New parser #2

Merged
ThePerfectComputer merged 51 commits from new_parser into main 2022-08-01 21:00:00 +00:00
3 changed files with 187 additions and 153 deletions
Showing only changes of commit 232b026f62 - Show all commits

View file

@ -1,8 +1,5 @@
use std::{fs::File}; use std::{fs::File};
use std::collections::HashMap; use std::collections::HashMap;
use chrono::format::format;
use num::BigInt;
use num::bigint::ToBigInt;
use super::*; use super::*;
@ -22,6 +19,82 @@ use std::num::{IntErrorKind, ParseIntError};
use function_name::named; use function_name::named;
fn binary_str_to_vec_u8(binary_str : &str) -> Result<Vec<u8>, String> {
let mut vec_u8 : Vec<u8> = Vec::new();
let mut binary_str_as_bytes = binary_str.as_bytes();
let mut tail_idx = binary_str_as_bytes.len();
// clamp head if provided binary str is less than 8 long
let mut head_idx =
if tail_idx >= 8
{binary_str_as_bytes.len() - 8}
else
{0};
while {tail_idx > 0} {
let curr_b_val = &binary_str_as_bytes[head_idx..tail_idx];
let val_u8 = base2_str_to_byte(curr_b_val)?;
vec_u8.push(val_u8);
if head_idx < 8 {
head_idx = 0
}
else {
head_idx = head_idx - 8;
}
if tail_idx < 8 {
tail_idx = 0
}
else {
tail_idx = tail_idx - 8;
}
}
Ok(vec_u8)
}
fn base2_str_to_byte(word : &[u8]) -> Result<u8, String> {
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. /// Sometimes, variables can be listed outside of scopes.
/// We call these floating vars. /// We call these floating vars.
pub(super) fn parse_orphaned_vars<'a>( pub(super) fn parse_orphaned_vars<'a>(
@ -118,15 +191,15 @@ fn parse_events<'a>(
"#" => { "#" => {
let value = &word[1..]; let value = &word[1..];
let (f, l )= (file!(), line!()); let (f, l )= (file!(), line!());
let value = BigInt::parse_bytes(value.as_bytes(), 10).ok_or( let mut value = binary_str_to_vec_u8(value).map_err(
format!("Error near {f}:{l}. Failed to parse {value} as BigInt at {cursor:?}").as_str())?; |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 // TODO : u32 helps with less memory, but should ideally likely be
// configurable. // configurable.
let (f, l )= (file!(), line!()); let (f, l )= (file!(), line!());
let start_idx = u32::try_from(vcd.timeline.len()).map_err( let start_idx = u32::try_from(vcd.timeline.len()).map_err(
|e| format!("Error near {f}:{l}. Failed to convert from usize to u32."))?; |e| format!("Error near {f}:{l}. Failed to convert from usize to u32."))?;
vcd.timeline_markers.push(StartIdx(start_idx)); vcd.timeline_markers.push(StartIdx(start_idx));
let (_, mut value) = value.to_bytes_be();
vcd.timeline.append(&mut value); vcd.timeline.append(&mut value);
} }
@ -136,7 +209,7 @@ fn parse_events<'a>(
let hash = &word[1..]; let hash = &word[1..];
let (f, l )= (file!(), line!()); let (f, l )= (file!(), line!());
let Signal_Idx(ref signal_idx) = signal_map.get(hash).ok_or( 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 // account for fact that signal idx could be an alias, so there
// could be one step of indirection // could be one step of indirection
@ -158,7 +231,7 @@ fn parse_events<'a>(
let signal = vcd.all_signals.get_mut(signal_idx).unwrap(); let signal = vcd.all_signals.get_mut(signal_idx).unwrap();
match signal { match signal {
Signal::Data {name, sig_type, ref mut signal_error, num_bits, 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 this is a bad signal, go ahead and skip it
if signal_error.is_some() {continue;} if signal_error.is_some() {continue;}
@ -175,7 +248,7 @@ fn parse_events<'a>(
`{num_bits}`. \ `{num_bits}`. \
This error occurred while parsing the vcd file at \ This error occurred while parsing the vcd file at \
{cursor:?}"); {cursor:?}");
signal_error.insert(msg); *signal_error = Some(msg);
continue; continue;
} }
} }
@ -195,13 +268,8 @@ fn parse_events<'a>(
|e| format!("Error near {f}:{l}. Failed to convert from usize to u32."))?; |e| format!("Error near {f}:{l}. Failed to convert from usize to u32."))?;
let timeline_idx = TimelineIdx(timeline_idx); let timeline_idx = TimelineIdx(timeline_idx);
let (f, l )= (file!(), line!()); u8_timeline_markers.push(timeline_idx);
let start_idx = u32::try_from(timeline.len()).map_err( u8_timeline.push(0u8);
|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(()) Ok(())
} }
Signal::Alias {..} => { Signal::Alias {..} => {
@ -220,7 +288,7 @@ fn parse_events<'a>(
let hash = &word[1..]; let hash = &word[1..];
let (f, l )= (file!(), line!()); let (f, l )= (file!(), line!());
let Signal_Idx(ref signal_idx) = signal_map.get(hash).ok_or( 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 // account for fact that signal idx could be an alias, so there
// could be one step of indirection // could be one step of indirection
@ -242,7 +310,7 @@ fn parse_events<'a>(
let signal = vcd.all_signals.get_mut(signal_idx).unwrap(); let signal = vcd.all_signals.get_mut(signal_idx).unwrap();
match signal { match signal {
Signal::Data {name, sig_type, ref mut signal_error, num_bits, 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 this is a bad signal, go ahead and skip it
if signal_error.is_some() {continue;} if signal_error.is_some() {continue;}
@ -259,7 +327,7 @@ fn parse_events<'a>(
`{num_bits}`. \ `{num_bits}`. \
