feat: skipComments

Author: shellscape

README.md

@@ -209,6 +209,13 @@ Default: `,`
 
 Specifies a single-character string to use as the column separator for each row.
 
+##### skipComments
+
+Type: `Boolean | String`<br>
+Default: `false`
+
+Instructs the parser to ignore lines which represent comments in a CSV file. Since there is no specification that dictates what a CSV comment looks like, comments should be considered non-standard. The "most common" character used to signify a comment in a CSV file is `"#"`. If this option is set to `true`, lines which begin with `#` will be skipped. If a custom character is needed to denote a commented line, this option may be set to a string which represents the leading character(s) signifying a comment line.
+
 ##### skipLines
 
 Type: `Number`<br>
@@ -275,6 +282,7 @@ Usage: csv-parser [filename?] [options]
   --quote,-q          Set the quote character ('"' by default)
   --remove            Remove columns from output by header name
   --separator,-s      Set the separator character ("," by default)
+  --skipComments,-c   Skip CSV comments that begin with '#'. Set a value to change the comment character.
   --skipLines,-l      Set the number of lines to skip to before parsing headers
   --strict            Require column length match headers length
   --version,-v        Print out the installed version

bin/csv-parser

@@ -8,6 +8,7 @@ const pkg = require('../package.json')
 
 const argv = minimist(process.argv, {
   alias: {
+    c: 'skipComments',
     e: 'escape',
     h: 'headers',
     o: 'output',
@@ -40,6 +41,7 @@ if (argv.help || (process.stdin.isTTY && !filename)) {
   --quote,-q          Set the quote character ('"' by default)
   --remove            Remove headers from output
   --separator,-s      Set the separator character ("," by default)
+  --skipComments,-c   Skip CSV comments that begin with '#'. Set a value to change the comment character.
   --skipLines,-l      Set the number of lines to skip to before parsing headers
   --strict            Require column length match headers length
   --version,-v        Print out the installed version
@@ -52,6 +54,7 @@ const output = (argv.output && argv.output !== '-') ? fs.createWriteStream(argv.
 const options = {
   separator: argv.separator,
   strict: argv.strict,
+  skipComments: argv.skipComments,
   skipLines: argv.skipLines
 }
 

index.d.ts

@@ -11,6 +11,7 @@ declare module 'csv-parser' {
     quote?: string;
     raw?: boolean;
     separator?: string;
+    skipComments?: number | string;
     skipLines?: number;
     maxRowBytes?: number;
     strict?: boolean;

index.js

@@ -15,6 +15,7 @@ const defaults = {
   quote: '"',
   raw: false,
   separator: ',',
+  skipComments: false,
   skipLines: null,
   maxRowBytes: Number.MAX_SAFE_INTEGER,
   strict: false
@@ -143,6 +144,14 @@ class CsvParser extends Transform {
       return this.mapValues({ header, index, value })
     }
 
+    const { skipComments } = this
+    if (skipComments) {
+      const char = typeof skipComments === 'string' ? skipComments : '#'
+      if (buf[0] === bufferFrom(char)) {
+        return
+      }
+    }
+
     for (let i = start; i < end; i++) {
       const isStartingQuote = !isQuoted && buf[i] === this.quote
       const isEndingQuote = isQuoted && buf[i] === this.quote && i + 1 <= end && buf[i + 1] === comma

package.json

@@ -28,7 +28,7 @@
     "commitmsg": "commitlint -e $GIT_PARAMS",
     "lint": "eslint .",
     "lint-staged": "lint-staged",
-    "test": "ava test/test.js"
+    "test": "ava"
   },
   "dependencies": {
     "buffer-alloc": "^1.1.0",

test/comment.test.js

@@ -0,0 +1,25 @@
+const test = require('ava')
+
+const { collect } = require('./helpers/helper')
+
+test.cb('comment', (t) => {
+  const verify = (err, lines) => {
+    t.false(err, 'no err')
+    t.snapshot(lines)
+    t.is(lines.length, 2, '2 rowa')
+    t.end()
+  }
+
+  collect('comment.csv', { skipComments: true }, verify)
+})
+
+test.cb('custom comment', (t) => {
+  const verify = (err, lines) => {
+    t.false(err, 'no err')
+    t.snapshot(lines)
+    t.is(lines.length, 2, '2 rows')
+    t.end()
+  }
+
+  collect('custom-comment.csv', { skipComments: '~' }, verify)
+})

test/data/comment.csv

@@ -0,0 +1,3 @@
+# comment
+a,b,c
+1,2,3

test/data/custom-comment.csv

@@ -0,0 +1,3 @@
+~ comment
+a,b,c
+1,2,3

test/helpers/helper.js

@@ -0,0 +1,33 @@
+const fs = require('fs')
+const path = require('path')
+
+const csv = require('../..')
+
+const read = fs.createReadStream
+
+// helpers
+function fixture (name) {
+  return path.join(__dirname, '../data', name)
+}
+
+function collect (file, opts, cb) {
+  if (typeof opts === 'function') return collect(file, null, opts)
+  const data = read(fixture(file))
+  const lines = []
+  const parser = csv(opts)
+  data
+    .pipe(parser)
+    .on('data', (line) => {
+      lines.push(line)
+    })
+    .on('error', (err) => {
+      cb(err, lines)
+    })
+    .on('end', () => {
+      // eslint-disable-next-line standard/no-callback-literal
+      cb(false, lines)
+    })
+  return parser
+}
+
+module.exports = { collect, fixture }

test/snapshots/comment.test.js.md

@@ -0,0 +1,31 @@
+# Snapshot report for `test/comment.test.js`
+
+The actual snapshot is saved in `comment.test.js.snap`.
+
+Generated by [AVA](https://ava.li).
+
+## comment
+
+> Snapshot 1
+
+    [
+      Row {
+        '# comment': 'a',
+      },
+      Row {
+        '# comment': '1',
+      },
+    ]
+
+## custom comment
+
+> Snapshot 1
+
+    [
+      Row {
+        '~ comment': 'a',
+      },
+      Row {
+        '~ comment': '1',
+      },
+    ]