openapi: 3.0.3
info:
title: Sketch Engine - API documentation
description: "An **application programming interface** (API) is a set of rules and\
\ protocols that allow different software applications to communicate with each\
\ other.\n \n\nIn the context of Sketch Engine, the API provides\
\ a standardized way for developers to access and use Sketch Engine's language\
\ data and text analysis \n tools in their own software applications.\
\ It is useful for anyone who needs to work with text, from analyzing text data\
\ such as searching collocations, \n generating word lists\
\ and keywords, and building text corpora (databases of written language), etc.\
\ With the API, developers can integrate these features \n \
\ into their own applications and create custom text analysis tools.\n\n \
\ \n\nThis **API documentation** outlines the Sketch Engine endpoints\
\ used mainly for working with corpora, including their creation, compilation\
\ and various \n functions such as word sketches, concordances,\
\ etc. The documentation describes the **requests** and responses of API calls,\
\ with most responses provided in \n either **JSON** or **plain\
\ text** format.\n\n \n\nYou can try every endpoint by **authenticating**\
\ with your **API key**, clicking **Try it out** on the endpoint you want to use,\
\ filling in the requested parameters, \n and executing the\
\ query.\n\n \n\nIt is **recommended** to use your **Sketch\
\ Engine API key** for **authentication** when calling the endpoints, otherwise\
\ it does not have to work. \n The **key** can be retrieved\
\ from the Sketch Engine dashboard by following these steps: select **More options**\
\ (upper right corner), then click on **My Account**.\n\n \n\
\n**Last update:** `2nd April 2024`"
version: 2.0.0
termsOfService: https://www.sketchengine.eu/terms-of-use/
contact:
name: Support
url: https://www.sketchengine.eu/contact-us/
externalDocs:
description: former API documentation
url: https://www.sketchengine.eu/documentation/api-documentation/
servers:
<!--#if expr="$HTTP_X_FORWARDED_PROTO" -->- url: <!--#echo var="HTTP_X_FORWARDED_PROTO" -->://<!--#echo var="HTTP_HOST" -->
<!--#else -->- url: http://<!--#echo var="HTTP_HOST" --><!--#endif -->
tags:
- name: Corpus Search
description: A variety of tools to search and analyse words or texts in the corpus
and generates their statistics.
- name: Corpora
description: Retrieves information about a corpus. Also creates, compiles and deletes
a corpus.
- name: Documents
description: Uploads new documents and deletes documents from a corpus. Adds and
edits document metadata.
- name: Filesets
description: Creates or deletes folders with documents (filesets) or shows their
content.
- name: Languages
description: Retrieves the list of languages.
- name: Somefiles
description: Uploads or updates aligned multilingual files to build a parallel corpus.
- name: Templates
description: Corpus template management.
- name: Users
description: Retrieves information about user accounts.
paths:
/search/corp_info:
get:
operationId: getCorpInfo
parameters:
- $ref: '#/components/parameters/001_corpname'
- $ref: '#/components/parameters/002_usesubcorp'
- $ref: '#/components/parameters/006_subcorpora'
- $ref: '#/components/parameters/003_gramrels'
- $ref: '#/components/parameters/004_corpcheck'
- $ref: '#/components/parameters/005_registry'
- $ref: '#/components/parameters/007_struct_attr_stats'
- $ref: '#/components/parameters/008_format'
tags:
- Corpus Search
summary: Statistics and information about the whole corpus.
description: "-"
responses:
'200':
description: '`OK`'
content:
application/json:
schema:
$ref: '#/components/schemas/01_corp_info'
/search/wordlist:
get:
operationId: getWordList
parameters:
- $ref: '#/components/parameters/001_corpname'
- $ref: '#/components/parameters/010_wlattr'
- $ref: '#/components/parameters/002_usesubcorp'
- $ref: '#/components/parameters/011_wlnums'
- $ref: '#/components/parameters/072_wlmaxfreq'
- $ref: '#/components/parameters/012_wlminfreq'
- $ref: '#/components/parameters/014_wlpat'
- $ref: '#/components/parameters/015_wlsort'
- $ref: '#/components/parameters/019_wlblacklist'
- $ref: '#/components/parameters/073_include_nonwords'
- $ref: '#/components/parameters/091_relfreq'
- $ref: '#/components/parameters/092_reldocf'
- $ref: '#/components/parameters/018_wlfile'
- $ref: '#/components/parameters/071_wlicase'
- $ref: '#/components/parameters/013_wlmaxitems'
- $ref: '#/components/parameters/093_wlpage'
- $ref: '#/components/parameters/008_format'
- $ref: '#/components/parameters/074_random'
- $ref: '#/components/parameters/089_wltype'
- $ref: '#/components/parameters/063_ngrams_n'
- $ref: '#/components/parameters/087_ngrams_max_n'
- $ref: '#/components/parameters/112_nest_ngrams'
- $ref: '#/components/parameters/057_simple_n'
- $ref: '#/components/parameters/088_usengrams'
tags:
- Corpus Search
summary: A list of word frequencies from the specified corpus.
description: This method can be used for generating frequency lists of all tokens,
lemmas, word forms etc. or for retrieving frequencies of concrete items. Regex
can be used for detailed criteria.
responses:
'200':
description: '`OK`'
content:
application/json:
schema:
$ref: '#/components/schemas/02_wordlist'
/search/struct_wordlist:
get:
operationId: getStructWordList
parameters:
- $ref: '#/components/parameters/001_corpname'
- $ref: '#/components/parameters/010_wlattr'
- $ref: '#/components/parameters/090_wlstruct_attr1'
- $ref: '#/components/parameters/102_wlstruct_attr2'
- $ref: '#/components/parameters/103_wlstruct_attr3'
- $ref: '#/components/parameters/011_wlnums'
- $ref: '#/components/parameters/072_wlmaxfreq'
- $ref: '#/components/parameters/012_wlminfreq'
- $ref: '#/components/parameters/013_wlmaxitems'
- $ref: '#/components/parameters/014_wlpat'
- $ref: '#/components/parameters/015_wlsort'
- $ref: '#/components/parameters/019_wlblacklist'
- $ref: '#/components/parameters/073_include_nonwords'
- $ref: '#/components/parameters/091_relfreq'
- $ref: '#/components/parameters/092_reldocf'
- $ref: '#/components/parameters/071_wlicase'
- $ref: '#/components/parameters/093_wlpage'
- $ref: '#/components/parameters/008_format'
- $ref: '#/components/parameters/074_random'
- $ref: '#/components/parameters/089_wltype'
tags:
- Corpus Search
summary: Provides a list of frequencies in the specified corpus. Offers more
flexibility.
description: The difference from the wordlist is that this enpoint allows to
customize how the results are displayed.
responses:
'200':
description: '`OK`'
content:
application/json:
schema:
$ref: '#/components/schemas/12_struct_wordlist'
/search/concordance:
get:
operationId: getConcordance
parameters:
- $ref: '#/components/parameters/001_corpname'
- $ref: '#/components/parameters/041_q'
- $ref: '#/components/parameters/127_concordance_query_queryselector'
- $ref: '#/components/parameters/128_concordance_query_iquery'
- $ref: '#/components/parameters/129_concordance_query_cql'
- $ref: '#/components/parameters/130_concordance_query_lemma'
- $ref: '#/components/parameters/131_concordance_query_char'
- $ref: '#/components/parameters/132_concordance_query_word'
- $ref: '#/components/parameters/133_concordance_query_phrase'
- $ref: '#/components/parameters/002_usesubcorp'
- $ref: '#/components/parameters/025_lpos'
- $ref: '#/components/parameters/077_default_attr'
- $ref: '#/components/parameters/058_attrs'
- $ref: '#/components/parameters/078_refs'
- $ref: '#/components/parameters/079_attr_allpos'
- $ref: '#/components/parameters/080_viewmode'
- $ref: '#/components/parameters/081_cup_hl'
- $ref: '#/components/parameters/082_structs'
- $ref: '#/components/parameters/083_fromp'
- $ref: '#/components/parameters/084_pagesize'
- $ref: '#/components/parameters/085_kwicleftctx'
- $ref: '#/components/parameters/086_kwicrightctx'
- $ref: '#/components/parameters/134_errcorr_switch'
- $ref: '#/components/parameters/135_cup_err_code'
- $ref: '#/components/parameters/136_cup_err'
- $ref: '#/components/parameters/137_cup_corr'
- $ref: '#/components/parameters/040_json'
- $ref: '#/components/parameters/039_asyn'
- $ref: '#/components/parameters/008_format'
tags:
- Corpus Search
summary: Concordance - shows the search word or phrase in context.
description: "The concordance allows complex criteria for searching the corpus.\
\ The queries can combine any data, metadata and annotations found in the\
\ corpus.\n\n `To make basic concordance its enough to use just corpname and\
\ q parameters.`"
responses:
'200':
description: '`OK`'
content:
application/json:
schema:
$ref: '#/components/schemas/06_concordance'
/search/fullref:
get:
operationId: getFullRef
parameters:
- $ref: '#/components/parameters/001_corpname'
- $ref: '#/components/parameters/111_pos'
summary: Returns all metadata of one concordance line.
description: Displays all available text types (metadata) related to the concrete
KWIC (hit) defined by its position in the corpus.
tags:
- Corpus Search
responses:
'200':
description: '`OK`'
content:
application/json:
schema:
$ref: '#/components/schemas/14_fullref'
/search/widectx:
get:
operationId: getWideCtx
parameters:
- $ref: '#/components/parameters/001_corpname'
- $ref: '#/components/parameters/111_pos'
- $ref: '#/components/parameters/138_hitlen'
- $ref: '#/components/parameters/082_structs'
- $ref: '#/components/parameters/139_detail_left_ctx'
- $ref: '#/components/parameters/140_detail_right_ctx'
summary: Returns extended context the KWIC in a concrete concordance line.
description: This is the equivalent of clicking KWIC in one concordance line
which displays a popup with an extended context.
tags:
- Corpus Search
responses:
'200':
description: '`OK`'
content:
application/json:
schema:
$ref: '#/components/schemas/16_widectx'
/search/freqml:
get:
operationId: getFreqMl
tags:
- Corpus Search
summary: "Calculates frequencies of words, lemmas\u2026 in the concordance."
description: The frequency of any [positional attribute] (https://www.sketchengine.eu/my_keywords/positional-attribute/)
such as word forms, lemmas, tags can be counted with this method. Structure
attributes (metadata/text types) can also be counted.
parameters:
- $ref: '#/components/parameters/001_corpname'
- $ref: '#/components/parameters/100_ml1attr'
- $ref: '#/components/parameters/101_ml1ctx'
- $ref: '#/components/parameters/141_ml2attr'
- $ref: '#/components/parameters/142_ml2ctx'
- $ref: '#/components/parameters/143_ml3attr'
- $ref: '#/components/parameters/144_ml3ctx'
- $ref: '#/components/parameters/145_ml4attr'
- $ref: '#/components/parameters/146_ml4ctx'
- $ref: '#/components/parameters/147_ml5attr'
- $ref: '#/components/parameters/148_ml5ctx'
- $ref: '#/components/parameters/149_ml6attr'
- $ref: '#/components/parameters/150_ml6ctx'
- $ref: '#/components/parameters/041_q'
- $ref: '#/components/parameters/002_usesubcorp'
- $ref: '#/components/parameters/044_fmaxitems'
- $ref: '#/components/parameters/094_fpage'
- $ref: '#/components/parameters/095_group'
- $ref: '#/components/parameters/096_showpoc'
- $ref: '#/components/parameters/097_showreltt'
- $ref: '#/components/parameters/098_showrel'
- $ref: '#/components/parameters/099_freqlevel'
- $ref: '#/components/parameters/040_json'
- $ref: '#/components/parameters/045_freq_sort'
- $ref: '#/components/parameters/008_format'
responses:
'200':
description: '`OK`'
content:
application/json:
schema:
$ref: '#/components/schemas/11_freqml'
/search/freq_distrib:
get:
operationId: getFregDistrib
parameters:
- $ref: '#/components/parameters/001_corpname'
- $ref: '#/components/parameters/118_res'
- $ref: '#/components/parameters/025_lpos'
- $ref: '#/components/parameters/077_default_attr'
- $ref: '#/components/parameters/058_attrs'
- $ref: '#/components/parameters/082_structs'
- $ref: '#/components/parameters/078_refs'
- $ref: '#/components/parameters/079_attr_allpos'
- $ref: '#/components/parameters/080_viewmode'
- $ref: '#/components/parameters/120_fc_lemword_window_type'
- $ref: '#/components/parameters/121_fc_lemword_wsize'
- $ref: '#/components/parameters/122_fc_lemword_type'
- $ref: '#/components/parameters/125_fc_pos_window_type'
- $ref: '#/components/parameters/123_fc_pos_wsize'
- $ref: '#/components/parameters/124_fc_pos_type'
- $ref: '#/components/parameters/040_json'
- $ref: '#/components/parameters/119_normalize'
- $ref: '#/components/parameters/008_format'
summary: Provides the distribution of hits in the corpus
description: "-"
tags:
- Corpus Search
responses:
'200':
description: '`OK`'
content:
application/json:
schema:
$ref: '#/components/schemas/13_freq_distrib'
/search/freqdist:
get:
operationId: getFreqDist
description: "-"
parameters:
- $ref: '#/components/parameters/166_corpname_freqdist'
- $ref: '#/components/parameters/010_wlattr'
- $ref: '#/components/parameters/162_diaattr'
- $ref: '#/components/parameters/163_sse'
- $ref: '#/components/parameters/164_threshold'
- $ref: '#/components/parameters/161_ctx'
- $ref: '#/components/parameters/167_wordlist'
- $ref: '#/components/parameters/165_json_freqdist'
tags:
- Corpus Search
summary: Utility for web interface only. Provides relative frequency data for
wordlist graphs within a specific time period, only for trend corpora.
responses:
'200':
description: '`OK`'
content:
application/json:
schema:
$ref: '#/components/schemas/19_freqdist'
/search/collx:
get:
operationId: getCollx
description: "-"
summary: Computes collocation candidates from a concordance.
tags:
- Corpus Search
parameters:
- $ref: '#/components/parameters/001_corpname'
- $ref: '#/components/parameters/041_q'
- $ref: '#/components/parameters/002_usesubcorp'
- $ref: '#/components/parameters/046_cattr'
- $ref: '#/components/parameters/053_csortfn'
- $ref: '#/components/parameters/052_cbgrfns'
- $ref: '#/components/parameters/047_cfromw'
- $ref: '#/components/parameters/048_ctow'
- $ref: '#/components/parameters/049_cminfreq'
- $ref: '#/components/parameters/050_cminbgr'
- $ref: '#/components/parameters/051_cmaxitems'
- $ref: '#/components/parameters/154_json_collx'
responses:
'200':
description: '`OK`'
content:
application/json:
schema:
$ref: '#/components/schemas/10_collx'
/search/subcorp:
get:
operationId: getSubCorp
parameters:
- $ref: '#/components/parameters/001_corpname'
- $ref: '#/components/parameters/054_subcname'
- $ref: '#/components/parameters/155_create'
- $ref: '#/components/parameters/055_delete'
- $ref: '#/components/parameters/156_q_subcorp'
- $ref: '#/components/parameters/157_struct'
- $ref: '#/components/parameters/160_json_subcorp'
- $ref: '#/components/parameters/008_format'
tags:
- Corpus Search
summary: Get a list of subcorpora in the corpus or create/delete a subcorpus.
description: There is two option how to create subcorpora in Sketch Engine from
`text types` => json parameter (corpus must be annotated for text types) or
from `concordances` => q + struct parameters.
responses:
'200':
description: '`OK`'
content:
application/json:
schema:
$ref: '#/components/schemas/07_subcorp'
/search/subcorpus_rename:
get:
operationId: subcorpusRename
description: "-"
parameters:
- $ref: '#/components/parameters/001_corpname'
- $ref: '#/components/parameters/158_subcorp_id'
- $ref: '#/components/parameters/159_new_subcorp_name'
tags:
- Corpus Search
summary: Rename subcorpus.
responses:
'200':
description: '`OK`'
content:
application/json:
schema:
$ref: '#/components/schemas/17_subcorpus_rename'
/search/subcorp_info:
get:
operationId: subcorpusInfo
description: "-"
parameters:
- $ref: '#/components/parameters/001_corpname'
- $ref: '#/components/parameters/054_subcname'
tags:
- Corpus Search
summary: Statistics about the subcorpus.
responses:
'200':
description: '`OK`'
content:
application/json:
schema:
$ref: '#/components/schemas/18_subcorp_info'
/search/extract_keywords:
get:
operationId: getExtractKeywords
parameters:
- $ref: '#/components/parameters/001_corpname'
- $ref: '#/components/parameters/056_ref_corpname'
- $ref: '#/components/parameters/002_usesubcorp'
- $ref: '#/components/parameters/057_simple_n'
- $ref: '#/components/parameters/018_wlfile'
- $ref: '#/components/parameters/019_wlblacklist'
- $ref: '#/components/parameters/115_attr'
- $ref: '#/components/parameters/060_alnum'
- $ref: '#/components/parameters/061_onealpha'
- $ref: '#/components/parameters/151_minfreq_extract_keywords'
- $ref: '#/components/parameters/152_maxfreq_extract_keywords'
- $ref: '#/components/parameters/062_max_keywords'
- $ref: '#/components/parameters/073_include_nonwords'
- $ref: '#/components/parameters/104_icase'
- $ref: '#/components/parameters/014_wlpat'
- $ref: '#/components/parameters/153_addfreqs'
- $ref: '#/components/parameters/092_reldocf'
- $ref: '#/components/parameters/088_usengrams'
- $ref: '#/components/parameters/063_ngrams_n'
- $ref: '#/components/parameters/087_ngrams_max_n'
- $ref: '#/components/parameters/008_format'
tags:
- Corpus Search
summary: Identifies keywords, key n-grams, key collocations and terms.
description: Keywords, key n-grams, key collocations and terms are identified
by comparing the focus corpus (or a subcorpus) to a refrence corpus (or a
subcorpus). It is the equivalent of using the Keywords and terms tool or using
the key option in n-grams or the word sketch.
responses:
"200":
description: '`OK`'
content:
application/json:
schema:
$ref: '#/components/schemas/08_extract_keywords'
/search/textypes_with_norms:
get:
operationId: getTextTypesWithNorms
description: "-"
parameters:
- $ref: '#/components/parameters/001_corpname'
summary: Returns a list of text types with values.
tags:
- Corpus Search
responses:
'200':
description: '`OK`'
content:
application/json:
schema:
$ref: '#/components/schemas/15_textypes_with_norms'
/search/attr_vals:
get:
operationId: getAttrVals
parameters:
- $ref: '#/components/parameters/001_corpname'
- $ref: '#/components/parameters/020_avattr'
- $ref: '#/components/parameters/021_avpat'
- $ref: '#/components/parameters/023_avfrom'
- $ref: '#/components/parameters/022_avmaxitems'
- $ref: '#/components/parameters/104_icase'
- $ref: '#/components/parameters/008_format'
tags:
- Corpus Search
summary: Utility for web interface only. A list of values for a given structure
attribute (avattr).
description: Not to be used outside the web interface. Replaced by a more powerful
wordlist.
responses:
'200':
description: '`OK`'
content:
application/json:
schema:
$ref: '#/components/schemas/09_attr_vals'
/ca/api/corpora:
get:
operationId: getCorpora
description: "-"
tags:
- Corpora
summary: Returns a list of all corpora accessible to you.
responses:
"200":
description: '`OK`'
content:
application/json:
schema:
type: object
properties:
data:
type: array
items:
$ref: '#/components/schemas/03_corpora_list'
post:
operationId: createCorpus
tags:
- Corpora
summary: Creates a new user corpus.
description: Creates a new empty corpus. Use **Documents** endpoints (and optionally
**Filesets**) to add data to the corpus.
requestBody:
description: "Set the language, corpus name and corpus description. \n\n -\
\ `info` => The additional information for a newly created corpus. (string)\
\ \n\n - `language_id` => Language iso-code. `ISO 639-1`. (string) \n\n\
\ - `name` => Unique `corpus name` for a newly created corpus. (string)"
content:
application/json:
schema:
$ref: '#/components/schemas/01_corpora_request'
required: true
responses:
"201":
description: '`Created`'
content:
application/json:
schema:
type: object
properties:
data:
$ref: '#/components/schemas/04_corpora_single'
/ca/api/corpora/{corpusId}:
parameters:
- $ref: '#/components/parameters/01_corpus_id'
get:
operationId: getCorpus
description: "-"
tags:
- Corpora
summary: Retrieves a user corpus.
responses:
"200":
description: '`OK`'
content:
application/json:
schema:
$ref: '#/components/schemas/04_corpora_single'
"403":
description: '`Forbidden`'
content:
application/json:
schema:
$ref: '#/components/schemas/27_forbidden_normal'
"404":
description: '`Not Found`'
content:
application/json:
schema:
$ref: '#/components/schemas/57_not_found_404'
put:
operationId: updateCorpus
description: "-"
tags:
- Corpora
summary: Updates a user corpus.
