small update

Don't throw away the right hand time of changes

Cargo.toml

@@ -1,13 +1,16 @@
 [package]
-name = "VCDViewer"
+name = "fastwave_backend"
 version = "0.1.0"
 edition = "2021"
 
+[profile.release]
+debug = 1
+
 # See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
 
 [dependencies]
 num = "0.4"
-clap = { version = "3.1.8", features = ["derive"] }
+clap = { version = "4.4.6", features = ["derive"] }
 chrono = "0.4"
-function_name = "0.3.0"
+# TODO : remove itertools once date parser is reworked.
-itertools = "0.10.3"
+itertools = "0.11"

LICENSE-YEHOWSHUA

@@ -0,0 +1,2 @@
+This codebase is also licensed to Yehowshua Immanuel to use
+in any manner Yehowshua Immanuel sees fit.

README.md

@@ -1,48 +1,131 @@
-Copyright - Yehowshua Immanuel
+Copyright(2023) - Yehowshua Immanuel
+
+# Vision
+Imagine being able to visualize a CPU pipeline diagram by merely loading a simulation waveform dump, sprinkling in a bit of code, and dragging and dropping some diagram blocks into the visualizer. This project aims to offer such an experience.
+
+Since this project is written in Rust, it should also be able to run in the browser via web-assembly.
+
+# Status
+As of January 2024, work on the Fastwave Backend is stalled. It has been a fun journey watching Fastwave enable the first iterations of the [surfer waveform viewer](https://surfer-project.org). Now surfer uses an even better backend called [Wellen](https://github.com/ekiwi/wellen?tab=readme-ov-file). Go check it out! I hear it's really good. Perhaps I will soon archive the Fastwave Backend.
+
+Browser demo: https://app.surfer-project.org/
+
+Screenshot of surfer frontend below:
+<img width="1609" alt="image" src="https://github.com/ThePerfectComputer/FastWaveBackend/assets/103011002/63deffc0-98b0-405f-b093-74d10b422b01">
 
 # A High performance, VCD Parser written in Rust
 
-## Current Features
+I hope for a GUI that eventually looks like the following...
- - pretty fast, parses 3.04 GB VCD file in ~67s on M1 Macbook Air with 
+
-   respect to 50s with GTKWave on the same device. FastWave currently
+![](assets/FastWaveMockup.png)
-   offers highly robust error handling which GTKWave doesn't have.
+
+# Current Features
+
+ - Robust Error Handling
+   
+   FastWave currently offers highly robust error handling(at least on the sample 
+   VCD files in this repository) which GTKWave doesn't have. For
+   example, selecting the ``UTILIZATON_ENABLED`` signal after opening 
+   [test2x2_regex22_string1.vcd](./test-vcd-files/xilinx_isim/test2x2_regex22_string1.vcd)
+   (one of the sample xilinx vcd test files) in GtkWave, will crash GtkWave since
+   this signal is malformed. FastWave on the otherhand simply notes that the
+   signal is malformed.
+
+# Performance
+
+## Methods
+I have been testing performance on a 3.04GB VCD file that can be found 
+[here](https://drive.google.com/file/d/1pfm2qo2l8fGTHHJ8TLrg1vSGaV_TUbp2/view?usp=sharing).
+
+For getting the GtkWave results, I fired up GtkWave, clicked on 
+``File``->``Open New Window``, and selected the VCD file linked to above.
+I started my stopwatch as soon as I pressed enter to beging loading the VCD
+file, and stopped my stopwatch once the GtkWave titlebar reached 100%.
+   
+To get the memory consumption, I opened Activity Monitor on Mac, and recorded
+the GtkWave memory usage before and after loading the large VCD file, and 
+took the difference.
+
+I noticed that when running FastWave in the VsCode terminal as opposed
+to the MacOS system terminal or the Lapce terminal, FastWave is notably
+slower.
+
+## Results
+
+LZ4 should really improve memory usage once I add it. Note that GTKWave uses LZ4 on the fly.
+
+| Software | Time(s) | Memory(MB) |
+|----------|---------|------------|
+| FastWave | ~27.30  | 1100+      |
+| GtkWave  | ~30     | 89.8       |
 
 
 # Current Limitations
 Unable to handle VCD files that have signals with more than 
 2^32 - 1 = 4,294,967,295 deltas/changes.
 
-## Running
+# Running
 
 This repository comes with several smaller VCD files emitted from
 various EDA tools. If you want a larger VCD file, grab one from
 [here](https://drive.google.com/file/d/1pfm2qo2l8fGTHHJ8TLrg1vSGaV_TUbp2/view?usp=sharing).
 
+Here are some examples you can run:
 The first build of the program may take some time.
 
-``cargo run --release test-vcd-files/aldec/SPI_Write.vcd``
+1. ``cargo run --release --example parse_vcd tests/vcd-files/aldec/SPI_Write.vcd``
+2. ``cargo run --release --example vcd``
 
 You can run all the tests with ``cargo test``
 
+# Testing on Bad Files
+You may wish to test the parser on a malformed VCD just to make
+sure that the parser gives useful/sane errors.
+
+Here's a command to test on a malformed VCD:
+``cargo run --release --example parse_vcd tests/vcd-files/VCD_file_with_errors.vcd``
+
+
 # TODO
 
-## Features
+## Features and Other
- - [ ] move parse_orphaned_vars to scopes.rs
+ - [ ] add documenting comments
+ - [ ] make signal query private until later?
+ - [ ] add signal query code to example once interface is finalized
+ - [ ] change crate name to vcd_fast_parse
+ - [ ] perhaps we should be looking up signal values on the VCD class
+ - [ ] perhaps we should be returning signal trees from the VCD class
+ - [ ] add lz4 compression support and compare memory perf before and after
+       - [ ] may need to refactor with allow for get_mut for dynamic
+             compression-decompression for multiple signal structs 
+             at once to allow for multi-threading
+ - [ ] test against large waveforms from the
+       [verilog-vcd-parser](https://github.com/ben-marshall/verilog-vcd-parser)
+       tool
+ - [ ] (a bit of work) consolidate error messages in validation phase
+ - [ ] once the access patterns of the GUI frontend are well understood,
+       create specific functions and restrict as many types to private
+       as possible
  - [ ] Print out git commit or release number.
- - [ ] Should be able to load waveform whilst viewing it live.
+ - [ ] do a read through all the code - look for uneeded code
-       - could be quite challenging to implement for various reasons
+ - [ ] Move part of the performance section to another markdown file.
- - [ ] Take a look at GTKWave parser to compare efficiency.
- - [ ] re-order all signal timelines as binary balanced trees with respect to timestamps
-       - support multithreaded re-ordering
 
 ## Repairs
+ - [ ] replace str bracket indices with get(slice)
  - [ ] make a custom date parser for possibly up to 18 different versions(that is, for each possible tool).
  - [ ] Consolidate error messages and add cursors throughout.
+ - [ ] Add file and line to the enum errors.
  - [ ] Fix warnings especially usage and restriction warnings once I'm
        able to successfully parse all sample VCDs.
 
 ## Code Consistency
- - [ ] Change error messages to line and filenames. Go through all calls to ``format!`` whilst also keeping performance in mind.
+ - [ ] Change error messages to line and filenames. Go through all calls to unwrap.
+   - [ ] search for any unwraps or any direct vectors indexing
+ - [ ] Handle TODOs
+ - [ ] Remove debug code/comments.
+
+## Documentation
+ - [ ] Document indexing structure with diagram and possibly include the rational
 
 ## Marketing
- - [ ] Send survey to community channel.
+ - [ ] Send survey to community 

examples/parse_vcd.rs

@@ -0,0 +1,33 @@
+// Copyright (C) 2022 Yehowshua Immanuel
+// This program is distributed under both the GPLV3 license
+// and the YEHOWSHUA license, both of which can be found at
+// the root of the folder containing the sources for this program.
+use clap::Parser;
+use std::fs::File;
+
+use fastwave_backend::parse_vcd;
+
+#[derive(Parser)]
+struct Cli {
+    /// The path to the file to read
+    path: std::path::PathBuf,
+}
+
+fn main() -> std::io::Result<()> {
+    let args = Cli::parse();
+
+    use std::time::Instant;
+
+    let now = Instant::now();
+    let file = File::open(&args.path)?;
+    parse_vcd(file).unwrap();
+    let elapsed = now.elapsed();
+
+    println!(
+        "Parsed VCD file {} : {:.2?}",
+        &args.path.as_os_str().to_str().unwrap(),
+        elapsed
+    );
+
+    Ok(())
+}

examples/vcd.rs

@@ -0,0 +1,81 @@
+// Copyright (C) 2022 Yehowshua Immanuel
+// This program is distributed under both the GPLV3 license
+// and the YEHOWSHUA license, both of which can be found at
+// the root of the folder containing the sources for this program.
+use std::fs::File;
+
+use fastwave_backend::{parse_vcd, ScopeIdx, SignalIdx, VCD};
+
+fn indented_print(indent: u8, name: &String) {
+    for _ in 0..indent {
+        print!("  |");
+    }
+    print!("---");
+    println!("{name}");
+}
+
+// TODO: refactor into more general visitor pattern that takes a
+// function as an argument.
+fn visit_all_scopes(vcd: &VCD) {
+    fn visit_all_scope_children(root_idx: ScopeIdx, vcd: &VCD, indent: u8) {
+        if vcd.child_scopes_by_idx(root_idx).is_empty() {
+        } else {
+            for child_scope_idx in vcd.child_scopes_by_idx(root_idx) {
+                indented_print(indent, vcd.scope_name_by_idx(child_scope_idx));
+                for signal_idx in vcd.get_children_signal_idxs(child_scope_idx) {
+                    let signal = vcd.signal_from_signal_idx(signal_idx);
+                    let SignalIdx(idx) = signal_idx;
+                    indented_print(indent + 1, &format!("{},{}", signal.name(), idx));
+                }
+                visit_all_scope_children(child_scope_idx, vcd, indent + 1);
+            }
+        }
+    }
+    for root_scope_idx in vcd.root_scopes_by_idx() {
+        indented_print(0, vcd.scope_name_by_idx(root_scope_idx));
+        visit_all_scope_children(root_scope_idx, vcd, 1u8);
+    }
+}
+
+fn main() -> std::io::Result<()> {
+    use std::time::Instant;
+
+    // we start by printing out the entire signal tree of
+    // a parsed VCD
+    let now = Instant::now();
+    let file_path = "tests/vcd-files/icarus/CPU.vcd";
+    let file = File::open(file_path)?;
+    let vcd = parse_vcd(file).unwrap();
+    let elapsed = now.elapsed();
+    println!("Parsed VCD file {} : {:.2?}", file_path, elapsed);
+
+    println!("Printing Scopes");
+    visit_all_scopes(&vcd);
+    println!("Done Printing Scopes");
+    println!();
+
+    // we then parse another VCD, print its signal tree and
+    // query some values on its timeline
+    let now = Instant::now();
+    let file_path = "tests/vcd-files/amaranth/up_counter.vcd";
+    let file = File::open(file_path)?;
+    let vcd = parse_vcd(file).unwrap();
+    let elapsed = now.elapsed();
+    println!("Parsed VCD file {} : {:.2?}", file_path, elapsed);
+
+    println!("Printing Scopes");
+    visit_all_scopes(&vcd);
+    println!("Done Printing Scopes");
+
+    let state_signal = vcd.signal_from_signal_idx(SignalIdx(4));
+    let name = state_signal.name();
+
+    let timestamps = vec![31499_000u32, 31500_000u32, 57760_000u32];
+    for timestamp in timestamps {
+        let time = num::BigUint::from(timestamp);
+        let val = state_signal.query_string_val_on_tmln(&time, &vcd).unwrap();
+        println!("Signal `{name}` has value `{val}` at time `{time}`");
+    }
+
+    Ok(())
+}

src/lib.rs

@@ -0,0 +1,12 @@
+// Copyright (C) 2022 Yehowshua Immanuel
+// This program is distributed under both the GPLV3 license
+// and the YEHOWSHUA license, both of which can be found at
+// the root of the folder containing the sources for this program.
+
+mod vcd;
+pub use vcd::parse::parse_vcd;
+pub use vcd::signal::{Signal, SignalType, SignalValue, SignalErrors};
+pub use vcd::types::{Metadata, Timescale, Version};
+pub use vcd::types::{ScopeIdx, SignalIdx, VCD};
+
+pub use num::BigUint;

src/main.rs

@@ -1,40 +0,0 @@
-use std::{fs::File};
-use clap::Parser;
-
-pub mod test;
-use test::*;
-
-pub mod vcd;
-use vcd::parse_vcd;
-
-use std::mem::size_of_val;
-
-#[derive(Parser)]
-struct Cli {
-    /// The path to the file to read
-    #[clap(parse(from_os_str))]
-    path: std::path::PathBuf}
-
-fn main() -> std::io::Result<()> {
-    let args = Cli::parse();
-
-    use std::time::Instant;
-    let now = Instant::now();
-
-    let file = File::open(&args.path)?;
-    let vcd = parse_vcd(file).unwrap(); 
-
-    let elapsed = now.elapsed();
-    println!("Elapsed: {:.2?}", elapsed);
-
-    vcd.print_longest_signal();
-    dbg!(size_of_val(&*vcd.timeline));
-    // unsafe {
-    //     let sz = size_of_val(&*vcd.timeline);
-    // }
-
-    // println!("printing signal tree");
-    // vcd.print_scopes();
-
-    Ok(())
-}

src/test.rs

@@ -1,2 +0,0 @@
-mod files;
-pub use files::*;

src/test/files.rs

@@ -1,71 +0,0 @@
-// TODO: we should eventually be able to only test on just
-// the files const
-pub const files : [&str; 30] = [
-    "./test-vcd-files/aldec/SPI_Write.vcd",
-    "./test-vcd-files/ghdl/alu.vcd",
-    "./test-vcd-files/ghdl/idea.vcd",
-    "./test-vcd-files/ghdl/pcpu.vcd",
-    "./test-vcd-files/gtkwave-analyzer/perm_current.vcd",
-    "./test-vcd-files/icarus/CPU.vcd",
-    "./test-vcd-files/icarus/rv32_soc_TB.vcd",
-    "./test-vcd-files/icarus/test1.vcd",
-    "./test-vcd-files/model-sim/CPU_Design.msim.vcd",
-    "./test-vcd-files/model-sim/clkdiv2n_tb.vcd",
-    "./test-vcd-files/my-hdl/Simple_Memory.vcd",
-    "./test-vcd-files/my-hdl/sigmoid_tb.vcd",
-    "./test-vcd-files/my-hdl/top.vcd",
-    "./test-vcd-files/ncsim/ffdiv_32bit_tb.vcd",
-    "./test-vcd-files/quartus/mipsHardware.vcd",
-    "./test-vcd-files/quartus/wave_registradores.vcd",
-    "./test-vcd-files/questa-sim/dump.vcd",
-    "./test-vcd-files/questa-sim/test.vcd",
-    "./test-vcd-files/riviera-pro/dump.vcd",
-    "./test-vcd-files/systemc/waveform.vcd",
-    "./test-vcd-files/treadle/GCD.vcd",
-    "./test-vcd-files/vcs/Apb_slave_uvm_new.vcd",
-    "./test-vcd-files/vcs/datapath_log.vcd",
-    "./test-vcd-files/vcs/processor.vcd",
-    "./test-vcd-files/verilator/swerv1.vcd",
-    "./test-vcd-files/verilator/vlt_dump.vcd",
-    "./test-vcd-files/vivado/iladata.vcd",
-    "./test-vcd-files/xilinx_isim/test.vcd",
-    "./test-vcd-files/xilinx_isim/test1.vcd",
-    // TODO : add signal ignore list to handle bitwidth mismatches
-    "./test-vcd-files/xilinx_isim/test2x2_regex22_string1.vcd"
-];
-
-pub const good_date_files : [&str; 24] = [
-    "./test-vcd-files/aldec/SPI_Write.vcd",
-    "./test-vcd-files/ghdl/alu.vcd",
-    "./test-vcd-files/ghdl/idea.vcd",
-    "./test-vcd-files/ghdl/pcpu.vcd",
-    "./test-vcd-files/gtkwave-analyzer/perm_current.vcd",
-    "./test-vcd-files/icarus/CPU.vcd",
-    "./test-vcd-files/icarus/rv32_soc_TB.vcd",
-    "./test-vcd-files/icarus/test1.vcd",
-    "./test-vcd-files/model-sim/CPU_Design.msim.vcd",
-    "./test-vcd-files/model-sim/clkdiv2n_tb.vcd",
-    "./test-vcd-files/my-hdl/Simple_Memory.vcd",
-    "./test-vcd-files/my-hdl/sigmoid_tb.vcd",
-    "./test-vcd-files/my-hdl/top.vcd",
-    "./test-vcd-files/questa-sim/dump.vcd",
-    "./test-vcd-files/questa-sim/test.vcd",
-    "./test-vcd-files/riviera-pro/dump.vcd",
-    "./test-vcd-files/vcs/Apb_slave_uvm_new.vcd",
-    "./test-vcd-files/vcs/datapath_log.vcd",
-    "./test-vcd-files/vcs/processor.vcd",
-    "./test-vcd-files/verilator/swerv1.vcd",
-    "./test-vcd-files/verilator/vlt_dump.vcd",
-    "./test-vcd-files/xilinx_isim/test.vcd",
-    "./test-vcd-files/xilinx_isim/test1.vcd",
-    "./test-vcd-files/xilinx_isim/test2x2_regex22_string1.vcd"
-];
-
-pub const bad_date_files : [&str; 6] = [
-    "./test-vcd-files/ncsim/ffdiv_32bit_tb.vcd",
-    "./test-vcd-files/quartus/mipsHardware.vcd",
-    "./test-vcd-files/quartus/wave_registradores.vcd",
-    "./test-vcd-files/systemc/waveform.vcd",
-    "./test-vcd-files/treadle/GCD.vcd",
-    "./test-vcd-files/vivado/iladata.vcd",
-];

src/vcd.rs

@@ -1,8 +1,10 @@
+// Copyright (C) 2022 Yehowshua Immanuel
+// This program is distributed under both the GPLV3 license
+// and the YEHOWSHUA license, both of which can be found at
+// the root of the folder containing the sources for this program.
+
+pub(crate) mod parse;
 mod reader;
-pub use reader::*;
+pub(crate) mod signal;
-
+pub(crate) mod types;
-mod types;
+mod utilities;
-pub use types::*;
-
-mod parse;
-pub use parse::*;

src/vcd/parse.rs

@@ -1,668 +1,35 @@
-use std::{fs::File};
+// Copyright (C) 2022 Yehowshua Immanuel
-use std::collections::HashMap;
+// This program is distributed under both the GPLV3 license
-use num::BigInt;
+// and the YEHOWSHUA license, both of which can be found at
-
+// the root of the folder containing the sources for this program.
-use super::*;
 
 mod combinator_atoms;
-use combinator_atoms::*;
+mod events;
-
-mod types;
-use types::*;
-
 mod metadata;
-use metadata::*;
-
 mod scopes;
-use scopes::*;
+mod types;
 
-use std::num::{IntErrorKind, ParseIntError};
+pub fn parse_vcd(file: impl std::io::Read) -> Result<super::types::VCD, String> {
+    let mut word_gen = super::reader::WordReader::new(file);
 
-use function_name::named;
+    let header = metadata::parse_metadata(&mut word_gen)?;
 
