exstruct 0.2.11__tar.gz → 0.2.51__tar.gz

{exstruct-0.2.11 → exstruct-0.2.51}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: exstruct
-Version: 0.2.11
+Version: 0.2.51
 Summary: Excel to structured JSON (tables, shapes, charts) for LLM/RAG pipelines
 Keywords: excel,structure,data,exstruct
 Author: harumiWeb
@@ -56,16 +56,16 @@ Description-Content-Type: text/markdown
 
 # ExStruct — Excel Structured Extraction Engine
 
-[![PyPI version](https://badge.fury.io/py/exstruct.svg)](https://pypi.org/project/exstruct/) [![PyPI Downloads](https://static.pepy.tech/personalized-badge/exstruct?period=total&units=INTERNATIONAL_SYSTEM&left_color=BLACK&right_color=GREEN&left_text=downloads)](https://pepy.tech/projects/exstruct) ![Licence: BSD-3-Clause](https://img.shields.io/badge/license-BSD--3--Clause-blue?style=flat-square) [![CI](https://github.com/harumiWeb/exstruct/actions/workflows/ci.yml/badge.svg)](https://github.com/harumiWeb/exstruct/actions/workflows/ci.yml)
+[![PyPI version](https://badge.fury.io/py/exstruct.svg)](https://pypi.org/project/exstruct/) [![PyPI Downloads](https://static.pepy.tech/personalized-badge/exstruct?period=total&units=INTERNATIONAL_SYSTEM&left_color=BLACK&right_color=GREEN&left_text=downloads)](https://pepy.tech/projects/exstruct) ![Licence: BSD-3-Clause](https://img.shields.io/badge/license-BSD--3--Clause-blue?style=flat-square) [![pytest](https://github.com/harumiWeb/exstruct/actions/workflows/pytest.yml/badge.svg)](https://github.com/harumiWeb/exstruct/actions/workflows/pytest.yml)
 
 ![ExStruct Image](/docs/assets/icon.webp)
 
-ExStruct reads Excel workbooks and outputs structured data (tables, shapes, charts) as JSON by default, with optional YAML/TOON formats. It targets both COM/Excel environments (rich extraction) and non-COM environments (cells + table candidates), with tunable detection heuristics and multiple output modes to fit LLM/RAG pipelines.
+ExStruct reads Excel workbooks and outputs structured data (cells, table candidates, shapes, charts, print areas/views, hyperlinks) as JSON by default, with optional YAML/TOON formats. It targets both COM/Excel environments (rich extraction) and non-COM environments (cells + table candidates + print areas), with tunable detection heuristics and multiple output modes to fit LLM/RAG pipelines.
 
 ## Features
 
-- **Excel → Structured JSON**: cells, shapes, charts, and table candidates per sheet.
-- **Output modes**: `light` (cells + table candidates only), `standard` (texted shapes + arrows, charts), `verbose` (all shapes with width/height).
+- **Excel → Structured JSON**: cells, shapes, charts, table candidates, and print areas/views per sheet.
+- **Output modes**: `light` (cells + table candidates + print areas; no COM, shapes/charts empty), `standard` (texted shapes + arrows, charts, print areas), `verbose` (all shapes with width/height, charts with size, print areas). Verbose also emits cell hyperlinks. Size output is flag-controlled.
 - **Formats**: JSON (compact by default, `--pretty` available), YAML, TOON (optional dependencies).
 - **Table detection tuning**: adjust heuristics at runtime via API.
 - **CLI rendering** (Excel required): optional PDF and per-sheet PNGs.
@@ -77,17 +77,18 @@ ExStruct reads Excel workbooks and outputs structured data (tables, shapes, char
 pip install exstruct
 ```
 
-Optional extras:
-
-- YAML: `pip install pyyaml`
-- TOON: `pip install python-toon`
-- Rendering (PDF/PNG): Excel + `pip install pypdfium2 pillow`
-- All extras at once: `pip install exstruct[yaml,toon,render]`
-
-Platform note:
-- Full extraction (shapes/charts) targets Windows + Excel (COM via xlwings). On other platforms, use `mode=light` to get cells + `table_candidates` safely.
-
-## Quick Start (CLI)
+Optional extras:
+
+- YAML: `pip install pyyaml`
+- TOON: `pip install python-toon`
+- Rendering (PDF/PNG): Excel + `pip install pypdfium2 pillow`
+- All extras at once: `pip install exstruct[yaml,toon,render]`
+
+Platform note:
+
+- Full extraction (shapes/charts) targets Windows + Excel (COM via xlwings). On other platforms, use `mode=light` to get cells + `table_candidates`.
+
+## Quick Start (CLI)
 
