Archives/gnosygnu_xowa
1
0
Fork 0
mirror of https://github.com/gnosygnu/xowa.git synced 2026-03-02 03:49:30 +00:00
Code Issues Projects Releases Wiki Activity

Search: Add more punctuation support

Browse Source
This commit is contained in:
gnosygnu
2017-03-01 16:37:47 -05:00
parent 9301973825
commit 8de3cf0cc6
10 changed files with 233 additions and 26 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
gplx.xowa.mediawiki/src/gplx/xowa/mediawiki/includes/parsers/Xomw_regex_boundary.java
View File

@@ -29,7 +29,7 @@ public class Xomw_regex_boundary { // THREAD.SAFE: trv is only for consistent in
}
public boolean Is_boundary_prv(byte[] src, int pos) {
if (pos == 0) return true; // BOS is true
int bgn = gplx.core.intls.Utf8_.Get_pos0_of_char_bwd(src, pos - 1);
int bgn = gplx.core.intls.Utf8_.Get_prv_char_pos0(src, pos);
byte b = src[bgn];
Object o = trie.Match_at_w_b0(trv, b, src, bgn, pos);
return o != null;

2
gplx.xowa.mediawiki/src/gplx/xowa/mediawiki/includes/parsers/magiclinks/Xomw_magiclinks_wkr.java
View File

@@ -285,7 +285,7 @@ class Xomw_regex_html_entity {
int numbers = 0;
int letters = 0;
while (cur >= src_end) {
int b_bgn = gplx.core.intls.Utf8_.Get_pos0_of_char_bwd(src, cur);
int b_bgn = gplx.core.intls.Utf8_.Get_prv_char_pos0_old(src, cur);
switch (src[b_bgn]) {
case Byte_ascii.Ltr_A: case Byte_ascii.Ltr_B: case Byte_ascii.Ltr_C: case Byte_ascii.Ltr_D: case Byte_ascii.Ltr_E:
case Byte_ascii.Ltr_F: case Byte_ascii.Ltr_G: case Byte_ascii.Ltr_H: case Byte_ascii.Ltr_I: case Byte_ascii.Ltr_J: