tia-lsp/src/diagnostics.lua

-- SCL Diagnostics - Linter functionality for the LSP server
-- Validates SCL code for undefined variables, unknown types, and syntax errors

local M = {}

-- Get script path for loading parser (same pattern as main.lua)
local script_path = debug.getinfo(1, "S").source:gsub("^@", ""):match("(.*/)") or ""
if script_path == "" then
  script_path = "."
end
if script_path:sub(1, 1) ~= "/" then
  local cwd = io.popen("pwd")
  if cwd then
    script_path = cwd:read("*l") .. "/" .. script_path
    cwd:close()
  end
end
package.path = package.path .. ";" .. script_path .. "/?.lua"

local parser = dofile(script_path .. "/parser.lua")
local builtin = dofile(script_path .. "/builtin_instructions.lua")

-- LSP diagnostic severity levels
local DiagnosticSeverity = {
  Error = 1,
  Warning = 2,
  Information = 3,
  Hint = 4,
}

--- Convert line/character to LSP position format
--- @param line number Zero-based line number
--- @param character number Zero-based character offset
--- @return table LSP Position object
local function position_to_lsp(line, character)
  return {
    line = line,
    character = character,
  }
end

--- Create LSP Range object from start and end positions
--- @param start_line number Start line (zero-based)
--- @param start_char number Start character (zero-based)
--- @param end_line number End line (zero-based)
--- @param end_char number End character (zero-based)
--- @return table LSP Range object
local function range_to_lsp(start_line, start_char, end_line, end_char)
  return {
    start = position_to_lsp(start_line, start_char),
    ["end"] = position_to_lsp(end_line, end_char),
  }
end

--- Validate SCL content and generate diagnostics
--- Checks for: undefined variables, invalid # prefix, unknown data types
--- @param content string The SCL source code to validate
--- @param workspace_types table Known types from workspace scanning
--- @param root_dir string Project root directory for additional type lookup
--- @return table Array of LSP Diagnostic objects
function M.validate_diagnostics(content, workspace_types, root_dir)
  local diagnostics = {}
  local lines = {}
  for line in content:gmatch("([^\n]*)\n") do
    table.insert(lines, line)
  end

  local variables, _ = parser.extract_variables(content)
  local types = parser.extract_types(content)
  local functions = parser.extract_functions(content)

  local all_types = {}
  for k, v in pairs(types) do all_types[k] = v end
  for k, v in pairs(workspace_types or {}) do all_types[k] = v end

  local in_var_section = false
  local var_section_start = nil

  for line_idx, line in ipairs(lines) do
    local trimmed = line:gsub("^%s+", ""):gsub("%s+$", "")
    local line_num = line_idx - 1

    if trimmed:match("^VAR[_A-Z]*%s*$") or
       trimmed:match("^VAR_INPUT%s*$") or
       trimmed:match("^VAR_OUTPUT%s*$") or
       trimmed:match("^VAR_IN_OUT%s*$") or
       trimmed:match("^VAR_TEMP%s*$") or
       trimmed:match("^VAR[_ ]*CONSTANT%s*$") or
       trimmed:match("^VAR[_ ]*RETAIN%s*$") or
       trimmed:match("^VAR[_ ]*NON_RETAIN%s*$") then
      in_var_section = true
      var_section_start = line_num
    elseif trimmed:match("^END_VAR%s*$") then
      in_var_section = false
      var_section_start = nil
    end

    -- Check if a hash-prefixed match is part of an IEC literal (TIME, S5TIME, etc.)
    local function is_iec_literal_at(line, match_start)
      if not line or not match_start then return false end
      if match_start <= 1 then return false end
      local prefix = line:sub(match_start - 1, match_start - 1):upper()
      return prefix == "T" or prefix == "D" or prefix == "S"
    end

    if not in_var_section then
      local hash_vars = {}
      for var in line:gmatch("#[%w_]+") do
        local var_name = var:sub(2)
        local match_start = line:find(var, 1, true)
        if not is_iec_literal_at(line, match_start) then
          hash_vars[var_name] = true
        end
      end

      for var_name, _ in pairs(hash_vars) do
        if not variables[var_name] and not all_types[var_name] then
          local var_start = line:find("#" .. var_name, 1, true)
          if var_start then
            table.insert(diagnostics, {
              range = range_to_lsp(line_num, var_start - 1, line_num, var_start + #var_name - 1),
              severity = DiagnosticSeverity.Error,
              message = string.format("Undefined variable: %s", var_name),
              code = "SCL001",
              source = "tia_lsp",
            })
          end
        end
      end
    end

    if in_var_section and (trimmed:match("^[%w_]+%s*%b{}%s*:") or trimmed:match("^[%w_]+%s*:")) then
      local var_name = trimmed:match("^([%w_]+)%s*%b{}%s*:") or trimmed:match("^([%w_]+)%s*:")
      local var_start = line:find(var_name, 1, true)

      if var_name and not var_name:match("^%d") then
        local has_hash = line:match("#" .. var_name)
        if has_hash then
          table.insert(diagnostics, {
            range = range_to_lsp(line_num, 0, line_num, #line),
            severity = DiagnosticSeverity.Error,
            message = "Variable declarations should NOT have '#' prefix in VAR section",
            code = "SCL002",
            source = "tia_lsp",
          })
        end

