(bionode#33) [Feature] Do the ncbi valid db checks at lib level

Do the db filter at lib level

Add tests to valid-dbs

Fix identation

Istanbul should use all the test files for coverage

cli.js

@@ -3,6 +3,8 @@ var JSONStream = require('JSONStream')
 var split = require('split2')
 var ncbi = require('./')
 var insight = require('./lib/anonymous-tracking')
+var validDbs = require('./lib/valid-dbs')
+
 var argv = require('yargs')
 .strict()
 .demandCommand(1)
@@ -75,63 +77,53 @@ bionode-ncbi plink tax sra -s --pretty`
 .boolean('pretty')
 .describe('pretty', 'Print human readable output instead of NDJSON')
 .choices('dlsource', ['assembly', 'sra'])
-.choices('db', [
-  'gquery', 'assembly', 'bioproject', 'biosample', 'biosystems', 'books',
-  'clinvar', 'clone', 'cdd', 'gap', 'dbvar', 'nucest', 'gene', 'genome', 'gds',
-  'geoprofiles', 'nucgss', 'gtr', 'homologene', 'medgen', 'mesh', 'ncbisearch',
-  'nlmcatalog', 'nuccore', 'omim', 'pmc', 'popset', 'probe', 'protein',
-  'proteinclusters', 'pcassay', 'pccompound', 'pcsubstance', 'pubmed',
-  'pubmedhealth', 'snp', 'sparcle', 'sra', 'structure', 'taxonomy', 'toolkit',
-  'toolkitall', 'toolkitbook', 'toolkitbookgh', 'unigene'
-])
-.example('databases available',
-`gquery (All Databases), assembly, bioproject, biosample, biosystems, \
-books, clinvar, clone, cdd (Conserved Domains), gap (dbGaP), dbvar, \
-nucest (EST), gene, genome, gds (GEO DataSets), geoprofiles (GEO Profiles), \
-nucgss (GSS), gtr (GTR), homologene, medgen, mesh, \
-ncbisearch (NCBI Web Site), nlmcatalog, nuccore (Nucleotide), omim, pmc, \
-popset, probe, protein, proteinclusters, pcassay (PubChem BioAssay), \
-pccompound (PubChem Compound), pcsubstance (PubChem Substance), \
-pubmed, pubmedhealth, snp, sparcle, sra, structure, \
-taxonomy, toolkit, toolkitall, toolkitbook, toolkitbookgh, unigene`
-)
+.example('databases available', validDbs.printDbs())
 .example(`DEBUG mode: export DEBUG='*'`)
 .argv
 
 if (argv.dlsource) { argv.db = argv.dlsource }
 
 insight.track('ncbi', 'cli')
 
-var ncbiStream = ncbi[argv._[0]](argv)
+try {
+  var ncbiStream = ncbi[argv._[0]](argv)
 
-var jsonStream
-if (argv.pretty) {
-  jsonStream = JSONStream.stringify(false, null, null, 2)
-} else {
-  jsonStream = JSONStream.stringify(false)
-}
+  var jsonStream
+  if (argv.pretty) {
+    jsonStream = JSONStream.stringify(false, null, null, 2)
+  } else {
+    jsonStream = JSONStream.stringify(false)
+  }
 
-ncbiStream.pipe(jsonStream).pipe(process.stdout)
+  ncbiStream.pipe(jsonStream).pipe(process.stdout)
 
-if (argv.stdin) {
-  insight.track('ncbi', 'stdin')
-  process.stdin.setEncoding('utf8')
+  if (argv.stdin) {
+    insight.track('ncbi', 'stdin')
+    process.stdin.setEncoding('utf8')
 
-  process.stdin
-  .pipe(split())
-  .pipe(JSONStream.parse())
-  .pipe(ncbiStream)
+    process.stdin
+    .pipe(split())
+    .pipe(JSONStream.parse())
+    .pipe(ncbiStream)
 
-  process.stdin.on('end', function () {
-    ncbiStream.end()
-  })
-}
+    process.stdin.on('end', function () {
+      ncbiStream.end()
+    })
+  }
 
-process.stdout.on('error', function (err) {
-  if (err.code === 'EPIPE') { process.exit(0) }
-})
+  process.stdout.on('error', function (err) {
+    if (err.code === 'EPIPE') { process.exit(0) }
+  })
 
-ncbiStream.on('error', function (error) {
-  console.error(error.message)
-  process.exit()
-})
+  ncbiStream.on('error', function (error) {
+    console.error(error.message)
+    process.exit()
+  })
+} catch (err) {
+  if (err instanceof validDbs.InvalidDbError) {
+    console.error(err.message)
+    console.log('Run "bionode-ncbi --help" to check the available dbs')
+  } else {
+    console.error(err)
+  }
+}

lib/bionode-ncbi.js

@@ -40,6 +40,9 @@ var cheerio = require('cheerio')
 var fasta = require('bionode-fasta')
 var insight = require('./anonymous-tracking')
 
+var validDbs = require('./valid-dbs')
+var InvalidDbError = validDbs.InvalidDbError
+
 var ncbi = exports
 
 var PROXY = typeof window !== 'undefined' ? 'http://cors.inb.io/' : ''
@@ -111,6 +114,10 @@ ncbi.search = function (db, term, cb) {
   var opts = typeof db === 'string' ? { db, term } : db
   cb = typeof term === 'function' ? term : cb
 
