You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lucene.apache.org by jp...@apache.org on 2019/09/05 06:55:25 UTC
[lucene-solr] branch branch_8x updated: LUCENE-8910 upgrade to icu
62.1 must be completed (#775)
This is an automated email from the ASF dual-hosted git repository.
jpountz pushed a commit to branch branch_8x
in repository https://gitbox.apache.org/repos/asf/lucene-solr.git
The following commit(s) were added to refs/heads/branch_8x by this push:
new cc40d2e LUCENE-8910 upgrade to icu 62.1 must be completed (#775)
cc40d2e is described below
commit cc40d2e77a40995cec79be991c9ae142065f1186
Author: mariemat <ma...@gmail.com>
AuthorDate: Thu Sep 5 08:51:24 2019 +0200
LUCENE-8910 upgrade to icu 62.1 must be completed (#775)
---
lucene/analysis/icu/src/data/utr30/nfc.txt | 17 ++++-
lucene/analysis/icu/src/data/utr30/nfkc.txt | 2 +-
lucene/analysis/icu/src/data/utr30/nfkc_cf.txt | 81 ++++++++++++++++++++-
.../org/apache/lucene/analysis/icu/utr30.nrm | Bin 59232 -> 59664 bytes
.../analysis/icu/GenerateUTR30DataFiles.java | 2 +-
5 files changed, 97 insertions(+), 5 deletions(-)
diff --git a/lucene/analysis/icu/src/data/utr30/nfc.txt b/lucene/analysis/icu/src/data/utr30/nfc.txt
index b41056d..c143c1c 100644
--- a/lucene/analysis/icu/src/data/utr30/nfc.txt
+++ b/lucene/analysis/icu/src/data/utr30/nfc.txt
@@ -9,7 +9,7 @@
#
# Complete data for Unicode NFC normalization.
-* Unicode 10.0.0
+* Unicode 11.0.0
# Canonical_Combining_Class (ccc) values
0300..0314:230
@@ -126,11 +126,13 @@
07EB..07F1:230
07F2:220
07F3:230
+07FD:220
0816..0819:230
081B..0823:230
0825..0827:230
0829..082D:230
0859..085B:220
+08D3:220
08D4..08E1:230
08E3:220
08E4..08E5:230
@@ -154,6 +156,7 @@
0953..0954:230
09BC:7
09CD:9
+09FE:230
0A3C:7
0A4D:9
0ABC:7
@@ -301,6 +304,12 @@ FE2E..FE2F:230
10A3F:9
10AE5:230
10AE6:220
+10D24..10D27:230
+10F46..10F47:220
+10F48..10F4A:230
+10F4B:220
+10F4C:230
+10F4D..10F50:220
11046:9
1107F:9
110B9:9
@@ -314,12 +323,13 @@ FE2E..FE2F:230
11236:7
112E9:7
112EA:9
-1133C:7
+1133B..1133C:7
1134D:9
11366..1136C:230
11370..11374:230
11442:9
11446:7
+1145E:230
114C2:9
114C3:7
115BF:9
@@ -328,12 +338,15 @@ FE2E..FE2F:230
116B6:9
116B7:7
1172B:9
+11839:9
+1183A:7
11A34:9
11A47:9
11A99:9
11C3F:9
11D42:7
11D44..11D45:9
+11D97:9
16AF0..16AF4:1
16B30..16B36:230
1BC9E:1
diff --git a/lucene/analysis/icu/src/data/utr30/nfkc.txt b/lucene/analysis/icu/src/data/utr30/nfkc.txt