 ```bash
 exstruct input.xlsx > output.json          # compact JSON to stdout (default)
@@ -95,6 +96,7 @@ exstruct input.xlsx -o out.json --pretty   # pretty JSON to a file
 exstruct input.xlsx --format yaml          # YAML (needs pyyaml)
 exstruct input.xlsx --format toon          # TOON (needs python-toon)
 exstruct input.xlsx --sheets-dir sheets/   # split per sheet in chosen format
+exstruct input.xlsx --print-areas-dir areas/  # split per print area (if any)
 exstruct input.xlsx --mode light           # cells + table candidates only
 exstruct input.xlsx --pdf --image          # PDF and PNGs (Excel required)
 ```
@@ -112,7 +114,7 @@ set_table_detection_params(table_score_threshold=0.3, density_min=0.04)
 wb = extract("input.xlsx", mode="standard")
 export(wb, Path("out.json"), pretty=False)  # compact JSON
 
-# Model helpers: iterate, index, and serialize directly from the models
+# Model helpers: iterate, index, and serialize directly
 first_sheet = wb["Sheet1"]           # __getitem__ access
 for name, sheet in wb:               # __iter__ yields (name, SheetData)
     print(name, len(sheet.rows))
@@ -120,15 +122,27 @@ wb.save("out.json", pretty=True)     # WorkbookData → file (by extension)
 first_sheet.save("sheet.json")       # SheetData → file (by extension)
 print(first_sheet.to_yaml())         # YAML text (requires pyyaml)
 
-# ExStructEngine: per-instance options for extraction/output
-from exstruct import ExStructEngine, StructOptions, OutputOptions
+# ExStructEngine: per-instance options (nested configs)
+from exstruct import ExStructEngine, StructOptions, OutputOptions, FormatOptions, FilterOptions, DestinationOptions
+
+engine = ExStructEngine(
+    options=StructOptions(mode="verbose"),  # verbose includes hyperlinks by default
+    output=OutputOptions(
+        format=FormatOptions(pretty=True),
+        filters=FilterOptions(include_shapes=False),  # drop shapes in output
+        destinations=DestinationOptions(sheets_dir=Path("out_sheets")),  # also write per-sheet files
+    ),
+)
+wb2 = engine.extract("input.xlsx")
+engine.export(wb2, Path("out_filtered.json"))  # drops shapes via filters
+
+# Enable hyperlinks in other modes
+engine_links = ExStructEngine(options=StructOptions(mode="standard", include_cell_links=True))
+with_links = engine_links.extract("input.xlsx")
 
-engine = ExStructEngine(
-    options=StructOptions(mode="standard"),
-    output=OutputOptions(include_shapes=False, pretty=True),
-)
-wb2 = engine.extract("input.xlsx")
-engine.export(wb2, Path("out_filtered.json"))  # drops shapes via OutputOptions
+# Export per print area (if print areas exist)
+from exstruct import export_print_areas_as
+export_print_areas_as(wb, "areas", fmt="json", pretty=True)
 ```
 
 **Note (non-COM environments):** If Excel COM is unavailable, extraction still runs and returns cells + `table_candidates`; `shapes`/`charts` will be empty.
@@ -151,8 +165,8 @@ Use higher thresholds to reduce false positives; lower them if true tables are m
 ## Output Modes
 
 - **light**: cells + table candidates (no COM needed).
-- **standard**: texted shapes + arrows, charts (COM if available), table candidates.
-- **verbose**: all shapes (with width/height), charts, table candidates.
+- **standard**: texted shapes + arrows, charts (COM if available), table candidates. Hyperlinks are off unless `include_cell_links=True`.
+- **verbose**: all shapes (with width/height), charts, table candidates, and cell hyperlinks.
 