-#[derive(Debug)]
+    // later, we'll need to map parsed ascii symbols to their
-enum BinaryParserErrTypes {x_value, z_value, u_value, other_value(char), too_long}
-
-fn binary_str_to_vec_u8(binary_str : &str) -> Result<Vec<u8>, BinaryParserErrTypes> {
-    let mut vec_u8 : Vec<u8> = Vec::new();
-    let mut binary_str_as_bytes = binary_str.as_bytes();
-
-    let mut tail_idx = binary_str_as_bytes.len();
-    // clamp head if provided binary str is less than 8 long
-    let mut head_idx = 
-        if tail_idx >= 8 
-            {binary_str_as_bytes.len() - 8}
-        else 
-            {0};
-    while {tail_idx > 0} {
-        let curr_b_val = &binary_str_as_bytes[head_idx..tail_idx];
-        let val_u8 = base2_str_to_byte(curr_b_val)?;
-        vec_u8.push(val_u8);
-
-
-        if head_idx < 8 {
-            head_idx = 0
-        }
-        else {
-            head_idx = head_idx - 8;
-        }
-
-        if tail_idx < 8 {
-            tail_idx = 0
-        }
-        else {
-            tail_idx = tail_idx - 8;
-        }
-
-    }
-    Ok(vec_u8)
-}
-
-fn base2_str_to_byte(word : &[u8]) -> Result<u8, BinaryParserErrTypes> {
-    let mut val = 0u8;
-
-    // shouldn't have more than 8 chars in str
-    let len = word.len();
-    if len > 8 {
-        let (f, l )= (file!(), line!());
-        let err = format!(
-            "Error near {f}:{l}. Base2 string has length {len} > 8.");
-        return Err(BinaryParserErrTypes::too_long)
-    }
-
-    let bit_lut = [
-        0b0000_0001u8,
-        0b0000_0010u8,
-        0b0000_0100u8,
-        0b0000_1000u8,
-        0b0001_0000u8,
-        0b0010_0000u8,
-        0b0100_0000u8,
-        0b1000_0000u8
-    ];
-
-    for (idx, chr) in word.iter().rev().enumerate() {
-        match chr {
-            b'1' => {val = bit_lut[idx] | val}
-            b'0' => {}
-            b'x' | b'X' => {return Err(BinaryParserErrTypes::x_value)}
-            b'z' | b'Z' => {return Err(BinaryParserErrTypes::z_value)}
-            b'u' | b'U' => {return Err(BinaryParserErrTypes::u_value)}
-            _    => {return Err(BinaryParserErrTypes::other_value(*chr as char))}
-        }
-
-    }
-
-    Ok(val)
-}
-
-/// Sometimes, variables can be listed outside of scopes.
-/// We call these floating vars.
-pub(super) fn parse_orphaned_vars<'a>(
-    word_reader      : &mut WordReader,
-    vcd              : &'a mut VCD,
-    signal_map       : &mut HashMap<String, Signal_Idx>
-) -> Result<(), String> {
-    // create scope for unscoped signals if such a scope does not
-    // yet exist
-    let scope_name = "Orphaned Signals";
-
-    // set default scope_idx to the count of existing scope as we
-    // generally set scope.self_idx to the number of existing scopes
-    // when that particular scope was inserted
-    let mut scope_idx = Scope_Idx(vcd.all_scopes.len());
-
-    // Override scope_idx if we find a scope named "Orphaned Signals"
-    // already exists
-    let mut scope_already_exists = false;
-    for scope in &vcd.all_scopes {
-        if scope.name == scope_name {
-            scope_idx = scope.self_idx;
-            scope_already_exists = true;
-            break
-        }
-    }
-
-    if !scope_already_exists {
-        vcd.all_scopes.push(
-            Scope {
-                name: scope_name.to_string(),
-                parent_idx: None,
-                self_idx: scope_idx,
-                child_signals: vec![],
-                child_scopes: vec![]
-            }
-        );
-        vcd.scope_roots.push(scope_idx);
-    }
-    
-    // we can go ahead and parse the current var as we've already encountered
-    // "$var" before now.
-    parse_var(word_reader, scope_idx, vcd, signal_map)?;
-
-    loop {
-        let next_word = word_reader.next_word();
-
-        // we shouldn't reach the end of the file here...
-        if next_word.is_none() {
-            let (f, l )= (file!(), line!());
-            let msg = format!("Error near {f}:{l}.\
-                               Reached end of file without terminating parser");
-            Err(msg)?;
-        };
-
-        let (word, cursor) = next_word.unwrap();
-
-        match word {
-            "$var" => {
-                parse_var(word_reader, scope_idx, vcd, signal_map)?;
-            }
-            "$scope" => {break}
-            _ => {
-                let (f, l )= (file!(), line!());
-                let msg = format!("Error near {f}:{l}.\
-                Expected $scope or $var, found {word} at {cursor:?}");
-                Err(msg)?;
-            }
-        };
-    }
-
-    Ok(())
-}
-
-#[named]
-fn parse_events<'a>(
-    word_reader      : &mut WordReader,
-    vcd              : &'a mut VCD,
-    signal_map       : &mut HashMap<String, Signal_Idx>
-) -> Result<(), String> {
-
-    loop {
-        let next_word = word_reader.next_word();
-        // if we've reached the end of the file, then there is obviously
-        // nothing left to do...
-        if next_word.is_none() {break};
-
-        let (word, cursor) = next_word.unwrap();
-        let Cursor(Line(_), Word(word_in_line_idx)) = cursor;
-        // we only want to match on the first word in a line
-        if word_in_line_idx != 1 {continue}
-        match &word[0..1] {
-            "$" => {}
-            "#" => {
-                let value = &word[1..];
-                let (f, l )= (file!(), line!());
-                let value = BigInt::parse_bytes(value.as_bytes(), 10).ok_or(
-                    format!("Error near {f}:{l}. Failed to parse {value} as BigInt at {cursor:?}").as_str())?;
-                let (_, mut value) = value.to_bytes_le();
-                    // TODO : u32 helps with less memory, but should ideally likely be
-                    // configurable.
-                let (f, l )= (file!(), line!());
-                let start_idx = u32::try_from(vcd.timeline.len()).map_err(
-                    |e| format!("Error near {f}:{l}. Failed to convert from usize to u32."))?;
-                vcd.timeline_markers.push(StartIdx(start_idx));
-                vcd.timeline.append(&mut value);
-            }
-            // handle the case of an n bit signal whose value must be parsed
-            "b" => {
-                let binary_value = &word[1..];
-                let observed_num_bits = binary_value.len();
-                let (f, l )= (file!(), line!());
-
-                let mut value_u8 : Vec<u8> = Vec::new();
-                let mut value_string = String::new();
-                
-                let mut store_as_string = false;
-
-                // If we encounter x or z in a value, we can recover from
-                // the error and store the value as a string.
-                // Or else, we we propagate up other errors.
-                match binary_str_to_vec_u8(binary_value) {
-                    Ok(result) => {value_u8 = result;}
-                    Err(BinaryParserErrTypes::x_value | 
-                        BinaryParserErrTypes::z_value |
-                        BinaryParserErrTypes::u_value
-                    ) => 
-                        {
-                            store_as_string = true;
-                            value_string    = binary_value.to_string();
-                        }
-                    Err(e) => {
-                        let (f, l )= (file!(), line!());
-                        Err(e).map_err(
-                            |e| format!("Error near {f}:{l}. Error {e:?} at {cursor:?}."))?;
-                    }
-                }
-                
-                // this word should be the signal alias
-                let (word, cursor) = word_reader.next_word().unwrap();
-
-                // lookup signal idx
-                let (f, l )= (file!(), line!());
-                let Signal_Idx(ref signal_idx) = signal_map.get(word).ok_or(
-                    format!("Error near {f}:{l}. Failed to lookup signal {word} at {cursor:?}"))?;
-
-                // account for fact that signal idx could be an alias, so there
-                // could be one step of indirection
-                let signal_idx = 
-                {
-                    let signal = vcd.all_signals.get(*signal_idx).unwrap();
-                    match signal {
-                    Signal::Data {..} => {*signal_idx}
-                    Signal::Alias {name, signal_alias} => {
-                            let Signal_Idx(ref signal_idx) = signal_alias;
-                            signal_idx.clone()
-
-                        }
-                    }
-                };
-
-                // after handling potential indirection, go ahead and update the timeline
-                // of the signal signal_idx references
-                let signal = vcd.all_signals.get_mut(signal_idx).unwrap();
-                match signal {
-                    Signal::Data {name, sig_type, ref mut signal_error, num_bits, 
-                    self_idx, u8_timeline, u8_timeline_markers, string_timeline,
-                    string_timeline_markers, ..} => {
-
-                        if signal_error.is_some() {continue;}
-
-                        // Get the observed number of bits for the value parsed earlier
-                        // and verify that it is not greater than the numbits declared
-                        // when the signal was declared.
-                        // Also account for the error case of a bitwidth of `None`
-                        match num_bits {
-                            Some(ref num_bits) => {
-                                if *num_bits > observed_num_bits {
-                                    let (f, l) = (file!(), line!());
-                                    let msg = format!("\
-                                        Error near {f}:{l}. The bitwidth for signal {name} \
-                                        of sig_type {sig_type:?} is expected to be `1` not \
-                                        `{num_bits}`. \
-                                        This error occurred while parsing the vcd file at \
-                                        {cursor:?}");
-                                    *signal_error = Some(msg);
-                                    continue;
-                                }
-                            }
-                            None => {
-                                let (f, l) = (file!(), line!());
-                                let msg = format!("\
-                                    Error near {f}:{l}. The bitwidth for signal {name} \
-                                    must be specified for a signal of type {sig_type:?}. \
-                                    This error occurred while parsing the vcd file at \
-                                    {cursor:?}");
-                                Err(msg)?;
-                            }
-                        };
-
-                        let (f, l )= (file!(), line!());
-                        let timeline_idx = u32::try_from(vcd.timeline.len()).map_err(
-                            |e| format!("Error near {f}:{l}. Failed to convert from usize to u32."))?;
-                        let timeline_idx = TimelineIdx(timeline_idx);
-
-                        if store_as_string {
-                            string_timeline_markers.push(timeline_idx);
-                            string_timeline.push(value_string);
-                            Ok(())
-
-                        }
-                        else {
-                            u8_timeline_markers.push(timeline_idx);
-                            u8_timeline.append(&mut value_u8);
-                            Ok(())
-                        }
-                    }
-                    Signal::Alias {..} => {
-                        let (f, l )= (file!(), line!());
-                        let msg = format!(
-                            "Error near {f}:{l}, a signal alias should not point to a signal alias.\n\
-                                This error occurred while parsing vcd file at {cursor:?}");
-                        Err(msg)
-                    }
-                }?;
-            }
-
-            // handle the case of a one bit signal whose value is set to `0`
-            "0" => {
-                // lookup signal idx
-                let hash = &word[1..];
-                let (f, l )= (file!(), line!());
-                let Signal_Idx(ref signal_idx) = signal_map.get(hash).ok_or(
-                    format!("Error near {f}:{l}. Failed to lookup signal {hash} at {cursor:?}"))?;
-
-                // account for fact that signal idx could be an alias, so there
-                // could be one step of indirection
-                let signal_idx = 
-                {
-                    let signal = vcd.all_signals.get(*signal_idx).unwrap();
-                    match signal {
-                    Signal::Data {..} => {*signal_idx}
-                    Signal::Alias {name, signal_alias} => {
-                            let Signal_Idx(ref signal_idx) = signal_alias;
-                            signal_idx.clone()
-
-                        }
-                    }
-                };
-
-                // after handling potential indirection, go ahead and update the timeline
-                // of the signal signal_idx references
-                let signal = vcd.all_signals.get_mut(signal_idx).unwrap();
-                match signal {
-                    Signal::Data {name, sig_type, ref mut signal_error, num_bits, 
-                    self_idx, u8_timeline, u8_timeline_markers, ..} => {
-
-                        // if this is a bad signal, go ahead and skip it
-                        if signal_error.is_some() {continue;}
-
-                        // Get bitwidth and verify that it is 1.
-                        // Also account for the error case of a bitwidth of `None`
-                        match num_bits {
-                            Some(ref num_bits) => {
-                                if *num_bits != 1 {
-                                    let (f, l) = (file!(), line!());
-                                    let msg = format!("\
-                                        Error near {f}:{l}. The bitwidth for signal {name} \
-                                        of sig_type {sig_type:?} is expected to be `1` not \
-                                        `{num_bits}`. \
-                                        This error occurred while parsing the vcd file at \
-                                        {cursor:?}");
-                                    *signal_error = Some(msg);
-                                    continue;
-                                }
-                            }
-                            None => {
-                                let (f, l) = (file!(), line!());
-                                let msg = format!("\
-                                    Error near {f}:{l}. The bitwidth for signal {name} \
-                                    must be specified for a signal of type {sig_type:?}. \
-                                    This error occurred while parsing the vcd file at \
-                                    {cursor:?}");
-                                Err(msg)?;
-                            }
-                        };
-
-                        let (f, l )= (file!(), line!());
-                        let timeline_idx = u32::try_from(vcd.timeline.len()).map_err(
-                            |e| format!("Error near {f}:{l}. Failed to convert from usize to u32."))?;
-                        let timeline_idx = TimelineIdx(timeline_idx);
-
-                        u8_timeline_markers.push(timeline_idx);
-                        u8_timeline.push(0u8);
-                        Ok(())
-                    }
-                    Signal::Alias {..} => {
-                        let (f, l )= (file!(), line!());
-                        let msg = format!(
-                            "Error near {f}:{l}, a signal alias should not point to a signal alias.\n\
-                             This error occurred while parsing vcd file at {cursor:?}");
-                        Err(msg)
-                    }
-                }?;
-            }
-
-            // other one bit cases
-            "x" | "X" | "z" | "Z" | "u" | "U" => {
-                let val = word.to_string();
-                // lokup signal idx
-                let hash = &word[1..];
-                let (f, l )= (file!(), line!());
-                let Signal_Idx(ref signal_idx) = signal_map.get(hash).ok_or(
-                    format!("Error near {f}:{l}. Failed to lookup signal {hash} at {cursor:?}"))?;
-
-                // account for fact that signal idx could be an alias, so there
-                // could be one step of indirection
-                let signal_idx = 
-                {
-                    let signal = vcd.all_signals.get(*signal_idx).unwrap();
-                    match signal {
-                    Signal::Data {..} => {*signal_idx}
-                    Signal::Alias {name, signal_alias} => {
-                            let Signal_Idx(ref signal_idx) = signal_alias;
-                            signal_idx.clone()
-
-                        }
-                    }
-                };
-
-                // after handling potential indirection, go ahead and update the timeline
-                // of the signal signal_idx references
-                let signal = vcd.all_signals.get_mut(signal_idx).unwrap();
-                match signal {
-                    Signal::Data {name, sig_type, ref mut signal_error, num_bits, 
-                    self_idx, u8_timeline, u8_timeline_markers, string_timeline,
-                    string_timeline_markers, ..} => {
-
-                        // if this is a bad signal, go ahead and skip it
-                        if signal_error.is_some() {continue;}
-
-                        // Get bitwidth and verify that it is 1.
-                        // Also account for the error case of a bitwidth of `None`
-                        match num_bits {
-                            Some(ref num_bits) => {
-                                if *num_bits != 1 {
-                                    let (f, l) = (file!(), line!());
-                                    let msg = format!("\
-                                        Error near {f}:{l}. The bitwidth for signal {name} \
-                                        of sig_type {sig_type:?} is expected to be `1` not \
-                                        `{num_bits}`. \
-                                        This error occurred while parsing the vcd file at \
-                                        {cursor:?}");
-                                    *signal_error = Some(msg);
-                                    continue;
-                                }
-                            }
-                            None => {
-                                let (f, l) = (file!(), line!());
-                                let msg = format!("\
-                                    Error near {f}:{l}. The bitwidth for signal {name} \
-                                    must be specified for a signal of type {sig_type:?}. \
-                                    This error occurred while parsing the vcd file at \
-                                    {cursor:?}");
-                                Err(msg)?;
-                            }
-                        };
-
-                        let (f, l )= (file!(), line!());
-                        let timeline_idx = u32::try_from(vcd.timeline.len()).map_err(
-                            |e| format!("Error near {f}:{l}. Failed to convert from usize to u32."))?;
-                        let timeline_idx = TimelineIdx(timeline_idx);
-
-                        string_timeline_markers.push(timeline_idx);
-                        string_timeline.push(val);
-                        Ok(())
-                    }
-                    Signal::Alias {..} => {
-                        let (f, l )= (file!(), line!());
-                        let msg = format!(
-                            "Error near {f}:{l}, a signal alias should not point to a signal alias.\n\
-                             This error occurred while parsing vcd file at {cursor:?}");
-                        Err(msg)
-                    }
-                }?;
-            }
-            "1" => {
-                // lokup signal idx
-                let hash = &word[1..];
-                let (f, l )= (file!(), line!());
-                let Signal_Idx(ref signal_idx) = signal_map.get(hash).ok_or(
-                    format!("Error near {f}:{l}. Failed to lookup signal {hash} at {cursor:?}"))?;
-
-                // account for fact that signal idx could be an alias, so there
-                // could be one step of indirection
-                let signal_idx = 
-                {
-                    let signal = vcd.all_signals.get(*signal_idx).unwrap();
-                    match signal {
-                    Signal::Data {..} => {*signal_idx}
-                    Signal::Alias {name, signal_alias} => {
-                            let Signal_Idx(ref signal_idx) = signal_alias;
-                            signal_idx.clone()
-
-                        }
-                    }
-                };
-
-                // after handling potential indirection, go ahead and update the timeline
-                // of the signal signal_idx references
-                let signal = vcd.all_signals.get_mut(signal_idx).unwrap();
-                match signal {
-                    Signal::Data {name, sig_type, ref mut signal_error, num_bits, 
-                    self_idx, u8_timeline, u8_timeline_markers, scope_parent, ..} => {
-
-                        // if this is a bad signal, go ahead and skip it
-                        if signal_error.is_some() {continue;}
-
-                        // Get bitwidth and verify that it is 1.
-                        // Also account for the error case of a bitwidth of `None`
-                        match num_bits {
-                            Some(ref num_bits) => {
-                                if *num_bits != 1 {
-                                    let (f, l) = (file!(), line!());
-                                    let msg = format!("\
-                                        Error near {f}:{l}. The bitwidth for signal {name} \
-                                        of sig_type {sig_type:?} is expected to be `1` not \
-                                        `{num_bits}`. \
-                                        This error occurred while parsing the vcd file at \
-                                        {cursor:?}");
-                                    *signal_error = Some(msg);
-                                    continue;
-                                }
-                            }
-                            None => {
-                                let (f, l) = (file!(), line!());
-                                let msg = format!("\
-                                    Error near {f}:{l}. The bitwidth for signal {name} \
-                                    must be specified for a signal of type {sig_type:?}. \
-                                    This error occurred while parsing the vcd file at \
-                                    {cursor:?}");
-                                Err(msg)?;
-                            }
-                        };
-
-                        let (f, l )= (file!(), line!());
-                        let timeline_idx = u32::try_from(vcd.timeline.len()).map_err(
-                            |e| format!("Error near {f}:{l}. Failed to convert from usize to u32."))?;
-                        let timeline_idx = TimelineIdx(timeline_idx);
-
-                        u8_timeline_markers.push(timeline_idx);
-                        u8_timeline.push(1u8);
-                        Ok(())
-                    }
-                    Signal::Alias {..} => {
-                        let (f, l )= (file!(), line!());
-                        let msg = format!(
-                            "Error near {f}:{l}, a signal alias should not point to a signal alias.\n\
-                             This error occurred while parsing vcd file at {cursor:?}");
-                        Err(msg)
-                    }
-                }?;
-            }
-
-            _ => {}
-        }
-    }
-
-    Ok(())
-}
-
-pub fn parse_vcd(file : File) -> Result<VCD, String> {
-    let mut word_gen = WordReader::new(file);
-
-    let header = parse_metadata(&mut word_gen)?;
-
-    // later, we'll need to map parsed ascii symbols to their 
     // respective signal indexes
     let mut signal_map = std::collections::HashMap::new();
 
-    // after we parse metadata, we form VCD object
+    // after we parse metadata, we form the VCD object
-    let mut vcd = VCD{
+    let mut vcd = super::types::VCD {
-        metadata           : header,
+        metadata: header,
-        timeline           : vec![],
+        tmstmps_encoded_as_u8s: vec![],
-        timeline_markers   : vec![],
+        all_signals: vec![],
-        all_signals        : vec![],
+        all_scopes: vec![],
-        all_scopes         : vec![],
+        root_scopes: vec![],
-        scope_roots        : vec![],
+        largest_timestamp: None,
     };
 
-    // The last word parse_metadata saw determines how we proceed.
+    scopes::parse_scopes(&mut word_gen, &mut vcd, &mut signal_map)?;
-    // There may be some orphan vars we must parse first before 
+    events::parse_events(&mut word_gen, &mut vcd, &mut signal_map)?;
-    // parsing scoped vars.
-    let (f, l ) = (file!(), line!());
-    let msg = format!("Error near {f}:{l}. Current word empty!");
-    let (word, cursor) = word_gen.curr_word().ok_or(msg)?;
-    match word {
-        "$scope" => {
-            parse_scopes(&mut word_gen, None, &mut vcd, &mut signal_map)
-        }
-        "$var" => {
-            parse_orphaned_vars(&mut word_gen, &mut vcd, &mut signal_map)?;
-            parse_scopes(&mut word_gen, None, &mut vcd, &mut signal_map)
-        }
-        _ => {
-            let (f, l )= (file!(), line!());
-            let msg = format!("Error near {f}:{l}.\
-                               Expected $scope or $var, found {word} at {cursor:?}");
-            Err(msg)
-        }
-
-    }?;
-    parse_events(&mut word_gen, &mut vcd, &mut signal_map)?;
 
