如何删除字符串中的所有标点符号和空格？

Question

我有这样的输入：

This is, ,,, *&% a ::; demo + String. +Need to**@!/// format:::::!!! this.`

需要输出：

ThisisademoStringNeedtoformatthis

我必须不使用使用str_trim。

编辑：我正在编写一个加密程序。在加密之前，我必须从字符串中删除所有标点符号并将所有小写字母转换为大写字母。

我添加了代码。在将其变为大写之前，我需要删除空格或任何标点符号。到目前为止，除了我们不允许使用的 str_trim 之外，我还没有在我的书中找到任何可以帮助解决这个问题的东西。

INCLUDE Irvine32.inc

.data
source  byte  "This is the source string",0

.code
main proc


mov  esi,0              ; index register
mov  ecx,SIZEOF source  ; loop counter
L1:
mov  al,source[esi]     ; get a character from source
and  source[esi], 11011111b     ; convert lower case to upper case
inc  esi                ; move to next character
loop L1                 ; repeat for entire string

mov edx, OFFSET source
call WriteString

exit
main endp
end main

Answer 1

您已经在尝试从小写更改为大写，所以，我会帮助您删除标点符号。接下来的代码使用我的建议：将大写字母移动到辅助字符串中，忽略标点符号。我用的是 EMU8086 编译器 :

.stack 100h
.data
source  db  "STRING, WITH. PUNCTUATION : AND * SPACES!$"
aux     db  "                                          "
.code
  mov  ax, @data
  mov  ds, ax

;REMOVE EVERYTHING BUT UPPERCASE LETTERS.

  mov  si, offset source   ; POINT TO STRING.
  mov  di, offset aux      ; POINT TO AUXILIARY.
L1:
  mov  al, [ si ]          ; get character from source
;CHECK IF END STRING ($).
  cmp  al, '$'
  je   finale
;CHECK IF CHAR IS UPPERCASE LETTER.
  cmp  al, 65
  jb   is_not_a_letter    ; CHAR IS LOWER THAN 'A'.
  cmp  al, 90
  ja   is_not_a_letter    ; CHAR IS HIGHER THAN 'Z'.
;COPY LETTER TO AUX STRING.
  mov  [ di ], al
  inc  di                ; POSITION FOR NEXT CHARACTER.
is_not_a_letter:
  inc  si                ; move to next character
  jmp  L1

finale:
  mov  [ di ], al        ; '$', NECESSARY TO PRINT.

;PRINT STRING.  
  mov  dx, OFFSET aux
  mov  ah, 9
  int  21h

;END PROGRAM.
  mov  ax, 4c00h
  int  21h

我以 '$' 结束字符串，因为我用 int 21h.

打印字符串

如您所见，我既没有使用 CX 也没有使用 LOOP 指令。我所做的是重复直到找到“$”。您可以这样做，直到找到 0。

Answer 2

这是我删除所有标点符号并将其转为大写后的代码。

INCLUDE Irvine32.inc

.data
source  byte  "STriNG, @# WITH.[][][ lalalala PUncTuATION : AND * SpaceS!", 0
target  byte  SIZEOF source DUP(0), 0                                           

.code
main PROC

    pushad

    mov edx, offset source
    call WriteString
    call CrlF
    mov edx, 0

    mov  esi, offset source 
    mov  edi, offset target      
L1:
    mov  al, [ esi ]          ; get character from source

    cmp  al, 0
    je   final

    cmp  al, 65
    jb   not_letter    ; if char is lower than 'A' jump to not letter
    cmp al, 122
    ja  not_letter     ; if char is greater than 'z' jump to not letter

    cmp al, 90
    ja Label1           ; jump if above 'Z'
    jmp next            ; false
    Label1:
    cmp al, 97
    jl Label2           ; jmp if less than 'a'
    jmp next            ; false
    Label2:             ; if both are true than is greater than 'Z' but less than 'a'
    jmp not_letter      ; jump to not letter

    next:
    mov  [ edi ], al
    inc  di                ; position to next character.

    not_letter:
    inc  si                ; move to next character
    jmp  L1

    final:
    mov  [ edi ], al     

    mov  edx, OFFSET target
    mov  ah, 9
    call WriteString
    call CrlF

    mov  esi,0              ; index register
    mov  ecx,SIZEOF source  ; loop counter
    L2:
    mov  al, target[esi]     ; get a character from source
    and  target[esi], 11011111b     ; convert lower case to upper case
    inc  esi                ; move to next character
    loop L2                 ; repeat for entire string

    mov edx, OFFSET target
    call WriteString
    call CrlF

    popad

  exit
  main endp
  end main

如何删除字符串中的所有标点符号和空格？

How to remove all punctuation and spaces in a string?

assembly

x86

masm

irvine32