NB-076
e5ab3baa46
## 核心变更 ### 1. 新PROCEDURE DIVISION解析器（procedure_parser.py） - 行级状态机替换旧的BrParser regex解析器 - 覆盖：IF/ELSE/END-IF（嵌套）、EVALUATE/WHEN/ALSO、 PERFORM UNTIL/VARYING、READ/AT END/NOT AT END、 SORT/MERGE、GO TO DEPENDING ON - 之前：3/37程序有分支检测 → 现在：37/37全部有分支 - 速度：~20ms/程序，纯规则引擎 ### 2. 桥接层（pipeline_bridge.py） - 新解析器为主，旧解析器3秒超时兜底 - 自动选取分支数更多的结果 ### 3. 线性路径枚举（design_mcdc.py） - 替换旧的Cartesian积路径枚举（O(2^N)）为每决策点独立枚举（O(N)） - 28-sysin: 162分支仅163条路径（之前需截断到60DP） - 消除了500路径硬上限和60DP截断 ### 4. 条件解析修复（cond.py） - NOT运算符规范化：X NOT = 5 → X <> 5 - 88-level反向：NOT WS-EOF-Y → parent <> value - 裸字段引用：NOT WS-EOF → WS-EOF <> 'Y' - 验证：1182个IF条件中0个NOT污染 ### 5. 约束字段过滤（__init__.py） - OF限定词剥离：STD-KEY OF MASTER-REC → STD-KEY - 下标字段解析：WS-ITEM(SUB) → WS-ITEM - 跳过不在fields_dict中的字段（group item/伪影） ### 6. 预处理器增强（read.py） - VALUE ALL剥离（VALUE ALL '*' → VALUE '*'） - &续行合并（COBOL多行字符串拼接） - PIC小数点点→V转换（Z(9)9.99. → Z(9)9V99.） - 缺少点号补全 ### 7. Grammar修复（grammar.lark） - OCCURS 1 TIME支持（原只认TIMES） - USAGE IS COMP支持（可选IS） - $符号在PICTURE_STRING中 - 无NAME条款支持（clause+） ### 8. Flatfile写入（flatfile.py） - 多记录FD支持（选字段最多的记录） - Path类型强制转换 - 回退零值记录 ### 9. Bug修复 - trace_to_root空列表保护（core.py） ### 10. 测试套件（S16-S21） - S16: 全量基准程序端到端 - S17: gcov运行时对比 - S18/S19: 桥接器验证 - S20: DISPLAY插桩运行时验证+gcov分支覆盖率 - S21: 条件解析修复验证 - 全部17/17回归测试通过 Co-Authored-By: Claude <noreply@anthropic.com>
532 lines
17 KiB
Python
532 lines
17 KiB
Python
"""??????? + COPYBOOK + DATA DIVISION?? + PIC"""
|
|
|
|
import re
|
|
from pathlib import Path
|
|
from lark import Lark, Transformer, v_args
|
|
|
|
from .models import FieldDef, PicInfo
|
|
|
|
|
|
# 鈹€鈹€ Preprocessor 鈹€鈹€
|
|
|
|
|
|
def _is_fixed_format(source: str) -> bool:
|
|
if re.search(r'>>SOURCE\s+FORMAT\s+IS\s+FREE', source, re.IGNORECASE):
|
|
return False
|
|
if re.search(r'>>SOURCE\s+FORMAT\s+IS\s+FIXED', source, re.IGNORECASE):
|
|
return True
|
|
lines = [l for l in source.splitlines() if l.strip()]
|
|
fixed_hits = 0
|
|
free_hits = 0
|
|
for line in lines[:10]:
|
|
if len(line) >= 72:
|
|
free_hits += 1
|
|
elif len(line) >= 7 and line[6] in ('*', '/', '-', 'D'):
|
|
fixed_hits += 1
|
|
return fixed_hits >= free_hits if (fixed_hits + free_hits) > 0 else True
|
|
|
|
|
|
def preprocess(source: str) -> str:
|
|
# COPY 预处理：展开或移除 COPY 语句
|
|
# Lark 语法不支持 COPY（这是预处理指令），必须在解析前处理
|
|
source = resolve_copybooks(source, '.')
