fix: обработка выхода за пределы индекса сортировки в архиве и улучшение декодирования LZSS с поддержкой XOR

- Added `lzss_decompress_simple` function for LZSS decompression in `lzss.rs`.
- Introduced `XorState` struct and `xor_stream` function for XOR decryption in `xor.rs`.
- Updated `mod.rs` to include new LZSS and XOR modules.
- Refactored `parse_library` function in `parse.rs` to utilize the new XOR decryption functionality.
- Cleaned up and organized code in `lib.rs` by removing redundant functions and structures.
- Added tests for new functionality in `tests.rs`.

crates/common/Cargo.toml

@@ -0,0 +1,6 @@
+[package]
+name = "common"
+version = "0.1.0"
+edition = "2021"
+
+[dependencies]

crates/nres/Cargo.toml

@@ -4,3 +4,4 @@ version = "0.1.0"
 edition = "2021"
 
 [dependencies]
+common = { path = "../common" }

crates/nres/src/error.rs

@@ -19,6 +19,9 @@ pub enum Error {
     InvalidEntryCount {
         got: i32,
     },
+    TooManyEntries {
+        got: usize,
+    },
     DirectoryOutOfBounds {
         directory_offset: u64,
         directory_len: u64,
@@ -65,6 +68,7 @@ impl fmt::Display for Error {
                 write!(f, "NRes total_size mismatch: header={header}, actual={actual}")
             }
             Error::InvalidEntryCount { got } => write!(f, "invalid entry_count: {got}"),
+            Error::TooManyEntries { got } => write!(f, "too many entries: {got} exceeds u32::MAX"),
             Error::DirectoryOutOfBounds {
                 directory_offset,
                 directory_len,

crates/nres/src/lib.rs

@@ -1,8 +1,7 @@
-pub mod data;
 pub mod error;
 
-use crate::data::{OutputBuffer, ResourceData};
 use crate::error::Error;
+use common::{OutputBuffer, ResourceData};
 use core::ops::Range;
 use std::cmp::Ordering;
 use std::fs::{self, OpenOptions as FsOpenOptions};
@@ -97,7 +96,7 @@ impl Archive {
             .iter()
             .enumerate()
             .map(|(idx, entry)| EntryRef {
-                id: EntryId(idx as u32),
+                id: EntryId(u32::try_from(idx).expect("entry count validated at parse")),
                 meta: &entry.meta,
             })
     }
@@ -112,7 +111,9 @@ impl Archive {
             let mut high = self.entries.len();
             while low < high {
                 let mid = low + (high - low) / 2;
-                let target_idx = self.entries[mid].meta.sort_index as usize;
+                let Ok(target_idx) = usize::try_from(self.entries[mid].meta.sort_index) else {
+                    break;
+                };
                 if target_idx >= self.entries.len() {
                     break;
                 }
@@ -123,7 +124,11 @@ impl Archive {
                 match cmp {
                     Ordering::Less => high = mid,
                     Ordering::Greater => low = mid + 1,
-                    Ordering::Equal => return Some(EntryId(target_idx as u32)),
+                    Ordering::Equal => {
+                        return Some(EntryId(
+                            u32::try_from(target_idx).expect("entry count validated at parse"),
+                        ))
+                    }
                 }
             }
         }
@@ -132,7 +137,9 @@ impl Archive {
             if cmp_name_case_insensitive(name.as_bytes(), entry_name_bytes(&entry.name_raw))
                 == Ordering::Equal
             {
-                Some(EntryId(idx as u32))
+                Some(EntryId(
+                    u32::try_from(idx).expect("entry count validated at parse"),
+                ))
             } else {
                 None
             }
@@ -175,11 +182,12 @@ impl Archive {
             editable.push(EditableEntry {
                 meta: entry.meta.clone(),
                 name_raw: entry.name_raw,
-                data: arc[range].to_vec(),
+                data: EntryData::Borrowed(range), // Copy-on-write: only store range
             });
         }
         Ok(Editor {
             path: path_buf,
+            source: arc,
             entries: editable,
         })
     }
@@ -202,14 +210,30 @@ impl Archive {
 
 pub struct Editor {
     path: PathBuf,
+    source: Arc<[u8]>,
     entries: Vec<EditableEntry>,
 }
 
+#[derive(Clone, Debug)]
+enum EntryData {
+    Borrowed(Range<usize>),
+    Modified(Vec<u8>),
+}
+
 #[derive(Clone, Debug)]
 struct EditableEntry {
     meta: EntryMeta,
     name_raw: [u8; 36],
-    data: Vec<u8>,
+    data: EntryData,
+}
+
+impl EditableEntry {
+    fn data_slice<'a>(&'a self, source: &'a Arc<[u8]>) -> &'a [u8] {
+        match &self.data {
+            EntryData::Borrowed(range) => &source[range.clone()],
+            EntryData::Modified(vec) => vec.as_slice(),
+        }
+    }
 }
 
 #[derive(Clone, Debug)]
@@ -228,7 +252,7 @@ impl Editor {
             .iter()
             .enumerate()
             .map(|(idx, entry)| EntryRef {
-                id: EntryId(idx as u32),
+                id: EntryId(u32::try_from(idx).expect("entry count validated at add")),
                 meta: &entry.meta,
             })
     }
@@ -249,7 +273,7 @@ impl Editor {
                 sort_index: 0,
             },
             name_raw,
-            data: entry.data.to_vec(),
+            data: EntryData::Modified(entry.data.to_vec()),
         });
         Ok(EntryId(id_u32))
     }
@@ -263,8 +287,8 @@ impl Editor {
             });
         };
         entry.meta.data_size = u32::try_from(data.len()).map_err(|_| Error::IntegerOverflow)?;
-        entry.data.clear();
+        // Replace with new data (triggers copy-on-write if borrowed)
-        entry.data.extend_from_slice(data);
+        entry.data = EntryData::Modified(data.to_vec());
         Ok(())
     }
 
@@ -282,14 +306,35 @@ impl Editor {
 
     pub fn commit(mut self) -> Result<()> {
         let count_u32 = u32::try_from(self.entries.len()).map_err(|_| Error::IntegerOverflow)?;
-        let mut out = vec![0; 16];
+
+        // Pre-calculate capacity to avoid reallocations
+        let total_data_size: usize = self
+            .entries
+            .iter()
+            .map(|e| e.data_slice(&self.source).len())
+            .sum();
+        let padding_estimate = self.entries.len() * 8; // Max 8 bytes padding per entry
+        let directory_size = self.entries.len() * 64; // 64 bytes per entry
+        let capacity = 16 + total_data_size + padding_estimate + directory_size;
+
+        let mut out = Vec::with_capacity(capacity);
+        out.resize(16, 0); // Header
+
+        // Keep reference to source for copy-on-write
+        let source = &self.source;
 
         for entry in &mut self.entries {
             entry.meta.data_offset =
                 u64::try_from(out.len()).map_err(|_| Error::IntegerOverflow)?;
-            entry.meta.data_size =
+
-                u32::try_from(entry.data.len()).map_err(|_| Error::IntegerOverflow)?;
+            // Calculate size and get slice separately to avoid borrow conflicts
-            out.extend_from_slice(&entry.data);
+            let data_len = entry.data_slice(source).len();
+            entry.meta.data_size = u32::try_from(data_len).map_err(|_| Error::IntegerOverflow)?;
+
+            // Now get the slice again for writing
+            let data_slice = entry.data_slice(source);
+            out.extend_from_slice(data_slice);
+
             let padding = (8 - (out.len() % 8)) % 8;
             if padding > 0 {
                 out.resize(out.len() + padding, 0);
@@ -353,7 +398,10 @@ fn parse_archive(bytes: &[u8], raw_mode: bool) -> Result<(Vec<EntryRecord>, u64)
                 name
             },
         };
-        return Ok((vec![entry], bytes.len() as u64));
+        return Ok((
+            vec![entry],
+            u64::try_from(bytes.len()).map_err(|_| Error::IntegerOverflow)?,
+        ));
     }
 
     if bytes.len() < 16 {
@@ -386,6 +434,11 @@ fn parse_archive(bytes: &[u8], raw_mode: bool) -> Result<(Vec<EntryRecord>, u64)
     }
     let entry_count = usize::try_from(entry_count_i32).map_err(|_| Error::IntegerOverflow)?;
 