requestBody:
description: " - `expert_mode` => Set to **True** if you are hard-core. (boolean)\
\ \n\n - `name` => Corpus name. **Given by user**. (string) \n\n - `info`\
\ => Additional info about corpus. (string) \n\n - `document_order` =>\
\ Can be set to enforce document order within the corpus. (list of integers)\
\ \n\n - `structures` => Available structures or tags in the corpus. Structures\
\ like **s** (sentence), **g** (glue), **doc** (document).(list) \n\n \
\ - `name` => Structure name. Example: **s**. (string) \n\n - `attributes`\
\ => A list of used attributes in corpus. (list) \n\n - `name` => The\
\ name of used attribute. (string) \n\n - `file_structure` => The structure\
\ in which individual documents should be wrapped. Usually **doc**. (string)\
\ \n\n - `onion_structure` => The structure for deduplication. Usually\
\ **p** (paragraph) or **Null** (no deduplication). (string) \n\n - `docstructure`\
\ => Structure in which individual documents should be wrapped. Usually\
\ **doc**. (string) \n\n - `sketch_grammar_id` => Name of sketch grammar\
\ file. For sketch grammars querying. Sketch grammar is a series of rules\
\ written in the CQL query language that search for collocations in a text\
\ corpus and categorize them according to\_their grammatical relations.\
\ Example: **preloaded/english-penn_tt-3.3.wsdef.m4**. (string) \n\n -\
\ `term_grammar_ir` => Name of term grammar file. Term grammar tells Sketch\
\ Engine which words and phrases should indentify as terms. Example: **/corpora/wsdef/english-penn_tt-terms-3.1.termdef.m4**.\
\ (string)"
content:
application/json:
schema:
$ref: '#/components/schemas/07_corpus_update'
responses:
"200":
description: '`OK`'
content:
application/json:
schema:
type: object
properties:
data:
$ref: '#/components/schemas/04_corpora_single'
"403":
description: '`Forbidden`'
content:
application/json:
schema:
$ref: '#/components/schemas/27_forbidden_normal'
"404":
description: '`Not Found`'
content:
application/json:
schema:
$ref: '#/components/schemas/57_not_found_404'
delete:
operationId: deleteCorpus
description: "-"
tags:
- Corpora
summary: Deletes a user corpus.
responses:
"204":
description: '`No Content`'
content: {}
"403":
description: '`Forbidden`'
content:
application/json:
schema:
$ref: '#/components/schemas/27_forbidden_normal'
"404":
description: '`Not Found`'
content:
application/json:
schema:
$ref: '#/components/schemas/57_not_found_404'
/ca/api/corpora/{corpusId}/can_be_compiled:
parameters:
- $ref: '#/components/parameters/01_corpus_id'
post:
operationId: checkCompilable
description: "-"
tags:
- Corpora
summary: Checks if the corpus fulfills all conditions to be compiled. (RPC)
requestBody:
description: ' In this documentation, an empty request is used mostly used
with the **RPC style** method where the content in a request is not needed
(in most cases). RPC style endpoints focus on performing **one action**
right (procedures, command) easier than **REST API**-based endpoints. It
is not as scalable as REST API style. RPC is mostly used with HTTP: GET
(to fetch information) and POST (to everything else) in CA api is it used
with POST HTTP method. '
content:
application/json:
schema:
$ref: '#/components/schemas/05_empty_request'
responses:
"200":
description: '`OK`'
content:
application/json:
schema:
$ref: '#/components/schemas/05_can_be_compiled'
"401":
description: '`Unauthorized`'
content:
application/json:
schema:
$ref: '#/components/schemas/20_unauthorized'
"403":
description: '`Forbidden`'
content:
application/json:
schema:
$ref: '#/components/schemas/21_forbidden'
"404":
description: '`Not Found`'
content:
application/json:
schema:
$ref: '#/components/schemas/45_not_found_RPC'
/ca/api/corpora/{corpusId}/get_progress:
parameters:
- $ref: '#/components/parameters/01_corpus_id'
post:
operationId: getCompilationProgress
description: "-"
tags:
- Corpora
summary: Retrieves the current progress of the corpus compilation. (RPC)
requestBody:
description: ' In this documentation, an empty request is used mostly used
with the **RPC style** method where the content in a request is not needed
(in most cases). RPC style endpoints focus on performing **one action**
right (procedures, command) easier than **REST API**-based endpoints. It
is not as scalable as REST API style. RPC is mostly used with HTTP: GET
(to fetch information) and POST (to everything else) in CA api is it used
with POST HTTP method. '
content:
application/json:
schema:
$ref: '#/components/schemas/05_empty_request'
required: true
responses:
"200":
description: '`OK`'
content:
application/json:
schema:
$ref: '#/components/schemas/06_get_progress'
"403":
description: '`Forbidden`'
content:
application/json:
schema:
$ref: '#/components/schemas/21_forbidden'
"404":
description: '`Not Found`'
content:
application/json:
schema:
$ref: '#/components/schemas/45_not_found_RPC'
/ca/api/corpora/{corpusId}/compile:
parameters:
- $ref: '#/components/parameters/01_corpus_id'
post:
operationId: compileCorpus
description: "-"
tags:
- Corpora
summary: Performs the corpus compilation. (RPC)
requestBody:
description: ' `Structures` or `structure attributes` in corpus which should
be compiled. Usually: `all`. (string) '
content:
application/json:
schema:
$ref: '#/components/schemas/02_compile_request'
required: true
responses:
"200":
description: '`OK`'
content:
application/json:
schema:
$ref: '#/components/schemas/69_rpc_style'
"400":
description: '`Bad Request`'
content:
application/json:
schema:
$ref: '#/components/schemas/29_bad_request_RPC_9'
"401":
description: '`Unauthorized`'
content:
application/json:
schema:
$ref: '#/components/schemas/23_unauthorized_rpc'
"403":
description: '`Forbidden`'
content:
application/json:
schema:
$ref: '#/components/schemas/21_forbidden'
"404":
description: '`Not Found`'
content:
application/json:
schema:
$ref: '#/components/schemas/45_not_found_RPC'
/ca/api/corpora/{corpusId}/logs/{logName}:
parameters:
- $ref: '#/components/parameters/01_corpus_id'
- $ref: '#/components/parameters/05_logname'
get:
operationId: getCompilationLog
tags:
- Corpora
summary: Show the compilation log file '.log' of the corpus.
description: If **logName** == **last.log** it shows the latest version of the
log file.
responses:
"200":
description: '`OK`'
content:
text/plain; charset=utf-8:
schema:
description: The log file of the corpus.
type: string
"401":
description: '`Unauthorized`'
"403":
description: '`Forbidden` (you need `read` permission)'
"404":
description: '`Not Found`'
"405":
description: '`Method Not Allowed`'
/ca/api/corpora/{corpusId}/download:
parameters:
- $ref: '#/components/parameters/01_corpus_id'
- $ref: '#/components/parameters/09_format'
- $ref: '#/components/parameters/10_file_structure'
- $ref: '#/components/parameters/11_aligned'
get:
operationId: getCorpusSource
tags:
- Corpora
summary: Downloads the documents from which the corpus was created (the source
files).
description: 'Example call can be: **https://app.sketchengine.eu/ca/api/corpora/{corpusId}/download?format=vert&file_structure=doc**.'
responses:
"200":
description: '`OK`'
content:
text/plain:
schema:
type: string
"400":
description: '`Bad Request` Examples: `ALIGNED_NOT_FOUND`, `ALIGNED_FORBIDDEN`,
`INVALID_FORMAT`.'
"401":
description: '`Unauthorized`'
"403":
description: '`Forbidden`'
"404":
description: '`Not Found`'
/ca/api/corpora/{corpusId}/cancel_job:
parameters:
- $ref: '#/components/parameters/01_corpus_id'
post:
operationId: cancelJob
description: "-"
tags:
- Corpora
summary: Cancels running tasks (e.g. compilation) relatated to the corpus. (RPC)
requestBody:
description: ' In this documentation, an empty request is used mostly used
with the **RPC style** method where the content in a request is not needed
(in most cases). RPC style endpoints focus on performing **one action**
right (procedures, command) easier than **REST API**-based endpoints. It
is not as scalable as REST API style. RPC is mostly used with HTTP: GET
(to fetch information) and POST (to everything else) in CA api is it used
with POST HTTP method. '
content:
application/json:
schema:
$ref: '#/components/schemas/05_empty_request'
responses:
"200":
description: '`OK`'
content:
application/json:
schema:
$ref: '#/components/schemas/69_rpc_style'
"401":
description: '`Unauthorized`'
content:
application/json:
schema:
$ref: '#/components/schemas/23_unauthorized_rpc'
"403":
description: '`Forbidden`'
content:
application/json:
schema:
$ref: '#/components/schemas/21_forbidden'
/ca/api/corpora/compile_aligned:
post:
operationId: compileAlignedCorpus
description: "-"
tags:
- Corpora
summary: Compiles a parallel corpus (consisting of two or more aligned corpora).
(RPC)
requestBody:
description: "List of corpus IDs used in aligned compilation. \n\n - `corpus_ids`\
\ => A list of **Corpus ID** of multilingual corpora. (integer) \n\n -\
\ `structures` => Represent if **all** structures should be used during\
\ compilation (in that case it should be contain just **all**) or just some\
\ of them. (string) "
content:
application/json:
schema:
$ref: '#/components/schemas/03_corpus_ids'
responses:
"200":
description: '`OK`'
content:
application/json:
schema:
$ref: '#/components/schemas/69_rpc_style'
"400":
description: '`Bad Request`'
content:
application/json:
schema:
$ref: '#/components/schemas/28_bad_request_RPC_8'
"403":
description: '`Forbidden`'
content:
application/json:
schema:
$ref: '#/components/schemas/21_forbidden'
/ca/api/corpora/align:
post:
operationId: segmentAlign
tags:
- Corpora
summary: Creates segment representing the same line in two languages in a parallel
corpus. (RPC)
description: Run if documents inserted into the corpus are not aligned.
requestBody:
description: "- `alignstruct` => According to which structure the document\
\ should be aligned. Usually, **\\<s>**. (string) \n\n - `auto` => **True**,\
\ when documents are not compiled. Sketch Engine will align them automatically.\
\ (boolean) \n\n - `corpus_ids` => A list of **Corpus ID** of multilingual\
\ corpus. (integer) "
content:
application/json:
schema:
$ref: '#/components/schemas/04_align_req'
responses:
"200":
description: '`OK`'
content:
application/json:
schema:
$ref: '#/components/schemas/69_rpc_style'
"400":
description: '`Bad Request`'
content:
application/json:
schema:
$ref: '#/components/schemas/17_bad_request_RPC_1'
"401":
description: '`Unauthorized`'
content:
application/json:
schema:
$ref: '#/components/schemas/23_unauthorized_rpc'
"403":
description: '`Forbidden`'
content:
application/json:
schema:
$ref: '#/components/schemas/21_forbidden'
/ca/api/corpora/{corpusId}/documents:
parameters:
- $ref: '#/components/parameters/01_corpus_id'
- $ref: '#/components/parameters/07_fileset_id_query'
get:
operationId: getAllDocuments
description: "-"
tags:
- Documents
summary: Retrieves a list of all documents in the corpus.
responses:
"200":
description: '`OK`'
content:
application/json:
schema:
$ref: '#/components/schemas/13_documents_get'
"401":
description: '`Unauthorized`'
content:
application/json:
schema:
$ref: '#/components/schemas/20_unauthorized'
"403":
description: '`Forbidden` (you need `view` permission).'
content:
application/json:
schema:
$ref: '#/components/schemas/27_forbidden_normal'
"404":
description: '`Not Found` (HTML response).'
post:
operationId: createNewDocument
description: "-"
tags:
- Documents
summary: Uploads a new document.
parameters:
- $ref: '#/components/parameters/01_corpus_id'
- $ref: '#/components/parameters/07_fileset_id_query'
- $ref: '#/components/parameters/18_wait_with_tagging'
requestBody:
description: File to upload.
content:
multipart/form-data:
schema:
properties:
file:
type: string
description: File to upload.
format: binary
responses:
"201":
description: '`Created`'
content:
application/json:
schema:
$ref: '#/components/schemas/14_documents_post'
"400":
description: '`Bad Request`'
content:
application/json:
schema:
$ref: '#/components/schemas/30_bad_request_10'
"401":
description: '`Unauthorized`'
content:
application/json:
schema:
$ref: '#/components/schemas/20_unauthorized'
"403":
description: '`Forbidden` (you need `upload` permission).'
content:
application/json:
schema:
$ref: '#/components/schemas/27_forbidden_normal'
"404":
description: '`Not Found` (HTML response).'
put:
operationId: updateDocumentMetadata
description: "-"
tags:
- Documents
summary: Edits the metadata of a document.
requestBody:
description: " - `id` => Unique numeric `document ID`. (integer) \n\n -\
\ `metadata` => Pairs of `attribute_name`:`value`."
content:
application/json:
schema:
$ref: '#/components/schemas/11_doc_metadata'
responses:
"200":
description: '`OK`'
content:
application/json:
schema:
$ref: '#/components/schemas/13_documents_get'
"400":
description: '`Bad Request`'
content:
application/json:
schema:
$ref: '#/components/schemas/31_bad_request_11'
"401":
description: '`Unauthorized`'
content:
application/json:
schema:
$ref: '#/components/schemas/20_unauthorized'
"403":
description: '`Forbidden` (you need `edit` permission).'
content:
application/json:
schema:
$ref: '#/components/schemas/27_forbidden_normal'
"404":
description: '`Not Found` (HTML response).'
/ca/api/corpora/{corpusId}/documents/{documentId}:
parameters:
- $ref: '#/components/parameters/01_corpus_id'
- $ref: '#/components/parameters/02_document_id'
get:
operationId: getDocument
description: "-"
tags:
- Documents
summary: Retrieves a specific document.
responses:
"200":
description: '`OK`'
content:
application/json:
schema:
$ref: '#/components/schemas/13_documents_get'
"401":
description: '`Unauthorized`'
content:
application/json:
schema:
$ref: '#/components/schemas/20_unauthorized'
"403":
description: '`Forbidden` (you need `view` permission).'
content:
application/json:
schema:
$ref: '#/components/schemas/27_forbidden_normal'
"404":
description: '`Not Found`'
content:
application/json:
schema:
$ref: '#/components/schemas/57_not_found_404'
put:
operationId: updateDocument
description: "-"
tags:
- Documents
summary: Updates documents to corpus.
requestBody:
description: " - `filename_display` => Name of documents. (string) \n\n -\
\ `id` => Unique numeric **document ID** to identify individual documents.\
\ (integer) \n\n - `inProgress` => Represents whether the currently edited\
\ document is in use. (boolean) \n\n - `isArchive` => Represents if the\
\ updated document is in a format like .zip (created via some archive manager).\
\ (boolean) \n\n - `metadata` => Metadata of document. For example, additional\
\ attributes and values. \n\n - `parameters` => Parameters for plaintext\
\ extraction. \n\n - `encoding` => Encoding standard of the document.\
\ Usually, **UTF-8**. (string) \n\n - `justext_stoplist` => Represent\
\ the list of unimportant words, in a specified language, from an NLP point\
\ of view. (string) \n\n - `permutation` => Changing the order of columns\
\ (applies only to **type=vert**). (integer) \n\n - `tmx_lang` => TMX\
\ (translation memory exchange). Language of document used for parallel\
\ corpus creation. (string) \n\n - `tmx_struct` => Alignment structure\
\ to be used for multilingual documents, **align** is the most used structure.\
\ Used within segment distinction, which sentence is in which language and\
\ to put sentences with the same meaning into one segment. (string) \n\n\
\ - `tmx_untranslated` => Placeholder for empty segments in multilingual\
\ documents. The segments which have no counterpart in a second language\
\ of parallel corpus. (string) \n\n - `type` => File format (.csv, .doc,\
\ .docx, .htm, .html). (string) \n\n - `unlegalese` => Convert **all-caps**\
\ text to **normal case**. (boolean) \n\n - `temporary` => Is document\
\ temporary or not. (boolean) \n\n - `word_count` => Total number of **words**\
\ (tokens minus punctuation etc.) in document. (integer) \n\n - `vertical_progress`\
\ => Progress of **vertical file** creation. (integer) \n\n - `vertical_error`\
\ => An error occured while creating the vertical file. If the creation\
\ was succesfull the value is **Null**. (string)"
content:
application/json:
schema:
$ref: '#/components/schemas/09_doc_put_req'
responses:
"200":
description: '`OK`'
content:
application/json:
schema:
$ref: '#/components/schemas/13_documents_get'
"400":
description: '`Bad Request`'
content:
application/json:
schema:
$ref: '#/components/schemas/31_bad_request_11'
"401":
description: '`Unauthorized`'
content:
application/json:
schema:
$ref: '#/components/schemas/20_unauthorized'
"403":
description: '`Forbidden` (you need `edit` permission).'
content:
application/json:
schema:
$ref: '#/components/schemas/27_forbidden_normal'
"404":
description: '`Not Found`'
content:
application/json:
schema:
$ref: '#/components/schemas/57_not_found_404'
delete:
operationId: deleteDocuments
tags:
- Documents
summary: Deletes one or more documents from the corpus.
description: 'To delete more documents, separate document ids with commas. Example
call: `https://app.sketchengine.eu/ca/api/corpora/{corpusId}/documents/{documentId_1},{documentId_2}`'
responses:
"204":
description: '`No Content`'
content: {}
"400":
description: '`Bad Request`'
content:
application/json:
schema:
$ref: '#/components/schemas/31_bad_request_11'
"401":
description: '`Unauthorized`'
content:
application/json:
schema:
$ref: '#/components/schemas/20_unauthorized'
"403":
description: '`Forbidden` (you need `delete` permission).'
content:
application/json:
schema:
$ref: '#/components/schemas/27_forbidden_normal'
"404":
description: '`Not Found`'
content:
application/json:
schema:
$ref: '#/components/schemas/57_not_found_404'
/ca/api/corpora/{corpusId}/documents/{documentId}/preview:
parameters:
- $ref: '#/components/parameters/01_corpus_id'
- $ref: '#/components/parameters/02_document_id'
post:
operationId: updateDocumentParameters
tags:
- Documents
summary: Updates document parameters. (RPC)
description: 'Updates parameters like: `File Type`, `Encoding`, etc.'
requestBody:
description: " - `auto_paragraphs` => Automatically insert paragraph breaks\
\ (**\\<p>**) in place of blank lines. (string) \n\n - `encoding` => Encoding\
\ standard of the document. Usually **UTF-8**. (string) \n\n - `justext_stoplist`\
\ => Represent the list of unimportant words, in a specified language, from\
\ an NLP point of view. (string) \n\n - `permutation` => Changing the order\
\ of columns (applies only to **type=vert**). \n\n - `tmx_lang` => TMX\
\ (translation memory exchange). Language of document used for parallel\
\ corpus creation. (string) \n\n - `tmx_struct` => Alignment structure\
\ to be used for multilingual documents, **align** is the most used structure.\
\ Used within segment distinction, which sentence is in which language and\
\ to put sentences with the same meaning into one segment. (string) \n\n\
\ - `tmx_untranslated` => Placeholder for empty segments in multilingual\
\ documents. The segments which have no counterpart in a second language\
\ of parallel corpus. (string) \n\n - `type` => File format (.csv, .doc,\
\ .docx, .htm, .html). (string) \n\n - `unlegalese` => Convert **all-caps**\
\ text to **normal case**. (boolean) "
content:
application/json:
schema:
$ref: '#/components/schemas/10_doc_preview'
responses:
"200":
description: '`OK`'
content:
application/json:
schema:
$ref: '#/components/schemas/15_doc_preview'
"403":
description: '`Forbidden`'
content:
application/json:
schema:
$ref: '#/components/schemas/21_forbidden'
/ca/api/corpora/{corpusId}/documents/{documentId}/original:
parameters:
- $ref: '#/components/parameters/01_corpus_id'
- $ref: '#/components/parameters/02_document_id'
get:
operationId: getDocumentOriginal
description: "-"
tags:
- Documents
summary: Downloads a corpus file in its original format (the format that was
uploaded). This method cannot be simulated in this online documentation.
responses:
"200":
description: '`OK`'
content:
application/octet-stream:
schema:
type: string
format: binary
description: The document was downloaded successfully in its original
format.
"401":
description: '`Unauthorized`'
"403":
description: '`Forbidden` (you need `view` permission).'
"404":
description: '`Not Found` (Html response).'
"405":
description: '`Method Not Allowed`'
/ca/api/corpora/{corpusId}/documents/{documentId}/plaintext:
parameters:
- $ref: '#/components/parameters/01_corpus_id'
- $ref: '#/components/parameters/02_document_id'
get:
operationId: getDocumentPlaintext
description: "-"
tags:
- Documents
summary: Retrieves 1KB of data in plaintext format. Can load more than 1KB.
responses:
"206":
description: '`Partial Content`'
content:
text/plain; charset=utf-8:
schema:
description: Document in plaintext format.
type: string
"401":
description: '`Unauthorized`'
"403":
description: '`Forbidden` (you need `view` permission).'
"404":
description: '`Not Found` (Html response).'
"405":
description: '`Method Not Allowed`'
"416":
description: '`Range Not Satisfiable`'
/ca/api/corpora/{corpusId}/documents/{documentId}/vertical:
parameters:
- $ref: '#/components/parameters/01_corpus_id'
- $ref: '#/components/parameters/02_document_id'
get:
operationId: getDocumentVertical
description: "-"
tags:
- Documents
summary: Retrieves 1KB of data in vertical format. Can load more than 1KB.
responses:
"206":
description: '`Partial Content`'
content:
text/plain; charset=utf-8:
schema:
description: Document in vertical format.
type: string
"401":
description: '`Unauthorized`'
"403":
description: '`Forbidden`'
"404":
description: '`Not Found` (Html response).'