|
|
|
|
# Strip EXEC ... END-EXEC blocks (CICS/SQL) before Lark parsing
|
|
source = re.sub(
|
|
r'EXEC\s+(?:CICS|SQL)\b.*?END-EXEC\.?',
|
|
'',
|
|
source, flags=re.IGNORECASE | re.DOTALL
|
|
)
|
|
|
|
# Strip commas from VALUE clauses (VALUE 'A', 'B', 'C' → VALUE 'A' 'B' 'C')
|
|
def _strip_value_commas(m):
|
|
return re.sub(r'\s*,\s*', ' ', m.group(0))
|
|
source = re.sub(r'VALUE\s+[^.\n]+', _strip_value_commas, source, flags=re.IGNORECASE)
|
|
|
|
# Strip ALL from VALUE ALL (VALUE ALL '*.' → VALUE '*.')
|
|
source = re.sub(r'\bVALUE\s+ALL\b', 'VALUE', source, flags=re.IGNORECASE)
|
|
|
|
# Collapse &-concatenated VALUE continuation lines
|
|
# COBOL uses & to split long literals across lines:
|
|
# "............................" &
|
|
# "............................"
|
|
# Match: (quote/X'...') + " &" + newline + (quote/X'...')
|
|
source = re.sub(
|
|
r'([Xx]?["\'])\s*&\s*\n\s*([Xx]?["\'])',
|
|
lambda m: m.group(1) + m.group(2),
|
|
source
|
|
)
|
|
|
|
# Remove trailing & at end of lines (standalone continuation markers)
|
|
source = re.sub(r'&(?=[^"\']*$)', '', source, flags=re.MULTILINE)
|
|
|
|
# Convert PIC decimal dots to V (implied decimal) for Lark compatibility
|
|
# PIC Z(9)9.99. → PIC Z(9)9V99. (only within PIC clause before DOT)
|
|
source = re.sub(
|
|
r'(PIC\s+)([A-Z0-9(),\-*/V\$]+)\.(\d+)',
|
|
r'\1\2V\3',
|
|
source, flags=re.IGNORECASE
|
|
)
|
|
|
|
fixed = _is_fixed_format(source)
|
|
lines = []
|
|
for raw_line in source.splitlines():
|
|
line = raw_line.rstrip()
|
|
if not line:
|
|
lines.append('')
|
|
continue
|
|
if fixed:
|
|
if len(line) >= 7 and line[6] in ('*', '/'):
|
|
continue
|
|
if len(line) >= 7 and line[6] == '-':
|
|
if lines:
|
|
lines[-1] = lines[-1] + ' ' + line[7:].lstrip()
|
|
continue
|
|
if len(line) >= 7 and line[6].upper() == 'D':
|
|
continue
|
|
content = line[6:] if len(line) >= 7 else line
|
|
else:
|
|
comment_pos = line.find('*>')
|
|
if comment_pos >= 0:
|
|
line = line[:comment_pos]
|
|
line = line.strip()
|
|
if not line:
|
|
continue
|
|
# Strip bare * comment lines in free format (after *> removal)
|
|
if line.startswith('*') and not line.startswith('*>'):
|
|
continue
|
|
content = line
|
|
lines.append(re.sub(r'\s+FALSE\s+[^\s.]+', '', content.upper()))
|
|
|
|
# Ensure DATA DIVISION lines with PIC/VALUE but no trailing DOT get one
|
|
# (handles COBOL programs where the period on a PIC clause is optional/omitted)
|
|
fixed_lines = []
|
|
for i, line in enumerate(lines):
|
|
stripped = line.strip()
|
|
if stripped and not stripped.endswith('.'):
|
|
# Lines inside DATA DIVISION that have PIC or VALUE but no DOT
|
|
if re.search(r'\b(PIC|VALUE|REDEFINES|OCCURS|USAGE)\b', stripped, re.IGNORECASE):
|
|
# Only fix if the NEXT line also looks like a data_item (level_num)
|
|
if i + 1 < len(lines) and re.match(r'^\s*(0[1-9]|[0-4][0-9]|49|66|77|88)\s', lines[i + 1]):
|
|
line = line.rstrip() + ' .'
