d35101ff"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/col-sentences-out.js":["ecaabe35-e24e-4d7b-931f-1f56d35101ff"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/itm-document-out.js":["ecaabe35-e24e-4d7b-931f-1f56d35101ff"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/print-tokens.js":["ecaabe35-e24e-4d7b-931f-1f56d35101ff"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/cache.js":["ecaabe35-e24e-4d7b-931f-1f56d35101ff"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/tokenizer.js":["ecaabe35-e24e-4d7b-931f-1f56d35101ff"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/recursive-tokenizer.js":["ecaabe35-e24e-4d7b-931f-1f56d35101ff"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/compile-trex.js":["ecaabe35-e24e-4d7b-931f-1f56d35101ff"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/tokens-mappers.js":["ecaabe35-e24e-4d7b-931f-1f56d35101ff"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/examples-compiler.js":["ecaabe35-e24e-4d7b-931f-1f56d35101ff"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/automaton.js":["ecaabe35-e24e-4d7b-931f-1f56d35101ff"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/compose-patterns.js":["ecaabe35-e24e-4d7b-931f-1f56d35101ff"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/helper.js":["ecaabe35-e24e-4d7b-931f-1f56d35101ff"],"/Users/neilsbohr/dev/winkjs/wink-nlp/utilities/bm25-vectorizer.js":["ecaabe35-e24e-4d7b-931f-1f56d35101ff"],"/Users/neilsbohr/dev/winkjs/wink-nlp/utilities/allowed.js":["ecaabe35-e24e-4d7b-931f-1f56d35101ff"],"/Users/neilsbohr/dev/winkjs/wink-nlp/utilities/similarity.js":["ecaabe35-e24e-4d7b-931f-1f56d35101ff"]},"externalIds":{}}
+{"processes":{"64286668-c8e7-4a6e-b8a7-c1395bfb6e04":{"parent":null,"children":[]}},"files":{"/Users/neilsbohr/dev/winkjs/wink-nlp/src/wink-nlp.js":["64286668-c8e7-4a6e-b8a7-c1395bfb6e04"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/dd-wrapper.js":["64286668-c8e7-4a6e-b8a7-c1395bfb6e04"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/constants.js":["64286668-c8e7-4a6e-b8a7-c1395bfb6e04"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/doc-v2.js":["64286668-c8e7-4a6e-b8a7-c1395bfb6e04"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/contained-entities.js":["64286668-c8e7-4a6e-b8a7-c1395bfb6e04"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/locate.js":["64286668-c8e7-4a6e-b8a7-c1395bfb6e04"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/get-parent-item.js":["64286668-c8e7-4a6e-b8a7-c1395bfb6e04"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/search.js":["64286668-c8e7-4a6e-b8a7-c1395bfb6e04"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/col-get-item.js":["64286668-c8e7-4a6e-b8a7-c1395bfb6e04"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/sel-get-item.js":["64286668-c8e7-4a6e-b8a7-c1395bfb6e04"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/col-each.js":["64286668-c8e7-4a6e-b8a7-c1395bfb6e04"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/sel-each.js":["64286668-c8e7-4a6e-b8a7-c1395bfb6e04"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/col-filter.js":["64286668-c8e7-4a6e-b8a7-c1395bfb6e04"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/sel-filter.js":["64286668-c8e7-4a6e-b8a7-c1395bfb6e04"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/itm-token-out.js":["64286668-c8e7-4a6e-b8a7-c1395bfb6e04"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/its.js":["64286668-c8e7-4a6e-b8a7-c1395bfb6e04"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/sort4FT.js":["64286668-c8e7-4a6e-b8a7-c1395bfb6e04"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/allowed.js":["64286668-c8e7-4a6e-b8a7-c1395bfb6e04"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/as.js":["64286668-c8e7-4a6e-b8a7-c1395bfb6e04"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/contained-markings.js":["64286668-c8e7-4a6e-b8a7-c1395bfb6e04"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/col-tokens-out.js":["64286668-c8e7-4a6e-b8a7-c1395bfb6e04"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/sel-tokens-out.js":["64286668-c8e7-4a6e-b8a7-c1395bfb6e04"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/itm-entity-out.js":["64286668-c8e7-4a6e-b8a7-c1395bfb6e04"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/col-entities-out.js":["64286668-c8e7-4a6e-b8a7-c1395bfb6e04"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/sel-entities-out.js":["64286668-c8e7-4a6e-b8a7-c1395bfb6e04"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/itm-sentence-out.js":["64286668-c8e7-4a6e-b8a7-c1395bfb6e04"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/col-sentences-out.js":["64286668-c8e7-4a6e-b8a7-c1395bfb6e04"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/itm-document-out.js":["64286668-c8e7-4a6e-b8a7-c1395bfb6e04"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/print-tokens.js":["64286668-c8e7-4a6e-b8a7-c1395bfb6e04"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/cache.js":["64286668-c8e7-4a6e-b8a7-c1395bfb6e04"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/tokenizer.js":["64286668-c8e7-4a6e-b8a7-c1395bfb6e04"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/recursive-tokenizer.js":["64286668-c8e7-4a6e-b8a7-c1395bfb6e04"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/compile-trex.js":["64286668-c8e7-4a6e-b8a7-c1395bfb6e04"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/tokens-mappers.js":["64286668-c8e7-4a6e-b8a7-c1395bfb6e04"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/examples-compiler.js":["64286668-c8e7-4a6e-b8a7-c1395bfb6e04"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/automaton.js":["64286668-c8e7-4a6e-b8a7-c1395bfb6e04"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/compose-patterns.js":["64286668-c8e7-4a6e-b8a7-c1395bfb6e04"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/identify-marked-area.js":["64286668-c8e7-4a6e-b8a7-c1395bfb6e04"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/helper.js":["64286668-c8e7-4a6e-b8a7-c1395bfb6e04"],"/Users/neilsbohr/dev/winkjs/wink-nlp/utilities/bm25-vectorizer.js":["64286668-c8e7-4a6e-b8a7-c1395bfb6e04"],"/Users/neilsbohr/dev/winkjs/wink-nlp/utilities/allowed.js":["64286668-c8e7-4a6e-b8a7-c1395bfb6e04"],"/Users/neilsbohr/dev/winkjs/wink-nlp/utilities/similarity.js":["64286668-c8e7-4a6e-b8a7-c1395bfb6e04"]},"externalIds":{}}