     Ok(vcd)
 }
-
-#[cfg(test)]
-mod tests {
-    use super::*;
-    use crate::test;
-    use std::fs::File;
-    #[test]
-    fn headers() {
-        // TODO: eventually, once all dates pass, merge the following
-        // two loops
-        // testing dates
-        for file in test::good_date_files {
-            let metadata = parse_metadata(
-                &mut WordReader::new(
-                    File::open(file)
-                    .unwrap()
-                )
-            );
-            assert!(metadata.is_ok());
-            assert!(metadata.unwrap().date.is_some());
-        }
-
-        for file in test::files {
-            let metadata = parse_metadata(
-                &mut WordReader::new(
-                    File::open(file)
-                    .unwrap()
-                )
-            );
-            assert!(metadata.is_ok());
-
-            let (scalar, timescale) = metadata.unwrap().timescale;
-            assert!(scalar.is_some());
-        }
-
-    }
-
-    #[test]
-    fn scopes() {
-        // see if we can parse all signal trees successfully
-        for file_name in test::files {
-            let file = File::open(file_name).unwrap();
-            let vcd = parse_vcd(file);
-
-            if !vcd.is_ok() {
-                dbg!(file_name);
-                vcd.unwrap();
-            }
-
-            // assert!(vcd.is_ok());
-        }
-
-    }
-}

src/vcd/parse/combinator_atoms.rs

@@ -1,104 +1,83 @@
+// Copyright (C) 2022 Yehowshua Immanuel
+// This program is distributed under both the GPLV3 license
+// and the YEHOWSHUA license, both of which can be found at
+// the root of the folder containing the sources for this program.
+use super::super::reader::{next_word, WordReader};
 use super::types::ParseResult;
-use super::reader::WordReader;
 
-pub(super) fn digit(chr : u8) -> bool {
+pub(super) fn digit(chr: u8) -> bool {
-    let zero = b'0' as u8;
+    let zero = b'0';
-    let nine = b'9' as u8;
+    let nine = b'9';
 
-    let between_zero_and_nine = (chr >= zero) && (nine >= chr);
+    (chr >= zero) && (nine >= chr)
-
-    return between_zero_and_nine
 }
 
-pub(super) fn take_until<'a>(word : &'a str, pattern : u8) -> ParseResult<'a> {
+pub(super) fn take_until(word: &str, pattern: u8) -> ParseResult<'_> {
-    let mut new_start  = 0;
+    let mut new_start = 0;
 
     for chr in word.as_bytes() {
-        if (*chr == pattern) {
+        if *chr == pattern {
-            break
+            break;
-        } 
+        } else {
-        else {
             new_start += 1;
         }
     }
 
-    return 
+    ParseResult {
-        ParseResult{
+        matched: &word[0..new_start],
-            matched  : &word[0..new_start],
+        residual: &word[new_start..],
-            residual : &word[new_start..]
-        };
-
-}
-
-// TODO: if I end up using simulator specific date parsers, ``take_until`` may
-// suffice rendering this function obselete, at which point I should delete it.
-pub(super) fn truncate_last_chr_when<'a>(word : &'a str, cond : fn(u8) -> bool) -> &'a str {
-    let last_chr = word.as_bytes().last().unwrap();
-    let mut new_end_index = word.len();
-
-    if cond(*last_chr) {
-        new_end_index -= 1;
     }
-    
-    return &word[0..new_end_index]
-
 }
 
-pub(super) fn take_while<'a>(word : &'a str, cond : fn(u8) -> bool) -> ParseResult<'a> {
+pub(super) fn take_while(word: &str, cond: fn(u8) -> bool) -> ParseResult<'_> {
-    let mut new_start  = 0;
+    let mut new_start = 0;
 
     for chr in word.as_bytes() {
-        if (cond(*chr)) {
+        if cond(*chr) {
             new_start += 1;
-        } 
+        } else {
-        else {
+            break;
-            break
         }
     }
 
-    return 
+    ParseResult {
-        ParseResult{
+        matched: &word[0..new_start],
-            matched  : &word[0..new_start],
+        residual: &word[new_start..],
-            residual : &word[new_start..]
+    }
-        };
-
 }
 
-pub(super) fn tag<'a>(word : &'a str, pattern : &'a str) -> ParseResult<'a> {
+pub(super) fn tag<'a>(word: &'a str, pattern: &'a str) -> ParseResult<'a> {
-    let lhs           = word.as_bytes().iter();
+    let lhs = word.as_bytes().iter();
-    let rhs           = pattern.as_bytes();
+    let rhs = pattern.as_bytes();
-    let iter          = lhs.zip(rhs);
+    let iter = lhs.zip(rhs);
     let mut new_start = 0;
 
     let mut res = true;
     for (c_lhs, c_rhs) in iter {
         res = res && (c_lhs == c_rhs);
-        if !res {break}
+        if !res {
+            break;
+        }
         new_start += 1;
     }
 
-    return 
+    ParseResult {
-        ParseResult{
+        matched: &word[0..new_start],
-            matched  : &word[0..new_start],
+        residual: &word[new_start..],
-            residual : &word[new_start..]
+    }
-        };
 }
 
-pub(super) fn ident(
+pub(super) fn ident<R: std::io::Read>(
-    word_reader : &mut WordReader,
+    word_reader: &mut WordReader<R>,
-    keyword : &str, 
+    keyword: &str,
 ) -> Result<(), String> {
     // let keyword = "module";
-
+    let (word, cursor) = next_word!(word_reader)?;
-    let err : Result<(), String> = Err(format!("reached end of file without parser leaving ident"));
-    let word = word_reader.next_word();
-    let (word, cursor) = word.ok_or(err).unwrap();
 
     if word == keyword {
-        return Ok(())
+        Ok(())
-    }
+    } else {
-    else {
         let err = format!("found keyword `{word}` but expected `{keyword}` on {cursor:?}");
-        return Err(err)
+        Err(err)
     }
-}
+}

src/vcd/parse/events.rs

@@ -0,0 +1,546 @@
+// Copyright (C) 2022 Yehowshua Immanuel
+// This program is distributed under both the GPLV3 license
+// and the YEHOWSHUA license, both of which can be found at
+// the root of the folder containing the sources for this program.
+
+use num::BigUint;
+use std::collections::HashMap;
+
+use super::super::reader::{next_word, Cursor, Line, Word, WordReader};
+use super::super::signal::{LsbIdxOfTmstmpValOnTmln, SignalEnum};
+use super::super::types::{SignalIdx, VCD};
+use super::super::utilities::{binary_str_to_vec_u8, BinaryParserErrTypes};
+
+pub(super) fn parse_events<R: std::io::Read>(
+    word_reader: &mut WordReader<R>,
+    vcd: &mut VCD,
+    signal_map: &mut HashMap<String, SignalIdx>,
+) -> Result<(), String> {
+    let mut curr_tmstmp_lsb_idx = 0u32;
+    let mut curr_tmstmp_len_u8 = 0u8;
+    loop {
+        let next_word = word_reader.next_word();
+
+        // The following is the only case where eof is not an error.
+        // If we've reached the end of the file, then there is obviously
+        // nothing left to do...
+        if next_word.is_none() {
+            break;
+        };
+
+        let (word, cursor) = next_word.unwrap();
+        let Cursor(Line(_), Word(word_in_line_idx)) = cursor;
+        // we only want to match on the first word in a line
+        if word_in_line_idx != 1 {
+            continue;
+        }
+        match &word[0..1] {
+            "$" => {}
+            "#" => {
+                let value = &word[1..];
+                let (f, l) = (file!(), line!());
+                let value_biguint = BigUint::parse_bytes(value.as_bytes(), 10)
+                    .ok_or(())
+                    .map_err(|_| {
+                        format!(
+                            "Error near {f}:{l}. Failed to parse {value} as BigInt at {cursor:?}"
+                        )
+                    })?;
+                let mut value = value_biguint.to_bytes_le();
+                // TODO : u32 helps with less memory, but should ideally likely be
+                // configurable.
+                curr_tmstmp_len_u8 = u8::try_from(value.len()).map_err(|_| {
+                    format!(
+                        "Error near {}:{}. Failed to convert from usize to u8.",
+                        file!(),
+                        line!()
+                    )
+                })?;
+                curr_tmstmp_lsb_idx =
+                    u32::try_from(vcd.tmstmps_encoded_as_u8s.len()).map_err(|_| {
+                        format!(
+                            "Error near {}:{}. Failed to convert from usize to u32.",
+                            file!(),
+                            line!()
+                        )
+                    })?;
+                vcd.tmstmps_encoded_as_u8s.append(&mut value);
+                vcd.largest_timestamp = Some(value_biguint);
+            }
+
+            // handle the case of an n bit signal whose value must be parsed
+            "b" => {
+                let binary_value = &word[1..];
+                let observed_num_bits = u32::try_from(binary_value.len()).map_err(|_| {
+                    format!(
+                        "Error near {}:{}, {cursor:?}. \
+                        Found signal with more than 2^32 - 1 bits.",
+                        file!(),
+                        line!()
+                    )
+                })?;
+
+                let mut value_u8: Vec<u8> = Vec::new();
+                let mut value_string = String::new();
+
+                let mut store_as_string = false;
+
+                // If we encounter other values than 0 or 1, we can recover from
+                // the error and store the value as a string.
+                // Or else, we propagate up other errors.
+                match binary_str_to_vec_u8(binary_value) {
+                    Ok(result) => {
+                        value_u8 = result;
+                    }
+                    Err(
+                        BinaryParserErrTypes::XValue
+                        | BinaryParserErrTypes::ZValue
+                        | BinaryParserErrTypes::UValue
+                        | BinaryParserErrTypes::WValue
+                        | BinaryParserErrTypes::HValue
+                        | BinaryParserErrTypes::DashValue
+                        | BinaryParserErrTypes::LValue,
+                    ) => {
+                        store_as_string = true;
+                        // Turn to lower case for consistency
+                        value_string = binary_value.to_ascii_lowercase();
+                    }
+                    Err(e) => {
+                        let (f, l) = (file!(), line!());
+                        Err(e).map_err(|e| {
+                            format!("Error near {f}:{l}. Error {e:?} at {cursor:?}.")
+                        })?;
+                    }
+                }
+
+                // this word should be the signal alias
+                let (word, cursor) = next_word!(word_reader)?;
+
+                // lookup signal idx
+                let signal_idx = signal_map.get(word).ok_or(()).map_err(|_| {
+                    format!(
+                        "Error near {}:{}. Failed to lookup signal {word} at {cursor:?}",
+                        file!(),
+                        line!()
+                    )
+                })?;
+
+                let signal = vcd.dealiasing_signal_idx_to_signal_lookup_mut(signal_idx)?;
+
+                match signal {
+                    SignalEnum::Data {
+                        name,
+                        signal_type,
+                        ref mut signal_error,
+                        num_bits,
+                        num_bytes,
+                        nums_encoded_as_fixed_width_le_u8,
+                        string_vals,
+                        lsb_indxs_of_num_tmstmp_vals_on_tmln,
+                        byte_len_of_num_tmstmp_vals_on_tmln,
+                        lsb_indxs_of_string_tmstmp_vals_on_tmln,
+                        byte_len_of_string_tmstmp_vals_on_tmln,
+                        ..
+                    } => {
+                        // we've already identified in a prior loop iteration that the signal has
+                        // an error
+                        if signal_error.is_some() {
+                            continue;
+                        }
+
+                        // Get the observed number of bits for the value parsed earlier
+                        // and verify that it is not greater than the numbits declared
+                        // when the signal was declared.
+                        // Also account for the error case of a bitwidth of `None`
+                        match num_bits {
+                            Some(ref num_bits) => {
+                                if observed_num_bits > *num_bits {
+                                    let (f, l) = (file!(), line!());
+                                    let msg = format!("\
+                                        Error near {f}:{l}. The bitwidth for signal {name} \
+                                        of signal_type {signal_type:?} is expected to be `{num_bits}` not \
+                                        `{observed_num_bits}`. \
+                                        This error occurred while parsing the vcd file at \
+                                        {cursor:?}");
+                                    *signal_error = Some(msg);
+                                    continue;
+                                }
+                            }
+                            None => {
+                                let (f, l) = (file!(), line!());
+                                let msg = format!(
+                                    "\
+                                    Error near {f}:{l}. The bitwidth for signal {name} \
+                                    must be specified for a signal of type {signal_type:?}. \
+                                    This error occurred while parsing the vcd file at \
+                                    {cursor:?}"
+                                );
+                                Err(msg)?;
+                            }
+                        };
+
+                        if store_as_string {
+                            lsb_indxs_of_string_tmstmp_vals_on_tmln
+                                .push(LsbIdxOfTmstmpValOnTmln(curr_tmstmp_lsb_idx));
+                            byte_len_of_string_tmstmp_vals_on_tmln.push(curr_tmstmp_len_u8);
+                            string_vals.push(value_string);
+                            Ok(())
+                        } else {
+                            // timestamp stuff
+                            lsb_indxs_of_num_tmstmp_vals_on_tmln
+                                .push(LsbIdxOfTmstmpValOnTmln(curr_tmstmp_lsb_idx));
+                            byte_len_of_num_tmstmp_vals_on_tmln.push(curr_tmstmp_len_u8);
+
+                            // value stuff
+                            // we may need to zero extend values
+                            // so that we end up storing all values
+                            // of a particular signal in a consistent
+                            // amount of bytes
+                            let bytes_required = num_bytes.ok_or_else(|| {
+                                format!("Error near {}:{}. num_bytes empty.", file!(), line!())
+                            })?;
+                            let mut curr_num_bytes =
+                                u16::try_from(value_u8.len()).map_err(|_| {
+                                    format!(
+                                        "Error near {}:{}. \
+                                     Found signal {name} with with value change of greater \
+                                     than 2^32 - 1 bits on {cursor:?}.",
+                                        file!(),
+                                        line!()
+                                    )
+                                })?;
+
+                            nums_encoded_as_fixed_width_le_u8.append(&mut value_u8);
+                            while curr_num_bytes < bytes_required {
+                                nums_encoded_as_fixed_width_le_u8.push(0u8);
+                                curr_num_bytes += 1;
+                            }
+                            Ok(())
+                        }
+                    }
+                    SignalEnum::Alias { .. } => {
+                        let (f, l) = (file!(), line!());
+                        let msg = format!(
+                            "Error near {f}:{l}, a signal alias should not point to a signal alias.\n\
+                                This error occurred while parsing vcd file at {cursor:?}");
+                        Err(msg)
+                    }
+                }?;
+            }
+
+            // handle the case of a one bit signal whose value is set to `0`
+            "0" => {
+                // lookup signal idx
+                let hash = &word[1..];
+                let signal_idx = signal_map.get(hash).ok_or(()).map_err(|_| {
+                    format!(
+                        "Error near {}:{}. Failed to lookup signal {hash} at {cursor:?}",
+                        file!(),
+                        line!()
+                    )
+                })?;
+
+                let signal = vcd.dealiasing_signal_idx_to_signal_lookup_mut(signal_idx)?;
+
+                match signal {
+                    SignalEnum::Data {
+                        name,
+                        signal_type,
+                        ref mut signal_error,
+                        num_bits,
+                        num_bytes,
+                        nums_encoded_as_fixed_width_le_u8,
+                        lsb_indxs_of_num_tmstmp_vals_on_tmln,
+                        byte_len_of_num_tmstmp_vals_on_tmln,
+                        ..
+                    } => {
+                        // if this is a bad signal, go ahead and skip it
+                        if signal_error.is_some() {
+                            continue;
+                        }
+
+                        // Get bitwidth and verify that it is 1.
+                        // Also account for the error case of a bitwidth of `None`
+                        match num_bits {
+                            Some(ref num_bits) => {
+                                if *num_bits != 1 {
+                                    let (f, l) = (file!(), line!());
+                                    let msg = format!(
+                                        "\
+                                        Error near {f}:{l}. The bitwidth for signal {name} \
+                                        of signal_type {signal_type:?} is expected to be `1` not \
+                                        `{num_bits}`. \
+                                        This error occurred while parsing the vcd file at \
+                                        {cursor:?}"
+                                    );
+                                    *signal_error = Some(msg);
+                                    continue;
+                                }
+                            }
+                            None => {
+                                let (f, l) = (file!(), line!());
+                                let msg = format!(
+                                    "\
+                                    Error near {f}:{l}. The bitwidth for signal {name} \
+                                    must be specified for a signal of type {signal_type:?}. \
+                                    This error occurred while parsing the vcd file at \
+                                    {cursor:?}"
+                                );
+                                Err(msg)?;
+                            }
+                        };
+                        // timestamp stuff
+                        lsb_indxs_of_num_tmstmp_vals_on_tmln
+                            .push(LsbIdxOfTmstmpValOnTmln(curr_tmstmp_lsb_idx));
+                        byte_len_of_num_tmstmp_vals_on_tmln.push(curr_tmstmp_len_u8);
+
+                        // value stuff
+                        // we may need to zero extend values
+                        // so that we end up storing all values
+                        // of a particular signal in a consistent
+                        // amount of bytes
+                        let bytes_required = num_bytes.ok_or_else(|| {
+                            format!("Error near {}:{}. num_bytes empty.", file!(), line!())
+                        })?;
+                        nums_encoded_as_fixed_width_le_u8.push(0u8);
+                        let mut curr_num_bytes = 1;
+                        while curr_num_bytes < bytes_required {
+                            nums_encoded_as_fixed_width_le_u8.push(0u8);
+                            curr_num_bytes += 1;
+                        }
+                        Ok(())
+                    }
+                    SignalEnum::Alias { .. } => {
+                        let (f, l) = (file!(), line!());
+                        let msg = format!(
+                            "Error near {f}:{l}, a signal alias should not point to a signal alias.\n\
+                             This error occurred while parsing vcd file at {cursor:?}");
+                        Err(msg)
+                    }
+                }?;
+            }
+
+            "1" => {
+                // lokup signal idx
+                let hash = &word[1..];
+                let signal_idx = signal_map.get(hash).ok_or(()).map_err(|_| {
+                    format!(
+                        "Error near {}:{}. Failed to lookup signal {hash} at {cursor:?}",
+                        file!(),
+                        line!()
+                    )
+                })?;
+
+                let signal = vcd.dealiasing_signal_idx_to_signal_lookup_mut(signal_idx)?;
+
+                match signal {
+                    SignalEnum::Data {
+                        name,
+                        signal_type,
+                        ref mut signal_error,
+                        num_bits,
+                        num_bytes,
+                        nums_encoded_as_fixed_width_le_u8,
+                        lsb_indxs_of_num_tmstmp_vals_on_tmln,
+                        byte_len_of_num_tmstmp_vals_on_tmln,
+                        ..
+                    } => {
+                        // if this is a bad signal, go ahead and skip it
+                        if signal_error.is_some() {
+                            continue;
+                        }
+
+                        // Get bitwidth and verify that it is 1.
+                        // Also account for the error case of a bitwidth of `None`
+                        match num_bits {
+                            Some(ref num_bits) => {
+                                if *num_bits != 1 {
+                                    let (f, l) = (file!(), line!());
+                                    let msg = format!(
+                                        "\
+                                        Error near {f}:{l}. The bitwidth for signal {name} \
+                                        of signal_type {signal_type:?} is expected to be `1` not \
+                                        `{num_bits}`. \
+                                        This error occurred while parsing the vcd file at \
+                                        {cursor:?}"
+                                    );
+                                    *signal_error = Some(msg);
+                                    continue;
+                                }
+                            }
+                            None => {
+                                let (f, l) = (file!(), line!());
+                                let msg = format!(
+                                    "\
+                                    Error near {f}:{l}. The bitwidth for signal {name} \
+                                    must be specified for a signal of type {signal_type:?}. \
+                                    This error occurred while parsing the vcd file at \
+                                    {cursor:?}"
+                                );
+                                Err(msg)?;
+                            }
+                        };
+                        // timestamp stuff
+                        lsb_indxs_of_num_tmstmp_vals_on_tmln
+                            .push(LsbIdxOfTmstmpValOnTmln(curr_tmstmp_lsb_idx));
+                        byte_len_of_num_tmstmp_vals_on_tmln.push(curr_tmstmp_len_u8);
+
+                        // value stuff
+                        // we may need to zero extend values
+                        // so that we end up storing all values
+                        // of a particular signal in a consistent
+                        // amount of bytes
+                        let bytes_required = num_bytes.ok_or_else(|| {
+                            format!("Error near {}:{}. num_bytes empty.", file!(), line!())
+                        })?;
+                        nums_encoded_as_fixed_width_le_u8.push(1u8);
+                        let mut curr_num_bytes = 1;
+                        while curr_num_bytes < bytes_required {
+                            nums_encoded_as_fixed_width_le_u8.push(0u8);
+                            curr_num_bytes += 1;
+                        }
+                        Ok(())
+                    }
+                    SignalEnum::Alias { .. } => {
+                        let (f, l) = (file!(), line!());
+                        let msg = format!(
+                            "Error near {f}:{l}, a signal alias should not point to a signal alias.\n\
+                             This error occurred while parsing vcd file at {cursor:?}");
+                        Err(msg)
+                    }
+                }?;
+            }
+
+            // other one bit cases
+            "x" | "X" | "z" | "Z" | "u" | "U" | "h" | "H" | "l" | "L" | "w" | "W" | "-" => {
+                // Select value and turn to lowercase for consistency
+                let val = word[0..1].to_ascii_lowercase();
+                // lokup signal idx
+                let hash = &word[1..];
+                let signal_idx = signal_map.get(hash).ok_or(()).map_err(|_| {
+                    format!(
+                        "Error near {}:{}. Failed to lookup signal {hash} at {cursor:?}",
+                        file!(),
+                        line!()
+                    )
+                })?;
+
+                let signal = vcd.dealiasing_signal_idx_to_signal_lookup_mut(signal_idx)?;
+
+                match signal {
+                    SignalEnum::Data {
+                        name,
+                        signal_type,
+                        ref mut signal_error,
+                        num_bits,
+                        string_vals,
+                        byte_len_of_string_tmstmp_vals_on_tmln,
+                        lsb_indxs_of_string_tmstmp_vals_on_tmln,
+                        ..
+                    } => {
+                        // if this is a bad signal, go ahead and skip it
+                        if signal_error.is_some() {
+                            continue;
+                        }
+
+                        // Get bitwidth and verify that it is 1.
+                        // Also account for the error case of a bitwidth of `None`
+                        match num_bits {
+                            Some(ref num_bits) => {
+                                if *num_bits != 1 {
+                                    let (f, l) = (file!(), line!());
+                                    let msg = format!(
+                                        "\
+                                        Error near {f}:{l}. The bitwidth for signal {name} \
+                                        of signal_type {signal_type:?} is expected to be `1` not \
+                                        `{num_bits}`. \
+                                        This error occurred while parsing the vcd file at \
+                                        {cursor:?}"
+                                    );
+                                    *signal_error = Some(msg);
+                                    continue;
+                                }
+                            }
+                            None => {
+                                let (f, l) = (file!(), line!());
+                                let msg = format!(
+                                    "\
+                                    Error near {f}:{l}. The bitwidth for signal {name} \
+                                    must be specified for a signal of type {signal_type:?}. \
+                                    This error occurred while parsing the vcd file at \
+                                    {cursor:?}"
+                                );
+                                Err(msg)?;
+                            }
+                        };
+
+                        // record timestamp at which this event occurs
+                        lsb_indxs_of_string_tmstmp_vals_on_tmln
+                            .push(LsbIdxOfTmstmpValOnTmln(curr_tmstmp_lsb_idx));
+                        byte_len_of_string_tmstmp_vals_on_tmln.push(curr_tmstmp_len_u8);
+
+                        // record value
+                        string_vals.push(val);
+                        Ok(())
+                    }
+                    SignalEnum::Alias { .. } => {
+                        let (f, l) = (file!(), line!());
+                        let msg = format!(
+                            "Error near {f}:{l}, a signal alias should not point to a signal alias.\n\
+                             This error occurred while parsing vcd file at {cursor:?}");
+                        Err(msg)
+                    }
+                }?;
+            }
+            // Store real values as a string as well and let the user parse it to an f64
+            "s" | " S" | "r" | "R" => {
+                let val = word[1..].to_string();
+                let (hash, cursor) = next_word!(word_reader)?;
+                // lokup signal idx
+                let signal_idx = signal_map.get(hash).ok_or(()).map_err(|_| {
+                    format!(
+                        "Error near {}:{}. Failed to lookup signal {hash} at {cursor:?}",
+                        file!(),
+                        line!()
+                    )
+                })?;
+
+                let signal = vcd.dealiasing_signal_idx_to_signal_lookup_mut(signal_idx)?;
+
+                match signal {
+                    SignalEnum::Data {
+                        ref mut signal_error,
+                        string_vals,
+                        byte_len_of_string_tmstmp_vals_on_tmln,
+                        lsb_indxs_of_string_tmstmp_vals_on_tmln,
+                        ..
+                    } => {
+                        // if this is a bad signal, go ahead and skip it
+                        if signal_error.is_some() {
+                            continue;
+                        }
+
+                        // record timestamp at which this event occurs
+                        lsb_indxs_of_string_tmstmp_vals_on_tmln
+                            .push(LsbIdxOfTmstmpValOnTmln(curr_tmstmp_lsb_idx));
+                        byte_len_of_string_tmstmp_vals_on_tmln.push(curr_tmstmp_len_u8);
+
+                        // record string value
+                        string_vals.push(val);
+                        Ok(())
+                    }
+                    SignalEnum::Alias { .. } => {
+                        let (f, l) = (file!(), line!());
+                        let msg = format!(
+                            "Error near {f}:{l}, a signal alias should not point to a signal alias.\n\
+                             This error occurred while parsing vcd file at {cursor:?}");
+                        Err(msg)
+                    }
+                }?;
+            }
+            _ => {}
+        }
+    }
+
+    Ok(())
+}

