From 915e9568211e86fecdf81b2fa3265f21863917e9 Mon Sep 17 00:00:00 2001 From: Yehowshua Immanuel Date: Tue, 17 May 2022 22:04:32 -0400 Subject: [PATCH 01/50] now parsing by space --- README.md | 5 +---- src/main.rs | 41 ++++++++++++++--------------------------- 2 files changed, 15 insertions(+), 31 deletions(-) diff --git a/README.md b/README.md index 8235c1f..d89ed64 100644 --- a/README.md +++ b/README.md @@ -20,10 +20,7 @@ The first build of the program may take some time. ``cargo run --release -- path/to/vcd/file`` ## TODO - - [x] Test positions with seeking - - [x] vcd should be argument - - [x] structure to store stream position against timestamp as string - - [x] structure to store stream position against timestamp as BigInt + - [ ] We need a way to merge lines. ### April 14 - [ ] store timestamps to struct diff --git a/src/main.rs b/src/main.rs index 5423c94..2171697 100644 --- a/src/main.rs +++ b/src/main.rs @@ -1,6 +1,7 @@ use std::io::prelude::*; use std::io; use std::fs::File; +use std::collections::BTreeMap; use num::*; use clap::Parser; @@ -17,44 +18,30 @@ struct Timestamp{ timestamp: BigInt } +struct Signal { + name : String, + timeline : BTreeMap, + children_arena: Vec, + parent_index : usize +} + fn main() -> std::io::Result<()> { let args = Cli::parse(); + let space = " ".as_bytes()[0]; let file = File::open(&args.path)?; let mut reader = io::BufReader::new(file); - let mut buffer = String::new(); - let mut timestamp_offsets = Vec::new(); - let mut timestamps = Vec::new(); + let mut buffer = Vec::::new(); + let mut word_count = 0u64; while { - let bytes_read = reader.read_line(&mut buffer).unwrap(); + let bytes_read = reader.read_until(space, &mut buffer).unwrap(); bytes_read > 0 } { - if &buffer[0..1] == "#" { - let pos = reader.stream_position().unwrap(); - timestamp_offsets.push(pos); - - let timestamp = { - let len = buffer.len(); - let str_val = &buffer[1..(len - 1)].as_bytes(); - BigInt::parse_bytes(str_val, 10).unwrap() - }; - timestamps.push(timestamp); - } - buffer.clear() + word_count += 1; } - - let index = 4; - let timestamp_offset = timestamp_offsets.get(index).unwrap(); - let timestamp = timestamps.get(index).unwrap(); - dbg!((timestamp_offset, timestamp)); - - // seek to where we found the first timestamp and read - // out the next line - reader.seek(io::SeekFrom::Start(*timestamp_offset)); - reader.read_line(&mut buffer); - dbg!(buffer); + dbg!(word_count); Ok(()) } -- 2.47.1 From da0bc62102b50820d2672d711f643bafff202e93 Mon Sep 17 00:00:00 2001 From: Yehowshua Immanuel Date: Wed, 18 May 2022 20:47:55 -0400 Subject: [PATCH 02/50] this loop is too slow - but may be useful for future reference --- README.md | 2 +- src/main.rs | 42 ++++++++++++++++++++++++++++++++++++++---- 2 files changed, 39 insertions(+), 5 deletions(-) diff --git a/README.md b/README.md index d89ed64..bca4068 100644 --- a/README.md +++ b/README.md @@ -17,7 +17,7 @@ a large VCD file from The first build of the program may take some time. -``cargo run --release -- path/to/vcd/file`` +``cargo run --release test-vcd-files/aldec/SPI_Write.vcd`` ## TODO - [ ] We need a way to merge lines. diff --git a/src/main.rs b/src/main.rs index 2171697..51a3ca2 100644 --- a/src/main.rs +++ b/src/main.rs @@ -18,6 +18,19 @@ struct Timestamp{ timestamp: BigInt } +struct Cursor{ + line: u64, + col : u64 +} + +enum Tokens { + Date, + End, + String, + Version, + Time, +} + struct Signal { name : String, timeline : BTreeMap, @@ -35,12 +48,33 @@ fn main() -> std::io::Result<()> { let mut buffer = Vec::::new(); let mut word_count = 0u64; - while { - let bytes_read = reader.read_until(space, &mut buffer).unwrap(); - bytes_read > 0 - } { + // while { + // let bytes_read = reader.read_until(b' ', &mut buffer).unwrap(); + // bytes_read > 0 + // } { + // word_count += 1; + + // if word_count < 5 { + // let string = std::str::from_utf8(&buffer).unwrap(); + // dbg!(string); + // } + // buffer.clear(); + // } + loop { + buffer.clear(); + let t = reader + .by_ref() + .bytes() + .map(|c| c.unwrap()) + .take_while(|c| + c != &b' ' && + c != &b'\n'); + buffer.extend(t); word_count += 1; + } + let string = std::str::from_utf8(&buffer).unwrap(); + dbg!(string); dbg!(word_count); Ok(()) -- 2.47.1 From de08a60f17349f754b99674c244d943d30f8fbc2 Mon Sep 17 00:00:00 2001 From: Yehowshua Immanuel Date: Wed, 18 May 2022 21:32:41 -0400 Subject: [PATCH 03/50] now yielding one word at a time when parsing VCDs --- src/main.rs | 43 ++++++++++++++++++------------------------- 1 file changed, 18 insertions(+), 25 deletions(-) diff --git a/src/main.rs b/src/main.rs index 51a3ca2..e2e1ef0 100644 --- a/src/main.rs +++ b/src/main.rs @@ -45,36 +45,29 @@ fn main() -> std::io::Result<()> { let file = File::open(&args.path)?; let mut reader = io::BufReader::new(file); - let mut buffer = Vec::::new(); + let mut buffer = String::new(); let mut word_count = 0u64; + let mut do_break = false; + let line_chunk_size = 25; - // while { - // let bytes_read = reader.read_until(b' ', &mut buffer).unwrap(); - // bytes_read > 0 - // } { - // word_count += 1; + while {!do_break} { + for _ in 0..line_chunk_size { + let bytes_read = reader.read_line(&mut buffer).unwrap(); + if bytes_read == 0 { + do_break = true; + break + } + } - // if word_count < 5 { - // let string = std::str::from_utf8(&buffer).unwrap(); - // dbg!(string); - // } - // buffer.clear(); - // } - loop { - buffer.clear(); - let t = reader - .by_ref() - .bytes() - .map(|c| c.unwrap()) - .take_while(|c| - c != &b' ' && - c != &b'\n'); - buffer.extend(t); - word_count += 1; + let words = buffer.split_ascii_whitespace(); + + for word in words { + word_count += 1; + } + buffer.clear(); } - let string = std::str::from_utf8(&buffer).unwrap(); - dbg!(string); + dbg!(word_count); Ok(()) -- 2.47.1 From 0497015783825260258f565b63050def2ca5bfa5 Mon Sep 17 00:00:00 2001 From: Yehowshua Immanuel Date: Wed, 18 May 2022 22:57:42 -0400 Subject: [PATCH 04/50] now we have an iterator - albeit somewhat slow --- Cargo.toml | 1 + README.md | 25 +++++++------------------ src/main.rs | 46 +++++++++++++++++++--------------------------- 3 files changed, 27 insertions(+), 45 deletions(-) diff --git a/Cargo.toml b/Cargo.toml index 494728b..78e1485 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -8,3 +8,4 @@ edition = "2021" [dependencies] num = "0.4" clap = { version = "3.1.8", features = ["derive"] } +next-gen = "0.1.1" \ No newline at end of file diff --git a/README.md b/README.md index bca4068..d655fe1 100644 --- a/README.md +++ b/README.md @@ -19,22 +19,11 @@ The first build of the program may take some time. ``cargo run --release test-vcd-files/aldec/SPI_Write.vcd`` -## TODO - - [ ] We need a way to merge lines. +# TODO + - [x] We need a way to merge lines. + - [ ] We need to start regression testing the parser over all files + - [ ] Take a look at GTKWave parser to compare effificiency. + - [ ] Send survey to community channel. -### April 14 - - [ ] store timestamps to struct - - [ ] Get file loading status - - [ ] Get all signal scopes - -### April 15 - - [ ] Re-factor to support hooks in the initial file ingest - - [ ] Modularize - -### April 15 - - [ ] Build tree per signal. - - [ ] Each signal also comes with a value change buffer to - avoid frequent disk readouts. - -# VCD Spec Questions -- [ ] I'm pretty sure that only one statement per line is allowed. \ No newline at end of file +### May 18 + - [ ] move while loop into word yielding iterator \ No newline at end of file diff --git a/src/main.rs b/src/main.rs index e2e1ef0..624397c 100644 --- a/src/main.rs +++ b/src/main.rs @@ -2,6 +2,7 @@ use std::io::prelude::*; use std::io; use std::fs::File; use std::collections::BTreeMap; +use ::next_gen::prelude::*; use num::*; use clap::Parser; @@ -13,24 +14,6 @@ struct Cli { path: std::path::PathBuf, } -struct Timestamp{ - file_offset: u64, - timestamp: BigInt -} - -struct Cursor{ - line: u64, - col : u64 -} - -enum Tokens { - Date, - End, - String, - Version, - Time, -} - struct Signal { name : String, timeline : BTreeMap, @@ -38,23 +21,21 @@ struct Signal { parent_index : usize } -fn main() -> std::io::Result<()> { - let args = Cli::parse(); - let space = " ".as_bytes()[0]; - let file = File::open(&args.path)?; +#[generator(yield(String))] +fn yield_words(file : File) { let mut reader = io::BufReader::new(file); let mut buffer = String::new(); let mut word_count = 0u64; - let mut do_break = false; + let mut EOF = false; let line_chunk_size = 25; - while {!do_break} { + while {!EOF} { for _ in 0..line_chunk_size { let bytes_read = reader.read_line(&mut buffer).unwrap(); if bytes_read == 0 { - do_break = true; + EOF = true; break } } @@ -62,13 +43,24 @@ fn main() -> std::io::Result<()> { let words = buffer.split_ascii_whitespace(); for word in words { - word_count += 1; + yield_!(word.to_string()); } buffer.clear(); } - dbg!(word_count); +} + +fn main() -> std::io::Result<()> { + let args = Cli::parse(); + + let file = File::open(&args.path)?; + let mut word_count = 0; + mk_gen!(let mut generator = yield_words(file)); + + for word in generator { + word_count += 1; + } Ok(()) } -- 2.47.1 From 9c4ddffb4253999c4831051d6efe763213431ee2 Mon Sep 17 00:00:00 2001 From: Yehowshua Immanuel Date: Wed, 18 May 2022 22:58:20 -0400 Subject: [PATCH 05/50] one day I'll be allowed to yield str refs --- src/main.rs | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/src/main.rs b/src/main.rs index 624397c..bec0fc8 100644 --- a/src/main.rs +++ b/src/main.rs @@ -22,7 +22,7 @@ struct Signal { } -#[generator(yield(String))] +#[generator(yield(&str))] fn yield_words(file : File) { let mut reader = io::BufReader::new(file); @@ -43,7 +43,7 @@ fn yield_words(file : File) { let words = buffer.split_ascii_whitespace(); for word in words { - yield_!(word.to_string()); + yield_!(word); } buffer.clear(); -- 2.47.1 From 7d1c0e16a835feb7c8ae49b5463bcb76bdfd027f Mon Sep 17 00:00:00 2001 From: Yehowshua Immanuel Date: Thu, 19 May 2022 03:44:24 -0400 Subject: [PATCH 06/50] preliminary parser progress --- Cargo.toml | 2 +- README.md | 37 ++++++++++++++++++++++++++++++++- src/main.rs | 59 +++++++++++++++++++++++++++++++++++++++++++---------- 3 files changed, 85 insertions(+), 13 deletions(-) diff --git a/Cargo.toml b/Cargo.toml index 78e1485..64aa6cf 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -8,4 +8,4 @@ edition = "2021" [dependencies] num = "0.4" clap = { version = "3.1.8", features = ["derive"] } -next-gen = "0.1.1" \ No newline at end of file +chrono = "0.4" \ No newline at end of file diff --git a/README.md b/README.md index d655fe1..3580a09 100644 --- a/README.md +++ b/README.md @@ -21,9 +21,44 @@ The first build of the program may take some time. # TODO - [x] We need a way to merge lines. + - [ ] Need to perform signal aliasing + - use vec of enum {Sig, Alias} + - [ ] Should insert nodes in BFS order - [ ] We need to start regression testing the parser over all files - [ ] Take a look at GTKWave parser to compare effificiency. - [ ] Send survey to community channel. ### May 18 - - [ ] move while loop into word yielding iterator \ No newline at end of file + - [ ] move while loop into word yielding iterator + +# Files +./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 +./test-vcd-files/xilinx_isim/test2x2_regex22_string1.vcd \ No newline at end of file diff --git a/src/main.rs b/src/main.rs index bec0fc8..a8f468b 100644 --- a/src/main.rs +++ b/src/main.rs @@ -2,7 +2,8 @@ use std::io::prelude::*; use std::io; use std::fs::File; use std::collections::BTreeMap; -use ::next_gen::prelude::*; +use chrono::prelude::*; +use std::rc::Rc; use num::*; use clap::Parser; @@ -14,16 +15,53 @@ struct Cli { path: std::path::PathBuf, } + +// TODO: implement any timescales greater than a second +enum Timescale {ps, ns, us, ms, s} + +struct Metadata { + date : DateTime, + version : String, + timescale : Timescale +} + struct Signal { name : String, timeline : BTreeMap, children_arena: Vec, parent_index : usize + +} + +struct SignalAlias { + name : String, + signal_alias : Rc +} + +enum SignalGeneric{ + Signal(Signal), + SignalAlias(SignalAlias), +} + +struct Scope { + name : String, + signals : Vec, + scopes : Vec, +} + +struct VCD { + metadata : Metadata, + top_scopes : Vec } -#[generator(yield(&str))] -fn yield_words(file : File) { +enum VCD_Parser_State {Date, Version, Timescale, SignalTree, Values} +enum Date_Parser_State {Date, Day, Month, HHMMSS, Year} + +fn parse_vcd(word: &str, mut state : VCD_Parser_State) {} +fn parse_date(word : &str, mut state : Date_Parser_State) {} + +fn yield_word_and_apply(file : File, mut f : impl FnMut(&str)) { let mut reader = io::BufReader::new(file); let mut buffer = String::new(); @@ -43,24 +81,23 @@ fn yield_words(file : File) { let words = buffer.split_ascii_whitespace(); for word in words { - yield_!(word); + f(word); } buffer.clear(); } - } fn main() -> std::io::Result<()> { let args = Cli::parse(); - let file = File::open(&args.path)?; - let mut word_count = 0; - mk_gen!(let mut generator = yield_words(file)); + // let dt = Utc.datetime_from_str("Fri Nov 28 12:00:09 2014", "%a %b %e %T %Y"); - for word in generator { - word_count += 1; - } + let file = File::open(&args.path)?; + let mut word_count = 0; + + yield_word_and_apply(file, |word| {word_count += 1}); + dbg!(word_count); Ok(()) } -- 2.47.1 From 825b947bad4005961afe5c23bc377ca5e4ec9beb Mon Sep 17 00:00:00 2001 From: Yehowshua Immanuel Date: Fri, 20 May 2022 22:52:26 -0400 Subject: [PATCH 07/50] Some changes including: - modify data structures to support arenas - preliminary work on parser --- README.md | 1 + src/main.rs | 113 +++++++++++++++++++++++++++++++++++++++------------- 2 files changed, 87 insertions(+), 27 deletions(-) diff --git a/README.md b/README.md index 3580a09..3bf6430 100644 --- a/README.md +++ b/README.md @@ -24,6 +24,7 @@ The first build of the program may take some time. - [ ] Need to perform signal aliasing - use vec of enum {Sig, Alias} - [ ] Should insert nodes in BFS order + - [ ] Change states to lowercase - [ ] We need to start regression testing the parser over all files - [ ] Take a look at GTKWave parser to compare effificiency. - [ ] Send survey to community channel. diff --git a/src/main.rs b/src/main.rs index a8f468b..a869248 100644 --- a/src/main.rs +++ b/src/main.rs @@ -12,54 +12,113 @@ use clap::Parser; struct Cli { /// The path to the file to read #[clap(parse(from_os_str))] - path: std::path::PathBuf, -} + path: std::path::PathBuf} // TODO: implement any timescales greater than a second enum Timescale {ps, ns, us, ms, s} +struct Scope_Idx(usize); +struct Signal_Idx(usize); + struct Metadata { - date : DateTime, + date : DateTime, version : String, - timescale : Timescale -} + timescale : Timescale} struct Signal { - name : String, - timeline : BTreeMap, - children_arena: Vec, - parent_index : usize - -} + name : String, + timeline : BTreeMap, + scope_parent : Scope_Idx} struct SignalAlias { name : String, - signal_alias : Rc -} + signal_alias : Signal_Idx} enum SignalGeneric{ Signal(Signal), - SignalAlias(SignalAlias), -} + SignalAlias(SignalAlias)} struct Scope { - name : String, - signals : Vec, - scopes : Vec, -} + name : String, + child_signals : Vec, + child_scopes : Vec} struct VCD { - metadata : Metadata, - top_scopes : Vec + metadata : Metadata, + all_signals : Vec, + // the root scope should always be placed at index 0 + all_scopes : Vec} + +#[derive(Debug)] +enum Date_Parser_State {Weekday, Month, Day, HHMMSS, Year} +#[derive(Debug)] +enum VCD_Parser_State { + Begin, + Date(Date_Parser_State), + Signal_Tree, Values} + +struct DateBuffer { + Weekday : String, + Month : String, + Day : String, + HHMMSS : String, + Year : String} + +struct VCD_Parser<'a> { + vcd_parser_state : VCD_Parser_State, + date_parser_state : Date_Parser_State, + date_buffer : DateBuffer, + + vcd : &'a VCD, + curr_scope : &'a Scope, + curr_parent_scope : &'a Scope} + +impl VCD { + pub fn new() -> Self { + let dt = Utc + .datetime_from_str("Thu Jan 1 00:00:00 1970", "%a %b %e %T %Y") + .unwrap(); + let metadata = Metadata { + date : dt, + version : "".to_string(), + timescale : Timescale::ps}; + let signal = Vec::::new(); + VCD { + metadata : metadata, + all_signals : Vec::::new(), + all_scopes : Vec::::new()}}} + +impl<'a> VCD_Parser<'a> { + pub fn new(&mut self, vcd : &'a VCD) { + self.vcd_parser_state = VCD_Parser_State::Begin; + self.date_parser_state = Date_Parser_State::Weekday; + self.vcd = vcd;} + + pub fn parse_word(&mut self, word : &str) -> Result<(), String> { + let mut state = &mut self.vcd_parser_state; + match state { + VCD_Parser_State::Begin => { + match word { + "$date" => {*state = VCD_Parser_State::Date(Date_Parser_State::Weekday); Ok(())}, + // "$version" => {*state = VCD_Parser_State::VERSION_ENTER; Ok(())}, + // "$timescale" => {*state = VCD_Parser_State::TIMESCALE_ENTER; Ok(())}, + _ => Err(format!("unsure what to do with {word:?}"))}}, + + VCD_Parser_State::Date(Date_Parser_State) => { + let res = self.parse_date(word); Ok(()) + } + _ => Err(format!("parser in bad state : {state:?}"))} + } + + pub fn parse_date(&mut self, word : &str) -> Result<(), String> { + let mut state = &mut self.date_parser_state; + Ok(()) + } } - -enum VCD_Parser_State {Date, Version, Timescale, SignalTree, Values} -enum Date_Parser_State {Date, Day, Month, HHMMSS, Year} - -fn parse_vcd(word: &str, mut state : VCD_Parser_State) {} -fn parse_date(word : &str, mut state : Date_Parser_State) {} +fn advance_VCD_parser_FSM(word: &str, mut state : VCD_Parser_State) {} +fn advance_Date_parser_FSM(word : &str, mut state : Date_Parser_State) {} fn yield_word_and_apply(file : File, mut f : impl FnMut(&str)) { let mut reader = io::BufReader::new(file); -- 2.47.1 From c471c828940b9c1ef1572143717b3e45150a45b9 Mon Sep 17 00:00:00 2001 From: Yehowshua Immanuel Date: Sat, 21 May 2022 15:22:05 -0400 Subject: [PATCH 08/50] This is starting to go somewhere and needs a re-factor --- src/main.rs | 24 ++++++++++++++++++------ 1 file changed, 18 insertions(+), 6 deletions(-) diff --git a/src/main.rs b/src/main.rs index a869248..324bffa 100644 --- a/src/main.rs +++ b/src/main.rs @@ -105,15 +105,27 @@ impl<'a> VCD_Parser<'a> { // "$timescale" => {*state = VCD_Parser_State::TIMESCALE_ENTER; Ok(())}, _ => Err(format!("unsure what to do with {word:?}"))}}, - VCD_Parser_State::Date(Date_Parser_State) => { - let res = self.parse_date(word); Ok(()) - } + VCD_Parser_State::Date(_) => self.parse_date(word), _ => Err(format!("parser in bad state : {state:?}"))} } pub fn parse_date(&mut self, word : &str) -> Result<(), String> { - let mut state = &mut self.date_parser_state; - Ok(()) + let mut state = &mut self.vcd_parser_state; + match state { + VCD_Parser_State::Date(Date_Parser_State::Weekday) => + { + self.date_buffer.Weekday = word.to_string(); + *state = VCD_Parser_State::Date(Date_Parser_State::Month); + Ok(()) + } + VCD_Parser_State::Date(Date_Parser_State::Month) => + { + self.date_buffer.Month = word.to_string(); + *state = VCD_Parser_State::Date(Date_Parser_State::Day); + Ok(()) + } + _ => Err(format!("unsure what to do with {state:?}")), + } } } @@ -159,4 +171,4 @@ fn main() -> std::io::Result<()> { yield_word_and_apply(file, |word| {word_count += 1}); dbg!(word_count); Ok(()) -} +} \ No newline at end of file -- 2.47.1 From e475bf78db11a3d38dea7b5f687a194272410b44 Mon Sep 17 00:00:00 2001 From: Yehowshua Immanuel Date: Sat, 21 May 2022 15:23:33 -0400 Subject: [PATCH 09/50] fix README --- README.md | 60 +++++++++++++++++++++++++++---------------------------- 1 file changed, 30 insertions(+), 30 deletions(-) diff --git a/README.md b/README.md index 3bf6430..97b645f 100644 --- a/README.md +++ b/README.md @@ -33,33 +33,33 @@ The first build of the program may take some time. - [ ] move while loop into word yielding iterator # Files -./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 -./test-vcd-files/xilinx_isim/test2x2_regex22_string1.vcd \ No newline at end of file + - ./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 + - ./test-vcd-files/xilinx_isim/test2x2_regex22_string1.vcd \ No newline at end of file -- 2.47.1 From 164ab0922abf63b45267c2f0c593a2d0e0033a3e Mon Sep 17 00:00:00 2001 From: Yehowshua Immanuel Date: Sat, 21 May 2022 17:55:27 -0400 Subject: [PATCH 10/50] add disclaimer --- README.md | 3 +++ 1 file changed, 3 insertions(+) diff --git a/README.md b/README.md index 97b645f..941ab34 100644 --- a/README.md +++ b/README.md @@ -1,3 +1,6 @@ +# Disclaimer +PROPRIETARY - Copyright - Yehowshua Immanuel + # The Beginnings of a high-performance, low memory footprint VCD Viewer in Rust for massive multi-GB waveforms ## Features -- 2.47.1 From 594f603cbb30a191c3fa02c0da60af86df3b1141 Mon Sep 17 00:00:00 2001 From: Yehowshua Immanuel Date: Sat, 21 May 2022 20:40:46 -0400 Subject: [PATCH 11/50] date now presumably parseable --- README.md | 6 ++++-- src/main.rs | 49 ++++++++++++++++++++++++++++++++++++++++++++----- 2 files changed, 48 insertions(+), 7 deletions(-) diff --git a/README.md b/README.md index 941ab34..e7da2bd 100644 --- a/README.md +++ b/README.md @@ -3,10 +3,12 @@ PROPRIETARY - Copyright - Yehowshua Immanuel # The Beginnings of a high-performance, low memory footprint VCD Viewer in Rust for massive multi-GB waveforms -## Features +## Current Features - very fast - - loads 200MB of VCD waveform per second on an 8 core 2017 desktop CPU with NVMe storage + - loads 400MB of VCD waveform per second on an 8 core 2017 desktop CPU with NVMe storage - consumes roughly between 10 - 50MB of memory per GB of waveform + +## Planed Features - elegant/pretty UI - can be easily ported to work in browser via webassembly - allows high-performance custom Rust plugins to manipulate and diff --git a/src/main.rs b/src/main.rs index 324bffa..71672c9 100644 --- a/src/main.rs +++ b/src/main.rs @@ -52,11 +52,14 @@ struct VCD { #[derive(Debug)] enum Date_Parser_State {Weekday, Month, Day, HHMMSS, Year} + #[derive(Debug)] enum VCD_Parser_State { Begin, Date(Date_Parser_State), - Signal_Tree, Values} + Parse_Version, + Parse_Signal_Tree, + Parse_Signal_Values} struct DateBuffer { Weekday : String, @@ -70,7 +73,7 @@ struct VCD_Parser<'a> { date_parser_state : Date_Parser_State, date_buffer : DateBuffer, - vcd : &'a VCD, + vcd : &'a mut VCD, curr_scope : &'a Scope, curr_parent_scope : &'a Scope} @@ -90,7 +93,7 @@ impl VCD { all_scopes : Vec::::new()}}} impl<'a> VCD_Parser<'a> { - pub fn new(&mut self, vcd : &'a VCD) { + pub fn new(&mut self, vcd : &'a mut VCD) { self.vcd_parser_state = VCD_Parser_State::Begin; self.date_parser_state = Date_Parser_State::Weekday; self.vcd = vcd;} @@ -100,7 +103,11 @@ impl<'a> VCD_Parser<'a> { match state { VCD_Parser_State::Begin => { match word { - "$date" => {*state = VCD_Parser_State::Date(Date_Parser_State::Weekday); Ok(())}, + "$date" => + { + *state = VCD_Parser_State::Date(Date_Parser_State::Weekday); + Ok(()) + } // "$version" => {*state = VCD_Parser_State::VERSION_ENTER; Ok(())}, // "$timescale" => {*state = VCD_Parser_State::TIMESCALE_ENTER; Ok(())}, _ => Err(format!("unsure what to do with {word:?}"))}}, @@ -124,7 +131,39 @@ impl<'a> VCD_Parser<'a> { *state = VCD_Parser_State::Date(Date_Parser_State::Day); Ok(()) } - _ => Err(format!("unsure what to do with {state:?}")), + VCD_Parser_State::Date(Date_Parser_State::Day) => + { + self.date_buffer.Day = word.to_string(); + *state = VCD_Parser_State::Date(Date_Parser_State::HHMMSS); + Ok(()) + } + VCD_Parser_State::Date(Date_Parser_State::HHMMSS) => + { + self.date_buffer.HHMMSS = word.to_string(); + *state = VCD_Parser_State::Date(Date_Parser_State::Year); + Ok(()) + } + VCD_Parser_State::Date(Date_Parser_State::Year) => + { + self.date_buffer.Year = word.to_string(); + + // now that we've successfully parsed all the date information, + // we store it to a d + let weekday = &self.date_buffer.Weekday; + let month = &self.date_buffer.Month; + let day = &self.date_buffer.Day; + let hhmmss = &self.date_buffer.HHMMSS; + let year = &self.date_buffer.Year; + + let date = &format!("{weekday} {month} {day} {hhmmss} {year}")[..]; + let dt = Utc.datetime_from_str(date, "%a %b %e %T %Y").unwrap(); + + self.vcd.metadata.date = dt; + + *state = VCD_Parser_State::Parse_Version; + Ok(()) + } + _ => Err(format!("{state:?} should be unreachable within DateParser.")), } } } -- 2.47.1 From 2a2eb8669b3efc6ee62b585970497392d2ac23d3 Mon Sep 17 00:00:00 2001 From: Yehowshua Immanuel Date: Sun, 22 May 2022 23:00:03 -0400 Subject: [PATCH 12/50] state machine seems to be working --- README.md | 6 +- src/main.rs | 159 ++++++++++++++++++++++++++++++++-------------------- 2 files changed, 98 insertions(+), 67 deletions(-) diff --git a/README.md b/README.md index e7da2bd..77b2fe9 100644 --- a/README.md +++ b/README.md @@ -26,17 +26,13 @@ The first build of the program may take some time. # TODO - [x] We need a way to merge lines. - - [ ] Need to perform signal aliasing - - use vec of enum {Sig, Alias} + - [ ] Include line and possible column numbers - [ ] Should insert nodes in BFS order - [ ] Change states to lowercase - [ ] We need to start regression testing the parser over all files - [ ] Take a look at GTKWave parser to compare effificiency. - [ ] Send survey to community channel. -### May 18 - - [ ] move while loop into word yielding iterator - # Files - ./test-vcd-files/aldec/SPI_Write.vcd - ./test-vcd-files/ghdl/alu.vcd diff --git a/src/main.rs b/src/main.rs index 71672c9..5815ffe 100644 --- a/src/main.rs +++ b/src/main.rs @@ -16,34 +16,46 @@ struct Cli { // TODO: implement any timescales greater than a second -enum Timescale {ps, ns, us, ms, s} +#[derive(Debug)] +enum Timescale {ps, ns, us, ms, s, unit} +#[derive(Debug)] struct Scope_Idx(usize); + +#[derive(Debug)] struct Signal_Idx(usize); +#[derive(Debug)] +enum Date {No_Date, Date(DateTime)} + +#[derive(Debug)] +enum Version {No_Version, Version(String)} + +#[derive(Debug)] struct Metadata { - date : DateTime, - version : String, + date : Date, + version : Version, timescale : Timescale} -struct Signal { - name : String, - timeline : BTreeMap, - scope_parent : Scope_Idx} - -struct SignalAlias { - name : String, - signal_alias : Signal_Idx} - +#[derive(Debug)] enum SignalGeneric{ - Signal(Signal), - SignalAlias(SignalAlias)} + Signal{ + name : String, + timeline : BTreeMap, + scope_parent : Scope_Idx}, + SignalAlias{ + name : String, + signal_alias : Signal_Idx} +} +#[derive(Debug)] struct Scope { name : String, child_signals : Vec, child_scopes : Vec} + +#[derive(Debug)] struct VCD { metadata : Metadata, all_signals : Vec, @@ -51,7 +63,8 @@ struct VCD { all_scopes : Vec} #[derive(Debug)] -enum Date_Parser_State {Weekday, Month, Day, HHMMSS, Year} +enum Date_Parser_State {Weekday, Month, Day, HHMMSS, Year, End} + #[derive(Debug)] enum VCD_Parser_State { @@ -62,11 +75,11 @@ enum VCD_Parser_State { Parse_Signal_Values} struct DateBuffer { - Weekday : String, - Month : String, - Day : String, - HHMMSS : String, - Year : String} + Weekday : Option, + Month : Option, + Day : Option, + HHMMSS : Option, + Year : Option} struct VCD_Parser<'a> { vcd_parser_state : VCD_Parser_State, @@ -74,8 +87,8 @@ struct VCD_Parser<'a> { date_buffer : DateBuffer, vcd : &'a mut VCD, - curr_scope : &'a Scope, - curr_parent_scope : &'a Scope} + curr_scope : Option<&'a Scope>, + curr_parent_scope : Option<&'a Scope>} impl VCD { pub fn new() -> Self { @@ -83,9 +96,9 @@ impl VCD { .datetime_from_str("Thu Jan 1 00:00:00 1970", "%a %b %e %T %Y") .unwrap(); let metadata = Metadata { - date : dt, - version : "".to_string(), - timescale : Timescale::ps}; + date : Date::No_Date, + version : Version::No_Version, + timescale : Timescale::unit}; let signal = Vec::::new(); VCD { metadata : metadata, @@ -93,27 +106,40 @@ impl VCD { all_scopes : Vec::::new()}}} impl<'a> VCD_Parser<'a> { - pub fn new(&mut self, vcd : &'a mut VCD) { - self.vcd_parser_state = VCD_Parser_State::Begin; - self.date_parser_state = Date_Parser_State::Weekday; - self.vcd = vcd;} + pub fn new(vcd : &'a mut VCD) -> Self { + let date_buffer = DateBuffer{ + Weekday : None, + Month : None, + Day : None, + HHMMSS : None, + Year : None + }; + VCD_Parser { + vcd_parser_state : VCD_Parser_State ::Begin, + date_parser_state : Date_Parser_State::Weekday, + date_buffer : date_buffer, + vcd : vcd, + curr_scope : None, + curr_parent_scope : None + + } + } pub fn parse_word(&mut self, word : &str) -> Result<(), String> { let mut state = &mut self.vcd_parser_state; + let t = &self.vcd; match state { - VCD_Parser_State::Begin => { + VCD_Parser_State::Begin => match word { - "$date" => - { - *state = VCD_Parser_State::Date(Date_Parser_State::Weekday); - Ok(()) - } - // "$version" => {*state = VCD_Parser_State::VERSION_ENTER; Ok(())}, - // "$timescale" => {*state = VCD_Parser_State::TIMESCALE_ENTER; Ok(())}, - _ => Err(format!("unsure what to do with {word:?}"))}}, - + "$date" => {*state = VCD_Parser_State::Date(Date_Parser_State::Weekday); Ok(())} + _ => Err(format!("unsure what to do with {word:?} in state `{state:?}`")) + } VCD_Parser_State::Date(_) => self.parse_date(word), - _ => Err(format!("parser in bad state : {state:?}"))} + // TODO : Enable the following in production + // _ => Err(format!("parser in bad state : {state:?}"))TODO : Disable the following in production + // TODO : Disable the following in production + _ => Err(format!("parser in bad state : {state:?}; {t:?}")) + } } pub fn parse_date(&mut self, word : &str) -> Result<(), String> { @@ -121,48 +147,57 @@ impl<'a> VCD_Parser<'a> { match state { VCD_Parser_State::Date(Date_Parser_State::Weekday) => { - self.date_buffer.Weekday = word.to_string(); + self.date_buffer.Weekday = Some(word.to_string()); *state = VCD_Parser_State::Date(Date_Parser_State::Month); Ok(()) } VCD_Parser_State::Date(Date_Parser_State::Month) => { - self.date_buffer.Month = word.to_string(); + self.date_buffer.Month = Some(word.to_string()); *state = VCD_Parser_State::Date(Date_Parser_State::Day); Ok(()) } VCD_Parser_State::Date(Date_Parser_State::Day) => { - self.date_buffer.Day = word.to_string(); + self.date_buffer.Day = Some(word.to_string()); *state = VCD_Parser_State::Date(Date_Parser_State::HHMMSS); Ok(()) } VCD_Parser_State::Date(Date_Parser_State::HHMMSS) => { - self.date_buffer.HHMMSS = word.to_string(); + self.date_buffer.HHMMSS = Some(word.to_string()); *state = VCD_Parser_State::Date(Date_Parser_State::Year); Ok(()) } VCD_Parser_State::Date(Date_Parser_State::Year) => { - self.date_buffer.Year = word.to_string(); + self.date_buffer.Year = Some(word.to_string()); // now that we've successfully parsed all the date information, - // we store it to a d - let weekday = &self.date_buffer.Weekday; - let month = &self.date_buffer.Month; - let day = &self.date_buffer.Day; - let hhmmss = &self.date_buffer.HHMMSS; - let year = &self.date_buffer.Year; + // we store it to the metadata.date struct + let weekday = &self.date_buffer.Weekday.as_ref().unwrap(); + let month = &self.date_buffer.Month.as_ref().unwrap(); + let day = &self.date_buffer.Day.as_ref().unwrap(); + let hhmmss = &self.date_buffer.HHMMSS.as_ref().unwrap(); + let year = &self.date_buffer.Year.as_ref().unwrap(); let date = &format!("{weekday} {month} {day} {hhmmss} {year}")[..]; - let dt = Utc.datetime_from_str(date, "%a %b %e %T %Y").unwrap(); + let dt = Utc.datetime_from_str(date, "%a %b %e %T %Y") + .expect(&format!("invalid date {date}")[..]); - self.vcd.metadata.date = dt; + self.vcd.metadata.date = Date::Date(dt); - *state = VCD_Parser_State::Parse_Version; + *state = VCD_Parser_State::Date(Date_Parser_State::End); Ok(()) } + VCD_Parser_State::Date(Date_Parser_State::End) => + { + let expected_word = "$end"; + match word { + expected_word => {*state = VCD_Parser_State::Parse_Version; Ok(())} + _ => Err(format!("expected `{expected_word}` but found `{word}`")) + } + } _ => Err(format!("{state:?} should be unreachable within DateParser.")), } } @@ -171,11 +206,10 @@ impl<'a> VCD_Parser<'a> { fn advance_VCD_parser_FSM(word: &str, mut state : VCD_Parser_State) {} fn advance_Date_parser_FSM(word : &str, mut state : Date_Parser_State) {} -fn yield_word_and_apply(file : File, mut f : impl FnMut(&str)) { +fn yield_word_and_apply(file : File, mut f : impl FnMut(&str) -> Result<(), String>) { let mut reader = io::BufReader::new(file); let mut buffer = String::new(); - let mut word_count = 0u64; let mut EOF = false; let line_chunk_size = 25; @@ -191,7 +225,7 @@ fn yield_word_and_apply(file : File, mut f : impl FnMut(&str)) { let words = buffer.split_ascii_whitespace(); for word in words { - f(word); + f(word).unwrap(); } buffer.clear(); @@ -202,12 +236,13 @@ fn yield_word_and_apply(file : File, mut f : impl FnMut(&str)) { fn main() -> std::io::Result<()> { let args = Cli::parse(); - // let dt = Utc.datetime_from_str("Fri Nov 28 12:00:09 2014", "%a %b %e %T %Y"); - let file = File::open(&args.path)?; - let mut word_count = 0; - yield_word_and_apply(file, |word| {word_count += 1}); - dbg!(word_count); + let mut vcd = VCD::new(); + let mut parser = VCD_Parser::new(&mut vcd); + + yield_word_and_apply(file, |word| {parser.parse_word(word)}); + dbg!(&vcd); + Ok(()) } \ No newline at end of file -- 2.47.1 From d22418cf2bc01ba74a54e2bdd414124f774de7f2 Mon Sep 17 00:00:00 2001 From: Yehowshua Immanuel Date: Mon, 23 May 2022 19:19:17 -0400 Subject: [PATCH 13/50] cleaner types --- src/main.rs | 29 +++++++++++++++-------------- 1 file changed, 15 insertions(+), 14 deletions(-) diff --git a/src/main.rs b/src/main.rs index 5815ffe..296405a 100644 --- a/src/main.rs +++ b/src/main.rs @@ -26,15 +26,12 @@ struct Scope_Idx(usize); struct Signal_Idx(usize); #[derive(Debug)] -enum Date {No_Date, Date(DateTime)} - -#[derive(Debug)] -enum Version {No_Version, Version(String)} +struct Version(String); #[derive(Debug)] struct Metadata { - date : Date, - version : Version, + date : Option>, + version : Option, timescale : Timescale} #[derive(Debug)] @@ -62,15 +59,18 @@ struct VCD { // the root scope should always be placed at index 0 all_scopes : Vec} +// TODO : Date_PArser_State -> Parse_Date #[derive(Debug)] enum Date_Parser_State {Weekday, Month, Day, HHMMSS, Year, End} +#[derive(Debug)] +enum Version_Parser_State {Parsing, Done} #[derive(Debug)] enum VCD_Parser_State { Begin, Date(Date_Parser_State), - Parse_Version, + Parse_Version(Version_Parser_State), Parse_Signal_Tree, Parse_Signal_Values} @@ -96,8 +96,8 @@ impl VCD { .datetime_from_str("Thu Jan 1 00:00:00 1970", "%a %b %e %T %Y") .unwrap(); let metadata = Metadata { - date : Date::No_Date, - version : Version::No_Version, + date : None, + version : None, timescale : Timescale::unit}; let signal = Vec::::new(); VCD { @@ -135,6 +135,7 @@ impl<'a> VCD_Parser<'a> { _ => Err(format!("unsure what to do with {word:?} in state `{state:?}`")) } VCD_Parser_State::Date(_) => self.parse_date(word), + VCD_Parser_State::Parse_Version(_) => self.parse_date(word), // TODO : Enable the following in production // _ => Err(format!("parser in bad state : {state:?}"))TODO : Disable the following in production // TODO : Disable the following in production @@ -185,7 +186,7 @@ impl<'a> VCD_Parser<'a> { let dt = Utc.datetime_from_str(date, "%a %b %e %T %Y") .expect(&format!("invalid date {date}")[..]); - self.vcd.metadata.date = Date::Date(dt); + self.vcd.metadata.date = Some(dt); *state = VCD_Parser_State::Date(Date_Parser_State::End); Ok(()) @@ -194,7 +195,10 @@ impl<'a> VCD_Parser<'a> { { let expected_word = "$end"; match word { - expected_word => {*state = VCD_Parser_State::Parse_Version; Ok(())} + expected_word => { + *state = VCD_Parser_State::Parse_Version(Version_Parser_State::Parsing); + Ok(()) + } _ => Err(format!("expected `{expected_word}` but found `{word}`")) } } @@ -203,9 +207,6 @@ impl<'a> VCD_Parser<'a> { } } -fn advance_VCD_parser_FSM(word: &str, mut state : VCD_Parser_State) {} -fn advance_Date_parser_FSM(word : &str, mut state : Date_Parser_State) {} - fn yield_word_and_apply(file : File, mut f : impl FnMut(&str) -> Result<(), String>) { let mut reader = io::BufReader::new(file); -- 2.47.1 From dad1fd2484f3ef48fb27f35c14fdb0d29ad167d3 Mon Sep 17 00:00:00 2001 From: Yehowshua Immanuel Date: Mon, 23 May 2022 23:45:14 -0400 Subject: [PATCH 14/50] notable refactoring and simplification; now able to parse version --- Cargo.toml | 3 +- src/main.rs | 171 ++++++++++++++++++++++++++-------------------------- 2 files changed, 87 insertions(+), 87 deletions(-) diff --git a/Cargo.toml b/Cargo.toml index 64aa6cf..05b725b 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -8,4 +8,5 @@ edition = "2021" [dependencies] num = "0.4" clap = { version = "3.1.8", features = ["derive"] } -chrono = "0.4" \ No newline at end of file +chrono = "0.4" +function_name = "0.3.0" \ No newline at end of file diff --git a/src/main.rs b/src/main.rs index 296405a..4c4281f 100644 --- a/src/main.rs +++ b/src/main.rs @@ -4,6 +4,7 @@ use std::fs::File; use std::collections::BTreeMap; use chrono::prelude::*; use std::rc::Rc; +use ::function_name::named; use num::*; use clap::Parser; @@ -59,32 +60,25 @@ struct VCD { // the root scope should always be placed at index 0 all_scopes : Vec} -// TODO : Date_PArser_State -> Parse_Date #[derive(Debug)] -enum Date_Parser_State {Weekday, Month, Day, HHMMSS, Year, End} +enum Date_Parser_State {Begin, Parsing} #[derive(Debug)] -enum Version_Parser_State {Parsing, Done} +enum Version_Parser_State {Begin, Parsing} +#[derive(Debug)] +enum Timescale_Parser_State {Begin, Parsing} #[derive(Debug)] -enum VCD_Parser_State { - Begin, +enum Parser_State { Date(Date_Parser_State), - Parse_Version(Version_Parser_State), + Version(Version_Parser_State), + Timescale(Timescale_Parser_State), Parse_Signal_Tree, Parse_Signal_Values} -struct DateBuffer { - Weekday : Option, - Month : Option, - Day : Option, - HHMMSS : Option, - Year : Option} - struct VCD_Parser<'a> { - vcd_parser_state : VCD_Parser_State, - date_parser_state : Date_Parser_State, - date_buffer : DateBuffer, + vcd_parser_state : Parser_State, + buffer : Option, vcd : &'a mut VCD, curr_scope : Option<&'a Scope>, @@ -107,21 +101,13 @@ impl VCD { impl<'a> VCD_Parser<'a> { pub fn new(vcd : &'a mut VCD) -> Self { - let date_buffer = DateBuffer{ - Weekday : None, - Month : None, - Day : None, - HHMMSS : None, - Year : None - }; VCD_Parser { - vcd_parser_state : VCD_Parser_State ::Begin, - date_parser_state : Date_Parser_State::Weekday, - date_buffer : date_buffer, + vcd_parser_state : Parser_State::Date(Date_Parser_State::Begin), + + buffer : None, vcd : vcd, curr_scope : None, curr_parent_scope : None - } } @@ -129,13 +115,8 @@ impl<'a> VCD_Parser<'a> { let mut state = &mut self.vcd_parser_state; let t = &self.vcd; match state { - VCD_Parser_State::Begin => - match word { - "$date" => {*state = VCD_Parser_State::Date(Date_Parser_State::Weekday); Ok(())} - _ => Err(format!("unsure what to do with {word:?} in state `{state:?}`")) - } - VCD_Parser_State::Date(_) => self.parse_date(word), - VCD_Parser_State::Parse_Version(_) => self.parse_date(word), + Parser_State::Date(_) => self.parse_date(word), + Parser_State::Version(_) => self.parse_version(word), // TODO : Enable the following in production // _ => Err(format!("parser in bad state : {state:?}"))TODO : Disable the following in production // TODO : Disable the following in production @@ -143,66 +124,84 @@ impl<'a> VCD_Parser<'a> { } } + #[named] pub fn parse_date(&mut self, word : &str) -> Result<(), String> { let mut state = &mut self.vcd_parser_state; match state { - VCD_Parser_State::Date(Date_Parser_State::Weekday) => - { - self.date_buffer.Weekday = Some(word.to_string()); - *state = VCD_Parser_State::Date(Date_Parser_State::Month); - Ok(()) - } - VCD_Parser_State::Date(Date_Parser_State::Month) => - { - self.date_buffer.Month = Some(word.to_string()); - *state = VCD_Parser_State::Date(Date_Parser_State::Day); - Ok(()) - } - VCD_Parser_State::Date(Date_Parser_State::Day) => - { - self.date_buffer.Day = Some(word.to_string()); - *state = VCD_Parser_State::Date(Date_Parser_State::HHMMSS); - Ok(()) - } - VCD_Parser_State::Date(Date_Parser_State::HHMMSS) => - { - self.date_buffer.HHMMSS = Some(word.to_string()); - *state = VCD_Parser_State::Date(Date_Parser_State::Year); - Ok(()) - } - VCD_Parser_State::Date(Date_Parser_State::Year) => - { - self.date_buffer.Year = Some(word.to_string()); - - // now that we've successfully parsed all the date information, - // we store it to the metadata.date struct - let weekday = &self.date_buffer.Weekday.as_ref().unwrap(); - let month = &self.date_buffer.Month.as_ref().unwrap(); - let day = &self.date_buffer.Day.as_ref().unwrap(); - let hhmmss = &self.date_buffer.HHMMSS.as_ref().unwrap(); - let year = &self.date_buffer.Year.as_ref().unwrap(); - - let date = &format!