3b150b6c54
Grammar fixes: 1. COPY regex: handle quoted names COPY "STD-REC.CPY" 2. Quoted name strip: remove quotes before file lookup 3. VALUE clause: support comma-separated 88-level values 4. PIC STRING: support decimal dot (ZZ9.99 -> PICTURE_STRING.99 + DOT) 5. LEVEL: use INT for level number (fixes 05/01/77 all levels) Results on 58 telecom billing COBOL programs: - Parse OK: 54/58 (93%) - Parse fail: 4 (special chars: TAB, X'01', U'NNNN', &) - Classification known issue: matching programs misclassified as '文件编成' because FILE-CONTROL keyword overrides matching signals (requires rule engine priority fix - separate issue) Co-Authored-By: Claude <noreply@anthropic.com>
40 lines
1.6 KiB
Plaintext
40 lines
1.6 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: INT
|
|
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_list
|
|
value_list: value_literal (","? 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 ("TO" 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]|[0-4][0-9]|49|77|88|[0-9]+/
|
|
NAME: /[A-Z][A-Z0-9-]*/i
|
|
PICTURE_STRING: /[0-9A-Z()+,\-*\/V]+(?:\.[0-9A-Z()+,\-*\/V]+)?/i
|
|
INT: /[0-9]+/
|
|
DOT: /\./
|
|
%import common.SIGNED_NUMBER
|
|
%import common.ESCAPED_STRING -> STRING
|
|
%import common.WS
|
|
%ignore WS
|