is_spammer.bash

BASH Shell 编程 经典教程 《高级SHELL脚本编程》中文版

        done
        eval $2=\( \$\{_st_reply\[@\]\} \)
    fi
    return 0
}

# The long forms, a.k.a., the parse it yourself versions

# RFC 2782   Service lookups
# dig +noall +nofail +answer _ldap._tcp.openldap.org -t srv
# _<service>._<protocol>.<domain_name>
# _ldap._tcp.openldap.org. 3600   IN      SRV     0 0 389 ldap.openldap.org.
# domain TTL Class SRV Priority Weight Port Target

# Forward lookup :: Name -> poor man's zone transfer
# long_fwd <domain_name> <array_name>
long_fwd() {
    local -a _lf_reply
    local -i _lf_rc
    local -i _lf_cnt
    IFS=${NO_WSP}
echo -n ':'
# echo 'lfwd: '${1}
    _lf_reply=( $(
        dig +noall +nofail +answer +authority +additional \
            ${1} -t soa ${1} -t mx ${1} -t any 2>/dev/null) )
    _lf_rc=$?
    if [ ${_lf_rc} -ne 0 ]
    then
        _trace_log[${#_trace_log[@]}]='# # # Zone lookup error '${_lf_rc}' on '${1}' # # #'
# [ ${_lf_rc} -ne 9 ] && pend_drop
        return ${_lf_rc}
    else
        # Some versions of 'dig' return warnings on stdout.
        _lf_cnt=${#_lf_reply[@]}
        for (( _lf = 0 ; _lf < ${_lf_cnt} ; _lf++ ))
        do
            [ 'x'${_lf_reply[${_lf}]:0:2} == 'x;;' ] &&
                unset _lf_reply[${_lf}]
        done
        eval $2=\( \$\{_lf_reply\[@\]\} \)
    fi
    return 0
}
#   The reverse lookup domain name corresponding to the IPv6 address:
#       4321:0:1:2:3:4:567:89ab
#   would be (nibble, I.E: Hexdigit) reversed:
#   b.a.9.8.7.6.5.0.4.0.0.0.3.0.0.0.2.0.0.0.1.0.0.0.0.0.0.0.1.2.3.4.IP6.ARPA.

# Reverse lookup :: Address -> poor man's delegation chain
# long_rev &lt;rev_ip_address&gt; &lt;array_name&gt;
long_rev() {
    local -a _lr_reply
    local -i _lr_rc
    local -i _lr_cnt
    local _lr_dns
    _lr_dns=${1}'.in-addr.arpa.'
    IFS=${NO_WSP}
echo -n ':'
# echo 'lrev: '${1}
    _lr_reply=( $(
         dig +noall +nofail +answer +authority +additional \
             ${_lr_dns} -t soa ${_lr_dns} -t any 2>/dev/null) )
    _lr_rc=$?
    if [ ${_lr_rc} -ne 0 ]
    then
        _trace_log[${#_trace_log[@]}]='# # # Delegation lookup error '${_lr_rc}' on '${1}' # # #'
# [ ${_lr_rc} -ne 9 ] && pend_drop
        return ${_lr_rc}
    else
        # Some versions of 'dig' return warnings on stdout.
        _lr_cnt=${#_lr_reply[@]}
        for (( _lr = 0 ; _lr < ${_lr_cnt} ; _lr++ ))
        do
            [ 'x'${_lr_reply[${_lr}]:0:2} == 'x;;' ] &&
                unset _lr_reply[${_lr}]
        done
        eval $2=\( \$\{_lr_reply\[@\]\} \)
    fi
    return 0
}

# # # Application specific functions # # #

# Mung a possible name; suppresses root and TLDs.
# name_fixup &lt;string&gt;
name_fixup(){
    local -a _nf_tmp
    local -i _nf_end
    local _nf_str
    local IFS
    _nf_str=$(to_lower ${1})
    _nf_str=$(to_dot ${_nf_str})
    _nf_end=${#_nf_str}-1
    [ ${_nf_str:${_nf_end}} != '.' ] &&
        _nf_str=${_nf_str}'.'
    IFS=${ADR_IFS}
    _nf_tmp=( ${_nf_str} )
    IFS=${WSP_IFS}
    _nf_end=${#_nf_tmp[@]}
    case ${_nf_end} in
    0) # No dots, only dots.
        echo
        return 1
    ;;
    1) # Only a TLD.
        echo
        return 1
    ;;
    2) # Maybe okay.
       echo ${_nf_str}
       return 0
       # Needs a lookup table?
       if [ ${#_nf_tmp[1]} -eq 2 ]
       then # Country coded TLD.
           echo
           return 1
       else
           echo ${_nf_str}
           return 0
       fi
    ;;
    esac
    echo ${_nf_str}
    return 0
}

