diff --git a/Cargo.toml b/Cargo.toml index 0b4dd2c..5664131 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -1,5 +1,5 @@ [package] -name = "fastwave_backend" +name = "fastwave" version = "0.1.0" edition = "2021" @@ -10,7 +10,7 @@ debug = 1 [dependencies] num = "0.4" -clap = { version = "4.4.6", features = ["derive"] } +clap = { version = "3.1.8", features = ["derive"] } chrono = "0.4" -# TODO : remove itertools once date parser is reworked. -itertools = "0.11" +itertools = "0.10.3" +backtrace = "0.3" \ No newline at end of file diff --git a/LICENSE-GPLV3 b/LICENSE similarity index 100% rename from LICENSE-GPLV3 rename to LICENSE diff --git a/LICENSE-YEHOWSHUA b/LICENSE-YEHOWSHUA deleted file mode 100644 index 180914d..0000000 --- a/LICENSE-YEHOWSHUA +++ /dev/null @@ -1,2 +0,0 @@ -This codebase is also licensed to Yehowshua Immanuel to use -in any manner Yehowshua Immanuel sees fit. \ No newline at end of file diff --git a/README.md b/README.md index 7890a1e..b673f0e 100644 --- a/README.md +++ b/README.md @@ -1,131 +1,48 @@ -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: -image +Copyright - Yehowshua Immanuel # A High performance, VCD Parser written in Rust -I hope for a GUI that eventually looks like the following... - -![](assets/FastWaveMockup.png) - -# 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 Features + - 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 + offers highly robust error handling which GTKWave doesn't have. # 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. -1. ``cargo run --release --example parse_vcd tests/vcd-files/aldec/SPI_Write.vcd`` -2. ``cargo run --release --example vcd`` +``cargo run --release test-vcd-files/aldec/SPI_Write.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 and Other - - [ ] 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 +## Features + - [ ] move parse_orphaned_vars to scopes.rs - [ ] Print out git commit or release number. - - [ ] do a read through all the code - look for uneeded code - - [ ] Move part of the performance section to another markdown file. + - [ ] Should be able to load waveform whilst viewing it live. + - could be quite challenging to implement for various reasons + - [ ] 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 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 + - [ ] Change error messages to line and filenames. Go through all calls to ``format!`` whilst also keeping performance in mind. ## Marketing - - [ ] Send survey to community + - [ ] Send survey to community channel. \ No newline at end of file diff --git a/assets/FastWaveMockup.png b/assets/FastWaveMockup.png deleted file mode 100644 index fbf030b..0000000 Binary files a/assets/FastWaveMockup.png and /dev/null differ diff --git a/examples/parse_vcd.rs b/examples/parse_vcd.rs deleted file mode 100644 index b1478c3..0000000 --- a/examples/parse_vcd.rs +++ /dev/null @@ -1,33 +0,0 @@ -// 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(()) -} diff --git a/examples/vcd.rs b/examples/vcd.rs deleted file mode 100644 index eb6b660..0000000 --- a/examples/vcd.rs +++ /dev/null @@ -1,81 +0,0 @@ -// 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(()) -} diff --git a/src/lib.rs b/src/lib.rs deleted file mode 100644 index 6bdb055..0000000 --- a/src/lib.rs +++ /dev/null @@ -1,12 +0,0 @@ -// 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; diff --git a/src/main.rs b/src/main.rs new file mode 100644 index 0000000..aab1585 --- /dev/null +++ b/src/main.rs @@ -0,0 +1,39 @@ +use std::{fs::File}; +use clap::Parser; + +pub mod 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(()) +} \ No newline at end of file diff --git a/src/test.rs b/src/test.rs new file mode 100644 index 0000000..18214a1 --- /dev/null +++ b/src/test.rs @@ -0,0 +1,2 @@ +mod files; +pub use files::*; \ No newline at end of file diff --git a/src/test/files.rs b/src/test/files.rs new file mode 100644 index 0000000..375de49 --- /dev/null +++ b/src/test/files.rs @@ -0,0 +1,71 @@ +// 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", +]; \ No newline at end of file diff --git a/src/vcd.rs b/src/vcd.rs index 53641e1..19f1a6c 100644 --- a/src/vcd.rs +++ b/src/vcd.rs @@ -1,10 +1,8 @@ -// 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(crate) mod signal; -pub(crate) mod types; -mod utilities; +pub use reader::*; + +mod types; +pub use types::*; + +mod parse; +pub use parse::*; \ No newline at end of file diff --git a/src/vcd/parse.rs b/src/vcd/parse.rs index 7ff2f89..320f8bb 100644 --- a/src/vcd/parse.rs +++ b/src/vcd/parse.rs @@ -1,35 +1,99 @@ -// 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 std::collections::HashMap; +use num::BigInt; + +use super::*; mod combinator_atoms; -mod events; -mod metadata; -mod scopes; +use combinator_atoms::*; + mod types; +use types::*; -pub fn parse_vcd(file: impl std::io::Read) -> Result { - let mut word_gen = super::reader::WordReader::new(file); +mod metadata; +use metadata::*; - let header = metadata::parse_metadata(&mut word_gen)?; +mod scopes; +use scopes::*; - // later, we'll need to map parsed ascii symbols to their +mod events; +use events::*; + +pub fn parse_vcd(file : File) -> Result { + 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 the VCD object - let mut vcd = super::types::VCD { - metadata: header, - tmstmps_encoded_as_u8s: vec![], - all_signals: vec![], - all_scopes: vec![], - root_scopes: vec![], - largest_timestamp: None, + let mut vcd = VCD{ + metadata : header, + timeline : vec![], + timeline_markers : vec![], + all_signals : vec![], + all_scopes : vec![], + scope_roots : vec![], }; - scopes::parse_scopes(&mut word_gen, &mut vcd, &mut signal_map)?; - events::parse_events(&mut word_gen, &mut vcd, &mut signal_map)?; + parse_scopes(&mut word_gen, &mut vcd, &mut signal_map)?; + 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()); + } + + } +} \ No newline at end of file diff --git a/src/vcd/parse/combinator_atoms.rs b/src/vcd/parse/combinator_atoms.rs index d2f9bf9..db77e94 100644 --- a/src/vcd/parse/combinator_atoms.rs +++ b/src/vcd/parse/combinator_atoms.rs @@ -1,83 +1,88 @@ -// 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 { - let zero = b'0'; - let nine = b'9'; +pub(super) fn digit(chr : u8) -> bool { + let zero = b'0' as u8; + let nine = b'9' as u8; - (chr >= zero) && (nine >= chr) + let between_zero_and_nine = (chr >= zero) && (nine >= chr); + + return between_zero_and_nine } -pub(super) fn take_until(word: &str, pattern: u8) -> ParseResult<'_> { - let mut new_start = 0; +pub(super) fn take_until<'a>(word : &'a str, pattern : u8) -> ParseResult<'a> { + let mut new_start = 0; for chr in word.as_bytes() { if *chr == pattern { - break; - } else { + break + } + else { new_start += 1; } } - ParseResult { - matched: &word[0..new_start], - residual: &word[new_start..], - } + return + ParseResult{ + matched : &word[0..new_start], + residual : &word[new_start..] + }; + } -pub(super) fn take_while(word: &str, cond: fn(u8) -> bool) -> ParseResult<'_> { - let mut new_start = 0; +pub(super) fn take_while<'a>(word : &'a str, cond : fn(u8) -> bool) -> ParseResult<'a> { + let mut new_start = 0; for chr in word.as_bytes() { if cond(*chr) { new_start += 1; - } else { - break; + } + else { + break } } - ParseResult { - matched: &word[0..new_start], - residual: &word[new_start..], - } + return + ParseResult{ + matched : &word[0..new_start], + residual : &word[new_start..] + }; + } -pub(super) fn tag<'a>(word: &'a str, pattern: &'a str) -> ParseResult<'a> { - let lhs = word.as_bytes().iter(); - let rhs = pattern.as_bytes(); - let iter = lhs.zip(rhs); +pub(super) fn tag<'a>(word : &'a str, pattern : &'a str) -> ParseResult<'a> { + let lhs = word.as_bytes().iter(); + let rhs = pattern.as_bytes(); + 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; } - ParseResult { - matched: &word[0..new_start], - residual: &word[new_start..], - } + return + ParseResult{ + matched : &word[0..new_start], + residual : &word[new_start..] + }; } -pub(super) fn ident( - word_reader: &mut WordReader, - keyword: &str, +pub(super) fn ident( + word_reader : &mut WordReader, + keyword : &str, ) -> Result<(), String> { // let keyword = "module"; - let (word, cursor) = next_word!