unicode-org · jowilco · Jun 6, 2024 · Jun 6, 2024 · Jun 6, 2024 · Jun 7, 2024
diff --git a/.gitignore b/.gitignore
@@ -43,6 +43,7 @@ perf-*.xml
 test-*.xml
 
 # Directories
+.idea/
 .settings/
 .vs/
 .vscode/

diff --git a/uax/uax42/Readme.md b/uax/uax42/Readme.md
@@ -0,0 +1,24 @@
+# Generating TR42
+
+## Step 1 - Generate property value fragments
+
+- Run org.unicode.xml.GeneratePropertyValues to populate the UNICODETOOLS_REPO_DIR/uax/uax42/fragments/ folder.
+
+## Step 2 - Generate TR42 index.html and index.rnc 
+
+- In UNICODETOOLS_REPO_DIR/uax/uax42/ run `mvn xml:transform`
+
+  index.html and index.rnc will be generated in UNICODETOOLS_REPO_DIR/uax/uax42/output/
+
+## Step 3 - Validate generated UAX XML files
+
+You'll need a [RELAX NG](https://relaxng.org/) schema validator. We'll use [jing-trang](https://github.
+com/relaxng/jing-trang) in this example.
+
+1. Clone and build [jing-trang](https://github.com/relaxng/jing-trang)
+2. Run the following:
+    ```
+   java -jar C:\_git\jing-trang\build\jing.jar -c UNICODETOOLS_REPO_DIR\uax\uax42\output\index.rnc <path to UAX xml file>
+   ```
+   Note that the UAX xml file has to be saved as NFD as the Unihan syntax regular expressions are expecting NFD.
+
diff --git a/uax/uax42/fragments/block/block.xml b/uax/uax42/fragments/block/block.xml
@@ -0,0 +1,10 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!--Manual-->
+<ucdxml:block xmlns:ucdxml="http://unicode.org/ns/2001/ucdxml" title="blocks" id='schema.block'>
+  ucd.content &amp;=
+    element blocks {
+      element block {
+        attribute first-cp { single-code-point },
+        attribute last-cp { single-code-point },
+        attribute name { text } }+ }?
+</ucdxml:block>
diff --git a/uax/uax42/fragments/boolean/boolean.xml b/uax/uax42/fragments/boolean/boolean.xml
@@ -0,0 +1,4 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<ucdxml:block xmlns:ucdxml="http://unicode.org/ns/2001/ucdxml" title="boolean" id='schema.boolean'>
+  boolean = "Y" | "N"
+</ucdxml:block>
diff --git a/uax/uax42/fragments/cjk-radicals/cjk-radicals.xml b/uax/uax42/fragments/cjk-radicals/cjk-radicals.xml
@@ -0,0 +1,10 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!--Manual-->
+<ucdxml:block xmlns:ucdxml="http://unicode.org/ns/2001/ucdxml" title="cjk radicals" id='schema.cjk-radicals'>
+  ucd.content &amp;=
+    element cjk-radicals {
+      element cjk-radical {
+        attribute number { xsd:string {pattern="[0-9]{1,3}'{0,3}"}},
+        attribute radical { single-code-point? },
+        attribute ideograph { single-code-point } }+ }?