("{weekday} {month} {day} {hhmmss} {year}")[..]; - let dt = Utc.datetime_from_str(date, "%a %b %e %T %Y") - .expect(&format!("invalid date {date}")[..]); - - self.vcd.metadata.date = Some(dt); - - *state = VCD_Parser_State::Date(Date_Parser_State::End); - Ok(()) - } - VCD_Parser_State::Date(Date_Parser_State::End) => - { - let expected_word = "$end"; + Parser_State::Date(Date_Parser_State::Begin) => match word { - expected_word => { - *state = VCD_Parser_State::Parse_Version(Version_Parser_State::Parsing); + "$date" => { + *state = Parser_State::Date(Date_Parser_State::Parsing); + Ok(()) + } + _ => { + *state = Parser_State::Version(Version_Parser_State::Begin); + self.parse_version(word); Ok(()) } - _ => Err(format!("expected `{expected_word}` but found `{word}`")) } + Parser_State::Date(Date_Parser_State::Parsing) => + match word { + "$end" => { + *state = Parser_State::Version(Version_Parser_State::Begin); + let s = self.buffer.take().unwrap(); + let dt = Utc.datetime_from_str(s.as_str(), "%a %b %e %T %Y") + .expect(&format!("invalid date {s}").as_str()); + self.vcd.metadata.date = Some(dt); + Ok(()) + } + _ => { + if let Some(ref mut buffer) = self.buffer { + buffer.push_str(" "); + buffer.push_str(word); + } + else { + self.buffer = Some(word.to_string()); + } + Ok(()) + } } - _ => Err(format!("{state:?} should be unreachable within DateParser.")), + _ => Err(format!("{state:?} should be unreachable within {}.",function_name!())), + + } + } + + #[named] + pub fn parse_version(&mut self, word : &str) -> Result<(), String> { + let mut state = &mut self.vcd_parser_state; + match state { + Parser_State::Version(Version_Parser_State::Begin) => + match word { + "$version" => { + *state = Parser_State::Version(Version_Parser_State::Parsing); + Ok(()) + } + _ => { + *state = Parser_State::Timescale(Timescale_Parser_State::Begin); + Ok(()) + } + } + Parser_State::Version(Version_Parser_State::Parsing) => + match word { + "$end" => { + *state = Parser_State::Timescale(Timescale_Parser_State::Begin); + let s = self.buffer.take().unwrap(); + self.vcd.metadata.version = Some(Version(s)); + Ok(()) + } + _ => { + if let Some(ref mut buffer) = self.buffer { + buffer.push_str(" "); + buffer.push_str(word); + } + else { + self.buffer = Some(word.to_string()); + } + Ok(()) + } + } + _ => Err(format!("{state:?} should be unreachable within {}.",function_name!())), + } } } -- 2.47.1 From cbafc89ab80fd910d8d17bc6574247622c41b115 Mon Sep 17 00:00:00 2001 From: Yehowshua Immanuel Date: Mon, 23 May 2022 23:59:57 -0400 Subject: [PATCH 15/50] shutting down for the night --- README.md | 7 ++++++- src/main.rs | 17 ++++++++--------- 2 files changed, 14 insertions(+), 10 deletions(-) diff --git a/README.md b/README.md index 77b2fe9..76499fc 100644 --- a/README.md +++ b/README.md @@ -26,13 +26,18 @@ The first build of the program may take some time. # TODO - [x] We need a way to merge lines. + - [ ] Consider what to do with don't care values + will probably just convert them to strings for now. + - [ ] Test for speed and see if stream of bytes is helpful - [ ] Include line and possible column numbers - - [ ] Should insert nodes in BFS order - [ ] Change states to lowercase - [ ] We need to start regression testing the parser over all files - [ ] Take a look at GTKWave parser to compare effificiency. - [ ] Send survey to community channel. +# Probably No Longer Needed + - [ ] Should insert nodes in BFS order + # Files - ./test-vcd-files/aldec/SPI_Write.vcd - ./test-vcd-files/ghdl/alu.vcd diff --git a/src/main.rs b/src/main.rs index 4c4281f..6b3391c 100644 --- a/src/main.rs +++ b/src/main.rs @@ -3,7 +3,6 @@ use std::io; use std::fs::File; use std::collections::BTreeMap; use chrono::prelude::*; -use std::rc::Rc; use ::function_name::named; use num::*; @@ -86,18 +85,16 @@ struct VCD_Parser<'a> { impl VCD { pub fn new() -> Self { - let dt = Utc - .datetime_from_str("Thu Jan 1 00:00:00 1970", "%a %b %e %T %Y") - .unwrap(); let metadata = Metadata { date : None, version : None, timescale : Timescale::unit}; - let signal = Vec::::new(); VCD { metadata : metadata, all_signals : Vec::::new(), - all_scopes : Vec::::new()}}} + all_scopes : Vec::::new()} + } + } impl<'a> VCD_Parser<'a> { pub fn new(vcd : &'a mut VCD) -> Self { @@ -120,7 +117,9 @@ impl<'a> VCD_Parser<'a> { // TODO : Enable the following in production // _ => Err(format!("parser in bad state : {state:?}"))TODO : Disable the following in production // TODO : Disable the following in production - _ => Err(format!("parser in bad state : {state:?}; {t:?}")) + _ => { + Err(format!("parser in bad state : {state:?}; {t:?}")) + } } } @@ -136,8 +135,7 @@ impl<'a> VCD_Parser<'a> { } _ => { *state = Parser_State::Version(Version_Parser_State::Begin); - self.parse_version(word); - Ok(()) + self.parse_version(word) } } Parser_State::Date(Date_Parser_State::Parsing) => @@ -178,6 +176,7 @@ impl<'a> VCD_Parser<'a> { } _ => { *state = Parser_State::Timescale(Timescale_Parser_State::Begin); + // TODO : add fallthrough to timescale Ok(()) } } -- 2.47.1 From 46683ae87b3d667ea29dcbebc5c63e9fca969b3b Mon Sep 17 00:00:00 2001 From: Yehowshua Immanuel Date: Fri, 27 May 2022 20:48:17 -0400 Subject: [PATCH 16/50] now parses timelines --- src/main.rs | 74 +++++++++++++++++++++++++++++++++++++++++++++++------ 1 file changed, 66 insertions(+), 8 deletions(-) diff --git a/src/main.rs b/src/main.rs index 6b3391c..d20cb75 100644 --- a/src/main.rs +++ b/src/main.rs @@ -32,7 +32,7 @@ struct Version(String); struct Metadata { date : Option>, version : Option, - timescale : Timescale} + timescale : (Option, Timescale)} #[derive(Debug)] enum SignalGeneric{ @@ -65,6 +65,8 @@ enum Date_Parser_State {Begin, Parsing} enum Version_Parser_State {Begin, Parsing} #[derive(Debug)] enum Timescale_Parser_State {Begin, Parsing} +#[derive(Debug)] +enum Signal_Tree_Parser_State {Begin, Parsing} #[derive(Debug)] @@ -72,7 +74,7 @@ enum Parser_State { Date(Date_Parser_State), Version(Version_Parser_State), Timescale(Timescale_Parser_State), - Parse_Signal_Tree, + Signal_Tree(Signal_Tree_Parser_State), Parse_Signal_Values} struct VCD_Parser<'a> { @@ -88,7 +90,7 @@ impl VCD { let metadata = Metadata { date : None, version : None, - timescale : Timescale::unit}; + timescale : (None, Timescale::unit)}; VCD { metadata : metadata, all_signals : Vec::::new(), @@ -114,8 +116,9 @@ impl<'a> VCD_Parser<'a> { match state { Parser_State::Date(_) => self.parse_date(word), Parser_State::Version(_) => self.parse_version(word), + Parser_State::Timescale(_) => self.parse_timescale(word), // TODO : Enable the following in production - // _ => Err(format!("parser in bad state : {state:?}"))TODO : Disable the following in production + // _ => Err(format!("parser in bad state : {state:?}")) // TODO : Disable the following in production _ => { Err(format!("parser in bad state : {state:?}; {t:?}")) @@ -141,10 +144,10 @@ impl<'a> VCD_Parser<'a> { Parser_State::Date(Date_Parser_State::Parsing) => match word { "$end" => { - *state = Parser_State::Version(Version_Parser_State::Begin); let s = self.buffer.take().unwrap(); let dt = Utc.datetime_from_str(s.as_str(), "%a %b %e %T %Y") - .expect(&format!("invalid date {s}").as_str()); + .expect(&format!("invalid date {s}").as_str()); + *state = Parser_State::Version(Version_Parser_State::Begin); self.vcd.metadata.date = Some(dt); Ok(()) } @@ -176,16 +179,71 @@ impl<'a> VCD_Parser<'a> { } _ => { *state = Parser_State::Timescale(Timescale_Parser_State::Begin); - // TODO : add fallthrough to timescale Ok(()) } } Parser_State::Version(Version_Parser_State::Parsing) => match word { "$end" => { - *state = Parser_State::Timescale(Timescale_Parser_State::Begin); let s = self.buffer.take().unwrap(); self.vcd.metadata.version = Some(Version(s)); + *state = Parser_State::Timescale(Timescale_Parser_State::Begin); + Ok(()) + } + _ => { + if let Some(ref mut buffer) = self.buffer { + buffer.push_str(" "); + buffer.push_str(word); + } + else { + self.buffer = Some(word.to_string()); + } + Ok(()) + } + } + _ => Err(format!("{state:?} should be unreachable within {}.",function_name!())), + + } + } + + #[named] + pub fn parse_timescale(&mut self, word : &str) -> Result<(), String> { + let mut state = &mut self.vcd_parser_state; + match state { + Parser_State::Timescale(Timescale_Parser_State::Begin) => + match word { + "$timescale" => { + *state = Parser_State::Timescale(Timescale_Parser_State::Parsing); + Ok(()) + } + _ => { + *state = Parser_State::Signal_Tree(Signal_Tree_Parser_State::Begin); + Ok(()) + } + } + Parser_State::Timescale(Timescale_Parser_State::Parsing) => + match word { + "$end" => { + let s = self.buffer.take().unwrap(); + let s = s.split_ascii_whitespace(); + let s = s.collect::>(); + + let scalar = s[0].to_string().parse::().unwrap(); + let unit = s[1]; + let unit = match unit { + "ps" => Ok(Timescale::ps), + "ns" => Ok(Timescale::ns), + "us" => Ok(Timescale::us), + "ms" => Ok(Timescale::ms), + "s" => Ok(Timescale::s), + // TODO : see if there is a way to easily print out all enum variants + // _ => Err(format!("{word} is not a valid unit of time in {Timescale}")) + _ => Err(format!("{unit} is not a valid unit")) + }.unwrap(); + + dbg!(s); + self.vcd.metadata.timescale = (Some(scalar), unit); + *state = Parser_State::Timescale(Timescale_Parser_State::Begin); Ok(()) } _ => { -- 2.47.1 From c04bf2273e92ef34fc3731e16187e3e0dfea9901 Mon Sep 17 00:00:00 2001 From: Yehowshua Immanuel Date: Sat, 28 May 2022 21:37:43 -0400 Subject: [PATCH 17/50] will probably abandon this --- src/main.rs | 77 +++++++++++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 72 insertions(+), 5 deletions(-) diff --git a/src/main.rs b/src/main.rs index d20cb75..8af6605 100644 --- a/src/main.rs +++ b/src/main.rs @@ -59,17 +59,17 @@ struct VCD { // the root scope should always be placed at index 0 all_scopes : Vec} -#[derive(Debug)] +#[derive(Debug, PartialEq)] enum Date_Parser_State {Begin, Parsing} -#[derive(Debug)] +#[derive(Debug, PartialEq)] enum Version_Parser_State {Begin, Parsing} -#[derive(Debug)] +#[derive(Debug, PartialEq)] enum Timescale_Parser_State {Begin, Parsing} -#[derive(Debug)] +#[derive(Debug, PartialEq)] enum Signal_Tree_Parser_State {Begin, Parsing} -#[derive(Debug)] +#[derive(Debug, PartialEq)] enum Parser_State { Date(Date_Parser_State), Version(Version_Parser_State), @@ -167,6 +167,73 @@ impl<'a> VCD_Parser<'a> { } } + #[named] + pub fn parse_statement( + &'a mut self, + curr_word : &str, + key_word : &str, + begin_state : Parser_State, + parsing_state : Parser_State, + end_state : Parser_State, + next_parser : fn(&'a mut VCD_Parser, &str) -> Result<(), String> + ) -> Result<(), String> { + let mut state = &mut self.vcd_parser_state; + + if (*state == begin_state) { + return match curr_word { + key_word => { + *state = Parser_State::Date(Date_Parser_State::Parsing); + Ok(()) + } + _ => { + *state = Parser_State::Version(Version_Parser_State::Begin); + next_parser(self, curr_word) + } + } + } + else { + Ok(()) + } + // Ok(()) + + // match state { + // Parser_State::Date(Date_Parser_State::Begin) => + // match curr_word { + // key_word => { + // *state = Parser_State::Date(Date_Parser_State::Parsing); + // Ok(()) + // } + // _ => { + // *state = Parser_State::Version(Version_Parser_State::Begin); + // self.parse_version(curr_word) + // } + // } + // Parser_State::Date(Date_Parser_State::Parsing) => + // match curr_word { + // "$end" => { + // let s = self.buffer.take().unwrap(); + // let dt = Utc.datetime_from_str(s.as_str(), "%a %b %e %T %Y") + // .expect(&format!("invalid date {s}").as_str()); + // *state = Parser_State::Version(Version_Parser_State::Begin); + // self.vcd.metadata.date = Some(dt); + // Ok(()) + // } + // _ => { + // if let Some(ref mut buffer) = self.buffer { + // buffer.push_str(" "); + // buffer.push_str(curr_word); + // } + // else { + // self.buffer = Some(curr_word.to_string()); + // } + // Ok(()) + // } + // } + // _ => Err(format!("{state:?} should be unreachable within {}.",function_name!())), + + // } + } + #[named] pub fn parse_version(&mut self, word : &str) -> Result<(), String> { let mut state = &mut self.vcd_parser_state; -- 2.47.1 From 08c505820825e9c607f741c3576c5c22f5decf7b Mon Sep 17 00:00:00 2001 From: Yehowshua Immanuel Date: Thu, 2 Jun 2022 16:51:56 -0400 Subject: [PATCH 18/50] now using pointer and string slices --- src/main.rs | 110 ++++++++++++++++++++++++++++++++++++++++++++-------- 1 file changed, 93 insertions(+), 17 deletions(-) diff --git a/src/main.rs b/src/main.rs index 8af6605..d08847f 100644 --- a/src/main.rs +++ b/src/main.rs @@ -8,6 +8,9 @@ use ::function_name::named; use num::*; use clap::Parser; +use std::slice; +use std::str; + #[derive(Parser)] struct Cli { /// The path to the file to read @@ -330,26 +333,30 @@ impl<'a> VCD_Parser<'a> { } } -fn yield_word_and_apply(file : File, mut f : impl FnMut(&str) -> Result<(), String>) { +struct Line(u32); +struct Col(u32); +struct Position(Line, Col); + +fn yield_word_and_apply(file : File, mut f : impl FnMut(&[u8], Position) -> Result<(), String>) { let mut reader = io::BufReader::new(file); let mut buffer = String::new(); - let mut EOF = false; - let line_chunk_size = 25; - while {!EOF} { - for _ in 0..line_chunk_size { - let bytes_read = reader.read_line(&mut buffer).unwrap(); - if bytes_read == 0 { - EOF = true; - break - } - } + let mut line = 0u32; + while true { + let bytes_read = reader.read_line(&mut buffer).unwrap(); + if bytes_read == 0 {break} - let words = buffer.split_ascii_whitespace(); + line += 1; + let mut col = 1u32; + + let mut words = buffer.split_ascii_whitespace(); for word in words { - f(word).unwrap(); + let word = word.as_bytes(); + let position = Position(Line(line), Col(col)); + f(word, position).unwrap(); + col += (word.len() as u32) + 1; } buffer.clear(); @@ -357,16 +364,85 @@ fn yield_word_and_apply(file : File, mut f : impl FnMut(&str) -> Result<(), Stri } +struct YieldByWord { + reader : io::BufReader, + words : Vec, + EOF : bool, + buffer : String, + str_slices : Vec<(*const u8, usize)>, +} + +impl YieldByWord { + fn new(file : File) -> YieldByWord { + let mut reader = io::BufReader::new(file); + YieldByWord { + reader : reader, + words : vec![], + EOF : false, + buffer : "".to_string(), + str_slices : vec![], + } + } + + fn next_word(&mut self) -> Option<&str> { + // if there are no more words, attempt to read more content + // from the file + if self.str_slices.is_empty() { + self.buffer.clear(); + + if self.EOF {return None} + + let line_chunk_size = 10; + + for _ in 0..line_chunk_size { + let bytes_read = self.reader.read_line(&mut self.buffer).unwrap(); + // we hit the end of the file, so we go ahead and return None + if bytes_read == 0 {self.EOF = true} + } + + let words = self.buffer.split_ascii_whitespace(); + self.str_slices = words + .rev() + .map(|s| (s.as_ptr(), s.len())) + .collect(); + } + + // if we make it here, we return the next word + unsafe { + let (ptr, len) = self.str_slices.pop().unwrap(); + let slice = slice::from_raw_parts(ptr, len); + return Some(str::from_utf8(slice).unwrap()); + }; + } +} + fn main() -> std::io::Result<()> { let args = Cli::parse(); let file = File::open(&args.path)?; + let mut word_gen = YieldByWord::new(file); + let mut word_count = 0; + let mut last_word = String::new(); - let mut vcd = VCD::new(); - let mut parser = VCD_Parser::new(&mut vcd); + // for word in 0..5 { + // dbg!(word_gen.next_word()); + // } + while word_gen.next_word().is_some() { + word_count += 1; + } + dbg!(word_count); - yield_word_and_apply(file, |word| {parser.parse_word(word)}); - dbg!(&vcd); + // loop { + // let next_word = word_gen.next_word(); + // if next_word.is_some() { + // last_word = next_word.unwrap(); + // } + // else { + // break + // } + // } + + // dbg!(last_word); Ok(()) } \ No newline at end of file -- 2.47.1 From 43563d0d7c781be9fc1a75885b00564426d0d192 Mon Sep 17 00:00:00 2001 From: Yehowshua Immanuel Date: Thu, 2 Jun 2022 20:02:09 -0400 Subject: [PATCH 19/50] nearly as fast as wc and now yield words --- src/main.rs | 387 ++++++++-------------------------------------------- 1 file changed, 57 insertions(+), 330 deletions(-) diff --git a/src/main.rs b/src/main.rs index d08847f..db9c605 100644 --- a/src/main.rs +++ b/src/main.rs @@ -11,32 +11,32 @@ use clap::Parser; use std::slice; use std::str; +use std::collections::VecDeque; + #[derive(Parser)] struct Cli { /// The path to the file to read #[clap(parse(from_os_str))] path: std::path::PathBuf} - -// TODO: implement any timescales greater than a second -#[derive(Debug)] -enum Timescale {ps, ns, us, ms, s, unit} - -#[derive(Debug)] -struct Scope_Idx(usize); - -#[derive(Debug)] -struct Signal_Idx(usize); - #[derive(Debug)] struct Version(String); +#[derive(Debug)] +enum Timescale {ps, ns, us, ms, s, unit} + #[derive(Debug)] struct Metadata { date : Option>, version : Option, timescale : (Option, Timescale)} +#[derive(Debug)] +struct Scope_Idx(usize); + +#[derive(Debug)] +struct Signal_Idx(usize); + #[derive(Debug)] enum SignalGeneric{ Signal{ @@ -62,32 +62,6 @@ struct VCD { // the root scope should always be placed at index 0 all_scopes : Vec} -#[derive(Debug, PartialEq)] -enum Date_Parser_State {Begin, Parsing} -#[derive(Debug, PartialEq)] -enum Version_Parser_State {Begin, Parsing} -#[derive(Debug, PartialEq)] -enum Timescale_Parser_State {Begin, Parsing} -#[derive(Debug, PartialEq)] -enum Signal_Tree_Parser_State {Begin, Parsing} - - -#[derive(Debug, PartialEq)] -enum Parser_State { - Date(Date_Parser_State), - Version(Version_Parser_State), - Timescale(Timescale_Parser_State), - Signal_Tree(Signal_Tree_Parser_State), - Parse_Signal_Values} - -struct VCD_Parser<'a> { - vcd_parser_state : Parser_State, - buffer : Option, - - vcd : &'a mut VCD, - curr_scope : Option<&'a Scope>, - curr_parent_scope : Option<&'a Scope>} - impl VCD { pub fn new() -> Self { let metadata = Metadata { @@ -101,275 +75,20 @@ impl VCD { } } -impl<'a> VCD_Parser<'a> { - pub fn new(vcd : &'a mut VCD) -> Self { - VCD_Parser { - vcd_parser_state : Parser_State::Date(Date_Parser_State::Begin), - buffer : None, - vcd : vcd, - curr_scope : None, - curr_parent_scope : None - } - } - - pub fn parse_word(&mut self, word : &str) -> Result<(), String> { - let mut state = &mut self.vcd_parser_state; - let t = &self.vcd; - match state { - Parser_State::Date(_) => self.parse_date(word), - Parser_State::Version(_) => self.parse_version(word), - Parser_State::Timescale(_) => self.parse_timescale(word), - // TODO : Enable the following in production - // _ => Err(format!("parser in bad state : {state:?}")) - // TODO : Disable the following in production - _ => { - Err(format!("parser in bad state : {state:?}; {t:?}")) - } - } - } - - #[named] - pub fn parse_date(&mut self, word : &str) -> Result<(), String> { - let mut state = &mut self.vcd_parser_state; - match state { - Parser_State::Date(Date_Parser_State::Begin) => - match word { - "$date" => { - *state = Parser_State::Date(Date_Parser_State::Parsing); - Ok(()) - } - _ => { - *state = Parser_State::Version(Version_Parser_State::Begin); - self.parse_version(word) - } - } - Parser_State::Date(Date_Parser_State::Parsing) => - match word { - "$end" => { - let s = self.buffer.take().unwrap(); - let dt = Utc.datetime_from_str(s.as_str(), "%a %b %e %T %Y") - .expect(&format!("invalid date {s}").as_str()); - *state = Parser_State::Version(Version_Parser_State::Begin); - self.vcd.metadata.date = Some(dt); - Ok(()) - } - _ => { - if let Some(ref mut buffer) = self.buffer { - buffer.push_str(" "); - buffer.push_str(word); - } - else { - self.buffer = Some(word.to_string()); - } - Ok(()) - } - } - _ => Err(format!("{state:?} should be unreachable within {}.",function_name!())), - - } - } - - #[named] - pub fn parse_statement( - &'a mut self, - curr_word : &str, - key_word : &str, - begin_state : Parser_State, - parsing_state : Parser_State, - end_state : Parser_State, - next_parser : fn(&'a mut VCD_Parser, &str) -> Result<(), String> - ) -> Result<(), String> { - let mut state = &mut self.vcd_parser_state; - - if (*state == begin_state) { - return match curr_word { - key_word => { - *state = Parser_State::Date(Date_Parser_State::Parsing); - Ok(()) - } - _ => { - *state = Parser_State::Version(Version_Parser_State::Begin); - next_parser(self, curr_word) - } - } - } - else { - Ok(()) - } - // Ok(()) - - // match state { - // Parser_State::Date(Date_Parser_State::Begin) => - // match curr_word { - // key_word => { - // *state = Parser_State::Date(Date_Parser_State::Parsing); - // Ok(()) - // } - // _ => { - // *state = Parser_State::Version(Version_Parser_State::Begin); - // self.parse_version(curr_word) - // } - // } - // Parser_State::Date(Date_Parser_State::Parsing) => - // match curr_word { - // "$end" => { - // let s = self.buffer.take().unwrap(); - // let dt = Utc.datetime_from_str(s.as_str(), "%a %b %e %T %Y") - // .expect(&format!("invalid date {s}").as_str()); - // *state = Parser_State::Version(Version_Parser_State::Begin); - // self.vcd.metadata.date = Some(dt); - // Ok(()) - // } - // _ => { - // if let Some(ref mut buffer) = self.buffer { - // buffer.push_str(" "); - // buffer.push_str(curr_word); - // } - // else { - // self.buffer = Some(curr_word.to_string()); - // } - // Ok(()) - // } - // } - // _ => Err(format!("{state:?} should be unreachable within {}.",function_name!())), - - // } - } - - #[named] - pub fn parse_version(&mut self, word : &str) -> Result<(), String> { - let mut state = &mut self.vcd_parser_state; - match state { - Parser_State::Version(Version_Parser_State::Begin) => - match word { - "$version" => { - *state = Parser_State::Version(Version_Parser_State::Parsing); - Ok(()) - } - _ => { - *state = Parser_State::Timescale(Timescale_Parser_State::Begin); - Ok(()) - } - } - Parser_State::Version(Version_Parser_State::Parsing) => - match word { - "$end" => { - let s = self.buffer.take().unwrap(); - self.vcd.metadata.version = Some(Version(s)); - *state = Parser_State::Timescale(Timescale_Parser_State::Begin); - Ok(()) - } - _ => { - if let Some(ref mut buffer) = self.buffer { - buffer.push_str(" "); - buffer.push_str(word); - } - else { - self.buffer = Some(word.to_string()); - } - Ok(()) - } - } - _ => Err(format!("{state:?} should be unreachable within {}.",function_name!())), - - } - } - - #[named] - pub fn parse_timescale(&mut self, word : &str) -> Result<(), String> { - let mut state = &mut self.vcd_parser_state; - match state { - Parser_State::Timescale(Timescale_Parser_State::Begin) => - match word { - "$timescale" => { - *state = Parser_State::Timescale(Timescale_Parser_State::Parsing); - Ok(()) - } - _ => { - *state = Parser_State::Signal_Tree(Signal_Tree_Parser_State::Begin); - Ok(()) - } - } - Parser_State::Timescale(Timescale_Parser_State::Parsing) => - match word { - "$end" => { - let s = self.buffer.take().unwrap(); - let s = s.split_ascii_whitespace(); - let s = s.collect::>(); - - let scalar = s[0].to_string().parse::().unwrap(); - let unit = s[1]; - let unit = match unit { - "ps" => Ok(Timescale::ps), - "ns" => Ok(Timescale::ns), - "us" => Ok(Timescale::us), - "ms" => Ok(Timescale::ms), - "s" => Ok(Timescale::s), - // TODO : see if there is a way to easily print out all enum variants - // _ => Err(format!("{word} is not a valid unit of time in {Timescale}")) - _ => Err(format!("{unit} is not a valid unit")) - }.unwrap(); - - dbg!(s); - self.vcd.metadata.timescale = (Some(scalar), unit); - *state = Parser_State::Timescale(Timescale_Parser_State::Begin); - Ok(()) - } - _ => { - if let Some(ref mut buffer) = self.buffer { - buffer.push_str(" "); - buffer.push_str(word); - } - else { - self.buffer = Some(word.to_string()); - } - Ok(()) - } - } - _ => Err(format!("{state:?} should be unreachable within {}.",function_name!())), - - } - } -} - -struct Line(u32); -struct Col(u32); -struct Position(Line, Col); - -fn yield_word_and_apply(file : File, mut f : impl FnMut(&[u8], Position) -> Result<(), String>) { - let mut reader = io::BufReader::new(file); - - let mut buffer = String::new(); - - let mut line = 0u32; - while true { - let bytes_read = reader.read_line(&mut buffer).unwrap(); - if bytes_read == 0 {break} - - line += 1; - let mut col = 1u32; - - let mut words = buffer.split_ascii_whitespace(); - - for word in words { - let word = word.as_bytes(); - let position = Position(Line(line), Col(col)); - f(word, position).unwrap(); - col += (word.len() as u32) + 1; - } - - buffer.clear(); - } - -} +#[derive(Debug)] +struct Line(usize); +#[derive(Debug)] +struct Word(usize); +#[derive(Debug)] +struct Cursor(Line, Word); struct YieldByWord { reader : io::BufReader, - words : Vec, EOF : bool, - buffer : String, - str_slices : Vec<(*const u8, usize)>, + buffers : Vec, + curr_line : usize, + str_slices : VecDeque<(*const u8, usize, Cursor)>, } impl YieldByWord { @@ -377,41 +96,57 @@ impl YieldByWord { let mut reader = io::BufReader::new(file); YieldByWord { reader : reader, - words : vec![], EOF : false, - buffer : "".to_string(), - str_slices : vec![], + buffers : vec![], + curr_line : 0, + str_slices : VecDeque::new() } } - fn next_word(&mut self) -> Option<&str> { + fn next_word(&mut self) -> Option<(&str, Cursor)> { // if there are no more words, attempt to read more content // from the file if self.str_slices.is_empty() { - self.buffer.clear(); + self.buffers.clear(); if self.EOF {return None} - let line_chunk_size = 10; + let num_buffers = 10; + + for buf_idx in 0..num_buffers { + self.buffers.push(String::new()); + self.curr_line += 1; + let bytes_read = self.reader.read_line(&mut self.buffers[buf_idx]).unwrap(); + + // 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; + break; + } + + let mut 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)) + } - for _ in 0..line_chunk_size { - let bytes_read = self.reader.read_line(&mut self.buffer).unwrap(); - // we hit the end of the file, so we go ahead and return None - if bytes_read == 0 {self.EOF = true} } + } - let words = self.buffer.split_ascii_whitespace(); - self.str_slices = words - .rev() - .map(|s| (s.as_ptr(), s.len())) - .collect(); + // 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 } // if we make it here, we return the next word unsafe { - let (ptr, len) = self.str_slices.pop().unwrap(); + let (ptr, len, position) = self.str_slices.pop_front().unwrap(); let slice = slice::from_raw_parts(ptr, len); - return Some(str::from_utf8(slice).unwrap()); + return Some((str::from_utf8(slice).unwrap(), position)); }; } } @@ -422,27 +157,19 @@ fn main() -> std::io::Result<()> { let file = File::open(&args.path)?; let mut word_gen = YieldByWord::new(file); let mut word_count = 0; - let mut last_word = String::new(); - // for word in 0..5 { - // dbg!(word_gen.next_word()); - // } while word_gen.next_word().is_some() { word_count += 1; } dbg!(word_count); // loop { - // let next_word = word_gen.next_word(); - // if next_word.is_some() { - // last_word = next_word.unwrap(); - // } - // else { - // break - // } + // let word = word_gen.next_word(); + // if word.is_none() {break}; + + // dbg!(word.unwrap()); // } - // dbg!(last_word); Ok(()) } \ No newline at end of file -- 2.47.1 From c65bdfefac9d2af0e6366fcaaf72da62c7dd14ef Mon Sep 17 00:00:00 2001 From: Yehowshua Immanuel Date: Fri, 3 Jun 2022 12:06:20 -0400 Subject: [PATCH 20/50] restructure 1 --- src/main.rs | 85 ++--------------------------------------------- src/vcd.rs | 2 ++ src/vcd/reader.rs | 83 +++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 88 insertions(+), 82 deletions(-) create mode 100644 src/vcd.rs create mode 100644 src/vcd/reader.rs diff --git a/src/main.rs b/src/main.rs index db9c605..6b37eff 100644 --- a/src/main.rs +++ b/src/main.rs @@ -1,5 +1,3 @@ -use std::io::prelude::*; -use std::io; use std::fs::File; use std::collections::BTreeMap; use chrono::prelude::*; @@ -8,10 +6,8 @@ use ::function_name::named; use num::*; use clap::Parser; -use std::slice; -use std::str; - -use std::collections::VecDeque; +pub mod vcd; +use vcd::*; #[derive(Parser)] struct Cli { @@ -76,86 +72,11 @@ impl VCD { } -#[derive(Debug)] -struct Line(usize); -#[derive(Debug)] -struct Word(usize); -#[derive(Debug)] -struct Cursor(Line, Word); - -struct YieldByWord { - reader : io::BufReader, - EOF : bool, - buffers : Vec, - curr_line : usize, - str_slices : VecDeque<(*const u8, usize, Cursor)>, -} - -impl YieldByWord { - fn new(file : File) -> YieldByWord { - let mut reader = io::BufReader::new(file); - YieldByWord { - reader : reader, - EOF : false, - buffers : vec![], - curr_line : 0, - str_slices : VecDeque::new() - } - } - - fn next_word(&mut self) -> Option<(&str, Cursor)> { - // if there are no more words, attempt to read more content - // from the file - if self.str_slices.is_empty() { - self.buffers.clear(); - - if self.EOF {return None} - - let num_buffers = 10; - - for buf_idx in 0..num_buffers { - self.buffers.push(String::new()); - self.curr_line += 1; - let bytes_read = self.reader.read_line(&mut self.buffers[buf_idx]).unwrap(); - - // 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; - break; - } - - let mut 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)) - } - - } - } - - // 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 - } - - // if we make it here, we return the next word - unsafe { - let (ptr, len, position) = self.str_slices.pop_front().unwrap(); - let slice = slice::from_raw_parts(ptr, len); - return Some((str::from_utf8(slice).unwrap(), position)); - }; - } -} - fn main() -> std::io::Result<()> { let args = Cli::parse(); let file = File::open(&args.path)?; - let mut word_gen = YieldByWord::new(file); + let mut word_gen = WordReader::new(file); let mut word_count = 0; while word_gen.next_word().is_some() { diff --git a/src/vcd.rs b/src/vcd.rs new file mode 100644 index 0000000..50db179 --- /dev/null +++ b/src/vcd.rs @@ -0,0 +1,2 @@ +mod reader; +pub use reader::*; \ No newline at end of file diff --git a/src/vcd/reader.rs b/src/vcd/reader.rs new file mode 100644 index 0000000..f6fc275 --- /dev/null +++ b/src/vcd/reader.rs @@ -0,0 +1,83 @@ +use super::*; + +use std::fs::File; +use std::collections::VecDeque; +use std::slice; +use std::str; +use std::io::prelude::*; +use std::io; + +#[derive(Debug)] +struct Line(usize); +#[derive(Debug)] +struct Word(usize); +#[derive(Debug)] +pub struct Cursor(Line, Word); + +pub struct WordReader { + reader : io::BufReader, + EOF : bool, + buffers : Vec, + curr_line : usize, + str_slices : VecDeque<(*const u8, usize, Cursor)>, +} + +impl WordReader { + pub fn new(file : File) -> WordReader { + let mut reader = io::BufReader::new(file); + WordReader { + reader : reader, + EOF : false, + buffers : vec![], + curr_line : 0, + str_slices : VecDeque::new() + } + } + + pub fn next_word(&mut self) -> Option<(&str, Cursor)> { + // if there are no more words, attempt to read more content + // from the file + if self.str_slices.is_empty() { + self.buffers.clear(); + + if self.EOF {return None} + + let num_buffers = 10; + + for buf_idx in 0..num_buffers { + self.buffers.push(String::new()); + self.curr_line += 1; + let bytes_read = self.reader.read_line(&mut self.buffers[buf_idx]).unwrap(); + + // 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; + break; + } + + let mut 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)) + } + + } + } + + // 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 + } + + // if we make it here, we return the next word + unsafe { + let (ptr, len, position) = self.str_slices.pop_front().unwrap(); + let slice = slice::from_raw_parts(ptr, len); + return Some((str::from_utf8(slice).unwrap(), position)); + }; + } +} \ No newline at end of file -- 2.47.1 From 1c006441fb14a9a03db61f1b11acd84a4c5577a0 Mon Sep 17 00:00:00 2001 From: Yehowshua Immanuel Date: Fri, 3 Jun 2022 21:06:46 -0400 Subject: [PATCH 21/50] restructuring and WIP --- src/main.rs | 84 ++++----------------- src/vcd.rs | 8 +- src/vcd/parse.rs | 188 ++++++++++++++++++++++++++++++++++++++++++++++ src/vcd/reader.rs | 2 - src/vcd/types.rs | 59 +++++++++++++++ 5 files changed, 270 insertions(+), 71 deletions(-) create mode 100644 src/vcd/parse.rs create mode 100644 src/vcd/types.rs diff --git a/src/main.rs b/src/main.rs index 6b37eff..b98e7eb 100644 --- a/src/main.rs +++ b/src/main.rs @@ -1,9 +1,4 @@ use std::fs::File; -use std::collections::BTreeMap; -use chrono::prelude::*; -use ::function_name::named; - -use num::*; use clap::Parser; pub mod vcd; @@ -15,74 +10,27 @@ struct Cli { #[clap(parse(from_os_str))] path: std::path::PathBuf} -#[derive(Debug)] -struct Version(String); - -#[derive(Debug)] -enum Timescale {ps, ns, us, ms, s, unit} - -#[derive(Debug)] -struct Metadata { - date : Option>, - version : Option, - timescale : (Option, Timescale)} - -#[derive(Debug)] -struct Scope_Idx(usize); - -#[derive(Debug)] -struct Signal_Idx(usize); - -#[derive(Debug)] -enum SignalGeneric{ - Signal{ - name : String, - timeline : BTreeMap, - scope_parent : Scope_Idx}, - SignalAlias{ - name : String, - signal_alias : Signal_Idx} -} - -#[derive(Debug)] -struct Scope { - name : String, - child_signals : Vec, - child_scopes : Vec} - - -#[derive(Debug)] -struct VCD { - metadata : Metadata, - all_signals : Vec, - // the root scope should always be placed at index 0 - all_scopes : Vec} - -impl VCD { - pub fn new() -> Self { - let metadata = Metadata { - date : None, - version : None, - timescale : (None, Timescale::unit)}; - VCD { - metadata : metadata, - all_signals : Vec::::new(), - all_scopes : Vec::::new()} - } - } - - fn main() -> std::io::Result<()> { let args = Cli::parse(); let file = File::open(&args.path)?; - let mut word_gen = WordReader::new(file); - let mut word_count = 0; + dbg!(["hello", "goodbye", "myworld"].contains(&"myworlde")); + // let mut word_gen = WordReader::new(file); + // let mut word_count = 0; + + // while word_gen.next_word().is_some() { + // word_count += 1; + // } + // dbg!(word_count); + + // let word1 = "hello world"; + // let word2 = "hello planet"; + // dbg!(&word1[0..6].len()); + dbg!(take_until("tea time now: and later", b':')); + // parse_vcd(file); + + // tag("my oh my"); - while word_gen.next_word().is_some() { - word_count += 1; - } - dbg!(word_count); // loop { // let word = word_gen.next_word(); diff --git a/src/vcd.rs b/src/vcd.rs index 50db179..19f1a6c 100644 --- a/src/vcd.rs +++ b/src/vcd.rs @@ -1,2 +1,8 @@ mod reader; -pub use reader::*; \ No newline at end of file +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 new file mode 100644 index 0000000..9771b07 --- /dev/null +++ b/src/vcd/parse.rs @@ -0,0 +1,188 @@ +use super::*; +use std::fs::File; +use ::function_name::named; + +#[derive(Debug)] +pub struct Residual<'a>(&'a str); + +pub fn take_until<'a>(word : &'a str, pattern : u8) -> Option<(&'a str, Residual)> { + let mut new_start = 0; + + for chr in word.as_bytes() { + if (*chr == pattern) { + return Some((&word[0..new_start], Residual(&word[new_start..]))); + } + else { + new_start += 1; + } + } + + None +} + +fn tag<'a>(word : &'a str, pattern : &'a str) -> Option<&'a str> { + 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 {return None} + new_start += 1; + } + + Some(&word[new_start..]) +} + +#[named] +fn parse_date(word_reader : &mut WordReader) -> Result<(), String> { + let mut parsed_day = false; + let mut parsed_month = false; + let mut parsed_date = false; + let mut parsed_hh = false; + let mut parsed_mm = false; + let mut parsed_ss = false; + let mut parsed_year = false; + let mut parsed_end = false; + + let day = { + // check for another word in the file + let (word, cursor) = word_reader.next_word().expect( + format!("reached end of file without parser leaving {}", function_name!()).as_str() + ); + + let days = ["Mon", "Tue", "Wed", "Thu", "Fri", "Sat", "Sun"]; + if !days.contains(&word) { + let msg = format!("reached end of file without parser leaving {}\n", function_name!()); + let 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)) + } + + word.to_string() + }; + + let month = { + // check for another word in the file + let (word, cursor) = word_reader.next_word().expect( + format!("reached end of file without parser leaving {}", function_name!()).as_str() + ); + + let months = [ + "Jan", "Feb", "Mar", "Apr", + "May", "Jun", "Jul", "Aug", + "Sept", "Oct", "Nov", "Dec", + ]; + + if !months.contains(&word) { + let msg = format!("reached end of file without parser leaving {}\n", function_name!()); + let 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)) + } + + word.to_string() + }; + + let date = { + // check for another word in the file + let (word, cursor) = word_reader.next_word().expect( + format!("reached end of file without parser leaving {}", function_name!()).as_str() + ); + + let date : u8 = word.to_string().parse().unwrap(); + + if date > 31 { + let msg = format!("reached end of file without parser leaving {}\n", function_name!()); + 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)) + + } + + word.to_string() + }; + + let (hh, mm, ss) = { + // check for another word in the file + let (word, cursor) = word_reader.next_word().expect( + format!("reached end of file without parser leaving {}", function_name!()).as_str() + ); + + let date : u8 = word.to_string().parse().unwrap(); + // let hh = take_until(word, b':').unwrap(); + + if date > 31 { + let msg = format!("reached end of file without parser leaving {}\n", function_name!()); + 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)) + + } + ("", "", "") + }; + + // else if !parsed_date { + + // } + // else if !parsed_hh { + + // } + // else if !parsed_mm { + + // } + // else if !parsed_ss { + + // } + // else if !parsed_year { + + // } + // else if !parsed_end { + + // } + + Ok(()) +} + +#[named] +fn parse_header(word_reader : &mut WordReader) -> Result<(), String> { + loop { + // check for another word in the file + let word = word_reader.next_word(); + + // if there isn't another word left in the file, then we exit + if word.is_none() { + return Err(format!("reached end of file without parser leaving {}", function_name!())) + } + + // destructure + let (word, cursor) = word.unwrap(); + let ident = tag(word, "$"); + + match tag(word, "$") { + // we hope that this word stars with a `$` + Some(ident) => { + match ident { + "date" => {println!("got date")} + "version" => {println!("got version")} + "timescale" => {println!("got timescale")} + "scope" => {return Ok(())} + _ => {} + } + } + // if not, then we keep looping + None => {} + } + + + } + // Ok() +} + +pub fn parse_vcd(file : File) { + let mut word_gen = WordReader::new(file); + + parse_header(&mut word_gen); +} \ No newline at end of file diff --git a/src/vcd/reader.rs b/src/vcd/reader.rs index f6fc275..b9c85e4 100644 --- a/src/vcd/reader.rs +++ b/src/vcd/reader.rs @@ -1,5 +1,3 @@ -use super::*; - use std::fs::File; use std::collections::VecDeque; use std::slice; diff --git a/src/vcd/types.rs b/src/vcd/types.rs new file mode 100644 index 0000000..336601a --- /dev/null +++ b/src/vcd/types.rs @@ -0,0 +1,59 @@ +use std::collections::BTreeMap; +use chrono::prelude::*; +use num::BigInt; + +#[derive(Debug)] +struct Version(String); + +#[derive(Debug)] +enum Timescale {ps, ns, us, ms, s, unit} + +#[derive(Debug)] +pub(super) struct Metadata { + date : Option>, + version : Option, + timescale : (Option, Timescale)} + +#[derive(Debug)] +struct Scope_Idx(usize); + +#[derive(Debug)] +struct Signal_Idx(usize); + +#[derive(Debug)] +enum SignalGeneric{ + Signal{ + name : String, + timeline : BTreeMap, + scope_parent : Scope_Idx}, + SignalAlias{ + name : String, + signal_alias : Signal_Idx} +} + +#[derive(Debug)] +struct Scope { + name : String, + child_signals : Vec, + child_scopes : Vec} + + +#[derive(Debug)] +struct VCD { + metadata : Metadata, + all_signals : Vec, + // the root scope should always be placed at index 0 + all_scopes : Vec} + +impl VCD { + pub fn new() -> Self { + let metadata = Metadata { + date : None, + version : None, + timescale : (None, Timescale::unit)}; + VCD { + metadata : metadata, + all_signals : Vec::::new(), + all_scopes : Vec::::new()} + } + } -- 2.47.1 From 4c7417c729bc1dd382b690ed884315e7fb931f36 Mon Sep 17 00:00:00 2001 From: Yehowshua Immanuel Date: Wed, 8 Jun 2022 21:45:47 -0400 Subject: [PATCH 22/50] date parser needs some more work --- Cargo.toml | 3 +- src/main.rs | 6 +- src/vcd/parse.rs | 152 ++++++++++++++++++++++++++++++----------------- src/vcd/types.rs | 10 ++-- 4 files changed, 109 insertions(+), 62 deletions(-) diff --git a/Cargo.toml b/Cargo.toml index 05b725b..18c1c50 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -9,4 +9,5 @@ edition = "2021" num = "0.4" clap = { version = "3.1.8", features = ["derive"] } chrono = "0.4" -function_name = "0.3.0" \ No newline at end of file +function_name = "0.3.0" +itertools = "0.10.3" \ No newline at end of file diff --git a/src/main.rs b/src/main.rs index b98e7eb..e077fa8 100644 --- a/src/main.rs +++ b/src/main.rs @@ -14,7 +14,7 @@ fn main() -> std::io::Result<()> { let args = Cli::parse(); let file = File::open(&args.path)?; - dbg!(["hello", "goodbye", "myworld"].contains(&"myworlde")); + // dbg!(["hello", "goodbye", "myworld"].contains(&"myworlde")); // let mut word_gen = WordReader::new(file); // let mut word_count = 0; @@ -26,8 +26,8 @@ fn main() -> std::io::Result<()> { // let word1 = "hello world"; // let word2 = "hello planet"; // dbg!(&word1[0..6].len()); - dbg!(take_until("tea time now: and later", b':')); - // parse_vcd(file); + // dbg!(take_until("tea time now: and later", b':')); + parse_vcd(file); // tag("my oh my"); diff --git a/src/vcd/parse.rs b/src/vcd/parse.rs index 9771b07..74ffb4c 100644 --- a/src/vcd/parse.rs +++ b/src/vcd/parse.rs @@ -1,4 +1,6 @@ use super::*; +use chrono::prelude::*; +use itertools::Itertools; use std::fs::File; use ::function_name::named; @@ -10,7 +12,7 @@ pub fn take_until<'a>(word : &'a str, pattern : u8) -> Option<(&'a str, Residual for chr in word.as_bytes() { if (*chr == pattern) { - return Some((&word[0..new_start], Residual(&word[new_start..]))); + return Some((&word[0..new_start], Residual(&word[new_start+1..]))); } else { new_start += 1; @@ -37,21 +39,17 @@ fn tag<'a>(word : &'a str, pattern : &'a str) -> Option<&'a str> { } #[named] -fn parse_date(word_reader : &mut WordReader) -> Result<(), String> { - let mut parsed_day = false; - let mut parsed_month = false; - let mut parsed_date = false; - let mut parsed_hh = false; - let mut parsed_mm = false; - let mut parsed_ss = false; - let mut parsed_year = false; - let mut parsed_end = false; +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), +) -> Result, String> { let day = { // check for another word in the file - let (word, cursor) = word_reader.next_word().expect( - format!("reached end of file without parser leaving {}", function_name!()).as_str() - ); + let (word, cursor) = word_and_ctx1; let days = ["Mon", "Tue", "Wed", "Thu", "Fri", "Sat", "Sun"]; if !days.contains(&word) { @@ -66,9 +64,7 @@ fn parse_date(word_reader : &mut WordReader) -> Result<(), String> { let month = { // check for another word in the file - let (word, cursor) = word_reader.next_word().expect( - format!("reached end of file without parser leaving {}", function_name!()).as_str() - ); + let (word, cursor) = word_and_ctx2; let months = [ "Jan", "Feb", "Mar", "Apr", @@ -88,9 +84,7 @@ fn parse_date(word_reader : &mut WordReader) -> Result<(), String> { let date = { // check for another word in the file - let (word, cursor) = word_reader.next_word().expect( - format!("reached end of file without parser leaving {}", function_name!()).as_str() - ); + let (word, cursor) = word_and_ctx3; let date : u8 = word.to_string().parse().unwrap(); @@ -106,48 +100,63 @@ fn parse_date(word_reader : &mut WordReader) -> Result<(), String> { }; let (hh, mm, ss) = { - // check for another word in the file - let (word, cursor) = word_reader.next_word().expect( - format!("reached end of file without parser leaving {}", function_name!()).as_str() - ); + // get hour + let (word, cursor) = word_and_ctx4; - let date : u8 = word.to_string().parse().unwrap(); - // let hh = take_until(word, b':').unwrap(); + let (hh, Residual(remainder)) = take_until(word, b':').unwrap(); + let hh : u8 = hh.to_string().parse().unwrap(); - if date > 31 { + if hh > 23 { let msg = format!("reached end of file without parser leaving {}\n", function_name!()); - let msg2 = format!("{word} is not a valid date : must be between 0 and 31\n"); + 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)) - } - ("", "", "") + + // get minute + let (mm, Residual(remainder)) = take_until(remainder, b':').unwrap(); + let mm : u8 = mm.to_string().parse().unwrap(); + + if mm > 60 { + let msg = format!("reached end of file without parser leaving {}\n", function_name!()); + 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)) + } + + // get second + let ss : u8 = remainder.to_string().parse().unwrap(); + + if ss > 60 { + let msg = format!("reached end of file without parser leaving {}\n", function_name!()); + 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)) + } + (hh.to_string(), mm.to_string(), ss.to_string()) }; - // else if !parsed_date { + let year = { + // check for another word in the file + let (word, cursor) = word_and_ctx5; + word.to_string() + }; - // } - // else if !parsed_hh { + let date = Utc.datetime_from_str( + format!("{day} {month} {date} {mm}:{hh}:{ss} {year}").as_str(), + "%a %b %e %T %Y").unwrap(); - // } - // else if !parsed_mm { - - // } - // else if !parsed_ss { - - // } - // else if !parsed_year { - - // } - // else if !parsed_end { - - // } - - Ok(()) + Ok(date) } #[named] -fn parse_header(word_reader : &mut WordReader) -> Result<(), String> { +fn parse_header(word_reader : &mut WordReader) -> Result { + let mut header = Metadata { + date : None, + version : None, + timescale : (None, Timescale::unit) + }; + loop { // check for another word in the file let word = word_reader.next_word(); @@ -165,10 +174,47 @@ fn parse_header(word_reader : &mut WordReader) -> Result<(), String> { // we hope that this word stars with a `$` Some(ident) => { match ident { - "date" => {println!("got date")} + "date" => { + let err_msg = format!("reached end of file without parser leaving {}", function_name!()); + // a date is typically composed of the 5 following words which can + // 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. + // + // While looking ahead, if one of the 5 words in `$end`, we have to + // immediately stop trying to get more words. + + let mut found_end = false; + let mut lookahead_5_words : Vec<(String, Cursor)> = Vec::new(); + + for word in 0..5 { + let (word, cursor) = word_reader.next_word().expect(err_msg.as_str()); + let word = word.to_string(); + match word.as_str() { + "$end" => { + found_end = true; + break; + } + _ => { + lookahead_5_words.push((word, cursor)); + } + }; + } + + // we no longer attempt to parse date if we weren't able to lookahead 5 + // words + if found_end {continue} + + let iter = lookahead_5_words + .iter() + .permutations(lookahead_5_words.len()); + // let parsed_date = parse_date(word_reader).unwrap(); + // header.date = Some(parsed_date); + } "version" => {println!("got version")} "timescale" => {println!("got timescale")} - "scope" => {return Ok(())} + "scope" => {break} _ => {} } } @@ -176,13 +222,13 @@ fn parse_header(word_reader : &mut WordReader) -> Result<(), String> { None => {} } - } - // Ok() + return Ok(header) } pub fn parse_vcd(file : File) { let mut word_gen = WordReader::new(file); - parse_header(&mut word_gen); + let header = parse_header(&mut word_gen).unwrap(); + dbg!(header); } \ No newline at end of file diff --git a/src/vcd/types.rs b/src/vcd/types.rs index 336601a..3e5dd21 100644 --- a/src/vcd/types.rs +++ b/src/vcd/types.rs @@ -3,16 +3,16 @@ use chrono::prelude::*; use num::BigInt; #[derive(Debug)] -struct Version(String); +pub(super) struct Version(String); #[derive(Debug)] -enum Timescale {ps, ns, us, ms, s, unit} +pub(super) enum Timescale {ps, ns, us, ms, s, unit} #[derive(Debug)] pub(super) struct Metadata { - date : Option>, - version : Option, - timescale : (Option, Timescale)} + pub(super) date : Option>, + pub(super) version : Option, + pub(super) timescale : (Option, Timescale)} #[derive(Debug)] struct Scope_Idx(usize); -- 2.47.1 From 14af6e94e386a46f31523160337dc4b1913b8732 Mon Sep 17 00:00:00 2001 From: Yehowshua Immanuel Date: Sat, 11 Jun 2022 00:01:53 -0400 Subject: [PATCH 23/50] now parsing date more robustly --- README.md | 1 + src/vcd/parse.rs | 134 +++++++++++++++++++++++++++++++++++++---------- 2 files changed, 107 insertions(+), 28 deletions(-) diff --git a/README.md b/README.md index 76499fc..c8055ef 100644 --- a/README.md +++ b/README.md @@ -29,6 +29,7 @@ The first build of the program may take some time. - [ ] Consider what to do with don't care values will probably just convert them to strings for now. - [ ] Test for speed and see if stream of bytes is helpful + - [ ] Split ``parse.rs``. It's getting too large. - [ ] Include line and possible column numbers - [ ] Change states to lowercase - [ ] We need to start regression testing the parser over all files diff --git a/src/vcd/parse.rs b/src/vcd/parse.rs index 74ffb4c..ea9072a 100644 --- a/src/vcd/parse.rs +++ b/src/vcd/parse.rs @@ -40,11 +40,11 @@ fn tag<'a>(word : &'a str, pattern : &'a str) -> Option<&'a str> { #[named] 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 = { @@ -86,7 +86,11 @@ fn parse_date( // check for another word in the file let (word, cursor) = word_and_ctx3; - let date : u8 = word.to_string().parse().unwrap(); + // let date : u8 = word.to_string().parse().unwrap(); + let date : u8 = match word.to_string().parse() { + Ok(date) => date, + Err(_) => {return Err("".to_string())} + }; if date > 31 { let msg = format!("reached end of file without parser leaving {}\n", function_name!()); @@ -96,15 +100,17 @@ fn parse_date( } - word.to_string() + date.to_string() }; let (hh, mm, ss) = { // get hour let (word, cursor) = word_and_ctx4; - let (hh, Residual(remainder)) = take_until(word, b':').unwrap(); - let hh : u8 = hh.to_string().parse().unwrap(); + let (hh, Residual(remainder)) = take_until(word, b':').ok_or("did not find colon")?; + let hh : u8 = hh.to_string() + .parse() + .map_err(|_| "failed to parse".to_string())?; if hh > 23 { let msg = format!("reached end of file without parser leaving {}\n", function_name!()); @@ -114,8 +120,10 @@ fn parse_date( } // get minute - let (mm, Residual(remainder)) = take_until(remainder, b':').unwrap(); - let mm : u8 = mm.to_string().parse().unwrap(); + let (mm, Residual(remainder)) = take_until(remainder, b':').ok_or("did not find colon")?; + let mm : u8 = mm.to_string() + .parse() + .map_err(|_| "failed to parse".to_string())?; if mm > 60 { let msg = format!("reached end of file without parser leaving {}\n", function_name!()); @@ -125,7 +133,10 @@ fn parse_date( } // get second - let ss : u8 = remainder.to_string().parse().unwrap(); + // let ss : u8 = remainder.to_string().parse().unwrap(); + let ss : u8 = remainder.to_string() + .parse() + .map_err(|_| "failed to parse".to_string())?; if ss > 60 { let msg = format!("reached end of file without parser leaving {}\n", function_name!()); @@ -142,16 +153,51 @@ fn parse_date( word.to_string() }; - let date = Utc.datetime_from_str( - format!("{day} {month} {date} {mm}:{hh}:{ss} {year}").as_str(), - "%a %b %e %T %Y").unwrap(); + // unfortunately, the minutes, seconds, and hour could occur in an + // unexpected order + let full_date = format!("{day} {month} {date} {mm}:{hh}:{ss} {year}"); + 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()) + } + + let full_date = format!("{day} {month} {date} {mm}:{ss}:{hh} {year}"); + 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()) + } + + let full_date = format!("{day} {month} {date} {ss}:{mm}:{hh} {year}"); + 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()) + } + + let full_date = format!("{day} {month} {date} {ss}:{hh}:{mm} {year}"); + 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()) + } + + let full_date = format!("{day} {month} {date} {hh}:{ss}:{mm} {year}"); + 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()) + } + + let full_date = format!("{day} {month} {date} {hh}:{mm}:{ss} {year}"); + let full_date = Utc.datetime_from_str(full_date.as_str(), "%a %b %e %T %Y"); + if full_date.is_ok() { + return Ok(full_date.unwrap()) + } + + Err("failed to parse dat".to_string()) - Ok(date) } #[named] -fn parse_header(word_reader : &mut WordReader) -> Result { - let mut header = Metadata { +fn parse_metadata(word_reader : &mut WordReader) -> Result { + let mut metadata = Metadata { date : None, version : None, timescale : (None, Timescale::unit) @@ -168,7 +214,6 @@ fn parse_header(word_reader : &mut WordReader) -> Result { // destructure let (word, cursor) = word.unwrap(); - let ident = tag(word, "$"); match tag(word, "$") { // we hope that this word stars with a `$` @@ -182,6 +227,11 @@ fn parse_header(word_reader : &mut WordReader) -> Result { // Thus, we must lookahead read the 5 next words, and try our date // parser on 5! = 120 permutations of the 5 words. // + // It is also possible that within each permutation, the hours, + // minutes, and seconds could be in an unusual order, which means + // that we may search up to 6 different permutations oh hh::mm:ss, + // for an upper bound total of 720 permutations + // // While looking ahead, if one of the 5 words in `$end`, we have to // immediately stop trying to get more words. @@ -206,15 +256,43 @@ fn parse_header(word_reader : &mut WordReader) -> Result { // words if found_end {continue} - let iter = lookahead_5_words - .iter() - .permutations(lookahead_5_words.len()); - // let parsed_date = parse_date(word_reader).unwrap(); - // header.date = Some(parsed_date); + 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(); + let arg_1 = (&w1[..], s1); + + let (w2, s2) = permutations.pop().unwrap(); + let arg_2 = (&w2[..], s2); + + let (w3, s3) = permutations.pop().unwrap(); + let arg_3 = (&w3[..], s3); + + let (w4, s4) = permutations.pop().unwrap(); + let arg_4 = (&w4[..], s4); + + let (w5, s5) = permutations.pop().unwrap(); + let arg_5 = (&w5[..], s5); + + let parsed_date = parse_date(arg_1, arg_2, arg_3, arg_4, arg_5); + + // store date and exit loop if a match is found + if parsed_date.is_ok() { + metadata.date = Some(parsed_date.unwrap()); + break + } + + } } - "version" => {println!("got version")} - "timescale" => {println!("got timescale")} + "version" => {println!("found version")} + "timescale" => {println!("found timescale")} + // in VCDs, the scope keyword indicates the end of the metadata section "scope" => {break} + // we keep searching for words until we've found one of the following + // keywords, ["version", "timescale", "scope"] _ => {} } } @@ -223,12 +301,12 @@ fn parse_header(word_reader : &mut WordReader) -> Result { } } - return Ok(header) + return Ok(metadata) } pub fn parse_vcd(file : File) { let mut word_gen = WordReader::new(file); - let header = parse_header(&mut word_gen).unwrap(); + let header = parse_metadata(&mut word_gen).unwrap(); dbg!(header); } \ No newline at end of file -- 2.47.1 From e7fb766302c25475c5f21b6c20637dbf630e0d4b Mon Sep 17 00:00:00 2001 From: Yehowshua Immanuel Date: Sun, 12 Jun 2022 15:32:00 -0400 Subject: [PATCH 24/50] now parsing version --- src/vcd/parse.rs | 60 +++++++++++++++++++++++++++++++++++++----------- src/vcd/types.rs | 2 +- 2 files changed, 47 insertions(+), 15 deletions(-) diff --git a/src/vcd/parse.rs b/src/vcd/parse.rs index ea9072a..b17ec59 100644 --- a/src/vcd/parse.rs +++ b/src/vcd/parse.rs @@ -155,6 +155,18 @@ fn parse_date( // unfortunately, the minutes, seconds, and hour could occur in an // unexpected order + let full_date = format!("{day} {month} {date} {hh}:{mm}:{ss} {year}"); + let full_date = Utc.datetime_from_str(full_date.as_str(), "%a %b %e %T %Y"); + if full_date.is_ok() { + return Ok(full_date.unwrap()) + } + + let full_date = format!("{day} {month} {date} {hh}:{ss}:{mm} {year}"); + 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()) + } + let full_date = format!("{day} {month} {date} {mm}:{hh}:{ss} {year}"); let full_date = Utc.datetime_from_str(full_date.as_str(), "%a %b %e %T %Y"); if full_date.is_ok() { @@ -179,20 +191,35 @@ fn parse_date( return Ok(full_date.unwrap()) } - let full_date = format!("{day} {month} {date} {hh}:{ss}:{mm} {year}"); - 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()) + Err("failed to parse date".to_string()) + +} + +#[named] +fn parse_version(word_reader : &mut WordReader) -> Result { + let mut version = String::new(); + + loop { + let word = word_reader.next_word(); + + // if there isn't another word left in the file, then we exit + if word.is_none() { + return Err(format!("reached end of file without parser leaving {}", function_name!())) + } + + let (word, cursor) = word.unwrap(); + + if word == "$end" { + // truncate trailing whitespace + let version = version[0..(version.len() - 1)].to_string(); + return Ok(Version(version)) + + } + else { + version.push_str(word); + version.push_str(" "); + } } - - let full_date = format!("{day} {month} {date} {hh}:{mm}:{ss} {year}"); - let full_date = Utc.datetime_from_str(full_date.as_str(), "%a %b %e %T %Y"); - if full_date.is_ok() { - return Ok(full_date.unwrap()) - } - - Err("failed to parse dat".to_string()) - } #[named] @@ -287,7 +314,12 @@ fn parse_metadata(word_reader : &mut WordReader) -> Result { } } - "version" => {println!("found version")} + "version" => { + let version = parse_version(word_reader); + if version.is_ok() { + metadata.version = Some(version.unwrap()); + } + } "timescale" => {println!("found timescale")} // in VCDs, the scope keyword indicates the end of the metadata section "scope" => {break} diff --git a/src/vcd/types.rs b/src/vcd/types.rs index 3e5dd21..38bda30 100644 --- a/src/vcd/types.rs +++ b/src/vcd/types.rs @@ -3,7 +3,7 @@ use chrono::prelude::*; use num::BigInt; #[derive(Debug)] -pub(super) struct Version(String); +pub(super) struct Version(pub String); #[derive(Debug)] pub(super) enum Timescale {ps, ns, us, ms, s, unit} -- 2.47.1 From b25cdaa170d68813dbe4a03488d177268cc10fc2 Mon Sep 17 00:00:00 2001 From: Yehowshua Immanuel Date: Sun, 12 Jun 2022 22:52:24 -0400 Subject: [PATCH 25/50] now parsing headers fully --- README.md | 1 + src/main.rs | 3 +- src/vcd/parse.rs | 89 ++++++++++++++++++++++++++++++++++++++++++++++-- 3 files changed, 90 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index c8055ef..02e147d 100644 --- a/README.md +++ b/README.md @@ -26,6 +26,7 @@ The first build of the program may take some time. # TODO - [x] We need a way to merge lines. + - [ ] Consolidate error messages and add cursors. - [ ] Consider what to do with don't care values will probably just convert them to strings for now. - [ ] Test for speed and see if stream of bytes is helpful diff --git a/src/main.rs b/src/main.rs index e077fa8..623b1ba 100644 --- a/src/main.rs +++ b/src/main.rs @@ -14,6 +14,8 @@ fn main() -> std::io::Result<()> { let args = Cli::parse(); let file = File::open(&args.path)?; + // dbg!(take_while("01234hello", digit)); + // dbg!(["hello", "goodbye", "myworld"].contains(&"myworlde")); // let mut word_gen = WordReader::new(file); // let mut word_count = 0; @@ -26,7 +28,6 @@ fn main() -> std::io::Result<()> { // let word1 = "hello world"; // let word2 = "hello planet"; // dbg!(&word1[0..6].len()); - // dbg!(take_until("tea time now: and later", b':')); parse_vcd(file); // tag("my oh my"); diff --git a/src/vcd/parse.rs b/src/vcd/parse.rs index b17ec59..f4d2755 100644 --- a/src/vcd/parse.rs +++ b/src/vcd/parse.rs @@ -7,6 +7,15 @@ use ::function_name::named; #[derive(Debug)] pub struct Residual<'a>(&'a str); +pub fn digit(chr : u8) -> bool { + let zero = b'0' as u8; + let nine = b'9' as u8; + + let between_zero_and_nine = (chr >= zero) && (nine >= chr); + + return between_zero_and_nine +} + pub fn take_until<'a>(word : &'a str, pattern : u8) -> Option<(&'a str, Residual)> { let mut new_start = 0; @@ -22,6 +31,24 @@ pub fn take_until<'a>(word : &'a str, pattern : u8) -> Option<(&'a str, Residual None } +pub fn take_while<'a>(word : &'a str, cond : fn(u8) -> bool) -> (&'a str, Residual) { + let mut new_start = 0; + dbg!(word); + + for chr in word.as_bytes() { + dbg!(&chr); + if (cond(*chr)) { + new_start += 1; + } + else { + break + } + } + + return (&word[0..new_start], Residual(&word[new_start..])); + +} + fn tag<'a>(word : &'a str, pattern : &'a str) -> Option<&'a str> { let lhs = word.as_bytes().iter(); let rhs = pattern.as_bytes(); @@ -86,7 +113,6 @@ fn parse_date( // check for another word in the file let (word, cursor) = word_and_ctx3; - // let date : u8 = word.to_string().parse().unwrap(); let date : u8 = match word.to_string().parse() { Ok(date) => date, Err(_) => {return Err("".to_string())} @@ -222,6 +248,59 @@ fn parse_version(word_reader : &mut WordReader) -> Result { } } +#[named] +fn parse_timescale(word_reader : &mut WordReader) -> Result<(Option, Timescale), String> { + let err_msg = format!("failed in {}", function_name!()); + + // we might see `scalarunit $end` or `scalar unit $end` + + // first get timescale + let (word, cursor) = word_reader.next_word().ok_or(&err_msg)?; + let word = word.to_string(); + dbg!(&word); + let (scalar, Residual(residual)) = take_while(word.as_str(), digit); + + let scalar : u32 = scalar.to_string().parse() + .map_err(|_| &err_msg)?; + + let timescale = { + if residual == "" { + dbg!("parse_timescale"); + let (word, cursor) = word_reader.next_word().ok_or(&err_msg)?; + let unit = match word { + "ps" => {Ok(Timescale::ps)} + "ns" => {Ok(Timescale::ns)} + "us" => {Ok(Timescale::us)} + "ms" => {Ok(Timescale::ms)} + "s" => {Ok(Timescale::s)} + _ => {Err(err_msg.to_string())} + }.unwrap(); + + (Some(scalar), unit) + } + else { + let unit = match residual { + "ps" => {Ok(Timescale::ps)} + "ns" => {Ok(Timescale::ns)} + "us" => {Ok(Timescale::us)} + "ms" => {Ok(Timescale::ms)} + "s" => {Ok(Timescale::s)} + _ => {Err(err_msg.to_string())} + }.unwrap(); + + (Some(scalar), unit) + } + }; + + // then check for the `$end` keyword + let (end, cursor) = word_reader.next_word().ok_or(&err_msg)?; + tag(end, "$end").ok_or(&err_msg)?; + + return Ok(timescale); + + Err("".to_string()) +} + #[named] fn parse_metadata(word_reader : &mut WordReader) -> Result { let mut metadata = Metadata { @@ -320,7 +399,13 @@ fn parse_metadata(word_reader : &mut WordReader) -> Result { metadata.version = Some(version.unwrap()); } } - "timescale" => {println!("found timescale")} + "timescale" => { + dbg!("here"); + let timescale = parse_timescale(word_reader); + if timescale.is_ok() { + metadata.timescale = timescale.unwrap(); + } + } // in VCDs, the scope keyword indicates the end of the metadata section "scope" => {break} // we keep searching for words until we've found one of the following -- 2.47.1 From a37c4c0f9520050dd2615ab232efb8769be6e4cd Mon Sep 17 00:00:00 2001 From: Yehowshua Immanuel Date: Fri, 17 Jun 2022 18:16:51 -0400 Subject: [PATCH 26/50] now using ParseResult as parser return type exclusively --- README.md | 6 ++- src/vcd/parse.rs | 138 +++++++++++++++++++++++++---------------------- 2 files changed, 78 insertions(+), 66 deletions(-) diff --git a/README.md b/README.md index 02e147d..641c3da 100644 --- a/README.md +++ b/README.md @@ -26,14 +26,16 @@ The first build of the program may take some time. # TODO - [x] We need a way to merge lines. + - [ ] We need to start regression testing the parser over all files + - [ ] Decide if I want to return option types + - [ ] Propagate all to question mark unwrap types. + - [ ] Don't want variation in hh:mm:ss - [ ] Consolidate error messages and add cursors. - [ ] Consider what to do with don't care values will probably just convert them to strings for now. - - [ ] Test for speed and see if stream of bytes is helpful - [ ] Split ``parse.rs``. It's getting too large. - [ ] Include line and possible column numbers - [ ] Change states to lowercase - - [ ] We need to start regression testing the parser over all files - [ ] Take a look at GTKWave parser to compare effificiency. - [ ] Send survey to community channel. diff --git a/src/vcd/parse.rs b/src/vcd/parse.rs index f4d2755..750b777 100644 --- a/src/vcd/parse.rs +++ b/src/vcd/parse.rs @@ -6,6 +6,8 @@ use ::function_name::named; #[derive(Debug)] pub struct Residual<'a>(&'a str); +#[derive(Debug)] +pub struct ParseResult<'a> {matched : &'a str, residual : &'a str} pub fn digit(chr : u8) -> bool { let zero = b'0' as u8; @@ -16,27 +18,30 @@ pub fn digit(chr : u8) -> bool { return between_zero_and_nine } -pub fn take_until<'a>(word : &'a str, pattern : u8) -> Option<(&'a str, Residual)> { +pub 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) { - return Some((&word[0..new_start], Residual(&word[new_start+1..]))); + break } else { new_start += 1; } } - None + return + ParseResult{ + matched : &word[0..new_start], + residual : &word[new_start..] + }; + } -pub fn take_while<'a>(word : &'a str, cond : fn(u8) -> bool) -> (&'a str, Residual) { +pub fn take_while<'a>(word : &'a str, cond : fn(u8) -> bool) -> ParseResult<'a> { let mut new_start = 0; - dbg!(word); for chr in word.as_bytes() { - dbg!(&chr); if (cond(*chr)) { new_start += 1; } @@ -45,11 +50,15 @@ pub fn take_while<'a>(word : &'a str, cond : fn(u8) -> bool) -> (&'a str, Residu } } - return (&word[0..new_start], Residual(&word[new_start..])); + return + ParseResult{ + matched : &word[0..new_start], + residual : &word[new_start..] + }; } -fn tag<'a>(word : &'a str, pattern : &'a str) -> Option<&'a str> { +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); @@ -58,11 +67,44 @@ fn tag<'a>(word : &'a str, pattern : &'a str) -> Option<&'a str> { let mut res = true; for (c_lhs, c_rhs) in iter { res = res && (c_lhs == c_rhs); - if !res {return None} + if !res {break} new_start += 1; } - Some(&word[new_start..]) + return + ParseResult{ + matched : &word[0..new_start], + residual : &word[new_start..] + }; +} + +impl<'a> ParseResult<'a> { + fn match_not_empty(& self) -> Result<(), String> { + if self.matched == "" { + return Err("failed".to_string()) + } + else { + return Ok(()) + } + } + + fn assert_match(& self) -> Result<&str, String> { + if self.matched == "" { + return Err("no match".to_string()) + } + else { + return Ok(self.matched) + } + } + + fn assert_residual(& self) -> Result<&str, String> { + if self.residual == "" { + return Err("no residual".to_string()) + } + else { + return Ok(self.residual) + } + } } #[named] @@ -133,8 +175,9 @@ fn parse_date( // get hour let (word, cursor) = word_and_ctx4; - let (hh, Residual(remainder)) = take_until(word, b':').ok_or("did not find colon")?; - let hh : u8 = hh.to_string() + let res = take_until(word, b':'); + res.assert_match()?; + let hh : u8 = res.matched.to_string() .parse() .map_err(|_| "failed to parse".to_string())?; @@ -146,8 +189,10 @@ fn parse_date( } // get minute - let (mm, Residual(remainder)) = take_until(remainder, b':').ok_or("did not find colon")?; - let mm : u8 = mm.to_string() + 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(|_| "failed to parse".to_string())?; @@ -160,7 +205,9 @@ fn parse_date( // get second // let ss : u8 = remainder.to_string().parse().unwrap(); - let ss : u8 = remainder.to_string() + 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(|_| "failed to parse".to_string())?; @@ -187,36 +234,6 @@ fn parse_date( return Ok(full_date.unwrap()) } - let full_date = format!("{day} {month} {date} {hh}:{ss}:{mm} {year}"); - 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()) - } - - let full_date = format!("{day} {month} {date} {mm}:{hh}:{ss} {year}"); - 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()) - } - - let full_date = format!("{day} {month} {date} {mm}:{ss}:{hh} {year}"); - 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()) - } - - let full_date = format!("{day} {month} {date} {ss}:{mm}:{hh} {year}"); - 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()) - } - - let full_date = format!("{day} {month} {date} {ss}:{hh}:{mm} {year}"); - 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()) - } - Err("failed to parse date".to_string()) } @@ -257,15 +274,14 @@ fn parse_timescale(word_reader : &mut WordReader) -> Result<(Option, Timesc // first get timescale let (word, cursor) = word_reader.next_word().ok_or(&err_msg)?; let word = word.to_string(); - dbg!(&word); - let (scalar, Residual(residual)) = take_while(word.as_str(), digit); + let ParseResult{matched, residual} = take_while(word.as_str(), digit); + let scalar = matched; let scalar : u32 = scalar.to_string().parse() .map_err(|_| &err_msg)?; let timescale = { if residual == "" { - dbg!("parse_timescale"); let (word, cursor) = word_reader.next_word().ok_or(&err_msg)?; let unit = match word { "ps" => {Ok(Timescale::ps)} @@ -294,7 +310,7 @@ fn parse_timescale(word_reader : &mut WordReader) -> Result<(Option, Timesc // then check for the `$end` keyword let (end, cursor) = word_reader.next_word().ok_or(&err_msg)?; - tag(end, "$end").ok_or(&err_msg)?; + tag(end, "$end").match_not_empty()?; return Ok(timescale); @@ -303,6 +319,8 @@ fn parse_timescale(word_reader : &mut WordReader) -> Result<(Option, Timesc #[named] fn parse_metadata(word_reader : &mut WordReader) -> Result { + let err_msg = format!("reached end of file without parser leaving {}", function_name!()); + let mut metadata = Metadata { date : None, version : None, @@ -311,20 +329,13 @@ fn parse_metadata(word_reader : &mut WordReader) -> Result { loop { // check for another word in the file - let word = word_reader.next_word(); + let (word, cursor) = word_reader.next_word().ok_or(&err_msg)?; - // if there isn't another word left in the file, then we exit - if word.is_none() { - return Err(format!("reached end of file without parser leaving {}", function_name!())) - } - - // destructure - let (word, cursor) = word.unwrap(); - - match tag(word, "$") { + let ParseResult{matched, residual} = tag(word, "$"); + match matched { // we hope that this word stars with a `$` - Some(ident) => { - match ident { + "$" => { + match residual { "date" => { let err_msg = format!("reached end of file without parser leaving {}", function_name!()); // a date is typically composed of the 5 following words which can @@ -400,7 +411,6 @@ fn parse_metadata(word_reader : &mut WordReader) -> Result { } } "timescale" => { - dbg!("here"); let timescale = parse_timescale(word_reader); if timescale.is_ok() { metadata.timescale = timescale.unwrap(); @@ -413,8 +423,8 @@ fn parse_metadata(word_reader : &mut WordReader) -> Result { _ => {} } } - // if not, then we keep looping - None => {} + // if word does not start with `$`, then we keep looping + _ => {} } } -- 2.47.1 From 5445891b8d843c35e1618f9fc976ac8267192656 Mon Sep 17 00:00:00 2001 From: Yehowshua Immanuel Date: Sat, 18 Jun 2022 01:00:01 -0400 Subject: [PATCH 27/50] add tests --- src/main.rs | 27 +----------------------- src/vcd/parse.rs | 54 ++++++++++++++++++++++++++++++++++++++++++++++++ src/vcd/types.rs | 2 +- 3 files changed, 56 insertions(+), 27 deletions(-) diff --git a/src/main.rs b/src/main.rs index 623b1ba..234f47a 100644 --- a/src/main.rs +++ b/src/main.rs @@ -13,33 +13,8 @@ struct Cli { fn main() -> std::io::Result<()> { let args = Cli::parse(); - let file = File::open(&args.path)?; - // dbg!(take_while("01234hello", digit)); - - // dbg!(["hello", "goodbye", "myworld"].contains(&"myworlde")); - // let mut word_gen = WordReader::new(file); - // let mut word_count = 0; - - // while word_gen.next_word().is_some() { - // word_count += 1; - // } - // dbg!(word_count); - - // let word1 = "hello world"; - // let word2 = "hello planet"; - // dbg!(&word1[0..6].len()); + let file = File::open(&args.path)?; parse_vcd(file); - // tag("my oh my"); - - - // loop { - // let word = word_gen.next_word(); - // if word.is_none() {break}; - - // dbg!(word.unwrap()); - // } - - Ok(()) } \ No newline at end of file diff --git a/src/vcd/parse.rs b/src/vcd/parse.rs index 750b777..198839a 100644 --- a/src/vcd/parse.rs +++ b/src/vcd/parse.rs @@ -284,6 +284,7 @@ fn parse_timescale(word_reader : &mut WordReader) -> Result<(Option, Timesc if residual == "" { let (word, cursor) = word_reader.next_word().ok_or(&err_msg)?; let unit = match word { + "fs" => {Ok(Timescale::fs)} "ps" => {Ok(Timescale::ps)} "ns" => {Ok(Timescale::ns)} "us" => {Ok(Timescale::us)} @@ -436,4 +437,57 @@ pub fn parse_vcd(file : File) { let header = parse_metadata(&mut word_gen).unwrap(); dbg!(header); +} + +#[cfg(test)] +mod tests { + use super::*; + use std::fs::File; + #[test] + fn headers() { + let files = vec![ + "./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", + "./test-vcd-files/xilinx_isim/test2x2_regex22_string1.vcd" + ]; + + for file in files { + let metadata = parse_metadata( + &mut WordReader::new( + File::open(file) + .unwrap() + ) + ); + assert!(metadata.is_ok()); + assert!(metadata.unwrap().date.is_some()); + } + + } } \ No newline at end of file diff --git a/src/vcd/types.rs b/src/vcd/types.rs index 38bda30..ed87467 100644 --- a/src/vcd/types.rs +++ b/src/vcd/types.rs @@ -6,7 +6,7 @@ use num::BigInt; pub(super) struct Version(pub String); #[derive(Debug)] -pub(super) enum Timescale {ps, ns, us, ms, s, unit} +pub(super) enum Timescale {fs, ps, ns, us, ms, s, unit} #[derive(Debug)] pub(super) struct Metadata { -- 2.47.1 From f5bb8d5a7c718e24a4dedd60d2518546d5f35b5b Mon Sep 17 00:00:00 2001 From: Yehowshua Immanuel Date: Sun, 19 Jun 2022 09:44:57 -0400 Subject: [PATCH 28/50] some re-org --- README.md | 16 +++-- src/vcd/parse.rs | 107 ++---------------------------- src/vcd/parse/combinator_atoms.rs | 70 +++++++++++++++++++ src/vcd/parse/types.rs | 25 +++++++ 4 files changed, 112 insertions(+), 106 deletions(-) create mode 100644 src/vcd/parse/combinator_atoms.rs create mode 100644 src/vcd/parse/types.rs diff --git a/README.md b/README.md index 641c3da..42e9eb9 100644 --- a/README.md +++ b/README.md @@ -26,14 +26,20 @@ The first build of the program may take some time. # TODO - [x] We need a way to merge lines. - - [ ] We need to start regression testing the parser over all files - - [ ] Decide if I want to return option types - - [ ] Propagate all to question mark unwrap types. - - [ ] Don't want variation in hh:mm:ss + - [x] We need to start regression testing the parser over all files + - [x] Decide if I want to return option types + - [x] Propagate all to question mark unwrap types. + - [x] Don't want variation in hh:mm:ss + - [x] parser_atoms -> combinator_atoms + - [x] make parse/types.rs + - [x] remove/replace calls to match_not_empty + - [ ] Split ``parse.rs``. It's getting too large. + - [ ] support parsing dates with commas + - [ ] move list of files to separate test file/folder + - [ ] Consolidate error messages and add cursors. - [ ] Consider what to do with don't care values will probably just convert them to strings for now. - - [ ] Split ``parse.rs``. It's getting too large. - [ ] Include line and possible column numbers - [ ] Change states to lowercase - [ ] Take a look at GTKWave parser to compare effificiency. diff --git a/src/vcd/parse.rs b/src/vcd/parse.rs index 198839a..3956214 100644 --- a/src/vcd/parse.rs +++ b/src/vcd/parse.rs @@ -1,111 +1,16 @@ -use super::*; use chrono::prelude::*; use itertools::Itertools; use std::fs::File; use ::function_name::named; -#[derive(Debug)] -pub struct Residual<'a>(&'a str); -#[derive(Debug)] -pub struct ParseResult<'a> {matched : &'a str, residual : &'a str} +use super::*; -pub fn digit(chr : u8) -> bool { - let zero = b'0' as u8; - let nine = b'9' as u8; +mod combinator_atoms; +use combinator_atoms::*; - let between_zero_and_nine = (chr >= zero) && (nine >= chr); +mod types; +use types::*; - return between_zero_and_nine -} - -pub 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 { - new_start += 1; - } - } - - return - ParseResult{ - matched : &word[0..new_start], - residual : &word[new_start..] - }; - -} - -pub 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 - } - } - - return - ParseResult{ - matched : &word[0..new_start], - residual : &word[new_start..] - }; - -} - -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} - new_start += 1; - } - - return - ParseResult{ - matched : &word[0..new_start], - residual : &word[new_start..] - }; -} - -impl<'a> ParseResult<'a> { - fn match_not_empty(& self) -> Result<(), String> { - if self.matched == "" { - return Err("failed".to_string()) - } - else { - return Ok(()) - } - } - - fn assert_match(& self) -> Result<&str, String> { - if self.matched == "" { - return Err("no match".to_string()) - } - else { - return Ok(self.matched) - } - } - - fn assert_residual(& self) -> Result<&str, String> { - if self.residual == "" { - return Err("no residual".to_string()) - } - else { - return Ok(self.residual) - } - } -} #[named] fn parse_date( @@ -311,7 +216,7 @@ fn parse_timescale(word_reader : &mut WordReader) -> Result<(Option, Timesc // then check for the `$end` keyword let (end, cursor) = word_reader.next_word().ok_or(&err_msg)?; - tag(end, "$end").match_not_empty()?; + tag(end, "$end").assert_match()?; return Ok(timescale); diff --git a/src/vcd/parse/combinator_atoms.rs b/src/vcd/parse/combinator_atoms.rs new file mode 100644 index 0000000..86ca84a --- /dev/null +++ b/src/vcd/parse/combinator_atoms.rs @@ -0,0 +1,70 @@ +use super::types::ParseResult; + +pub(super) fn digit(chr : u8) -> bool { + let zero = b'0' as u8; + let nine = b'9' as u8; + + let between_zero_and_nine = (chr >= zero) && (nine >= chr); + + return between_zero_and_nine +} + +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 { + new_start += 1; + } + } + + return + ParseResult{ + matched : &word[0..new_start], + residual : &word[new_start..] + }; + +} + +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 + } + } + + 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); + 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} + new_start += 1; + } + + return + ParseResult{ + matched : &word[0..new_start], + residual : &word[new_start..] + }; +} diff --git a/src/vcd/parse/types.rs b/src/vcd/parse/types.rs new file mode 100644 index 0000000..8bab3d4 --- /dev/null +++ b/src/vcd/parse/types.rs @@ -0,0 +1,25 @@ +#[derive(Debug)] +pub(super) struct ParseResult<'a> { + 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 == "" { + return Err("no match".to_string()) + } + else { + return Ok(self.matched) + } + } + + 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 -- 2.47.1 From dbae68ba3b49de281811c9cd575491142735de44 Mon Sep 17 00:00:00 2001 From: Yehowshua Immanuel Date: Tue, 21 Jun 2022 21:06:51 -0400 Subject: [PATCH 29/50] finish splitting up parse.rs --- README.md | 6 +- src/vcd/parse.rs | 326 +------------------------------------ src/vcd/parse/metadata.rs | 331 ++++++++++++++++++++++++++++++++++++++ 3 files changed, 338 insertions(+), 325 deletions(-) create mode 100644 src/vcd/parse/metadata.rs diff --git a/README.md b/README.md index 42e9eb9..d8b45c1 100644 --- a/README.md +++ b/README.md @@ -24,6 +24,8 @@ The first build of the program may take some time. ``cargo run --release test-vcd-files/aldec/SPI_Write.vcd`` +You can run all the tests with ``cargo test`` + # TODO - [x] We need a way to merge lines. - [x] We need to start regression testing the parser over all files @@ -33,9 +35,11 @@ The first build of the program may take some time. - [x] parser_atoms -> combinator_atoms - [x] make parse/types.rs - [x] remove/replace calls to match_not_empty - - [ ] Split ``parse.rs``. It's getting too large. + - [x] Split ``parse.rs``. It's getting too large. - [ ] support parsing dates with commas - [ ] move list of files to separate test file/folder + - [ ] Fix warning especially usage and restriction warnings once I'm + able to successfully parse all sample VCDs. - [ ] Consolidate error messages and add cursors. - [ ] Consider what to do with don't care values diff --git a/src/vcd/parse.rs b/src/vcd/parse.rs index 3956214..b22bf71 100644 --- a/src/vcd/parse.rs +++ b/src/vcd/parse.rs @@ -11,331 +11,9 @@ use combinator_atoms::*; mod types; use types::*; +mod metadata; +use metadata::*; -#[named] -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), -) -> 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!