transcript-parser - npm Package Compare versions

Comparing version 0.6.0 to 0.7.0

lib/parser.js

@@ -8,3 +8,3 @@ 'use strict';
 const Promise = require('bluebird');
-const readline = require('readline');
+const es = require('event-stream');
 
@@ -24,3 +24,3 @@
     regex: {
-      newLine: /\r?\n/,
+      newLine: /(?:\r?\n)+/,
       action: /\([A-Z\ ]+\)\ ?/,
@@ -48,4 +48,3 @@ speaker: /^((?:\[\d{1,2}:\d{1,2}:\d{1,2}\]\ ?)?[A-Z\d\ \/,.\-\(\)]+?)(?:\ ?\[[A-z\ ]+\])? ?:\ ?/,
 
-  lines = _.map(lines, line => {
-    if(line.length <= 0) return '';
+  lines = _.reduce(lines, (out, line) => {
     if(this.settings.removeActions)
@@ -57,6 +56,6 @@ line = removeAll(line, this.regex.action);
       line = removeAll(line, this.regex.timestamp);
-    return line;
-  });
 
-  lines = _.filter(lines, line => (line.length > 0)); //Remove newly blank lines
+    if(line.length > 0) out.push(line);
+    return out;
+  }, []);
 
@@ -101,3 +100,2 @@ //Output object
 proto.parseOne = function(transcript, cb) {
-  const hasCallback = (typeof cb !== 'undefined' && cb !== null);
   //Output object
@@ -110,20 +108,19 @@ const output = {};
   let speaker = 'none'; //Current speaker
+  let ignore = false, match = null;
 
-  return Promise.try(() => {
-    //Remove blank lines
-    let lines = _.filter(transcript.split(this.regex.newLine), line => (line.length > 0));
-    let ignore = false, match = null;
+  return Promise
+    .try(() => {
+      return Promise.reduce(transcript.split(this.regex.newLine), (out, line) => {
+        if(this.settings.removeActions)
+          line = removeAll(line, this.regex.action);
+        if(this.settings.removeAnnotations)
+          line = removeAll(line, this.regex.annotation);
+        else if(this.settings.removeTimestamps)
+          line = removeAll(line, this.regex.timestamp);
 
-    lines = _.map(lines, line => {
-      if(this.settings.removeActions)
-        line = removeAll(line, this.regex.action);
-      if(this.settings.removeAnnotations)
-        line = removeAll(line, this.regex.annotation);
-      else if(this.settings.removeTimestamps)
-        line = removeAll(line, this.regex.timestamp);
-      return line;
-    });
-
-    lines = _.filter(lines, line => (line.length > 0)); //Remove newly blank lines
-    _.each(lines, (line) => {
+        if(line.length > 0) out.push(line);
+        return out;
+      }, []);
+    })
+    .each(line => {
       if((match = this.regex.speaker.exec(line)) !== null) {
@@ -147,9 +144,7 @@ //Regex match
       output.order.push(speaker);
-    });
-    if(hasCallback) cb(null, output);
-    return Promise.resolve(output);
-  }).catch(err => {
-    if(hasCallback) cb(err);
-    else return Promise.reject(err);
-  });
+    })
+    .then(() => {
+      return Promise.resolve(output);
+    })
+    .asCallback(cb);
 };
@@ -255,5 +250,2 @@
 proto.parseStream = function(inputStream, cb) {
-  const lineStream = readline.createInterface({
-    input: inputStream
-  });
   //Output object
@@ -269,27 +261,30 @@ const output = {};
 
-  lineStream.on('line', line => {
-    if(line === null) return;
-    line = this.filterLine(line);
-    if(!line) return;
+  inputStream
+    .pipe(es.split(this.regex.newLine))
+    .pipe(es.mapSync(line => {
+      if(line === null) return;
+      line = this.filterLine(line);
+      if(!line) return;
 
-    if((match = this.regex.speaker.exec(line)) !== null) {
-      speaker = match[1].trim(); //Regex match - is speaker
-      //Remove the speaker from the line
-      line = line.replace(this.regex.speaker, '');
-      ignore = (this.settings.blacklist.indexOf(speaker) > -1);
-    }
+      if((match = this.regex.speaker.exec(line)) !== null) {
+        speaker = match[1].trim(); //Regex match - is speaker
+        //Remove the speaker from the line
+        line = line.replace(this.regex.speaker, '');
+        ignore = (this.settings.blacklist.indexOf(speaker) > -1);
+      }
 