"405":
description: '`Method Not Allowed`'
"416":
description: '`Range Not Satisfiable`'
/ca/api/corpora/{corpusId}/documents/{documentId}/expand_archive:
parameters:
- $ref: '#/components/parameters/01_corpus_id'
- $ref: '#/components/parameters/02_document_id'
post:
operationId: expandArchive
description: "-"
tags:
- Documents
summary: Expands a ZIP file. (if the corpus files were uploaded as a zip archive).
Expanding is not necessary for the corpus to work.(RPC)
requestBody:
description: ' In this documentation, an empty request is used mostly used
with the **RPC style** method where the content in a request is not needed
(in most cases). RPC style endpoints focus on performing **one action**
right (procedures, command) easier than **REST API**-based endpoints. It
is not as scalable as REST API style. RPC is mostly used with HTTP: GET
(to fetch information) and POST (to everything else) in CA api is it used
with POST HTTP method. '
content:
application/json:
schema:
$ref: '#/components/schemas/05_empty_request'
responses:
"200":
description: '`OK`'
content:
application/json:
schema:
$ref: '#/components/schemas/16_rpc_expand_archive'
"400":
description: '`Bad Request`'
content:
application/json:
schema:
$ref: '#/components/schemas/33_bad_request_13'
"403":
description: '`Forbidden (you need edit permission)`'
content:
application/json:
schema:
$ref: '#/components/schemas/21_forbidden'
"404":
description: '`Not Found` (Html response).'
/ca/api/corpora/{corpusId}/documents/{documentId}/cancel_job:
parameters:
- $ref: '#/components/parameters/01_corpus_id'
- $ref: '#/components/parameters/02_document_id'
post:
operationId: cancelDocumentJob
tags:
- Documents
summary: Cancels running task which is in direct relation to the document. (RPC)
description: An example task that can be canceled is `uploading file`.
requestBody:
description: ' In this documentation, an empty request is used mostly used
with the **RPC style** method where the content in a request is not needed
(in most cases). RPC style endpoints focus on performing **one action**
right (procedures, command) easier than **REST API**-based endpoints. It
is not as scalable as REST API style. RPC is mostly used with HTTP: GET
(to fetch information) and POST (to everything else) in CA api is it used
with POST HTTP method. '
content:
application/json:
schema:
$ref: '#/components/schemas/05_empty_request'
responses:
"200":
description: '`OK`'
content:
application/json:
schema:
$ref: '#/components/schemas/69_rpc_style'
"403":
description: '`Forbidden` (you need `edit` permission).'
content:
application/json:
schema:
$ref: '#/components/schemas/21_forbidden'
"404":
description: '`Not Found`'
content:
application/json:
schema:
$ref: '#/components/schemas/45_not_found_RPC'
/ca/api/corpora/{corpusId}/documents/{documentId}/get_progress:
parameters:
- $ref: '#/components/parameters/01_corpus_id'
- $ref: '#/components/parameters/02_document_id'
post:
operationId: getProgress
tags:
- Documents
summary: Shows the actual progress of the currently running task related to
documents. (RPC)
description: Used in tasks like `uploading` new files which will be used to
create or expand the corpora.
requestBody:
description: ' In this documentation, an empty request is used mostly used
with the **RPC style** method where the content in a request is not needed
(in most cases). RPC style endpoints focus on performing **one action**
right (procedures, command) easier than **REST API**-based endpoints. It
is not as scalable as REST API style. RPC is mostly used with HTTP: GET
(to fetch information) and POST (to everything else) in CA api is it used
with POST HTTP method. '
content:
application/json:
schema:
$ref: '#/components/schemas/05_empty_request'
responses:
"200":
description: '`OK`'
content:
application/json:
schema:
$ref: '#/components/schemas/06_get_progress'
"403":
description: '`Forbidden` (you need permission to `view` to the specified
corpus).'
content:
application/json:
schema:
$ref: '#/components/schemas/21_forbidden'
"404":
description: '`Not Found`'
content:
application/json:
schema:
$ref: '#/components/schemas/45_not_found_RPC'
/ca/api/corpora/{corpusId}/filesets:
parameters:
- $ref: '#/components/parameters/01_corpus_id'
- $ref: '#/components/parameters/19_compile_when_finished'
get:
operationId: getFileSets
description: "-"
tags:
- Filesets
summary: List of "subdirectories", i.e. unzipped archives or WebBootCaT runs
for a given corpus.
responses:
"200":
description: '`OK`'
content:
application/json:
schema:
type: object
properties:
data:
type: array
items:
$ref: '#/components/schemas/58_fileset'
"401":
description: '`Unauthorized`'
content:
application/json:
schema:
$ref: '#/components/schemas/20_unauthorized'
"403":
description: '`Forbidden` (you need permission to `upload` to the specified
corpus).'
content:
application/json:
schema:
$ref: '#/components/schemas/27_forbidden_normal'
"404":
description: '`Not Found`'
content:
application/json:
schema:
$ref: '#/components/schemas/57_not_found_404'
post:
operationId: createFileSet
tags:
- Filesets
summary: Creates new fileset by the web-crawler.
description: Used within creating or expanding corpus.
requestBody:
description: "Setting parameters to improve web-crawler accuracy. \n\n -\
\ `bl_max_total_kw` => **Blacklist max total keyword**. Means that web page\
\ or document will be discarded if it contains more words from the denylist\
\ (blacklist) than this limit. (integer) \n\n - `bl_max_unique_kw` => **Blacklist\
\ max unique keyword**. Means that web page or document will be discarded\
\ if it contains more unique words from the denylist (blacklist) than this\
\ limit. (integer) \n\n - `black_list` => A list (separated by whitespaces)\
\ of **blocked words**, words you don't want to see in your future corpus.\
\ (string) \n\n - `input_type` => Input types the web-crawler will works\
\ with. Example: **urls**. (string) \n\n - `max_cleaned_file_size` => Web\
\ pages and documents with a size **over** this limit (**in kB**) will be\
\ ignored. (integer) \n\n - `max_file_size` => Web pages and documents\
\ with a size **over** this limit (**in kB**) will be ignored. (integer)\
\ \n\n - `min_cleaned_file_size` => Web pages and documents **smaller**\
\ than this limit (**in kB**) after cleaning will be ignored. Cleaning involves\
\ conversion to plain text, removing boilerplate text (e.g. navigation menus,\
\ legal text, disclaimers and other repetitive content). (integer) \n\n\
\ - `min_file_size` => Web pages and documents with a **size below** this\
\ limit (**in kB**) will be ignored. (integer) \n\n - `name` => Texts will\
\ be organized into a corpus folder with this name. (string) \n\n - `seed_word`\
\ => A list of words according to which the URLs were chosen to be searched.\
\ (string) \n\n - `white_list` => A list (separated by whitespaces) of\
\ allowed words, words you want to see in your future corpus. (list of string)\
\ \n\n - `wl_min_kw_ratio` => **Whitelist minimal keywords ratio**. Means\
\ that web page or document will be included only if the percentage of allowlist\
\ words compared to total words is higher than this limit. (integer) \n\n\
\ - `wl_min_total_kw` => **Whitelist minimal total keywords**. Means that\
\ web page or document will be included only if it contains more words from\
\ the allowlist (whitelist) than this limit. (integer) \n\n - `wl_min_unique_kw`\
\ => **Whitelist minimal unique keywords**. Means that a web page or document\
\ will be included only if it contains more words from the allowlist (whitelist)\
\ than this limit. (integer)"
content:
application/json:
schema:
$ref: '#/components/schemas/13_filesets_creation'
required: true
responses:
"201":
description: '`Created`'
content:
application/json:
schema:
type: object
properties:
data:
$ref: '#/components/schemas/61_fileset_creation'
"400":
description: '`Bad Request`'
content:
application/json:
schema:
$ref: '#/components/schemas/34_bad_request_14'
"401":
description: '`Unauthorized`'
content:
application/json:
schema:
$ref: '#/components/schemas/20_unauthorized'
"403":
description: '`Forbidden` (you need permission to `upload` to the specified
corpus).'
content:
application/json:
schema:
$ref: '#/components/schemas/27_forbidden_normal'
"404":
description: '`Not Found`'
content:
application/json:
schema:
$ref: '#/components/schemas/57_not_found_404'
/ca/api/corpora/{corpusId}/filesets/{filesetId}:
parameters:
- $ref: '#/components/parameters/01_corpus_id'
- $ref: '#/components/parameters/06_fileset_id'
get:
operationId: getFileSet
description: "-"
tags:
- Filesets
summary: Returns information about a specific "subdirectory".
responses:
"200":
description: '`OK`'
content:
application/json:
schema:
type: object
properties:
data:
$ref: '#/components/schemas/58_fileset'
"401":
description: '`Unauthorized`'
content:
application/json:
schema:
$ref: '#/components/schemas/20_unauthorized'
"403":
description: '`Forbidden` (you need permission to `view`).'
content:
application/json:
schema:
$ref: '#/components/schemas/27_forbidden_normal'
"404":
description: '`Not Found`'
content:
application/json:
schema:
$ref: '#/components/schemas/57_not_found_404'
delete:
operationId: deleteFileSet
description: "-"
tags:
- Filesets
summary: Deletes subdirectory containing document (for creating corpus).
responses:
"204":
description: '`No Content`'
content: {}
"400":
description: '`Bad Request`'
content:
application/json:
schema:
$ref: '#/components/schemas/32_bad_request_12'
"401":
description: '`Unauthorized`'
content:
application/json:
schema:
$ref: '#/components/schemas/20_unauthorized'
"403":
description: '`Forbidden` (you need permission to `delete`).'
content:
application/json:
schema:
$ref: '#/components/schemas/27_forbidden_normal'
"404":
description: '`Not Found`'
content:
application/json:
schema:
$ref: '#/components/schemas/57_not_found_404'
/ca/api/corpora/{corpusId}/filesets/{filesetId}/cancel_job:
parameters:
- $ref: '#/components/parameters/01_corpus_id'
- $ref: '#/components/parameters/06_fileset_id'
post:
operationId: cancelFileSetJob
tags:
- Filesets
summary: Cancel running task. (RPC)
description: 'Example: cancel downloading data from websites by web-crawler.'
requestBody:
description: ' In this documentation, an empty request is used mostly used
with the **RPC style** method where the content in a request is not needed
(in most cases). RPC style endpoints focus on performing **one action**
right (procedures, command) easier than **REST API**-based endpoints. It
is not as scalable as REST API style. RPC is mostly used with HTTP: GET
(to fetch information) and POST (to everything else) in CA api is it used
with POST HTTP method. '
content:
application/json:
schema:
$ref: '#/components/schemas/05_empty_request'
responses:
"200":
description: '`OK`'
content:
application/json:
schema:
$ref: '#/components/schemas/69_rpc_style'
"401":
description: '`Unauthorized`'
content:
application/json:
schema:
$ref: '#/components/schemas/23_unauthorized_rpc'
"403":
description: '`Forbidden` (you need `upload` permission).'
content:
application/json:
schema:
$ref: '#/components/schemas/21_forbidden'
"404":
description: '`Not Found`'
content:
application/json:
schema:
$ref: '#/components/schemas/45_not_found_RPC'
/ca/api/corpora/{corpusId}/filesets/{filesetId}/get_progress:
parameters:
- $ref: '#/components/parameters/01_corpus_id'
- $ref: '#/components/parameters/06_fileset_id'
post:
operationId: getFileSetProgress
tags:
- Filesets
summary: Shows the actual progress of a running task related to filesets. (RPC)
description: A task like `downloading content from web` to create corpus with
web crawler.
requestBody:
description: ' In this documentation, an empty request is used mostly used
with the **RPC style** method where the content in a request is not needed
(in most cases). RPC style endpoints focus on performing **one action**
right (procedures, command) easier than **REST API**-based endpoints. It
is not as scalable as REST API style. RPC is mostly used with HTTP: GET
(to fetch information) and POST (to everything else) in CA api is it used
with POST HTTP method. '
content:
application/json:
schema:
$ref: '#/components/schemas/05_empty_request'
responses:
"200":
description: '`OK`'
content:
application/json:
schema:
$ref: '#/components/schemas/59_filesets_get_progress'
"403":
description: '`Forbidden` (you need `view` permission).'
content:
application/json:
schema:
$ref: '#/components/schemas/21_forbidden'
"404":
description: '`Not Found`'
content:
application/json:
schema:
$ref: '#/components/schemas/45_not_found_RPC'
/ca/api/languages:
get:
operationId: getLanguages
description: "-"
tags:
- Languages
summary: Retrieves a list of all languages.
responses:
"200":
description: '`OK`'
content:
application/json:
schema:
type: object
properties:
data:
type: array
items:
$ref: '#/components/schemas/63_language'
/ca/api/somefiles:
post:
operationId: uploadAligendDocuments
description: "-"
tags:
- Somefiles
summary: Upload aligned documents for creating parallel corpus.
requestBody:
description: Aligned multilingual file (mostly in '.tmx' file type).
content:
multipart/form-data; boundary={boundary}:
schema:
description: Aligned multilingual file (mostly in '.tmx' file type).
type: string
responses:
"201":
description: '`Created`'
content:
application/json:
schema:
$ref: '#/components/schemas/78_somefiles_post'
"400":
description: '`Bad Request`'
content:
application/json:
schema:
$ref: '#/components/schemas/40_bad_request_20'
/ca/api/somefiles/{somefileId}:
parameters:
- $ref: '#/components/parameters/08_somefile_id'
get:
operationId: getAlignedDocuments
description: "-"
tags:
- Somefiles
summary: Retrieves specific multilingual file metadata.
responses:
"200":
description: '`OK`'
content:
application/json:
schema:
$ref: '#/components/schemas/78_somefiles_post'
"404":
description: '`Not Found`'
content:
application/json:
schema:
$ref: '#/components/schemas/57_not_found_404'
put:
operationId: updateAlignedDocs
description: "-"
tags:
- Somefiles
summary: Updates multilingual file metadata.
requestBody:
description: " - `corpora` \n\n - `guessed_language_code` \n\n - `language_id`\
\ => Language iso-code. **ISO 639-1**. (string) \n\n - `name` => Language\
\ name in **English**. (string) "
content:
application/json:
schema:
$ref: '#/components/schemas/19_somefiles_put'
responses:
"200":
description: '`OK`'
content:
application/json:
schema:
type: object
properties:
data:
$ref: '#/components/schemas/12_corpora_single_full'
"400":
description: '`Bad Request`'
content:
application/json:
schema:
$ref: '#/components/schemas/33_bad_request_13'
"404":
description: '`Not Found`'
content:
application/json:
schema:
$ref: '#/components/schemas/57_not_found_404'
/ca/api/tagsets/{templateId}:
parameters:
- $ref: '#/components/parameters/03_template_id'
get:
operationId: getUserTemplate
description: "-"
tags:
- Templates
summary: Retrieves details of specified user template / tagset.
responses:
"200":
description: '`OK`'
content:
application/json:
schema:
$ref: '#/components/schemas/79_template'
"401":
description: '`Unauthorized`'
content:
application/json:
schema:
$ref: '#/components/schemas/20_unauthorized'
"403":
description: '`Forbidden` (you need permission to `read`).'
content:
application/json:
schema:
$ref: '#/components/schemas/27_forbidden_normal'
"404":
description: '`Not Found`'
content:
application/json:
schema:
$ref: '#/components/schemas/57_not_found_404'
put:
operationId: updateUserTemplate
description: "-"
tags:
- Templates
summary: Updates specified user template/tagset.
requestBody:
description: " - `id` => Alphanumeric **template/tagset ID**. The terms **tagset**\
\ and **templates** are interchangeable. (string) \n\n - `name` => Name\
\ of **template/tagset** file. (string) \n\n - `owner_id` => Unique numeric\
\ owner ID (usually you). If tagset/template is preloaded Null. (integer)\
\ \n\n - `owner_name` => Tagset/template owner name (usually you). If tagset/template\
\ is preloaded Null. (string) \n\n - `has_pipeline` => Vertical creation\
\ is supported. False for legacy templates. (boolean) \n\n - `has_tags`\
\ => Morphological tagging is supported. (boolean) \n\n - `has_lemmas`\
\ => Lemmatization is supported. (boolean) \n\n - `static_attributes` =>\
\ A list of attributes which can appear in corpus. \n\n - `structures`\
\ => A list of used structures. Examples \\<s>, \\<g>. \n\n - `tagsetdoc`\
\ => URL leading to template/tagset documentation. (string) \n\n - `content`\
\ => Content of tagset. (string) \n\n - `default_sketchgrammar_id` => Not\
\ ID, as you probably imagine, but filename of preselected sketchgrammar\
\ (.m4 format). (string) \n\n - `default_termgrammar_id` => Not ID, as\
\ you probably imagine, but filename of preselected sketchgrammar (.m4 format).\
\ (string) \n\n - `sharing` => List. \n\n - `users` => The ID of user\
\ you share template with. \n\n - `id` => The ID of group you share template\
\ with."
content:
application/x-www-form-urlencoded; charset=UTF-8:
schema:
$ref: '#/components/schemas/80_template_put'
responses:
"200":
description: '`OK`'
content:
application/json:
schema:
type: object
properties:
data:
$ref: '#/components/schemas/79_template'
"400":
description: '`Bad Request`'
content:
application/json:
schema:
$ref: '#/components/schemas/33_bad_request_13'
"401":
description: '`Unauthorized`'
content:
application/json:
schema:
$ref: '#/components/schemas/20_unauthorized'
"403":
description: '`Forbidden` (you need to be `owner` of the template).'
content:
application/json:
schema:
$ref: '#/components/schemas/27_forbidden_normal'
"404":
description: '`Not Found`'
content:
application/json:
schema:
$ref: '#/components/schemas/57_not_found_404'
delete:
operationId: deleteUserTemplate
description: "-"
tags:
- Templates
summary: Deletes user template.
responses:
"204":
description: '`No Content`'
content: {}
"400":
description: '`Bad Request`'
content:
application/json:
schema:
$ref: '#/components/schemas/33_bad_request_13'
"401":
description: '`Unauthorized`'
content:
application/json:
schema:
$ref: '#/components/schemas/20_unauthorized'
"403":
description: '`Forbidden` (you need to be `owner` of the template).'
content:
application/json:
schema:
$ref: '#/components/schemas/27_forbidden_normal'
"404":
description: '`Not Found`'
content:
application/json:
schema:
$ref: '#/components/schemas/57_not_found_404'
/ca/api/users/me/get_used_space:
post:
operationId: "getUsedSpace"
description: "-"
tags:
- Users
summary: Retrieves the user's current word space state (default 1 000 000 words).
(RPC)
requestBody:
description: ' In this documentation, an empty request is used mostly used
with the **RPC style** method where the content in a request is not needed
(in most cases). RPC style endpoints focus on performing **one action**
right (procedures, command) easier than **REST API**-based endpoints. It
is not as scalable as REST API style. RPC is mostly used with HTTP: GET
(to fetch information) and POST (to everything else) in CA api is it used
with POST HTTP method. '
content:
application/json:
schema:
$ref: '#/components/schemas/05_empty_request'
responses:
"200":
description: '`OK`'
content:
application/json:
schema:
$ref: '#/components/schemas/81_get_used_space'
"401":
description: '`Unauthorized`'
content:
application/json:
schema:
$ref: '#/components/schemas/23_unauthorized_rpc'
components:
parameters:
001_corpname:
in: query
name: corpname
schema:
type: string
required: true
description: Corpus name. To query your own corpus (e.g. username john, corpus
mycorpus), `use` value `user/john/mycorpus`.
example: preloaded/bnc2_tt21
002_usesubcorp:
in: query
name: usesubcorp
schema:
type: string
description: The name of the `subcorpus`. The `default` value `empty string`
refers to the entire corpus. An example for `preloaded/bnc2_tt21` can be `Written
Academic` or `1960-1974`.
003_gramrels:
in: query
name: gramrels
schema:
type: integer
enum:
- 0
- 1
description: A list of grammatical relations from the correspoding `sketch grammar`.
004_corpcheck:
in: query
name: corpcheck
schema:
type: integer
enum:
- 0
- 1
description: Results of the last corpcheck (if available in the compilation
log).
005_registry:
in: query
name: registry
schema:
type: integer
enum:
- 0
- 1
description: The content of the registry file (registry_dump and registry_text).
006_subcorpora:
in: query
name: subcorpora
schema:
type: integer
enum:
- 0
- 1
description: A parameter to obtain the list of subcorpora and their sizes (e.g.
number of tokens, words).
007_struct_attr_stats:
in: query
name: struct_attr_stats
schema:
type: integer
enum:
- 0
- 1
description: The lexicon sizes of structure attributes.
008_format:
in: query
name: format
schema:
type: string
enum:
- json
- xml
- csv
- tsv
- txt
- xls
description: The `format` of the output. `Empty value` is interpreted as `JSON`.
Not every endpoint supports all formats.
010_wlattr:
in: query
name: wlattr
schema:
type: string
example: lc
required: true
description: "Sets the corpus attribute you want to work with. Some corpora\
\ may have specific additional attributes.\n\n Basic examples:\n - word\n\
\ - lc\n - lemma\n - lemma_lc\n - lempos\n - lempos_lc\n - tag\n - pos\n\n\
\ For list of available word list attributes see **/ca/api/corpora/{corpusId}**"
011_wlnums:
in: query
name: wlnums
schema:
type: string
default: frq
enum:
- frq
- docf
- arf
description: 'The type of frequency. The values stand for: `frq` -> absolute
or raw frequency, `docf` -> document frequency. `arf` -> average reduced frequency.'
