msdoc2docx 0.7.0__tar.gz

msdoc2docx-0.7.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 doc2docx contributors
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

msdoc2docx-0.7.0/PKG-INFO

@@ -0,0 +1,84 @@
+Metadata-Version: 2.4
+Name: msdoc2docx
+Version: 0.7.0
+Summary: A specification-driven, pure-Python Word binary .doc to .docx converter
+Author: doc2docx contributors
+License: MIT
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Dynamic: license-file
+
+# doc2docx
+
+`doc2docx` is a specification-driven, pure-Python converter for Microsoft Word
+97–2003 binary `.doc` files. It does not invoke Microsoft Word, LibreOffice,
+COM, Java, or an external conversion executable.
+
+The current M0–M5b implementation supports unencrypted CFB/OLE Word documents,
+the `0Table`/`1Table` selection mechanism, CLX piece tables, compressed and
+UTF-16LE text pieces, and the main document story. It reads CHPX/PAPX FKPs and
+preserves a useful first set of direct character and paragraph properties. It
+also reads the SttbfFfn font table, emits DOCX font definitions, converts
+paragraph/character styles with `basedOn` inheritance, resolves style-relative
+toggles, and applies simple and complex piece-level PRMs in specification order.
+It reconstructs tables from DOC cell/row markers, including nested tables, and
+preserves their column grid, preferred cell widths, basic merges, alignment,
+row sizing, Word 97 borders and shading, and default or range-specific cell
+margins. It also follows main-story `PlcfSed` records through `Sed.fcSepx` to
+each `Sepx.grpprl`, reconstructing single or multiple sections. Section-break
+types, paper size, portrait/landscape orientation, page margins, header/footer
+distance, and gutter width are emitted as WordprocessingML section properties.
+It parses `PlcfHdd`, removes each story's guard paragraph, preserves the six
+default/even/first header and footer positions per section, and retains empty-story
+inheritance. Header/footer parts, relationships, first-page rules, and the DOP
+facing-pages setting are written as native DOCX package parts.
+
+## Usage
+
+```console
+python -m pip install msdoc2docx
+doc2docx input.doc
+doc2docx input.doc -o output.docx --report report.json
+doc2docx inspect input.doc --json
+```
+
+To install from a local source checkout instead, run `python -m pip install .`.
+
+Python API:
+
+```python
+from doc2docx import convert
+
+result = convert("input.doc", "output.docx")
+print(result.report.to_dict())
+```
+
+M5b currently preserves bold, italic, strike, double strike, capitalization,
+hidden text, underline, text color, highlight, font size, vertical alignment,
+paragraph justification, indents, spacing, line spacing, and keep/page-break
+flags, font names, paragraph/character style references, style inheritance,
+basic section/page layout, and ordinary paragraph/table content in headers and
+footers.
+Conditional table styles, newer color-based table shading, cell spacing,
+numbering styles, multi-column layout, page-number settings, header/footer
+textboxes and shapes, other secondary stories, images, live fields, embedded
+objects, and encrypted documents are intentionally deferred to later iterations.
+Unsupported or lossy content is reported rather than silently treated as fully
+converted.
+
+## Tests
+
+The test suite uses only the Python standard library:
+
+```console
+PYTHONPATH=src python -m unittest discover -v
+```
+
+It includes constructed CFB version 3/version 4 files, regular and mini streams,
+both Table stream variants, mixed compressed/UTF-16 text pieces, UTF-16 surrogate
+pair coordinates, CHPX/PAPX and piece-level PRM formatting, font/style table
+parsing, nested table reconstruction, grids, cell margins and shading, PlcfSed and
+Sepx page-layout parsing, multi-section break placement, PlcfHdd guard and story
+mapping, header/footer OPC relationships, malformed input checks, CLI coverage,
+and end-to-end DOCX package validation.