CHANGELOG.md

@@ -0,1 +1,9 @@
+# [Improving mark's functionality in custom entities](https://github.com/winkjs/wink-nlp/releases/tag/1.13.0)
+## Version 1.13.0 December 09, 2022
+
+### ✨ Features
+- Mark allows marking w.r.t. the last element of the pattern. For example if a pattern matches `a fluffy cat` then `mark: [-2, -1]` will extract `fluffy cat` — especially useful when the match length is unknown. 💃
+- Improved error handling while processing mark's arguments.  🙌
+
+
 # [Operational update](https://github.com/winkjs/wink-nlp/releases/tag/1.12.3)
@@ -2,0 +10,0 @@ ## Version 1.12.3 November 18, 2022

package.json

 {
   "name": "wink-nlp",
-  "version": "1.12.3",
+  "version": "1.13.0",
   "description": "Developer friendly Natural Language Processing ✨",
@@ -49,8 +49,8 @@ "keywords": [
     "benchmark": "^2.1.4",
-    "chai": "^4.3.6",
+    "chai": "^4.3.7",
     "coveralls": "^3.1.1",
     "docker": "^1.0.0",
     "dtslint": "^4.2.1",
-    "eslint": "^8.25.0",
-    "mocha": "^10.0.0",
+    "eslint": "^8.29.0",
+    "mocha": "^10.1.0",
     "nyc": "^15.1.0"
@@ -57,0 +57,0 @@ },

README.md

@@ -15,5 +15,5 @@ # winkNLP
 ## Build amazing apps quickly
-| [Wikipedia article timeline](https://winkjs.org/showcase-timeline/) | [Context aware word cloud](https://observablehq.com/@winkjs/how-to-create-a-context-aware-word-cloud) | [Key sentences detection](https://observablehq.com/@winkjs/how-to-visualize-key-sentences-in-a-document) |
+| [Wikipedia article timeline](https://observablehq.com/@winkjs/how-to-visualize-timeline-of-a-wiki-article) | [Context aware word cloud](https://observablehq.com/@winkjs/how-to-create-a-context-aware-word-cloud) | [Key sentences detection](https://observablehq.com/@winkjs/how-to-visualize-key-sentences-in-a-document) |
 | --- | --- | --- |
-| [<img src="https://user-images.githubusercontent.com/29990/202497363-19c30578-8146-4f36-9c4b-4de613610837.png">](https://winkjs.org/showcase-timeline/)| [<img src="https://user-images.githubusercontent.com/29990/202506181-1a926ee0-788f-4aa1-aeac-a097f09fe747.png">](https://observablehq.com/@winkjs/how-to-create-a-context-aware-word-cloud)|[<img src="https://user-images.githubusercontent.com/29990/202506490-7f999d12-8319-4969-b92b-0649559ffbe6.png">](https://observablehq.com/@winkjs/how-to-visualize-key-sentences-in-a-document)|
+| [<img src="https://user-images.githubusercontent.com/29990/202497363-19c30578-8146-4f36-9c4b-4de613610837.png">](https://observablehq.com/@winkjs/how-to-visualize-timeline-of-a-wiki-article)| [<img src="https://user-images.githubusercontent.com/29990/202506181-1a926ee0-788f-4aa1-aeac-a097f09fe747.png">](https://observablehq.com/@winkjs/how-to-create-a-context-aware-word-cloud)|[<img src="https://user-images.githubusercontent.com/29990/202506490-7f999d12-8319-4969-b92b-0649559ffbe6.png">](https://observablehq.com/@winkjs/how-to-visualize-key-sentences-in-a-document)|
 
