263 lines
7.3 KiB
Plaintext
263 lines
7.3 KiB
Plaintext
|
// FuncScannerBox — Function definition scanner for Stage-B compiler
|
||
|
|
// Policy: Extract method definitions from Hako source (conservative, minimal)
|
||
|
|
// Toggle: HAKO_STAGEB_FUNC_SCAN=1
|
||
|
|
// Scope: method <name>(params) { ... } outside of main (same box Main)
|
||
|
|
// Output: [{"name":"<name>","params":[...],"body_json":"<Program JSON>","box":"Main"}]
|
||
|
|
|
||
|
|
using lang.compiler.parser.box as ParserBox
|
||
|
|
|
||
|
|
static box FuncScannerBox {
|
||
|
|
// Scan source for method definitions (excluding main)
|
||
|
|
// Returns ArrayBox of method definitions
|
||
|
|
method scan_functions(source, box_name) {
|
||
|
|
local methods = new ArrayBox()
|
||
|
|
local s = "" + source
|
||
|
|
local n = s.length()
|
||
|
|
local i = 0
|
||
|
|
|
||
|
|
loop(i < n) {
|
||
|
|
// Search for "method " pattern
|
||
|
|
local k = -1
|
||
|
|
{
|
||
|
|
local pat = "method "
|
||
|
|
local m = pat.length()
|
||
|
|
local j = i
|
||
|
|
loop(j + m <= n) {
|
||
|
|
if s.substring(j, j + m) == pat { k = j break }
|
||
|
|
j = j + 1
|
||
|
|
}
|
||
|
|
}
|
||
|
|
if k < 0 { break }
|
||
|
|
i = k + 7 // skip "method "
|
||
|
|
|
||
|
|
// Extract method name (alphanumeric until '(')
|
||
|
|
local name_start = i
|
||
|
|
local name_end = -1
|
||
|
|
{
|
||
|
|
local j = i
|
||
|
|
loop(j < n) {
|
||
|
|
local ch = s.substring(j, j + 1)
|
||
|
|
if ch == "(" { name_end = j break }
|
||
|
|
j = j + 1
|
||
|
|
}
|
||
|
|
}
|
||
|
|
if name_end < 0 { break }
|
||
|
|
local method_name = s.substring(name_start, name_end)
|
||
|
|
|
||
|
|
// Skip main (already extracted as body)
|
||
|
|
if method_name == "main" { i = name_end continue }
|
||
|
|
|
||
|
|
// Find '(' after name
|
||
|
|
local lparen = name_end
|
||
|
|
|
||
|
|
// Find matching ')' for params (skip strings)
|
||
|
|
local rparen = -1
|
||
|
|
{
|
||
|
|
local j = lparen + 1
|
||
|
|
local in_str = 0
|
||
|
|
local esc = 0
|
||
|
|
loop(j < n) {
|
||
|
|
local ch = s.substring(j, j + 1)
|
||
|
|
if in_str == 1 {
|
||
|
|
if esc == 1 { esc = 0 j = j + 1 continue }
|
||
|
|
if ch == "\\" { esc = 1 j = j + 1 continue }
|
||
|
|
if ch == "\"" { in_str = 0 j = j + 1 continue }
|
||
|
|
j = j + 1
|
||
|
|
continue
|
||
|
|
}
|
||
|
|
if ch == "\"" { in_str = 1 j = j + 1 continue }
|
||
|
|
if ch == ")" { rparen = j break }
|
||
|
|
j = j + 1
|
||
|
|
}
|
||
|
|
}
|
||
|
|
if rparen < 0 { break }
|
||
|
|
|
||
|
|
// Extract params (minimal: comma-separated names)
|
||
|
|
local params_str = s.substring(lparen + 1, rparen)
|
||
|
|
local params = me._parse_params(params_str)
|
||
|
|
|
||
|
|
// Find opening '{' after ')'
|
||
|
|
local lbrace = -1
|
||
|
|
{
|
||
|
|
