From fe5f20c043c8e964620dc367d12efac3541c366f Mon Sep 17 00:00:00 2001
From: "Maxim.Mossienko" <maxim.mossienko@jetbrains.com>
Date: Tue, 15 Nov 2011 15:32:48 +0400
Subject: [PATCH] IDEA-76562 Suppressing spell checking for eastern Asian
 languages looks incomplete

---
 .../inspections/IdentifierSplitter.java       | 17 +++++++++++++-
 .../inspections/PlainTextSplitter.java        | 22 +++++++++----------
 .../testData/inspection/java/Japaneese.java   |  2 +-
 3 files changed, 28 insertions(+), 13 deletions(-)

diff --git a/plugins/spellchecker/src/com/intellij/spellchecker/inspections/IdentifierSplitter.java b/plugins/spellchecker/src/com/intellij/spellchecker/inspections/IdentifierSplitter.java
index 8c8f124659e8..66c65d958102 100644
--- a/plugins/spellchecker/src/com/intellij/spellchecker/inspections/IdentifierSplitter.java
+++ b/plugins/spellchecker/src/com/intellij/spellchecker/inspections/IdentifierSplitter.java
@@ -84,7 +84,7 @@ public class IdentifierSplitter extends BaseSplitter {
   }
 
   @NotNull
-  public static List<TextRange> splitByCase(@NotNull String text, @NotNull TextRange range) {
+  private static List<TextRange> splitByCase(@NotNull String text, @NotNull TextRange range) {
     //System.out.println("text = " + text + " range = " + range);
     List<TextRange> result = new ArrayList<TextRange>();
     int i = range.getStartOffset();
@@ -92,6 +92,21 @@ public class IdentifierSplitter extends BaseSplitter {
     int prevType = Character.MATH_SYMBOL;
     while (i < range.getEndOffset()) {
       final char ch = text.charAt(i);
+      if (ch >= '\u3040' && ch <= '\u309f' || // Hiragana
+          ch >= '\u30A0' && ch <= '\u30ff' || // Katakana
+          ch >= '\u4E00' && ch <= '\u9FFF' || // CJK Unified ideographs
+          ch >= '\uF900' && ch <= '\uFAFF' || // CJK Compatibility Ideographs
+          ch >= '\uFF00' && ch <= '\uFFEF' //Halfwidth and Fullwidth Forms of Katakana & Fullwidth ASCII variants
+         ) {
+        if (s >= 0) {
+          add(text, result, i, s);
+          s = -1;
+        }
+        prevType = Character.MATH_SYMBOL;
+        ++i;
+        continue;
+      }
+
       final int type = Character.getType(ch);
       if (type == Character.LOWERCASE_LETTER ||
           type == Character.UPPERCASE_LETTER ||
diff --git a/plugins/spellchecker/src/com/intellij/spellchecker/inspections/PlainTextSplitter.java b/plugins/spellchecker/src/com/intellij/spellchecker/inspections/PlainTextSplitter.java
index 579536abd1b1..0ec175a083bd 100644
--- a/plugins/spellchecker/src/com/intellij/spellchecker/inspections/PlainTextSplitter.java
+++ b/plugins/spellchecker/src/com/intellij/spellchecker/inspections/PlainTextSplitter.java
@@ -52,17 +52,17 @@ public class PlainTextSplitter extends BaseSplitter {
     if (Verifier.checkCharacterData(substring) != null) {
       return;
     }
-    for(int i = 0; i < text.length(); ++i) {
-      final char ch = text.charAt(i);
-      if (ch >= '\u3040' && ch <= '\u309f' || // Hiragana
-          ch >= '\u30A0' && ch <= '\u30ff' || // Katakana
-          ch >= '\u4E00' && ch <= '\u9FFF' || // CJK Unified ideographs
-          ch >= '\uF900' && ch <= '\uFAFF' || // CJK Compatibility Ideographs
-          ch >= '\uFF00' && ch <= '\uFFEF' //Halfwidth and Fullwidth Forms of Katakana & Fullwidth ASCII variants
-         ) {
-        return;
-      }
-    }
+    //for(int i = 0; i < text.length(); ++i) {
+    //  final char ch = text.charAt(i);
+    //  if (ch >= '\u3040' && ch <= '\u309f' || // Hiragana
+    //      ch >= '\u30A0' && ch <= '\u30ff' || // Katakana
+    //      ch >= '\u4E00' && ch <= '\u9FFF' || // CJK Unified ideographs
+    //      ch >= '\uF900' && ch <= '\uFAFF' || // CJK Compatibility Ideographs
+    //      ch >= '\uFF00' && ch <= '\uFFEF' //Halfwidth and Fullwidth Forms of Katakana & Fullwidth ASCII variants
+    //     ) {
+    //    return;
+    //  }
+    //}
 
     List<TextRange> toCheck;
     if (text.indexOf('@')>0) {
diff --git a/plugins/spellchecker/testData/inspection/java/Japaneese.java b/plugins/spellchecker/testData/inspection/java/Japaneese.java
index 617fc02f086d..3eae1726a235 100644
--- a/plugins/spellchecker/testData/inspection/java/Japaneese.java
+++ b/plugins/spellchecker/testData/inspection/java/Japaneese.java
@@ -16,7 +16,7 @@
 /** CJK Compatibility Ideographs (F900 - FAFF)
  * 﨎鶴﨎鶴﨎鶴
  */
-
+/* 私は<TYPO>Jaba</TYPO>が好きです。私は<TYPO>Jaba</TYPO>が好きです。*/
 /**
  * プロセス毎に使われるコールスタックは一つだけ !!!
  */