Prune ghost words from affix expansion and stop frequency loader creating words
- Add PruneOrphanWords post-import step that deletes words with no
definitions, synonyms, translations, pronunciations, etymology,
synsets, or frequency data
- Remove INSERT path from CETEMPublico loader — frequency data should
annotate existing words, not create new ones (was inflating pt-PT
from 136K real words to 718K)
- Add hasLetter filter to hunspell, affix, and dicionario loaders to
block punctuation entries like ".", ",", "(" from entering the DB
- Move hasLetter helper to scowl.go alongside other shared filters
Impact: en 655K→129K, pt-PT 1.5M→136K, fr 80K→56K (on reimport)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
@@ -48,7 +48,7 @@ func (a AffixLoader) Load(db *sql.DB, dataDir string) error {
|
||||
seen := make(map[string]struct{})
|
||||
for _, entry := range dicEntries {
|
||||
for _, form := range expandWord(entry.word, entry.flags, rules) {
|
||||
if containsDigit(form) || containsSpace(form) {
|
||||
if !hasLetter(form) || containsDigit(form) || containsSpace(form) {
|
||||
continue
|
||||
}
|
||||
if _, dup := seen[form]; dup {
|
||||
|
||||
Reference in New Issue
Block a user