+</ucdxml:block>
diff --git a/uax/uax42/fragments/datatypes/code points.xml b/uax/uax42/fragments/datatypes/code points.xml
@@ -0,0 +1,9 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!--Manual-->
+<ucdxml:block xmlns:ucdxml="http://unicode.org/ns/2001/ucdxml" title="datatype for code points" id='schema.datatypes'>
+  single-code-point = xsd:string { pattern = "(|[1-9A-F]|(10))[0-9A-F]{4}" }
+
+  one-or-more-code-points = list { single-code-point + }
+  zero-or-more-code-points = list { single-code-point * }
+  two-code-points = list { single-code-point, single-code-point }
+</ucdxml:block>
diff --git a/uax/uax42/fragments/datatypes/datatypes.xml b/uax/uax42/fragments/datatypes/datatypes.xml
@@ -0,0 +1,5 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!--Manual-->
+<ucdxml:block xmlns:ucdxml="http://unicode.org/ns/2001/ucdxml" title="datatypes declaration" id='schema.datatypes'>
+  # default; datatypes xsd = "http://www.w3.org/2001/XMLSchema-datatypes"
+</ucdxml:block>
diff --git a/uax/uax42/fragments/datatypes/jis-code-point.xml b/uax/uax42/fragments/datatypes/jis-code-point.xml
@@ -0,0 +1,5 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!--Manual-->
+<ucdxml:block xmlns:ucdxml="http://unicode.org/ns/2001/ucdxml" title="datatype for code points" id='schema.datatypes'>
+  jis-code-point = xsd:string { pattern = "[0-9A-F]{4}" }
+</ucdxml:block>
diff --git a/uax/uax42/fragments/description/description.xml b/uax/uax42/fragments/description/description.xml
@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!--Manual-->
+<ucdxml:block xmlns:ucdxml="http://unicode.org/ns/2001/ucdxml" title="description" id='schema.description'>
+  ucd.content &amp;=
+    element description { text }?
+</ucdxml:block>
diff --git a/uax/uax42/fragments/do-not-emit/do-not-emit.xml b/uax/uax42/fragments/do-not-emit/do-not-emit.xml
@@ -0,0 +1,22 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<ucdxml:block xmlns:ucdxml="http://unicode.org/ns/2001/ucdxml" title="do-not-emit" id='schema.do-not-emit'>
+  ucd.content &amp;=
+    element do-not-emit {
+      element instead {
+        attribute of { one-or-more-code-points },
+        attribute use { one-or-more-code-points },
+        attribute because { "Bengali_Khanda_Ta"
+                          | "Deprecated"
+                          | "Discouraged"
+                          | "Dotless_Form"
+                          | "Hamza_Form"
+                          | "Indic_Atomic_Consonant"
+                          | "Indic_Consonant_Conjunct"
+                          | "Indic_Vowel_Letter"
+                          | "Malayalam_Chillu"
+                          | "Precomposed_Form"
+                          | "Precomposed_Hieroglyph"
+                          | "Preferred_Spelling"
+                          | "Tamil_Shrii"
+      } }+ }?
+</ucdxml:block>
diff --git a/uax/uax42/fragments/emoji-data/Emoji.xml b/uax/uax42/fragments/emoji-data/Emoji.xml
@@ -0,0 +1,20 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<ucdxml:block xmlns:ucdxml="http://unicode.org/ns/2001/ucdxml" title="Emoji properties" id='schema.emoji-data'>
+  code-point-attributes &amp;=
+    attribute Emoji { boolean }?
+
+  code-point-attributes &amp;=
+    attribute EPres { boolean }?
+
+  code-point-attributes &amp;=
+    attribute EMod { boolean }?
+
+  code-point-attributes &amp;=
+    attribute EBase { boolean }?
+
+  code-point-attributes &amp;=
+    attribute EComp { boolean }?
+
+  code-point-attributes &amp;=
+    attribute ExtPict { boolean }?
+</ucdxml:block>
diff --git a/uax/uax42/fragments/emoji-sources/emoji-sources.xml b/uax/uax42/fragments/emoji-sources/emoji-sources.xml
@@ -0,0 +1,11 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!--Manual-->
+<ucdxml:block xmlns:ucdxml="http://unicode.org/ns/2001/ucdxml" title="emoji sources" id='schema.emoji-sources'>
+  ucd.content &amp;=
+    element emoji-sources {
+      element emoji-source {
+        attribute unicode { one-or-more-code-points },
+        attribute docomo { jis-code-point? },
+        attribute kddi { jis-code-point? },
+        attribute softbank { jis-code-point? } }+ }?
