Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Convert stop words filter from SortedSet/Array to Object #170

Closed
wants to merge 2 commits into from
Closed

Convert stop words filter from SortedSet/Array to Object #170

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
379d707
Resolves #169. Convert stop words filter from SortedSet/Array to Obje…
bvaughn Aug 2, 2015
9dbfeca
Updated stop words filter to avoid collisions with Object.prototype p…
bvaughn Aug 4, 2015
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
249 changes: 123 additions & 126 deletions lib/stop_word_filter.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,132 +16,129 @@
* @see lunr.Pipeline
*/
lunr.stopWordFilter = function (token) {
if (lunr.stopWordFilter.stopWords.indexOf(token) === -1) return token
if (token && lunr.stopWordFilter.stopWords[token] !== token) return token;
}

lunr.stopWordFilter.stopWords = new lunr.SortedSet
lunr.stopWordFilter.stopWords.length = 119
lunr.stopWordFilter.stopWords.elements = [
"",
"a",
"able",
"about",
"across",
"after",
"all",
"almost",
"also",
"am",
"among",
"an",
"and",
"any",
"are",
"as",
"at",
"be",
"because",
"been",
"but",
"by",
"can",
"cannot",
"could",
"dear",
"did",
"do",
"does",
"either",
"else",
"ever",
"every",
"for",
"from",
"get",
"got",
"had",
"has",
"have",
"he",
"her",
"hers",
"him",
"his",
"how",
"however",
"i",
"if",
"in",
"into",
"is",
"it",
"its",
"just",
"least",
"let",
"like",
"likely",
"may",
"me",
"might",
"most",
"must",
"my",
"neither",
"no",
"nor",
"not",
"of",
"off",
"often",
"on",
"only",
"or",
"other",
"our",
"own",
"rather",
"said",
"say",
"says",
"she",
"should",
"since",
"so",
"some",
"than",
"that",
"the",
"their",
"them",
"then",
"there",
"these",
"they",
"this",
"tis",
"to",
"too",
"twas",
"us",
"wants",
"was",
"we",
"were",
"what",
"when",
"where",
"which",
"while",
"who",
"whom",
"why",
"will",
"with",
"would",
"yet",
"you",
"your"
]
lunr.stopWordFilter.stopWords = {
a: 'a',
able: 'able',
about: 'about',
across: 'across',
after: 'after',
all: 'all',
almost: 'almost',
also: 'also',
am: 'am',
among: 'among',
an: 'an',
and: 'and',
any: 'any',
are: 'are',
as: 'as',
at: 'at',
be: 'be',
because: 'because',
been: 'been',
but: 'but',
by: 'by',
can: 'can',
cannot: 'cannot',
could: 'could',
dear: 'dear',
did: 'did',
do: 'do',
does: 'does',
either: 'either',
else: 'else',
ever: 'ever',
every: 'every',
for: 'for',
from: 'from',
get: 'get',
got: 'got',
had: 'had',
has: 'has',
have: 'have',
he: 'he',
her: 'her',
hers: 'hers',
him: 'him',
his: 'his',
how: 'how',
however: 'however',
i: 'i',
if: 'if',
in: 'in',
into: 'into',
is: 'is',
it: 'it',
its: 'its',
just: 'just',
least: 'least',
let: 'let',
like: 'like',
likely: 'likely',
may: 'may',
me: 'me',
might: 'might',
most: 'most',
must: 'must',
my: 'my',
neither: 'neither',
no: 'no',
nor: 'nor',
not: 'not',
of: 'of',
off: 'off',
often: 'often',
on: 'on',
only: 'only',
or: 'or',
other: 'other',
our: 'our',
own: 'own',
rather: 'rather',
said: 'said',
say: 'say',
says: 'says',
she: 'she',
should: 'should',
since: 'since',
so: 'so',
some: 'some',
than: 'than',
that: 'that',
the: 'the',
their: 'their',
them: 'them',
then: 'then',
there: 'there',
these: 'these',
they: 'they',
this: 'this',
tis: 'tis',
to: 'to',
too: 'too',
twas: 'twas',
us: 'us',
wants: 'wants',
was: 'was',
we: 'we',
were: 'were',
what: 'what',
when: 'when',
where: 'where',
which: 'which',
while: 'while',
who: 'who',
whom: 'whom',
why: 'why',
will: 'will',
with: 'with',
would: 'would',
yet: 'yet',
you: 'you',
your: 'your'
}

lunr.Pipeline.registerFunction(lunr.stopWordFilter, 'stopWordFilter')
lunr.Pipeline.registerFunction(lunr.stopWordFilter, 'stopWordFilter')
8 changes: 8 additions & 0 deletions test/stop_word_filter_test.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,6 +16,14 @@ test('non stop words pass through', function () {
})
})

test('should not filter Object.prototype terms', function () {
var nonStopWords = ['constructor', 'hasOwnProperty', 'toString', 'valueOf']

nonStopWords.forEach(function (word) {
equal(lunr.stopWordFilter(word), word)
})
})

test('should be registered with lunr.Pipeline', function () {
equal(lunr.stopWordFilter.label, 'stopWordFilter')
deepEqual(lunr.Pipeline.registeredFunctions['stopWordFilter'], lunr.stopWordFilter)
Expand Down