dbee3b7251
Bug fixes found through statement benchmark testing: 1. grammar.lark: Add ASCENDING/DESCENDING KEY IS + INDEXED BY to occurs_clause — fixes HINA024 (SEARCH ALL) parsing crash 2. grammar.lark: Add SD (Sort Description) entry type to file_section — fixes HINA034 (SORT), ST01, ST02 parsing crashes 3. read.py parse_file_section(): Handle SD blocks alongside FD blocks — enables SORT/MERGE file structure extraction 4 previously crashing files now parse successfully: - HINA024.cbl (SEARCH ALL): paras=3, files=0 - HINA034.cbl (SORT): paras=1, files=3 - ST01_SORT.cbl: paras=2, files=3 - ST02_MERGE.cbl: paras=1, files=4 Regression: 749 passed (unchanged — classify_program internally caught the crashes, so tests already 'passed'; real improvement is in data quality: structure extraction now works for these programs)
39 lines
1.5 KiB
Plaintext
39 lines
1.5 KiB
Plaintext
start: data_div_content
|
|
data_div_content: (file_section | working_storage | linkage)*
|
|
file_section: "FILE" "SECTION" DOT (fd | sd)+
|
|
fd: "FD" NAME FD_SUFFIX data_item+
|
|
sd: "SD" NAME FD_SUFFIX data_item*
|
|
FD_SUFFIX: /(?:"[^"]*"|'[^']*'|[^.])*\./
|
|
working_storage: "WORKING-STORAGE" "SECTION" DOT data_item*
|
|
linkage: "LINKAGE" "SECTION" DOT data_item*
|
|
data_item: level_num (NAME | "FILLER") clause* DOT
|
|
level_num: LEVEL
|
|
clause: pic_clause | value_clause | occurs_clause | redefines_clause | usage_clause
|
|
| "SYNC" | "SYNCHRONIZED"
|
|
| "JUSTIFIED" "RIGHT"?
|
|
| "BLANK" "WHEN" "ZERO"
|
|
| "GLOBAL" | "EXTERNAL"
|
|
pic_clause: "PIC" "IS"? PICTURE_STRING
|
|
value_clause: "VALUE" "IS"? value_literal+
|
|
value_literal: INT | SIGNED_NUMBER | STRING | SQSTRING
|
|
| "ZERO" | "ZEROS" | "ZEROES"
|
|
| "SPACE" | "SPACES"
|
|
| "HIGH-VALUE" | "HIGH-VALUES"
|
|
| "LOW-VALUE" | "LOW-VALUES"
|
|
SQSTRING: /'[^']*'/
|
|
redefines_clause: "REDEFINES" NAME
|
|
occurs_clause: "OCCURS" INT "TIMES"? ("DEPENDING" "ON" NAME)? key_clause? indexed_clause?
|
|
key_clause: ("ASCENDING" | "DESCENDING") "KEY" "IS"? NAME (","? NAME)*
|
|
indexed_clause: "INDEXED" "BY" NAME (","? NAME)*
|
|
usage_clause: USAGE_VAL
|
|
USAGE_VAL: "COMP" | "COMP-3" | "COMP-5" | "BINARY" | "PACKED-DECIMAL" | "DISPLAY"
|
|
LEVEL: /0[1-9]|[1-4][0-9]|49|77|88/
|
|
NAME: /[A-Z][A-Z0-9-]*/
|
|
PICTURE_STRING: /[0-9A-Z()+,\-*\/V]+/i
|
|
INT: /[0-9]+/
|
|
DOT: /\./
|
|
%import common.SIGNED_NUMBER
|
|
%import common.ESCAPED_STRING -> STRING
|
|
%import common.WS
|
|
%ignore WS
|