diff --git a/Makefile b/Makefile index b019187..2d5a641 100644 --- a/Makefile +++ b/Makefile @@ -23,9 +23,9 @@ clean-documentation: documentation: # make sure to install the correct jsonschema2md tool: # npm install -g @adobe/jsonschema2md - jsonschema2md -d json/newspaper/ -n -v 06 -o docs - jsonschema2md -d json/topic_model/ -n -v 06 -o docs - jsonschema2md -d json/language_identification/ -n -v 06 -o docs + jsonschema2md -d json/newspaper/ --header false -n -v 06 -o docs -x - -s propTable + jsonschema2md -d json/topic_model/ --header false -n -v 06 -o docs -x - -s propTable + jsonschema2md -d json/language_identification/ --header false -n -v 06 -o docs -x - -s propTable #jsonschema2md -d json/linguistic_annotation/ -n -v 06 -o docs diff --git a/README.md b/README.md index feee791..f9f1d8e 100644 --- a/README.md +++ b/README.md @@ -43,7 +43,7 @@ The 'impresso - Media Monitoring of the Past' project is funded by the Swiss Nat ## License -Copyright (C) 2020 The *impresso* team. Contributors to this program include: [Simon Clematide](https://github.com/simon-clematide), [Maud Ehrmann](https://github.com/e-maud) and [Matteo Romanello](http://github.com/mromanello/) ). +Copyright (C) 2020 The *impresso* team. Contributors to this program include: [Simon Clematide](https://github.com/simon-clematide), [Maud Ehrmann](https://github.com/e-maud) and [Matteo Romanello](http://github.com/mromanello/). This program is free software: you can redistribute it and/or modify it under the terms of the GNU Affero General Public License as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version. This program is distributed in the hope that it will be useful, but without any warranty; without even the implied warranty of merchantability or fitness for a particular purpose. See the [GNU Affero General Public License](https://github.com/impresso/impresso-schemas/blob/master/LICENSE) for more details. diff --git a/docs/contentitem-properties-cc.md b/docs/contentitem-properties-cc.md index f29917a..b3a7975 100644 --- a/docs/contentitem-properties-cc.md +++ b/docs/contentitem-properties-cc.md @@ -1,16 +1,3 @@ -# Untitled boolean in Content Item Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/contentitem.schema.json#/properties/cc -``` - -True if image box coordinates are known to be correct, False otherwise - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [contentitem.schema.json\*](../out/contentitem.schema.json "open original schema") | - ## cc Type `boolean` diff --git a/docs/contentitem-properties-d.md b/docs/contentitem-properties-d.md index cd2caa5..57929fb 100644 --- a/docs/contentitem-properties-d.md +++ b/docs/contentitem-properties-d.md @@ -1,16 +1,3 @@ -# Untitled string in Content Item Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/contentitem.schema.json#/properties/d -``` - -issue date (yyyy-mm-dd) - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [contentitem.schema.json\*](../out/contentitem.schema.json "open original schema") | - ## d Type `string` diff --git a/docs/contentitem-properties-ft.md b/docs/contentitem-properties-ft.md index 7b2df60..97d77bf 100644 --- a/docs/contentitem-properties-ft.md +++ b/docs/contentitem-properties-ft.md @@ -1,16 +1,3 @@ -# Untitled string in Content Item Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/contentitem.schema.json#/properties/ft -``` - -the rebuilt fulltext - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [contentitem.schema.json\*](../out/contentitem.schema.json "open original schema") | - ## ft Type `string` diff --git a/docs/contentitem-properties-id.md b/docs/contentitem-properties-id.md index 68d634e..6917deb 100644 --- a/docs/contentitem-properties-id.md +++ b/docs/contentitem-properties-id.md @@ -1,16 +1,3 @@ -# Untitled string in Content Item Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/contentitem.schema.json#/properties/id -``` - -The unique identifier for a content item (CI) - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [contentitem.schema.json\*](../out/contentitem.schema.json "open original schema") | - ## id Type `string` diff --git a/docs/contentitem-properties-lb-items.md b/docs/contentitem-properties-lb-items.md index 74b6542..066eb21 100644 --- a/docs/contentitem-properties-lb-items.md +++ b/docs/contentitem-properties-lb-items.md @@ -1,16 +1,3 @@ -# Untitled number in Content Item Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/contentitem.schema.json#/properties/lb/items -``` - - - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [contentitem.schema.json\*](../out/contentitem.schema.json "open original schema") | - ## items Type `number` diff --git a/docs/contentitem-properties-lb.md b/docs/contentitem-properties-lb.md index 301f978..d3fb1eb 100644 --- a/docs/contentitem-properties-lb.md +++ b/docs/contentitem-properties-lb.md @@ -1,16 +1,3 @@ -# Untitled array in Content Item Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/contentitem.schema.json#/properties/lb -``` - -text offsets of physical line breaks (relative to 'ft' field) - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [contentitem.schema.json\*](../out/contentitem.schema.json "open original schema") | - ## lb Type `number[]` diff --git a/docs/contentitem-properties-lg.md b/docs/contentitem-properties-lg.md index 3e0c7c6..f723bd6 100644 --- a/docs/contentitem-properties-lg.md +++ b/docs/contentitem-properties-lg.md @@ -1,16 +1,3 @@ -# Untitled string in Content Item Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/contentitem.schema.json#/properties/lg -``` - -two letter language code - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [contentitem.schema.json\*](../out/contentitem.schema.json "open original schema") | - ## lg Type `string` diff --git a/docs/contentitem-properties-olr.md b/docs/contentitem-properties-olr.md index b421169..4892712 100644 --- a/docs/contentitem-properties-olr.md +++ b/docs/contentitem-properties-olr.md @@ -1,16 +1,3 @@ -# Untitled boolean in Content Item Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/contentitem.schema.json#/properties/olr -``` - -True if optical layout recognition was applied to the issue this content item originates from. - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [contentitem.schema.json\*](../out/contentitem.schema.json "open original schema") | - ## olr Type `boolean` diff --git a/docs/contentitem-properties-pb-items.md b/docs/contentitem-properties-pb-items.md index d8be385..066eb21 100644 --- a/docs/contentitem-properties-pb-items.md +++ b/docs/contentitem-properties-pb-items.md @@ -1,16 +1,3 @@ -# Untitled number in Content Item Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/contentitem.schema.json#/properties/pb/items -``` - - - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [contentitem.schema.json\*](../out/contentitem.schema.json "open original schema") | - ## items Type `number` diff --git a/docs/contentitem-properties-pb.md b/docs/contentitem-properties-pb.md index f2f1d28..e2468f5 100644 --- a/docs/contentitem-properties-pb.md +++ b/docs/contentitem-properties-pb.md @@ -1,16 +1,3 @@ -# Untitled array in Content Item Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/contentitem.schema.json#/properties/pb -``` - -text offsets of physical paragraph breaks (relative to 'ft' field) - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [contentitem.schema.json\*](../out/contentitem.schema.json "open original schema") | - ## pb Type `number[]` diff --git a/docs/contentitem-properties-pp-items.md b/docs/contentitem-properties-pp-items.md index f57eda6..066eb21 100644 --- a/docs/contentitem-properties-pp-items.md +++ b/docs/contentitem-properties-pp-items.md @@ -1,16 +1,3 @@ -# Untitled number in Content Item Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/contentitem.schema.json#/properties/pp/items -``` - - - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [contentitem.schema.json\*](../out/contentitem.schema.json "open original schema") | - ## items Type `number` diff --git a/docs/contentitem-properties-pp.md b/docs/contentitem-properties-pp.md index 6f13513..459cd7a 100644 --- a/docs/contentitem-properties-pp.md +++ b/docs/contentitem-properties-pp.md @@ -1,16 +1,3 @@ -# Untitled array in Content Item Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/contentitem.schema.json#/properties/pp -``` - -array of page numbers over which the CI spans; it's the physical page number issue-based, as we get it from the OCR. - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [contentitem.schema.json\*](../out/contentitem.schema.json "open original schema") | - ## pp Type `number[]` diff --git a/docs/contentitem-properties-ppreb-items-properties-id.md b/docs/contentitem-properties-ppreb-items-properties-id.md index 43217c0..6917deb 100644 --- a/docs/contentitem-properties-ppreb-items-properties-id.md +++ b/docs/contentitem-properties-ppreb-items-properties-id.md @@ -1,16 +1,3 @@ -# Untitled string in Content Item Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/contentitem.schema.json#/properties/ppreb/items/properties/id -``` - -canonical ID - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [contentitem.schema.json\*](../out/contentitem.schema.json "open original schema") | - ## id Type `string` diff --git a/docs/contentitem-properties-ppreb-items-properties-n.md b/docs/contentitem-properties-ppreb-items-properties-n.md index 596d1ea..a1a4906 100644 --- a/docs/contentitem-properties-ppreb-items-properties-n.md +++ b/docs/contentitem-properties-ppreb-items-properties-n.md @@ -1,16 +1,3 @@ -# Untitled number in Content Item Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/contentitem.schema.json#/properties/ppreb/items/properties/n -``` - -page number - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [contentitem.schema.json\*](../out/contentitem.schema.json "open original schema") | - ## n Type `number` diff --git a/docs/contentitem-properties-ppreb-items-properties-t-items-properties-c.md b/docs/contentitem-properties-ppreb-items-properties-t-items-properties-c.md index 9b92ce4..b2801bb 100644 --- a/docs/contentitem-properties-ppreb-items-properties-t-items-properties-c.md +++ b/docs/contentitem-properties-ppreb-items-properties-t-items-properties-c.md @@ -1,16 +1,3 @@ -# Untitled array in Content Item Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/contentitem.schema.json#/properties/ppreb/items/properties/t/items/properties/c -``` - -page coordinates of token - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [contentitem.schema.json\*](../out/contentitem.schema.json "open original schema") | - ## c Type `array` diff --git a/docs/contentitem-properties-ppreb-items-properties-t-items-properties-l.md b/docs/contentitem-properties-ppreb-items-properties-t-items-properties-l.md index bd9d7a1..b5b170c 100644 --- a/docs/contentitem-properties-ppreb-items-properties-t-items-properties-l.md +++ b/docs/contentitem-properties-ppreb-items-properties-t-items-properties-l.md @@ -1,16 +1,3 @@ -# Untitled number in Content Item Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/contentitem.schema.json#/properties/ppreb/items/properties/t/items/properties/l -``` - -token length - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [contentitem.schema.json\*](../out/contentitem.schema.json "open original schema") | - ## l Type `number` diff --git a/docs/contentitem-properties-ppreb-items-properties-t-items-properties-s.md b/docs/contentitem-properties-ppreb-items-properties-t-items-properties-s.md index f2057ab..d2960ac 100644 --- a/docs/contentitem-properties-ppreb-items-properties-t-items-properties-s.md +++ b/docs/contentitem-properties-ppreb-items-properties-t-items-properties-s.md @@ -1,16 +1,3 @@ -# Untitled number in Content Item Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/contentitem.schema.json#/properties/ppreb/items/properties/t/items/properties/s -``` - -offset start (relative to ft field) - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [contentitem.schema.json\*](../out/contentitem.schema.json "open original schema") | - ## s Type `number` diff --git a/docs/contentitem-properties-ppreb-items-properties-t-items-properties.md b/docs/contentitem-properties-ppreb-items-properties-t-items-properties.md index 6fbdf48..c89940c 100644 --- a/docs/contentitem-properties-ppreb-items-properties-t-items-properties.md +++ b/docs/contentitem-properties-ppreb-items-properties-t-items-properties.md @@ -1,16 +1,3 @@ -# Untitled undefined type in Content Item Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/contentitem.schema.json#/properties/ppreb/items/properties/t/items/properties -``` - - - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [contentitem.schema.json\*](../out/contentitem.schema.json "open original schema") | - ## properties Type unknown diff --git a/docs/contentitem-properties-ppreb-items-properties-t-items.md b/docs/contentitem-properties-ppreb-items-properties-t-items.md index 83f60ed..360ad52 100644 --- a/docs/contentitem-properties-ppreb-items-properties-t-items.md +++ b/docs/contentitem-properties-ppreb-items-properties-t-items.md @@ -1,16 +1,3 @@ -# Untitled object in Content Item Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/contentitem.schema.json#/properties/ppreb/items/properties/t/items -``` - - - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ------------ | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | No | Forbidden | Allowed | none | [contentitem.schema.json\*](../out/contentitem.schema.json "open original schema") | - ## items Type `object` ([Details](contentitem-properties-ppreb-items-properties-t-items.md)) diff --git a/docs/contentitem-properties-ppreb-items-properties-t.md b/docs/contentitem-properties-ppreb-items-properties-t.md index bfb27a2..cf123c1 100644 --- a/docs/contentitem-properties-ppreb-items-properties-t.md +++ b/docs/contentitem-properties-ppreb-items-properties-t.md @@ -1,16 +1,3 @@ -# Untitled array in Content Item Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/contentitem.schema.json#/properties/ppreb/items/properties/t -``` - -a list of tokens - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [contentitem.schema.json\*](../out/contentitem.schema.json "open original schema") | - ## t Type `object[]` ([Details](contentitem-properties-ppreb-items-properties-t-items.md)) diff --git a/docs/contentitem-properties-ppreb-items-properties.md b/docs/contentitem-properties-ppreb-items-properties.md index 186163d..c89940c 100644 --- a/docs/contentitem-properties-ppreb-items-properties.md +++ b/docs/contentitem-properties-ppreb-items-properties.md @@ -1,16 +1,3 @@ -# Untitled undefined type in Content Item Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/contentitem.schema.json#/properties/ppreb/items/properties -``` - - - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [contentitem.schema.json\*](../out/contentitem.schema.json "open original schema") | - ## properties Type unknown diff --git a/docs/contentitem-properties-ppreb-items.md b/docs/contentitem-properties-ppreb-items.md index ad57522..e51471e 100644 --- a/docs/contentitem-properties-ppreb-items.md +++ b/docs/contentitem-properties-ppreb-items.md @@ -1,16 +1,3 @@ -# Untitled object in Content Item Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/contentitem.schema.json#/properties/ppreb/items -``` - - - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ------------ | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | No | Forbidden | Allowed | none | [contentitem.schema.json\*](../out/contentitem.schema.json "open original schema") | - ## items Type `object` ([Details](contentitem-properties-ppreb-items.md)) diff --git a/docs/contentitem-properties-ppreb.md b/docs/contentitem-properties-ppreb.md index e58c4e2..ef7cc34 100644 --- a/docs/contentitem-properties-ppreb.md +++ b/docs/contentitem-properties-ppreb.md @@ -1,16 +1,3 @@ -# Untitled array in Content Item Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/contentitem.schema.json#/properties/ppreb -``` - -a list of rebuilt pages - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [contentitem.schema.json\*](../out/contentitem.schema.json "open original schema") | - ## ppreb Type `object[]` ([Details](contentitem-properties-ppreb-items.md)) diff --git a/docs/contentitem-properties-rb-items.md b/docs/contentitem-properties-rb-items.md index 4bcaaf7..066eb21 100644 --- a/docs/contentitem-properties-rb-items.md +++ b/docs/contentitem-properties-rb-items.md @@ -1,16 +1,3 @@ -# Untitled number in Content Item Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/contentitem.schema.json#/properties/rb/items -``` - - - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [contentitem.schema.json\*](../out/contentitem.schema.json "open original schema") | - ## items Type `number` diff --git a/docs/contentitem-properties-rb.md b/docs/contentitem-properties-rb.md index 5ec7d7f..59a14be 100644 --- a/docs/contentitem-properties-rb.md +++ b/docs/contentitem-properties-rb.md @@ -1,16 +1,3 @@ -# Untitled array in Content Item Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/contentitem.schema.json#/properties/rb -``` - -text offsets of page regions (relative to 'ft' field) - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [contentitem.schema.json\*](../out/contentitem.schema.json "open original schema") | - ## rb Type `number[]` diff --git a/docs/contentitem-properties-s3v.md b/docs/contentitem-properties-s3v.md index 55eea7c..3b36384 100644 --- a/docs/contentitem-properties-s3v.md +++ b/docs/contentitem-properties-s3v.md @@ -1,16 +1,3 @@ -# Untitled string in Content Item Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/contentitem.schema.json#/properties/s3v -``` - -S3 version ID of the corresponding issue.json file - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [contentitem.schema.json\*](../out/contentitem.schema.json "open original schema") | - ## s3v Type `string` diff --git a/docs/contentitem-properties-tp.md b/docs/contentitem-properties-tp.md index 7b06321..84759d1 100644 --- a/docs/contentitem-properties-tp.md +++ b/docs/contentitem-properties-tp.md @@ -1,16 +1,3 @@ -# Untitled string in Content Item Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/contentitem.schema.json#/properties/tp -``` - -content item type (e.g. 