012_wlminfreq:
in: query
name: wlminfreq
schema:
type: integer
description: Sets the minimum frequency limit. Items with a lower frequency
will not be included.
013_wlmaxitems:
in: query
name: wlmaxitems
schema:
type: integer
description: Sets the number of items to be returned in the API response. It
is not limited for user corpora, in preloaded corpora can be some limitation.
This parameter is often used with wlpage to help with pagination in frontend
development.
example: 100
014_wlpat:
in: query
name: wlpat
schema:
type: string
description: Sets a regex to filter the results. Relevant only in a simple wordlist.
example: .*
015_wlsort:
in: query
name: wlsort
schema:
type: string
enum:
- frq
- docf
description: Sets the sorting of the results. The default is `frq`, i.e. by
absolute frequency. Docf means document frequency.
018_wlfile:
in: query
name: wlfile
schema:
type: string
description: Defines the allow list (formerly known as whitelist), the list
of words which should be included in the list. See also `wlblacklist`.
019_wlblacklist:
in: query
name: wlblacklist
schema:
type: string
description: A deny list (formerly known as blacklist) is a list of items that
should be excluded from the result. The values should be be separated by a
newline symbol (without commas between values). In the URL, the newline symbol
is `%0A`.
020_avattr:
in: query
name: avattr
schema:
type: string
required: true
example: bncdoc.alltyp
description: Selects a structure attribute (reffered to as text type in the
web interface). Corpora have different numbers structure attributes and their
values. You can find them in the response of the `corpus_info` method in `freqttattrs`
or `subcorpattrs` keys. Not all of them have attributes to show.
021_avpat:
in: query
name: avpat
schema:
type: string
description: A regex to filter the results. Empty string defaults to `.*` (match
everything).
022_avmaxitems:
in: query
name: avmaxitems
schema:
type: integer
description: The number of items to return.
023_avfrom:
in: query
name: avfrom
schema:
type: integer
description: The starting index from which to return the results.
025_lpos:
in: query
name: lpos
schema:
type: string
enum:
- -n
- -v
- -j
- -a
- -d
- -i
description: The part of speech of the lemma. The concrete values depend on
the corpus. If the corpus contains the `lempos` attribute and `lpos` is empty,
the result defaults to the most frequent part of speech of the lemma.
039_asyn:
in: query
name: asyn
schema:
type: integer
enum:
- 0
- 1
description: Switches the asynchronous processing on/off. ON = partial results
are returned as soon as the first page is filled with results. OFF = results
are returned only after the search is completed. Normally, ON is used in the
web interface and OFF when using the API.
040_json:
in: query
name: json
schema:
type: object
example:
{"concordance_query":[{"queryselector":"iqueryrow","iquery":"test"}]}
description: "An optinal way of **wraping parameters**. It is possible to send\
\ all parametres via this parameter only.\n\n The most frequent uses are:\n\
\n `queryselector`: To select the query type. Supported options are: **cqlrow**,\
\ **iqueryrow**, **lemmarow**, **charrow**, **phraserow**, **wordrow**. For\
\ more information see concordance_query parameters.\n\n `iquery`: Use with\
\ `iqueryrow`. \n\n `cql`: Use with `cqlrow`.\n\n `lemma`: Use with `lemmarow`.\n\
\n `lpos`: The part of speech of the lemma.\n\n `qmcase`: Sets the attribute\
\ to its lowercased version, i.e. the data are extracted from a lowercased\
\ version of the corpus. It used for case insensitive analysis. 1 = case sensitive),\
\ 0 = lowercased corpus/case insensitive).\n\n\n`char`: Use with charrow.\n\
\n `phrase`: Use with phraserow.\n\n `word`: Use with wordrow\n\n\n`name`:\
\ \n\n `pnfilter`: \n\n `inclkwic`: \n\n `filfpos`: \n\n `filtpos`: \n\n `desc`:\
\ \n\n `q`: \n\n"
041_q:
in: query
name: q
schema:
type: string
example: q[lemma="test"]
description: The CQL query. Regexes are supported for `lemma`, `phrase` and
`word` types. The `iquery` supports simplified wildcards (see concordance_query[iquery]).
If you decide to use the concordance_query in a json parameter, you do not
have to use this parameter.
044_fmaxitems:
in: query
name: fmaxitems
schema:
type: integer
default: 50
description: The number of items in one response.
045_freq_sort:
in: query
name: freq_sort
schema:
type: string
default: frq
enum:
- frq
- rel
description: The identifier of the sorted column. Use `frq` (default) to sort
by frequency.
046_cattr:
in: query
name: cattr
schema:
type: string
default: word
description: The (positional attribute)[https://www.sketchengine.eu/my_keywords/positional-attribute/]
(lemma, word form etc.) used in the computation.
047_cfromw:
in: query
name: cfromw
schema:
type: integer
default: -5
description: The left boundary of the window in which the collocations should
be identified. Defined by the token position left or right of KWIC.
048_ctow:
in: query
name: ctow
schema:
type: integer
default: 5
description: The right boundary of the window in which the collocations should
be identified. Defined by the token position left or right of KWIC.
049_cminfreq:
in: query
name: cminfreq
schema:
type: integer
default: 5
description: The minimum frequency of the token in the corpus.
050_cminbgr:
in: query
name: cminbgr
schema:
type: integer
default: 3
description: The minimum frequency of the token in the window defined by `cfromw`
and `ctow`.
051_cmaxitems:
in: query
name: cmaxitems
schema:
type: integer
default: 50
description: Sets the maximum number of items in the response.
052_cbgrfns:
in: query
name: cbgrfns
schema:
type: string
description: "Defines the types of statistics (association measures) to be computed.\n\
\n`t` -> T-score\n\n`m` -> MI\n\n`3` -> MI3\n\n`l` -> log likelihood\n\n`s`\
\ -> min. sensitivity\n\n`p` -> MI.log_f\n\n`r` -> relative freq.\n\n`f` ->\
\ absolute freq.\n\n`d` -> logDice.\n\n To send one value just type the value\
\ for example `t`. If you need to send more values write it as `[\"t\",\"\
m\",\"d\",\"3\",\"l\",\"s\",\"p\"]`."
053_csortfn:
in: query
name: csortfn
schema:
type: string
default: m
enum:
- t
- m
- "3"
- l
- s
- p
- r
- f
- d
description: Function according to which the result is sorted.
054_subcname:
in: query
name: subcname
schema:
type: string
required: true
description: Name of the subcorpus.
055_delete:
in: query
name: delete
schema:
type: integer
default: 0
enum:
- 0
- 1
description: Set to `1` if the corpus should be deleted. Only user subcorpora
can be deleted. Nothing will be deleted if left empty (default value == 0).
056_ref_corpname:
in: query
name: ref_corpname
schema:
type: string
required: true
description: Corpus name of the reference corpus, it must have the same processing
(the same attributes, the same term grammar).
057_simple_n:
in: query
name: simple_n
schema:
type: string
default: "1"
enum:
- "1"
- "0"
description: The smoothing parameter for (simple maths) [https://www.sketchengine.eu/documentation/simple-maths/].
058_attrs:
in: query
name: attrs
schema:
type: string
default: word
description: A list of comma-delimited attributes that are returned together
with each token. Other examples are:`word, lc, lemma, tag` etc..
060_alnum:
in: query
name: alnum
schema:
type: integer
default: 1
enum:
- 1
- 0
description: Limits the results to items containing only alphanumeric characters.
061_onealpha:
in: query
name: onealpha
schema:
type: integer
default: 1
enum:
- 1
- 0
description: Limits the results to items containing at least one alphanumberic
character. Words such as 16-year-old or 3D will be included.
062_max_keywords:
in: query
name: max_keywords
schema:
type: integer
default: 100
description: The number of items to be returned in the response.
063_ngrams_n:
in: query
name: ngrams_n
schema:
type: integer
enum:
- 2
- 3
- 4
- 5
description: The minimum n-gram length. Usually used with `ngrams_max_n` and
`usengrams`.
071_wlicase:
in: query
name: wlicase
schema:
type: integer
default: 0
enum:
- 1
- 0
description: Sets the case sensitivity of the corpus, i.e. the data are extracted
from a lowercased version of the corpus. It is used for case insensitive analysis.
Parameter "1" means case sensitivity, "0" means case insensitivity.
072_wlmaxfreq:
in: query
name: wlmaxfreq
schema:
type: integer
description: Sets the maximum frequency limit in the wordlist.
073_include_nonwords:
in: query
name: include_nonwords
schema:
type: integer
enum:
- 1
- 0
description: Includes, or excludes, nonwords in the in the result. Nonwords
are tokens which do not start with letter of the alphabet (e.g. numbers, punctuation).
The regex to match the nonwords is `[^[:alpha:]].*`. Certain specialized corpora
may use their own specific definition of nonwords.
074_random:
in: query
name: random
schema:
type: integer
enum:
- 1
- 0
description: Parameter that represents if the wordlist is created from the first
10 milions lines of corpus. One if yes, no if he wordlist is created from
the whole corpus.
deprecated: true
077_default_attr:
in: query
name: default_attr
schema:
type: string
description: The attribute applied to tokens in the query which do not have
an attribute specified explicitly as part of the query.
078_refs:
in: query
name: refs
schema:
type: string
example: =bncdoc.alltyp
description: The text type (metadata) for which statistics should be calculated
from the concordance. The default is `bncdoc.alltyp` (all available text types
are included). Text types (attributes and there values) differ between corpora).
You can find them in the response of `corpus_info` method in `freqttattrs`
or `subcorpattrs` keys. Not all of them have attributes to show.
079_attr_allpos:
in: query
name: attr_allpos
schema:
type: string
default: all
enum:
- kw
- all
description: Determines which tokens will be returned with additional attributes
defined in `attrs`. `kw` will add the attributes to the KWIC only. `all` will
return them with all tokens.
080_viewmode:
in: query
name: viewmode
schema:
type: string
enum:
- sen
- kwic
description: Switches between sentence view and the KWIC view. `sen` returns
complete sentences without trimming them. `kwic` returns the KWIC view with
the query in the centre and some context left and right.
081_cup_hl:
in: query
name: cup_hl
schema:
type: string
enum:
- q
- e
- c
- b
description: "Only used with error-annotated corpora. It determines what should\
\ be highlighted. It is set to 'q' for corpora without error annotation. Meaning\
\ of individual options:\n\n - `q` -> to higlight query result.\n\n - `e`\
\ -> to higlight errors.\n\n - `c` -> to highlight corrections.\n\n - `b`\
\ -> to highlight both erros and corrections.\n\n Example of such a corpus\
\ can be `preloaded/enwiki_error_sample_sentences`."
082_structs:
in: query
name: structs
schema:
type: string
example: s,g
description: A list of comma-delimited structures (=structure tags) that should
be included in the result.
083_fromp:
in: query
name: fromp
schema:
type: integer
example: 1
description: The number of the page that should be returned.
084_pagesize:
in: query
name: pagesize
schema:
type: integer
example: 20
description: The number of lines in the concordance.
085_kwicleftctx:
in: query
name: kwicleftctx
schema:
type: string
example: 100#
description: The size of the left context in KWIC view. Number of tokens.
086_kwicrightctx:
in: query
name: kwicrightctx
schema:
type: string
example: 100#
description: The size of the right context in KWIC view. Number of tokens.
087_ngrams_max_n:
in: query
name: ngrams_max_n
schema:
type: integer
enum:
- 2
- 3
- 4
- 5
- 6
description: The maximum n-gram length. The maximum is `6`.
088_usengrams:
in: query
name: usengrams
schema:
type: integer
enum:
- 0
- 1
description: Represent if n-grams should be extracted or just simple keywords.
089_wltype:
in: query
name: wltype
schema:
type: string
enum:
- simple
- struct_wordlist
example: simple
description: Parameter to set the format of ouput. Is it always set to `simple`,
for the `struct_wordlist` is another enpoint called `struct_wordlist`.
deprecated: true
090_wlstruct_attr1:
in: query
name: wlstruct_attr1
schema:
type: string
enum:
- word
- lemma
- tag
- lempos
description: Sets the attributes used for generating the wordlist. Up to 3 attributes
are allowed (see wlstruct_attr2 and wlstruct_attr3). Some corpora may contain
additional specific attributes.
required: true
091_relfreq:
in: query
name: relfreq
schema:
type: integer
enum:
- 1
- 0
description: Includes the relative frequency of each item in the result.
092_reldocf:
in: query
name: reldocf
schema:
type: integer
enum:
- 1
- 0
description: Calculate the document frequency for each item in the result. Must
be used with `addfreqs` set to `docf`.
093_wlpage:
in: query
name: wlpage
schema:
type: integer
description: To select page of the response. The number of items on the page
is specified by parameter wlmaxitems.
094_fpage:
in: query
name: fpage
schema:
type: integer
description: The number of the response batch (page). The number of items in
each batch is specified by `fmaxitems`.
095_group:
in: query
name: group
schema:
type: integer
enum:
- 1
- 0
description: If there are more attributes (e.g. m1attr, m2attr), the results
can be grouped by the first column/attribute.
096_showpoc:
in: query
name: showpoc
schema:
type: integer
enum:
- 1
- 0
description: Includes the percentage of the concordance in the result.
097_showreltt:
in: query
name: showreltt
schema:
type: integer
enum:
- 1
- 0
description: Includes relative in text types value in the result.
098_showrel:
in: query
name: showrel
schema:
type: integer
enum:
- 1
- 0
description: Includes the relative frequency in the result.
099_freqlevel:
in: query
name: freqlevel
schema:
type: integer
enum:
- 1
- 2
- 3
- 4
- 5
- 6
description: The number of attributes for which the frequencies should be counted.
100_ml1attr:
in: query
name: ml1attr
required: true
schema:
type: string
example: word
description: Used to count the frequency of positional attributes [attributes](https://www.sketchengine.eu/my_keywords/positional-attribute/)
or structure attributes (metadata/text types) of any token in the concordance.\n\n
A maximum of 6 attributes is allowed (e.g. ml2attr, ml3attr). At least one
attribute is required.
101_ml1ctx:
in: query
name: ml1ctx
required: true
schema:
type: string
example: -1<0
description: " Position of the selected attribute in the concordance. **Minus**\
\ means **left** context (-1<0). **Plus** means **right** context (6>0). **At\
\ least one attribute is required, the others are optional.** Every attribute\
\ (ml1attr, ml2attr. etc.) needs it's **own** context position (e.g. if 3\
\ attributes are selected three context position **needs to** be set ml1ctx,\
\ ml2ctx, ml3ctx).\n\n\n**Positions can be referenced as follows:**\n\n `integer\
\ number` - where **0** is the first token in **KWIC**, **-1** the rightmost\
\ token in the left context etc.\n\n `1:x` - where **x** is one of the corpus\
\ structures (e.g. \u201Cdoc\u201D or \u201Cs\u201D if the corpus has the\
\ particular markup). Its meaning is the first token in the structure, except\
\ when it is the right boundary of a range - then it is the last token in\
\ the structure. Also, other numbers can be used, e.g. -2:x, 3:x, etc. (-1\
\ is the same as 1 with meaning \u201Cstructure containing KWIC\u201D)\n\n\
\ `a<0` - where **a** stands for a position reference as described in the\
\ first two points with meaning '**a** positions before/after the firs KWIC\
\ position' (so this is equivalent to **a**)\n\n `a>0` - where **a** stands\
\ for the same position reference with meaning 'positions before/after the\
\ last KWIC position'\n\n in the previous two points, if **0** is substituted\
\ with a natural number **k**, it means 'before/after **k**-th collocation'\
\ instead of 'before/after KWIC'. Collocations are special token groups in\
\ the context, that can be added using positive filters (see below).\n\n\n\
`Ranges` can be referenced as a~b where **a**, **b** stand for token identifiers\
\ as above. Examples of positions and ranges:\n\n `-1<0` - rightmost token\
\ in the left context\n\n `3>0` - third token in right context\n\n `0>0` -\
\ last token in KWIC\n\n `0<0` - first token in KWIC\n\n `0<0~0>0` - range\
\ of KWIC\n\n `-1<0~1>0` - range of KWIC with one token from the left context\
\ and one from the right context\n\n `1:s` - first token in the sentence containing\
\ KWIC (or its first token)\n\n `1:s>0` - first token in the sentence containing\
\ KWIC (or its last token)\n\n `0<1` - first token of the first-added collocation.\n\
\n\n`Examples:`\n\n sword/ **1>0~3>0**\n\n sword/ **1>0~3>0**\n\n slemma/\
\ **0<0~0>0**\n\n sword/i **-1**\n\n sword/ **0** word/ir **-1<0** tag/r **-2<0**\n\
\n "
102_wlstruct_attr2:
in: query
name: wlstruct_attr2
schema:
type: string
enum:
- word
- lemma
- tag
- lempos
description: Additional optional attribute that should be included in the result.
103_wlstruct_attr3:
in: query
name: wlstruct_attr3
schema:
type: string
enum:
- word
- lemma
- tag
- lempos
description: Additional optional attribute that should be included in the result.
104_icase:
in: query
name: icase
schema:
type: integer
enum:
- 1
- 0
description: Switches to the `lc` attribute, i.e. the lower-cased version of
the corpus to allow case insensitive searching. `1` means that case sensitivity
is off, `0` means it is on.
111_pos:
in: query
name: pos
schema:
type: integer
example: 10336
description: The position of the first token of KWIC in the corpus.
112_nest_ngrams:
in: query
name: nest_ngrams
schema:
type: integer
enum:
- 1
- 0
description: N-grams which are sub-ngrams of a longer n-gram will be grouped
together with the longer n-gram. Nesting only works when a `ngrams_n` and
`ngrams_max_n` are different values.
115_attr:
in: query
name: attr
schema:
type: string
default: word
enum:
- lemma
- word
- TERM
- WSCOLLOC
description: "Switches between the computation of keywords, terms, key n-grams\
\ and key collocations. With keywords and n-grams, it also sets the attribute\
\ to be used for the computation.\n\n For keywords, set to the required attribute,\
\ usually `lc`, `word` or `lemma`.\n\n For n-grams, set to the required attribute\
\ and set `usengrams`, `ngrams_n` and `ngrams_max_n`.\n\n For terms, set the\
\ attribute to `TERM`.\n\n For collocations (word sketch triples, equivalent\
\ of using the Word Sketch with AS A LIST option in the web interace), set\
\ the attribute to `WSCOLLOC`. Consider using `wlpat`. "
118_res:
in: query
name: res
schema:
type: integer
example: 50
description: ''
119_normalize:
in: query
name: normalize
schema:
type: integer
example: 0
description: ''
120_fc_lemword_window_type:
in: query
name: fc_lemword_window_type
schema:
type: string
example: both
description: ''
121_fc_lemword_wsize:
in: query
name: fc_lemword_wsize
schema:
type: integer
example: 5
description: ''
122_fc_lemword_type:
in: query
name: fc_lemword_type
schema:
type: string
example: all
description: ''
123_fc_pos_wsize:
in: query
name: fc_pos_wsize
schema:
type: integer
example: 5
description: ''
124_fc_pos_type:
in: query
name: fc_pos_type
schema:
type: string
example: all
description: ''
125_fc_pos_window_type:
in: query
name: fc_pos_window_type
schema:
type: integer
example: 5
description: ''
127_concordance_query_queryselector:
in: query
name: concordance_query[queryselector]
schema:
type: string
enum:
- iquery
- cqlrow
- lemmarow
- charrow
- wordrow
- phraserow
description: The query type. You can send it directly or via the `json` parameter,
the results are the same.
128_concordance_query_iquery:
in: query
name: concordance_query[iquery]
schema:
type: string
description: "Only works when `queryselector` is set to `iqueryrow`. Type a\
\ word or phrase.\n\n These special wildcards are supported .\n\nUse the `asterisk\
\ (*)` for any number of unspecified characters. Use a `question mark (?)`\
\ for exactly one unspecified character. Use the `pipe (|)` to include more\
\ than one word or phrase. Use `two hyphens (--)` to find a word which is\
\ hyphenated, non-hyphenated or spelt as two separate words."
129_concordance_query_cql:
in: query
name: concordance_query[cql]
schema:
type: string
description: Only works when `queryselector` is set to `cqlrow`. Type the query
using the [cql](https://www.sketchengine.eu/documentation/corpus-querying/)
query language.
130_concordance_query_lemma:
in: query
name: concordance_query[lemma]
schema:
type: string
description: Only works when `queryselector` is set to `lemmarow`. Type the
lemma. Regex is supported.
131_concordance_query_char:
in: query
name: concordance_query[char]
schema:
type: string
description: Only works when `queryselector` is set to `charrow`. Type the characters
that the tokens should contain. Regex is supported.
132_concordance_query_word:
in: query
name: concordance_query[word]
schema:
type: string
description: Only works when `queryselector` is set to `wordrow`. Type the word
form. Regex is supported.
133_concordance_query_phrase:
in: query
name: concordance_query[phrase]
schema:
type: string
description: Only works when `queryselector` is set to `phraserow`. Type the
phrase. Regex is supported.
134_errcorr_switch:
in: query
name: errcorr_switch
schema:
type: string
enum:
- corr
- err
description: (Only for error-annotated corpora.) Determines what should be highlighted.
Corr means **correction** and err means **error**. An **example** of such
a corpus is `preloaded/enwiki_error_sample_sentences`.