src/vcd/parse/metadata.rs

@@ -1,29 +1,33 @@
-use chrono::prelude::*;
+// Copyright (C) 2022 Yehowshua Immanuel
+// This program is distributed under both the GPLV3 license
+// and the YEHOWSHUA license, both of which can be found at
+// the root of the folder containing the sources for this program.
+use chrono::prelude::{DateTime, Utc};
 use itertools::Itertools;
-use std::fs::File;
-use function_name::named;
 
-use super::*;
+use super::super::reader::{next_word, Cursor, WordReader};
+use super::super::types::{Metadata, Timescale, Version};
+
+use super::combinator_atoms::{digit, tag, take_until, take_while};
+use super::types::ParseResult;
 
-#[named]
 pub(super) fn parse_date(
-    word_and_ctx1 : (&str, &Cursor),
+    word_and_ctx1: (&str, &Cursor),
-    word_and_ctx2 : (&str, &Cursor),
+    word_and_ctx2: (&str, &Cursor),
-    word_and_ctx3 : (&str, &Cursor),
+    word_and_ctx3: (&str, &Cursor),
-    word_and_ctx4 : (&str, &Cursor),
+    word_and_ctx4: (&str, &Cursor),
-    word_and_ctx5 : (&str, &Cursor),
+    word_and_ctx5: (&str, &Cursor),
 ) -> Result<DateTime<Utc>, String> {
-
     let day = {
         // check for another word in the file
         let (word, cursor) = word_and_ctx1;
-    
+
         let days = ["Mon", "Tue", "Wed", "Thu", "Fri", "Sat", "Sun"];
         if !days.contains(&word) {
-            let msg  = format!("reached end of file without parser leaving {}\n", function_name!());
+            let msg = format!("Error near {}:{}.", file!(), line!());
             let msg2 = format!("{word} is not a valid weekday : expected one of {days:?}\n");
             let msg3 = format!("failure location: {cursor:?}");
-            return Err(format!("{}{}{}", msg, msg2, msg3))
+            return Err(format!("{}{}{}", msg, msg2, msg3));
         }
 
         word.to_string()
@@ -34,16 +38,14 @@ pub(super) fn parse_date(
         let (word, cursor) = word_and_ctx2;
 
         let months = [
-            "Jan", "Feb", "Mar", "Apr", 
+            "Jan", "Feb", "Mar", "Apr", "May", "Jun", "Jul", "Aug", "Sept", "Oct", "Nov", "Dec",
-            "May", "Jun", "Jul", "Aug", 
+        ];
-            "Sept", "Oct", "Nov", "Dec", 
-            ];
 
         if !months.contains(&word) {
-            let msg  = format!("reached end of file without parser leaving {}\n", function_name!());
+            let msg = format!("Error near {}:{}.", file!(), line!());
             let msg2 = format!("{word} is not a valid month : expected one of {months:?}\n");
             let msg3 = format!("failure location: {cursor:?}");
-            return Err(format!("{}{}{}", msg, msg2, msg3))
+            return Err(format!("{}{}{}", msg, msg2, msg3));
         }
 
         word.to_string()
@@ -53,17 +55,16 @@ pub(super) fn parse_date(
         // check for another word in the file
         let (word, cursor) = word_and_ctx3;
 
-        let date : u8 = match word.to_string().parse() {
+        let date: u8 = match word.to_string().parse() {
             Ok(date) => date,
-            Err(_) => {return Err("".to_string())}
+            Err(e) => return Err(format!("Error near {}:{}. {e}", file!(), line!())),
         };
 
         if date > 31 {
-            let msg  = format!("reached end of file without parser leaving {}\n", function_name!());
+            let msg = format!("Error near {}:{}.", file!(), line!());
             let msg2 = format!("{word} is not a valid date : must be between 0 and 31\n");
             let msg3 = format!("failure location: {cursor:?}");
-            return Err(format!("{}{}{}", msg, msg2, msg3))
+            return Err(format!("{}{}{}", msg, msg2, msg3));
-
         }
 
         date.to_string()
@@ -75,170 +76,173 @@ pub(super) fn parse_date(
 
         let res = take_until(word, b':');
         res.assert_match()?;
-        let hh : u8 = res.matched.to_string()
+        let hh: u8 = res
-                        .parse()
+            .matched
-                        .map_err(|_| "failed to parse".to_string())?;
+            .to_string()
+            .parse()
+            .map_err(|e| format!("Error near {}:{}. {e}", file!(), line!()))?;
 
         if hh > 23 {
-            let msg  = format!("reached end of file without parser leaving {}\n", function_name!());
+            let msg = format!("Error near {}:{}.", file!(), line!());
             let msg2 = format!("{hh} is not a valid hour : must be between 0 and 23\n");
             let msg3 = format!("failure location: {cursor:?}");
-            return Err(format!("{}{}{}", msg, msg2, msg3))
+            return Err(format!("{}{}{}", msg, msg2, msg3));
         }
 
         // get minute
         let word = &res.residual[1..]; // chop off colon which is at index 0
         let res = take_until(word, b':');
         res.assert_match()?;
-        let mm : u8 = res.matched.to_string()
+        let mm: u8 = res
-                        .parse()
+            .matched
-                        .map_err(|_| "failed to parse".to_string())?;
+            .to_string()
+            .parse()
+            .map_err(|e| format!("Error near {}:{}. {e}", file!(), line!()))?;
 
         if mm > 60 {
-            let msg  = format!("reached end of file without parser leaving {}\n", function_name!());
+            let msg = format!("Error near {}:{}.", file!(), line!());
             let msg2 = format!("{mm} is not a valid minute : must be between 0 and 60\n");
             let msg3 = format!("failure location: {cursor:?}");
-            return Err(format!("{}{}{}", msg, msg2, msg3))
+            return Err(format!("{}{}{}", msg, msg2, msg3));
         }
 
         // get second
         // let ss : u8 = remainder.to_string().parse().unwrap();
         res.assert_residual()?;
         let residual = &res.residual[1..]; // chop of colon which is at index 0
-        let ss : u8 = residual.to_string()
+        let ss: u8 = residual
-                        .parse()
+            .to_string()
-                        .map_err(|_| "failed to parse".to_string())?;
+            .parse()
+            .map_err(|e| format!("Error near {}:{}. {e}", file!(), line!()))?;
 
         if ss > 60 {
-            let msg  = format!("reached end of file without parser leaving {}\n", function_name!());
+            let msg = format!("Error near {}:{}.", file!(), line!());
             let msg2 = format!("{ss} is not a valid second : must be between 0 and 60\n");
             let msg3 = format!("failure location: {cursor:?}");
-            return Err(format!("{}{}{}", msg, msg2, msg3))
+            return Err(format!("{}{}{}", msg, msg2, msg3));
         }
         (hh.to_string(), mm.to_string(), ss.to_string())
     };
 
     let year = {
         // check for another word in the file
-        let (word, cursor) = word_and_ctx5;
+        let (word, _) = word_and_ctx5;
         word.to_string()
     };
 
-    // unfortunately, the minutes, seconds, and hour could occur in an 
+    // unfortunately, the minutes, seconds, and hour could occur in an
     // unexpected order
     let full_date = format!("{day} {month} {date} {hh}:{mm}:{ss} {year}");
-    let full_date = Utc.datetime_from_str(full_date.as_str(), "%a %b %e %T %Y");
+    let full_date = DateTime::parse_from_str(full_date.as_str(), "%a %b %e %T %Y");
     if full_date.is_ok() {
-        return Ok(full_date.unwrap())
+        return Ok(full_date.unwrap().into());
     }
 
-    Err("failed to parse date".to_string())
+    Err(format!(
-
+        "Error near {}:{}. Failed to parse date.",
+        file!(),
+        line!()
+    ))
 }
 
-#[named]
+pub(super) fn parse_version<R: std::io::Read>(
-pub(super) fn parse_version(word_reader : &mut WordReader) -> Result<Version, String> {
+    word_reader: &mut WordReader<R>,
+) -> Result<Version, String> {
     let mut version = String::new();
 
     loop {
-        let word = word_reader.next_word();
+        let (word, _) = next_word!(word_reader)?;
-
-        // if there isn't another word left in the file, then we exit
-        if word.is_none() {
-            return Err(format!("reached end of file without parser leaving {}", function_name!()))
-        }
-
-        let (word, cursor) = word.unwrap();
 
         if word == "$end" {
             // truncate trailing whitespace
-            let version = version[0..(version.len() -  1)].to_string();
+            let version = version[0..(version.len() - 1)].to_string();
-            return Ok(Version(version))
+            return Ok(Version(version));
-
+        } else {
-        }
-        else {
             version.push_str(word);
-            version.push_str(" ");
+            version.push(' ');
         }
     }
 }
 
-#[named]
+pub(super) fn parse_timescale<R: std::io::Read>(
-pub(super) fn parse_timescale(word_reader : &mut WordReader) -> Result<(Option<u32>, Timescale), String> {
+    word_reader: &mut WordReader<R>,
-    let err_msg = format!("failed in {}", function_name!());
+) -> Result<(Option<u32>, Timescale), String> {
-
+    // we might see `1ps $end` or `1 ps $end`
-    // we might see `scalarunit $end` or `scalar unit $end`
-
     // first get timescale
-    let (word, cursor) = word_reader.next_word().ok_or(&err_msg)?;
+    let (word, _) = next_word!(word_reader)?;
-    let word = word.to_string();
+    let ParseResult { matched, residual } = take_while(word, digit);
-    let ParseResult{matched, residual} = take_while(word.as_str(), digit);
     let scalar = matched;
 
-    let scalar : u32 = scalar.to_string().parse()
+    let scalar: u32 = scalar
-                        .map_err(|_| &err_msg)?;
+        .to_string()
+        .parse()
+        .map_err(|e| format!("Error near {}:{}. {e}", file!(), line!()))?;
 
     let timescale = {
-        if residual == "" {
+        if residual.is_empty() {
-            let (word, cursor) = word_reader.next_word().ok_or(&err_msg)?;
+            let (word, _) = next_word!(word_reader)?;
             let unit = match word {
-                "fs" => {Ok(Timescale::fs)}
+                "fs" => Ok(Timescale::Fs),
-                "ps" => {Ok(Timescale::ps)}
+                "ps" => Ok(Timescale::Ps),
-                "ns" => {Ok(Timescale::ns)}
+                "ns" => Ok(Timescale::Ns),
-                "us" => {Ok(Timescale::us)}
+                "us" => Ok(Timescale::Us),
-                "ms" => {Ok(Timescale::ms)}
+                "ms" => Ok(Timescale::Ms),
-                "s"  => {Ok(Timescale::s)}
+                "s" => Ok(Timescale::S),
-                _    => {Err(err_msg.to_string())}
+                _ => Err(format!(
-            }.unwrap();
+                    "Error near {}:{}. Unknown unit {word}.",
-        
+                    file!(),
+                    line!()
+                )),
+            }?;
+
             (Some(scalar), unit)
-        }
+        } else {
-        else {
             let unit = match residual {
-                "ps" => {Ok(Timescale::ps)}
+                "fs" => Ok(Timescale::Fs),
-                "ns" => {Ok(Timescale::ns)}
+                "ps" => Ok(Timescale::Ps),
-                "us" => {Ok(Timescale::us)}
+                "ns" => Ok(Timescale::Ns),
-                "ms" => {Ok(Timescale::ms)}
+                "us" => Ok(Timescale::Us),
-                "s"  => {Ok(Timescale::s)}
+                "ms" => Ok(Timescale::Ms),
-                _    => {Err(err_msg.to_string())}
+                "s" => Ok(Timescale::S),
-            }.unwrap();
+                _ => Err(format!(
-        
+                    "Error near {}:{}. Unknown unit {residual}.",
+                    file!(),
+                    line!()
+                )),
+            }?;
+
             (Some(scalar), unit)
         }
     };
 
     // then check for the `$end` keyword
-    let (end, cursor) = word_reader.next_word().ok_or(&err_msg)?;
+    let (word, _) = next_word!(word_reader)?;
-    tag(end, "$end").assert_match()?;
+    tag(word, "$end").assert_match()?;
 
-    return Ok(timescale);
+    Ok(timescale)
-
-    Err("".to_string())
 }
 
-#[named]
+pub(super) fn parse_metadata<R: std::io::Read>(
-pub(super) fn parse_metadata(word_reader : &mut WordReader) -> Result<Metadata, String> {
+    word_reader: &mut WordReader<R>,
-    let err_msg = format!("reached end of file without parser leaving {}", function_name!());
+) -> Result<Metadata, String> {
-
     let mut metadata = Metadata {
-        date : None,
+        date: None,
-        version : None,
+        version: None,
-        timescale : (None, Timescale::unit)
+        timescale: (None, Timescale::Unit),
     };
 
     loop {
         // check for another word in the file
-        let (word, cursor) = word_reader.next_word().ok_or(&err_msg)?;
+        let (word, _) = next_word!(word_reader)?;
 
-        let ParseResult{matched, residual} = tag(word, "$");
+        let ParseResult { matched, residual } = tag(word, "$");
         match matched {
             // we hope that this word stars with a `$`
-            "$" =>  {
+            "$" => {
                 match residual {
-                    "date"      => {
+                    "date" => {
-                        let err_msg = format!("reached end of file without parser leaving {}", function_name!());
+                        // a date is typically composed of the 5 following words which can
-                        // a date is typically composed of the 5 following words which can 
+                        // occur in any order:
-                        // occur in any order: 
                         // {Day, Month, Date(number in month), hh:mm:ss, year}.
                         // Thus, we must lookahead read the 5 next words, and try our date
                         // parser on 5! = 120 permutations of the 5 words.
@@ -248,14 +252,14 @@ pub(super) fn parse_metadata(word_reader : &mut WordReader) -> Result<Metadata,
                         // that we may search up to 6 different permutations oh hh::mm:ss,
                         // for an upper bound total of 720 permutations
                         //
-                        // While looking ahead, if one of the 5 words in `$end`, we have to 
+                        // While looking ahead, if one of the 5 words in `$end`, we have to
                         // immediately stop trying to get more words.
 
                         let mut found_end = false;
-                        let mut lookahead_5_words : Vec<(String, Cursor)> = Vec::new();
+                        let mut lookahead_5_words: Vec<(String, Cursor)> = Vec::new();
 
-                        for word in 0..5 {
+                        for _ in 0..5 {
-                            let (word, cursor) = word_reader.next_word().expect(err_msg.as_str());
+                            let (word, cursor) = next_word!(word_reader)?;
                             let word = word.to_string();
                             match word.as_str() {
                                 "$end" => {
@@ -270,12 +274,14 @@ pub(super) fn parse_metadata(word_reader : &mut WordReader) -> Result<Metadata,
 
                         // we no longer attempt to parse date if we weren't able to lookahead 5
                         // words
-                        if found_end {continue}
+                        if found_end {
+                            continue;
+                        }
+
+                        let permutations = lookahead_5_words
+                            .iter()
+                            .permutations(lookahead_5_words.len());
 
-                        let permutations =  lookahead_5_words
-                                            .iter()
-                                            .permutations(lookahead_5_words.len());
-                        
                         // go ahead and search for a match amongst permuted date text
                         for mut permutations in permutations {
                             let (w1, s1) = permutations.pop().unwrap();
@@ -297,13 +303,12 @@ pub(super) fn parse_metadata(word_reader : &mut WordReader) -> Result<Metadata,
 
                             // store date and exit loop if a match is found
                             if parsed_date.is_ok() {
-                                metadata.date = Some(parsed_date.unwrap());
+                                metadata.date = Some(parsed_date?);
-                                break
+                                break;
                             }
-
                         }
                     }
-                    "version"   => {
+                    "version" => {
                         let version = parse_version(word_reader);
                         if version.is_ok() {
                             metadata.version = Some(version.unwrap());
@@ -315,8 +320,8 @@ pub(super) fn parse_metadata(word_reader : &mut WordReader) -> Result<Metadata,
                             metadata.timescale = timescale.unwrap();
                         }
                     }
-                    "scope"     => {break}
+                    "scope" => break,
-                    "var"       => {break}
+                    "var" => break,
                     // we keep searching for words until we've found one of the following
                     // keywords, ["version", "timescale", "scope", "var"]
                     _ => {}
@@ -325,7 +330,6 @@ pub(super) fn parse_metadata(word_reader : &mut WordReader) -> Result<Metadata,
             // if word does not start with `$`, then we keep looping
             _ => {}
         }
-
     }
-    return Ok(metadata)
+    Ok(metadata)
-}
+}

src/vcd/parse/scopes.rs

@@ -1,198 +1,442 @@
-//! part of the vcd parser that handles parsing the signal tree and
+// Copyright (C) 2022 Yehowshua Immanuel
-//! building the resulting signal tree
+// This program is distributed under both the GPLV3 license
-use function_name::named;
+// and the YEHOWSHUA license, both of which can be found at
+// the root of the folder containing the sources for this program.
 