'ar' for article, 'ad' for advertisement) - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [contentitem.schema.json\*](../out/contentitem.schema.json "open original schema") | - ## tp Type `string` diff --git a/docs/contentitem-properties-ts.md b/docs/contentitem-properties-ts.md index e090e86..34c56e0 100644 --- a/docs/contentitem-properties-ts.md +++ b/docs/contentitem-properties-ts.md @@ -1,16 +1,3 @@ -# Untitled string in Content Item Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/contentitem.schema.json#/properties/ts -``` - -timestamp of creation of the JSON file (e.g. '2018-09-18T08:00:08Z') - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [contentitem.schema.json\*](../out/contentitem.schema.json "open original schema") | - ## ts Type `string` diff --git a/docs/contentitem-properties.md b/docs/contentitem-properties.md index 9dbdc27..c89940c 100644 --- a/docs/contentitem-properties.md +++ b/docs/contentitem-properties.md @@ -1,16 +1,3 @@ -# Untitled undefined type in Content Item Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/contentitem.schema.json#/properties -``` - - - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [contentitem.schema.json\*](../out/contentitem.schema.json "open original schema") | - ## properties Type unknown diff --git a/docs/contentitem.md b/docs/contentitem.md index 8fa5202..e268dac 100644 --- a/docs/contentitem.md +++ b/docs/contentitem.md @@ -1,16 +1,3 @@ -# Content Item Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/contentitem.schema.json -``` - -A newspaper content item (e.g. article, advertisement, etc.). - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ------------ | :---------------- | --------------------- | ------------------- | -------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | No | Forbidden | Allowed | none | [contentitem.schema.json](../out/contentitem.schema.json "open original schema") | - ## Content Item Type `object` ([Content Item](contentitem.md)) diff --git a/docs/issue-definitions-metadata-properties-id.md b/docs/issue-definitions-metadata-properties-id.md index c06b481..6917deb 100644 --- a/docs/issue-definitions-metadata-properties-id.md +++ b/docs/issue-definitions-metadata-properties-id.md @@ -1,16 +1,3 @@ -# Untitled string in Newspaper Issue Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/issue.schema.json#/definitions/metadata/properties/id -``` - -Content item ID (e.g. `GDL-1900-01-02-a-i0001`). - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [issue.schema.json\*](../out/issue.schema.json "open original schema") | - ## id Type `string` diff --git a/docs/issue-definitions-metadata-properties-iiif_link.md b/docs/issue-definitions-metadata-properties-iiif_link.md index 4656da0..78b3f7d 100644 --- a/docs/issue-definitions-metadata-properties-iiif_link.md +++ b/docs/issue-definitions-metadata-properties-iiif_link.md @@ -1,16 +1,3 @@ -# Untitled string in Newspaper Issue Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/issue.schema.json#/definitions/metadata/properties/iiif_link -``` - -IIIF image link, depending on content item type (if `tp == image`) - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [issue.schema.json\*](../out/issue.schema.json "open original schema") | - ## iiif_link Type `string` diff --git a/docs/issue-definitions-metadata-properties-l.md b/docs/issue-definitions-metadata-properties-l.md index 5c2617b..7255809 100644 --- a/docs/issue-definitions-metadata-properties-l.md +++ b/docs/issue-definitions-metadata-properties-l.md @@ -1,16 +1,3 @@ -# Untitled string in Newspaper Issue Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/issue.schema.json#/definitions/metadata/properties/l -``` - -Language of the content item. - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [issue.schema.json\*](../out/issue.schema.json "open original schema") | - ## l Type `string` diff --git a/docs/issue-definitions-metadata-properties-pp-items.md b/docs/issue-definitions-metadata-properties-pp-items.md index acb4eeb..fb6d93c 100644 --- a/docs/issue-definitions-metadata-properties-pp-items.md +++ b/docs/issue-definitions-metadata-properties-pp-items.md @@ -1,16 +1,3 @@ -# Untitled integer in Newspaper Issue Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/issue.schema.json#/definitions/metadata/properties/pp/items -``` - - - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [issue.schema.json\*](../out/issue.schema.json "open original schema") | - ## items Type `integer` diff --git a/docs/issue-definitions-metadata-properties-pp.md b/docs/issue-definitions-metadata-properties-pp.md index d21602c..48d75cf 100644 --- a/docs/issue-definitions-metadata-properties-pp.md +++ b/docs/issue-definitions-metadata-properties-pp.md @@ -1,16 +1,3 @@ -# Untitled array in Newspaper Issue Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/issue.schema.json#/definitions/metadata/properties/pp -``` - -Page numbers over which the content item spans. - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [issue.schema.json\*](../out/issue.schema.json "open original schema") | - ## pp Type `integer[]` diff --git a/docs/issue-definitions-metadata-properties-t.md b/docs/issue-definitions-metadata-properties-t.md index 0f76f38..4f9a41a 100644 --- a/docs/issue-definitions-metadata-properties-t.md +++ b/docs/issue-definitions-metadata-properties-t.md @@ -1,16 +1,3 @@ -# Untitled string in Newspaper Issue Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/issue.schema.json#/definitions/metadata/properties/t -``` - -Title of the content item. - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [issue.schema.json\*](../out/issue.schema.json "open original schema") | - ## t Type `string` diff --git a/docs/issue-definitions-metadata-properties-tp.md b/docs/issue-definitions-metadata-properties-tp.md index 690061f..546c182 100644 --- a/docs/issue-definitions-metadata-properties-tp.md +++ b/docs/issue-definitions-metadata-properties-tp.md @@ -1,16 +1,3 @@ -# Untitled string in Newspaper Issue Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/issue.schema.json#/definitions/metadata/properties/tp -``` - -Type of the content item. - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [issue.schema.json\*](../out/issue.schema.json "open original schema") | - ## tp Type `string` diff --git a/docs/issue-definitions-metadata-properties.md b/docs/issue-definitions-metadata-properties.md index 7cff59f..c89940c 100644 --- a/docs/issue-definitions-metadata-properties.md +++ b/docs/issue-definitions-metadata-properties.md @@ -1,16 +1,3 @@ -# Untitled undefined type in Newspaper Issue Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/issue.schema.json#/definitions/metadata/properties -``` - - - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [issue.schema.json\*](../out/issue.schema.json "open original schema") | - ## properties Type unknown diff --git a/docs/issue-definitions-metadata.md b/docs/issue-definitions-metadata.md index c3f74ed..5ceb7b2 100644 --- a/docs/issue-definitions-metadata.md +++ b/docs/issue-definitions-metadata.md @@ -1,16 +1,3 @@ -# Untitled object in Newspaper Issue Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/issue.schema.json#/definitions/metadata -``` - - - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ------------ | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | No | Forbidden | Allowed | none | [issue.schema.json\*](../out/issue.schema.json "open original schema") | - ## metadata Type `object` ([Details](issue-definitions-metadata.md)) diff --git a/docs/issue-definitions.md b/docs/issue-definitions.md index 1641ac1..0664bcd 100644 --- a/docs/issue-definitions.md +++ b/docs/issue-definitions.md @@ -1,16 +1,3 @@ -# Untitled undefined type in Newspaper Issue Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/issue.schema.json#/definitions -``` - - - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [issue.schema.json\*](../out/issue.schema.json "open original schema") | - ## definitions Type unknown diff --git a/docs/issue-properties-ar.md b/docs/issue-properties-ar.md index a2a1231..31f9b07 100644 --- a/docs/issue-properties-ar.md +++ b/docs/issue-properties-ar.md @@ -1,19 +1,3 @@ -# Untitled string in Newspaper Issue Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/issue.schema.json#/properties/ar -``` - -Access rights. Three possible situations are defined: -1\. open public: access without NDA, user could redistribute (as defined per Terms of Use) -2\. open private: access without an NDA, user cannot redistribute (private/academic use only) -3\. closed : accessible only upon signing an NDA, user cannot redistribute - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [issue.schema.json\*](../out/issue.schema.json "open original schema") | - ## ar Type `string` diff --git a/docs/issue-properties-cdt.md b/docs/issue-properties-cdt.md index 9ecbce6..84132d8 100644 --- a/docs/issue-properties-cdt.md +++ b/docs/issue-properties-cdt.md @@ -1,16 +1,3 @@ -# Untitled string in Newspaper Issue Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/issue.schema.json#/properties/cdt -``` - -Creation date timestamp (of the JSON file). - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [issue.schema.json\*](../out/issue.schema.json "open original schema") | - ## cdt Type `string` diff --git a/docs/issue-properties-i-items-properties.md b/docs/issue-properties-i-items-properties.md index 9484d75..c89940c 100644 --- a/docs/issue-properties-i-items-properties.md +++ b/docs/issue-properties-i-items-properties.md @@ -1,16 +1,3 @@ -# Untitled undefined type in Newspaper Issue Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/issue.schema.json#/properties/i/items/properties -``` - - - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [issue.schema.json\*](../out/issue.schema.json "open original schema") | - ## properties Type unknown diff --git a/docs/issue-properties-i-items.md b/docs/issue-properties-i-items.md index ef79702..a41547a 100644 --- a/docs/issue-properties-i-items.md +++ b/docs/issue-properties-i-items.md @@ -1,16 +1,3 @@ -# Untitled object in Newspaper Issue Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/issue.schema.json#/properties/i/items -``` - -A content item (e.g. article, advertisement, etc.) - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ------------ | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | No | Forbidden | Allowed | none | [issue.schema.json\*](../out/issue.schema.json "open original schema") | - ## items Type `object` ([Details](issue-properties-i-items.md)) diff --git a/docs/issue-properties-i.md b/docs/issue-properties-i.md index ca20f62..c4e9203 100644 --- a/docs/issue-properties-i.md +++ b/docs/issue-properties-i.md @@ -1,16 +1,3 @@ -# Untitled array in Newspaper Issue Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/issue.schema.json#/properties/i -``` - -The content items contained in the newspaper issue. - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [issue.schema.json\*](../out/issue.schema.json "open original schema") | - ## i Type `object[]` ([Details](issue-properties-i-items.md)) diff --git a/docs/issue-properties-id.md b/docs/issue-properties-id.md index 5aaf958..6917deb 100644 --- a/docs/issue-properties-id.md +++ b/docs/issue-properties-id.md @@ -1,16 +1,3 @@ -# Untitled string in Newspaper Issue Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/issue.schema.json#/properties/id -``` - -Canonical ID of the newspaper issue (e.g. GDL-1900-01-02-a) - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [issue.schema.json\*](../out/issue.schema.json "open original schema") | - ## id Type `string` diff --git a/docs/issue-properties-n.md b/docs/issue-properties-n.md index b9abaab..d381d7d 100644 --- a/docs/issue-properties-n.md +++ b/docs/issue-properties-n.md @@ -1,16 +1,3 @@ -# Untitled string in Newspaper Issue Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/issue.schema.json#/properties/n -``` - -Notes. - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [issue.schema.json\*](../out/issue.schema.json "open original schema") | - ## n Type `string` diff --git a/docs/issue-properties-pp-items.md b/docs/issue-properties-pp-items.md index bc732b2..98d2045 100644 --- a/docs/issue-properties-pp-items.md +++ b/docs/issue-properties-pp-items.md @@ -1,16 +1,3 @@ -# Untitled string in Newspaper Issue Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/issue.schema.json#/properties/pp/items -``` - - - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [issue.schema.json\*](../out/issue.schema.json "open original schema") | - ## items Type `string` diff --git a/docs/issue-properties-pp.md b/docs/issue-properties-pp.md index 9a9957f..b56fb98 100644 --- a/docs/issue-properties-pp.md +++ b/docs/issue-properties-pp.md @@ -1,16 +1,3 @@ -# Untitled array in Newspaper Issue Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/issue.schema.json#/properties/pp -``` - -Canonical IDs of pages in the issue, without file extension (e.g. GDL-1900-01-02-a-p0004). - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [issue.schema.json\*](../out/issue.schema.json "open original schema") | - ## pp Type `string[]` diff --git a/docs/issue-properties-s-items-properties-f.md b/docs/issue-properties-s-items-properties-f.md index a3c511d..547e5d6 100644 --- a/docs/issue-properties-s-items-properties-f.md +++ b/docs/issue-properties-s-items-properties-f.md @@ -1,16 +1,3 @@ -# Untitled string in Newspaper Issue Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/issue.schema.json#/properties/s/items/properties/f -``` - -Font name - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [issue.schema.json\*](../out/issue.schema.json "open original schema") | - ## f Type `string` diff --git a/docs/issue-properties-s-items-properties-fs.md b/docs/issue-properties-s-items-properties-fs.md index 58c950d..ec70c0b 100644 --- a/docs/issue-properties-s-items-properties-fs.md +++ b/docs/issue-properties-s-items-properties-fs.md @@ -1,16 +1,3 @@ -# Untitled number in Newspaper Issue Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/issue.schema.json#/properties/s/items/properties/fs -``` - -Font size - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [issue.schema.json\*](../out/issue.schema.json "open original schema") | - ## fs Type `number` diff --git a/docs/issue-properties-s-items-properties-id.md b/docs/issue-properties-s-items-properties-id.md index e98e3fe..f491427 100644 --- a/docs/issue-properties-s-items-properties-id.md +++ b/docs/issue-properties-s-items-properties-id.md @@ -1,16 +1,3 @@ -# Untitled integer in Newspaper Issue Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/issue.schema.json#/properties/s/items/properties/id -``` - -Local ID of the style - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [issue.schema.json\*](../out/issue.schema.json "open original schema") | - ## id Type `integer` diff --git a/docs/issue-properties-s-items-properties-rgb-items.md b/docs/issue-properties-s-items-properties-rgb-items.md index 349eda1..fb6d93c 100644 --- a/docs/issue-properties-s-items-properties-rgb-items.md +++ b/docs/issue-properties-s-items-properties-rgb-items.md @@ -1,16 +1,3 @@ -# Untitled integer in Newspaper Issue Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/issue.schema.json#/properties/s/items/properties/rgb/items -``` - - - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [issue.schema.json\*](../out/issue.schema.json "open original schema") | - ## items Type `integer` diff --git a/docs/issue-properties-s-items-properties-rgb.md b/docs/issue-properties-s-items-properties-rgb.md index da538a0..38bc955 100644 --- a/docs/issue-properties-s-items-properties-rgb.md +++ b/docs/issue-properties-s-items-properties-rgb.md @@ -1,16 +1,3 @@ -# Untitled array in Newspaper Issue Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/issue.schema.json#/properties/s/items/properties/rgb -``` - -Color of the text (in RGB). - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [issue.schema.json\*](../out/issue.schema.json "open original schema") | - ## rgb Type `integer[]` diff --git a/docs/issue-properties-s-items-properties.md b/docs/issue-properties-s-items-properties.md index b39434c..c89940c 100644 --- a/docs/issue-properties-s-items-properties.md +++ b/docs/issue-properties-s-items-properties.md @@ -1,16 +1,3 @@ -# Untitled undefined type in Newspaper Issue Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/issue.schema.json#/properties/s/items/properties -``` - - - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [issue.schema.json\*](../out/issue.schema.json "open original schema") | - ## properties Type unknown diff --git a/docs/issue-properties-s-items.md b/docs/issue-properties-s-items.md index 28908b2..d180d05 100644 --- a/docs/issue-properties-s-items.md +++ b/docs/issue-properties-s-items.md @@ -1,16 +1,3 @@ -# Untitled object in Newspaper Issue Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/issue.schema.json#/properties/s/items -``` - - - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ------------ | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | No | Forbidden | Allowed | none | [issue.schema.json\*](../out/issue.schema.json "open original schema") | - ## items Type `object` ([Details](issue-properties-s-items.md)) diff --git a/docs/issue-properties-s.md b/docs/issue-properties-s.md index 8f53494..752457a 100644 --- a/docs/issue-properties-s.md +++ b/docs/issue-properties-s.md @@ -1,22 +1,3 @@ -# Untitled array in Newspaper Issue Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/issue.schema.json#/properties/s -``` - -The text style as defined in the OCR output. -Each style consists of: - -- a name (`id`) -- a type-face (`f`) -- a font-size (`fs`) -- a color (`rgb`). - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [issue.schema.json\*](../out/issue.schema.json "open original schema") | - ## s Type `object[]` ([Details](issue-properties-s-items.md)) diff --git a/docs/issue-properties.md b/docs/issue-properties.md index 6ee6e49..c89940c 100644 --- a/docs/issue-properties.md +++ b/docs/issue-properties.md @@ -1,16 +1,3 @@ -# Untitled undefined type in Newspaper Issue Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/issue.schema.json#/properties -``` - - - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [issue.schema.json\*](../out/issue.schema.json "open original schema") | - ## properties Type unknown diff --git a/docs/issue.md b/docs/issue.md index c7d1d74..a56dfc1 100644 --- a/docs/issue.md +++ b/docs/issue.md @@ -1,16 +1,3 @@ -# Newspaper Issue Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/issue.schema.json -``` - -Logical representation of the contents of a newspaper issue. - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ------------ | :---------------- | --------------------- | ------------------- | -------------------------------------------------------------------- | -| Can be instantiated | Yes | Unknown status | No | Forbidden | Allowed | none | [issue.schema.json](../out/issue.schema.json "open original schema") | - ## Newspaper Issue Type `object` ([Newspaper Issue](issue.md)) diff --git a/docs/language_identification-definitions-langiso639type.md b/docs/language_identification-definitions-langiso639type.md new file mode 100644 index 0000000..fe6edd0 --- /dev/null +++ b/docs/language_identification-definitions-langiso639type.md @@ -0,0 +1,13 @@ +## langISO639Type Type + +`string` ([langISO639Type](language_identification-definitions-langiso639type.md)) + +## langISO639Type Constraints + +**pattern**: the string must match the following regular expression: + +```regexp +^[a-z]{2,3}$ +``` + +[try pattern](https://regexr.com/?expression=%5E%5Ba-z%5D%7B2%2C3%7D%24 "try regular expression with regexr.com") diff --git a/docs/language_identification-definitions-lid-properties-lang.md b/docs/language_identification-definitions-lid-properties-lang.md deleted file mode 100644 index 29f0b1d..0000000 --- a/docs/language_identification-definitions-lid-properties-lang.md +++ /dev/null @@ -1,26 +0,0 @@ -# Untitled string in undefined Schema - -```txt -https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/definitions/lid/properties/lang -``` - - - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [language_identification.schema.json\*](../out/language_identification.schema.json "open original schema") | - -## lang Type - -`string` - -## lang Constraints - -**pattern**: the string must match the following regular expression: - -```regexp -^[a-z]{2}$ -``` - -[try pattern](https://regexr.com/?expression=%5E%5Ba-z%5D%7B2%7D%24 "try regular expression with regexr.com") diff --git a/docs/language_identification-definitions-lid-properties-prob.md b/docs/language_identification-definitions-lid-properties-prob.md deleted file mode 100644 index 4576c05..0000000 --- a/docs/language_identification-definitions-lid-properties-prob.md +++ /dev/null @@ -1,16 +0,0 @@ -# Untitled number in undefined Schema - -```txt -https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/definitions/lid/properties/prob -``` - -Probability of prediction - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [language_identification.schema.json\*](../out/language_identification.schema.json "open original schema") | - -## prob Type - -`number` diff --git a/docs/language_identification-definitions-lid-properties.md b/docs/language_identification-definitions-lid-properties.md deleted file mode 100644 index 155b2ea..0000000 --- a/docs/language_identification-definitions-lid-properties.md +++ /dev/null @@ -1,16 +0,0 @@ -# Untitled schema Schema - -```txt -https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/definitions/lid/properties -``` - - - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [language_identification.schema.json\*](../out/language_identification.schema.json "open original schema") | - -## properties Type - -unknown diff --git a/docs/language_identification-definitions-lid.md b/docs/language_identification-definitions-lid.md deleted file mode 100644 index fb14bbb..0000000 --- a/docs/language_identification-definitions-lid.md +++ /dev/null @@ -1,65 +0,0 @@ -# Untitled object in undefined Schema - -```txt -https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/definitions/lid -``` - -Predicted language and its probability - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ------------ | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | No | Forbidden | Allowed | none | [language_identification.schema.json\*](../out/language_identification.schema.json "open original schema") | - -## lid Type - -`object` ([Details](language_identification-definitions-lid.md)) - -# undefined Properties - -| Property | Type | Required | Nullable | Defined by | -| :------------ | -------- | -------- | -------------- | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -| [lang](#lang) | `string` | Required | cannot be null | [Untitled schema](language_identification-definitions-lid-properties-lang.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/definitions/lid/properties/lang") | -| [prob](#prob) | `number` | Required | cannot be null | [Untitled schema](language_identification-definitions-lid-properties-prob.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/definitions/lid/properties/prob") | - -## lang - - - - -`lang` - -- is required -- Type: `string` -- cannot be null -- defined in: [Untitled schema](language_identification-definitions-lid-properties-lang.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/definitions/lid/properties/lang") - -### lang Type - -`string` - -### lang Constraints - -**pattern**: the string must match the following regular expression: - -```regexp -^[a-z]{2}$ -``` - -[try pattern](https://regexr.com/?expression=%5E%5Ba-z%5D%7B2%7D%24 "try regular expression with regexr.com") - -## prob - -Probability of prediction - - -`prob` - -- is required -- Type: `number` -- cannot be null -- defined in: [Untitled schema](language_identification-definitions-lid-properties-prob.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/definitions/lid/properties/prob") - -### prob Type - -`number` diff --git a/docs/language_identification-definitions-lidtype-properties-langiso639type.md b/docs/language_identification-definitions-lidtype-properties-langiso639type.md new file mode 100644 index 0000000..3df58a2 --- /dev/null +++ b/docs/language_identification-definitions-lidtype-properties-langiso639type.md @@ -0,0 +1,13 @@ +## lang Type + +`string` ([langISO639Type](language_identification-definitions-lidtype-properties-langiso639type.md)) + +## lang Constraints + +**pattern**: the string must match the following regular expression: + +```regexp +^[a-z]{2,3}$ +``` + +[try pattern](https://regexr.com/?expression=%5E%5Ba-z%5D%7B2%2C3%7D%24 "try regular expression with regexr.com") diff --git a/docs/language_identification-definitions-lidtype-properties-probtype.md b/docs/language_identification-definitions-lidtype-properties-probtype.md new file mode 100644 index 0000000..0db8a89 --- /dev/null +++ b/docs/language_identification-definitions-lidtype-properties-probtype.md @@ -0,0 +1,9 @@ +## prob Type + +`number` ([probType](language_identification-definitions-lidtype-properties-probtype.md)) + +## prob Constraints + +**maximum**: the value of this number must smaller than or equal to: `1` + +**minimum**: the value of this number must greater than or equal to: `0` diff --git a/docs/language_identification-definitions-lidtype-properties.md b/docs/language_identification-definitions-lidtype-properties.md new file mode 100644 index 0000000..c89940c --- /dev/null +++ b/docs/language_identification-definitions-lidtype-properties.md @@ -0,0 +1,3 @@ +## properties Type + +unknown diff --git a/docs/language_identification-definitions-lidtype.md b/docs/language_identification-definitions-lidtype.md new file mode 100644 index 0000000..c6d77bf --- /dev/null +++ b/docs/language_identification-definitions-lidtype.md @@ -0,0 +1,58 @@ +## lidType Type + +`object` ([lidType](language_identification-definitions-lidtype.md)) + +# lidType Properties + +| Property | Type | Required | Nullable | Defined by | +| :------------ | -------- | -------- | -------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| [lang](#lang) | `string` | Required | cannot be null | [Impresso Language Identification Information](language_identification-definitions-lidtype-properties-langiso639type.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/definitions/lidType/properties/lang") | +| [prob](#prob) | `number` | Required | cannot be null | [Impresso Language Identification Information](language_identification-definitions-lidtype-properties-probtype.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/definitions/lidType/properties/prob") | + +## lang + +Two- or three-letter ISO language abbreviation, cf. or + + +`lang` + +- is required +- Type: `string` ([langISO639Type](language_identification-definitions-lidtype-properties-langiso639type.md)) +- cannot be null +- defined in: [Impresso Language Identification Information](language_identification-definitions-lidtype-properties-langiso639type.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/definitions/lidType/properties/lang") + +### lang Type + +`string` ([langISO639Type](language_identification-definitions-lidtype-properties-langiso639type.md)) + +### lang Constraints + +**pattern**: the string must match the following regular expression: + +```regexp +^[a-z]{2,3}$ +``` + +[try pattern](https://regexr.com/?expression=%5E%5Ba-z%5D%7B2%2C3%7D%24 "try regular expression with regexr.com") + +## prob + +Probability of the prediction + + +`prob` + +- is required +- Type: `number` ([probType](language_identification-definitions-lidtype-properties-probtype.md)) +- cannot be null +- defined in: [Impresso Language Identification Information](language_identification-definitions-lidtype-properties-probtype.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/definitions/lidType/properties/prob") + +### prob Type + +`number` ([probType](language_identification-definitions-lidtype-properties-probtype.md)) + +### prob Constraints + +**maximum**: the value of this number must smaller than or equal to: `1` + +**minimum**: the value of this number must greater than or equal to: `0` diff --git a/docs/language_identification-definitions-probtype.md b/docs/language_identification-definitions-probtype.md new file mode 100644 index 0000000..7c468d4 --- /dev/null +++ b/docs/language_identification-definitions-probtype.md @@ -0,0 +1,9 @@ +## probType Type + +`number` ([probType](language_identification-definitions-probtype.md)) + +## probType Constraints + +**maximum**: the value of this number must smaller than or equal to: `1` + +**minimum**: the value of this number must greater than or equal to: `0` diff --git a/docs/language_identification-definitions-versiontype-properties-ts.md b/docs/language_identification-definitions-versiontype-properties-ts.md new file mode 100644 index 0000000..da7e9b2 --- /dev/null +++ b/docs/language_identification-definitions-versiontype-properties-ts.md @@ -0,0 +1,13 @@ +## ts Type + +`string` + +## ts Constraints + +**pattern**: the string must match the following regular expression: + +```regexp +^[0-9]{4}-[0-9]{2}-[0-9]{2}T[0-9]{2}:[0-9]{2}:[0-9]{2}(Z|\+00:00)$ +``` + +[try pattern](https://regexr.com/?expression=%5E%5B0-9%5D%7B4%7D-%5B0-9%5D%7B2%7D-%5B0-9%5D%7B2%7DT%5B0-9%5D%7B2%7D%3A%5B0-9%5D%7B2%7D%3A%5B0-9%5D%7B2%7D(Z%7C%5C%2B00%3A00)%24 "try regular expression with regexr.com") diff --git a/docs/language_identification-definitions-versiontype-properties-versiontype.md b/docs/language_identification-definitions-versiontype-properties-versiontype.md new file mode 100644 index 0000000..032484d --- /dev/null +++ b/docs/language_identification-definitions-versiontype-properties-versiontype.md @@ -0,0 +1,3 @@ +## versionType Type + +`string` diff --git a/docs/language_identification-definitions-versiontype-properties.md b/docs/language_identification-definitions-versiontype-properties.md new file mode 100644 index 0000000..c89940c --- /dev/null +++ b/docs/language_identification-definitions-versiontype-properties.md @@ -0,0 +1,3 @@ +## properties Type + +unknown diff --git a/docs/language_identification-definitions-versiontype.md b/docs/language_identification-definitions-versiontype.md new file mode 100644 index 0000000..ea1b18e --- /dev/null +++ b/docs/language_identification-definitions-versiontype.md @@ -0,0 +1,52 @@ +## versionType Type + +`object` ([versionType](language_identification-definitions-versiontype.md)) + +# versionType Properties + +| Property | Type | Required | Nullable | Defined by | +| :-------------------------- | -------- | -------- | -------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| [versionType](#versiontype) | `string` | Optional | cannot be null | [Impresso Language Identification Information](language_identification-definitions-versiontype-properties-versiontype.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/definitions/versionType/properties/versionType") | +| [ts](#ts) | `string` | Required | cannot be null | [Impresso Language Identification Information](language_identification-definitions-versiontype-properties-ts.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/definitions/versionType/properties/ts") | + +## versionType + +Version of tool. Either date or output of command 'git describe' + + +`versionType` + +- is optional +- Type: `string` +- cannot be null +- defined in: [Impresso Language Identification Information](language_identification-definitions-versiontype-properties-versiontype.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/definitions/versionType/properties/versionType") + +### versionType Type + +`string` + +## ts + +timestamp of creation of the JSON file (e.g. '2018-09-18T08:00:08+00:00') + + +`ts` + +- is required +- Type: `string` +- cannot be null +- defined in: [Impresso Language Identification Information](language_identification-definitions-versiontype-properties-ts.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/definitions/versionType/properties/ts") + +### ts Type + +`string` + +### ts Constraints + +**pattern**: the string must match the following regular expression: + +```regexp +^[0-9]{4}-[0-9]{2}-[0-9]{2}T[0-9]{2}:[0-9]{2}:[0-9]{2}(Z|\+00:00)$ +``` + +[try pattern](https://regexr.com/?expression=%5E%5B0-9%5D%7B4%7D-%5B0-9%5D%7B2%7D-%5B0-9%5D%7B2%7DT%5B0-9%5D%7B2%7D%3A%5B0-9%5D%7B2%7D%3A%5B0-9%5D%7B2%7D(Z%7C%5C%2B00%3A00)%24 "try regular expression with regexr.com") diff --git a/docs/language_identification-definitions.md b/docs/language_identification-definitions.md index 50431dd..0664bcd 100644 --- a/docs/language_identification-definitions.md +++ b/docs/language_identification-definitions.md @@ -1,16 +1,3 @@ -# Untitled schema Schema - -```txt -https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/definitions -``` - - - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [language_identification.schema.json\*](../out/language_identification.schema.json "open original schema") | - ## definitions Type unknown diff --git a/docs/language_identification-properties-alphabetical_ratio.md b/docs/language_identification-properties-alphabetical_ratio.md index c1e173c..d8b3c48 100644 --- a/docs/language_identification-properties-alphabetical_ratio.md +++ b/docs/language_identification-properties-alphabetical_ratio.md @@ -1,16 +1,9 @@ -# Untitled number in undefined Schema - -```txt -https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/alphabetical_ratio -``` - -Ratio of alphabetical characters (letters) wtr to text length of content item +## alphabetical_ratio Type +`number` -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [language_identification.schema.json\*](../out/language_identification.schema.json "open original schema") | +## alphabetical_ratio Constraints -## alphabetical_ratio Type +**maximum**: the value of this number must smaller than or equal to: `1` -`number` +**minimum**: the value of this number must greater than or equal to: `0` diff --git a/docs/language_identification-properties-id.md b/docs/language_identification-properties-id.md index 7dd611e..6917deb 100644 --- a/docs/language_identification-properties-id.md +++ b/docs/language_identification-properties-id.md @@ -1,16 +1,3 @@ -# Untitled string in undefined Schema - -```txt -https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/id -``` - -Canonical ID of the newspaper issue (e.g. GDL-1900-01-02-a), cf. - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [language_identification.schema.json\*](../out/language_identification.schema.json "open original schema") | - ## id Type `string` diff --git a/docs/language_identification-properties-impresso_ft.md b/docs/language_identification-properties-impresso_ft.md index 2a2ee43..08b09fe 100644 --- a/docs/language_identification-properties-impresso_ft.md +++ b/docs/language_identification-properties-impresso_ft.md @@ -1,16 +1,3 @@ -# Untitled array in undefined Schema - -```txt -https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/impresso_ft -``` - -List of predicted languages using a FastText model trained on Impresso articles, sorted by probability - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [language_identification.schema.json\*](../out/language_identification.schema.json "open original schema") | - ## impresso_ft Type -`object[]` ([Details](language_identification-definitions-lid.md)) +`object[]` ([lidType](language_identification-definitions-lidtype.md)) diff --git a/docs/language_identification-properties-langdetect.md b/docs/language_identification-properties-langdetect.md index 8df14c9..5ec6b1c 100644 --- a/docs/language_identification-properties-langdetect.md +++ b/docs/language_identification-properties-langdetect.md @@ -1,16 +1,3 @@ -# Untitled array in undefined Schema - -```txt -https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/langdetect -``` - -List of predicted languages using Langdetect, sorted by probability - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [language_identification.schema.json\*](../out/language_identification.schema.json "open original schema") | - ## langdetect Type -`object[]` ([Details](language_identification-definitions-lid.md)) +`object[]` ([lidType](language_identification-definitions-lidtype.md)) diff --git a/docs/language_identification-properties-langid.md b/docs/language_identification-properties-langid.md index 12cad56..597fd8e 100644 --- a/docs/language_identification-properties-langid.md +++ b/docs/language_identification-properties-langid.md @@ -1,16 +1,3 @@ -# Untitled array in undefined Schema - -```txt -https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/langid -``` - -List of predicted languages using Langid, sorted by probability - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [language_identification.schema.json\*](../out/language_identification.schema.json "open original schema") | - ## langid Type -`object[]` ([Details](language_identification-definitions-lid.md)) +`object[]` ([lidType](language_identification-definitions-lidtype.md)) diff --git a/docs/language_identification-properties-len.md b/docs/language_identification-properties-len.md index 657584e..12cdf49 100644 --- a/docs/language_identification-properties-len.md +++ b/docs/language_identification-properties-len.md @@ -1,16 +1,7 @@ -# Untitled integer in undefined Schema - -```txt -https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/len -``` - -Length of content item - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [language_identification.schema.json\*](../out/language_identification.schema.json "open original schema") | - ## len Type `integer` + +## len Constraints + +**minimum**: the value of this number must greater than or equal to: `0` diff --git a/docs/language_identification-properties-lg-oneof-langiso639type.md b/docs/language_identification-properties-lg-oneof-langiso639type.md new file mode 100644 index 0000000..c1c241e --- /dev/null +++ b/docs/language_identification-properties-lg-oneof-langiso639type.md @@ -0,0 +1,13 @@ +## 1 Type + +`string` ([langISO639Type](language_identification-properties-lg-oneof-langiso639type.md)) + +## 1 Constraints + +**pattern**: the string