transcript-parser - npm Package Compare versions

Comparing version 0.0.1 to 0.0.2

app.js

@@ -15,3 +15,6 @@ "use strict";
   this.defaultSettings = {
-    removeActions: true
+    removeActions: true,
+    removeAnnotations: true,
+    removeTimestamps: true, //Overriden by removeAnnotations
+    removeUnknownSpeaker: false
   };
@@ -21,4 +24,4 @@ this.settings = _.assign(this.defaultSettings, options);
     newLine: /\r?\n/,
-    newLineOrAction: /(?:\r?\n|\([A-Z\ ]+\))/,
-    speaker: /^([A-Z\d\ \/,.\-\(\)]+)(?: \[.+\])?:/,
+    action: /\([A-Z\ ]+\)\ ?/,
+    speaker: /^([A-Z\d\ \/,.\-\(\)]+)(?: \[.+\])?:\ ?/,
     timestamp: /\[\d{1,2}:\d{1,2}:\d{1,2}\]\ ?/,
@@ -33,12 +36,21 @@ annotation: /\[.+?\]\ ?/
 proto.parseOne = function(transcript) {
-  const lines = transcript.split(this.settings.removeActions?
-    this.regex.newLineOrAction : this.regex.newLine)
-    //Remove blank lines
-    .filter(line => line.length > 0)
+  var lines = transcript.split(this.regex.newLine)
+    .filter(line => line.length > 0); //Remove blank lines
+  lines = (this.settings.removeActions) ? lines.map(line => line.split(this.regex.action).join('')): lines;
+  if(this.settings.removeAnnotations) {
     //Remove annotations
-    .map(line => line.split(this.regex.annotation).join(''));
+    lines = lines.map(line => line.split(this.regex.annotation).join(''));
+  } else if(this.settings.removeTimestamps) {
+    //Remove timestamps
+    lines = lines.map(line => line.split(this.regex.timestamp).join(''));
+  }
+
+  //Output object
   const output = {};
+  //Object containing the speakers and their lines
   output.speaker = {};
+  //List of the speakers, in order
   output.order = [];
 
+  //Current speaker
   var speaker = 'none';
@@ -51,8 +63,10 @@
     }
-    if(!(speaker in output.speaker)) {
+    if(!(speaker in output.speaker) &&
+      (!this.settings.removeUnknownSpeaker || speaker !== 'none')) {
       output.speaker[speaker] = [];
     }
-    output.speaker[speaker].push(lines[i]);
-    output.order.push(speaker);
-
+    if(!this.settings.removeUnknownSpeaker || speaker !== 'none') {
+      output.speaker[speaker].push(lines[i]);
+      output.order.push(speaker);
+    }
   }
@@ -59,0 +73,0 @@ return output;

package.json

 {
   "name": "transcript-parser",
-  "version": "0.0.1",
+  "version": "0.0.2",
   "description": "Parses plaintext speech/debate/radio transcripts into JavaScript objects.",
@@ -5,0 +5,0 @@ "main": "app.js",

README.md

 transcript-parser
 =================
-
 [![Build Status](https://travis-ci.org/willshiao/transcript-parser.svg?branch=master)](https://travis-ci.org/willshiao/transcript-parser)
 
-Parses plaintext speech/debate/radio transcripts into JavaScript objects.
+## Description
+
+Parses plaintext speech/debate/radio transcripts into JavaScript objects. It is still in early development and is not stable. Pull requests are welcome.
+
+## Usage
+
+`npm install transcript-parser`
+
+    const fs = require('fs');
+    const TranscriptParser = require('transcript-parser');
+    const tp = new TranscriptParser();
+    
+    //Do not use readFileSync in production
+    const output = tp.parseOne(fs.readFileSync('transcript.txt', {encoding: 'UTF-8'}));
+    console.log(output);
+
+
+## Config
+
+The constructor for `TranscriptParser` accepts an options argument.
+
+Options:
+
+- removeActions
+    + default: `true`
+    + Specifies if the parser should remove actions (e.g. "(APPLAUSE)").
+- removeAnnotations
+    + default: `true`
+    + Specifies if the parser should remove annotations (surrounded by `[]`).
+- removeTimestamps
+    + default: `true`
+    + **True if `removeAnnotations` is true**
+    + Specifies if the parser should remove timestamps (in the `[##:##:##]` format).
+- removeUnknownSpeaker
+    + default: `false`
+    + Specifies if the parser should remove lines that have no associated speaker.
+
+
+## Documentation
+
+### .parseOne()
+
+The `parseOne()` method parses a string and returns an object representing it.
+
+#### Syntax
+
+`tp.parseOne(_transcript_)`
+
+##### Parameters
+
+- `transcript`
+    - The transcript, as a `string`.

test/parser.js

@@ -9,4 +9,26 @@ "use strict";
 describe('TranscriptParser', function() {
-  const tp = new TranscriptParser();
-  describe('#parse()', function(){
+  
+  describe('contructor', function() {
+    it('should remove actions by default', function() {
+      const tp = new TranscriptParser();
+      var result = tp.parseOne('PERSON A: Hello, (PAUSES) (DRINKS WATER) my name is Bob.(APPLAUSE)');
+      result.speaker.should.eql({
+        'PERSON A': [
+          'Hello, my name is Bob.'
+        ]
+      });
+    });
+    it('should respect the removeActions setting', function() {
+      const tp = new TranscriptParser({removeActions: false});
+      var result = tp.parseOne('PERSON A: Hello, (PAUSES) (DRINKS WATER) my name is Bob.(APPLAUSE)');
+      result.speaker.should.eql({
+        'PERSON A': [
+          'Hello, (PAUSES) (DRINKS WATER) my name is Bob.(APPLAUSE)'
+        ]
+      });
+    });
+  });
+
+  describe('#parseOne()', function(){
+    const tp = new TranscriptParser();
     it('should parse a transcript with no errors', function(done) {
@@ -13,0 +35,0 @@ fs.readFileAsync('test/transcripts/sample_1.txt', {encoding: 'UTF-8'})

test/regex.js

 "use strict";
 const TranscriptParser = require('../app.js');
 const chai = require('chai');
-
 chai.should();
 
+
 describe('TranscriptParser', function() {
@@ -19,10 +19,6 @@ const transcriptParser = new TranscriptParser();
 
-    describe('.newLineOrAction', function() {
-      it('should split newlines', function() {
-        const testStr = 'a\nb\r\nc';
-        testStr.split(regex.newLineOrAction).should.eql(['a','b','c']);
-      });
+    describe('.action', function() {
       it('should split actions', function() {
-        const testStr = 'The(LOUD APPLAUSE)chicken(SILENCE)crossed(LAUGHTER)';
-        testStr.split(regex.newLineOrAction).should.eql(['The','chicken','crossed','']);
+        const testStr = 'The (LOUD APPLAUSE) chicken (SILENCE) crossed (LAUGHTER)';
+        testStr.split(regex.action).should.eql(['The ','chicken ','crossed ','']);
       });
@@ -29,0 +25,0 @@ });

No alert changes

Improved metrics

Total package byte prevSize

75676

increased by3.5%

Lines of code

150

increased by25%

Number of lines in readme file

56

increased by700%

No dependency changes