|
|
fixed_lines.append(line)
|
|
return '\n'.join(fixed_lines)
|
|
|
|
|
|
def extract_data_division(source: str) -> str:
|
|
m = re.search(r'DATA\s+DIVISION\s*\.', source)
|
|
if not m:
|
|
return ''
|
|
start = m.end()
|
|
end_m = re.search(r'PROCEDURE\s+DIVISION', source[start:])
|
|
if end_m:
|
|
end = start + end_m.start()
|
|
else:
|
|
end = len(source)
|
|
return source[start:end].strip()
|
|
|
|
|
|
def extract_procedure_division(source: str) -> str:
|
|
m = re.search(r'PROCEDURE\s+DIVISION', source)
|
|
if not m:
|
|
return ''
|
|
return source[m.start():].strip()
|
|
|
|
|
|
# 鈹€鈹€ COPYBOOK Resolution 鈹€鈹€
|
|
|
|
_COPYBOOK_EXTENSIONS = ['.cpy', '.cbl', '.cpb', '']
|
|
|
|
|
|
def resolve_copybooks(source: str, source_dir: str, _recursion_depth: int = 0,
|
|
extra_search_paths: list[str] = None) -> str:
|
|
"""Find COPY statements and replace with copybook content.
|
|
|
|
Searches from source_dir first, then extra_search_paths.
|
|
"""
|
|
_RE_COPY = re.compile(
|
|
r"^\s*COPY\s+(\w[\w-]*|\"[^\"]*\"|\'[^\']*\')(?:\s+REPLACING\s+(.+?))?\s*\.?\s*$",
|
|
re.IGNORECASE
|
|
)
|
|
_RE_PAIR = re.compile(r"==(.+?)==\s+BY\s+==(.+?)==", re.IGNORECASE)
|
|
search_dirs = [source_dir] + (extra_search_paths or [])
|
|
|
|
lines = source.split('\n')
|
|
result = []
|
|
for line in lines:
|
|
m = _RE_COPY.match(line)
|
|
if m:
|
|
raw_name = m.group(1)
|
|
name = raw_name.strip('"').strip("'").upper()
|
|
found = None
|
|
for sd in search_dirs:
|
|
for ext in _COPYBOOK_EXTENSIONS:
|
|
p = Path(sd, name + ext)
|
|
if p.exists():
|
|
found = p
|
|
break
|
|
if found:
|
|
break
|
|
if found:
|
|
if _recursion_depth > 10:
|
|
logger.warning(f"COPY circular dependency detected for {name}, skipping")
|
|
continue
|
|
cb = found.read_text(encoding='utf-8')
|
|
# Recursively resolve nested COPY inside the copybook
|
|
cb = resolve_copybooks(cb, source_dir, _recursion_depth + 1)
|
|
if m.group(2):
|
|
pairs = _RE_PAIR.findall(m.group(2))
|
|
for old, new in pairs:
|
|
cb = re.sub(
|
|
re.escape(old.strip()), new.strip(),
|
|
cb, flags=re.IGNORECASE
|
|
)
|
|
# 展开 COPYBOOK 内容，不添加注释行（避免 Lark 在 FD 块内看到注释）
|
|
result.append(cb)
|
|
else:
|
|
# COPY 未找到时完全跳过（预处理指令，Lark 不应处理）
|
|
# 该行可能在 FD/SD 块内，保留会破坏 Lark 解析
|
|
pass
|
|
else:
|
|
result.append(line)
|
|
return '\n'.join(result)
|
|
|
|
|
|
# 鈹€鈹€ Lark Grammar 鈹€鈹€
|
|
|
|
_GRAMMAR_CACHE = None
|
|
|
|
|
|
def _get_grammar() -> str:
|
|
global _GRAMMAR_CACHE
|
|
if _GRAMMAR_CACHE is None:
|
|
lark_path = Path(__file__).parent / 'grammar.lark'
|
|
_GRAMMAR_CACHE = lark_path.read_text(encoding='utf-8')
|
|
return _GRAMMAR_CACHE
|
|
|
|
|
|
# 鈹€鈹€ Data Transformer 鈹€鈹€
|
|
|
|
@v_args(inline=True)
|
|
class DataTransformer(Transformer):
|
|
def __init__(self):
