Merge pull request #38 from impresso/text_reuse_schemas

Text reuse schemas

Makefile

@@ -16,6 +16,8 @@ tests:
 	jsonschema -V Draft202012Validator -i examples/entities/example1.json  json/entities/entities.schema.json && $(print-test-ok)|| $(print-test-failed)
 	jsonschema -V Draft202012Validator -i examples/entities/example2.json  json/entities/entities.schema.json && $(print-test-ok)|| $(print-test-failed)
 	jsonschema -V Draft202012Validator -i examples/versioning_manifest/canonical_v0-0-1.json  json/versioning/manifest.schema.json && $(print-test-ok)|| $(print-test-failed)
+	jsonschema -V Draft202012Validator -i examples/text_reuse/tr_cluster_example.json  json/text_reuse/cluster.schema.json && $(print-test-ok)|| $(print-test-failed)
+	jsonschema -V Draft202012Validator -i examples/text_reuse/tr_passage_example.json  json/text_reuse/passage.schema.json && $(print-test-ok)|| $(print-test-failed)
 
 
 clean-documentation:
@@ -30,6 +32,7 @@ documentation:
 	jsonschema2md -d json/entities/ --header false -n -v 2020-12 -o docs -x -  -s propTable
 	#jsonschema2md -d json/linguistic_annotation/ -n -v 06 -o docs
 	jsonschema2md -d json/versioning/ --header false -n -v 2024-02 -o docs -x -  -s propTable
+	jsonschema2md -d json/text_reuse/ --header false -n -v 2024-09 -o docs -x -  -s propTable
 
 ##########################################################################################
 # Simple macros for tests

docs/cluster-properties-cluster_size.md

@@ -0,0 +1,3 @@
+## cluster\_size Type
+
+`integer`

docs/cluster-properties-doc_ids-items.md

@@ -0,0 +1,13 @@
+## items Type
+
+`string`
+
+## items Constraints
+
+**pattern**: the string must match the following regular expression: 
+
+```regexp
+^[a-zA-Z0-9]+-\d{4}-(0[1-9]|1[0-2])-(0[1-9]|[12]\d|3[01])-[a-z]-i\d{4}$
+```
+
+[try pattern](https://regexr.com/?expression=%5E%5Ba-zA-Z0-9%5D%2B-%5Cd%7B4%7D-\(0%5B1-9%5D%7C1%5B0-2%5D\)-\(0%5B1-9%5D%7C%5B12%5D%5Cd%7C3%5B01%5D\)-%5Ba-z%5D-i%5Cd%7B4%7D%24 "try regular expression with regexr.com")

docs/cluster-properties-doc_ids.md

@@ -0,0 +1,3 @@
+## doc\_ids Type
+
+`string[]`

docs/cluster-properties-id.md

@@ -0,0 +1,3 @@
+## id Type
+
+`string`

docs/cluster-properties-lexical_overlap.md

@@ -0,0 +1,3 @@
+## lexical\_overlap Type
+
+`number`

docs/cluster-properties-max_date.md

@@ -0,0 +1,13 @@
+## max\_date Type
+
+`string`
+
+## max\_date Constraints
+
+**pattern**: the string must match the following regular expression: 
+
+```regexp
+^(\d{4})-(0[1-9]|1[0-2])-(0[1-9]|[12]\d|3[01])$
+```
+
+[try pattern](https://regexr.com/?expression=%5E\(%5Cd%7B4%7D\)-\(0%5B1-9%5D%7C1%5B0-2%5D\)-\(0%5B1-9%5D%7C%5B12%5D%5Cd%7C3%5B01%5D\)%24 "try regular expression with regexr.com")

docs/cluster-properties-min_date.md

@@ -0,0 +1,13 @@
+## min\_date Type
+
+`string`
+
+## min\_date Constraints
+
+**pattern**: the string must match the following regular expression: 
+
+```regexp
+^(\d{4})-(0[1-9]|1[0-2])-(0[1-9]|[12]\d|3[01])$
+```
+
+[try pattern](https://regexr.com/?expression=%5E\(%5Cd%7B4%7D\)-\(0%5B1-9%5D%7C1%5B0-2%5D\)-\(0%5B1-9%5D%7C%5B12%5D%5Cd%7C3%5B01%5D\)%24 "try regular expression with regexr.com")

