numbers-parser 4.18.1__tar.gz → 4.18.2__tar.gz

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.
Files changed (98) hide show
  1. {numbers_parser-4.18.1/src/numbers_parser.egg-info → numbers_parser-4.18.2}/PKG-INFO +1 -1
  2. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/pyproject.toml +7 -4
  3. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/_csv2numbers.py +10 -10
  4. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/_unpack_numbers.py +7 -0
  5. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/constants.py +5 -1
  6. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/iwafile.py +29 -0
  7. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/model.py +88 -90
  8. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/xrefs.py +2 -240
  9. {numbers_parser-4.18.1 → numbers_parser-4.18.2/src/numbers_parser.egg-info}/PKG-INFO +1 -1
  10. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/tests/test_cat_numbers.py +5 -0
  11. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/tests/test_coverage.py +54 -3
  12. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/tests/test_unpack_numbers.py +31 -0
  13. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/LICENSE.rst +0 -0
  14. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/README.md +0 -0
  15. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/setup.cfg +0 -0
  16. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/__init__.py +0 -0
  17. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/_cat_numbers.py +0 -0
  18. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/bullets.py +0 -0
  19. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/cell.py +0 -0
  20. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/containers.py +0 -0
  21. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/currencies.py +0 -0
  22. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/data/empty.numbers +0 -0
  23. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/document.py +0 -0
  24. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/exceptions.py +0 -0
  25. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/experimental.py +0 -0
  26. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/formula.py +0 -0
  27. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/generated/TNArchives_pb2.py +0 -0
  28. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/generated/TNArchives_sos_pb2.py +0 -0
  29. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/generated/TNCommandArchives_pb2.py +0 -0
  30. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/generated/TNCommandArchives_sos_pb2.py +0 -0
  31. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/generated/TSAArchives_pb2.py +0 -0
  32. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/generated/TSAArchives_sos_pb2.py +0 -0
  33. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/generated/TSACommandArchives_sos_pb2.py +0 -0
  34. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/generated/TSCEArchives_pb2.py +0 -0
  35. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/generated/TSCH3DArchives_pb2.py +0 -0
  36. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/generated/TSCHArchives_Common_pb2.py +0 -0
  37. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/generated/TSCHArchives_GEN_pb2.py +0 -0
  38. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/generated/TSCHArchives_pb2.py +0 -0
  39. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/generated/TSCHArchives_sos_pb2.py +0 -0
  40. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/generated/TSCHCommandArchives_pb2.py +0 -0
  41. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/generated/TSCHPreUFFArchives_pb2.py +0 -0
  42. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/generated/TSCKArchives_pb2.py +0 -0
  43. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/generated/TSCKArchives_sos_pb2.py +0 -0
  44. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/generated/TSDArchives_pb2.py +0 -0
  45. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/generated/TSDArchives_sos_pb2.py +0 -0
  46. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/generated/TSDCommandArchives_pb2.py +0 -0
  47. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/generated/TSKArchives_pb2.py +0 -0
  48. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/generated/TSPArchiveMessages_pb2.py +0 -0
  49. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/generated/TSPDatabaseMessages_pb2.py +0 -0
  50. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/generated/TSPMessages_pb2.py +0 -0
  51. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/generated/TSSArchives_pb2.py +0 -0
  52. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/generated/TSSArchives_sos_pb2.py +0 -0
  53. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/generated/TSTArchives_pb2.py +0 -0
  54. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/generated/TSTArchives_sos_pb2.py +0 -0
  55. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/generated/TSTCommandArchives_pb2.py +0 -0
  56. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/generated/TSTStylePropertyArchiving_pb2.py +0 -0
  57. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/generated/TSWPArchives_pb2.py +0 -0
  58. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/generated/TSWPArchives_sos_pb2.py +0 -0
  59. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/generated/TSWPCommandArchives_pb2.py +0 -0
  60. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/generated/__init__.py +0 -0
  61. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/generated/fontmap.py +0 -0
  62. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/generated/functionmap.py +0 -0
  63. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/generated/mapping.py +0 -0
  64. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/iwork.py +0 -0
  65. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/numbers_cache.py +0 -0
  66. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/numbers_uuid.py +0 -0
  67. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser/roman.py +0 -0
  68. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser.egg-info/SOURCES.txt +0 -0
  69. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser.egg-info/dependency_links.txt +0 -0
  70. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser.egg-info/entry_points.txt +0 -0
  71. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser.egg-info/requires.txt +0 -0
  72. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/src/numbers_parser.egg-info/top_level.txt +0 -0
  73. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/tests/test_all_formulas.py +0 -0
  74. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/tests/test_api_change.py +0 -0
  75. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/tests/test_borders.py +0 -0
  76. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/tests/test_bullets.py +0 -0
  77. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/tests/test_categories.py +0 -0
  78. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/tests/test_create_cells.py +0 -0
  79. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/tests/test_csv2numbers.py +0 -0
  80. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/tests/test_currency.py +0 -0
  81. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/tests/test_folder.py +0 -0
  82. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/tests/test_formatting.py +0 -0
  83. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/tests/test_formulas.py +0 -0
  84. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/tests/test_issues.py +0 -0
  85. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/tests/test_large.py +0 -0
  86. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/tests/test_memory_leaks.py +0 -0
  87. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/tests/test_merges.py +0 -0
  88. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/tests/test_package.py +0 -0
  89. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/tests/test_properties.py +0 -0
  90. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/tests/test_roman.py +0 -0
  91. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/tests/test_save.py +0 -0
  92. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/tests/test_slices.py +0 -0
  93. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/tests/test_styles.py +0 -0
  94. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/tests/test_table_size.py +0 -0
  95. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/tests/test_tables.py +0 -0
  96. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/tests/test_unsupported.py +0 -0
  97. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/tests/test_uuids.py +0 -0
  98. {numbers_parser-4.18.1 → numbers_parser-4.18.2}/tests/test_version.py +0 -0
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: numbers-parser
3
- Version: 4.18.1
3
+ Version: 4.18.2
4
4
  Summary: Read and write Apple Numbers spreadsheets
5
5
  Author-email: Jon Connell <python@figsandfudge.com>
6
6
  License-Expression: MIT
@@ -22,7 +22,7 @@ classifiers = [
22
22
  description = "Read and write Apple Numbers spreadsheets"
23
23
  name = "numbers-parser"
24
24
  readme = "README.md"
25
- version = "4.18.1"
25
+ version = "4.18.2"
26
26
 