# Grope and mung original input(s).
split_input() {
    [ ${#uc_name[@]} -gt 0 ] || return 0
    local -i _si_cnt
    local -i _si_len
    local _si_str
    unique_lines uc_name uc_name
    _si_cnt=${#uc_name[@]}
    for (( _si = 0 ; _si < _si_cnt ; _si++ ))
    do
        _si_str=${uc_name[$_si]}
        if is_address ${_si_str}
        then
            uc_address[${#uc_address[@]}]=${_si_str}
            unset uc_name[$_si]
        else
            if ! uc_name[$_si]=$(name_fixup ${_si_str})
            then
                unset ucname[$_si]
            fi
        fi
    done
    uc_name=( ${uc_name[@]} )
    _si_cnt=${#uc_name[@]}
    _trace_log[${#_trace_log[@]}]='# # # Input '${_si_cnt}' unchecked name input(s). # # #'
    _si_cnt=${#uc_address[@]}
    _trace_log[${#_trace_log[@]}]='# # # Input '${_si_cnt}' unchecked address input(s). # # #'
    return 0
}

# # # Discovery functions -- recursively interlocked by external data # # #
# # # The leading 'if list is empty; return 0' in each is required. # # #

# Recursion limiter
# limit_chk() &lt;next_level&gt;
limit_chk() {
    local -i _lc_lmt
    # Check indirection limit.
    if [ ${indirect} -eq 0 ] || [ $# -eq 0 ]
    then
        # The 'do-forever' choice
        echo 1                 # Any value will do.
        return 0               # OK to continue.
    else
        # Limiting is in effect.
        if [ ${indirect} -lt ${1} ]
        then
            echo ${1}          # Whatever.
            return 1           # Stop here.
        else
            _lc_lmt=${1}+1     # Bump the given limit.
            echo ${_lc_lmt}    # Echo it.
            return 0           # OK to continue.
        fi
    fi
}

# For each name in uc_name:
#     Move name to chk_name.
#     Add addresses to uc_address.
#     Pend expand_input_address.
#     Repeat until nothing new found.
# expand_input_name &lt;indirection_limit&gt;
expand_input_name() {
    [ ${#uc_name[@]} -gt 0 ] || return 0
    local -a _ein_addr
    local -a _ein_new
    local -i _ucn_cnt
    local -i _ein_cnt
    local _ein_tst
    _ucn_cnt=${#uc_name[@]}

    if  ! _ein_cnt=$(limit_chk ${1})
    then
        return 0
    fi

    for (( _ein = 0 ; _ein < _ucn_cnt ; _ein++ ))
    do
        if short_fwd ${uc_name[${_ein}]} _ein_new
        then
            for (( _ein_cnt = 0 ; _ein_cnt < ${#_ein_new[@]}; _ein_cnt++ ))
            do
                _ein_tst=${_ein_new[${_ein_cnt}]}
                if is_address ${_ein_tst}
                then
                    _ein_addr[${#_ein_addr[@]}]=${_ein_tst}
                fi
           done
        fi
    done
    unique_lines _ein_addr _ein_addr     # Scrub duplicates.
    edit_exact chk_address _ein_addr     # Scrub pending detail.
    edit_exact known_address _ein_addr   # Scrub already detailed.
    if [ ${#_ein_addr[@]} -gt 0 ]        # Anything new?
    then
        uc_address=( ${uc_address[@]} ${_ein_addr[@]} )
        pend_func expand_input_address ${1}
        _trace_log[${#_trace_log[@]}]='# # # Added '${#_ein_addr[@]}' unchecked address input(s). # # #'
    fi
    edit_exact chk_name uc_name          # Scrub pending detail.
    edit_exact known_name uc_name        # Scrub already detailed.
    if [ ${#uc_name[@]} -gt 0 ]
    then
        chk_name=( ${chk_name[@]} ${uc_name[@]}  )
        pend_func detail_each_name ${1}
    fi
    unset uc_name[@]
    return 0
}