+</ucdxml:block>
diff --git a/uax/uax42/fragments/named-sequences/named-sequences.xml b/uax/uax42/fragments/named-sequences/named-sequences.xml
@@ -0,0 +1,15 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!--Manual-->
+<ucdxml:block xmlns:ucdxml="http://unicode.org/ns/2001/ucdxml" title="named sequences" id='schema.named-sequences'>
+  ucd.content &amp;=
+    element named-sequences {
+      element named-sequence {
+        attribute cps { one-or-more-code-points },
+        attribute name { text } }+ }?
+
+  ucd.content &amp;=
+    element provisional-named-sequences {
+      element named-sequence {
+        attribute cps { one-or-more-code-points },
+        attribute name { text } }+ }?
+</ucdxml:block>
diff --git a/uax/uax42/fragments/namespace/namespace.xml b/uax/uax42/fragments/namespace/namespace.xml
@@ -0,0 +1,5 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!--Manual-->
+<ucdxml:block xmlns:ucdxml="http://unicode.org/ns/2001/ucdxml" title="namespace declaration" id='schema.namespace'>
+  default namespace ucd = "http://www.unicode.org/ns/2003/ucd/1.0"
+</ucdxml:block>
diff --git a/uax/uax42/fragments/normalization-corrections/normalization-corrections.xml b/uax/uax42/fragments/normalization-corrections/normalization-corrections.xml
@@ -0,0 +1,11 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!--Manual-->
+<ucdxml:block xmlns:ucdxml="http://unicode.org/ns/2001/ucdxml" title="normalization corrections" id='schema.normalization-corrections'>
+  ucd.content &amp;=
+    element normalization-corrections {
+      element normalization-correction {
+        attribute cp { single-code-point },
+        attribute old { one-or-more-code-points },
+        attribute new { one-or-more-code-points },
+        attribute version { text } }+ }?
+</ucdxml:block>
diff --git a/uax/uax42/fragments/nushu/Nushu.xml b/uax/uax42/fragments/nushu/Nushu.xml
@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<ucdxml:block xmlns:ucdxml="http://unicode.org/ns/2001/ucdxml" title="Nushu data" id='schema.nushu'>
+  code-point-attributes &amp;=
+    attribute kSrc_NushuDuben { xsd:string { pattern="[0-9]+\.[0-9]+" } }?
+
+  code-point-attributes &amp;=
+    attribute kReading { xsd:string }?
+</ucdxml:block>
diff --git a/uax/uax42/fragments/properties/Bidi_C.xml b/uax/uax42/fragments/properties/Bidi_C.xml
@@ -0,0 +1,5 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<ucdxml:block xmlns:ucdxml="http://unicode.org/ns/2001/ucdxml" title="Bidi_C attribute" id='schema.properties'>
+  code-point-attributes &amp;=
+    attribute Bidi_C { boolean }?
+</ucdxml:block>
diff --git a/uax/uax42/fragments/properties/Bidi_M.xml b/uax/uax42/fragments/properties/Bidi_M.xml
@@ -0,0 +1,5 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<ucdxml:block xmlns:ucdxml="http://unicode.org/ns/2001/ucdxml" title="Bidi_M attribute" id='schema.properties'>
+  code-point-attributes &amp;=
+    attribute Bidi_M { boolean }?
+</ucdxml:block>
diff --git a/uax/uax42/fragments/properties/InCB.xml b/uax/uax42/fragments/properties/InCB.xml
@@ -0,0 +1,9 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<ucdxml:block xmlns:ucdxml="http://unicode.org/ns/2001/ucdxml" title="InCB attribute" id='schema.properties'>
+  code-point-attributes &amp;=
+    attribute InCB { "Consonant"
+                   | "Extend"
+                   | "Linker"
+                   | "None"
+                   }?