27
27
  [project.urls]
28
28
  repository = "https://github.com/masaccio/numbers-parser"
@@ -56,7 +56,10 @@ docs = [
56
56
  "sphinx-toolbox>=3.5",
57
57
  "sphinx-nefertiti>=0.7",
58
58
  "sphinx-markdown-builder>=0.6",
59
- "sphinx-copybutton>=0.5",
59
+ "sphinx-copybutton>=0.5.2",
60
+ # Security updates
61
+ "urllib3>=2.6.0",
62
+ "filelock>=3.20.1"
60
63
  ]
61
64
  bootstrap = [
62
65
  "rich>=14.0",
@@ -84,10 +87,10 @@ omit = ["src/numbers_parser/generated/*.py"]
84
87
 
85
88
  [tool.coverage.html]
86
89
  directory = "coverage_html_report"
87
- show_contexts = true
90
+ show_contexts = false
88
91
 
89
92
  [tool.pytest.ini_options]
90
- addopts = "--cov=src/numbers_parser --cov-report=html --cov-report=term-missing:skip-covered --cov-context=test"
93
+ addopts = "--cov=src/numbers_parser --cov-report=html --cov-report=term-missing:skip-covered"
91
94
 
92
95
  [tool.tox]
93
96
  requires = ["tox>=4.0"]
@@ -6,10 +6,10 @@ import argparse
6
6
  import contextlib
7
7
  import csv
8
8
  import re
9
+ import sys
9
10
  from dataclasses import dataclass
10
11
  from datetime import datetime, timezone
11
12
  from pathlib import Path
12
- from sys import exit, stderr
13
13
  from typing import NamedTuple
14
14
 
15
15
  from dateutil.parser import parse
@@ -381,11 +381,11 @@ def main() -> None:
381
381
 
382
382
  if args.version:
383
383
  print(_get_version())
384
- exit(0)
384
+ sys.exit(0)
385
385
  elif len(args.csvfile) == 0:
386
- print("At least one CSV file is required", file=stderr)
387
- parser.print_help(stderr)
388
- exit(1)
386
+ print("At least one CSV file is required", file=sys.stderr)
387
+ parser.print_help(sys.stderr)
388
+ sys.exit(1)
389
389
 
390
390
  if args.output is None:
391
391
  output_filenames = [Path(x).with_suffix(".numbers") for x in args.csvfile]
@@ -393,8 +393,8 @@ def main() -> None:
393
393
  output_filenames = args.output
394
394
 
395
395
  if len(args.csvfile) != len(output_filenames):
396
- print("The numbers of input and output file names do not match", file=stderr)
397
- exit(1)
396
+ print("The numbers of input and output file names do not match", file=sys.tderr)
397
+ sys.exit(1)
398
398
 
399
399
  try:
400
400
  for input_filename, output_filename in zip(args.csvfile, output_filenames):
@@ -414,10 +414,10 @@ def main() -> None:
414
414
  converter.delete_columns(args.delete)
415
415
  converter.save()
416
416
  except RuntimeError as e:
417
- print(e, file=stderr)
418
- exit(1)
417
+ print(e, file=sys.stderr)
418
+ sys.exit(1)
419
419
 
420
420
 
421
- if __name__ == "__main__": # pragma: no cover
421
+ if __name__ == "__main__":
422
422
  # execute only if run as a script
423
423
  main()
@@ -30,6 +30,7 @@ class NumbersUnpacker(IWorkHandler):
30
30
  pretty_storage: bool = False
31
31
  pretty: bool = False
32
32
  compact_json: bool = False
33
+ redact_strings: bool = False
33
34
  output_dir: str = None
34
35
 
35
36
  def store_file(self, filename: str, blob: bytes) -> None:
@@ -41,6 +42,10 @@ class NumbersUnpacker(IWorkHandler):
41
42
  target_path = target_path.replace(".iwa", "")
42
43
  target_path += ".json"
43
44
  with open(target_path, "w") as out:
45
+ if self.redact_strings:
46
+ for chunk in blob.chunks:
47
+ for archive in chunk.archives:
48
+ archive.redact_strings()
44
49
  data = blob.to_dict()
45
50
  if self.hex_uuids or self.pretty:
46
51
  self.prettify_uuids(data)
@@ -123,6 +128,7 @@ def main() -> None:
123
128
  help="Format JSON compactly as possible",
124
129
  )
125
130
  parser.add_argument("--pretty", action="store_true", help="Enable all prettifying options")
131
+ parser.add_argument("--redact", action="store_true", help="Redact strings in the output")
126
132
  parser.add_argument("--output", "-o", help="directory name to unpack into")
127
133
  parser.add_argument("--debug", default=False, action="store_true", help="Enable debug logging")
128
134
  args = parser.parse_args()
@@ -153,6 +159,7 @@ def main() -> None:
153
159
  pretty=args.pretty,
154
160
  pretty_storage=args.pretty_storage,
155
161
  compact_json=args.compact_json,
162
+ redact_strings=args.redact,
156
163
  output_dir=output_dir,
157
164
  ),
158
165
  )
@@ -5,7 +5,8 @@ from math import ceil
5
5
 