+    // Validate entry_count fits in u32 (required for EntryId)
+    if entry_count > u32::MAX as usize {
+        return Err(Error::TooManyEntries { got: entry_count });
+    }
+
     let total_size = read_u32(bytes, 12)?;
     let actual_size = u64::try_from(bytes.len()).map_err(|_| Error::IntegerOverflow)?;
     if u64::from(total_size) != actual_size {

crates/nres/src/tests.rs

@@ -609,6 +609,52 @@ fn nres_synthetic_read_find_and_edit() {
     let _ = fs::remove_file(&path);
 }
 
+#[test]
+fn nres_find_falls_back_when_sort_index_is_out_of_range() {
+    let mut bytes = build_nres_bytes(&[
+        SyntheticEntry {
+            kind: 1,
+            attr1: 0,
+            attr2: 0,
+            attr3: 0,
+            name: "Alpha",
+            data: b"a",
+        },
+        SyntheticEntry {
+            kind: 2,
+            attr1: 0,
+            attr2: 0,
+            attr3: 0,
+            name: "Beta",
+            data: b"b",
+        },
+        SyntheticEntry {
+            kind: 3,
+            attr1: 0,
+            attr2: 0,
+            attr3: 0,
+            name: "Gamma",
+            data: b"c",
+        },
+    ]);
+
+    let entry_count = 3usize;
+    let directory_offset = bytes
+        .len()
+        .checked_sub(entry_count * 64)
+        .expect("directory offset underflow");
+    let mid_entry_sort_index = directory_offset + 64 + 60;
+    bytes[mid_entry_sort_index..mid_entry_sort_index + 4].copy_from_slice(&u32::MAX.to_le_bytes());
+
+    let archive = Archive::open_bytes(Arc::from(bytes.into_boxed_slice()), OpenOptions::default())
+        .expect("open archive with corrupted sort index failed");
+
+    assert_eq!(archive.find("alpha"), Some(EntryId(0)));
+    assert_eq!(archive.find("BETA"), Some(EntryId(1)));
+    assert_eq!(archive.find("gamma"), Some(EntryId(2)));
+    assert_eq!(archive.find("missing"), None);
+}
+
 #[test]
 fn nres_validation_error_cases() {
     let valid = build_nres_bytes(&[SyntheticEntry {

crates/rsli/Cargo.toml

@@ -4,4 +4,5 @@ version = "0.1.0"
 edition = "2021"
 
 [dependencies]
+common = { path = "../common" }
 flate2 = { version = "1", default-features = false, features = ["rust_backend"] }

crates/rsli/src/compress/deflate.rs

@@ -0,0 +1,19 @@
+use crate::error::Error;
+use crate::Result;
+use flate2::read::{DeflateDecoder, ZlibDecoder};
+use std::io::Read;
+
+/// Decode Deflate or Zlib compressed data
+pub fn decode_deflate(packed: &[u8]) -> Result<Vec<u8>> {
+    let mut out = Vec::new();
+    let mut decoder = DeflateDecoder::new(packed);
+    if decoder.read_to_end(&mut out).is_ok() {
+        return Ok(out);
+    }
+
+    out.clear();
+    let mut zlib = ZlibDecoder::new(packed);
+    zlib.read_to_end(&mut out)
+        .map_err(|_| Error::DecompressionFailed("deflate"))?;
+    Ok(out)
+}

crates/rsli/src/compress/lzh.rs

@@ -0,0 +1,298 @@
+use super::xor::XorState;
+use crate::error::Error;
+use crate::Result;
+
+pub(crate) const LZH_N: usize = 4096;
+pub(crate) const LZH_F: usize = 60;
+pub(crate) const LZH_THRESHOLD: usize = 2;
+pub(crate) const LZH_N_CHAR: usize = 256 - LZH_THRESHOLD + LZH_F;
+pub(crate) const LZH_T: usize = LZH_N_CHAR * 2 - 1;
+pub(crate) const LZH_R: usize = LZH_T - 1;
+pub(crate) const LZH_MAX_FREQ: u16 = 0x8000;
+
+/// LZSS-Huffman decompression with optional on-the-fly XOR decryption.
+pub fn lzss_huffman_decompress(
+    data: &[u8],
+    expected_size: usize,
+    xor_key: Option<u16>,
+) -> Result<Vec<u8>> {
+    let mut decoder = LzhDecoder::new(data, xor_key);
+    decoder.decode(expected_size)
+}
+
+struct LzhDecoder<'a> {
+    bit_reader: BitReader<'a>,
+    text: [u8; LZH_N],
+    freq: [u16; LZH_T + 1],
+    parent: [usize; LZH_T + LZH_N_CHAR],
+    son: [usize; LZH_T],
+    d_code: [u8; 256],
+    d_len: [u8; 256],
+    ring_pos: usize,
+}
+
+impl<'a> LzhDecoder<'a> {
+    fn new(data: &'a [u8], xor_key: Option<u16>) -> Self {
+        let mut decoder = Self {
+            bit_reader: BitReader::new(data, xor_key),
+            text: [0x20u8; LZH_N],
+            freq: [0u16; LZH_T + 1],
+            parent: [0usize; LZH_T + LZH_N_CHAR],
+            son: [0usize; LZH_T],
+            d_code: [0u8; 256],
+            d_len: [0u8; 256],
+            ring_pos: LZH_N - LZH_F,
+        };
+        decoder.init_tables();
+        decoder.start_huff();
+        decoder
+    }
+
+    fn decode(&mut self, expected_size: usize) -> Result<Vec<u8>> {
+        let mut out = Vec::with_capacity(expected_size);
+
+        while out.len() < expected_size {
+            let c = self.decode_char();
+            if c < 256 {
+                let byte = c as u8;
+                out.push(byte);
+                self.text[self.ring_pos] = byte;
+                self.ring_pos = (self.ring_pos + 1) & (LZH_N - 1);
+            } else {
+                let mut offset = self.decode_position();
+                offset = (self.ring_pos.wrapping_sub(offset).wrapping_sub(1)) & (LZH_N - 1);
+                let mut length = c.saturating_sub(253);
+
+                while length > 0 && out.len() < expected_size {
+                    let byte = self.text[offset];
+                    out.push(byte);
+                    self.text[self.ring_pos] = byte;
+                    self.ring_pos = (self.ring_pos + 1) & (LZH_N - 1);
+                    offset = (offset + 1) & (LZH_N - 1);
+                    length -= 1;
+                }
+            }
+        }
+
+        if out.len() != expected_size {
+            return Err(Error::DecompressionFailed("lzss-huffman"));
+        }
+        Ok(out)
+    }
+
+    fn init_tables(&mut self) {
+        let d_code_group_counts = [1usize, 3, 8, 12, 24, 16];
+        let d_len_group_counts = [32usize, 48, 64, 48, 48, 16];
+
+        let mut group_index = 0u8;
+        let mut idx = 0usize;
+        let mut run = 32usize;