# For each address in uc_address:
#     Move address to chk_address.
#     Add names to uc_name.
#     Pend expand_input_name.
#     Repeat until nothing new found.
# expand_input_address &lt;indirection_limit&gt;
expand_input_address() {
    [ ${#uc_address[@]} -gt 0 ] || return 0
    local -a _eia_addr
    local -a _eia_name
    local -a _eia_new
    local -i _uca_cnt
    local -i _eia_cnt
    local _eia_tst
    unique_lines uc_address _eia_addr
    unset uc_address[@]
    edit_exact been_there_addr _eia_addr
    _uca_cnt=${#_eia_addr[@]}
    [ ${_uca_cnt} -gt 0 ] &&
        been_there_addr=( ${been_there_addr[@]} ${_eia_addr[@]} )

    for (( _eia = 0 ; _eia < _uca_cnt ; _eia++ ))
    do
            if short_rev ${_eia_addr[${_eia}]} _eia_new
            then
                for (( _eia_cnt = 0 ; _eia_cnt < ${#_eia_new[@]} ; _eia_cnt++ ))
                do
                    _eia_tst=${_eia_new[${_eia_cnt}]}
                    if _eia_tst=$(name_fixup ${_eia_tst})
                    then
                        _eia_name[${#_eia_name[@]}]=${_eia_tst}
                    fi
                done
            fi
    done
    unique_lines _eia_name _eia_name     # Scrub duplicates.
    edit_exact chk_name _eia_name        # Scrub pending detail.
    edit_exact known_name _eia_name      # Scrub already detailed.
    if [ ${#_eia_name[@]} -gt 0 ]        # Anything new?
    then
        uc_name=( ${uc_name[@]} ${_eia_name[@]} )
        pend_func expand_input_name ${1}
        _trace_log[${#_trace_log[@]}]='# # # Added '${#_eia_name[@]}' unchecked name input(s). # # #'
    fi
    edit_exact chk_address _eia_addr     # Scrub pending detail.
    edit_exact known_address _eia_addr   # Scrub already detailed.
    if [ ${#_eia_addr[@]} -gt 0 ]        # Anything new?
    then
        chk_address=( ${chk_address[@]} ${_eia_addr[@]} )
        pend_func detail_each_address ${1}
    fi
    return 0
}

# The parse-it-yourself zone reply.
# The input is the chk_name list.
# detail_each_name &lt;indirection_limit&gt;
detail_each_name() {
    [ ${#chk_name[@]} -gt 0 ] || return 0
    local -a _den_chk       # Names to check
    local -a _den_name      # Names found here
    local -a _den_address   # Addresses found here
    local -a _den_pair      # Pairs found here
    local -a _den_rev       # Reverse pairs found here
    local -a _den_tmp       # Line being parsed
    local -a _den_auth      # SOA contact being parsed
    local -a _den_new       # The zone reply
    local -a _den_pc        # Parent-Child gets big fast
    local -a _den_ref       # So does reference chain
    local -a _den_nr        # Name-Resource can be big
    local -a _den_na        # Name-Address
    local -a _den_ns        # Name-Service
    local -a _den_achn      # Chain of Authority
    local -i _den_cnt       # Count of names to detail
    local -i _den_lmt       # Indirection limit
    local _den_who          # Named being processed
    local _den_rec          # Record type being processed
    local _den_cont         # Contact domain
    local _den_str          # Fixed up name string
    local _den_str2         # Fixed up reverse
    local IFS=${WSP_IFS}

    # Local, unique copy of names to check
    unique_lines chk_name _den_chk
    unset chk_name[@]       # Done with globals.

    # Less any names already known
    edit_exact known_name _den_chk
    _den_cnt=${#_den_chk[@]}

    # If anything left, add to known_name.
    [ ${_den_cnt} -gt 0 ] &&
        known_name=( ${known_name[@]} ${_den_chk[@]} )

    # for the list of (previously) unknown names . . .
    for (( _den = 0 ; _den < _den_cnt ; _den++ ))
    do
        _den_who=${_den_chk[${_den}]}
        if long_fwd ${_den_who} _den_new
        then
            unique_lines _den_new _den_new
            if [ ${#_den_new[@]} -eq 0 ]
            then
                _den_pair[${#_den_pair[@]}]='0.0.0.0 '${_den_who}
            fi