|
|
super().__init__()
|
|
self.fields = []
|
|
self._last_parent = None
|
|
self._pending = []
|
|
|
|
def start(self, *items):
|
|
for f in self._pending:
|
|
f['section'] = f.get('section', 'WORKING-STORAGE')
|
|
self.fields.append(f)
|
|
self._pending = []
|
|
return self.fields
|
|
|
|
def file_section(self, *args):
|
|
for f in self._pending:
|
|
f['section'] = 'FILE'
|
|
self.fields.append(f)
|
|
self._pending = []
|
|
return None
|
|
|
|
def working_storage(self, *args):
|
|
for f in self._pending:
|
|
f['section'] = 'WORKING-STORAGE'
|
|
self.fields.append(f)
|
|
self._pending = []
|
|
return None
|
|
|
|
def linkage(self, *args):
|
|
for f in self._pending:
|
|
f['section'] = 'LINKAGE'
|
|
self.fields.append(f)
|
|
self._pending = []
|
|
return None
|
|
|
|
def data_item(self, level_num, name, *clauses):
|
|
level = int(str(level_num))
|
|
name = str(name)
|
|
is_filler = (name.upper() == 'FILLER')
|
|
pic = None
|
|
value = None
|
|
values = None
|
|
redefines = None
|
|
usage = None
|
|
occurs_count = 0
|
|
occurs_depending = None
|
|
for c in clauses:
|
|
if isinstance(c, dict):
|
|
if 'pic' in c:
|
|
pic = c['pic']
|
|
if 'value' in c:
|
|
value = c['value']
|
|
if 'values' in c:
|
|
values = c['values']
|
|
if 'redefines' in c:
|
|
redefines = c['redefines']
|
|
if 'usage' in c:
|
|
usage = c['usage']
|
|
if 'occurs' in c:
|
|
occurs_count = c['occurs']
|
|
if 'depends' in c:
|
|
occurs_depending = c['depends']
|
|
|
|
base = {
|
|
'level': level,
|
|
'name': name,
|
|
'pic': pic if pic else None,
|
|
'value': value,
|
|
'values': values,
|
|
'is_filler': is_filler,
|
|
'redefines': redefines,
|
|
'usage': usage,
|
|
'occurs': occurs_count,
|
|
'occurs_depending': occurs_depending,
|
|
}
|
|
|
|
if pic is not None:
|
|
self._pending.append(base)
|
|
self._last_parent = name
|
|
elif level == 88 and value is not None:
|
|
base.update({
|
|
'pic': None,
|
|
'value': value.strip("'").strip('"'),
|
|
'values': [v.strip("'").strip('"') for v in values] if values else None,
|
|
'is_88': True,
|
|
'parent': self._last_parent or '',
|
|
})
|
|
self._pending.append(base)
|
|
else:
|
|
# 组项目（无 PIC，有下级字段）
|
|
self._pending.append(base)
|
|
self._last_parent = name
|
|
return None
|
|
|
|
def clause(self, *args):
|
|
# ?????????? dict??????? token
|
|
result = {}
|
|
for a in args:
|
|
if isinstance(a, dict):
|
|
result.update(a)
|
|
elif isinstance(a, str) and a.upper() in (
|
|
'COMP', 'COMP-3', 'COMP-5', 'BINARY', 'PACKED-DECIMAL', 'DISPLAY',
|
|
):
|
|
result['usage'] = a.upper()
|
|
return result if result else None
|
|
|
|
def pic_clause(self, *args):
|
|
return {'pic': str(args[-1])}
|
|
|
|
def usage_clause(self, token):
|
|
return {'usage': str(token)}
|
|
|
|
