#*
ABOUT
remove trivial commands from the output of a bash history file.
The original file is not changed.
The purpose of this script is to remove commands like 'ls' or 'cd'
and many others from a bash history file. The script looks for
comments (beginning with # ) that are above the command and does
*not* remove the command if it has a comment associated with it.
It also looks for the timestamp.
This is an example of a simple text file filter script that is
tricky or impossible to do in sed the stream editor, because it
involves multiline recognition and the amalgamation of multiple
comment lines into one comment.
TESTING
use the helper functions in helpers.pars.sh to translate to other
languages and run.
* run with the pep/nom interpreter
>> pep -f eg/bash.hist.trivial.pss ~/.bash_history
* translate to dart and run
-----
pep -f tr/nom.todart.pss eg/bash.hist.trivial.pss > bash.hist.trivial.dart
dart compile exe bash.hist.trivial.dart
cat ~/.bash_history | ./bash.hist.trivial.exe
,,,,
Actually the dart translator requires the 'characters' package in order
to handle unicode grapheme clusters properly, so you need to install
that package with 'dart pub get' etc for this to run.
There are many other nom translators which dont have any dependencies.
NOTES
Sudden thought: there is really no reason to parse all the "records" before
printing them. For the sake of speed and memory use, we can just print
records as we find them. Yes this would be better.
HISTORY
9 april 2025
Adapting this from bash.history.pss just to remove trivial commands.
29 june 2022
Tested with different translators: java, go, python, ruby, c
tcl. All seem to work, but with a small variation on the number
of commands eliminated (about +/- 10)
18 june 2021
Re-examining this to make more useful. Marking trivial commands and
only removing them if they have no attached comment. Also outputting in
standardized order: comment/timestamp/command. removing all commands
of 4 letters or less. Working on this makes me want to have a
shell command syntax: eg shell; which will execute the workspace as
a shell command!! why not? It would make nom a more generally useful
scripting tool. The workspace would be replaced with the output of the
command.
*#
begin {
# the empty recordset trick to simplify the grammar rules
add "recordset*"; push;
}
read;
[\n] {
# just to debug
# lines; print;
clear;
}
whilenot [\n];
# ignore blank lines
"",[:space:] { clear; .reparse }
put;
B"#".!"#" {
[#0123456789] {
clear; add "timestamp*"; push; .reparse
}
clear; add "comment*"; push; .reparse
}
# tag the command as trivial if it is
# for later removal. If there is a comment above it we may keep it anyway
# tag as trivial all commands less than 5 characters
clip; clip; clip; clip;
"" { clear; add "trivial*"; push; .reparse }
clear; get;
B"df ","df",B"du ",B"mv ",B"cp ",B"less ",B"vim ",B"rm ",B"mkdir ",
B"find ",B"locate ",B"cd ","cd",B"ls ",B"open ",B"man ",
B"blog.",B"evince",B"stuff",B"play ",B"chmod ",B"aircrack",
B"mutt",
"ls","pwd","hist","books","bk","ho","hist",
"updatedb","bashrc","vimrc","os","cos","ccos","make" {
clear; add "trivial*"; push; .reparse
}
clear; add "command*"; push;
parse>
# for debugging to watch the parse stack reductions as they happen
# add "line "; lines; add " char "; chars; add ": "; print; clear;
#add "line "; lines; add ": "; print; clear;
#unstack; print; stack; add "\n"; print; clear;
# ----------------
# 2 tokens
pop; pop;
# ignore duplicated timestamps.
"timestamp*timestamp*" {
clear; ++; get; --; put; clear;
add "timestamp*"; push; .reparse
}
# handle multiline comments
"comment*comment*" {
clear; get; add "\n"; ++; get; --; put; clear;
add "comment*"; push; .reparse
}
# dont need because an initial recordset always exists
# actually can just print and delete.
"recordset*record*" {
clear; get; add "\n"; ++; get; --; put; clear;
# debug code
# a+; count; add " record!\n"; print; clear;
add "recordset*"; push; .reparse
}
# this will be compiled differently from r*r*
"recordset*command*" {
clear; get; add "\n"; ++; get; --; put; clear;
add "recordset*"; push; .reparse
}
"recordset*trivial*" {
a+; # count filtered commands
clear; add "recordset*"; push; .reparse
}
(eof) {
# clean up trailing comments etc
"recordset*timestamp*","recordset*comment*" {
clear; add "recordset*record*"; push; push; .reparse
}
}
# 3 tokens
pop;
# remove trivial commands without comments
"recordset*timestamp*trivial*" {
a+; # count filtered commands
clear; add "recordset*"; push; .reparse
}
# ignore duplicated timestamps.
"timestamp*comment*timestamp*" {
clear; ++; get; --; put; clear; ++; ++; get; --; put; --; clear;
add "comment*timestamp*"; push; push; .reparse
}
# amalgamate comments before and after the timestamp
"comment*timestamp*comment*" {
clear;
get; ++; ++; add "\n"; get; --; --; put; clear;
add "comment*timestamp*"; push; push; .reparse
}
"comment*timestamp*command*","comment*timestamp*trivial*" {
clear; get; add "\n"; ++; get; add "\n"; ++; get; --; --; put; clear;
add "record*"; push; .reparse
}
# dont remove trivial commands with comments
"timestamp*comment*command*","timestamp*comment*trivial*" {
clear;
# switch the order to make comment precede timestamp
++; get; add "\n"; --; get; add "\n";
++; ++; get; --; --; put; clear;
add "record*"; push; .reparse
}
"recordset*timestamp*command*" {
clear; ++; get; add "\n"; ++; get; --; put; --; clear;
add "recordset*record*"; push; push; .reparse
}
# resolve commands and trivial command with comments
"recordset*comment*command*","recordset*comment*trivial*" {
clear; ++; get; add "\n"; ++; get; --; put; --; clear;
add "recordset*record*"; push; push; .reparse
}
push; push; push;
(eof) {
pop; pop;
!"recordset*" {
push; push; add "# History file did not parse well!\n"; print; clear;
add "# Parse stack was: "; print; clear; unstack; add "\n"; print;
quit;
}
"recordset*" {
clear; get;
add "\n# History file parsed and filtered by ";
add " pars/eg/bash.hist.trivial.pss \n";
add "# "; count;
add " trivial commands (without preceding comments) were removed.\n";
print;
}
}