            # Parse each line in the reply.
            for (( _line = 0 ; _line < ${#_den_new[@]} ; _line++ ))
            do
                IFS=${NO_WSP}$'\x09'$'\x20'
                _den_tmp=( ${_den_new[${_line}]} )
                IFS=${WSP_IFS}
                # If usable record and not a warning message . . .
                if [ ${#_den_tmp[@]} -gt 4 ] && [ 'x'${_den_tmp[0]} != 'x;;' ]
                then
                    _den_rec=${_den_tmp[3]}
                    _den_nr[${#_den_nr[@]}]=${_den_who}' '${_den_rec}
                    # Begin at RFC1033 (+++)
                    case ${_den_rec} in

                         #&lt;name&gt;  [&lt;ttl&gt;]  [&lt;class&gt;]  SOA  &lt;origin&gt;  &lt;person&gt;
                    SOA) # Start Of Authority
                        if _den_str=$(name_fixup ${_den_tmp[0]})
                        then
                            _den_name[${#_den_name[@]}]=${_den_str}
                            _den_achn[${#_den_achn[@]}]=${_den_who}' '${_den_str}' SOA'
                            # SOA origin -- domain name of master zone record
                            if _den_str2=$(name_fixup ${_den_tmp[4]})
                            then
                                _den_name[${#_den_name[@]}]=${_den_str2}
                                _den_achn[${#_den_achn[@]}]=${_den_who}' '${_den_str2}' SOA.O'
                            fi
                            # Responsible party e-mail address (possibly bogus).
                            # Possibility of [e-mail] ignored.
                            set -f
                            if _den_str2=$(name_fixup ${_den_tmp[5]})
                            then
                                IFS=${ADR_IFS}
                                _den_auth=( ${_den_str2} )
                                IFS=${WSP_IFS}
                                if [ ${#_den_auth[@]} -gt 2 ]
                                then
                                     _den_cont=${_den_auth[1]}
                                     for (( _auth = 2 ; _auth < ${#_den_auth[@]} ; _auth++ ))
                                     do
                                       _den_cont=${_den_cont}'.'${_den_auth[${_auth}]}
                                     done
                                     _den_name[${#_den_name[@]}]=${_den_cont}'.'
                                     _den_achn[${#_den_achn[@]}]=${_den_who}' '${_den_cont}'. SOA.C'
                                fi
                            fi
                            set +f
                        fi
                    ;;


                    A) # IP(v4) Address Record
                        if _den_str=$(name_fixup ${_den_tmp[0]})
                        then
                            _den_name[${#_den_name[@]}]=${_den_str}
                            _den_pair[${#_den_pair[@]}]=${_den_tmp[4]}' '${_den_str}
                            _den_na[${#_den_na[@]}]=${_den_str}' '${_den_tmp[4]}
                            _den_ref[${#_den_ref[@]}]=${_den_who}' '${_den_str}' A'
                        else
                            _den_pair[${#_den_pair[@]}]=${_den_tmp[4]}' unknown.domain'
                            _den_na[${#_den_na[@]}]='unknown.domain '${_den_tmp[4]}
                            _den_ref[${#_den_ref[@]}]=${_den_who}' unknown.domain A'
                        fi
                        _den_address[${#_den_address[@]}]=${_den_tmp[4]}
                        _den_pc[${#_den_pc[@]}]=${_den_who}' '${_den_tmp[4]}
                    ;;

                    NS) # Name Server Record
                        # Domain name being serviced (may be other than current)
                        if _den_str=$(name_fixup ${_den_tmp[0]})
                        then
                            _den_name[${#_den_name[@]}]=${_den_str}
                            _den_ref[${#_den_ref[@]}]=${_den_who}' '${_den_str}' NS'

                            # Domain name of service provider
                            if _den_str2=$(name_fixup ${_den_tmp[4]})
                            then
                                _den_name[${#_den_name[@]}]=${_den_str2}
                                _den_ref[${#_den_ref[@]}]=${_den_who}' '${_den_str2}' NSH'
                                _den_ns[${#_den_ns[@]}]=${_den_str2}' NS'
                                _den_pc[${#_den_pc[@]}]=${_den_str}' '${_den_str2}
                            fi
                        fi
                    ;;

                    MX) # Mail Server Record
                        # Domain name being serviced (wildcards not handled here)
                        if _den_str=$(name_fixup ${_den_tmp[0]})
                        then
                            _den_name[${#_den_name[@]}]=${_den_str}
                            _den_ref[${#_den_ref[@]}]=${_den_who}' '${_den_str}' MX'
                        fi