index 8b71727..416c680 100644
--- a/lucene/analysis/icu/src/data/utr30/nfkc.txt
+++ b/lucene/analysis/icu/src/data/utr30/nfkc.txt
@@ -13,7 +13,7 @@
# to NFKC one-way mappings.
# Use this file as the second gennorm2 input file after nfc.txt.
-* Unicode 10.0.0
+* Unicode 11.0.0
00A0>0020
00A8>0020 0308
diff --git a/lucene/analysis/icu/src/data/utr30/nfkc_cf.txt b/lucene/analysis/icu/src/data/utr30/nfkc_cf.txt
index 726c5b5..d37386e 100644
--- a/lucene/analysis/icu/src/data/utr30/nfkc_cf.txt
+++ b/lucene/analysis/icu/src/data/utr30/nfkc_cf.txt
@@ -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 10.0.0
+* Unicode 11.0.0
0041>0061
0042>0062
@@ -648,6 +648,52 @@
1C86>044A
1C87>0463
1C88>A64B
+1C90>10D0
+1C91>10D1
+1C92>10D2
+1C93>10D3
+1C94>10D4
+1C95>10D5
+1C96>10D6
+1C97>10D7
+1C98>10D8
+1C99>10D9
+1C9A>10DA
+1C9B>10DB
+1C9C>10DC
+1C9D>10DD
+1C9E>10DE
+1C9F>10DF
+1CA0>10E0
+1CA1>10E1
+1CA2>10E2
+1CA3>10E3
+1CA4>10E4
+1CA5>10E5
+1CA6>10E6
+1CA7>10E7
+1CA8>10E8
+1CA9>10E9
+1CAA>10EA
+1CAB>10EB
+1CAC>10EC
+1CAD>10ED
+1CAE>10EE
+1CAF>10EF
+1CB0>10F0
+1CB1>10F1
+1CB2>10F2
+1CB3>10F3
+1CB4>10F4
+1CB5>10F5
+1CB6>10F6
+1CB7>10F7
+1CB8>10F8
+1CB9>10F9
+1CBA>10FA
+1CBD>10FD
+1CBE>10FE
+1CBF>10FF
1D2C>0061
1D2D>00E6
1D2E>0062
@@ -2403,6 +2449,7 @@ A7B2>029D
A7B3>AB53
A7B4>A7B5
A7B6>A7B7
+A7B8>A7B9
A7F8>0127
A7F9>0153
AB5C>A727
@@ -3984,6 +4031,38 @@ FFF0..FFF8>
118BD>118DD
118BE>118DE
118BF>118DF
+16E40>16E60
+16E41>16E61
+16E42>16E62
+16E43>16E63
+16E44>16E64
+16E45>16E65
+16E46>16E66
+16E47>16E67
+16E48>16E68
+16E49>16E69
+16E4A>16E6A
+16E4B>16E6B
+16E4C>16E6C
+16E4D>16E6D
+16E4E>16E6E
+16E4F>16E6F
+16E50>16E70
+16E51>16E71
+16E52>16E72
+16E53>16E73
+16E54>16E74
+16E55>16E75
+16E56>16E76
+16E57>16E77
+16E58>16E78
+16E59>16E79
+16E5A>16E7A
+16E5B>16E7B
+16E5C>16E7C
+16E5D>16E7D
+16E5E>16E7E
+16E5F>16E7F
1BCA0..1BCA3>
1D15E>1D157 1D165
1D15F>1D158 1D165
diff --git a/lucene/analysis/icu/src/resources/org/apache/lucene/analysis/icu/utr30.nrm b/lucene/analysis/icu/src/resources/org/apache/lucene/analysis/icu/utr30.nrm
index 4ded6c9..4c31f90 100644
Binary files a/lucene/analysis/icu/src/resources/org/apache/lucene/analysis/icu/utr30.nrm and b/lucene/analysis/icu/src/resources/org/apache/lucene/analysis/icu/utr30.nrm differ
diff --git a/lucene/analysis/icu/src/tools/java/org/apache/lucene/analysis/icu/GenerateUTR30DataFiles.java b/lucene/analysis/icu/src/tools/java/org/apache/lucene/analysis/icu/GenerateUTR30DataFiles.java
index 042fa37..6a7cf53 100644
--- a/lucene/analysis/icu/src/tools/java/org/apache/lucene/analysis/icu/GenerateUTR30DataFiles.java
+++ b/lucene/analysis/icu/src/tools/java/org/apache/lucene/analysis/icu/GenerateUTR30DataFiles.java
@@ -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/tags";
- private static final String ICU_RELEASE_TAG = "release-60-2";
+ private static final String ICU_RELEASE_TAG = "release-62-1";
private static final String ICU_DATA_NORM2_PATH = "icu4c/source/data/unidata/norm2";
private static final String NFC_TXT = "nfc.txt";
private static final String NFKC_TXT = "nfkc.txt";