("reached end of file without parser leaving {}\n", function_name!()); - 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)) - } - - word.to_string() - }; - - let month = { - // check for another word in the file - let (word, cursor) = word_and_ctx2; - - let months = [ - "Jan", "Feb", "Mar", "Apr", - "May", "Jun", "Jul", "Aug", - "Sept", "Oct", "Nov", "Dec", - ]; - - if !months.contains(&word) { - let msg = format!("reached end of file without parser leaving {}\n", function_name!()); - let 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)) - } - - word.to_string() - }; - - let date = { - // check for another word in the file - let (word, cursor) = word_and_ctx3; - - let date : u8 = match word.to_string().parse() { - Ok(date) => date, - Err(_) => {return Err("".to_string())} - }; - - if date > 31 { - let msg = format!("reached end of file without parser leaving {}\n", function_name!()); - 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)) - - } - - date.to_string() - }; - - let (hh, mm, ss) = { - // get hour - let (word, cursor) = word_and_ctx4; - - let res = take_until(word, b':'); - res.assert_match()?; - let hh : u8 = res.matched.to_string() - .parse() - .map_err(|_| "failed to parse".to_string())?; - - if hh > 23 { - let msg = format!("reached end of file without parser leaving {}\n", function_name!()); - 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)) - } - - // 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(|_| "failed to parse".to_string())?; - - if mm > 60 { - let msg = format!("reached end of file without parser leaving {}\n", function_name!()); - 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)) - } - - // 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(|_| "failed to parse".to_string())?; - - if ss > 60 { - let msg = format!("reached end of file without parser leaving {}\n", function_name!()); - 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)) - } - (hh.to_string(), mm.to_string(), ss.to_string()) - }; - - let year = { - // check for another word in the file - let (word, cursor) = word_and_ctx5; - word.to_string() - }; - - // unfortunately, the minutes, seconds, and hour could occur in an - // unexpected order - let full_date = format!("{day} {month} {date} {hh}:{mm}:{ss} {year}"); - let full_date = Utc.datetime_from_str(full_date.as_str(), "%a %b %e %T %Y"); - if full_date.is_ok() { - return Ok(full_date.unwrap()) - } - - Err("failed to parse date".to_string()) - -} - -#[named] -fn parse_version(word_reader : &mut WordReader) -> Result { - let mut version = String::new(); - - loop { - let word = word_reader.next_word(); - - // if there isn't another word left in the file, then we exit - if word.is_none() { - return Err(format!("reached end of file without parser leaving {}", function_name!())) - } - - let (word, cursor) = word.unwrap(); - - if word == "$end" { - // truncate trailing whitespace - let version = version[0..(version.len() - 1)].to_string(); - return Ok(Version(version)) - - } - else { - version.push_str(word); - version.push_str(" "); - } - } -} - -#[named] -fn parse_timescale(word_reader : &mut WordReader) -> Result<(Option, Timescale), String> { - let err_msg = format!("failed in {}", function_name!()); - - // we might see `scalarunit $end` or `scalar unit $end` - - // first get timescale - let (word, cursor) = word_reader.next_word().ok_or(&err_msg)?; - let word = word.to_string(); - let ParseResult{matched, residual} = take_while(word.as_str(), digit); - let scalar = matched; - - let scalar : u32 = scalar.to_string().parse() - .map_err(|_| &err_msg)?; - - let timescale = { - if residual == "" { - let (word, cursor) = word_reader.next_word().ok_or(&err_msg)?; - let unit = match word { - "fs" => {Ok(Timescale::fs)} - "ps" => {Ok(Timescale::ps)} - "ns" => {Ok(Timescale::ns)} - "us" => {Ok(Timescale::us)} - "ms" => {Ok(Timescale::ms)} - "s" => {Ok(Timescale::s)} - _ => {Err(err_msg.to_string())} - }.unwrap(); - - (Some(scalar), unit) - } - else { - let unit = match residual { - "ps" => {Ok(Timescale::ps)} - "ns" => {Ok(Timescale::ns)} - "us" => {Ok(Timescale::us)} - "ms" => {Ok(Timescale::ms)} - "s" => {Ok(Timescale::s)} - _ => {Err(err_msg.to_string())} - }.unwrap(); - - (Some(scalar), unit) - } - }; - - // then check for the `$end` keyword - let (end, cursor) = word_reader.next_word().ok_or(&err_msg)?; - tag(end, "$end").assert_match()?; - - return Ok(timescale); - - Err("".to_string()) -} - -#[named] -fn parse_metadata(word_reader : &mut WordReader) -> Result { - let err_msg = format!("reached end of file without parser leaving {}", function_name!()); - - let mut metadata = Metadata { - date : None, - version : None, - timescale : (None, Timescale::unit) - }; - - loop { - // check for another word in the file - let (word, cursor) = word_reader.next_word().ok_or(&err_msg)?; - - let ParseResult{matched, residual} = tag(word, "$"); - match matched { - // we hope that this word stars with a `$` - "$" => { - match residual { - "date" => { - let err_msg = format!("reached end of file without parser leaving {}", function_name!()); - // a date is typically composed of the 5 following words which can - // 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. - // - // It is also possible that within each permutation, the hours, - // minutes, and seconds could be in an unusual order, which means - // 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 `$end`, we have to - // immediately stop trying to get more words. - - let mut found_end = false; - let mut lookahead_5_words : Vec<(String, Cursor)> = Vec::new(); - - for word in 0..5 { - let (word, cursor) = word_reader.next_word().expect(err_msg.as_str()); - let word = word.to_string(); - match word.as_str() { - "$end" => { - found_end = true; - break; - } - _ => { - lookahead_5_words.push((word, cursor)); - } - }; - } - - // 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()); - - // go ahead and search for a match amongst permuted date text - for mut permutations in permutations { - let (w1, s1) = permutations.pop().unwrap(); - let arg_1 = (&w1[..], s1); - - let (w2, s2) = permutations.pop().unwrap(); - let arg_2 = (&w2[..], s2); - - let (w3, s3) = permutations.pop().unwrap(); - let arg_3 = (&w3[..], s3); - - let (w4, s4) = permutations.pop().unwrap(); - let arg_4 = (&w4[..], s4); - - let (w5, s5) = permutations.pop().unwrap(); - let arg_5 = (&w5[..], s5); - - let parsed_date = parse_date(arg_1, arg_2, arg_3, arg_4, arg_5); - - // store date and exit loop if a match is found - if parsed_date.is_ok() { - metadata.date = Some(parsed_date.unwrap()); - break - } - - } - } - "version" => { - let version = parse_version(word_reader); - if version.is_ok() { - metadata.version = Some(version.unwrap()); - } - } - "timescale" => { - let timescale = parse_timescale(word_reader); - if timescale.is_ok() { - metadata.timescale = timescale.unwrap(); - } - } - // in VCDs, the scope keyword indicates the end of the metadata section - "scope" => {break} - // we keep searching for words until we've found one of the following - // keywords, ["version", "timescale", "scope"] - _ => {} - } - } - // if word does not start with `$`, then we keep looping - _ => {} - } - - } - return Ok(metadata) -} pub fn parse_vcd(file : File) { let mut word_gen = WordReader::new(file); diff --git a/src/vcd/parse/metadata.rs b/src/vcd/parse/metadata.rs new file mode 100644 index 0000000..8f07566 --- /dev/null +++ b/src/vcd/parse/metadata.rs @@ -0,0 +1,331 @@ +use chrono::prelude::*; +use itertools::Itertools; +use std::fs::File; +use ::function_name::named; + +use super::*; + +#[named] +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), +) -> 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!("reached end of file without parser leaving {}\n", function_name!()); + 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)) + } + + word.to_string() + }; + + let month = { + // check for another word in the file + let (word, cursor) = word_and_ctx2; + + let months = [ + "Jan", "Feb", "Mar", "Apr", + "May", "Jun", "Jul", "Aug", + "Sept", "Oct", "Nov", "Dec", + ]; + + if !months.contains(&word) { + let msg = format!("reached end of file without parser leaving {}\n", function_name!()); + let 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)) + } + + word.to_string() + }; + + let date = { + // check for another word in the file + let (word, cursor) = word_and_ctx3; + + let date : u8 = match word.to_string().parse() { + Ok(date) => date, + Err(_) => {return Err("".to_string())} + }; + + if date > 31 { + let msg = format!("reached end of file without parser leaving {}\n", function_name!()); + 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)) + + } + + date.to_string() + }; + + let (hh, mm, ss) = { + // get hour + let (word, cursor) = word_and_ctx4; + + let res = take_until(word, b':'); + res.assert_match()?; + let hh : u8 = res.matched.to_string() + .parse() + .map_err(|_| "failed to parse".to_string())?; + + if hh > 23 { + let msg = format!("reached end of file without parser leaving {}\n", function_name!()); + 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)) + } + + // 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(|_| "failed to parse".to_string())?; + + if mm > 60 { + let msg = format!("reached end of file without parser leaving {}\n", function_name!()); + 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)) + } + + // 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(|_| "failed to parse".to_string())?; + + if ss > 60 { + let msg = format!("reached end of file without parser leaving {}\n", function_name!()); + 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)) + } + (hh.to_string(), mm.to_string(), ss.to_string()) + }; + + let year = { + // check for another word in the file + let (word, cursor) = word_and_ctx5; + word.to_string() + }; + + // unfortunately, the minutes, seconds, and hour could occur in an + // unexpected order + let full_date = format!("{day} {month} {date} {hh}:{mm}:{ss} {year}"); + let full_date = Utc.datetime_from_str(full_date.as_str(), "%a %b %e %T %Y"); + if full_date.is_ok() { + return Ok(full_date.unwrap()) + } + + Err("failed to parse date".to_string()) + +} + +#[named] +pub(super) fn parse_version(word_reader : &mut WordReader) -> Result { + let mut version = String::new(); + + loop { + let word = word_reader.next_word(); + + // if there isn't another word left in the file, then we exit + if word.is_none() { + return Err(format!("reached end of file without parser leaving {}", function_name!())) + } + + let (word, cursor) = word.unwrap(); + + if word == "$end" { + // truncate trailing whitespace + let version = version[0..(version.len() - 1)].to_string(); + return Ok(Version(version)) + + } + else { + version.push_str(word); + version.push_str(" "); + } + } +} + +#[named] +pub(super) fn parse_timescale(word_reader : &mut WordReader) -> Result<(Option, Timescale), String> { + let err_msg = format!("failed in {}", function_name!()); + + // we might see `scalarunit $end` or `scalar unit $end` + + // first get timescale + let (word, cursor) = word_reader.next_word().ok_or(&err_msg)?; + let word = word.to_string(); + let ParseResult{matched, residual} = take_while(word.as_str(), digit); + let scalar = matched; + + let scalar : u32 = scalar.to_string().parse() + .map_err(|_| &err_msg)?; + + let timescale = { + if residual == "" { + let (word, cursor) = word_reader.next_word().ok_or(&err_msg)?; + let unit = match word { + "fs" => {Ok(Timescale::fs)} + "ps" => {Ok(Timescale::ps)} + "ns" => {Ok(Timescale::ns)} + "us" => {Ok(Timescale::us)} + "ms" => {Ok(Timescale::ms)} + "s" => {Ok(Timescale::s)} + _ => {Err(err_msg.to_string())} + }.unwrap(); + + (Some(scalar), unit) + } + else { + let unit = match residual { + "ps" => {Ok(Timescale::ps)} + "ns" => {Ok(Timescale::ns)} + "us" => {Ok(Timescale::us)} + "ms" => {Ok(Timescale::ms)} + "s" => {Ok(Timescale::s)} + _ => {Err(err_msg.to_string())} + }.unwrap(); + + (Some(scalar), unit) + } + }; + + // then check for the `$end` keyword + let (end, cursor) = word_reader.next_word().ok_or(&err_msg)?; + tag(end, "$end").assert_match()?; + + return Ok(timescale); + + Err("".to_string()) +} + +#[named] +pub(super) fn parse_metadata(word_reader : &mut WordReader) -> Result { + let err_msg = format!("reached end of file without parser leaving {}", function_name!()); + + let mut metadata = Metadata { + date : None, + version : None, + timescale : (None, Timescale::unit) + }; + + loop { + // check for another word in the file + let (word, cursor) = word_reader.next_word().ok_or(&err_msg)?; + + let ParseResult{matched, residual} = tag(word, "$"); + match matched { + // we hope that this word stars with a `$` + "$" => { + match residual { + "date" => { + let err_msg = format!("reached end of file without parser leaving {}", function_name!()); + // a date is typically composed of the 5 following words which can + // 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. + // + // It is also possible that within each permutation, the hours, + // minutes, and seconds could be in an unusual order, which means + // 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 `$end`, we have to + // immediately stop trying to get more words. + + let mut found_end = false; + let mut lookahead_5_words : Vec<(String, Cursor)> = Vec::new(); + + for word in 0..5 { + let (word, cursor) = word_reader.next_word().expect(err_msg.as_str()); + let word = word.to_string(); + match word.as_str() { + "$end" => { + found_end = true; + break; + } + _ => { + lookahead_5_words.push((word, cursor)); + } + }; + } + + // 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()); + + // go ahead and search for a match amongst permuted date text + for mut permutations in permutations { + let (w1, s1) = permutations.pop().unwrap(); + let arg_1 = (&w1[..], s1); + + let (w2, s2) = permutations.pop().unwrap(); + let arg_2 = (&w2[..], s2); + + let (w3, s3) = permutations.pop().unwrap(); + let arg_3 = (&w3[..], s3); + + let (w4, s4) = permutations.pop().unwrap(); + let arg_4 = (&w4[..], s4); + + let (w5, s5) = permutations.pop().unwrap(); + let arg_5 = (&w5[..], s5); + + let parsed_date = parse_date(arg_1, arg_2, arg_3, arg_4, arg_5); + + // store date and exit loop if a match is found + if parsed_date.is_ok() { + metadata.date = Some(parsed_date.unwrap()); + break + } + + } + } + "version" => { + let version = parse_version(word_reader); + if version.is_ok() { + metadata.version = Some(version.unwrap()); + } + } + "timescale" => { + let timescale = parse_timescale(word_reader); + if timescale.is_ok() { + metadata.timescale = timescale.unwrap(); + } + } + // in VCDs, the scope keyword indicates the end of the metadata section + "scope" => {break} + // we keep searching for words until we've found one of the following + // keywords, ["version", "timescale", "scope"] + _ => {} + } + } + // if word does not start with `$`, then we keep looping + _ => {} + } + + } + return Ok(metadata) +} \ No newline at end of file -- 2.47.1 From 8b9114499e48c13c9eac66ef11edb510fee8ca9e Mon Sep 17 00:00:00 2001 From: Void User Date: Thu, 23 Jun 2022 20:52:39 -0400 Subject: [PATCH 30/50] a bit of restructuring to support more modular tests --- src/test/files.rs | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) create mode 100644 src/test/files.rs diff --git a/src/test/files.rs b/src/test/files.rs new file mode 100644 index 0000000..e658a97 --- /dev/null +++ b/src/test/files.rs @@ -0,0 +1,32 @@ +pub const 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/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", + "./test-vcd-files/xilinx_isim/test2x2_regex22_string1.vcd" +]; \ No newline at end of file -- 2.47.1 From 77235a19bc8537edc4b40d91f02ec20410950727 Mon Sep 17 00:00:00 2001 From: Void User Date: Thu, 23 Jun 2022 20:54:27 -0400 Subject: [PATCH 31/50] missed some files by committing in the wrong folder --- src/main.rs | 3 +++ src/test.rs | 2 ++ src/vcd/parse.rs | 36 ++---------------------------------- 3 files changed, 7 insertions(+), 34 deletions(-) create mode 100644 src/test.rs diff --git a/src/main.rs b/src/main.rs index 234f47a..45723cd 100644 --- a/src/main.rs +++ b/src/main.rs @@ -1,6 +1,9 @@ use std::fs::File; use clap::Parser; +pub mod test; +use test::*; + pub mod vcd; use vcd::*; 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/vcd/parse.rs b/src/vcd/parse.rs index b22bf71..816f22a 100644 --- a/src/vcd/parse.rs +++ b/src/vcd/parse.rs @@ -25,43 +25,11 @@ pub fn parse_vcd(file : File) { #[cfg(test)] mod tests { use super::*; + use crate::test; use std::fs::File; #[test] fn headers() { - let files = vec![ - "./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", - "./test-vcd-files/xilinx_isim/test2x2_regex22_string1.vcd" - ]; - - for file in files { + for file in test::files { let metadata = parse_metadata( &mut WordReader::new( File::open(file) -- 2.47.1 From 21661d7967177a8011c5eee5be36fbb6d5702adc Mon Sep 17 00:00:00 2001 From: Void User Date: Thu, 23 Jun 2022 20:56:44 -0400 Subject: [PATCH 32/50] no longer need a list of files in the REAMDE --- README.md | 36 ++---------------------------------- 1 file changed, 2 insertions(+), 34 deletions(-) diff --git a/README.md b/README.md index d8b45c1..750c0a2 100644 --- a/README.md +++ b/README.md @@ -36,8 +36,8 @@ You can run all the tests with ``cargo test`` - [x] make parse/types.rs - [x] remove/replace calls to match_not_empty - [x] Split ``parse.rs``. It's getting too large. + - [x] move list of files to separate test file/folder - [ ] support parsing dates with commas - - [ ] move list of files to separate test file/folder - [ ] Fix warning especially usage and restriction warnings once I'm able to successfully parse all sample VCDs. @@ -50,36 +50,4 @@ You can run all the tests with ``cargo test`` - [ ] Send survey to community channel. # Probably No Longer Needed - - [ ] Should insert nodes in BFS order - -# Files - - ./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 - - ./test-vcd-files/xilinx_isim/test2x2_regex22_string1.vcd \ No newline at end of file + - [ ] Should insert nodes in BFS order \ No newline at end of file -- 2.47.1 From 29d72b6e9c470f1427accc9c5893923cdc5ee65c Mon Sep 17 00:00:00 2001 From: Yehowshua Immanuel Date: Fri, 24 Jun 2022 22:22:55 -0400 Subject: [PATCH 33/50] postpone adding date support for ncsim, quartus, treadle, and vivado --- src/test/files.rs | 52 ++++++++++++++++++++++++++----- src/vcd/parse.rs | 18 ++++++++++- src/vcd/parse/combinator_atoms.rs | 14 +++++++++ 3 files changed, 76 insertions(+), 8 deletions(-) diff --git a/src/test/files.rs b/src/test/files.rs index e658a97..4cea310 100644 --- a/src/test/files.rs +++ b/src/test/files.rs @@ -1,4 +1,6 @@ -pub const files : [&str; 24] = [ +// 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", @@ -12,21 +14,57 @@ pub const files : [&str; 24] = [ "./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/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/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/vivado/iladata.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 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/parse.rs b/src/vcd/parse.rs index 816f22a..5fc9a69 100644 --- a/src/vcd/parse.rs +++ b/src/vcd/parse.rs @@ -29,7 +29,10 @@ mod tests { use std::fs::File; #[test] fn headers() { - for file in test::files { + // 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) @@ -40,5 +43,18 @@ mod tests { 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()); + } + } } \ No newline at end of file diff --git a/src/vcd/parse/combinator_atoms.rs b/src/vcd/parse/combinator_atoms.rs index 86ca84a..0627d3e 100644 --- a/src/vcd/parse/combinator_atoms.rs +++ b/src/vcd/parse/combinator_atoms.rs @@ -29,6 +29,20 @@ pub(super) fn take_until<'a>(word : &'a str, pattern : u8) -> ParseResult<'a> { } +// TODO: if I end up using simulator specific date parsers, ``take_until`` may +// suffice rendering this function obselete, at which point I should delete it. +pub(super) fn truncate_last_chr_when<'a>(word : &'a str, cond : fn(u8) -> bool) -> &'a str { + let last_chr = word.as_bytes().last().unwrap(); + let mut new_end_index = word.len(); + + if cond(*last_chr) { + new_end_index -= 1; + } + + return &word[0..new_end_index] + +} + pub(super) fn take_while<'a>(word : &'a str, cond : fn(u8) -> bool) -> ParseResult<'a> { let mut new_start = 0; -- 2.47.1 From 49d103fd56e0c0425fb0fd8474916064354bf5d8 Mon Sep 17 00:00:00 2001 From: Yehowshua Immanuel Date: Tue, 12 Jul 2022 20:02:45 -0400 Subject: [PATCH 34/50] some incomplete changes --- src/main.rs | 3 ++- src/vcd/parse.rs | 33 ++++++++++++++++++++++++++++++++- src/vcd/parse/metadata.rs | 2 +- src/vcd/reader.rs | 12 ++++++++++-- src/vcd/types.rs | 16 ++++++++-------- 5 files changed, 53 insertions(+), 13 deletions(-) diff --git a/src/main.rs b/src/main.rs index 45723cd..2d87fcd 100644 --- a/src/main.rs +++ b/src/main.rs @@ -5,7 +5,7 @@ pub mod test; use test::*; pub mod vcd; -use vcd::*; +use vcd::parse_vcd; #[derive(Parser)] struct Cli { @@ -16,6 +16,7 @@ struct Cli { fn main() -> std::io::Result<()> { let args = Cli::parse(); + let file = File::open(&args.path)?; parse_vcd(file); diff --git a/src/vcd/parse.rs b/src/vcd/parse.rs index 5fc9a69..f507f4f 100644 --- a/src/vcd/parse.rs +++ b/src/vcd/parse.rs @@ -14,12 +14,43 @@ use types::*; mod metadata; use metadata::*; +// use function_name::named; + +#[named] +fn parse_signal_tree<'a>( + word_reader : &mut WordReader, + vcd : &'a mut VCD +) -> Result<&'a mut VCD, String> { + let err : Result<&'a mut VCD, String> = Err(format!("reached end of file without parser leaving {}", function_name!())); + // we assume we've already seen a `$scope` once + // by the time we reach this function + // let scope_name = + loop { + let word = word_reader.next_word(); + + // if there isn't another word left in the file, then we exit + if word.is_none() { + return err; + } + } + Ok(vcd) +} + pub fn parse_vcd(file : File) { let mut word_gen = WordReader::new(file); let header = parse_metadata(&mut word_gen).unwrap(); - dbg!(header); + dbg!(&header); + + // let (word, cursor) = word_gen.next_word().unwrap(); + // cursor.error(word).unwrap(); + + let mut vcd = VCD{ + metadata: header, + all_signals: vec![], + all_scopes: vec![] + }; } #[cfg(test)] diff --git a/src/vcd/parse/metadata.rs b/src/vcd/parse/metadata.rs index 8f07566..7e0cc91 100644 --- a/src/vcd/parse/metadata.rs +++ b/src/vcd/parse/metadata.rs @@ -1,7 +1,7 @@ use chrono::prelude::*; use itertools::Itertools; use std::fs::File; -use ::function_name::named; +use function_name::named; use super::*; diff --git a/src/vcd/reader.rs b/src/vcd/reader.rs index b9c85e4..f361716 100644 --- a/src/vcd/reader.rs +++ b/src/vcd/reader.rs @@ -12,6 +12,14 @@ struct Word(usize); #[derive(Debug)] pub struct Cursor(Line, Word); +impl Cursor { + pub(super) fn error(&self, word : &str) -> Result<(), String> { + let Cursor(Line(line_no), Word(word_no)) = self; + Err(format!("Error on word '{word}' {word_no} words into line {line_no}!")) + } + +} + pub struct WordReader { reader : io::BufReader, EOF : bool, @@ -21,7 +29,7 @@ pub struct WordReader { } impl WordReader { - pub fn new(file : File) -> WordReader { + pub(super) fn new(file : File) -> WordReader { let mut reader = io::BufReader::new(file); WordReader { reader : reader, @@ -32,7 +40,7 @@ impl WordReader { } } - pub fn next_word(&mut self) -> Option<(&str, Cursor)> { + pub(super) fn next_word(&mut self) -> Option<(&str, Cursor)> { // if there are no more words, attempt to read more content // from the file if self.str_slices.is_empty() { diff --git a/src/vcd/types.rs b/src/vcd/types.rs index ed87467..858c122 100644 --- a/src/vcd/types.rs +++ b/src/vcd/types.rs @@ -15,13 +15,13 @@ pub(super) struct Metadata { pub(super) timescale : (Option, Timescale)} #[derive(Debug)] -struct Scope_Idx(usize); +pub(super) struct Scope_Idx(usize); #[derive(Debug)] -struct Signal_Idx(usize); +pub(super) struct Signal_Idx(usize); #[derive(Debug)] -enum SignalGeneric{ +pub(super) enum SignalGeneric{ Signal{ name : String, timeline : BTreeMap, @@ -32,18 +32,18 @@ enum SignalGeneric{ } #[derive(Debug)] -struct Scope { +pub(super) struct Scope { name : String, child_signals : Vec, child_scopes : Vec} #[derive(Debug)] -struct VCD { - metadata : Metadata, - all_signals : Vec, +pub struct VCD { + pub(super) metadata : Metadata, + pub(super) all_signals : Vec, // the root scope should always be placed at index 0 - all_scopes : Vec} + pub(super) all_scopes : Vec} impl VCD { pub fn new() -> Self { -- 2.47.1 From 8bcd2bc8ec0514506bce80042119efd962d845e2 Mon Sep 17 00:00:00 2001 From: Yehowshua Immanuel Date: Thu, 14 Jul 2022 16:46:11 -0400 Subject: [PATCH 35/50] seems to be able to parse signal tree --- .gitignore | 38 ++++ src/main.rs | 2 +- src/vcd/parse.rs | 245 +++++++++++++++++++-- src/vcd/parse/combinator_atoms.rs | 20 ++ src/vcd/types.rs | 65 +++--- test-vcd-files/amaranth/up_counter.vcd | 287 +++++++++++++++++++++++++ test-vcd-files/sources.csv | 8 +- 7 files changed, 611 insertions(+), 54 deletions(-) create mode 100644 test-vcd-files/amaranth/up_counter.vcd diff --git a/.gitignore b/.gitignore index 96ef6c0..1a1541a 100644 --- a/.gitignore +++ b/.gitignore @@ -1,2 +1,40 @@ /target Cargo.lock + +# Created by https://www.toptal.com/developers/gitignore/api/macos +# Edit at https://www.toptal.com/developers/gitignore?templates=macos + +### macOS ### +# General +.DS_Store +.AppleDouble +.LSOverride + +# Icon must end with two \r +Icon + + +# Thumbnails +._* + +# Files that might appear in the root of a volume +.DocumentRevisions-V100 +.fseventsd +.Spotlight-V100 +.TemporaryItems +.Trashes +.VolumeIcon.icns +.com.apple.timemachine.donotpresent + +# Directories potentially created on remote AFP share +.AppleDB +.AppleDesktop +Network Trash Folder +Temporary Items +.apdisk + +### macOS Patch ### +# iCloud generated files +*.icloud + +# End of https://www.toptal.com/developers/gitignore/api/macos diff --git a/src/main.rs b/src/main.rs index 2d87fcd..69ae197 100644 --- a/src/main.rs +++ b/src/main.rs @@ -18,7 +18,7 @@ fn main() -> std::io::Result<()> { let file = File::open(&args.path)?; - parse_vcd(file); + parse_vcd(file).unwrap(); Ok(()) } \ No newline at end of file diff --git a/src/vcd/parse.rs b/src/vcd/parse.rs index f507f4f..1c6a37f 100644 --- a/src/vcd/parse.rs +++ b/src/vcd/parse.rs @@ -1,6 +1,7 @@ use chrono::prelude::*; use itertools::Itertools; -use std::fs::File; +use std::{fs::File}; +use std::collections::{BTreeMap, HashMap}; use ::function_name::named; use super::*; @@ -14,43 +15,251 @@ use types::*; mod metadata; use metadata::*; -// use function_name::named; +#[named] +fn parse_var<'a>( + word_reader : &mut WordReader, + parent_scope_idx : Scope_Idx, + vcd : &'a mut VCD, + signal_map : &mut HashMap +) -> Result<(), String> { + let err = format!("reached end of file without parser leaving {}", function_name!()); + let (word, cursor) = word_reader.next_word().ok_or(&err)?; + let expected_types = "[integer, parameter, real, reg, string, wire]"; + + // $var parameter 3 a IDLE $end + // ^^^^^^^^^ - var_type + let var_type = match word { + "integer" => {Ok(Sig_Type::Integer)} + "parameter" => {Ok(Sig_Type::Parameter)} + "real" => {Ok(Sig_Type::Real)} + "reg" => {Ok(Sig_Type::Reg)} + "string" => {Ok(Sig_Type::Str)} + "wire" => {Ok(Sig_Type::Wire)} + _ => { + let err = format!("found keyword `{word}` but expected one of {expected_types} on {cursor:?}"); + Err(err) + } + }?; + + let (word, cursor) = word_reader.next_word().ok_or(&err)?; + let parse_err = format!("failed to parse as usize on {cursor:?}"); + + // $var parameter 3 a IDLE $end + // ^ - no_bits + let no_bits = match var_type { + Sig_Type::Integer | Sig_Type::Parameter | + Sig_Type::Real | Sig_Type::Reg | + Sig_Type::Wire => { + let no_bits = word.parse::().expect(parse_err.as_str()); + Some(no_bits) + } + // for strings, we don't really care what the number of bits is + _ => {None} + }; + + // $var parameter 3 a IDLE $end + // ^ - signal_alias + let (word, cursor) = word_reader.next_word().ok_or(&err)?; + let signal_alias = word.to_string(); + + // $var parameter 3 a IDLE $end + // ^^^^ - full_signal_name(can extend until $end) + let mut full_signal_name = Vec::::new(); + loop { + let (word, cursor) = word_reader.next_word().ok_or(&err)?; + match word { + "$end" => {break} + _ => {full_signal_name.push(word.to_string())} + } + } + let full_signal_name = full_signal_name.join(" "); + + // Is the current variable an alias to a signal already encountered? + // if so, handle ref_signal_idx accordingly, if not, add signal to hash + // map + let (signal, signal_idx) = match signal_map.get(&signal_alias) { + Some(ref_signal_idx) => { + let signal_idx = Signal_Idx(vcd.all_signals.len()); + let signal = Signal::Alias{ + name: full_signal_name, + signal_alias: *ref_signal_idx}; + (signal, signal_idx) + } + None => { + let signal_idx = Signal_Idx(vcd.all_signals.len()); + signal_map.insert(signal_alias.to_string(), signal_idx); + let signal = Signal::Data{ + name: full_signal_name, + sig_type: var_type, + num_bits: no_bits, + self_idx: signal_idx, + timeline: BTreeMap::new(), + scope_parent: parent_scope_idx }; + (signal, signal_idx) + } + }; + + vcd.all_signals.push(signal); + let Scope_Idx(parent_scope_idx_usize) = parent_scope_idx; + let parent_scope = vcd.all_scopes.get_mut(parent_scope_idx_usize).unwrap(); + parent_scope.child_signals.push(signal_idx); + + Ok(()) +} #[named] fn parse_signal_tree<'a>( - word_reader : &mut WordReader, - vcd : &'a mut VCD -) -> Result<&'a mut VCD, String> { - let err : Result<&'a mut VCD, String> = Err(format!("reached end of file without parser leaving {}", function_name!())); - // we assume we've already seen a `$scope` once - // by the time we reach this function - // let scope_name = - loop { - let word = word_reader.next_word(); + word_reader : &mut WordReader, + parent_scope_idx : Option, + vcd : &'a mut VCD, + signal_map : &mut HashMap +) -> Result<(), String> { - // if there isn't another word left in the file, then we exit - if word.is_none() { - return err; + // $scope module reg_mag_i $end + // ^^^^^^ - module keyword + let err = format!("reached end of file without parser leaving {}", function_name!()); + ident(word_reader, "module")?; + + // $scope module reg_mag_i $end + // ^^^^^^^^^ - scope name + let (scope_name, _) = word_reader.next_word().ok_or(err)?; + + let curr_scope_idx = Scope_Idx(vcd.all_scopes.len()); + + // register this scope as a child of the current parent scope + // if there is a parent scope + match parent_scope_idx { + Some(Scope_Idx(parent_scope_idx)) => { + let parent_scope = vcd.all_scopes.get_mut(parent_scope_idx).unwrap(); + parent_scope.child_scopes.push(curr_scope_idx); + } + None => {} + } + + // 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![] + } + ); + + // $scope module reg_mag_i $end + // ^^^^ - end keyword + ident(word_reader, "$end")?; + + let err = format!("reached end of file without parser leaving {}", function_name!()); + loop { + let (word, cursor) = word_reader.next_word().ok_or(&err)?; + let ParseResult{matched, residual} = tag(word, "$"); + match matched { + // we hope that this word stars with a `$` + "$" => { + match residual { + "scope" => { + // recursive - parse inside of current scope tree + parse_signal_tree(word_reader, Some(curr_scope_idx), vcd, signal_map); + } + "var" => { + parse_var(word_reader, curr_scope_idx, vcd, signal_map)?; + } + "upscope" => { + ident(word_reader, "$end")?; + break + } + _ => { + let err = format!("found keyword `{residual}` but expected `$scope`, `$var`, or `$upscope` on {cursor:?}"); + return Err(err) + } + } + } + _ => { + let err = format!("found keyword `{matched}` but expected `$` on {cursor:?}"); + return Err(err) + } } } - Ok(vcd) + + // TODO : remove the following Ok(()) once we add loop above + Ok(()) } +// #[named] +// fn parse_signal_tree_outer<'a>( +// word_reader : &mut WordReader, +// vcd : &'a mut VCD, +// signal_map : &mut HashMap +// ) -> Result<(), String> { +// // We assume we've already seen a `$scope` once by the time we reach this function, +// // that why its call `parse_signal_tree_outer` and not just `parse_signal_tree`. +// // If our WordReader had a `putback` function, we wouldn't need to have a +// // `parse_signal_tree_outer`. -pub fn parse_vcd(file : File) { +// // the current scope is the parent scope + +// // $scope module reg_mag_i $end +// // ^^^^^^ - module keyword +// let err = format!("reached end of file without parser leaving {}", function_name!()); +// ident(word_reader, "module")?; + +// // $scope module reg_mag_i $end +// // ^^^^^^^^^ - scope name +// let (scope_name, _) = word_reader.next_word().ok_or(err)?; + +// let curr_scope_idx = Scope_Idx(vcd.all_scopes.len()); + +// // register this scope as a child of the current parent scope +// let Scope_Idx(parent_scope_idx_usize) = parent_scope_idx; +// let parent_scope = vcd.all_scopes.get_mut(parent_scope_idx_usize).unwrap(); +// parent_scope.child_scopes.push(curr_scope_idx); + +// 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![] +// } +// ); + +// // $scope module reg_mag_i $end +// // ^^^^ - end keyword +// ident(word_reader, "$end")?; + +// // recursive - parse inside of current scope tree +// parse_signal_tree(word_reader, curr_scope_idx, vcd, signal_map); + +// // ascend from parsing inside of current scope tree, expect $upscope $end +// ident(word_reader, "$upscope")?; +// ident(word_reader, "$end")?; + +// Ok(()) +// } + + +pub fn parse_vcd(file : File) -> Result<(), String> { let mut word_gen = WordReader::new(file); - let header = parse_metadata(&mut word_gen).unwrap(); + let header = parse_metadata(&mut word_gen)?; dbg!(&header); // let (word, cursor) = word_gen.next_word().unwrap(); // cursor.error(word).unwrap(); + let mut signal_map = std::collections::HashMap::new(); let mut vcd = VCD{ metadata: header, all_signals: vec![], - all_scopes: vec![] + all_scopes: vec![], }; + + parse_signal_tree(&mut word_gen, None, &mut vcd, &mut signal_map)?; + dbg!(&vcd.all_scopes); + Ok(()) } #[cfg(test)] diff --git a/src/vcd/parse/combinator_atoms.rs b/src/vcd/parse/combinator_atoms.rs index 0627d3e..ee180ad 100644 --- a/src/vcd/parse/combinator_atoms.rs +++ b/src/vcd/parse/combinator_atoms.rs @@ -1,4 +1,5 @@ use super::types::ParseResult; +use super::reader::WordReader; pub(super) fn digit(chr : u8) -> bool { let zero = b'0' as u8; @@ -82,3 +83,22 @@ pub(super) fn tag<'a>(word : &'a str, pattern : &'a str) -> ParseResult<'a> { residual : &word[new_start..] }; } + +pub(super) fn ident( + word_reader : &mut WordReader, + keyword : &str, +) -> Result<(), String> { + // let keyword = "module"; + + let err : Result<(), String> = Err(format!