-    if(ignore || (speaker === 'none' && this.settings.removeUnknownSpeakers)) return;
-    //If the speaker's key doesn't already exist
-    if(!(speaker in output.speaker)) {
-      //Set the output's speaker key to a new empty array
-      output.speaker[speaker] = [];
-    }
-    //If the speaker is defined or the setting to remove undefined speakers is false
-    //Add the text to the output speaker's key and speaker name to the order array
-    output.speaker[speaker].push(line);
-    output.order.push(speaker);
-  }).on('close', () => {
-    return cb(null, output);
-  });
+      if(ignore || (speaker === 'none' && this.settings.removeUnknownSpeakers)) return;
+      //If the speaker's key doesn't already exist
+      if(!(speaker in output.speaker)) {
+        //Set the output's speaker key to a new empty array
+        output.speaker[speaker] = [];
+      }
+      //If the speaker is defined or the setting to remove undefined speakers is false
+      //Add the text to the output speaker's key and speaker name to the order array
+      output.speaker[speaker].push(line);
+      output.order.push(speaker);
+    }))
+    .on('close', () => {
+      return cb(null, output);
+    });
 
@@ -296,0 +291,0 @@ };

package.json

 {
   "name": "transcript-parser",
-  "version": "0.6.0",
+  "version": "0.7.0",
   "description": "Parses plaintext speech/debate/radio transcripts into JavaScript objects.",
@@ -39,4 +39,5 @@ "main": "app.js",
     "bluebird": "^3.3.4",
+    "event-stream": "^3.3.4",
     "lodash": "^4.9.0"
   }
 }

README.md

@@ -5,2 +5,3 @@ transcript-parser
 [![Coverage Status](https://coveralls.io/repos/github/willshiao/transcript-parser/badge.svg?branch=master)](https://coveralls.io/github/willshiao/transcript-parser?branch=master)
+[![npm](https://img.shields.io/npm/v/transcript-parser.svg?maxAge=2592000)](https://www.npmjs.com/package/transcript-parser)
 
@@ -11,4 +12,6 @@ ## Description
 
-Tested for Node.js versions >= 4.4.6
+Tests can be run with `npm test` and a benchmark can be run with `npm run benchmark`. For a full coverage report using [Istanbul](https://github.com/gotwarlost/istanbul), run `npm run travis-test`.
 
+Tested for Node.js >= v4.4.6
+
 ## Usage
@@ -18,27 +21,30 @@
 
-    const fs = require('fs');
-    const TranscriptParser = require('transcript-parser');
-    const tp = new TranscriptParser();
-    
-    //Synchronous example
-    const parsed = tp.parseOneSync(fs.readFileSync('transcript.txt', {encoding: 'UTF-8'}));
+```node
+'use strict';
+const fs = require('fs');
+const TranscriptParser = require('transcript-parser');
+const tp = new TranscriptParser();
+
+//Synchronous example
+const parsed = tp.parseOneSync(fs.readFileSync('transcript.txt', 'utf8'));
+console.log(parsed);
+
+//Asynchronous example
+fs.readFile('transcript.txt', (err, data) => {
+  if(err) return console.error('Error:', err);
+  tp.parseOne(data, (err, parsed) => {
+    if(err) return console.error('Error:', err);
     console.log(parsed);
-    
-    //Asynchronous example
-    fs.readFile('transcript.txt', (err, data) => {
-      if(err) return console.error('Error:', err);
-      tp.parseOne(data, (err, parsed => {
-        if(err) return console.error('Error:', err);
-        console.log(parsed);
-      }));
-    });
-    
-    //Stream example
-    const stream = fs.createReadStream('transcript.txt', 'utf8');
-    tp.parseStream(stream, (err, parsed) => {
-      if(err) return console.error('Error:', err);
-      console.log(parsed);
-    });
+  }));
+});
 
+//Stream example
+const stream = fs.createReadStream('transcript.txt', 'utf8');
+tp.parseStream(stream, (err, parsed) => {
+  if(err) return console.error('Error:', err);
+  console.log(parsed);
+});
+```
 
+
 ## Config
@@ -156,2 +162,1 @@
     + A callback to be executed on function completion or error.
-

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

Major refactor

Supply chain risk

Package has recently undergone a major refactor. It may be unstable or indicate significant internal changes. Use caution when updating to versions that include significant changes.

Found 1 instance in 1 package

Improved metrics

Number of lines in readme file

159

increased by3.25%

Number of medium supply chain risk alerts

0

decreased by-100%

Worsened metrics

Total package byte prevSize

17836

decreased by-0.04%

Dependency count

3

increased by50%

Lines of code

271

decreased by-1.45%

Dependency changes

• + Addedevent-stream@^3.3.4

• + Addedduplexer@0.1.2(transitive)

• + Addedevent-stream@3.3.5(transitive)

• + Addedfrom@0.1.7(transitive)

• + Addedmap-stream@0.0.7(transitive)

• + Addedpause-stream@0.0.11(transitive)

• + Addedsplit@1.0.1(transitive)

• + Addedstream-combiner@0.2.2(transitive)

• + Addedthrough@2.3.8(transitive)