reading a string within a string

[white scorpion]

Hi All,

i'm trying to figure out a way to read a string within the string and then fill the new buffer with the characters behind the string.

explanation:

Code Select Expand


string1 db "this is the main string which <title> this is the title </title> needs to be used.
",0
buffer db 80 dup (?)


well, the thing i'm trying to achieve is getting the text between the <title> blocks into the buffer,
so that buffer = "this is the title"


i've tried it using the following code:

Code Select Expand


lea eax,string1
lea ebx,buffer
run:
cmp byte ptr [eax],'<'
inc eax
jne run
cmp byte ptr [eax],'T'
inc eax
jne run
cmp byte ptr [eax],'I'
inc eax
jne run
cmp byte ptr [eax],'T'
inc eax
jne run
cmp byte ptr [eax],'L'
inc eax
jne run
cmp byte ptr [eax],'E'
inc eax
jne run
cmp byte ptr [eax],'>'
inc eax
jne run
run2:
mov ecx,[eax]
mov [ebx],ecx
inc eax
cmp byte ptr [eax],'<'
jne run2
mov ecx,0
mov [eax],ecx


the above code was only meant for the first part, copying everything from after <title> to the buffer, but it won't start copying :(


any ideas would be highly appreciated ;)

[donkey]

Well, you have to scan ahead until you reach the point in the string you want, you can use an instr type function for that. I think there is one in MASM32. Once you know the point to start and the length to copy you can use lstrcpyn to copy a specific number of bytes or just rep movsb them. Here is an instr function in GoAsm syntax from my strings library...

Code Select Expand

lszInstr FRAME pString,pFind,StartChar
uses esi,edi,ebx
LOCAL len :D

invoke lszLen,[pFind]
push eax
invoke lszLen,[pString]
mov ebx,eax
pop edx
cmp edx,eax
jle >
mov eax,-1
ret
:

mov eax,[StartChar]
or eax,eax
jns >
mov eax,-1
ret
:

sub ebx,edx
inc edx
mov [len],ebx
mov ebx,[StartChar]
:
mov ecx,edx
mov eax,[pString]
lea edi,[eax+ebx]
mov esi,[pFind]
repe cmpsb
or ecx,ecx
jz >E1
inc ebx
cmp ebx,[len]
jbe <

xor eax,eax
dec eax
ret

E1:
mov eax,ebx
RET
ENDF

Code Select Expand

lszInstr:
Finds an instance of one string in another beginning at a supplied point
Parameters:
pString = Pointer to a null terminated string to search
pFind = Pointer to a null terminated string to find
StartChar = 0 based index of the character at which to begin the search
Returns the 0 based index where the string was found, -1 if not found

[white scorpion]

hi, thanks for replying,

i already found the macro @instr for masm32, but i couldn't figure out what i could do with the return value..
i will study this function and if i can't get it to work then i'm a afraid i will indeed have to do it manually by movsb and cmpsb.

thanks for your help ;)

[donkey]

Hi,

As far as I know @instr is a compile time only macro, I assumed you were looking for something run-time. I think there is an szInstr or something function in MASM32 that is a runtime function.

[white scorpion]

well, i will show you what i'm trying to do:

Code Select Expand



.386
.model flat,stdcall
option casemap:none


;the include files needed for our program
;------------------------------------------------------
include \masm32\include\windows.inc
include \masm32\include\masm32.inc
include \masm32\include\kernel32.inc
include \masm32\include\user32.inc
include \masm32\include\wsock32.inc

includelib \masm32\lib\masm32.lib
includelib \masm32\lib\kernel32.lib
includelib \masm32\lib\user32.lib
includelib \masm32\lib\wsock32.lib

;the data section
;@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
.data
wsadata WSADATA<>
sa sockaddr_in <>
err     db "Error, closing down.",0
wsaerr  db "unable to start wsa.",0
host    db "http://www.whatismyip.com",0
sendms  db "GET / HTTP/1.1",13,10,
           "Host: www.whatismyip.com",13,10,
           "User-Agent: Mozilla/5.0 (Windows; U; Windows NT 5.1; rv:1.7.3) Gecko/20041001 Firefox/0.10.1",13,10,
           "Accept: text/xml,application/xml,application/xhtml+xml,text/html;q=0.9,text/plain;q=0.8,image/png,*/*;q=0.5",13,10,
           "Accept-Language: en-us,en;q=0.5",13,10,
           "Accept-Encoding: gzip,deflate",13,10,
           "Accept-Charset: ISO-8859-1,utf-8;q=0.7,*;q=0.7",13,10,13,10,0
recvbuf db 3000 dup (?)

;the uninitialized data section
;@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
.data?

sock    dd ?

;the code section
;@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
.code
start:

invoke WSAStartup,101h,addr wsadata
.if eax!=NULL
invoke StdOut,addr wsaerr
invoke ExitProcess,1
.endif
invoke socket,AF_INET,SOCK_STREAM,0
.if eax==INVALID_SOCKET
invoke StdOut,addr err
invoke WSACleanup
invoke ExitProcess,1
.endif
mov sock,eax

mov sa.sin_family,AF_INET
invoke htons,80
mov sa.sin_port,ax
invoke gethostbyname,addr host
mov eax,[eax+12]
mov eax,[eax]
mov eax,[eax]
mov sa.sin_addr,eax

invoke connect,sock,addr sa,sizeof sa
.if eax==SOCKET_ERROR
invoke StdOut,addr err
invoke WSACleanup
invoke ExitProcess,1
.endif

invoke send,sock,addr sendms,sizeof sendms,0
.if eax==0
invoke StdOut,addr err
invoke WSACleanup
invoke ExitProcess,1
.endif

invoke recv,sock,addr recvbuf,sizeof recvbuf,0
.if eax==SOCKET_ERROR or 0
invoke StdOut,addr err
invoke WSACleanup
invoke ExitProcess,1
.endif

invoke StdOut,addr recvbuf

invoke WSACleanup
invoke ExitProcess,0
end start

as you can see this program makes a connection to www.whatismyip.com, well since the ip is given in the title i want to extract the ip from the recvbuf.

i wrote this program since i needed a program to learn about sockets in asm, but while writing this program you can see i bumped up to the next problem....