("reached end of file without parser leaving ident")); + let word = word_reader.next_word(); + let (word, cursor) = word.ok_or(err).unwrap(); + + if word == keyword { + return Ok(()) + } + 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/types.rs b/src/vcd/types.rs index 858c122..c1b0598 100644 --- a/src/vcd/types.rs +++ b/src/vcd/types.rs @@ -1,4 +1,4 @@ -use std::collections::BTreeMap; +use std::collections::{BTreeMap, HashMap}; use chrono::prelude::*; use num::BigInt; @@ -14,46 +14,49 @@ pub(super) struct Metadata { pub(super) version : Option, pub(super) timescale : (Option, Timescale)} -#[derive(Debug)] -pub(super) struct Scope_Idx(usize); +#[derive(Debug, Copy, Clone)] +pub(super) struct Scope_Idx(pub(super) usize); + +#[derive(Debug, Copy, Clone)] +pub(super) struct Signal_Idx(pub(super) usize); #[derive(Debug)] -pub(super) struct Signal_Idx(usize); +pub(super) enum Sig_Type {Integer, Parameter, Real, Reg, Str, Wire,} #[derive(Debug)] -pub(super) enum SignalGeneric{ - Signal{ - name : String, - timeline : BTreeMap, - scope_parent : Scope_Idx}, - SignalAlias{ - name : String, - signal_alias : Signal_Idx} +pub(super) enum Sig_Value { + Numeric(BigInt), + NonNumeric(String)} + +#[derive(Debug)] +pub(super) enum Signal{ + Data{ + name : String, + sig_type : Sig_Type, + num_bits : Option, + // TODO : may be able to remove self_idx + self_idx : Signal_Idx, + timeline : BTreeMap, + scope_parent : Scope_Idx}, + Alias{ + name : String, + signal_alias : Signal_Idx} } #[derive(Debug)] pub(super) struct Scope { - name : String, - child_signals : Vec, - child_scopes : Vec} + pub(super) name : String, + + pub(super) parent_idx : Option, + // TODO : may be able to remove self_idx + pub(super) self_idx : Scope_Idx, + + pub(super) child_signals : Vec, + pub(super) child_scopes : Vec} #[derive(Debug)] pub struct VCD { pub(super) metadata : Metadata, - pub(super) all_signals : Vec, - // the root scope should always be placed at index 0 - pub(super) all_scopes : Vec} - -impl VCD { - pub fn new() -> Self { - let metadata = Metadata { - date : None, - version : None, - timescale : (None, Timescale::unit)}; - VCD { - metadata : metadata, - all_signals : Vec::::new(), - all_scopes : Vec::::new()} - } - } + pub(super) all_signals : Vec, + pub(super) all_scopes : Vec} \ No newline at end of file diff --git a/test-vcd-files/amaranth/up_counter.vcd b/test-vcd-files/amaranth/up_counter.vcd new file mode 100644 index 0000000..db12ca7 --- /dev/null +++ b/test-vcd-files/amaranth/up_counter.vcd @@ -0,0 +1,287 @@ +$comment Generated by Amaranth $end +$date 2022-07-13 18:48:57.685239 $end +$timescale 1 ps $end +$scope module bench $end +$scope module top $end +$var wire 1 ! clk $end +$var wire 1 " rst $end +$var wire 1 # ovf $end +$var wire 16 $ count $end +$var string 1 % state $end +$var wire 1 & en $end +$upscope $end +$upscope $end +$enddefinitions $end +#0 +$dumpvars +0! +0" +0# +b0 $ +sTOP/0 % +0& +$end +#500000 +1! +#1000000 +0! +#1500000 +1! +#2000000 +0! +#2500000 +1! +#3000000 +0! +#3500000 +1! +#4000000 +0! +#4500000 +1! +#5000000 +0! +#5500000 +1! +#6000000 +0! +#6500000 +1! +#7000000 +0! +#7500000 +1! +#8000000 +0! +#8500000 +1! +#9000000 +0! +#9500000 +1! +#10000000 +0! +#10500000 +1! +#11000000 +0! +#11500000 +1! +#12000000 +0! +#12500000 +1! +#13000000 +0! +#13500000 +1! +#14000000 +0! +#14500000 +1! +#15000000 +0! +#15500000 +1! +#16000000 +0! +#16500000 +1! +#17000000 +0! +#17500000 +1! +#18000000 +0! +#18500000 +1! +#19000000 +0! +#19500000 +1! +#20000000 +0! +#20500000 +1! +#21000000 +0! +#21500000 +1! +#22000000 +0! +#22500000 +1! +#23000000 +0! +#23500000 +1! +#24000000 +0! +#24500000 +1! +#25000000 +0! +#25500000 +1! +#26000000 +0! +#26500000 +1! +#27000000 +0! +#27500000 +1! +#28000000 +0! +#28500000 +1! +#29000000 +0! +#29500000 +1! +#30000000 +0! +#30500000 +1& +1! +#31000000 +0! +#31500000 +sBOTTOM/2 % +b1 $ +1! +#32000000 +0! +#32500000 +b10 $ +1! +#33000000 +0! +#33500000 +b11 $ +1! +#34000000 +0! +#34500000 +b100 $ +1! +#35000000 +0! +#35500000 +b101 $ +1! +#36000000 +0! +#36500000 +b110 $ +1! +#37000000 +0! +#37500000 +b111 $ +1! +#38000000 +0! +#38500000 +b1000 $ +1! +#39000000 +0! +#39500000 +b1001 $ +1! +#40000000 +0! +#40500000 +b1010 $ +1! +#41000000 +0! +#41500000 +b1011 $ +1! +#42000000 +0! +#42500000 +b1100 $ +1! +#43000000 +0! +#43500000 +b1101 $ +1! +#44000000 +0! +#44500000 +b1110 $ +1! +#45000000 +0! +#45500000 +b1111 $ +1! +#46000000 +0! +#46500000 +b10000 $ +1! +#47000000 +0! +#47500000 +b10001 $ +1! +#48000000 +0! +#48500000 +b10010 $ +1! +#49000000 +0! +#49500000 +b10011 $ +1! +#50000000 +0! +#50500000 +b10100 $ +1! +#51000000 +0! +#51500000 +b10101 $ +1! +#52000000 +0! +#52500000 +b10110 $ +1! +#53000000 +0! +#53500000 +b10111 $ +1! +#54000000 +0! +#54500000 +b11000 $ +1! +#55000000 +0! +#55500000 +1# +b11001 $ +1! +#56000000 +0! +#56500000 +sTOP/0 % +0# +b0 $ +1! +#57000000 +0! +#57500000 +sBOTTOM/2 % +b1 $ +1! +#58000000 diff --git a/test-vcd-files/sources.csv b/test-vcd-files/sources.csv index 081cf83..b9b58e9 100644 --- a/test-vcd-files/sources.csv +++ b/test-vcd-files/sources.csv @@ -1,4 +1,4 @@ -Icarus,Verilator,GHDL,VCS,QuestaSim,ModelSim,Quartus,SystemC,Treadle,Aldec,Riviera-PRO,MyHDL,ncsim,xilinx_isim,vivado,GTKWave-Analyzer -https://github.com/dpretet/vcd/blob/master/test1.vcd,https://github.com/wavedrom/vcd-samples/blob/trunk/swerv1.vcd,https://raw.githubusercontent.com/AdoobII/idea_21s/main/vhdl/idea.vcd,https://raw.githubusercontent.com/ameyjain/8-bit-Microprocessor/master/8-bit%20microprocessor/processor.vcd,https://github.com/mr-gaurav/Sequence-Counter/blob/main/test.vcd,https://github.com/Mohammad-Heydariii/Digital-Systems-Lab-Course/blob/main/Lab_project4/modelsim_files/clkdiv2n_tb.vcd,https://github.com/PedroTLemos/ProjetoInfraHard/blob/master/mipsHardware.vcd,https://github.com/jroslindo/Mips-Systemc/blob/main/REGISTRADORES_32_bits/wave_registradores.vcd,https://github.com/chipsalliance/treadle/blob/master/src/test/resources/GCD.vcd,https://github.com/SVeilleux9/FPGA-GPIO-Extender/blob/main/Firmware/aldec/SPI_Write/SPI_Write.vcd,https://github.com/prathampathak/Tic-Tac-Tao/blob/main/dump.vcd,https://github.com/aibtw/myHdl_Projects/blob/main/SimpleMemory/Simple_Memory.vcd,https://github.com/amiteee78/RTL_design/blob/master/ffdiv_32bit/ffdiv_32bit_prop_binom/run_cad/ffdiv_32bit_tb.vcd,https://github.com/mukul54/qrs-peak-fpga/blob/master/utkarsh/utkarsh.sim/sim_1/behav/xsim/test.vcd,https://github.com/saharmalmir/Eth2Ser/blob/master/UART2ETH.runs/impl_1/iladata.vcd,https://github.com/Asfagus/Network-Switch/blob/main/perm_current.vcd -https://github.com/ombhilare999/riscv-core/blob/master/src/rv32_soc_TB.vcd,https://github.com/bigBrain1901/nPOWER-ISA-5-STAGE-PIPELINED-CPU/blob/master/post_compile_files/vlt_dump.vcd,https://github.com/gaoqqt2n/CPU/blob/master/SuperPipelineCPU/vcdfile/pcpu.vcd,https://raw.githubusercontent.com/Akashay-Singla/RISC-V/main/Pipeline/datapath_log.vcd,https://github.com/SparshAgarwal/Computer-Architecture/blob/master/hw3/hw3_1/dump.vcd,https://github.com/sh619/Songyu_Huang-Chisel/blob/main/MU0_final_version/simulation/qsim/CPU_Design.msim.vcd,,https://github.com/amrhas/PDRNoC/blob/VCRouter/noctweak/Debug/waveform.vcd.vcd,,,,https://github.com/Abhishek010397/Programming-RISC-V/blob/master/top.vcd,,https://github.com/DanieleParravicini/regex_coprocessor/blob/master/scripts/sim/test2x2_regex22_string1.vcd,https://github.com/BradMcDanel/multiplication-free-dnn/blob/master/verilog/iladata.vcd, -https://github.com/b06902044/computer_architecture/blob/main/CPU.vcd,,https://github.com/charlycop/VLSI-1/blob/master/EXEC/ALU/alu.vcd,https://raw.githubusercontent.com/sathyapriyanka/APB_UVC_UVM/main/Apb_slave_uvm_new.vcd,,,,,,,,https://github.com/DarthSkipper/myHDL_Sigmoid/blob/master/out/testbench/sigmoid_tb.vcd,,https://github.com/pabloec1729/Hashes-generator/blob/master/RTL/velocidad/test.vcd,, +Icarus,Verilator,GHDL,VCS,QuestaSim,ModelSim,Quartus,SystemC,Treadle,Aldec,Riviera-PRO,MyHDL,ncsim,xilinx_isim,vivado,GTKWave-Analyzer,Amaranth +https://github.com/dpretet/vcd/blob/master/test1.vcd,https://github.com/wavedrom/vcd-samples/blob/trunk/swerv1.vcd,https://raw.githubusercontent.com/AdoobII/idea_21s/main/vhdl/idea.vcd,https://raw.githubusercontent.com/ameyjain/8-bit-Microprocessor/master/8-bit%20microprocessor/processor.vcd,https://github.com/mr-gaurav/Sequence-Counter/blob/main/test.vcd,https://github.com/Mohammad-Heydariii/Digital-Systems-Lab-Course/blob/main/Lab_project4/modelsim_files/clkdiv2n_tb.vcd,https://github.com/PedroTLemos/ProjetoInfraHard/blob/master/mipsHardware.vcd,https://github.com/jroslindo/Mips-Systemc/blob/main/REGISTRADORES_32_bits/wave_registradores.vcd,https://github.com/chipsalliance/treadle/blob/master/src/test/resources/GCD.vcd,https://github.com/SVeilleux9/FPGA-GPIO-Extender/blob/main/Firmware/aldec/SPI_Write/SPI_Write.vcd,https://github.com/prathampathak/Tic-Tac-Tao/blob/main/dump.vcd,https://github.com/aibtw/myHdl_Projects/blob/main/SimpleMemory/Simple_Memory.vcd,https://github.com/amiteee78/RTL_design/blob/master/ffdiv_32bit/ffdiv_32bit_prop_binom/run_cad/ffdiv_32bit_tb.vcd,https://github.com/mukul54/qrs-peak-fpga/blob/master/utkarsh/utkarsh.sim/sim_1/behav/xsim/test.vcd,https://github.com/saharmalmir/Eth2Ser/blob/master/UART2ETH.runs/impl_1/iladata.vcd,https://github.com/Asfagus/Network-Switch/blob/main/perm_current.vcd,Locally Simulated File +https://github.com/ombhilare999/riscv-core/blob/master/src/rv32_soc_TB.vcd,https://github.com/bigBrain1901/nPOWER-ISA-5-STAGE-PIPELINED-CPU/blob/master/post_compile_files/vlt_dump.vcd,https://github.com/gaoqqt2n/CPU/blob/master/SuperPipelineCPU/vcdfile/pcpu.vcd,https://raw.githubusercontent.com/Akashay-Singla/RISC-V/main/Pipeline/datapath_log.vcd,https://github.com/SparshAgarwal/Computer-Architecture/blob/master/hw3/hw3_1/dump.vcd,https://github.com/sh619/Songyu_Huang-Chisel/blob/main/MU0_final_version/simulation/qsim/CPU_Design.msim.vcd,,https://github.com/amrhas/PDRNoC/blob/VCRouter/noctweak/Debug/waveform.vcd.vcd,,,,https://github.com/Abhishek010397/Programming-RISC-V/blob/master/top.vcd,,https://github.com/DanieleParravicini/regex_coprocessor/blob/master/scripts/sim/test2x2_regex22_string1.vcd,https://github.com/BradMcDanel/multiplication-free-dnn/blob/master/verilog/iladata.vcd,, +https://github.com/b06902044/computer_architecture/blob/main/CPU.vcd,,https://github.com/charlycop/VLSI-1/blob/master/EXEC/ALU/alu.vcd,https://raw.githubusercontent.com/sathyapriyanka/APB_UVC_UVM/main/Apb_slave_uvm_new.vcd,,,,,,,,https://github.com/DarthSkipper/myHDL_Sigmoid/blob/master/out/testbench/sigmoid_tb.vcd,,https://github.com/pabloec1729/Hashes-generator/blob/master/RTL/velocidad/test.vcd,,, -- 2.47.1 From 217dea1d417a9d51ce841d2aeb95af4bf837b6f8 Mon Sep 17 00:00:00 2001 From: Yehowshua Immanuel Date: Thu, 14 Jul 2022 18:52:12 -0400 Subject: [PATCH 36/50] good stopping point for today --- README.md | 16 ++------- src/vcd/parse.rs | 87 +++++++++++++++++++----------------------------- src/vcd/types.rs | 3 +- 3 files changed, 39 insertions(+), 67 deletions(-) diff --git a/README.md b/README.md index 750c0a2..6146e63 100644 --- a/README.md +++ b/README.md @@ -27,25 +27,15 @@ The first build of the program may take some time. You can run all the tests with ``cargo test`` # TODO - - [x] We need a way to merge lines. - - [x] We need to start regression testing the parser over all files - - [x] Decide if I want to return option types - - [x] Propagate all to question mark unwrap types. - - [x] Don't want variation in hh:mm:ss - - [x] parser_atoms -> combinator_atoms - - [x] make parse/types.rs - - [x] remove/replace calls to match_not_empty - - [x] Split ``parse.rs``. It's getting too large. - - [x] move list of files to separate test file/folder + - [ ] support multiple root scopes - [ ] support parsing dates with commas - [ ] Fix warning especially usage and restriction warnings once I'm able to successfully parse all sample VCDs. - - [ ] Consolidate error messages and add cursors. + - [ ] Consolidate error messages and add cursors throughout. - [ ] Consider what to do with don't care values - will probably just convert them to strings for now. + will probably just convert them to strings for now. - [ ] Include line and possible column numbers - - [ ] Change states to lowercase - [ ] Take a look at GTKWave parser to compare effificiency. - [ ] Send survey to community channel. diff --git a/src/vcd/parse.rs b/src/vcd/parse.rs index 1c6a37f..280c2ae 100644 --- a/src/vcd/parse.rs +++ b/src/vcd/parse.rs @@ -187,59 +187,38 @@ fn parse_signal_tree<'a>( Ok(()) } -// #[named] -// fn parse_signal_tree_outer<'a>( -// word_reader : &mut WordReader, -// vcd : &'a mut VCD, -// signal_map : &mut HashMap -// ) -> Result<(), String> { -// // We assume we've already seen a `$scope` once by the time we reach this function, -// // that why its call `parse_signal_tree_outer` and not just `parse_signal_tree`. -// // If our WordReader had a `putback` function, we wouldn't need to have a -// // `parse_signal_tree_outer`. +// TODO : make this a generic traversal function that applies specified +// functions upon encountering scopes and signals +fn print_signal_tree( + root_scope_idx : Scope_Idx, + all_scopes : &Vec, + all_signals : &Vec, + depth : usize) +{ + let indent = " ".repeat(depth * 4); + let Scope_Idx(root_scope_idx) = root_scope_idx; + let root_scope = &all_scopes[root_scope_idx]; + let root_scope_name = &root_scope.name; -// // the current scope is the parent scope + println!("{indent}scope: {root_scope_name}"); -// // $scope module reg_mag_i $end -// // ^^^^^^ - module keyword -// let err = format!("reached end of file without parser leaving {}", function_name!()); -// ident(word_reader, "module")?; - -// // $scope module reg_mag_i $end -// // ^^^^^^^^^ - scope name -// let (scope_name, _) = word_reader.next_word().ok_or(err)?; - -// let curr_scope_idx = Scope_Idx(vcd.all_scopes.len()); - -// // register this scope as a child of the current parent scope -// let Scope_Idx(parent_scope_idx_usize) = parent_scope_idx; -// let parent_scope = vcd.all_scopes.get_mut(parent_scope_idx_usize).unwrap(); -// parent_scope.child_scopes.push(curr_scope_idx); - -// 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![] -// } -// ); - -// // $scope module reg_mag_i $end -// // ^^^^ - end keyword -// ident(word_reader, "$end")?; - -// // recursive - parse inside of current scope tree -// parse_signal_tree(word_reader, curr_scope_idx, vcd, signal_map); - -// // ascend from parsing inside of current scope tree, expect $upscope $end -// ident(word_reader, "$upscope")?; -// ident(word_reader, "$end")?; - -// Ok(()) -// } + for Signal_Idx(ref signal_idx) in &root_scope.child_signals { + let child_signal = &all_signals[*signal_idx]; + let name = match child_signal { + Signal::Data{name, ..} => {name} + Signal::Alias{name, ..} => {name} + }; + println!("{indent} - sig: {name}") + } + println!(); + for scope_idx in &root_scope.child_scopes { + // let Scope_Idx(ref scope_idx_usize) = scope_idx; + // let child_scope = &all_scopes[*scope_idx_usize]; + print_signal_tree(*scope_idx, all_scopes, all_signals, depth+1); + } + // let root = vcd.all_scopes; +} pub fn parse_vcd(file : File) -> Result<(), String> { let mut word_gen = WordReader::new(file); @@ -252,13 +231,15 @@ pub fn parse_vcd(file : File) -> Result<(), String> { let mut signal_map = std::collections::HashMap::new(); let mut vcd = VCD{ - metadata: header, + metadata : header, all_signals: vec![], - all_scopes: vec![], + all_scopes : vec![], + scope_roots: vec![], }; parse_signal_tree(&mut word_gen, None, &mut vcd, &mut signal_map)?; - dbg!(&vcd.all_scopes); + println!("printing signal tree"); + print_signal_tree(Scope_Idx(0), &vcd.all_scopes, &vcd.all_signals, 0); Ok(()) } diff --git a/src/vcd/types.rs b/src/vcd/types.rs index c1b0598..2ab566b 100644 --- a/src/vcd/types.rs +++ b/src/vcd/types.rs @@ -59,4 +59,5 @@ pub(super) struct Scope { pub struct VCD { pub(super) metadata : Metadata, pub(super) all_signals : Vec, - pub(super) all_scopes : Vec} \ No newline at end of file + pub(super) all_scopes : Vec, + pub(super) scope_roots : Vec} \ No newline at end of file -- 2.47.1 From 298bbe1969b4f0ef67c02f8be65ea66f07164f08 Mon Sep 17 00:00:00 2001 From: Yehowshua Immanuel Date: Fri, 15 Jul 2022 20:48:02 -0400 Subject: [PATCH 37/50] able to parse all signal trees --- src/main.rs | 5 +- src/vcd/parse.rs | 129 ++++++++++++++++++++++++++++++++--------------- src/vcd/types.rs | 47 ++++++++++++++++- 3 files changed, 137 insertions(+), 44 deletions(-) diff --git a/src/main.rs b/src/main.rs index 69ae197..e10377c 100644 --- a/src/main.rs +++ b/src/main.rs @@ -18,7 +18,10 @@ fn main() -> std::io::Result<()> { let file = File::open(&args.path)?; - parse_vcd(file).unwrap(); + let vcd = parse_vcd(file).unwrap(); + + println!("printing signal tree"); + vcd.print_scopes(); Ok(()) } \ No newline at end of file diff --git a/src/vcd/parse.rs b/src/vcd/parse.rs index 280c2ae..0195d6c 100644 --- a/src/vcd/parse.rs +++ b/src/vcd/parse.rs @@ -35,6 +35,8 @@ fn parse_var<'a>( "reg" => {Ok(Sig_Type::Reg)} "string" => {Ok(Sig_Type::Str)} "wire" => {Ok(Sig_Type::Wire)} + "tri1" => {Ok(Sig_Type::Tri1)} + "time" => {Ok(Sig_Type::Time)} _ => { let err = format!("found keyword `{word}` but expected one of {expected_types} on {cursor:?}"); Err(err) @@ -118,22 +120,38 @@ fn parse_signal_tree<'a>( // $scope module reg_mag_i $end // ^^^^^^ - module keyword let err = format!("reached end of file without parser leaving {}", function_name!()); - ident(word_reader, "module")?; + let (keyword, cursor) = word_reader.next_word().ok_or(&err)?; + + // TODO : just check if keyword is in expected + let expected = ["module", "begin", "task", "function"]; + match keyword { + "module" => {Ok(())} + "begin" => {Ok(())} + "task" => {Ok(())} + "function" => {Ok(())} + _ => { + let err = format!("found keyword `{keyword}` but expected one of `{expected:?}` on {cursor:?}"); + Err(err) + } + }.unwrap(); // $scope module reg_mag_i $end // ^^^^^^^^^ - scope name - let (scope_name, _) = word_reader.next_word().ok_or(err)?; + let (scope_name, _) = word_reader.next_word().ok_or(&err)?; let curr_scope_idx = Scope_Idx(vcd.all_scopes.len()); // register this scope as a child of the current parent scope - // if there is a parent scope + // if there is a parent scope, or else we register this scope as + // root scope match parent_scope_idx { Some(Scope_Idx(parent_scope_idx)) => { let parent_scope = vcd.all_scopes.get_mut(parent_scope_idx).unwrap(); parent_scope.child_scopes.push(curr_scope_idx); } - None => {} + None => { + vcd.scope_roots.push(curr_scope_idx) + } } // add this scope to list of existing scopes @@ -161,7 +179,7 @@ fn parse_signal_tree<'a>( match residual { "scope" => { // recursive - parse inside of current scope tree - parse_signal_tree(word_reader, Some(curr_scope_idx), vcd, signal_map); + parse_signal_tree(word_reader, Some(curr_scope_idx), vcd, signal_map)?; } "var" => { parse_var(word_reader, curr_scope_idx, vcd, signal_map)?; @@ -170,8 +188,14 @@ fn parse_signal_tree<'a>( ident(word_reader, "$end")?; break } + // we ignore comments + "comment" => { + loop { + if ident(word_reader, "$end").is_ok() {break} + } + } _ => { - let err = format!("found keyword `{residual}` but expected `$scope`, `$var`, or `$upscope` on {cursor:?}"); + let err = format!("found keyword `{residual}` but expected `$scope`, `$var`, `$comment`, or `$upscope` on {cursor:?}"); return Err(err) } } @@ -187,47 +211,52 @@ fn parse_signal_tree<'a>( Ok(()) } -// TODO : make this a generic traversal function that applies specified -// functions upon encountering scopes and signals -fn print_signal_tree( - root_scope_idx : Scope_Idx, - all_scopes : &Vec, - all_signals : &Vec, - depth : usize) -{ - let indent = " ".repeat(depth * 4); - let Scope_Idx(root_scope_idx) = root_scope_idx; - let root_scope = &all_scopes[root_scope_idx]; - let root_scope_name = &root_scope.name; +#[named] +fn parse_scopes<'a>( + word_reader : &mut WordReader, + parent_scope_idx : Option, + vcd : &'a mut VCD, + signal_map : &mut HashMap +) -> Result<(), String> { + // we've already seen `$scope`, so here we just jump right in + parse_signal_tree(word_reader, None, vcd, signal_map)?; - println!("{indent}scope: {root_scope_name}"); + let err = format!("reached end of file without parser leaving {}", function_name!()); + let expected_keywords = ["$scope", "$enddefinitions"]; - for Signal_Idx(ref signal_idx) in &root_scope.child_signals { - let child_signal = &all_signals[*signal_idx]; - let name = match child_signal { - Signal::Data{name, ..} => {name} - Signal::Alias{name, ..} => {name} - }; - println!("{indent} - sig: {name}") + loop { + let (word, cursor) = word_reader.next_word().ok_or(&err)?; + match word { + "$scope" => { + parse_signal_tree(word_reader, None, vcd, signal_map)?; + } + "$enddefinitions" => { + ident(word_reader, "$end")?; + break + } + // we ignore comments + "comment" => { + loop { + if ident(word_reader, "$end").is_ok() {break} + } + } + _ => { + let err = format!("found keyword `{word}` but expected oneof `{expected_keywords:?}` on {cursor:?}"); + return Err(err) + + } + } } - println!(); - for scope_idx in &root_scope.child_scopes { - // let Scope_Idx(ref scope_idx_usize) = scope_idx; - // let child_scope = &all_scopes[*scope_idx_usize]; - print_signal_tree(*scope_idx, all_scopes, all_signals, depth+1); - } - // let root = vcd.all_scopes; + Ok(()) } -pub fn parse_vcd(file : File) -> Result<(), String> { + +pub fn parse_vcd(file : File) -> Result { let mut word_gen = WordReader::new(file); let header = parse_metadata(&mut word_gen)?; - dbg!(&header); - // let (word, cursor) = word_gen.next_word().unwrap(); - // cursor.error(word).unwrap(); let mut signal_map = std::collections::HashMap::new(); let mut vcd = VCD{ @@ -237,10 +266,9 @@ pub fn parse_vcd(file : File) -> Result<(), String> { scope_roots: vec![], }; - parse_signal_tree(&mut word_gen, None, &mut vcd, &mut signal_map)?; - println!("printing signal tree"); - print_signal_tree(Scope_Idx(0), &vcd.all_scopes, &vcd.all_signals, 0); - Ok(()) + parse_scopes(&mut word_gen, None, &mut vcd, &mut signal_map)?; + + Ok(vcd) } #[cfg(test)] @@ -278,4 +306,23 @@ mod tests { } } + + #[test] + fn scopes() { + // TODO: eventually, once all dates pass, merge the following + // two loops + // testing dates + 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/types.rs b/src/vcd/types.rs index 2ab566b..51c5ce8 100644 --- a/src/vcd/types.rs +++ b/src/vcd/types.rs @@ -21,7 +21,7 @@ pub(super) struct Scope_Idx(pub(super) usize); pub(super) struct Signal_Idx(pub(super) usize); #[derive(Debug)] -pub(super) enum Sig_Type {Integer, Parameter, Real, Reg, Str, Wire,} +pub(super) enum Sig_Type {Integer, Parameter, Real, Reg, Str, Wire, Tri1, Time} #[derive(Debug)] pub(super) enum Sig_Value { @@ -60,4 +60,47 @@ pub struct VCD { pub(super) metadata : Metadata, pub(super) all_signals : Vec, pub(super) all_scopes : Vec, - pub(super) scope_roots : Vec} \ No newline at end of file + pub(super) scope_roots : Vec} + +impl VCD { + // TODO : make this a generic traversal function that applies specified + // functions upon encountering scopes and signals + fn print_scope_tree( + &self, + root_scope_idx : Scope_Idx, + depth : usize) + { + let all_scopes = &self.all_scopes; + let all_signals = &self.all_signals; + + let indent = " ".repeat(depth * 4); + let Scope_Idx(root_scope_idx) = root_scope_idx; + let root_scope = &all_scopes[root_scope_idx]; + let root_scope_name = &root_scope.name; + + println!("{indent}scope: {root_scope_name}"); + + for Signal_Idx(ref signal_idx) in &root_scope.child_signals { + let child_signal = &all_signals[*signal_idx]; + let name = match child_signal { + Signal::Data{name, ..} => {name} + Signal::Alias{name, ..} => {name} + }; + println!("{indent} - sig: {name}") + } + println!(); + + for scope_idx in &root_scope.child_scopes { + // let Scope_Idx(ref scope_idx_usize) = scope_idx; + // let child_scope = &all_scopes[*scope_idx_usize]; + self.print_scope_tree(*scope_idx, depth+1); + } + // let root = vcd.all_scopes; + } + + pub fn print_scopes(&self) { + for scope_root in &self.scope_roots { + self.print_scope_tree(*scope_root, 0); + } + } +} \ No newline at end of file -- 2.47.1 From 932250e41605d131cb65bf609edb3dac65a25022 Mon Sep 17 00:00:00 2001 From: Yehowshua Immanuel Date: Mon, 18 Jul 2022 12:53:44 -0400 Subject: [PATCH 38/50] some re-org and cleanup --- README.md | 3 +- src/vcd/parse.rs | 245 +--------------------------------------- src/vcd/parse/scopes.rs | 235 ++++++++++++++++++++++++++++++++++++++ 3 files changed, 240 insertions(+), 243 deletions(-) create mode 100644 src/vcd/parse/scopes.rs diff --git a/README.md b/README.md index 6146e63..c5315b3 100644 --- a/README.md +++ b/README.md @@ -27,10 +27,11 @@ The first build of the program may take some time. You can run all the tests with ``cargo test`` # TODO - - [ ] support multiple root scopes - [ ] support parsing dates with commas - [ ] Fix warning especially usage and restriction warnings once I'm able to successfully parse all sample VCDs. + - [ ] Should be able to load waveform whilst viewing it live. + - could be quite challenging to implement for various reasons - [ ] Consolidate error messages and add cursors throughout. - [ ] Consider what to do with don't care values diff --git a/src/vcd/parse.rs b/src/vcd/parse.rs index 0195d6c..c7821f1 100644 --- a/src/vcd/parse.rs +++ b/src/vcd/parse.rs @@ -1,8 +1,5 @@ -use chrono::prelude::*; -use itertools::Itertools; use std::{fs::File}; use std::collections::{BTreeMap, HashMap}; -use ::function_name::named; use super::*; @@ -15,242 +12,8 @@ use types::*; mod metadata; use metadata::*; -#[named] -fn parse_var<'a>( - word_reader : &mut WordReader, - parent_scope_idx : Scope_Idx, - vcd : &'a mut VCD, - signal_map : &mut HashMap -) -> Result<(), String> { - let err = format!("reached end of file without parser leaving {}", function_name!()); - let (word, cursor) = word_reader.next_word().ok_or(&err)?; - let expected_types = "[integer, parameter, real, reg, string, wire]"; - - // $var parameter 3 a IDLE $end - // ^^^^^^^^^ - var_type - let var_type = match word { - "integer" => {Ok(Sig_Type::Integer)} - "parameter" => {Ok(Sig_Type::Parameter)} - "real" => {Ok(Sig_Type::Real)} - "reg" => {Ok(Sig_Type::Reg)} - "string" => {Ok(Sig_Type::Str)} - "wire" => {Ok(Sig_Type::Wire)} - "tri1" => {Ok(Sig_Type::Tri1)} - "time" => {Ok(Sig_Type::Time)} - _ => { - let err = format!("found keyword `{word}` but expected one of {expected_types} on {cursor:?}"); - Err(err) - } - }?; - - let (word, cursor) = word_reader.next_word().ok_or(&err)?; - let parse_err = format!("failed to parse as usize on {cursor:?}"); - - // $var parameter 3 a IDLE $end - // ^ - no_bits - let no_bits = match var_type { - Sig_Type::Integer | Sig_Type::Parameter | - Sig_Type::Real | Sig_Type::Reg | - Sig_Type::Wire => { - let no_bits = word.parse::().expect(parse_err.as_str()); - Some(no_bits) - } - // for strings, we don't really care what the number of bits is - _ => {None} - }; - - // $var parameter 3 a IDLE $end - // ^ - signal_alias - let (word, cursor) = word_reader.next_word().ok_or(&err)?; - let signal_alias = word.to_string(); - - // $var parameter 3 a IDLE $end - // ^^^^ - full_signal_name(can extend until $end) - let mut full_signal_name = Vec::::new(); - loop { - let (word, cursor) = word_reader.next_word().ok_or(&err)?; - match word { - "$end" => {break} - _ => {full_signal_name.push(word.to_string())} - } - } - let full_signal_name = full_signal_name.join(" "); - - // Is the current variable an alias to a signal already encountered? - // if so, handle ref_signal_idx accordingly, if not, add signal to hash - // map - let (signal, signal_idx) = match signal_map.get(&signal_alias) { - Some(ref_signal_idx) => { - let signal_idx = Signal_Idx(vcd.all_signals.len()); - let signal = Signal::Alias{ - name: full_signal_name, - signal_alias: *ref_signal_idx}; - (signal, signal_idx) - } - None => { - let signal_idx = Signal_Idx(vcd.all_signals.len()); - signal_map.insert(signal_alias.to_string(), signal_idx); - let signal = Signal::Data{ - name: full_signal_name, - sig_type: var_type, - num_bits: no_bits, - self_idx: signal_idx, - timeline: BTreeMap::new(), - scope_parent: parent_scope_idx }; - (signal, signal_idx) - } - }; - - vcd.all_signals.push(signal); - let Scope_Idx(parent_scope_idx_usize) = parent_scope_idx; - let parent_scope = vcd.all_scopes.get_mut(parent_scope_idx_usize).unwrap(); - parent_scope.child_signals.push(signal_idx); - - Ok(()) -} - -#[named] -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 err = format!("reached end of file without parser leaving {}", function_name!()); - let (keyword, cursor) = word_reader.next_word().ok_or(&err)?; - - // TODO : just check if keyword is in expected - let expected = ["module", "begin", "task", "function"]; - match keyword { - "module" => {Ok(())} - "begin" => {Ok(())} - "task" => {Ok(())} - "function" => {Ok(())} - _ => { - let err = format!("found keyword `{keyword}` but expected one of `{expected:?}` on {cursor:?}"); - Err(err) - } - }.unwrap(); - - // $scope module reg_mag_i $end - // ^^^^^^^^^ - scope name - let (scope_name, _) = word_reader.next_word().ok_or(&err)?; - - let curr_scope_idx = Scope_Idx(vcd.all_scopes.len()); - - // register this scope as a child of the current parent scope - // if there is a parent scope, or else we register this scope as - // root scope - match parent_scope_idx { - Some(Scope_Idx(parent_scope_idx)) => { - let parent_scope = vcd.all_scopes.get_mut(parent_scope_idx).unwrap(); - parent_scope.child_scopes.push(curr_scope_idx); - } - None => { - vcd.scope_roots.push(curr_scope_idx) - } - } - - // add this scope to list of existing scopes - 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![] - } - ); - - // $scope module reg_mag_i $end - // ^^^^ - end keyword - ident(word_reader, "$end")?; - - let err = format!("reached end of file without parser leaving {}", function_name!()); - loop { - let (word, cursor) = word_reader.next_word().ok_or(&err)?; - let ParseResult{matched, residual} = tag(word, "$"); - match matched { - // we hope that this word stars with a `$` - "$" => { - match residual { - "scope" => { - // recursive - parse inside of current scope tree - parse_signal_tree(word_reader, Some(curr_scope_idx), vcd, signal_map)?; - } - "var" => { - parse_var(word_reader, curr_scope_idx, vcd, signal_map)?; - } - "upscope" => { - ident(word_reader, "$end")?; - break - } - // we ignore comments - "comment" => { - loop { - if ident(word_reader, "$end").is_ok() {break} - } - } - _ => { - let err = format!("found keyword `{residual}` but expected `$scope`, `$var`, `$comment`, or `$upscope` on {cursor:?}"); - return Err(err) - } - } - } - _ => { - let err = format!("found keyword `{matched}` but expected `$` on {cursor:?}"); - return Err(err) - } - } - } - - // TODO : remove the following Ok(()) once we add loop above - Ok(()) -} - -#[named] -fn parse_scopes<'a>( - word_reader : &mut WordReader, - parent_scope_idx : Option, - vcd : &'a mut VCD, - signal_map : &mut HashMap -) -> Result<(), String> { - // we've already seen `$scope`, so here we just jump right in - parse_signal_tree(word_reader, None, vcd, signal_map)?; - - let err = format!("reached end of file without parser leaving {}", function_name!()); - let expected_keywords = ["$scope", "$enddefinitions"]; - - loop { - let (word, cursor) = word_reader.next_word().ok_or(&err)?; - match word { - "$scope" => { - parse_signal_tree(word_reader, None, vcd, signal_map)?; - } - "$enddefinitions" => { - ident(word_reader, "$end")?; - break - } - // we ignore comments - "comment" => { - loop { - if ident(word_reader, "$end").is_ok() {break} - } - } - _ => { - let err = format!("found keyword `{word}` but expected oneof `{expected_keywords:?}` on {cursor:?}"); - return Err(err) - - } - } - } - - Ok(()) -} - +mod scopes; +use scopes::*; pub fn parse_vcd(file : File) -> Result { let mut word_gen = WordReader::new(file); @@ -309,9 +72,7 @@ mod tests { #[test] fn scopes() { - // TODO: eventually, once all dates pass, merge the following - // two loops - // testing dates + // 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); diff --git a/src/vcd/parse/scopes.rs b/src/vcd/parse/scopes.rs new file mode 100644 index 0000000..b1a1f1e --- /dev/null +++ b/src/vcd/parse/scopes.rs @@ -0,0 +1,235 @@ +//! part of the vcd parser that handles parsing the signal tree and +//! building the resulting signal tree +use function_name::named; + +use super::*; + +#[named] +pub(super) fn parse_var<'a>( + word_reader : &mut WordReader, + parent_scope_idx : Scope_Idx, + vcd : &'a mut VCD, + signal_map : &mut HashMap +) -> Result<(), String> { + let err = format!("reached end of file without parser leaving {}", function_name!()); + let (word, cursor) = word_reader.next_word().ok_or(&err)?; + let expected_types = ["integer", "parameter", "real", "reg", "string", "wire", "tri1", "time"]; + + // $var parameter 3 a IDLE $end + // ^^^^^^^^^ - var_type + let var_type = match word { + "integer" => {Ok(Sig_Type::Integer)} + "parameter" => {Ok(Sig_Type::Parameter)} + "real" => {Ok(Sig_Type::Real)} + "reg" => {Ok(Sig_Type::Reg)} + "string" => {Ok(Sig_Type::Str)} + "wire" => {Ok(Sig_Type::Wire)} + "tri1" => {Ok(Sig_Type::Tri1)} + "time" => {Ok(Sig_Type::Time)} + _ => { + let err = format!("found keyword `{word}` but expected one of {expected_types:?} on {cursor:?}"); + Err(err) + } + }?; + + let (word, cursor) = word_reader.next_word().ok_or(&err)?; + let parse_err = format!("failed to parse as usize on {cursor:?}"); + + // $var parameter 3 a IDLE $end + // ^ - no_bits + let no_bits = match var_type { + Sig_Type::Integer | Sig_Type::Parameter | + Sig_Type::Real | Sig_Type::Reg | + Sig_Type::Wire => { + let no_bits = word.parse::().expect(parse_err.as_str()); + Some(no_bits) + } + // for strings, we don't really care what the number of bits is + _ => {None} + }; + + // $var parameter 3 a IDLE $end + // ^ - signal_alias + let (word, cursor) = word_reader.next_word().ok_or(&err)?; + let signal_alias = word.to_string(); + + // $var parameter 3 a IDLE $end + // ^^^^ - full_signal_name(can extend until $end) + let mut full_signal_name = Vec::::new(); + loop { + let (word, cursor) = word_reader.next_word().ok_or(&err)?; + match word { + "$end" => {break} + _ => {full_signal_name.push(word.to_string())} + } + } + let full_signal_name = full_signal_name.join(" "); + + // Is the current variable an alias to a signal already encountered? + // if so, handle ref_signal_idx accordingly, if not, add signal to hash + // map + let (signal, signal_idx) = match signal_map.get(&signal_alias) { + Some(ref_signal_idx) => { + let signal_idx = Signal_Idx(vcd.all_signals.len()); + let signal = Signal::Alias{ + name: full_signal_name, + signal_alias: *ref_signal_idx}; + (signal, signal_idx) + } + None => { + let signal_idx = Signal_Idx(vcd.all_signals.len()); + signal_map.insert(signal_alias.to_string(), signal_idx); + let signal = Signal::Data{ + name: full_signal_name, + sig_type: var_type, + num_bits: no_bits, + self_idx: signal_idx, + timeline: BTreeMap::new(), + scope_parent: parent_scope_idx }; + (signal, signal_idx) + } + }; + + vcd.all_signals.push(signal); + let Scope_Idx(parent_scope_idx_usize) = parent_scope_idx; + let parent_scope = vcd.all_scopes.get_mut(parent_scope_idx_usize).unwrap(); + parent_scope.child_signals.push(signal_idx); + + Ok(()) +} + +#[named] +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 err = format!("reached end of file without parser leaving {}", function_name!()); + let (keyword, cursor) = word_reader.next_word().ok_or(&err)?; + + let expected = ["module", "begin", "task", "function"]; + if expected.contains(&keyword) { + Ok(()) + } else { + let err = format!("found keyword `{keyword}` but expected one of `{expected:?}` on {cursor:?}"); + Err(err) + }?; + + // $scope module reg_mag_i $end + // ^^^^^^^^^ - scope name + let (scope_name, _) = word_reader.next_word().ok_or(&err)?; + + let curr_scope_idx = Scope_Idx(vcd.all_scopes.len()); + + // register this scope as a child of the current parent scope + // if there is a parent scope, or else we register this scope as + // root scope + match parent_scope_idx { + Some(Scope_Idx(parent_scope_idx)) => { + let parent_scope = vcd.all_scopes.get_mut(parent_scope_idx).unwrap(); + parent_scope.child_scopes.push(curr_scope_idx); + } + None => { + vcd.scope_roots.push(curr_scope_idx) + } + } + + // add this scope to list of existing scopes + 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![] + } + ); + + // $scope module reg_mag_i $end + // ^^^^ - end keyword + ident(word_reader, "$end")?; + + let err = format!("reached end of file without parser leaving {}", function_name!()); + loop { + let (word, cursor) = word_reader.next_word().ok_or(&err)?; + let ParseResult{matched, residual} = tag(word, "$"); + match matched { + // we hope that this word stars with a `$` + "$" => { + match residual { + "scope" => { + // recursive - parse inside of current scope tree + parse_signal_tree(word_reader, Some(curr_scope_idx), vcd, signal_map)?; + } + "var" => { + parse_var(word_reader, curr_scope_idx, vcd, signal_map)?; + } + "upscope" => { + ident(word_reader, "$end")?; + break + } + // we ignore comments + "comment" => { + loop { + if ident(word_reader, "$end").is_ok() {break} + } + } + _ => { + let err = format!("found keyword `{residual}` but expected `$scope`, `$var`, `$comment`, or `$upscope` on {cursor:?}"); + return Err(err) + } + } + } + _ => { + let err = format!("found keyword `{matched}` but expected `$` on {cursor:?}"); + return Err(err) + } + } + } + + Ok(()) +} + +#[named] +pub(super) fn parse_scopes<'a>( + word_reader : &mut WordReader, + parent_scope_idx : Option, + vcd : &'a mut VCD, + signal_map : &mut HashMap +) -> Result<(), String> { + // we've already seen `$scope`, so here we just jump right in + parse_signal_tree(word_reader, None, vcd, signal_map)?; + + let err = format!("reached end of file without parser leaving {}", function_name!()); + let expected_keywords = ["$scope", "$enddefinitions"]; + + loop { + let (word, cursor) = word_reader.next_word().ok_or(&err)?; + match word { + "$scope" => { + parse_signal_tree(word_reader, None, vcd, signal_map)?; + } + "$enddefinitions" => { + ident(word_reader, "$end")?; + break + } + // we ignore comments + "comment" => { + loop { + if ident(word_reader, "$end").is_ok() {break} + } + } + _ => { + let err = format!("found keyword `{word}` but expected oneof `{expected_keywords:?}` on {cursor:?