tablewise 1.1.0__tar.gz

tablewise-1.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Luis Francisco Palomares Gamarra
+
+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.

tablewise-1.1.0/PKG-INFO

@@ -0,0 +1,217 @@
+Metadata-Version: 2.4
+Name: tablewise
+Version: 1.1.0
+Summary: Convierte PDF/Word/Excel/PowerPoint a Markdown con cabecera de procedencia, listo para un RAG
+Author: Luis Francisco Palomares Gamarra
+License: MIT License
+        
+        Copyright (c) 2026 Luis Francisco Palomares Gamarra
+        
+        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.
+        
+Keywords: markdown,rag,pdf,docx,xlsx,markitdown,docling
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Environment :: MacOS X
+Classifier: Topic :: Text Processing :: Markup :: Markdown
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Provides-Extra: excel
+Requires-Dist: openpyxl>=3.1; extra == "excel"
+Provides-Extra: docling
+Requires-Dist: docling; extra == "docling"
+Provides-Extra: dev
+Requires-Dist: pytest>=8; extra == "dev"
+Requires-Dist: openpyxl>=3.1; extra == "dev"
+Requires-Dist: PyYAML>=6; extra == "dev"
+Dynamic: license-file
+
+# Tablewise
+
+**Spreadsheet-grade document conversion to Markdown, with provenance.**
+PDF, Word, Excel and PowerPoint in; clean, citable Markdown out — built for RAG,
+LLM ingestion and audit trails.
+
+Every output file starts with a header that tells your retrieval layer where the
+text came from:
+
+```markdown
+---
+source: "2026-budget.xlsx"
+engine: "excel"
+converted: 2026-10-22
+---
+```
+
+Three front ends, one decision engine:
+
+- **`tablewise` CLI** — one document in, one `.md` out. Scripts, agents, batches.
+- **Desktop app** (Tkinter) — for people who do not live in a terminal.
+- **Hosted API** — `POST /v1/convert`, per-month plans, no install. See
+  [PRICING.md](PRICING.md).
+
+## The problem it solves
+
+Most converters flatten a financial table into something no model can use. A
+three-level header (`Hotel · 2026 · Real/Budget · Jan..Dec`) comes out as 70
+columns named `Unnamed: 12`, formulas vanish, and a percentage becomes `0.8769`.
+A RAG built on that answers with the wrong number and no way to prove it.
+
+Tablewise routes spreadsheets to an engine that reads the sheet as a sheet:
+
+| Hotel | 2026 | 2026 | 2026 |
+|  | Real | Budget | Last year |
+|  | Jan | Feb | Jan |
+| ADR | 120.50 | 110 | 105.25 |
+| Occupancy | 87.69% |  |  |
+
+- Merged cells and multi-level headers preserved as a real Markdown table.
+- Dates as `YYYY-MM-DD`, percentages with their format, `-0.00` never appears.
+- Hidden sheets kept but labelled `(hidden sheet)`.
+- A formula that was never recalculated says `(formula not calculated)` instead
+  of an empty cell that a model reads as zero.
+- Deterministic: no AI, no network, same bytes in → same Markdown out.
+
+## Quickstart
+
+```bash
+pip install -e .            # installs the `tablewise` command
+tablewise report.pdf                    # -> ~/md-repo/report.md
+tablewise budget.xlsx -o ~/md-repo -n "2026 budget"
+tablewise contract.docx --dry-run       # print the engine command, do not run it
+```
+
+The desktop app:
+
+```bash
+python tablewise_app.py
+```
+
+The API:
+
+```bash
+curl -X POST https://api.tablewise.dev/v1/convert \
+  -H "Authorization: Bearer $TABLEWISE_API_KEY" \
+  -F "file=@budget.xlsx"
+```
+
+## Why not just MarkItDown / Docling?
+
+They are good engines and Tablewise uses both. The difference is the routing,
+the table fidelity and the provenance — not a new parser.