+</ucdxml:block>
diff --git a/uax/uax42/fragments/properties/InPC.xml b/uax/uax42/fragments/properties/InPC.xml
@@ -0,0 +1,21 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<ucdxml:block xmlns:ucdxml="http://unicode.org/ns/2001/ucdxml" title="InPC attribute" id='schema.properties'>
+  code-point-attributes &amp;=
+    attribute InPC { "Bottom"
+                   | "Bottom_And_Left"
+                   | "Bottom_And_Right"
+                   | "Left"
+                   | "Left_And_Right"
+                   | "NA"
+                   | "Overstruck"
+                   | "Right"
+                   | "Top"
+                   | "Top_And_Bottom"
+                   | "Top_And_Bottom_And_Left"
+                   | "Top_And_Bottom_And_Right"
+                   | "Top_And_Left"
+                   | "Top_And_Left_And_Right"
+                   | "Top_And_Right"
+                   | "Visual_Order_Left"
+                   }?
+</ucdxml:block>
diff --git a/uax/uax42/fragments/properties/InSC.xml b/uax/uax42/fragments/properties/InSC.xml
@@ -0,0 +1,42 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<ucdxml:block xmlns:ucdxml="http://unicode.org/ns/2001/ucdxml" title="InSC attribute" id='schema.properties'>
+  code-point-attributes &amp;=
+    attribute InSC { "Avagraha"
+                   | "Bindu"
+                   | "Brahmi_Joining_Number"
+                   | "Cantillation_Mark"
+                   | "Consonant"
+                   | "Consonant_Dead"
+                   | "Consonant_Final"
+                   | "Consonant_Head_Letter"
+                   | "Consonant_Initial_Postfixed"
+                   | "Consonant_Killer"
+                   | "Consonant_Medial"
+                   | "Consonant_Placeholder"
+                   | "Consonant_Preceding_Repha"
+                   | "Consonant_Prefixed"
+                   | "Consonant_Subjoined"
+                   | "Consonant_Succeeding_Repha"
+                   | "Consonant_With_Stacker"
+                   | "Gemination_Mark"
+                   | "Invisible_Stacker"
+                   | "Joiner"
+                   | "Modifying_Letter"
+                   | "Non_Joiner"
+                   | "Nukta"
+                   | "Number"
+                   | "Number_Joiner"
+                   | "Other"
+                   | "Pure_Killer"
+                   | "Register_Shifter"
+                   | "Reordering_Killer"
+                   | "Syllable_Modifier"
+                   | "Tone_Letter"
+                   | "Tone_Mark"
+                   | "Virama"
+                   | "Visarga"
+                   | "Vowel"
+                   | "Vowel_Dependent"
+                   | "Vowel_Independent"
+                   }?
+</ucdxml:block>
diff --git a/uax/uax42/fragments/properties/JSN.xml b/uax/uax42/fragments/properties/JSN.xml
@@ -0,0 +1,5 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<ucdxml:block xmlns:ucdxml="http://unicode.org/ns/2001/ucdxml" title="JSN attribute" id='schema.properties'>
+  code-point-attributes &amp;=
+    attribute JSN { xsd:string { pattern="[A-Z]{0,3}" } }?
+</ucdxml:block>
diff --git a/uax/uax42/fragments/properties/Join_C.xml b/uax/uax42/fragments/properties/Join_C.xml
@@ -0,0 +1,5 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<ucdxml:block xmlns:ucdxml="http://unicode.org/ns/2001/ucdxml" title="joining properties" id='schema.properties'>
+  code-point-attributes &amp;=
+    attribute Join_C { boolean }?
+</ucdxml:block>
diff --git a/uax/uax42/fragments/properties/Name_Alias.xml b/uax/uax42/fragments/properties/Name_Alias.xml
@@ -0,0 +1,10 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<ucdxml:block xmlns:ucdxml="http://unicode.org/ns/2001/ucdxml" title="name-alias element" id='schema.properties'>
+  code-point-attributes &amp;=
+    element name-alias {
+      attribute alias { xsd:string { pattern="[a-zA-Z0-9]+(( -|- |[\-_ ])[a-zA-Z0-9]+)*" } }?,
+      attribute type  { "abbreviation" | "alternate"
+                      | "control" | "correction"
+                      | "figment"
+                      }? } *
+</ucdxml:block>