Skip to content

Suggestions: fix fuzzy skip bug and add distance-2 diacritic fallback #4

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
pashol wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Suggestions: fix fuzzy skip bug and add distance-2 diacritic fallback #4

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
24 changes: 23 additions & 1 deletion srcs/juloo.keyboard2/suggestions/Suggestions.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -127,7 +127,7 @@ int query_suggestions(Cdict dict, String word, String[] dst, int max_count, bool
Cdict.Result r_for_suffixes = (r_exact.found || r_exact.prefix_ptr != 0) ? r_exact : r_alt;
int[] suffixes = dict.suffixes(r_for_suffixes, max_count);
// Disable distance search for small words
int[] dist = (word.length() < 3 || i + 1 >= max_count) ? NO_RESULTS :
int[] dist = (word.length() < 3 || i >= max_count) ? NO_RESULTS :
dict.distance(word, 1, max_count);
for (int j = 0; j < max_count && i < max_count; j++)
{
Expand All @@ -144,12 +144,34 @@ int query_suggestions(Cdict dict, String word, String[] dst, int max_count, bool
dst[i++] = w;
}
}
// Distance-2 fallback: catches diacritic substitutions (e.g. "oppis" → "öppis").
// ö is 2 bytes in UTF-8, so its byte-level edit distance from 'o' is 2, not 1.
// Only fired for pure-ASCII input (user omitted an accent) and words ≥ 5 chars
// to avoid noisy candidates on short inputs.
if (word.length() >= 5 && i < max_count && is_pure_ascii(word))
{
int remaining = max_count - i;
int[] dist2 = dict.distance(word, 2, remaining);
for (int j = 0; j < dist2.length && i < max_count; j++)
{
String w = dict.word(dist2[j]);
if (!already_in(dst, i, w))
dst[i++] = w;
}
}
// Capitalize the full dst array when user typed a capital or cursor is at sentence start
if (first_char_upper || sentence_start)
capitalize_results(dst);
return i;
}

static boolean is_pure_ascii(String word)
{
for (int k = 0; k < word.length(); k++)
if (word.charAt(k) >= 0x80) return false;
return true;
}

static boolean already_in(String[] dst, int count, String word)
{
for (int k = 0; k < count; k++)
Expand Down
Loading