This error occurred while parsing the vcd file at \ This error occurred while parsing the vcd file at \
{cursor:?}"); {cursor:?}");
signal_error.insert(msg); *signal_error = Some(msg);
continue; continue;
} }
} }
@ -279,13 +347,8 @@ fn parse_events<'a>(
|e| format!("Error near {f}:{l}. Failed to convert from usize to u32."))?; |e| format!("Error near {f}:{l}. Failed to convert from usize to u32."))?;
let timeline_idx = TimelineIdx(timeline_idx); let timeline_idx = TimelineIdx(timeline_idx);
let (f, l )= (file!(), line!()); u8_timeline_markers.push(timeline_idx);
let start_idx = u32::try_from(timeline.len()).map_err( u8_timeline.push(1u8);
|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(()) Ok(())
} }
Signal::Alias {..} => { Signal::Alias {..} => {
@ -299,80 +362,94 @@ fn parse_events<'a>(
} }
// handle the case of an n bit signal whose value must be parse // handle the case of an n bit signal whose value must be parse
// "b" => { "b" => {
// // let binary_value = &word[1..]; let binary_value = &word[1..];
// // let (f, l )= (file!(), line!()); let observed_num_bits = binary_value.len();
// // let value = BigInt::parse_bytes(binary_value.as_bytes(), 2).ok_or( let (f, l )= (file!(), line!());
// // format!("Error near {f}:{l}. Failed to parse {binary_value} as BigInt at {cursor:?}").as_str())?; let mut value = binary_str_to_vec_u8(binary_value).map_err(
// // let (_, mut value) = value.to_bytes_be(); |e| format!("Error near {f}:{l}. Failed to parse {binary_value} as \
at {cursor:?} with error {e}"))?;
// // this word should be the signal alias // this word should be the signal alias
// let (word, cursor) = word_reader.next_word().unwrap(); let (word, cursor) = word_reader.next_word().unwrap();
// // lookup signal idx // lookup signal idx
// let (f, l )= (file!(), line!()); let (f, l )= (file!(), line!());
// let Signal_Idx(ref signal_idx) = signal_map.get(word).ok_or( 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())?; format!("Error near {f}:{l}. Failed to lookup signal {word} at {cursor:?}"))?;
// // account for fact that signal idx could be an alias, so there // account for fact that signal idx could be an alias, so there
// // could be one step of indirection // could be one step of indirection
// let signal_idx = let signal_idx =
// { {
// let signal = vcd.all_signals.get(*signal_idx).unwrap(); let signal = vcd.all_signals.get(*signal_idx).unwrap();
// match signal { match signal {
// Signal::Data {..} => {*signal_idx} Signal::Data {..} => {*signal_idx}
// Signal::Alias {name, signal_alias} => { Signal::Alias {name, signal_alias} => {
// let Signal_Idx(ref signal_idx) = signal_alias; let Signal_Idx(ref signal_idx) = signal_alias;
// signal_idx.clone() signal_idx.clone()
// } }
// } }
// }; };
// // after handling potential indirection, go ahead and update the timeline // after handling potential indirection, go ahead and update the timeline
// // of the signal signal_idx references // of the signal signal_idx references
// let signal = vcd.all_signals.get_mut(signal_idx).unwrap(); let signal = vcd.all_signals.get_mut(signal_idx).unwrap();
// match signal { match signal {
// Signal::Data {name, sig_type, num_bits, 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, ..} => {
// // 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!()); if signal_error.is_some() {continue;}
// 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!()); // Get the observed number of bits for the value parsed earlier
// let start_idx = u32::try_from(timeline.len()).map_err( // and verify that it is not greater than the numbits declared
// |e| format!("Error near {f}:{l}. Failed to convert from usize to u32."))?; // when the signal was declared.
// let start_idx = StartIdx(start_idx); // Also account for the error case of a bitwidth of `None`
// let pair = (timeline_idx, start_idx); match num_bits {
// // timeline_markers.push(pair); Some(ref num_bits) => {
// // timeline.append(&mut [0u8, 1u8, 2u8]); if *num_bits > observed_num_bits {
// timeline.push(0u8); let (f, l) = (file!(), line!());
// timeline.push(1u8); let msg = format!("\
// timeline.push(2u8); Error near {f}:{l}. The bitwidth for signal {name} \
// Ok(()) of sig_type {sig_type:?} is expected to be `1` not \
// } `{num_bits}`. \
// Signal::Alias {..} => { This error occurred while parsing the vcd file at \
// let (f, l )= (file!(), line!()); {cursor:?}");
// let msg = format!( println!("Encountered bad signal {name}.");
// "Error near {f}:{l}, a signal alias should not point to a signal alias.\n\ *signal_error = Some(msg);
// This error occurred while parsing vcd file at {cursor:?}"); continue;
// Err(msg) }
// } }
// }?; 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<VCD, String> {
// parsing scoped vars. // parsing scoped vars.
let (f, l ) = (file!(), line!()); let (f, l ) = (file!(), line!());
let msg = format!("Error near {f}:{l}. Current word empty!"); 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 { match word {
"$scope" => { "$scope" => {
parse_scopes(&mut word_gen, None, &mut vcd, &mut signal_map) parse_scopes(&mut word_gen, None, &mut vcd, &mut signal_map)

