dataspector 1.0.0__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -0,0 +1,324 @@
1
+ """Enums, compiled regular expressions, and lookup tables for :mod:`dataspector.coboller`."""
2
+
3
+ from __future__ import annotations
4
+
5
+ import re
6
+ from enum import StrEnum
7
+
8
+
9
+ class Usage(StrEnum):
10
+ """COBOL ``USAGE`` storage representations."""
11
+
12
+ DISPLAY = "DISPLAY"
13
+ DISPLAY_1 = "DISPLAY-1"
14
+ COMP = "COMP"
15
+ COMP_1 = "COMP-1"
16
+ COMP_2 = "COMP-2"
17
+ COMP_3 = "COMP-3"
18
+ COMP_5 = "COMP-5"
19
+ COMP_6 = "COMP-6"
20
+ COMP_X = "COMP-X"
21
+ BINARY_CHAR = "BINARY-CHAR"
22
+ BINARY_SHORT = "BINARY-SHORT"
23
+ BINARY_LONG = "BINARY-LONG"
24
+ BINARY_DOUBLE = "BINARY-DOUBLE"
25
+ FLOAT_SHORT = "FLOAT-SHORT"
26
+ FLOAT_LONG = "FLOAT-LONG"
27
+ NATIONAL = "NATIONAL"
28
+ UTF_8 = "UTF-8"
29
+ BIT = "BIT"
30
+ POINTER = "POINTER"
31
+ PROCEDURE_POINTER = "PROCEDURE-POINTER"
32
+ FUNCTION_POINTER = "FUNCTION-POINTER"
33
+ INDEX = "INDEX"
34
+
35
+
36
+ class SignMode(StrEnum):
37
+ """COBOL sign encoding modes for ``USAGE DISPLAY`` signed numeric items."""
38
+
39
+ NONE = "NONE"
40
+ TRAILING_OVERPUNCH = "TRAILING"
41
+ LEADING_OVERPUNCH = "LEADING"
42
+ TRAILING_SEPARATE = "TRAILING SEPARATE"
43
+ LEADING_SEPARATE = "LEADING SEPARATE"
44
+
45
+
46
+ class DataCategory(StrEnum):
47
+ """COBOL data category of an elementary item."""
48
+
49
+ ALPHABETIC = "ALPHABETIC"
50
+ ALPHANUMERIC = "ALPHANUMERIC"
51
+ NATIONAL = "NATIONAL"
52
+ UTF8 = "UTF8"
53
+ DBCS = "DBCS"
54
+ BIT = "BIT"
55
+ INTEGER = "INTEGER"
56
+ DECIMAL = "DECIMAL"
57
+ NUMERIC_EDITED = "NUMERIC_EDITED"
58
+ EXTERNAL_FLOAT = "EXTERNAL_FLOAT"
59
+ BINARY = "BINARY"
60
+ PACKED_DECIMAL = "PACKED_DECIMAL"
61
+ PACKED_UNSIGNED = "PACKED_UNSIGNED"
62
+ FLOAT = "FLOAT"
63
+ POINTER = "POINTER"
64
+ INDEX = "INDEX"
65
+
66
+
67
+ FieldKind = DataCategory
68
+
69
+ USAGE_ALIASES: dict[str, Usage] = {
70
+ "DISPLAY": Usage.DISPLAY,
71
+ "DISPLAY-1": Usage.DISPLAY_1,
72
+ "COMP": Usage.COMP,
73
+ "COMPUTATIONAL": Usage.COMP,
74
+ "COMP-4": Usage.COMP,
75
+ "COMPUTATIONAL-4": Usage.COMP,
76
+ "BINARY": Usage.COMP,
77
+ "COMP-1": Usage.COMP_1,
78
+ "COMPUTATIONAL-1": Usage.COMP_1,
79