135_cup_err_code:
in: query
name: cup_err_code
schema:
type: string
enum:
- .*
- lexicosemantic
- punct
- spelling
- style
- typographical
- unclassified
description: (Only for error-annotated corpora). Determines which error type
to higlight. An example of such a corpus is `preloaded/enwiki_error_sample_sentences`.
136_cup_err:
in: query
name: cup_err
schema:
type: string
description: (Only for error-annotated corpora.) An error token to search.
137_cup_corr:
in: query
name: cup_corr
schema:
type: string
description: (Only for error-annotated corpora.) A correction token to search.
138_hitlen:
in: query
name: hitlen
schema:
type: integer
example: 1
description: Only used by the web interface. Indicates the number of tokens
that should be highlighted in red.
139_detail_left_ctx:
in: query
name: detail_left_ctx
schema:
type: integer
example: 50
description: Size of the left context in tokens.
140_detail_right_ctx:
in: query
name: detail_right_ctx
schema:
type: integer
example: 50
description: Size of the right context in tokens.
141_ml2attr:
in: query
name: ml2attr
schema:
type: string
example: word
description: Used to count the frequency of positional attributes [attributes](https://www.sketchengine.eu/my_keywords/positional-attribute/).
Just like `ml1attr` but optional.
142_ml2ctx:
in: query
name: ml2ctx
schema:
type: string
example: -1<0
description: Position of the selected attribute in the concordance. Minus means
left context (-1<0). Plus means right context (6>0). Just like ml1ctx but
optional.
143_ml3attr:
in: query
name: ml3attr
schema:
type: string
example: word
description: Used to count the frequency of positional attributes [attributes](https://www.sketchengine.eu/my_keywords/positional-attribute/).
Just like `ml1attr` but optional.
144_ml3ctx:
in: query
name: ml3ctx
schema:
type: string
example: -1<0
description: Position of the selected attribute in the concordance. Minus means
left context (-1<0). Plus means right context (6>0). Just like ml1ctx but
optional.
145_ml4attr:
in: query
name: ml4attr
schema:
type: string
example: word
description: Used to count the frequency of positional attributes [attributes](https://www.sketchengine.eu/my_keywords/positional-attribute/).
Just like `ml1attr` but optional.
146_ml4ctx:
in: query
name: ml4ctx
schema:
type: string
example: -1<0
description: Position of the selected attribute in the concordance. Minus means
left context (-1<0). Plus means right context (6>0). Just like ml1ctx but
optional.
147_ml5attr:
in: query
name: ml5attr
schema:
type: string
example: word
description: Used to count the frequency of positional attributes [attributes](https://www.sketchengine.eu/my_keywords/positional-attribute/).
Just like `ml1attr` but optional.
148_ml5ctx:
in: query
name: ml5ctx
schema:
type: string
example: -1<0
description: Position of the selected attribute in the concordance. Minus means
left context (-1<0). Plus means right context (6>0). Just like ml1ctx but
optional.
149_ml6attr:
in: query
name: ml6attr
schema:
type: string
example: word
description: Used to count the frequency of positional attributes [attributes](https://www.sketchengine.eu/my_keywords/positional-attribute/).
Just like `ml1attr` but optional.
150_ml6ctx:
in: query
name: ml6ctx
schema:
type: string
example: -1<0
description: Position of the selected attribute in the concordance. Minus means
left context (-1<0). Plus means right context (6>0). Just like ml1ctx but
optional.
151_minfreq_extract_keywords:
in: query
name: minfreq
schema:
type: string
description: Sets the minimum frequency of the item.
example: auto
152_maxfreq_extract_keywords:
in: query
name: maxfreq
schema:
type: integer
description: Sets the maximum frequency of the item.
153_addfreqs:
in: query
name: addfreqs
schema:
type: string
default: docf
description: Represent what kind of frequnecy should be calculated. When used
with `reldocf` it is set to `docf` to calculate document frequency.
154_json_collx:
in: query
name: json
schema:
type: object
example:
{"concordance_query":[{"queryselector":"iqueryrow","iquery":"test"}],"cbgrfns":["t","m","3","l","s","p","r","f","d"]}
description: "An optinal way of **wraping parameters**. It is possible to send\
\ all relevant parametres via this parameter only. It is classic JSON format.\n\
\n The most frequent uses are:\n\n `queryselector`: To select the query type.\
\ Supported options are: **cqlrow**, **iqueryrow**, **lemmarow**, **charrow**,\
\ **phraserow**, **wordrow**.\n\n `iquery`: Use with `iqueryrow`. \n\n `cql`:\
\ Use with `cqlrow`.\n\n `lemma`: Use with `lemmarow`.\n\n `lpos`: The part\
\ of speech of the lemma.\n\n `qmcase`: Sets the attribute to its lowercased\
\ version, i.e. the data are extracted from a lowercased version of the corpus.\
\ It used for case insensitive analysis. 1 = case sensitive), 0 = lowercased\
\ corpus/case insensitive).\n\n `char`: Use with charrow.\n\n `phrase`: Use\
\ with phraserow.\n\n `word`: Use with wordrow\n\n `cbgrfns`: If you need\
\ to send more cbgrfnsDefines the types of statistics (association measures)\
\ to be computed. See example."
155_create:
in: query
name: create
schema:
type: integer
default: 0
enum:
- 0
- 1
description: Set to `1` if new subcorpus should be created. Subcorpus will not
be created if left empty (default value == 0).
156_q_subcorp:
in: query
name: q
schema:
type: string
example: >-
q=alemma,[lc="test" | lemma_lc="test"]
description: "Query for creating subcorpora from concordance. \n\nThe search\
\ criteria are specified within brackets following a prefix like `alemma`\
\ or `aword`. This prefix often indicates the type of linguistic search (e.g.,\
\ lemma-based, word-based). The criteria within the brackets can include checks\
\ for specific words, lemmas, parts of speech and more, using operators like\
\ | (OR), & (AND), and regular expressions. \n\nThe lists of available attributes,\
\ pos tags for specific corpus can be obtained via `/search/corp_info`.\n\n\
\n`Examples:`\n\n\n - Simple word or lemma search in the BNC corpus: \n\n\
\ **q=alemma,[lc=\"test\" | lemma_lc=\"test\"]**\n\n\n - Search for nouns\
\ with the lemma 'test' in a case-sensitive manner: \n\n **q=alemma,[lempos_lc=\"\
(test)-n\"]**\n\n\n - Search for verbs with the lemma 'test', case-insensitive:\
\ \n\n **q=alemma,[lempos=\"(test)-v\"]**\n\n\n - Searching for a specific\
\ phrase 'test' in a case-sensitive manner: \n\n **q=aword,[word=\"test\"\
]**\n\n\n - Searching for the numeral '1955': \n\n **q=alemma,[word=\"\
1955\" & tag=\"CD\"]**\n\n\n - Regex-based search for words containing the\
\ character 'h': \n\n **q=alemma,[word=\".\\*h.\\*\"]**\n\n\n - Complex\
\ search involving the lemma 'book' followed by up to three words, then a\
\ verb: \n\n **q=alemma,[lemma=\"book\"][]{1,3}[tag=\"V.\\*\"]**"
157_struct:
in: query
name: struct
schema:
type: string
example: doc
description: Which corpus structure should be used in new subcorpus. Used withim
concordance type of subcorpus. The lists of structures can be obtained via
`/search/corp_info`.
158_subcorp_id:
in: query
name: subcorp_id
schema:
type: string
required: true
description: The name of subcorpus you want to rename.
159_new_subcorp_name:
in: query
name: new_subcorp_name
schema:
type: string
required: true
description: A new name for the subcorpus.
160_json_subcorp:
in: query
name: json
schema:
type: object
example:
sca_bncdoc.alltyp:
- Spoken context-governed
description: "Used to specify text types for a subcorpus. Takes a JSON object\
\ as input, where the key-value pairs define the specific attributes. The\
\ attributes can vary depending on the corpus.\n\n When using the json parameter\
\ in a query, you can define a JSON object with one or more attributes. Each\
\ attribute can have a single value or an array of values.\n\n\nThe list of\
\ available text types for specific corpus can be obtained via `/search/corp_info`\
\ just add `sca_` in front the name (see examples).\n\n\n`Examples:`\n\n\n\
\ - To create a subcorpus based on a specific spoken text type from the BNC\
\ corpus: \n\n **{\"sca_bncdoc.alltyp\":[\"Spoken context-governed\"]}**\n\
\n\n - To filter texts from the BNC corpus that are both spoken context-governed\
\ and spoken demographic: \n\n **{\"sca_bncdoc.alltyp\":[\"Spoken context-governed\"\
,\"Spoken demographic\"]}**\n\n\n - To select texts from the BNC corpus from\
\ a specific time period (1960-1974): \n\n **{\"sca_bncdoc.alltim\":[\"\
1960-1974\"]}**\n\n\n - To create a subcorpus with texts from specific authors\
\ and time periods, along with regional specifications: \n\n **{\"sca_bncdoc.author\"\
: [\"Author1\",\"Author2\",...],\"sca_bncdoc.alltim\": [\"1985-1993\",\"1975-1984\"\
], \"sca_bncdoc.wripp\": [\"UK (unspecific)\",\"Ireland\"]}**\n\n\n - To filter\
\ texts from the Ententen corpus based on domain and topic: \n\n **{\"\
sca_doc.tld\":[\"org\",\"com\"], \"sca_doc.topic\": [\"arts\",\"beauty & fashion\"\
,\"cars & bikes\",\"culture & entertainment\"]}**\n\n\n - For a user-specific\
\ corpus, filtering based on document ID and filename: \n\n **{\"sca_doc.id\"\
:[\"file29173711\"],\"sca_doc.filename\":[\"Filename.pdf\"]}**"
161_ctx:
in: query
name: ctx
schema:
type: string
example: 0~0>0
description: " **Minus** means **left** context (-1<0). **Plus** means **right**\
\ context (6>0).\n\n\n**Positions can be referenced as follows:**\n\n `integer\
\ number` - where **0** is the first token, **-1** the rightmost token in\
\ the left context etc.\n\n `1:x` - where **x** is one of the corpus structures\
\ (e.g. \u201Cdoc\u201D or \u201Cs\u201D if the corpus has the particular\
\ markup). Its meaning is the first token in the structure, except when it\
\ is the right boundary of a range - then it is the last token in the structure.\
\ Also, other numbers can be used, e.g. -2:x, 3:x, etc. (-1 is the same as\
\ 1 with meaning \u201Cstructure containing searched word\u201D)\n\n `a<0`\
\ - where **a** stands for a position reference as described in the first\
\ two points with meaning '**a** positions before/after the first searched\
\ word position' (so this is equivalent to **a**)\n\n `a>0` - where **a**\
\ stands for the same position reference with meaning 'positions before/after\
\ the last searched word position'\n\n in the previous two points, if **0**\
\ is substituted with a natural number **k**, it means 'before/after **k**-th\
\ collocation' instead of 'before/after KWIC'. Collocations are special token\
\ groups in the context, that can be added using positive filters (see below).\n\
\n\n`Ranges` can be referenced as a~b where **a**, **b** stand for token identifiers\
\ as above. Examples of positions and ranges:\n\n `-1<0` - rightmost token\
\ in the left context\n\n `3>0` - third token in right context\n\n `0>0` -\
\ last token\n\n `0<0` - first token\n\n `0<0~0>0` - range\n\n `-1<0~1>0`\
\ - range with one token from the left context and one from the right context\n\
\n `1:s` - first token in the sentence containing searched word (or its first\
\ token)\n\n `1:s>0` - first token in the sentence containing searched word\
\ (or its last token)\n\n `0<1` - first token of the first-added collocation.\n\
\n\n`Examples:`\n\n sword/ **1>0~3>0**\n\n sword/ **1>0~3>0**\n\n slemma/\
\ **0<0~0>0**\n\n sword/i **-1**\n\n sword/ **0**\n\n word/ir **-1<0**\n\n\
\ tag/r **-2<0**\n\n "
162_diaattr:
in: query
name: diaattr
required: true
schema:
type: string
example: doc.month
description: A diachronic attribute to be selected. Available attributes **can
differ** in corpora. Examples can be **doc.year** or **doc.month**.
163_sse:
in: query
name: sse
schema:
type: string
enum:
- "1"
- "0"
required: true
description: '`1`: display results during calculation
`0`: display results after all data has been calculated (can take quite a
lot of time).'
164_threshold:
in: query
name: threshold
schema:
type: string
example: "0.05"
required: true
description: Determines which periods are included in the results. It signifies
the percentage above the average size, acting as a **limit**. When relative
frequency (rel_frq) surpasses this limit, it is discarded (moved to **removed_freqdist**
object).
165_json_freqdist:
in: query
name: json
schema:
type: object
example:
wordlist:
- the
- ','
- \.
- to
- and
- of
- a
- in
- '"'
- for
- that
- is
- it
- 'on'
- with
- as
- was
- i
- you
- at
- this
- be
- are
- from
- have
- by
- ':'
- he
- has
- '''s'
- \)
- but
- \(
- we
- an
- they
- will
- ''''
- not
- his
- said
- or
- their
- can
- n't
- more
- "\u2013"
- your
- one
- who
description: "An optinal way of **wraping parameters**. It is possible to send\
\ all relevant parametres via this parameter only. It is classic JSON format.\n\
\n `wordlist`: words for which the relative frequency should be counted.\n\
\n"
166_corpname_freqdist:
in: query
name: corpname
schema:
type: string
required: true
description: Corpus name. To query your own corpus (e.g. username john, corpus
mycorpus), `use` value `user/john/mycorpus`.
example: preloaded/trends_et_3
167_wordlist:
in: query
name: wordlist
description: 'A wordlist of words for which the relative frequency should be
counted. No exact example is here because it is already set in `JSON` parameter.\Example:
[''the'',''a'',''lion''].'
schema:
type: string
01_corpus_id:
name: corpusId
in: path
description: Numeric corpus ID. For corpora querying.
required: true
schema:
type: integer
02_document_id:
name: documentId
in: path
description: Document ID. For document querying.
required: true
schema:
type: integer
03_template_id:
name: templateId
in: path
description: 'Numerical template ID, but preloaded templates do not have ID
but you can query them by their name. Example: `UNIVERSAL_3`.'
required: true
schema:
type: string
05_logname:
name: logName
in: path
description: Name of log file. Name 'last.log' show the newest log for that
corpus.
example: last.log
required: true
schema:
type: string
06_fileset_id:
name: filesetId
in: path
description: ID of file subdirectories. If sets to 0 it will return top-level
folder of documents, so if you have a web corpora with folders web1 and web2
it will return web1.
required: true
schema:
type: integer
07_fileset_id_query:
name: fileset_id
in: query
description: ID of file subdirectory. **0** stands for default document directory
with name `upload`.
schema:
type: integer
08_somefile_id:
name: somefileId
in: path
description: Alphanumeric multilanguage file ID
required: true
schema:
type: string
09_format:
name: format
in: query
description: File format in which the corpus should be downloaded. Just three
formats are supported.
required: true
schema:
type: string
example: txt, vert, tmx
10_file_structure:
name: file_structure
in: query
description: 'The contents of each file will be enclosed in a XML like structure
of the specified name with the filename as its id attribute and the URL (if
available) as the url attribute. If empty document boundaries will be lost.
Example: `doc`.'
schema:
type: string
11_aligned:
name: aligned
in: query
description: Required when you want to download parallel corpora, **when format
== tmx.** Specify aligned corpus name.
schema:
type: string
18_wait_with_tagging:
name: wait_with_tagging
in: query
description: Delay tagging by given number of `seconds`.
schema:
type: integer
19_compile_when_finished:
name: compile_when_finished
in: query
description: Start corpus compiling after web-crawler finishes downloading content
from the internet.
schema:
type: integer
schemas:
01_corp_info:
type: object
properties:
wposlist:
description: A list of WPOS (`Word Part Of Speech`). Presented as a pair
of WPOS names and regular expression matching the WPOS tags.
type: array
items:
type: array
items:
type: string
example: >-
["adjective","J.*"]
description: At [tagsets](https://www.sketchengine.eu/tagsets/) you
can find the meaning of used POS tags for 55 languages. Make sure
you select the correct language.
lposlist:
description: A list of LPOS (`Lemma Part Of Speech`). Presented as a pair
of LPOS names and LPOS tags. Used in Concordance forms.
type: array
items:
type: array
items:
type: string
example: >-
["adjective","-j"]
description: Other examples can be [ "adverb", "-a" ], [ "conjunction",
"-c" ], [ "noun", "-n" ] etc. To see all pairs of LPOSLIST you execute
the endpoint via the `Try it Out button`.
wsposlist:
description: Has the same format as LPOSLIST but WSPOSLIST is used in Word
Sketch and Thesaurus forms.
type: array
items:
type: array
items:
type: string
example: >-
["adjective","-j"]
description: Same as in LPOSLIST. To see all pairs of WSPOSLIST you
execute the endpoint via the `Try it Out button`.'
attributes:
description: A list of objects containing detailed information about attributes
occuring in specified corpora.
type: array
items:
type: object
properties:
name:
type: string
example: lempos_lc
description: Name of attribute. Lempos_lc = Lemma part of speech lowercase.
id_range:
type: integer
example: 524493
description: The number of attributes of the given name in the corpus.
Each is counted only once even if it appears in corpus many times.
label:
type: string
example: lempos(lowercase)
description: An extra description.
dynamic:
type: string
example: utf8lowercase
description: Represents the rule according which the attribute should
be derived from the original attribute. The attribute `lempos_lc`
is derived from `lempos` to save disk space etc. [Read more](https://www.sketchengine.eu/documentation/corpus-configuration-file-all-features/#Dynamicattributes).
fromattr:
type: string
example: lempos
description: A name of attribute this attribute is derived from. Empty
string if the attribute is not derived from any.
structs:
description: A list of structures in the corpus.
type: array
items:
type: string
name:
type: string
example: British National Corpus (BNC)
description: The full name of the corpus.
lang:
type: string
example: English
description: The language of the corpus.
infohref:
type: string
example: https://www.sketchengine.eu/british-national-corpus/
description: An URL with more information about the corpus. Empty string
if none.
info:
type: string
example: "A balanced English corpus of samples of a written and spoken language\
\ of British English from the later part of the 20th century (1969\u2013\
1994). The spoken part is accompanied by audio recordings."
description: More information about the corpus.
encoding:
type: string
example: UTF-8
description: The used character encoding in the corpus.
tagsetdoc:
type: string
example: https://www.sketchengine.eu/english-treetagger-pipeline-2/
description: An URL with more information about the POS tagger used in the
corpus. Information like meanings of POS tags, comparition with other
tagsets for specified language etc.
defaultattr:
type: string
example: lc
description: The default attribute for the corpus. Usually `word` or `lc`.
starattr:
type: string
unicameral:
type: boolean
example: false
description: A boolean value indicating if the corpus is unicameral (not
distinguishing between upper and lower case).
righttoleft:
type: boolean
example: false
description: The order of writing in language of the used corpus.
errsetdoc:
type: string
wsattr:
type: string
example: lempos_lc
description: The attribute name for which word sketches are computed, e.g.
`lempos`.
wsdef:
type: string
example: /corpora/wsdef/english-penn_tt-3.1.wsdef.m4
description: A path to the `used` word sketches grammar definition file.
termdef:
type: string
example: /corpora/wsdef/english-penn_tt-terms-3.1.termdef.m4
description: A path to the term grammar definition file used in the corpus.
diachronic:
description: A list of diachronic subcorporas. Diachronic corpus is corpus
with timestamps to watch development of the language in time.
type: array
items:
type: string
example: bncdoc.year
aligned:
description: A list of aligned corpora names. `Example used here is from
different corpus because BNC corpus is not parallel.`
type: array
items:
type: array
items:
type: string
example: a_czech
description: Just the corpname of the aligned corpora. Parallel corpora
support just two languages (corpora).
aligned_details:
description: Is shown only if the specified corpus is parallel. A list of
dictionaries containing detailed information about each aligned subcorpus.
type: array
items:
type: object
properties:
name:
type: string
example: Example_1
description: The name of the aligned corpus.
language_name:
type: string
example: Czech
description: The language of the aligned corpus.
Wposlist:
type: array
items:
type: object
properties:
n:
type: string
example: noun
description: The name of the part of speech category
v:
type: string
example: k1.*
description: A regex matching the category
Lposlist:
type: array
items:
type: object
properties:
n:
type: string
example: noun
description: Name of part of speech category
v:
type: string
example: -n
description: The shortcut for better representation of a speech
category.
has_case:
type: boolean
description: Represent if the language of aligned corpus differentiates
between upper case and lower case.
has_lemma:
type: boolean
description: Represent if the language of aligned corpus has lemma
of not.
tagsetdoc:
type: string
example: https://www.sketchengine.eu/tagset-reference-for-czech
description: URL with closer information.
freqttattrs:
description: A list of attributes (text types) that will be used for Frequency.
