Programmer 400 Programmer 400 - 7 months ago 19
Bash Question

Is the bug in the grammar or in the code?

I'm not sure if this grammar is correct for a shell command language that should also be able to execute single-quotes and double-quotes. It seems that non-trivial commands work e.g.

ls -al | sort | wc -l
but the simple one does not work with single-quotes:
echo 'foo bar'
does not work.

%{
#include "shellparser.h"
%}

%option reentrant
%option noyywrap

%x SINGLE_QUOTED
%x DOUBLE_QUOTED

%%

"|" { return PIPE; }

[ \t\r] { }
[\n] { return EOL; }

[a-zA-Z0-9_\.\-]+ { return FILENAME; }

['] { BEGIN(SINGLE_QUOTED); }
<SINGLE_QUOTED>[^']+ { }
<SINGLE_QUOTED>['] { BEGIN(INITIAL); return ARGUMENT; }
<SINGLE_QUOTED><<EOF>> { return -1; }

["] { BEGIN(DOUBLE_QUOTED); }
<DOUBLE_QUOTED>[^"]+ { }
<DOUBLE_QUOTED>["] { BEGIN(INITIAL); return ARGUMENT; }
<DOUBLE_QUOTED><<EOF>> { return -1; }

[^ \t\r\n|'"]+ { return ARGUMENT; }

%%


My code that scans and parses the shell is

params[0] = NULL;
printf("> ");
i=1;
do {
lexCode = yylex(scanner);
text = strdup(yyget_text(scanner));//yyget_text(scanner);
/*printf("lexCode %d command %s inc:%d", lexCode, text, i);*/
ca = text;
if (lexCode != EOL) {
params[i++] = text;
}
Parse(shellParser, lexCode, text);
if (lexCode == EOL) {
dump_argv("Before exec_arguments", i, params);
exec_arguments(i, params);
corpse_collector();
Parse(shellParser, 0, NULL);
i=1;
}
} while (lexCode > 0);

if (-1 == lexCode) {
fprintf(stderr, "The scanner encountered an error.\n");
}


The CMake build file is

cmake_minimum_required(VERSION 3.0)
project(openshell)
find_package(FLEX)
FLEX_TARGET(ShellScanner shellscanner.l shellscanner.c)
set(CMAKE_VERBOSE_MAKEFILE on)
include_directories(/usr/include/readline)
ADD_EXECUTABLE(lemon lemon.c)
add_custom_command(OUTPUT shellparser.c COMMAND lemon -s shellparser.y DEPENDS shellparser.y)
add_executable(openshell shellparser.c ${FLEX_ShellScanner_OUTPUTS} main.c openshell.h errors.c errors.h util.c util.h stack.c stack.h shellscanner.l shellscanner.h)
file(GLOB SOURCES "./*.c")
target_link_libraries(openshell ${READLINE_LIBRARY} ${FLEX_LIBRARIES})
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -Wall -O3 -std=c99")


My project is available on my github. A typical shell session, where only some commands work due to some bug, is as follows.

> ls -al | sort | wc
argument ::= FILENAME .
argumentList ::= argument .
command ::= FILENAME argumentList .
command ::= FILENAME .
command ::= FILENAME .
commandList ::= command .
commandList ::= command PIPE commandList .
commandList ::= command PIPE commandList .
{(null)} {ls} {-al} {|} {sort} {|} {wc}
45 398 2270
3874: child 3881 status 0x0000
in ::= in commandList EOL .
> who
command ::= FILENAME .
commandList ::= command .
{(null)} {who}
dac :0 2016-04-18 05:17 (:0)
dac pts/2 2016-04-18 05:20 (:0)
3874: child 3887 status 0x0000
in ::= in commandList EOL .
> ls -al | awk '{print $1}'
argument ::= FILENAME .
argumentList ::= argument .
command ::= FILENAME argumentList .
argument ::= ARGUMENT .
argumentList ::= argument .
command ::= FILENAME argumentList .
commandList ::= command .
commandList ::= command PIPE commandList .
{(null)} {ls} {-al} {|} {awk} {'}
awk: cmd. line:1: '
awk: cmd. line:1: ^ invalid char ''' in expression
3874: child 3896 status 0x0100
in ::= in commandList EOL .
>


I can observe that both commands get the same bug:
echo 'foo bar'
gets garbled to
{echo} {'}
when we want it to result in
{echo} {foo bar}
so that the shell strips the quotes and executes the command like this

char *cmd[] = { "/usr/bin/echo", "foo bar", 0 };

Answer

The problem is in rule

<SINGLE_QUOTED>[^']+ { }

since it removes all characters inside quotes. All you get as "yytext" is the closing quote (due to rule <SINGLE_QUOTED>['] ...). You have to store somewhere the text and use it when the closing quote is detected. E.g. (very poor coding style, error checking etc. omitted, sorry)

<SINGLE_QUOTED>[^']+    { mystring = strdup(yytext); }

<SINGLE_QUOTED>[']      { BEGIN(INITIAL);
      /*  mystring contains the whole string now,
           yytext contains only "'" */
                          return ARGUMENT; }
Comments