6
6
  import enum_tools.documentation
7
7
 
8
- # Path to package date varies by Python version
8
+ # Path to package data varies by Python version so we can
9
+ # only ever generate coverage for one
9
10
  try:
10
11
  from importlib.resources import files
11
12
  except ImportError: # pragma: nocover
@@ -165,6 +166,9 @@ DATETIME_FIELD_MAP = OrderedDict(
165
166
  ],
166
167
  )
167
168
 
169
+ # From TSCEArchives
170
+ COLON_TRACT_NODE = 67
171
+
168
172
 
169
173
  class CellType(IntEnum):
170
174
  EMPTY = 1
@@ -228,6 +228,35 @@ class IWAArchiveSegment:
228
228
  + [obj.SerializeToString() for obj in self.objects],
229
229
  )
230
230
 
231
+ def redact_strings(self) -> None:
232
+ str_index = 0
233
+
234
+ def redact_message(message):
235
+ nonlocal str_index
236
+
237
+ if isinstance(message, ProtobufPatch):
238
+ message = message.data
239
+
240
+ for field, value in message.ListFields():
241
+ if field.type == field.TYPE_MESSAGE:
242
+ if field.is_repeated:
243
+ for item in value:
244
+ redact_message(item)
245
+ else:
246
+ redact_message(value)
247
+ elif field.type == field.TYPE_STRING:
248
+ if field.is_repeated:
249
+ for i in range(len(value)):
250
+ str_index += 1
251
+ value[i] = f"REDACT-{str_index}"
252
+ else:
253
+ str_index += 1
254
+ setattr(message, field.name, f"REDACT-{str_index}")
255
+
256
+ for obj in self.objects:
257
+ redact_message(obj)
258
+ _ = str_index
259
+
231
260
 
232
261
  def message_to_dict(message):
233
262
  if hasattr(message, "to_dict"):
@@ -1,15 +1,15 @@
1
1
  from __future__ import annotations
2
2
 
3
+ import logging
3
4
  import re
4
5
  from array import array
5
6
  from collections import defaultdict
6
- from datetime import timedelta
7
+ from datetime import datetime, timedelta
7
8
  from hashlib import sha1
8
9
  from itertools import chain
9
10
  from math import floor
10
11
  from pathlib import Path
11
12
  from struct import pack
12
- from typing import TYPE_CHECKING
13
13
  from warnings import warn
14
14
 
15
15
  from numbers_parser.bullets import (
@@ -37,6 +37,7 @@ from numbers_parser.cell import (
37
37
  )
38
38
  from numbers_parser.constants import (
39
39
  ALLOWED_FORMATTING_PARAMETERS,
40
+ COLON_TRACT_NODE,
40
41
  CUSTOM_FORMAT_TYPE_MAP,
41
42
  CUSTOM_TEXT_PLACEHOLDER,
42
43
  DEFAULT_COLUMN_WIDTH,
@@ -83,8 +84,8 @@ from numbers_parser.numbers_cache import Cacheable, cache
83
84
  from numbers_parser.numbers_uuid import NumbersUUID, uuid_to_hex
84
85
  from numbers_parser.xrefs import CellRange, ScopedNameRefCache
85
86
 
86
- if TYPE_CHECKING:
87
- from datetime import datetime
87
+ logger = logging.getLogger(__name__)
88
+ debug = logger.debug
88
89
 
89
90
 
90
91
  def create_font_name_map(font_map: dict) -> dict:
@@ -829,6 +830,14 @@ class _NumbersModel(Cacheable):
829
830
  return self.objects[ce_id]
830
831
 
831
832
  def add_merge_range(self, table_id, row_start, row_end, col_start, col_end) -> None:
833
+ debug(
834
+ "Add merge: table_id=%d, [%d,%d]->[%d,%d]",
835
+ table_id,
836
+ row_start,
837
+ row_end,
838
+ col_start,
839
+ col_end,
840
+ )
832
841
  size = (row_end - row_start + 1, col_end - col_start + 1)
833
842
  for row in range(row_start, row_end + 1):
834
843
  for col in range(col_start, col_end + 1):
@@ -840,33 +849,42 @@ class _NumbersModel(Cacheable):
840
849
  self._merge_cells[table_id].add_anchor(row_start, col_start, size)
841
850
 
842
851
  @cache()
843
- def calculate_merges_using_formula_stores(self, table_id) -> None:
852
+ def calculate_merges_using_formula_stores(self, table_id) -> int:
853
+ def range_end(archive: object) -> int:
854
+ # range_end is optional
855
+ return archive.range_end if archive.HasField("range_end") else archive.range_begin
856
+
844
857
  table_model = self.objects[table_id]
845
858
  formulas = table_model.merge_owner.formula_store.formulas
846
859
  if len(formulas) == 0:
847
- return
860
+ debug("table=%s: no formula store merges", self.table_name(table_id))
861
+ return 0
848
862
 
863
+ merge_count = 0
849
864
  for formula in formulas:
850
865
  node = formula.formula.AST_node_array.AST_node[0]
851
- # COLON_TRACT_NODE=67
852
- if node.AST_node_type != 67:
866
+ if node.AST_node_type != COLON_TRACT_NODE:
853
867
  continue
868
+ merge_count += 1
854
869
  self.add_merge_range(
855
870
  table_id,
856
871
  node.AST_colon_tract.absolute_row[0].range_begin,
857
- node.AST_colon_tract.absolute_row[0].range_end,
872
+ range_end(node.AST_colon_tract.absolute_row[0]),
858
873
  node.AST_colon_tract.absolute_column[0].range_begin,
859
- node.AST_colon_tract.absolute_column[0].range_end,
874
+ range_end(node.AST_colon_tract.absolute_column[0]),
860
875
  )
876
+ debug("table=%s: %d formula store merges found", self.table_name(table_id), merge_count)
877
+ return merge_count
861
878
 
