numbers-parser 4.15.1__tar.gz → 4.16.2__tar.gz

{numbers_parser-4.15.1 → numbers_parser-4.16.2}/PKG-INFO

@@ -1,31 +1,26 @@
-Metadata-Version: 2.3
+Metadata-Version: 2.4
 Name: numbers-parser
-Version: 4.15.1
+Version: 4.16.2
 Summary: Read and write Apple Numbers spreadsheets
-License: MIT
-Author: Jon Connell
-Author-email: python@figsandfudge.com
-Requires-Python: >=3.9,<4.0
-Classifier: License :: OSI Approved :: MIT License
-Classifier: Operating System :: OS Independent
-Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.9
-Classifier: Programming Language :: Python :: 3.10
-Classifier: Programming Language :: Python :: 3.11
-Classifier: Programming Language :: Python :: 3.12
-Classifier: Programming Language :: Python :: 3.13
+Author-email: Jon Connell <python@figsandfudge.com>
+License-Expression: MIT
+Project-URL: repository, https://github.com/masaccio/numbers-parser
+Project-URL: documentation, https://github.com/masaccio/numbers-parser/blob/main/README.md
 Classifier: Topic :: Office/Business :: Financial :: Spreadsheet
-Requires-Dist: compact-json (>=1.1.3,<2.0.0)
-Requires-Dist: enum-tools (>=0.11)
-Requires-Dist: importlib-resources (>=6.1)
-Requires-Dist: protobuf (>=4.0,<6.0)
-Requires-Dist: python-dateutil (>=2.9.0.post0,<3.0.0)
-Requires-Dist: python-snappy (>=0.7,<0.8)
-Requires-Dist: setuptools (>=70.0.0)
-Requires-Dist: sigfig (>=1.3.3,<2.0.0)
-Project-URL: Documentation, https://github.com/masaccio/numbers-parser/blob/main/README.md
-Project-URL: Repository, https://github.com/masaccio/numbers-parser
+Classifier: Programming Language :: Python :: 3
+Classifier: Operating System :: OS Independent
+Requires-Python: <4.0,>=3.9
 Description-Content-Type: text/markdown
+License-File: LICENSE.rst
+Requires-Dist: compact-json<2.0.0,>=1.1.3
+Requires-Dist: protobuf<6.0,>=4.0
+Requires-Dist: python-snappy<1.0,>=0.7
+Requires-Dist: sigfig<2.0.0,>=1.3.3
+Requires-Dist: setuptools>=70.0.0
+Requires-Dist: importlib-resources>=6.1
+Requires-Dist: enum-tools>=0.11
+Requires-Dist: python-dateutil<3.0.0.0,>=2.9.0.post0
+Dynamic: license-file
 
 # numbers-parser
 
@@ -485,8 +480,15 @@ The following limitations are expected to always remain:
 - Password-encrypted documents cannot be opened. You must first re-save without
   a password to read (see [issue 88](https://github.com/masaccio/numbers-parser/issues/88) for details).
   A UnsupportedError exception is raised when such documents are opened.
+- Due to changes in the format of Numbers documents, decoding of category groups
+  (introduced in `numbers-parser` version 4.16) is supported only for documents
+  created by Numbers 12.0 and later. No warnings are issued for earlier
+  Numbers documents.
+- Only standard macOS fonts are not supported. If a document includes a non-standard
+  font, numbers-parser will issue a UnsupportedWarning and default styles to
+  Helvetica Neue. Reading font names from the system would add additional system-specific
+  dependencies to the package and so this is not planned to changed.
 
 ## License
 
 All code in this repository is licensed under the [MIT License](https://github.com/masaccio/numbers-parser/blob/master/LICENSE.rst).
-

{numbers_parser-4.15.1 → numbers_parser-4.16.2}/README.md

@@ -456,6 +456,14 @@ The following limitations are expected to always remain:
 - Password-encrypted documents cannot be opened. You must first re-save without
   a password to read (see [issue 88](https://github.com/masaccio/numbers-parser/issues/88) for details).
   A UnsupportedError exception is raised when such documents are opened.
+- Due to changes in the format of Numbers documents, decoding of category groups
+  (introduced in `numbers-parser` version 4.16) is supported only for documents
+  created by Numbers 12.0 and later. No warnings are issued for earlier
+  Numbers documents.
+- Only standard macOS fonts are not supported. If a document includes a non-standard
+  font, numbers-parser will issue a UnsupportedWarning and default styles to
+  Helvetica Neue. Reading font names from the system would add additional system-specific
+  dependencies to the package and so this is not planned to changed.
 
 ## License
 

{numbers_parser-4.15.1 → numbers_parser-4.16.2}/pyproject.toml

@@ -1,73 +1,81 @@
-[tool.poetry]
-authors = ["Jon Connell <python@figsandfudge.com>"]
+[project]
+authors = [
+    {name = "Jon Connell", email = "python@figsandfudge.com"},
+]
+license = "MIT"
+requires-python = "<4.0,>=3.9"
+dependencies = [
+    "compact-json<2.0.0,>=1.1.3",
+    "protobuf<6.0,>=4.0",
+    "python-snappy<1.0,>=0.7",
+    "sigfig<2.0.0,>=1.3.3",
+    "setuptools>=70.0.0",
+    "importlib-resources>=6.1",
+    "enum-tools>=0.11",
+    "python-dateutil<3.0.0.0,>=2.9.0.post0",
+]
 classifiers = [
-  "Topic :: Office/Business :: Financial :: Spreadsheet",
-  "Programming Language :: Python :: 3",
-  "Operating System :: OS Independent",
+    "Topic :: Office/Business :: Financial :: Spreadsheet",
+    "Programming Language :: Python :: 3",
+    "Operating System :: OS Independent",
 ]
 description = "Read and write Apple Numbers spreadsheets"
-documentation = "https://github.com/masaccio/numbers-parser/blob/main/README.md"
-license = "MIT"
 name = "numbers-parser"
-packages = [{include = "numbers_parser", from = "src"}]
 readme = "README.md"
+version = "4.16.2"
+
+[project.urls]
 repository = "https://github.com/masaccio/numbers-parser"
-version = "4.15.1"
+documentation = "https://github.com/masaccio/numbers-parser/blob/main/README.md"
 
-[tool.poetry.scripts]
+[project.scripts]
 cat-numbers = "numbers_parser._cat_numbers:main"
 unpack-numbers = "numbers_parser._unpack_numbers:main"
 csv2numbers = "numbers_parser._csv2numbers:main"
 
-[tool.poetry.dependencies]
-compact-json = "^1.1.3"
-protobuf = ">=4.0,<6.0"
-python = ">=3.9,<4.0"
-python-snappy = "^0.7"
-sigfig = "^1.3.3"
-setuptools = ">=70.0.0"
-importlib-resources = ">=6.1"
-enum-tools = ">=0.11"
-python-dateutil = "^2.9.0.post0"
-
-[tool.poetry.group.dev.dependencies]
-gprof2dot = "^2022.7.29"
-line-profiler = "^4.0.3"
-mock = ">=5.1.0"
-pytest = ">=7.2.0"
-pytest-check = ">=1.0"
-pytest-console-scripts = "^1.3.1"
-pytest-cov = ">=4.0,>=5.0"
-pytest-xdist = "^3.3.1"
-ruff = "*"
-tox = "^4.11.4"
-python-magic = ">=0.4"
-tqdm = ">=4.66"
-colorama = "^0.4.6"
-pympler = "^1.1"
-
-[tool.poetry.group.docs]
-optional = true
-
-[tool.poetry.group.docs.dependencies]
-sphinx = ">= 7.3"
-enum-tools = ">=0.11"
-sphinx-toolbox = ">=3.5"
-sphinx-nefertiti = ">=0.7"
-sphinx-markdown-builder = ">=0.6"
-sphinx-copybutton = ">=0.5"
-
-[tool.poetry.group.bootstrap]
-optional = true
-
-[tool.poetry.group.bootstrap.dependencies]
-pyobjc-core = ">=10.2"
-pyobjc-framework-Cocoa = ">=10.2"
-py2app = ">=0.28"
+[dependency-groups]
+dev = [
+    "gprof2dot<2023.0.0,>=2022.7.29",
+    "line-profiler<5.0.0,>=4.0.3",
+    "mock>=5.1.0",
+    "pytest>=7.2.0",
+    "pytest-check>=1.0",
+    "pytest-console-scripts<2.0.0,>=1.3.1",
+    "pytest-cov>=4.0,>=5.0",
+    "pytest-xdist<4.0.0,>=3.3.1",
+    "ruff",
+    "tox<5.0.0,>=4.11.4",
+    "python-magic>=0.4",
+    "tqdm>=4.66",
+    "colorama<1.0.0,>=0.4.6",
+    "pympler<2.0,>=1.1",
+]
+docs = [
+    "sphinx>=7.3",
+    "enum-tools>=0.11",
+    "sphinx-toolbox>=3.5",
+    "sphinx-nefertiti>=0.7",
+    "sphinx-markdown-builder>=0.6",
+    "sphinx-copybutton>=0.5",
+]
+bootstrap = [
+    "pyobjc-core>=10.2",
+    "pyobjc-framework-Cocoa>=10.2",
+    "py2app>=0.28",
+]
 