@@ -23,3 +23,3 @@ Head to  [live examples](https://winkjs.org/examples.html) to explore further.
 ## Blazing fast
-WinkNLP can easily process large amount of raw text at speeds over <mark>**650,000 tokens/second**</mark> on a M1 Macbook Pro in both browser and Node.js environments. It even runs smoothly on a low-end smartphone's browser.
+WinkNLP can easily process large amount of raw text at speeds over **650,000 tokens/second**&nbsp; on a M1 Macbook Pro in both browser and Node.js environments. It even runs smoothly on a low-end smartphone's browser.
 
@@ -35,12 +35,14 @@ | Environment | Benchmarking Command |
 <table>
-<tr><td width="330px;">Fast, lossless & multilingual tokenizer ⚡️</td><td>For example, the text string <b><code style="font-size: 0.9em">"¡Hola! नमस्कार! Hi! Bonjour chéri"</code></b> tokenizes as <code style="font-size: 0.9em">["¡", "Hola", "!", "नमस्कार", "!", "Hi", "!", "Bonjour", "chéri"]</code>.  It tokenizes text at a speed close to <b>4 million</b> tokens/second on a M1 MBP's browser.</td></tr>
-<tr><td>Developer friendly and intuitive <a href="https://winkjs.org/wink-nlp/getting-started.html">API</a> 💚</td><td>As simple as DOM manipulation; most <a href="https://observablehq.com/@winkjs/how-to-build-a-naive-wikification-tool?collection=@winkjs/winknlp-recipes">live examples</a> have <b>30-40</b> lines of code.</td></tr>
-<tr><td>Best-in-class <a href="https://winkjs.org/wink-nlp/visualizing-markup.html">text visualization</a> 🖼</td><td>Programmatically <b><a href="https://winkjs.org/wink-nlp/markup.html">mark</a></b> tokens, sentences, entities, etc. using HTML mark or any other tag of your choice.</td></tr>
-<tr><td>Extensive text processing features ♻️</td><td>Checkout how a <a href="https://github.com/winkjs/wink-naive-bayes-text-classifier#readme">Naive Bayes classifier</a> achieves <b>impressive</b> chatbot intent classification accuracy with right kind of preprocessing with winkNLP.</td></tr>
-<tr><td>Pre-trained <a href="https://winkjs.org/wink-nlp/language-models.html">language models</a> 🔠</td><td>Compact sizes starting from <b>&lt;3MB</b>.</td></tr>
-<tr><td>Host of <a href="https://winkjs.org/wink-nlp/its-as-helper.html">utilities & tools</a> 💼</td><td>BM25 vectorizer; Several similarity methods – Cosine, Tversky, Sørensen-Dice, Otsuka-Ochiai; Helpers to get bag of words, frequency table, lemma/stem, stop word removal and many more.</td></tr>
+<tr><td width="330px;">🐎 Fast, lossless & multilingual tokenizer </td><td>For example, the multilingual text string <b><code style="font-size: 0.9em">"¡Hola! नमस्कार! Hi! Bonjour chéri"</code></b>  is tokenized as <code style="font-size: 0.9em">["¡", "Hola", "!", "नमस्कार", "!", "Hi", "!", "Bonjour", "chéri"]</code>.  The tokenizer processes text at a speed close to <b>4 million</b> tokens/second on a M1 MBP's browser.</td></tr>
+<tr><td>✨ Developer friendly and intuitive <a href="https://winkjs.org/wink-nlp/getting-started.html">API</a></td><td>With winkNLP, process any text using a simple, declarative syntax; most <a href="https://observablehq.com/@winkjs/how-to-build-a-naive-wikification-tool?collection=@winkjs/winknlp-recipes">live examples</a> have <b>30-40</b> lines of code.</td></tr>
+<tr><td>🖼 Best-in-class <a href="https://winkjs.org/wink-nlp/visualizing-markup.html">text visualization</a></td><td>Programmatically <b><a href="https://winkjs.org/wink-nlp/markup.html">mark</a></b> tokens, sentences, entities, etc. using HTML mark or any other tag of your choice.</td></tr>
+<tr><td>♻️ Extensive text processing features</td><td>Remove and/or retain tokens with specific attributes such as part-of-speech, named entity type, token type, stop word, shape and many more; compute Flesch reading ease score; generate n-grams; normalize, lemmatise or stem. Checkout how with the right kind of text preprocessing, even <a href="https://github.com/winkjs/wink-naive-bayes-text-classifier#readme">Naive Bayes classifier</a> achieves <b>impressive (≥90%)</b> accuracy in sentiment analysis and chatbot intent classification tasks.</td></tr>
+<tr><td>🔠 Pre-trained <a href="https://winkjs.org/wink-nlp/language-models.html">language models</a></td><td>Compact sizes starting from <b>&lt;3MB</b> – reduced model loading time drastically.</td></tr>
+<tr><td>💼 Host of <a href="https://winkjs.org/wink-nlp/its-as-helper.html">utilities & tools</a></td><td>BM25 vectorizer; Several similarity methods – Cosine, Tversky, Sørensen-Dice, Otsuka-Ochiai; Helpers to get bag of words, frequency table, lemma/stem, stop word removal and many more.</td></tr>
 </table>
 