862
879
  @cache()
863
- def calculate_merges_using_dependency_archives(self, table_id) -> None:
880
+ def calculate_merges_using_dependency_archives(self, table_id) -> int:
864
881
  """Extract all the merge cell ranges for the Table."""
865
882
  # See details in Numbers.md#merge-ranges.
866
883
  owner_id_map = self.owner_id_map()
867
884
  table_base_id = self.table_base_id(table_id)
868
885
 
869
886
  formula_table_ids = self.find_refs("FormulaOwnerDependenciesArchive")
887
+ merge_count = 0
870
888
  for formula_id in formula_table_ids:
871
889
  dependencies = self.objects[formula_id]
872
890
  if dependencies.owner_kind != OwnerKind.MERGE_OWNER:
@@ -875,6 +893,7 @@ class _NumbersModel(Cacheable):
875
893
  to_owner_id = record.internal_range_reference.owner_id
876
894
  if owner_id_map[to_owner_id] == table_base_id:
877
895
  record_range = record.internal_range_reference.range
896
+ merge_count += 1
878
897
  self.add_merge_range(
879
898
  table_id,
880
899
  record_range.top_left_row,
@@ -882,13 +901,21 @@ class _NumbersModel(Cacheable):
882
901
  record_range.top_left_column,
883
902
  record_range.bottom_right_column,
884
903
  )
904
+ debug(
905
+ "table=%s: %d dependency archive merges found",
906
+ self.table_name(table_id),
907
+ merge_count,
908
+ )
909
+ return merge_count
885
910
 
886
911
  @cache()
887
912
  def calculate_merges_using_region_map(self, table_id) -> None:
888
913
  base_data_store = self.objects[table_id].base_data_store
889
914
  if base_data_store.merge_region_map.identifier == 0:
915
+ debug("table=%s: no merge_region_map", self.table_name(table_id))
890
916
  return
891
917
 
918
+ merge_count = 0
892
919
  cell_ranges = self.objects[base_data_store.merge_region_map.identifier]
893
920
  for cell_range in cell_ranges.cell_range:
894
921
  (col_start, row_start) = (
@@ -901,26 +928,39 @@ class _NumbersModel(Cacheable):
901
928
  )
902
929
  row_end = row_start + num_rows - 1
903
930
  col_end = col_start + num_columns - 1
931
+ merge_count += 1
904
932
  self.add_merge_range(table_id, row_start, row_end, col_start, col_end)
933
+ debug(
934
+ "table=%s: %d merge_region_map merges found",
935
+ self.table_name(table_id),
936
+ merge_count,
937
+ )
905
938
 
906
939
  def merge_cells(self, table_id):
907
- self.calculate_merges_using_formula_stores(table_id)
908
- self.calculate_merges_using_dependency_archives(table_id)
940
+ if self.calculate_merges_using_formula_stores(table_id) > 0:
941
+ return self._merge_cells[table_id]
942
+ if self.calculate_merges_using_dependency_archives(table_id) > 0:
943
+ return self._merge_cells[table_id]
909
944
  self.calculate_merges_using_region_map(table_id)
910
945
  return self._merge_cells[table_id]
911
946
 
912
947
  def table_id_to_sheet_id(self, table_id: int) -> int:
913
- for sheet_id in self.sheet_ids(): # pragma: no branch
914
- if table_id in self.table_ids(sheet_id):
915
- return sheet_id
916
- return None
948
+ return next(
949
+ (sheet_id for sheet_id in self.sheet_ids() if table_id in self.table_ids(sheet_id)),
950
+ None,
951
+ )
917
952
 
918
953
  @cache()
919
954
  def table_uuids_to_id(self, table_uuid) -> int | None:
920
- for sheet_id in self.sheet_ids(): # pragma: no branch # noqa: RET503
921
- for table_id in self.table_ids(sheet_id):
922
- if table_uuid == self.table_base_id(table_id):
923
- return table_id
955
+ return next(
956
+ (
957
+ table_id
958
+ for sheet_id in self.sheet_ids()
959
+ for table_id in self.table_ids(sheet_id)
960
+ if table_uuid == self.table_base_id(table_id)
961
+ ),
962
+ None,
963
+ )
924
964
 
925
965
  def node_to_ref(self, table_id: int, row: int, col: int, node):
926
966
  def resolve_range(is_absolute, absolute_list, relative_list, offset, max_val):
@@ -2553,36 +2593,28 @@ class _NumbersModel(Cacheable):
2553
2593
  # datas never appears to be an empty list (default themes include images)
2554
2594
  return max(image_ids) + 1
2555
2595
 