 [build-system]
-build-backend = "poetry.core.masonry.api"
-requires = ["poetry-core>=1.0.0"]
+requires = ["setuptools >= 61.0"]
+build-backend = "setuptools.build_meta"
+
+[tool.setuptools.packages.find]
+where = ["src"]
+include = ["numbers_parser*"]
+exclude = ["*tests*"]
+namespaces = false  # disable scanning PEP 420 namespaces
+
+[tool.setuptools.package-data]
+"numbers_parser" = ["data/*"]
 
 [tool.coverage.run]
 branch = true
@@ -189,3 +197,4 @@ ban-relative-imports = "all"
 "src/build/protodump.py" = ["PLR2004", "INP001", "PTH", "S110", "N806"]
 "src/debug/**" = ["INP001"]
 "tests/**" = ["PLR2004", "S101", "D103", "ANN201", "ANN001"]
+

numbers_parser-4.16.2/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

{numbers_parser-4.15.1 → numbers_parser-4.16.2}/src/numbers_parser/_unpack_numbers.py

@@ -49,13 +49,7 @@ class NumbersUnpacker(IWorkHandler):
                 if self.compact_json or self.pretty:
                     formatter = Formatter()
                     formatter.indent_spaces = 2
-                    formatter.max_inline_complexity = 100
-                    formatter.max_compact_list_complexity = 100
-                    formatter.max_inline_length = 160
-                    formatter.max_compact_list_complexity = 2
-                    formatter.simple_bracket_padding = True
-                    formatter.nested_bracket_padding = False
-                    formatter.always_expand_depth = 10
+                    formatter.max_inline_length = 180
                     pretty_json = formatter.serialize(data)
                     out.write(pretty_json)
                 else:

{numbers_parser-4.15.1 → numbers_parser-4.16.2}/src/numbers_parser/constants.py

@@ -5,15 +5,16 @@ from math import ceil
 
 import enum_tools.documentation
 
+# Path to package date varies by Python version
 try:
     from importlib.resources import files
-# Can't cover exception using modern python
 except ImportError:  # pragma: nocover
     from importlib_resources import files
 
 __all__ = [
     "CellPadding",
     "CellType",
+    "CellValueType",
     "ControlFormattingType",
     "DurationStyle",
     "DurationUnits",
@@ -112,7 +113,7 @@ def _day_of_year(value: datetime) -> int:
 
 def _week_of_month(value: datetime) -> int:
     """Return the week number in a month for a datetime."""
-    return int(ceil((value.day + value.replace(day=1).weekday()) / 7.0))
+    return ceil((value.day + value.replace(day=1).weekday()) / 7.0)
 
 
 DATETIME_FIELD_MAP = OrderedDict(
@@ -399,6 +400,14 @@ class CellInteractionType(IntEnum):
     TOGGLE = 8
 
 
+class CellValueType(IntEnum):
+    NIL_TYPE = 1
+    BOOLEAN_TYPE = 2
+    DATE_TYPE = 3
+    NUMBER_TYPE = 4
+    STRING_TYPE = 5
+
+
 CONTROL_CELL_TYPE_MAP = {
     FormattingType.POPUP: CellInteractionType.POPUP,
     FormattingType.SLIDER: CellInteractionType.SLIDER,

{numbers_parser-4.15.1 → numbers_parser-4.16.2}/src/numbers_parser/document.py

@@ -40,14 +40,6 @@ if TYPE_CHECKING:  # pragma: nocover
 __all__ = ["Document", "Sheet", "Table"]
 
 
-# class Sheet:
-#     pass
-
-
-# class Table:
-#     pass
-
-
 class Document:
     """
     Create an instance of a new Numbers document.
@@ -1007,6 +999,34 @@ class Table(Cacheable):
             msg = "style must be a Style object or style name"
             raise TypeError(msg)
 