def value_clause(self, *args):
|
|
values = []
|
|
for a in args:
|
|
if isinstance(a, str) and a.upper() in ('VALUE', 'IS'):
|
|
continue
|
|
val = str(a).strip("'").strip('"')
|
|
values.append(val)
|
|
return {'value': values[0], 'values': values} if values else {'value': None}
|
|
|
|
def value_literal(self, *args):
|
|
if args:
|
|
return str(args[-1])
|
|
return ''
|
|
|
|
def occurs_clause(self, *args):
|
|
result = {'occurs': int(args[0])}
|
|
if len(args) >= 2:
|
|
result['depends'] = str(args[1])
|
|
return result
|
|
|
|
def redefines_clause(self, *args):
|
|
return {'redefines': str(args[-1])}
|
|
|
|
def level_num(self, token):
|
|
return token
|
|
|
|
def NAME(self, token):
|
|
return str(token)
|
|
|
|
def PICTURE_STRING(self, token):
|
|
return str(token)
|
|
|
|
def INT(self, token):
|
|
return int(token)
|
|
|
|
|
|
# 鈹€鈹€ PIC Parser 鈹€鈹€
|
|
|
|
def _expand_pic(s: str) -> str:
|
|
result = ''
|
|
i = 0
|
|
while i < len(s):
|
|
if s[i] == '(':
|
|
j = s.find(')', i)
|
|
if j > i + 1:
|
|
count = int(s[i + 1:j])
|
|
if result:
|
|
result += result[-1] * (count - 1)
|
|
i = j + 1
|
|
continue
|
|
result += s[i]
|
|
i += 1
|
|
return result
|
|
|
|
|
|
def parse_pic(pic_str: str) -> PicInfo:
|
|
info = PicInfo()
|
|
s = pic_str.upper().strip()
|
|
if not s:
|
|
return info
|
|
if s.startswith('S'):
|
|
info.signed = True
|
|
s = s[1:]
|
|
expanded = _expand_pic(s)
|
|
if expanded[0] == '9':
|
|
info.type = 'numeric'
|
|
if 'V' in expanded:
|
|
parts = expanded.split('V')
|
|
info.digits = parts[0].count('9')
|
|
info.decimal = parts[1].count('9')
|
|
else:
|
|
info.digits = expanded.count('9')
|
|
info.decimal = 0
|
|
elif expanded[0] == 'X':
|
|
info.type = 'alphanumeric'
|
|
info.length = len(expanded)
|
|
elif expanded[0] == 'A':
|
|
info.type = 'alphabetic'
|
|
info.length = len(expanded)
|
|
elif expanded[0] in ('Z', '*', '$', '+', '-'):
|
|
info.type = 'numeric-edited'
|
|
info.digits = expanded.count('9')
|
|
if 'V' in expanded:
|
|
info.decimal = expanded.split('V')[1].count('9')
|
|
elif '.' in expanded:
|
|
info.decimal = expanded.split('.')[1].count('9')
|
|
info.length = len(expanded)
|
|
elif expanded.endswith('CR') or expanded.endswith('DB'):
|
|
info.type = 'numeric-edited'
|
|
stripped = expanded[:-2]
|
|
info.digits = stripped.count('9')
|
|
if 'V' in stripped:
|
|
info.decimal = stripped.split('V')[1].count('9')
|
|
elif '.' in stripped:
|
|
info.decimal = stripped.split('.')[1].count('9')
|
|
info.length = len(expanded)
|
|
else:
|
|
info.type = 'alphanumeric'
|
|
info.length = len(expanded)
|
|
return info
|
|
|
|
|
|
# 鈹€鈹€ DATA DIVISION 鍏ュ彛 鈹€鈹€
|
|
|
|
def parse_data_division(data_div_text: str) -> list[FieldDef]:
|
|
"""??DATA DIVISION???FieldDef????PIC???"""