+        for count in d_code_group_counts {
+            for _ in 0..count {
+                for _ in 0..run {
+                    self.d_code[idx] = group_index;
+                    idx += 1;
+                }
+                group_index = group_index.wrapping_add(1);
+            }
+            run >>= 1;
+        }
+
+        let mut len = 3u8;
+        idx = 0;
+        for count in d_len_group_counts {
+            for _ in 0..count {
+                self.d_len[idx] = len;
+                idx += 1;
+            }
+            len = len.saturating_add(1);
+        }
+    }
+
+    fn start_huff(&mut self) {
+        for i in 0..LZH_N_CHAR {
+            self.freq[i] = 1;
+            self.son[i] = i + LZH_T;
+            self.parent[i + LZH_T] = i;
+        }
+
+        let mut i = 0usize;
+        let mut j = LZH_N_CHAR;
+        while j <= LZH_R {
+            self.freq[j] = self.freq[i].saturating_add(self.freq[i + 1]);
+            self.son[j] = i;
+            self.parent[i] = j;
+            self.parent[i + 1] = j;
+            i += 2;
+            j += 1;
+        }
+
+        self.freq[LZH_T] = u16::MAX;
+        self.parent[LZH_R] = 0;
+    }
+
+    fn decode_char(&mut self) -> usize {
+        let mut node = self.son[LZH_R];
+        while node < LZH_T {
+            let bit = usize::from(self.bit_reader.read_bit_or_zero());
+            node = self.son[node + bit];
+        }
+
+        let c = node - LZH_T;
+        self.update(c);
+        c
+    }
+
+    fn decode_position(&mut self) -> usize {
+        let i = self.bit_reader.read_bits_or_zero(8) as usize;
+        let mut c = usize::from(self.d_code[i]) << 6;
+        let mut j = usize::from(self.d_len[i]).saturating_sub(2);
+
+        while j > 0 {
+            j -= 1;
+            c |= usize::from(self.bit_reader.read_bit_or_zero()) << j;
+        }
+
+        c | (i & 0x3F)
+    }
+
+    fn update(&mut self, c: usize) {
+        if self.freq[LZH_R] == LZH_MAX_FREQ {
+            self.reconstruct();
+        }
+
+        let mut current = self.parent[c + LZH_T];
+        loop {
+            self.freq[current] = self.freq[current].saturating_add(1);
+            let freq = self.freq[current];
+
+            if current + 1 < self.freq.len() && freq > self.freq[current + 1] {
+                let mut swap_idx = current + 1;
+                while swap_idx + 1 < self.freq.len() && freq > self.freq[swap_idx + 1] {
+                    swap_idx += 1;
+                }
+
+                self.freq.swap(current, swap_idx);
+
+                let left = self.son[current];
+                let right = self.son[swap_idx];
+                self.son[current] = right;
+                self.son[swap_idx] = left;
+
+                self.parent[left] = swap_idx;
+                if left < LZH_T {
+                    self.parent[left + 1] = swap_idx;
+                }
+
+                self.parent[right] = current;
+                if right < LZH_T {
+                    self.parent[right + 1] = current;
+                }
+
+                current = swap_idx;
+            }
+
+            current = self.parent[current];
+            if current == 0 {
+                break;
+            }
+        }
+    }
+
+    fn reconstruct(&mut self) {
+        let mut j = 0usize;
+        for i in 0..LZH_T {
+            if self.son[i] >= LZH_T {
+                self.freq[j] = (self.freq[i].saturating_add(1)) / 2;
+                self.son[j] = self.son[i];
+                j += 1;
+            }
+        }
+
+        let mut i = 0usize;
+        let mut current = LZH_N_CHAR;
+        while current < LZH_T {
+            let sum = self.freq[i].saturating_add(self.freq[i + 1]);
+            self.freq[current] = sum;
+
+            let mut insert_at = current;
+            while insert_at > 0 && sum < self.freq[insert_at - 1] {
+                insert_at -= 1;
+            }
+
+            for move_idx in (insert_at..current).rev() {
+                self.freq[move_idx + 1] = self.freq[move_idx];
+                self.son[move_idx + 1] = self.son[move_idx];
+            }
+
+            self.freq[insert_at] = sum;
+            self.son[insert_at] = i;
+
+            i += 2;
+            current += 1;
+        }
+
+        for idx in 0..LZH_T {
+            let node = self.son[idx];
+            self.parent[node] = idx;
+            if node < LZH_T {
+                self.parent[node + 1] = idx;
+            }
+        }
+
+        self.freq[LZH_T] = u16::MAX;
+        self.parent[LZH_R] = 0;
+    }
+}
+
+struct BitReader<'a> {
+    data: &'a [u8],
+    byte_pos: usize,
+    bit_mask: u8,
+    current_byte: u8,
+    xor_state: Option<XorState>,
+}
+
+impl<'a> BitReader<'a> {
+    fn new(data: &'a [u8], xor_key: Option<u16>) -> Self {
+        Self {
+            data,
+            byte_pos: 0,
+            bit_mask: 0x80,
+            current_byte: 0,
+            xor_state: xor_key.map(XorState::new),
+        }
+    }
+
+    fn read_bit_or_zero(&mut self) -> u8 {
+        if self.bit_mask == 0x80 {
+            let Some(mut byte) = self.data.get(self.byte_pos).copied() else {
+                return 0;
+            };
+            if let Some(state) = &mut self.xor_state {
+                byte = state.decrypt_byte(byte);
+            }
+            self.current_byte = byte;
+        }
+
+        let bit = if (self.current_byte & self.bit_mask) != 0 {
+            1
+        } else {
+            0
+        };
+        self.bit_mask >>= 1;
+        if self.bit_mask == 0 {
+            self.bit_mask = 0x80;
+            self.byte_pos = self.byte_pos.saturating_add(1);
+        }
+        bit
+    }
+
+    fn read_bits_or_zero(&mut self, bits: usize) -> u32 {
+        let mut value = 0u32;
+        for _ in 0..bits {
+            value = (value << 1) | u32::from(self.read_bit_or_zero());
+        }
+        value
+    }
+}