+    def categorized_data(self) -> dict | None:
+        """
+        Return the table's data organised into categories, if enabled or ``None``
+        if the table has not had categoried enabled.
+
+        The data is a dictionary with the category names as keys and a list
+        dictionaries for each row in that category of the table. The table heading
+        row is used as the keys for the row dictionary.
+
+        Example
+        -------
+        .. code:: python
+
+            "Transport": [
+                {"Description": "Airplane", "Category": "Transport" },
+                {"Description": "Bicycle", "Category": "Transport" },
+                {"Description": "Bus", "Category": "Transport"},
+            ],
+            "Fruit": [
+                {"Description": "Apple", "Category": "Fruit" },
+                {"Description": "Banana", "Category": "Fruit" },
+            ],
+
+        For tables with multiple categories, the top-level dictionary is nested.
+
+        """
+        return self._model.table_category_data(self._table_id)
+
     def add_row(
         self,
         num_rows: int | None = 1,

{numbers_parser-4.15.1 → numbers_parser-4.16.2}/src/numbers_parser/model.py

@@ -8,6 +8,8 @@ from itertools import chain
 from math import floor
 from pathlib import Path
 from struct import pack
+from typing import TYPE_CHECKING
+from warnings import warn
 
 from numbers_parser.bullets import (
     BULLET_CONVERSION,
@@ -37,6 +39,7 @@ from numbers_parser.constants import (
     CUSTOM_TEXT_PLACEHOLDER,
     DEFAULT_COLUMN_WIDTH,
     DEFAULT_DOCUMENT,
+    DEFAULT_FONT,
     DEFAULT_PRE_BNC_BYTES,
     DEFAULT_ROW_HEIGHT,
     DEFAULT_TABLE_OFFSET,
@@ -48,11 +51,12 @@ from numbers_parser.constants import (
     MAX_TILE_SIZE,
     PACKAGE_ID,
     CellInteractionType,
+    CellValueType,
     FormatType,
     OwnerKind,
 )
 from numbers_parser.containers import ObjectStore
-from numbers_parser.exceptions import UnsupportedError
+from numbers_parser.exceptions import UnsupportedError, UnsupportedWarning
 from numbers_parser.formula import TableFormulas
 from numbers_parser.generated import TNArchives_pb2 as TNArchives
 from numbers_parser.generated import TSAArchives_pb2 as TSAArchives
@@ -76,6 +80,9 @@ from numbers_parser.numbers_cache import Cacheable, cache
 from numbers_parser.numbers_uuid import NumbersUUID, uuid_to_hex
 from numbers_parser.xrefs import CellRange, ScopedNameRefCache
 
+if TYPE_CHECKING:
+    from datetime import datetime
+
 
 def create_font_name_map(font_map: dict) -> dict:
     new_font_map = {}
@@ -238,6 +245,7 @@ class _NumbersModel(Cacheable):
             "left": defaultdict(),
         }
         self.name_ref_cache = ScopedNameRefCache(self)
+        self.missing_fonts = {}
         self.calculate_table_uuid_map()
 
     def save(self, filepath: Path, package: bool) -> None:
@@ -289,7 +297,7 @@ class _NumbersModel(Cacheable):
         # which is an ordered list that matches the storage buffers, but
         # identifies which row a storage buffer belongs to (empty rows have
         # no storage buffers).
-        row_bucket_map = {i: None for i in range(self.objects[table_id].number_of_rows)}
+        row_bucket_map = dict.fromkeys(range(self.objects[table_id].number_of_rows))
         bds = self.objects[table_id].base_data_store
         bucket_ids = [x.identifier for x in bds.rowHeaders.buckets]
         idx = 0
@@ -2268,6 +2276,16 @@ class _NumbersModel(Cacheable):
     def cell_font_name(self, obj: Cell | object) -> str:
         style = self.cell_text_style(obj) if isinstance(obj, Cell) else obj
         font_name = self.char_property(style, "font_name")
+        if font_name not in FONT_NAME_TO_FAMILY:
+            if font_name not in self.missing_fonts:
+                warn(
+                    f"Custom font '{font_name}' unsupported; falling back to {DEFAULT_FONT}",
+                    UnsupportedWarning,
+                    stacklevel=2,
+                )
+                self.missing_fonts[font_name] = True
+            return DEFAULT_FONT
+
         return FONT_NAME_TO_FAMILY[font_name]
 
     def cell_first_indent(self, obj: Cell | object) -> float:
@@ -2550,6 +2568,108 @@ class _NumbersModel(Cacheable):
         # datas never appears to be an empty list (default themes include images)
         return max(image_ids) + 1
 
