You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lucene.apache.org by rm...@apache.org on 2014/10/07 04:38:15 UTC

svn commit: r1629796 - in /lucene/dev/branches/lucene5995: lucene/ lucene/analysis/icu/src/data/uax29/ lucene/analysis/icu/src/data/utr30/ lucene/analysis/icu/src/java/org/apache/lucene/analysis/icu/segmentation/ lucene/analysis/icu/src/resources/org/a...

Author: rmuir
Date: Tue Oct  7 02:38:14 2014
New Revision: 1629796

URL: http://svn.apache.org/r1629796
Log:
LUCENE-5995: upgrade to ICU 54.1

Added:
    lucene/dev/branches/lucene5995/lucene/licenses/icu4j-54.1.jar.sha1
    lucene/dev/branches/lucene5995/solr/licenses/icu4j-54.1.jar.sha1
Removed:
    lucene/dev/branches/lucene5995/lucene/analysis/icu/src/data/uax29/Myanmar.rbbi
    lucene/dev/branches/lucene5995/lucene/analysis/icu/src/resources/org/apache/lucene/analysis/icu/segmentation/Myanmar.brk
    lucene/dev/branches/lucene5995/lucene/licenses/icu4j-53.1.jar.sha1
    lucene/dev/branches/lucene5995/solr/licenses/icu4j-53.1.jar.sha1
Modified:
    lucene/dev/branches/lucene5995/lucene/CHANGES.txt
    lucene/dev/branches/lucene5995/lucene/analysis/icu/src/data/utr30/BasicFoldings.txt
    lucene/dev/branches/lucene5995/lucene/analysis/icu/src/data/utr30/DiacriticFolding.txt
    lucene/dev/branches/lucene5995/lucene/analysis/icu/src/data/utr30/NativeDigitFolding.txt
    lucene/dev/branches/lucene5995/lucene/analysis/icu/src/data/utr30/nfc.txt
    lucene/dev/branches/lucene5995/lucene/analysis/icu/src/data/utr30/nfkc.txt
    lucene/dev/branches/lucene5995/lucene/analysis/icu/src/data/utr30/nfkc_cf.txt
    lucene/dev/branches/lucene5995/lucene/analysis/icu/src/java/org/apache/lucene/analysis/icu/segmentation/DefaultICUTokenizerConfig.java
    lucene/dev/branches/lucene5995/lucene/analysis/icu/src/resources/org/apache/lucene/analysis/icu/segmentation/Default.brk
    lucene/dev/branches/lucene5995/lucene/analysis/icu/src/resources/org/apache/lucene/analysis/icu/segmentation/Khmer.brk
    lucene/dev/branches/lucene5995/lucene/analysis/icu/src/resources/org/apache/lucene/analysis/icu/utr30.nrm
    lucene/dev/branches/lucene5995/lucene/analysis/icu/src/test/org/apache/lucene/analysis/icu/segmentation/TestICUTokenizer.java
    lucene/dev/branches/lucene5995/lucene/analysis/icu/src/tools/java/org/apache/lucene/analysis/icu/GenerateUTR30DataFiles.java
    lucene/dev/branches/lucene5995/lucene/ivy-versions.properties

Modified: lucene/dev/branches/lucene5995/lucene/CHANGES.txt
URL: http://svn.apache.org/viewvc/lucene/dev/branches/lucene5995/lucene/CHANGES.txt?rev=1629796&r1=1629795&r2=1629796&view=diff
==============================================================================
--- lucene/dev/branches/lucene5995/lucene/CHANGES.txt (original)
+++ lucene/dev/branches/lucene5995/lucene/CHANGES.txt Tue Oct  7 02:38:14 2014
@@ -221,6 +221,8 @@ Build
 * LUCENE-5962: Rename diffSources.py to createPatch.py and make it work with all text file types.
   (Ryan Ernst)
 
+* LUCENE-5995: Upgrade ICU to 54.1 (Robert Muir)
+
 Other
 
 * LUCENE-5563: Removed sep layout: which has fallen behind on features and doesn't