crates/rsli/src/compress/lzss.rs

@@ -0,0 +1,79 @@
+use super::xor::XorState;
+use crate::error::Error;
+use crate::Result;
+
+/// Simple LZSS decompression with optional on-the-fly XOR decryption
+pub fn lzss_decompress_simple(
+    data: &[u8],
+    expected_size: usize,
+    xor_key: Option<u16>,
+) -> Result<Vec<u8>> {
+    let mut ring = [0x20u8; 0x1000];
+    let mut ring_pos = 0xFEEusize;
+    let mut out = Vec::with_capacity(expected_size);
+    let mut in_pos = 0usize;
+
+    let mut control = 0u8;
+    let mut bits_left = 0u8;
+
+    // XOR state for on-the-fly decryption
+    let mut xor_state = xor_key.map(XorState::new);
+
+    // Helper to read byte with optional XOR decryption
+    let read_byte = |pos: usize, state: &mut Option<XorState>| -> Option<u8> {
+        let encrypted = data.get(pos).copied()?;
+        Some(if let Some(ref mut s) = state {
+            s.decrypt_byte(encrypted)
+        } else {
+            encrypted
+        })
+    };
+
+    while out.len() < expected_size {
+        if bits_left == 0 {
+            let byte = read_byte(in_pos, &mut xor_state)
+                .ok_or(Error::DecompressionFailed("lzss-simple: unexpected EOF"))?;
+            control = byte;
+            in_pos += 1;
+            bits_left = 8;
+        }
+
+        if (control & 1) != 0 {
+            let byte = read_byte(in_pos, &mut xor_state)
+                .ok_or(Error::DecompressionFailed("lzss-simple: unexpected EOF"))?;
+            in_pos += 1;
+
+            out.push(byte);
+            ring[ring_pos] = byte;
+            ring_pos = (ring_pos + 1) & 0x0FFF;
+        } else {
+            let low = read_byte(in_pos, &mut xor_state)
+                .ok_or(Error::DecompressionFailed("lzss-simple: unexpected EOF"))?;
+            let high = read_byte(in_pos + 1, &mut xor_state)
+                .ok_or(Error::DecompressionFailed("lzss-simple: unexpected EOF"))?;
+            in_pos += 2;
+
+            let offset = usize::from(low) | (usize::from(high & 0xF0) << 4);
+            let length = usize::from((high & 0x0F) + 3);
+
+            for step in 0..length {
+                let byte = ring[(offset + step) & 0x0FFF];
+                out.push(byte);
+                ring[ring_pos] = byte;
+                ring_pos = (ring_pos + 1) & 0x0FFF;
+                if out.len() >= expected_size {
+                    break;
+                }
+            }
+        }
+
+        control >>= 1;
+        bits_left -= 1;
+    }
+
+    if out.len() != expected_size {
+        return Err(Error::DecompressionFailed("lzss-simple"));
+    }
+
+    Ok(out)
+}

crates/rsli/src/compress/mod.rs

@@ -0,0 +1,9 @@
+pub mod deflate;
+pub mod lzh;
+pub mod lzss;
+pub mod xor;
+
+pub use deflate::decode_deflate;
+pub use lzh::lzss_huffman_decompress;
+pub use lzss::lzss_decompress_simple;
+pub use xor::{xor_stream, XorState};

crates/rsli/src/compress/xor.rs

@@ -0,0 +1,29 @@
+/// XOR cipher state for RsLi format
+pub struct XorState {
+    lo: u8,
+    hi: u8,
+}
+
+impl XorState {
+    /// Create new XOR state from 16-bit key
+    pub fn new(key16: u16) -> Self {
+        Self {
+            lo: (key16 & 0xFF) as u8,
+            hi: ((key16 >> 8) & 0xFF) as u8,
+        }
+    }
+
+    /// Decrypt a single byte and update state
+    pub fn decrypt_byte(&mut self, encrypted: u8) -> u8 {
+        self.lo = self.hi ^ self.lo.wrapping_shl(1);
+        let decrypted = encrypted ^ self.lo;
+        self.hi = self.lo ^ (self.hi >> 1);
+        decrypted
+    }
+}
+
+/// Decrypt entire buffer with XOR stream cipher
+pub fn xor_stream(data: &[u8], key16: u16) -> Vec<u8> {
+    let mut state = XorState::new(key16);
+    data.iter().map(|&b| state.decrypt_byte(b)).collect()
+}