(word_reader)?; + + let (word, cursor) = word_reader.next_word()?; if word == keyword { - Ok(()) - } else { - let err = format!("found keyword `{word}` but expected `{keyword}` on {cursor:?}"); - Err(err) + return Ok(()) } -} + else { + let err = format!("found keyword `{word}` but expected `{keyword}` on {cursor:?}"); + return Err(err) + } +} \ No newline at end of file diff --git a/src/vcd/parse/events.rs b/src/vcd/parse/events.rs index 3f42048..14bb81c 100644 --- a/src/vcd/parse/events.rs +++ b/src/vcd/parse/events.rs @@ -1,152 +1,177 @@ -// 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. +//! part of the vcd parser that handles parsing the signal tree and +//! building the resulting signal tree +use super::*; -use num::BigUint; -use std::collections::HashMap; +#[derive(Debug)] +pub(super) enum BinaryParserErrTypes {XValue, ZValue, UValue, OtherValue(char), TooLong} -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}; +// We build a quick and not so dirty bit string parser. +fn base2_str_to_byte(word : &[u8]) -> Result { + let mut val = 0u8; -pub(super) fn parse_events( - word_reader: &mut WordReader, - vcd: &mut VCD, - signal_map: &mut HashMap, + // 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] | val} + 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)} + _ => {return Err(BinaryParserErrTypes::OtherValue(*chr as char))} + } + + } + + Ok(val) +} + +fn binary_str_to_vec_u8(binary_str : &str) -> Result, BinaryParserErrTypes> { + let mut vec_u8 : Vec = 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 = head_idx - 8; + } + + if tail_idx < 8 { + tail_idx = 0 + } + else { + tail_idx = tail_idx - 8; + } + + } + Ok(vec_u8) +} + +pub(super) fn parse_events<'a>( + word_reader : &mut WordReader, + vcd : &'a mut VCD, + signal_map : &mut HashMap ) -> 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; - }; + if next_word.is_err() {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; - } + 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); + 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( + |_| 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 = u32::try_from(binary_value.len()).map_err(|_| { - format!( - "Error near {}:{}, {cursor:?}. \ - Found signal with more than 2^32 - 1 bits.", - file!(), - line!() - ) - })?; + let observed_num_bits = binary_value.len(); - let mut value_u8: Vec = Vec::new(); + let mut value_u8 : Vec = 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 + // 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 propagate up other errors. + // Or else, we 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(); - } + Ok(result) => {value_u8 = result;} + Err(BinaryParserErrTypes::XValue | + BinaryParserErrTypes::ZValue | + BinaryParserErrTypes::UValue + ) => + { + 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:?}.") - })?; + 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)?; + let (word, cursor) = word_reader.next_word().unwrap(); // 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 (f, l )= (file!(), line!()); + let SignalIdx(ref signal_idx) = signal_map.get(word).ok_or( + format!("Error near {f}:{l}. Failed to lookup signal {word} at {cursor:?}"))?; - let signal = vcd.dealiasing_signal_idx_to_signal_lookup_mut(signal_idx)?; + // 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 {signal_alias, ..} => { + let SignalIdx(ref signal_idx) = signal_alias; + signal_idx.clone() - 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; } + } + }; + + // 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, + 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 @@ -158,7 +183,7 @@ pub(super) fn parse_events( 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 \ + of sig_type {sig_type:?} is expected to be `{num_bits}` not \ `{observed_num_bits}`. \ This error occurred while parsing the vcd file at \ {cursor:?}"); @@ -168,58 +193,58 @@ pub(super) fn parse_events( } None => { let (f, l) = (file!(), line!()); - let msg = format!( - "\ + let msg = format!("\ Error near {f}:{l}. The bitwidth for signal {name} \ - must be specified for a signal of type {signal_type:?}. \ + must be specified for a signal of type {sig_type:?}. \ This error occurred while parsing the vcd file at \ - {cursor:?}" - ); + {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); + let (f, l )= (file!(), line!()); + let timeline_idx = u32::try_from(vcd.timeline.len()).map_err( + |_| format!("Error near {f}:{l}. Failed to convert from usize to u32."))?; + let timeline_idx = TimelineIdx(timeline_idx); - // value stuff - // we may need to zero extend values + if store_as_string { + string_timeline_markers.push(timeline_idx); + string_timeline.push(value_string); + Ok(()) + + } + else { + u8_timeline_markers.push(timeline_idx); + + let mut curr_num_bytes = value_u8.len(); + u8_timeline.append(&mut value_u8); + + // 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!() - ) - })?; + let num_bits = num_bits.unwrap(); + let bytes_required = (num_bits / 8) + + if (num_bits % 8) > 0 {1} else {0}; - 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); + // useful for debugging + // let err = format!("Error at {cursor:?}.\ + // num_bits = {num_bits}, \ + // observed_bits = {observed_num_bits}, \ + // curr_num_bytes = {curr_num_bytes}, \ + // bytes_required = {bytes_required} \ + // for signal {name}"); + // Err(err)?; + + u8_timeline.push(0u8); curr_num_bytes += 1; } Ok(()) } } - SignalEnum::Alias { .. } => { - let (f, l) = (file!(), line!()); + 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:?}"); @@ -232,32 +257,34 @@ pub(super) fn parse_events( "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 (f, l )= (file!(), line!()); + let SignalIdx(ref signal_idx) = signal_map.get(hash).ok_or( + format!("Error near {f}:{l}. Failed to lookup signal {hash} at {cursor:?}"))?; - let signal = vcd.dealiasing_signal_idx_to_signal_lookup_mut(signal_idx)?; + // 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 {signal_alias, ..} => { + let SignalIdx(ref signal_idx) = signal_alias; + signal_idx.clone() - 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; } + } + }; + + // 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, + 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` @@ -265,53 +292,38 @@ pub(super) fn parse_events( Some(ref num_bits) => { if *num_bits != 1 { let (f, l) = (file!(), line!()); - let msg = format!( - "\ + let msg = format!("\ Error near {f}:{l}. The bitwidth for signal {name} \ - of signal_type {signal_type:?} is expected to be `1` not \ + of sig_type {sig_type:?} is expected to be `1` not \ `{num_bits}`. \ This error occurred while parsing the vcd file at \ - {cursor:?}" - ); + {cursor:?}"); *signal_error = Some(msg); continue; } } None => { let (f, l) = (file!(), line!()); - let msg = format!( - "\ + let msg = format!("\ Error near {f}:{l}. The bitwidth for signal {name} \ - must be specified for a signal of type {signal_type:?}. \ + must be specified for a signal of type {sig_type:?}. \ This error occurred while parsing the vcd file at \ - {cursor:?}" - ); + {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; - } + let (f, l )= (file!(), line!()); + let timeline_idx = u32::try_from(vcd.timeline.len()).map_err( + |_| 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(()) } - SignalEnum::Alias { .. } => { - let (f, l) = (file!(), line!()); + 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:?