Modified: lucene/dev/branches/lucene5995/lucene/analysis/icu/src/data/utr30/BasicFoldings.txt
URL: http://svn.apache.org/viewvc/lucene/dev/branches/lucene5995/lucene/analysis/icu/src/data/utr30/BasicFoldings.txt?rev=1629796&r1=1629795&r2=1629796&view=diff
==============================================================================
--- lucene/dev/branches/lucene5995/lucene/analysis/icu/src/data/utr30/BasicFoldings.txt (original)
+++ lucene/dev/branches/lucene5995/lucene/analysis/icu/src/data/utr30/BasicFoldings.txt Tue Oct  7 02:38:14 2014
@@ -49,6 +49,7 @@
 2E17>002D
 2E1A>002D
 2E3A..2E3B>002D
+2E40>002D
 301C>002D
 3030>002D
 30A0>002D

Modified: lucene/dev/branches/lucene5995/lucene/analysis/icu/src/data/utr30/DiacriticFolding.txt
URL: http://svn.apache.org/viewvc/lucene/dev/branches/lucene5995/lucene/analysis/icu/src/data/utr30/DiacriticFolding.txt?rev=1629796&r1=1629795&r2=1629796&view=diff
==============================================================================
--- lucene/dev/branches/lucene5995/lucene/analysis/icu/src/data/utr30/DiacriticFolding.txt (original)
+++ lucene/dev/branches/lucene5995/lucene/analysis/icu/src/data/utr30/DiacriticFolding.txt Tue Oct  7 02:38:14 2014
@@ -102,6 +102,7 @@
 1939..193B>
 1A75..1A7C>
 1A7F>
+1AB0..1ABD>
 1B34>
 1B44>
 1B6B..1B73>
@@ -111,8 +112,10 @@
 1CD0..1CE8>
 1CED>
 1CF4>
+1CF8..1CF9>
 1D2C..1D6A>
 1DC4..1DCF>
+1DF5>
 1DFD..1DFF>
 1FBD>
 1FBF..1FC1>
@@ -128,6 +131,7 @@
 A66F>
 A67C..A67D>
 A67F>
+A69C..A69D>
 A6F0..A6F1>
 A717..A721>
 A788>
@@ -138,27 +142,43 @@ A92B..A92E>
 A953>
 A9B3>
 A9C0>
-AA7B>
+A9E5>
+AA7B..AA7D>
 AABF..AAC2>
 AAF6>
+AB5B..AB5F>
 ABEC..ABED>
 FB1E>
-FE20..FE26>
+FE20..FE2D>
 FF3E>
 FF40>
 FF70>
 FF9E..FF9F>
 FFE3>
+102E0>
+10AE5..10AE6>
 110B9..110BA>
 11133..11134>
+11173>
 111C0>
+11235..11236>
+112E9..112EA>
+1133C>
+1134D>
+11366..1136C>
+11370..11374>
+114C2..114C3>
+115BF..115C0>
+1163F>
 116B6..116B7>
+16AF0..16AF4>
 16F8F..16F9F>
 1D167..1D169>
 1D16D..1D172>
 1D17B..1D182>
 1D185..1D18B>
 1D1AA..1D1AD>
+1E8D0..1E8D6>
 