+
+| | MarkItDown | Docling | Tablewise |
+|---|---|---|---|
+| Excel with merged / multi-level header | flattened | partial | read as a sheet |
+| Formula never recalculated | empty cell | empty cell | labelled |
+| Provenance header on every file | no | no | yes |
+| Deterministic, no AI, no network | yes | yes (heavy) | yes |
+| Desktop GUI for non-technical users | no | no | yes |
+| Hosted API with per-month plans and batch | no | no | yes |
+
+## Engine routing
+
+Each extension has exactly one owner:
+
+- `.xlsx` `.xlsm` `.xltx` `.xltm` → `motor_excel.py` (openpyxl, local, no AI)
+- `.pdf` `.docx` `.pptx` → `motor_docling.py` (Docling, local, no AI)
+- `.doc` `.rtf` `.odt` → `textutil` (macOS) → HTML → `motor_docling.py`
+- `.xls` `.ppt` (Office 97-2003) → LibreOffice → `.xlsx`/`.pptx` → `motor_excel.py` / `motor_docling.py`
+- everything else (CSV, HTML, EPUB, …) → MarkItDown
+
+The two own engines are `motor_excel.py` and `motor_docling.py`. A format
+without an available engine is refused with an explicit message, never silently
+degraded.
+
+## CLI reference
+
+```
+tablewise DOCUMENT [-o DIR] [-n NAME] [--python PATH] [--markitdown PATH]
+                   [--force] [--dry-run] [-q] [--version]
+```
+
+- Never overwrites an existing `.md` without `--force`.
+- Exit codes: `0` ok · `1` the engine produced no file · `2` invalid input.
+- `--python` / `TABLEWISE_PYTHON`: interpreter that carries docling/openpyxl.
+- `--markitdown` / `TABLEWISE_MARKITDOWN`: MarkItDown executable.
+
+## Hosted API
+
+The API is the same engine behind HTTP, for teams that cannot install anything:
+
+| Plan | Units / month | Price |
+|---|---|---|
+| Free | 50 | $0 |
+| Starter | 1,000 | $19 |
+| Pro | 5,000 | $49 |
+| Business | 25,000 | $149 |
+
+One unit = one PDF page, one spreadsheet sheet, one slide, or one document.
+Overage $0.015/unit. Annual −20%. The full contract (quota, DPA, refunds) is in
+[PRICING.md](PRICING.md) and on the website.
+
+## Development
+
+Runner: `pytest`, using the engines virtualenv (it carries openpyxl and PyYAML):
+
+```bash
+.venv/bin/python3 -m pytest -q              # 432 tests
+.venv/bin/python3 -m pytest server/tests -q # 46 API tests
+```
+
+| File | What it covers |
+|---|---|
+| `tests/test_core.py` | `tablewise_core.py`: extension routing, safe names, engine command (`shlex`, `~`), YAML frontmatter, atomic write, free name |
+| `tests/test_motor_excel.py` | `motor_excel.py` on synthetic books: merged cells, unevaluated formulas, empty rows/columns, dates, hidden sheets, safety ceiling |
+| `tests/test_cli_motores.py` | engine CLI contract by subprocess (exit code + message, never a traceback) |
+| `tests/test_motor_docling.py` | `.doc`/`.rtf`/`.odt` preconversion to HTML with `textutil` (no Docling import; skipped off macOS) |
+| `tests/test_preconversion.py` | LibreOffice (`soffice`): lookup outside PATH and `.xls` → `.xlsx` keeping merges (skipped without LibreOffice) |
+| `tests/test_preconversion_errores.py` | `preconversion.py` with simulated `subprocess.run`: timeout, tool that cannot start, exit 0 without file, error code, own profile |
+| `tests/test_motor_docling_convertir.py` | `motor_docling.convertir` with an injected fake Docling: empty output, temp cleanup, `.ppt` routing, uppercase extensions |
+| `tests/test_entradas_externas.py` | `.xls` path, malformed array formulas, backslashes in the YAML header, non-UTF-8 output, BOM and CRLF |
+| `tests/test_preconversion_ejecutables_falsos.py` | textutil/LibreOffice boundary with fake executables |
+| `tests/test_app_convertir.py` | `App.convert()` with fake tkinter and engine: existing `.md` (cancel / numbered copy / overwrite), failing engine, non-UTF-8 output, partial writes |
+| `tests/test_motor_docling_cli.py` | `motor_docling` CLI with a fake `docling` package |
+| `tests/test_red_sintaxis.py` | regression net: every application file is valid Python and the app imports without opening a window |
+| `tests/test_cli.py` | `tablewise` CLI: same decisions as the app, `--dry-run`, no overwrite without `--force`, exit codes |
+| `tests/test_docs.py` | drift net: this README lists every test file and every routed extension |
+
+No test uses real documents.