2556
- @classmethod
2557
- def cell_value_to_key(
2558
- cls,
2559
- cell_value: TSCEArchives.CellValueArchive,
2560
- ) -> str | int | bool | datetime:
2561
- """Convert a CellValueArchive to a key."""
2562
- cell_value_type = cell_value.cell_value_type
2563
- if cell_value_type == CellValueType.STRING_TYPE:
2564
- return cell_value.string_value.value
2565
- if cell_value_type == CellValueType.NUMBER_TYPE:
2566
- return cell_value.number_value.value
2567
- if cell_value_type == CellValueType.BOOLEAN_TYPE:
2568
- return cell_value.boolean_value.value
2569
- if cell_value_type == CellValueType.DATE_TYPE:
2570
- # "yyyy"
2571
- # "yyyy-QQQ"
2572
- # "LLLL yyyy"
2573
- # "yyyy'-W'w"
2574
- # "d/M/yyyy"
2575
- # "EEEE"
2576
- return _decode_date_format(
2577
- cell_value.date_value.format.date_time_format,
2578
- EPOCH + timedelta(seconds=cell_value.date_value.value),
2579
- )
2580
- return None
2581
-
2582
2596
  @cache(num_args=0)
2583
2597
  def group_uuid_values(self):
2598
+ def cell_value_to_key(
2599
+ cell_value: TSCEArchives.CellValueArchive,
2600
+ ) -> str | int | bool | datetime:
2601
+ """Convert a CellValueArchive to a key."""
2602
+ cell_value_type = cell_value.cell_value_type
2603
+ if cell_value_type == CellValueType.STRING_TYPE:
2604
+ return cell_value.string_value.value
2605
+ if cell_value_type == CellValueType.NUMBER_TYPE:
2606
+ return cell_value.number_value.value
2607
+ if cell_value_type == CellValueType.BOOLEAN_TYPE:
2608
+ return cell_value.boolean_value.value
2609
+ if cell_value_type == CellValueType.DATE_TYPE:
2610
+ return _decode_date_format(
2611
+ cell_value.date_value.format.date_time_format,
2612
+ EPOCH + timedelta(seconds=cell_value.date_value.value),
2613
+ )
2614
+ return None
2615
+
2584
2616
  return {
2585
- NumbersUUID(self.objects[_id].group_uid): _NumbersModel.cell_value_to_key(
2617
+ NumbersUUID(self.objects[_id].group_uid): cell_value_to_key(
2586
2618
  self.objects[_id].group_cell_value,
2587
2619
  )
2588
2620
  for _id in self.find_refs("GroupNodeArchive")
@@ -2626,81 +2658,47 @@ class _NumbersModel(Cacheable):
2626
2658
  parent_relationships(None, category_archive.group_node_root.child, group_parents)
2627
2659
 
2628
2660
  row = 0
2629
- row_mapper = {}
2630
- header = []
2631
- in_header = True
2632
-
2661
+ row_mapper: dict[int, int] = {}
2633
2662
  nodes: dict[NumbersUUID, dict] = {}
2634
2663
  root_children: dict = {}
2635
2664
  stack: list[NumbersUUID | None] = []
2636
- # rows that are not in any group (rare) kept here
2637
- root_rows: list = []
2638
2665
 
2639
2666
  for uuid in row_uid_for_index:
2640
2667
  if uuid in group_uuids:
2641
- # this UUID is a group heading
2642
- in_header = False
2643
2668
  parent = group_parents.get(uuid)
2669
+ nodes[uuid] = {"key": group_uuids[uuid], "children": {}, "rows": []}
2644
2670
 
2645
- # ensure node exists
2646
- if uuid not in nodes:
2647
- nodes[uuid] = {
2648
- "key": group_uuids[uuid],
2649
- "children": {},
2650
- "rows": [],
2651
- }
2652
-
2653
- # attach node to its parent (or root)
2654
2671
  if parent is None:
2655
- if nodes[uuid]["key"] not in root_children:
2656
- root_children[nodes[uuid]["key"]] = nodes[uuid]
2672
+ root_children[nodes[uuid]["key"]] = nodes[uuid]
2657
2673
  else:
2658
2674
  if parent not in nodes:
2659
- nodes[parent] = {
2660
- "key": group_uuids[parent],
2661
- "children": {},
2662
- "rows": [],
2663
- }
2675
+ nodes[parent] = {"key": group_uuids[parent], "children": {}, "rows": []}
2664
2676
  parent_node = nodes[parent]
2665
- if nodes[uuid]["key"] not in parent_node["children"]:
2666
- parent_node["children"][nodes[uuid]["key"]] = nodes[uuid]
2677
+ parent_node["children"][nodes[uuid]["key"]] = nodes[uuid]
2667
2678
 
2668
- # update stack to current nesting (pop until parent is on top)
2669
2679
  while stack and stack[-1] != parent:
2670
2680
  stack.pop()
2671
2681
  stack.append(uuid)
2672
2682
  else:
2673
2683
  mapped_row = row_uuid_to_offset[uuid]
2674
- if in_header:
2675
- header.append(self._table_data[table_id][mapped_row])
2676
- # assign this row to the deepest open group, or root
2677
- elif stack:
2684
+ if stack:
2678
2685
  nodes[stack[-1]]["rows"].append(self._table_data[table_id][mapped_row])
2679
- else:
2680
- root_rows.append(self._table_data[table_id][mapped_row])
2681
2686
 
2682
2687
  row_mapper[row] = mapped_row
2683
2688
  row += 1
2684
2689
 
2685
- # helper to convert node dicts to nested mapping (keys -> children or rows)
2686
2690
  def node_to_structure(node: dict):
2687
2691
  if not node["children"]:
2688
2692
  return node["rows"]
2689
2693
  out = {}
2690
2694
  for child_key, child_node in node["children"].items():
2691
2695
  out[child_key] = node_to_structure(child_node)
2692
- # if this node also has rows in addition to children, include them under a special key
2693
- if node["rows"]:
2694
- out["_rows"] = node["rows"]
2695
2696
  return out
2696
2697
 
2697
- maximally_nested = {}
2698
+ self._table_categories_data[table_id] = {}
2698
2699
  for key, node in root_children.items():
2699
- maximally_nested[key] = node_to_structure(node)
2700
- if root_rows:
2701
- maximally_nested["_rows"] = root_rows
2700
+ self._table_categories_data[table_id][key] = node_to_structure(node)
2702
2701
 
2703
- self._table_categories_data[table_id] = maximally_nested
2704
2702
  self._table_categories_row_mapper[table_id] = {
2705
2703
  row: row_uuid_to_offset[uuid]
2706
2704
  for row, uuid in enumerate(
@@ -2,7 +2,6 @@ from __future__ import annotations
2
2
 