-WinkJS also has packages like [Naive Bayes classifier](https://github.com/winkjs/wink-naive-bayes-text-classifier), [multi-class averaged perceptron](https://github.com/winkjs/wink-perceptron) and [popular token and string distance methods](https://github.com/winkjs/wink-distance), which complement winkNLP. 
 
+> WinkJS also has packages like [Naive Bayes classifier](https://github.com/winkjs/wink-naive-bayes-text-classifier), [multi-class averaged perceptron](https://github.com/winkjs/wink-perceptron) and [popular token and string distance methods](https://github.com/winkjs/wink-distance), which complement winkNLP.
+
+
 ## Documentation
@@ -131,3 +133,3 @@ - [Concepts](https://winkjs.org/wink-nlp/getting-started.html) — everything you need to know to get started.
 
-### New feature ✨
+### New feature 🌟
 Looking for a new feature, request it via the [new features & ideas](https://github.com/winkjs/wink-nlp/discussions/categories/new-features-ideas) discussion forum  or consider becoming a [contributor](https://github.com/winkjs/wink-nlp/blob/master/CONTRIBUTING.md).
@@ -143,2 +145,2 @@
 
-It is licensed under the terms of the MIT License.
+It is licensed under the terms of the MIT License.

src/automaton.js

@@ -35,3 +35,4 @@ //     wink-nlp
 /* eslint-disable guard-for-in */
-var composePatterns = require( './compose-patterns.js' );
+const composePatterns = require( './compose-patterns.js' );
+const identifyMarkedArea = require( './identify-marked-area.js' );
 
@@ -176,3 +177,3 @@ const eosTokenN = 2070000;
       // execution. Update must happen as a deep copy & not directly!
-      markedStates[ state ] = [ mark[ 0 ], ( length - mark[ 1 ] - 1 ) ];
+      markedStates[ state ] = identifyMarkedArea( mark, length );
     }
@@ -263,3 +264,2 @@
     var mark = markedStates[ m0 ];
-
     var customProperty = customPropertyAtStates[ m0 ];
@@ -266,0 +266,0 @@ if ( mark ) {