 # Latin script "composed" that do not further decompose, so decompose here
 # These are from AsciiFoldingFilter

Modified: lucene/dev/branches/lucene5995/lucene/analysis/icu/src/data/utr30/NativeDigitFolding.txt
URL: http://svn.apache.org/viewvc/lucene/dev/branches/lucene5995/lucene/analysis/icu/src/data/utr30/NativeDigitFolding.txt?rev=1629796&r1=1629795&r2=1629796&view=diff
==============================================================================
--- lucene/dev/branches/lucene5995/lucene/analysis/icu/src/data/utr30/NativeDigitFolding.txt (original)
+++ lucene/dev/branches/lucene5995/lucene/analysis/icu/src/data/utr30/NativeDigitFolding.txt Tue Oct  7 02:38:14 2014
@@ -151,6 +151,16 @@
 0D6D>0037   # MALAYALAM DIGIT SEVEN
 0D6E>0038   # MALAYALAM DIGIT EIGHT
 0D6F>0039   # MALAYALAM DIGIT NINE
+0DE6>0030   # SINHALA LITH DIGIT ZERO
+0DE7>0031   # SINHALA LITH DIGIT ONE
+0DE8>0032   # SINHALA LITH DIGIT TWO
+0DE9>0033   # SINHALA LITH DIGIT THREE
+0DEA>0034   # SINHALA LITH DIGIT FOUR
+0DEB>0035   # SINHALA LITH DIGIT FIVE
+0DEC>0036   # SINHALA LITH DIGIT SIX
+0DED>0037   # SINHALA LITH DIGIT SEVEN
+0DEE>0038   # SINHALA LITH DIGIT EIGHT
+0DEF>0039   # SINHALA LITH DIGIT NINE
 0E50>0030   # THAI DIGIT ZERO
 0E51>0031   # THAI DIGIT ONE
 0E52>0032   # THAI DIGIT TWO
@@ -388,6 +398,16 @@ A9D6>0036   # JAVANESE DIGIT SIX
 A9D7>0037   # JAVANESE DIGIT SEVEN
 A9D8>0038   # JAVANESE DIGIT EIGHT
 A9D9>0039   # JAVANESE DIGIT NINE
+A9F0>0030   # MYANMAR TAI LAING DIGIT ZERO
+A9F1>0031   # MYANMAR TAI LAING DIGIT ONE
+A9F2>0032   # MYANMAR TAI LAING DIGIT TWO
+A9F3>0033   # MYANMAR TAI LAING DIGIT THREE
+A9F4>0034   # MYANMAR TAI LAING DIGIT FOUR
+A9F5>0035   # MYANMAR TAI LAING DIGIT FIVE
+A9F6>0036   # MYANMAR TAI LAING DIGIT SIX
+A9F7>0037   # MYANMAR TAI LAING DIGIT SEVEN
+A9F8>0038   # MYANMAR TAI LAING DIGIT EIGHT
+A9F9>0039   # MYANMAR TAI LAING DIGIT NINE
 AA50>0030   # CHAM DIGIT ZERO
 AA51>0031   # CHAM DIGIT ONE
 AA52>0032   # CHAM DIGIT TWO
@@ -480,6 +500,36 @@ ABF9>0039   # MEETEI MAYEK DIGIT NINE
 111D7>0037   # SHARADA DIGIT SEVEN
 111D8>0038   # SHARADA DIGIT EIGHT
 111D9>0039   # SHARADA DIGIT NINE
+112F0>0030   # KHUDAWADI DIGIT ZERO
+112F1>0031   # KHUDAWADI DIGIT ONE
+112F2>0032   # KHUDAWADI DIGIT TWO