-use super::*;
+/// part of the vcd parser that handles parsing the signal tree and
+/// building the resulting signal tree
+use std::collections::HashMap;
 
-#[named]
+use super::super::reader::{curr_word, next_word, WordReader};
-pub(super) fn parse_var<'a>(
+use super::super::signal::{SignalEnum, SignalType};
-    word_reader      : &mut WordReader,
+use super::super::types::{Scope, ScopeIdx, SignalIdx, VCD};
-    parent_scope_idx : Scope_Idx,
+
-    vcd              : &'a mut VCD,
+use super::combinator_atoms::{ident, tag};
-    signal_map       : &mut HashMap<String, Signal_Idx>
+use super::types::ParseResult;
+
+pub(super) fn parse_var<R: std::io::Read>(
+    word_reader: &mut WordReader<R>,
+    parent_scope_idx: ScopeIdx,
+    vcd: &mut VCD,
+    signal_map: &mut HashMap<String, SignalIdx>,
+    path: &Vec<String>,
 ) -> Result<(), String> {
-    let err = format!("reached end of file without parser leaving {}", function_name!());
+    let (word, cursor) = next_word!(word_reader)?;
-    let (word, cursor) = word_reader.next_word().ok_or(&err)?;
+    let expected_types = [
-    let expected_types = ["integer", "parameter", "real", "reg", "string", "wire", "tri1", "time"];
+        "event",
+        "integer",
+        "parameter",
+        "real",
+        "realtime",
+        "reg",
+        "string",
+        "supply0",
+        "supply1",
+        "time",
+        "tri",
+        "triand",
+        "trior",
+        "trireg",
+        "tri0",
+        "tri1",
+        "wand",
+        "wire",
+        "wor",
+    ];
 
     // $var parameter 3 a IDLE $end
     //      ^^^^^^^^^ - var_type
     let var_type = match word {
-        "integer"    => {Ok(Sig_Type::Integer)}
+        "event" => Ok(SignalType::Event),
-        "parameter"  => {Ok(Sig_Type::Parameter)}
+        "integer" => Ok(SignalType::Integer),
-        "real"       => {Ok(Sig_Type::Real)}
+        "parameter" => Ok(SignalType::Parameter),
-        "reg"        => {Ok(Sig_Type::Reg)}
+        "real" => Ok(SignalType::Real),
-        "string"     => {Ok(Sig_Type::Str)}
+        "realtime" => Ok(SignalType::RealTime),
-        "wire"       => {Ok(Sig_Type::Wire)}
+        "reg" => Ok(SignalType::Reg),
-        "tri1"       => {Ok(Sig_Type::Tri1)}
+        "string" => Ok(SignalType::Str),
-        "time"       => {Ok(Sig_Type::Time)}
+        "supply0" => Ok(SignalType::Supply0),
+        "supply1" => Ok(SignalType::Supply1),
+        "tri" => Ok(SignalType::Tri),
+        "triand" => Ok(SignalType::TriAnd),
+        "trior" => Ok(SignalType::TriOr),
+        "trireg" => Ok(SignalType::TriReg),
+        "tri0" => Ok(SignalType::Tri0),
+        "tri1" => Ok(SignalType::Tri1),
+        "time" => Ok(SignalType::Time),
+        "wand" => Ok(SignalType::WAnd),
+        "wire" => Ok(SignalType::Wire),
+        "wor" => Ok(SignalType::WOr),
         _ => {
-            let err = format!("found keyword `{word}` but expected one of {expected_types:?} on {cursor:?}");
+            let err = format!(
+                "Error near {}:{} \
+                               found keyword `{word}` but expected one of \
+                               {expected_types:?} on {cursor:?}",
+                file!(),
+                line!()
+            );
             Err(err)
         }
     }?;
 
-    let (word, cursor) = word_reader.next_word().ok_or(&err)?;
+    let (word, cursor) = next_word!(word_reader)?;
+
     let parse_err = format!("failed to parse as usize on {cursor:?}");
 
     // $var parameter 3 a IDLE $end
-    //                ^ - no_bits
+    //                ^ - num_bits
-    let no_bits = match var_type {
+    let num_bits = match var_type {
-        Sig_Type::Integer | Sig_Type::Parameter |
+        SignalType::Event
-        Sig_Type::Real    | Sig_Type::Reg       |
+        | SignalType::Integer
-        Sig_Type::Wire    | Sig_Type::Tri1      |
+        | SignalType::Parameter
-        Sig_Type::Time => {
+        | SignalType::Reg
-            let no_bits = word.parse::<usize>().expect(parse_err.as_str());
+        | SignalType::Supply0
-            Some(no_bits)
+        | SignalType::Supply1
+        | SignalType::Tri
+        | SignalType::TriAnd
+        | SignalType::TriOr
+        | SignalType::TriReg
+        | SignalType::Tri0
+        | SignalType::Tri1
+        | SignalType::Time
+        | SignalType::WAnd
+        | SignalType::Wire
+        | SignalType::WOr => {
+            let num_bits = word
+                .parse::<usize>()
+                .unwrap_or_else(|_| panic!("{}", parse_err));
+            let num_bits = u32::try_from(num_bits).map_err(|_| {
+                format!(
+                    "Error near {}:{} while parsing vcd file at {cursor:?}. \
+                     This signal has {num_bits} > 2^32 - 1 bits.",
+                    file!(),
+                    line!()
+                )
+            })?;
+            Some(num_bits)
         }
-        // for strings, we don't really care what the number of bits is
+        // for strings, reals, and realtimes we don't really care what the number of bits is
-        _ => {None}
+        _ => None,
     };
 
     // $var parameter 3 a IDLE $end
     //                  ^ - signal_alias
-    let (word, cursor) = word_reader.next_word().ok_or(&err)?;
+    let (word, _) = next_word!(word_reader)?;
     let signal_alias = word.to_string();
-    // dbg!(&signal_alias);
 
     // $var parameter 3 a IDLE $end
     //                    ^^^^ - full_signal_name(can extend until $end)
     let mut full_signal_name = Vec::<String>::new();
+    let mut size = None;
     loop {
-        let (word, cursor) = word_reader.next_word().ok_or(&err)?;
+        let (word, _) = next_word!(word_reader)?;
         match word {
-            "$end" => {break}
+            "$end" => break,
-            _      => {full_signal_name.push(word.to_string())}
+            other if other.starts_with('[') => size = Some(other.to_string()),
+            _ => full_signal_name.push(word.to_string()),
         }
     }
     let full_signal_name = full_signal_name.join(" ");
 
+    let num_bytes = if num_bits.is_some() {
+        let bytes_required = SignalEnum::bytes_required(num_bits.unwrap(), &full_signal_name)?;
+        Some(bytes_required)
+    } else {
+        None
+    };
+
     // Is the current variable an alias to a signal already encountered?
     // if so, handle ref_signal_idx accordingly, if not, add signal to hash
     // map
     let (signal, signal_idx) = match signal_map.get(&signal_alias) {
         Some(ref_signal_idx) => {
-            let signal_idx = Signal_Idx(vcd.all_signals.len());
+            let signal_idx = SignalIdx(vcd.all_signals.len());
-            let signal = Signal::Alias{
+            let signal = SignalEnum::Alias {
-                name: full_signal_name,
+                name: full_signal_name.clone(),
-                signal_alias: *ref_signal_idx};
+                path: path
+                    .iter()
+                    .cloned()
+                    .chain([full_signal_name])
+                    .collect::<Vec<String>>(),
+                signal_alias: *ref_signal_idx,
+            };
             (signal, signal_idx)
         }
         None => {
-            let signal_idx = Signal_Idx(vcd.all_signals.len());
+            let signal_idx = SignalIdx(vcd.all_signals.len());
             signal_map.insert(signal_alias.to_string(), signal_idx);
-            let signal = Signal::Data{
+            let signal = SignalEnum::Data {
-                name: full_signal_name,
+                name: full_signal_name.clone(),
-                sig_type: var_type,
+                path: path
+                    .iter()
+                    .cloned()
+                    .chain([full_signal_name])
+                    .collect::<Vec<String>>(),
+                signal_type: var_type,
+                index: size,
                 signal_error: None,
-                num_bits: no_bits,
+                num_bits,
+                num_bytes,
                 self_idx: signal_idx,
-                u8_timeline: vec![],
+                nums_encoded_as_fixed_width_le_u8: vec![],
-                u8_timeline_markers: vec![],
+                string_vals: vec![],
-                string_timeline: vec![],
+                lsb_indxs_of_num_tmstmp_vals_on_tmln: vec![],
-                string_timeline_markers: vec![],
+                byte_len_of_num_tmstmp_vals_on_tmln: vec![],
-                scope_parent: parent_scope_idx };
+                byte_len_of_string_tmstmp_vals_on_tmln: vec![],
+                lsb_indxs_of_string_tmstmp_vals_on_tmln: vec![],
+            };
             (signal, signal_idx)
         }
     };
 
     vcd.all_signals.push(signal);
-    let Scope_Idx(parent_scope_idx_usize) = parent_scope_idx;
+    let ScopeIdx(parent_scope_idx_usize) = parent_scope_idx;
     let parent_scope = vcd.all_scopes.get_mut(parent_scope_idx_usize).unwrap();
     parent_scope.child_signals.push(signal_idx);
 
     Ok(())
 }
 
-#[named]
+/// Sometimes, variables can be listed outside of scopes.
-pub(super) fn parse_signal_tree<'a>(
+/// We call these orphaned vars.
-    word_reader      : &mut WordReader,
+fn parse_orphaned_vars<R: std::io::Read>(
-    parent_scope_idx : Option<Scope_Idx>,
+    word_reader: &mut WordReader<R>,
-    vcd              : &'a mut VCD,
+    vcd: &mut VCD,
-    signal_map       : &mut HashMap<String, Signal_Idx>
+    signal_map: &mut HashMap<String, SignalIdx>,
 ) -> Result<(), String> {
+    // create scope for unscoped signals if such a scope does not
+    // yet exist
+    let scope_name = "Orphaned Signals";
 
+    // set default scope_idx to the count of existing scope as we
+    // generally set scope.self_idx to the number of existing scopes
+    // when that particular scope was inserted
+    let mut scope_idx = ScopeIdx(vcd.all_scopes.len());
+
+    // Override scope_idx if we find a scope named "Orphaned Signals"
+    // already exists
+    let mut scope_already_exists = false;
+    for scope in &vcd.all_scopes {
+        if scope.name == scope_name {
+            scope_idx = scope.self_idx;
+            scope_already_exists = true;
+            break;
+        }
+    }
+
+    if !scope_already_exists {
+        vcd.all_scopes.push(Scope {
+            name: scope_name.to_string(),
+            self_idx: scope_idx,
+            child_signals: vec![],
+            child_scopes: vec![],
+        });
+        vcd.root_scopes.push(scope_idx);
+    }
+
+    // we can go ahead and parse the current var as we've already encountered
+    // "$var" before now.
+    parse_var(word_reader, scope_idx, vcd, signal_map, &vec![])?;
+
+    loop {
+        let (word, cursor) = next_word!(word_reader)?;
+
+        match word {
+            "$var" => {
+                parse_var(word_reader, scope_idx, vcd, signal_map, &vec![])?;
+            }
+            "$scope" => break,
+            _ => {
+                let msg = format!(
+                    "Error near {}:{}.\
+                          Expected $scope or $var, found \
+                          {word} at {cursor:?}",
+                    file!(),
+                    line!()
+                );
+                Err(msg)?;
+            }
+        };
+    }
+
+    Ok(())
+}
+
+fn parse_scopes_inner<R: std::io::Read>(
+    word_reader: &mut WordReader<R>,
+    parent_scope_idx: Option<ScopeIdx>,
+    vcd: &mut VCD,
+    signal_map: &mut HashMap<String, SignalIdx>,
+    path: &Vec<String>,
+) -> Result<(), String> {
     // $scope module reg_mag_i $end
     //        ^^^^^^ - module keyword
-    let err = format!("reached end of file without parser leaving {}", function_name!());
+    let (keyword, cursor) = next_word!(word_reader)?;
-    let (keyword, cursor) = word_reader.next_word().ok_or(&err)?;
 
-    let expected = ["module", "begin", "task", "function"];
+    let expected = ["module", "begin", "task", "function", "fork"];
     if expected.contains(&keyword) {
         Ok(())
     } else {
-        let err = format!("found keyword `{keyword}` but expected one of `{expected:?}` on {cursor:?}");
+        let err = format!(
+            "Error near {}:{}. \
+                            found keyword `{keyword}` but expected one of \
+                            {expected:?} on {cursor:?}",
+            file!(),
+            line!()
+        );
         Err(err)
     }?;
 
     // $scope module reg_mag_i $end
     //               ^^^^^^^^^ - scope name
-    let (scope_name, _) = word_reader.next_word().ok_or(&err)?;
+    let (scope_name, _) = next_word!(word_reader)?;
+    // In some cases there are VCD files which have scopes without names.
+    // since these occur in the wild, we'll tolerate them even if it is unclear
+    // if it is supported or not by the spec.
+    if scope_name != "$end" {
+        let mut path = path.clone();
+        path.push(scope_name.to_string());
 
-    let curr_scope_idx = Scope_Idx(vcd.all_scopes.len());
+        let curr_scope_idx = ScopeIdx(vcd.all_scopes.len());
-    
-    // register this scope as a child of the current parent scope
-    // if there is a parent scope, or else we register this scope as
-    // root scope
-    match parent_scope_idx {
-        Some(Scope_Idx(parent_scope_idx)) => {
-            let parent_scope = vcd.all_scopes.get_mut(parent_scope_idx).unwrap();
-            parent_scope.child_scopes.push(curr_scope_idx);
-        }
-        None => {
-            vcd.scope_roots.push(curr_scope_idx)
-        }
-    }
 
-    // add this scope to list of existing scopes
+        // register this scope as a child of the current parent scope
-    vcd.all_scopes.push(
+        // if there is a parent scope, or else we register this scope as
-        Scope {
+        // root scope
+        match parent_scope_idx {
+            Some(ScopeIdx(parent_scope_idx)) => {
+                let parent_scope = vcd.all_scopes.get_mut(parent_scope_idx).unwrap();
+                parent_scope.child_scopes.push(curr_scope_idx);
+            }
+            None => vcd.root_scopes.push(curr_scope_idx),
+        }
+
+        // add this scope to list of existing scopes
+        vcd.all_scopes.push(Scope {
             name: scope_name.to_string(),
-            parent_idx: parent_scope_idx,
             self_idx: curr_scope_idx,
             child_signals: vec![],
-            child_scopes: vec![]
+            child_scopes: vec![],
-        }
+        });
-    );
 
-    // $scope module reg_mag_i $end
+        // $scope module reg_mag_i $end
-    //                         ^^^^ - end keyword
+        //                         ^^^^ - end keyword
-    ident(word_reader, "$end")?;
+        ident(word_reader, "$end")?;
 
-    let err = format!("reached end of file without parser leaving {}", function_name!());
+        loop {
-    loop {
+            let (word, cursor) = next_word!(word_reader)?;
-        let (word, cursor) = word_reader.next_word().ok_or(&err)?;
+            let ParseResult { matched, residual } = tag(word, "$");
-        let ParseResult{matched, residual} = tag(word, "$");
+            match matched {
-        match matched {
+                // we hope that this word starts with a `$`
-            // we hope that this word starts with a `$`
+                "$" => {
-            "$" =>  {
+                    match residual {
-                match residual {
+                        "scope" => {
-                    "scope" => {
+                            // recursive - parse inside of current scope tree
-                        // recursive - parse inside of current scope tree
+                            parse_scopes_inner(
-                        parse_signal_tree(word_reader, Some(curr_scope_idx), vcd, signal_map)?;
+                                word_reader,
-                    }
+                                Some(curr_scope_idx),
-                    "var" => {
+                                vcd,
-                        parse_var(word_reader, curr_scope_idx, vcd, signal_map)?;
+                                signal_map,
-                    }
+                                &path,
-                    "upscope" => {
+                            )?;
-                        ident(word_reader, "$end")?;
+                        }
-                        break
+                        "var" => {
-                    }
+                            parse_var(word_reader, curr_scope_idx, vcd, signal_map, &path)?;
-                    // we ignore comments
+                        }
-                    "comment" => {
+                        "upscope" => {
-                        loop {
+                            ident(word_reader, "$end")?;
-                            if ident(word_reader, "$end").is_ok() {break}
+                            break;
+                        }
+                        // we ignore comments
+                        "comment" => loop {
+                            if ident(word_reader, "$end").is_ok() {
+                                break;
+                            }
+                        },
+                        _ => {
+                            let err = format!(
+                                "Error near {}:{}. \
+                                               found keyword `{residual}` but expected \
+                                               `$scope`, `$var`, `$comment`, or `$upscope` \
+                                               on {cursor:?}",
+                                file!(),
+                                line!()
+                            );
+                            return Err(err);
                         }
                     }
-                    _ => {
+                }
-                        let err = format!("found keyword `{residual}` but expected `$scope`, `$var`, `$comment`, or `$upscope` on {cursor:?}");
+                _ => {
-                        return Err(err)
+                    let err = format!(
-                    }
+                        "Error near {}:{}. \
+                                      found keyword `{matched}` but \
+                                      expected `$` on {cursor:?}",
+                        file!(),
+                        line!()
+                    );
+                    return Err(err);
                 }
             }
-            _ => {
+        }
-                let err = format!("found keyword `{matched}` but expected `$` on {cursor:?}");
+    } else {
-                return Err(err)
+        // We'll be conservative and only allow new scopes in this case, and make the nameless
+        // scope completely transparent. I.e.
+        // $scope module a $end
+        //   $scope module $end
+        //     $scope module b $end
+        //       ...
+        //     $upscope
+        //   $upscope
+        // $upscope
+        // will create `a.b`
+        loop {
+            let (word, cursor) = next_word!(word_reader)?;
+            let ParseResult { matched, residual } = tag(word, "$");
+            match matched {
+                // we hope that this word starts with a `$`
+                "$" => {
+                    match residual {
+                        "scope" => {
+                            // recursive - parse inside of current scope tree
+                            parse_scopes_inner(
+                                word_reader,
+                                parent_scope_idx,
+                                vcd,
+                                signal_map,
+                                &path,
+                            )?;
+                        }
+                        "upscope" => {
+                            ident(word_reader, "$end")?;
+                            break;
+                        }
+                        // we ignore comments
+                        "comment" => loop {
+                            if ident(word_reader, "$end").is_ok() {
+                                break;
+                            }
+                        },
+                        _ => {
+                            let err = format!(
+                                "Error near {}:{}. \
+                                               found keyword `{residual}` in annonyoums scope but expected \
+                                               `$scope`, `$comment`, or `$upscope` \
+                                               on {cursor:?}",
+                                file!(),
+                                line!()
+                            );
+                            return Err(err);
+                        }
+                    }
+                }
+                _ => {
+                    let err = format!(
+                        "Error near {}:{}. \
+                                      found keyword `{matched}` but \
+                                      expected `$` on {cursor:?}",
+                        file!(),
+                        line!()
+                    );
+                    return Err(err);
+                }
             }
         }
     }
@@ -200,42 +444,79 @@ pub(super) fn parse_signal_tree<'a>(
     Ok(())
 }
 
-#[named]
+pub(super) fn parse_scopes<R: std::io::Read>(
-pub(super) fn parse_scopes<'a>(
+    word_reader: &mut WordReader<R>,
-    word_reader      : &mut WordReader,
+    vcd: &mut VCD,
-    parent_scope_idx : Option<Scope_Idx>,
+    signal_map: &mut HashMap<String, SignalIdx>,
-    vcd              : &'a mut VCD,
-    signal_map       : &mut HashMap<String, Signal_Idx>
 ) -> Result<(), String> {
-    // we've already seen `$scope`, so here we just jump right in
+    // get the current word
-    parse_signal_tree(word_reader, None, vcd, signal_map)?;
+    let (word, _) = curr_word!(word_reader)?;
 