}"); + return Err(err) + + } + } + } + + Ok(()) +} \ No newline at end of file -- 2.47.1 From 24622c71c2224f8207628aa6a9e6cea383ba8e3a Mon Sep 17 00:00:00 2001 From: Yehowshua Immanuel Date: Tue, 19 Jul 2022 13:48:22 -0400 Subject: [PATCH 39/50] getting started on parsing timeline events --- README.md | 9 +++++++-- src/vcd/parse.rs | 32 +++++++++++++++++++++++++++++++- src/vcd/parse/scopes.rs | 2 +- src/vcd/types.rs | 6 +++++- 4 files changed, 44 insertions(+), 5 deletions(-) diff --git a/README.md b/README.md index c5315b3..0070709 100644 --- a/README.md +++ b/README.md @@ -8,7 +8,7 @@ PROPRIETARY - Copyright - Yehowshua Immanuel - loads 400MB of VCD waveform per second on an 8 core 2017 desktop CPU with NVMe storage - consumes roughly between 10 - 50MB of memory per GB of waveform -## Planed Features +## Planned Features - elegant/pretty UI - can be easily ported to work in browser via webassembly - allows high-performance custom Rust plugins to manipulate and @@ -27,7 +27,8 @@ The first build of the program may take some time. You can run all the tests with ``cargo test`` # TODO - - [ ] support parsing dates with commas + - [ ] make a custon date parser for possibly up to 18 different versions(that + is, for each possible tool). - [ ] Fix warning especially usage and restriction warnings once I'm able to successfully parse all sample VCDs. - [ ] Should be able to load waveform whilst viewing it live. @@ -40,5 +41,9 @@ You can run all the tests with ``cargo test`` - [ ] Take a look at GTKWave parser to compare effificiency. - [ ] Send survey to community channel. +# Questions to Answer + - [ ] Is it safe to assume that we may treat any values before the first + non-zero timestamp as having occured on `#0`? + # Probably No Longer Needed - [ ] Should insert nodes in BFS order \ No newline at end of file diff --git a/src/vcd/parse.rs b/src/vcd/parse.rs index c7821f1..4ab523c 100644 --- a/src/vcd/parse.rs +++ b/src/vcd/parse.rs @@ -1,5 +1,7 @@ use std::{fs::File}; -use std::collections::{BTreeMap, HashMap}; +use std::collections::HashMap; +use num::BigInt; +use num::bigint::ToBigInt; use super::*; @@ -15,6 +17,32 @@ use metadata::*; mod scopes; use scopes::*; +use function_name::named; + +#[named] +fn parse_events<'a>( + word_reader : &mut WordReader, + vcd : &'a mut VCD, + signal_map : &mut HashMap +) -> Result<(), String> { + + loop { + let next_word = word_reader.next_word(); + // if we've reached the end of the file, then there is obviously + // nothing left to do... + if next_word.is_none() {break}; + + let (word, cursor) = next_word.unwrap(); + match &word[0..1] { + "$" => {continue} + "#" => {continue} + _ => {} + } + } + + Ok(()) +} + pub fn parse_vcd(file : File) -> Result { let mut word_gen = WordReader::new(file); @@ -24,12 +52,14 @@ pub fn parse_vcd(file : File) -> Result { let mut vcd = VCD{ metadata : header, + cursor : 0.to_bigint().unwrap(), all_signals: vec![], all_scopes : vec![], scope_roots: vec![], }; parse_scopes(&mut word_gen, None, &mut vcd, &mut signal_map)?; + // parse_events(&mut word_gen, &mut vcd, &mut signal_map)?; Ok(vcd) } diff --git a/src/vcd/parse/scopes.rs b/src/vcd/parse/scopes.rs index b1a1f1e..d03001c 100644 --- a/src/vcd/parse/scopes.rs +++ b/src/vcd/parse/scopes.rs @@ -84,7 +84,7 @@ pub(super) fn parse_var<'a>( sig_type: var_type, num_bits: no_bits, self_idx: signal_idx, - timeline: BTreeMap::new(), + timeline: vec![], scope_parent: parent_scope_idx }; (signal, signal_idx) } diff --git a/src/vcd/types.rs b/src/vcd/types.rs index 51c5ce8..6796179 100644 --- a/src/vcd/types.rs +++ b/src/vcd/types.rs @@ -23,6 +23,9 @@ pub(super) struct Signal_Idx(pub(super) usize); #[derive(Debug)] pub(super) enum Sig_Type {Integer, Parameter, Real, Reg, Str, Wire, Tri1, Time} +#[derive(Debug)] +pub(super) struct TimeStamp(BigInt); + #[derive(Debug)] pub(super) enum Sig_Value { Numeric(BigInt), @@ -36,7 +39,7 @@ pub(super) enum Signal{ num_bits : Option, // TODO : may be able to remove self_idx self_idx : Signal_Idx, - timeline : BTreeMap, + timeline : Vec<(TimeStamp, Sig_Value)>, scope_parent : Scope_Idx}, Alias{ name : String, @@ -58,6 +61,7 @@ pub(super) struct Scope { #[derive(Debug)] pub struct VCD { pub(super) metadata : Metadata, + pub(super) cursor : BigInt, pub(super) all_signals : Vec, pub(super) all_scopes : Vec, pub(super) scope_roots : Vec} -- 2.47.1 From 711d9ca055095c4163a07d005b7a02f125e0ec1e Mon Sep 17 00:00:00 2001 From: ThePerfectComputer <103011002+ThePerfectComputer@users.noreply.github.com> Date: Tue, 19 Jul 2022 13:49:39 -0400 Subject: [PATCH 40/50] Create LICENSE --- LICENSE | 674 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 674 insertions(+) create mode 100644 LICENSE diff --git a/LICENSE b/LICENSE new file mode 100644 index 0000000..f288702 --- /dev/null +++ b/LICENSE @@ -0,0 +1,674 @@ + GNU GENERAL PUBLIC LICENSE + Version 3, 29 June 2007 + + Copyright (C) 2007 Free Software Foundation, Inc. + Everyone is permitted to copy and distribute verbatim copies + of this license document, but changing it is not allowed. + + Preamble + + The GNU General Public License is a free, copyleft license for +software and other kinds of works. + + The licenses for most software and other practical works are designed +to take away your freedom to share and change the works. By contrast, +the GNU General Public License is intended to guarantee your freedom to +share and change all versions of a program--to make sure it remains free +software for all its users. We, the Free Software Foundation, use the +GNU General Public License for most of our software; it applies also to +any other work released this way by its authors. You can apply it to +your programs, too. + + When we speak of free software, we are referring to freedom, not +price. Our General Public Licenses are designed to make sure that you +have the freedom to distribute copies of free software (and charge for +them if you wish), that you receive source code or can get it if you +want it, that you can change the software or use pieces of it in new +free programs, and that you know you can do these things. + + To protect your rights, we need to prevent others from denying you +these rights or asking you to surrender the rights. Therefore, you have +certain responsibilities if you distribute copies of the software, or if +you modify it: responsibilities to respect the freedom of others. + + For example, if you distribute copies of such a program, whether +gratis or for a fee, you must pass on to the recipients the same +freedoms that you received. You must make sure that they, too, receive +or can get the source code. And you must show them these terms so they +know their rights. + + Developers that use the GNU GPL protect your rights with two steps: +(1) assert copyright on the software, and (2) offer you this License +giving you legal permission to copy, distribute and/or modify it. + + For the developers' and authors' protection, the GPL clearly explains +that there is no warranty for this free software. For both users' and +authors' sake, the GPL requires that modified versions be marked as +changed, so that their problems will not be attributed erroneously to +authors of previous versions. + + Some devices are designed to deny users access to install or run +modified versions of the software inside them, although the manufacturer +can do so. This is fundamentally incompatible with the aim of +protecting users' freedom to change the software. The systematic +pattern of such abuse occurs in the area of products for individuals to +use, which is precisely where it is most unacceptable. Therefore, we +have designed this version of the GPL to prohibit the practice for those +products. If such problems arise substantially in other domains, we +stand ready to extend this provision to those domains in future versions +of the GPL, as needed to protect the freedom of users. + + Finally, every program is threatened constantly by software patents. +States should not allow patents to restrict development and use of +software on general-purpose computers, but in those that do, we wish to +avoid the special danger that patents applied to a free program could +make it effectively proprietary. To prevent this, the GPL assures that +patents cannot be used to render the program non-free. + + The precise terms and conditions for copying, distribution and +modification follow. + + TERMS AND CONDITIONS + + 0. Definitions. + + "This License" refers to version 3 of the GNU General Public License. + + "Copyright" also means copyright-like laws that apply to other kinds of +works, such as semiconductor masks. + + "The Program" refers to any copyrightable work licensed under this +License. Each licensee is addressed as "you". "Licensees" and +"recipients" may be individuals or organizations. + + To "modify" a work means to copy from or adapt all or part of the work +in a fashion requiring copyright permission, other than the making of an +exact copy. The resulting work is called a "modified version" of the +earlier work or a work "based on" the earlier work. + + A "covered work" means either the unmodified Program or a work based +on the Program. + + To "propagate" a work means to do anything with it that, without +permission, would make you directly or secondarily liable for +infringement under applicable copyright law, except executing it on a +computer or modifying a private copy. Propagation includes copying, +distribution (with or without modification), making available to the +public, and in some countries other activities as well. + + To "convey" a work means any kind of propagation that enables other +parties to make or receive copies. Mere interaction with a user through +a computer network, with no transfer of a copy, is not conveying. + + An interactive user interface displays "Appropriate Legal Notices" +to the extent that it includes a convenient and prominently visible +feature that (1) displays an appropriate copyright notice, and (2) +tells the user that there is no warranty for the work (except to the +extent that warranties are provided), that licensees may convey the +work under this License, and how to view a copy of this License. If +the interface presents a list of user commands or options, such as a +menu, a prominent item in the list meets this criterion. + + 1. Source Code. + + The "source code" for a work means the preferred form of the work +for making modifications to it. "Object code" means any non-source +form of a work. + + A "Standard Interface" means an interface that either is an official +standard defined by a recognized standards body, or, in the case of +interfaces specified for a particular programming language, one that +is widely used among developers working in that language. + + The "System Libraries" of an executable work include anything, other +than the work as a whole, that (a) is included in the normal form of +packaging a Major Component, but which is not part of that Major +Component, and (b) serves only to enable use of the work with that +Major Component, or to implement a Standard Interface for which an +implementation is available to the public in source code form. A +"Major Component", in this context, means a major essential component +(kernel, window system, and so on) of the specific operating system +(if any) on which the executable work runs, or a compiler used to +produce the work, or an object code interpreter used to run it. + + The "Corresponding Source" for a work in object code form means all +the source code needed to generate, install, and (for an executable +work) run the object code and to modify the work, including scripts to +control those activities. However, it does not include the work's +System Libraries, or general-purpose tools or generally available free +programs which are used unmodified in performing those activities but +which are not part of the work. For example, Corresponding Source +includes interface definition files associated with source files for +the work, and the source code for shared libraries and dynamically +linked subprograms that the work is specifically designed to require, +such as by intimate data communication or control flow between those +subprograms and other parts of the work. + + The Corresponding Source need not include anything that users +can regenerate automatically from other parts of the Corresponding +Source. + + The Corresponding Source for a work in source code form is that +same work. + + 2. Basic Permissions. + + All rights granted under this License are granted for the term of +copyright on the Program, and are irrevocable provided the stated +conditions are met. This License explicitly affirms your unlimited +permission to run the unmodified Program. The output from running a +covered work is covered by this License only if the output, given its +content, constitutes a covered work. This License acknowledges your +rights of fair use or other equivalent, as provided by copyright law. + + You may make, run and propagate covered works that you do not +convey, without conditions so long as your license otherwise remains +in force. You may convey covered works to others for the sole purpose +of having them make modifications exclusively for you, or provide you +with facilities for running those works, provided that you comply with +the terms of this License in conveying all material for which you do +not control copyright. Those thus making or running the covered works +for you must do so exclusively on your behalf, under your direction +and control, on terms that prohibit them from making any copies of +your copyrighted material outside their relationship with you. + + Conveying under any other circumstances is permitted solely under +the conditions stated below. Sublicensing is not allowed; section 10 +makes it unnecessary. + + 3. Protecting Users' Legal Rights From Anti-Circumvention Law. + + No covered work shall be deemed part of an effective technological +measure under any applicable law fulfilling obligations under article +11 of the WIPO copyright treaty adopted on 20 December 1996, or +similar laws prohibiting or restricting circumvention of such +measures. + + When you convey a covered work, you waive any legal power to forbid +circumvention of technological measures to the extent such circumvention +is effected by exercising rights under this License with respect to +the covered work, and you disclaim any intention to limit operation or +modification of the work as a means of enforcing, against the work's +users, your or third parties' legal rights to forbid circumvention of +technological measures. + + 4. Conveying Verbatim Copies. + + You may convey verbatim copies of the Program's source code as you +receive it, in any medium, provided that you conspicuously and +appropriately publish on each copy an appropriate copyright notice; +keep intact all notices stating that this License and any +non-permissive terms added in accord with section 7 apply to the code; +keep intact all notices of the absence of any warranty; and give all +recipients a copy of this License along with the Program. + + You may charge any price or no price for each copy that you convey, +and you may offer support or warranty protection for a fee. + + 5. Conveying Modified Source Versions. + + You may convey a work based on the Program, or the modifications to +produce it from the Program, in the form of source code under the +terms of section 4, provided that you also meet all of these conditions: + + a) The work must carry prominent notices stating that you modified + it, and giving a relevant date. + + b) The work must carry prominent notices stating that it is + released under this License and any conditions added under section + 7. This requirement modifies the requirement in section 4 to + "keep intact all notices". + + c) You must license the entire work, as a whole, under this + License to anyone who comes into possession of a copy. This + License will therefore apply, along with any applicable section 7 + additional terms, to the whole of the work, and all its parts, + regardless of how they are packaged. This License gives no + permission to license the work in any other way, but it does not + invalidate such permission if you have separately received it. + + d) If the work has interactive user interfaces, each must display + Appropriate Legal Notices; however, if the Program has interactive + interfaces that do not display Appropriate Legal Notices, your + work need not make them do so. + + A compilation of a covered work with other separate and independent +works, which are not by their nature extensions of the covered work, +and which are not combined with it such as to form a larger program, +in or on a volume of a storage or distribution medium, is called an +"aggregate" if the compilation and its resulting copyright are not +used to limit the access or legal rights of the compilation's users +beyond what the individual works permit. Inclusion of a covered work +in an aggregate does not cause this License to apply to the other +parts of the aggregate. + + 6. Conveying Non-Source Forms. + + You may convey a covered work in object code form under the terms +of sections 4 and 5, provided that you also convey the +machine-readable Corresponding Source under the terms of this License, +in one of these ways: + + a) Convey the object code in, or embodied in, a physical product + (including a physical distribution medium), accompanied by the + Corresponding Source fixed on a durable physical medium + customarily used for software interchange. + + b) Convey the object code in, or embodied in, a physical product + (including a physical distribution medium), accompanied by a + written offer, valid for at least three years and valid for as + long as you offer spare parts or customer support for that product + model, to give anyone who possesses the object code either (1) a + copy of the Corresponding Source for all the software in the + product that is covered by this License, on a durable physical + medium customarily used for software interchange, for a price no + more than your reasonable cost of physically performing this + conveying of source, or (2) access to copy the + Corresponding Source from a network server at no charge. + + c) Convey individual copies of the object code with a copy of the + written offer to provide the Corresponding Source. This + alternative is allowed only occasionally and noncommercially, and + only if you received the object code with such an offer, in accord + with subsection 6b. + + d) Convey the object code by offering access from a designated + place (gratis or for a charge), and offer equivalent access to the + Corresponding Source in the same way through the same place at no + further charge. You need not require recipients to copy the + Corresponding Source along with the object code. If the place to + copy the object code is a network server, the Corresponding Source + may be on a different server (operated by you or a third party) + that supports equivalent copying facilities, provided you maintain + clear directions next to the object code saying where to find the + Corresponding Source. Regardless of what server hosts the + Corresponding Source, you remain obligated to ensure that it is + available for as long as needed to satisfy these requirements. + + e) Convey the object code using peer-to-peer transmission, provided + you inform other peers where the object code and Corresponding + Source of the work are being offered to the general public at no + charge under subsection 6d. + + A separable portion of the object code, whose source code is excluded +from the Corresponding Source as a System Library, need not be +included in conveying the object code work. + + A "User Product" is either (1) a "consumer product", which means any +tangible personal property which is normally used for personal, family, +or household purposes, or (2) anything designed or sold for incorporation +into a dwelling. In determining whether a product is a consumer product, +doubtful cases shall be resolved in favor of coverage. For a particular +product received by a particular user, "normally used" refers to a +typical or common use of that class of product, regardless of the status +of the particular user or of the way in which the particular user +actually uses, or expects or is expected to use, the product. A product +is a consumer product regardless of whether the product has substantial +commercial, industrial or non-consumer uses, unless such uses represent +the only significant mode of use of the product. + + "Installation Information" for a User Product means any methods, +procedures, authorization keys, or other information required to install +and execute modified versions of a covered work in that User Product from +a modified version of its Corresponding Source. The information must +suffice to ensure that the continued functioning of the modified object +code is in no case prevented or interfered with solely because +modification has been made. + + If you convey an object code work under this section in, or with, or +specifically for use in, a User Product, and the conveying occurs as +part of a transaction in which the right of possession and use of the +User Product is transferred to the recipient in perpetuity or for a +fixed term (regardless of how the transaction is characterized), the +Corresponding Source conveyed under this section must be accompanied +by the Installation Information. But this requirement does not apply +if neither you nor any third party retains the ability to install +modified object code on the User Product (for example, the work has +been installed in ROM). + + The requirement to provide Installation Information does not include a +requirement to continue to provide support service, warranty, or updates +for a work that has been modified or installed by the recipient, or for +the User Product in which it has been modified or installed. Access to a +network may be denied when the modification itself materially and +adversely affects the operation of the network or violates the rules and +protocols for communication across the network. + + Corresponding Source conveyed, and Installation Information provided, +in accord with this section must be in a format that is publicly +documented (and with an implementation available to the public in +source code form), and must require no special password or key for +unpacking, reading or copying. + + 7. Additional Terms. + + "Additional permissions" are terms that supplement the terms of this +License by making exceptions from one or more of its conditions. +Additional permissions that are applicable to the entire Program shall +be treated as though they were included in this License, to the extent +that they are valid under applicable law. If additional permissions +apply only to part of the Program, that part may be used separately +under those permissions, but the entire Program remains governed by +this License without regard to the additional permissions. + + When you convey a copy of a covered work, you may at your option +remove any additional permissions from that copy, or from any part of +it. (Additional permissions may be written to require their own +removal in certain cases when you modify the work.) You may place +additional permissions on material, added by you to a covered work, +for which you have or can give appropriate copyright permission. + + Notwithstanding any other provision of this License, for material you +add to a covered work, you may (if authorized by the copyright holders of +that material) supplement the terms of this License with terms: + + a) Disclaiming warranty or limiting liability differently from the + terms of sections 15 and 16 of this License; or + + b) Requiring preservation of specified reasonable legal notices or + author attributions in that material or in the Appropriate Legal + Notices displayed by works containing it; or + + c) Prohibiting misrepresentation of the origin of that material, or + requiring that modified versions of such material be marked in + reasonable ways as different from the original version; or + + d) Limiting the use for publicity purposes of names of licensors or + authors of the material; or + + e) Declining to grant rights under trademark law for use of some + trade names, trademarks, or service marks; or + + f) Requiring indemnification of licensors and authors of that + material by anyone who conveys the material (or modified versions of + it) with contractual assumptions of liability to the recipient, for + any liability that these contractual assumptions directly impose on + those licensors and authors. + + All other non-permissive additional terms are considered "further +restrictions" within the meaning of section 10. If the Program as you +received it, or any part of it, contains a notice stating that it is +governed by this License along with a term that is a further +restriction, you may remove that term. If a license document contains +a further restriction but permits relicensing or conveying under this +License, you may add to a covered work material governed by the terms +of that license document, provided that the further restriction does +not survive such relicensing or conveying. + + If you add terms to a covered work in accord with this section, you +must place, in the relevant source files, a statement of the +additional terms that apply to those files, or a notice indicating +where to find the applicable terms. + + Additional terms, permissive or non-permissive, may be stated in the +form of a separately written license, or stated as exceptions; +the above requirements apply either way. + + 8. Termination. + + You may not propagate or modify a covered work except as expressly +provided under this License. Any attempt otherwise to propagate or +modify it is void, and will automatically terminate your rights under +this License (including any patent licenses granted under the third +paragraph of section 11). + + However, if you cease all violation of this License, then your +license from a particular copyright holder is reinstated (a) +provisionally, unless and until the copyright holder explicitly and +finally terminates your license, and (b) permanently, if the copyright +holder fails to notify you of the violation by some reasonable means +prior to 60 days after the cessation. + + Moreover, your license from a particular copyright holder is +reinstated permanently if the copyright holder notifies you of the +violation by some reasonable means, this is the first time you have +received notice of violation of this License (for any work) from that +copyright holder, and you cure the violation prior to 30 days after +your receipt of the notice. + + Termination of your rights under this section does not terminate the +licenses of parties who have received copies or rights from you under +this License. If your rights have been terminated and not permanently +reinstated, you do not qualify to receive new licenses for the same +material under section 10. + + 9. Acceptance Not Required for Having Copies. + + You are not required to accept this License in order to receive or +run a copy of the Program. Ancillary propagation of a covered work +occurring solely as a consequence of using peer-to-peer transmission +to receive a copy likewise does not require acceptance. However, +nothing other than this License grants you permission to propagate or +modify any covered work. These actions infringe copyright if you do +not accept this License. Therefore, by modifying or propagating a +covered work, you indicate your acceptance of this License to do so. + + 10. Automatic Licensing of Downstream Recipients. + + Each time you convey a covered work, the recipient automatically +receives a license from the original licensors, to run, modify and +propagate that work, subject to this License. You are not responsible +for enforcing compliance by third parties with this License. + + An "entity transaction" is a transaction transferring control of an +organization, or substantially all assets of one, or subdividing an +organization, or merging organizations. If propagation of a covered +work results from an entity transaction, each party to that +transaction who receives a copy of the work also receives whatever +licenses to the work the party's predecessor in interest had or could +give under the previous paragraph, plus a right to possession of the +Corresponding Source of the work from the predecessor in interest, if +the predecessor has it or can get it with reasonable efforts. + + You may not impose any further restrictions on the exercise of the +rights granted or affirmed under this License. For example, you may +not impose a license fee, royalty, or other charge for exercise of +rights granted under this License, and you may not initiate litigation +(including a cross-claim or counterclaim in a lawsuit) alleging that +any patent claim is infringed by making, using, selling, offering for +sale, or importing the Program or any portion of it. + + 11. Patents. + + A "contributor" is a copyright holder who authorizes use under this +License of the Program or a work on which the Program is based. The +work thus licensed is called the contributor's "contributor version". + + A contributor's "essential patent claims" are all patent claims +owned or controlled by the contributor, whether already acquired or +hereafter acquired, that would be infringed by some manner, permitted +by this License, of making, using, or selling its contributor version, +but do not include claims that would be infringed only as a +consequence of further modification of the contributor version. For +purposes of this definition, "control" includes the right to grant +patent sublicenses in a manner consistent with the requirements of +this License. + + Each contributor grants you a non-exclusive, worldwide, royalty-free +patent license under the contributor's essential patent claims, to +make, use, sell, offer for sale, import and otherwise run, modify and +propagate the contents of its contributor version. + + In the following three paragraphs, a "patent license" is any express +agreement or commitment, however denominated, not to enforce a patent +(such as an express permission to practice a patent or covenant not to +sue for patent infringement). To "grant" such a patent license to a +party means to make such an agreement or commitment not to enforce a +patent against the party. + + If you convey a covered work, knowingly relying on a patent license, +and the Corresponding Source of the work is not available for anyone +to copy, free of charge and under the terms of this License, through a +publicly available network server or other readily accessible means, +then you must either (1) cause the Corresponding Source to be so +available, or (2) arrange to deprive yourself of the benefit of the +patent license for this particular work, or (3) arrange, in a manner +consistent with the requirements of this License, to extend the patent +license to downstream recipients. "Knowingly relying" means you have +actual knowledge that, but for the patent license, your conveying the +covered work in a country, or your recipient's use of the covered work +in a country, would infringe one or more identifiable patents in that +country that you have reason to believe are valid. + + If, pursuant to or in connection with a single transaction or +arrangement, you convey, or propagate by procuring conveyance of, a +covered work, and grant a patent license to some of the parties +receiving the covered work authorizing them to use, propagate, modify +or convey a specific copy of the covered work, then the patent license +you grant is automatically extended to all recipients of the covered +work and works based on it. + + A patent license is "discriminatory" if it does not include within +the scope of its coverage, prohibits the exercise of, or is +conditioned on the non-exercise of one or more of the rights that are +specifically granted under this License. You may not convey a covered +work if you are a party to an arrangement with a third party that is +in the business of distributing software, under which you make payment +to the third party based on the extent of your activity of conveying +the work, and under which the third party grants, to any of the +parties who would receive the covered work from you, a discriminatory +patent license (a) in connection with copies of the covered work +conveyed by you (or copies made from those copies), or (b) primarily +for and in connection with specific products or compilations that +contain the covered work, unless you entered into that arrangement, +or that patent license was granted, prior to 28 March 2007. + + Nothing in this License shall be construed as excluding or limiting +any implied license or other defenses to infringement that may +otherwise be available to you under applicable patent law. + + 12. No Surrender of Others' Freedom. + + If conditions are imposed on you (whether by court order, agreement or +otherwise) that contradict the conditions of this License, they do not +excuse you from the conditions of this License. If you cannot convey a +covered work so as to satisfy simultaneously your obligations under this +License and any other pertinent obligations, then as a consequence you may +not convey it at all. For example, if you agree to terms that obligate you +to collect a royalty for further conveying from those to whom you convey +the Program, the only way you could satisfy both those terms and this +License would be to refrain entirely from conveying the Program. + + 13. Use with the GNU Affero General Public License. + + Notwithstanding any other provision of this License, you have +permission to link or combine any covered work with a work licensed +under version 3 of the GNU Affero General Public License into a single +combined work, and to convey the resulting work. The terms of this +License will continue to apply to the part which is the covered work, +but the special requirements of the GNU Affero General Public License, +section 13, concerning interaction through a network will apply to the +combination as such. + + 14. Revised Versions of this License. + + The Free Software Foundation may publish revised and/or new versions of +the GNU General Public License from time to time. Such new versions will +be similar in spirit to the present version, but may differ in detail to +address new problems or concerns. + + Each version is given a distinguishing version number. If the +Program specifies that a certain numbered version of the GNU General +Public License "or any later version" applies to it, you have the +option of following the terms and conditions either of that numbered +version or of any later version published by the Free Software +Foundation. If the Program does not specify a version number of the +GNU General Public License, you may choose any version ever published +by the Free Software Foundation. + + If the Program specifies that a proxy can decide which future +versions of the GNU General Public License can be used, that proxy's +public statement of acceptance of a version permanently authorizes you +to choose that version for the Program. + + Later license versions may give you additional or different +permissions. However, no additional obligations are imposed on any +author or copyright holder as a result of your choosing to follow a +later version. + + 15. Disclaimer of Warranty. + + THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY +APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT +HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY +OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, +THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR +PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM +IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF +ALL NECESSARY SERVICING, REPAIR OR CORRECTION. + + 16. Limitation of Liability. + + IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING +WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS +THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY +GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE +USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF +DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD +PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS), +EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF +SUCH DAMAGES. + + 17. Interpretation of Sections 15 and 16. + + If the disclaimer of warranty and limitation of liability provided +above cannot be given local legal effect according to their terms, +reviewing courts shall apply local law that most closely approximates +an absolute waiver of all civil liability in connection with the +Program, unless a warranty or assumption of liability accompanies a +copy of the Program in return for a fee. + + END OF TERMS AND CONDITIONS + + How to Apply These Terms to Your New Programs + + If you develop a new program, and you want it to be of the greatest +possible use to the public, the best way to achieve this is to make it +free software which everyone can redistribute and change under these terms. + + To do so, attach the following notices to the program. It is safest +to attach them to the start of each source file to most effectively +state the exclusion of warranty; and each file should have at least +the "copyright" line and a pointer to where the full notice is found. + + + Copyright (C) + + This program is free software: you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation, either version 3 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program. If not, see . + +Also add information on how to contact you by electronic and paper mail. + + If the program does terminal interaction, make it output a short +notice like this when it starts in an interactive mode: + + Copyright (C) + This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'. + This is free software, and you are welcome to redistribute it + under certain conditions; type `show c' for details. + +The hypothetical commands `show w' and `show c' should show the appropriate +parts of the General Public License. Of course, your program's commands +might be different; for a GUI interface, you would use an "about box". + + You should also get your employer (if you work as a programmer) or school, +if any, to sign a "copyright disclaimer" for the program, if necessary. +For more information on this, and how to apply and follow the GNU GPL, see +. + + The GNU General Public License does not permit incorporating your program +into proprietary programs. If your program is a subroutine library, you +may consider it more useful to permit linking proprietary applications with +the library. If this is what you want to do, use the GNU Lesser General +Public License instead of this License. But first, please read +. -- 2.47.1 From d8989d9c7668a9c270ed024081b06ea193800cac Mon Sep 17 00:00:00 2001 From: Yehowshua Immanuel Date: Tue, 19 Jul 2022 22:05:00 -0400 Subject: [PATCH 41/50] I broke something --- src/main.rs | 5 ++--- src/vcd/parse.rs | 41 ++++++++++++++++++++++++++++++++++++++--- src/vcd/reader.rs | 6 +++--- src/vcd/types.rs | 4 ++-- 4 files changed, 45 insertions(+), 11 deletions(-) diff --git a/src/main.rs b/src/main.rs index e10377c..0995ccd 100644 --- a/src/main.rs +++ b/src/main.rs @@ -16,12 +16,11 @@ struct Cli { fn main() -> std::io::Result<()> { let args = Cli::parse(); - let file = File::open(&args.path)?; let vcd = parse_vcd(file).unwrap(); - println!("printing signal tree"); - vcd.print_scopes(); + // println!("printing signal tree"); + // vcd.print_scopes(); Ok(()) } \ No newline at end of file diff --git a/src/vcd/parse.rs b/src/vcd/parse.rs index 4ab523c..77352b4 100644 --- a/src/vcd/parse.rs +++ b/src/vcd/parse.rs @@ -32,10 +32,44 @@ fn parse_events<'a>( // nothing left to do... if next_word.is_none() {break}; + let (word, cursor) = next_word.unwrap(); match &word[0..1] { - "$" => {continue} - "#" => {continue} + "$" => {} + "#" => { + let value = &word[1..]; + let time_cursor = BigInt::parse_bytes(value.as_bytes(), 10).ok_or( + format!("failed to parse {value} as BigInt at {cursor:?}").as_str())?; + vcd.cursor = time_cursor; + } + "0" => { + // 0 must be in the first word in the line + let Cursor(Line(_), Word(word_in_line_idx)) = cursor; + if word_in_line_idx == 1 { + let hash = &word[1..].to_string(); + let Signal_Idx(ref signal_idx) = signal_map.get(hash).ok_or( + format!("failed to lookup signal {hash} at {cursor:?}").as_str())?; + + // let value = 0.to_bigint().unwrap(); + // let pair = (TimeStamp(vcd.cursor.clone()), Sig_Value::Numeric(value)); + // timeline.push(pair); + let signal_idx = + { + let signal = vcd.all_signals.get(*signal_idx).unwrap(); + match signal { + Signal::Data {..} => {signal_idx} + Signal::Alias {name, signal_alias} => { + let Signal_Idx(ref signal_idx) = signal_alias; + signal_idx + + } + } + }; + + let signal = vcd.all_signals.get_mut(*signal_idx).unwrap(); + } + } + "1" => {} _ => {} } } @@ -59,7 +93,8 @@ pub fn parse_vcd(file : File) -> Result { }; parse_scopes(&mut word_gen, None, &mut vcd, &mut signal_map)?; - // parse_events(&mut word_gen, &mut vcd, &mut signal_map)?; + parse_events(&mut word_gen, &mut vcd, &mut signal_map)?; + dbg!(&vcd.cursor); Ok(vcd) } diff --git a/src/vcd/reader.rs b/src/vcd/reader.rs index f361716..a10c4ca 100644 --- a/src/vcd/reader.rs +++ b/src/vcd/reader.rs @@ -6,11 +6,11 @@ use std::io::prelude::*; use std::io; #[derive(Debug)] -struct Line(usize); +pub(super) struct Line(pub(super) usize); #[derive(Debug)] -struct Word(usize); +pub(super) struct Word(pub(super) usize); #[derive(Debug)] -pub struct Cursor(Line, Word); +pub(super) struct Cursor(pub(super) Line, pub(super) Word); impl Cursor { pub(super) fn error(&self, word : &str) -> Result<(), String> { diff --git a/src/vcd/types.rs b/src/vcd/types.rs index 6796179..edaec97 100644 --- a/src/vcd/types.rs +++ b/src/vcd/types.rs @@ -24,7 +24,7 @@ pub(super) struct Signal_Idx(pub(super) usize); pub(super) enum Sig_Type {Integer, Parameter, Real, Reg, Str, Wire, Tri1, Time} #[derive(Debug)] -pub(super) struct TimeStamp(BigInt); +pub(super) struct TimeStamp(pub(super) BigInt); #[derive(Debug)] pub(super) enum Sig_Value { @@ -61,7 +61,7 @@ pub(super) struct Scope { #[derive(Debug)] pub struct VCD { pub(super) metadata : Metadata, - pub(super) cursor : BigInt, + pub (super) cursor : BigInt, pub(super) all_signals : Vec, pub(super) all_scopes : Vec, pub(super) scope_roots : Vec} -- 2.47.1 From 3658833af3a950e9f66204a61d62476e26c41b18 Mon Sep 17 00:00:00 2001 From: Yehowshua Immanuel Date: Wed, 20 Jul 2022 10:38:56 -0400 Subject: [PATCH 42/50] wow - things are really working --- README.md | 3 ++ src/main.rs | 2 +- src/vcd/parse.rs | 101 ++++++++++++++++++++++++++++++++++++----------- 3 files changed, 83 insertions(+), 23 deletions(-) diff --git a/README.md b/README.md index 0070709..90d8723 100644 --- a/README.md +++ b/README.md @@ -31,6 +31,9 @@ You can run all the tests with ``cargo test`` is, for each possible tool). - [ ] Fix warning especially usage and restriction warnings once I'm able to successfully parse all sample VCDs. + - [ ] Change error messages to line and filenames. Go through all calls to ``format!`` + whilst also keep performance in mind. + - [ ] Print out git commit or release number. - [ ] Should be able to load waveform whilst viewing it live. - could be quite challenging to implement for various reasons diff --git a/src/main.rs b/src/main.rs index 0995ccd..5c0d88c 100644 --- a/src/main.rs +++ b/src/main.rs @@ -17,7 +17,7 @@ fn main() -> std::io::Result<()> { let args = Cli::parse(); let file = File::open(&args.path)?; - let vcd = parse_vcd(file).unwrap(); + let vcd = parse_vcd(file).unwrap(); // println!("printing signal tree"); // vcd.print_scopes(); diff --git a/src/vcd/parse.rs b/src/vcd/parse.rs index 77352b4..180bb88 100644 --- a/src/vcd/parse.rs +++ b/src/vcd/parse.rs @@ -34,6 +34,9 @@ fn parse_events<'a>( let (word, cursor) = next_word.unwrap(); + let Cursor(Line(_), Word(word_in_line_idx)) = cursor; + // we only want to match on the first word in a line + if word_in_line_idx != 1 {continue} match &word[0..1] { "$" => {} "#" => { @@ -43,33 +46,87 @@ fn parse_events<'a>( vcd.cursor = time_cursor; } "0" => { - // 0 must be in the first word in the line - let Cursor(Line(_), Word(word_in_line_idx)) = cursor; - if word_in_line_idx == 1 { - let hash = &word[1..].to_string(); - let Signal_Idx(ref signal_idx) = signal_map.get(hash).ok_or( - format!("failed to lookup signal {hash} at {cursor:?}").as_str())?; + // lokup signal idx + let hash = &word[1..].to_string(); + let Signal_Idx(ref signal_idx) = signal_map.get(hash).ok_or( + format!("failed to lookup signal {hash} at {cursor:?}").as_str())?; - // let value = 0.to_bigint().unwrap(); - // let pair = (TimeStamp(vcd.cursor.clone()), Sig_Value::Numeric(value)); - // timeline.push(pair); - let signal_idx = - { - let signal = vcd.all_signals.get(*signal_idx).unwrap(); - match signal { - Signal::Data {..} => {signal_idx} - Signal::Alias {name, signal_alias} => { - let Signal_Idx(ref signal_idx) = signal_alias; - signal_idx + // 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.clone()} + Signal::Alias {name, signal_alias} => { + let Signal_Idx(ref signal_idx) = signal_alias; + signal_idx.clone() - } } - }; + } + }; - let signal = vcd.all_signals.get_mut(*signal_idx).unwrap(); - } + // 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, num_bits, + self_idx, timeline, scope_parent} => { + let value = 0.to_bigint().unwrap(); + let pair = (TimeStamp(vcd.cursor.clone()), Sig_Value::Numeric(value)); + timeline.push(pair); + Ok(()) + } + Signal::Alias {..} => { + let (f, l )= (file!(), line!()); + let msg = format!( + "Error near {f}:{l}, a signal alias should not point to a signal alias.