Text types are metadata attached to the corpus structures. You can access
it via Sketch Engine dashboard -> Corpus Info -> Text Type Analysis.
type: array
items:
type: string
example: '["bncdoc.alltyp", "bncdoc.alltim", "bncdoc.author", "bncdoc.wripp",
"bncdoc.sporeg", "bncdoc.scgdom", "bncdoc.wridom", "bncdoc.spolog",
"event.desc", "bncdoc.wrimed", "bncdoc.year", "bncdoc.genre"]'
subcorpattrs:
description: A list of subcorpus attributes for the corpus.
type: array
items:
type: string
example: '["bncdoc.alltyp", "bncdoc.alltim", "bncdoc.author", "bncdoc.wripp",
"bncdoc.sporeg", "bncdoc.scgdom", "bncdoc.wridom", "bncdoc.spolog",
"event.desc", "bncdoc.wrimed", "bncdoc.year", "bncdoc.genre"]'
shortref:
type: string
example: =bncdoc.alltyp
description: The attribute of a structure to display as a default reference
in the left-hand column of a concordance. The syntax is like `=structure.attribute`,
e.g. `=doc.id` for displaying only the value of `doc.id`.
docstructure:
type: string
example: bncdoc
description: A structures that is considered as individual documents. Usually
`doc`.
newversion:
type: string
example: ''
description: Information about the new version of the corpus, if available.
Empty string if not.
structures:
description: A list of structures appearing in corpus.
type: array
items:
type: object
properties:
name:
type: string
example: head
description: The name of the structure.
label:
type: string
description: Just some extra information. Empty string if none.
attributes:
description: More detailed information.
type: array
items:
type: object
properties:
name:
type: string
example: rend
description: Name of attribute.
label:
type: string
example: ''
description: An extra information about attribute. Empty string
if none.
dynamic:
type: string
description: Dynamic (derived) attribute. Empty string if none.
[Read more](https://www.sketchengine.eu/documentation/corpus-configuration-file-all-features/#Dynamicattributes)
fromattr:
type: string
description: A name of attribute this attribute is derived from.
Empty string if none.
size:
type: integer
example: 5
description: Number of occurences.
size:
type: integer
example: 14868944
description: Number of occurences of `head` structure in this case.
is_error_corpus:
type: boolean
example: false
description: A boolean value indicating if the corpus is an error corpus
(not compiled etc.).
structctx:
type: string
example: ''
description: The structural context for the corpus. Empty string if none.
deffilerlink:
type: boolean
example: false
description: A boolean value indicating if the default filter link is enabled.
defaultstructs:
description: A list of default structures for the corpus.
type: array
items:
type: string
wsttattrs:
type: string
description: The text types for which the word highlights [Read more](https://www.sketchengine.eu/find-x-word-highlights/)
are computed.
terms_compiled:
type: boolean
example: true
description: A boolean value indicating if the terms file is compiled.
compiled:
type: string
example: 06/30/2017 07:34:25
description: A date of compilation in format `mm/dd/yyyy hh:mm:ss`.
gramrels:
type: array
items:
type: string
sizes:
type: object
properties:
tokencount:
type: string
example: '112345722'
wordcount:
type: string
example: '96134547'
doccount:
type: string
example: '4054'
description: Document counter.
parcount:
type: string
example: '1514906'
description: Paragraph counter.
sentcount:
type: string
example: '6052190'
description: Sentences counter.
normsum:
type: string
example: '96134547'
description: Wordcount after normalization.
alsizes:
description: A list of tuples containing sizes of aligned corpora.
type: array
items:
type: string
registry_dump:
type: string
description: The registry dump for the corpus (detailed information about
corpus setting), if the registry parameter is set.
registry_text:
type: string
description: The registry text for the corpus (detailed information about
corpus setting), if the registry parameter is set.
subcorpora:
type: array
items:
type: object
properties:
n:
type: string
example: Test
description: A name of subcorpus.
name:
type: string
example: Test
description: A name of subcorpus.
user:
type: integer
example: 1
description: Represent if subcorpora is created by user or not.
tokens:
type: integer
example: 271454
description: Number of tokens in subcorpus.
relsize:
type: number
example: 0.24162379765559744
description: The percentage of subcorpus size from total corpus size.
words:
type: integer
example: 232283
description: Number of words in subcorpus.
struct:
type: string
example: s
query:
type: string
example: Q:q[lc="dog" | lemma_lc="dog"]
api_version:
type: string
example: 5.62.3
description: Current API version.
manatee_version:
type: string
example: 2.36.7-SkE-2.219.2
description: Current version of Manatee.
request:
description: Just summary section of parsed query parameters used in this
endpoint call. These parameters are all documented in the beggining of
every endpoint box (after you unwrap the endpoint).
type: object
properties:
subcorpora:
type: string
example: '1'
struct_attr_stats:
type: string
example: '1'
corpname:
type: string
example: preloaded/bnc2_tt21
02_wordlist:
type: object
properties:
new_maxitems:
type: integer
example: 20000
wllimit:
type: integer
example: 1000
description: Word list limit, amount of words to be display.
lastpage:
type: integer
example: 0
note:
type: string
example: You are allowed to see only 1000 items.
description: An additional note to displayed results.
total:
type: integer
example: 165953
description: Number if displayed items (word - frequency).
totalfrq:
type: integer
example: 111680004
description: Sum of all frequencies.
items:
description: A result list.
type: array
items:
type: object
properties:
str:
type: string
example: the
description: The word to which the frequency has been calculated.
frq:
type: integer
example: 6054939
description: The word frequency.
relfreq:
type: number
example: 53895.59026
description: The relative word frequency. Relative frequency is a
way of expressing how often something happens compared to other
events or items in a given group.
wlattr_label:
type: string
example: word(lowercase)
frtp:
type: string
example: frequency
description: Frequency type. Other possible values can be `average reduced
frequency`, `document frequency`, `score`.
api_version:
type: string
example: 5.62.3
manatee_version:
type: string
example: 2.36.7-SkE-2.219.2
request:
description: Just summary section of parsed query parameters used in this
endpoint call. These parameters are all documented in the beggining of
every endpoint box.
type: object
properties:
wlminfreq:
type: string
example: '5'
random:
type: string
example: '0'
include_nonwords:
type: string
example: '1'
wltype:
type: string
example: simple
wlmaxitems:
type: string
example: '20000'
wlsort:
type: string
example: frq
wlicase:
type: string
example: '1'
wlpage:
type: string
example: '1'
reldocf:
type: string
example: '1'
wlpat:
type: string
example: .*
relfreq:
type: string
example: '1'
wlattr:
type: string
example: lc
wlmaxfreq:
type: string
example: '0'
corpname:
type: string
example: preloaded/bnc2_tt21
06_concordance:
type: object
properties:
Lines:
type: array
items:
type: object
properties:
toknum:
type: integer
example: 10336
hitlen:
type: integer
example: 1
Refs:
type: array
items:
type: string
example: Written books and periodicals
Tbl_refs:
type: array
items:
type: string
example: Written books and periodicals
Left:
type: array
items:
type: object
properties:
strc:
type: string
example: <s>
Kwic:
type: array
items:
type: object
properties:
str:
type: string
example: dogs
coll:
type: integer
example: 1
Right:
type: array
items:
type: object
properties:
str:
type: string
example: </s>
Links:
type: array
items:
type: string
linegroup:
type: string
example: _
linegroup_id:
type: integer
example: 0
fromp:
type: integer
example: 1
concsize:
type: integer
example: 12087
concordance_size_limit:
type: integer
example: 10000
Sort_idx:
type: array
items:
type: string
righttoleft:
type: boolean
example: false
Aligned_rtl:
type: array
items:
type: string
numofcolls:
type: integer
example: 0
finished:
type: integer
example: 1
fullsize:
type: integer
example: 12087
relsize:
type: number
example: 107.59
q:
type: array
items:
type: string
example: q[lc=\"dog\" | lemma_lc=\"dog\"]
Desc:
type: object
properties:
op:
type: string
example: Query
arg:
type: string
example: '[lc=\"dog\" | lemma_lc=\"dog\"]'
nicearg:
type: string
example: dog
rel:
type: number
example: 107.59
size:
type: integer
example: 12087
tourl:
type: string
example: q=q%5Blc%3D%22dog%22+%7C+lemma_lc%3D%22dog%22%5D
port:
type: integer
example: 0
gdex_scores:
type: array
items:
type: string
sc_strcts:
type: array
items:
type: array
items:
type: string
example: bncdoc
api_version:
type: string
example: 5.63.1
manatee_version:
type: string
example: 2.36.7-SkE-2.221
request:
type: object
properties:
concordance_query:
type: array
items:
type: object
properties:
queryselector:
type: string
example: iqueryrow
iquery:
type: string
example: dog
corpname:
type: string
example: preloaded/bnc2_tt21
kwicleftctx:
type: string
example: 100#
structs:
type: string
example: s,g
viewmode:
type: string
example: sen
attr_allpos:
type: string
example: all
fromp:
type: string
example: '1'
json:
type: string
example: '{\"concordance_query\":[{\"queryselector\":\"iqueryrow\",\"iquery\":\"dog\"}]}'
kwicrightctx:
type: string
example: 100#
refs:
type: string
example: =bncdoc.alltyp
cup_hl:
type: string
example: q
attrs:
type: string
example: word
pagesize:
type: string
example: '20'
07_subcorp:
type: object
properties:
subcname:
type: string
example: Australian domain .au
SubcorpList:
type: array
items:
type: object
properties:
n:
type: string
example: Australian domain .au
name:
type: string
example: Australian domain .au
user:
type: integer
example: 0
api_version:
type: string
example: 5.63.1
manatee_version:
type: string
example: 2.36.7-SkE-2.221
request:
type: object
properties:
corpname:
type: string
example: preloaded/ententen13_tt2_1
08_extract_keywords:
type: object
properties:
keywords:
type: array
items:
type: object
properties:
item:
type: string
example: "galsk\xFD"
score:
type: number
example: 2411.16
frq1:
type: integer
example: 2
frq2:
type: integer
example: 512
rel_frq1:
type: number
example: 4291.8457
rel_frq2:
type: number
example: 0.78041
query:
type: string
example: "[lemma=\\\"galsk\xFD\\\"]"
referece_corpus_name:
type: string
example: Slovak Web 2011 (skTenTen11)
reference_corpus_size:
type: integer
example: 656067998
reference_subcorpus_size:
type: integer
example: 656067998
subcorpus_size:
type: integer
example: 466
corpus_size:
type: integer
example: 466
total:
type: integer
example: 175
totalfrq1:
type: integer
example: 466
totalfrq2:
type: integer
example: 250525622
wllimit:
type: integer
example: 1000
note:
type: string
example: ''
api_version:
type: string
example: 5.63.1
manatee_version:
type: string
example: 2.36.7-SkE-2.221
request:
type: object
properties:
alnum:
type: string
example: '1'
maxfreq:
type: string
example: '0'
minfreq:
type: string
example: '1'
wlpat:
type: string
example: .*
attr:
type: string
example: lemma
keywords:
type: string
example: '1'
ref_corpname:
type: string
example: preloaded/sktenten11_rft1
simple_n:
type: string
example: '1'
k_attr:
type: string
example: lemma
include_nonwords:
type: string
example: '0'
reldocf:
type: string
example: :"0"
icase:
type: string
example: '1'
onealpha:
type: string
example: '1'
max_keywords:
type: string
example: '1000'
corpname:
type: string
example: user/matuskostka1/aaaaa_slovak
09_attr_vals:
type: object
properties:
query:
type: string
example: .*
description: The regular expression from query parameter `avpat`.
suggestions:
type: array
items:
type: string
example: "[ \"Cookson, Neil Andrew\", \u2026 ]"
description: Suggestions for avattr `bncdoc.author`.
no_more_values:
type: boolean
example: false
description: Represent if the `suggestion` list is complete.
api_version:
type: string
example: 5.63.1
manatee_version:
type: string
example: 2.36.7-SkE-2.221
request:
type: object
properties:
avpat:
type: string
example: .*
avmaxitems:
type: string
example: '15'
ajax:
type: string
example: '1'
corpname:
type: string
example: preloaded/bnc2_tt21
avfrom:
type: string
example: '0'
icase:
type: string
example: '1'
avattr:
type: string
example: bncdoc.author
10_collx:
type: object
properties:
Head:
type: array
items:
type: object
properties:
n:
type: string
example: Cooccurrence count
s:
type: string
example: f
style:
type: string
example: ' style="word-wrap: break-word; width: 5em;"'
Items:
type: array
items:
type: object
properties:
str:
type: string
example: Belvin
freq:
type: integer
example: 7
coll_freq:
type: integer
example: 5
Stats:
type: array
items:
type: object
properties:
s:
type: string
example: '2.64537'
n:
type: string
example: t
pfilter:
type: string
example: q=P-5+5+1+%5Bword%3D%22Belvin%22%5D
nfilter:
type: string
example: q=N-5+5+1+%5Bword%3D%22Belvin%22%5D
lastpage:
type: integer
example: 0
wllimit:
type: integer
example: 1000
concsize:
type: integer
example: 22685
Desc:
type: array
items:
type: object
properties:
op:
type: string
example: Query
arg:
type: string
example: '[lemma="test"]'
nicearg:
type: string
example: test
rel:
type: number
example: 202.22
size:
type: integer
example: 22685
tourl:
type: string
example: q=q%5Blemma%3D%22test%22%5D
api_version:
type: string
example: 5.63.1
manatee_version:
type: string
example: 2.36.7-SkE-2.223.6
request:
description: Just summary section of parsed query parameters used in this
endpoint call. These parameters are all documented in the beggining of
every endpoint box (after you unwrap the endpoint).
type: object
properties:
csortfn:
type: string
example: m
corpname:
type: string
example: preloaded/bnc2
q:
type: string
example: q[lemma="test"]
11_freqml:
type: object
properties:
fcrit:
type: string
example: fcrit=word%2Fe+-1%3C0+lemma%2Fe+-1%3C0
FCrit:
type: array
items:
type: object
properties:
fcrit:
type: string
example: word/e -1<0 lemma/e -1<0
Blocks:
type: array
items:
type: object
properties:
Head:
type: array
items:
type: object
properties:
n:
type: string
example: word
s:
type: integer
example: 0
id:
type: string
example: word/e
total:
type: integer
example: 1700
totalfrq:
type: integer
example: 12087
Items:
type: array
items:
type: object
properties:
Word:
type: array
items:
type: object
properties:
n:
type: string
example: the
frq:
type: integer
example: 2621
rel:
type: integer
example: 0
reltt:
type: integer
example: 0
norm:
type: integer
example: 0
fbar:
type: integer
example: 301
relbar:
type: integer
example: 0
freqbar:
type: integer
example: 0
pfilter:
type: string
example: ;q=p-1%3C0+-1%3C0+0+%5Bword%3D%22the%22%5D;q=p-1%3C0+-1%3C0+0+%5Blemma%3D%22the%22%5D
nfilter:
type: string
pfilter_list:
type: array
items:
type: array
items:
type: string
example: p-1<0 -1<0 0 [word="the"]
poc:
type: number
example: 21.684454372466284
fpm:
type: number
example: 23.329771292938062
paging:
type: integer
example: 1
concsize:
type: integer
example: 12087
fullsize:
type: integer
example: 14297
Desc:
type: array
items:
type: object
properties:
op:
type: string
example: Query
arg:
type: string
example: '[lc="dog" | lemma_lc="dog"]'
nicearg:
type: string
example: dog
rel:
type: number
example: 107.59
size:
type: integer
example: 12087
tourl:
type: string
example: q=q%5Blc%3D%22dog%22+%7C+lemma_lc%3D%22dog%22%5D
numofcolls:
type: integer
example: 0
hitlen:
type: integer
example: 1
wllimit:
type: integer
example: 1000
lastpage:
type: integer
example: 0
ml:
type: boolean
example: true
api_version:
type: string
example: 5.63.12
manatee_version:
type: string
example: 2.36.7-SkE-2.223.6
request:
description: Just summary section of parsed query parameters used in this
endpoint call. These parameters are all documented in the beggining of
every endpoint box.
type: object
properties:
concordance_query:
type: array
items:
type: object
properties:
queryselector:
type: string
example: iqueryrow
iquery:
type: string
example: dog
format:
type: string
example: json
fpage:
type: string
example: '1'
showpoc:
type: string
example: '1'
freqlevel:
type: string
example: '2'
group:
type: string
example: '1'
freq_sort:
type: string
example: freq
ml1ctx:
type: string
example: -1<0
showreltt:
type: string
example: '1'
ml2attr:
type: string
example: lemma
ml1attr:
type: string
example: word
ml2ctx:
type: string
example: -1<0
fmaxitems:
type: string
example: '5000'
corpname:
type: string
example: preloaded/bnc2_tt21
showrel:
type: string
example: '1'
12_struct_wordlist:
type: object
properties:
fcrit:
type: string
example: fcrit=lemma%2Fe+0+word%2Fe+0+lempos%2Fe+0
FCrit:
type: array
items:
type: object
properties:
fcrit:
type: string
example: lemma/e 0 word/e 0 lempos/e 0
Blocks:
type: array
items:
type: object
properties:
Head:
type: array
items:
type: object
properties:
n:
type: string
example: lemma
s:
type: integer
example: 0
id:
type: string
example: lemma/e
total:
type: integer
example: 77
totalfrq:
type: integer
example: 13931
Items:
type: array
items:
type: object
properties:
Word:
type: array
items:
type: object
properties:
n:
type: string
example: dog
frq:
type: integer
example: 6829
rel:
type: integer
example: 0
reltt:
type: integer
example: 0
norm:
type: integer
example: 0
fbar:
type: integer
example: 301
relbar:
type: integer
example: 0
freqbar:
type: integer
example: 0
pfilter:
type: string
example: ;q=p0+0+0+%5Blemma%3D%22dog%22%5D;q=p0+0+0+%5Bword%3D%22dog%22%5D;q=p0+0+0+%5Blempos%3D%22dog-n%22%5D
nfilter:
type: string
pfilter_list:
type: array
items:
type: array
items:
type: string
example: p0 0 0 [lemma="dog"]
poc:
type: number
example: 47.765265440302166
fpm:
type: number
example: 60.78558113676994
paging:
type: integer
example: 1
concsize:
type: integer
example: 14297
fullsize:
type: integer
example: 14297
Desc:
type: array
items:
type: object
properties:
op:
type: string
example: Query
arg:
type: string
example: '[lemma_lc="(dog.*)"]'
nicearg:
type: string
example: (dog.*)
rel:
type: number
example: 127.26
size:
type: integer
example: 14297
tourl:
type: string
example: q=q%5Blemma_lc%3D%22%28dog.%2A%29%22%5D
numofcolls:
type: integer
example: 0
hitlen:
type: integer
example: 1
wllimit:
type: integer
example: 1000
lastpage:
type: integer
example: 1
ml:
type: boolean
example: true
api_version:
type: string
example: 5.63.12
manatee_version:
type: string
example: 2.36.7-SkE-2.223.6
request:
description: Just summary section of parsed query parameters used in this
endpoint call. These parameters are all documented in the beggining of
every endpoint box.
type: object
properties:
wlmaxfreq:
type: string
example: '0'
wlpage:
type: string
example: '1'
random:
type: string
example: '0'
wlstruct_attr1:
type: string
example: lemma
wltype:
type: string
example: struct_wordlist
fmaxitems:
type: string
example: '20000'
wlpat:
type: string
example: (dog.*)
wlnums:
type: string
example: frq
wlattr:
type: string
example: lemma_lc
wlicase:
type: string
example: '1'
wlmaxitems:
type: string
example: '20000'
wlstruct_attr3:
type: string
example: lempos
relfreq:
type: string
example: '1'
include_nonwords:
type: string
example: '1'
wlsort:
type: string
example: frq
wlstruct_attr2:
type: string
example: word
corpname:
type: string
example: preloaded/bnc2_tt21
reldocf:
type: string
example: '1'
wlminfreq:
type: string
example: '5'
13_freq_distrib:
type: object
properties:
dots:
type: array
items:
type: object
properties:
frq:
type: integer
example: 64
description: ''
pos:
type: integer
example: 0
description: ''
beg:
type: integer
example: 72053
description: ''
end:
type: integer
example: 2475660
description: ''
granularity:
type: integer
example: 50
description: ''
api_version:
type: string
example: 5.63.12
manatee_version:
type: string
example: 2.36-7-SkE-2.223.6
request:
type: object
properties:
concordance_query:
type: array
items:
type: object
properties:
queryselector:
type: string
example: lemmarow
lemma:
type: string
example: cat
lpos:
type: string
example: -n
qmcase:
type: integer
example: 0
structs:
type: string
example: s,g
fc_lemword_type:
type: string
example: all
attrs:
type: string
example: word
json:
type: string
example: '{"concordance_query":[{"queryselector":"lemmarow","lemma":"cat","lpos":"-n","qmcase":false}]}'
res:
type: string
example: '50'
fc_lemword_window_type:
type: string
example: both
normalize:
type: string
example: '0'
format:
type: string
example: json
attr_allpos:
type: string
example: all
fc_pos_type:
type: string
example: all
fc_pos_wsize:
type: string
example: '5'
refs:
type: string
example: =bncdoc.alltyp
viewmode:
type: string
example: sen
lpos:
type: string
example: -n
corpname:
type: string
example: preloaded/bnc2_tt21
default_attr:
type: string
example: lemma
fc_lemword_wsize:
type: string
example: '5'
fc_pos_window_type:
type: string
example: both
14_fullref:
type: object
properties:
Refs:
type: array
items:
type: object
properties:
name:
type: string
example: Token number
id:
type: string
example: '#'
val:
type: string
example: '6270887'
bncdoc_id:
type: string
example: J1C
bncdoc_author:
type: string
example: ===NONE===
bncdoc_year:
type: string
example: ===NONE===
bncdoc_title:
type: string
example: '[Leeds United e-mail list]'
bncdoc_info:
type: string
example: '[Leeds United e-mail list]. Sample containing about 41810 words
of unpublished miscellanea (domain: leisure)'
bncdoc_allava:
type: string
example: Ownership has not been claimed
bncdoc_alltim:
type: string
example: 1985-1993
bncdoc_alltyp:
type: string
example: Written miscellaneous
bncdoc_genre:
type: string
example: W_email
u_who:
type: string
example: ''
s_audio:
type: string
example: ===NONE===
api_version:
type: string
example: 5.63.12
manatee_version:
type: string
example: 2.36.7-SkE-2.223.6
request:
type: object
properties:
corpname:
type: string
example: preloaded/bnc2_tt21
pos:
type: string
example: '6270887'
15_textypes_with_norms:
type: object
properties:
Blocks:
type: array
items:
type: object
properties:
Line:
type: array
items:
type: object
properties:
name:
type: string
example: bncdoc.alltyp
label:
type: string
example: Text type
attr_doc:
type: string
example: ''
attr_doc_label:
type: string
example: ''
Values:
type: array
items:
type: object
properties:
v:
type: string
example: Spoken context-governed
xcnt:
type: integer
example: 757
Normlist:
type: array
items:
type: object
properties:
n:
type: string
example: freq
label:
type: string
example: Document counts
api_version:
type: string
example: 5.63.12
manatee_version:
type: string
example: 2.36.7-SkE-2.223.6
request:
type: object
properties:
corpname:
type: string
example: preloaded/bnc2_tt21
16_widectx:
type: object
properties:
wrapdetail:
type: string
example: <p>
deletewrap:
type: boolean
example: true
content:
type: array
items:
type: object
properties:
str:
type: string
example: ', in Hungarian also means "majority of", "its belongings",
"its goods", "its best portion", a type of pork, and may also be
incorrectly identified as an agglutination of a frequent abbreviation
in mailing lists.'