docs/cluster-properties-newspapers-items.md

@@ -0,0 +1,3 @@
+## items Type
+
+`string`

docs/cluster-properties-newspapers.md

@@ -0,0 +1,3 @@
+## newspapers Type
+
+`string[]`

docs/cluster-properties-passages-items.md

@@ -0,0 +1,13 @@
+## items Type
+
+`string`
+
+## items Constraints
+
+**pattern**: the string must match the following regular expression: 
+
+```regexp
+^[a-zA-Z0-9]+-\d{4}-(0[1-9]|1[0-2])-(0[1-9]|[12]\d|3[01])-[a-z]-i\d{4}@\d+:\d+$
+```
+
+[try pattern](https://regexr.com/?expression=%5E%5Ba-zA-Z0-9%5D%2B-%5Cd%7B4%7D-\(0%5B1-9%5D%7C1%5B0-2%5D\)-\(0%5B1-9%5D%7C%5B12%5D%5Cd%7C3%5B01%5D\)-%5Ba-z%5D-i%5Cd%7B4%7D%40%5Cd%2B%3A%5Cd%2B%24 "try regular expression with regexr.com")

docs/cluster-properties-passages.md

@@ -0,0 +1,3 @@
+## passages Type
+
+`string[]`

docs/cluster-properties-time_delta.md

@@ -0,0 +1,3 @@
+## time\_delta Type
+
+`integer`

docs/cluster.md

@@ -0,0 +1,199 @@
+## Text-Reuse Cluster Type
+
+`object` ([Text-Reuse Cluster](cluster.md))
+
+# Text-Reuse Cluster Properties
+
+| Property                             | Type      | Required | Nullable       | Defined by                                                                                                                                                                |
+| :----------------------------------- | :-------- | :------- | :------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| [id](#id)                            | `string`  | Required | cannot be null | [Text-Reuse Cluster](cluster-properties-id.md "https://impresso.github.io/impresso-schemas/json/text_reuse/cluster.schema.json#/properties/id")                           |
+| [min\_date](#min_date)               | `string`  | Required | cannot be null | [Text-Reuse Cluster](cluster-properties-min_date.md "https://impresso.github.io/impresso-schemas/json/text_reuse/cluster.schema.json#/properties/min_date")               |
+| [max\_date](#max_date)               | `string`  | Required | cannot be null | [Text-Reuse Cluster](cluster-properties-max_date.md "https://impresso.github.io/impresso-schemas/json/text_reuse/cluster.schema.json#/properties/max_date")               |
+| [cluster\_size](#cluster_size)       | `integer` | Required | cannot be null | [Text-Reuse Cluster](cluster-properties-cluster_size.md "https://impresso.github.io/impresso-schemas/json/text_reuse/cluster.schema.json#/properties/cluster_size")       |
+| [time\_delta](#time_delta)           | `integer` | Required | cannot be null | [Text-Reuse Cluster](cluster-properties-time_delta.md "https://impresso.github.io/impresso-schemas/json/text_reuse/cluster.schema.json#/properties/time_delta")           |
+| [newspapers](#newspapers)            | `array`   | Required | cannot be null | [Text-Reuse Cluster](cluster-properties-newspapers.md "https://impresso.github.io/impresso-schemas/json/text_reuse/cluster.schema.json#/properties/newspapers")           |
+| [passages](#passages)                | `array`   | Required | cannot be null | [Text-Reuse Cluster](cluster-properties-passages.md "https://impresso.github.io/impresso-schemas/json/text_reuse/cluster.schema.json#/properties/passages")               |
+| [doc\_ids](#doc_ids)                 | `array`   | Required | cannot be null | [Text-Reuse Cluster](cluster-properties-doc_ids.md "https://impresso.github.io/impresso-schemas/json/text_reuse/cluster.schema.json#/properties/doc_ids")                 |
+| [lexical\_overlap](#lexical_overlap) | `number`  | Required | cannot be null | [Text-Reuse Cluster](cluster-properties-lexical_overlap.md "https://impresso.github.io/impresso-schemas/json/text_reuse/cluster.schema.json#/properties/lexical_overlap") |
+
+## id
+
+Unique identifier for this cluster.
+
+`id`
+
+*   is required
+
+*   Type: `string`
+
+*   cannot be null
+