\n\ + This error occurred while parsing vcd file at {cursor:?}"); + Err(msg) + } + }?; + } + "1" => { + // lokup signal idx + let hash = &word[1..].to_string(); + let Signal_Idx(ref signal_idx) = signal_map.get(hash).ok_or( + format!("failed to lookup signal {hash} at {cursor:?}").as_str())?; + + // 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.clone()} + Signal::Alias {name, signal_alias} => { + let Signal_Idx(ref signal_idx) = signal_alias; + signal_idx.clone() + + } + } + }; + + // after handling potential indirection, go ahead and update the timeline + // of the signal signal_idx references + let signal = vcd.all_signals.get_mut(signal_idx).unwrap(); + match signal { + Signal::Data {name, sig_type, num_bits, + self_idx, timeline, scope_parent} => { + let value = 1.to_bigint().unwrap(); + let pair = (TimeStamp(vcd.cursor.clone()), Sig_Value::Numeric(value)); + timeline.push(pair); + Ok(()) + } + Signal::Alias {..} => { + let (f, l )= (file!(), line!()); + let msg = format!( + "Error near {f}:{l}, a signal alias should not point to a signal alias.\n\ + This error occurred while parsing vcd file at {cursor:?}"); + Err(msg) + } + }?; } - "1" => {} _ => {} } } -- 2.47.1 From 18a69872ab89623a95e8c398f851705ce948e524 Mon Sep 17 00:00:00 2001 From: Yehowshua Immanuel Date: Mon, 25 Jul 2022 21:16:15 -0400 Subject: [PATCH 43/50] saving progress so far --- README.md | 1 + src/main.rs | 8 + src/vcd/parse.rs | 325 ++++++++++++++++++++++++++++++++----- src/vcd/parse/metadata.rs | 4 +- src/vcd/parse/scopes.rs | 1 + src/vcd/reader.rs | 25 ++- src/vcd/types.rs | 53 +++++- test-vcd-files/sources.csv | 21 ++- 8 files changed, 379 insertions(+), 59 deletions(-) diff --git a/README.md b/README.md index 90d8723..791fb1f 100644 --- a/README.md +++ b/README.md @@ -33,6 +33,7 @@ You can run all the tests with ``cargo test`` able to successfully parse all sample VCDs. - [ ] Change error messages to line and filenames. Go through all calls to ``format!`` whilst also keep performance in mind. + - [ ] Create compressed fungible numeric enums with good heuristic support. - [ ] Print out git commit or release number. - [ ] Should be able to load waveform whilst viewing it live. - could be quite challenging to implement for various reasons diff --git a/src/main.rs b/src/main.rs index 5c0d88c..8ff2fef 100644 --- a/src/main.rs +++ b/src/main.rs @@ -16,9 +16,17 @@ struct Cli { 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(); + // println!("printing signal tree"); // vcd.print_scopes(); diff --git a/src/vcd/parse.rs b/src/vcd/parse.rs index 180bb88..d9a1d0b 100644 --- a/src/vcd/parse.rs +++ b/src/vcd/parse.rs @@ -1,5 +1,6 @@ use std::{fs::File}; use std::collections::HashMap; +use chrono::format::format; use num::BigInt; use num::bigint::ToBigInt; @@ -17,8 +18,84 @@ use metadata::*; mod scopes; use scopes::*; +use std::num::{IntErrorKind, ParseIntError}; + use function_name::named; +/// Sometimes, variables can be listed outside of scopes. +/// We call these floating vars. +pub(super) fn parse_orphaned_vars<'a>( + word_reader : &mut WordReader, + vcd : &'a mut VCD, + signal_map : &mut HashMap +) -> Result<(), String> { + // create scope for unscoped signals if such a scope does not + // yet exist + let scope_name = "Orphaned Signals"; + + // set default scope_idx to the count of existing scope as we + // generally set scope.self_idx to the number of existing scopes + // when that particular scope was inserted + let mut scope_idx = Scope_Idx(vcd.all_scopes.len()); + + // Override scope_idx if we find a scope named "Orphaned Signals" + // already exists + let mut scope_already_exists = false; + for scope in &vcd.all_scopes { + if scope.name == scope_name { + scope_idx = scope.self_idx; + scope_already_exists = true; + break + } + } + + if !scope_already_exists { + vcd.all_scopes.push( + Scope { + name: scope_name.to_string(), + parent_idx: None, + self_idx: scope_idx, + child_signals: vec![], + child_scopes: vec![] + } + ); + vcd.scope_roots.push(scope_idx); + } + + // we can go ahead and parse the current var as we've already encountered + // "$var" before now. + parse_var(word_reader, scope_idx, vcd, signal_map)?; + + loop { + let next_word = word_reader.next_word(); + + // we shouldn't reach the end of the file here... + if next_word.is_none() { + let (f, l )= (file!(), line!()); + let msg = format!("Error near {f}:{l}.\ + Reached end of file without terminating parser"); + Err(msg)?; + }; + + let (word, cursor) = next_word.unwrap(); + + match word { + "$var" => { + parse_var(word_reader, scope_idx, vcd, signal_map)?; + } + "$scope" => {break} + _ => { + let (f, l )= (file!(), line!()); + let msg = format!("Error near {f}:{l}.\ + Expected $scope or $var, found {word} at {cursor:?}"); + Err(msg)?; + } + }; + } + + Ok(()) +} + #[named] fn parse_events<'a>( word_reader : &mut WordReader, @@ -41,9 +118,142 @@ fn parse_events<'a>( "$" => {} "#" => { let value = &word[1..]; - let time_cursor = BigInt::parse_bytes(value.as_bytes(), 10).ok_or( - format!("failed to parse {value} as BigInt at {cursor:?}").as_str())?; - vcd.cursor = time_cursor; + // we try to parse the timestamp into the Value unsigned + // variant used to hold the previous timestamp. Doing this + // may fail with PosOverflow, which we would store in parse_ok, + // and later try to remedy with bigger unsigned variants of Value. + let parse_ok = + if let Value::u8(_) = vcd.cursor { + let value = value.parse::(); + match value { + Ok(value) => { + vcd.cursor = Value::u8(value); + Ok(()) + } + Err(e) => Err(e) + } + } + else if let Value::u16(_) = vcd.cursor { + let value = value.parse::(); + match value { + Ok(value) => { + vcd.cursor = Value::u16(value); + Ok(()) + } + Err(e) => Err(e) + } + } + else if let Value::u32(_) = vcd.cursor { + let value = value.parse::(); + match value { + Ok(value) => { + vcd.cursor = Value::u32(value); + Ok(()) + } + Err(e) => Err(e) + } + } + else if let Value::u64(_) = vcd.cursor { + let value = value.parse::(); + match value { + Ok(value) => { + vcd.cursor = Value::u64(value); + Ok(()) + } + Err(e) => Err(e) + } + } + else { + let value = BigInt::parse_bytes(value.as_bytes(), 10).ok_or( + format!("failed to parse {value} as BigInt at {cursor:?}").as_str())?; + vcd.cursor = Value::BigInt(value); + Ok(()) + }; + + + // If there was no parse error, we don't evaluate any more logic + // in this match arm and simply continue to the next iteration of + // the outer loop to evaluate the next word. + if parse_ok.is_ok() { + continue + } + + // Try parsing value as u16 since there was a previous + // PosOverflow error, and record if this parse attempt + // was Ok or Err in parse_ok. + let parse_ok = + { + let e = parse_ok.unwrap_err(); + // There could have been other parse errors... + // Return Err below if there were. + if e.kind() != &IntErrorKind::PosOverflow { + Err(format!("{e:?}"))?; + } + + match value.parse::() { + Ok(value) => { + vcd.cursor = Value::u16(value); + Ok(()) + } + Err(e) => Err(e) + } + }; + + // If there was no parse error, we don't evaluate any more logic + // in this match arm and simply continue to the next iteration of + // the outer loop to evaluate the next word. + if parse_ok.is_ok() { + continue + } + + // Try parsing value as u32 since there was a previous + // PosOverflow error, and record if this parse attempt + // was Ok or Err in parse_ok. + let parse_ok = + { + let e = parse_ok.unwrap_err(); + // There could have been other parse errors... + // Return Err below if there were. + if e.kind() != &IntErrorKind::PosOverflow { + Err(format!("{e:?}"))?; + } + + match value.parse::() { + Ok(value) => { + vcd.cursor = Value::u32(value); + Ok(()) + } + Err(e) => Err(e) + } + }; + + // If there was no parse error, we don't evaluate any more logic + // in this match arm and simply continue to the next iteration of + // the outer loop to evaluate the next word. + if parse_ok.is_ok() { + continue + } + + // Try parsing value as u64 since there was a previous + // PosOverflow error, and record if this parse attempt + // was Ok or Err in parse_ok. + let parse_ok = + { + let e = parse_ok.unwrap_err(); + // There could have been other parse errors... + // Return Err below if there were. + if e.kind() != &IntErrorKind::PosOverflow { + Err(format!("{e:?}"))?; + } + + match value.parse::() { + Ok(value) => { + vcd.cursor = Value::u64(value); + Ok(()) + } + Err(e) => Err(e) + } + }; } "0" => { // lokup signal idx @@ -68,12 +278,13 @@ fn parse_events<'a>( // 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(); + let signal = vcd.all_signals.get_mut(0usize).unwrap(); + // let signal = vcd.all_signals.get_mut(signal_idx).unwrap(); match signal { Signal::Data {name, sig_type, num_bits, self_idx, timeline, scope_parent} => { let value = 0.to_bigint().unwrap(); - let pair = (TimeStamp(vcd.cursor.clone()), Sig_Value::Numeric(value)); + let pair = (vcd.cursor.clone(), Value::u8(0)); timeline.push(pair); Ok(()) } @@ -86,47 +297,47 @@ fn parse_events<'a>( } }?; } - "1" => { - // lokup signal idx - let hash = &word[1..].to_string(); - let Signal_Idx(ref signal_idx) = signal_map.get(hash).ok_or( - format!("failed to lookup signal {hash} at {cursor:?}").as_str())?; + // "1" => { + // // lokup signal idx + // let hash = &word[1..].to_string(); + // let Signal_Idx(ref signal_idx) = signal_map.get(hash).ok_or( + // format!("failed to lookup signal {hash} at {cursor:?}").as_str())?; - // 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.clone()} - Signal::Alias {name, signal_alias} => { - let Signal_Idx(ref signal_idx) = signal_alias; - signal_idx.clone() + // // 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.clone()} + // Signal::Alias {name, signal_alias} => { + // let Signal_Idx(ref signal_idx) = signal_alias; + // signal_idx.clone() - } - } - }; + // } + // } + // }; - // after handling potential indirection, go ahead and update the timeline - // of the signal signal_idx references - let signal = vcd.all_signals.get_mut(signal_idx).unwrap(); - match signal { - Signal::Data {name, sig_type, num_bits, - self_idx, timeline, scope_parent} => { - let value = 1.to_bigint().unwrap(); - let pair = (TimeStamp(vcd.cursor.clone()), Sig_Value::Numeric(value)); - timeline.push(pair); - Ok(()) - } - Signal::Alias {..} => { - let (f, l )= (file!(), line!()); - let msg = format!( - "Error near {f}:{l}, a signal alias should not point to a signal alias.\n\ - This error occurred while parsing vcd file at {cursor:?}"); - Err(msg) - } - }?; - } + // // 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, num_bits, + // self_idx, timeline, scope_parent} => { + // let value = 1.to_bigint().unwrap(); + // let pair = (TimeStamp(vcd.cursor.clone()), Sig_Value::Numeric(value)); + // timeline.push(pair); + // Ok(()) + // } + // Signal::Alias {..} => { + // let (f, l )= (file!(), line!()); + // let msg = format!( + // "Error near {f}:{l}, a signal alias should not point to a signal alias.\n\ + // This error occurred while parsing vcd file at {cursor:?}"); + // Err(msg) + // } + // }?; + // } _ => {} } } @@ -139,17 +350,41 @@ pub fn parse_vcd(file : File) -> Result { let header = parse_metadata(&mut word_gen)?; + // later, we'll need to map parsed ascii symbols to their + // respective signal indexes let mut signal_map = std::collections::HashMap::new(); + // after we parse metadata, we form VCD object let mut vcd = VCD{ metadata : header, - cursor : 0.to_bigint().unwrap(), + cursor : Value::u8(0), all_signals: vec![], all_scopes : vec![], scope_roots: vec![], }; - parse_scopes(&mut word_gen, None, &mut vcd, &mut signal_map)?; + // The last word parse_metadata saw determines how we proceed. + // There may be some orphan vars we must parse first before + // parsing scoped vars. + let (f, l ) = (file!(), line!()); + let msg = format!("Error near {f}:{l}. Current word empty!"); + let (word, cursor) = word_gen.curr_word().expect(msg.as_str()); + match word { + "$scope" => { + parse_scopes(&mut word_gen, None, &mut vcd, &mut signal_map) + } + "$var" => { + parse_orphaned_vars(&mut word_gen, &mut vcd, &mut signal_map)?; + parse_scopes(&mut word_gen, None, &mut vcd, &mut signal_map) + } + _ => { + let (f, l )= (file!(), line!()); + let msg = format!("Error near {f}:{l}.\ + Expected $scope or $var, found {word} at {cursor:?}"); + Err(msg) + } + + }?; parse_events(&mut word_gen, &mut vcd, &mut signal_map)?; dbg!(&vcd.cursor); diff --git a/src/vcd/parse/metadata.rs b/src/vcd/parse/metadata.rs index 7e0cc91..5d8c956 100644 --- a/src/vcd/parse/metadata.rs +++ b/src/vcd/parse/metadata.rs @@ -315,10 +315,10 @@ pub(super) fn parse_metadata(word_reader : &mut WordReader) -> Result {break} + "var" => {break} // we keep searching for words until we've found one of the following - // keywords, ["version", "timescale", "scope"] + // keywords, ["version", "timescale", "scope", "var"] _ => {} } } diff --git a/src/vcd/parse/scopes.rs b/src/vcd/parse/scopes.rs index d03001c..cbe4ad9 100644 --- a/src/vcd/parse/scopes.rs +++ b/src/vcd/parse/scopes.rs @@ -52,6 +52,7 @@ pub(super) fn parse_var<'a>( // ^ - signal_alias let (word, cursor) = word_reader.next_word().ok_or(&err)?; let signal_alias = word.to_string(); + // dbg!(&signal_alias); // $var parameter 3 a IDLE $end // ^^^^ - full_signal_name(can extend until $end) diff --git a/src/vcd/reader.rs b/src/vcd/reader.rs index a10c4ca..d6437a9 100644 --- a/src/vcd/reader.rs +++ b/src/vcd/reader.rs @@ -5,11 +5,11 @@ use std::str; use std::io::prelude::*; use std::io; -#[derive(Debug)] +#[derive(Debug, Clone)] pub(super) struct Line(pub(super) usize); -#[derive(Debug)] +#[derive(Debug, Clone)] pub(super) struct Word(pub(super) usize); -#[derive(Debug)] +#[derive(Debug, Clone)] pub(super) struct Cursor(pub(super) Line, pub(super) Word); impl Cursor { @@ -26,6 +26,7 @@ pub struct WordReader { buffers : Vec, curr_line : usize, str_slices : VecDeque<(*const u8, usize, Cursor)>, + curr_slice : Option<(*const u8, usize, Cursor)>, } impl WordReader { @@ -36,7 +37,8 @@ impl WordReader { EOF : false, buffers : vec![], curr_line : 0, - str_slices : VecDeque::new() + str_slices : VecDeque::new(), + curr_slice : None } } @@ -83,7 +85,22 @@ impl WordReader { unsafe { 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)); }; } + + pub(super) fn curr_word(&mut self) -> Option<(&str, Cursor)> { + match &self.curr_slice { + Some(slice) => { + unsafe { + let (ptr, len, position) = slice.clone(); + let slice = slice::from_raw_parts(ptr, len); + Some((str::from_utf8(slice).unwrap(), position)) + } + + } + None => {None} + } + } } \ No newline at end of file diff --git a/src/vcd/types.rs b/src/vcd/types.rs index edaec97..bb9bc2a 100644 --- a/src/vcd/types.rs +++ b/src/vcd/types.rs @@ -1,3 +1,4 @@ +use core::time; use std::collections::{BTreeMap, HashMap}; use chrono::prelude::*; use num::BigInt; @@ -24,11 +25,26 @@ pub(super) struct Signal_Idx(pub(super) usize); pub(super) enum Sig_Type {Integer, Parameter, Real, Reg, Str, Wire, Tri1, Time} #[derive(Debug)] -pub(super) struct TimeStamp(pub(super) BigInt); +pub(super) enum TimeStamp { + u8(u8), + u16(u16), + u32(u32), + u64(u64), + BigInt(BigInt), +} + +#[derive(Debug, Clone)] +pub(super) enum Value { + u8(u8), + u16(u16), + u32(u32), + u64(u64), + BigInt(BigInt), +} #[derive(Debug)] pub(super) enum Sig_Value { - Numeric(BigInt), + Numeric(u64), NonNumeric(String)} #[derive(Debug)] @@ -39,7 +55,7 @@ pub(super) enum Signal{ num_bits : Option, // TODO : may be able to remove self_idx self_idx : Signal_Idx, - timeline : Vec<(TimeStamp, Sig_Value)>, + timeline : Vec<(Value, Value)>, scope_parent : Scope_Idx}, Alias{ name : String, @@ -61,7 +77,7 @@ pub(super) struct Scope { #[derive(Debug)] pub struct VCD { pub(super) metadata : Metadata, - pub (super) cursor : BigInt, + pub (super) cursor : Value, pub(super) all_signals : Vec, pub(super) all_scopes : Vec, pub(super) scope_roots : Vec} @@ -107,4 +123,33 @@ impl VCD { self.print_scope_tree(*scope_root, 0); } } + + 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, + sig_type, + num_bits, + self_idx, + timeline, + scope_parent } => { + if timeline.len() > max_len { + max_len = timeline.len(); + let Signal_Idx(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/test-vcd-files/sources.csv b/test-vcd-files/sources.csv index b9b58e9..0f6a722 100644 --- a/test-vcd-files/sources.csv +++ b/test-vcd-files/sources.csv @@ -1,4 +1,17 @@ -Icarus,Verilator,GHDL,VCS,QuestaSim,ModelSim,Quartus,SystemC,Treadle,Aldec,Riviera-PRO,MyHDL,ncsim,xilinx_isim,vivado,GTKWave-Analyzer,Amaranth -https://github.com/dpretet/vcd/blob/master/test1.vcd,https://github.com/wavedrom/vcd-samples/blob/trunk/swerv1.vcd,https://raw.githubusercontent.com/AdoobII/idea_21s/main/vhdl/idea.vcd,https://raw.githubusercontent.com/ameyjain/8-bit-Microprocessor/master/8-bit%20microprocessor/processor.vcd,https://github.com/mr-gaurav/Sequence-Counter/blob/main/test.vcd,https://github.com/Mohammad-Heydariii/Digital-Systems-Lab-Course/blob/main/Lab_project4/modelsim_files/clkdiv2n_tb.vcd,https://github.com/PedroTLemos/ProjetoInfraHard/blob/master/mipsHardware.vcd,https://github.com/jroslindo/Mips-Systemc/blob/main/REGISTRADORES_32_bits/wave_registradores.vcd,https://github.com/chipsalliance/treadle/blob/master/src/test/resources/GCD.vcd,https://github.com/SVeilleux9/FPGA-GPIO-Extender/blob/main/Firmware/aldec/SPI_Write/SPI_Write.vcd,https://github.com/prathampathak/Tic-Tac-Tao/blob/main/dump.vcd,https://github.com/aibtw/myHdl_Projects/blob/main/SimpleMemory/Simple_Memory.vcd,https://github.com/amiteee78/RTL_design/blob/master/ffdiv_32bit/ffdiv_32bit_prop_binom/run_cad/ffdiv_32bit_tb.vcd,https://github.com/mukul54/qrs-peak-fpga/blob/master/utkarsh/utkarsh.sim/sim_1/behav/xsim/test.vcd,https://github.com/saharmalmir/Eth2Ser/blob/master/UART2ETH.runs/impl_1/iladata.vcd,https://github.com/Asfagus/Network-Switch/blob/main/perm_current.vcd,Locally Simulated File -https://github.com/ombhilare999/riscv-core/blob/master/src/rv32_soc_TB.vcd,https://github.com/bigBrain1901/nPOWER-ISA-5-STAGE-PIPELINED-CPU/blob/master/post_compile_files/vlt_dump.vcd,https://github.com/gaoqqt2n/CPU/blob/master/SuperPipelineCPU/vcdfile/pcpu.vcd,https://raw.githubusercontent.com/Akashay-Singla/RISC-V/main/Pipeline/datapath_log.vcd,https://github.com/SparshAgarwal/Computer-Architecture/blob/master/hw3/hw3_1/dump.vcd,https://github.com/sh619/Songyu_Huang-Chisel/blob/main/MU0_final_version/simulation/qsim/CPU_Design.msim.vcd,,https://github.com/amrhas/PDRNoC/blob/VCRouter/noctweak/Debug/waveform.vcd.vcd,,,,https://github.com/Abhishek010397/Programming-RISC-V/blob/master/top.vcd,,https://github.com/DanieleParravicini/regex_coprocessor/blob/master/scripts/sim/test2x2_regex22_string1.vcd,https://github.com/BradMcDanel/multiplication-free-dnn/blob/master/verilog/iladata.vcd,, -https://github.com/b06902044/computer_architecture/blob/main/CPU.vcd,,https://github.com/charlycop/VLSI-1/blob/master/EXEC/ALU/alu.vcd,https://raw.githubusercontent.com/sathyapriyanka/APB_UVC_UVM/main/Apb_slave_uvm_new.vcd,,,,,,,,https://github.com/DarthSkipper/myHDL_Sigmoid/blob/master/out/testbench/sigmoid_tb.vcd,,https://github.com/pabloec1729/Hashes-generator/blob/master/RTL/velocidad/test.vcd,,, +Icarus,https://github.com/dpretet/vcd/blob/master/test1.vcd,https://github.com/ombhilare999/riscv-core/blob/master/src/rv32_soc_TB.vcd,https://github.com/b06902044/computer_architecture/blob/main/CPU.vcd +Verilator,https://github.com/wavedrom/vcd-samples/blob/trunk/swerv1.vcd,https://github.com/bigBrain1901/nPOWER-ISA-5-STAGE-PIPELINED-CPU/blob/master/post_compile_files/vlt_dump.vcd, +GHDL,https://raw.githubusercontent.com/AdoobII/idea_21s/main/vhdl/idea.vcd,https://github.com/gaoqqt2n/CPU/blob/master/SuperPipelineCPU/vcdfile/pcpu.vcd,https://github.com/charlycop/VLSI-1/blob/master/EXEC/ALU/alu.vcd +VCS,https://raw.githubusercontent.com/ameyjain/8-bit-Microprocessor/master/8-bit%20microprocessor/processor.vcd,https://raw.githubusercontent.com/Akashay-Singla/RISC-V/main/Pipeline/datapath_log.vcd,https://raw.githubusercontent.com/sathyapriyanka/APB_UVC_UVM/main/Apb_slave_uvm_new.vcd +QuestaSim,https://github.com/mr-gaurav/Sequence-Counter/blob/main/test.vcd,https://github.com/SparshAgarwal/Computer-Architecture/blob/master/hw3/hw3_1/dump.vcd, +ModelSim,https://github.com/Mohammad-Heydariii/Digital-Systems-Lab-Course/blob/main/Lab_project4/modelsim_files/clkdiv2n_tb.vcd,https://github.com/sh619/Songyu_Huang-Chisel/blob/main/MU0_final_version/simulation/qsim/CPU_Design.msim.vcd, +Quartus,https://github.com/PedroTLemos/ProjetoInfraHard/blob/master/mipsHardware.vcd,, +SystemC,https://github.com/jroslindo/Mips-Systemc/blob/main/REGISTRADORES_32_bits/wave_registradores.vcd,https://github.com/amrhas/PDRNoC/blob/VCRouter/noctweak/Debug/waveform.vcd.vcd, +Treadle,https://github.com/chipsalliance/treadle/blob/master/src/test/resources/GCD.vcd,, +Aldec,https://github.com/SVeilleux9/FPGA-GPIO-Extender/blob/main/Firmware/aldec/SPI_Write/SPI_Write.vcd,, +Riviera-PRO,https://github.com/prathampathak/Tic-Tac-Tao/blob/main/dump.vcd,, +MyHDL,https://github.com/aibtw/myHdl_Projects/blob/main/SimpleMemory/Simple_Memory.vcd,https://github.com/Abhishek010397/Programming-RISC-V/blob/master/top.vcd,https://github.com/DarthSkipper/myHDL_Sigmoid/blob/master/out/testbench/sigmoid_tb.vcd +ncsim,https://github.com/amiteee78/RTL_design/blob/master/ffdiv_32bit/ffdiv_32bit_prop_binom/run_cad/ffdiv_32bit_tb.vcd,, +xilinx_isim,https://github.com/mukul54/qrs-peak-fpga/blob/master/utkarsh/utkarsh.sim/sim_1/behav/xsim/test.vcd,https://github.com/DanieleParravicini/regex_coprocessor/blob/master/scripts/sim/test2x2_regex22_string1.vcd,https://github.com/pabloec1729/Hashes-generator/blob/master/RTL/velocidad/test.vcd +vivado,https://github.com/saharmalmir/Eth2Ser/blob/master/UART2ETH.runs/impl_1/iladata.vcd,https://github.com/BradMcDanel/multiplication-free-dnn/blob/master/verilog/iladata.vcd, +GTKWave-Analyzer,https://github.com/Asfagus/Network-Switch/blob/main/perm_current.vcd,, +Amaranth,Locally Simulated File,, \ No newline at end of file -- 2.47.1 From 504913c719d8509382a14c377dba428fa176f2f3 Mon Sep 17 00:00:00 2001 From: Yehowshua Immanuel Date: Wed, 27 Jul 2022 09:35:44 -0400 Subject: [PATCH 44/50] still broken - but I need to save progress --- src/vcd/parse.rs | 73 ++++++++++++++++++++++++++++++++++++++++++------ src/vcd/types.rs | 10 +++++-- 2 files changed, 72 insertions(+), 11 deletions(-) diff --git a/src/vcd/parse.rs b/src/vcd/parse.rs index d9a1d0b..45e3dc3 100644 --- a/src/vcd/parse.rs +++ b/src/vcd/parse.rs @@ -164,8 +164,9 @@ fn parse_events<'a>( } } else { + let (f, l )= (file!(), line!()); let value = BigInt::parse_bytes(value.as_bytes(), 10).ok_or( - format!("failed to parse {value} as BigInt at {cursor:?}").as_str())?; + format!("Error near {f}:{l}. Failed to parse {value} as BigInt at {cursor:?}").as_str())?; vcd.cursor = Value::BigInt(value); Ok(()) }; @@ -187,12 +188,14 @@ fn parse_events<'a>( // There could have been other parse errors... // Return Err below if there were. if e.kind() != &IntErrorKind::PosOverflow { - Err(format!("{e:?}"))?; + let (f, l )= (file!(), line!()); + Err(format!("Error near {f}:{l}. {e:?}"))?; } match value.parse::() { Ok(value) => { vcd.cursor = Value::u16(value); + println!("switching to u16"); Ok(()) } Err(e) => Err(e) @@ -215,12 +218,14 @@ fn parse_events<'a>( // There could have been other parse errors... // Return Err below if there were. if e.kind() != &IntErrorKind::PosOverflow { - Err(format!("{e:?}"))?; + let (f, l )= (file!(), line!()); + Err(format!("Error near {f}:{l}. {e:?}"))?; } match value.parse::() { Ok(value) => { vcd.cursor = Value::u32(value); + println!("switching to u32"); Ok(()) } Err(e) => Err(e) @@ -243,17 +248,66 @@ fn parse_events<'a>( // There could have been other parse errors... // Return Err below if there were. if e.kind() != &IntErrorKind::PosOverflow { - Err(format!("{e:?}"))?; + let (f, l )= (file!(), line!()); + Err(format!("Error near {f}:{l}. {e:?}"))?; } match value.parse::() { Ok(value) => { vcd.cursor = Value::u64(value); + println!("switching to u64"); Ok(()) } Err(e) => Err(e) } }; + + // If there was no parse error, we don't evaluate any more logic + // in this match arm and simply continue to the next iteration of + // the outer loop to evaluate the next word. + if parse_ok.is_ok() { + continue + } + + // Try parsing value as u64 since there was a previous + // PosOverflow error, and record if this parse attempt + // was Ok or Err in parse_ok. + let parse_ok = + { + let e = parse_ok.unwrap_err(); + // There could have been other parse errors... + // Return Err below if there were. + if e.kind() != &IntErrorKind::PosOverflow { + let (f, l )= (file!(), line!()); + Err(format!("Error near {f}:{l}. {e:?}"))?; + } + + match value.parse::() { + Ok(value) => { + vcd.cursor = Value::u64(value); + println!("switching to u64"); + Ok(()) + } + Err(e) => Err(e) + } + }; + + // Try parsing value as BigInt since there was a previous + // PosOverflow error and propagate any Result Errors. + let e = parse_ok.unwrap_err(); + // There could have been other parse errors... + // Return Err below if there were. + if e.kind() != &IntErrorKind::PosOverflow { + let (f, l )= (file!(), line!()); + Err(format!("Error near {f}:{l}. {e:?}"))?; + } + + 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())?; + vcd.cursor = Value::BigInt(value); + println!("switching to BigInt"); + } "0" => { // lokup signal idx @@ -278,14 +332,14 @@ fn parse_events<'a>( // after handling potential indirection, go ahead and update the timeline // of the signal signal_idx references - let signal = vcd.all_signals.get_mut(0usize).unwrap(); - // let signal = vcd.all_signals.get_mut(signal_idx).unwrap(); + let signal = vcd.all_signals.get_mut(signal_idx).unwrap(); match signal { Signal::Data {name, sig_type, num_bits, self_idx, timeline, scope_parent} => { - let value = 0.to_bigint().unwrap(); - let pair = (vcd.cursor.clone(), Value::u8(0)); - timeline.push(pair); + // let pair = (0.to_bigint(), Value::u8(0)); + let pair = (Value::u8(0), Value::u8(0)); + let t = 0u32.to_be_bytes(); + // timeline.push(pair); Ok(()) } Signal::Alias {..} => { @@ -358,6 +412,7 @@ pub fn parse_vcd(file : File) -> Result { let mut vcd = VCD{ metadata : header, cursor : Value::u8(0), + timeline : vec![], all_signals: vec![], all_scopes : vec![], scope_roots: vec![], diff --git a/src/vcd/types.rs b/src/vcd/types.rs index bb9bc2a..127d343 100644 --- a/src/vcd/types.rs +++ b/src/vcd/types.rs @@ -21,6 +21,9 @@ pub(super) struct Scope_Idx(pub(super) usize); #[derive(Debug, Copy, Clone)] pub(super) struct Signal_Idx(pub(super) usize); +#[derive(Debug, Copy, Clone)] +pub(super) struct TimelineIdx(pub(super) usize); + #[derive(Debug)] pub(super) enum Sig_Type {Integer, Parameter, Real, Reg, Str, Wire, Tri1, Time} @@ -42,6 +45,8 @@ pub(super) enum Value { BigInt(BigInt), } +pub type BigNum = Vec; + #[derive(Debug)] pub(super) enum Sig_Value { Numeric(u64), @@ -55,7 +60,7 @@ pub(super) enum Signal{ num_bits : Option, // TODO : may be able to remove self_idx self_idx : Signal_Idx, - timeline : Vec<(Value, Value)>, + timeline : Vec<(TimelineIdx, BigNum)>, scope_parent : Scope_Idx}, Alias{ name : String, @@ -77,7 +82,8 @@ pub(super) struct Scope { #[derive(Debug)] pub struct VCD { pub(super) metadata : Metadata, - pub (super) cursor : Value, + pub(super) cursor : Value, + pub(super) timeline : Vec, pub(super) all_signals : Vec, pub(super) all_scopes : Vec, pub(super) scope_roots : Vec} -- 2.47.1 From eb379e4ce61f5e9770b1754cb54facf19421cc4e Mon Sep 17 00:00:00 2001 From: Yehowshua Immanuel Date: Thu, 28 Jul 2022 10:43:58 -0400 Subject: [PATCH 45/50] update README --- README.md | 18 ++++++++---------- 1 file changed, 8 insertions(+), 10 deletions(-) diff --git a/README.md b/README.md index 791fb1f..98e5a8c 100644 --- a/README.md +++ b/README.md @@ -1,18 +1,16 @@ -# Disclaimer -PROPRIETARY - Copyright - Yehowshua Immanuel +Copyright - Yehowshua Immanuel -# The Beginnings of a high-performance, low memory footprint VCD Viewer in Rust for massive multi-GB waveforms +# A High performance, VCD Parser written in Rust ## Current Features - - very fast - - loads 400MB of VCD waveform per second on an 8 core 2017 desktop CPU with NVMe storage - - consumes roughly between 10 - 50MB of memory per GB of waveform + - pretty fast ## Planned Features - - elegant/pretty UI - - can be easily ported to work in browser via webassembly - - allows high-performance custom Rust plugins to manipulate and - generate new waveforms live + - rapid log2n scrubbing through a signal's timeline + +# Current Limitations +Unable to handle VCD files that have signals with more than +2^32 - 1 = 4,294,967,295 deltas/changes. ## Running -- 2.47.1 From 0052baf196728f9b9ecc8b95d0b84211f18b809c Mon Sep 17 00:00:00 2001 From: Yehowshua Immanuel Date: Sat, 30 Jul 2022 19:58:54 -0400 Subject: [PATCH 46/50] add support for mismatching bitdwidths --- src/main.rs | 8 +- src/test/files.rs | 1 + src/vcd/parse.rs | 414 +++++++++++++++++++--------------------- src/vcd/parse/scopes.rs | 4 +- src/vcd/types.rs | 46 ++++- 5 files changed, 245 insertions(+), 228 deletions(-) diff --git a/src/main.rs b/src/main.rs index 8ff2fef..a84f406 100644 --- a/src/main.rs +++ b/src/main.rs @@ -1,4 +1,4 @@ -use std::fs::File; +use std::{fs::File}; use clap::Parser; pub mod test; @@ -7,6 +7,8 @@ use test::*; pub mod vcd; use vcd::parse_vcd; +use std::mem::size_of_val; + #[derive(Parser)] struct Cli { /// The path to the file to read @@ -26,6 +28,10 @@ fn main() -> std::io::Result<()> { 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(); diff --git a/src/test/files.rs b/src/test/files.rs index 4cea310..6498b8c 100644 --- a/src/test/files.rs +++ b/src/test/files.rs @@ -30,6 +30,7 @@ pub const files : [&str; 30] = [ "./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" ]; diff --git a/src/vcd/parse.rs b/src/vcd/parse.rs index 45e3dc3..9267a20 100644 --- a/src/vcd/parse.rs +++ b/src/vcd/parse.rs @@ -109,7 +109,6 @@ fn parse_events<'a>( // nothing left to do... if next_word.is_none() {break}; - let (word, cursor) = next_word.unwrap(); let Cursor(Line(_), Word(word_in_line_idx)) = cursor; // we only want to match on the first word in a line @@ -118,202 +117,26 @@ fn parse_events<'a>( "$" => {} "#" => { let value = &word[1..]; - // we try to parse the timestamp into the Value unsigned - // variant used to hold the previous timestamp. Doing this - // may fail with PosOverflow, which we would store in parse_ok, - // and later try to remedy with bigger unsigned variants of Value. - let parse_ok = - if let Value::u8(_) = vcd.cursor { - let value = value.parse::(); - match value { - Ok(value) => { - vcd.cursor = Value::u8(value); - Ok(()) - } - Err(e) => Err(e) - } - } - else if let Value::u16(_) = vcd.cursor { - let value = value.parse::(); - match value { - Ok(value) => { - vcd.cursor = Value::u16(value); - Ok(()) - } - Err(e) => Err(e) - } - } - else if let Value::u32(_) = vcd.cursor { - let value = value.parse::(); - match value { - Ok(value) => { - vcd.cursor = Value::u32(value); - Ok(()) - } - Err(e) => Err(e) - } - } - else if let Value::u64(_) = vcd.cursor { - let value = value.parse::(); - match value { - Ok(value) => { - vcd.cursor = Value::u64(value); - Ok(()) - } - Err(e) => Err(e) - } - } - else { - 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())?; - vcd.cursor = Value::BigInt(value); - Ok(()) - }; - - - // If there was no parse error, we don't evaluate any more logic - // in this match arm and simply continue to the next iteration of - // the outer loop to evaluate the next word. - if parse_ok.is_ok() { - continue - } - - // Try parsing value as u16 since there was a previous - // PosOverflow error, and record if this parse attempt - // was Ok or Err in parse_ok. - let parse_ok = - { - let e = parse_ok.unwrap_err(); - // There could have been other parse errors... - // Return Err below if there were. - if e.kind() != &IntErrorKind::PosOverflow { - let (f, l )= (file!(), line!()); - Err(format!("Error near {f}:{l}. {e:?}"))?; - } - - match value.parse::() { - Ok(value) => { - vcd.cursor = Value::u16(value); - println!("switching to u16"); - Ok(()) - } - Err(e) => Err(e) - } - }; - - // If there was no parse error, we don't evaluate any more logic - // in this match arm and simply continue to the next iteration of - // the outer loop to evaluate the next word. - if parse_ok.is_ok() { - continue - } - - // Try parsing value as u32 since there was a previous - // PosOverflow error, and record if this parse attempt - // was Ok or Err in parse_ok. - let parse_ok = - { - let e = parse_ok.unwrap_err(); - // There could have been other parse errors... - // Return Err below if there were. - if e.kind() != &IntErrorKind::PosOverflow { - let (f, l )= (file!(), line!()); - Err(format!("Error near {f}:{l}. {e:?}"))?; - } - - match value.parse::() { - Ok(value) => { - vcd.cursor = Value::u32(value); - println!("switching to u32"); - Ok(()) - } - Err(e) => Err(e) - } - }; - - // If there was no parse error, we don't evaluate any more logic - // in this match arm and simply continue to the next iteration of - // the outer loop to evaluate the next word. - if parse_ok.is_ok() { - continue - } - - // Try parsing value as u64 since there was a previous - // PosOverflow error, and record if this parse attempt - // was Ok or Err in parse_ok. - let parse_ok = - { - let e = parse_ok.unwrap_err(); - // There could have been other parse errors... - // Return Err below if there were. - if e.kind() != &IntErrorKind::PosOverflow { - let (f, l )= (file!(), line!()); - Err(format!("Error near {f}:{l}. {e:?}"))?; - } - - match value.parse::() { - Ok(value) => { - vcd.cursor = Value::u64(value); - println!("switching to u64"); - Ok(()) - } - Err(e) => Err(e) - } - }; - - // If there was no parse error, we don't evaluate any more logic - // in this match arm and simply continue to the next iteration of - // the outer loop to evaluate the next word. - if parse_ok.is_ok() { - continue - } - - // Try parsing value as u64 since there was a previous - // PosOverflow error, and record if this parse attempt - // was Ok or Err in parse_ok. - let parse_ok = - { - let e = parse_ok.unwrap_err(); - // There could have been other parse errors... - // Return Err below if there were. - if e.kind() != &IntErrorKind::PosOverflow { - let (f, l )= (file!(), line!()); - Err(format!("Error near {f}:{l}. {e:?}"))?; - } - - match value.parse::() { - Ok(value) => { - vcd.cursor = Value::u64(value); - println!("switching to u64"); - Ok(()) - } - Err(e) => Err(e) - } - }; - - // Try parsing value as BigInt since there was a previous - // PosOverflow error and propagate any Result Errors. - let e = parse_ok.unwrap_err(); - // There could have been other parse errors... - // Return Err below if there were. - if e.kind() != &IntErrorKind::PosOverflow { - let (f, l )= (file!(), line!()); - Err(format!("Error near {f}:{l}. {e:?}"))?; - } - 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())?; - vcd.cursor = Value::BigInt(value); - println!("switching to BigInt"); - + // TODO : u32 helps with less memory, but should ideally likely be + // configurable. + let (f, l )= (file!(), line!()); + let start_idx = u32::try_from(vcd.timeline.len()).map_err( + |e| format!("Error near {f}:{l}. Failed to convert from usize to u32."))?; + vcd.timeline_markers.push(StartIdx(start_idx)); + let (_, mut value) = value.to_bytes_be(); + vcd.timeline.append(&mut value); } + + // handle the case of a one bit signal whose value is set to `0` "0" => { - // lokup signal idx - let hash = &word[1..].to_string(); + // lookup signal idx + let hash = &word[1..]; + let (f, l )= (file!(), line!()); let Signal_Idx(ref signal_idx) = signal_map.get(hash).ok_or( - format!("failed to lookup signal {hash} at {cursor:?}").as_str())?; + format!("Error near {f}:{l}. Failed to lookup signal {hash} at {cursor:?}").as_str())?; // account for fact that signal idx could be an alias, so there // could be one step of indirection @@ -321,7 +144,7 @@ fn parse_events<'a>( { let signal = vcd.all_signals.get(*signal_idx).unwrap(); match signal { - Signal::Data {..} => {signal_idx.clone()} + Signal::Data {..} => {*signal_idx} Signal::Alias {name, signal_alias} => { let Signal_Idx(ref signal_idx) = signal_alias; signal_idx.clone() @@ -334,28 +157,162 @@ fn parse_events<'a>( // of the signal signal_idx references let signal = vcd.all_signals.get_mut(signal_idx).unwrap(); match signal { - Signal::Data {name, sig_type, num_bits, - self_idx, timeline, scope_parent} => { - // let pair = (0.to_bigint(), Value::u8(0)); - let pair = (Value::u8(0), Value::u8(0)); - let t = 0u32.to_be_bytes(); - // timeline.push(pair); + Signal::Data {name, sig_type, ref mut signal_error, num_bits, + self_idx, timeline, timeline_markers, scope_parent} => { + + // if this is a bad signal, go ahead and skip it + if signal_error.is_some() {continue;} + + // Get bitwidth and verify that it is 1. + // Also account for the error case of a bitwidth of `None` + match num_bits { + Some(ref num_bits) => { + if *num_bits != 1 { + let (f, l) = (file!(), line!()); + let msg = format!("\ + Error near {f}:{l}. The bitwidth for signal {name} \ + of sig_type {sig_type:?} is expected to be `1` not \ + `{num_bits}`. \ + This error occurred while parsing the vcd file at \ + {cursor:?}"); + signal_error.insert(msg); + continue; + } + } + None => { + let (f, l) = (file!(), line!()); + let msg = format!("\ + Error near {f}:{l}. The bitwidth for signal {name} \ + must be specified for a signal of type {sig_type:?}. \ + This error occurred while parsing the vcd file at \ + {cursor:?}"); + Err(msg)?; + } + }; + + let (f, l )= (file!(), line!()); + let timeline_idx = u32::try_from(vcd.timeline.len()).map_err( + |e| format!("Error near {f}:{l}. Failed to convert from usize to u32."))?; + let timeline_idx = TimelineIdx(timeline_idx); + + let (f, l )= (file!(), line!()); + let start_idx = u32::try_from(timeline.len()).map_err( + |e| format!("Error near {f}:{l}. Failed to convert from usize to u32."))?; + let start_idx = StartIdx(start_idx); + // let pair = (timeline_idx, start_idx); + timeline_markers.push(timeline_idx); + timeline.push(0u8); Ok(()) } Signal::Alias {..} => { let (f, l )= (file!(), line!()); let msg = format!( "Error near {f}:{l}, a signal alias should not point to a signal alias.\n\ - This error occurred while parsing vcd file at {cursor:?}"); + This error occurred while parsing vcd file at {cursor:?}"); Err(msg) } }?; } - // "1" => { - // // lokup signal idx - // let hash = &word[1..].to_string(); - // let Signal_Idx(ref signal_idx) = signal_map.get(hash).ok_or( - // format!("failed to lookup signal {hash} at {cursor:?}").as_str())?; + + // handle the case of a one bit signal whose value is set to `1` + "1" => { + // lokup signal idx + let hash = &word[1..]; + let (f, l )= (file!(), line!()); + let Signal_Idx(ref signal_idx) = signal_map.get(hash).ok_or( + format!("Error near {f}:{l}. Failed to lookup signal {hash} at {cursor:?}").as_str())?; + + // account for fact that signal idx could be an alias, so there + // could be one step of indirection + let signal_idx = + { + let signal = vcd.all_signals.get(*signal_idx).unwrap(); + match signal { + Signal::Data {..} => {*signal_idx} + Signal::Alias {name, signal_alias} => { + let Signal_Idx(ref signal_idx) = signal_alias; + signal_idx.clone() + + } + } + }; + + // after handling potential indirection, go ahead and update the timeline + // of the signal signal_idx references + let signal = vcd.all_signals.get_mut(signal_idx).unwrap(); + match signal { + Signal::Data {name, sig_type, ref mut signal_error, num_bits, + self_idx, timeline, timeline_markers, scope_parent} => { + + // if this is a bad signal, go ahead and skip it + if signal_error.is_some() {continue;} + + // Get bitwidth and verify that it is 1. + // Also account for the error case of a bitwidth of `None` + match num_bits { + Some(ref num_bits) => { + if *num_bits != 1 { + let (f, l) = (file!(), line!()); + let msg = format!