}"); @@ -323,32 +335,34 @@ pub(super) fn parse_events( "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 (f, l )= (file!(), line!()); + let SignalIdx(ref signal_idx) = signal_map.get(hash).ok_or( + format!("Error near {f}:{l}. Failed to lookup signal {hash} at {cursor:?}"))?; - let signal = vcd.dealiasing_signal_idx_to_signal_lookup_mut(signal_idx)?; + // 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 {signal_alias, ..} => { + let SignalIdx(ref signal_idx) = signal_alias; + signal_idx.clone() - 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; } + } + }; + + // 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, + 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` @@ -356,53 +370,38 @@ pub(super) fn parse_events( Some(ref num_bits) => { if *num_bits != 1 { let (f, l) = (file!(), line!()); - let msg = format!( - "\ + let msg = format!("\ Error near {f}:{l}. The bitwidth for signal {name} \ - of signal_type {signal_type:?} is expected to be `1` not \ + of sig_type {sig_type:?} is expected to be `1` not \ `{num_bits}`. \ This error occurred while parsing the vcd file at \ - {cursor:?}" - ); + {cursor:?}"); *signal_error = Some(msg); continue; } } None => { let (f, l) = (file!(), line!()); - let msg = format!( - "\ + let msg = format!("\ Error near {f}:{l}. The bitwidth for signal {name} \ - must be specified for a signal of type {signal_type:?}. \ + must be specified for a signal of type {sig_type:?}. \ This error occurred while parsing the vcd file at \ - {cursor:?}" - ); + {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; - } + let (f, l )= (file!(), line!()); + let timeline_idx = u32::try_from(vcd.timeline.len()).map_err( + |_| 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(()) } - SignalEnum::Alias { .. } => { - let (f, l) = (file!(), line!()); + 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:?}"); @@ -410,38 +409,39 @@ pub(super) fn parse_events( } }?; } - // 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(); + "x" | "X" | "z" | "Z" | "u" | "U" => { + let val = word.to_string(); // 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 (f, l )= (file!(), line!()); + let SignalIdx(ref signal_idx) = signal_map.get(hash).ok_or( + format!("Error near {f}:{l}. Failed to lookup signal {hash} at {cursor:?}"))?; - let signal = vcd.dealiasing_signal_idx_to_signal_lookup_mut(signal_idx)?; + // 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 {signal_alias, ..} => { + let SignalIdx(ref signal_idx) = signal_alias; + signal_idx.clone() - 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; } + } + }; + + // 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, + 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` @@ -449,42 +449,38 @@ pub(super) fn parse_events( Some(ref num_bits) => { if *num_bits != 1 { let (f, l) = (file!(), line!()); - let msg = format!( - "\ + let msg = format!("\ Error near {f}:{l}. The bitwidth for signal {name} \ - of signal_type {signal_type:?} is expected to be `1` not \ + of sig_type {sig_type:?} is expected to be `1` not \ `{num_bits}`. \ This error occurred while parsing the vcd file at \ - {cursor:?}" - ); + {cursor:?}"); *signal_error = Some(msg); continue; } } None => { let (f, l) = (file!(), line!()); - let msg = format!( - "\ + let msg = format!("\ Error near {f}:{l}. The bitwidth for signal {name} \ - must be specified for a signal of type {signal_type:?}. \ + must be specified for a signal of type {sig_type:?}. \ This error occurred while parsing the vcd file at \ - {cursor:?}" - ); + {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); + let (f, l )= (file!(), line!()); + let timeline_idx = u32::try_from(vcd.timeline.len()).map_err( + |_| format!("Error near {f}:{l}. Failed to convert from usize to u32."))?; + let timeline_idx = TimelineIdx(timeline_idx); - // record value - string_vals.push(val); + string_timeline_markers.push(timeline_idx); + string_timeline.push(val); Ok(()) } - SignalEnum::Alias { .. } => { - let (f, l) = (file!(), line!()); + 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:?}"); @@ -492,55 +488,10 @@ pub(super) fn parse_events( } }?; } - // 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(()) -} +} \ No newline at end of file diff --git a/src/vcd/parse/metadata.rs b/src/vcd/parse/metadata.rs index 6e94a7c..7f62fcf 100644 --- a/src/vcd/parse/metadata.rs +++ b/src/vcd/parse/metadata.rs @@ -1,33 +1,26 @@ -// 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 chrono::prelude::*; use itertools::Itertools; -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; +use super::*; pub(super) fn parse_date( - word_and_ctx1: (&str, &Cursor), - word_and_ctx2: (&str, &Cursor), - word_and_ctx3: (&str, &Cursor), - word_and_ctx4: (&str, &Cursor), - word_and_ctx5: (&str, &Cursor), + word_and_ctx1 : (&str, &Cursor), + word_and_ctx2 : (&str, &Cursor), + word_and_ctx3 : (&str, &Cursor), + word_and_ctx4 : (&str, &Cursor), + word_and_ctx5 : (&str, &Cursor), ) -> Result, 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!("Error near {}:{}.", file!(), line!()); + 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() @@ -38,14 +31,16 @@ pub(super) fn parse_date( let (word, cursor) = word_and_ctx2; let months = [ - "Jan", "Feb", "Mar", "Apr", "May", "Jun", "Jul", "Aug", "Sept", "Oct", "Nov", "Dec", - ]; + "Jan", "Feb", "Mar", "Apr", + "May", "Jun", "Jul", "Aug", + "Sept", "Oct", "Nov", "Dec", + ]; if !months.contains(&word) { - let msg = format!("Error near {}:{}.", file!(), line!()); + 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() @@ -55,16 +50,17 @@ 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(e) => return Err(format!("Error near {}:{}. {e}", file!(), line!())), + Err(e) => {return Err(format!("Error near {}:{}. {e}", file!(), line!()))} }; if date > 31 { - let msg = format!("Error near {}:{}.", file!(), line!()); + 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() @@ -76,50 +72,45 @@ pub(super) fn parse_date( let res = take_until(word, b':'); res.assert_match()?; - let hh: u8 = res - .matched - .to_string() - .parse() - .map_err(|e| format!("Error near {}:{}. {e}", file!(), line!()))?; + let hh : u8 = res.matched.to_string() + .parse() + .map_err(|e| format!("Error near {}:{}. {e}", file!(), line!()))?; if hh > 23 { - let msg = format!("Error near {}:{}.", file!(), line!()); + 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() - .parse() - .map_err(|e| format!("Error near {}:{}. {e}", file!(), line!()))?; + let mm : u8 = res.matched.to_string() + .parse() + .map_err(|e| format!("Error near {}:{}. {e}", file!(), line!()))?; if mm > 60 { - let msg = format!("Error near {}:{}.", file!(), line!()); + 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() - .parse() - .map_err(|e| format!("Error near {}:{}. {e}", file!(), line!()))?; + let ss : u8 = residual.to_string() + .parse() + .map_err(|e| format!("Error near {}:{}. {e}", file!(), line!()))?; if ss > 60 { - let msg = format!("Error near {}:{}.", file!(), line!()); + 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()) }; @@ -130,119 +121,107 @@ pub(super) fn parse_date( 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 = DateTime::parse_from_str(full_date.as_str(), "%a %b %e %T %Y"); + let full_date = Utc.datetime_from_str(full_date.as_str(), "%a %b %e %T %Y"); if full_date.is_ok() { - return Ok(full_date.unwrap().into()); + return Ok(full_date.unwrap()) } - Err(format!( - "Error near {}:{}. Failed to parse date.", - file!(), - line!() - )) + Err(format!("Error near {}:{}. Failed to parse date.", file!(), line!())) + } -pub(super) fn parse_version( - word_reader: &mut WordReader, -) -> Result { +pub(super) fn parse_version(word_reader : &mut WordReader) -> Result { let mut version = String::new(); loop { - let (word, _) = next_word!