class:
type: string
example: ''
leftlink:
type: string
example: pos=831745;detail_left_ctx=110;detail_right_ctx=50
rightlink:
type: string
example: pos=831745;detail_left_ctx=50;detail_right_ctx=110
pos:
type: integer
example: 831745
maxcontent:
type: integer
example: 200
api_version:
type: string
example: 5.63.12
manatee_version:
type: string
example: 2.36.7-SkE-2.223.6
request:
type: object
properties:
detail_left_ctx:
type: string
example: '50'
corpname:
type: string
example: preloaded/ententen21_tt31
hitlen:
type: string
example: '1'
pos:
type: string
example: '831745'
detail_right_ctx:
type: string
example: '50'
structs:
type: string
example: s,g
17_subcorpus_rename:
type: object
properties:
status:
type: string
example: OK
corpus:
type: string
example: preloaded/bnc2_tt31
subcorp_id2name:
type: object
properties:
test:
type: string
example: test_2
api_version:
type: string
example: 5.66.5
manatee_version:
type: string
example: 2.36.7-SkE-2.225.6
request:
type: object
properties:
subcorp_id:
type: string
example: test
new_subcorp_name:
type: string
example: test_2
corpname:
type: string
example: preloaded/bnc2_tt31
18_subcorp_info:
type: object
properties:
subcorp:
type: string
example: test_4
corpsize:
type: integer
example: 112338376
subcsize:
type: integer
example: 112338376
api_version:
type: string
example: 5.66.5
manatee_version:
type: string
example: 2.36.7-SkE-2.225.6
request:
type: object
properties:
subcname:
type: string
example: test_2
corpname:
type: string
example: preloaded/bnc2_tt31
19_freqdist:
type: object
properties:
lc:
type: string
example: the
freqdist:
type: object
properties:
2021-11:
description: The name is variable according selected period (wlattr).
type: object
properties:
frq:
type: integer
example: 679638
rel_frq:
type: number
format: float
example: 3022.91023457566
period_size:
type: number
format: float
example: 224829038
removed_freqdist:
type: object
properties:
2023-08:
description: The name is variable according selected period (wlattr).
type: object
properties:
frq:
type: integer
example: 0
rel_frq:
type: number
format: float
example: 0
period_size:
type: number
format: float
example: 429451774.0
average_norm:
type: number
format: float
example: 136780187.25
norm_limit:
type: number
format: float
example: 6839009.362500001
01_corpora_request:
description: Request for post method to set `name`, `language`, `tagset`, and
additional information to the corpus.
type: object
properties:
info:
type: string
description: The additional information for a newly created corpus.
example: Example description of user corpus.
language_id:
type: string
description: Language iso-code. `ISO 639-1`.
example: en
name:
type: string
description: Unique `corpus name` for a newly created corpus.
example: Example corpus
tagset_id:
type: string
description: Name of used tagset.
example: TT_ENG_V3
02_compile_request:
type: object
properties:
structures:
type: string
description: '`Structures` and `structure attributes` in corpus which should
be compiled. Usually: `all`.'
example: all
03_corpus_ids:
type: object
properties:
corpus_ids:
type: array
items:
type: integer
description: A list of `Corpus ID` of multilingual corpora.
example:
- 842464
- 842463
04_align_req:
type: object
properties:
alignstruct:
type: string
description: According to which structure the document should be aligned.
Usually, `/<s>`.
example: s
auto:
type: boolean
description: True, when documents are not compiled. Sketch Engine will align
them automatically.
example: true
corpus_ids:
type: array
items:
type: integer
description: A list of `Corpus ID` of multilingual corpus. ID's in example
does not exist.
example:
- 842464
- 842463
05_empty_request:
type: object
description: 'In this documentation, an empty request is used mostly used with
the `RPC style` method where the content in a request is not needed (in most
cases). RPC style endpoints focus on `performing` one action right (procedures,
command) easier than REST API-based endpoints. It is not as scalable as REST
API style. RPC is mostly used with HTTP: GET (to fetch information) and POST
(to everything else) in CA api is it used with POST HTTP method.'
07_corpus_update:
type: object
description: All possible paramaters that can be changed in user corpus. In
corpus update `you don't have to use all parameters`, just the parameters
you change.
properties:
expert_mode:
type: boolean
description: Set to `True` if you are hard-core.
example: false
name:
type: string
description: Corpus name. `Given by user`.
example: Example corpus 2
info:
type: string
description: Additional info about corpus.
example: Example description of user corpus 2
document_order:
description: Can be set to enforce document order within the corpus.
type: array
items:
type: integer
lang_filter:
type: boolean
example: true
structures:
description: Available structures or tags in the corpus. Structures like
`s` (sentence), `g` (glue), `doc` (document).
type: array
items:
type: object
properties:
name:
type: string
description: 'Structure name. Example: `s`'
attributes:
description: A list of used attributes in corpus.
type: array
items:
type: object
properties:
name:
type: string
description: The name of used attribute.
file_structure:
type: string
description: The structure in which individual documents should be wrapped.
Usually `doc`.
example: doc
onion_structure:
type: string
description: The structure for deduplication. Usually `p` (paragraph), `doc`
or `Null` (no deduplication).'
example: doc
docstructure:
type: string
description: Structure in which individual documents should be wrapped.
Usually `doc`.
example: doc
sketch_grammar_id:
type: string
description: "`Sketch grammar ID` (name of sketch grammar file). For sketch\
\ grammars querying. Sketch grammar is a series of rules written in the\
\ CQL query language that search for collocations in a text corpus and\
\ categorize them according to\_their grammatical relations. Example:\
\ `preloaded/english-penn_tt-3.3.wsdef.m4`."
example: preloaded/english-penn_tt-3.3.wsdef.m4
term_grammar_id:
type: string
description: '`Term grammar ID` (name of term grammar file). Term grammar
tells Sketch Engine which words and phrases should indentify as terms.
Example: `/corpora/wsdef/english-penn_tt-terms-3.1.termdef.m4`.'
example: preloaded/english-penn_tt-terms-3.1.termdef.m4
09_doc_put_req:
type: object
properties:
filename_display:
type: string
description: Name of documents.
id:
type: integer
description: Unique numeric `document ID` to identify individual documents.
inProgress:
type: boolean
description: Represents whether the currently edited document is in use.
isArchive:
type: boolean
description: Represents if the updated document is in a format like .zip
(created via some archive manager).
metadata:
type: object
description: Metadata of document. For example, additional `attributes and
values`.
parameters:
type: object
description: Parameters for plaintext extraction.
properties:
encoding:
type: string
description: Encoding standard of the document. Usually, `UTF-8`.
justext_stoplist:
type: string
description: Represent the list of unimportant words, in a specified
language, from an NLP point of view.
permutation:
type: array
items:
type: integer
description: Changing the order of columns (applies only to `type=vert`).
tmx_lang:
type: string
description: TMX (translation memory exchange). Language of document
used for parallel corpus creation.
tmx_struct:
type: string
description: Alignment structure to be used for multilingual documents,
`align` is the most used structure. Used within segment distinction,
which sentence is in which language and to put sentences with the
same meaning into one segment.
tmx_untranslated:
type: string
description: Placeholder for empty segments in multilingual documents.
The segments which have no counterpart in a second language of parallel
corpus.
type:
type: string
description: File format (.csv, .doc, .docx, .htm, .html etc.).
unlegalese:
type: boolean
description: Convert `all-caps` text to `normal case`.
temporary:
type: boolean
description: Is document temporary or not.
word_count:
type: integer
description: Total number of `words` (tokens minus punctuation etc.) in
document.
vertical_progress:
type: integer
description: Progress of `vertical file` creation.
vertical_error:
type: string
description: An error occured while creating the vertical file. If the creation
was succesfull the value is `Null`.
10_doc_preview:
type: object
properties:
auto_paragraphs:
type: string
description: Automatically insert paragraph breaks (`\<p>`) in place of
blank lines.
encoding:
type: string
description: Encoding standard of the document. Usually `UTF-8`.
justext_stoplist:
type: string
description: Represent the list of unimportant words, in a specified language,
from an NLP point of view.
permutation:
type: array
items:
type: integer
description: Changing the order of columns (applies only to `type=vert`).
tmx_lang:
type: string
description: TMX (translation memory exchange). Language of document used
for parallel corpus creation.
tmx_struct:
type: string
description: Alignment structure to be used for multilingual documents,
`align` is the most used structure. Used within segment distinction, which
sentence is in which language and to put sentences with the same meaning
into one segment.
tmx_untranslated:
type: string
description: Placeholder for empty segments in multilingual documents. The
segments which have no counterpart in a second language of parallel corpus.
type:
type: string
description: File format (`.csv`, `.doc`, `.docx`, `.htm`, `.html` etc.).
unlegalese:
type: boolean
description: Convert `all-caps` text to `normal case`.
11_doc_metadata:
type: array
items:
type: object
properties:
id:
type: integer
description: Unique numeric `document ID`.
metadata:
type: object
description: Pairs of `attribute_name`:`value`.
13_filesets_creation:
type: object
properties:
bl_max_total_kw:
type: integer
description: 'Stands for: `blacklist max total keyword`. Means that web
page or document will be discarded if it contains more words from the
denylist (blacklist) than this limit.'
bl_max_unique_kw:
type: integer
description: 'Stands for: `blacklist max unique keyword`. Means that web
page or document will be discarded if it contains more unique words from
the denylist (blacklist) than this limit.'
black_list:
type: string
description: A list (separated by whitespaces) of `blocked words`, words
you don't want to see in your future corpus.
input_type:
type: string
description: 'Input types the web-crawler will works with. Example: `urls`'
max_cleaned_file_size:
type: integer
description: Web pages and documents with a size `over` this limit (`in
kB`) will be ignored.
max_file_size:
type: integer
description: Web pages and documents with a size `over` this limit (`in
kB`) will be ignored.
min_cleaned_file_size:
type: integer
description: Web pages and documents `smaller` than this limit (`in kB`)
after cleaning will be ignored. Cleaning involves conversion to plain
text, removing boilerplate text (e.g. navigation menus, legal text, disclaimers
and other repetitive content).
min_file_size:
type: integer
description: Web pages and documents with a `size below` this limit (`in
kB`) will be ignored.
name:
type: integer
description: Texts will be organized into a corpus folder `with this name`.
seed_words:
description: A list of words according to which the `URLs` were chosen to
be searched.
type: array
items:
type: string
white_list:
type: string
description: A list (separated by whitespaces) of `allowed words`, words
you want to see in your future corpus.
wl_min_kw_ratio:
type: integer
description: 'Stands for: `whitelist minimal keywords ratio`. Means that
web page or document will be included only if the `percentage` of allowlist
words compared to total words is `higher` than this limit.'
wl_min_total_kw:
type: integer
description: 'Stands for: `whitelist minimal total keywords`. Means that
web page or document will be included only if it contains `more words`
from the `allowlist` (whitelist) than this limit.'
wl_min_unique_kw:
type: integer
description: 'Stands for: `whitelist minimal unique keywords`. Means that
a web page or document will be included only if it contains `more words`
from the `allowlist` (whitelist) than this limit.'
19_somefiles_put:
type: object
properties:
corpora:
type: object
properties:
guessed_language_code:
type: object
properties:
language_id:
type: string
description: Language iso-code. `ISO 639-1`.
name:
type: string
description: Language name in `English`.
03_corpora_list:
type: object
properties:
id:
description: Unique numeric `corpus ID` for corpus building.
type: integer
owner_id:
description: Unique numeric `owner ID` (usually you).
type: integer
owner_name:
description: Corpus `owner name` (usually you).
type: string
corpname:
description: Unique `corpus name` for corpus querying.
type: string
language_id:
description: Language iso-code. `ISO 639-1`.
type: string
language_name:
type: string
description: Language name in `English`.
tagset_id:
type: integer
description: '`Tagset ID`. Tagset is list of part-of-speech tags (POS tags)
for specified language. They are `preselected` to the most relevant one
and can be changed only in user corpora. `Tagsets` can be refered also
as `templates`.'
sketch_grammar_id:
type: string
description: "`Sketch grammar ID`. Sketch grammar is a series of rules written\
\ in the CQL query language that search for collocations in a text corpus\
\ and categorize them according to\_their grammatical relations."
term_grammar_id:
type: string
description: '`Term grammar ID`. Term grammar tells Sketch Engine which
words and phrases should indentify as terms.'
sizes:
type: object
description: Corpus sizes. `Null` if corpus is not compiled.
properties:
doccount:
type: integer
description: Total number of `documents` in corpus.
parcount:
type: integer
description: Total number of `paragraphs` in corpus.
sentcount:
type: integer
description: Total number of `sentences` in corpus.
wordcount:
type: integer
description: Total number of `words` (tokens minus punctuation etc.)
in corpus.
tokencount:
type: integer
description: Total number of `tokens` in corpus.
created:
type: string
description: Date and time of corpus creation in format `YYYY-MM-DD HH:MM:SS`.
needs_recompiling:
type: boolean
description: '`True` if corpus documents have been altered since last compilation.'
user_can_read:
type: boolean
description: Corpus can be queried a `specific user`. Ignore all corpora
where this is false.
user_can_refer:
type: boolean
description: Corpus can be used as a `reference corpus` even by anonymous
users.
user_can_upload:
type: boolean
description: Corpus is owned by you or shared with you. You can upload documents
to it.
user_can_manage:
description: Corpus is owned by you or shared with you with `full privileges`.
type: boolean
is_shared:
type: boolean
description: True if corpus is shared with other users.
new_version:
type: string
description: If set, the old corpus is deprecated in favor of a new one.
name:
type: string
description: Corpus name. `Given by user.`
info:
type: string
description: Additional info about corpus.
aligned:
description: List of other corpora (corpus ID) within the `same` multi-lingual
set (parallel corpus).
type: array
items:
type: string
docstructure:
type: string
description: Structure in which individual documents should be wrapped.
Usually `doc`.
04_corpora_single:
type: object
properties:
id:
description: Unique numeric `corpus ID` for corpus building.
type: integer
owner_id:
description: Unique numeric `owner ID` (usually you).
type: integer
owner_name:
description: Corpus `owner name` (usually you).
type: string
corpname:
description: Unique `corpus name` for corpus querying.
type: string
language_id:
description: Language iso-code. `ISO 639-1`.
type: string
language_name:
description: Language name in `English`.
type: string
sketch_grammar_id:
description: "`Sketch grammar ID` (name of sketch grammar file). Sketch\
\ grammar is a series of rules written in the CQL query language that\
\ search for collocations in a text corpus and categorize them according\
\ to\_their grammatical relations. Example: `preloaded/english-penn_tt-3.3.wsdef.m4`."
type: string
term_grammar_id:
description: '`Term grammar ID` (name of term grammar file). Term grammar
tells Sketch Engine which words and phrases should indentify as terms.
Example: `/corpora/wsdef/english-penn_tt-terms-3.1.termdef.m4`.'
type: string
sizes:
description: Corpus sizes. `Null` if corpus is not compiled.
type: object
properties:
doccount:
type: integer
description: Total number of `documents` in corpus.
parcount:
type: integer
description: Total number of `paragraphs` in corpus.
sentcount:
type: integer
description: Total number of `sentences` in corpus.
wordcount:
type: integer
description: Total number of `words` (tokens minus punctuation etc.)
in corpus.
tokencount:
type: integer
description: Total number of `tokens` in corpus.
created:
type: string
description: Date and time of corpus creation in format `YYYY-MM-DD HH:MM:SS`.
needs_recompiling:
description: True if corpus documents have been altered since last compilation.
type: boolean
user_can_read:
type: boolean
description: Corpus can be queried by a `specific user`. Ignore all corpora
where this is false.
user_can_refer:
type: boolean
description: Corpus can be used as a `reference corpus` even by anonymous
users.
user_can_upload:
type: boolean
description: Corpus is owned by you or shared with and you can upload documents
to it.
user_can_manage:
description: Corpus is owned by you or shared with you with `full privileges`.
type: boolean
is_shared:
type: boolean
description: '`True` if corpus is shared with other users.'
new_version:
type: string
description: If set, the old corpus is deprecated in favor of a new one.
name:
description: Corpus name. `Given by user`.
type: string
info:
description: Additional info about corpus.
type: string
aligned:
description: Other corpora within the `same` multi-lingual set (parallel
corpus).
type: array
items:
type: string
docstructure:
description: Structure in which individual documents should be wrapped.
Usually `doc`.
type: string
is_error_corpus:
description: Current state of corpus.
type: boolean
attrlist:
description: 'Attributes appearing in corpus documents. Attributes like:
`word`, `tag`, `lempos`, `pos`, `lemma`, etc.'
type: array
items:
type: string
tagset_id:
description: Tagset ID. Tagset is list of part-of-speech tags (POS tags)
for specified language. They are `preselected` to the most relevant one
and can be changed only in user corpora. The terms `tagset` and `templates`
are interchangeable.
type: integer
reference_corpus:
description: Default reference corpus for `keyword extraction`.
type: string
progress:
description: 'Compilation status: `0` if not compiled, `100` if compiled
successfully, `-1` if failed, otherwise in progress.'
type: integer
error:
description: Informs about last compilation error, if any error `None`.
type: string
document_count:
description: The amount of documents the corpus was build from.
type: integer
can_be_upgraded:
description: '`True` if corpus template is outdated and can be upgraded.
The terms `tagset` and `templates` are interchangeable.'
type: boolean
available_structures:
description: All `structures`/`attributes` that appear in corpus documents.
type: array
items:
type: object
properties:
name:
type: string
description: Structure name.
freq:
type: integer
description: Frequency of structure.
attributes:
type: array
items:
type: string
description: List of used attributes.
file_structure:
description: The structure in which individual documents should be wrapped.
Usually `doc`.
type: string
onion_structure:
description: The structure for deduplication. Usually `p` (paragraph) or
`Null` (no deduplication).'
type: string
expert_mode:
description: Set to `True` if you are hard-core.
type: boolean
document_order:
description: Not mandatory. Can be set to enforce document order within
the corpus.
type: array
items:
type: integer
use_all_structure:
description: Use `all` structures available in corpus.
type: boolean
structures:
description: Available `structures` or `tags` in the corpus. Structures
like `s` (sentence), `g` (glue), `doc` (document).
type: array
items:
type: object
properties:
name:
type: string
description: Structure name.
attributes:
description: A list of used attributes in corpus.
type: array
items:
type: object
properties:
name:
type: string
description: The name of used attribute.
05_can_be_compiled:
type: object
properties:
result:
type: object
properties:
can_be_compiled:
type: boolean
description: True, if the corpus does not contain any potential error,
which can break compilation.
reason:
type: string
description: 'Description of problem why it cannot be compiled. If none
Null. Example: `QUOTA_EXCEEDED` or `EMPTY`.'
error:
type: string
description: Unexpected server error. If none Null.
06_get_progress:
type: object
properties:
result:
type: object
properties:
progress:
type: integer
description: 'Compilation status: `0` if not compiled, `100` if compiled
successfully, `-1` if failed, otherwise in progress.'
error:
type: string
example: ""
description: Problem description. If none Null.
error:
type: string
example: ""
description: Unexpected server error. If none Null.
12_corpora_single_full:
type: object
properties:
id:
description: Unique numeric `corpus ID` for corpus building.
type: integer
owner_id:
description: Unique numeric `owner ID` (usually you).
type: integer
owner_name:
description: Corpus `owner name` (usually you).
type: string
corpname:
description: Unique `corpus name` for corpus querying.
type: string
language_id:
description: Language iso-code. `ISO 639-1`.
type: string
language_name:
description: Language name in `English`.
type: string
sketch_grammar_id:
description: "`Sketch grammar ID` (name of sketch grammar file). Sketch\
\ grammar is a series of rules written in the CQL query language that\
\ search for collocations in a text corpus and categorize them according\
\ to\_their grammatical relations. Example: `preloaded/english-penn_tt-3.3.wsdef.m4`."
type: string
term_grammar_id:
description: '`Term grammar ID` (name of term grammar file). Term grammar
tells Sketch Engine which words and phrases should indentify as terms.