[MichaelW]

Quick and dirty. See macros.asm to unravel the macros.

Code Select Expand


; ««««««««««««««««««««««««««««««««««««««««««««««««««««««««««

    .486                       ; create 32 bit code
    .model flat, stdcall       ; 32 bit memory model
    option casemap :none       ; case sensitive

    include \masm32\include\windows.inc
    include \masm32\include\masm32.inc
    include \masm32\include\kernel32.inc

    includelib \masm32\lib\masm32.lib
    includelib \masm32\lib\kernel32.lib

    include \masm32\macros\macros.asm

; ««««««««««««««««««««««««««««««««««««««««««««««««««««««««««
    .data
      string1 db "this is the main string which <title> this is the title </title> needs to be used.",0
      buffer  db 80 dup(0)
    .code
; ««««««««««««««««««««««««««««««««««««««««««««««««««««««««««
start:
; ««««««««««««««««««««««««««««««««««««««««««««««««««««««««««
    ; Char position for istring is a 1-based index.
    mov   ebx, istring(1, ADDR string1, chr$("<title>"))
    mov   edi, istring(ebx, ADDR string1, chr$("</title>"))
    ; Overwrite first char of 2nd search string with null.
    mov   BYTE PTR [string1+edi-1], 0
    add   ebx, OFFSET string1 + @SizeStr(<<title>>) - 1
    mov   eax, cat$(ADDR buffer, ebx)
    ; Restore first char of 2nd search string.
    mov   BYTE PTR [string1+edi-1], '<'

    print ADDR buffer
    mov   eax, input(13,10,13,10,"Press enter to exit...")
    exit
; ««««««««««««««««««««««««««««««««««««««««««««««««««««««««««

end start


[white scorpion]

Thanks for your reply..

with the following code i still get some errors, but at least now i know what to look for :D

Code Select Expand



.386
.model flat,stdcall
option casemap:none


;the include files needed for our program
;------------------------------------------------------
include \masm32\include\windows.inc
include \masm32\include\masm32.inc
include \masm32\include\kernel32.inc
include \masm32\include\user32.inc
include \masm32\include\wsock32.inc

includelib \masm32\lib\masm32.lib
includelib \masm32\lib\kernel32.lib
includelib \masm32\lib\user32.lib
includelib \masm32\lib\wsock32.lib

;the data section
;@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
.data
wsadata WSADATA<>
sa sockaddr_in <>
err     db "Error, closing down.",0
wsaerr  db "unable to start wsa.",0
host    db "http://www.whatismyip.com",0
sendms  db "GET / HTTP/1.1",13,10,
           "Host: www.whatismyip.com",13,10,
           "User-Agent: Mozilla/5.0 (Windows; U; Windows NT 5.1; rv:1.7.3) Gecko/20041001 Firefox/0.10.1",13,10,
           "Accept: text/xml,application/xml,application/xhtml+xml,text/html;q=0.9,text/plain;q=0.8,image/png,*/*;q=0.5",13,10,
           "Accept-Language: en-us,en;q=0.5",13,10,
           "Accept-Encoding: gzip,deflate",13,10,
           "Accept-Charset: ISO-8859-1,utf-8;q=0.7,*;q=0.7",13,10,13,10,0
recvbuf db 3000 dup (?)
buffer  db 400 dup (?)

;the uninitialized data section
;@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
.data?

sock    dd ?

;the code section
;@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
.code
start:

invoke WSAStartup,101h,addr wsadata
.if eax!=NULL
invoke StdOut,addr wsaerr
invoke ExitProcess,1
.endif
invoke socket,AF_INET,SOCK_STREAM,0
.if eax==INVALID_SOCKET
invoke StdOut,addr err
invoke WSACleanup
invoke ExitProcess,1
.endif
mov sock,eax

mov sa.sin_family,AF_INET
invoke htons,80
mov sa.sin_port,ax
invoke gethostbyname,addr host
mov eax,[eax+12]
mov eax,[eax]
mov eax,[eax]
mov sa.sin_addr,eax

invoke connect,sock,addr sa,sizeof sa
.if eax==SOCKET_ERROR
invoke StdOut,addr err
invoke WSACleanup
invoke ExitProcess,1
.endif

invoke send,sock,addr sendms,sizeof sendms,0
.if eax==0
invoke StdOut,addr err
invoke WSACleanup
invoke ExitProcess,1
.endif

invoke recv,sock,addr recvbuf,sizeof recvbuf,0
.if eax==SOCKET_ERROR or 0
invoke StdOut,addr err
invoke WSACleanup
invoke ExitProcess,1
.endif

; Char position for istring is a 1-based index.
    mov   ebx, istring(1, addr recvbuf, chr$("<TITLE>"))
    mov   edi, istring(ebx, addr recvbuf, chr$("</TITLE>"))
    ; Overwrite first char of 2nd search string with null.
    mov   BYTE PTR [recvbuf+edi-1], 0
    add   ebx, OFFSET recvbuf + @SizeStr(<<TITLE>>) - 1
    mov   eax, cat$(addr buffer, ebx)
    ; Restore first char of 2nd search string.
    mov   BYTE PTR [recvbuf+edi-1], '<'
invoke StdOut,addr buffer

invoke WSACleanup
invoke ExitProcess,0
end start