+    def table_category_data(self, table_id: int) -> dict | None:
+        category_owner_id = self.objects[table_id].category_owner.identifier
+        category_archive_id = self.objects[category_owner_id].group_by[0].identifier
+        category_archive = self.objects[category_archive_id]
+        if not category_archive.is_enabled:
+            return None
+
+        table_info = self.objects[self.table_info_id(table_id)]
+        category_order = self.objects[table_info.category_order.identifier]
+        row_uid_map = self.objects[category_order.uid_map.identifier]
+        sorted_row_uuids = [
+            NumbersUUID(row_uid_map.sorted_row_uids[i]).hex for i in row_uid_map.row_uid_for_index
+        ]
+
+        data = self._table_data[table_id]
+        header = [cell.value for cell in data[0]]
+
+        def index_set_to_offsets(index_set: TSCEArchives.IndexSetArchive) -> list[int]:
+            """Convert an IndexSetArchive to a list of offsets."""
+            offsets = []
+            for entry in index_set.entries:
+                if entry.HasField("range_end"):
+                    offsets += list(range(entry.range_begin, entry.range_end + 1))
+                else:
+                    offsets += list(range(entry.range_begin, entry.range_begin + 1))
+            return offsets
+
+        def cell_value_to_key(
+            cell_value: TSCEArchives.CellValueArchive,
+        ) -> str | int | bool | datetime:
+            """Convert a CellValueArchive to a key."""
+            cell_value_type = cell_value.cell_value_type
+            if cell_value_type == CellValueType.STRING_TYPE:
+                return cell_value.string_value.value
+            if cell_value_type == CellValueType.NUMBER_TYPE:
+                return cell_value.number_value.value
+            if cell_value_type == CellValueType.BOOLEAN_TYPE:
+                return cell_value.boolean_value.value
+            # Must be DATE_TYPE
+            return cell_value.date_value.value
+
+        group_node_to_key = {
+            NumbersUUID(self.objects[_id].group_uid).hex: cell_value_to_key(
+                self.objects[_id].group_cell_value,
+            )
+            for _id in self.find_refs("GroupNodeArchive")
+        }
+        group_uuids = [NumbersUUID(x.group_uid).hex for x in category_archive.group_node_root.child]
+        group_uuids = [uuid for uuid in sorted_row_uuids if uuid in group_uuids]
+
+        def group_hierarchy(parent: str, children: list):
+            nodes = {}
+            for child in children:
+                group_uuid = NumbersUUID(child.group_uid).hex
+                if len(child.child) > 0:
+                    nodes[group_uuid] = group_hierarchy(group_uuid, child.child)
+                else:
+                    nodes[group_uuid] = None
+            return nodes
+
+        def assign_rows_to_categories(parent: str, children: list, categories: dict):
+            for child in children:
+                group_uuid = NumbersUUID(child.group_uid).hex
+                if len(child.child) == 0:
+                    key = cell_value_to_key(child.group_cell_value)
+
+                    row_offsets = index_set_to_offsets(child.row_lookup_uids)
+                    categories[group_uuid] = {
+                        "key": key,
+                        "parent": parent,
+                        "rows": [
+                            {header[col]: cell.value for col, cell in enumerate(data[row])}
+                            for row in row_offsets
+                        ],
+                    }
+                else:
+                    categories[group_uuid] = {
+                        "key": group_node_to_key[group_uuid],
+                        "parent": parent,
+                        "rows": None,
+                    }
+                    assign_rows_to_categories(group_uuid, child.child, categories)
+
+        category_tree = group_hierarchy(
+            NumbersUUID(category_archive.group_node_root.group_uid).hex,
+            category_archive.group_node_root.child,
+        )
+
+        categories = {}
+        assign_rows_to_categories(None, category_archive.group_node_root.child, categories)
+
+        def merge_trees(a: dict, b: dict):
+            new_tree = {}
+            for k, v in a.items():
+                if v is not None:
+                    new_tree[b[k]["key"]] = merge_trees(v, b)
+                else:
+                    new_tree[b[k]["key"]] = b[k]["rows"]
+            return new_tree
+
+        return merge_trees(category_tree, categories)
+
 
 def rgb(obj) -> RGB:
     """Convert a TSPArchives.Color into an RGB tuple."""

{numbers_parser-4.15.1 → numbers_parser-4.16.2}/src/numbers_parser/numbers_cache.py

@@ -3,7 +3,7 @@ from functools import wraps
 
 
 class Cacheable:
-    def __new__(cls, *args, **kwargs):
+    def __new__(cls, *_args, **_kwargs):
         obj = object.__new__(cls)
         obj._cache = defaultdict(lambda: defaultdict(dict))
         return obj