fix reading the correct prefix length

README.md

@@ -29,12 +29,19 @@ cargo build
 cargo run --bin count_sigma -- --file ./data/tudocomp/einstein.en.txt
 ```
 
+
 compute the 5th Fibonacci word
 ```
 cargo run --bin word -- -n fibonacci -k 5
 ```
 
-
 Datasets can be found at http://dolomit.cs.tu-dortmund.de/tudocomp/
 
 The output format of the analytic tools is compatible with [sqlplot](https://github.com/koeppl/sqlplot).
+
+## CAVEATS
+
+ - The BWT computation requires that the zero byte does not occur in your input. To enforce that, you can use the `escape` program to escape all zero bytes.
+For instance, `escape -f 0 -t 255 -e 254 | count_r` escapes 0 with the escape byte 254 to byte 255, and pipes the input to `count_r` counting the number of BWT runs.
+
+

src/bin/count_z.rs

@@ -199,7 +199,7 @@ fn main() {
     let result_format = format!(
         "RESULT file={} length={} ",
         core::get_filename(&args.infilename),
-        args.prefixlength
+        sa.len()
     );
 
     now = Instant::now();

src/bin/escape.rs

@@ -42,8 +42,8 @@ struct Args {
     #[arg(short, long)]
     to_symbols: Vec<u8>,
 
-    /// list byte codes that are safe and equal of length to from
-    #[arg(short, long)]
+    /// if true, invert the conversion
+    #[arg(long)]
     is_reversion: bool,
 }
 
@@ -73,9 +73,9 @@ fn main() {
     let mut writer = io::stream_or_stdout(core::stringopt_stropt(&args.outfilename));
 
     //@ sanity checks
-    assert_eq!(args.from_symbols.len(), args.to_symbols.len());
-    assert!(!args.from_symbols.contains(&args.escape_symbol));
-    assert!(!args.to_symbols.contains(&args.escape_symbol));
+    assert_eq!(args.from_symbols.len(), args.to_symbols.len(), "The set of --from and --to symbols must be of equal size!");
+    assert!(!args.from_symbols.contains(&args.escape_symbol), "The set of --from symbols must not contain the escape symbol!");
+    assert!(!args.to_symbols.contains(&args.escape_symbol), "The set of --to symbols must not contain the escape symbol!");
     assert!(!args
         .from_symbols
         .iter()

src/bin/is_stringattractor.rs

@@ -181,11 +181,11 @@ fn is_attractor(text: &[u8], attractor: &[u64]) -> bool {
     };
     let suffix_edges = lcp_intervals(text, &sa, &lcp);
 
-    use succinct::BitVector;
+    // use succinct::BitVector;
     use succinct::*;
     // use succinct::Select1Support;
-    use succinct::bit_vec::BitVecMut;
-    use succinct::BinSearchSelect;
+    // use succinct::bit_vec::BitVecMut;
+    // use succinct::BinSearchSelect;
 
     let attractor_positions = {
         let mut v = BitVector::with_fill(n as u64, false);
@@ -194,7 +194,7 @@ fn is_attractor(text: &[u8], attractor: &[u64]) -> bool {
         }
         v
     };
-    use succinct::Rank9;
+    // use succinct::Rank9;
     //TODO: remove clone() calls!
     let rank = Rank9::new(attractor_positions.clone());
     let select = BinSearchSelect::new(rank.clone()); //@ starts with index 0

src/core.rs

@@ -8,9 +8,10 @@ use more_asserts::assert_lt;
 use more_asserts::debug_assert_lt;
 
 pub fn bwt_from_text_by_sa(text: &Vec<u8>) -> Vec<u8> {
+    assert_gt!(!text.len(), 0);
     let n = text.len();
     let mut sa = vec![0; n];
-    assert!(!text[..text.len() - 1].iter().any(|&x| x == 0));
+    assert!(!text[..text.len() - 1].iter().any(|&x| x == 0), "the input text contains bytes equal to zero!");
     cdivsufsort::sort_in_place(text, sa.as_mut_slice());
     let mut bwt = vec![text[0]; n];
     // let mut rsa = vec![0; n];
@@ -236,6 +237,7 @@ pub fn bit_size(i: usize) -> u8 {
 
 pub fn compute_phi<T: AsPrimitive<usize> + num::cast::FromPrimitive>(sa: &[T]) -> Vec<T> {
     let mut phi = vec![T::from_usize(0).unwrap(); sa.len()];
+    assert_gt!(sa.len(), 0);
     for i in 1..sa.len() {
         phi[sa[i].as_()] = sa[i - 1];
     }

src/io.rs

@@ -13,13 +13,16 @@ pub fn file2byte_vector(filename: &str, prefix_length: usize) -> Vec<u8> {
         metadata.len()
     };
     assert!(buffer_length <= std::usize::MAX as u64);
-    let mut buffer = Vec::new();
-    buffer.reserve_exact(buffer_length as usize);
 
-    match f.read_to_end(&mut buffer) {
-        Ok(length) => assert_eq!(length, buffer.len()),
-        Err(x) => panic!("in file2byte_vector: {}", x),
-    };
+    let mut buffer = vec![0; buffer_length as usize];
+    f.read_exact(&mut buffer).unwrap();
+
+    // let mut buffer = Vec::new();
+    // buffer.reserve_exact(buffer_length as usize);
+    // match f.read_to_end(&mut buffer) {
+    //     Ok(length) => assert_eq!(length, buffer.len()),
+    //     Err(x) => panic!("in file2byte_vector: {}", x),
+    // };
     buffer
 }