lazar/tia-lsp
0
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

feat: diagnostics & parser spec conformance (Phase 5)

Browse Source 
diagnostics.lua:
- Add VAR DB_SPECIFIC to section detection
- Make all VAR/END_VAR detection case-insensitive (matches grammar)
- Replace 20-line hardcoded type check list with builtin.is_known_data_type()
  and builtin.is_known_type_or_instruction() — now uses the expanded
  DATA_TYPES table from Phase 4 instead of inline string comparisons
- Add attribute validation: warn on unknown per-variable attributes
  (SCL005). Valid attributes: ExternalWritable, ExternalVisible,
  ExternalAccessible, S7_SetPoint, S7_Optimized_Access
- Allow optional semicolon after END_VAR

parser.lua:
- Add VAR DB_SPECIFIC to section detection and var_type classification
- Make all block detection case-insensitive (FUNCTION_BLOCK, FUNCTION,
  ORGANIZATION_BLOCK, END_FUNCTION_BLOCK, etc.)
- Make TYPE/END_TYPE, STRUCT/END_STRUCT, VAR/END_VAR case-insensitive
- Fix VAR RETAIN vs VAR NON_RETAIN classification (NON_RETAIN was
  matching the RETAIN branch first)
- Allow optional semicolon after END_VAR and END_STRUCT

formatter.lua:
- Add VAR DB_SPECIFIC and VAR_DB_SPECIFIC to BLOCKS and VAR_KEYWORDS
- Fix get_keyword() to handle multi-word VAR keywords (VAR NON_RETAIN,
  VAR DB_SPECIFIC, VAR CONSTANT, VAR RETAIN) — normalizes spaces to
  underscores so the keyword lookup succeeds
- Fix is_new_statement detection for space-form VAR keywords

All 38 formatter tests pass. Parser and diagnostics load without errors.
This commit is contained in:
lazar
2026-07-18 20:11:41 +02:00
parent d9338ca470
commit aecda669bd
3 changed files with 88 additions and 57 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/diagnostics.lua
+41 -26
View File
@@ -80,21 +80,50 @@ function M.validate_diagnostics(content, workspace_types, root_dir)
local trimmed = line:gsub("^%s+", ""):gsub("%s+$", "") local trimmed = line:gsub("^%s+", ""):gsub("%s+$", "")
local line_num = line_idx - 1 local line_num = line_idx - 1
if trimmed:match("^VAR[_A-Z]*%s*$") or if trimmed:upper():match("^VAR[_A-Z]*%s*$") or
trimmed:match("^VAR_INPUT%s*$") or trimmed:upper():match("^VAR_INPUT%s*$") or
trimmed:match("^VAR_OUTPUT%s*$") or trimmed:upper():match("^VAR_OUTPUT%s*$") or
trimmed:match("^VAR_IN_OUT%s*$") or trimmed:upper():match("^VAR_IN_OUT%s*$") or
trimmed:match("^VAR_TEMP%s*$") or trimmed:upper():match("^VAR_TEMP%s*$") or
trimmed:match("^VAR[_ ]*CONSTANT%s*$") or trimmed:upper():match("^VAR[_ ]*CONSTANT%s*$") or
trimmed:match("^VAR[_ ]*RETAIN%s*$") or trimmed:upper():match("^VAR[_ ]*RETAIN%s*$") or
trimmed:match("^VAR[_ ]*NON_RETAIN%s*$") then trimmed:upper():match("^VAR[_ ]*NON_RETAIN%s*$") or
trimmed:upper():match("^VAR[_ ]*DB_SPECIFIC%s*$") then
in_var_section = true in_var_section = true
var_section_start = line_num var_section_start = line_num
elseif trimmed:match("^END_VAR%s*$") then elseif trimmed:upper():match("^END_VAR%s*;?%s*$") then
in_var_section = false in_var_section = false
var_section_start = nil var_section_start = nil
end end
-- Validate VAR access attributes ({ ExternalWritable, ExternalVisible, ... })
-- Spec: only ExternalWritable, ExternalVisible, ExternalAccessible, S7_SetPoint
-- are valid per-variable attributes in VAR sections.