3
3
  import re
4
4
  from collections import defaultdict
5
- from contextlib import suppress
6
5
  from dataclasses import dataclass, field, replace
7
6
  from enum import IntEnum
8
7
 
@@ -67,8 +66,7 @@ class CellRange:
67
66
  _table_names: list[str] = field(init=False, default=None, repr=False)
68
67
 
69
68
  def __post_init__(self):
70
- if self._table_names is None:
71
- self._initialize_table_data()
69
+ self._initialize_table_data()
72
70
  self.model.name_ref_cache.refresh()
73
71
  self._set_sheet_ids()
74
72
 
@@ -304,9 +302,7 @@ class ScopedNameRefCache:
304
302
  scopes[idx] = None
305
303
  else:
306
304
  name = data_lookup(table_id, idx)
307
- if name is None:
308
- scopes[idx] = None
309
- elif self._exact_count(all_names, name) > 1:
305
+ if self._exact_count(all_names, name) > 1:
310
306
  names.append(None)
311
307
  scopes[idx] = None
312
308
  else:
@@ -371,240 +367,6 @@ class ScopedNameRefCache:
371
367
  for sid in self.model.sheet_ids()
372
368
  }
373
369
 
374
- def _scoped_ref_to_cell_ref(self, ref: ScopedNameRef) -> CellRange:
375
- """Convert a ScopedNameRef into a CellRange."""
376
- return CellRange(
377
- model=self.model,
378
- to_table_id=ref.table_id,
379
- row_start=ref.offset if ref.axis == TableAxis.ROW else None,
380
- col_start=ref.offset if ref.axis == TableAxis.COLUMN else None,
381
- )
382
-
383
- @staticmethod
384
- def _name_in_cell_range(name: str, cell_range: list[CellRange]) -> int:
385
- """Check whether the given name is found among a list of ScopedNameRefs."""
386
- match = [
387
- cell.offset
388
- for cell in cell_range.values()
389
- if isinstance(cell, ScopedNameRef) and cell.name == name
390
- ]
391
- if len(match) == 0:
392
- return -1
393
- return match[0]
394
-
395
- def _deref_doc_scope(self, from_table_id: int, name: str) -> CellRange:
396
- """Try and use a name reference in the document scope or current sheet."""
397
- name = name.replace("''", "'")
398
- if name.startswith("'") and name.endswith("'"):
399
- name = name[1:-1]
400
-
401
- # Try using the name as document scope
402
- if self._name_in_cell_range(name, self.doc_name_refs) >= 0:
403
- return self._scoped_ref_to_cell_ref(self.doc_name_refs[name])
404
-
405
- # Next, try the the current sheet scope
406
- from_sheet_id = self.model.table_id_to_sheet_id(from_table_id)
407
- if self._name_in_cell_range(name, self.sheet_name_refs[from_sheet_id]) >= 0:
408
- return self._scoped_ref_to_cell_ref(self.sheet_name_refs[from_sheet_id][name])
409
-
410
- msg = f"'{name}' does not exist or scope is ambiguous"
411
- raise ValueError(msg)
412
-
413
- def _deref_single_scope(self, from_table_id: int, name_scope: str, name: str) -> CellRange:
414
- """
415
- Resolve a name using a single scope. The scopy could be one of:
416
- - A sheet name
417
- - A table within the current sheet
418
- - A unique table name anwhere in the document
419
- """
420
- name = name.replace("''", "'")
421
- if name.startswith("'") and name.endswith("'"):
422
- name = name[1:-1]
423
-
424
- from_sheet_id = self.model.table_id_to_sheet_id(from_table_id)
425
-
426
- # 1. Try resolving the name treating the scope as a sheet name
427
- if name_scope in self.sheet_name_to_id:
428
- to_sheet_id = self.sheet_name_to_id[name_scope]
429
- if name in self.sheet_name_refs[to_sheet_id]:
430
- return self._scoped_ref_to_cell_ref(self.sheet_name_refs[to_sheet_id][name])
431
-
432
- # 2. Try resolving as a name the current sheet
433
- from_sheet_name = self.sheet_id_to_name[from_sheet_id]
434
- if self._name_in_cell_range(name, self.sheet_name_refs[from_sheet_id]) >= 0:
435
- return self._scoped_ref_to_cell_ref(self.sheet_name_refs[from_sheet_id][name])
436
-
437
- # 4. Try resolving as a name in a unique table in the document
438
- if name_scope in self.unique_table_name_to_id:
439
- to_table_id = self.unique_table_name_to_id[name_scope]
440
- if self._name_in_cell_range(name, self.table_name_refs[to_table_id]) >= 0:
441
- # Name is valid in table scope and table name is document-unique
442
- return self._scoped_ref_to_cell_ref(self.table_name_refs[to_table_id][name])
443
-
444
- # 4. Try resolving as a name in a table in the current sheet
445
- if name_scope in self.sheet_table_name_to_id[from_sheet_name]:
446
- to_table_id = self.sheet_table_name_to_id[from_sheet_name][name_scope]
447
- # Name is valid in a table in the current sheet
448
- if (offset := self._name_in_cell_range(name, self.row_ranges[to_table_id])) >= 0:
449
- return CellRange(
450
- model=self.model,
451
- to_table_id=to_table_id,
452
- row_start=offset,
453
- )
454
- if (offset := self._name_in_cell_range(name, self.col_ranges[to_table_id])) >= 0:
455
- return CellRange(
456
- model=self.model,
457
- to_table_id=to_table_id,
458
- col_start=offset,
459
- )
460
-
461
- # 5. Try resolving the name as a row or column reference
462
- with suppress(IndexError):
463
- col_start = xl_col_to_offset(name)
464
- if col_start:
465
- return CellRange(model=self.model, to_table_id=to_table_id, col_start=col_start)
466
-
467
- msg = f"'{name_scope}::{name}' does not exist or scope is ambiguous"
468
- raise ValueError(msg)
469
-
470
- def _deref_name(
471
- self,
472
- from_table_id: int,
473
