Comparing version 0.0.2 to 0.0.3
@@ -1,1 +0,1 @@ | ||
{"processes":{"48d0a4ef-b50d-41b8-87bb-9d862294cf39":{"parent":null,"children":[]}},"files":{"/Users/neilsbohr/dev/winkjs/wink-nlp/src/wink-nlp.js":["48d0a4ef-b50d-41b8-87bb-9d862294cf39"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/dd-wrapper.js":["48d0a4ef-b50d-41b8-87bb-9d862294cf39"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/constants.js":["48d0a4ef-b50d-41b8-87bb-9d862294cf39"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/doc-v2.js":["48d0a4ef-b50d-41b8-87bb-9d862294cf39"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/contained-entities.js":["48d0a4ef-b50d-41b8-87bb-9d862294cf39"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/locate.js":["48d0a4ef-b50d-41b8-87bb-9d862294cf39"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/get-parent-item.js":["48d0a4ef-b50d-41b8-87bb-9d862294cf39"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/search.js":["48d0a4ef-b50d-41b8-87bb-9d862294cf39"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/col-get-item.js":["48d0a4ef-b50d-41b8-87bb-9d862294cf39"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/sel-get-item.js":["48d0a4ef-b50d-41b8-87bb-9d862294cf39"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/col-each.js":["48d0a4ef-b50d-41b8-87bb-9d862294cf39"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/sel-each.js":["48d0a4ef-b50d-41b8-87bb-9d862294cf39"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/col-filter.js":["48d0a4ef-b50d-41b8-87bb-9d862294cf39"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/sel-filter.js":["48d0a4ef-b50d-41b8-87bb-9d862294cf39"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/itm-token-out.js":["48d0a4ef-b50d-41b8-87bb-9d862294cf39"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/its.js":["48d0a4ef-b50d-41b8-87bb-9d862294cf39"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/allowed.js":["48d0a4ef-b50d-41b8-87bb-9d862294cf39"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/as.js":["48d0a4ef-b50d-41b8-87bb-9d862294cf39"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/contained-markings.js":["48d0a4ef-b50d-41b8-87bb-9d862294cf39"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/col-tokens-out.js":["48d0a4ef-b50d-41b8-87bb-9d862294cf39"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/sel-tokens-out.js":["48d0a4ef-b50d-41b8-87bb-9d862294cf39"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/itm-entity-out.js":["48d0a4ef-b50d-41b8-87bb-9d862294cf39"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/col-entities-out.js":["48d0a4ef-b50d-41b8-87bb-9d862294cf39"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/sel-entities-out.js":["48d0a4ef-b50d-41b8-87bb-9d862294cf39"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/itm-sentence-out.js":["48d0a4ef-b50d-41b8-87bb-9d862294cf39"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/col-sentences-out.js":["48d0a4ef-b50d-41b8-87bb-9d862294cf39"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/itm-document-out.js":["48d0a4ef-b50d-41b8-87bb-9d862294cf39"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/print-tokens.js":["48d0a4ef-b50d-41b8-87bb-9d862294cf39"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/cache.js":["48d0a4ef-b50d-41b8-87bb-9d862294cf39"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/tokenizer.js":["48d0a4ef-b50d-41b8-87bb-9d862294cf39"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/recursive-tokenizer.js":["48d0a4ef-b50d-41b8-87bb-9d862294cf39"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/compile-trex.js":["48d0a4ef-b50d-41b8-87bb-9d862294cf39"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/tokens-mappers.js":["48d0a4ef-b50d-41b8-87bb-9d862294cf39"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/examples-compiler.js":["48d0a4ef-b50d-41b8-87bb-9d862294cf39"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/automaton.js":["48d0a4ef-b50d-41b8-87bb-9d862294cf39"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/compose-patterns.js":["48d0a4ef-b50d-41b8-87bb-9d862294cf39"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/helper.js":["48d0a4ef-b50d-41b8-87bb-9d862294cf39"]},"externalIds":{}} | ||
{"processes":{"4169bb6d-81f9-49d1-b6ce-6bce099ad6ce":{"parent":null,"children":[]}},"files":{"/Users/neilsbohr/dev/winkjs/wink-nlp/src/wink-nlp.js":["4169bb6d-81f9-49d1-b6ce-6bce099ad6ce"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/dd-wrapper.js":["4169bb6d-81f9-49d1-b6ce-6bce099ad6ce"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/constants.js":["4169bb6d-81f9-49d1-b6ce-6bce099ad6ce"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/doc-v2.js":["4169bb6d-81f9-49d1-b6ce-6bce099ad6ce"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/contained-entities.js":["4169bb6d-81f9-49d1-b6ce-6bce099ad6ce"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/locate.js":["4169bb6d-81f9-49d1-b6ce-6bce099ad6ce"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/get-parent-item.js":["4169bb6d-81f9-49d1-b6ce-6bce099ad6ce"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/search.js":["4169bb6d-81f9-49d1-b6ce-6bce099ad6ce"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/col-get-item.js":["4169bb6d-81f9-49d1-b6ce-6bce099ad6ce"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/sel-get-item.js":["4169bb6d-81f9-49d1-b6ce-6bce099ad6ce"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/col-each.js":["4169bb6d-81f9-49d1-b6ce-6bce099ad6ce"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/sel-each.js":["4169bb6d-81f9-49d1-b6ce-6bce099ad6ce"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/col-filter.js":["4169bb6d-81f9-49d1-b6ce-6bce099ad6ce"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/sel-filter.js":["4169bb6d-81f9-49d1-b6ce-6bce099ad6ce"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/itm-token-out.js":["4169bb6d-81f9-49d1-b6ce-6bce099ad6ce"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/its.js":["4169bb6d-81f9-49d1-b6ce-6bce099ad6ce"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/allowed.js":["4169bb6d-81f9-49d1-b6ce-6bce099ad6ce"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/as.js":["4169bb6d-81f9-49d1-b6ce-6bce099ad6ce"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/contained-markings.js":["4169bb6d-81f9-49d1-b6ce-6bce099ad6ce"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/col-tokens-out.js":["4169bb6d-81f9-49d1-b6ce-6bce099ad6ce"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/sel-tokens-out.js":["4169bb6d-81f9-49d1-b6ce-6bce099ad6ce"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/itm-entity-out.js":["4169bb6d-81f9-49d1-b6ce-6bce099ad6ce"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/col-entities-out.js":["4169bb6d-81f9-49d1-b6ce-6bce099ad6ce"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/sel-entities-out.js":["4169bb6d-81f9-49d1-b6ce-6bce099ad6ce"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/itm-sentence-out.js":["4169bb6d-81f9-49d1-b6ce-6bce099ad6ce"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/col-sentences-out.js":["4169bb6d-81f9-49d1-b6ce-6bce099ad6ce"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/itm-document-out.js":["4169bb6d-81f9-49d1-b6ce-6bce099ad6ce"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/api/print-tokens.js":["4169bb6d-81f9-49d1-b6ce-6bce099ad6ce"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/cache.js":["4169bb6d-81f9-49d1-b6ce-6bce099ad6ce"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/tokenizer.js":["4169bb6d-81f9-49d1-b6ce-6bce099ad6ce"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/recursive-tokenizer.js":["4169bb6d-81f9-49d1-b6ce-6bce099ad6ce"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/compile-trex.js":["4169bb6d-81f9-49d1-b6ce-6bce099ad6ce"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/tokens-mappers.js":["4169bb6d-81f9-49d1-b6ce-6bce099ad6ce"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/examples-compiler.js":["4169bb6d-81f9-49d1-b6ce-6bce099ad6ce"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/automaton.js":["4169bb6d-81f9-49d1-b6ce-6bce099ad6ce"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/compose-patterns.js":["4169bb6d-81f9-49d1-b6ce-6bce099ad6ce"],"/Users/neilsbohr/dev/winkjs/wink-nlp/src/helper.js":["4169bb6d-81f9-49d1-b6ce-6bce099ad6ce"]},"externalIds":{}} |
{ | ||
"name": "wink-nlp", | ||
"version": "0.0.2", | ||
"version": "0.0.3", | ||
"description": "Natural Language Processing", | ||
@@ -5,0 +5,0 @@ "keywords": [ |
@@ -154,3 +154,3 @@ // wink-nlp | ||
// Access the parent document. | ||
api.document = () => methods; | ||
api.parentDocument = () => methods; | ||
// Access the parent entity, **if any.** | ||
@@ -245,3 +245,3 @@ api.parentEntity = () => getParentItem( index, entities, itemEntity ); | ||
// Access the parent document. | ||
api.document = () => methods; | ||
api.parentDocument = () => methods; | ||
// Markup this entity. | ||
@@ -328,3 +328,3 @@ api.markup = ( beginMarker, endMarker ) => markings.push( [ entities[ index ][ 0 ], entities[ index ][ 1 ], beginMarker, endMarker ] ); | ||
// Access the parent document. | ||
api.document = () => methods; | ||
api.parentDocument = () => methods; | ||
// Markup this entity. | ||
@@ -410,3 +410,3 @@ api.markup = ( beginMarker, endMarker ) => markings.push( [ customEntities[ index ][ 0 ], customEntities[ index ][ 1 ], beginMarker, endMarker ] ); | ||
// Access the parent document. | ||
api.document = () => methods; | ||
api.parentDocument = () => methods; | ||
// Markup this sentence. | ||
@@ -413,0 +413,0 @@ api.markup = ( beginMarker, endMarker ) => markings.push( [ sentences[ index ][ 0 ], sentences[ index ][ 1 ], beginMarker, endMarker ] ); |
@@ -39,14 +39,14 @@ // wink-nlp | ||
// This is inspired by `wink-tokenizer`, which is regex driven and | ||
// used recursion. While this still driven by regexes, it does not use recursion. | ||
// The algorithm is outlined below: | ||
// 1. First split on a **single space** character to obtain all the tokens including | ||
// extra spaces between the tokens (if any). Remember, the extra spaces will | ||
// appear as empty strings in the array. | ||
// 2. Test each token with `categoryRgxs` and tag its category accordingly. Each regex in | ||
// this array tests one unique token category, viz. **word**, **number**, or | ||
// **email**. This array is sorted in the decreasing order of the probability | ||
// of occurence of token type that it tests — this ensures higher | ||
// execution speed. | ||
/** | ||
* Creates an instance of tokenizer. | ||
* | ||
* @param {object} trex language specific regular expressions needed for | ||
* tokenization. This includes helper, linear and | ||
* recursive. | ||
* @param {object} categories tokens categories and their map to numeric code. | ||
* @param {object} preserve language specific suffixes and prefixes to be preserved. | ||
* @return {function} that performs the tokenization based on the | ||
* above configuration. | ||
* @private | ||
*/ | ||
var tokenizer = function ( trex, categories, preserve ) { | ||
@@ -53,0 +53,0 @@ // Maximum number of preceding spaces allowed. |
License Policy Violation
LicenseThis package is not allowed per your license policy. Review the package's license to ensure compliance.
Found 1 instance in 1 package
License Policy Violation
LicenseThis 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 riskPackage 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
4718
0
440798