+  if (Object.keys(validDbs.dbs).indexOf(opts.db) < 0) {
+    throw new InvalidDbError('The database "' + opts.db + '" is not a valid ncbi database')
+  }
+
   var stream = pumpify.obj(
     createAPISearchUrl(opts.db, opts.term),
     requestStream(true),

lib/valid-dbs.js

@@ -0,0 +1,72 @@
+
+var dbs = {
+  gquery: 'All Databases',
+  assembly: 'Assembly',
+  bioproject: 'BioProject',
+  biosample: 'BioSample',
+  biosystems: 'BioSystems',
+  books: 'Books',
+  clinvar: 'ClinVar',
+  clone: 'Clone',
+  cdd: 'Conserved Domains',
+  gap: 'dbGaP',
+  dbvar: 'dbVar',
+  nucest: 'EST',
+  gene: 'Gene',
+  genome: 'Genome',
+  gds: 'GEO DataSets',
+  geoprofiles: 'GEO Profiles',
+  nucgss: 'GSS',
+  gtr: 'GTR',
+  homologene: 'HomoloGene',
+  medgen: 'MedGen',
+  mesh: 'MeSH',
+  ncbisearch: 'NCBI Web Site',
+  nlmcatalog: 'NLM Catalog',
+  nuccore: 'Nucleotide',
+  omim: 'OMIM',
+  pmc: 'PMC',
+  popset: 'PopSet',
+  probe: 'Probe',
+  protein: 'Protein',
+  proteinclusters: 'Protein Clusters',
+  pcassay: 'PubChem BioAssay',
+  pccompound: 'PubChem Compound',
+  pcsubstance: 'PubChem Substance',
+  pubmed: 'PubMed',
+  pubmedhealth: 'PubMed Health',
+  snp: 'SNP',
+  sparcle: 'Sparcle',
+  sra: 'SRA',
+  structure: 'Structure',
+  taxonomy: 'Taxonomy',
+  toolkit: 'ToolKit',
+  toolkitall: 'ToolKitAll',
+  toolkitbook: 'ToolKitBook',
+  toolkitbookgh: 'ToolKitBookgh',
+  unigene: 'UniGene'
+}
+
+function printDbs (dbsObject) {
+  dbsObject = dbsObject || dbs
+
+  var keys = Object.keys(dbsObject)
+  return keys.reduce((acc, k, i) => {
+    acc = acc + k + ' (' + dbsObject[k] + ')'
+    if (i < keys.length - 1) {
+      acc = acc + '\n'
+    }
+    return acc
+  }, '')
+}
+
+function InvalidDbError (msg) {
+  this.name = 'InvalidDbError'
+  this.message = msg
+}
+
+InvalidDbError.prototype = new Error('Invalid database')
+
+module.exports.dbs = dbs
+module.exports.InvalidDbError = InvalidDbError
+module.exports.printDbs = printDbs

package.json

@@ -60,10 +60,10 @@
     "bionode-ncbi": "cli.js"
   },
   "scripts": {
-    "test": "standard && dependency-check . && node test/*.js | tap-spec",
+    "test": "standard && dependency-check . && tape test/**/*.js | tap-spec",
     "test-browser": "browserify test/*.js -d | testling -x 'open -a \"Google Chrome\"' | tap-spec",
-    "coverage": "standard && dependency-check . && istanbul cover test/bionode-ncbi.js --report lcovonly -- | tap-spec && rm -rf ./coverage",
-    "coveralls": "istanbul cover test/bionode-ncbi.js --report lcovonly -- | tap-spec && cat ./coverage/lcov.info | ./node_modules/.bin/coveralls && rm -rf ./coverage",
+    "coverage": "standard && dependency-check . && istanbul cover tape test/**/*.js --report lcovonly -- | tap-spec && rm -rf ./coverage",
+    "coveralls": "istanbul cover tape test/**/*.js --report lcovonly -- | tap-spec && cat ./coverage/lcov.info | ./node_modules/.bin/coveralls && rm -rf ./coverage",
     "build-browser": "browserify -r ./index.js:bionode-ncbi | uglifyjs > bionode-ncbi.min.js",
     "build-docs": "docco ./lib/bionode-ncbi.js"
   },

test/valid-dbs.js

@@ -0,0 +1,27 @@
+var tape = require('tape')
+var tapeNock = require('tape-nock')
+var validDbs = require('../lib/valid-dbs')
+var ncbi = require('../lib/bionode-ncbi')
+
+var test = tapeNock(tape)
+
+test('valid-dbs printDbs', t => {
+  var dummy = {fakedb: 'Fake!', another: 'Another'}
+
+  var expected = 'fakedb (Fake!)\nanother (Another)'
+
+  t.equals(validDbs.printDbs(dummy), expected, 'printDbs returns the expected string')
+
+  t.end()
+})
+
+// TODO move this test to a suite just for bionode-ncbi search
+test('bionode-ncbi search', t => {
+  t.plan(1)
+
+  try {
+    ncbi.search('invalid', 'human')
+  } catch (err) {
+    t.assert(err instanceof validDbs.InvalidDbError, 'call search with wrong db throws InvalidDbError')
+  }
+})