+
+## Limits and security
+
+- Upload limit 25 MB and 2,000 units per request (configurable).
+- Engines run as subprocesses with a timeout; a hung converter cannot take the
+  worker down.
+- API keys are stored as SHA-256 hashes and shown once.
+- No document content is logged. See `web/privacy.html` and `web/dpa.html`.
+- macOS-only pieces: `textutil` (`.doc`/`.rtf`/`.odt`) and the Tkinter app.
+  LibreOffice is needed for `.xls`/`.ppt`.
+
+## License
+
+MIT. See [LICENSE](LICENSE).
+
+---
+
+Spanish engineering log, kept for continuity: [README.es.md](README.es.md).

tablewise-1.1.0/README.md

@@ -0,0 +1,169 @@
+# Tablewise
+
+**Spreadsheet-grade document conversion to Markdown, with provenance.**
+PDF, Word, Excel and PowerPoint in; clean, citable Markdown out — built for RAG,
+LLM ingestion and audit trails.
+
+Every output file starts with a header that tells your retrieval layer where the
+text came from:
+
+```markdown
+---
+source: "2026-budget.xlsx"
+engine: "excel"
+converted: 2026-10-22
+---
+```
+
+Three front ends, one decision engine:
+
+- **`tablewise` CLI** — one document in, one `.md` out. Scripts, agents, batches.
+- **Desktop app** (Tkinter) — for people who do not live in a terminal.
+- **Hosted API** — `POST /v1/convert`, per-month plans, no install. See
+  [PRICING.md](PRICING.md).
+
+## The problem it solves
+
+Most converters flatten a financial table into something no model can use. A
+three-level header (`Hotel · 2026 · Real/Budget · Jan..Dec`) comes out as 70
+columns named `Unnamed: 12`, formulas vanish, and a percentage becomes `0.8769`.
+A RAG built on that answers with the wrong number and no way to prove it.
+
+Tablewise routes spreadsheets to an engine that reads the sheet as a sheet:
+
+| Hotel | 2026 | 2026 | 2026 |
+|  | Real | Budget | Last year |
+|  | Jan | Feb | Jan |
+| ADR | 120.50 | 110 | 105.25 |
+| Occupancy | 87.69% |  |  |
+
+- Merged cells and multi-level headers preserved as a real Markdown table.
+- Dates as `YYYY-MM-DD`, percentages with their format, `-0.00` never appears.
+- Hidden sheets kept but labelled `(hidden sheet)`.
+- A formula that was never recalculated says `(formula not calculated)` instead
+  of an empty cell that a model reads as zero.
+- Deterministic: no AI, no network, same bytes in → same Markdown out.
+
+## Quickstart
+
+```bash
+pip install -e .            # installs the `tablewise` command
+tablewise report.pdf                    # -> ~/md-repo/report.md
+tablewise budget.xlsx -o ~/md-repo -n "2026 budget"
+tablewise contract.docx --dry-run       # print the engine command, do not run it
+```
+
+The desktop app:
+
+```bash
+python tablewise_app.py
+```
+
+The API:
+
+```bash
+curl -X POST https://api.tablewise.dev/v1/convert \
+  -H "Authorization: Bearer $TABLEWISE_API_KEY" \
+  -F "file=@budget.xlsx"
+```
+
+## Why not just MarkItDown / Docling?
+
+They are good engines and Tablewise uses both. The difference is the routing,
+the table fidelity and the provenance — not a new parser.
