ICU-62141.0.1.tar.gz

[apple/icu.git] / icuSources / data / translit / Han_Latin_Names.txt

diff --git a/icuSources/data/translit/Han_Latin_Names.txt b/icuSources/data/translit/Han_Latin_Names.txt
index 487fc05ccdd86a41a3bb4783650e15896af252db..406a9ef7afaae7f536557c5b3681487f8dea9fb7 100644 (file)
--- a/icuSources/data/translit/Han_Latin_Names.txt
+++ b/icuSources/data/translit/Han_Latin_Names.txt
@@ -1,20 +1,71 @@
-# ***************************************************************************
-# *
-# *  Copyright (C) 2004-2011, International Business Machines
-# *  Corporation; Unicode, Inc.; and others.  All Rights Reserved.
-# *
-# ***************************************************************************
+# © 2016 and later: Unicode, Inc. and others.
+# License & terms of use: http://www.unicode.org/copyright.html#License
+#

 # File: Han_Latin_Names.txt
 # File: Han_Latin_Names.txt

-# Generated from CLDR 
+# Generated from CLDR

 #
 #

+
+# This transform is primarily intended to produce readings for Chinese surnames, or for full
+# Chinese personal names - surname first - that occur at the beginning of a contiguous Han substring
+# (i.e. at the beginning of text, or immediately preceded by space or other non-Han characters).
+# Several Han characters have different readings in surnames, than the readings found in Han-Latin.
+# ----
+# Insert marker at start of each Han sequence (including Han after space).
+# Do this before ::Han-Spacedhan() to catch Han after space in original text,
+# and to apply before all other rules.
+$startOfHanMarker = \uFDD1;
+[:^script=Han:] { ([:script=Han:]) → $startOfHanMarker $1;
+# Need Spacedhan so the name transliterations get spaced properly

 ::Han-Spacedhan();
 ::Han-Spacedhan();

+# Convert special name readings that depend on next character
+令 } \u0020? 狐 →líng;
+万 } \u0020? 俟 →mò;
+澹 } \u0020? 台 →tán;
+# The following maps 长 to the standard Han-Latin reading zhǎng for this case,
+# to override the normal Han-Latin/Names reading 长→cháng further below
+$startOfHanMarker{ 长 } \u0020? 孙 →zhǎng;
+# Convert single characters with special name readings
+$startOfHanMarker{ 秘→bì;
+$startOfHanMarker{ 卜→bǔ;

 长→cháng;
 长→cháng;

+$startOfHanMarker{ 种→chóng;
+$startOfHanMarker{ 重→chóng;
+$startOfHanMarker{ 刀→diāo;
+干→gān;

 葛→gě;
 葛→gě;

-贾→jǐa;
-賈→jǐa;
+$startOfHanMarker{ 盖→gě;
+$startOfHanMarker{ 过→guō;
+$startOfHanMarker{ 华→huà;
+$startOfHanMarker{ 纪→jǐ;

 筠→jūn;
 筠→jūn;

-沈→shěn;
+靓→liàng;
+$startOfHanMarker{ 牟→mù;
+$startOfHanMarker{ 粘→nián;
+$startOfHanMarker{ 区→ōu;
+$startOfHanMarker{ 繁→pó;
+仇→qiú;
+$startOfHanMarker{ 任→rén;
+$startOfHanMarker{ 单→shàn;
+$startOfHanMarker{ 召→shào;
+$startOfHanMarker{ 折→shé;
+$startOfHanMarker{ 舍→shè;
+$startOfHanMarker{ 沈→shěn;

 峙→shì;
 峙→shì;

+隗→wěi;
+$startOfHanMarker{ 解→xiè;

 莘→xīn;
 莘→xīn;

+$startOfHanMarker{ 燕→yān;
+$startOfHanMarker{ 尉→yù;
+$startOfHanMarker{ 乐→yuè;
+$startOfHanMarker{ 员→yùn;
+$startOfHanMarker{ 查→zhā;
+翟→zhái;

 曾→zēng;
 曾→zēng;

+# Convert $startOfHanMarkers to space, or to nothing if they are at the beginning of text.
+# Need to do this as a separate pass to get the spacing right.
+::Null();
+[^$]{ $startOfHanMarker →\u0020;
+$startOfHanMarker →;
+# Then run the normal Han-Latin transform for the rest

 ::Han-Latin();
 ::Han-Latin();

+