Example: `/corpora/wsdef/english-penn_tt-terms-3.1.termdef.m4`.'
type: string
sizes:
description: Corpus sizes. `Null` if corpus is not compiled.
type: object
properties:
doccount:
type: integer
description: Total number of `documents` in corpus.
parcount:
type: integer
description: Total number of `paragraphs` in corpus.
sentcount:
type: integer
description: Total number of `sentences` in corpus.
wordcount:
type: integer
description: Total number of `words` (tokens minus punctuation etc.)
in corpus.
tokencount:
type: integer
description: Total number of `tokens` in corpus.
is_sgdev:
type: boolean
description: TODO
is_featured:
type: boolean
description: TOOD
access_level:
type: boolean
description: TODO
access_on_demand:
type: boolean
description: TODO
terms_of_use:
type: string
description: TODO
sort_to_end:
type: boolean
description: TODO
tags:
type: array
items:
type: string
description: TODO
created:
type: string
description: Date and time of corpus creation in format `YYYY-MM-DD HH:MM:SS`.
needs_recompiling:
description: True if corpus documents have been altered since last compilation.
type: boolean
user_can_read:
type: boolean
description: Corpus can be queried by a `specific user`. Ignore all corpora
where this is false.
user_can_refer:
type: boolean
description: Corpus can be used as a `reference corpus` even by anonymous
users.
user_can_upload:
type: boolean
description: Corpus is owned by you or shared with and you can upload documents
to it.
user_can_manage:
description: Corpus is owned by you or shared with you with `full privileges`.
type: boolean
is_shared:
type: boolean
description: '`True` if corpus is shared with other users.'
new_version:
type: string
description: If set, the old corpus is deprecated in favor of a new one.
name:
description: Corpus name. `Given by user`.
type: string
info:
description: Additional info about corpus.
type: string
wsdef:
description: 'Default word sketch definition. Example: `/corpora/wsdef/serbian-multext-rft1-1.0.wsdef.txt`.'
type: string
termdef:
description: Default term definition.
type: string
diachronic:
description: Is this corpus developing over time to keep track in vocabulary
changes, grammar and language usage. If yes what time period does the
corpus cover.
type: string
aligned:
description: Other corpora within the `same` multi-lingual set (parallel
corpus).
type: array
items:
type: string
docstructure:
description: Structure in which individual documents should be wrapped.
Usually `doc`.
type: string
is_error_corpus:
description: Current state of corpus.
type: boolean
attrlist:
description: 'Attributes appearing in corpus documents. Attributes like:
`word`, `tag`, `lempos`, `pos`, `lemma`, etc.'
type: array
items:
type: string
tagset_id:
description: Tagset ID. Tagset is list of part-of-speech tags (POS tags)
for specified language. They are `preselected` to the most relevant one
and can be changed only in user corpora. The terms `tagset` and `templates`
are interchangeable.
type: integer
reference_corpus:
description: Default reference corpus for `keyword extraction`.
type: string
progress:
description: 'Compilation status: `0` if not compiled, `100` if compiled
successfully, `-1` if failed, otherwise in progress.'
type: integer
error:
description: Informs about last compilation error, if any error `None`.
type: string
document_count:
description: The amount of documents the corpus was build from.
type: integer
can_be_upgraded:
description: '`True` if corpus template is outdated and can be upgraded.
The terms `tagset` and `templates` are interchangeable.'
type: boolean
available_structures:
description: All `structures`/`attributes` that appear in corpus documents.
type: array
items:
type: object
properties:
name:
type: string
description: Structure name.
freq:
type: integer
description: Frequency of structure.
attributes:
type: array
items:
type: string
description: List of used attributes.
file_structure:
description: The structure in which individual documents should be wrapped.
Usually `doc`.
type: string
onion_structure:
description: The structure for deduplication. Usually `p` (paragraph) or
`Null` (no deduplication).'
type: string
expert_mode:
description: Set to `True` if you are hard-core.
type: boolean
document_order:
description: Not mandatory. Can be set to enforce document order within
the corpus.
type: array
items:
type: integer
use_all_structure:
description: Use `all` structures available in corpus.
type: boolean
structures:
description: Available `structures` or `tags` in the corpus. Structures
like `s` (sentence), `g` (glue), `doc` (document).
type: array
items:
type: object
properties:
name:
type: string
description: Structure name.
attributes:
description: A list of used attributes in corpus.
type: array
items:
type: object
properties:
name:
type: string
description: The name of used attribute.
13_documents_get:
type: array
items:
type: object
properties:
id:
type: integer
description: Unique numeric `document ID` to identify individual documents
from which the corpus was created.
filename_display:
type: string
description: The name of the document.
parameters:
description: Parameters for plaintext extraction.
type: object
properties:
type:
type: string
description: 'File format. Possible formats: `.csv`, `.doc`, `.docx`,
`.htm`, `.html` etc..'
encoding:
type: string
description: Encoding standard of the document. Usually `UTF-8`.
tmx_lang:
type: string
description: TMX (translation memory exchange). Language of document
used for parallel corpus creation.
tmx_struct:
type: string
description: Alignment structure to be used for multilingual documents,
`align` is the most used structure. Used within segment distinction,
which sentence is in which language and to put sentences with the
same meaning into one segment.
unlegalese:
type: boolean
description: Convert `all-caps` text to `normal case`.
permutation:
type: array
items:
type: integer
description: Changing the order of columns (applies only to `type=vert`).
auto_paragraphs:
type: string
description: Automatically insert paragraph breaks (\<p>) in place
of blank lines.
justext_stoplist:
type: string
description: Represent the list of unimportant words, in a specified
language, from an NLP point of view.
tmx_untranslated:
type: string
description: Placeholder for empty segments in multilingual documents.
The segments which have no counterpart in a second language of parallel
corpus.
temporary:
type: boolean
description: Is document temporary or not.
word_count:
type: integer
description: Total number of `words` (tokens minus punctuation etc.) in
document.
vertical_progress:
type: integer
description: Progress of `vertical file` creation.
vertical_error:
description: An error occured while creating the vertical file. If the
creation was succesfull the value is `Null`.
type: string
metadata:
type: object
description: Metadata of document. For example, additional `attributes
and values`.
14_documents_post:
type: array
items:
type: object
properties:
id:
type: integer
description: Unique numeric `document ID` to identify individual documents
from which the corpus was created.
filename_display:
type: string
description: The name of the document.
parameters:
description: Parameters for plaintext extraction.
type: object
properties:
type:
type: string
description: 'File format. Possible formats: `.csv`, `.doc`, `.docx`,
`.htm`, `.html` etc..'
tmx_struct:
type: string
description: Alignment structure to be used for multilingual documents,
`align` is the most used structure. Used within segment distinction,
which sentence is in which language and to put sentences with the
same meaning into one segment.
tmx_untranslated:
type: string
description: Placeholder for empty segments in multilingual documents.
The segments which have no counterpart in a second language of parallel
corpus.
unlegalese:
type: boolean
description: Convert `all-caps` text to `normal case`.
justext_stoplist:
type: string
description: Represent the list of unimportant words, in a specified
language, from an NLP point of view.
tmx_lang:
type: string
description: TMX (translation memory exchange). Language of document
used for parallel corpus creation.
permutation:
type: array
items:
type: integer
description: Changing the order of columns (applies only to `type=vert`).
temporary:
type: boolean
description: Is document temporary or not.
word_count:
type: integer
description: Total number of `words` (tokens minus punctuation etc.) in
document.
vertical_progress:
type: integer
description: Progress of `vertical file` creation.
vertical_error:
description: An error occured while creating the vertical file. If the
creation was succesfull the value is `Null`.
type: string
metadata:
description: Metadata of document. For example, additional `attributes
and values`.
type: object
15_doc_preview:
type: object
properties:
result:
type: string
description: Showcase of few lines from the file the corpus was created
from (1kB).
error:
type: string
description: Unexpected server error. If none Null.
16_rpc_expand_archive:
type: object
properties:
result:
type: integer
description: Returns fileset ID.
error:
type: string
description: Unexpected server error. If none Null.
57_not_found_404:
type: object
properties:
error:
type: string
example: PreloadedCorpus/UserCorpus/Document/Tagset/Grammar/GdexConf matching
query does not exist.
45_not_found_RPC:
type: object
properties:
result:
type: boolean
description: Result of succesfully finished request otherwise Null.
error:
type: string
example: PreloadedCorpus/UserCorpus/Document/Tagset/Grammar/GdexConf/SiteLicence
matching query does not exist.
17_bad_request_RPC_1:
type: object
properties:
result:
type: boolean
description: Result of succesfully finished request otherwise Null.
example: true
error:
type: string
description: 'Examples: `READ_ONLY`, `INVALID_CORPUS_IDS`. You do not have
permissions for it or you inputted IDs are not correct.'
28_bad_request_RPC_8:
type: object
properties:
result:
type: boolean
description: Result of succesfully finished request otherwise Null.
error:
type: string
description: 'Examples: `QUOTA_EXCEEDED`, `READ_ONLY`, `INVALID_CORPUS_IDS`,
`CORPUS_BUSY`.'
29_bad_request_RPC_9:
type: object
properties:
result:
type: boolean
description: Result of succesfully finished request otherwise Null.
error:
type: string
description: 'Examples: `QUOTA_EXCEEDED`, `READ_ONLY`.'
30_bad_request_10:
type: object
properties:
error:
type: string
description: 'Examples: `QUOTA_EXCEEDED`, `READ_ONLY`, `CORPUS_BUSY`, `DAILY_TAGGING_EXCEEDED`,
`INVALID_URL`, `NO_DATA`.'
31_bad_request_11:
type: object
properties:
error:
type: string
description: 'Examples: `READ_ONLY`, `CORPUS_BUSY`, `INVALID_METADATA`.'
32_bad_request_12:
type: object
properties:
error:
type: string
description: 'Examples: `READ_ONLY`, `CORPUS_BUSY`.'
33_bad_request_13:
type: object
properties:
error:
type: string
description: 'Examples: `READ_ONLY`.'
34_bad_request_14:
type: object
properties:
error:
type: string
description: 'Examples: `READ_ONLY`, `QUOTA_EXCEEDED`, `DAILY_TAGGING_EXCEEDED`,
`CORPUS_BUSY`.'
40_bad_request_20:
type: object
properties:
error:
type: string
description: 'Examples: `READ_ONLY`, `QUOTA_EXCEEDED`, `DAILY_TAGGING_EXCEEDED`,
`NO_DATA`.'
27_forbidden_normal:
type: object
properties:
error:
type: string
description: 'Example: `Permission denied`. You do not have required permissions
for specified corpus, document, template or other stuff. Permissions like
(read, manage, edit, delete, superuser, etc.).'
21_forbidden:
type: object
properties:
result:
type: boolean
description: Result of succesfully finished request otherwise Null.
error:
type: string
description: 'Example: `Permission denied`. You do not have required permissions
for specified corpus, document, template or other stuff. Permissions like
(read, manage, edit, delete, superuser, etc.).'
20_unauthorized:
type: object
properties:
error:
type: string
description: 'Exampple: `Unauthorized`. You need to authorize first, use
API key from Sketch Engine.'
23_unauthorized_rpc:
type: object
properties:
result:
type: boolean
description: Result of succesfully finished request otherwise Null.
error:
type: string
description: 'Example: `Unauthorized`. You need to authorize first, use
API key from Sketch Engine.'
58_fileset:
type: object
properties:
progress:
type: integer
description: 'Fileset creation status: `0` if not started, `100` if finished
succesfully, -1 if failed, otherwise in progress. Example: downloading
content for corpus creation from the Internet.'
time_elapsed:
type: integer
description: Duration of action with filesets (in seconds).
error:
type: string
description: Description of problem. If none Null.
id:
type: integer
description: Fileset ID.
name:
type: string
description: Fileset name. `Given by user (except the main one with ID =
0).`
word_count:
type: integer
description: Total number of `words` (tokens minus punctuation etc.) in
document.
web_crawl:
type: object
properties:
input_type:
type: string
description: '`Source URL` from where the words were downloaded/extracted:
website, documents...'
seed_words:
type: array
items:
type: string
description: A `List of words` acording which the web-crawler will
search and gather data from URLs containing them.
urls:
type: array
items:
type: string
description: A `List of URLs` to be searched by web-crawler.
site:
type: array
items:
type: string
description: Specific website to be searched by web-crawler.
data_downloaded:
type: integer
description: The amount of data `downloaded` by a web-crawler to create
corpus.
remaining_files_count:
type: integer
description: Counter of files found by web-crawler during crawling,
`waiting` to be processed.
processed_files_count:
type: integer
description: Counter of `already processed` files.
unprocessed_files_count:
type: integer
description: Counter of files which `cannot` be processed because `invalid
content type`, `size`, `duplication` etc..
invalid_content_types_count:
type: integer
description: Counter of files containing content like `navigation links`,
`advertisement`, `headers`, `footers` etc..
unable_to_convert_count:
type: integer
description: Counter for files whose format cannot be converted to one
of the supported formats.
duplicate_count:
type: integer
description: Counter for files with repeating content.
time_elapsed:
type: integer
description: Duration of words gathering with web-crawler (in seconds).
average_file_processing_time:
type: integer
description: Average time to process single file (in seconds).
59_filesets_get_progress:
type: object
properties:
result:
type: object
properties:
progress:
type: integer
description: 'Fileset creation status: `0` if not started, `100` if
finished succesfully, -1 if failed, otherwise in progress. Example:
downloading content for corpus creation from the Internet.'
time_elapsed:
type: number
format: float
description: Duration of action with filesets (in second).
error:
type: string
description: Description of problem why it cannot be done.
word_count:
type: integer
description: Amount of words(tokens minus punctuation etc.) downloaded
by web-crawler.
error:
type: string
description: Unexpected server error.
61_fileset_creation:
type: object
properties:
progress:
type: integer
description: 'Fileset creation status: `0` if not started, `100` if finished
succesfully, -1 if failed, otherwise in progress. Example: downloading
content for corpus creation from the Internet.'
time_elapsed:
type: integer
description: Duration of action with filesets (in seconds).
error:
type: string
description: Description of problem. If none Null.
id:
type: integer
description: Fileset ID.
name:
type: string
description: Fileset name. `Given by user (except the main one with ID =
0).`
word_count:
type: integer
description: Total number of `words` (tokens minus punctuation etc.) in
document.
web_crawl:
type: object
properties:
input_type:
type: string
description: '`Source URL` from where the words were downloaded/extracted:
website, documents...'
seed_words:
type: array
items:
type: string
description: A `List of words` acording which the web-crawler will
search and gather data from URLs containing them.
urls:
type: array
items:
type: string
description: A `List of URLs` to be searched by web-crawler.
site:
type: array
items:
type: string
description: Specific website to be searched by web-crawler.
data_downloaded:
type: integer
description: The amount of data `downloaded` by a web-crawler to create
corpus.
remaining_files_count:
type: integer
description: Counter of files found by web-crawler during crawling,
`waiting` to be processed.
processed_files_count:
type: integer
description: Counter of `already processed` files.
unprocessed_files_count:
type: integer
description: Counter of files which `cannot` be processed because `invalid
content type`, `size`, `duplication` etc..
invalid_content_types_count:
type: integer
description: Counter of files containing content like `navigation links`,
`advertisement`, `headers`, `footers` etc..
unable_to_retrieve_count:
type: integer
description: Cannot return count.
invalid_size_count:
type: integer
description: Counter for sizes that are bigger or smaller as defined
limits (max_file_size, min_file_size).
invalid_cleaned_size_count:
type: integer
description: Counter for sizes that are bigger or smaller as defined
limits (max_file_size, min_file_size).
keywords_filter_applied_count:
type: integer
description: Amounth of filter usage.
unable_to_convert_count:
type: integer
description: Counter for files whose format cannot be converted to one
of the supported formats.
duplicate_count:
type: integer
description: Counter for files with repeating content.
time_elapsed:
type: integer
description: Duration of words gathering with web-crawler (in seconds).
average_file_processing_time:
type: integer
description: Average time to process single file (in seconds).
63_language:
type: object
properties:
id:
type: string
description: Language iso-code. `ISO 639-1`.
name:
type: string
description: Language name in `English`.
autonym:
type: string
description: Language name in that language.
default_tagset_id:
type: string
description: '`Tagset ID.` Tagset is list of part-of-speech tags (POS tags)
for specified language. Defaulty preselected to the most relevant one.
For user corpora can be changed. The terms `tagset` and `templates` are
interchangeable.'
reference_corpus:
type: string
description: Default `reference` corpus.
has_term_grammar:
type: boolean
description: True if `term extraction` is supported.
script:
type: string
description: 'Used script. Example: `Latin`, `Cyrillic`, etc.'
69_rpc_style:
type: object
properties:
result:
type: boolean
description: Represent whether request was finished successfully or not.
error:
type: string
description: 'Unexpected server error. Example: `QUOTA_EXCEEDED`. If none
Null.'
78_somefiles_post:
type: object
properties:
data:
type: object
properties:
id:
type: string
description: An alphanumeric `somefile ID`.
name:
type: string
description: Name of `multilingual file`.
file_type:
type: string
description: 'File type of multilingual file: `.tmx`, .`.xlsx`, etc.'
owner_id:
type: integer
description: Unique numeric `owner ID` (usually you).
temporary:
type: boolean
description: Is document temporary or not.
encoding:
type: string
description: Encoding standard of the document. Usually `UTF-8`.
guessed_languages:
type: object
description: 'An object of automatically guessed languages of inserted
files during multilingual corpus creation. Maximum: `2`, because Sketch
Engine support multilingual corpora only from 2 languages yet.'
properties:
language_1:
type: string
language_2:
type: string
79_template:
type: object
properties:
id:
type: string
description: Alphanumeric `template/tagset ID`. The terms `tagset` and `templates`
are interchangeable.
name:
type: string
description: Name of `template/tagset file`.
owner_id:
type: integer
description: Unique numeric `owner ID` (usually you). If tagset/template
is preloaded `Null`.
owner_name:
type: string
description: Tagset/template `owner name` (usually you). If tagset/template
is preloaded `Null`.
has_pipeline:
type: boolean
description: Vertical creation is supported. False for legacy templates.
has_tags:
type: boolean
description: Morphological tagging is supported.
has_lemmas:
type: boolean
description: Lemmatization is supported.
static_attributes:
type: array
description: A list of attributes which can appear in corpus.
items:
type: string
structures:
type: array
description: A list of used structures. Examples `<s>`, `<g>`.
items:
type: string
tagsetdoc:
type: string
description: '`URL` leading to template/tagset documentation.'
content:
type: string
description: Content of tagset.
default_sketchgrammar_id:
type: string
description: Not ID, as you probably imagine, but filename of preselected
sketchgrammar (`.m4` format).
default_termgrammar_id:
type: string
description: Not ID, as you probably imagine, but filename of preselected
sketchgrammar (`.m4` format).
sharing:
type: object
properties:
users:
type: array
items:
type: object
properties:
id:
type: integer
description: The ID of user you share template with.
name:
type: string
description: The name of user you share template with.
email:
type: string
description: The email of user you share template with.
user_group:
type: array
items:
type: object
properties:
id:
type: integer
description: The ID of group you share template with.
name:
type: string
description: The name of group you share template with.
80_template_put:
type: object
properties:
id:
type: string
description: Alphanumeric `template/tagset ID`. The terms `tagset` and `templates`
are interchangeable.
name:
type: string
description: Name of `template/tagset file`.
owner_id:
type: integer
description: Unique numeric `owner ID` (usually you). If tagset/template
is preloaded `Null`.
owner_name:
type: string
description: Tagset/template `owner name` (usually you). If tagset/template
is preloaded `Null`.
has_pipeline:
type: boolean
description: Vertical creation is supported. False for legacy templates.
has_tags:
type: boolean
description: Morphological tagging is supported.
has_lemmas:
type: boolean
description: Lemmatization is supported.
static_attributes:
type: array
description: A list of attributes which can appear in corpus.
items:
type: string
structures:
type: array
description: A list of used structures. Examples `<s>`, `<g>`.
items:
type: string
tagsetdoc:
type: string
description: '`URL` leading to template/tagset documentation.'
content:
type: string
description: Content of tagset.
default_sketchgrammar_id:
type: string
description: Not ID, as you probably imagine, but filename of preselected
sketchgrammar (`.m4` format).
default_termgrammar_id:
type: string
description: Not ID, as you probably imagine, but filename of preselected
sketchgrammar (`.m4` format).
sharing:
type: object
properties:
users:
type: array
items:
type: object
properties:
id:
type: integer
description: The ID of user you share template with.
user_group:
type: array
items:
type: object
properties:
id:
type: integer
description: The ID of group you share template with.
81_get_used_space:
type: object
properties:
result:
type: object
properties:
space_used:
type: integer
description: The current maximal amount of words in the user's corpora.
space_total:
type: integer
example: 1000000
description: Default maximal amount of words. The default is set to
`1 000 000` words. It can be changed.
error:
type: string
description: Unexpected server error. If none Null.
securitySchemes:
basicAuth:
type: http
scheme: basic
security:
- basicAuth: []