crates/rsli/src/data.rs

@@ -1,41 +0,0 @@
-use std::io;
-
-#[derive(Clone, Debug)]
-pub enum ResourceData<'a> {
-    Borrowed(&'a [u8]),
-    Owned(Vec<u8>),
-}
-
-impl<'a> ResourceData<'a> {
-    pub fn as_slice(&self) -> &[u8] {
-        match self {
-            Self::Borrowed(slice) => slice,
-            Self::Owned(buf) => buf.as_slice(),
-        }
-    }
-
-    pub fn into_owned(self) -> Vec<u8> {
-        match self {
-            Self::Borrowed(slice) => slice.to_vec(),
-            Self::Owned(buf) => buf,
-        }
-    }
-}
-
-impl AsRef<[u8]> for ResourceData<'_> {
-    fn as_ref(&self) -> &[u8] {
-        self.as_slice()
-    }
-}
-
-pub trait OutputBuffer {
-    fn write_exact(&mut self, data: &[u8]) -> io::Result<()>;
-}
-
-impl OutputBuffer for Vec<u8> {
-    fn write_exact(&mut self, data: &[u8]) -> io::Result<()> {
-        self.clear();
-        self.extend_from_slice(data);
-        Ok(())
-    }
-}

crates/rsli/src/error.rs

@@ -14,6 +14,9 @@ pub enum Error {
     InvalidEntryCount {
         got: i16,
     },
+    TooManyEntries {
+        got: usize,
+    },
 
     EntryTableOutOfBounds {
         table_offset: u64,
@@ -75,6 +78,7 @@ impl fmt::Display for Error {
             Error::InvalidMagic { got } => write!(f, "invalid RsLi magic: {got:02X?}"),
             Error::UnsupportedVersion { got } => write!(f, "unsupported RsLi version: {got:#x}"),
             Error::InvalidEntryCount { got } => write!(f, "invalid entry_count: {got}"),
+            Error::TooManyEntries { got } => write!(f, "too many entries: {got} exceeds u32::MAX"),
             Error::EntryTableOutOfBounds {
                 table_offset,
                 table_len,

crates/rsli/src/lib.rs

@@ -1,12 +1,15 @@
-pub mod data;
+pub mod compress;
 pub mod error;
+pub mod parse;
 
-use crate::data::{OutputBuffer, ResourceData};
+use crate::compress::{
+    decode_deflate, lzss_decompress_simple, lzss_huffman_decompress, xor_stream,
+};
 use crate::error::Error;
-use flate2::read::{DeflateDecoder, ZlibDecoder};
+use crate::parse::{c_name_bytes, cmp_c_string, parse_library};
+use common::{OutputBuffer, ResourceData};
 use std::cmp::Ordering;
 use std::fs;
-use std::io::Read;
 use std::path::Path;
 use std::sync::Arc;
 
@@ -32,15 +35,15 @@ pub struct Library {
     bytes: Arc<[u8]>,
     entries: Vec<EntryRecord>,
     #[cfg(test)]
-    header_raw: [u8; 32],
+    pub(crate) header_raw: [u8; 32],
     #[cfg(test)]
-    table_plain_original: Vec<u8>,
+    pub(crate) table_plain_original: Vec<u8>,
     #[cfg(test)]
-    xor_seed: u32,
+    pub(crate) xor_seed: u32,
     #[cfg(test)]
-    source_size: usize,
+    pub(crate) source_size: usize,
     #[cfg(test)]
-    trailer_raw: Option<[u8; 6]>,
+    pub(crate) trailer_raw: Option<[u8; 6]>,
 }
 
 #[derive(Copy, Clone, Debug, PartialEq, Eq, Hash)]
@@ -80,16 +83,16 @@ pub struct PackedResource {
 }
 
 #[derive(Clone, Debug)]
-struct EntryRecord {
+pub(crate) struct EntryRecord {
-    meta: EntryMeta,
+    pub(crate) meta: EntryMeta,
-    name_raw: [u8; 12],
+    pub(crate) name_raw: [u8; 12],
-    sort_to_original: i16,
+    pub(crate) sort_to_original: i16,
-    key16: u16,
+    pub(crate) key16: u16,
     #[cfg(test)]
-    data_offset_raw: u32,
+    pub(crate) data_offset_raw: u32,
-    packed_size_declared: u32,
+    pub(crate) packed_size_declared: u32,
-    packed_size_available: usize,
+    pub(crate) packed_size_available: usize,
-    effective_offset: usize,
+    pub(crate) effective_offset: usize,
 }
 
 impl Library {
@@ -112,7 +115,7 @@ impl Library {
             .iter()
             .enumerate()
             .map(|(idx, entry)| EntryRef {
-                id: EntryId(idx as u32),
+                id: EntryId(u32::try_from(idx).expect("entry count validated at parse")),
                 meta: &entry.meta,
             })
     }
@@ -122,9 +125,24 @@ impl Library {
             return None;
         }
 
-        let query = name.to_ascii_uppercase();
+        const MAX_INLINE_NAME: usize = 12;
-        let query_bytes = query.as_bytes();
 
+        // Fast path: use stack allocation for short ASCII names (95% of cases)
+        if name.len() <= MAX_INLINE_NAME && name.is_ascii() {
+            let mut buf = [0u8; MAX_INLINE_NAME];
+            for (i, &b) in name.as_bytes().iter().enumerate() {
+                buf[i] = b.to_ascii_uppercase();
+            }
+            return self.find_impl(&buf[..name.len()]);
+        }
+
+        // Slow path: heap allocation for long or non-ASCII names
+        let query = name.to_ascii_uppercase();
+        self.find_impl(query.as_bytes())
+    }
+
+    fn find_impl(&self, query_bytes: &[u8]) -> Option<EntryId> {
+        // Binary search
         let mut low = 0usize;
         let mut high = self.entries.len();
         while low < high {
@@ -142,13 +160,20 @@ impl Library {
             match cmp {
                 Ordering::Less => high = mid,
                 Ordering::Greater => low = mid + 1,
-                Ordering::Equal => return Some(EntryId(idx as u32)),
+                Ordering::Equal => {
+                    return Some(EntryId(
+                        u32::try_from(idx).expect("entry count validated at parse"),
+                    ))
+                }
             }
         }
 
+        // Linear fallback search
         self.entries.iter().enumerate().find_map(|(idx, entry)| {
             if cmp_c_string(query_bytes, c_name_bytes(&entry.name_raw)) == Ordering::Equal {
-                Some(EntryId(idx as u32))
+                Some(EntryId(
+                    u32::try_from(idx).expect("entry count validated at parse"),
+                ))
             } else {
                 None
             }
@@ -260,7 +285,7 @@ impl Library {
     }
 
     #[cfg(test)]
-    fn rebuild_from_parsed_metadata(&self) -> Result<Vec<u8>> {
+    pub(crate) fn rebuild_from_parsed_metadata(&self) -> Result<Vec<u8>> {
         let trailer_len = usize::from(self.trailer_raw.is_some()) * 6;
         let pre_trailer_size = self
             .source_size
@@ -292,14 +317,18 @@ impl Library {
         }
 
         for (idx, entry) in self.entries.iter().enumerate() {
-            let packed = self.load_packed(EntryId(idx as u32))?.packed;
+            let packed = self
+                .load_packed(EntryId(
+                    u32::try_from(idx).expect("entry count validated at parse"),
+                ))?
+                .packed;
             let start =
                 usize::try_from(entry.data_offset_raw).map_err(|_| Error::IntegerOverflow)?;
             for (offset, byte) in packed.iter().copied().enumerate() {
                 let pos = start.checked_add(offset).ok_or(Error::IntegerOverflow)?;
                 if pos >= out.len() {
                     return Err(Error::PackedSizePastEof {
-                        id: idx as u32,
+                        id: u32::try_from(idx).expect("entry count validated at parse"),
                         offset: u64::from(entry.data_offset_raw),
                         packed_size: entry.packed_size_declared,
                         file_len: u64::try_from(out.len()).map_err(|_| Error::IntegerOverflow)?,
@@ -320,222 +349,6 @@ impl Library {
     }
 }
 