+ "COMP-2": Usage.COMP_2,
80
+ "COMPUTATIONAL-2": Usage.COMP_2,
81
+ "COMP-3": Usage.COMP_3,
82
+ "COMPUTATIONAL-3": Usage.COMP_3,
83
+ "PACKED-DECIMAL": Usage.COMP_3,
84
+ "COMP-5": Usage.COMP_5,
85
+ "COMPUTATIONAL-5": Usage.COMP_5,
86
+ "COMP-6": Usage.COMP_6,
87
+ "COMPUTATIONAL-6": Usage.COMP_6,
88
+ "COMP-X": Usage.COMP_X,
89
+ "COMPUTATIONAL-X": Usage.COMP_X,
90
+ "BINARY-CHAR": Usage.BINARY_CHAR,
91
+ "BINARY-SHORT": Usage.BINARY_SHORT,
92
+ "BINARY-LONG": Usage.BINARY_LONG,
93
+ "BINARY-DOUBLE": Usage.BINARY_DOUBLE,
94
+ "FLOAT-SHORT": Usage.FLOAT_SHORT,
95
+ "FLOAT-LONG": Usage.FLOAT_LONG,
96
+ "NATIONAL": Usage.NATIONAL,
97
+ "UTF-8": Usage.UTF_8,
98
+ "BIT": Usage.BIT,
99
+ "POINTER": Usage.POINTER,
100
+ "PROCEDURE-POINTER": Usage.PROCEDURE_POINTER,
101
+ "FUNCTION-POINTER": Usage.FUNCTION_POINTER,
102
+ "INDEX": Usage.INDEX,
103
+ }
104
+
105
+ BINARY_USAGES: frozenset[Usage] = frozenset(
106
+ {
107
+ Usage.DISPLAY_1,
108
+ Usage.COMP,
109
+ Usage.COMP_1,
110
+ Usage.COMP_2,
111
+ Usage.COMP_3,
112
+ Usage.COMP_5,
113
+ Usage.COMP_6,
114
+ Usage.COMP_X,
115
+ Usage.BINARY_CHAR,
116
+ Usage.BINARY_SHORT,
117
+ Usage.BINARY_LONG,
118
+ Usage.BINARY_DOUBLE,
119
+ Usage.FLOAT_SHORT,
120
+ Usage.FLOAT_LONG,
121
+ Usage.NATIONAL,
122
+ Usage.UTF_8,
123
+ Usage.BIT,
124
+ Usage.POINTER,
125
+ Usage.PROCEDURE_POINTER,
126
+ Usage.FUNCTION_POINTER,
127
+ Usage.INDEX,
128
+ }
129
+ )
130
+
131
+ SELF_SIZED_USAGES: frozenset[Usage] = frozenset(
132
+ {
133
+ Usage.COMP_1,
134
+ Usage.COMP_2,
135
+ Usage.FLOAT_SHORT,
136
+ Usage.FLOAT_LONG,
137
+ Usage.BINARY_CHAR,
138
+ Usage.BINARY_SHORT,
139
+ Usage.BINARY_LONG,
140
+ Usage.BINARY_DOUBLE,
141
+ Usage.POINTER,
142
+ Usage.PROCEDURE_POINTER,
143
+ Usage.FUNCTION_POINTER,
144
+ Usage.INDEX,
145
+ }
146
+ )
147
+
148
+ FIXED_BINARY_SIZES: dict[Usage, int] = {
149
+ Usage.BINARY_CHAR: 1,
150
+ Usage.BINARY_SHORT: 2,
151
+ Usage.BINARY_LONG: 4,
152
+ Usage.BINARY_DOUBLE: 8,
153
+ }
154
+
155
+ PIC_REPEAT = re.compile(r"(?P<section>[^\s()])\((?P<repeat>\d+)\)")
156
+ PIC_FLOAT = re.compile(r"^S?[9P]*V[9P]+$|^S?[9Z]*[.V][9Z]+$")
157
+ PIC_INT = re.compile(r"^S?[9P]+$")
158
+ PIC_NUMERIC_PURE = re.compile(r"^S?[9PV]+$")
159