+
+| | MarkItDown | Docling | Tablewise |
+|---|---|---|---|
+| Excel with merged / multi-level header | flattened | partial | read as a sheet |
+| Formula never recalculated | empty cell | empty cell | labelled |
+| Provenance header on every file | no | no | yes |
+| Deterministic, no AI, no network | yes | yes (heavy) | yes |
+| Desktop GUI for non-technical users | no | no | yes |
+| Hosted API with per-month plans and batch | no | no | yes |
+
+## Engine routing
+
+Each extension has exactly one owner:
+
+- `.xlsx` `.xlsm` `.xltx` `.xltm` → `motor_excel.py` (openpyxl, local, no AI)
+- `.pdf` `.docx` `.pptx` → `motor_docling.py` (Docling, local, no AI)
+- `.doc` `.rtf` `.odt` → `textutil` (macOS) → HTML → `motor_docling.py`
+- `.xls` `.ppt` (Office 97-2003) → LibreOffice → `.xlsx`/`.pptx` → `motor_excel.py` / `motor_docling.py`
+- everything else (CSV, HTML, EPUB, …) → MarkItDown
+
+The two own engines are `motor_excel.py` and `motor_docling.py`. A format
+without an available engine is refused with an explicit message, never silently
+degraded.
+
+## CLI reference
+
+```
+tablewise DOCUMENT [-o DIR] [-n NAME] [--python PATH] [--markitdown PATH]
+                   [--force] [--dry-run] [-q] [--version]
+```
+
+- Never overwrites an existing `.md` without `--force`.
+- Exit codes: `0` ok · `1` the engine produced no file · `2` invalid input.
+- `--python` / `TABLEWISE_PYTHON`: interpreter that carries docling/openpyxl.
+- `--markitdown` / `TABLEWISE_MARKITDOWN`: MarkItDown executable.
+
+## Hosted API
+
+The API is the same engine behind HTTP, for teams that cannot install anything:
+
+| Plan | Units / month | Price |
+|---|---|---|
+| Free | 50 | $0 |
+| Starter | 1,000 | $19 |
+| Pro | 5,000 | $49 |
+| Business | 25,000 | $149 |
+
+One unit = one PDF page, one spreadsheet sheet, one slide, or one document.
+Overage $0.015/unit. Annual −20%. The full contract (quota, DPA, refunds) is in
+[PRICING.md](PRICING.md) and on the website.
+
+## Development
+
+Runner: `pytest`, using the engines virtualenv (it carries openpyxl and PyYAML):
+
+```bash
+.venv/bin/python3 -m pytest -q              # 432 tests
+.venv/bin/python3 -m pytest server/tests -q # 46 API tests
+```
+
+| File | What it covers |
+|---|---|
+| `tests/test_core.py` | `tablewise_core.py`: extension routing, safe names, engine command (`shlex`, `~`), YAML frontmatter, atomic write, free name |
+| `tests/test_motor_excel.py` | `motor_excel.py` on synthetic books: merged cells, unevaluated formulas, empty rows/columns, dates, hidden sheets, safety ceiling |
+| `tests/test_cli_motores.py` | engine CLI contract by subprocess (exit code + message, never a traceback) |
+| `tests/test_motor_docling.py` | `.doc`/`.rtf`/`.odt` preconversion to HTML with `textutil` (no Docling import; skipped off macOS) |
+| `tests/test_preconversion.py` | LibreOffice (`soffice`): lookup outside PATH and `.xls` → `.xlsx` keeping merges (skipped without LibreOffice) |
+| `tests/test_preconversion_errores.py` | `preconversion.py` with simulated `subprocess.run`: timeout, tool that cannot start, exit 0 without file, error code, own profile |
+| `tests/test_motor_docling_convertir.py` | `motor_docling.convertir` with an injected fake Docling: empty output, temp cleanup, `.ppt` routing, uppercase extensions |
+| `tests/test_entradas_externas.py` | `.xls` path, malformed array formulas, backslashes in the YAML header, non-UTF-8 output, BOM and CRLF |
+| `tests/test_preconversion_ejecutables_falsos.py` | textutil/LibreOffice boundary with fake executables |
+| `tests/test_app_convertir.py` | `App.convert()` with fake tkinter and engine: existing `.md` (cancel / numbered copy / overwrite), failing engine, non-UTF-8 output, partial writes |
+| `tests/test_motor_docling_cli.py` | `motor_docling` CLI with a fake `docling` package |
+| `tests/test_red_sintaxis.py` | regression net: every application file is valid Python and the app imports without opening a window |
+| `tests/test_cli.py` | `tablewise` CLI: same decisions as the app, `--dry-run`, no overwrite without `--force`, exit codes |
+| `tests/test_docs.py` | drift net: this README lists every test file and every routed extension |
+
+No test uses real documents.