src/examples-compiler.js

@@ -60,8 +60,21 @@ //     wink-nlp
 /**
- * Creates instance of compiler using input arguments.
- * @param  {JSON}     cerModel    meta model used during compilation.
- * @param  {object}   cache       the wink-nlp cache.
- * @param  {function} tokenize    tokenizer function from wink-nlp.
- * @param  {boolean}  matchValue  config.matchValue of learnCustomEntities() API.
- * @return {object}               contains run function.
+ * It transforms the input patterns for custom entity recognition into a model,
+ * which is run by winkNLP's `readDoc()` method. The model is created by
+ * the `learnCustomEntities()` method of core winkNLP using this compiler. Brefore
+ * the compiler can be **run**, its instance must be created using the following
+ * parameters:
+ *
+ * @param  {JSON}     cerModel    precompiled custom entity meta model — handles escaping
+ *                                of entity literals. For example `^ADJ` will match
+ *                                with token `ADJ` (or `adj` based on `matchValue` in
+ *                                `cerConfig`), whereas `ADJ` will match with the
+ *                                adjective part-of-speech of a token.
+ * @param  {object}   cache       of lexicon, which is required to deliver performance.
+ * @param  {function} tokenize    is instantiated from core tokenizer, which tokenises the
+ *                                input patterns. It is used in the `tokenizeText()` private
+ *                                method of compiler.
+ * @param  {boolean}  matchValue  match value flag — defines match on either `value` or
+ *                                `normal` of tokens.<br/>
+ * @return {object}               contains **run** function, which can compile the input
+ *                                pattern into a model.
  * @private
@@ -76,2 +89,4 @@ */
   cerAutomata.importJSON( cerModel );
+  // On pattern detection, we need to save the custom property — `preserve`
+  // created by the `cerModel's` execution.
   cerAutomata.setOnPatternDetectionFn( ( match, customProperty ) => ( match.push( customProperty ) ) );
@@ -78,0 +93,0 @@

src/helper.js

@@ -35,10 +35,60 @@ //     wink-nlp
 
+/**
+ * Tests if argument `v` is a JS object.
+ *
+ * @param {*} v       is tested for a valid JS object.
+ * @returns {boolean} ture if `v` is a valid JS object, otherwise false.
+ */
 helper.isObject = function ( v ) {
-  return ( v && ( Object.prototype.toString.call( v ) === '[object Object]' ) ) ? true : false; // eslint-disable-line no-unneeded-ternary
+  return ( Object.prototype.toString.call( v ) === '[object Object]' );
 }; // isObject()
 
+/**
+ * Tests if argument `v` is a JS array.
+ *
+ * @param {*} v       is tested for a valid JS array.
+ * @returns {boolean} ture if `v` is a valid JS array, otherwise false.
+ */
 helper.isArray = function ( v ) {
-  return ( ( v !== undefined ) && ( v !== null ) && ( Object.prototype.toString.call( v ) === '[object Array]' ) );
+  return ( Object.prototype.toString.call( v ) === '[object Array]' );
 }; // isArray()
 
+/**
+ * Tests if argument `n` is a finite integer.
+ *
+ * @param {*} n       is tested for a finite integer.
+ * @returns {boolean} ture if `n` is a finite integer, otherwise false.
+ */
+helper.isFiniteInteger = function ( n ) {
+  return (
+    ( typeof n === 'number' ) &&
+    !isNaN( n ) &&
+    isFinite( n ) &&
+    ( n === Math.round( n ) )
+  );
+}; // isFiniteInteger()
+
+/**
+ * Tests if argument `a` contains one or more finite integers.
+ *
+ * @param {*} a       is tested for an array of finite integers.
+ * @returns {boolean} ture if `n` is an array of finite integers, otherwise false.
+ */
+helper.isIntegerArray = function ( a ) {
+  // If it is not an array, return `false`.
+  if ( !helper.isArray( a ) ) return false;
+
+  // Has no element i.e. no finite integer — return `false`.
+  if ( a.length === 0 ) return false;
+
+  // Test every element for a finite integer.
+  for ( let i = 0; i < a.length; i += 1 ) {
+    // Any failure means immediately return `false`.
+    if ( !helper.isFiniteInteger( a[ i ] ) ) return false;
+  }
+
+  // It is an array and contains all finite integers, return `true`.
+  return true;
+}; // isIntegerArray()
+
 module.exports = helper;

src/wink-nlp.js

@@ -355,2 +355,10 @@ //     wink-nlp
           }
+          // If mark is present then it should be an array of integers **and** its length must
+          // be equal to 2 **and** start index <= end index.
+          if ( ( ex.mark !== undefined ) &&
+                ( !helper.isIntegerArray( ex.mark ) ||
+                ( ex.mark.length !== 2 ) ||
+                ( ex.mark.length === 2 && ex.mark[ 0 ] > ex.mark[ 1 ] ) ) ) {
+            throw Error( `wink-nlp: mark should be an array containing start & end indexes, instead found:\n\n${JSON.stringify( ex.mark, null, 2 )}` );
+          }
         } else {
@@ -357,0 +365,0 @@ // Example is not an object.

New alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

Fixed alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

Improved metrics

Total package byte prevSize

584883

increased by2.13%

Number of package files

61

increased by1.67%

Lines of code

6076

increased by2.17%

Number of lines in readme file

142

increased by2.16%

No dependency changes