+112F3>0033   # KHUDAWADI DIGIT THREE
+112F4>0034   # KHUDAWADI DIGIT FOUR
+112F5>0035   # KHUDAWADI DIGIT FIVE
+112F6>0036   # KHUDAWADI DIGIT SIX
+112F7>0037   # KHUDAWADI DIGIT SEVEN
+112F8>0038   # KHUDAWADI DIGIT EIGHT
+112F9>0039   # KHUDAWADI DIGIT NINE
+114D0>0030   # TIRHUTA DIGIT ZERO
+114D1>0031   # TIRHUTA DIGIT ONE
+114D2>0032   # TIRHUTA DIGIT TWO
+114D3>0033   # TIRHUTA DIGIT THREE
+114D4>0034   # TIRHUTA DIGIT FOUR
+114D5>0035   # TIRHUTA DIGIT FIVE
+114D6>0036   # TIRHUTA DIGIT SIX
+114D7>0037   # TIRHUTA DIGIT SEVEN
+114D8>0038   # TIRHUTA DIGIT EIGHT
+114D9>0039   # TIRHUTA DIGIT NINE
+11650>0030   # MODI DIGIT ZERO
+11651>0031   # MODI DIGIT ONE
+11652>0032   # MODI DIGIT TWO
+11653>0033   # MODI DIGIT THREE
+11654>0034   # MODI DIGIT FOUR
+11655>0035   # MODI DIGIT FIVE
+11656>0036   # MODI DIGIT SIX
+11657>0037   # MODI DIGIT SEVEN
+11658>0038   # MODI DIGIT EIGHT
+11659>0039   # MODI DIGIT NINE
 116C0>0030   # TAKRI DIGIT ZERO
 116C1>0031   # TAKRI DIGIT ONE
 116C2>0032   # TAKRI DIGIT TWO
@@ -490,4 +540,34 @@ ABF9>0039   # MEETEI MAYEK DIGIT NINE
 116C7>0037   # TAKRI DIGIT SEVEN
 116C8>0038   # TAKRI DIGIT EIGHT
 116C9>0039   # TAKRI DIGIT NINE
+118E0>0030   # WARANG CITI DIGIT ZERO
+118E1>0031   # WARANG CITI DIGIT ONE
+118E2>0032   # WARANG CITI DIGIT TWO
+118E3>0033   # WARANG CITI DIGIT THREE
+118E4>0034   # WARANG CITI DIGIT FOUR
+118E5>0035   # WARANG CITI DIGIT FIVE
+118E6>0036   # WARANG CITI DIGIT SIX
+118E7>0037   # WARANG CITI DIGIT SEVEN
+118E8>0038   # WARANG CITI DIGIT EIGHT
+118E9>0039   # WARANG CITI DIGIT NINE
+16A60>0030   # MRO DIGIT ZERO
+16A61>0031   # MRO DIGIT ONE
+16A62>0032   # MRO DIGIT TWO
+16A63>0033   # MRO DIGIT THREE
+16A64>0034   # MRO DIGIT FOUR
+16A65>0035   # MRO DIGIT FIVE
+16A66>0036   # MRO DIGIT SIX
+16A67>0037   # MRO DIGIT SEVEN
+16A68>0038   # MRO DIGIT EIGHT
+16A69>0039   # MRO DIGIT NINE
+16B50>0030   # PAHAWH HMONG DIGIT ZERO
+16B51>0031   # PAHAWH HMONG DIGIT ONE
+16B52>0032   # PAHAWH HMONG DIGIT TWO
+16B53>0033   # PAHAWH HMONG DIGIT THREE
+16B54>0034   # PAHAWH HMONG DIGIT FOUR
+16B55>0035   # PAHAWH HMONG DIGIT FIVE
+16B56>0036   # PAHAWH HMONG DIGIT SIX
+16B57>0037   # PAHAWH HMONG DIGIT SEVEN
+16B58>0038   # PAHAWH HMONG DIGIT EIGHT
+16B59>0039   # PAHAWH HMONG DIGIT NINE
 

