Stt adapter IBM - andrew d anderson (#123)

* Add IBM Watson TTS Json import support.

* Fix IBM TTS index.test.js

* Update src/lib/Util/adapters/ibm/index.js

Co-Authored-By: AndrewDAnderson <[email protected]>

* major refactor - working

cleaned up the code making it more in line with the logic in the other adapter, and better setup for accomodating change over time

* fixed test by updating example

was missing speaker info

* mend

* changes from PR review

Author: pietrop

README.md

@@ -88,9 +88,11 @@ import { TranscriptEditor } from "@bbc/react-transcript-editor";
 
 <!-- _High level overview of system architecture_ -->
 
-Uses [`create-component-lib`](https://www.npmjs.com/package/create-component-lib) as explaied in this [blog post](https://hackernoon.com/creating-a-library-of-react-components-using-create-react-app-without-ejecting-d182df690c6b) to setup the environment to develop this React component.
+uses [`create-component-lib`](https://www.npmjs.com/package/create-component-lib) as explaied in this [blog post](https://hackernoon.com/creating-a-library-of-react-components-using-create-react-app-without-ejecting-d182df690c6b) to setup the environment to develop this React.
 
 This uses [Create React App 2.0](https://reactjs.org/blog/2018/10/01/create-react-app-v2.html) so we are using [CSS Modules](https://github.com/css-modules/css-modules) to contain the scope of the css for this component.
+<!-- 
+Uses CSS grid-layout https://medium.com/samsung-internet-dev/common-responsive-layouts-with-css-grid-and-some-without-245a862f48df -->
 
 > Place everything you want to publish to npm inside `src/lib`.
 
@@ -175,7 +177,7 @@ See [CONTRIBUTING.md](./CONTRIBUTING.md) guidelines and [CODE_OF_CONDUCT.md](./C
 
 ## Licence
 
-See [LICENCE.md](./LICENCE.md)
+<!-- mention MIT Licence -->
 
 ## Legal Disclaimer
 

docs/features-list.md

@@ -56,10 +56,10 @@ Import Transcript Json - Adapters
 - [x] News Labs API - BBC Kaldi
 - [x] autoEdit 2
 - [x] AWS Transcriber
+- [x] IBM Watson STT
+- [X] Speechmatics
 - [ ] Gentle Transcription 
 - [ ] Gentle Alignment Json
-- [ ] IBM Watson STT
-- [X] Speechmatics
 - [ ] AssemblyAI
 - [ ] Rev
 - [ ] Srt

src/lib/Util/adapters/amazon-transcribe/index.js

@@ -1,35 +1,41 @@
-import generateEntitiesRanges from '../generate-entities-ranges/index.js';
-
 /**
- * Helper function to generate draft.js entities,
- * see unit test for example data structure
- * it adds offset and length to recognise word in draftjs
+ * Converts AWS Transcribe Json to DraftJs
+ * see `sample` folder for example of input and output as well as `example-usage.js`
  */
 
+import generateEntitiesRanges from '../generate-entities-ranges/index.js';
+
+export const stripLeadingSpace = word => {
+  return word.replace(/^\s/, '');
+};
+
 /**
  *  @param {json} words  - List of words
  *  @param {string} wordAttributeName - eg 'punct' or 'text' or etc.
  * attribute for the word object containing the text. eg word ={ punct:'helo', ... }
  *  or eg word ={ text:'helo', ... }
  */
-
-export const getBestAlternativeForWord = (word) => {
+export const getBestAlternativeForWord = word => {
   if (/punctuation/.test(word.type)) {
     return Object.assign(word.alternatives[0], { confidence: 1 }); //Transcribe doesn't provide a confidence for punctuation
   }
-  const wordWithHighestConfidence = word.alternatives.reduce(function(prev, current) {
-    return (parseFloat(prev.confidence) > parseFloat(current.confidence)) ? prev : current;
+  const wordWithHighestConfidence = word.alternatives.reduce(function(
+    prev,
+    current
+  ) {
+    return parseFloat(prev.confidence) > parseFloat(current.confidence)
+      ? prev
+      : current;
   });
 
   return wordWithHighestConfidence;
 };
 
 /**
-Normalizes words so they can be used in
- the generic generateEntitiesRanges() method
-**/
-
-const normalizeWord = (currentWord, previousWord) => {
+ * Normalizes words so they can be used in
+ * the generic generateEntitiesRanges() method
+ **/
+const normalizeWord = currentWord => {
   const bestAlternative = getBestAlternativeForWord(currentWord);
 
   return {
@@ -52,7 +58,7 @@ export const appendPunctuationToPreviousWord = (punctuation, previousWord) => {
   };
 };
 
-export const mapPunctuationItemsToWords = (words) => {
+export const mapPunctuationItemsToWords = words => {
   const itemsToRemove = [];
   const dirtyArray = words.map((word, index) => {
     let previousWord = {};
@@ -61,8 +67,7 @@ export const mapPunctuationItemsToWords = (words) => {
       previousWord = words[index - 1];
 
       return appendPunctuationToPreviousWord(word, previousWord);
-    }
-    else {
+    } else {
       return word;
     }
   });
@@ -72,17 +77,12 @@ export const mapPunctuationItemsToWords = (words) => {
   });
 };
 