local j = rparen + 1
|
||
|
|
local in_str = 0
|
||
|
|
local esc = 0
|
||
|
|
loop(j < n) {
|
||
|
|
local ch = s.substring(j, j + 1)
|
||
|
|
if in_str == 1 {
|
||
|
|
if esc == 1 { esc = 0 j = j + 1 continue }
|
||
|
|
if ch == "\\" { esc = 1 j = j + 1 continue }
|
||
|
|
if ch == "\"" { in_str = 0 j = j + 1 continue }
|
||
|
|
j = j + 1
|
||
|
|
continue
|
||
|
|
}
|
||
|
|
if ch == "\"" { in_str = 1 j = j + 1 continue }
|
||
|
|
if ch == "{" { lbrace = j break }
|
||
|
|
j = j + 1
|
||
|
|
}
|
||
|
|
}
|
||
|
|
if lbrace < 0 { break }
|
||
|
|
|
||
|
|
// Find matching '}' (balanced)
|
||
|
|
local rbrace = -1
|
||
|
|
{
|
||
|
|
local depth = 0
|
||
|
|
local j = lbrace
|
||
|
|
local in_str = 0
|
||
|
|
local esc = 0
|
||
|
|
loop(j < n) {
|
||
|
|
local ch = s.substring(j, j + 1)
|
||
|
|
if in_str == 1 {
|
||
|
|
if esc == 1 { esc = 0 j = j + 1 continue }
|
||
|
|
if ch == "\\" { esc = 1 j = j + 1 continue }
|
||
|
|
if ch == "\"" { in_str = 0 j = j + 1 continue }
|
||
|
|
j = j + 1
|
||
|
|
continue
|
||
|
|
}
|
||
|
|
if ch == "\"" { in_str = 1 j = j + 1 continue }
|
||
|
|
if ch == "{" { depth = depth + 1 j = j + 1 continue }
|
||
|
|
if ch == "}" {
|
||
|
|
depth = depth - 1
|
||
|
|
j = j + 1
|
||
|
|
if depth == 0 { rbrace = j - 1 break }
|
||
|
|
continue
|
||
|
|
}
|
||
|
|
j = j + 1
|
||
|
|
}
|
||
|
|
}
|
||
|
|
if rbrace < 0 { break }
|
||
|
|
|
||
|
|
// Extract method body (inside braces)
|
||
|
|
local method_body = s.substring(lbrace + 1, rbrace)
|
||
|
|
|
||
|
|
// Strip comments from method body
|
||
|
|
method_body = me._strip_comments(method_body)
|
||
|
|
|
||
|
|
// Trim method body
|
||
|
|
method_body = me._trim(method_body)
|
||
|
|
|
||
|
|
// Parse method body to JSON (statement list)
|
||
|
|
local body_json = null
|
||
|
|
if method_body.length() > 0 {
|
||
|
|
local p = new ParserBox()
|
||
|
|
p.stage3_enable(1)
|
||
|
|
body_json = p.parse_program2(method_body)
|
||
|
|
}
|
||
|
|
|
||
|
|
// Store method definition
|
||
|
|
if body_json != null && body_json != "" {
|
||
|
|
local def = new MapBox()
|
||
|
|
def.set("name", method_name)
|
||
|
|
def.set("params", params)
|
||
|
|
def.set("body_json", body_json)
|
||
|
|
def.set("box", box_name)
|
||
|
|
methods.push(def)
|
||
|
|
}
|
||
|
|
i = rbrace
|
||
|
|
}
|
||
|
|
|
||
|
|
return methods
|
||
|
|
}
|
||
|
|
|
||
|
|
// Helper: parse comma-separated parameter names
|
||
|
|
method _parse_params(params_str) {
|
||
|
|
local params = new ArrayBox()
|
||
|
|
local pstr = "" + params_str
|
||
|
|
local pn = pstr.length()
|
||
|
|
local pstart = 0
|
||
|
|
|
||
|
|
loop(pstart < pn) {
|
||
|
|
// Skip whitespace
|
||
|
|
loop(pstart < pn) {
|
||
|
|
local ch = pstr.substring(pstart, pstart + 1)
|
||
|
|