+*   defined in: [Text-Reuse Cluster](cluster-properties-id.md "https://impresso.github.io/impresso-schemas/json/text_reuse/cluster.schema.json#/properties/id")
+
+### id Type
+
+`string`
+
+## min\_date
+
+Earliest date represented in the article passages of the cluster
+
+`min_date`
+
+*   is required
+
+*   Type: `string`
+
+*   cannot be null
+
+*   defined in: [Text-Reuse Cluster](cluster-properties-min_date.md "https://impresso.github.io/impresso-schemas/json/text_reuse/cluster.schema.json#/properties/min_date")
+
+### min\_date Type
+
+`string`
+
+### min\_date Constraints
+
+**pattern**: the string must match the following regular expression: 
+
+```regexp
+^(\d{4})-(0[1-9]|1[0-2])-(0[1-9]|[12]\d|3[01])$
+```
+
+[try pattern](https://regexr.com/?expression=%5E\(%5Cd%7B4%7D\)-\(0%5B1-9%5D%7C1%5B0-2%5D\)-\(0%5B1-9%5D%7C%5B12%5D%5Cd%7C3%5B01%5D\)%24 "try regular expression with regexr.com")
+
+## max\_date
+
+Latest date represented in the article passages of the cluster
+
+`max_date`
+
+*   is required
+
+*   Type: `string`
+
+*   cannot be null
+
+*   defined in: [Text-Reuse Cluster](cluster-properties-max_date.md "https://impresso.github.io/impresso-schemas/json/text_reuse/cluster.schema.json#/properties/max_date")
+
+### max\_date Type
+
+`string`
+
+### max\_date Constraints
+
+**pattern**: the string must match the following regular expression: 
+
+```regexp
+^(\d{4})-(0[1-9]|1[0-2])-(0[1-9]|[12]\d|3[01])$
+```
+
+[try pattern](https://regexr.com/?expression=%5E\(%5Cd%7B4%7D\)-\(0%5B1-9%5D%7C1%5B0-2%5D\)-\(0%5B1-9%5D%7C%5B12%5D%5Cd%7C3%5B01%5D\)%24 "try regular expression with regexr.com")
+
+## cluster\_size
+
+Number of article passages present in the cluster.
+
+`cluster_size`
+
+*   is required
+
+*   Type: `integer`
+
+*   cannot be null
+
+*   defined in: [Text-Reuse Cluster](cluster-properties-cluster_size.md "https://impresso.github.io/impresso-schemas/json/text_reuse/cluster.schema.json#/properties/cluster_size")
+
+### cluster\_size Type
+
+`integer`
+
+## time\_delta
+
+Number of days between min\_date and max\_date.
+
+`time_delta`
+
+*   is required
+
+*   Type: `integer`
+
+*   cannot be null
+
+*   defined in: [Text-Reuse Cluster](cluster-properties-time_delta.md "https://impresso.github.io/impresso-schemas/json/text_reuse/cluster.schema.json#/properties/time_delta")
+
+### time\_delta Type
+
+`integer`
+
+## newspapers
+
+List of all newspapers represented in this cluster with article passages.
+
+`newspapers`
+
+*   is required
+
+*   Type: `string[]`
+
+*   cannot be null
+
+*   defined in: [Text-Reuse Cluster](cluster-properties-newspapers.md "https://impresso.github.io/impresso-schemas/json/text_reuse/cluster.schema.json#/properties/newspapers")
+
+### newspapers Type
+
+`string[]`
+
+## passages
+
+List of all article passages composing this cluster.
+
+`passages`
+
+*   is required
+
+*   Type: `string[]`
+
+*   cannot be null
+
+*   defined in: [Text-Reuse Cluster](cluster-properties-passages.md "https://impresso.github.io/impresso-schemas/json/text_reuse/cluster.schema.json#/properties/passages")
+
+### passages Type
+
+`string[]`
+
+## doc\_ids
+
+List of all article passages composing this cluster.
+
+`doc_ids`
+
+*   is required
+
+*   Type: `string[]`
+
+*   cannot be null
+
+*   defined in: [Text-Reuse Cluster](cluster-properties-doc_ids.md "https://impresso.github.io/impresso-schemas/json/text_reuse/cluster.schema.json#/properties/doc_ids")
+
+### doc\_ids Type
+
+`string[]`
+
+## lexical\_overlap
+
+Computed average lexical overlap of the passages within the cluster.
+
+`lexical_overlap`
+
+*   is required
+
+*   Type: `number`
+
+*   cannot be null
+
+*   defined in: [Text-Reuse Cluster](cluster-properties-lexical_overlap.md "https://impresso.github.io/impresso-schemas/json/text_reuse/cluster.schema.json#/properties/lexical_overlap")
+
+### lexical\_overlap Type
+
+`number`