msdoc2docx-0.7.0/README.md

@@ -0,0 +1,73 @@
+# doc2docx
+
+`doc2docx` is a specification-driven, pure-Python converter for Microsoft Word
+97–2003 binary `.doc` files. It does not invoke Microsoft Word, LibreOffice,
+COM, Java, or an external conversion executable.
+
+The current M0–M5b implementation supports unencrypted CFB/OLE Word documents,
+the `0Table`/`1Table` selection mechanism, CLX piece tables, compressed and
+UTF-16LE text pieces, and the main document story. It reads CHPX/PAPX FKPs and
+preserves a useful first set of direct character and paragraph properties. It
+also reads the SttbfFfn font table, emits DOCX font definitions, converts
+paragraph/character styles with `basedOn` inheritance, resolves style-relative
+toggles, and applies simple and complex piece-level PRMs in specification order.
+It reconstructs tables from DOC cell/row markers, including nested tables, and
+preserves their column grid, preferred cell widths, basic merges, alignment,
+row sizing, Word 97 borders and shading, and default or range-specific cell
+margins. It also follows main-story `PlcfSed` records through `Sed.fcSepx` to
+each `Sepx.grpprl`, reconstructing single or multiple sections. Section-break
+types, paper size, portrait/landscape orientation, page margins, header/footer
+distance, and gutter width are emitted as WordprocessingML section properties.
+It parses `PlcfHdd`, removes each story's guard paragraph, preserves the six
+default/even/first header and footer positions per section, and retains empty-story
+inheritance. Header/footer parts, relationships, first-page rules, and the DOP
+facing-pages setting are written as native DOCX package parts.
+
+## Usage
+
+```console
+python -m pip install msdoc2docx
+doc2docx input.doc
+doc2docx input.doc -o output.docx --report report.json
+doc2docx inspect input.doc --json
+```
+
+To install from a local source checkout instead, run `python -m pip install .`.
+
+Python API:
+
+```python
+from doc2docx import convert
+
+result = convert("input.doc", "output.docx")
+print(result.report.to_dict())
+```
+
+M5b currently preserves bold, italic, strike, double strike, capitalization,
+hidden text, underline, text color, highlight, font size, vertical alignment,
+paragraph justification, indents, spacing, line spacing, and keep/page-break
+flags, font names, paragraph/character style references, style inheritance,
+basic section/page layout, and ordinary paragraph/table content in headers and
+footers.
+Conditional table styles, newer color-based table shading, cell spacing,
+numbering styles, multi-column layout, page-number settings, header/footer
+textboxes and shapes, other secondary stories, images, live fields, embedded
+objects, and encrypted documents are intentionally deferred to later iterations.
+Unsupported or lossy content is reported rather than silently treated as fully
+converted.
+
+## Tests
+
+The test suite uses only the Python standard library:
+
+```console
+PYTHONPATH=src python -m unittest discover -v
+```
+
+It includes constructed CFB version 3/version 4 files, regular and mini streams,
+both Table stream variants, mixed compressed/UTF-16 text pieces, UTF-16 surrogate
+pair coordinates, CHPX/PAPX and piece-level PRM formatting, font/style table
+parsing, nested table reconstruction, grids, cell margins and shading, PlcfSed and
+Sepx page-layout parsing, multi-section break placement, PlcfHdd guard and story
+mapping, header/footer OPC relationships, malformed input checks, CLI coverage,
+and end-to-end DOCX package validation.

msdoc2docx-0.7.0/pyproject.toml

@@ -0,0 +1,19 @@
+[build-system]
+requires = ["setuptools>=68"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "msdoc2docx"
+version = "0.7.0"
+description = "A specification-driven, pure-Python Word binary .doc to .docx converter"
+readme = "README.md"
+requires-python = ">=3.11"
+license = {text = "MIT"}
+authors = [{name = "doc2docx contributors"}]
+dependencies = []
+
+[project.scripts]
+doc2docx = "doc2docx.cli:main"
+
+[tool.setuptools.packages.find]
+where = ["src"]

msdoc2docx-0.7.0/setup.cfg

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

msdoc2docx-0.7.0/src/doc2docx/__init__.py

@@ -0,0 +1,6 @@
+"""Public API for doc2docx."""
+
+from .converter import ConversionResult, convert, inspect_doc
+
+__all__ = ["ConversionResult", "convert", "inspect_doc"]
+__version__ = "0.7.0"