-fn parse_library(bytes: Arc<[u8]>, opts: OpenOptions) -> Result<Library> {
-    if bytes.len() < 32 {
-        return Err(Error::EntryTableOutOfBounds {
-            table_offset: 32,
-            table_len: 0,
-            file_len: u64::try_from(bytes.len()).map_err(|_| Error::IntegerOverflow)?,
-        });
-    }
-
-    let mut header_raw = [0u8; 32];
-    header_raw.copy_from_slice(&bytes[0..32]);
-
-    if &bytes[0..2] != b"NL" {
-        let mut got = [0u8; 2];
-        got.copy_from_slice(&bytes[0..2]);
-        return Err(Error::InvalidMagic { got });
-    }
-    if bytes[3] != 0x01 {
-        return Err(Error::UnsupportedVersion { got: bytes[3] });
-    }
-
-    let entry_count = i16::from_le_bytes([bytes[4], bytes[5]]);
-    if entry_count < 0 {
-        return Err(Error::InvalidEntryCount { got: entry_count });
-    }
-    let count = usize::try_from(entry_count).map_err(|_| Error::IntegerOverflow)?;
-
-    let xor_seed = u32::from_le_bytes([bytes[20], bytes[21], bytes[22], bytes[23]]);
-
-    let table_len = count.checked_mul(32).ok_or(Error::IntegerOverflow)?;
-    let table_offset = 32usize;
-    let table_end = table_offset
-        .checked_add(table_len)
-        .ok_or(Error::IntegerOverflow)?;
-    if table_end > bytes.len() {
-        return Err(Error::EntryTableOutOfBounds {
-            table_offset: u64::try_from(table_offset).map_err(|_| Error::IntegerOverflow)?,
-            table_len: u64::try_from(table_len).map_err(|_| Error::IntegerOverflow)?,
-            file_len: u64::try_from(bytes.len()).map_err(|_| Error::IntegerOverflow)?,
-        });
-    }
-
-    let table_enc = &bytes[table_offset..table_end];
-    let table_plain_original = xor_stream(table_enc, (xor_seed & 0xFFFF) as u16);
-    if table_plain_original.len() != table_len {
-        return Err(Error::EntryTableDecryptFailed);
-    }
-
-    let (overlay, trailer_raw) = parse_ao_trailer(&bytes, opts.allow_ao_trailer)?;
-    #[cfg(not(test))]
-    let _ = trailer_raw;
-
-    let mut entries = Vec::with_capacity(count);
-    for idx in 0..count {
-        let row = &table_plain_original[idx * 32..(idx + 1) * 32];
-
-        let mut name_raw = [0u8; 12];
-        name_raw.copy_from_slice(&row[0..12]);
-
-        let flags_signed = i16::from_le_bytes([row[16], row[17]]);
-        let sort_to_original = i16::from_le_bytes([row[18], row[19]]);
-        let unpacked_size = u32::from_le_bytes([row[20], row[21], row[22], row[23]]);
-        let data_offset_raw = u32::from_le_bytes([row[24], row[25], row[26], row[27]]);
-        let packed_size_declared = u32::from_le_bytes([row[28], row[29], row[30], row[31]]);
-
-        let method_raw = (flags_signed as u16 as u32) & 0x1E0;
-        let method = parse_method(method_raw);
-
-        let effective_offset_u64 = u64::from(data_offset_raw)
-            .checked_add(u64::from(overlay))
-            .ok_or(Error::IntegerOverflow)?;
-        let effective_offset =
-            usize::try_from(effective_offset_u64).map_err(|_| Error::IntegerOverflow)?;
-
-        let packed_size_usize =
-            usize::try_from(packed_size_declared).map_err(|_| Error::IntegerOverflow)?;
-        let mut packed_size_available = packed_size_usize;
-
-        let end = effective_offset_u64
-            .checked_add(u64::from(packed_size_declared))
-            .ok_or(Error::IntegerOverflow)?;
-        let file_len_u64 = u64::try_from(bytes.len()).map_err(|_| Error::IntegerOverflow)?;
-
-        if end > file_len_u64 {
-            if method_raw == 0x100 && end == file_len_u64 + 1 {
-                if opts.allow_deflate_eof_plus_one {
-                    packed_size_available = packed_size_available
-                        .checked_sub(1)
-                        .ok_or(Error::IntegerOverflow)?;
-                } else {
-                    return Err(Error::DeflateEofPlusOneQuirkRejected { id: idx as u32 });
-                }
-            } else {
-                return Err(Error::PackedSizePastEof {
-                    id: idx as u32,
-                    offset: effective_offset_u64,
-                    packed_size: packed_size_declared,
-                    file_len: file_len_u64,
-                });
-            }
-        }
-
-        let available_end = effective_offset
-            .checked_add(packed_size_available)
-            .ok_or(Error::IntegerOverflow)?;
-        if available_end > bytes.len() {
-            return Err(Error::EntryDataOutOfBounds {
-                id: idx as u32,
-                offset: effective_offset_u64,
-                size: packed_size_declared,
-                file_len: file_len_u64,
-            });
-        }
-
-        let name = decode_name(c_name_bytes(&name_raw));
-
-        entries.push(EntryRecord {
-            meta: EntryMeta {
-                name,
-                flags: i32::from(flags_signed),
-                method,
-                data_offset: effective_offset_u64,
-                packed_size: packed_size_declared,
-                unpacked_size,
-            },
-            name_raw,
-            sort_to_original,
-            key16: sort_to_original as u16,
-            #[cfg(test)]
-            data_offset_raw,
-            packed_size_declared,
-            packed_size_available,
-            effective_offset,
-        });
-    }
-
-    let presorted_flag = u16::from_le_bytes([bytes[14], bytes[15]]);
-    if presorted_flag == 0xABBA {
-        for entry in &entries {
-            let idx = i32::from(entry.sort_to_original);
-            if idx < 0 || usize::try_from(idx).map_err(|_| Error::IntegerOverflow)? >= count {
-                return Err(Error::CorruptEntryTable(
-                    "sort_to_original is not a valid permutation index",
-                ));
-            }
-        }
-    } else {
-        let mut sorted: Vec<usize> = (0..count).collect();
-        sorted.sort_by(|a, b| {
-            cmp_c_string(
-                c_name_bytes(&entries[*a].name_raw),
-                c_name_bytes(&entries[*b].name_raw),
-            )
-        });
-        for (idx, entry) in entries.iter_mut().enumerate() {
-            entry.sort_to_original =
-                i16::try_from(sorted[idx]).map_err(|_| Error::IntegerOverflow)?;
-            entry.key16 = entry.sort_to_original as u16;
-        }
-    }
-
-    #[cfg(test)]
-    let source_size = bytes.len();
-
-    Ok(Library {
-        bytes,
-        entries,
-        #[cfg(test)]
-        header_raw,
-        #[cfg(test)]
-        table_plain_original,
-        #[cfg(test)]
-        xor_seed,
-        #[cfg(test)]
-        source_size,
-        #[cfg(test)]
-        trailer_raw,
-    })
-}
-
-fn parse_ao_trailer(bytes: &[u8], allow: bool) -> Result<(u32, Option<[u8; 6]>)> {
-    if !allow || bytes.len() < 6 {
-        return Ok((0, None));
-    }
-
-    if &bytes[bytes.len() - 6..bytes.len() - 4] != b"AO" {
-        return Ok((0, None));
-    }
-
-    let mut trailer = [0u8; 6];
-    trailer.copy_from_slice(&bytes[bytes.len() - 6..]);
-    let overlay = u32::from_le_bytes([trailer[2], trailer[3], trailer[4], trailer[5]]);
-
-    if u64::from(overlay) > u64::try_from(bytes.len()).map_err(|_| Error::IntegerOverflow)? {
-        return Err(Error::MediaOverlayOutOfBounds {
-            overlay,
-            file_len: u64::try_from(bytes.len()).map_err(|_| Error::IntegerOverflow)?,
-        });
-    }
-
-    Ok((overlay, Some(trailer)))
-}
-
-fn parse_method(raw: u32) -> PackMethod {
-    match raw {
-        0x000 => PackMethod::None,
-        0x020 => PackMethod::XorOnly,
-        0x040 => PackMethod::Lzss,
-        0x060 => PackMethod::XorLzss,
-        0x080 => PackMethod::LzssHuffman,
-        0x0A0 => PackMethod::XorLzssHuffman,
-        0x100 => PackMethod::Deflate,
-        other => PackMethod::Unknown(other),
-    }
-}
-
 fn decode_payload(
     packed: &[u8],
     method: PackMethod,
@@ -563,15 +376,15 @@ fn decode_payload(
             }
             xor_stream(&packed[..expected], key16)
         }
-        PackMethod::Lzss => lzss_decompress_simple(packed, expected)?,
+        PackMethod::Lzss => lzss_decompress_simple(packed, expected, None)?,
         PackMethod::XorLzss => {
-            let decrypted = xor_stream(packed, key16);
+            // Optimized: XOR on-the-fly during decompression instead of creating temp buffer
-            lzss_decompress_simple(&decrypted, expected)?
+            lzss_decompress_simple(packed, expected, Some(key16))?
         }
-        PackMethod::LzssHuffman => lzss_huffman_decompress(packed, expected)?,
+        PackMethod::LzssHuffman => lzss_huffman_decompress(packed, expected, None)?,
         PackMethod::XorLzssHuffman => {
-            let decrypted = xor_stream(packed, key16);
+            // Optimized: XOR on-the-fly during decompression
-            lzss_huffman_decompress(&decrypted, expected)?
+            lzss_huffman_decompress(packed, expected, Some(key16))?
         }
         PackMethod::Deflate => decode_deflate(packed)?,
         PackMethod::Unknown(raw) => return Err(Error::UnsupportedMethod { raw }),
@@ -587,391 +400,6 @@ fn decode_payload(
     Ok(out)
 }
 