if ch == " " || ch == "\t" || ch == "\n" || ch == "\r" { pstart = pstart + 1 } else { break }
|
||
|
|
}
|
||
|
|
if pstart >= pn { break }
|
||
|
|
|
||
|
|
// Find next comma or end
|
||
|
|
local pend = pstart
|
||
|
|
loop(pend < pn) {
|
||
|
|
local ch = pstr.substring(pend, pend + 1)
|
||
|
|
if ch == "," { break }
|
||
|
|
pend = pend + 1
|
||
|
|
}
|
||
|
|
|
||
|
|
// Extract param name (trim)
|
||
|
|
local pname = pstr.substring(pstart, pend)
|
||
|
|
pname = me._trim(pname)
|
||
|
|
if pname.length() > 0 { params.push(pname) }
|
||
|
|
pstart = pend + 1
|
||
|
|
}
|
||
|
|
|
||
|
|
return params
|
||
|
|
}
|
||
|
|
|
||
|
|
// Helper: strip comments from source
|
||
|
|
method _strip_comments(source) {
|
||
|
|
local s = "" + source
|
||
|
|
local out = ""
|
||
|
|
local i = 0
|
||
|
|
local n = s.length()
|
||
|
|
local in_str = 0
|
||
|
|
local esc = 0
|
||
|
|
local in_line = 0
|
||
|
|
local in_block = 0
|
||
|
|
|
||
|
|
loop(i < n) {
|
||
|
|
local ch = s.substring(i, i + 1)
|
||
|
|
if in_line == 1 {
|
||
|
|
if ch == "\n" { in_line = 0 out = out + ch }
|
||
|
|
i = i + 1
|
||
|
|
continue
|
||
|
|
}
|
||
|
|
if in_block == 1 {
|
||
|
|
if ch == "*" && i + 1 < n && s.substring(i + 1, i + 2) == "/" { in_block = 0 i = i + 2 continue }
|
||
|
|
i = i + 1
|
||
|
|
continue
|
||
|
|
}
|
||
|
|
if in_str == 1 {
|
||
|
|
if esc == 1 { out = out + ch esc = 0 i = i + 1 continue }
|
||
|
|
if ch == "\\" { out = out + ch esc = 1 i = i + 1 continue }
|
||
|
|
if ch == "\"" { out = out + ch in_str = 0 i = i + 1 continue }
|
||
|
|
out = out + ch
|
||
|
|
i = i + 1
|
||
|
|
continue
|
||
|
|
}
|
||
|
|
// Not in string/comment
|
||
|
|
if ch == "\"" { out = out + ch in_str = 1 i = i + 1 continue }
|
||
|
|
if ch == "/" && i + 1 < n {
|
||
|
|
local ch2 = s.substring(i + 1, i + 2)
|
||
|
|
if ch2 == "/" { in_line = 1 i = i + 2 continue }
|
||
|
|
if ch2 == "*" { in_block = 1 i = i + 2 continue }
|
||
|
|
}
|
||
|
|
out = out + ch
|
||
|
|
i = i + 1
|
||
|
|
}
|
||
|
|
|
||
|
|
return out
|
||
|
|
}
|
||
|
|
|
||
|
|
// Helper: trim whitespace from string
|
||
|
|
method _trim(s) {
|
||
|
|
local str = "" + s
|
||
|
|
local n = str.length()
|
||
|
|
local b = 0
|
||
|
|
|
||
|
|
// left trim (space, tab, CR, LF)
|
||
|
|
loop(b < n) {
|
||
|
|
local ch = str.substring(b, b + 1)
|
||
|
|
if ch == " " || ch == "\t" || ch == "\r" || ch == "\n" { b = b + 1 } else { break }
|
||
|
|
}
|
||
|
|
|
||
|
|
// right trim
|
||
|
|
local e = n
|
||
|
|
loop(e > b) {
|
||
|
|
local ch = str.substring(e - 1, e)
|
||
|
|
if ch == " " || ch == "\t" || ch == "\r" || ch == "\n" { e = e - 1 } else { break }
|
||
|
|
}
|
||
|
|
|
||
|
|
if e > b { return str.substring(b, e) }
|
||
|
|
return ""
|
||
|
|
}
|
||
|
|
}
|