 ## Error Handling / Fallbacks
 
@@ -181,6 +195,7 @@ To show how well exstruct can structure Excel, we parse a workbook that combines
 (Screenshot below is the actual sample Excel sheet)
 ![Sample Excel](/docs/assets/demo_sheet.png)
 Sample workbook: `sample/sample.xlsx`
+Sample workbook: `sample/sample.xlsx`
 
 ### 1. Input: Excel Sheet Overview
 
@@ -367,6 +382,12 @@ In short, **exstruct = “an engine that converts Excel into a format AI can und
 - Default JSON is compact to reduce tokens; use `--pretty` or `pretty=True` when readability matters.
 - Field `table_candidates` replaces `tables`; adjust downstream consumers accordingly.
 
+## Print Areas (PrintArea / PrintAreaView)
+
+- `SheetData.print_areas` holds print areas (cell coordinates) in light/standard/verbose.
+- Use `export_print_areas_as(...)` or CLI `--print-areas-dir` to write one file per print area (nothing is written if none exist).
+- `PrintAreaView` includes rows and table candidates inside the area, plus shapes/charts that overlap the area (size-less shapes are treated as points). `normalize=True` rebases row/col indices to the area origin.
+
 ## License
 
 BSD-3-Clause. See `LICENSE` for details.
@@ -374,17 +395,3 @@ BSD-3-Clause. See `LICENSE` for details.
 ## Documentation
 
 - API Reference (GitHub Pages): https://harumiweb.github.io/exstruct/
-# Engine option cheat sheet
-
-| Option class   | Field               | Meaning |
-| -------------- | ------------------- | ------- |
-| StructOptions  | mode                | "light"/"standard"/"verbose" |
-|                | table_params        | Dict passed to `set_table_detection_params` (table_score_threshold, density_min, coverage_min, min_nonempty_cells) |
-| OutputOptions  | fmt                 | Default format ("json"/"yaml"/"yml"/"toon") |
-|                | pretty / indent     | Pretty-print JSON and control indent |
-|                | include_rows        | Include rows (False to drop) |
-|                | include_shapes      | Include shapes |
-|                | include_charts      | Include charts |
-|                | include_tables      | Include table_candidates |
-|                | sheets_dir          | Optional directory for per-sheet exports |
-|                | stream              | Default stream when output_path is None |

{exstruct-0.2.11 → exstruct-0.2.51}/README.md

@@ -1,15 +1,15 @@
 # ExStruct — Excel Structured Extraction Engine
 
-[![PyPI version](https://badge.fury.io/py/exstruct.svg)](https://pypi.org/project/exstruct/) [![PyPI Downloads](https://static.pepy.tech/personalized-badge/exstruct?period=total&units=INTERNATIONAL_SYSTEM&left_color=BLACK&right_color=GREEN&left_text=downloads)](https://pepy.tech/projects/exstruct) ![Licence: BSD-3-Clause](https://img.shields.io/badge/license-BSD--3--Clause-blue?style=flat-square) [![CI](https://github.com/harumiWeb/exstruct/actions/workflows/ci.yml/badge.svg)](https://github.com/harumiWeb/exstruct/actions/workflows/ci.yml)
+[![PyPI version](https://badge.fury.io/py/exstruct.svg)](https://pypi.org/project/exstruct/) [![PyPI Downloads](https://static.pepy.tech/personalized-badge/exstruct?period=total&units=INTERNATIONAL_SYSTEM&left_color=BLACK&right_color=GREEN&left_text=downloads)](https://pepy.tech/projects/exstruct) ![Licence: BSD-3-Clause](https://img.shields.io/badge/license-BSD--3--Clause-blue?style=flat-square) [![pytest](https://github.com/harumiWeb/exstruct/actions/workflows/pytest.yml/badge.svg)](https://github.com/harumiWeb/exstruct/actions/workflows/pytest.yml)
 