-fn decode_deflate(packed: &[u8]) -> Result<Vec<u8>> {
-    let mut out = Vec::new();
-    let mut decoder = DeflateDecoder::new(packed);
-    if decoder.read_to_end(&mut out).is_ok() {
-        return Ok(out);
-    }
-
-    out.clear();
-    let mut zlib = ZlibDecoder::new(packed);
-    zlib.read_to_end(&mut out)
-        .map_err(|_| Error::DecompressionFailed("deflate"))?;
-    Ok(out)
-}
-
-fn xor_stream(data: &[u8], key16: u16) -> Vec<u8> {
-    let mut lo = (key16 & 0xFF) as u8;
-    let mut hi = ((key16 >> 8) & 0xFF) as u8;
-
-    let mut out = Vec::with_capacity(data.len());
-    for value in data {
-        lo = hi ^ lo.wrapping_shl(1);
-        out.push(value ^ lo);
-        hi = lo ^ (hi >> 1);
-    }
-    out
-}
-
-fn lzss_decompress_simple(data: &[u8], expected_size: usize) -> Result<Vec<u8>> {
-    let mut ring = [0x20u8; 0x1000];
-    let mut ring_pos = 0xFEEusize;
-    let mut out = Vec::with_capacity(expected_size);
-    let mut in_pos = 0usize;
-
-    let mut control = 0u8;
-    let mut bits_left = 0u8;
-
-    while out.len() < expected_size {
-        if bits_left == 0 {
-            let Some(byte) = data.get(in_pos).copied() else {
-                break;
-            };
-            control = byte;
-            in_pos += 1;
-            bits_left = 8;
-        }
-
-        if (control & 1) != 0 {
-            let Some(byte) = data.get(in_pos).copied() else {
-                break;
-            };
-            in_pos += 1;
-
-            out.push(byte);
-            ring[ring_pos] = byte;
-            ring_pos = (ring_pos + 1) & 0x0FFF;
-        } else {
-            let (Some(low), Some(high)) =
-                (data.get(in_pos).copied(), data.get(in_pos + 1).copied())
-            else {
-                break;
-            };
-            in_pos += 2;
-
-            let offset = usize::from(low) | (usize::from(high & 0xF0) << 4);
-            let length = usize::from((high & 0x0F) + 3);
-
-            for step in 0..length {
-                let byte = ring[(offset + step) & 0x0FFF];
-                out.push(byte);
-                ring[ring_pos] = byte;
-                ring_pos = (ring_pos + 1) & 0x0FFF;
-                if out.len() >= expected_size {
-                    break;
-                }
-            }
-        }
-
-        control >>= 1;
-        bits_left -= 1;
-    }
-
-    if out.len() != expected_size {
-        return Err(Error::DecompressionFailed("lzss-simple"));
-    }
-
-    Ok(out)
-}
-
-const LZH_N: usize = 4096;
-const LZH_F: usize = 60;
-const LZH_THRESHOLD: usize = 2;
-const LZH_N_CHAR: usize = 256 - LZH_THRESHOLD + LZH_F;
-const LZH_T: usize = LZH_N_CHAR * 2 - 1;
-const LZH_R: usize = LZH_T - 1;
-const LZH_MAX_FREQ: u16 = 0x8000;
-
-fn lzss_huffman_decompress(data: &[u8], expected_size: usize) -> Result<Vec<u8>> {
-    let mut decoder = LzhDecoder::new(data);
-    decoder.decode(expected_size)
-}
-
-struct LzhDecoder<'a> {
-    bit_reader: BitReader<'a>,
-    text: [u8; LZH_N],
-    freq: [u16; LZH_T + 1],
-    parent: [usize; LZH_T + LZH_N_CHAR],
-    son: [usize; LZH_T],
-    d_code: [u8; 256],
-    d_len: [u8; 256],
-    ring_pos: usize,
-}
-
-impl<'a> LzhDecoder<'a> {
-    fn new(data: &'a [u8]) -> Self {
-        let mut decoder = Self {
-            bit_reader: BitReader::new(data),
-            text: [0x20u8; LZH_N],
-            freq: [0u16; LZH_T + 1],
-            parent: [0usize; LZH_T + LZH_N_CHAR],
-            son: [0usize; LZH_T],
-            d_code: [0u8; 256],
-            d_len: [0u8; 256],
-            ring_pos: LZH_N - LZH_F,
-        };
-        decoder.init_tables();
-        decoder.start_huff();
-        decoder
-    }
-
-    fn decode(&mut self, expected_size: usize) -> Result<Vec<u8>> {
-        let mut out = Vec::with_capacity(expected_size);
-
-        while out.len() < expected_size {
-            let c = self.decode_char();
-            if c < 256 {
-                let byte = c as u8;
-                out.push(byte);
-                self.text[self.ring_pos] = byte;
-                self.ring_pos = (self.ring_pos + 1) & (LZH_N - 1);
-            } else {
-                let mut offset = self.decode_position();
-                offset = (self.ring_pos.wrapping_sub(offset).wrapping_sub(1)) & (LZH_N - 1);
-                let mut length = c.saturating_sub(253);
-
-                while length > 0 && out.len() < expected_size {
-                    let byte = self.text[offset];
-                    out.push(byte);
-                    self.text[self.ring_pos] = byte;
-                    self.ring_pos = (self.ring_pos + 1) & (LZH_N - 1);
-                    offset = (offset + 1) & (LZH_N - 1);
-                    length -= 1;
-                }
-            }
-        }
-
-        if out.len() != expected_size {
-            return Err(Error::DecompressionFailed("lzss-huffman"));
-        }
-        Ok(out)
-    }
-
-    fn init_tables(&mut self) {
-        let d_code_group_counts = [1usize, 3, 8, 12, 24, 16];
-        let d_len_group_counts = [32usize, 48, 64, 48, 48, 16];
-
-        let mut group_index = 0u8;
-        let mut idx = 0usize;
-        let mut run = 32usize;
-        for count in d_code_group_counts {
-            for _ in 0..count {
-                for _ in 0..run {
-                    self.d_code[idx] = group_index;
-                    idx += 1;
-                }
-                group_index = group_index.wrapping_add(1);
-            }
-            run >>= 1;
-        }
-
-        let mut len = 3u8;
-        idx = 0;
-        for count in d_len_group_counts {
-            for _ in 0..count {
-                self.d_len[idx] = len;
-                idx += 1;
-            }
-            len = len.saturating_add(1);
-        }
-    }
-
-    fn start_huff(&mut self) {
-        for i in 0..LZH_N_CHAR {
-            self.freq[i] = 1;
-            self.son[i] = i + LZH_T;
-            self.parent[i + LZH_T] = i;
-        }
-
-        let mut i = 0usize;
-        let mut j = LZH_N_CHAR;
-        while j <= LZH_R {
-            self.freq[j] = self.freq[i].saturating_add(self.freq[i + 1]);
-            self.son[j] = i;
-            self.parent[i] = j;
-            self.parent[i + 1] = j;
-            i += 2;
-            j += 1;
-        }
-
-        self.freq[LZH_T] = u16::MAX;
-        self.parent[LZH_R] = 0;
-    }
-
-    fn decode_char(&mut self) -> usize {
-        let mut node = self.son[LZH_R];
-        while node < LZH_T {
-            let bit = usize::from(self.bit_reader.read_bit_or_zero());
-            node = self.son[node + bit];
-        }
-
-        let c = node - LZH_T;
-        self.update(c);
-        c
-    }
-
-    fn decode_position(&mut self) -> usize {
-        let i = self.bit_reader.read_bits_or_zero(8) as usize;
-        let mut c = usize::from(self.d_code[i]) << 6;
-        let mut j = usize::from(self.d_len[i]).saturating_sub(2);
-
-        while j > 0 {
-            j -= 1;
-            c |= usize::from(self.bit_reader.read_bit_or_zero()) << j;
-        }
-
-        c | (i & 0x3F)
-    }
-
-    fn update(&mut self, c: usize) {
-        if self.freq[LZH_R] == LZH_MAX_FREQ {
-            self.reconstruct();
-        }
-
-        let mut current = self.parent[c + LZH_T];
-        loop {
-            self.freq[current] = self.freq[current].saturating_add(1);
-            let freq = self.freq[current];
-
-            if current + 1 < self.freq.len() && freq > self.freq[current + 1] {
-                let mut swap_idx = current + 1;
-                while swap_idx + 1 < self.freq.len() && freq > self.freq[swap_idx + 1] {
-                    swap_idx += 1;
-                }
-
-                self.freq.swap(current, swap_idx);
-
-                let left = self.son[current];
-                let right = self.son[swap_idx];
-                self.son[current] = right;
-                self.son[swap_idx] = left;
-
-                self.parent[left] = swap_idx;
-                if left < LZH_T {
-                    self.parent[left + 1] = swap_idx;
-                }
-
-                self.parent[right] = current;
-                if right < LZH_T {
-                    self.parent[right + 1] = current;
-                }
-
-                current = swap_idx;
-            }
-
-            current = self.parent[current];
-            if current == 0 {
-                break;
-            }
-        }
-    }
-
-    fn reconstruct(&mut self) {
-        let mut j = 0usize;
-        for i in 0..LZH_T {
-            if self.son[i] >= LZH_T {
-                self.freq[j] = (self.freq[i].saturating_add(1)) / 2;
-                self.son[j] = self.son[i];
-                j += 1;
-            }
-        }
-
-        let mut i = 0usize;
-        let mut current = LZH_N_CHAR;
-        while current < LZH_T {
-            let sum = self.freq[i].saturating_add(self.freq[i + 1]);
-            self.freq[current] = sum;
-
-            let mut insert_at = current;
-            while insert_at > 0 && sum < self.freq[insert_at - 1] {
-                insert_at -= 1;
-            }
-
-            for move_idx in (insert_at..current).rev() {
-                self.freq[move_idx + 1] = self.freq[move_idx];
-                self.son[move_idx + 1] = self.son[move_idx];
-            }
-
-            self.freq[insert_at] = sum;
-            self.son[insert_at] = i;
-
-            i += 2;
-            current += 1;
-        }
-
-        for idx in 0..LZH_T {
-            let node = self.son[idx];
-            self.parent[node] = idx;
-            if node < LZH_T {
-                self.parent[node + 1] = idx;
-            }
-        }
-
-        self.freq[LZH_T] = u16::MAX;
-        self.parent[LZH_R] = 0;
-    }
-}
-
-struct BitReader<'a> {
-    data: &'a [u8],
-    byte_pos: usize,
-    bit_mask: u8,
-}
-
-impl<'a> BitReader<'a> {
-    fn new(data: &'a [u8]) -> Self {
-        Self {
-            data,
-            byte_pos: 0,
-            bit_mask: 0x80,
-        }
-    }
-
-    fn read_bit_or_zero(&mut self) -> u8 {
-        let Some(byte) = self.data.get(self.byte_pos).copied() else {
-            return 0;
-        };
-
-        let bit = if (byte & self.bit_mask) != 0 { 1 } else { 0 };
-        self.bit_mask >>= 1;
-        if self.bit_mask == 0 {
-            self.bit_mask = 0x80;
-            self.byte_pos = self.byte_pos.saturating_add(1);
-        }
-        bit
-    }
-
-    fn read_bits_or_zero(&mut self, bits: usize) -> u32 {
-        let mut value = 0u32;
-        for _ in 0..bits {
-            value = (value << 1) | u32::from(self.read_bit_or_zero());
-        }
-        value
-    }
-}
-
-fn decode_name(name: &[u8]) -> String {
-    name.iter().map(|b| char::from(*b)).collect()
-}
-
-fn c_name_bytes(raw: &[u8; 12]) -> &[u8] {
-    let len = raw.iter().position(|&b| b == 0).unwrap_or(raw.len());
-    &raw[..len]
-}
-
-fn cmp_c_string(a: &[u8], b: &[u8]) -> Ordering {
-    let min_len = a.len().min(b.len());
-    let mut idx = 0usize;
-    while idx < min_len {
-        if a[idx] != b[idx] {
-            return a[idx].cmp(&b[idx]);
-        }
-        idx += 1;
-    }
-    a.len().cmp(&b.len())
-}
-
 fn needs_xor_key(method: PackMethod) -> bool {
     matches!(
         method,