("\ + Error near {f}:{l}. The bitwidth for signal {name} \ + of sig_type {sig_type:?} is expected to be `1` not \ + `{num_bits}`. \ + This error occurred while parsing the vcd file at \ + {cursor:?}"); + signal_error.insert(msg); + continue; + } + } + None => { + let (f, l) = (file!(), line!()); + let msg = format!("\ + Error near {f}:{l}. The bitwidth for signal {name} \ + must be specified for a signal of type {sig_type:?}. \ + This error occurred while parsing the vcd file at \ + {cursor:?}"); + Err(msg)?; + } + }; + + let (f, l )= (file!(), line!()); + let timeline_idx = u32::try_from(vcd.timeline.len()).map_err( + |e| format!("Error near {f}:{l}. Failed to convert from usize to u32."))?; + let timeline_idx = TimelineIdx(timeline_idx); + + let (f, l )= (file!(), line!()); + let start_idx = u32::try_from(timeline.len()).map_err( + |e| format!("Error near {f}:{l}. Failed to convert from usize to u32."))?; + let start_idx = StartIdx(start_idx); + // let pair = (timeline_idx, start_idx); + timeline_markers.push(timeline_idx); + timeline.push(1u8); + Ok(()) + } + Signal::Alias {..} => { + let (f, l )= (file!(), line!()); + let msg = format!( + "Error near {f}:{l}, a signal alias should not point to a signal alias.\n\ + This error occurred while parsing vcd file at {cursor:?}"); + Err(msg) + } + }?; + } + + // handle the case of an n bit signal whose value must be parse + // "b" => { + // // let binary_value = &word[1..]; + // // let (f, l )= (file!(), line!()); + // // let value = BigInt::parse_bytes(binary_value.as_bytes(), 2).ok_or( + // // format!("Error near {f}:{l}. Failed to parse {binary_value} as BigInt at {cursor:?}").as_str())?; + // // let (_, mut value) = value.to_bytes_be(); + + // // this word should be the signal alias + // let (word, cursor) = word_reader.next_word().unwrap(); + + // // lookup signal idx + // let (f, l )= (file!(), line!()); + // let Signal_Idx(ref signal_idx) = signal_map.get(word).ok_or( + // format!("Error near {f}:{l}. Failed to lookup signal {word} at {cursor:?}").as_str())?; // // account for fact that signal idx could be an alias, so there // // could be one step of indirection @@ -363,7 +320,7 @@ fn parse_events<'a>( // { // let signal = vcd.all_signals.get(*signal_idx).unwrap(); // match signal { - // Signal::Data {..} => {signal_idx.clone()} + // Signal::Data {..} => {*signal_idx} // Signal::Alias {name, signal_alias} => { // let Signal_Idx(ref signal_idx) = signal_alias; // signal_idx.clone() @@ -377,10 +334,34 @@ fn parse_events<'a>( // let signal = vcd.all_signals.get_mut(signal_idx).unwrap(); // match signal { // Signal::Data {name, sig_type, num_bits, - // self_idx, timeline, scope_parent} => { - // let value = 1.to_bigint().unwrap(); - // let pair = (TimeStamp(vcd.cursor.clone()), Sig_Value::Numeric(value)); - // timeline.push(pair); + // self_idx, timeline, timeline_markers, scope_parent} => { + // // get bitwidth, while accounting for the error case when + // // numbits is None + // let num_bits = { + // let (f, l) = (file!(), line!()); + // let msg = format!("\ + // Error near {f}:{l}. The bitwidth for signal {name} \ + // must be specified for a signal of type {sig_type:?}. \ + // This error occurred while parsing the vcd file at \ + // {cursor:?}"); + // num_bits.as_ref().ok_or(msg)? + // }; + + // let (f, l )= (file!(), line!()); + // let timeline_idx = u32::try_from(vcd.timeline.len()).map_err( + // |e| format!("Error near {f}:{l}. Failed to convert from usize to u32."))?; + // let timeline_idx = TimelineIdx(timeline_idx); + + // let (f, l )= (file!(), line!()); + // let start_idx = u32::try_from(timeline.len()).map_err( + // |e| format!("Error near {f}:{l}. Failed to convert from usize to u32."))?; + // let start_idx = StartIdx(start_idx); + // let pair = (timeline_idx, start_idx); + // // timeline_markers.push(pair); + // // timeline.append(&mut [0u8, 1u8, 2u8]); + // timeline.push(0u8); + // timeline.push(1u8); + // timeline.push(2u8); // Ok(()) // } // Signal::Alias {..} => { @@ -410,12 +391,12 @@ pub fn parse_vcd(file : File) -> Result { // after we parse metadata, we form VCD object let mut vcd = VCD{ - metadata : header, - cursor : Value::u8(0), - timeline : vec![], - all_signals: vec![], - all_scopes : vec![], - scope_roots: vec![], + metadata : header, + timeline : vec![], + timeline_markers : vec![], + all_signals : vec![], + all_scopes : vec![], + scope_roots : vec![], }; // The last word parse_metadata saw determines how we proceed. @@ -423,7 +404,7 @@ pub fn parse_vcd(file : File) -> Result { // parsing scoped vars. let (f, l ) = (file!(), line!()); let msg = format!("Error near {f}:{l}. Current word empty!"); - let (word, cursor) = word_gen.curr_word().expect(msg.as_str()); + let (word, cursor) = word_gen.curr_word().ok_or(msg.as_str())?; match word { "$scope" => { parse_scopes(&mut word_gen, None, &mut vcd, &mut signal_map) @@ -441,7 +422,6 @@ pub fn parse_vcd(file : File) -> Result { }?; parse_events(&mut word_gen, &mut vcd, &mut signal_map)?; - dbg!(&vcd.cursor); Ok(vcd) } diff --git a/src/vcd/parse/scopes.rs b/src/vcd/parse/scopes.rs index cbe4ad9..b275c56 100644 --- a/src/vcd/parse/scopes.rs +++ b/src/vcd/parse/scopes.rs @@ -40,7 +40,7 @@ pub(super) fn parse_var<'a>( let no_bits = match var_type { Sig_Type::Integer | Sig_Type::Parameter | Sig_Type::Real | Sig_Type::Reg | - Sig_Type::Wire => { + Sig_Type::Wire | Sig_Type::Tri1 => { let no_bits = word.parse::().expect(parse_err.as_str()); Some(no_bits) } @@ -83,9 +83,11 @@ pub(super) fn parse_var<'a>( let signal = Signal::Data{ name: full_signal_name, sig_type: var_type, + signal_error: None, num_bits: no_bits, self_idx: signal_idx, timeline: vec![], + timeline_markers: vec![], scope_parent: parent_scope_idx }; (signal, signal_idx) } diff --git a/src/vcd/types.rs b/src/vcd/types.rs index 127d343..45be6c2 100644 --- a/src/vcd/types.rs +++ b/src/vcd/types.rs @@ -22,7 +22,10 @@ pub(super) struct Scope_Idx(pub(super) usize); pub(super) struct Signal_Idx(pub(super) usize); #[derive(Debug, Copy, Clone)] -pub(super) struct TimelineIdx(pub(super) usize); +pub(super) struct TimelineIdx(pub(super) u32); + +#[derive(Debug, Copy, Clone)] +pub struct StartIdx(pub(super) u32); #[derive(Debug)] pub(super) enum Sig_Type {Integer, Parameter, Real, Reg, Str, Wire, Tri1, Time} @@ -55,12 +58,18 @@ pub(super) enum Sig_Value { #[derive(Debug)] pub(super) enum Signal{ Data{ - name : String, - sig_type : Sig_Type, - num_bits : Option, + name : String, + sig_type : Sig_Type, + // I've seen a 0 bit signal parameter in a xilinx + // simulation before that gets assigne 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 : Signal_Idx, - timeline : Vec<(TimelineIdx, BigNum)>, + self_idx : Signal_Idx, + timeline : Vec, + timeline_markers : Vec<(TimelineIdx)>, scope_parent : Scope_Idx}, Alias{ name : String, @@ -79,11 +88,12 @@ pub(super) struct Scope { pub(super) child_scopes : Vec} +// TODO: document how timeline is represented #[derive(Debug)] pub struct VCD { pub(super) metadata : Metadata, - pub(super) cursor : Value, - pub(super) timeline : Vec, + pub timeline : Vec, + pub timeline_markers : Vec, pub(super) all_signals : Vec, pub(super) all_scopes : Vec, pub(super) scope_roots : Vec} @@ -130,6 +140,24 @@ impl VCD { } } + // pub fn average_len(&self) -> f64{ + // let mut total_lens = 0.0; + // for el in &self.timeline { + // total_lens += el.len() as f64; + // } + + // return total_lens/(self.timeline.len() as f64); + // } + + // pub fn total_len(&self) -> usize{ + // let mut total_lens = 0usize; + // for el in &self.timeline { + // total_lens += el.len(); + // } + + // return total_lens; + // } + pub fn print_longest_signal(&self) { let mut idx = 0usize; let mut max_len = 0usize; @@ -144,7 +172,7 @@ impl VCD { num_bits, self_idx, timeline, - scope_parent } => { + .. } => { if timeline.len() > max_len { max_len = timeline.len(); let Signal_Idx(idx_usize) = self_idx; -- 2.47.1 From 232b026f62ec6302597ad673d12e6c13c4fd13b6 Mon Sep 17 00:00:00 2001 From: Yehowshua Immanuel Date: Mon, 1 Aug 2022 10:11:05 -0400 Subject: [PATCH 47/50] things are much faster now, but x/z values not yet supported --- src/vcd/parse.rs | 265 ++++++++++++++++++++++++++-------------- src/vcd/parse/scopes.rs | 8 +- src/vcd/types.rs | 67 ++-------- 3 files changed, 187 insertions(+), 153 deletions(-) diff --git a/src/vcd/parse.rs b/src/vcd/parse.rs index 9267a20..8f21be5 100644 --- a/src/vcd/parse.rs +++ b/src/vcd/parse.rs @@ -1,8 +1,5 @@ use std::{fs::File}; use std::collections::HashMap; -use chrono::format::format; -use num::BigInt; -use num::bigint::ToBigInt; use super::*; @@ -22,6 +19,82 @@ use std::num::{IntErrorKind, ParseIntError}; use function_name::named; +fn binary_str_to_vec_u8(binary_str : &str) -> Result, String> { + let mut vec_u8 : Vec = Vec::new(); + let mut binary_str_as_bytes = binary_str.as_bytes(); + + let mut tail_idx = binary_str_as_bytes.len(); + // clamp head if provided binary str is less than 8 long + let mut head_idx = + if tail_idx >= 8 + {binary_str_as_bytes.len() - 8} + else + {0}; + while {tail_idx > 0} { + let curr_b_val = &binary_str_as_bytes[head_idx..tail_idx]; + let val_u8 = base2_str_to_byte(curr_b_val)?; + vec_u8.push(val_u8); + + + if head_idx < 8 { + head_idx = 0 + } + else { + head_idx = head_idx - 8; + } + + if tail_idx < 8 { + tail_idx = 0 + } + else { + tail_idx = tail_idx - 8; + } + + } + Ok(vec_u8) +} + +fn base2_str_to_byte(word : &[u8]) -> Result { + let mut val = 0u8; + + // shouldn't have more than 8 chars in str + let len = word.len(); + if len > 8 { + let (f, l )= (file!(), line!()); + let err = format!( + "Error near {f}:{l}. Base2 string has length {len} > 8."); + return Err(err) + } + + 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' => {} + _ => { + let chr = *chr as char; + let (f, l )= (file!(), line!()); + let err = format!( + "Error near {f}:{l}. Expected 1 or 0 in base2 string but got {chr}"); + return Err(err) + } + } + + } + + Ok(val) +} + /// Sometimes, variables can be listed outside of scopes. /// We call these floating vars. pub(super) fn parse_orphaned_vars<'a>( @@ -118,15 +191,15 @@ fn parse_events<'a>( "#" => { let value = &word[1..]; let (f, l )= (file!(), line!()); - let value = BigInt::parse_bytes(value.as_bytes(), 10).ok_or( - format!("Error near {f}:{l}. Failed to parse {value} as BigInt at {cursor:?}").as_str())?; + let mut value = binary_str_to_vec_u8(value).map_err( + |e| format!("Error near {f}:{l}. Failed to parse {value} as \ + at {cursor:?} with error {e}"))?; // TODO : u32 helps with less memory, but should ideally likely be // configurable. let (f, l )= (file!(), line!()); let start_idx = u32::try_from(vcd.timeline.len()).map_err( |e| format!("Error near {f}:{l}. Failed to convert from usize to u32."))?; vcd.timeline_markers.push(StartIdx(start_idx)); - let (_, mut value) = value.to_bytes_be(); vcd.timeline.append(&mut value); } @@ -136,7 +209,7 @@ fn parse_events<'a>( let hash = &word[1..]; let (f, l )= (file!(), line!()); let Signal_Idx(ref signal_idx) = signal_map.get(hash).ok_or( - format!("Error near {f}:{l}. Failed to lookup signal {hash} at {cursor:?}").as_str())?; + format!("Error near {f}:{l}. Failed to lookup signal {hash} at {cursor:?}"))?; // account for fact that signal idx could be an alias, so there // could be one step of indirection @@ -158,7 +231,7 @@ fn parse_events<'a>( let signal = vcd.all_signals.get_mut(signal_idx).unwrap(); match signal { Signal::Data {name, sig_type, ref mut signal_error, num_bits, - self_idx, timeline, timeline_markers, scope_parent} => { + self_idx, u8_timeline, u8_timeline_markers, ..} => { // if this is a bad signal, go ahead and skip it if signal_error.is_some() {continue;} @@ -175,7 +248,7 @@ fn parse_events<'a>( `{num_bits}`. \ This error occurred while parsing the vcd file at \ {cursor:?}"); - signal_error.insert(msg); + *signal_error = Some(msg); continue; } } @@ -195,13 +268,8 @@ fn parse_events<'a>( |e| format!("Error near {f}:{l}. Failed to convert from usize to u32."))?; let timeline_idx = TimelineIdx(timeline_idx); - let (f, l )= (file!(), line!()); - let start_idx = u32::try_from(timeline.len()).map_err( - |e| format!("Error near {f}:{l}. Failed to convert from usize to u32."))?; - let start_idx = StartIdx(start_idx); - // let pair = (timeline_idx, start_idx); - timeline_markers.push(timeline_idx); - timeline.push(0u8); + u8_timeline_markers.push(timeline_idx); + u8_timeline.push(0u8); Ok(()) } Signal::Alias {..} => { @@ -220,7 +288,7 @@ fn parse_events<'a>( let hash = &word[1..]; let (f, l )= (file!(), line!()); let Signal_Idx(ref signal_idx) = signal_map.get(hash).ok_or( - format!("Error near {f}:{l}. Failed to lookup signal {hash} at {cursor:?}").as_str())?; + format!("Error near {f}:{l}. Failed to lookup signal {hash} at {cursor:?}"))?; // account for fact that signal idx could be an alias, so there // could be one step of indirection @@ -242,7 +310,7 @@ fn parse_events<'a>( let signal = vcd.all_signals.get_mut(signal_idx).unwrap(); match signal { Signal::Data {name, sig_type, ref mut signal_error, num_bits, - self_idx, timeline, timeline_markers, scope_parent} => { + self_idx, u8_timeline, u8_timeline_markers, scope_parent, ..} => { // if this is a bad signal, go ahead and skip it if signal_error.is_some() {continue;} @@ -259,7 +327,7 @@ fn parse_events<'a>( `{num_bits}`. \ This error occurred while parsing the vcd file at \ {cursor:?}"); - signal_error.insert(msg); + *signal_error = Some(msg); continue; } } @@ -279,13 +347,8 @@ fn parse_events<'a>( |e| format!("Error near {f}:{l}. Failed to convert from usize to u32."))?; let timeline_idx = TimelineIdx(timeline_idx); - let (f, l )= (file!(), line!()); - let start_idx = u32::try_from(timeline.len()).map_err( - |e| format!("Error near {f}:{l}. Failed to convert from usize to u32."))?; - let start_idx = StartIdx(start_idx); - // let pair = (timeline_idx, start_idx); - timeline_markers.push(timeline_idx); - timeline.push(1u8); + u8_timeline_markers.push(timeline_idx); + u8_timeline.push(1u8); Ok(()) } Signal::Alias {..} => { @@ -299,80 +362,94 @@ fn parse_events<'a>( } // handle the case of an n bit signal whose value must be parse - // "b" => { - // // let binary_value = &word[1..]; - // // let (f, l )= (file!(), line!()); - // // let value = BigInt::parse_bytes(binary_value.as_bytes(), 2).ok_or( - // // format!("Error near {f}:{l}. Failed to parse {binary_value} as BigInt at {cursor:?}").as_str())?; - // // let (_, mut value) = value.to_bytes_be(); + "b" => { + let binary_value = &word[1..]; + let observed_num_bits = binary_value.len(); + let (f, l )= (file!(), line!()); + let mut value = binary_str_to_vec_u8(binary_value).map_err( + |e| format!("Error near {f}:{l}. Failed to parse {binary_value} as \ + at {cursor:?} with error {e}"))?; - // // this word should be the signal alias - // let (word, cursor) = word_reader.next_word().unwrap(); + // this word should be the signal alias + let (word, cursor) = word_reader.next_word().unwrap(); - // // lookup signal idx - // let (f, l )= (file!(), line!()); - // let Signal_Idx(ref signal_idx) = signal_map.get(word).ok_or( - // format!("Error near {f}:{l}. Failed to lookup signal {word} at {cursor:?}").as_str())?; + // lookup signal idx + let (f, l )= (file!(), line!()); + let Signal_Idx(ref signal_idx) = signal_map.get(word).ok_or( + format!("Error near {f}:{l}. Failed to lookup signal {word} at {cursor:?}"))?; - // // account for fact that signal idx could be an alias, so there - // // could be one step of indirection - // let signal_idx = - // { - // let signal = vcd.all_signals.get(*signal_idx).unwrap(); - // match signal { - // Signal::Data {..} => {*signal_idx} - // Signal::Alias {name, signal_alias} => { - // let Signal_Idx(ref signal_idx) = signal_alias; - // signal_idx.clone() + // account for fact that signal idx could be an alias, so there + // could be one step of indirection + let signal_idx = + { + let signal = vcd.all_signals.get(*signal_idx).unwrap(); + match signal { + Signal::Data {..} => {*signal_idx} + Signal::Alias {name, signal_alias} => { + let Signal_Idx(ref signal_idx) = signal_alias; + signal_idx.clone() - // } - // } - // }; + } + } + }; - // // after handling potential indirection, go ahead and update the timeline - // // of the signal signal_idx references - // let signal = vcd.all_signals.get_mut(signal_idx).unwrap(); - // match signal { - // Signal::Data {name, sig_type, num_bits, - // self_idx, timeline, timeline_markers, scope_parent} => { - // // get bitwidth, while accounting for the error case when - // // numbits is None - // let num_bits = { - // let (f, l) = (file!(), line!()); - // let msg = format!("\ - // Error near {f}:{l}. The bitwidth for signal {name} \ - // must be specified for a signal of type {sig_type:?}. \ - // This error occurred while parsing the vcd file at \ - // {cursor:?}"); - // num_bits.as_ref().ok_or(msg)? - // }; + // after handling potential indirection, go ahead and update the timeline + // of the signal signal_idx references + let signal = vcd.all_signals.get_mut(signal_idx).unwrap(); + match signal { + Signal::Data {name, sig_type, ref mut signal_error, num_bits, + self_idx, u8_timeline, u8_timeline_markers, scope_parent, ..} => { - // let (f, l )= (file!(), line!()); - // let timeline_idx = u32::try_from(vcd.timeline.len()).map_err( - // |e| format!("Error near {f}:{l}. Failed to convert from usize to u32."))?; - // let timeline_idx = TimelineIdx(timeline_idx); + if signal_error.is_some() {continue;} - // let (f, l )= (file!(), line!()); - // let start_idx = u32::try_from(timeline.len()).map_err( - // |e| format!("Error near {f}:{l}. Failed to convert from usize to u32."))?; - // let start_idx = StartIdx(start_idx); - // let pair = (timeline_idx, start_idx); - // // timeline_markers.push(pair); - // // timeline.append(&mut [0u8, 1u8, 2u8]); - // timeline.push(0u8); - // timeline.push(1u8); - // timeline.push(2u8); - // Ok(()) - // } - // Signal::Alias {..} => { - // let (f, l )= (file!(), line!()); - // let msg = format!( - // "Error near {f}:{l}, a signal alias should not point to a signal alias.\n\ - // This error occurred while parsing vcd file at {cursor:?}"); - // Err(msg) - // } - // }?; - // } + // Get the observed number of bits for the value parsed earlier + // and verify that it is not greater than the numbits declared + // when the signal was declared. + // Also account for the error case of a bitwidth of `None` + match num_bits { + Some(ref num_bits) => { + if *num_bits > observed_num_bits { + let (f, l) = (file!(), line!()); + let msg = format!("\ + Error near {f}:{l}. The bitwidth for signal {name} \ + of sig_type {sig_type:?} is expected to be `1` not \ + `{num_bits}`. \ + This error occurred while parsing the vcd file at \ + {cursor:?}"); + println!("Encountered bad signal {name}."); + *signal_error = Some(msg); + continue; + } + } + None => { + let (f, l) = (file!(), line!()); + let msg = format!("\ + Error near {f}:{l}. The bitwidth for signal {name} \ + must be specified for a signal of type {sig_type:?}. \ + This error occurred while parsing the vcd file at \ + {cursor:?}"); + Err(msg)?; + } + }; + + let (f, l )= (file!(), line!()); + let timeline_idx = u32::try_from(vcd.timeline.len()).map_err( + |e| format!("Error near {f}:{l}. Failed to convert from usize to u32."))?; + let timeline_idx = TimelineIdx(timeline_idx); + + u8_timeline_markers.push(timeline_idx); + u8_timeline.append(&mut value); + Ok(()) + } + Signal::Alias {..} => { + let (f, l )= (file!(), line!()); + let msg = format!( + "Error near {f}:{l}, a signal alias should not point to a signal alias.\n\ + This error occurred while parsing vcd file at {cursor:?}"); + Err(msg) + } + }?; + } _ => {} } } @@ -404,7 +481,7 @@ pub fn parse_vcd(file : File) -> Result { // parsing scoped vars. let (f, l ) = (file!(), line!()); let msg = format!("Error near {f}:{l}. Current word empty!"); - let (word, cursor) = word_gen.curr_word().ok_or(msg.as_str())?; + let (word, cursor) = word_gen.curr_word().ok_or(msg)?; match word { "$scope" => { parse_scopes(&mut word_gen, None, &mut vcd, &mut signal_map) diff --git a/src/vcd/parse/scopes.rs b/src/vcd/parse/scopes.rs index b275c56..cf2e36f 100644 --- a/src/vcd/parse/scopes.rs +++ b/src/vcd/parse/scopes.rs @@ -86,8 +86,10 @@ pub(super) fn parse_var<'a>( signal_error: None, num_bits: no_bits, self_idx: signal_idx, - timeline: vec![], - timeline_markers: vec![], + u8_timeline: vec![], + u8_timeline_markers: vec![], + string_timeline: vec![], + string_timeline_markers: vec![], scope_parent: parent_scope_idx }; (signal, signal_idx) } @@ -161,7 +163,7 @@ pub(super) fn parse_signal_tree<'a>( let (word, cursor) = word_reader.next_word().ok_or(&err)?; let ParseResult{matched, residual} = tag(word, "$"); match matched { - // we hope that this word stars with a `$` + // we hope that this word starts with a `$` "$" => { match residual { "scope" => { diff --git a/src/vcd/types.rs b/src/vcd/types.rs index 45be6c2..6c13095 100644 --- a/src/vcd/types.rs +++ b/src/vcd/types.rs @@ -1,7 +1,4 @@ -use core::time; -use std::collections::{BTreeMap, HashMap}; use chrono::prelude::*; -use num::BigInt; #[derive(Debug)] pub(super) struct Version(pub String); @@ -30,46 +27,25 @@ pub struct StartIdx(pub(super) u32); #[derive(Debug)] pub(super) enum Sig_Type {Integer, Parameter, Real, Reg, Str, Wire, Tri1, Time} -#[derive(Debug)] -pub(super) enum TimeStamp { - u8(u8), - u16(u16), - u32(u32), - u64(u64), - BigInt(BigInt), -} - -#[derive(Debug, Clone)] -pub(super) enum Value { - u8(u8), - u16(u16), - u32(u32), - u64(u64), - BigInt(BigInt), -} - -pub type BigNum = Vec; - -#[derive(Debug)] -pub(super) enum Sig_Value { - Numeric(u64), - NonNumeric(String)} - #[derive(Debug)] pub(super) enum Signal{ Data{ name : String, sig_type : Sig_Type, // I've seen a 0 bit signal parameter in a xilinx - // simulation before that gets assigne 1 bit values. + // 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 : Signal_Idx, - timeline : Vec, - timeline_markers : Vec<(TimelineIdx)>, + // we could encounter a mix of pure values and strings + // for the same signal timeline + u8_timeline : Vec, + u8_timeline_markers : Vec<(TimelineIdx)>, + string_timeline : Vec, + string_timeline_markers : Vec<(TimelineIdx)>, scope_parent : Scope_Idx}, Alias{ name : String, @@ -81,7 +57,6 @@ pub(super) struct Scope { pub(super) name : String, pub(super) parent_idx : Option, - // TODO : may be able to remove self_idx pub(super) self_idx : Scope_Idx, pub(super) child_signals : Vec, @@ -127,11 +102,9 @@ impl VCD { println!(); for scope_idx in &root_scope.child_scopes { - // let Scope_Idx(ref scope_idx_usize) = scope_idx; - // let child_scope = &all_scopes[*scope_idx_usize]; self.print_scope_tree(*scope_idx, depth+1); } - // let root = vcd.all_scopes; + } pub fn print_scopes(&self) { @@ -140,24 +113,6 @@ impl VCD { } } - // pub fn average_len(&self) -> f64{ - // let mut total_lens = 0.0; - // for el in &self.timeline { - // total_lens += el.len() as f64; - // } - - // return total_lens/(self.timeline.len() as f64); - // } - - // pub fn total_len(&self) -> usize{ - // let mut total_lens = 0usize; - // for el in &self.timeline { - // total_lens += el.len(); - // } - - // return total_lens; - // } - pub fn print_longest_signal(&self) { let mut idx = 0usize; let mut max_len = 0usize; @@ -171,10 +126,10 @@ impl VCD { sig_type, num_bits, self_idx, - timeline, + u8_timeline, .. } => { - if timeline.len() > max_len { - max_len = timeline.len(); + if u8_timeline.len() > max_len { + max_len = u8_timeline.len(); let Signal_Idx(idx_usize) = self_idx; idx = *idx_usize; signal_name = name.clone(); -- 2.47.1 From 557f385336061dd44d26cae20d2400bef9e98c36 Mon Sep 17 00:00:00 2001 From: Yehowshua Immanuel Date: Mon, 1 Aug 2022 12:29:25 -0400 Subject: [PATCH 48/50] update README --- README.md | 41 +++++++++++++++++++---------------------- 1 file changed, 19 insertions(+), 22 deletions(-) diff --git a/README.md b/README.md index 98e5a8c..d76621e 100644 --- a/README.md +++ b/README.md @@ -3,10 +3,8 @@ Copyright - Yehowshua Immanuel # A High performance, VCD Parser written in Rust ## Current Features - - pretty fast + - pretty fast, parses 3.04 GB VCD file in ~62s on M1 Macbook Air. -## Planned Features - - rapid log2n scrubbing through a signal's timeline # Current Limitations Unable to handle VCD files that have signals with more than @@ -14,8 +12,8 @@ Unable to handle VCD files that have signals with more than ## Running -Make sure you have a test vcd file to get you started. You can grab -a large VCD file from +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). The first build of the program may take some time. @@ -25,27 +23,26 @@ The first build of the program may take some time. You can run all the tests with ``cargo test`` # TODO - - [ ] make a custon date parser for possibly up to 18 different versions(that - is, for each possible tool). - - [ ] Fix warning especially usage and restriction warnings once I'm - able to successfully parse all sample VCDs. - - [ ] Change error messages to line and filenames. Go through all calls to ``format!`` - whilst also keep performance in mind. - - [ ] Create compressed fungible numeric enums with good heuristic support. + +## Features + - [ ] handle signals with x or z as string + - the one bit parsers may also need to handle string + - move parse_orphaned_vars to scopes.rs - [ ] Print out git commit or release number. - [ ] 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 + - [ ] 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. - - [ ] Consider what to do with don't care values - will probably just convert them to strings for now. - - [ ] Include line and possible column numbers - - [ ] Take a look at GTKWave parser to compare effificiency. - - [ ] Send survey to community channel. + - [ ] Fix warnings especially usage and restriction warnings once I'm + able to successfully parse all sample VCDs. -# Questions to Answer - - [ ] Is it safe to assume that we may treat any values before the first - non-zero timestamp as having occured on `#0`? +## Code Consistency + - [ ] Change error messages to line and filenames. Go through all calls to ``format!`` whilst also keeping performance in mind. -# Probably No Longer Needed - - [ ] Should insert nodes in BFS order \ No newline at end of file +## Marketing + - [ ] Send survey to community channel. \ No newline at end of file -- 2.47.1 From 8f763ae52b28214f142986d99056c9e50e34747c Mon Sep 17 00:00:00 2001 From: Yehowshua Immanuel Date: Mon, 1 Aug 2022 12:31:43 -0400 Subject: [PATCH 49/50] cargo test not passing --- README.md | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/README.md b/README.md index d76621e..a56be8c 100644 --- a/README.md +++ b/README.md @@ -2,6 +2,10 @@ Copyright - Yehowshua Immanuel # A High performance, VCD Parser written in Rust +x/z value parsing currently fails in ``cargo test``. + +A fix is coming. + ## Current Features - pretty fast, parses 3.04 GB VCD file in ~62s on M1 Macbook Air. -- 2.47.1 From e9aa4735dd2b0f1c40a18d4b214be864651d322f Mon Sep 17 00:00:00 2001 From: Yehowshua Immanuel Date: Mon, 1 Aug 2022 16:52:42 -0400 Subject: [PATCH 50/50] things seem pretty stable now --- README.md | 12 +- src/vcd/parse.rs | 316 +++++++++++++++++++++++++++------------- src/vcd/parse/scopes.rs | 3 +- 3 files changed, 219 insertions(+), 112 deletions(-) diff --git a/README.md b/README.md index a56be8c..b673f0e 100644 --- a/README.md +++ b/README.md @@ -2,12 +2,10 @@ Copyright - Yehowshua Immanuel # A High performance, VCD Parser written in Rust -x/z value parsing currently fails in ``cargo test``. - -A fix is coming. - ## Current Features - - pretty fast, parses 3.04 GB VCD file in ~62s on M1 Macbook Air. + - 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 @@ -29,9 +27,7 @@ You can run all the tests with ``cargo test`` # TODO ## Features - - [ ] handle signals with x or z as string - - the one bit parsers may also need to handle string - - move parse_orphaned_vars to scopes.rs + - [ ] move parse_orphaned_vars to scopes.rs - [ ] Print out git commit or release number. - [ ] Should be able to load waveform whilst viewing it live. - could be quite challenging to implement for various reasons diff --git a/src/vcd/parse.rs b/src/vcd/parse.rs index 8f21be5..e9a7b46 100644 --- a/src/vcd/parse.rs +++ b/src/vcd/parse.rs @@ -1,5 +1,6 @@ use std::{fs::File}; use std::collections::HashMap; +use num::BigInt; use super::*; @@ -19,7 +20,10 @@ use std::num::{IntErrorKind, ParseIntError}; use function_name::named; -fn binary_str_to_vec_u8(binary_str : &str) -> Result, String> { +#[derive(Debug)] +enum BinaryParserErrTypes {x_value, z_value, u_value, other_value(char), too_long} + +fn binary_str_to_vec_u8(binary_str : &str) -> Result, BinaryParserErrTypes> { let mut vec_u8 : Vec = Vec::new(); let mut binary_str_as_bytes = binary_str.as_bytes(); @@ -54,7 +58,7 @@ fn binary_str_to_vec_u8(binary_str : &str) -> Result, String> { Ok(vec_u8) } -fn base2_str_to_byte(word : &[u8]) -> Result { +fn base2_str_to_byte(word : &[u8]) -> Result { let mut val = 0u8; // shouldn't have more than 8 chars in str @@ -63,7 +67,7 @@ fn base2_str_to_byte(word : &[u8]) -> Result { let (f, l )= (file!(), line!()); let err = format!( "Error near {f}:{l}. Base2 string has length {len} > 8."); - return Err(err) + return Err(BinaryParserErrTypes::too_long) } let bit_lut = [ @@ -81,13 +85,10 @@ fn base2_str_to_byte(word : &[u8]) -> Result { match chr { b'1' => {val = bit_lut[idx] | val} b'0' => {} - _ => { - let chr = *chr as char; - let (f, l )= (file!(), line!()); - let err = format!( - "Error near {f}:{l}. Expected 1 or 0 in base2 string but got {chr}"); - return Err(err) - } + b'x' | b'X' => {return Err(BinaryParserErrTypes::x_value)} + b'z' | b'Z' => {return Err(BinaryParserErrTypes::z_value)} + b'u' | b'U' => {return Err(BinaryParserErrTypes::u_value)} + _ => {return Err(BinaryParserErrTypes::other_value(*chr as char))} } } @@ -191,9 +192,9 @@ fn parse_events<'a>( "#" => { let value = &word[1..]; let (f, l )= (file!(), line!()); - let mut value = binary_str_to_vec_u8(value).map_err( - |e| format!("Error near {f}:{l}. Failed to parse {value} as \ - at {cursor:?} with error {e}"))?; + 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!()); @@ -202,6 +203,125 @@ fn parse_events<'a>( vcd.timeline_markers.push(StartIdx(start_idx)); vcd.timeline.append(&mut value); } + // handle the case of an n bit signal whose value must be parsed + "b" => { + let binary_value = &word[1..]; + let observed_num_bits = binary_value.len(); + let (f, l )= (file!(), line!()); + + let mut value_u8 : Vec = Vec::new(); + let mut value_string = String::new(); + + let mut store_as_string = false; + + // If we encounter x or z in a value, we can recover from + // the error and store the value as a string. + // Or else, we we propagate up other errors. + match binary_str_to_vec_u8(binary_value) { + Ok(result) => {value_u8 = result;} + Err(BinaryParserErrTypes::x_value | + BinaryParserErrTypes::z_value | + BinaryParserErrTypes::u_value + ) => + { + store_as_string = true; + value_string = binary_value.to_string(); + } + Err(e) => { + let (f, l )= (file!(), line!()); + Err(e).map_err( + |e| format!("Error near {f}:{l}. Error {e:?} at {cursor:?}."))?; + } + } + + // this word should be the signal alias + let (word, cursor) = word_reader.next_word().unwrap(); + + // lookup signal idx + let (f, l )= (file!(), line!()); + let Signal_Idx(ref signal_idx) = signal_map.get(word).ok_or( + format!("Error near {f}:{l}. Failed to lookup signal {word} at {cursor:?}"))?; + + // account for fact that signal idx could be an alias, so there + // could be one step of indirection + let signal_idx = + { + let signal = vcd.all_signals.get(*signal_idx).unwrap(); + match signal { + Signal::Data {..} => {*signal_idx} + Signal::Alias {name, signal_alias} => { + let Signal_Idx(ref signal_idx) = signal_alias; + signal_idx.clone() + + } + } + }; + + // after handling potential indirection, go ahead and update the timeline + // of the signal signal_idx references + let signal = vcd.all_signals.get_mut(signal_idx).unwrap(); + match signal { + Signal::Data {name, sig_type, ref mut signal_error, num_bits, + self_idx, u8_timeline, u8_timeline_markers, string_timeline, + string_timeline_markers, ..} => { + + if signal_error.is_some() {continue;} + + // Get the observed number of bits for the value parsed earlier + // and verify that it is not greater than the numbits declared + // when the signal was declared. + // Also account for the error case of a bitwidth of `None` + match num_bits { + Some(ref num_bits) => { + if *num_bits > observed_num_bits { + let (f, l) = (file!(), line!()); + let msg = format!("\ + Error near {f}:{l}. The bitwidth for signal {name} \ + of sig_type {sig_type:?} is expected to be `1` not \ + `{num_bits}`. \ + This error occurred while parsing the vcd file at \ + {cursor:?}"); + *signal_error = Some(msg); + continue; + } + } + None => { + let (f, l) = (file!(), line!()); + let msg = format!("\ + Error near {f}:{l}. The bitwidth for signal {name} \ + must be specified for a signal of type {sig_type:?}. \ + This error occurred while parsing the vcd file at \ + {cursor:?}"); + Err(msg)?; + } + }; + + let (f, l )= (file!(), line!()); + let timeline_idx = u32::try_from(vcd.timeline.len()).map_err( + |e| format!("Error near {f}:{l}. Failed to convert from usize to u32."))?; + let timeline_idx = TimelineIdx(timeline_idx); + + if store_as_string { + string_timeline_markers.push(timeline_idx); + string_timeline.push(value_string); + Ok(()) + + } + else { + u8_timeline_markers.push(timeline_idx); + u8_timeline.append(&mut value_u8); + Ok(()) + } + } + Signal::Alias {..} => { + let (f, l )= (file!(), line!()); + let msg = format!( + "Error near {f}:{l}, a signal alias should not point to a signal alias.\n\ + This error occurred while parsing vcd file at {cursor:?}"); + Err(msg) + } + }?; + } // handle the case of a one bit signal whose value is set to `0` "0" => { @@ -282,7 +402,86 @@ fn parse_events<'a>( }?; } - // handle the case of a one bit signal whose value is set to `1` + // other one bit cases + "x" | "X" | "z" | "Z" | "u" | "U" => { + let val = word.to_string(); + // lokup signal idx + let hash = &word[1..]; + let (f, l )= (file!(), line!()); + let Signal_Idx(ref signal_idx) = signal_map.get(hash).ok_or( + format!("Error near {f}:{l}. Failed to lookup signal {hash} at {cursor:?}"))?; + + // account for fact that signal idx could be an alias, so there + // could be one step of indirection + let signal_idx = + { + let signal = vcd.all_signals.get(*signal_idx).unwrap(); + match signal { + Signal::Data {..} => {*signal_idx} + Signal::Alias {name, signal_alias} => { + let Signal_Idx(ref signal_idx) = signal_alias; + signal_idx.clone() + + } + } + }; + + // after handling potential indirection, go ahead and update the timeline + // of the signal signal_idx references + let signal = vcd.all_signals.get_mut(signal_idx).unwrap(); + match signal { + Signal::Data {name, sig_type, ref mut signal_error, num_bits, + self_idx, u8_timeline, u8_timeline_markers, string_timeline, + string_timeline_markers, ..} => { + + // if this is a bad signal, go ahead and skip it + if signal_error.is_some() {continue;} + + // Get bitwidth and verify that it is 1. + // Also account for the error case of a bitwidth of `None` + match num_bits { + Some(ref num_bits) => { + if *num_bits != 1 { + let (f, l) = (file!(), line!()); + let msg = format!("\ + Error near {f}:{l}. The bitwidth for signal {name} \ + of sig_type {sig_type:?} is expected to be `1` not \ + `{num_bits}`. \ + This error occurred while parsing the vcd file at \ + {cursor:?}"); + *signal_error = Some(msg); + continue; + } + } + None => { + let (f, l) = (file!(), line!()); + let msg = format!("\ + Error near {f}:{l}. The bitwidth for signal {name} \ + must be specified for a signal of type {sig_type:?}. \ + This error occurred while parsing the vcd file at \ + {cursor:?}"); + Err(msg)?; + } + }; + + let (f, l )= (file!(), line!()); + let timeline_idx = u32::try_from(vcd.timeline.len()).map_err( + |e| format!("Error near {f}:{l}. Failed to convert from usize to u32."))?; + let timeline_idx = TimelineIdx(timeline_idx); + + string_timeline_markers.push(timeline_idx); + string_timeline.push(val); + Ok(()) + } + Signal::Alias {..} => { + let (f, l )= (file!(), line!()); + let msg = format!( + "Error near {f}:{l}, a signal alias should not point to a signal alias.\n\ + This error occurred while parsing vcd file at {cursor:?}"); + Err(msg) + } + }?; + } "1" => { // lokup signal idx let hash = &word[1..]; @@ -361,95 +560,6 @@ fn parse_events<'a>( }?; } - // handle the case of an n bit signal whose value must be parse - "b" => { - let binary_value = &word[1..]; - let observed_num_bits = binary_value.len(); - let (f, l )= (file!(), line!()); - let mut value = binary_str_to_vec_u8(binary_value).map_err( - |e| format!("Error near {f}:{l}. Failed to parse {binary_value} as \ - at {cursor:?} with error {e}"))?; - - // this word should be the signal alias - let (word, cursor) = word_reader.next_word().unwrap(); - - // lookup signal idx - let (f, l )= (file!(), line!()); - let Signal_Idx(ref signal_idx) = signal_map.get(word).ok_or( - format!("Error near {f}:{l}. Failed to lookup signal {word} at {cursor:?}"))?; - - // account for fact that signal idx could be an alias, so there - // could be one step of indirection - let signal_idx = - { - let signal = vcd.all_signals.get(*signal_idx).unwrap(); - match signal { - Signal::Data {..} => {*signal_idx} - Signal::Alias {name, signal_alias} => { - let Signal_Idx(ref signal_idx) = signal_alias; - signal_idx.clone() - - } - } - }; - - // after handling potential indirection, go ahead and update the timeline - // of the signal signal_idx references - let signal = vcd.all_signals.get_mut(signal_idx).unwrap(); - match signal { - Signal::Data {name, sig_type, ref mut signal_error, num_bits, - self_idx, u8_timeline, u8_timeline_markers, scope_parent, ..} => { - - if signal_error.is_some() {continue;} - - // Get the observed number of bits for the value parsed earlier - // and verify that it is not greater than the numbits declared - // when the signal was declared. - // Also account for the error case of a bitwidth of `None` - match num_bits { - Some(ref num_bits) => { - if *num_bits > observed_num_bits { - let (f, l) = (file!(), line!()); - let msg = format!("\ - Error near {f}:{l}. The bitwidth for signal {name} \ - of sig_type {sig_type:?} is expected to be `1` not \ - `{num_bits}`. \ - This error occurred while parsing the vcd file at \ - {cursor:?}"); - println!("Encountered bad signal {name}."); - *signal_error = Some(msg); - continue; - } - } - None => { - let (f, l) = (file!(), line!()); - let msg = format!("\ - Error near {f}:{l}. The bitwidth for signal {name} \ - must be specified for a signal of type {sig_type:?}. \ - This error occurred while parsing the vcd file at \ - {cursor:?}"); - Err(msg)?; - } - }; - - let (f, l )= (file!(), line!()); - let timeline_idx = u32::try_from(vcd.timeline.len()).map_err( - |e| format!("Error near {f}:{l}. Failed to convert from usize to u32."))?; - let timeline_idx = TimelineIdx(timeline_idx); - - u8_timeline_markers.push(timeline_idx); - u8_timeline.append(&mut value); - Ok(()) - } - Signal::Alias {..} => { - let (f, l )= (file!(), line!()); - let msg = format!( - "Error near {f}:{l}, a signal alias should not point to a signal alias.\n\ - This error occurred while parsing vcd file at {cursor:?}"); - Err(msg) - } - }?; - } _ => {} } } diff --git a/src/vcd/parse/scopes.rs b/src/vcd/parse/scopes.rs index cf2e36f..c3a1243 100644 --- a/src/vcd/parse/scopes.rs +++ b/src/vcd/parse/scopes.rs @@ -40,7 +40,8 @@ pub(super) fn parse_var<'a>( let no_bits = match var_type { Sig_Type::Integer | Sig_Type::Parameter | Sig_Type::Real | Sig_Type::Reg | - Sig_Type::Wire | Sig_Type::Tri1 => { + Sig_Type::Wire | Sig_Type::Tri1 | + Sig_Type::Time => { let no_bits = word.parse::().expect(parse_err.as_str()); Some(no_bits) } -- 2.47.1