(word_reader)?; + let (word, _) = word_reader.next_word()?; if word == "$end" { // truncate trailing whitespace - let version = version[0..(version.len() - 1)].to_string(); - return Ok(Version(version)); - } else { + let version = version[0..(version.len() - 1)].to_string(); + return Ok(Version(version)) + + } + else { version.push_str(word); - version.push(' '); + version.push_str(" "); } } } -pub(super) fn parse_timescale( - word_reader: &mut WordReader, -) -> Result<(Option, Timescale), String> { +pub(super) fn parse_timescale(word_reader : &mut WordReader) -> Result<(Option, Timescale), String> { + // we might see `1ps $end` or `1 ps $end` // first get timescale - let (word, _) = next_word!(word_reader)?; - let ParseResult { matched, residual } = take_while(word, digit); + let (word, _) = word_reader.next_word()?; + let word = word.to_string(); + let ParseResult{matched, residual} = take_while(word.as_str(), digit); let scalar = matched; - let scalar: u32 = scalar - .to_string() - .parse() - .map_err(|e| format!("Error near {}:{}. {e}", file!(), line!()))?; + let scalar : u32 = scalar.to_string().parse() + .map_err(|e| format!("Error near {}:{}. {e}", file!(), line!()))?; let timescale = { - if residual.is_empty() { - let (word, _) = next_word!(word_reader)?; + if residual == "" { + let (word, _) = word_reader.next_word()?; let unit = match word { - "fs" => Ok(Timescale::Fs), - "ps" => Ok(Timescale::Ps), - "ns" => Ok(Timescale::Ns), - "us" => Ok(Timescale::Us), - "ms" => Ok(Timescale::Ms), - "s" => Ok(Timescale::S), - _ => Err(format!( - "Error near {}:{}. Unknown unit {word}.", - file!(), - line!() - )), - }?; - + "fs" => {Ok(Timescale::Fs)} + "ps" => {Ok(Timescale::Ps)} + "ns" => {Ok(Timescale::Ns)} + "us" => {Ok(Timescale::Us)} + "ms" => {Ok(Timescale::Ms)} + "s" => {Ok(Timescale::S)} + _ => {Err(format!("Error near {}:{}. Unknown unit {word}.", file!(), line!()))} + }.unwrap(); + (Some(scalar), unit) - } else { + } + else { let unit = match residual { - "fs" => Ok(Timescale::Fs), - "ps" => Ok(Timescale::Ps), - "ns" => Ok(Timescale::Ns), - "us" => Ok(Timescale::Us), - "ms" => Ok(Timescale::Ms), - "s" => Ok(Timescale::S), - _ => Err(format!( - "Error near {}:{}. Unknown unit {residual}.", - file!(), - line!() - )), - }?; - + "fs" => {Ok(Timescale::Fs)} + "ps" => {Ok(Timescale::Ps)} + "ns" => {Ok(Timescale::Ns)} + "us" => {Ok(Timescale::Us)} + "ms" => {Ok(Timescale::Ms)} + "s" => {Ok(Timescale::S)} + _ => {Err(format!("Error near {}:{}. Unknown unit {residual}.", file!(), line!()))} + }.unwrap(); + (Some(scalar), unit) } }; // then check for the `$end` keyword - let (word, _) = next_word!(word_reader)?; - tag(word, "$end").assert_match()?; + let (end, _) = word_reader.next_word()?; + tag(end, "$end").assert_match()?; + + return Ok(timescale); - Ok(timescale) } -pub(super) fn parse_metadata( - word_reader: &mut WordReader, -) -> Result { +pub(super) fn parse_metadata(word_reader : &mut WordReader) -> Result { + let mut metadata = Metadata { - date: None, - version: None, - timescale: (None, Timescale::Unit), + date : None, + version : None, + timescale : (None, Timescale::Unit) }; loop { // check for another word in the file - let (word, _) = next_word!(word_reader)?; + let (word, _) = word_reader.next_word()?; - let ParseResult { matched, residual } = tag(word, "$"); + let ParseResult{matched, residual} = tag(word, "$"); match matched { // we hope that this word stars with a `$` - "$" => { + "$" => { match residual { - "date" => { - // a date is typically composed of the 5 following words which can - // occur in any order: + "date" => { + // a date is typically composed of the 5 following words which can + // occur in any order: // {Day, Month, Date(number in month), hh:mm:ss, year}. // Thus, we must lookahead read the 5 next words, and try our date // parser on 5! = 120 permutations of the 5 words. @@ -252,14 +231,14 @@ pub(super) fn parse_metadata( // that we may search up to 6 different permutations oh hh::mm:ss, // for an upper bound total of 720 permutations // - // While looking ahead, if one of the 5 words in `$end`, we have to + // While looking ahead, if one of the 5 words in `$end`, we have to // immediately stop trying to get more words. let mut found_end = false; - let mut lookahead_5_words: Vec<(String, Cursor)> = Vec::new(); + let mut lookahead_5_words : Vec<(String, Cursor)> = Vec::new(); for _ in 0..5 { - let (word, cursor) = next_word!(word_reader)?; + let (word, cursor) = word_reader.next_word()?; let word = word.to_string(); match word.as_str() { "$end" => { @@ -274,14 +253,12 @@ pub(super) fn parse_metadata( // we no longer attempt to parse date if we weren't able to lookahead 5 // words - if found_end { - continue; - } - - let permutations = lookahead_5_words - .iter() - .permutations(lookahead_5_words.len()); + if found_end {continue} + 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(); @@ -303,12 +280,13 @@ pub(super) fn parse_metadata( // store date and exit loop if a match is found if parsed_date.is_ok() { - metadata.date = Some(parsed_date?); - break; + metadata.date = Some(parsed_date.unwrap()); + break } + } } - "version" => { + "version" => { let version = parse_version(word_reader); if version.is_ok() { metadata.version = Some(version.unwrap()); @@ -320,8 +298,8 @@ pub(super) fn parse_metadata( metadata.timescale = timescale.unwrap(); } } - "scope" => break, - "var" => break, + "scope" => {break} + "var" => {break} // we keep searching for words until we've found one of the following // keywords, ["version", "timescale", "scope", "var"] _ => {} @@ -330,6 +308,7 @@ pub(super) fn parse_metadata( // if word does not start with `$`, then we keep looping _ => {} } + } - Ok(metadata) -} + return Ok(metadata) +} \ No newline at end of file diff --git a/src/vcd/parse/scopes.rs b/src/vcd/parse/scopes.rs index 5fe106b..fa62188 100644 --- a/src/vcd/parse/scopes.rs +++ b/src/vcd/parse/scopes.rs @@ -1,189 +1,94 @@ -// 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. +//! part of the vcd parser that handles parsing the signal tree and +//! building the resulting signal tree +use super::*; -/// part of the vcd parser that handles parsing the signal tree and -/// building the resulting signal tree -use std::collections::HashMap; - -use super::super::reader::{curr_word, next_word, WordReader}; -use super::super::signal::{SignalEnum, SignalType}; -use super::super::types::{Scope, ScopeIdx, SignalIdx, VCD}; - -use super::combinator_atoms::{ident, tag}; -use super::types::ParseResult; - -pub(super) fn parse_var( - word_reader: &mut WordReader, - parent_scope_idx: ScopeIdx, - vcd: &mut VCD, - signal_map: &mut HashMap, - path: &Vec, +pub(super) fn parse_var<'a>( + word_reader : &mut WordReader, + parent_scope_idx : ScopeIdx, + vcd : &'a mut VCD, + signal_map : &mut HashMap ) -> Result<(), String> { - let (word, cursor) = next_word!(word_reader)?; - let expected_types = [ - "event", - "integer", - "parameter", - "real", - "realtime", - "reg", - "string", - "supply0", - "supply1", - "time", - "tri", - "triand", - "trior", - "trireg", - "tri0", - "tri1", - "wand", - "wire", - "wor", - ]; + let (word, cursor) = word_reader.next_word()?; + let expected_types = ["integer", "parameter", "real", "reg", "string", "wire", "tri1", "time"]; // $var parameter 3 a IDLE $end // ^^^^^^^^^ - var_type let var_type = match word { - "event" => Ok(SignalType::Event), - "integer" => Ok(SignalType::Integer), - "parameter" => Ok(SignalType::Parameter), - "real" => Ok(SignalType::Real), - "realtime" => Ok(SignalType::RealTime), - "reg" => Ok(SignalType::Reg), - "string" => Ok(SignalType::Str), - "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), + "integer" => {Ok(SigType::Integer)} + "parameter" => {Ok(SigType::Parameter)} + "real" => {Ok(SigType::Real)} + "reg" => {Ok(SigType::Reg)} + "string" => {Ok(SigType::Str)} + "wire" => {Ok(SigType::Wire)} + "tri1" => {Ok(SigType::Tri1)} + "time" => {Ok(SigType::Time)} _ => { - let err = format!