View file

@ -86,8 +86,10 @@ pub(super) fn parse_var<'a>(
signal_error: None, signal_error: None,
num_bits: no_bits, num_bits: no_bits,
self_idx: signal_idx, self_idx: signal_idx,
timeline: vec![], u8_timeline: vec![],
timeline_markers: vec![], u8_timeline_markers: vec![],
string_timeline: vec![],
string_timeline_markers: vec![],
scope_parent: parent_scope_idx }; scope_parent: parent_scope_idx };
(signal, signal_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 (word, cursor) = word_reader.next_word().ok_or(&err)?;
let ParseResult{matched, residual} = tag(word, "$"); let ParseResult{matched, residual} = tag(word, "$");
match matched { match matched {
// we hope that this word stars with a `$` // we hope that this word starts with a `$`
"$" => { "$" => {
match residual { match residual {
"scope" => { "scope" => {

View file

@ -1,7 +1,4 @@
use core::time;
use std::collections::{BTreeMap, HashMap};
use chrono::prelude::*; use chrono::prelude::*;
use num::BigInt;
#[derive(Debug)] #[derive(Debug)]
pub(super) struct Version(pub String); pub(super) struct Version(pub String);
@ -30,46 +27,25 @@ pub struct StartIdx(pub(super) u32);
#[derive(Debug)] #[derive(Debug)]
pub(super) enum Sig_Type {Integer, Parameter, Real, Reg, Str, Wire, Tri1, Time} 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<u8>;
#[derive(Debug)]
pub(super) enum Sig_Value {
Numeric(u64),
NonNumeric(String)}
#[derive(Debug)] #[derive(Debug)]
pub(super) enum Signal{ pub(super) enum Signal{
Data{ Data{
name : String, name : String,
sig_type : Sig_Type, sig_type : Sig_Type,
// I've seen a 0 bit signal parameter in a xilinx // 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 // I consider this to be bad behavior. We capture such
// errors in the following type. // errors in the following type.
signal_error : Option<String>, signal_error : Option<String>,
num_bits : Option<usize>, num_bits : Option<usize>,
// TODO : may be able to remove self_idx // TODO : may be able to remove self_idx
self_idx : Signal_Idx, self_idx : Signal_Idx,
timeline : Vec<u8>, // we could encounter a mix of pure values and strings
timeline_markers : Vec<(TimelineIdx)>, // for the same signal timeline
u8_timeline : Vec<u8>,
u8_timeline_markers : Vec<(TimelineIdx)>,
string_timeline : Vec<String>,
string_timeline_markers : Vec<(TimelineIdx)>,
scope_parent : Scope_Idx}, scope_parent : Scope_Idx},
Alias{ Alias{
name : String, name : String,
@ -81,7 +57,6 @@ pub(super) struct Scope {
pub(super) name : String, pub(super) name : String,
pub(super) parent_idx : Option<Scope_Idx>, pub(super) parent_idx : Option<Scope_Idx>,
// TODO : may be able to remove self_idx
pub(super) self_idx : Scope_Idx, pub(super) self_idx : Scope_Idx,
pub(super) child_signals : Vec<Signal_Idx>, pub(super) child_signals : Vec<Signal_Idx>,
@ -127,11 +102,9 @@ impl VCD {
println!(); println!();
for scope_idx in &root_scope.child_scopes { 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); self.print_scope_tree(*scope_idx, depth+1);
} }
// let root = vcd.all_scopes;
} }
pub fn print_scopes(&self) { 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) { pub fn print_longest_signal(&self) {
let mut idx = 0usize; let mut idx = 0usize;
let mut max_len = 0usize; let mut max_len = 0usize;
@ -171,10 +126,10 @@ impl VCD {
sig_type, sig_type,
num_bits, num_bits,
self_idx, self_idx,
timeline, u8_timeline,
.. } => { .. } => {
if timeline.len() > max_len { if u8_timeline.len() > max_len {
max_len = timeline.len(); max_len = u8_timeline.len();
let Signal_Idx(idx_usize) = self_idx; let Signal_Idx(idx_usize) = self_idx;
idx = *idx_usize; idx = *idx_usize;
signal_name = name.clone(); signal_name = name.clone();