Keep all Binary_Property/Alphabetic

Flet · Dec 18, 2020 · df6c9cb · df6c9cb
1 parent ae2c3b3
commit df6c9cb
Show file tree

Hide file tree

Showing 3 changed files with 15 additions and 25 deletions.
diff --git a/_generated_unicode_regex.js b/_generated_unicode_regex.js
diff --git a/script/generate-regex.js b/script/generate-regex.js
@@ -4,25 +4,15 @@ const path = require('path')
 const regenerate = require('regenerate')
 
 const set = regenerate()
-  .add(require('unicode-12.1.0/General_Category/Close_Punctuation/code-points.js'))
-  .add(require('unicode-12.1.0/General_Category/Control/code-points.js'))
-  .add(require('unicode-12.1.0/General_Category/Currency_Symbol/code-points.js'))
-  .add(require('unicode-12.1.0/General_Category/Dash_Punctuation/code-points.js'))
-  .remove('-') // Except Hyphen-Minus
-  .add(require('unicode-12.1.0/General_Category/Final_Punctuation/code-points.js'))
-  .add(require('unicode-12.1.0/General_Category/Format/code-points.js'))
-  .add(require('unicode-12.1.0/General_Category/Initial_Punctuation/code-points.js'))
-  .add(require('unicode-12.1.0/General_Category/Line_Separator/code-points.js'))
-  .add(require('unicode-12.1.0/General_Category/Math_Symbol/code-points.js'))
-  .add(require('unicode-12.1.0/General_Category/Modifier_Symbol/code-points.js'))
-  .add(require('unicode-12.1.0/General_Category/Open_Punctuation/code-points.js'))
-  .add(require('unicode-12.1.0/General_Category/Other_Number/code-points.js'))
-  .add(require('unicode-12.1.0/General_Category/Other_Punctuation/code-points.js'))
-  .add(require('unicode-12.1.0/General_Category/Other_Symbol/code-points.js'))
-  .add(require('unicode-12.1.0/General_Category/Paragraph_Separator/code-points.js'))
-  .add(require('unicode-12.1.0/General_Category/Private_Use/code-points.js'))
-  .add(require('unicode-12.1.0/General_Category/Surrogate/code-points.js'))
-  .add(require('unicode-12.1.0/General_Category/Unassigned/code-points.js'))
+  .addRange(0x0, 0x10ffff) // Everything
+  .remove(require('unicode-12.1.0/Binary_Property/Alphabetic/code-points.js')) // Overlaps General_Category/Other_Symbol
+  .remove(require('unicode-12.1.0/General_Category/Connector_Punctuation/code-points.js'))
+  .remove(require('unicode-12.1.0/General_Category/Decimal_Number/code-points.js'))
+  .remove(require('unicode-12.1.0/General_Category/Enclosing_Mark/code-points.js'))
+  .remove(require('unicode-12.1.0/General_Category/Nonspacing_Mark/code-points.js'))
+  .remove(require('unicode-12.1.0/General_Category/Space_Separator/code-points.js'))
+  .remove(require('unicode-12.1.0/General_Category/Spacing_Mark/code-points.js'))
+  .remove('-') // General_Category/Dash_Punctuation exception
 
 console.log(`/${set.toString()}/g`)
 // Then you might want to use a template like this to write the result to a file, along with any regex flags you might need:

diff --git a/test/index.js b/test/index.js
@@ -217,7 +217,7 @@ var testCases = [
   require('./General_Category/Format.json'),
   require('./General_Category/Initial_Punctuation.json'),
   require('./General_Category/Letter_Number.json'),
-  //require('./General_Category/Line_Separator.json'),
+  //require('./General_Category/Line_Separator.json'), // Presumably d/t .trim()? Not worth fixing?
   require('./General_Category/Lowercase_Letter.json'),
   require('./General_Category/Math_Symbol.json'),
   require('./General_Category/Modifier_Letter.json'),
@@ -227,12 +227,12 @@ var testCases = [
   require('./General_Category/Other_Letter.json'),
   require('./General_Category/Other_Number.json'),
   require('./General_Category/Other_Punctuation.json'),
-  //require('./General_Category/Other_Symbol.json'),
-  //require('./General_Category/Paragraph_Separator.json'),
+  require('./General_Category/Other_Symbol.json'),
+  //require('./General_Category/Paragraph_Separator.json'), // Presumably d/t .trim()? Not worth fixing?
   require('./General_Category/Private_Use.json'),
-  //require('./General_Category/Space_Separator.json'),
+  //require('./General_Category/Space_Separator.json'), // Presumably d/t .trim()? Not worth fixing?
   require('./General_Category/Spacing_Mark.json'),
-  //require('./General_Category/Surrogate.json'),
+  //require('./General_Category/Surrogate.json'), // Not sure why I can't strip U+DFFF?
   require('./General_Category/Titlecase_Letter.json'),
   require('./General_Category/Unassigned.json'),
   require('./General_Category/Uppercase_Letter.json'),