 ![ExStruct Image](/docs/assets/icon.webp)
 
-ExStruct reads Excel workbooks and outputs structured data (tables, shapes, charts) as JSON by default, with optional YAML/TOON formats. It targets both COM/Excel environments (rich extraction) and non-COM environments (cells + table candidates), with tunable detection heuristics and multiple output modes to fit LLM/RAG pipelines.
+ExStruct reads Excel workbooks and outputs structured data (cells, table candidates, shapes, charts, print areas/views, hyperlinks) as JSON by default, with optional YAML/TOON formats. It targets both COM/Excel environments (rich extraction) and non-COM environments (cells + table candidates + print areas), with tunable detection heuristics and multiple output modes to fit LLM/RAG pipelines.
 
 ## Features
 
-- **Excel → Structured JSON**: cells, shapes, charts, and table candidates per sheet.
-- **Output modes**: `light` (cells + table candidates only), `standard` (texted shapes + arrows, charts), `verbose` (all shapes with width/height).
+- **Excel → Structured JSON**: cells, shapes, charts, table candidates, and print areas/views per sheet.
+- **Output modes**: `light` (cells + table candidates + print areas; no COM, shapes/charts empty), `standard` (texted shapes + arrows, charts, print areas), `verbose` (all shapes with width/height, charts with size, print areas). Verbose also emits cell hyperlinks. Size output is flag-controlled.
 - **Formats**: JSON (compact by default, `--pretty` available), YAML, TOON (optional dependencies).
 - **Table detection tuning**: adjust heuristics at runtime via API.
 - **CLI rendering** (Excel required): optional PDF and per-sheet PNGs.
@@ -21,17 +21,18 @@ ExStruct reads Excel workbooks and outputs structured data (tables, shapes, char
 pip install exstruct
 ```
 
-Optional extras:
-
-- YAML: `pip install pyyaml`
-- TOON: `pip install python-toon`
-- Rendering (PDF/PNG): Excel + `pip install pypdfium2 pillow`
-- All extras at once: `pip install exstruct[yaml,toon,render]`
-
-Platform note:
-- Full extraction (shapes/charts) targets Windows + Excel (COM via xlwings). On other platforms, use `mode=light` to get cells + `table_candidates` safely.
-
-## Quick Start (CLI)
+Optional extras:
+
+- YAML: `pip install pyyaml`
+- TOON: `pip install python-toon`
+- Rendering (PDF/PNG): Excel + `pip install pypdfium2 pillow`
+- All extras at once: `pip install exstruct[yaml,toon,render]`
+
+Platform note:
+
+- Full extraction (shapes/charts) targets Windows + Excel (COM via xlwings). On other platforms, use `mode=light` to get cells + `table_candidates`.
+
+## Quick Start (CLI)
 