+ PIC_EXTERNAL_FLOAT = re.compile(r"^[S+-]?9*(?:[.V,]9*)?E[+-]?9+$")
160
+ PIC_ALPHA_ONLY = re.compile(r"^A+$")
161
+ PIC_NATIONAL_ONLY = re.compile(r"^N+$")
162
+ PIC_DBCS_ONLY = re.compile(r"^G+$")
163
+ PIC_UTF8_ONLY = re.compile(r"^U+$")
164
+ PIC_BIT_ONLY = re.compile(r"^1+$")
165
+ PIC_EDITED_MARKERS = re.compile(r"[Z*$.,+\-]|CR|DB")
166
+
167
+ LEVEL_START_RE = re.compile(r"^\s*(?P<level>\d{2})\b(?P<rest>.*)$")
168
+ REDEFINES_RE = re.compile(r"\bREDEFINES\s+(?P<redefines>[A-Z0-9_-]+)", re.I)
169
+ OCCURS_RE = re.compile(
170
+ r"\bOCCURS\s+(?:(?P<min>\d+)\s+TO\s+)?(?P<occurs>\d+)(?:\s+TIMES)?(?:\s+DEPENDING\s+(?:ON\s+)?(?P<depending>[A-Z0-9_-]+))?",
171
+ re.I,
172
+ )
173
+ INDEXED_RE = re.compile(r"\bINDEXED\s+(?:BY\s+)?(?P<indexedby>[A-Z0-9_-]+)", re.I)
174
+ PIC_RE = re.compile(r"\b(?:PICTURE|PIC)\s+(?:IS\s+)?(?P<pic>\S+)", re.I)
175
+ BYTE_LENGTH_RE = re.compile(r"\bBYTE-LENGTH\s+(?P<byte_length>\d+)\b", re.I)
176
+ USAGE_RE = re.compile(
177
+ r"\b(?:USAGE\s+(?:IS\s+)?)?(?P<usage>"
178
+ r"COMPUTATIONAL-[1-6X]|COMP-[1-6X]|COMPUTATIONAL|COMP|"
179
+ r"PACKED-DECIMAL|BINARY-DOUBLE|BINARY-LONG|BINARY-SHORT|BINARY-CHAR|BINARY|"
180
+ r"FLOAT-SHORT|FLOAT-LONG|DISPLAY-1|DISPLAY|"
181
+ r"PROCEDURE-POINTER|FUNCTION-POINTER|POINTER|NATIONAL|UTF-8|BIT|INDEX)\b",
182
+ re.I,
183
+ )
184
+ BINARY_SIGN_QUALIFIER_RE = re.compile(
185
+ r"\bBINARY-(?:CHAR|SHORT|LONG|DOUBLE)\s+(?P<qual>SIGNED|UNSIGNED)\b",
186
+ re.I,
187
+ )
188
+ SIGN_RE = re.compile(
189
+ r"\bSIGN\s+(?:IS\s+)?(?P<pos>LEADING|TRAILING)(?:\s+(?P<sep>SEPARATE)(?:\s+CHARACTER)?)?",
190
+ re.I,
191
+ )
192
+ VALUE_RE = re.compile(
193
+ r"\bVALUES?\s+(?:IS\s+|ARE\s+)?(?P<value>.+?)(?=\s+(?:REDEFINES|OCCURS|PIC|PICTURE|USAGE|SIGN|BLANK|JUSTIFIED|JUST|SYNC|SYNCHRONIZED|COMP|BINARY|PACKED-DECIMAL|DISPLAY|NATIONAL|UTF-8|BIT|FLOAT-SHORT|FLOAT-LONG|POINTER|PROCEDURE-POINTER|FUNCTION-POINTER|INDEX|BYTE-LENGTH)\b|$)",
194
+ re.I,
195
+ )
196
+ BLANK_ZERO_RE = re.compile(r"\bBLANK\s+(?:WHEN\s+)?ZEROS?\b", re.I)
197
+ JUSTIFIED_RE = re.compile(r"\bJUST(?:IFIED)?(?:\s+RIGHT)?\b", re.I)
198
+ DECIMAL_COMMA_RE = re.compile(r"\bDECIMAL-POINT\s+IS\s+COMMA\b", re.I)
199
+
200
+ SKIP_LINE_PREFIXES: tuple[str, ...] = (
201