must match the following regular expression: + +```regexp +^[a-z]{2,3}$ +``` + +[try pattern](https://regexr.com/?expression=%5E%5Ba-z%5D%7B2%2C3%7D%24 "try regular expression with regexr.com") diff --git a/docs/language_identification-properties-lg-oneof-null.md b/docs/language_identification-properties-lg-oneof-null.md new file mode 100644 index 0000000..22d2179 --- /dev/null +++ b/docs/language_identification-properties-lg-oneof-null.md @@ -0,0 +1,3 @@ +## 0 Type + +`null`, the value must be null ([null](language_identification-properties-lg-oneof-null.md)) diff --git a/docs/language_identification-properties-lg.md b/docs/language_identification-properties-lg.md new file mode 100644 index 0000000..90ff26a --- /dev/null +++ b/docs/language_identification-properties-lg.md @@ -0,0 +1,8 @@ +## lg Type + +`string` ([Details](language_identification-properties-lg.md)) + +one (and only one) of + +- [null](language_identification-properties-lg-oneof-null.md "check type definition") +- [langISO639Type](language_identification-properties-lg-oneof-langiso639type.md "check type definition") diff --git a/docs/language_identification-properties-lg_decision.md b/docs/language_identification-properties-lg_decision.md new file mode 100644 index 0000000..5ed396f --- /dev/null +++ b/docs/language_identification-properties-lg_decision.md @@ -0,0 +1,15 @@ +## lg_decision Type + +`string` + +## lg_decision Constraints + +**enum**: the value of this property must be equal to one of the following values: + +| Value | Explanation | +| :---------------------- | ----------- | +| `"all"` | | +| `"all-but-impresso-ft"` | | +| `"voting"` | | +| `"dominant-by-len"` | | +| `"dominant-by-lowvote"` | | diff --git a/docs/language_identification-properties-orig_lg-oneof-langiso639type.md b/docs/language_identification-properties-orig_lg-oneof-langiso639type.md new file mode 100644 index 0000000..0b77d72 --- /dev/null +++ b/docs/language_identification-properties-orig_lg-oneof-langiso639type.md @@ -0,0 +1,13 @@ +## 1 Type + +`string` ([langISO639Type](language_identification-properties-orig_lg-oneof-langiso639type.md)) + +## 1 Constraints + +**pattern**: the string must match the following regular expression: + +```regexp +^[a-z]{2,3}$ +``` + +[try pattern](https://regexr.com/?expression=%5E%5Ba-z%5D%7B2%2C3%7D%24 "try regular expression with regexr.com") diff --git a/docs/language_identification-properties-orig_lg-oneof-null.md b/docs/language_identification-properties-orig_lg-oneof-null.md new file mode 100644 index 0000000..3cf1c89 --- /dev/null +++ b/docs/language_identification-properties-orig_lg-oneof-null.md @@ -0,0 +1,3 @@ +## 0 Type + +`null`, the value must be null ([null](language_identification-properties-orig_lg-oneof-null.md)) diff --git a/docs/language_identification-properties-orig_lg.md b/docs/language_identification-properties-orig_lg.md index cea0b9b..99bd7dd 100644 --- a/docs/language_identification-properties-orig_lg.md +++ b/docs/language_identification-properties-orig_lg.md @@ -1,26 +1,8 @@ -# Untitled schema Schema - -```txt -https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/orig_lg -``` - -Original language of the content item as provided by the meta data, cf. - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [language_identification.schema.json\*](../out/language_identification.schema.json "open original schema") | - ## orig_lg Type -`string` - -## orig_lg Constraints - -**pattern**: the string must match the following regular expression: +`string` ([Details](language_identification-properties-orig_lg.md)) -```regexp -^[a-z]{2}$ -``` +one (and only one) of -[try pattern](https://regexr.com/?expression=%5E%5Ba-z%5D%7B2%7D%24 "try regular expression with regexr.com") +- [null](language_identification-properties-orig_lg-oneof-null.md "check type definition") +- [langISO639Type](language_identification-properties-orig_lg-oneof-langiso639type.md "check type definition") diff --git a/docs/language_identification-properties-tp.md b/docs/language_identification-properties-tp.md index a1f3c87..84759d1 100644 --- a/docs/language_identification-properties-tp.md +++ b/docs/language_identification-properties-tp.md @@ -1,16 +1,3 @@ -# Untitled string in undefined Schema - -```txt -https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/tp -``` - -Type of the content item, cf. - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [language_identification.schema.json\*](../out/language_identification.schema.json "open original schema") | - ## tp Type `string` diff --git a/docs/language_identification-properties-versiontype-1.md b/docs/language_identification-properties-versiontype-1.md new file mode 100644 index 0000000..f7f0486 --- /dev/null +++ b/docs/language_identification-properties-versiontype-1.md @@ -0,0 +1,52 @@ +## language_identifier_version Type + +`object` ([versionType](language_identification-properties-versiontype-1.md)) + +# versionType Properties + +| Property | Type | Required | Nullable | Defined by | +| :-------------------------- | -------- | -------- | -------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| [versionType](#versiontype) | `string` | Optional | cannot be null | [Impresso Language Identification Information](language_identification-definitions-versiontype-properties-versiontype.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/definitions/versionType/properties/versionType") | +| [ts](#ts) | `string` | Required | cannot be null | [Impresso Language Identification Information](language_identification-definitions-versiontype-properties-ts.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/definitions/versionType/properties/ts") | + +## versionType + +Version of tool. Either date or output of command 'git describe' + + +`versionType` + +- is optional +- Type: `string` +- cannot be null +- defined in: [Impresso Language Identification Information](language_identification-definitions-versiontype-properties-versiontype.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/definitions/versionType/properties/versionType") + +### versionType Type + +`string` + +## ts + +timestamp of creation of the JSON file (e.g. '2018-09-18T08:00:08+00:00') + + +`ts` + +- is required +- Type: `string` +- cannot be null +- defined in: [Impresso Language Identification Information](language_identification-definitions-versiontype-properties-ts.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/definitions/versionType/properties/ts") + +### ts Type + +`string` + +### ts Constraints + +**pattern**: the string must match the following regular expression: + +```regexp +^[0-9]{4}-[0-9]{2}-[0-9]{2}T[0-9]{2}:[0-9]{2}:[0-9]{2}(Z|\+00:00)$ +``` + +[try pattern](https://regexr.com/?expression=%5E%5B0-9%5D%7B4%7D-%5B0-9%5D%7B2%7D-%5B0-9%5D%7B2%7DT%5B0-9%5D%7B2%7D%3A%5B0-9%5D%7B2%7D%3A%5B0-9%5D%7B2%7D(Z%7C%5C%2B00%3A00)%24 "try regular expression with regexr.com") diff --git a/docs/language_identification-properties-versiontype.md b/docs/language_identification-properties-versiontype.md new file mode 100644 index 0000000..1756b2c --- /dev/null +++ b/docs/language_identification-properties-versiontype.md @@ -0,0 +1,52 @@ +## impresso_language_identifier_version Type + +`object` ([versionType](language_identification-properties-versiontype.md)) + +# versionType Properties + +| Property | Type | Required | Nullable | Defined by | +| :-------------------------- | -------- | -------- | -------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| [versionType](#versiontype) | `string` | Optional | cannot be null | [Impresso Language Identification Information](language_identification-definitions-versiontype-properties-versiontype.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/definitions/versionType/properties/versionType") | +| [ts](#ts) | `string` | Required | cannot be null | [Impresso Language Identification Information](language_identification-definitions-versiontype-properties-ts.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/definitions/versionType/properties/ts") | + +## versionType + +Version of tool. Either date or output of command 'git describe' + + +`versionType` + +- is optional +- Type: `string` +- cannot be null +- defined in: [Impresso Language Identification Information](language_identification-definitions-versiontype-properties-versiontype.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/definitions/versionType/properties/versionType") + +### versionType Type + +`string` + +## ts + +timestamp of creation of the JSON file (e.g. '2018-09-18T08:00:08+00:00') + + +`ts` + +- is required +- Type: `string` +- cannot be null +- defined in: [Impresso Language Identification Information](language_identification-definitions-versiontype-properties-ts.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/definitions/versionType/properties/ts") + +### ts Type + +`string` + +### ts Constraints + +**pattern**: the string must match the following regular expression: + +```regexp +^[0-9]{4}-[0-9]{2}-[0-9]{2}T[0-9]{2}:[0-9]{2}:[0-9]{2}(Z|\+00:00)$ +``` + +[try pattern](https://regexr.com/?expression=%5E%5B0-9%5D%7B4%7D-%5B0-9%5D%7B2%7D-%5B0-9%5D%7B2%7DT%5B0-9%5D%7B2%7D%3A%5B0-9%5D%7B2%7D%3A%5B0-9%5D%7B2%7D(Z%7C%5C%2B00%3A00)%24 "try regular expression with regexr.com") diff --git a/docs/language_identification-properties-votes-items-0-properties-langiso639type.md b/docs/language_identification-properties-votes-items-0-properties-langiso639type.md new file mode 100644 index 0000000..d81b29d --- /dev/null +++ b/docs/language_identification-properties-votes-items-0-properties-langiso639type.md @@ -0,0 +1,13 @@ +## lang Type + +`string` ([langISO639Type](language_identification-properties-votes-items-0-properties-langiso639type.md)) + +## lang Constraints + +**pattern**: the string must match the following regular expression: + +```regexp +^[a-z]{2,3}$ +``` + +[try pattern](https://regexr.com/?expression=%5E%5Ba-z%5D%7B2%2C3%7D%24 "try regular expression with regexr.com") diff --git a/docs/language_identification-properties-votes-items-0-properties-vote.md b/docs/language_identification-properties-votes-items-0-properties-vote.md new file mode 100644 index 0000000..55a09b3 --- /dev/null +++ b/docs/language_identification-properties-votes-items-0-properties-vote.md @@ -0,0 +1,3 @@ +## vote Type + +`number` diff --git a/docs/language_identification-properties-votes-items-0-properties.md b/docs/language_identification-properties-votes-items-0-properties.md new file mode 100644 index 0000000..c89940c --- /dev/null +++ b/docs/language_identification-properties-votes-items-0-properties.md @@ -0,0 +1,3 @@ +## properties Type + +unknown diff --git a/docs/language_identification-properties-votes-items-0.md b/docs/language_identification-properties-votes-items-0.md new file mode 100644 index 0000000..7c57174 --- /dev/null +++ b/docs/language_identification-properties-votes-items-0.md @@ -0,0 +1,52 @@ +## 0 Type + +`object` ([Details](language_identification-properties-votes-items-0.md)) + +# undefined Properties + +| Property | Type | Required | Nullable | Defined by | +| :------------ | -------- | -------- | -------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | +| [lang](#lang) | `string` | Required | cannot be null | [Impresso Language Identification Information](language_identification-properties-votes-items-0-properties-langiso639type.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/votes/items/0/properties/lang") | +| [vote](#vote) | `number` | Required | cannot be null | [Impresso Language Identification Information](language_identification-properties-votes-items-0-properties-vote.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/votes/items/0/properties/vote") | + +## lang + +Two- or three-letter ISO language abbreviation, cf. or + + +`lang` + +- is required +- Type: `string` ([langISO639Type](language_identification-properties-votes-items-0-properties-langiso639type.md)) +- cannot be null +- defined in: [Impresso Language Identification Information](language_identification-properties-votes-items-0-properties-langiso639type.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/votes/items/0/properties/lang") + +### lang Type + +`string` ([langISO639Type](language_identification-properties-votes-items-0-properties-langiso639type.md)) + +### lang Constraints + +**pattern**: the string must match the following regular expression: + +```regexp +^[a-z]{2,3}$ +``` + +[try pattern](https://regexr.com/?expression=%5E%5Ba-z%5D%7B2%2C3%7D%24 "try regular expression with regexr.com") + +## vote + + + + +`vote` + +- is required +- Type: `number` +- cannot be null +- defined in: [Impresso Language Identification Information](language_identification-properties-votes-items-0-properties-vote.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/votes/items/0/properties/vote") + +### vote Type + +`number` diff --git a/docs/language_identification-properties-votes.md b/docs/language_identification-properties-votes.md new file mode 100644 index 0000000..5a51d42 --- /dev/null +++ b/docs/language_identification-properties-votes.md @@ -0,0 +1,5 @@ +## votes Type + +an array where each item follows the corresponding schema in the following list: + +1. [Untitled object in Impresso Language Identification Information](language_identification-properties-votes-items-0.md "check type definition") diff --git a/docs/language_identification-properties-wp_ft.md b/docs/language_identification-properties-wp_ft.md index d4c4eee..990b3f6 100644 --- a/docs/language_identification-properties-wp_ft.md +++ b/docs/language_identification-properties-wp_ft.md @@ -1,16 +1,3 @@ -# Untitled array in undefined Schema - -```txt -https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/wp_ft -``` - -List of predicted languages using a FastText model trained on Wikipedia, sorted by probability - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [language_identification.schema.json\*](../out/language_identification.schema.json "open original schema") | - ## wp_ft Type -`object[]` ([Details](language_identification-definitions-lid.md)) +`object[]` ([lidType](language_identification-definitions-lidtype.md)) diff --git a/docs/language_identification-properties.md b/docs/language_identification-properties.md index d72923a..c89940c 100644 --- a/docs/language_identification-properties.md +++ b/docs/language_identification-properties.md @@ -1,16 +1,3 @@ -# Untitled schema Schema - -```txt -https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties -``` - - - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [language_identification.schema.json\*](../out/language_identification.schema.json "open original schema") | - ## properties Type unknown diff --git a/docs/language_identification.md b/docs/language_identification.md index 2e10759..730f53d 100644 --- a/docs/language_identification.md +++ b/docs/language_identification.md @@ -1,69 +1,131 @@ -# Untitled object in undefined Schema +## Impresso Language Identification Information Type + +`object` ([Impresso Language Identification Information](language_identification.md)) + +# Impresso Language Identification Information Properties + +| Property | Type | Required | Nullable | Defined by | +| :---------------------------------------------------------------------------- | --------- | -------- | -------------- | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| [id](#id) | `string` | Required | cannot be null | [Impresso Language Identification Information](language_identification-properties-id.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/id") | +| [orig_lg](#orig_lg) | Merged | Required | can be null | [Impresso Language Identification Information](language_identification-properties-orig_lg.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/orig_lg") | +| [lg](#lg) | Merged | Required | can be null | [Impresso Language Identification Information](language_identification-properties-lg.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/lg") | +| [lg_decision](#lg_decision) | `string` | Optional | cannot be null | [Impresso Language Identification Information](language_identification-properties-lg_decision.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/lg_decision") | +| [tp](#tp) | `string` | Required | cannot be null | [Impresso Language Identification Information](language_identification-properties-tp.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/tp") | +| [len](#len) | `integer` | Required | cannot be null | [Impresso Language Identification Information](language_identification-properties-len.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/len") | +| [impresso_language_identifier_version](#impresso_language_identifier_version) | `object` | Optional | cannot be null | [Impresso Language Identification Information](language_identification-properties-versiontype.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/impresso_language_identifier_version") | +| [language_identifier_version](#language_identifier_version) | `object` | Optional | cannot be null | [Impresso Language Identification Information](language_identification-properties-versiontype-1.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/language_identifier_version") | +| [alphabetical_ratio](#alphabetical_ratio) | `number` | Optional | can be null | [Impresso Language Identification Information](language_identification-properties-alphabetical_ratio.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/alphabetical_ratio") | +| [langdetect](#langdetect) | `array` | Optional | cannot be null | [Impresso Language Identification Information](language_identification-properties-langdetect.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/langdetect") | +| [langid](#langid) | `array` | Optional | cannot be null | [Impresso Language Identification Information](language_identification-properties-langid.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/langid") | +| [impresso_ft](#impresso_ft) | `array` | Optional | cannot be null | [Impresso Language Identification Information](language_identification-properties-impresso_ft.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/impresso_ft") | +| [wp_ft](#wp_ft) | `array` | Optional | cannot be null | [Impresso Language Identification Information](language_identification-properties-wp_ft.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/wp_ft") | +| [votes](#votes) | `array` | Optional | cannot be null | [Impresso Language Identification Information](language_identification-properties-votes.