 ```bash
 exstruct input.xlsx > output.json          # compact JSON to stdout (default)
@@ -39,6 +40,7 @@ exstruct input.xlsx -o out.json --pretty   # pretty JSON to a file
 exstruct input.xlsx --format yaml          # YAML (needs pyyaml)
 exstruct input.xlsx --format toon          # TOON (needs python-toon)
 exstruct input.xlsx --sheets-dir sheets/   # split per sheet in chosen format
+exstruct input.xlsx --print-areas-dir areas/  # split per print area (if any)
 exstruct input.xlsx --mode light           # cells + table candidates only
 exstruct input.xlsx --pdf --image          # PDF and PNGs (Excel required)
 ```
@@ -56,7 +58,7 @@ set_table_detection_params(table_score_threshold=0.3, density_min=0.04)
 wb = extract("input.xlsx", mode="standard")
 export(wb, Path("out.json"), pretty=False)  # compact JSON
 
-# Model helpers: iterate, index, and serialize directly from the models
+# Model helpers: iterate, index, and serialize directly
 first_sheet = wb["Sheet1"]           # __getitem__ access
 for name, sheet in wb:               # __iter__ yields (name, SheetData)
     print(name, len(sheet.rows))
@@ -64,15 +66,27 @@ wb.save("out.json", pretty=True)     # WorkbookData → file (by extension)
 first_sheet.save("sheet.json")       # SheetData → file (by extension)
 print(first_sheet.to_yaml())         # YAML text (requires pyyaml)
 
-# ExStructEngine: per-instance options for extraction/output
-from exstruct import ExStructEngine, StructOptions, OutputOptions
+# ExStructEngine: per-instance options (nested configs)
+from exstruct import ExStructEngine, StructOptions, OutputOptions, FormatOptions, FilterOptions, DestinationOptions
+
+engine = ExStructEngine(
+    options=StructOptions(mode="verbose"),  # verbose includes hyperlinks by default
+    output=OutputOptions(
+        format=FormatOptions(pretty=True),
+        filters=FilterOptions(include_shapes=False),  # drop shapes in output
+        destinations=DestinationOptions(sheets_dir=Path("out_sheets")),  # also write per-sheet files
+    ),
+)
+wb2 = engine.extract("input.xlsx")
+engine.export(wb2, Path("out_filtered.json"))  # drops shapes via filters
+
+# Enable hyperlinks in other modes
+engine_links = ExStructEngine(options=StructOptions(mode="standard", include_cell_links=True))
+with_links = engine_links.extract("input.xlsx")
 
-engine = ExStructEngine(
-    options=StructOptions(mode="standard"),
-    output=OutputOptions(include_shapes=False, pretty=True),
-)
-wb2 = engine.extract("input.xlsx")
-engine.export(wb2, Path("out_filtered.json"))  # drops shapes via OutputOptions
+# Export per print area (if print areas exist)
+from exstruct import export_print_areas_as
+export_print_areas_as(wb, "areas", fmt="json", pretty=True)
 ```
 
 **Note (non-COM environments):** If Excel COM is unavailable, extraction still runs and returns cells + `table_candidates`; `shapes`/`charts` will be empty.
@@ -95,8 +109,8 @@ Use higher thresholds to reduce false positives; lower them if true tables are m
 ## Output Modes
 
 - **light**: cells + table candidates (no COM needed).
-- **standard**: texted shapes + arrows, charts (COM if available), table candidates.
-- **verbose**: all shapes (with width/height), charts, table candidates.
+- **standard**: texted shapes + arrows, charts (COM if available), table candidates. Hyperlinks are off unless `include_cell_links=True`.
+- **verbose**: all shapes (with width/height), charts, table candidates, and cell hyperlinks.
 
 ## Error Handling / Fallbacks
 
@@ -125,6 +139,7 @@ To show how well exstruct can structure Excel, we parse a workbook that combines
 (Screenshot below is the actual sample Excel sheet)
 ![Sample Excel](/docs/assets/demo_sheet.png)
 Sample workbook: `sample/sample.xlsx`
+Sample workbook: `sample/sample.xlsx`
 
 ### 1. Input: Excel Sheet Overview
 
@@ -311,6 +326,12 @@ In short, **exstruct = “an engine that converts Excel into a format AI can und
 - Default JSON is compact to reduce tokens; use `--pretty` or `pretty=True` when readability matters.
 - Field `table_candidates` replaces `tables`; adjust downstream consumers accordingly.
 
+## Print Areas (PrintArea / PrintAreaView)
+
+- `SheetData.print_areas` holds print areas (cell coordinates) in light/standard/verbose.
+- Use `export_print_areas_as(...)` or CLI `--print-areas-dir` to write one file per print area (nothing is written if none exist).
+- `PrintAreaView` includes rows and table candidates inside the area, plus shapes/charts that overlap the area (size-less shapes are treated as points). `normalize=True` rebases row/col indices to the area origin.
+
 ## License
 
 BSD-3-Clause. See `LICENSE` for details.
@@ -318,17 +339,3 @@ BSD-3-Clause. See `LICENSE` for details.
 ## Documentation
 