( - "Error near {}:{} \ + let err = format!("Error near {}:{} \ found keyword `{word}` but expected one of \ - {expected_types:?} on {cursor:?}", - file!(), - line!() - ); + {expected_types:?} on {cursor:?}", file!(), line!()); Err(err) } }?; - let (word, cursor) = next_word!(word_reader)?; - + let (word, cursor) = word_reader.next_word()?; let parse_err = format!("failed to parse as usize on {cursor:?}"); // $var parameter 3 a IDLE $end - // ^ - num_bits - let num_bits = match var_type { - SignalType::Event - | SignalType::Integer - | SignalType::Parameter - | SignalType::Reg - | SignalType::Supply0 - | 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::() - .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) + // ^ - no_bits + let no_bits = match var_type { + SigType::Integer | SigType::Parameter | + SigType::Real | SigType::Reg | + SigType::Wire | SigType::Tri1 | + SigType::Time => { + let no_bits = word.parse::().expect(parse_err.as_str()); + Some(no_bits) } - // for strings, reals, and realtimes we don't really care what the number of bits is - _ => None, + // for strings, we don't really care what the number of bits is + _ => {None} }; // $var parameter 3 a IDLE $end // ^ - signal_alias - let (word, _) = next_word!(word_reader)?; + let (word, _) = word_reader.next_word()?; let signal_alias = word.to_string(); // $var parameter 3 a IDLE $end // ^^^^ - full_signal_name(can extend until $end) let mut full_signal_name = Vec::::new(); - let mut size = None; loop { - let (word, _) = next_word!(word_reader)?; + let (word, _) = word_reader.next_word()?; match word { - "$end" => break, - other if other.starts_with('[') => size = Some(other.to_string()), - _ => full_signal_name.push(word.to_string()), + "$end" => {break} + _ => {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 = SignalIdx(vcd.all_signals.len()); - let signal = SignalEnum::Alias { - name: full_signal_name.clone(), - path: path - .iter() - .cloned() - .chain([full_signal_name]) - .collect::>(), - signal_alias: *ref_signal_idx, - }; + let signal = Signal::Alias{ + name: full_signal_name, + signal_alias: *ref_signal_idx}; (signal, signal_idx) } None => { let signal_idx = SignalIdx(vcd.all_signals.len()); signal_map.insert(signal_alias.to_string(), signal_idx); - let signal = SignalEnum::Data { - name: full_signal_name.clone(), - path: path - .iter() - .cloned() - .chain([full_signal_name]) - .collect::>(), - signal_type: var_type, - index: size, + let signal = Signal::Data{ + name: full_signal_name, + sig_type: var_type, signal_error: None, - num_bits, - num_bytes, + num_bits: no_bits, self_idx: signal_idx, - nums_encoded_as_fixed_width_le_u8: vec![], - string_vals: vec![], - lsb_indxs_of_num_tmstmp_vals_on_tmln: vec![], - byte_len_of_num_tmstmp_vals_on_tmln: vec![], - byte_len_of_string_tmstmp_vals_on_tmln: vec![], - lsb_indxs_of_string_tmstmp_vals_on_tmln: vec![], - }; + u8_timeline: vec![], + u8_timeline_markers: vec![], + string_timeline: vec![], + string_timeline_markers: vec![], + scope_parent: parent_scope_idx }; (signal, signal_idx) } }; @@ -198,10 +103,10 @@ pub(super) fn parse_var( /// Sometimes, variables can be listed outside of scopes. /// We call these orphaned vars. -fn parse_orphaned_vars( - word_reader: &mut WordReader, - vcd: &mut VCD, - signal_map: &mut HashMap, +fn parse_orphaned_vars<'a>( + word_reader : &mut WordReader, + vcd : &'a mut VCD, + signal_map : &mut HashMap ) -> Result<(), String> { // create scope for unscoped signals if such a scope does not // yet exist @@ -219,40 +124,39 @@ fn parse_orphaned_vars( if scope.name == scope_name { scope_idx = scope.self_idx; scope_already_exists = true; - break; + 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); + 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, &vec![])?; + parse_var(word_reader, scope_idx, vcd, signal_map)?; loop { - let (word, cursor) = next_word!(word_reader)?; + let (word, cursor) = word_reader.next_word()?; match word { "$var" => { - parse_var(word_reader, scope_idx, vcd, signal_map, &vec![])?; + parse_var(word_reader, scope_idx, vcd, signal_map)?; } - "$scope" => break, + "$scope" => {break} _ => { - let msg = format!( - "Error near {}:{}.\ + let msg = format!("Error near {}:{}.\ Expected $scope or $var, found \ - {word} at {cursor:?}", - file!(), - line!() - ); + {word} at {cursor:?}", file!(), line!()); Err(msg)?; } }; @@ -261,182 +165,99 @@ fn parse_orphaned_vars( Ok(()) } -fn parse_scopes_inner( - word_reader: &mut WordReader, - parent_scope_idx: Option, - vcd: &mut VCD, - signal_map: &mut HashMap, - path: &Vec, +pub(super) fn parse_signal_tree<'a>( + word_reader : &mut WordReader, + parent_scope_idx : Option, + vcd : &'a mut VCD, + signal_map : &mut HashMap ) -> Result<(), String> { + // $scope module reg_mag_i $end // ^^^^^^ - module keyword - let (keyword, cursor) = next_word!(word_reader)?; + let (keyword, cursor) = word_reader.next_word()?; - let expected = ["module", "begin", "task", "function", "fork"]; + let expected = ["module", "begin", "task", "function"]; if expected.contains(&keyword) { Ok(()) } else { - let err = format!( - "Error near {}:{}. \ + let err = format!("Error near {}:{}. \ found keyword `{keyword}` but expected one of \ - {expected:?} on {cursor:?}", - file!(), - line!() - ); + {expected:?} on {cursor:?}", file!(), line!()); Err(err) }?; // $scope module reg_mag_i $end // ^^^^^^^^^ - scope name - let (scope_name, _) = next_word!(word_reader)?; - // In some cases there are VCD files which have scopes without names. - // since these occur in the wild, we'll tolerate them even if it is unclear - // if it is supported or not by the spec. - if scope_name != "$end" { - let mut path = path.clone(); - path.push(scope_name.to_string()); + let (scope_name, _) = word_reader.next_word()?; - 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(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), + 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(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.scope_roots.push(curr_scope_idx) + } + } - // add this scope to list of existing scopes - vcd.all_scopes.push(Scope { + // 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 $end - // ^^^^ - end keyword - ident(word_reader, "$end")?; + // $scope module reg_mag_i $end + // ^^^^ - end keyword + ident(word_reader, "$end")?; - loop { - let (word, cursor) = next_word!(word_reader)?; - let ParseResult { matched, residual } = tag(word, "$"); - match matched { - // we hope that this word starts with a `$` - "$" => { - match residual { - "scope" => { - // recursive - parse inside of current scope tree - parse_scopes_inner( - word_reader, - Some(curr_scope_idx), - vcd, - signal_map, - &path, - )?; - } - "var" => { - parse_var(word_reader, curr_scope_idx, vcd, signal_map, &path)?; - } - "upscope" => { - ident(word_reader, "$end")?; - break; - } - // we ignore comments - "comment" => loop { - if ident(word_reader, "$end").is_ok() { - break; - } - }, - _ => { - let err = format!( - "Error near {}:{}. \ - found keyword `{residual}` but expected \ - `$scope`, `$var`, `$comment`, or `$upscope` \ - on {cursor:?}", - file!(), - line!() - ); - return Err(err); + loop { + let (word, cursor) = word_reader.next_word()?; + let ParseResult{matched, residual} = tag(word, "$"); + match matched { + // we hope that this word starts with a `$` + "$" => { + match residual { + "scope" => { + // recursive - parse inside of current scope tree + parse_signal_tree(word_reader, Some(curr_scope_idx), vcd, signal_map)?; + } + "var" => { + parse_var(word_reader, curr_scope_idx, vcd, signal_map)?; + } + "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 `{matched}` but \ - expected `$` on {cursor:?