+
+## Limits and security
+
+- Upload limit 25 MB and 2,000 units per request (configurable).
+- Engines run as subprocesses with a timeout; a hung converter cannot take the
+  worker down.
+- API keys are stored as SHA-256 hashes and shown once.
+- No document content is logged. See `web/privacy.html` and `web/dpa.html`.
+- macOS-only pieces: `textutil` (`.doc`/`.rtf`/`.odt`) and the Tkinter app.
+  LibreOffice is needed for `.xls`/`.ppt`.
+
+## License
+
+MIT. See [LICENSE](LICENSE).
+
+---
+
+Spanish engineering log, kept for continuity: [README.es.md](README.es.md).

tablewise-1.1.0/motor_docling.py

@@ -0,0 +1,80 @@
+"""
+Conversor de PDF/Word/PowerPoint (y escaneados) a Markdown con Docling
+(IBM, open source, 100% local, gratis) -- sustituye a MarkItDown para estos
+formatos porque reconstruye tablas complejas con celdas combinadas en vez
+de volcarlas en crudo (ver README.md, "Piloto de alternativas gratis",
+23/08/2026).
+
+Import diferido: docling carga modelos pesados (layout/tabla) la primera
+vez que se usa. Se importa dentro de convertir(), no al importar el
+módulo, para que cargar este fichero sea barato -- solo paga el coste
+quien de verdad convierte un documento (invocado siempre como subprocess
+en un venv aparte, nunca dentro del proceso de la GUI Tkinter).
+
+CLI: python motor_docling.py <origen> <destino.md>
+Librería: from motor_docling import convertir
+"""
+import sys
+import tempfile
+from pathlib import Path
+
+from tablewise_core import EXTENSIONES_TEXTUTIL, escribir_atomico, misma_ruta
+from preconversion import con_soffice, con_textutil
+
+
+class ConversionVacia(Exception):
+    """Docling no produjo ningún contenido."""
+
+
+def preconvertir(origen: Path, carpeta: Path) -> Path:
+    """Lo que Docling no lee bien, a un formato que sí:
+    - .doc/.rtf/.odt → HTML con textutil (macOS). HTML y no .docx: el
+      .docx de textutil aplana las tablas, y la ruta nativa de Docling para
+      .doc también (pasa por LibreOffice y saca "ConceptoImporte...").
+    - .ppt → .pptx con LibreOffice.
+    Lo demás se devuelve tal cual."""
+    ext = origen.suffix.lower()
+    if ext in EXTENSIONES_TEXTUTIL:
+        return con_textutil(origen, carpeta)
+    if ext == ".ppt":
+        return con_soffice(origen, "pptx", carpeta)
+    return origen
+
+
+def convertir(origen: Path) -> str:
+    from docling.document_converter import DocumentConverter
+
+    converter = DocumentConverter()
+    with tempfile.TemporaryDirectory(prefix="tablewise-") as tmp:
+        resultado = converter.convert(str(preconvertir(origen, Path(tmp))))
+    md = resultado.document.export_to_markdown()
+    if not md.strip():
+        raise ConversionVacia(f"Docling no produjo contenido para {origen.name}.")
+    return md
+
+
+if __name__ == "__main__":
+    if len(sys.argv) < 3:
+        sys.exit("Uso: python motor_docling.py <origen> <destino.md>")
+    origen = Path(sys.argv[1]).expanduser()
+    destino = Path(sys.argv[2]).expanduser()
+    if not origen.exists():
+        sys.exit(f"No existe: {origen}")
+    if misma_ruta(origen, destino):
+        sys.exit(f"El destino es el propio documento de origen ({origen.name}): "
+                 "no se sobrescribe.")
+
+    try:
+        md = convertir(origen)
+    except ConversionVacia as e:
+        sys.exit(str(e))
+    except Exception as e:
+        sys.exit(f"motor_docling falló con {origen.name}: {e}")
+
+    try:
+        escribir_atomico(destino, md)
+    except (OSError, UnicodeError) as e:
+        # Sin esto, un destino no escribible acababa en traceback crudo,
+        # que la app enseña tal cual en el diálogo de error.
+        sys.exit(f"No se pudo escribir {destino}: {e}")
+    print(f"Guardado en {destino} ({len(md)} caracteres)")