- name_scope_1: str,
474
- name_scope_2: str,
475
- name: str,
476
- ) -> CellRange:
477
- if not name_scope_1 and not name_scope_2:
478
- return self._deref_doc_scope(from_table_id, name)
479
-
480
- if not name_scope_1:
481
- return self._deref_single_scope(from_table_id, name_scope_2, name)
482
-
483
- # Full sheet::table::name scope
484
- try:
485
- to_table_id = self.sheet_table_name_to_id[name_scope_1][name_scope_2]
486
- if (offset := self._name_in_cell_range(name, self.row_ranges[to_table_id])) >= 0:
487
- return CellRange(
488
- model=self.model,
489
- to_table_id=to_table_id,
490
- row_start=offset,
491
- )
492
- if (offset := self._name_in_cell_range(name, self.col_ranges[to_table_id])) >= 0:
493
- return CellRange(
494
- model=self.model,
495
- to_table_id=to_table_id,
496
- col_start=offset,
497
- )
498
- except KeyError:
499
- # Catch invalid sheet/table names and fall through
500
- pass
501
-
502
- msg = f"'{name_scope_1}::{name_scope_2}::{name}' does not exist or scope is ambiguous"
503
- raise ValueError(msg)
504
-
505
- def lookup_named_ref(self, from_table_id: int, ref: CellRange) -> CellRange:
506
- def range_error_message(ref: CellRange):
507
- msg = f"{ref.name_scope_1}::" if ref.name_scope_1 else ""
508
- msg += f"{ref.name_scope_2}::" if ref.name_scope_2 else ""
509
- msg += ref.row_start
510
- msg += f":{ref.row_end}" if ref.row_end else ""
511
- return f"'{msg}' does not exist or scope is ambiguous"
512
-
513
- self.model.name_ref_cache.refresh()
514
- if ref.row_start and ref.row_end:
515
- # Numbers will use the reduced scope of one part of a range to scope the other
516
- # so start:en d in a document scope will resolve if either of the references can
517
- # be resolved in that scope.
518
- start_ref, end_ref = None, None
519
- with suppress(ValueError):
520
- start_ref = self._deref_name(
521
- from_table_id,
522
- ref.name_scope_1,
523
- ref.name_scope_2,
524
- ref.row_start,
525
- )
526
- with suppress(ValueError):
527
- end_ref = self._deref_name(
528
- from_table_id,
529
- ref.name_scope_1,
530
- ref.name_scope_2,
531
- ref.row_end,
532
- )
533
-
534
- if start_ref is None and end_ref is None:
535
- raise ValueError(range_error_message(ref))
536
-
537
- if start_ref is None:
538
- row_start = [
539
- v.offset
540
- for k, v in self.row_ranges[end_ref.to_table_id].items()
541
- if v is not None and v.name == ref.row_start
542
- ]
543
- col_start = [
544
- v.offset
545
- for k, v in self.col_ranges[end_ref.to_table_id].items()
546
- if v is not None and v.name == ref.row_start
547
- ]
548
- if len(row_start) == 0 and len(col_start) == 0:
549
- raise ValueError(range_error_message(ref))
550
-
551
- start_ref = CellRange(
552
- model=self.model,
553
- to_table_id=end_ref.to_table_id,
554
- row_start=row_start[0] if row_start else None,
555
- col_start=col_start[0] if col_start else None,
556
- )
557
- elif end_ref is None:
558
- row_end = [
559
- v.offset
560
- for k, v in self.row_ranges[start_ref.to_table_id].items()
561
- if v is not None and v.name == ref.row_end
562
- ]
563
- col_end = [
564
- v.offset
565
- for k, v in self.col_ranges[start_ref.to_table_id].items()
566
- if v is not None and v.name == ref.row_end
567
- ]
568
- if len(row_end) == 0 and len(col_end) == 0:
569
- raise ValueError(range_error_message(ref))
570
- end_ref = CellRange(
571
- model=self.model,
572
- to_table_id=start_ref.to_table_id,
573
- row_start=row_end[0] if row_end else None,
574
- col_start=col_end[0] if col_end else None,
575
- )
576
- elif start_ref.row_start is None:
577
- return CellRange(
578
- model=self.model,
579
- to_table_id=start_ref.to_table_id,
580
- col_start=start_ref.col_start,
581
- col_end=end_ref.col_start,
582
- )
583
- elif start_ref.col_start is None:
584
- return CellRange(
585
- model=self.model,
586
- to_table_id=start_ref.to_table_id,
587
- row_start=start_ref.row_start,
588
- row_end=end_ref.row_start,
589
- )
590
- start_ref.row_end = end_ref.row_start
591
- start_ref.col_end = end_ref.col_start
592
- return start_ref
593
-
594
- if ref.row_start:
595
- return self._deref_name(
596
- from_table_id,
597
- ref.name_scope_1,
598
- ref.name_scope_2,
599
- ref.row_start,
600
- )
601
- return self._deref_name(
602
- from_table_id,
603
- ref.name_scope_1,
604
- ref.name_scope_2,
605
- ref.col_start,
606
- )
607
-
608
370
  def calculate_named_ranges(self):
609
371
  """
610
372
  Find the globally unique row and column headers and the table unique
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: numbers-parser
3
- Version: 4.18.1
3
+ Version: 4.18.2
4
4
  Summary: Read and write Apple Numbers spreadsheets
5
5
  Author-email: Jon Connell <python@figsandfudge.com>
6
6
  License-Expression: MIT
@@ -284,3 +284,8 @@ def test_errors(script_runner):
284
284
  assert not ret.success
285
285
  assert "invalid.numbers: no such file or directory" in ret.stderr
286
286
  assert ret.stdout == ""
287
+
288
+ ret = script_runner.run(["cat-numbers", "--experimental=ERROR"], print_result=False)
289
+ assert not ret.success
290
+ assert "invalid experimental feature: ERROR" in ret.stderr
291
+ assert ret.stdout == ""
@@ -1,4 +1,5 @@
1
1
  from datetime import datetime
2
+ from unittest.mock import patch
2
3
 