crates/rsli/src/parse.rs

@@ -0,0 +1,249 @@
+use crate::compress::xor::xor_stream;
+use crate::error::Error;
+use crate::{EntryMeta, EntryRecord, Library, OpenOptions, PackMethod, Result};
+use std::cmp::Ordering;
+use std::sync::Arc;
+
+pub fn parse_library(bytes: Arc<[u8]>, opts: OpenOptions) -> Result<Library> {
+    if bytes.len() < 32 {
+        return Err(Error::EntryTableOutOfBounds {
+            table_offset: 32,
+            table_len: 0,
+            file_len: u64::try_from(bytes.len()).map_err(|_| Error::IntegerOverflow)?,
+        });
+    }
+
+    let mut header_raw = [0u8; 32];
+    header_raw.copy_from_slice(&bytes[0..32]);
+
+    if &bytes[0..2] != b"NL" {
+        let mut got = [0u8; 2];
+        got.copy_from_slice(&bytes[0..2]);
+        return Err(Error::InvalidMagic { got });
+    }
+    if bytes[3] != 0x01 {
+        return Err(Error::UnsupportedVersion { got: bytes[3] });
+    }
+
+    let entry_count = i16::from_le_bytes([bytes[4], bytes[5]]);
+    if entry_count < 0 {
+        return Err(Error::InvalidEntryCount { got: entry_count });
+    }
+    let count = usize::try_from(entry_count).map_err(|_| Error::IntegerOverflow)?;
+
+    // Validate entry_count fits in u32 (required for EntryId)
+    if count > u32::MAX as usize {
+        return Err(Error::TooManyEntries { got: count });
+    }
+
+    let xor_seed = u32::from_le_bytes([bytes[20], bytes[21], bytes[22], bytes[23]]);
+
+    let table_len = count.checked_mul(32).ok_or(Error::IntegerOverflow)?;
+    let table_offset = 32usize;
+    let table_end = table_offset
+        .checked_add(table_len)
+        .ok_or(Error::IntegerOverflow)?;
+    if table_end > bytes.len() {
+        return Err(Error::EntryTableOutOfBounds {
+            table_offset: u64::try_from(table_offset).map_err(|_| Error::IntegerOverflow)?,
+            table_len: u64::try_from(table_len).map_err(|_| Error::IntegerOverflow)?,
+            file_len: u64::try_from(bytes.len()).map_err(|_| Error::IntegerOverflow)?,
+        });
+    }
+
+    let table_enc = &bytes[table_offset..table_end];
+    let table_plain_original = xor_stream(table_enc, (xor_seed & 0xFFFF) as u16);
+    if table_plain_original.len() != table_len {
+        return Err(Error::EntryTableDecryptFailed);
+    }
+
+    let (overlay, trailer_raw) = parse_ao_trailer(&bytes, opts.allow_ao_trailer)?;
+    #[cfg(not(test))]
+    let _ = trailer_raw;
+
+    let mut entries = Vec::with_capacity(count);
+    for idx in 0..count {
+        let row = &table_plain_original[idx * 32..(idx + 1) * 32];
+
+        let mut name_raw = [0u8; 12];
+        name_raw.copy_from_slice(&row[0..12]);
+
+        let flags_signed = i16::from_le_bytes([row[16], row[17]]);
+        let sort_to_original = i16::from_le_bytes([row[18], row[19]]);
+        let unpacked_size = u32::from_le_bytes([row[20], row[21], row[22], row[23]]);
+        let data_offset_raw = u32::from_le_bytes([row[24], row[25], row[26], row[27]]);
+        let packed_size_declared = u32::from_le_bytes([row[28], row[29], row[30], row[31]]);
+
+        let method_raw = (flags_signed as u16 as u32) & 0x1E0;
+        let method = parse_method(method_raw);
+
+        let effective_offset_u64 = u64::from(data_offset_raw)
+            .checked_add(u64::from(overlay))
+            .ok_or(Error::IntegerOverflow)?;
+        let effective_offset =
+            usize::try_from(effective_offset_u64).map_err(|_| Error::IntegerOverflow)?;
+
+        let packed_size_usize =
+            usize::try_from(packed_size_declared).map_err(|_| Error::IntegerOverflow)?;
+        let mut packed_size_available = packed_size_usize;
+
+        let end = effective_offset_u64
+            .checked_add(u64::from(packed_size_declared))
+            .ok_or(Error::IntegerOverflow)?;
+        let file_len_u64 = u64::try_from(bytes.len()).map_err(|_| Error::IntegerOverflow)?;
+
+        if end > file_len_u64 {
+            if method_raw == 0x100 && end == file_len_u64 + 1 {
+                if opts.allow_deflate_eof_plus_one {
+                    packed_size_available = packed_size_available
+                        .checked_sub(1)
+                        .ok_or(Error::IntegerOverflow)?;
+                } else {
+                    return Err(Error::DeflateEofPlusOneQuirkRejected {
+                        id: u32::try_from(idx).expect("entry count validated at parse"),
+                    });
+                }
+            } else {
+                return Err(Error::PackedSizePastEof {
+                    id: u32::try_from(idx).expect("entry count validated at parse"),
+                    offset: effective_offset_u64,
+                    packed_size: packed_size_declared,
+                    file_len: file_len_u64,
+                });
+            }
+        }
+
+        let available_end = effective_offset
+            .checked_add(packed_size_available)
+            .ok_or(Error::IntegerOverflow)?;
+        if available_end > bytes.len() {
+            return Err(Error::EntryDataOutOfBounds {
+                id: u32::try_from(idx).expect("entry count validated at parse"),
+                offset: effective_offset_u64,
+                size: packed_size_declared,
+                file_len: file_len_u64,
+            });
+        }
+
+        let name = decode_name(c_name_bytes(&name_raw));
+
+        entries.push(EntryRecord {
+            meta: EntryMeta {
+                name,
+                flags: i32::from(flags_signed),
+                method,
+                data_offset: effective_offset_u64,
+                packed_size: packed_size_declared,
+                unpacked_size,
+            },
+            name_raw,
+            sort_to_original,
+            key16: sort_to_original as u16,
+            #[cfg(test)]
+            data_offset_raw,
+            packed_size_declared,
+            packed_size_available,
+            effective_offset,
+        });
+    }
+
+    let presorted_flag = u16::from_le_bytes([bytes[14], bytes[15]]);
+    if presorted_flag == 0xABBA {
+        for entry in &entries {
+            let idx = i32::from(entry.sort_to_original);
+            if idx < 0 || usize::try_from(idx).map_err(|_| Error::IntegerOverflow)? >= count {
+                return Err(Error::CorruptEntryTable(
+                    "sort_to_original is not a valid permutation index",
+                ));
+            }
+        }
+    } else {
+        let mut sorted: Vec<usize> = (0..count).collect();
+        sorted.sort_by(|a, b| {
+            cmp_c_string(
+                c_name_bytes(&entries[*a].name_raw),
+                c_name_bytes(&entries[*b].name_raw),
+            )
+        });
+        for (idx, entry) in entries.iter_mut().enumerate() {
+            entry.sort_to_original =
+                i16::try_from(sorted[idx]).map_err(|_| Error::IntegerOverflow)?;
+            entry.key16 = entry.sort_to_original as u16;
+        }
+    }
+
+    #[cfg(test)]
+    let source_size = bytes.len();
+
+    Ok(Library {
+        bytes,
+        entries,
+        #[cfg(test)]
+        header_raw,
+        #[cfg(test)]
+        table_plain_original,
+        #[cfg(test)]
+        xor_seed,
+        #[cfg(test)]
+        source_size,
+        #[cfg(test)]
+        trailer_raw,
+    })
+}
+
+fn parse_ao_trailer(bytes: &[u8], allow: bool) -> Result<(u32, Option<[u8; 6]>)> {
+    if !allow || bytes.len() < 6 {
+        return Ok((0, None));
+    }
+
+    if &bytes[bytes.len() - 6..bytes.len() - 4] != b"AO" {
+        return Ok((0, None));
+    }
+
+    let mut trailer = [0u8; 6];
+    trailer.copy_from_slice(&bytes[bytes.len() - 6..]);
+    let overlay = u32::from_le_bytes([trailer[2], trailer[3], trailer[4], trailer[5]]);
+
+    if u64::from(overlay) > u64::try_from(bytes.len()).map_err(|_| Error::IntegerOverflow)? {
+        return Err(Error::MediaOverlayOutOfBounds {
+            overlay,
+            file_len: u64::try_from(bytes.len()).map_err(|_| Error::IntegerOverflow)?,
+        });
+    }
+
+    Ok((overlay, Some(trailer)))
+}
+
+pub fn parse_method(raw: u32) -> PackMethod {
+    match raw {
+        0x000 => PackMethod::None,
+        0x020 => PackMethod::XorOnly,
+        0x040 => PackMethod::Lzss,
+        0x060 => PackMethod::XorLzss,
+        0x080 => PackMethod::LzssHuffman,
+        0x0A0 => PackMethod::XorLzssHuffman,
+        0x100 => PackMethod::Deflate,
+        other => PackMethod::Unknown(other),
+    }
+}
+
+fn decode_name(name: &[u8]) -> String {
+    name.iter().map(|b| char::from(*b)).collect()
+}
+
+pub fn c_name_bytes(raw: &[u8; 12]) -> &[u8] {
+    let len = raw.iter().position(|&b| b == 0).unwrap_or(raw.len());
+    &raw[..len]
+}
+
+pub fn cmp_c_string(a: &[u8], b: &[u8]) -> Ordering {
+    let min_len = a.len().min(b.len());
+    let mut idx = 0usize;
+    while idx < min_len {
+        if a[idx] != b[idx] {
+            return a[idx].cmp(&b[idx]);
+        }
+        idx += 1;
+    }
+    a.len().cmp(&b.len())
+}

crates/rsli/src/tests.rs

@@ -1,4 +1,6 @@
 use super::*;
+use crate::compress::lzh::{LZH_MAX_FREQ, LZH_N_CHAR, LZH_R, LZH_T};
+use crate::compress::xor::xor_stream;
 use flate2::write::DeflateEncoder;
 use flate2::Compression;
 use std::any::Any;
@@ -665,6 +667,44 @@ fn rsli_synthetic_all_methods_roundtrip() {
     let _ = fs::remove_file(&path);
 }
 
+#[test]
+fn rsli_xorlzss_huffman_on_the_fly_roundtrip() {
+    let plain: Vec<u8> = (0..512u16).map(|i| b'A' + (i % 26) as u8).collect();
+    let entries = vec![SyntheticRsliEntry {
+        name: "XLZH_ONFLY".to_string(),
+        method_raw: 0x0A0,
+        plain: plain.clone(),
+        declared_packed_size: None,
+    }];
+
+    let bytes = build_rsli_bytes(
+        &entries,
+        &RsliBuildOptions {
+            seed: 0x0BAD_C0DE,
+            presorted: true,
+            overlay: 0,
+            add_ao_trailer: false,
+        },
+    );
+    let path = write_temp_file("rsli-xorlzh-onfly", &bytes);
+
+    let library = Library::open_path(&path).expect("open synthetic XLZH archive failed");
+    let id = library
+        .find("XLZH_ONFLY")
+        .expect("find XLZH_ONFLY entry failed");
+
+    let loaded = library.load(id).expect("load XLZH_ONFLY failed");
+    assert_eq!(loaded, plain);
+
+    let packed = library
+        .load_packed(id)
+        .expect("load_packed XLZH_ONFLY failed");
+    let unpacked = library.unpack(&packed).expect("unpack XLZH_ONFLY failed");
+    assert_eq!(unpacked, loaded);
+
+    let _ = fs::remove_file(&path);
+}
+
 #[test]
 fn rsli_synthetic_overlay_and_ao_trailer() {
     let entries = vec![SyntheticRsliEntry {