|
|
grammar = _get_grammar()
|
|
parser = Lark(grammar, parser='earley', lexer='dynamic')
|
|
tree = parser.parse(data_div_text)
|
|
|
|
transformer = DataTransformer()
|
|
raw = transformer.transform(tree)
|
|
|
|
result = []
|
|
for r in raw:
|
|
pic = r.get('pic', '')
|
|
info = parse_pic(pic) if pic else None
|
|
f = FieldDef(
|
|
name=r['name'],
|
|
level=r['level'],
|
|
pic=pic,
|
|
pic_info=info,
|
|
is_filler=r.get('is_filler', False),
|
|
occurs_count=r.get('occurs', 0),
|
|
occurs_depending=r.get('occurs_depending'),
|
|
redefines=r.get('redefines'),
|
|
usage=r.get('usage'),
|
|
value=r.get('value'),
|
|
values=r.get('values'),
|
|
is_88=r.get('is_88', False),
|
|
parent=r.get('parent'),
|
|
section=r.get('section'),
|
|
)
|
|
result.append(f)
|
|
return result
|
|
|
|
|
|
# 鈹€鈹€ FILE-CONTROL / FILE SECTION / OPEN 瑙ｆ瀽 鈹€鈹€
|
|
|
|
|
|
def parse_file_control(source: str) -> dict:
|
|
"""Parse FILE-CONTROL paragraph.
|
|
|
|
Returns dict:
|
|
{filename: {"assign_to": str, "organization": str | None}}
|
|
"""
|
|
m = re.search(r'FILE-CONTROL\.(.*?)(?=DATA\s+DIVISION|\Z)', source, re.DOTALL | re.IGNORECASE)
|
|
if not m:
|
|
return {}
|
|
fc = m.group(1)
|
|
result = {}
|
|
for sel_m in re.finditer(
|
|
r'SELECT\s+(\w[\w-]*)\s+[^.]*?\bASSIGN\s+TO\s+(["\'])(.*?)\2',
|
|
fc, re.IGNORECASE
|
|
):
|
|
fname = sel_m.group(1).upper()
|
|
assign_to = sel_m.group(3).upper()
|
|
# Extract ORGANIZATION clause within this SELECT statement
|
|
org_m = re.search(
|
|
r'ORGANIZATION\s+(?:IS\s+)?(\w[\w-]*)',
|
|
sel_m.group(0), re.IGNORECASE
|
|
)
|
|
org = org_m.group(1).upper() if org_m else None
|
|
result[fname] = {
|
|
"assign_to": assign_to,
|
|
"organization": org,
|
|
}
|
|
return result
|
|
|
|
|
|
def parse_file_section(source: str) -> dict:
|
|
"""?? FILE SECTION??? {?????: [01?????...]}"""
|
|
m = re.search(r'FILE\s+SECTION\.(.*?)(?=WORKING-STORAGE\s+SECTION|LINKAGE\s+SECTION|\Z)',
|
|
source, re.DOTALL | re.IGNORECASE)
|
|
if not m:
|
|
return {}
|
|
fs = m.group(1)
|
|
result = {}
|
|
# FD 和 SD 条目
|
|
blocks = re.split(r'\n\s*(?=(?:FD|SD)\s+)', fs.strip())
|
|
for block in blocks:
|
|
m = re.match(r'(FD|SD)\s+(\w[\w-]*)', block, re.IGNORECASE)
|
|
if not m:
|
|
continue
|
|
entry_type = m.group(1).upper() # "FD" or "SD"
|
|
name = m.group(2).upper()
|
|
# 找 01 层记录
|
|
recs = re.findall(r'^\s*0{0,1}1\s+(\w[\w-]*)', block, re.MULTILINE)
|
|
result[name] = [r.upper() for r in recs]
|
|
return result
|
|
|
|
|
|
def scan_open_statements(source: str) -> dict:
|
|
"""?? OPEN ????? {?????: 'INPUT'|'OUTPUT'|'I-O'}"""
|
|
dirs = {}
|
|
for m in re.finditer(
|
|
r'OPEN\s+((?:INPUT|OUTPUT|I-O)\s+[\w\s-]+'
|
|
r'(?:\s+(?:INPUT|OUTPUT|I-O)\s+[\w\s-]+)*)',
|
|
source, re.IGNORECASE
|
|
):
|
|
full = m.group(1)
|
|
for seg_m in re.finditer(
|
|
r'(INPUT|OUTPUT|I-O)\s+([\w\s-]+)', full, re.IGNORECASE
|
|
):
|
|
direction = seg_m.group(1).upper()
|
|
for fname in re.findall(r'\w[\w-]*', seg_m.group(2)):
|
|
if fname.upper() not in ('INPUT', 'OUTPUT', 'I-O'):
|
|
dirs[fname.upper()] = direction
|
|
return dirs
|