Modified: lucene/dev/branches/lucene5995/lucene/analysis/icu/src/data/utr30/nfc.txt
URL: http://svn.apache.org/viewvc/lucene/dev/branches/lucene5995/lucene/analysis/icu/src/data/utr30/nfc.txt?rev=1629796&r1=1629795&r2=1629796&view=diff
==============================================================================
--- lucene/dev/branches/lucene5995/lucene/analysis/icu/src/data/utr30/nfc.txt (original)
+++ lucene/dev/branches/lucene5995/lucene/analysis/icu/src/data/utr30/nfc.txt Tue Oct  7 02:38:14 2014
@@ -1,4 +1,4 @@
-# Copyright (C) 1999-2013, International Business Machines
+# Copyright (C) 1999-2014, International Business Machines
 # Corporation and others.  All Rights Reserved.
 #
 # file name: nfc.txt
@@ -7,7 +7,7 @@
 #
 # Complete data for Unicode NFC normalization.
 
-* Unicode 6.3.0
+* Unicode 7.0.0
 
 # Canonical_Combining_Class (ccc) values
 0300..0314:230
@@ -142,7 +142,7 @@
 08F6:220
 08F7..08F8:230
 08F9..08FA:220
-08FB..08FE:230
+08FB..08FF:230
 093C:7
 094D:9
 0951:230
@@ -199,6 +199,10 @@
 1A60:9
 1A75..1A7C:230
 1A7F:220
+1AB0..1AB4:230
+1AB5..1ABA:220
+1ABB..1ABC:230
+1ABD:220
 1B34:7
 1B44:9
 1B6B:230
@@ -217,6 +221,7 @@
 1CE2..1CE8:1
 1CED:220
 1CF4:230
+1CF8..1CF9:230
 1DC0..1DC1:230
 1DC2:220
 1DC3..1DC9:230
@@ -226,7 +231,7 @@
 1DCE:214
 1DCF:220
 1DD0:202
-1DD1..1DE6:230
+1DD1..1DF5:230
 1DFC:233
 1DFD:220
 1DFE:230
@@ -274,21 +279,44 @@ AAF6:9
 ABED:9
 FB1E:26
 FE20..FE26:230
+FE27..FE2D:220
 101FD:220
+102E0:220
+10376..1037A:230
 10A0D:220
 10A0F:230
 10A38:230
 10A39:1
 10A3A:220
 10A3F:9
+10AE5:230
+10AE6:220
 11046:9
+1107F:9
 110B9:9
 110BA:7
 11100..11102:230
 11133..11134:9
+11173:7
 111C0:9
+11235:9
+11236:7
+112E9:7
+112EA:9
+1133C:7
+1134D:9
+11366..1136C:230
+11370..11374:230
+114C2:9
+114C3:7
+115BF:9
+115C0:7
+1163F:9
 116B6:9
 116B7:7
+16AF0..16AF4:1
+16B30..16B36:230
+1BC9E:1
 1D165..1D166:216
 1D167..1D169:1
 1D16D:226
@@ -298,6 +326,7 @@ FE20..FE26:230
 1D18A..1D18B:220
 1D1AA..1D1AD:230
 1D242..1D244:230
+1E8D0..1E8D6:220
 
 # Canonical decomposition mappings
 00C0>0041 0300  # one-way: diacritic 0300
@@ -1798,6 +1827,13 @@ FB4E>05E4 05BF
 110AB>110A5 110BA  # one-way: diacritic 110BA
 1112E=11131 11127
 1112F=11132 11127
+1134B=11347 1133E
+1134C=11347 11357
+114BB=114B9 114BA
+114BC=114B9 114B0
+114BE=114B9 114BD
+115BA=115B8 115AF
+115BB=115B9 115AF
 1D15E>1D157 1D165
 1D15F>1D158 1D165
 1D160>1D15F 1D16E

Modified: lucene/dev/branches/lucene5995/lucene/analysis/icu/src/data/utr30/nfkc.txt
URL: http://svn.apache.org/viewvc/lucene/dev/branches/lucene5995/lucene/analysis/icu/src/data/utr30/nfkc.txt?rev=1629796&r1=1629795&r2=1629796&view=diff
==============================================================================
--- lucene/dev/branches/lucene5995/lucene/analysis/icu/src/data/utr30/nfkc.txt (original)
+++ lucene/dev/branches/lucene5995/lucene/analysis/icu/src/data/utr30/nfkc.txt Tue Oct  7 02:38:14 2014
@@ -1,4 +1,4 @@
-# Copyright (C) 1999-2013, International Business Machines
+# Copyright (C) 1999-2014, International Business Machines
 # Corporation and others.  All Rights Reserved.
 #
 # file name: nfkc.txt
@@ -11,7 +11,7 @@
 # to NFKC one-way mappings.
 # Use this file as the second gennorm2 input file after nfc.txt.
 
-* Unicode 6.3.0
+* Unicode 7.0.0
 
 00A0>0020
 00A8>0020 0308
@@ -1361,9 +1361,15 @@
 33FD>0033 0030 65E5
 33FE>0033 0031 65E5
 33FF>0067 0061 006C
+A69C>044A
+A69D>044C
 A770>A76F
 A7F8>0126
 A7F9>0153
+AB5C>A727
+AB5D>AB37
+AB5E>026B
+AB5F>AB52
 FB00>0066 0066
 FB01>0066 0069
 FB02>0066 006C