}", - file!(), - line!() - ); - return Err(err); + _ => { + let err = format!("Error near {}:{}. \ + found keyword `{residual}` but expected \ + `$scope`, `$var`, `$comment`, or `$upscope` \ + on {cursor:?}", file!(), line!()); + return Err(err) + } } } - } - } else { - // 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); - } + _ => { + let err = format!("Error near {}:{}. \ + found keyword `{matched}` but \ + expected `$` on {cursor:?}", file!(), line!()); + return Err(err) } } } @@ -444,79 +265,69 @@ fn parse_scopes_inner( Ok(()) } -pub(super) fn parse_scopes( - word_reader: &mut WordReader, - vcd: &mut VCD, - signal_map: &mut HashMap, +pub(super) fn parse_scopes<'a>( + word_reader : &mut WordReader, + vcd : &'a mut VCD, + signal_map : &mut HashMap ) -> Result<(), String> { // get the current word - let (word, _) = curr_word!(word_reader)?; + let (word, _) = word_reader.curr_word()?; // we may have orphaned vars that occur before the first scope if word == "$var" { parse_orphaned_vars(word_reader, vcd, signal_map)?; - } - + } + // get the current word - let (word, cursor) = curr_word!(word_reader)?; + let (word, cursor) = word_reader.curr_word()?; // 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 {}:{}.\ + let msg = format!("Error near {}:{}.\ Expected $scope or $var, found \ - {word} at {cursor:?}", - file!(), - line!() - ); - return Err(msg); + {word} at {cursor:?}", file!(), line!()); + return Err(msg) } // now for the interesting part - parse_scopes_inner(word_reader, None, vcd, signal_map, &vec![])?; + parse_signal_tree(word_reader, None, vcd, signal_map)?; // let err = format!("reached end of file without parser leaving {}", function_name!()); let expected_keywords = ["$scope", "$enddefinitions"]; // there could be multiple signal trees, and unfortunately, we - // can't merge the earlier call to `parse_scopes_inner` into this loop - // because this loop gets a word from `next_word` instead of + // can't merge the earlier call to `parse_signal_tree` into this loop + // because this loop gets a word from `next_word` instead of // `curr_word()`. loop { - let (word, cursor) = next_word!(word_reader)?; - + let (word, cursor) = word_reader.next_word()?; match word { "$scope" => { - parse_scopes_inner(word_reader, None, vcd, signal_map, &vec![])?; + parse_signal_tree(word_reader, None, vcd, signal_map)?; } "$enddefinitions" => { ident(word_reader, "$end")?; - break; + break } - "$comment" => { + "comment" => { // although we don't store comments, we still need to advance the // word_reader cursor to the end of the comment loop { - if ident(word_reader, "$end").is_ok() { - break; - } + if ident(word_reader, "$end").is_ok() {break} } } _ => { - let err = format!( - "Error near {}:{} \ + let err = format!("Error near {}:{} \ found keyword `{word}` but expected one of \ - {expected_keywords:?} on {cursor:?}", - file!(), - line!() - ); - return Err(err); + {expected_keywords:?} on {cursor:?}", file!(), line!()); + return Err(err) + } } } Ok(()) -} +} \ No newline at end of file diff --git a/src/vcd/parse/types.rs b/src/vcd/parse/types.rs index 25644ff..8bab3d4 100644 --- a/src/vcd/parse/types.rs +++ b/src/vcd/parse/types.rs @@ -1,27 +1,25 @@ -// 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) residual: &'a str, -} + pub(super) matched : &'a str, + pub(super) residual : &'a str} impl<'a> ParseResult<'a> { - pub(super) fn assert_match(&self) -> Result<&str, String> { - if self.matched.is_empty() { - Err("no match".to_string()) - } else { - Ok(self.matched) + + pub(super) fn assert_match(& self) -> Result<&str, String> { + if self.matched == "" { + return Err("no match".to_string()) + } + else { + return Ok(self.matched) } } - pub(super) fn assert_residual(&self) -> Result<&str, String> { - if self.residual.is_empty() { - Err("no residual".to_string()) - } else { - Ok(self.residual) + pub(super) fn assert_residual(& self) -> Result<&str, String> { + if self.residual == "" { + return Err("no residual".to_string()) + } + else { + return Ok(self.residual) } } -} +} \ No newline at end of file diff --git a/src/vcd/reader.rs b/src/vcd/reader.rs index 6ef242f..0548677 100644 --- a/src/vcd/reader.rs +++ b/src/vcd/reader.rs @@ -1,12 +1,11 @@ -// 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 std::collections::VecDeque; -use std::io; -use std::io::BufRead; use std::slice; use std::str; +use std::io::prelude::*; +use std::io; + +use backtrace::{ Backtrace, BacktraceFrame, BacktraceSymbol }; #[derive(Debug, Clone)] pub(super) struct Line(pub(super) usize); @@ -14,30 +13,35 @@ pub(super) struct Line(pub(super) usize); pub(super) struct Word(pub(super) usize); #[derive(Debug, Clone)] pub(super) struct Cursor(pub(super) Line, pub(super) Word); +#[derive(Debug)] +pub(super) enum FileStatus{Eof} -pub(super) struct WordReader { - reader: io::BufReader, - eof: bool, - buffers: Vec, - curr_line: usize, - str_slices: VecDeque<(*const u8, usize, Cursor)>, - curr_slice: Option<(*const u8, usize, Cursor)>, +pub struct WordReader { + reader : io::BufReader, + eof : bool, + buffers : Vec, + curr_line : usize, + str_slices : VecDeque<(*const u8, usize, Cursor)>, + curr_slice : Option<(*const u8, usize, Cursor)>, } -impl WordReader { - pub(super) fn new(file: R) -> WordReader { + +impl WordReader { + pub(super) fn new(file : File) -> WordReader { let reader = io::BufReader::new(file); WordReader { - reader, - eof: false, - buffers: vec![], - curr_line: 0, - str_slices: VecDeque::new(), - curr_slice: None, + reader : reader, + eof : false, + buffers : vec![], + curr_line : 0, + str_slices : VecDeque::new(), + curr_slice : None } } - pub(super) fn next_word(&mut self) -> Option<(&str, Cursor)> { + + pub(super) fn next_word(&mut self) -> Result<(&str, Cursor), FileStatus> { + // although reaching the eof is not technically an error, in most cases, // we treat it like one in the rest of the codebase. @@ -46,9 +50,7 @@ impl WordReader { if self.str_slices.is_empty() { self.buffers.clear(); - if self.eof { - return None; - } + if self.eof {return Err(FileStatus::Eof)} let num_buffers = 10; @@ -60,25 +62,25 @@ 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 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 Err(FileStatus::Eof) } // if we make it here, we return the next word @@ -86,46 +88,53 @@ impl WordReader { let (ptr, len, position) = self.str_slices.pop_front().unwrap(); let slice = slice::from_raw_parts(ptr, len); self.curr_slice = Some((ptr, len, position.clone())); - return Some((str::from_utf8(slice).unwrap(), position)); + return Ok((str::from_utf8(slice).unwrap(), position)); }; } - pub(super) fn curr_word(&mut self) -> Option<(&str, Cursor)> { + pub(super) fn curr_word(&mut self) -> Result<(&str, Cursor), FileStatus> { match &self.curr_slice { - Some(slice) => unsafe { - let (ptr, len, position) = slice.clone(); - let slice = slice::from_raw_parts(ptr, len); - return Some((str::from_utf8(slice).unwrap(), position)); - }, - None => None, + Some(slice) => { + unsafe { + let (ptr, len, position) = slice.clone(); + let slice = slice::from_raw_parts(ptr, len); + Ok((str::from_utf8(slice).unwrap(), position)) + } + + } + None => {Err(FileStatus::Eof)} } } } -macro_rules! next_word { - ($word_reader:ident) => { - $word_reader.next_word().ok_or(()).map_err(|_| { - format!( - "Error near {}:{}. Did not expect to reach end of file here.", - file!(), - line!() - ) - }) - }; +fn previous_symbol(level: u32) -> Option { + let (trace, curr_file, curr_line) = (Backtrace::new(), file!(), line!()); + let frames = trace.frames(); + frames.iter() + .flat_map(BacktraceFrame::symbols) + .skip_while(|s| s.filename().map(|p| !p.ends_with(curr_file)).unwrap_or(true) + || s.lineno() != Some(curr_line)) + .nth(1 + level as usize).cloned() } -macro_rules! curr_word { - ($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!