3
4
  import pytest
4
5
 
@@ -34,7 +35,7 @@ from numbers_parser.experimental import (
34
35
  )
35
36
  from numbers_parser.generated import TSKArchives_pb2 as TSKArchives
36
37
  from numbers_parser.numbers_uuid import NumbersUUID
37
- from numbers_parser.xrefs import xl_col_to_name, xl_range, xl_rowcol_to_cell
38
+ from numbers_parser.xrefs import xl_col_to_name, xl_col_to_offset, xl_range, xl_rowcol_to_cell
38
39
 
39
40
 
40
41
  def test_containers():
@@ -170,6 +171,13 @@ def test_range_exceptions():
170
171
  _ = xl_rowcol_to_cell(0, -2)
171
172
  assert "column reference -2 below zero" in str(e)
172
173
 
174
+ with pytest.raises(IndexError) as e:
175
+ _ = xl_col_to_offset("!!!")
176
+ assert "invalid cell reference" in str(e)
177
+
178
+ assert xl_col_to_offset(None) == 0
179
+ assert xl_col_to_offset("A") == 0
180
+
173
181
  with pytest.raises(IndexError) as e:
174
182
  _ = xl_col_to_name(-2)
175
183
  assert "column reference -2 below zero" in str(e)
@@ -305,8 +313,51 @@ def test_invalid_format():
305
313
  cell._text_format_id = None
306
314
  assert cell._custom_format() == cell.value
307
315
 
308
-
309
- def test_invalid_format_2():
310
316
  with pytest.raises(FileFormatError) as e:
311
317
  _ = Document("tests/data/invalid-index-zip.numbers")
312
318
  assert "invalid Numbers document" in str(e)
319
+
320
+
321
+ @pytest.mark.script_launch_mode("inprocess")
322
+ def test_cli_main_blocks(capsys):
323
+ from numbers_parser._cat_numbers import main as cat_main
324
+ from numbers_parser._csv2numbers import main as csv2_main
325
+ from numbers_parser._unpack_numbers import main as unpack_main
326
+
327
+ with (
328
+ patch("numbers_parser._cat_numbers.__name__", "test"),
329
+ patch("sys.exit") as _,
330
+ patch("sys.argv", ["test", "--help"]) as _,
331
+ ):
332
+ cat_main()
333
+ captured = capsys.readouterr()
334
+ assert "usage: test [-h]" in captured.out
335
+
336
+ with (
337
+ patch("numbers_parser._csv2numbers.__name__", "test"),
338
+ patch("sys.exit") as _,
339
+ patch("sys.argv", ["test", "--help"]) as _,
340
+ ):
341
+ csv2_main()
342
+ captured = capsys.readouterr()
343
+ assert "usage: test [-h]" in captured.out
344
+
345
+ with (
346
+ patch("numbers_parser._unpack_numbers.__name__", "test"),
347
+ patch("sys.exit") as _,
348
+ patch("sys.argv", ["test", "--help"]) as _,
349
+ ):
350
+ unpack_main()
351
+ captured = capsys.readouterr()
352
+ assert "usage: test [-h]" in captured.out
353
+
354
+ assert callable(csv2_main)
355
+ assert callable(cat_main)
356
+ assert callable(unpack_main)
357
+
358
+
359
+ def test_xref_quoting():
360
+ doc = Document("tests/data/test-xref-coverage.numbers")
361
+ table = doc.default_table
362
+ assert table.cell("C2").formula == "SUM(Column '''A''')"
363
+ assert table.cell("C3").formula == "COUNTA('Column X & Y')"
@@ -78,6 +78,37 @@ def test_unpack_dir(script_runner, tmp_path):
78
78
  assert "XXX_COL_3" in strings
79
79
 
80
80
 
81
+ @pytest.mark.script_launch_mode("inprocess")
82
+ def test_unpack_redacted(script_runner, tmp_path):
83
+ output_dir = tmp_path / "test"
84
+ ret = script_runner.run(
85
+ [
86
+ "unpack-numbers",
87
+ "--redact",
88
+ "--output",
89
+ str(output_dir),
90
+ "tests/data/test-5.numbers",
91
+ ],
92
+ print_result=False,
93
+ )
94
+ assert ret.success
95
+ assert ret.stdout == ""
96
+ with open(str(output_dir / "Index/CalculationEngine.json")) as f:
97
+ data = json.load(f)
98
+ table_model_archive = next(
99
+ x["objects"][0]
100
+ for x in data["chunks"][0]["archives"]
101
+ if x["objects"][0]["_pbtype"] == "TST.TableModelArchive"
102
+ )
103
+ assert table_model_archive["table_name"].startswith("REDACT-")
104
+
105
+ string_table_id = table_model_archive["base_data_store"]["stringTable"]["identifier"]
106
+ with open(str(output_dir / f"Index/Tables/DataList-{string_table_id}.json")) as f:
107
+ data = json.load(f)
108
+ string_table = data["chunks"][0]["archives"][0]["objects"][0]
109
+ assert all(x["string"].startswith("REDACT-") for x in string_table["entries"])
110
+
111
+
81
112
  @pytest.mark.script_launch_mode("inprocess")
82
113
  def test_unpack_hex(script_runner, tmp_path):
83
114
  output_dir = tmp_path / "test"