spacy-token-parser


Namespacy-token-parser JSON
Version 0.1.16 PyPI version JSON
download
home_pagehttps://github.com/craigtrim/spacy-token-parser
SummaryUse spaCy to Parse Input Tokens
upload_time2023-07-15 05:37:42
maintainerCraig Trim
docs_urlNone
authorCraig Trim
requires_python>=3.8.5,<4.0.0
licenseNone
keywords nlp nlu ai parser spacy
VCS
bugtrack_url
requirements No requirements were recorded.
Travis-CI No Travis.
coveralls test coverage No coveralls.
            # spaCy Token Parser (spacy-token-parser)
Use spaCy to Parse Input Tokens

## Usage

Call the service with this code
```python
from spacy_token_parser import parse_tokens

parse_tokens(input_text.split())
```

The output is a tuple.

The first element of the tuple is a list of dictionary tokens (below).

The second element of the tuple is a wrapped instance of `spacy.tokens.doc.Doc`.

### List Output
```json
[
   {
      "dep":"compound",
      "ent":"NORP",
      "head":"5665575797947403677",
      "id":"6042939320535660714",
      "is_alpha":true,
      "is_punct":false,
      "is_stop":false,
      "is_wordnet":true,
      "lemma":"american",
      "noun_number":"singular",
      "other":{
         "head_i":3,
         "head_idx":24,
         "head_orth":5665575797947403677,
         "head_text":"films",
         "i":0,
         "idx":0,
         "orth":6042939320535660714
      },
      "pos":"PROPN",
      "sentiment":0.0,
      "shape":"xxxx",
      "tag":"NNP",
      "tense":"",
      "text":"american",
      "verb_form":"",
      "x":0,
      "y":8
   },
   {
      "dep":"compound",
      "ent":"",
      "head":"5665575797947403677",
      "id":"16602643206033239142",
      "is_alpha":true,
      "is_punct":false,
      "is_stop":false,
      "is_wordnet":true,
      "lemma":"silent",
      "noun_number":"singular",
      "other":{
         "head_i":3,
         "head_idx":24,
         "head_orth":5665575797947403677,
         "head_text":"films",
         "i":1,
         "idx":9,
         "orth":16602643206033239142
      },
      "pos":"PROPN",
      "sentiment":0.0,
      "shape":"xxxx",
      "tag":"NNP",
      "tense":"",
      "text":"silent",
      "verb_form":"",
      "x":8,
      "y":14
   },
   {
      "dep":"compound",
      "ent":"",
      "head":"5665575797947403677",
      "id":"16417888112635110788",
      "is_alpha":true,
      "is_punct":false,
      "is_stop":false,
      "is_wordnet":true,
      "lemma":"feature",
      "noun_number":"singular",
      "other":{
         "head_i":3,
         "head_idx":24,
         "head_orth":5665575797947403677,
         "head_text":"films",
         "i":2,
         "idx":16,
         "orth":16417888112635110788
      },
      "pos":"NOUN",
      "sentiment":0.0,
      "shape":"xxxx",
      "tag":"NN",
      "tense":"",
      "text":"feature",
      "verb_form":"",
      "x":14,
      "y":21
   },
   {
      "dep":"ROOT",
      "ent":"",
      "head":"5665575797947403677",
      "id":"5665575797947403677",
      "is_alpha":true,
      "is_punct":false,
      "is_stop":false,
      "is_wordnet":true,
      "lemma":"film",
      "noun_number":"plural",
      "other":{
         "head_i":3,
         "head_idx":24,
         "head_orth":5665575797947403677,
         "head_text":"films",
         "i":3,
         "idx":24,
         "orth":5665575797947403677
      },
      "pos":"NOUN",
      "sentiment":0.0,
      "shape":"xxxx",
      "tag":"NNS",
      "tense":"",
      "text":"films",
      "verb_form":"",
      "x":21,
      "y":26
   }
]
```

            