 - API Reference (GitHub Pages): https://harumiweb.github.io/exstruct/
-# Engine option cheat sheet
-
-| Option class   | Field               | Meaning |
-| -------------- | ------------------- | ------- |
-| StructOptions  | mode                | "light"/"standard"/"verbose" |
-|                | table_params        | Dict passed to `set_table_detection_params` (table_score_threshold, density_min, coverage_min, min_nonempty_cells) |
-| OutputOptions  | fmt                 | Default format ("json"/"yaml"/"yml"/"toon") |
-|                | pretty / indent     | Pretty-print JSON and control indent |
-|                | include_rows        | Include rows (False to drop) |
-|                | include_shapes      | Include shapes |
-|                | include_charts      | Include charts |
-|                | include_tables      | Include table_candidates |
-|                | sheets_dir          | Optional directory for per-sheet exports |
-|                | stream              | Default stream when output_path is None |

exstruct-0.2.51/pyproject.toml

@@ -0,0 +1,111 @@
+[project]
+name = "exstruct"
+version = "0.2.51"
+description = "Excel to structured JSON (tables, shapes, charts) for LLM/RAG pipelines"
+readme = "README.md"
+license = { file = "LICENSE" }
+keywords = ["excel", "structure", "data", "exstruct"]
+authors = [
+    { name = "harumiWeb", email = "ganaharumi@outlook.jp" }
+]
+requires-python = ">=3.11"
+dependencies = [
+    "numpy>=2.3.5",
+    "openpyxl>=3.1.5",
+    "pandas>=2.3.3",
+    "pydantic>=2.12.5",
+    "scipy>=1.16.3",
+    "xlwings>=0.33.16",
+]
+
+[build-system]
+requires = ["uv_build>=0.8.4,<0.9.0"]
+build-backend = "uv_build"
+
+[dependency-groups]
+dev = [
+    "mkdocs-material>=9.7.0",
+    "mypy>=1.19.0",
+    "pytest>=9.0.1",
+    "pytest-cov>=7.0.0",
+    "pytest-mock>=3.15.1",
+    "ruff>=0.14.8",
+]
+
+[project.optional-dependencies]
+yaml = ["pyyaml>=6.0.3"]
+toon = ["python-toon>=0.1.3"]
+render = ["pypdfium2>=5.1.0", "Pillow>=12.0.0"]
+
+[project.scripts]
+exstruct = "exstruct.cli.main:main"
+
+[project.urls]
+Homepage = "https://harumiweb.github.io/exstruct/"
+Repository = "https://github.com/harumiWeb/exstruct"
+Issues = "https://github.com/harumiWeb/exstruct/issues"
+Documentation = "https://harumiweb.github.io/exstruct/"
+
+[tool.coverage.run]
+omit = [
+    "tests/*",
+    "*/test_*.py",
+    "*/gen_py/*",
+]
+
+[tool.ruff]
+target-version = "py311"
+src = ["exstruct"]
+
+select = [
+    "E",   # pycodestyle errors
+    "W",   # pycodestyle warnings
+    "F",   # pyflakes
+    "I",   # import sorting
+    "UP",  # pyupgrade
+    "B",   # flake8-bugbear
+    "N",   # naming
+    "C90", # complexity
+    "A",   # flake8-builtins
+    "ANN", # type annotations
+]
+
+ignore = [
+    "E501",   # 行長は許容（Excel JSON は長くなりがち）
+    "B008",   # Pydantic の default_factory を誤検知するため
+    "ANN101", # self に型を要求されてしまうため
+    "ANN102", # cls も同様
+]
+
+fix = true
+
+# 型ヒントのスタイル
+[tool.ruff.lint]
+extend-select = ["ANN"]
+
+# import の並び替え設定
+[tool.ruff.isort]
+combine-as-imports = true
+known-first-party = ["exstruct"]
+force-sort-within-sections = true
+
+# 複雑度チェック（関数の最大複雑度）
+[tool.ruff.mccabe]
+max-complexity = 12
+
+[tool.ruff.per-file-ignores]
+"tests/**/*.py" = ["N802", "N803", "N806"]
+
+
+[tool.mypy]
+packages = ["exstruct"]
+python_version = "3.11"
+
+# 外部ライブラリは一切チェックしない
+ignore_missing_imports = true
+
+# 自作コードは厳密にチェックする
+strict = true
+
+# Pydantic v2 向け
+plugins = ["pydantic.mypy"]