-    let err = format!("reached end of file without parser leaving {}", function_name!());
+    // we may have orphaned vars that occur before the first scope
+    if word == "$var" {
+        parse_orphaned_vars(word_reader, vcd, signal_map)?;
+    }
+
+    // get the current word
+    let (word, cursor) = curr_word!(word_reader)?;
+
+    // the current word should be "scope", as `parse_orphaned_vars`(if it
+    // was called), should have terminated upon encountering "$scope".
+    // If `parse_orphaned_vars` was not called, `parse_scopes` should still
+    // have only been called if the caller encountered the word "$scope"
+    if word != "$scope" {
+        let msg = format!(
+            "Error near {}:{}.\
+                           Expected $scope or $var, found \
+                           {word} at {cursor:?}",
+            file!(),
+            line!()
+        );
+        return Err(msg);
+    }
+
+    // now for the interesting part
+    parse_scopes_inner(word_reader, None, vcd, signal_map, &vec![])?;
+
+    // let err = format!("reached end of file without parser leaving {}", function_name!());
     let expected_keywords = ["$scope", "$enddefinitions"];
 
+    // there could be multiple signal trees, and unfortunately, we
+    // can't merge the earlier call to `parse_scopes_inner` into this loop
+    // because this loop gets a word from `next_word` instead of
+    // `curr_word()`.
     loop {
-        let (word, cursor) = word_reader.next_word().ok_or(&err)?;
+        let (word, cursor) = next_word!(word_reader)?;
+
         match word {
             "$scope" => {
-                parse_signal_tree(word_reader, None, vcd, signal_map)?;
+                parse_scopes_inner(word_reader, None, vcd, signal_map, &vec![])?;
             }
             "$enddefinitions" => {
                 ident(word_reader, "$end")?;
-                break
+                break;
             }
-            // we ignore comments
+            "$comment" => {
-            "comment" => {
+                // although we don't store comments, we still need to advance the
+                // word_reader cursor to the end of the comment
                 loop {
-                    if ident(word_reader, "$end").is_ok() {break}
+                    if ident(word_reader, "$end").is_ok() {
+                        break;
+                    }
                 }
             }
             _ => {
-                let err = format!("found keyword `{word}` but expected oneof `{expected_keywords:?}` on {cursor:?}");
+                let err = format!(
-                return Err(err)
+                    "Error near {}:{} \
-    
+                                found keyword `{word}` but expected one of \
+                                {expected_keywords:?} on {cursor:?}",
+                    file!(),
+                    line!()
+                );
+                return Err(err);
             }
         }
     }
 
     Ok(())
-}
+}

src/vcd/parse/types.rs

@@ -1,25 +1,27 @@
+// Copyright (C) 2022 Yehowshua Immanuel
+// This program is distributed under both the GPLV3 license
+// and the YEHOWSHUA license, both of which can be found at
+// the root of the folder containing the sources for this program.
 #[derive(Debug)]
 pub(super) struct ParseResult<'a> {
-    pub(super) matched : &'a str, 
+    pub(super) matched: &'a str,
-    pub(super) residual : &'a str}
+    pub(super) residual: &'a str,
+}
 
 impl<'a> ParseResult<'a> {
-
+    pub(super) fn assert_match(&self) -> Result<&str, String> {
-    pub(super) fn assert_match(& self) -> Result<&str, String> {
+        if self.matched.is_empty() {
-        if self.matched == "" {
+            Err("no match".to_string())
-            return Err("no match".to_string())
+        } else {
-        }
+            Ok(self.matched)
-        else {
-            return Ok(self.matched)
         }
     }
 
-    pub(super) fn assert_residual(& self) -> Result<&str, String> {
+    pub(super) fn assert_residual(&self) -> Result<&str, String> {
-        if self.residual == "" {
+        if self.residual.is_empty() {
-            return Err("no residual".to_string())
+            Err("no residual".to_string())
-        }
+        } else {
-        else {
+            Ok(self.residual)
-            return Ok(self.residual)
         }
     }
-}
+}

src/vcd/reader.rs

@@ -1,9 +1,12 @@
-use std::fs::File;
+// Copyright (C) 2022 Yehowshua Immanuel
+// This program is distributed under both the GPLV3 license
+// and the YEHOWSHUA license, both of which can be found at
+// the root of the folder containing the sources for this program.
 use std::collections::VecDeque;
+use std::io;
+use std::io::BufRead;
 use std::slice;
 use std::str;
-use std::io::prelude::*;
-use std::io;
 
 #[derive(Debug, Clone)]
 pub(super) struct Line(pub(super) usize);
@@ -12,43 +15,40 @@ pub(super) struct Word(pub(super) usize);
 #[derive(Debug, Clone)]
 pub(super) struct Cursor(pub(super) Line, pub(super) Word);
 
-impl Cursor {
+pub(super) struct WordReader<R: io::Read> {
-    pub(super) fn error(&self, word : &str) -> Result<(), String> {
+    reader: io::BufReader<R>,
-        let Cursor(Line(line_no), Word(word_no)) = self;
+    eof: bool,
-        Err(format!("Error on word '{word}' {word_no} words into line {line_no}!"))
+    buffers: Vec<String>,
-    }
+    curr_line: usize,
-
+    str_slices: VecDeque<(*const u8, usize, Cursor)>,
+    curr_slice: Option<(*const u8, usize, Cursor)>,
 }
 
-pub struct WordReader {
+impl<R: std::io::Read> WordReader<R> {
-    reader       : io::BufReader<File>,
+    pub(super) fn new(file: R) -> WordReader<R> {
-    EOF          : bool,
+        let reader = io::BufReader::new(file);
-    buffers      : Vec<String>,
-    curr_line    : usize,
-    str_slices   : VecDeque<(*const u8, usize, Cursor)>,
-    curr_slice   : Option<(*const u8, usize, Cursor)>,
-}
-
-impl WordReader {
-    pub(super) fn new(file : File) -> WordReader {
-        let mut reader = io::BufReader::new(file);
         WordReader {
-            reader       : reader,
+            reader,
-            EOF          : false,
+            eof: false,
-            buffers      : vec![],
+            buffers: vec![],
-            curr_line    : 0,
+            curr_line: 0,
-            str_slices   : VecDeque::new(),
+            str_slices: VecDeque::new(),
-            curr_slice   : None
+            curr_slice: None,
         }
     }
 
     pub(super) fn next_word(&mut self) -> Option<(&str, Cursor)> {
-        // if there are no more words, attempt to read more content
+        // although reaching the eof is not technically an error, in most cases,
+        // we treat it like one in the rest of the codebase.
+
+        // if there are no more words in the buffer, attempt to read more content
         // from the file
         if self.str_slices.is_empty() {
             self.buffers.clear();
 
-            if self.EOF {return None}
+            if self.eof {
+                return None;
+            }
 
             let num_buffers = 10;
 
@@ -60,25 +60,25 @@ impl WordReader {
                 // if we've reached the end of the file on the first attempt to read
                 // a line in this for loop, no further attempts are necessary and we
                 if bytes_read == 0 {
-                    self.EOF = true; 
+                    self.eof = true;
                     break;
                 }
 
-                let mut words = self.buffers[buf_idx].split_ascii_whitespace();
+                let words = self.buffers[buf_idx].split_ascii_whitespace();
-                
+
                 for word in words.enumerate() {
                     let (word_idx, word) = word;
                     let position = Cursor(Line(self.curr_line), Word(word_idx + 1));
-                    self.str_slices.push_back((word.as_ptr(), word.len(), position))
+                    self.str_slices
+                        .push_back((word.as_ptr(), word.len(), position))
                 }
-
             }
         }
 
         // if after we've attempted to read in more content from the file,
         // there are still no words...
         if self.str_slices.is_empty() {
-            return None
+            return None;
         }
 
         // if we make it here, we return the next word
@@ -92,15 +92,40 @@ impl WordReader {
 
     pub(super) fn curr_word(&mut self) -> Option<(&str, Cursor)> {
         match &self.curr_slice {
-            Some(slice) => {
+            Some(slice) => unsafe {
-                unsafe {
+                let (ptr, len, position) = slice.clone();
-                    let (ptr, len, position) = slice.clone();
+                let slice = slice::from_raw_parts(ptr, len);
-                    let slice = slice::from_raw_parts(ptr, len);
+                return Some((str::from_utf8(slice).unwrap(), position));
-                    Some((str::from_utf8(slice).unwrap(), position))
+            },
-                }
+            None => None,
-
-            }
-            None => {None}
         }
     }
-}
+}
+
+macro_rules! next_word {
+    ($word_reader:ident) => {
+        $word_reader.next_word().ok_or(()).map_err(|_| {
+            format!(
+                "Error near {}:{}. Did not expect to reach end of file here.",
+                file!(),
+                line!()
+            )
+        })
+    };
+}
+
+macro_rules! curr_word {
+    ($word_reader:ident) => {
+        $word_reader.curr_word().ok_or(()).map_err(|_| {
+            format!(
+                "Error near {}:{}. A call to curr_word! shouldn't \
+                 fail unless next_word has not yet been invoked.",
+                file!(),
+                line!()
+            )
+        })
+    };
+}
+
+pub(super) use curr_word;
+pub(super) use next_word;

