Apache
/
lucene
mirror of https://github.com/apache/lucene.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

LUCENE-9786: Hunspell suggestions: try moving the last character into the middle (#2399)

This commit is contained in:
Peter Gromov 2021-02-19 20:15:57 +01:00 committed by GitHub
parent 3ddc3c04a5
commit 5325d2e6f4
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
5 changed files with 11 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
lucene/analysis/common/src/java/org/apache/lucene/analysis/hunspell/ModifyingSuggester.java
View File

@ -245,11 +245,14 @@ class ModifyingSuggester {
private void tryMovingChar(String word) { private void tryMovingChar(String word) {
for (int i = 0; i < word.length(); i++) { for (int i = 0; i < word.length(); i++) {
for (int j = i + 2; j < word.length() && j <= i + MAX_CHAR_DISTANCE; j++) {
String prefix = word.substring(0, i); String prefix = word.substring(0, i);
for (int j = i + 2; j < word.length() && j <= i + MAX_CHAR_DISTANCE; j++) {
trySuggestion(prefix + word.substring(i + 1, j) + word.charAt(i) + word.substring(j)); trySuggestion(prefix + word.substring(i + 1, j) + word.charAt(i) + word.substring(j));
trySuggestion(prefix + word.charAt(j) + word.substring(i, j) + word.substring(j + 1)); trySuggestion(prefix + word.charAt(j) + word.substring(i, j) + word.substring(j + 1));
} }
if (i < word.length() - 1) {
trySuggestion(prefix + word.substring(i + 1) + word.charAt(i));
}
} }
} }

2
lucene/analysis/common/src/test/org/apache/lucene/analysis/hunspell/sug.aff
View File

@ -13,7 +13,7 @@
# switch off ngram suggestion for testing # switch off ngram suggestion for testing
MAXNGRAMSUGS 0 MAXNGRAMSUGS 0
TRY - TRY -b
REP 2 REP 2
REP alot a_lot REP alot a_lot
REP inspite in_spite REP inspite in_spite

3
lucene/analysis/common/src/test/org/apache/lucene/analysis/hunspell/sug.dic
View File

@ -13,3 +13,6 @@ permanent-vacation/?
in in
spite spite
inspire inspire
Saiph
sahib
ship

2
lucene/analysis/common/src/test/org/apache/lucene/analysis/hunspell/sug.sug
View File

@ -12,4 +12,4 @@ Gandhi
McDonald McDonald
permanent permanent
in, in a in, in a
Saiph, Ship, Sahib

1
lucene/analysis/common/src/test/org/apache/lucene/analysis/hunspell/sug.wrong
View File

@ -14,3 +14,4 @@ permqnent
permanent-vacation permanent-vacation
permqnent-vacation permqnent-vacation
ina ina
Sahip