local ALLOWED_VAR_ATTRIBUTES = {
ExternalWritable = true,
ExternalVisible = true,
ExternalAccessible = true,
ExternalWRITABLE = true, -- case variant
ExternalVISIBLE = true,
ExternalACCESSIBLE = true,
S7_SetPoint = true,
S7_Optimized_Access = true,
}
for attr_name in line:gmatch("{%s*(%w+)%s*:=") do
if not ALLOWED_VAR_ATTRIBUTES[attr_name] then
local attr_start = line:find(attr_name, 1, true)
if attr_start then
table.insert(diagnostics, {
range = range_to_lsp(line_num, attr_start - 1, line_num, attr_start + #attr_name - 1),
severity = DiagnosticSeverity.Warning,
message = string.format("Unknown variable attribute: %s", attr_name),
code = "SCL005",
source = "tia_lsp",
})
end
end
end
-- Check if a hash-prefixed match is part of an IEC literal (TIME, S5TIME, etc.) -- Check if a hash-prefixed match is part of an IEC literal (TIME, S5TIME, etc.)
local function is_iec_literal_at(line, match_start) local function is_iec_literal_at(line, match_start)
if not line or not match_start then return false end if not line or not match_start then return false end
@@ -187,23 +216,9 @@ function M.validate_diagnostics(content, workspace_types, root_dir)
base_type = type_part:match('.*%s+OF%s+"([^"]+)"') or type_part:match(".*%s+OF%s+([%w_]+)") base_type = type_part:match('.*%s+OF%s+"([^"]+)"') or type_part:match(".*%s+OF%s+([%w_]+)")
end end
local upper_type = base_type and base_type:upper() or nil local upper_type = base_type and base_type:upper() or nil
if base_type and base_type ~= "" and not all_types[base_type] and if base_type and base_type ~= "" and
upper_type ~= "BOOL" and upper_type ~= "INT" and upper_type ~= "DINT" and not all_types[base_type] and
upper_type ~= "REAL" and upper_type ~= "LREAL" and upper_type ~= "BYTE" and not builtin.is_known_data_type(upper_type) 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 not builtin.is_known_type_or_instruction(upper_type) then
table.insert(diagnostics, { table.insert(diagnostics, {
range = range_to_lsp(line_num, 0, line_num, #line), range = range_to_lsp(line_num, 0, line_num, #line),
src/formatter.lua
+15 -2
View File
@@ -53,6 +53,8 @@ local BLOCKS = {
["VAR_CONSTANT"] = "END_VAR", ["VAR_CONSTANT"] = "END_VAR",
["VAR_RETAIN"] = "END_VAR", ["VAR_RETAIN"] = "END_VAR",
["VAR_NON_RETAIN"] = "END_VAR", ["VAR_NON_RETAIN"] = "END_VAR",
["VAR DB_SPECIFIC"] = "END_VAR",
["VAR_DB_SPECIFIC"] = "END_VAR",
} }
local SAME_LEVEL = { local SAME_LEVEL = {
@@ -82,6 +84,8 @@ local VAR_KEYWORDS = {
["VAR_CONSTANT"] = true, ["VAR_CONSTANT"] = true,
["VAR_RETAIN"] = true, ["VAR_RETAIN"] = true,
["VAR_NON_RETAIN"] = true, ["VAR_NON_RETAIN"] = true,
["VAR DB_SPECIFIC"] = true,
["VAR_DB_SPECIFIC"] = true,
} }
local DECLARATIONS = { local DECLARATIONS = {
@@ -325,6 +329,12 @@ function M.format_document(content, options)
end end
local function get_keyword(trimmed) local function get_keyword(trimmed)
-- Handle multi-word VAR keywords: "VAR NON_RETAIN", "VAR DB_SPECIFIC", "VAR CONSTANT", "VAR RETAIN"
local var_multi = trimmed:upper():match("^(VAR%s+[%w_]+)")
if var_multi then
-- Normalize to underscore form: "VAR NON_RETAIN" -> "VAR_NON_RETAIN"
return var_multi:gsub("%s+", "_")
end
return trimmed:match("^([%w_]+)") or trimmed:match("^(%w+)") return trimmed:match("^([%w_]+)") or trimmed:match("^(%w+)")
end end
@@ -418,15 +428,18 @@ function M.format_document(content, options)
if in_assignment and not ends_assignment then if in_assignment and not ends_assignment then
