added documentation about token hyphenation in the page schema (close…

…s issue #4)
impresso · Oct 8, 2019 · 7864709 · 7864709
1 parent f0c8f4b
commit 7864709
Show file tree

Hide file tree

Showing 3 changed files with 68 additions and 0 deletions.
diff --git a/docs/page.schema.json b/docs/page.schema.json
@@ -77,6 +77,18 @@
                                                         "s": {
                                                             "type": "integer",
                                                             "description": "A style ID as defined in issue.schema.json/s"
+                                                        },
+                                                        "gn": {
+                                                            "type": "boolean",
+                                                            "description": "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`."
+                                                        },
+                                                        "hy": {
+                                                            "type": "boolean",
+                                                            "description": "Indicates whether the token constitutes the first part of a hyphenated word. When not specified it is assumed to be `false`."
+                                                        },
+                                                        "nf": {
+                                                            "type": "string",
+                                                            "description": "It is specified on the second part of a hyphenated word, and contains its normalized (reconstructed) form."
                                                         }
                                                     },
                                                     "required": [

diff --git a/docs/page.schema.md b/docs/page.schema.md
@@ -186,6 +186,9 @@ All items must be of the type: `object` with following properties:
 | Property | Type    | Required     |
 | -------- | ------- | ------------ |
 | `c`      | array   | **Required** |
+| `gn`     | boolean | Optional     |
+| `hy`     | boolean | Optional     |
+| `nf`     | string  | Optional     |
 | `s`      | integer | Optional     |
 | `tx`     | string  | **Required** |
 
@@ -204,6 +207,47 @@ Array type: `integer[]`
 
 All items must be of the type: `integer`
 
+#### 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`.
+
+`gn`
+
+- is optional
+- type: `boolean`
+
+##### gn Type
+
+`boolean`
+
+#### hy
+
+Indicates whether the token constitutes the first part of a hyphenated word. When not specified it is assumed to be
+`false`.
+
+`hy`
+
+- is optional
+- type: `boolean`
+
+##### hy Type
+
+`boolean`
+
+#### nf
+
+It is specified on the second part of a hyphenated word, and contains its normalized (reconstructed) form.
+
+`nf`
+
+- is optional
+- type: `string`
+
+##### nf Type
+
+`string`
+
 #### s
 
 A style ID as defined in issue.schema.json/s

diff --git a/json/newspaper/page.schema.json b/json/newspaper/page.schema.json
@@ -77,6 +77,18 @@
                                                         "s": {
                                                             "type": "integer",
                                                             "description": "A style ID as defined in issue.schema.json/s"
+                                                        },
+                                                        "gn": {
+                                                            "type": "boolean",
+                                                            "description": "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`."
+                                                        },
+                                                        "hy":{
+                                                          "type": "boolean",
+                                                          "description": "Indicates whether the token constitutes the first part of a hyphenated word. When not specified it is assumed to be `false`."
+                                                        },
+                                                        "nf":{
+                                                          "type": "string",
+                                                          "description": "It is specified on the second part of a hyphenated word, and contains its normalized (reconstructed) form."
                                                         }
                                                     },
                                                     "required": ["c", "tx"]