Modified: lucene/dev/branches/lucene5995/lucene/analysis/icu/src/data/utr30/nfkc_cf.txt
URL: http://svn.apache.org/viewvc/lucene/dev/branches/lucene5995/lucene/analysis/icu/src/data/utr30/nfkc_cf.txt?rev=1629796&r1=1629795&r2=1629796&view=diff
==============================================================================
--- lucene/dev/branches/lucene5995/lucene/analysis/icu/src/data/utr30/nfkc_cf.txt (original)
+++ lucene/dev/branches/lucene5995/lucene/analysis/icu/src/data/utr30/nfkc_cf.txt Tue Oct  7 02:38:14 2014
@@ -1,5 +1,5 @@
 # Unicode Character Database
-# Copyright (c) 1991-2013 Unicode, Inc.
+# Copyright (c) 1991-2014 Unicode, Inc.
 # For terms of use, see http://www.unicode.org/terms_of_use.html
 # For documentation, see http://www.unicode.org/reports/tr44/
 #
@@ -12,7 +12,7 @@
 # and reformatted into syntax for the gennorm2 Normalizer2 data generator tool.
 # Use this file as the third gennorm2 input file after nfc.txt and nfkc.txt.
 
-* Unicode 6.3.0
+* Unicode 7.0.0
 
 0041>0061
 0042>0062
@@ -286,6 +286,7 @@
 0376>0377
 037A>0020 03B9
 037E>003B
+037F>03F3
 0384>0020 0301
 0385>0020 0308 0301
 0386>03AC
@@ -498,6 +499,10 @@
 0522>0523
 0524>0525
 0526>0527
+0528>0529
+052A>052B
+052C>052D
+052E>052F
 0531>0561
 0532>0562
 0533>0563
@@ -2308,6 +2313,10 @@ A690>A691
 A692>A693
 A694>A695
 A696>A697
+A698>A699
+A69A>A69B
+A69C>044A
+A69D>044C
 A722>A723
 A724>A725
 A726>A727
@@ -2359,14 +2368,28 @@ A78B>A78C
 A78D>0265
 A790>A791
 A792>A793
+A796>A797
+A798>A799
+A79A>A79B
+A79C>A79D
+A79E>A79F
 A7A0>A7A1
 A7A2>A7A3
 A7A4>A7A5
 A7A6>A7A7
 A7A8>A7A9
 A7AA>0266
+A7AB>025C
+A7AC>0261
+A7AD>026C
+A7B0>029E
+A7B1>0287
 A7F8>0127
 A7F9>0153
+AB5C>A727
+AB5D>AB37
+AB5E>026B
+AB5F>AB52
 F900>8C48
 F901>66F4
 F902>8ECA
@@ -3743,6 +3766,39 @@ FFF0..FFF8>
 10425>1044D
 10426>1044E
 10427>1044F
+118A0>118C0
+118A1>118C1
+118A2>118C2
+118A3>118C3
+118A4>118C4
+118A5>118C5
+118A6>118C6
+118A7>118C7
+118A8>118C8
+118A9>118C9
+118AA>118CA
+118AB>118CB
+118AC>118CC
+118AD>118CD
+118AE>118CE
+118AF>118CF
+118B0>118D0
+118B1>118D1
+118B2>118D2
+118B3>118D3
+118B4>118D4
+118B5>118D5
+118B6>118D6
+118B7>118D7
+118B8>118D8
+118B9>118D9
+118BA>118DA
+118BB>118DB
+118BC>118DC
+118BD>118DD
+118BE>118DE
+118BF>118DF
+1BCA0..1BCA3>
 1D15E>1D157 1D165
 1D15F>1D158 1D165
 1D160>1D158 1D165 1D16E

Modified: lucene/dev/branches/lucene5995/lucene/analysis/icu/src/java/org/apache/lucene/analysis/icu/segmentation/DefaultICUTokenizerConfig.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/lucene5995/lucene/analysis/icu/src/java/org/apache/lucene/analysis/icu/segmentation/DefaultICUTokenizerConfig.java?rev=1629796&r1=1629795&r2=1629796&view=diff
==============================================================================
--- lucene/dev/branches/lucene5995/lucene/analysis/icu/src/java/org/apache/lucene/analysis/icu/segmentation/DefaultICUTokenizerConfig.java (original)
+++ lucene/dev/branches/lucene5995/lucene/analysis/icu/src/java/org/apache/lucene/analysis/icu/segmentation/DefaultICUTokenizerConfig.java Tue Oct  7 02:38:14 2014
@@ -35,8 +35,8 @@ import com.ibm.icu.util.ULocale;
  * ({@link BreakIterator#getWordInstance(ULocale) BreakIterator.getWordInstance(ULocale.ROOT)}), 
  * but with the following tailorings:
  * <ul>
- *   <li>Thai, Lao, and CJK text is broken into words with a dictionary. 
- *   <li>Myanmar, and Khmer text is broken into syllables
+ *   <li>Thai, Lao, Myanmar, and CJK text is broken into words with a dictionary. 
+ *   <li>Khmer text is broken into syllables
  *   based on custom BreakIterator rules.
  * </ul>
  * @lucene.experimental
@@ -67,8 +67,6 @@ public class DefaultICUTokenizerConfig e
     readBreakIterator("Default.brk");
   private static final BreakIterator khmerBreakIterator = 
     readBreakIterator("Khmer.brk");
-  private static final BreakIterator myanmarBreakIterator = 
-    readBreakIterator("Myanmar.brk");
   
