exstruct 0.2.2__tar.gz → 0.2.3__tar.gz

{exstruct-0.2.2 → exstruct-0.2.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: exstruct
-Version: 0.2.2
+Version: 0.2.3
 Summary: Excel to structured JSON (tables, shapes, charts) for LLM/RAG pipelines
 Keywords: excel,structure,data,exstruct
 Author: harumiWeb
@@ -60,12 +60,12 @@ Description-Content-Type: text/markdown
 
 ![ExStruct Image](/docs/assets/icon.webp)
 
-ExStruct reads Excel workbooks and outputs structured data (tables, shapes, charts, 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), 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). Verbose also emits cell hyperlinks.
+- **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.
@@ -85,7 +85,8 @@ Optional extras:
 - 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.
+
+- Full extraction (shapes/charts) targets Windows + Excel (COM via xlwings). On other platforms, use `mode=light` to get cells + `table_candidates`.
 
 ## Quick Start (CLI)
 
@@ -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))
@@ -120,19 +122,23 @@ 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
-
-engine = ExStructEngine(
-    options=StructOptions(mode="verbose"),  # verbose includes hyperlinks by default
-    output=OutputOptions(include_shapes=False, pretty=True),
-)
-wb2 = engine.extract("input.xlsx")
-engine.export(wb2, Path("out_filtered.json"))  # drops shapes via OutputOptions
-
-# Enable hyperlinks in other modes
-engine_links = ExStructEngine(options=StructOptions(mode="standard", include_cell_links=True))
-with_links = engine_links.extract("input.xlsx")
+# ExStructEngine: per-instance options for extraction/output
+from exstruct import ExStructEngine, StructOptions, OutputOptions
+
+engine = ExStructEngine(
+    options=StructOptions(mode="verbose"),  # verbose includes hyperlinks by default
+    output=OutputOptions(include_shapes=False, pretty=True),
+)
+wb2 = engine.extract("input.xlsx")
+engine.export(wb2, Path("out_filtered.json"))  # drops shapes via OutputOptions
+
+# Enable hyperlinks in other modes
+engine_links = ExStructEngine(options=StructOptions(mode="standard", include_cell_links=True))
+with_links = engine_links.extract("input.xlsx")
+
+# 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.
@@ -152,11 +158,11 @@ set_table_detection_params(
 
 Use higher thresholds to reduce false positives; lower them if true tables are missed.
 
-## Output Modes
-
-- **light**: cells + table candidates (no COM needed).
-- **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.
+## Output Modes
+
+- **light**: cells + table candidates (no COM needed).
+- **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
 
@@ -185,6 +191,7 @@ 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
 
@@ -371,6 +378,12 @@ 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.
@@ -378,18 +391,3 @@ 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) |
-|                | include_cell_links  | Include cell hyperlinks in `rows[*].links` (None -> auto: verbose=True, others=False) |
-| 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-0.2.2 → exstruct-0.2.3}/README.md

@@ -4,12 +4,12 @@
 
 ![ExStruct Image](/docs/assets/icon.webp)
 
-ExStruct reads Excel workbooks and outputs structured data (tables, shapes, charts, 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), 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). Verbose also emits cell hyperlinks.
+- **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.
@@ -29,7 +29,8 @@ Optional extras:
 - 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.
+
+- Full extraction (shapes/charts) targets Windows + Excel (COM via xlwings). On other platforms, use `mode=light` to get cells + `table_candidates`.
 
