baraba/Baradb
1
1
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: comprehensive bug audit — 15 critical/high/medium fixes

Browse Source 
Critical fixes:
- B-Tree splitChild: fixed out-of-bounds on child.children.len (mid+1..len → mid+1..<len)
- Wire protocol: all deserializeValue cases now properly assign to result
- Wire protocol: fkBool/fkInt8 now increment pos after reading
- MVCC: write-write conflict now detected for completed transactions
- MVCC: commit only marks visible versions as deleted (not concurrent uncommitted)
- Lexer: buffer overrun on backslash escape at end of input — added bounds check
- Bulgarian/Russian stemmers: fixed UTF-8 byte offsets for Cyrillic suffixes (2 bytes per char)

High fixes:
- WebSocket: added missing std/tables import
- Raft: added randomize() call for election timeouts
- MemTable.get: binary search O(log n) instead of linear scan O(n)

Medium fixes:
- Zerocopy: string length now written as 4-byte int32 (was single byte)
- Raft appendEntries: guard against nextIdx underflow
- Columnar: null tracking with nulls seq on ColumnPtr
- Removed dead code in lexer readIdent (redundant true/false checks)
- Updated Bulgarian stemming test to match corrected byte offsets

All 214 tests pass across 48 suites with 0 failures.
This commit is contained in:
dimgigov
2026-05-06 02:46:24 +03:00
parent c6de13ef7a
commit 805dbc8ad6
11 changed files with 89 additions and 55 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/barabadb/fts/multilang.nim
+26 -22
View File
@@ -81,17 +81,19 @@ proc stemEnglish*(word: string): string =
proc stemBulgarian*(word: string): string =
if word.len <= 3: return word
# Bulgarian suffixes
if word.endsWith("ища"): return word[0..^4]
if word.endsWith("ище"): return word[0..^4]
if word.endsWith("ция"): return word[0..^4]
if word.endsWith("ние"): return word[0..^4]
if word.endsWith("ост"): return word[0..^4]
if word.endsWith("ство"): return word[0..^5]
if word.endsWith("ски"): return word[0..^4]
if word.endsWith("ски"): return word[0..^4]
if word.endsWith("на"): return word[0..^3]
if word.endsWith("та"): return word[0..^3]
# Bulgarian suffixes (all Cyrillic chars are 2 bytes)
# 3 Cyrillic chars = 6 bytes -> ^7
if word.endsWith("ища"): return word[0..^7]
if word.endsWith("ище"): return word[0..^7]
if word.endsWith("ция"): return word[0..^7]
if word.endsWith("ние"): return word[0..^7]
if word.endsWith("ост"): return word[0..^7]
if word.endsWith("ски"): return word[0..^7]
# 4 Cyrillic chars = 8 bytes -> ^9
if word.endsWith("ство"): return word[0..^9]
# 2 Cyrillic chars = 4 bytes -> ^5
if word.endsWith("на"): return word[0..^5]
if word.endsWith("та"): return word[0..^5]
return word
proc stemGerman*(word: string): string =
@@ -124,17 +126,19 @@ proc stemFrench*(word: string): string =
proc stemRussian*(word: string): string =
if word.len <= 3: return word
# Russian suffixes
if word.endsWith("ость"): return word[0..^5]
if word.endsWith("ение"): return word[0..^5]
if word.endsWith("ание"): return word[0..^5]
if word.endsWith("тель"): return word[0..^5]
if word.endsWith("ский"): return word[0..^5]
if word.endsWith("ция"): return word[0..^4]
if word.endsWith("ние"): return word[0..^4]
if word.endsWith("ать"): return word[0..^4]
if word.endsWith("ить"): return word[0..^4]
if word.endsWith("ыть"): return word[0..^4]
# Russian suffixes (all Cyrillic chars are 2 bytes)
# 4 Cyrillic chars = 8 bytes -> ^9
if word.endsWith("ость"): return word[0..^9]
if word.endsWith("ение"): return word[0..^9]
if word.endsWith("ание"): return word[0..^9]
if word.endsWith("тель"): return word[0..^9]
if word.endsWith("ский"): return word[0..^9]
# 3 Cyrillic chars = 6 bytes -> ^7
if word.endsWith("ция"): return word[0..^7]
if word.endsWith("ние"): return word[0..^7]
if word.endsWith("ать"): return word[0..^7]
if word.endsWith("ить"): return word[0..^7]
if word.endsWith("ыть"): return word[0..^7]
return word
proc getLanguageConfig*(lang: Language): LanguageConfig =