   // TODO: deprecate this boolean? you only care if you are doing super-expert stuff...
   private final boolean cjkAsWords;
@@ -94,7 +92,6 @@ public class DefaultICUTokenizerConfig e
   public BreakIterator getBreakIterator(int script) {
     switch(script) {
       case UScript.KHMER: return (BreakIterator)khmerBreakIterator.clone();
-      case UScript.MYANMAR: return (BreakIterator)myanmarBreakIterator.clone();
       case UScript.JAPANESE: return (BreakIterator)cjkBreakIterator.clone();
       default: return (BreakIterator)defaultBreakIterator.clone();
     }

Modified: lucene/dev/branches/lucene5995/lucene/analysis/icu/src/resources/org/apache/lucene/analysis/icu/segmentation/Default.brk
URL: http://svn.apache.org/viewvc/lucene/dev/branches/lucene5995/lucene/analysis/icu/src/resources/org/apache/lucene/analysis/icu/segmentation/Default.brk?rev=1629796&r1=1629795&r2=1629796&view=diff
==============================================================================
Binary files - no diff available.

Modified: lucene/dev/branches/lucene5995/lucene/analysis/icu/src/resources/org/apache/lucene/analysis/icu/segmentation/Khmer.brk
URL: http://svn.apache.org/viewvc/lucene/dev/branches/lucene5995/lucene/analysis/icu/src/resources/org/apache/lucene/analysis/icu/segmentation/Khmer.brk?rev=1629796&r1=1629795&r2=1629796&view=diff
==============================================================================
Binary files - no diff available.

Modified: lucene/dev/branches/lucene5995/lucene/analysis/icu/src/resources/org/apache/lucene/analysis/icu/utr30.nrm
URL: http://svn.apache.org/viewvc/lucene/dev/branches/lucene5995/lucene/analysis/icu/src/resources/org/apache/lucene/analysis/icu/utr30.nrm?rev=1629796&r1=1629795&r2=1629796&view=diff
==============================================================================
Binary files - no diff available.

Modified: lucene/dev/branches/lucene5995/lucene/analysis/icu/src/test/org/apache/lucene/analysis/icu/segmentation/TestICUTokenizer.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/lucene5995/lucene/analysis/icu/src/test/org/apache/lucene/analysis/icu/segmentation/TestICUTokenizer.java?rev=1629796&r1=1629795&r2=1629796&view=diff
==============================================================================
--- lucene/dev/branches/lucene5995/lucene/analysis/icu/src/test/org/apache/lucene/analysis/icu/segmentation/TestICUTokenizer.java (original)
+++ lucene/dev/branches/lucene5995/lucene/analysis/icu/src/test/org/apache/lucene/analysis/icu/segmentation/TestICUTokenizer.java Tue Oct  7 02:38:14 2014
@@ -122,6 +122,10 @@ public class TestICUTokenizer extends Ba
     assertAnalyzesTo(a, "ພາສາລາວ", new String[] { "ພາສາ", "ລາວ"}, new String[] { "<ALPHANUM>", "<ALPHANUM>" });
   }
   