        local type_part = nil
        local brace_depth = 0
        local comment_depth = 0
        local line_comment = false
        local type_colon = nil
        for i = 1, #line do
          local c = line:sub(i, i)
          local next_c = line:sub(i+1, i+1)
          if c == "/" and next_c == "/" then
            line_comment = true
          elseif line_comment then
            -- Skip everything after //
          elseif c == "(" and next_c == "*" then
            comment_depth = comment_depth + 1
          elseif c == "*" and next_c == ")" and comment_depth > 0 then
            comment_depth = comment_depth - 1
          elseif c == "{" and comment_depth == 0 then
            brace_depth = brace_depth + 1
          elseif c == "}" and comment_depth == 0 then
            brace_depth = brace_depth - 1
          elseif c == ":" and brace_depth == 0 and comment_depth == 0 and next_c ~= "=" then
            -- Only capture colon that's NOT followed by = (not := assignment)
            type_colon = i
          end
        end
        if type_colon then
          type_part = line:sub(type_colon + 1)
        end
        if type_part then
          type_part = type_part:gsub("%s*%(%*.-%*%)", "")  -- Remove block comments (* ... *) with leading whitespace
          type_part = type_part:gsub("%s*//.*$", "")      -- Remove line comments // ...
          type_part = type_part:gsub("%s*:=.*$", "")
          type_part = type_part:gsub("%s*;.*$", "")  -- Remove trailing semicolon
          type_part = type_part:gsub("%s*$", "")
          type_part = type_part:gsub("^%s+", "")

          -- Handle quoted type names like "MyUDT"
          local base_type = type_part:match('^"([^"]+)"') or type_part:match("^([%w_]+)")
          if type_part:match("%s+OF%s+") then
            base_type = type_part:match('.*%s+OF%s+"([^"]+)"') or type_part:match(".*%s+OF%s+([%w_]+)")
          end
          local upper_type = base_type and base_type:upper() or nil
          if base_type and base_type ~= "" and not all_types[base_type] and
             upper_type ~= "BOOL" and upper_type ~= "INT" and upper_type ~= "DINT" and
             upper_type ~= "REAL" and upper_type ~= "LREAL" and upper_type ~= "BYTE" and
             upper_type ~= "WORD" and upper_type ~= "DWORD" and upper_type ~= "LWORD" and
             upper_type ~= "CHAR" and upper_type ~= "STRING" and upper_type ~= "WCHAR" and
             upper_type ~= "WSTRING" and upper_type ~= "TIME" and upper_type ~= "DATE" and
             upper_type ~= "TIME_OF_DAY" and upper_type ~= "DATE_AND_TIME" and
             upper_type ~= "S5TIME" and upper_type ~= "LTIME" and
             upper_type ~= "USINT" and upper_type ~= "SINT" and upper_type ~= "UINT" and
             upper_type ~= "UDINT" and upper_type ~= "LINT" and upper_type ~= "ULINT" and
             upper_type ~= "TOD" and upper_type ~= "DTL" and
             upper_type ~= "IEC_TIMER" and upper_type ~= "TON_TIME" and
             upper_type ~= "TOF_TIME" and upper_type ~= "TONR_TIME" and
             upper_type ~= "TP_TIME" and upper_type ~= "IEC_TON" and
             upper_type ~= "IEC_TOF" and upper_type ~= "IEC_TP" and
             upper_type ~= "IEC_COUNTER" and upper_type ~= "CTU" and
             upper_type ~= "CTD" and upper_type ~= "CTUD" and
             not builtin.is_known_type_or_instruction(upper_type) then
            table.insert(diagnostics, {
              range = range_to_lsp(line_num, 0, line_num, #line),
              severity = DiagnosticSeverity.Warning,
              message = string.format("Unknown data type: %s", base_type),
              code = "SCL003",
              source = "tia_lsp",
            })
          end
        end
      end
    end

    if trimmed:match("^%s*//") or trimmed:match("^%s*%(%*") then
      -- Skip comments
    else
      for assignment in line:gmatch("#[%w_]+%s*:=") do
        local var_name = assignment:match("#([%w_]+)")
        if var_name and in_var_section then
          local assign_start = line:find("#" .. var_name, 1, true)
          table.insert(diagnostics, {
            range = range_to_lsp(line_num, assign_start - 1, line_num, assign_start + #var_name),
            severity = DiagnosticSeverity.Error,
            message = "Cannot use '#' prefix for variables in VAR section",
            code = "SCL004",
            source = "tia_lsp",
          })
        end
      end
    end
  end

  for func_idx, func in ipairs(functions) do
    local func_content = ""
    for i = func.start + 1, func.final - 1 do
      if lines[i + 1] then
        func_content = func_content .. lines[i + 1] .. "\n"
      end
    end

    local func_vars, _ = parser.extract_variables(func_content)
    local all_vars = {}
    for k, v in pairs(variables) do all_vars[k] = v end
    for k, v in pairs(func_vars) do
      all_vars[k] = v
    end
  end

  return diagnostics
end

return M