Raw data

            {
    "_id": null,
    "home_page": "https://github.com/craigtrim/spacy-token-parser",
    "name": "spacy-token-parser",
    "maintainer": "Craig Trim",
    "docs_url": null,
    "requires_python": ">=3.8.5,<4.0.0",
    "maintainer_email": "craigtrim@gmail.com",
    "keywords": "nlp,nlu,ai,parser,spacy",
    "author": "Craig Trim",
    "author_email": "craigtrim@gmail.com",
    "download_url": "https://files.pythonhosted.org/packages/9a/cc/bb39463f6ad21d0d8cf54960f083b513b2f8290e6f4341368838e8a185d4/spacy_token_parser-0.1.16.tar.gz",
    "platform": null,
    "description": "# spaCy Token Parser (spacy-token-parser)\nUse spaCy to Parse Input Tokens\n\n## Usage\n\nCall the service with this code\n```python\nfrom spacy_token_parser import parse_tokens\n\nparse_tokens(input_text.split())\n```\n\nThe output is a tuple.\n\nThe first element of the tuple is a list of dictionary tokens (below).\n\nThe second element of the tuple is a wrapped instance of `spacy.tokens.doc.Doc`.\n\n### List Output\n```json\n[\n   {\n      \"dep\":\"compound\",\n      \"ent\":\"NORP\",\n      \"head\":\"5665575797947403677\",\n      \"id\":\"6042939320535660714\",\n      \"is_alpha\":true,\n      \"is_punct\":false,\n      \"is_stop\":false,\n      \"is_wordnet\":true,\n      \"lemma\":\"american\",\n      \"noun_number\":\"singular\",\n      \"other\":{\n         \"head_i\":3,\n         \"head_idx\":24,\n         \"head_orth\":5665575797947403677,\n         \"head_text\":\"films\",\n         \"i\":0,\n         \"idx\":0,\n         \"orth\":6042939320535660714\n      },\n      \"pos\":\"PROPN\",\n      \"sentiment\":0.0,\n      \"shape\":\"xxxx\",\n      \"tag\":\"NNP\",\n      \"tense\":\"\",\n      \"text\":\"american\",\n      \"verb_form\":\"\",\n      \"x\":0,\n      \"y\":8\n   },\n   {\n      \"dep\":\"compound\",\n      \"ent\":\"\",\n      \"head\":\"5665575797947403677\",\n      \"id\":\"16602643206033239142\",\n      \"is_alpha\":true,\n      \"is_punct\":false,\n      \"is_stop\":false,\n      \"is_wordnet\":true,\n      \"lemma\":\"silent\",\n      \"noun_number\":\"singular\",\n      \"other\":{\n         \"head_i\":3,\n         \"head_idx\":24,\n         \"head_orth\":5665575797947403677,\n         \"head_text\":\"films\",\n         \"i\":1,\n         \"idx\":9,\n         \"orth\":16602643206033239142\n      },\n      \"pos\":\"PROPN\",\n      \"sentiment\":0.0,\n      \"shape\":\"xxxx\",\n      \"tag\":\"NNP\",\n      \"tense\":\"\",\n      \"text\":\"silent\",\n      \"verb_form\":\"\",\n      \"x\":8,\n      \"y\":14\n   },\n   {\n      \"dep\":\"compound\",\n      \"ent\":\"\",\n      \"head\":\"5665575797947403677\",\n      \"id\":\"16417888112635110788\",\n      \"is_alpha\":true,\n      \"is_punct\":false,\n      \"is_stop\":false,\n      \"is_wordnet\":true,\n      \"lemma\":\"feature\",\n      \"noun_number\":\"singular\",\n      \"other\":{\n         \"head_i\":3,\n         \"head_idx\":24,\n         \"head_orth\":5665575797947403677,\n         \"head_text\":\"films\",\n         \"i\":2,\n         \"idx\":16,\n         \"orth\":16417888112635110788\n      },\n      \"pos\":\"NOUN\",\n      \"sentiment\":0.0,\n      \"shape\":\"xxxx\",\n      \"tag\":\"NN\",\n      \"tense\":\"\",\n      \"text\":\"feature\",\n      \"verb_form\":\"\",\n      \"x\":14,\n      \"y\":21\n   },\n   {\n      \"dep\":\"ROOT\",\n      \"ent\":\"\",\n      \"head\":\"5665575797947403677\",\n      \"id\":\"5665575797947403677\",\n      \"is_alpha\":true,\n      \"is_punct\":false,\n      \"is_stop\":false,\n      \"is_wordnet\":true,\n      \"lemma\":\"film\",\n      \"noun_number\":\"plural\",\n      \"other\":{\n         \"head_i\":3,\n         \"head_idx\":24,\n         \"head_orth\":5665575797947403677,\n         \"head_text\":\"films\",\n         \"i\":3,\n         \"idx\":24,\n         \"orth\":5665575797947403677\n      },\n      \"pos\":\"NOUN\",\n      \"sentiment\":0.0,\n      \"shape\":\"xxxx\",\n      \"tag\":\"NNS\",\n      \"tense\":\"\",\n      \"text\":\"films\",\n      \"verb_form\":\"\",\n      \"x\":21,\n      \"y\":26\n   }\n]\n```\n",
    "bugtrack_url": null,
    "license": "None",
    "summary": "Use spaCy to Parse Input Tokens",
    "version": "0.1.16",
    "project_urls": {
        "Bug Tracker": "https://github.com/craigtrim/spacy-token-parser/issues",
        "Homepage": "https://github.com/craigtrim/spacy-token-parser",
        "Repository": "https://github.com/craigtrim/spacy-token-parser"
    },
    "split_keywords": [
        "nlp",
        "nlu",
        "ai",
        "parser",
        "spacy"
    ],
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "b68a5cede13645b09a28c1f4a366c2b6b8b78b859ecf85cf78bdccab66db2e55",
                "md5": "3268c05b94b044af2db38c562ae5b942",
                "sha256": "44bdcdbb86596db9fe12ab1ff486b9d740bf61e6ab4f509a8d568a7fe0fd0407"
            },
            "downloads": -1,
            "filename": "spacy_token_parser-0.1.16-py3-none-any.whl",
            "has_sig": false,
            "md5_digest": "3268c05b94b044af2db38c562ae5b942",
            "packagetype": "bdist_wheel",
            "python_version": "py3",
            "requires_python": ">=3.8.5,<4.0.0",
            "size": 15867,
            "upload_time": "2023-07-15T05:37:40",
            "upload_time_iso_8601": "2023-07-15T05:37:40.177223Z",
            "url": "https://files.pythonhosted.org/packages/b6/8a/5cede13645b09a28c1f4a366c2b6b8b78b859ecf85cf78bdccab66db2e55/spacy_token_parser-0.1.16-py3-none-any.whl",
            "yanked": false,
            "yanked_reason": null
        },
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "9accbb39463f6ad21d0d8cf54960f083b513b2f8290e6f4341368838e8a185d4",
                "md5": "192456ed014ba79196265c3a008e5a50",
                "sha256": "6a82d11eeb50028f53b6985b5842904b952e152f3da7770c90ffae3fe95c66ca"
            },
            "downloads": -1,
            "filename": "spacy_token_parser-0.1.16.tar.gz",
            "has_sig": false,
            "md5_digest": "192456ed014ba79196265c3a008e5a50",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": ">=3.8.5,<4.0.0",
            "size": 10395,
            "upload_time": "2023-07-15T05:37:42",
            "upload_time_iso_8601": "2023-07-15T05:37:42.873085Z",
            "url": "https://files.pythonhosted.org/packages/9a/cc/bb39463f6ad21d0d8cf54960f083b513b2f8290e6f4341368838e8a185d4/spacy_token_parser-0.1.16.tar.gz",
            "yanked": false,
            "yanked_reason": null
        }
    ],
    "upload_time": "2023-07-15 05:37:42",
    "github": true,
    "gitlab": false,
    "bitbucket": false,
    "codeberg": false,
    "github_user": "craigtrim",
    "github_project": "spacy-token-parser",
    "github_not_found": true,
    "lcname": "spacy-token-parser"
}
        
Elapsed time: 0.32732s