+  public void testMyanmar() throws Exception {
+    assertAnalyzesTo(a, "သက်ဝင်လှုပ်ရှားစေပြီး", new String[] { "သက်ဝင်", "လှုပ်ရှား", "စေ", "ပြီး" });
+  }
+  
   public void testThai() throws Exception {
     assertAnalyzesTo(a, "การที่ได้ต้องแสดงว่างานดี. แล้วเธอจะไปไหน? ๑๒๓๔",
         new String[] { "การ", "ที่", "ได้", "ต้อง", "แสดง", "ว่า", "งาน", "ดี", "แล้ว", "เธอ", "จะ", "ไป", "ไหน", "๑๒๓๔"});

Modified: lucene/dev/branches/lucene5995/lucene/analysis/icu/src/tools/java/org/apache/lucene/analysis/icu/GenerateUTR30DataFiles.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/lucene5995/lucene/analysis/icu/src/tools/java/org/apache/lucene/analysis/icu/GenerateUTR30DataFiles.java?rev=1629796&r1=1629795&r2=1629796&view=diff
==============================================================================
--- lucene/dev/branches/lucene5995/lucene/analysis/icu/src/tools/java/org/apache/lucene/analysis/icu/GenerateUTR30DataFiles.java (original)
+++ lucene/dev/branches/lucene5995/lucene/analysis/icu/src/tools/java/org/apache/lucene/analysis/icu/GenerateUTR30DataFiles.java Tue Oct  7 02:38:14 2014
@@ -63,7 +63,7 @@ import java.util.regex.Pattern;
 public class GenerateUTR30DataFiles {
   private static final String ICU_SVN_TAG_URL
       = "http://source.icu-project.org/repos/icu/icu/tags";
-  private static final String ICU_RELEASE_TAG = "release-52-1";
+  private static final String ICU_RELEASE_TAG = "release-54-1";
   private static final String ICU_DATA_NORM2_PATH = "source/data/unidata/norm2";
   private static final String NFC_TXT = "nfc.txt";
   private static final String NFKC_TXT = "nfkc.txt";

Modified: lucene/dev/branches/lucene5995/lucene/ivy-versions.properties
URL: http://svn.apache.org/viewvc/lucene/dev/branches/lucene5995/lucene/ivy-versions.properties?rev=1629796&r1=1629795&r2=1629796&view=diff
==============================================================================
--- lucene/dev/branches/lucene5995/lucene/ivy-versions.properties (original)
+++ lucene/dev/branches/lucene5995/lucene/ivy-versions.properties Tue Oct  7 02:38:14 2014
@@ -35,7 +35,7 @@ com.google.inject.guice.version = 3.0
 /com.googlecode.concurrentlinkedhashmap/concurrentlinkedhashmap-lru = 1.2
 /com.googlecode.juniversalchardet/juniversalchardet = 1.0.3
 /com.googlecode.mp4parser/isoparser = 1.0.2
-/com.ibm.icu/icu4j = 53.1
+/com.ibm.icu/icu4j = 54.1
 /com.pff/java-libpst = 0.8.1
 /com.spatial4j/spatial4j = 0.4.1
 

Added: lucene/dev/branches/lucene5995/lucene/licenses/icu4j-54.1.jar.sha1
URL: http://svn.apache.org/viewvc/lucene/dev/branches/lucene5995/lucene/licenses/icu4j-54.1.jar.sha1?rev=1629796&view=auto
==============================================================================
--- lucene/dev/branches/lucene5995/lucene/licenses/icu4j-54.1.jar.sha1 (added)
+++ lucene/dev/branches/lucene5995/lucene/licenses/icu4j-54.1.jar.sha1 Tue Oct  7 02:38:14 2014
@@ -0,0 +1 @@
+3f66ecd5871467598bc81662817b80612a0a907f

Added: lucene/dev/branches/lucene5995/solr/licenses/icu4j-54.1.jar.sha1
URL: http://svn.apache.org/viewvc/lucene/dev/branches/lucene5995/solr/licenses/icu4j-54.1.jar.sha1?rev=1629796&view=auto
==============================================================================
--- lucene/dev/branches/lucene5995/solr/licenses/icu4j-54.1.jar.sha1 (added)
+++ lucene/dev/branches/lucene5995/solr/licenses/icu4j-54.1.jar.sha1 Tue Oct  7 02:38:14 2014
@@ -0,0 +1 @@
+3f66ecd5871467598bc81662817b80612a0a907f