| Index: source/data/translit/Han_Latin_Names.txt
|
| diff --git a/source/data/translit/Han_Latin_Names.txt b/source/data/translit/Han_Latin_Names.txt
|
| old mode 100755
|
| new mode 100644
|
| index 648547f42185e5ac845670bed8246963a84d7c3b..5167217e1c902e2678dd9d92338a2ee132d71d3a
|
| --- a/source/data/translit/Han_Latin_Names.txt
|
| +++ b/source/data/translit/Han_Latin_Names.txt
|
| @@ -1,19 +1,30 @@
|
| -# ***************************************************************************
|
| -# *
|
| -# * Copyright (C) 2004-2015, 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
|
| -# 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();
|
| +# 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;
|
| @@ -48,7 +59,11 @@ $startOfHanMarker{ 员→yùn;
|
| $startOfHanMarker{ 查→zhā;
|
| 翟→zhái;
|
| 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();
|
| +
|
|
|