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/votes") | -```txt -https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json -``` +## id -A representation for the language identifications of various models per content item. +The unique identifier for a content item, cf. -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ------------ | :---------------- | --------------------- | ------------------- | -------------------------------------------------------------------------------------------------------- | -| Can be instantiated | Yes | Unknown status | No | Forbidden | Allowed | none | [language_identification.schema.json](../out/language_identification.schema.json "open original schema") | +`id` + +- is required +- Type: `string` +- cannot be null +- defined in: [Impresso Language Identification Information](language_identification-properties-id.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/id") + +### id Type -## Untitled object in undefined Type +`string` -`object` ([Details](language_identification.md)) +## orig_lg -# undefined Properties +Original language of the content item as provided by the metadata, cf. -| Property | Type | Required | Nullable | Defined by | -| :---------------------------------------- | --------- | -------- | -------------- | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -| [tp](#tp) | `string` | Required | cannot be null | [Untitled schema](language_identification-properties-tp.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/tp") | -| [id](#id) | `string` | Required | cannot be null | [Untitled schema](language_identification-properties-id.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/id") | -| [len](#len) | `integer` | Required | cannot be null | [Untitled schema](language_identification-properties-len.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/len") | -| [orig_lg](#orig_lg) | `string` | Required | can be null | [Untitled schema](language_identification-properties-orig_lg.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/orig_lg") | -| [alphabetical_ratio](#alphabetical_ratio) | `number` | Optional | cannot be null | [Untitled schema](language_identification-properties-alphabetical_ratio.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/alphabetical_ratio") | -| [langdetect](#langdetect) | `array` | Optional | cannot be null | [Untitled schema](language_identification-properties-langdetect.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/langdetect") | -| [langid](#langid) | `array` | Optional | cannot be null | [Untitled schema](language_identification-properties-langid.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/langid") | -| [impresso_ft](#impresso_ft) | `array` | Optional | cannot be null | [Untitled schema](language_identification-properties-impresso_ft.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/impresso_ft") | -| [wp_ft](#wp_ft) | `array` | Optional | cannot be null | [Untitled schema](language_identification-properties-wp_ft.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/wp_ft") | -## tp +`orig_lg` -Type of the content item, cf. +- is required +- Type: `string` ([Details](language_identification-properties-orig_lg.md)) +- can be null +- defined in: [Impresso Language Identification Information](language_identification-properties-orig_lg.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/orig_lg") +### orig_lg Type -`tp` +`string` ([Details](language_identification-properties-orig_lg.md)) + +one (and only one) of + +- [null](language_identification-properties-orig_lg-oneof-null.md "check type definition") +- [langISO639Type](language_identification-properties-orig_lg-oneof-langiso639type.md "check type definition") + +## lg + +Computed language of the content item, cf. + + +`lg` - is required +- Type: `string` ([Details](language_identification-properties-lg.md)) +- can be null +- defined in: [Impresso Language Identification Information](language_identification-properties-lg.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/lg") + +### lg Type + +`string` ([Details](language_identification-properties-lg.md)) + +one (and only one) of + +- [null](language_identification-properties-lg-oneof-null.md "check type definition") +- [langISO639Type](language_identification-properties-lg-oneof-langiso639type.md "check type definition") + +## lg_decision + +An identifier for the decision strategy applied to the content item: 'all' = all LID systems/info agree; 'all-but-impresso-ft' = all LID except impresso_ft agree on a language other than de/fr; 'dominant-by-len' = the most frequent language of the ensemble decisions is selected because there are too few characters; 'dominant-by-lowvote' = the most frequent language of the ensemble decisions is selected because there are too few votes; 'voting' = the language with the highest vote count is selected + + +`lg_decision` + +- is optional - Type: `string` - cannot be null -- defined in: [Untitled schema](language_identification-properties-tp.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/tp") +- defined in: [Impresso Language Identification Information](language_identification-properties-lg_decision.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/lg_decision") -### tp Type +### lg_decision Type `string` -## id +### lg_decision Constraints -Canonical ID of the newspaper issue (e.g. GDL-1900-01-02-a), cf. +**enum**: the value of this property must be equal to one of the following values: +| Value | Explanation | +| :---------------------- | ----------- | +| `"all"` | | +| `"all-but-impresso-ft"` | | +| `"voting"` | | +| `"dominant-by-len"` | | +| `"dominant-by-lowvote"` | | -`id` +## tp + +Type of the content item, cf. + + +`tp` - is required - Type: `string` - cannot be null -- defined in: [Untitled schema](language_identification-properties-id.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/id") +- defined in: [Impresso Language Identification Information](language_identification-properties-tp.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/tp") -### id Type +### tp Type `string` ## len -Length of content item +Number of characters of content item `len` @@ -71,54 +133,70 @@ Length of content item - is required - Type: `integer` - cannot be null -- defined in: [Untitled schema](language_identification-properties-len.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/len") +- defined in: [Impresso Language Identification Information](language_identification-properties-len.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/len") ### len Type `integer` -## orig_lg +### len Constraints -Original language of the content item as provided by the meta data, cf. +**minimum**: the value of this number must greater than or equal to: `0` +## impresso_language_identifier_version -`orig_lg` +Administrative information on tool version and data creation time. -- is required -- Type: `string` -- can be null -- defined in: [Untitled schema](language_identification-properties-orig_lg.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/orig_lg") -### orig_lg Type +`impresso_language_identifier_version` -`string` +- is optional +- Type: `object` ([versionType](language_identification-properties-versiontype.md)) +- cannot be null +- defined in: [Impresso Language Identification Information](language_identification-properties-versiontype.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/impresso_language_identifier_version") -### orig_lg Constraints +### impresso_language_identifier_version Type -**pattern**: the string must match the following regular expression: +`object` ([versionType](language_identification-properties-versiontype.md)) -```regexp -^[a-z]{2}$ -``` +## language_identifier_version -[try pattern](https://regexr.com/?expression=%5E%5Ba-z%5D%7B2%7D%24 "try regular expression with regexr.com") +Administrative information on tool version and data creation time. + + +`language_identifier_version` + +- is optional +- Type: `object` ([versionType](language_identification-properties-versiontype-1.md)) +- cannot be null +- defined in: [Impresso Language Identification Information](language_identification-properties-versiontype-1.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/language_identifier_version") + +### language_identifier_version Type + +`object` ([versionType](language_identification-properties-versiontype-1.md)) ## alphabetical_ratio -Ratio of alphabetical characters (letters) wtr to text length of content item +Ratio of alphabetical characters (Unicode letter class matched by \\w) w.r.t. text length of content item `alphabetical_ratio` - is optional - Type: `number` -- cannot be null -- defined in: [Untitled schema](language_identification-properties-alphabetical_ratio.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/alphabetical_ratio") +- can be null +- defined in: [Impresso Language Identification Information](language_identification-properties-alphabetical_ratio.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/alphabetical_ratio") ### alphabetical_ratio Type `number` +### alphabetical_ratio Constraints + +**maximum**: the value of this number must smaller than or equal to: `1` + +**minimum**: the value of this number must greater than or equal to: `0` + ## langdetect List of predicted languages using Langdetect, sorted by probability @@ -127,13 +205,13 @@ List of predicted languages using Langdetect, sorted by probability `langdetect` - is optional -- Type: `object[]` ([Details](language_identification-properties-langdetect-items.md)) +- Type: `object[]` ([lidType](language_identification-properties-langdetect-lidtype.md)) - cannot be null -- defined in: [Untitled schema](language_identification-properties-langdetect.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/langdetect") +- defined in: [Impresso Language Identification Information](language_identification-properties-langdetect.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/langdetect") ### langdetect Type -`object[]` ([Details](language_identification-properties-langdetect-items.md)) +`object[]` ([lidType](language_identification-properties-langdetect-lidtype.md)) ## langid @@ -143,13 +221,13 @@ List of predicted languages using Langid, sorted by probability `langid` - is optional -- Type: `object[]` ([Details](language_identification-properties-langid-items.md)) +- Type: `object[]` ([lidType](language_identification-properties-langid-lidtype.md)) - cannot be null -- defined in: [Untitled schema](language_identification-properties-langid.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/langid") +- defined in: [Impresso Language Identification Information](language_identification-properties-langid.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/langid") ### langid Type -`object[]` ([Details](language_identification-properties-langid-items.md)) +`object[]` ([lidType](language_identification-properties-langid-lidtype.md)) ## impresso_ft @@ -159,13 +237,13 @@ List of predicted languages using a FastText model trained on Impresso articles, `impresso_ft` - is optional -- Type: `object[]` ([Details](language_identification-properties-impresso_ft-items.md)) +- Type: `object[]` ([lidType](language_identification-properties-impresso_ft-lidtype.md)) - cannot be null -- defined in: [Untitled schema](language_identification-properties-impresso_ft.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/impresso_ft") +- defined in: [Impresso Language Identification Information](language_identification-properties-impresso_ft.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/impresso_ft") ### impresso_ft Type -`object[]` ([Details](language_identification-properties-impresso_ft-items.md)) +`object[]` ([lidType](language_identification-properties-impresso_ft-lidtype.md)) ## wp_ft @@ -175,67 +253,170 @@ List of predicted languages using a FastText model trained on Wikipedia, sorted `wp_ft` - is optional -- Type: `object[]` ([Details](language_identification-properties-wp_ft-items.md)) +- Type: `object[]` ([lidType](language_identification-properties-wp_ft-lidtype.md)) - cannot be null -- defined in: [Untitled schema](language_identification-properties-wp_ft.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/wp_ft") +- defined in: [Impresso Language Identification Information](language_identification-properties-wp_ft.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/wp_ft") ### wp_ft Type -`object[]` ([Details](language_identification-properties-wp_ft-items.md)) +`object[]` ([lidType](language_identification-properties-wp_ft-lidtype.md)) -# Untitled object in undefined Definitions +## votes -## Definitions group lid + + + +`votes` + +- is optional +- Type: an array where each item follows the corresponding schema in the following list: + + 1. [Untitled object in Impresso Language Identification Information](language_identification-properties-votes-items-0.md "check type definition") +- cannot be null +- defined in: [Impresso Language Identification Information](language_identification-properties-votes.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/properties/votes") + +### votes Type + +an array where each item follows the corresponding schema in the following list: + +1. [Untitled object in Impresso Language Identification Information](language_identification-properties-votes-items-0.md "check type definition") + +# Impresso Language Identification Information Definitions + +## Definitions group lidType Reference this group by using ```json -{"$ref":"https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/definitions/lid"} +{"$ref":"https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/definitions/lidType"} ``` -| Property | Type | Required | Nullable | Defined by | -| :------------ | -------- | -------- | -------------- | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -| [lang](#lang) | `string` | Required | cannot be null | [Untitled schema](language_identification-definitions-lid-properties-lang.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/definitions/lid/properties/lang") | -| [prob](#prob) | `number` | Required | cannot be null | [Untitled schema](language_identification-definitions-lid-properties-prob.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/definitions/lid/properties/prob") | +| Property | Type | Required | Nullable | Defined by | +| :------------ | -------- | -------- | -------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| [lang](#lang) | `string` | Required | cannot be null | [Impresso Language Identification Information](language_identification-definitions-lidtype-properties-langiso639type.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/definitions/lidType/properties/lang") | +| [prob](#prob) | `number` | Required | cannot be null | [Impresso Language Identification Information](language_identification-definitions-lidtype-properties-probtype.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/definitions/lidType/properties/prob") | ### lang - +Two- or three-letter ISO language abbreviation, cf. or `lang` - is required -- Type: `string` +- Type: `string` ([langISO639Type](language_identification-definitions-lidtype-properties-langiso639type.md)) - cannot be null -- defined in: [Untitled schema](language_identification-definitions-lid-properties-lang.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/definitions/lid/properties/lang") +- defined in: [Impresso Language Identification Information](language_identification-definitions-lidtype-properties-langiso639type.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/definitions/lidType/properties/lang") #### lang Type -`string` +`string` ([langISO639Type](language_identification-definitions-lidtype-properties-langiso639type.md)) #### lang Constraints **pattern**: the string must match the following regular expression: ```regexp -^[a-z]{2}$ +^[a-z]{2,3}$ ``` -[try pattern](https://regexr.com/?expression=%5E%5Ba-z%5D%7B2%7D%24 "try regular expression with regexr.com") +[try pattern](https://regexr.com/?expression=%5E%5Ba-z%5D%7B2%2C3%7D%24 "try regular expression with regexr.com") ### prob -Probability of prediction +Probability of the prediction `prob` - is required -- Type: `number` +- Type: `number` ([probType](language_identification-definitions-lidtype-properties-probtype.md)) - cannot be null -- defined in: [Untitled schema](language_identification-definitions-lid-properties-prob.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/definitions/lid/properties/prob") +- defined in: [Impresso Language Identification Information](language_identification-definitions-lidtype-properties-probtype.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/definitions/lidType/properties/prob") #### prob Type -`number` +`number` ([probType](language_identification-definitions-lidtype-properties-probtype.md)) + +#### prob Constraints + +**maximum**: the value of this number must smaller than or equal to: `1` + +**minimum**: the value of this number must greater than or equal to: `0` + +## Definitions group langISO639Type + +Reference this group by using + +```json +{"$ref":"https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/definitions/langISO639Type"} +``` + +| Property | Type | Required | Nullable | Defined by | +| :------- | ---- | -------- | -------- | :--------- | + +## Definitions group probType + +Reference this group by using + +```json +{"$ref":"https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/definitions/probType"} +``` + +| Property | Type | Required | Nullable | Defined by | +| :------- | ---- | -------- | -------- | :--------- | + +## Definitions group versionType + +Reference this group by using + +```json +{"$ref":"https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/definitions/versionType"} +``` + +| Property | Type | Required | Nullable | Defined by | +| :-------------------------- | -------- | -------- | -------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| [versionType](#versiontype) | `string` | Optional | cannot be null | [Impresso Language Identification Information](language_identification-definitions-versiontype-properties-versiontype.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/definitions/versionType/properties/versionType") | +| [ts](#ts) | `string` | Required | cannot be null | [Impresso Language Identification Information](language_identification-definitions-versiontype-properties-ts.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/definitions/versionType/properties/ts") | + +### versionType + +Version of tool. Either date or output of command 'git describe' + + +`versionType` + +- is optional +- Type: `string` +- cannot be null +- defined in: [Impresso Language Identification Information](language_identification-definitions-versiontype-properties-versiontype.