docs/contentitem-properties-ro.md

@@ -0,0 +1,3 @@
+## ro Type
+
+`integer`

docs/contentitem.md

@@ -15,6 +15,7 @@
 | [d](#d)         | `string`  | Optional | cannot be null | [Content Item](contentitem-properties-d.md "https://impresso.github.io/impresso-schemas/json/newspaper/contentitem.schema.json#/properties/d")         |
 | [ts](#ts)       | `string`  | Required | cannot be null | [Content Item](contentitem-properties-ts.md "https://impresso.github.io/impresso-schemas/json/newspaper/contentitem.schema.json#/properties/ts")       |
 | [lg](#lg)       | `string`  | Optional | cannot be null | [Content Item](contentitem-properties-lg.md "https://impresso.github.io/impresso-schemas/json/newspaper/contentitem.schema.json#/properties/lg")       |
+| [ro](#ro)       | `integer` | Optional | cannot be null | [Content Item](contentitem-properties-ro.md "https://impresso.github.io/impresso-schemas/json/newspaper/contentitem.schema.json#/properties/ro")       |
 | [ft](#ft)       | `string`  | Optional | cannot be null | [Content Item](contentitem-properties-ft.md "https://impresso.github.io/impresso-schemas/json/newspaper/contentitem.schema.json#/properties/ft")       |
 | [lb](#lb)       | `array`   | Optional | cannot be null | [Content Item](contentitem-properties-lb.md "https://impresso.github.io/impresso-schemas/json/newspaper/contentitem.schema.json#/properties/lb")       |
 | [pb](#pb)       | `array`   | Optional | cannot be null | [Content Item](contentitem-properties-pb.md "https://impresso.github.io/impresso-schemas/json/newspaper/contentitem.schema.json#/properties/pb")       |
@@ -217,6 +218,24 @@ two letter language code
 
 [try pattern](https://regexr.com/?expression=%5E%5Ba-z%5D%7B2%7D%24 "try regular expression with regexr.com")
 
+## ro
+
+Reading order index of the content item, for the table of contents view on the interface. If not defined, the CI number (after 'i' in the ID) should be used.
+
+`ro`
+
+*   is optional
+
+*   Type: `integer`
+
+*   cannot be null
+
+*   defined in: [Content Item](contentitem-properties-ro.md "https://impresso.github.io/impresso-schemas/json/newspaper/contentitem.schema.json#/properties/ro")
+
+### ro Type
+
+`integer`
+
 ## ft
 
 the rebuilt fulltext

docs/issue-definitions-metadata-properties-ro.md

@@ -0,0 +1,3 @@
+## ro Type
+
+`integer`