local starts_with_operator = is_assignment_continuation(trimmed) local starts_with_operator = is_assignment_continuation(trimmed)
-- New statement if: starts with keyword OR contains := (new assignment) OR starts with block ender -- New statement if: starts with keyword OR contains := (new assignment) OR starts with block ender
local first_word = trimmed:match("^([%w_]+)") local first_word = trimmed:match("^([%w_]+)") or trimmed:match("^([%w_]+%s+[%w_]+)")
local starts_block_ender = first_word and ( local starts_block_ender = first_word and (
trimmed:match("^END_") or trimmed:match("^END_") or
BLOCKS[first_word] ~= nil BLOCKS[first_word] ~= nil
) )
-- Normalize VAR forms: "VAR NON_RETAIN" -> "VAR_NON_RETAIN", "VAR DB_SPECIFIC" -> "VAR_DB_SPECIFIC"
local normalized_var = trimmed:upper():gsub("VAR%s+", "VAR_"):gsub("^VAR_NON_RETAIN$", "VAR_NON_RETAIN")
local is_new_statement = trimmed:match(":=") or starts_block_ender or ( local is_new_statement = trimmed:match(":=") or starts_block_ender or (
trimmed:match("^%w+") and ( trimmed:match("^%w+") and (
SAME_LEVEL[trimmed:match("^([%w_]+)")] or SAME_LEVEL[trimmed:match("^([%w_]+)")] or
VAR_KEYWORDS[trimmed:match("^([%w_]+)")] VAR_KEYWORDS[trimmed:match("^([%w_]+)")] or
VAR_KEYWORDS[normalized_var:match("^([%w_]+[_%w]+)")]
) )
) )
if starts_with_operator or not is_new_statement then if starts_with_operator or not is_new_statement then
src/parser.lua
+31 -28
View File
@@ -24,8 +24,8 @@ function M.extract_variables(content)
local function process_line(line, line_num) local function process_line(line, line_num)
local trimmed = line:gsub("^%s+", ""):gsub("%s+$", "") local trimmed = line:gsub("^%s+", ""):gsub("%s+$", "")
-- Detect block start (with or without quotes) -- Detect block start (with or without quotes) — case-insensitive
local fb_name = trimmed:match('FUNCTION_BLOCK%s+"([^"]+)"') or trimmed:match("^FUNCTION_BLOCK%s+([%w_]+)") local fb_name = trimmed:match('[Ff][Uu][Nn][Cc][Tt][Ii][Oo][Nn]_[Bb][Ll][Oo][Cc][Kk]%s+"([^"]+)"') or trimmed:match("^[Ff][Uu][Nn][Cc][Tt][Ii][Oo][Nn]_[Bb][Ll][Oo][Cc][Kk]%s+([%w_]+)")
if fb_name then if fb_name then
current_block = { name = fb_name, kind = "function_block" } current_block = { name = fb_name, kind = "function_block" }
in_var_section = false in_var_section = false
@@ -33,7 +33,7 @@ function M.extract_variables(content)
return return
end end
local ob_name = trimmed:match('ORGANIZATION_BLOCK%s+"([^"]+)"') or trimmed:match("^ORGANIZATION_BLOCK%s+([%w_]+)") local ob_name = trimmed:match('[Oo][Rr][Gg][Aa][Nn][Ii][Zz][Aa][Tt][Ii][Oo][Nn]_[Bb][Ll][Oo][Cc][Kk]%s+"([^"]+)"') or trimmed:match("^[Oo][Rr][Gg][Aa][Nn][Ii][Zz][Aa][Tt][Ii][Oo][Nn]_[Bb][Ll][Oo][Cc][Kk]%s+([%w_]+)")
if ob_name then if ob_name then
current_block = { name = ob_name, kind = "organization_block" } current_block = { name = ob_name, kind = "organization_block" }
in_var_section = false in_var_section = false
@@ -41,7 +41,7 @@ function M.extract_variables(content)
return return
end end
local fn_name = trimmed:match('FUNCTION%s+"([^"]+)"') or trimmed:match("^FUNCTION%s+([%w_]+)") local fn_name = trimmed:match('[Ff][Uu][Nn][Cc][Tt][Ii][Oo][Nn]%s+"([^"]+)"') or trimmed:match("^[Ff][Uu][Nn][Cc][Tt][Ii][Oo][Nn]%s+([%w_]+)")
if fn_name then if fn_name then
current_block = { name = fn_name, kind = "function" } current_block = { name = fn_name, kind = "function" }
in_var_section = false in_var_section = false
@@ -49,60 +49,63 @@ function M.extract_variables(content)
return return
end end
if trimmed:match("^END_FUNCTION_BLOCK") or if trimmed:upper():match("^END_FUNCTION_BLOCK") or