 ## Quick Start (CLI)
 
@@ -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))
@@ -64,19 +66,23 @@ 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
-
-engine = ExStructEngine(
-    options=StructOptions(mode="verbose"),  # verbose includes hyperlinks by default
-    output=OutputOptions(include_shapes=False, pretty=True),
-)
-wb2 = engine.extract("input.xlsx")
-engine.export(wb2, Path("out_filtered.json"))  # drops shapes via OutputOptions
-
-# Enable hyperlinks in other modes
-engine_links = ExStructEngine(options=StructOptions(mode="standard", include_cell_links=True))
-with_links = engine_links.extract("input.xlsx")
+# ExStructEngine: per-instance options for extraction/output
+from exstruct import ExStructEngine, StructOptions, OutputOptions
+
+engine = ExStructEngine(
+    options=StructOptions(mode="verbose"),  # verbose includes hyperlinks by default
+    output=OutputOptions(include_shapes=False, pretty=True),
+)
+wb2 = engine.extract("input.xlsx")
+engine.export(wb2, Path("out_filtered.json"))  # drops shapes via OutputOptions
+
+# Enable hyperlinks in other modes
+engine_links = ExStructEngine(options=StructOptions(mode="standard", include_cell_links=True))
+with_links = engine_links.extract("input.xlsx")
+
+# 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.
@@ -96,11 +102,11 @@ set_table_detection_params(
 
 Use higher thresholds to reduce false positives; lower them if true tables are missed.
 
-## Output Modes
-
-- **light**: cells + table candidates (no COM needed).
-- **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.
+## Output Modes
+
+- **light**: cells + table candidates (no COM needed).
+- **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
 
@@ -129,6 +135,7 @@ 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
 
@@ -315,6 +322,12 @@ 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.
@@ -322,18 +335,3 @@ 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) |
-|                | include_cell_links  | Include cell hyperlinks in `rows[*].links` (None -> auto: verbose=True, others=False) |
-| 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-0.2.2 → exstruct-0.2.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "exstruct"
-version = "0.2.2"
+version = "0.2.3"
 description = "Excel to structured JSON (tables, shapes, charts) for LLM/RAG pipelines"
 readme = "README.md"
 license = { file = "LICENSE" }

exstruct-0.2.3/src/exstruct/__init__.py

@@ -0,0 +1,215 @@
+from __future__ import annotations
+
+from pathlib import Path
+from typing import Literal, Optional, 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",
+    "ExStructEngine",
+    "StructOptions",
+    "OutputOptions",
+]
+
+
+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: Optional[Literal["json", "yaml", "yml", "toon"]] = 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-0.2.2 → exstruct-0.2.3}/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:

{exstruct-0.2.2 → exstruct-0.2.3}/src/exstruct/core/charts.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 import logging
-from typing import Dict, List, Optional
+from typing import Dict, List, Optional, Literal
 
 import xlwings as xw
 
@@ -166,7 +166,7 @@ def parse_series_formula(formula: str) -> Optional[Dict[str, Optional[str]]]:
     }
 
 
-def get_charts(sheet: xw.Sheet) -> List[Chart]:
+def get_charts(sheet: xw.Sheet, mode: Literal["light", "standard", "verbose"] = "standard") -> List[Chart]:
     """Parse charts in a sheet into Chart models; failed charts carry an error field."""
     charts: List[Chart] = []
     for ch in sheet.charts:
@@ -182,6 +182,14 @@ def get_charts(sheet: xw.Sheet) -> List[Chart]:
             chart_type_label = XL_CHART_TYPE_MAP.get(
                 chart_type_num, f"unknown_{chart_type_num}"
             )
+            chart_width: Optional[int] = None
+            chart_height: Optional[int] = None
+            try:
+                chart_width = int(ch.width)
+                chart_height = int(ch.height)
+            except Exception:
+                chart_width = None
+                chart_height = None
 
             for s in chart_com.SeriesCollection():
                 parsed = parse_series_formula(getattr(s, "Formula", ""))
@@ -220,6 +228,8 @@ def get_charts(sheet: xw.Sheet) -> List[Chart]:
                 title=title,
                 y_axis_title=y_axis_title,
                 y_axis_range=y_axis_range,  # type: ignore
+                w=chart_width,
+                h=chart_height,
                 series=series_list,
                 l=int(ch.left),
                 t=int(ch.top),