() - ) - }) - }; -} +impl From for String { + fn from(f: FileStatus) -> String { + let sym = previous_symbol(1); + let filename = sym + .as_ref() + .and_then(BacktraceSymbol::filename) + .map_or(None, |path| {path.to_str()}) + .unwrap_or("(Couldn't determine filename)"); + let lineno = sym + .as_ref() + .and_then(BacktraceSymbol::lineno) + .map_or(None, |path| {Some(path.to_string())}) + .unwrap_or("(Couldn't determine line number)".to_string()); -pub(super) use curr_word; -pub(super) use next_word; + match f { + FileStatus::Eof => format!( + "Error near {filename}:{lineno} \ + No more words left in vcd file."), + } + } +} \ No newline at end of file diff --git a/src/vcd/signal.rs b/src/vcd/signal.rs deleted file mode 100644 index b87e1a2..0000000 --- a/src/vcd/signal.rs +++ /dev/null @@ -1,715 +0,0 @@ -// 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 { - pub current: Option<(TimeStamp, T)>, - pub next: Option, -} - -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 { - 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 { - 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 { - 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, 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, 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, - signal_type: SignalType, - /// The optional [start:end] part of the signal name that is sometimes - /// added to signals - index: Option, - /// 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, - num_bits: Option, - num_bytes: Option, - /// 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, - string_vals: Vec, - /// we could do Vec<(LsbIdxOfTmstmpValOnTmln, u8)>, but I - /// suspect that Vec 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, - byte_len_of_num_tmstmp_vals_on_tmln: Vec, - byte_len_of_string_tmstmp_vals_on_tmln: Vec, - lsb_indxs_of_string_tmstmp_vals_on_tmln: Vec, - }, - Alias { - name: String, - path: Vec, - 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 { - 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 { - 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, - ) -> 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, - ) -> 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 { - 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, - all_signals: &Vec, - ) -> Result, 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, - all_signals: &Vec, - ) -> Result, 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), - }); - } -} diff --git a/src/vcd/types.rs b/src/vcd/types.rs index 7ef3a54..0a9e004 100644 --- a/src/vcd/types.rs +++ b/src/vcd/types.rs @@ -1,144 +1,142 @@ -// use crate::Signal; - -// 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::signal::{Signal, SignalEnum}; -use chrono::prelude::{DateTime, Utc}; -use num::BigUint; -use std::fmt; - -#[derive(Debug, Clone)] -pub struct Version(pub String); - -#[derive(Debug, Clone, Copy, Eq, PartialEq)] -pub enum Timescale { - Fs, - Ps, - Ns, - Us, - Ms, - S, - Unit, -} - -impl fmt::Display for Timescale { - fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { - match self { - Timescale::Fs => write!(f, "fs"), - Timescale::Ps => write!(f, "ps"), - Timescale::Ns => write!(f, "ns"), - Timescale::Us => write!(f, "μs"), - Timescale::Ms => write!(f, "ms"), - Timescale::S => write!(f, "s"), - Timescale::Unit => write!(f, "unit"), - } - } -} +use chrono::prelude::*; #[derive(Debug)] -pub struct Metadata { - pub date: Option>, - pub version: Option, - pub timescale: (Option, Timescale), +pub(super) struct Version(pub String); + +#[derive(Debug)] +pub(super) enum Timescale {Fs, Ps, Ns, Us, Ms, S, Unit} + +#[derive(Debug)] +pub(super) struct Metadata { + pub(super) date : Option>, + pub(super) version : Option, + pub(super) timescale : (Option, Timescale)} + +#[derive(Debug, Copy, Clone)] +pub(super) struct ScopeIdx(pub(super) usize); + +#[derive(Debug, Copy, Clone)] +pub(super) struct SignalIdx(pub(super) usize); + +#[derive(Debug, Copy, Clone)] +pub(super) struct TimelineIdx(pub(super) u32); + +#[derive(Debug, Copy, Clone)] +pub struct StartIdx(pub(super) u32); + +#[derive(Debug)] +pub(super) enum SigType {Integer, Parameter, Real, Reg, Str, Wire, Tri1, Time} + +#[derive(Debug)] +pub(super) enum Signal{ + Data{ + name : String, + sig_type : SigType, + // 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, + num_bits : Option, + // TODO : may be able to remove self_idx + self_idx : SignalIdx, + // we could encounter a mix of pure values and strings + // for the same signal timeline + u8_timeline : Vec, + u8_timeline_markers : Vec, + string_timeline : Vec, + string_timeline_markers : Vec, + scope_parent : ScopeIdx}, + Alias{ + name : String, + signal_alias : SignalIdx} } -// 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) self_idx: ScopeIdx, + pub(super) parent_idx : Option, + pub(super) self_idx : ScopeIdx, - pub(super) child_signals: Vec, - pub(super) child_scopes: Vec, -} + pub(super) child_signals : Vec, + pub(super) child_scopes : Vec} + +// TODO: document how timeline is represented #[derive(Debug)] pub struct VCD { - pub metadata: Metadata, - // Since we only need to store values when there is an actual change - // in the timeline, we keep a vector that stores the time at which an - // event occurs. Time t is always stored/encoded as the minimum length sequence - // of u8. - // 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, - pub(super) all_signals: Vec, - pub(super) all_scopes: Vec, - pub(super) root_scopes: Vec, - pub(super) largest_timestamp: Option, -} + pub(super) metadata : Metadata, + pub timeline : Vec, + pub timeline_markers : Vec, + pub(super) all_signals : Vec, + pub(super) all_scopes : Vec, + pub(super) scope_roots : Vec} impl VCD { - pub fn root_scopes_by_idx(&self) -> Vec { - self.root_scopes.clone() - } - pub fn child_scopes_by_idx(&self, scope_idx: ScopeIdx) -> Vec { - 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 { - 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]; + // TODO : make this a generic traversal function that applies specified + // functions upon encountering scopes and signals + fn print_scope_tree( + &self, + root_scope_idx : ScopeIdx, + depth : usize) + { + let all_scopes = &self.all_scopes; + let all_signals = &self.all_signals; - // dereference signal if Signal::Alias, or keep idx if Signal::Data - let signal_idx = match signal { - SignalEnum::Data { self_idx, .. } => *self_idx, - SignalEnum::Alias { signal_alias, .. } => *signal_alias, - }; + let indent = " ".repeat(depth * 4); + let ScopeIdx(root_scope_idx) = root_scope_idx; + let root_scope = &all_scopes[root_scope_idx]; + let root_scope_name = &root_scope.name; - // 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!() - )), + println!("{indent}scope: {root_scope_name}"); + + for SignalIdx(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 print_scopes(&self) { + for scope_root in &self.scope_roots { + self.print_scope_tree(*scope_root, 0); } } - pub fn max_timestamp(&self) -> &Option { - &self.largest_timestamp + pub fn print_longest_signal(&self) { + let mut idx = 0usize; + let mut max_len = 0usize; + let mut signal_name = String::new(); + + for signal in &self.all_signals { + match signal { + Signal::Alias {..} => {} + Signal::Data { + name, + self_idx, + u8_timeline, + .. } => { + if u8_timeline.len() > max_len { + max_len = u8_timeline.len(); + let SignalIdx(idx_usize) = self_idx; + idx = *idx_usize; + signal_name = name.clone(); + } + + } + } + } + + dbg!