trimmed:match("^END_ORGANIZATION_BLOCK") or trimmed:upper():match("^END_ORGANIZATION_BLOCK") or
trimmed:match("^END_FUNCTION") then trimmed:upper():match("^END_FUNCTION") then
current_block = nil current_block = nil
in_var_section = false in_var_section = false
in_struct_section = false in_struct_section = false
return return
end end
-- Handle TYPE sections (for .udt files with STRUCT) -- Handle TYPE sections (for .udt files with STRUCT) — case-insensitive
if trimmed:match("^TYPE") and (trimmed:match("^TYPE%s") or trimmed:match('^TYPE"') or trimmed == "TYPE") then if trimmed:upper():match("^TYPE") and (trimmed:upper():match("^TYPE%s") or trimmed:upper():match('^TYPE"') or trimmed:upper() == "TYPE") then
in_struct_section = true in_struct_section = true
var_type = "STRUCT_FIELD" var_type = "STRUCT_FIELD"
return return
end end
if trimmed:match("^END_TYPE") then if trimmed:upper():match("^END_TYPE") then
in_struct_section = false in_struct_section = false
return return
end end
if trimmed:match("^VAR[_A-Z]*%s*$") or if trimmed:upper():match("^VAR[_A-Z]*%s*$") or
trimmed:match("^VAR_INPUT%s*$") or trimmed:upper():match("^VAR_INPUT%s*$") or
trimmed:match("^VAR_OUTPUT%s*$") or trimmed:upper():match("^VAR_OUTPUT%s*$") or
trimmed:match("^VAR_IN_OUT%s*$") or trimmed:upper():match("^VAR_IN_OUT%s*$") or
trimmed:match("^VAR_TEMP%s*$") or trimmed:upper():match("^VAR_TEMP%s*$") or
trimmed:match("^VAR[_ ]*CONSTANT%s*$") or trimmed:upper():match("^VAR[_ ]*CONSTANT%s*$") or
trimmed:match("^VAR[_ ]*RETAIN%s*$") or trimmed:upper():match("^VAR[_ ]*RETAIN%s*$") or
trimmed:match("^VAR[_ ]*NON_RETAIN%s*$") then trimmed:upper():match("^VAR[_ ]*NON_RETAIN%s*$") or
trimmed:upper():match("^VAR[_ ]*DB_SPECIFIC%s*$") then
in_var_section = true in_var_section = true
in_struct_section = false in_struct_section = false
if trimmed:match("INPUT") then var_type = "VAR_INPUT" local upper_trimmed = trimmed:upper()
elseif trimmed:match("OUTPUT") then var_type = "VAR_OUTPUT" if upper_trimmed:match("INPUT") then var_type = "VAR_INPUT"
elseif trimmed:match("IN_OUT") then var_type = "VAR_IN_OUT" elseif upper_trimmed:match("OUTPUT") then var_type = "VAR_OUTPUT"
elseif trimmed:match("TEMP") then var_type = "VAR_TEMP" elseif upper_trimmed:match("IN_OUT") then var_type = "VAR_IN_OUT"
elseif trimmed:match("CONSTANT") then var_type = "VAR_CONSTANT" elseif upper_trimmed:match("TEMP") then var_type = "VAR_TEMP"
elseif trimmed:match("RETAIN") then var_type = "VAR_RETAIN" elseif upper_trimmed:match("CONSTANT") then var_type = "VAR_CONSTANT"
elseif trimmed:match("NON_RETAIN") then var_type = "VAR_NON_RETAIN" elseif upper_trimmed:match("RETAIN") and not upper_trimmed:match("NON_RETAIN") then var_type = "VAR_RETAIN"
elseif upper_trimmed:match("NON_RETAIN") then var_type = "VAR_NON_RETAIN"
elseif upper_trimmed:match("DB_SPECIFIC") then var_type = "VAR_DB_SPECIFIC"
else var_type = "VAR" end else var_type = "VAR" end
return return
end end
if trimmed:match("^END_VAR%s*$") then if trimmed:upper():match("^END_VAR%s*;?%s*$") then
in_var_section = false in_var_section = false
return return
end end
if trimmed:match("^STRUCT%s*$") then if trimmed:upper():match("^STRUCT%s*$") then
in_struct_section = true in_struct_section = true
var_type = "STRUCT_FIELD" var_type = "STRUCT_FIELD"
return return
end end
if trimmed:match("^END_STRUCT%s*$") then if trimmed:upper():match("^END_STRUCT%s*;?%s*$") then
in_struct_section = false in_struct_section = false
return return
end end