Skip to content

Commit f68dd65

Browse files
committed
sample lines from the TGH 2013 data file
1 parent b31b5e3 commit f68dd65

File tree

1 file changed

+15
-0
lines changed

1 file changed

+15
-0
lines changed

unicodetools/src/main/java/org/unicode/draft/ReadTGHSet.java

Lines changed: 15 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -9,6 +9,21 @@
99
public class ReadTGHSet {
1010
public static void main(String[] args) throws FileNotFoundException {
1111
UnicodeSet set = new UnicodeSet();
12+
// tgh2013-8105.txt file from Ken Lunde with lines like the following,
13+
// with tabs between fields.
14+
// # URO (7,832)
15+
// U+4E00 1
16+
// U+4E01 5
17+
// U+4E03 7
18+
// U+4E07 35
19+
// ...
20+
// # Extension A (77)
21+
// U+3447 6602
22+
// U+344A 6700
23+
// ...
24+
// # Extension E (108)
25+
// U+2B8B8 7019
26+
// U+2BAC7 7519
1227
Scanner sc =
1328
new Scanner(new File("/usr/local/google/home/mscherer/Downloads/tgh2013-8105.txt"));
1429
while (sc.hasNextLine()) {

0 commit comments

Comments
 (0)