src/vcd/signal.rs

@@ -0,0 +1,715 @@
+// Copyright (C) 2022 Yehowshua Immanuel
+// This program is distributed under both the GPLV3 license
+// and the YEHOWSHUA license, both of which can be found at
+// the root of the folder containing the sources for this program.
+use super::types;
+use super::types::SignalIdx;
+use num::BigUint;
+
+// Index to the least significant byte of a timestamp
+// value on the timeline
+#[derive(Debug, Copy, Clone)]
+pub struct LsbIdxOfTmstmpValOnTmln(pub(super) u32);
+
+#[derive(Debug, Eq, PartialEq, Clone)]
+pub enum SignalType {
+    Event,
+    Integer,
+    Parameter,
+    Real,
+    RealTime,
+    Reg,
+    Str,
+    Supply0,
+    Supply1,
+    Time,
+    Tri,
+    TriAnd,
+    TriOr,
+    TriReg,
+    Tri0,
+    Tri1,
+    WAnd,
+    Wire,
+    WOr,
+}
+
+#[derive(Debug, PartialEq)]
+pub enum SignalValue {
+    BigUint(BigUint),
+    String(String),
+}
+
+pub struct QueryResult<T> {
+    pub current: Option<(TimeStamp, T)>,
+    pub next: Option<TimeStamp>,
+}
+
+pub struct Signal<'a>(pub(super) &'a SignalEnum);
+
+impl<'a> Signal<'a> {
+    pub fn name(&self) -> String {
+        let Signal(signal_enum) = &self;
+        signal_enum.name()
+    }
+
+    pub fn name_with_index(&self) -> String {
+        let Signal(signal_enum) = &self;
+        signal_enum.name_with_index()
+    }
+
+    pub fn index(&self) -> Option<String> {
+        let Signal(signal_enum) = &self;
+        signal_enum.index()
+    }
+
+    pub fn path(&self) -> &[String] {
+        match self.0 {
+            SignalEnum::Data { path, .. } => path,
+            SignalEnum::Alias { path, .. } => path,
+        }
+    }
+
+    pub fn signal_type(&self) -> Option<&SignalType> {
+        let Signal(signal_enum) = &self;
+        signal_enum.signal_type()
+    }
+
+    pub fn real_idx(&self) -> SignalIdx {
+        match self.0 {
+            SignalEnum::Data { self_idx, .. } => *self_idx,
+            SignalEnum::Alias { signal_alias, .. } => *signal_alias,
+        }
+    }
+
+    pub fn num_bits(&self) -> Option<u32> {
+        let Signal(signal_enum) = &self;
+        signal_enum.bits_required()
+    }
+
+    // NOTE: (zoq) I am removing thse because they aren't used in Surfer so I can't test them
+    // properly
+    /*
+    pub fn query_string_val_on_tmln(
+        &self,
+        desired_time: &BigUint,
+        vcd: &types::VCD,
+    ) -> Result<String, SignalErrors> {
+        let Signal(signal_enum) = &self;
+        signal_enum
+            .query_string_val_on_tmln(desired_time, &vcd.tmstmps_encoded_as_u8s, &vcd.all_signals)
+            .map(|QueryResult{current, next: _}| current.map(|c| c.1))
+    }
+
+    pub fn query_num_val_on_tmln(
+        &self,
+        desired_time: &BigUint,
+        vcd: &types::VCD,
+    ) -> Result<Option<BigUint>, SignalErrors> {
+        let Signal(signal_enum) = &self;
+        signal_enum
+            .query_num_val_on_tmln(desired_time, &vcd.tmstmps_encoded_as_u8s, &vcd.all_signals)
+            .map(|QueryResult{current, next: _}| current.map(|c| c.1))
+    }
+    */
+
+    pub fn query_val_on_tmln(
+        &self,
+        desired_time: &BigUint,
+        vcd: &types::VCD,
+    ) -> Result<QueryResult<SignalValue>, SignalErrors> {
+        let Signal(signal_enum) = &self;
+        let num_query_out = signal_enum.query_num_val_on_tmln(
+            desired_time,
+            &vcd.tmstmps_encoded_as_u8s,
+            &vcd.all_signals,
+        );
+        let str_query_out = signal_enum.query_string_val_on_tmln(
+            desired_time,
+            &vcd.tmstmps_encoded_as_u8s,
+            &vcd.all_signals,
+        );
+
+        // Both num and str will return the newest value that is closest to
+        // the desired time. If both have valid values, select the most recent
+        // one
+        match (num_query_out, str_query_out) {
+            (Ok(num_result), Ok(str_result)) => {
+                let next = match (num_result.next, str_result.next) {
+                    (Some(n), Some(s)) => Some(n.min(s)),
+                    (Some(n), None) => Some(n),
+                    (None, Some(s)) => Some(s),
+                    (None, None) => None,
+                };
+
+                match (num_result.current, str_result.current) {
+                    (Some((num_time, num_value)), Some((str_time, str_value))) => {
+                        if num_time > str_time {
+                            Ok(QueryResult {
+                                current: Some((num_time, SignalValue::BigUint(num_value))),
+                                next,
+                            })
+                        } else {
+                            Ok(QueryResult {
+                                current: Some((str_time, SignalValue::String(str_value))),
+                                next,
+                            })
+                        }
+                    }
+                    (Some((num_time, num_val)), None) => Ok(QueryResult {
+                        current: Some((num_time, SignalValue::BigUint(num_val))),
+                        next,
+                    }),
+                    (None, Some((str_time, str_value))) => Ok(QueryResult {
+                        current: Some((str_time, SignalValue::String(str_value))),
+                        next,
+                    }),
+                    (None, None) => Ok(QueryResult {
+                        current: None,
+                        next,
+                    }),
+                }
+            }
+            (_e, Err(e)) => Err(e),
+            (Err(e), _e) => Err(e),
+        }
+    }
+}
+
+#[derive(Debug)]
+pub(super) enum SignalEnum {
+    Data {
+        name: String,
+        path: Vec<String>,
+        signal_type: SignalType,
+        /// The optional [start:end] part of the signal name that is sometimes
+        /// added to signals
+        index: Option<String>,
+        /// I've seen a 0 bit signal parameter in a xilinx
+        /// simulation before that gets assigned 1 bit values.
+        /// I consider this to be bad behavior. We capture such
+        /// errors in the following type:
+        signal_error: Option<String>,
+        num_bits: Option<u32>,
+        num_bytes: Option<u16>,
+        /// TODO : may be able to remove self_idx
+        self_idx: SignalIdx,
+        /// A signal may take on a new value and hold that value
+        /// for sometime. We only need to record the value of a signal
+        /// when it changes(the is what VCDs tend to do).
+        /// A signal may need x amount of bytes to record its largest
+        /// possible value, so we record every single value of a given
+        /// signal as a sequence of x number of u8s.
+        /// For example, we might find that `my_signal.
+        /// nums_encoded_as_fixed_width_le_u8`
+        /// has two 32 bit values, namely, 1 and 2, encoded as follows:
+        /// my_signal.nums_encoded_as_fixed_width_le_u8 = vec![1u8, 0u8,
+        /// 0u8, 0u8, 2u8, 0u8, 0u8, 0u8];
+        nums_encoded_as_fixed_width_le_u8: Vec<u8>,
+        string_vals: Vec<String>,
+        /// we could do Vec<(LsbIdxOfTmstmpValOnTmln, u8)>, but I
+        /// suspect that Vec<LsbIdxOfTmstmpValOnTmln> is more cache
+        /// friendly. We use ``LsbIdxOfTmstmpValOnTmln`` to index into
+        /// the LSB of a particular timestamp encoded as the
+        /// minimum length u8 sequence within
+        /// ``vcd.tmstmps_encoded_as_u8s``, and we use the values in
+        /// ``byte_len_of_num_tmstmp_vals_on_tmln`` to determine how
+        /// many u8 values a particular timestamp is composed of.
+        lsb_indxs_of_num_tmstmp_vals_on_tmln: Vec<LsbIdxOfTmstmpValOnTmln>,
+        byte_len_of_num_tmstmp_vals_on_tmln: Vec<u8>,
+        byte_len_of_string_tmstmp_vals_on_tmln: Vec<u8>,
+        lsb_indxs_of_string_tmstmp_vals_on_tmln: Vec<LsbIdxOfTmstmpValOnTmln>,
+    },
+    Alias {
+        name: String,
+        path: Vec<String>,
+        signal_alias: SignalIdx,
+    },
+}
+
+#[derive(Debug)]
+pub enum SignalErrors {
+    EmptyTimeline,
+    TimelineNotMultiple,
+    StrTmlnLenMismatch,
+    OrderingFailure {
+        lhs_time: BigUint,
+        mid_time: BigUint,
+        rhs_time: BigUint,
+    },
+    PointsToAlias,
+    NoNumBytes,
+    Other(String),
+}
+
+// these are thin type aliases primarily to make code more readable later on
+type TimeStamp = BigUint;
+type SignalValNum = BigUint;
+
+// getter functions
+impl SignalEnum {
+    pub fn name(&self) -> String {
+        match self {
+            SignalEnum::Data { name, .. } => name,
+            SignalEnum::Alias { name, .. } => name,
+        }
+        .clone()
+    }
+
+    pub fn signal_type(&self) -> Option<&SignalType> {
+        match self {
+            SignalEnum::Data { signal_type, .. } => Some(signal_type),
+            // TODO: Follow aliases?
+            SignalEnum::Alias { .. } => None,
+        }
+        .clone()
+    }
+
+    pub fn name_with_index(&self) -> String {
+        match self {
+            SignalEnum::Data {
+                name, index: None, ..
+            } => format!("{name}"),
+            SignalEnum::Data {
+                name,
+                index: Some(size),
+                ..
+            } => format!("{name} {size}"),
+            SignalEnum::Alias { name, .. } => name.clone(),
+        }
+    }
+
+    pub fn index(&self) -> Option<String> {
+        match self {
+            SignalEnum::Data { index, .. } => index.clone(),
+            SignalEnum::Alias { .. } => None,
+        }
+    }
+}
+
+// helper functions ultimately used by Signal's query functions later on
+impl SignalEnum {
+    /// Computes the bytes required to store a signal's numerical value
+    /// using the num_bits which another function would provide from
+    /// the num_bits field of the Signal::Data variant.
+    pub(super) fn bytes_required(num_bits: u32, name: &String) -> Result<u16, String> {
+        let bytes_required = (num_bits / 8) + if (num_bits % 8) > 0 { 1 } else { 0 };
+        let bytes_required = u16::try_from(bytes_required).map_err(|_| {
+            format!(
+                "Error near {}:{}. Signal {name} of length num_bits requires \
+                        {bytes_required} > 65536 bytes.",
+                file!(),
+                line!()
+            )
+        })?;
+        Ok(bytes_required)
+    }
+    /// This function takes an event_idx which(is used to index into the
+    /// global timeline field of a VCD struct instance) and computes
+    /// the time pointed at by event_idx.
+    /// This function also uses the same idx to index into the
+    /// string_vals field of an instance of the Signal::Data variant
+    ///  and gets a string value.
+    /// The function returns a tuple of the timestamp and string value.
+    fn time_and_str_val_at_event_idx(
+        &self,
+        event_idx: usize,
+        tmstmps_encoded_as_u8s: &Vec<u8>,
+    ) -> Result<(TimeStamp, &str), SignalErrors> {
+        let (
+            string_vals,
+            lsb_indxs_of_string_tmstmp_vals_on_tmln,
+            byte_len_of_string_tmstmp_vals_on_tmln,
+        ) = match self {
+            SignalEnum::Data {
+                string_vals,
+                lsb_indxs_of_string_tmstmp_vals_on_tmln,
+                byte_len_of_string_tmstmp_vals_on_tmln,
+                ..
+            } => Ok((
+                string_vals,
+                lsb_indxs_of_string_tmstmp_vals_on_tmln,
+                byte_len_of_string_tmstmp_vals_on_tmln,
+            )),
+            SignalEnum::Alias { .. } => Err(SignalErrors::PointsToAlias),
+        }?;
+
+        // get index
+        let LsbIdxOfTmstmpValOnTmln(timestamp_idx) =
+            lsb_indxs_of_string_tmstmp_vals_on_tmln[event_idx];
+        let timestamp_idx = timestamp_idx as usize;
+
+        if byte_len_of_string_tmstmp_vals_on_tmln.is_empty() {
+            return Err(SignalErrors::EmptyTimeline);
+        }
+
+        // form timestamp
+        let byte_len = byte_len_of_string_tmstmp_vals_on_tmln[event_idx] as usize;
+        let timestamp = &tmstmps_encoded_as_u8s[timestamp_idx..(timestamp_idx + byte_len)];
+        let timestamp = BigUint::from_bytes_le(timestamp);
+
+        // get signal value
+        let signal_val = string_vals[event_idx].as_str();
+
+        Ok((timestamp, signal_val))
+    }
+    /// This function takes an event_idx which(is used to index into the
+    /// global timeline field of a VCD struct instance) and computes
+    /// the time pointed at by event_idx.
+    /// This function also uses the same idx to index into the
+    /// nums_encoded_as_fixed_width_le_u8 and
+    /// byte_len_of_num_tmstmp_vals_on_tmln fields of an instance
+    /// of the Signal::Data variant to compute the signal's corresponding
+    /// numerical value at the time pointed at by event_didx.
+    /// The function returns a tuple of the timestamp and numerical
+    /// value.
+    fn time_and_num_val_at_event_idx(
+        &self,
+        event_idx: usize,
+        tmstmps_encoded_as_u8s: &Vec<u8>,
+    ) -> Result<(TimeStamp, SignalValNum), SignalErrors> {
+        let (
+            num_bytes,
+            nums_encoded_as_fixed_width_le_u8,
+            lsb_indxs_of_num_tmstmp_vals_on_tmln,
+            byte_len_of_num_tmstmp_vals_on_tmln,
+        ) = match self {
+            SignalEnum::Data {
+                num_bytes,
+                nums_encoded_as_fixed_width_le_u8,
+                lsb_indxs_of_num_tmstmp_vals_on_tmln,
+                byte_len_of_num_tmstmp_vals_on_tmln,
+                ..
+            } => Ok((
+                num_bytes,
+                nums_encoded_as_fixed_width_le_u8,
+                lsb_indxs_of_num_tmstmp_vals_on_tmln,
+                byte_len_of_num_tmstmp_vals_on_tmln,
+            )),
+            SignalEnum::Alias { .. } => Err(SignalErrors::PointsToAlias),
+        }?;
+
+        // get index
+        let LsbIdxOfTmstmpValOnTmln(timestamp_idx) =
+            lsb_indxs_of_num_tmstmp_vals_on_tmln[event_idx];
+        let timestamp_idx = timestamp_idx as usize;
+
+        // form timestamp
+        let byte_len = byte_len_of_num_tmstmp_vals_on_tmln[event_idx] as usize;
+        let timestamp = &tmstmps_encoded_as_u8s[timestamp_idx..(timestamp_idx + byte_len)];
+        let timestamp = BigUint::from_bytes_le(timestamp);
+
+        // get signal value
+        let bytes_per_value = num_bytes.ok_or_else(|| SignalErrors::NoNumBytes)?;
+        let bytes_per_value = bytes_per_value as usize;
+        let start_idx = event_idx * bytes_per_value;
+        let end_idx = (event_idx + 1) * bytes_per_value;
+        let signal_val = &nums_encoded_as_fixed_width_le_u8[start_idx..end_idx];
+        let signal_val = BigUint::from_bytes_le(signal_val);
+
+        Ok((timestamp, signal_val))
+    }
+
+    fn bits_required(&self) -> Option<u32> {
+        match self {
+            SignalEnum::Data { num_bits, .. } => *num_bits,
+            // TODO: Follow aliases?
+            SignalEnum::Alias { .. } => None,
+        }
+    }
+}
+
+// Val and string query functions.
+// Function that take in a desired time on the timeline for a
+// specific signal and return a numerical or string value in a Result,
+// or an error in a Result.
+impl SignalEnum {
+    pub fn query_string_val_on_tmln(
+        &self,
+        desired_time: &BigUint,
+        tmstmps_encoded_as_u8s: &Vec<u8>,
+        all_signals: &Vec<SignalEnum>,
+    ) -> Result<QueryResult<String>, SignalErrors> {
+        let signal_idx = match self {
+            Self::Data { self_idx, .. } => {
+                let SignalIdx(idx) = self_idx;
+                *idx
+            }
+            Self::Alias {
+                name: _,
+                signal_alias,
+                path: _,
+            } => {
+                let SignalIdx(idx) = signal_alias;
+                *idx
+            }
+        };
+
+        // if the signal idx points to data variant of the signal,
+        // extract:
+        // 1. the vector of string values
+        // 2. the vector of indices into timeline where events occur
+        //    for this signal
+        // else we propagate Err(..).
+        let (string_vals, lsb_indxs_of_string_tmstmp_vals_on_tmln) = match &all_signals[signal_idx]
+        {
+            SignalEnum::Data {
+                ref string_vals,
+                ref lsb_indxs_of_string_tmstmp_vals_on_tmln,
+                ..
+            } => Ok((string_vals, lsb_indxs_of_string_tmstmp_vals_on_tmln)),
+            SignalEnum::Alias { .. } => Err(SignalErrors::PointsToAlias),
+        }?;
+        // this signal should at least have some events, otherwise, trying to index into
+        // an empty vector later on would fail
+        if lsb_indxs_of_string_tmstmp_vals_on_tmln.is_empty() {
+            return Ok(QueryResult {
+                current: None,
+                next: None
+            });
+        }
+
+        // the vector of string timeline lsb indices should have the same
+        // length as the vector of string values
+        if string_vals.len() != lsb_indxs_of_string_tmstmp_vals_on_tmln.len() {
+            return Err(SignalErrors::StrTmlnLenMismatch);
+        }
+
+        // check if we're requesting a value that occurs before the recorded
+        // start of the timeline
+        let (timeline_start_time, _) =
+            self.time_and_str_val_at_event_idx(0, tmstmps_encoded_as_u8s)?;
+        if *desired_time < timeline_start_time {
+            return Ok(QueryResult {
+                current: None,
+                next: Some(timeline_start_time),
+            });
+        }
+
+        let mut lower_idx = 0usize;
+        let mut upper_idx = lsb_indxs_of_string_tmstmp_vals_on_tmln.len() - 1;
+        let (timeline_end_time, timeline_end_val) =
+            self.time_and_str_val_at_event_idx(upper_idx, tmstmps_encoded_as_u8s)?;
+
+        // check if we're requesting a value that occurs beyond the end of the timeline,
+        // if so, return the last value in this timeline
+        if *desired_time > timeline_end_time {
+            return Ok(QueryResult {
+                current: Some((timeline_end_time, timeline_end_val.to_string())),
+                next: None,
+            });
+        }
+
+        // This while loop is the meat of the lookup. Performance is log2(n),
+        // where n is the number of events on the timeline.
+        // We can assume that by the time we get here, that the desired_time
+        // is an event that occurs on the timeline, given that we handle any events
+        // occuring after or before the recorded tiimeline in the code above.
+        while lower_idx <= upper_idx {
+            let mid_idx = lower_idx + ((upper_idx - lower_idx) / 2);
+            let (curr_time, curr_val) =
+                self.time_and_str_val_at_event_idx(mid_idx, tmstmps_encoded_as_u8s)?;
+            let ordering = curr_time.cmp(desired_time);
+
+            match ordering {
+                std::cmp::Ordering::Less => {
+                    lower_idx = mid_idx + 1;
+                }
+                std::cmp::Ordering::Equal => {
+                    let next_time = if mid_idx < lsb_indxs_of_string_tmstmp_vals_on_tmln.len() - 1 {
+                        Some(
+                            self.time_and_str_val_at_event_idx(
+                                mid_idx + 1,
+                                tmstmps_encoded_as_u8s,
+                            )?
+                            .0,
+                        )
+                    } else {
+                        None
+                    };
+                    return Ok(QueryResult {
+                        current: Some((curr_time, curr_val.to_string())),
+                        next: next_time,
+                    });
+                }
+                std::cmp::Ordering::Greater => {
+                    upper_idx = mid_idx - 1;
+                }
+            }
+        }
+
+        let (left_time, left_val) =
+            self.time_and_str_val_at_event_idx(lower_idx - 1, tmstmps_encoded_as_u8s)?;
+        let (right_time, _) =
+            self.time_and_str_val_at_event_idx(lower_idx, tmstmps_encoded_as_u8s)?;
+
+        let ordered_left = left_time < *desired_time;
+        let ordered_right = *desired_time < right_time;
+        if !(ordered_left && ordered_right) {
+            return Err(SignalErrors::OrderingFailure {
+                lhs_time: left_time,
+                mid_time: desired_time.clone(),
+                rhs_time: right_time,
+            });
+        }
+
+        Ok(QueryResult {
+            current: Some((left_time, left_val.to_string())),
+            next: Some(right_time),
+        })
+    }
+    pub fn query_num_val_on_tmln(
+        &self,
+        desired_time: &BigUint,
+        tmstmps_encoded_as_u8s: &Vec<u8>,
+        all_signals: &Vec<SignalEnum>,
+    ) -> Result<QueryResult<BigUint>, SignalErrors> {
+        let signal_idx = match self {
+            Self::Data { self_idx, .. } => {
+                let SignalIdx(idx) = self_idx;
+                *idx
+            }
+            Self::Alias {
+                name: _,
+                path: _,
+                signal_alias,
+            } => {
+                let SignalIdx(idx) = signal_alias;
+                *idx
+            }
+        };
+
+        // if the signal idx points to data variant of the signal,
+        // extract:
+        // 1. the vector of LE u8 compressed values
+        // 2. the vector of indices into timeline where events occur
+        //    for this signal
+        // 3. the number of bytes per value for this signal
+        // else we propagate Err(..).
+        let (nums_encoded_as_fixed_width_le_u8, lsb_indxs_of_num_tmstmp_vals_on_tmln, num_bytes) =
+            match &all_signals[signal_idx] {
+                SignalEnum::Data {
+                    num_bytes,
+                    ref nums_encoded_as_fixed_width_le_u8,
+                    ref lsb_indxs_of_num_tmstmp_vals_on_tmln,
+                    ..
+                } => {
+                    if num_bytes.is_none() {
+                        return Err(SignalErrors::NoNumBytes);
+                    }
+                    Ok((
+                        nums_encoded_as_fixed_width_le_u8,
+                        lsb_indxs_of_num_tmstmp_vals_on_tmln,
+                        num_bytes,
+                    ))
+                }
+                SignalEnum::Alias { .. } => Err(SignalErrors::PointsToAlias),
+            }?;
+        // this signal should at least have some events, otherwise, trying to index into
+        // an empty vector later on would fail
+        if lsb_indxs_of_num_tmstmp_vals_on_tmln.is_empty() {
+            return Ok(QueryResult {
+                current: None,
+                next: None
+            });
+        }
+
+        // assertion that value_sequence is a proper multiple of
+        // timeline_markers
+        let bytes_required = num_bytes.ok_or_else(|| {
+            SignalErrors::Other(format!(
+                "Error near {}:{}. num_bytes empty.",
+                file!(),
+                line!()
+            ))
+        })?;
+        if nums_encoded_as_fixed_width_le_u8.len()
+            != (lsb_indxs_of_num_tmstmp_vals_on_tmln.len() * (bytes_required as usize))
+        {
+            return Err(SignalErrors::TimelineNotMultiple);
+        }
+
+        // check if we're requesting a value that occurs before the recorded
+        // start of the timeline
+        let (timeline_start_time, _) =
+            self.time_and_num_val_at_event_idx(0, tmstmps_encoded_as_u8s)?;
+        if *desired_time < timeline_start_time {
+            return Ok(QueryResult {
+                current: None,
+                next: Some(timeline_start_time),
+            });
+        }
+
+        let mut lower_idx = 0usize;
+        let mut upper_idx = lsb_indxs_of_num_tmstmp_vals_on_tmln.len() - 1;
+        let (timeline_end_time, timeline_end_val) =
+            self.time_and_num_val_at_event_idx(upper_idx, tmstmps_encoded_as_u8s)?;
+
+        // check if we're requesting a value that occurs beyond the end of the timeline,
+        // if so, return the last value in this timeline
+        if *desired_time > timeline_end_time {
+            return Ok(QueryResult {
+                current: Some((timeline_end_time, timeline_end_val)),
+                next: None,
+            });
+        }
+
+        // This while loop is the meat of the lookup. Performance is log2(n),
+        // where n is the number of events on the timeline.
+        // We can assume that by the time we get here, that the desired_time
+        // is an event that occurs on the timeline, given that we handle any events
+        // occuring after or before the recorded tiimeline in the code above.
+        while lower_idx <= upper_idx {
+            let mid_idx = lower_idx + ((upper_idx - lower_idx) / 2);
+            let (curr_time, curr_val) =
+                self.time_and_num_val_at_event_idx(mid_idx, tmstmps_encoded_as_u8s)?;
+            let ordering = curr_time.cmp(desired_time);
+
+            match ordering {
+                std::cmp::Ordering::Less => {
+                    lower_idx = mid_idx + 1;
+                }
+                std::cmp::Ordering::Equal => {
+                    let next_time = if mid_idx < lsb_indxs_of_num_tmstmp_vals_on_tmln.len() - 1 {
+                        Some(
+                            self.time_and_num_val_at_event_idx(
+                                mid_idx + 1,
+                                tmstmps_encoded_as_u8s,
+                            )?
+                            .0,
+                        )
+                    } else {
+                        None
+                    };
+                    return Ok(QueryResult {
+                        current: Some((curr_time, curr_val)),
+                        next: next_time,
+                    });
+                }
+                std::cmp::Ordering::Greater => {
+                    upper_idx = mid_idx - 1;
+                }
+            }
+        }
+
+        let (left_time, left_val) =
+            self.time_and_num_val_at_event_idx(lower_idx - 1, tmstmps_encoded_as_u8s)?;
+        let (right_time, _) =
+            self.time_and_num_val_at_event_idx(lower_idx, tmstmps_encoded_as_u8s)?;
+
+        let ordered_left = left_time < *desired_time;
+        let ordered_right = *desired_time < right_time;
+        if !(ordered_left && ordered_right) {
+            return Err(SignalErrors::OrderingFailure {
+                lhs_time: left_time,
+                mid_time: desired_time.clone(),
+                rhs_time: right_time,
+            });
+        }
+
+        return Ok(QueryResult {
+            current: Some((left_time, left_val)),
+            next: Some(right_time),
+        });
+    }
+}

src/vcd/types.rs

@@ -1,144 +1,144 @@
-use chrono::prelude::*;
+// use crate::Signal;
 
-#[derive(Debug)]
+// Copyright (C) 2022 Yehowshua Immanuel
-pub(super) struct Version(pub String);
+// This program is distributed under both the GPLV3 license
+// and the YEHOWSHUA license, both of which can be found at
+// the root of the folder containing the sources for this program.
+use super::signal::{Signal, SignalEnum};
+use chrono::prelude::{DateTime, Utc};
+use num::BigUint;
+use std::fmt;
 
-#[derive(Debug)]
+#[derive(Debug, Clone)]
-pub(super) enum Timescale {fs, ps, ns, us, ms, s, unit}
+pub struct Version(pub String);
 
-#[derive(Debug)]
+#[derive(Debug, Clone, Copy, Eq, PartialEq)]
-pub(super) struct Metadata {
+pub enum Timescale {
-    pub(super) date      : Option<DateTime<Utc>>,
+    Fs,
-    pub(super) version   : Option<Version>,
+    Ps,
-    pub(super) timescale : (Option<u32>, Timescale)}
+    Ns,
+    Us,
+    Ms,
+    S,
+    Unit,
+}
 
-#[derive(Debug, Copy, Clone)]
+impl fmt::Display for Timescale {
-pub(super) struct Scope_Idx(pub(super) usize);
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
-
+        match self {
-#[derive(Debug, Copy, Clone)]
+            Timescale::Fs => write!(f, "fs"),
-pub(super) struct Signal_Idx(pub(super) usize);
+            Timescale::Ps => write!(f, "ps"),
-
+            Timescale::Ns => write!(f, "ns"),
-#[derive(Debug, Copy, Clone)]
+            Timescale::Us => write!(f, "μs"),
-pub(super) struct TimelineIdx(pub(super) u32);
+            Timescale::Ms => write!(f, "ms"),
-
+            Timescale::S => write!(f, "s"),
-#[derive(Debug, Copy, Clone)]
+            Timescale::Unit => write!(f, "unit"),
-pub struct StartIdx(pub(super) u32);
+        }
-
+    }
-#[derive(Debug)]
-pub(super) enum Sig_Type {Integer, Parameter, Real, Reg, Str, Wire, Tri1, Time}
-
-#[derive(Debug)]
-pub(super) enum Signal{
-    Data{
-         name             : String,
-         sig_type         : Sig_Type,
-         // I've seen a 0 bit signal parameter in a xilinx
-         // simulation before that gets assigned 1 bit values.
-         // I consider this to be bad behavior. We capture such
-         // errors in the following type.
-         signal_error     : Option<String>,
-         num_bits         : Option<usize>,
-         // TODO : may be able to remove self_idx
-         self_idx         : Signal_Idx,
-         // we could encounter a mix of pure values and strings
-         // for the same signal timeline
-         u8_timeline             : Vec<u8>,
-         u8_timeline_markers     : Vec<(TimelineIdx)>,
-         string_timeline         : Vec<String>,
-         string_timeline_markers : Vec<(TimelineIdx)>,
-         scope_parent : Scope_Idx},
-    Alias{
-         name         : String,
-         signal_alias : Signal_Idx}
 }
 
+#[derive(Debug)]
+pub struct Metadata {
+    pub date: Option<DateTime<Utc>>,
+    pub version: Option<Version>,
+    pub timescale: (Option<u32>, Timescale),
+}
+
+// We do a lot of arena allocation in this codebase.
+#[derive(Debug, Copy, Clone, PartialEq, Eq, Hash, PartialOrd, Ord)]
+pub struct ScopeIdx(pub usize);
+
+#[derive(Debug, Copy, Clone, PartialEq, Eq, Hash, PartialOrd, Ord)]
+pub struct SignalIdx(pub usize);
+
 #[derive(Debug)]
 pub(super) struct Scope {
-    pub(super) name          : String,
+    pub(super) name: String,
 
-    pub(super) parent_idx    : Option<Scope_Idx>,
+    pub(super) self_idx: ScopeIdx,
-    pub(super) self_idx      : Scope_Idx,
 
-    pub(super) child_signals : Vec<Signal_Idx>,
+    pub(super) child_signals: Vec<SignalIdx>,
-    pub(super) child_scopes  : Vec<Scope_Idx>}
+    pub(super) child_scopes: Vec<ScopeIdx>,
+}
 
-
-// TODO: document how timeline is represented
 #[derive(Debug)]
 pub struct VCD {
-    pub(super) metadata    : Metadata,
+    pub metadata: Metadata,
-    pub timeline           : Vec<u8>,
+    // Since we only need to store values when there is an actual change
-    pub timeline_markers   : Vec<StartIdx>,
+    // in the timeline, we keep a vector that stores the time at which an
-    pub(super) all_signals : Vec<Signal>,
+    // event occurs. Time t is always stored/encoded as the minimum length sequence
-    pub(super) all_scopes  : Vec<Scope>,
+    // of u8.
-    pub(super) scope_roots : Vec<Scope_Idx>}
+    // We essentially fill ``tmstmps_encoded_as_u8s`` with BigUints converted
+    // to sequences of little endian u8s.
+    // It is up to the signals to keep track of the start/stop indices in the
+    // vector of u8s that constitute a timestamp value. Signals don't have to
+    // keep track of all timestamp values, a given signal only needs to keep
+    // track of the timestamps at which the given signal value changes.
+    pub(super) tmstmps_encoded_as_u8s: Vec<u8>,
+    pub(super) all_signals: Vec<SignalEnum>,
+    pub(super) all_scopes: Vec<Scope>,
+    pub(super) root_scopes: Vec<ScopeIdx>,
+    pub(super) largest_timestamp: Option<BigUint>,
+}
 
 impl VCD {
-    // TODO : make this a generic traversal function that applies specified 
+    pub fn root_scopes_by_idx(&self) -> Vec<ScopeIdx> {
-    // functions upon encountering scopes and signals
+        self.root_scopes.clone()
-    fn print_scope_tree(
-        &self,
-        root_scope_idx : Scope_Idx,
-        depth : usize)
-    {
-        let all_scopes  = &self.all_scopes;
-        let all_signals = &self.all_signals;
-
-        let indent = " ".repeat(depth * 4);
-        let Scope_Idx(root_scope_idx) = root_scope_idx;
-        let root_scope = &all_scopes[root_scope_idx];
-        let root_scope_name = &root_scope.name;
-
-        println!("{indent}scope: {root_scope_name}");
-
-        for Signal_Idx(ref signal_idx) in &root_scope.child_signals {
-            let child_signal = &all_signals[*signal_idx];
-            let name = match child_signal {
-                Signal::Data{name, ..} => {name}
-                Signal::Alias{name, ..} => {name}
-            };
-            println!("{indent} - sig: {name}")
-        }
-        println!();
-
-        for scope_idx in &root_scope.child_scopes {
-            self.print_scope_tree(*scope_idx, depth+1);
-        }
-
     }
+    pub fn child_scopes_by_idx(&self, scope_idx: ScopeIdx) -> Vec<ScopeIdx> {
+        let ScopeIdx(idx) = scope_idx;
+        let scope = &self.all_scopes[idx];
+        scope.child_scopes.clone()
+    }
+    pub fn get_children_signal_idxs(&self, scope_idx: ScopeIdx) -> Vec<SignalIdx> {
+        let ScopeIdx(idx) = scope_idx;
+        let scope = &self.all_scopes[idx];
+        scope.child_signals.clone()
+    }
+    pub fn scope_name_by_idx(&self, scope_idx: ScopeIdx) -> &String {
+        let ScopeIdx(idx) = scope_idx;
+        let scope = &self.all_scopes[idx];
+        &scope.name
+    }
+    pub fn signal_from_signal_idx(&self, idx: SignalIdx) -> Signal<'_> {
+        let SignalIdx(idx) = idx;
+        let signal_enum = &self.all_signals[idx];
+        return Signal(signal_enum);
+    }
+    /// We take in a Signal and attempt to de-alias that signal if it is of
+    /// variant ``Signal::Alias``. If it is of variant ``Signal::Alias`` and points to
+    /// another alias, that's an error. Otherwise, we return the ``Signal::Data``
+    /// pointed to by the ``Signal::Alias``.
+    /// If the Signal is of varint ``Signal::Data``, then that can be returned directly.
+    pub(super) fn dealiasing_signal_idx_to_signal_lookup_mut<'a>(
+        &'a mut self,
+        idx: &SignalIdx,
+    ) -> Result<&'a mut SignalEnum, String> {
+        // get the signal pointed to be SignalIdx from the arena
+        let SignalIdx(idx) = idx;
+        let signal = &self.all_signals[*idx];
 
-    pub fn print_scopes(&self) {
+        // dereference signal if Signal::Alias, or keep idx if Signal::Data
-        for scope_root in &self.scope_roots {
+        let signal_idx = match signal {
-            self.print_scope_tree(*scope_root, 0);
+            SignalEnum::Data { self_idx, .. } => *self_idx,
+            SignalEnum::Alias { signal_alias, .. } => *signal_alias,
+        };
+
+        // Should now  point to Signal::Data variant, or else there's an error
+        let SignalIdx(idx) = signal_idx;
+        let signal = self.all_signals.get_mut(idx).unwrap();
+        match signal {
+            SignalEnum::Data { .. } => Ok(signal),
+            SignalEnum::Alias { .. } => Err(format!(
+                "Error near {}:{}. A signal alias shouldn't \
+                 point to a signal alias.",
+                file!(),
+                line!()
+            )),
         }
     }
 
-    pub fn print_longest_signal(&self) {
+    pub fn max_timestamp(&self) -> &Option<BigUint> {
-        let mut idx = 0usize;
+        &self.largest_timestamp
-        let mut max_len = 0usize;
-        let mut signal_name = String::new();
-
-        for signal in &self.all_signals {
-            match signal {
-                Signal::Alias {..} => {}
-                Signal::Data { 
-                    name, 
-                    sig_type, 
-                    num_bits, 
-                    self_idx, 
-                    u8_timeline, 
-                    .. } => {
-                        if u8_timeline.len() > max_len {
-                            max_len = u8_timeline.len();
-                            let Signal_Idx(idx_usize) = self_idx;
-                            idx = *idx_usize;
-                            signal_name = name.clone();
-                        }
-
-                    }
-            }
-        }
-
-        dbg!((idx, max_len, signal_name));
     }
-}
+}

src/vcd/utilities.rs

@@ -0,0 +1,86 @@
+// Copyright (C) 2022 Yehowshua Immanuel
+// This program is distributed under both the GPLV3 license
+// and the YEHOWSHUA license, both of which can be found at
+// the root of the folder containing the sources for this program.
+#[derive(Debug)]
+pub(super) enum BinaryParserErrTypes {
+    XValue,
+    ZValue,
+    UValue,
+    HValue,
+    LValue,
+    DashValue,
+    WValue,
+    OtherValue(char),
+    TooLong,
+}
+
+// We build a quick and not so dirty bit string parser.
+fn base2_str_to_byte(word: &[u8]) -> Result<u8, BinaryParserErrTypes> {
+    let mut val = 0u8;
+
+    // shouldn't have more than 8 chars in str
+    let len = word.len();
+    if len > 8 {
+        return Err(BinaryParserErrTypes::TooLong);
+    }
+
+    let bit_lut = [
+        0b0000_0001u8,
+        0b0000_0010u8,
+        0b0000_0100u8,
+        0b0000_1000u8,
+        0b0001_0000u8,
+        0b0010_0000u8,
+        0b0100_0000u8,
+        0b1000_0000u8,
+    ];
+
+    for (idx, chr) in word.iter().rev().enumerate() {
+        match chr {
+            b'1' => val |= bit_lut[idx],
+            b'0' => {}
+            b'x' | b'X' => return Err(BinaryParserErrTypes::XValue),
+            b'z' | b'Z' => return Err(BinaryParserErrTypes::ZValue),
+            b'u' | b'U' => return Err(BinaryParserErrTypes::UValue),
+            b'l' | b'L' => return Err(BinaryParserErrTypes::LValue),
+            b'h' | b'H' => return Err(BinaryParserErrTypes::HValue),
+            b'w' | b'W' => return Err(BinaryParserErrTypes::WValue),
+            b'-' => return Err(BinaryParserErrTypes::DashValue),
+            _ => return Err(BinaryParserErrTypes::OtherValue(*chr as char)),
+        }
+    }
+
+    Ok(val)
+}
+
+pub(super) fn binary_str_to_vec_u8(binary_str: &str) -> Result<Vec<u8>, BinaryParserErrTypes> {
+    let mut vec_u8: Vec<u8> = Vec::new();
+    let binary_str_as_bytes = binary_str.as_bytes();
+
+    let mut tail_idx = binary_str_as_bytes.len();
+    // clamp head if provided binary str is less than 8 long
+    let mut head_idx = if tail_idx >= 8 {
+        binary_str_as_bytes.len() - 8
+    } else {
+        0
+    };
+    while tail_idx > 0 {
+        let curr_b_val = &binary_str_as_bytes[head_idx..tail_idx];
+        let val_u8 = base2_str_to_byte(curr_b_val)?;
+        vec_u8.push(val_u8);
+
+        if head_idx < 8 {
+            head_idx = 0
+        } else {
+            head_idx -= 8;
+        }
+
+        if tail_idx < 8 {
+            tail_idx = 0
+        } else {
+            tail_idx -= 8;
+        }
+    }
+    Ok(vec_u8)
+}

tests/files.rs

@@ -0,0 +1,77 @@
+// Copyright (C) 2022 Yehowshua Immanuel
+// This program is distributed under both the GPLV3 license
+// and the YEHOWSHUA license, both of which can be found at
+// the root of the folder containing the sources for this program.
+
+// TODO: we should eventually be able to only test on just
+// the files const
+pub const FILES: [&str; 31] = [
+    "./tests/vcd-files/aldec/SPI_Write.vcd",
+    "./tests/vcd-files/ghdl/alu.vcd",
+    "./tests/vcd-files/ghdl/idea.vcd",
+    "./tests/vcd-files/ghdl/pcpu.vcd",
+    "./tests/vcd-files/gtkwave-analyzer/perm_current.vcd",
+    "./tests/vcd-files/icarus/CPU.vcd",
+    "./tests/vcd-files/icarus/rv32_soc_TB.vcd",
+    "./tests/vcd-files/icarus/test1.vcd",
+    "./tests/vcd-files/model-sim/CPU_Design.msim.vcd",
+    "./tests/vcd-files/model-sim/clkdiv2n_tb.vcd",
+    "./tests/vcd-files/my-hdl/Simple_Memory.vcd",
+    "./tests/vcd-files/my-hdl/sigmoid_tb.vcd",
+    "./tests/vcd-files/my-hdl/top.vcd",
+    "./tests/vcd-files/ncsim/ffdiv_32bit_tb.vcd",
+    "./tests/vcd-files/quartus/mipsHardware.vcd",
+    "./tests/vcd-files/quartus/wave_registradores.vcd",
+    "./tests/vcd-files/questa-sim/dump.vcd",
+    "./tests/vcd-files/questa-sim/test.vcd",
+    "./tests/vcd-files/riviera-pro/dump.vcd",
+    "./tests/vcd-files/systemc/waveform.vcd",
+    "./tests/vcd-files/treadle/GCD.vcd",
+    "./tests/vcd-files/vcs/Apb_slave_uvm_new.vcd",
+    "./tests/vcd-files/vcs/datapath_log.vcd",
+    "./tests/vcd-files/vcs/processor.vcd",
+    "./tests/vcd-files/verilator/swerv1.vcd",
+    "./tests/vcd-files/verilator/vlt_dump.vcd",
+    "./tests/vcd-files/vivado/iladata.vcd",
+    "./tests/vcd-files/xilinx_isim/test.vcd",
+    "./tests/vcd-files/xilinx_isim/test1.vcd",
+    // TODO : add signal ignore list to handle bitwidth mismatches
+    "./tests/vcd-files/xilinx_isim/test2x2_regex22_string1.vcd",
+    "./tests/vcd-files/scope_with_comment.vcd",
+];
+
+pub const GOOD_DATE_FILES: [&str; 24] = [
+    "./test-vcd-files/aldec/SPI_Write.vcd",
+    "./test-vcd-files/ghdl/alu.vcd",
+    "./test-vcd-files/ghdl/idea.vcd",
+    "./test-vcd-files/ghdl/pcpu.vcd",
+    "./test-vcd-files/gtkwave-analyzer/perm_current.vcd",
+    "./test-vcd-files/icarus/CPU.vcd",
+    "./test-vcd-files/icarus/rv32_soc_TB.vcd",
+    "./test-vcd-files/icarus/test1.vcd",
+    "./test-vcd-files/model-sim/CPU_Design.msim.vcd",
+    "./test-vcd-files/model-sim/clkdiv2n_tb.vcd",
+    "./test-vcd-files/my-hdl/Simple_Memory.vcd",
+    "./test-vcd-files/my-hdl/sigmoid_tb.vcd",
+    "./test-vcd-files/my-hdl/top.vcd",
+    "./test-vcd-files/questa-sim/dump.vcd",
+    "./test-vcd-files/questa-sim/test.vcd",
+    "./test-vcd-files/riviera-pro/dump.vcd",
+    "./test-vcd-files/vcs/Apb_slave_uvm_new.vcd",
+    "./test-vcd-files/vcs/datapath_log.vcd",
+    "./test-vcd-files/vcs/processor.vcd",
+    "./test-vcd-files/verilator/swerv1.vcd",
+    "./test-vcd-files/verilator/vlt_dump.vcd",
+    "./test-vcd-files/xilinx_isim/test.vcd",
+    "./test-vcd-files/xilinx_isim/test1.vcd",
+    "./test-vcd-files/xilinx_isim/test2x2_regex22_string1.vcd",
+];
+
+pub const BAD_DATE_FILES: [&str; 6] = [
+    "./test-vcd-files/ncsim/ffdiv_32bit_tb.vcd",
+    "./test-vcd-files/quartus/mipsHardware.vcd",
+    "./test-vcd-files/quartus/wave_registradores.vcd",
+    "./test-vcd-files/systemc/waveform.vcd",
+    "./test-vcd-files/treadle/GCD.vcd",
+    "./test-vcd-files/vivado/iladata.vcd",
+];

tests/integration_test.rs

@@ -0,0 +1,22 @@
+// Copyright (C) 2022 Yehowshua Immanuel
+// This program is distributed under both the GPLV3 license
+// and the YEHOWSHUA license, both of which can be found at
+// the root of the folder containing the sources for this program.
+use std::fs::File;
+
+mod files;
+use files::*;
+
+#[test]
+fn parse_all_VCDs() {
+    // see if we can parse all signal trees successfully
+    for file_name in FILES {
+        let file = File::open(file_name).unwrap();
+        let vcd = fastwave_backend::parse_vcd(file);
+
+        if !vcd.is_ok() {
+            dbg!(file_name);
+            vcd.unwrap();
+        }
+    }
+}

tests/vcd-files/VCD_file_with_errors.vcd

@@ -0,0 +1,92 @@
+$date
+Thu Dec 17 17:19:03 2020
+$end
+$version
+Aldec HDL Simulator Version 10.03.3558
+$end
+$timescale
+1 ps
+$end
+
+$scope module tb $end
+
+$scope module t $end
+$var wire 1 ! CLK $end
+$var wire 1 " LED $end
+$var wire 1 # PIN_10 $end
+$var wire 1 $ PIN_11 $end
+$var wire 1 % PIN_12 $end
+$var wire 1 & PIN_13 $end
+$var wire 1 ' SPI_In $end
+$var wire 1 ( SPI_Out $end
+$var wire 1 ) SPI_Data_Available $end
+$var wire 1 * RegMap_In $end
+$var wire 1 + RegMap_Out $end
+$var wire 1 , RegMap_Data_Available $end
+$var wire 8 - AddrBus [7:0] $end
+$var wire 8 . DataBus [7:0] $end
+
+$scope module controller $end
+$var wire 1 ! clk $end
+$var wire 1 " LED $end
+$var wire 8 . DataBus [7:0] $end
+$var wire 1 ) SPI_Data_Available $end
+$var wire 1 , RegMap_Data_available $end
+$var wire 8 / addr [7:0] $end
+$var wire 8 0 data [7:0] $end
+$var wire 1 1 BusActive $end
+$var reg 8 2 AddrBus [7:0] $end
+$var reg 1 3 SPI_In $end
+$var reg 1 4 SPI_Out $end
+$var reg 1 5 RegMap_In $end
+$var reg 1 6 RegMap_Out $end
+$var reg 1 7 LED_state $end
+$var reg 3 8 block [2:0] $end
+$var reg 3 9 doing [2:0] $end
+$var parameter 3 : IDLE $end
+$var parameter 3 ; READ_ADDR $end
+$var parameter 3 < READ_DATA $end
+$var parameter 3 = TX $end
+$var parameter 3 > SPI $end
+$upscope $end
+
+
+$scope module reg_mag_i $end
+$var wire 1 ! clk $end
+$var wire 1 + RegMap_Out $end
+$var wire 1 * RegMap_In $end
+$var wire 8 - AddrBus [7:0] $end
+$var wire 8 . DataBus [7:0] $end
+$var wire 1 ? r_w $end
+$var wire 1 @ outputData $end
+$var wire 1 A inputData $end
+$var reg 1 B RegMap_Data_Available $end
+$var reg 8 C inData [7:0] $end
+$var reg 8 D inAddr [7:0] $end
+$var reg 8 E outData [7:0] $end
+$var reg 1 F addr_rcv $end
+$var reg 1 G data_rcv $end
+$var reg 2 H state [1:0] $end
+$var parameter 2 I INIT $end
+$var parameter 2 J IDLE $end
+$var parameter 2 K RX $end
+$var parameter 2 L TX $end
+$var parameter 32 M MAXADDRESS $end
+$upscope $end
+
+
+$scope module SPI_i $end
+$var wire 1 ! clk $end
+$var wire 1 # SCK $end
+$var wire 1 $ SSEL $end
+$var wire 1 % MOSI $end
+$var wire 1 & MISO $end
+$var wire 1 ' SPI_In $end
+$var wire 1 ( SPI_Out $end
+$var wire 8 - AddrBus [7:0] $end
+$var wire 8 . DataBus [7:0] $end
+$var wire 1 N SCK_risingedge $end
+$var wire 1 O SCK_fallingedge $end
+$var wire 1 P SSEL_active $end
+$var wire 1 Q MOSI_data $end
+$var reg 1 R SPI_Data_Available $end

tests/vcd-files/scope_with_comment.vcd

@@ -0,0 +1,296 @@
+$date
+	Sat Dec 26 15:33:14 2020
+$end
+$version
+	ModelSim Version 10.5b
+$end
+$timescale
+	1ns
+$end
+
+$scope module clkdiv2n_tb $end
+$comment foo $end
+$var reg 1 ! clk $end
+$var reg 1 " reset $end
+$var wire 1 # clk_out $end
+
+$scope module t1 $end
+$var parameter 32 $ WIDTH $end
+$var parameter 32 % N $end
+$var wire 1 & clk $end
+$var wire 1 ' reset $end
+$var wire 1 # clk_out $end
+$var reg 3 ( r_reg [2:0] $end
+$var wire 1 ) r_nxt [2] $end
+$var wire 1 * r_nxt [1] $end
+$var wire 1 + r_nxt [0] $end
+$var reg 1 , clk_track $end
+$upscope $end
+$comment foo $end
+$upscope $end
+$comment foo $end
+$enddefinitions $end
+#0
+$comment foo $end
+$dumpvars
+0!
+x"
+bx (
+x,
+b11 $
+b110 %
+x#
+x+
+x*
+x)
+x'
+0&
+$end
+#5
+1"
+1'
+b0 (
+0,
+1+
+0*
+0)
+0#
+#10
+1!
+1&
+#15
+0"
+0'
+#20
+0!
+0&
+#30
+1!
+1&
+b1 (
+0+
+1*
+#40
+0!
+0&
+#50
+1!
+1&
+b10 (
+1+
+#60
+0!
+0&
+#70
+1!
+1&
+b11 (
+0+
+0*
+1)
+#80
+0!
+0&
+#90
+1!
+1&
+b100 (
+1+
+#100
+0!
+0&
+#110
+1!
+1&
+b101 (
+0+
+1*
+#120
+0!
+0&
+#130
+1!
+1&
+b0 (
+1,
+1+
+0*
+0)
+1#
+#140
+0!
+0&
+#150
+1!
+1&
+b1 (
+0+
+1*
+#160
+0!
+0&
+#170
+1!
+1&
+b10 (
+1+
+#180
+0!
+0&
+#190
+1!
+1&
+b11 (
+0+
+0*
+1)
+#200
+0!
+0&
+#210
+1!
+1&
+b100 (
+1+
+#220
+0!
+0&
+#230
+1!
+1&
+b101 (
+0+
+1*
+#240
+0!
+0&
+#250
+1!
+1&
+b0 (
+0,
+1+
+0*
+0)
+0#
+#260
+0!
+0&
+#270
+1!
+1&
+b1 (
+0+
+1*
+#280
+0!
+0&
+#290
+1!
+1&
+b10 (
+1+
+#300
+0!
+0&
+#310
+1!
+1&
+b11 (
+0+
+0*
+1)
+#320
+0!
+0&
+#330
+1!
+1&
+b100 (
+1+
+#340
+0!
+0&
+#350
+1!
+1&
+b101 (
+0+
+1*
+#360
+0!
+0&
+#370
+1!
+1&
+b0 (
+1,
+1+
+0*
+0)
+1#
+#380
+0!
+0&
+#390
+1!
+1&
+b1 (
+0+
+1*
+#400
+0!
+0&
+#410
+1!
+1&
+b10 (
+1+
+#420
+0!
+0&
+#430
+1!
+1&
+b11 (
+0+
+0*
+1)
+#440
+0!
+0&
+#450
+1!
+1&
+b100 (
+1+
+#460
+0!
+0&
+#470
+1!
+1&
+b101 (
+0+
+1*
+#480
+0!
+0&
+#490
+1!
+1&
+b0 (
+0,
+1+
+0*
+0)
+0#
+#500
+0!
+0&
+#510
+1!
+1&
+b1 (
+0+
+1*