exstruct-0.2.51/src/exstruct/__init__.py

@@ -0,0 +1,217 @@
+from __future__ import annotations
+
+from pathlib import Path
+from typing import Literal, TextIO
+
+from .core.cells import set_table_detection_params
+from .core.integrate import extract_workbook
+from .engine import ExStructEngine, OutputOptions, StructOptions
+from .io import (
+    save_as_json,
+    save_as_toon,
+    save_as_yaml,
+    save_print_area_views,
+    save_sheets,
+    serialize_workbook,
+)
+from .models import (
+    CellRow,
+    Chart,
+    ChartSeries,
+    PrintArea,
+    PrintAreaView,
+    Shape,
+    SheetData,
+    WorkbookData,
+)
+from .render import export_pdf, export_sheet_images
+
+__all__ = [
+    "extract",
+    "export",
+    "export_sheets",
+    "export_sheets_as",
+    "export_print_areas_as",
+    "export_pdf",
+    "export_sheet_images",
+    "process_excel",
+    "ExtractionMode",
+    "CellRow",
+    "Shape",
+    "ChartSeries",
+    "Chart",
+    "SheetData",
+    "WorkbookData",
+    "PrintArea",
+    "PrintAreaView",
+    "set_table_detection_params",
+    "extract_workbook",
+    "ExStructEngine",
+    "StructOptions",
+    "OutputOptions",
+    "serialize_workbook",
+]
+
+
+ExtractionMode = Literal["light", "standard", "verbose"]
+
+
+def extract(file_path: str | Path, mode: ExtractionMode = "standard") -> WorkbookData:
+    """
+    Extract an Excel workbook into WorkbookData.
+
+    Args:
+        file_path: Path to .xlsx/.xlsm/.xls.
+        mode: "light" / "standard" / "verbose"
+            - light: cells + table detection only (no COM, shapes/charts empty). Print areas via openpyxl.
+            - standard: texted shapes + arrows + charts (COM if available), print areas included. Shape/chart size is kept but hidden by default in output.
+            - verbose: all shapes (including textless) with size, charts with size.
+    """
+    include_links = True if mode == "verbose" else False
+    engine = ExStructEngine(
+        options=StructOptions(mode=mode, include_cell_links=include_links)
+    )
+    return engine.extract(file_path, mode=mode)
+
+
+def export(
+    data: WorkbookData,
+    path: str | Path,
+    fmt: Literal["json", "yaml", "yml", "toon"] | None = None,
+    *,
+    pretty: bool = False,
+    indent: int | None = None,
+) -> None:
+    """
+    Save WorkbookData to a file (format inferred from extension).
+
+    Args:
+        data: WorkbookData from `extract` or similar
+        path: destination path; extension is used to infer format
+        fmt: explicitly set format if desired (json/yaml/yml/toon)
+        pretty: pretty-print JSON
+        indent: JSON indent width (defaults to 2 when pretty=True and indent is None)
+    """
+    dest = Path(path)
+    format_hint = (fmt or dest.suffix.lstrip(".") or "json").lower()
+    match format_hint:
+        case "json":
+            save_as_json(data, dest, pretty=pretty, indent=indent)
+        case "yaml" | "yml":
+            save_as_yaml(data, dest)
+        case "toon":
+            save_as_toon(data, dest)
+        case _:
+            raise ValueError(f"Unsupported export format: {format_hint}")
+
+
+def export_sheets(data: WorkbookData, dir_path: str | Path) -> dict[str, Path]:
+    """
+    Export each sheet as an individual JSON file.
+
+    - Payload: {book_name, sheet_name, sheet: SheetData}
+    - Returns: {sheet_name: Path}
+    """
+    return save_sheets(data, Path(dir_path), fmt="json")
+
+
+def export_sheets_as(
+    data: WorkbookData,
+    dir_path: str | Path,
+    fmt: Literal["json", "yaml", "yml", "toon"] = "json",
+    *,
+    pretty: bool = False,
+    indent: int | None = None,
+) -> dict[str, Path]:
+    """Export each sheet in the given format (json/yaml/toon); returns sheet name to path map."""
+    return save_sheets(data, Path(dir_path), fmt=fmt, pretty=pretty, indent=indent)
+
+
+def export_print_areas_as(
+    data: WorkbookData,
+    dir_path: str | Path,
+    fmt: Literal["json", "yaml", "yml", "toon"] = "json",
+    *,
+    pretty: bool = False,
+    indent: int | None = None,
+    normalize: bool = False,
+) -> dict[str, Path]:
+    """
+    Export each print area as a PrintAreaView.
+
+    Args:
+        data: WorkbookData that contains print areas
+        dir_path: output directory
+        fmt: json/yaml/yml/toon
+        pretty/indent: JSON formatting options
+        normalize: rebase row/col indices to the print-area origin when True
+    Returns:
+        dict mapping area key to path (e.g., "Sheet1#1": /.../Sheet1_area1_...json)
+    """
+    return save_print_area_views(
+        data,
+        Path(dir_path),
+        fmt=fmt,
+        pretty=pretty,
+        indent=indent,
+        normalize=normalize,
+    )
+
+
+def process_excel(
+    file_path: Path,
+    output_path: Path | None = None,
+    out_fmt: str = "json",
+    image: bool = False,
+    pdf: bool = False,
+    dpi: int = 72,
+    mode: ExtractionMode = "standard",
+    pretty: bool = False,
+    indent: int | None = None,
+    sheets_dir: Path | None = None,
+    print_areas_dir: Path | None = None,
+    stream: TextIO | None = None,
+) -> None:
+    """
+    Convenience wrapper: extract → serialize (file or stdout) → optional PDF/PNG.
+
+    Args:
+        file_path: input Excel
+        output_path: None for stdout; otherwise, write to file
+        out_fmt: json/yaml/yml/toon
+        image/pdf: True to also output PNG/PDF (requires Excel + pypdfium2)
+        dpi: DPI for image output
+        mode: light/standard/verbose (same meaning as `extract`)
+        pretty/indent: JSON formatting
+        sheets_dir: directory to write per-sheet files
+        print_areas_dir: directory to write per-print-area files
+        stream: IO override when output_path is None
+    """
+    engine = ExStructEngine(
+        options=StructOptions(mode=mode),
+        output=OutputOptions(
+            fmt=out_fmt,
+            pretty=pretty,
+            indent=indent,
+            sheets_dir=sheets_dir,
+            print_areas_dir=print_areas_dir,
+            include_print_areas=None if mode == "light" else True,
+            include_shape_size=True if mode == "verbose" else False,
+            include_chart_size=True if mode == "verbose" else False,
+            stream=stream,
+        ),
+    )
+    engine.process(
+        file_path=file_path,
+        output_path=output_path,
+        out_fmt=out_fmt,
+        image=image,
+        pdf=pdf,
+        dpi=dpi,
+        mode=mode,
+        pretty=pretty,
+        indent=indent,
+        sheets_dir=sheets_dir,
+        print_areas_dir=print_areas_dir,
+        stream=stream,
+    )

{exstruct-0.2.11 → exstruct-0.2.51}/src/exstruct/cli/main.py

@@ -57,6 +57,11 @@ def build_parser() -> argparse.ArgumentParser:
         type=Path,
         help="Optional directory to write one file per sheet (format follows --format).",
     )
+    parser.add_argument(
+        "--print-areas-dir",
+        type=Path,
+        help="Optional directory to write one file per print area (format follows --format).",
+    )
     return parser
 
 
@@ -80,6 +85,7 @@ def main(argv: list[str] | None = None) -> int:
             mode=args.mode,
             pretty=args.pretty,
             sheets_dir=args.sheets_dir,
+            print_areas_dir=args.print_areas_dir,
         )
         return 0
     except Exception as e: