使用regexp提取glsl函数体

Question

我在使用javascript提取glsl脚本中的函数时遇到了问题。

下面是glsl的内容：

 precision highp float;                           
  varying vec4 v_color;                                 
  #if USE_TEXTURE                                       
      varying vec2 v_uv0;                               
      uniform sampler2D texture;                        
  #endif                                                
vec2 sfx_func_uv_to_01(vec4 ucrect, vec2 uv) {
    return vec2(
        sfx_func_uv_to_01(ucrect[0], ucrect[0] + ucrect[2], uv.x),
        1.0 - sfx_func_uv_to_01(ucrect[1], ucrect[1] - ucrect[3], uv.y)
    );
}
vec2 sfx_func_uv_to_01(vec4 ucrect, vec2 uv) {
    return vec2(1.0, 2.0);
}
vec4 sfx_fs_output_uv_quarter(vec2 uv, vec4 color) {
    vec4 result = color;
    return result;
}
 void main () {                                    
    vec2 uv = v_uv0;                                  
    vec4 color = texture2D(texture, uv);              
    gl_FragColor = color;
}                                             

我想用正文提取脚本中的4个函数。所以我尝试了reg：

/^(vec4|vec3|vec2|float|int).*\{.*\}/gms

而js代码是：

for (const match of glsl1.matchAll(/^(vec4|vec3|vec2|float|int).*\{.*\}/gms)) {
    console.log(match[0]);
}

我只得到一个结果，而不是4个函数：

vec2 sfx_func_uv_to_01(vec4 ucrect, vec2 uv) {
    return vec2(
        sfx_func_uv_to_01(ucrect[0], ucrect[0] + ucrect[2], uv.x),
        1.0 - sfx_func_uv_to_01(ucrect[1], ucrect[1] - ucrect[3], uv.y)
    );
}
vec2 sfx_func_uv_to_01(vec4 ucrect, vec2 uv) {
    return vec2(1.0, 2.0);
}
vec4 sfx_fs_output_uv_quarter(vec2 uv, vec4 color) {
    vec4 result = color;
    return result;
}
 void main () {                                    
    vec2 uv = v_uv0;                                  
    vec4 color = texture2D(texture, uv);              
    gl_FragColor = color;
}    

我为多行文本寻找非贪婪模式的解决方案，但徒劳无功。

任何建议都将不胜感激，谢谢:)

Answer 1

使用

/^(\s*)(vec4|vec3|vec2|float|int|void).*?{[\s\S]*?^\1}\s*$/gm

参见proof。

说明

--------------------------------------------------------------------------------
  ^                        the beginning of the string
--------------------------------------------------------------------------------
  (                        group and capture to \1:
--------------------------------------------------------------------------------
    \s*                      whitespace (\n, \r, \t, \f, and " ") (0
                             or more times (matching the most amount
                             possible))
--------------------------------------------------------------------------------
  )                        end of \1
--------------------------------------------------------------------------------
  (                        group and capture to \2:
--------------------------------------------------------------------------------
    vec4                     'vec4'
--------------------------------------------------------------------------------
   |                        OR
--------------------------------------------------------------------------------
    vec3                     'vec3'
--------------------------------------------------------------------------------
   |                        OR
--------------------------------------------------------------------------------
    vec2                     'vec2'
--------------------------------------------------------------------------------
   |                        OR
--------------------------------------------------------------------------------
    float                    'float'
--------------------------------------------------------------------------------
   |                        OR
--------------------------------------------------------------------------------
    int                      'int'
--------------------------------------------------------------------------------
   |                        OR
--------------------------------------------------------------------------------
    void                     'void'
--------------------------------------------------------------------------------
  )                        end of \2
--------------------------------------------------------------------------------
  .*?                      any character except \n (0 or more times
                           (matching the least amount possible))
--------------------------------------------------------------------------------
  {                        '{'
--------------------------------------------------------------------------------
  [\s\S]*?                 any character of: whitespace (\n, \r, \t,
                           \f, and " "), non-whitespace (all but \n,
                           \r, \t, \f, and " ") (0 or more times
                           (matching the least amount possible))
--------------------------------------------------------------------------------
  ^                        the beginning of the string
--------------------------------------------------------------------------------
  \1                       what was matched by capture \1
--------------------------------------------------------------------------------
  }                        '}'
--------------------------------------------------------------------------------
  \s*                      whitespace (\n, \r, \t, \f, and " ") (0 or
                           more times (matching the most amount
                           possible))
--------------------------------------------------------------------------------
  $                        before an optional \n, and the end of the
                           string

Answer 2

我不敢尝试使用正则表达式来跟踪花括号的无限嵌套，而是尝试使用g开关沿着函数头进行split() (这样就保留了分隔符)，然后将头-体对连接起来。代码假设在第一个函数定义之前有一些前言，这对于大多数GLSL源来说可能是正确的，并且不期望在函数之间有任何东西(尽管code=code.substr(0,code.lastIndexOf("}")+1);可能可以解决这种情况)。

​

const source=`precision highp float;                           
  varying vec4 v_color;                                 
  #if USE_TEXTURE                                       
      varying vec2 v_uv0;                               
      uniform sampler2D texture;                        
  #endif                                                
vec2 sfx_func_uv_to_01(vec4 ucrect, vec2 uv) {
    return vec2(
        sfx_func_uv_to_01(ucrect[0], ucrect[0] + ucrect[2], uv.x),
        1.0 - sfx_func_uv_to_01(ucrect[1], ucrect[1] - ucrect[3], uv.y)
    );
}
vec2 sfx_func_uv_to_01(vec4 ucrect, vec2 uv) {
    return vec2(1.0, 2.0);
}
vec4 sfx_fs_output_uv_quarter(vec2 uv, vec4 color) {
    vec4 result = color;
    return result;
}
int trap(){if(true){whatever}}
 void main () {                                    
    vec2 uv = v_uv0;                                  
    vec4 color = texture2D(texture, uv);              
    gl_FragColor = color;
}               `;

const blocks=source.split(/((?:vec4|vec3|vec2|float|int|void)\s+[\w]+\s*\(.*?\))/gs);
console.log("Header");
console.log(blocks.shift());
for(let i=1;blocks.length;i++){
  console.log("Function #"+i);
  console.log(blocks.shift()+blocks.shift());
}

​

添加int trap(){if(true){whatever}} fake函数是为了表明这种方法不必担心嵌套的花括号。