((idx, max_len, signal_name)); } -} +} \ No newline at end of file diff --git a/src/vcd/utilities.rs b/src/vcd/utilities.rs deleted file mode 100644 index 55c7c70..0000000 --- a/src/vcd/utilities.rs +++ /dev/null @@ -1,86 +0,0 @@ -// 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 { - 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, BinaryParserErrTypes> { - let mut vec_u8: Vec = 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) -} diff --git a/tests/vcd-files/VCD_file_with_errors.vcd b/test-vcd-files/VCD_file_with_errors.vcd similarity index 100% rename from tests/vcd-files/VCD_file_with_errors.vcd rename to test-vcd-files/VCD_file_with_errors.vcd diff --git a/tests/vcd-files/aldec/SPI_Write.vcd b/test-vcd-files/aldec/SPI_Write.vcd similarity index 100% rename from tests/vcd-files/aldec/SPI_Write.vcd rename to test-vcd-files/aldec/SPI_Write.vcd diff --git a/tests/vcd-files/amaranth/up_counter.vcd b/test-vcd-files/amaranth/up_counter.vcd similarity index 100% rename from tests/vcd-files/amaranth/up_counter.vcd rename to test-vcd-files/amaranth/up_counter.vcd diff --git a/tests/vcd-files/ghdl/alu.vcd b/test-vcd-files/ghdl/alu.vcd similarity index 100% rename from tests/vcd-files/ghdl/alu.vcd rename to test-vcd-files/ghdl/alu.vcd diff --git a/tests/vcd-files/ghdl/idea.vcd b/test-vcd-files/ghdl/idea.vcd similarity index 100% rename from tests/vcd-files/ghdl/idea.vcd rename to test-vcd-files/ghdl/idea.vcd diff --git a/tests/vcd-files/ghdl/pcpu.vcd b/test-vcd-files/ghdl/pcpu.vcd similarity index 100% rename from tests/vcd-files/ghdl/pcpu.vcd rename to test-vcd-files/ghdl/pcpu.vcd diff --git a/tests/vcd-files/gtkwave-analyzer/perm_current.vcd b/test-vcd-files/gtkwave-analyzer/perm_current.vcd similarity index 100% rename from tests/vcd-files/gtkwave-analyzer/perm_current.vcd rename to test-vcd-files/gtkwave-analyzer/perm_current.vcd diff --git a/tests/vcd-files/icarus/CPU.vcd b/test-vcd-files/icarus/CPU.vcd similarity index 100% rename from tests/vcd-files/icarus/CPU.vcd rename to test-vcd-files/icarus/CPU.vcd diff --git a/tests/vcd-files/icarus/rv32_soc_TB.vcd b/test-vcd-files/icarus/rv32_soc_TB.vcd similarity index 100% rename from tests/vcd-files/icarus/rv32_soc_TB.vcd rename to test-vcd-files/icarus/rv32_soc_TB.vcd diff --git a/tests/vcd-files/icarus/test1.vcd b/test-vcd-files/icarus/test1.vcd similarity index 100% rename from tests/vcd-files/icarus/test1.vcd rename to test-vcd-files/icarus/test1.vcd diff --git a/tests/vcd-files/model-sim/CPU_Design.msim.vcd b/test-vcd-files/model-sim/CPU_Design.msim.vcd similarity index 100% rename from tests/vcd-files/model-sim/CPU_Design.msim.vcd rename to test-vcd-files/model-sim/CPU_Design.msim.vcd diff --git a/tests/vcd-files/model-sim/clkdiv2n_tb.vcd b/test-vcd-files/model-sim/clkdiv2n_tb.vcd similarity index 100% rename from tests/vcd-files/model-sim/clkdiv2n_tb.vcd rename to test-vcd-files/model-sim/clkdiv2n_tb.vcd diff --git a/tests/vcd-files/my-hdl/Simple_Memory.vcd b/test-vcd-files/my-hdl/Simple_Memory.vcd similarity index 100% rename from tests/vcd-files/my-hdl/Simple_Memory.vcd rename to test-vcd-files/my-hdl/Simple_Memory.vcd diff --git a/tests/vcd-files/my-hdl/sigmoid_tb.vcd b/test-vcd-files/my-hdl/sigmoid_tb.vcd similarity index 100% rename from tests/vcd-files/my-hdl/sigmoid_tb.vcd rename to test-vcd-files/my-hdl/sigmoid_tb.vcd diff --git a/tests/vcd-files/my-hdl/top.vcd b/test-vcd-files/my-hdl/top.vcd similarity index 100% rename from tests/vcd-files/my-hdl/top.vcd rename to test-vcd-files/my-hdl/top.vcd diff --git a/tests/vcd-files/ncsim/ffdiv_32bit_tb.vcd b/test-vcd-files/ncsim/ffdiv_32bit_tb.vcd similarity index 100% rename from tests/vcd-files/ncsim/ffdiv_32bit_tb.vcd rename to test-vcd-files/ncsim/ffdiv_32bit_tb.vcd diff --git a/tests/vcd-files/quartus/mipsHardware.vcd b/test-vcd-files/quartus/mipsHardware.vcd similarity index 100% rename from tests/vcd-files/quartus/mipsHardware.vcd rename to test-vcd-files/quartus/mipsHardware.vcd diff --git a/tests/vcd-files/quartus/wave_registradores.vcd b/test-vcd-files/quartus/wave_registradores.vcd similarity index 100% rename from tests/vcd-files/quartus/wave_registradores.vcd rename to test-vcd-files/quartus/wave_registradores.vcd diff --git a/tests/vcd-files/questa-sim/dump.vcd b/test-vcd-files/questa-sim/dump.vcd similarity index 100% rename from tests/vcd-files/questa-sim/dump.vcd rename to test-vcd-files/questa-sim/dump.vcd diff --git a/tests/vcd-files/questa-sim/test.vcd b/test-vcd-files/questa-sim/test.vcd similarity index 100% rename from tests/vcd-files/questa-sim/test.vcd rename to test-vcd-files/questa-sim/test.vcd diff --git a/tests/vcd-files/riviera-pro/dump.vcd b/test-vcd-files/riviera-pro/dump.vcd similarity index 100% rename from tests/vcd-files/riviera-pro/dump.vcd rename to test-vcd-files/riviera-pro/dump.vcd diff --git a/tests/vcd-files/sources.csv b/test-vcd-files/sources.csv similarity index 100% rename from tests/vcd-files/sources.csv rename to test-vcd-files/sources.csv diff --git a/tests/vcd-files/systemc/waveform.vcd b/test-vcd-files/systemc/waveform.vcd similarity index 100% rename from tests/vcd-files/systemc/waveform.vcd rename to test-vcd-files/systemc/waveform.vcd diff --git a/tests/vcd-files/treadle/GCD.vcd b/test-vcd-files/treadle/GCD.vcd similarity index 100% rename from tests/vcd-files/treadle/GCD.vcd rename to test-vcd-files/treadle/GCD.vcd diff --git a/tests/vcd-files/vcs/Apb_slave_uvm_new.vcd b/test-vcd-files/vcs/Apb_slave_uvm_new.vcd similarity index 100% rename from tests/vcd-files/vcs/Apb_slave_uvm_new.vcd rename to test-vcd-files/vcs/Apb_slave_uvm_new.vcd diff --git a/tests/vcd-files/vcs/datapath_log.vcd b/test-vcd-files/vcs/datapath_log.vcd similarity index 100% rename from tests/vcd-files/vcs/datapath_log.vcd rename to test-vcd-files/vcs/datapath_log.vcd diff --git a/tests/vcd-files/vcs/processor.vcd b/test-vcd-files/vcs/processor.vcd similarity index 100% rename from tests/vcd-files/vcs/processor.vcd rename to test-vcd-files/vcs/processor.vcd diff --git a/tests/vcd-files/verilator/swerv1.vcd b/test-vcd-files/verilator/swerv1.vcd similarity index 100% rename from tests/vcd-files/verilator/swerv1.vcd rename to test-vcd-files/verilator/swerv1.vcd diff --git a/tests/vcd-files/verilator/vlt_dump.vcd b/test-vcd-files/verilator/vlt_dump.vcd similarity index 100% rename from tests/vcd-files/verilator/vlt_dump.vcd rename to test-vcd-files/verilator/vlt_dump.vcd diff --git a/tests/vcd-files/vivado/iladata.vcd b/test-vcd-files/vivado/iladata.vcd similarity index 100% rename from tests/vcd-files/vivado/iladata.vcd rename to test-vcd-files/vivado/iladata.vcd diff --git a/tests/vcd-files/xilinx_isim/test.vcd b/test-vcd-files/xilinx_isim/test.vcd similarity index 100% rename from tests/vcd-files/xilinx_isim/test.vcd rename to test-vcd-files/xilinx_isim/test.vcd diff --git a/tests/vcd-files/xilinx_isim/test1.vcd b/test-vcd-files/xilinx_isim/test1.vcd similarity index 100% rename from tests/vcd-files/xilinx_isim/test1.vcd rename to test-vcd-files/xilinx_isim/test1.vcd diff --git a/tests/vcd-files/xilinx_isim/test2x2_regex22_string1.vcd b/test-vcd-files/xilinx_isim/test2x2_regex22_string1.vcd similarity index 100% rename from tests/vcd-files/xilinx_isim/test2x2_regex22_string1.vcd rename to test-vcd-files/xilinx_isim/test2x2_regex22_string1.vcd diff --git a/tests/files.rs b/tests/files.rs deleted file mode 100644 index 38c08b2..0000000 --- a/tests/files.rs +++ /dev/null @@ -1,77 +0,0 @@ -// 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", -]; diff --git a/tests/integration_test.rs b/tests/integration_test.rs deleted file mode 100644 index 48e13d9..0000000 --- a/tests/integration_test.rs +++ /dev/null @@ -1,22 +0,0 @@ -// 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(); - } - } -} diff --git a/tests/vcd-files/scope_with_comment.vcd b/tests/vcd-files/scope_with_comment.vcd deleted file mode 100644 index cf17910..0000000 --- a/tests/vcd-files/scope_with_comment.vcd +++ /dev/null @@ -1,296 +0,0 @@ -$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*