-export const stripLeadingSpace = (word) => {
-  return word.replace(/^\s/, '');
-};
-
 /**
  * groups words list from amazon transcribe transcript based on punctuation.
  * @todo To be more accurate, should introduce an honorifics library to do the splitting of the words.
- * @param {array} words - array of words opbjects from kaldi transcript
+ * @param {array} words - array of words objects from kaldi transcript
  */
-
-const groupWordsInParagraphs = (words) => {
+const groupWordsInParagraphs = words => {
   const results = [];
   let paragraph = {
     words: [],
@@ -106,11 +106,13 @@ const groupWordsInParagraphs = (words) => {
   return results;
 };
 
-const amazonTranscribeToDraft = (amazonTranscribeJson) => {
+const amazonTranscribeToDraft = amazonTranscribeJson => {
   const results = [];
   const tmpWords = amazonTranscribeJson.results.items;
   const wordsWithRemappedPunctuation = mapPunctuationItemsToWords(tmpWords);
-  const wordsByParagraphs = groupWordsInParagraphs(wordsWithRemappedPunctuation);
+  const wordsByParagraphs = groupWordsInParagraphs(
+    wordsWithRemappedPunctuation
+  );
   wordsByParagraphs.forEach((paragraph, i) => {
     const draftJsContentBlockParagraph = {
       text: paragraph.text.join(' '),
@@ -122,7 +124,7 @@ const amazonTranscribeToDraft = (amazonTranscribeJson) => {
       },
       // the entities as ranges are each word in the space-joined text,
       // so it needs to be compute for each the offset from the beginning of the paragraph and the length
-      entityRanges: generateEntitiesRanges(paragraph.words, 'text'), // wordAttributeName
+      entityRanges: generateEntitiesRanges(paragraph.words, 'text') // wordAttributeName
     };
     results.push(draftJsContentBlockParagraph);
   });

src/lib/Util/adapters/autoEdit2/index.js

@@ -1,31 +1,6 @@
 /**
- * Convert autoEdit2 Json
- *
- * into
- *
- ```
- const blocks = [
-        {
-            text: 'Hello',
-            type: 'paragraph',
-            data: {
-            speaker: 'Foo',
-            },
-            entityRanges: [],
-        },
-        {
-            text: 'World',
-            type: 'paragraph',
-            data: {
-            speaker: 'Bar',
-            },
-            entityRanges: [],
-        },
-        ];
-```
- *
- * See samples folder and test file
- * for reference data structures
+ * Convert autoEdit2 Json to draftJS
+ * see `sample` folder for example of input and output as well as `example-usage.js`
  */
 
 import generateEntitiesRanges from '../generate-entities-ranges/index';

src/lib/Util/adapters/bbc-kaldi/index.js

@@ -1,118 +1,6 @@
 /**
- * Convert BBC Kaldi json
- ```
- {
-    "action": "audio-transcribe",
-    "retval": {
-      "status": true,
-      "wonid": "octo:2692ea33-d595-41d8-bfd5-aa7f2d2f89ee",
-      "punct": "There is a day. About ten years ago when  ...",
-      "words": [
-        {
-          "start": 13.02,
-          "confidence": 0.68,
-          "end": 13.17,
-          "word": "there",
-          "punct": "There",
-          "index": 0
-        },
-        {
-          "start": 13.17,
-          "confidence": 0.61,
-          "end": 13.38,
-          "word": "is",
-          "punct": "is",
-          "index": 1
-        },
-        ...
-```
- *
- * into
- *
- ```
- const blocks = [
-  {
-    "text": "There is a day.",
-    "type": "paragraph",
-    "data": {
-      "speaker": "TBC 0",
-      "words": [
-        {
-          "start": 13.02,
-          "confidence": 0.68,
-          "end": 13.17,
-          "word": "there",
-          "punct": "There",
-          "index": 0
-        },
-        {
-          "start": 13.17,
-          "confidence": 0.61,
-          "end": 13.38,
-          "word": "is",
-          "punct": "is",
-          "index": 1
-        },
-        {
-          "start": 13.38,
-          "confidence": 0.99,
-          "end": 13.44,
-          "word": "a",
-          "punct": "a",
-          "index": 2
-        },
-        {
-          "start": 13.44,
-          "confidence": 1,
-          "end": 13.86,
-          "word": "day",
-          "punct": "day.",
-          "index": 3
-        }
-      ],
-      "start": 13.02
-    },
-    "entityRanges": [
-      {
-        "start": 13.02,
-        "end": 13.17,
-        "confidence": 0.68,
-        "text": "There",
-        "offset": 0,
-        "length": 5,
-        "key": "li6c6ld"
-      },
-      {
-        "start": 13.17,
-        "end": 13.38,
-        "confidence": 0.61,
-        "text": "is",
-        "offset": 6,
-        "length": 2,
-        "key": "pcgzkp6"
-      },
-      {
-        "start": 13.38,
-        "end": 13.44,
-        "confidence": 0.99,
-        "text": "a",
-        "offset": 9,
-        "length": 1,
-        "key": "ngomd9"
-      },
-      {
-        "start": 13.44,
-        "end": 13.86,
-        "confidence": 1,
-        "text": "day.",
-        "offset": 11,
-        "length": 4,
-        "key": "sgmfl4f"
-      }
-    ]
-  },
-  ...
-```
+ * Convert BBC Kaldi json to draftJs
+ * see `sample` folder for example of input and output as well as `example-usage.js`
  *
  */
 

src/lib/Util/adapters/ibm/example-usage.js

@@ -0,0 +1,6 @@
+import ibmToDraft from './index.js';
+import ibmTedTalkTranscript from './sample/ibmTedTalkTranscript.sample.json';
+
+const result = ibmToDraft(ibmTedTalkTranscript);
+
+console.log(JSON.stringify(result, null, 2));