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/definitions/versionType/properties/versionType") + +#### versionType Type + +`string` + +### ts + +timestamp of creation of the JSON file (e.g. '2018-09-18T08:00:08+00:00') + + +`ts` + +- is required +- Type: `string` +- cannot be null +- defined in: [Impresso Language Identification Information](language_identification-definitions-versiontype-properties-ts.md "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json#/definitions/versionType/properties/ts") + +#### ts Type + +`string` + +#### ts Constraints + +**pattern**: the string must match the following regular expression: + +```regexp +^[0-9]{4}-[0-9]{2}-[0-9]{2}T[0-9]{2}:[0-9]{2}:[0-9]{2}(Z|\+00:00)$ +``` + +[try pattern](https://regexr.com/?expression=%5E%5B0-9%5D%7B4%7D-%5B0-9%5D%7B2%7D-%5B0-9%5D%7B2%7DT%5B0-9%5D%7B2%7D%3A%5B0-9%5D%7B2%7D%3A%5B0-9%5D%7B2%7D(Z%7C%5C%2B00%3A00)%24 "try regular expression with regexr.com") diff --git a/docs/page-properties-cc.md b/docs/page-properties-cc.md index 0dd53c6..b3a7975 100644 --- a/docs/page-properties-cc.md +++ b/docs/page-properties-cc.md @@ -1,16 +1,3 @@ -# Untitled boolean in Newspaper Page Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/page.schema.json#/properties/cc -``` - -Flag indicating whether the legacy coordinates have been converted into IIIF-compliant ones. - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | -------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [page.schema.json\*](../out/page.schema.json "open original schema") | - ## cc Type `boolean` diff --git a/docs/page-properties-cdt.md b/docs/page-properties-cdt.md index 9812152..84132d8 100644 --- a/docs/page-properties-cdt.md +++ b/docs/page-properties-cdt.md @@ -1,16 +1,3 @@ -# Untitled string in Newspaper Page Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/page.schema.json#/properties/cdt -``` - -Creation date timestamp (of the JSON file). - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | -------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [page.schema.json\*](../out/page.schema.json "open original schema") | - ## cdt Type `string` diff --git a/docs/page-properties-id.md b/docs/page-properties-id.md index cff424f..6917deb 100644 --- a/docs/page-properties-id.md +++ b/docs/page-properties-id.md @@ -1,16 +1,3 @@ -# Untitled string in Newspaper Page Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/page.schema.json#/properties/id -``` - -Canonical ID of the newspaper page (e.g. GDL-1900-01-02-a-p0001) - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | -------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [page.schema.json\*](../out/page.schema.json "open original schema") | - ## id Type `string` diff --git a/docs/page-properties-iiif.md b/docs/page-properties-iiif.md index b312534..8b87cb7 100644 --- a/docs/page-properties-iiif.md +++ b/docs/page-properties-iiif.md @@ -1,16 +1,3 @@ -# Untitled string in Newspaper Page Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/page.schema.json#/properties/iiif -``` - -URI of the IIIF Manifest of the newspaper page image. - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | -------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [page.schema.json\*](../out/page.schema.json "open original schema") | - ## iiif Type `string` diff --git a/docs/page-properties-r-items-properties-c-items.md b/docs/page-properties-r-items-properties-c-items.md index d34b77a..fb6d93c 100644 --- a/docs/page-properties-r-items-properties-c-items.md +++ b/docs/page-properties-r-items-properties-c-items.md @@ -1,16 +1,3 @@ -# Untitled integer in Newspaper Page Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/page.schema.json#/properties/r/items/properties/c/items -``` - - - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | -------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [page.schema.json\*](../out/page.schema.json "open original schema") | - ## items Type `integer` diff --git a/docs/page-properties-r-items-properties-c.md b/docs/page-properties-r-items-properties-c.md index a2ff7a5..19472ed 100644 --- a/docs/page-properties-r-items-properties-c.md +++ b/docs/page-properties-r-items-properties-c.md @@ -1,16 +1,3 @@ -# Untitled array in Newspaper Page Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/page.schema.json#/properties/r/items/properties/c -``` - -Coordinates of image-region, following IIIF regions schema (x, y, width, height). - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | -------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [page.schema.json\*](../out/page.schema.json "open original schema") | - ## c Type `integer[]` diff --git a/docs/page-properties-r-items-properties-p-items-properties-l-items-properties-c-items.md b/docs/page-properties-r-items-properties-p-items-properties-l-items-properties-c-items.md index 76289bc..fb6d93c 100644 --- a/docs/page-properties-r-items-properties-p-items-properties-l-items-properties-c-items.md +++ b/docs/page-properties-r-items-properties-p-items-properties-l-items-properties-c-items.md @@ -1,16 +1,3 @@ -# Untitled integer in Newspaper Page Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/page.schema.json#/properties/r/items/properties/p/items/properties/l/items/properties/c/items -``` - - - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | -------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [page.schema.json\*](../out/page.schema.json "open original schema") | - ## items Type `integer` diff --git a/docs/page-properties-r-items-properties-p-items-properties-l-items-properties-c.md b/docs/page-properties-r-items-properties-p-items-properties-l-items-properties-c.md index 6a2740f..19472ed 100644 --- a/docs/page-properties-r-items-properties-p-items-properties-l-items-properties-c.md +++ b/docs/page-properties-r-items-properties-p-items-properties-l-items-properties-c.md @@ -1,16 +1,3 @@ -# Untitled array in Newspaper Page Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/page.schema.json#/properties/r/items/properties/p/items/properties/l/items/properties/c -``` - -Coordinates of image-region. - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | -------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [page.schema.json\*](../out/page.schema.json "open original schema") | - ## c Type `integer[]` diff --git a/docs/page-properties-r-items-properties-p-items-properties-l-items-properties-t-items-properties-c-items.md b/docs/page-properties-r-items-properties-p-items-properties-l-items-properties-t-items-properties-c-items.md index 93a8a9d..fb6d93c 100644 --- a/docs/page-properties-r-items-properties-p-items-properties-l-items-properties-t-items-properties-c-items.md +++ b/docs/page-properties-r-items-properties-p-items-properties-l-items-properties-t-items-properties-c-items.md @@ -1,16 +1,3 @@ -# Untitled integer in Newspaper Page Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/page.schema.json#/properties/r/items/properties/p/items/properties/l/items/properties/t/items/properties/c/items -``` - - - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | -------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [page.schema.json\*](../out/page.schema.json "open original schema") | - ## items Type `integer` diff --git a/docs/page-properties-r-items-properties-p-items-properties-l-items-properties-t-items-properties-c.md b/docs/page-properties-r-items-properties-p-items-properties-l-items-properties-t-items-properties-c.md index 4dbface..19472ed 100644 --- a/docs/page-properties-r-items-properties-p-items-properties-l-items-properties-t-items-properties-c.md +++ b/docs/page-properties-r-items-properties-p-items-properties-l-items-properties-t-items-properties-c.md @@ -1,16 +1,3 @@ -# Untitled array in Newspaper Page Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/page.schema.json#/properties/r/items/properties/p/items/properties/l/items/properties/t/items/properties/c -``` - -Coordinates of image-region. - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | -------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [page.schema.json\*](../out/page.schema.json "open original schema") | - ## c Type `integer[]` diff --git a/docs/page-properties-r-items-properties-p-items-properties-l-items-properties-t-items-properties-gn.md b/docs/page-properties-r-items-properties-p-items-properties-l-items-properties-t-items-properties-gn.md index e9d9af5..b9839fa 100644 --- a/docs/page-properties-r-items-properties-p-items-properties-l-items-properties-t-items-properties-gn.md +++ b/docs/page-properties-r-items-properties-p-items-properties-l-items-properties-t-items-properties-gn.md @@ -1,16 +1,3 @@ -# Untitled boolean in Newspaper Page Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/page.schema.json#/properties/r/items/properties/p/items/properties/l/items/properties/t/items/properties/gn -``` - -Indicates whether the token is/should be followed by a whitespace. `gn==true` means no white space is required (`gn` stands for 'glue next'). When not specified it is assumed to be `false`. - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | -------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [page.schema.json\*](../out/page.schema.json "open original schema") | - ## gn Type `boolean` diff --git a/docs/page-properties-r-items-properties-p-items-properties-l-items-properties-t-items-properties-hy.md b/docs/page-properties-r-items-properties-p-items-properties-l-items-properties-t-items-properties-hy.md index e841caa..9120fbf 100644 --- a/docs/page-properties-r-items-properties-p-items-properties-l-items-properties-t-items-properties-hy.md +++ b/docs/page-properties-r-items-properties-p-items-properties-l-items-properties-t-items-properties-hy.md @@ -1,16 +1,3 @@ -# Untitled boolean in Newspaper Page Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/page.schema.json#/properties/r/items/properties/p/items/properties/l/items/properties/t/items/properties/hy -``` - -Indicates whether the token constitutes the former part of a hyphenated word (including hyphen). When not specified it is assumed to be `false`. - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | -------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [page.schema.json\*](../out/page.schema.json "open original schema") | - ## hy Type `boolean` diff --git a/docs/page-properties-r-items-properties-p-items-properties-l-items-properties-t-items-properties-nf.md b/docs/page-properties-r-items-properties-p-items-properties-l-items-properties-t-items-properties-nf.md index 35ddf0b..0d2ea7c 100644 --- a/docs/page-properties-r-items-properties-p-items-properties-l-items-properties-t-items-properties-nf.md +++ b/docs/page-properties-r-items-properties-p-items-properties-l-items-properties-t-items-properties-nf.md @@ -1,16 +1,3 @@ -# Untitled string in Newspaper Page Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/page.schema.json#/properties/r/items/properties/p/items/properties/l/items/properties/t/items/properties/nf -``` - -It is specified on the latter part(s) of a hyphenated word, and contains its normalized (dehyphenated) form. - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | -------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [page.schema.json\*](../out/page.schema.json "open original schema") | - ## nf Type `string` diff --git a/docs/page-properties-r-items-properties-p-items-properties-l-items-properties-t-items-properties-s.md b/docs/page-properties-r-items-properties-p-items-properties-l-items-properties-t-items-properties-s.md index 96d2c90..b6232b6 100644 --- a/docs/page-properties-r-items-properties-p-items-properties-l-items-properties-t-items-properties-s.md +++ b/docs/page-properties-r-items-properties-p-items-properties-l-items-properties-t-items-properties-s.md @@ -1,16 +1,3 @@ -# Untitled integer in Newspaper Page Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/page.schema.json#/properties/r/items/properties/p/items/properties/l/items/properties/t/items/properties/s -``` - -A style ID as defined in issue.schema.json/s - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | -------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [page.schema.json\*](../out/page.schema.json "open original schema") | - ## s Type `integer` diff --git a/docs/page-properties-r-items-properties-p-items-properties-l-items-properties-t-items-properties-tx.md b/docs/page-properties-r-items-properties-p-items-properties-l-items-properties-t-items-properties-tx.md index e229449..14d93a6 100644 --- a/docs/page-properties-r-items-properties-p-items-properties-l-items-properties-t-items-properties-tx.md +++ b/docs/page-properties-r-items-properties-p-items-properties-l-items-properties-t-items-properties-tx.md @@ -1,16 +1,3 @@ -# Untitled string in Newspaper Page Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/page.schema.json#/properties/r/items/properties/p/items/properties/l/items/properties/t/items/properties/tx -``` - -Token surface form. - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | -------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [page.schema.json\*](../out/page.schema.json "open original schema") | - ## tx Type `string` diff --git a/docs/page-properties-r-items-properties-p-items-properties-l-items-properties-t-items-properties.md b/docs/page-properties-r-items-properties-p-items-properties-l-items-properties-t-items-properties.md index 7e75d0e..c89940c 100644 --- a/docs/page-properties-r-items-properties-p-items-properties-l-items-properties-t-items-properties.md +++ b/docs/page-properties-r-items-properties-p-items-properties-l-items-properties-t-items-properties.md @@ -1,16 +1,3 @@ -# Untitled undefined type in Newspaper Page Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/page.schema.json#/properties/r/items/properties/p/items/properties/l/items/properties/t/items/properties -``` - - - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | -------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [page.schema.json\*](../out/page.schema.json "open original schema") | - ## properties Type unknown diff --git a/docs/page-properties-r-items-properties-p-items-properties-l-items-properties-t-items.md b/docs/page-properties-r-items-properties-p-items-properties-l-items-properties-t-items.md index f1e3d6b..887fc3c 100644 --- a/docs/page-properties-r-items-properties-p-items-properties-l-items-properties-t-items.md +++ b/docs/page-properties-r-items-properties-p-items-properties-l-items-properties-t-items.md @@ -1,16 +1,3 @@ -# Untitled object in Newspaper Page Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/page.schema.json#/properties/r/items/properties/p/items/properties/l/items/properties/t/items -``` - - - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ------------ | :---------------- | --------------------- | ------------------- | -------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | No | Forbidden | Allowed | none | [page.schema.json\*](../out/page.schema.json "open original schema") | - ## items Type `object` ([Details](page-properties-r-items-properties-p-items-properties-l-items-properties-t-items.md)) diff --git a/docs/page-properties-r-items-properties-p-items-properties-l-items-properties-t.md b/docs/page-properties-r-items-properties-p-items-properties-l-items-properties-t.md index 7c3b1c9..99eb873 100644 --- a/docs/page-properties-r-items-properties-p-items-properties-l-items-properties-t.md +++ b/docs/page-properties-r-items-properties-p-items-properties-l-items-properties-t.md @@ -1,16 +1,3 @@ -# Untitled array in Newspaper Page Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/page.schema.json#/properties/r/items/properties/p/items/properties/l/items/properties/t -``` - -Tokens (as detected by the OCR engine). - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | -------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [page.schema.json\*](../out/page.schema.json "open original schema") | - ## t Type `object[]` ([Details](page-properties-r-items-properties-p-items-properties-l-items-properties-t-items.md)) diff --git a/docs/page-properties-r-items-properties-p-items-properties-l-items-properties.md b/docs/page-properties-r-items-properties-p-items-properties-l-items-properties.md index 21ce61f..c89940c 100644 --- a/docs/page-properties-r-items-properties-p-items-properties-l-items-properties.md +++ b/docs/page-properties-r-items-properties-p-items-properties-l-items-properties.md @@ -1,16 +1,3 @@ -# Untitled undefined type in Newspaper Page Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/page.schema.json#/properties/r/items/properties/p/items/properties/l/items/properties -``` - - - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | -------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [page.schema.json\*](../out/page.schema.json "open original schema") | - ## properties Type unknown diff --git a/docs/page-properties-r-items-properties-p-items-properties-l-items.md b/docs/page-properties-r-items-properties-p-items-properties-l-items.md index fc84d89..09f19ee 100644 --- a/docs/page-properties-r-items-properties-p-items-properties-l-items.md +++ b/docs/page-properties-r-items-properties-p-items-properties-l-items.md @@ -1,16 +1,3 @@ -# Untitled object in Newspaper Page Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/page.schema.json#/properties/r/items/properties/p/items/properties/l/items -``` - - - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ------------ | :---------------- | --------------------- | ------------------- | -------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | No | Forbidden | Allowed | none | [page.schema.json\*](../out/page.schema.json "open original schema") | - ## items Type `object` ([Details](page-properties-r-items-properties-p-items-properties-l-items.md)) diff --git a/docs/page-properties-r-items-properties-p-items-properties-l.md b/docs/page-properties-r-items-properties-p-items-properties-l.md index 8f65348..6d3116f 100644 --- a/docs/page-properties-r-items-properties-p-items-properties-l.md +++ b/docs/page-properties-r-items-properties-p-items-properties-l.md @@ -1,16 +1,3 @@ -# Untitled array in Newspaper Page Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/page.schema.json#/properties/r/items/properties/p/items/properties/l -``` - -Lines of text (belonging to a given paragraph) - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | -------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [page.schema.json\*](../out/page.schema.json "open original schema") | - ## l Type `object[]` ([Details](page-properties-r-items-properties-p-items-properties-l-items.md)) diff --git a/docs/page-properties-r-items-properties-p-items-properties.md b/docs/page-properties-r-items-properties-p-items-properties.md index 0dcc571..c89940c 100644 --- a/docs/page-properties-r-items-properties-p-items-properties.md +++ b/docs/page-properties-r-items-properties-p-items-properties.md @@ -1,16 +1,3 @@ -# Untitled undefined type in Newspaper Page Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/page.schema.json#/properties/r/items/properties/p/items/properties -``` - - - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | -------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [page.schema.json\*](../out/page.schema.json "open original schema") | - ## properties Type unknown diff --git a/docs/page-properties-r-items-properties-p-items.md b/docs/page-properties-r-items-properties-p-items.md index bdcd8fa..b19697b 100644 --- a/docs/page-properties-r-items-properties-p-items.md +++ b/docs/page-properties-r-items-properties-p-items.md @@ -1,16 +1,3 @@ -# Untitled object in Newspaper Page Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/page.schema.json#/properties/r/items/properties/p/items -``` - - - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ------------ | :---------------- | --------------------- | ------------------- | -------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | No | Forbidden | Allowed | none | [page.schema.json\*](../out/page.schema.json "open original schema") | - ## items Type `object` ([Details](page-properties-r-items-properties-p-items.md)) diff --git a/docs/page-properties-r-items-properties-p.md b/docs/page-properties-r-items-properties-p.md index c18f6d6..58df1bf 100644 --- a/docs/page-properties-r-items-properties-p.md +++ b/docs/page-properties-r-items-properties-p.md @@ -1,16 +1,3 @@ -# Untitled array in Newspaper Page Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/page.schema.json#/properties/r/items/properties/p -``` - -Text paragraphs. - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | -------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [page.schema.json\*](../out/page.schema.json "open original schema") | - ## p Type `object[]` ([Details](page-properties-r-items-properties-p-items.md)) diff --git a/docs/page-properties-r-items-properties-pof.md b/docs/page-properties-r-items-properties-pof.md index 3e02746..ea42666 100644 --- a/docs/page-properties-r-items-properties-pof.md +++ b/docs/page-properties-r-items-properties-pof.md @@ -1,16 +1,3 @@ -# Untitled string in Newspaper Page Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/page.schema.json#/properties/r/items/properties/pOf -``` - -The canonical ID of the content item to which the page region belongs. - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | -------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [page.schema.json\*](../out/page.schema.json "open original schema") | - ## pOf Type `string` diff --git a/docs/page-properties-r-items-properties.md b/docs/page-properties-r-items-properties.md index d6fcdd7..c89940c 100644 --- a/docs/page-properties-r-items-properties.md +++ b/docs/page-properties-r-items-properties.md @@ -1,16 +1,3 @@ -# Untitled undefined type in Newspaper Page Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/page.schema.json#/properties/r/items/properties -``` - - - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | -------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [page.schema.json\*](../out/page.schema.json "open original schema") | - ## properties Type unknown diff --git a/docs/page-properties-r-items.md b/docs/page-properties-r-items.md index af1d8d0..56e4b8b 100644 --- a/docs/page-properties-r-items.md +++ b/docs/page-properties-r-items.md @@ -1,16 +1,3 @@ -# Untitled object in Newspaper Page Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/page.schema.json#/properties/r/items -``` - -Page region. - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ------------ | :---------------- | --------------------- | ------------------- | -------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | No | Forbidden | Allowed | none | [page.schema.json\*](../out/page.schema.json "open original schema") | - ## items Type `object` ([Details](page-properties-r-items.md)) diff --git a/docs/page-properties-r.md b/docs/page-properties-r.md index 52d344c..4062390 100644 --- a/docs/page-properties-r.md +++ b/docs/page-properties-r.md @@ -1,16 +1,3 @@ -# Untitled array in Newspaper Page Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/page.schema.json#/properties/r -``` - -Page regions. - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | -------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [page.schema.json\*](../out/page.schema.json "open original schema") | - ## r Type `object[]` ([Details](page-properties-r-items.md)) diff --git a/docs/page-properties.md b/docs/page-properties.md index 1d7a8c6..c89940c 100644 --- a/docs/page-properties.md +++ b/docs/page-properties.md @@ -1,16 +1,3 @@ -# Untitled undefined type in Newspaper Page Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/page.schema.json#/properties -``` - - - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | -------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [page.schema.json\*](../out/page.schema.json "open original schema") | - ## properties Type unknown diff --git a/docs/page.md b/docs/page.md index 11e3e6d..aabd1d2 100644 --- a/docs/page.md +++ b/docs/page.md @@ -1,16 +1,3 @@ -# Newspaper Page Schema - -```txt -https://impresso.github.io/impresso-schemas/json/newspaper/page.schema.json -``` - -Physical representation of a newspaper page as recognized by a given OCR engine. - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ------------ | :---------------- | --------------------- | ------------------- | ------------------------------------------------------------------ | -| Can be instantiated | No | Unknown status | No | Forbidden | Allowed | none | [page.schema.json](../out/page.schema.json "open original schema") | - ## Newspaper Page Type `object` ([Newspaper Page](page.md)) diff --git a/docs/topic_assignment-definitions-topic-properties-p.md b/docs/topic_assignment-definitions-topic-properties-p.md index dbf0d91..862e085 100644 --- a/docs/topic_assignment-definitions-topic-properties-p.md +++ b/docs/topic_assignment-definitions-topic-properties-p.md @@ -1,16 +1,3 @@ -# Untitled number in undefined Schema - -```txt -https://impresso.github.io/impresso-schemas/json/topic_model/topic_assignment.schema.json#/definitions/topic/properties/p -``` - -Probability or proportion of topic - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | -------------------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [topic_assignment.schema.json\*](../out/topic_assignment.schema.json "open original schema") | - ## p Type `number` diff --git a/docs/topic_assignment-definitions-topic-properties-t.md b/docs/topic_assignment-definitions-topic-properties-t.md index e0236f8..aef8be5 100644 --- a/docs/topic_assignment-definitions-topic-properties-t.md +++ b/docs/topic_assignment-definitions-topic-properties-t.md @@ -1,16 +1,3 @@ -# Untitled schema Schema - -```txt -https://impresso.github.io/impresso-schemas/json/topic_model/topic_assignment.schema.json#/definitions/topic/properties/t -``` - -Topic id - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | -------------------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [topic_assignment.schema.json\*](../out/topic_assignment.schema.json "open original schema") | - ## t Type any of the folllowing: `integer` or `string` ([Details](topic_assignment-definitions-topic-properties-t.md)) diff --git a/docs/topic_assignment-definitions-topic-properties.md b/docs/topic_assignment-definitions-topic-properties.md index 8ada97c..c89940c 100644 --- a/docs/topic_assignment-definitions-topic-properties.md +++ b/docs/topic_assignment-definitions-topic-properties.md @@ -1,16 +1,3 @@ -# Untitled schema Schema - -```txt -https://impresso.github.io/impresso-schemas/json/topic_model/topic_assignment.schema.json#/definitions/topic/properties -``` - - - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | -------------------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [topic_assignment.schema.json\*](../out/topic_assignment.schema.json "open original schema") | - ## properties Type unknown diff --git a/docs/topic_assignment-definitions-topic.md b/docs/topic_assignment-definitions-topic.md index 437f419..bb02f54 100644 --- a/docs/topic_assignment-definitions-topic.md +++ b/docs/topic_assignment-definitions-topic.md @@ -1,16 +1,3 @@ -# Untitled object in undefined Schema - -```txt -https://impresso.github.io/impresso-schemas/json/topic_model/topic_assignment.schema.json#/definitions/topic -``` - -The probability/proportion of a topic in the document - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ------------ | :---------------- | --------------------- | ------------------- | -------------------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | No | Forbidden | Allowed | none | [topic_assignment.schema.json\*](../out/topic_assignment.schema.json "open original schema") | - ## topic Type `object` ([Details](topic_assignment-definitions-topic.md)) diff --git a/docs/topic_assignment-definitions.md b/docs/topic_assignment-definitions.md index e7b66ef..0664bcd 100644 --- a/docs/topic_assignment-definitions.md +++ b/docs/topic_assignment-definitions.md @@ -1,16 +1,3 @@ -# Untitled schema Schema - -```txt -https://impresso.github.io/impresso-schemas/json/topic_model/topic_assignment.schema.json#/definitions -``` - - - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | -------------------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [topic_assignment.schema.json\*](../out/topic_assignment.schema.json "open original schema") | - ## definitions Type unknown diff --git a/docs/topic_assignment-properties-ci_ref.md b/docs/topic_assignment-properties-ci_ref.md index 36f50d5..8253840 100644 --- a/docs/topic_assignment-properties-ci_ref.md +++ b/docs/topic_assignment-properties-ci_ref.md @@ -1,16 +1,3 @@ -# Untitled string in undefined Schema - -```txt -https://impresso.github.io/impresso-schemas/json/topic_model/topic_assignment.schema.json#/properties/ci_ref -``` - -Reference to canonical content item id, typically an article - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | -------------------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [topic_assignment.schema.json\*](../out/topic_assignment.schema.json "open original schema") | - ## ci_ref Type `string` diff --git a/docs/topic_assignment-properties-lang.md b/docs/topic_assignment-properties-lang.md index ba338a7..39c21a3 100644 --- a/docs/topic_assignment-properties-lang.md +++ b/docs/topic_assignment-properties-lang.md @@ -1,16 +1,3 @@ -# Untitled string in undefined Schema - -```txt -https://impresso.github.io/impresso-schemas/json/topic_model/topic_assignment.schema.json#/properties/lang -``` - - - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | -------------------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [topic_assignment.schema.json\*](../out/topic_assignment.schema.json "open original schema") | - ## lang Type `string` diff --git a/docs/topic_assignment-properties-topic_count.md b/docs/topic_assignment-properties-topic_count.md index 81ba63d..8619d4a 100644 --- a/docs/topic_assignment-properties-topic_count.md +++ b/docs/topic_assignment-properties-topic_count.md @@ -1,16 +1,3 @@ -# Untitled integer in undefined Schema - -```txt -https://impresso.github.io/impresso-schemas/json/topic_model/topic_assignment.schema.json#/properties/topic_count -``` - -The number of topics in the topic model - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | -------------------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [topic_assignment.schema.json\*](../out/topic_assignment.schema.json "open original schema") | - ## topic_count Type `integer` diff --git a/docs/topic_assignment-properties-topic_model.md b/docs/topic_assignment-properties-topic_model.md index c7c4216..28ca953 100644 --- a/docs/topic_assignment-properties-topic_model.md +++ b/docs/topic_assignment-properties-topic_model.md @@ -1,16 +1,3 @@ -# Untitled string in undefined Schema - -```txt -https://impresso.github.io/impresso-schemas/json/topic_model/topic_assignment.schema.json#/properties/topic_model -``` - -internal symbolic name of the model, starts with tm - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | -------------------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [topic_assignment.schema.json\*](../out/topic_assignment.schema.json "open original schema") | - ## topic_model Type `string` diff --git a/docs/topic_assignment-properties-topics.md b/docs/topic_assignment-properties-topics.md index af7f9ad..008ea2e 100644 --- a/docs/topic_assignment-properties-topics.md +++ b/docs/topic_assignment-properties-topics.md @@ -1,16 +1,3 @@ -# Untitled array in undefined Schema - -```txt -https://impresso.github.io/impresso-schemas/json/topic_model/topic_assignment.schema.json#/properties/topics -``` - -Sparse representation of topics - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | -------------------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [topic_assignment.schema.json\*](../out/topic_assignment.schema.json "open original schema") | - ## topics Type `object[]` ([Details](topic_assignment-definitions-topic.md)) diff --git a/docs/topic_assignment-properties.md b/docs/topic_assignment-properties.md index a3a7ce8..c89940c 100644 --- a/docs/topic_assignment-properties.md +++ b/docs/topic_assignment-properties.md @@ -1,16 +1,3 @@ -# Untitled schema Schema - -```txt -https://impresso.github.io/impresso-schemas/json/topic_model/topic_assignment.schema.json#/properties -``` - - - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | -------------------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [topic_assignment.schema.json\*](../out/topic_assignment.schema.json "open original schema") | - ## properties Type unknown diff --git a/docs/topic_assignment.md b/docs/topic_assignment.md index a03bb01..702e5e1 100644 --- a/docs/topic_assignment.md +++ b/docs/topic_assignment.md @@ -1,16 +1,3 @@ -# Untitled object in undefined Schema - -```txt -https://impresso.github.io/impresso-schemas/json/topic_model/topic_assignment.schema.json -``` - -A representation for the probabilistic assignments of the topics of a topic model to content items. - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ------------ | :---------------- | --------------------- | ------------------- | ------------------------------------------------------------------------------------------ | -| Can be instantiated | Yes | Unknown status | No | Forbidden | Allowed | none | [topic_assignment.schema.json](../out/topic_assignment.schema.json "open original schema") | - ## Untitled object in undefined Type `object` ([Details](topic_assignment.md)) diff --git a/docs/topic_description-definitions-word_prob-properties-prob.md b/docs/topic_description-definitions-word_prob-properties-prob.md index 68b3f0a..fc0f0aa 100644 --- a/docs/topic_description-definitions-word_prob-properties-prob.md +++ b/docs/topic_description-definitions-word_prob-properties-prob.md @@ -1,16 +1,3 @@ -# Untitled number in undefined Schema - -```txt -https://impresso.github.io/impresso-schemas/json/topic_model/topic_description.schema.json#/definitions/word_prob/properties/prob -``` - - - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [topic_description.schema.json\*](../out/topic_description.schema.json "open original schema") | - ## prob Type `number` diff --git a/docs/topic_description-definitions-word_prob-properties-word.md b/docs/topic_description-definitions-word_prob-properties-word.md index d48908a..95c2a31 100644 --- a/docs/topic_description-definitions-word_prob-properties-word.md +++ b/docs/topic_description-definitions-word_prob-properties-word.md @@ -1,16 +1,3 @@ -# Untitled string in undefined Schema - -```txt -https://impresso.github.io/impresso-schemas/json/topic_model/topic_description.schema.json#/definitions/word_prob/properties/word -``` - - - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [topic_description.schema.json\*](../out/topic_description.schema.json "open original schema") | - ## word Type `string` diff --git a/docs/topic_description-definitions-word_prob-properties.md b/docs/topic_description-definitions-word_prob-properties.md index 1c5cff8..c89940c 100644 --- a/docs/topic_description-definitions-word_prob-properties.md +++ b/docs/topic_description-definitions-word_prob-properties.md @@ -1,16 +1,3 @@ -# Untitled schema Schema - -```txt -https://impresso.github.io/impresso-schemas/json/topic_model/topic_description.schema.json#/definitions/word_prob/properties -``` - - - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [topic_description.schema.json\*](../out/topic_description.schema.json "open original schema") | - ## properties Type unknown diff --git a/docs/topic_description-definitions-word_prob.md b/docs/topic_description-definitions-word_prob.md index 1469e3e..b7a171a 100644 --- a/docs/topic_description-definitions-word_prob.md +++ b/docs/topic_description-definitions-word_prob.md @@ -1,16 +1,3 @@ -# Untitled object in undefined Schema - -```txt -https://impresso.github.io/impresso-schemas/json/topic_model/topic_description.schema.json#/definitions/word_prob -``` - -A (partial) probability distribution of words for a topic. - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ------------ | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | No | Forbidden | Allowed | none | [topic_description.schema.json\*](../out/topic_description.schema.json "open original schema") | - ## word_prob Type `object` ([Details](topic_description-definitions-word_prob.md)) diff --git a/docs/topic_description-definitions.md b/docs/topic_description-definitions.md index 81aa80e..0664bcd 100644 --- a/docs/topic_description-definitions.md +++ b/docs/topic_description-definitions.md @@ -1,16 +1,3 @@ -# Untitled schema Schema - -```txt -https://impresso.github.io/impresso-schemas/json/topic_model/topic_description.schema.json#/definitions -``` - - - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [topic_description.schema.json\*](../out/topic_description.schema.json "open original schema") | - ## definitions Type unknown diff --git a/docs/topic_description-properties-lg.md b/docs/topic_description-properties-lg.md index d71d672..2c1f578 100644 --- a/docs/topic_description-properties-lg.md +++ b/docs/topic_description-properties-lg.md @@ -1,16 +1,3 @@ -# Untitled string in undefined Schema - -```txt -https://impresso.github.io/impresso-schemas/json/topic_model/topic_description.schema.json#/properties/lg -``` - - - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [topic_description.schema.json\*](../out/topic_description.schema.json "open original schema") | - ## lg Type `string` diff --git a/docs/topic_description-properties-meta.md b/docs/topic_description-properties-meta.md index b50bf9e..1975a9d 100644 --- a/docs/topic_description-properties-meta.md +++ b/docs/topic_description-properties-meta.md @@ -1,16 +1,3 @@ -# Untitled string in undefined Schema - -```txt -https://impresso.github.io/impresso-schemas/json/topic_model/topic_description.schema.json#/properties/meta -``` - - - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [topic_description.schema.json\*](../out/topic_description.schema.json "open original schema") | - ## meta Type `string` diff --git a/docs/topic_description-properties-topic.md b/docs/topic_description-properties-topic.md index 51e4fa5..6c5cbee 100644 --- a/docs/topic_description-properties-topic.md +++ b/docs/topic_description-properties-topic.md @@ -1,16 +1,3 @@ -# Untitled integer in undefined Schema - -```txt -https://impresso.github.io/impresso-schemas/json/topic_model/topic_description.schema.json#/properties/topic -``` - - - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [topic_description.schema.json\*](../out/topic_description.schema.json "open original schema") | - ## topic Type `integer` diff --git a/docs/topic_description-properties-topic_description.md b/docs/topic_description-properties-topic_description.md index 8f179b0..6185d71 100644 --- a/docs/topic_description-properties-topic_description.md +++ b/docs/topic_description-properties-topic_description.md @@ -1,16 +1,3 @@ -# Untitled string in undefined Schema - -```txt -https://impresso.github.io/impresso-schemas/json/topic_model/topic_description.schema.json#/properties/topic_description -``` - - - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [topic_description.schema.json\*](../out/topic_description.schema.json "open original schema") | - ## topic_description Type `string` diff --git a/docs/topic_description-properties-topic_model.md b/docs/topic_description-properties-topic_model.md index 10f09f3..28ca953 100644 --- a/docs/topic_description-properties-topic_model.md +++ b/docs/topic_description-properties-topic_model.md @@ -1,16 +1,3 @@ -# Untitled string in undefined Schema - -```txt -https://impresso.github.io/impresso-schemas/json/topic_model/topic_description.schema.json#/properties/topic_model -``` - - - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [topic_description.schema.json\*](../out/topic_description.schema.json "open original schema") | - ## topic_model Type `string` diff --git a/docs/topic_description-properties-word_probs.md b/docs/topic_description-properties-word_probs.md index 04984c1..866f64e 100644 --- a/docs/topic_description-properties-word_probs.md +++ b/docs/topic_description-properties-word_probs.md @@ -1,16 +1,3 @@ -# Untitled array in undefined Schema - -```txt -https://impresso.github.io/impresso-schemas/json/topic_model/topic_description.schema.json#/properties/word_probs -``` - - - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [topic_description.schema.json\*](../out/topic_description.schema.json "open original schema") | - ## word_probs Type `object[]` ([Details](topic_description-definitions-word_prob.md)) diff --git a/docs/topic_description-properties.md b/docs/topic_description-properties.md index 39c881a..c89940c 100644 --- a/docs/topic_description-properties.md +++ b/docs/topic_description-properties.md @@ -1,16 +1,3 @@ -# Untitled schema Schema - -```txt -https://impresso.github.io/impresso-schemas/json/topic_model/topic_description.schema.json#/properties -``` - - - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ----------------------- | :---------------- | --------------------- | ------------------- | ---------------------------------------------------------------------------------------------- | -| Can be instantiated | No | Unknown status | Unknown identifiability | Forbidden | Allowed | none | [topic_description.schema.json\*](../out/topic_description.schema.json "open original schema") | - ## properties Type unknown diff --git a/docs/topic_description.md b/docs/topic_description.md index 262b412..94f86a6 100644 --- a/docs/topic_description.md +++ b/docs/topic_description.md @@ -1,16 +1,3 @@ -# Untitled object in undefined Schema - -```txt -https://impresso.github.io/impresso-schemas/json/topic_model/topic_description.schema.json -``` - -A representation for each topic (=probability distribution of words) of a topic model. - - -| Abstract | Extensible | Status | Identifiable | Custom Properties | Additional Properties | Access Restrictions | Defined In | -| :------------------ | ---------- | -------------- | ------------ | :---------------- | --------------------- | ------------------- | -------------------------------------------------------------------------------------------- | -| Can be instantiated | Yes | Unknown status | No | Forbidden | Allowed | none | [topic_description.schema.json](../out/topic_description.schema.json "open original schema") | - ## Untitled object in undefined Type `object` ([Details](topic_description.md)) diff --git a/examples/language_identification/example0.json b/examples/language_identification/example0.json index 635093b..598cf2a 100644 --- a/examples/language_identification/example0.json +++ b/examples/language_identification/example0.json @@ -1,31 +1,63 @@ { - "tp": "ar", - "id": "luxzeit1858-1859-01-01-a-i0001", - "len": 1138, - "orig_lg": "de", - "alphabetical_ratio": 0.76, - "langdetect": [ - { - "lang": "de", - "prob": 1 - } - ], - "langid": [ - { - "lang": "de", - "prob": 1 - } - ], - "impresso_ft": [ - { - "lang": "de", - "prob": 1 - } - ], - "wp_ft": [ - { - "lang": "de", - "prob": 0.99 - } - ] -} \ No newline at end of file + "id": "luxzeit1858-1859-01-18-a-i0026", + "lg": "fr", + "lg_decision": "voting", + "tp": "tb", + "len": 63, + "orig_lg": null, + "alphabetical_ratio": 0.254, + "impresso_language_identifier_version": { + "version": "v1.4.1", + "ts": "2020-12-28T10:27:11+00:00" + }, + "language_identifier_version": { + "version": "v1.4.1", + "ts": "2020-12-28T10:15:45+00:00" + }, + "impresso_ft": [ + { + "lang": "fr", + "prob": 0.969 + }, + { + "lang": "de", + "prob": 0.03 + } + ], + "langdetect": [ + { + "lang": "ro", + "prob": 0.667 + }, + { + "lang": "ca", + "prob": 0.333 + } + ], + "langid": [ + { + "lang": "ro", + "prob": 0.655 + } + ], + "wp_ft": [ + { + "lang": "es", + "prob": 0.305 + }, + { + "lang": "ca", + "prob": 0.121 + }, + { + "lang": "war", + "prob": 0.106 + } + ], + "votes": [ + { + "lang": "fr", + "vote": 0.942 + } + ] +} diff --git a/examples/language_identification/example1.json b/examples/language_identification/example1.json index d71878a..e801152 100644 --- a/examples/language_identification/example1.json +++ b/examples/language_identification/example1.json @@ -1,6 +1,7 @@ { - "tp": "img", - "id": "luxzeit1858-1859-01-01-a-i0017", - "len": 0, - "orig_lg": null -} \ No newline at end of file + "id": "HRV-1801-08-05-a-i0012", + "lg": null, + "tp": "img", + "len": 0, + "orig_lg": null +} diff --git a/examples/language_identification/example2.json b/examples/language_identification/example2.json index fc84b69..779160b 100644 --- a/examples/language_identification/example2.json +++ b/examples/language_identification/example2.json @@ -1,43 +1,41 @@ { - "tp": "tb", - "id": "luxzeit1858-1859-01-01-a-i0019", - "len": 278, - "orig_lg": null, - "alphabetical_ratio": 0.39, - "langdetect": [ - { - "lang": "de", - "prob": 1 - } - ], - "langid": [ - { - "lang": "lb", - "prob": 0.94 - } - ], - "impresso_ft": [ - { - "lang": "de", - "prob": 0.99 - }, - { - "lang": "fr", - "prob": 0.01 - } - ], - "wp_ft": [ - { - "lang": "uk", - "prob": 0.14 - }, - { - "lang": "es", - "prob": 0.07 - }, - { - "lang": "lb", - "prob": 0.06 - } - ] -} \ No newline at end of file + "id": "HRV-1801-08-08-a-i0010", + "lg": "de", + "lg_decision": "all", + "tp": "ar", + "len": 2701, + "orig_lg": null, + "alphabetical_ratio": 0.758, + "impresso_language_identifier_version": { + "version": "v1.4.1", + "ts": "2020-12-28T10:27:10+00:00" + }, + "language_identifier_version": { + "version": "v1.4.1", + "ts": "2020-12-28T10:15:15+00:00" + }, + "impresso_ft": [ + { + "lang": "de", + "prob": 0.999 + } + ], + "langdetect": [ + { + "lang": "de", + "prob": 1.0 + } + ], + "langid": [ + { + "lang": "de", + "prob": 1.0 + } + ], + "wp_ft": [ + { + "lang": "de", + "prob": 0.993 + } + ] +} diff --git a/json/language_identification/language_identification.schema.json b/json/language_identification/language_identification.schema.json index 0ae399a..38b839e 100644 --- a/json/language_identification/language_identification.schema.json +++ b/json/language_identification/language_identification.schema.json @@ -1,87 +1,190 @@ { - "$schema": "http://json-schema.org/draft-06/schema#", - "$id": "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json", - "description": "A representation for the language identifications of various models per content item.", - "type": "object", - "properties": { - "tp": { - "type": "string", - "description": "Type of the content item, cf. https://github.com/impresso/impresso-schemas/blob/master/json/newspaper/contentitem.schema.json" - }, - "id": { - "type": "string", - "description": "Canonical ID of the newspaper issue (e.g. GDL-1900-01-02-a), cf. https://github.com/impresso/impresso-schemas/blob/master/json/newspaper/contentitem.schema.json" - }, - "len": { - "type": "integer", - "description": "Length of content item" - }, - "orig_lg": { - "type": [ - "string", - "null" - ], - "description": "Original language of the content item as provided by the meta data, cf. https://github.com/impresso/impresso-schemas/blob/master/json/newspaper/contentitem.schema.json", - "pattern": "^[a-z]{2}$" - }, - "alphabetical_ratio": { - "type": "number", - "description": "Ratio of alphabetical characters (letters) wtr to text length of content item" - }, - "langdetect": { - "type": "array", - "items": { - "$ref": "#/definitions/lid" - }, - "description": "List of predicted languages using Langdetect, sorted by probability" + "$schema": "http://json-schema.org/draft-06/schema#", + "$id": "https://impresso.github.io/impresso-schemas/json/language_identification/language_identification.schema.json", + "title": "Impresso Language Identification Information", + "description": "A representation for information relevant to impresso's content item language recognition. This defines the output of the following impresso NLP component. https://github.com/impresso/impresso-language-identification ", + "type": "object", + "properties": { + "id": { + "type": "string", + "description": "The unique identifier for a content item, cf. https://github.com/impresso/impresso-schemas/blob/master/json/newspaper/contentitem.schema.json" + }, + "orig_lg": { + "type": [ + "string", + "null" + ], + "oneOf": [ + { + "title": "null", + "description": "No information on language from original metadata is available.", + "type": "null" }, - "langid": { - "type": "array", - "items": { - "$ref": "#/definitions/lid" - }, - "description": "List of predicted languages using Langid, sorted by probability" + { + "$ref": "#/definitions/langISO639Type" + } + ], + "description": "Original language of the content item as provided by the metadata, cf. https://github.com/impresso/impresso-schemas/blob/master/json/newspaper/contentitem.schema.json" + }, + "lg": { + "type": [ + "string", + "null" + ], + "oneOf": [ + { + "title": "null", + "type": "null" }, - "impresso_ft": { - "type": "array", - "items": { - "$ref": "#/definitions/lid" + { + "$ref": "#/definitions/langISO639Type" + } + ], + "description": "Computed language of the content item, cf. https://github.com/impresso/impresso-schemas/blob/master/json/newspaper/contentitem.schema.json" + }, + "lg_decision": { + "enum": [ + "all", + "all-but-impresso-ft", + "voting", + "dominant-by-len", + "dominant-by-lowvote" + ], + "type": "string", + "description": "An identifier for the decision strategy applied to the content item: 'all' = all LID systems/info agree; 'all-but-impresso-ft' = all LID except impresso_ft agree on a language other than de/fr; 'dominant-by-len' = the most frequent language of the ensemble decisions is selected because there are too few characters; 'dominant-by-lowvote' = the most frequent language of the ensemble decisions is selected because there are too few votes; 'voting' = the language with the highest vote count is selected " + }, + "tp": { + "type": "string", + "description": "Type of the content item, cf. https://github.com/impresso/impresso-schemas/blob/master/json/newspaper/contentitem.schema.json" + }, + "len": { + "type": "integer", + "description": "Number of characters of content item", + "minimum": 0 + }, + "impresso_language_identifier_version": { + "$ref": "#/definitions/versionType", + "description": "Version information of used impresso language identifier script and the file creation timestamp" + }, + "language_identifier_version": { + "$ref": "#/definitions/versionType", + "description": "Version information of used impresso language identifier script and the timestamp of the file used for the decision" + }, + "alphabetical_ratio": { + "type": [ + "number", + "null" + ], + "description": "Ratio of alphabetical characters (Unicode letter class matched by \\w) w.r.t. text length of content item", + "minimum": 0, + "maximum": 1 + }, + "langdetect": { + "type": "array", + "items": { + "$ref": "#/definitions/lidType" + }, + "description": "List of predicted languages using Langdetect, sorted by probability" + }, + "langid": { + "type": "array", + "items": { + "$ref": "#/definitions/lidType" + }, + "description": "List of predicted languages using Langid, sorted by probability" + }, + "impresso_ft": { + "type": "array", + "items": { + "$ref": "#/definitions/lidType" + }, + "description": "List of predicted languages using a FastText model trained on Impresso articles, sorted by probability" + }, + "wp_ft": { + "type": "array", + "items": { + "$ref": "#/definitions/lidType" + }, + "description": "List of predicted languages using a FastText model trained on Wikipedia, sorted by probability" + }, + "votes": { + "type": "array", + "items": [ + { + "type": "object", + "properties": { + "lang": { + "$ref": "#/definitions/langISO639Type" }, - "description": "List of predicted languages using a FastText model trained on Impresso articles, sorted by probability" + "vote": { + "type": "number" + } + }, + "required": [ + "lang", + "vote" + ] + } + ] + } + }, + "required": [ + "tp", + "id", + "len", + "lg", + "orig_lg" + ], + "definitions": { + "lidType": { + "title": "lidType", + "description": "Predicted language and its probability", + "type": "object", + "properties": { + "lang": { + "$ref": "#/definitions/langISO639Type" }, - "wp_ft": { - "type": "array", - "items": { - "$ref": "#/definitions/lid" - }, - "description": "List of predicted languages using a FastText model trained on Wikipedia, sorted by probability" + "prob": { + "$ref": "#/definitions/probType" } + }, + "required": [ + "lang", + "prob" + ] }, - "required": [ - "tp", - "id", - "len", - "orig_lg" - ], - "definitions": { - "lid": { - "description": "Predicted language and its probability", - "type": "object", - "properties": { - "lang": { - "type": "string", - "description": "https://en.wikipedia.org/wiki/List_of_ISO_639-2_codes", - "pattern": "^[a-z]{2}$" - }, - "prob": { - "type": "number", - "description": "Probability of prediction" - } - }, - "required": [ - "lang", - "prob" - ] + "langISO639Type": { + "type": "string", + "title": "langISO639Type", + "description": "Two- or three-letter ISO language abbreviation, cf. https://en.wikipedia.org/wiki/List_of_ISO_639-2_codes or https://en.wikipedia.org/wiki/List_of_ISO_639-3_codes", + "pattern": "^[a-z]{2,3}$" + }, + "probType": { + "type": "number", + "title": "probType", + "description": "Probability of the prediction", + "minimum": 0, + "maximum": 1 + }, + "versionType": { + "title": "versionType", + "description": "Administrative information on tool version and data creation time.", + "type": "object", + "properties": { + "versionType": { + "description": "Version of tool. Either date or output of command 'git describe'", + "type": "string" + }, + "ts": { + "description": "timestamp of creation of the JSON file (e.g. '2018-09-18T08:00:08+00:00')", + "type": "string", + "pattern": "^[0-9]{4}-[0-9]{2}-[0-9]{2}T[0-9]{2}:[0-9]{2}:[0-9]{2}(Z|\\+00:00)$" } + }, + "required": [ + "ts", + "version" + ] } -} \ No newline at end of file + } +} diff --git a/scripts/jsonlschema.py b/scripts/jsonlschema.py new file mode 100755 index 0000000..1c57b1d --- /dev/null +++ b/scripts/jsonlschema.py @@ -0,0 +1,109 @@ +#!/usr/bin/python3 +# -*- coding: utf-8 -*- +""" +Validate a jsonline file (raw or compressed) against a schema +""" + +__appname__ = "jsonlschema" +__author__ = "simon.clematide@uzh.ch" +__version__ = "v1.0" + + +import sys +import logging +import json +from jsonschema import validate +from smart_open import open +from typing import Iterable +log = logging.getLogger(__name__) + +sys.stdin.reconfigure(encoding='utf-8') +sys.stdout.reconfigure(encoding='utf-8') +sys.stderr.reconfigure(encoding='utf-8') + + +class JSONLSchemaValidator(object): + + def __init__(self, schema, input_files, output_file=None): + self.input_files = input_files + self.output_writer = open(output_file, mode="w", encoding="utf-8") if output_file is not None else sys.stdout + self.schema = json.load(open(schema,encoding="utf-8")) + + def run(self) -> None: + + try: + self.process() + except: + self.output_writer.close() + + + def process(self) -> None: + for jo in self.next_json_object(): + validate(instance=jo, schema=self.schema) + print(json.dumps(jo,ensure_ascii=False,separators=(",", ":")),file=self.output_writer) + + + + def next_json_object(self) -> Iterable[dict]: + """Yield each json object. + + :return: Iterator over json objects. + :rtype: Iterable[dict] + + """ + + for infile in self.input_files: + with open(infile, encoding="utf-8") as infile: + for line in infile: + yield json.loads(line) + + + + +if __name__ == '__main__': + import argparse + description = "" + epilog = "" + parser = argparse.ArgumentParser(description=description, epilog=epilog) + parser.add_argument('-l', '--logfile', dest='logfile', + help='write log to FILE', metavar='FILE') + parser.add_argument('-v', '--verbose', dest='verbose',default=2,type=int, metavar="LEVEL", + help='set verbosity level: 0=CRITICAL, 1=ERROR, 2=WARNING, 3=INFO 4=DEBUG (default %(default)s)') + + parser.add_argument( + "-o", + "--output-file", + default="/dev/stdout", + help="Output file, writing to stdout if not specified", + ) + + parser.add_argument( + "-i", + "--input-files", + metavar="JSONL", + nargs="*", + help="Input files, reading from stdin if not provided", + ) + parser.add_argument( + "schema", + metavar="SCHEMA", + help="path to schema", + ) + + arguments = parser.parse_args() + + log_levels = [logging.CRITICAL, logging.ERROR, logging.WARNING, + logging.INFO, logging.DEBUG] + logging.basicConfig(level=log_levels[arguments.verbose], + format='%(asctime)-15s %(levelname)s: %(message)s') + + + jsonl_schema_validator_args = { + "schema", + "output_file", + "input_files", + } + # launching application ... + JSONLSchemaValidator( + **{k: v for k, v in vars(arguments).items() if k in jsonl_schema_validator_args} + ).run()