msdoc2docx-0.7.0/src/doc2docx/__main__.py

@@ -0,0 +1,4 @@
+from .cli import main
+
+raise SystemExit(main())
+

msdoc2docx-0.7.0/src/doc2docx/binary/__init__.py

@@ -0,0 +1,4 @@
+from .reader import BinaryReader
+
+__all__ = ["BinaryReader"]
+

msdoc2docx-0.7.0/src/doc2docx/binary/reader.py

@@ -0,0 +1,87 @@
+"""Small, bounded little-endian binary reader."""
+
+from __future__ import annotations
+
+import struct
+
+from ..errors import BinaryBoundsError
+
+
+class BinaryReader:
+    def __init__(
+        self,
+        data: bytes | bytearray | memoryview,
+        *,
+        label: str = "binary data",
+        base_offset: int = 0,
+    ) -> None:
+        self._data = memoryview(data).cast("B")
+        self._position = 0
+        self.label = label
+        self.base_offset = base_offset
+
+    def __len__(self) -> int:
+        return len(self._data)
+
+    @property
+    def position(self) -> int:
+        return self._position
+
+    @property
+    def remaining(self) -> int:
+        return len(self._data) - self._position
+
+    def _check(self, offset: int, size: int) -> None:
+        if offset < 0 or size < 0 or offset > len(self._data) - size:
+            absolute = self.base_offset + max(offset, 0)
+            raise BinaryBoundsError(
+                f"{self.label}: read of {size} bytes at offset 0x{absolute:X} "
+                f"exceeds {len(self._data)}-byte structure"
+            )
+
+    def seek(self, offset: int) -> None:
+        self._check(offset, 0)
+        self._position = offset
+
+    def skip(self, size: int) -> None:
+        self.seek(self._position + size)
+
+    def read(self, size: int) -> bytes:
+        self._check(self._position, size)
+        start = self._position
+        self._position += size
+        return self._data[start : start + size].tobytes()
+
+    def read_at(self, offset: int, size: int) -> bytes:
+        self._check(offset, size)
+        return self._data[offset : offset + size].tobytes()
+
+    def subreader(self, offset: int, size: int, *, label: str | None = None) -> "BinaryReader":
+        self._check(offset, size)
+        return BinaryReader(
+            self._data[offset : offset + size],
+            label=label or self.label,
+            base_offset=self.base_offset + offset,
+        )
+
+    def _unpack(self, fmt: str, size: int) -> int:
+        self._check(self._position, size)
+        value = struct.unpack_from(fmt, self._data, self._position)[0]
+        self._position += size
+        return int(value)
+
+    def u8(self) -> int:
+        return self._unpack("<B", 1)
+
+    def u16(self) -> int:
+        return self._unpack("<H", 2)
+
+    def u32(self) -> int:
+        return self._unpack("<I", 4)
+
+    def i32(self) -> int:
+        return self._unpack("<i", 4)
+
+    def u64(self) -> int:
+        return self._unpack("<Q", 8)
+

msdoc2docx-0.7.0/src/doc2docx/cfb/__init__.py

@@ -0,0 +1,5 @@
+from .container import CompoundFile, CompoundFileLimits
+from .directory import DirectoryEntry, ObjectType
+
+__all__ = ["CompoundFile", "CompoundFileLimits", "DirectoryEntry", "ObjectType"]
+

msdoc2docx-0.7.0/src/doc2docx/cfb/constants.py

@@ -0,0 +1,9 @@
+CFB_SIGNATURE = bytes.fromhex("D0CF11E0A1B11AE1")
+
+MAXREGSECT = 0xFFFFFFFA
+DIFSECT = 0xFFFFFFFC
+FATSECT = 0xFFFFFFFD
+ENDOFCHAIN = 0xFFFFFFFE
+FREESECT = 0xFFFFFFFF
+NOSTREAM = 0xFFFFFFFF
+