+ "IDENTIFICATION",
202
+ "ID ",
203
+ "PROGRAM-ID",
204
+ "ENVIRONMENT",
205
+ "CONFIGURATION",
206
+ "INPUT-OUTPUT",
207
+ "FILE-CONTROL",
208
+ "SELECT ",
209
+ "DATA ",
210
+ "FILE ",
211
+ "WORKING-STORAGE",
212
+ "LOCAL-STORAGE",
213
+ "LINKAGE ",
214
+ "FD ",
215
+ "SD ",
216
+ "LABEL ",
217
+ "RECORD ",
218
+ "BLOCK ",
219
+ "PROCEDURE",
220
+ "STOP ",
221
+ "EXIT",
222
+ "COPY ",
223
+ )
224
+
225
+ CLAUSE_KEYWORDS: frozenset[str] = frozenset(
226
+ {
227
+ "PIC",
228
+ "PICTURE",
229
+ "USAGE",
230
+ "REDEFINES",
231
+ "OCCURS",
232
+ "VALUE",
233
+ "VALUES",
234
+ "SIGN",
235
+ "COMP",
236
+ "COMP-1",
237
+ "COMP-2",
238
+ "COMP-3",
239
+ "COMP-4",
240
+ "COMP-5",
241
+ "COMP-6",
242
+ "COMP-X",
243
+ "COMPUTATIONAL",
244
+ "BINARY",
245
+ "BINARY-CHAR",
246
+ "BINARY-SHORT",
247
+ "BINARY-LONG",
248
+ "BINARY-DOUBLE",
249
+ "FLOAT-SHORT",
250
+ "FLOAT-LONG",
251
+ "PACKED-DECIMAL",
252
+ "DISPLAY",
253
+ "DISPLAY-1",
254
+ "NATIONAL",
255
+ "UTF-8",
256
+ "BIT",
257
+ "POINTER",
258
+ "PROCEDURE-POINTER",
259
+ "FUNCTION-POINTER",
260
+ "INDEX",
261
+ }
262
+ )
263
+
264
+ ASCII_OVERPUNCH_POS: dict[str, str] = {
265
+ "{": "0",
266
+ "A": "1",
267
+ "B": "2",
268
+ "C": "3",
269
+ "D": "4",
270
+ "E": "5",
271
+ "F": "6",
272
+ "G": "7",
273
+ "H": "8",
274
+ "I": "9",
275
+ }
276
+ ASCII_OVERPUNCH_NEG: dict[str, str] = {
277
+ "}": "0",
278
+ "J": "1",
279
+ "K": "2",
280
+ "L": "3",
281
+ "M": "4",
282
+ "N": "5",
283
+ "O": "6",
284
+ "P": "7",
285
+ "Q": "8",
286
+ "R": "9",
287
+ "p": "0",
288
+ "q": "1",
289
+ "r": "2",
290
+ "s": "3",
291
+ "t": "4",
292
+ "u": "5",
293
+ "v": "6",
294
+ "w": "7",
295
+ "x": "8",
296
+ "y": "9",
297
+ }
298
+ DIGIT_TO_ASCII_POS: dict[str, str] = {v: k for k, v in ASCII_OVERPUNCH_POS.items()}
299
+ DIGIT_TO_ASCII_NEG: dict[str, str] = {
300
+ "0": "}",
301
+ "1": "J",
302
+ "2": "K",
303
+ "3": "L",
304
+ "4": "M",
305
+ "5": "N",
306
+ "6": "O",
307
+ "7": "P",
308
+ "8": "Q",
309
+ "9": "R",
310
+ }
311
+
312
+ EBCDIC_ENCODINGS: frozenset[str] = frozenset(
313
+ {
314
+ "cp037",
315
+ "cp273",
316
+ "cp500",
317
+ "cp875",
318
+ "cp1026",
319
+ "cp1140",
320
+ "ebcdic",
321
+ "ibm037",
322
+ "ibm500",
323
+ }
324
+ )