trowel 0.3.1

Premium excavation report drafting tool for CRM archaeologists

Trowel ⛏

The archaeologist's essential tool for careful finishing work.

A premium desktop application that transforms digital excavation data into compliance-ready archaeological reports — covering the full post-excavation lifecycle from field data to repository submission.

No GPU required. No cloud dependency. Your data never leaves your machine.

---

📢 Beta testers wanted — If you're a CRM archaeologist, heritage consultant, or field director, we'd love your feedback. Open a Discussion or file an issue. Your data never leaves your machine — no sign-up or account needed.

---

What Trowel Does

Commercial archaeologists spend up to 40% of project budgets on post-excavation report writing. SHPO rejection rates reach 79% on spatial grounds alone. Grey literature backlogs exceed 425,000 reports. Trowel fixes this by:

• Auto-generating prose from structured field data using deterministic Natural Language Generation — no LLM hallucinations in your stratigraphy
• Building compliance-ready reports for 19 jurisdictions: UK (CIfA/MoRPHE), US (Section 106/NHPA + 5 SHPO state configs), Australia (NSW Heritage + Burra Charter), Scotland, Wales, Ireland, Netherlands, France, Germany, Canada-Ontario, New Zealand, South Africa
• Structured report model with provenance tracking — every paragraph links to its source data record (GIS feature, context sheet, photo, find). Enables bidirectional tracing and audit trails per CIfA 2025 AI guidelines
• \label{}/\ref{} cross-referencing — labels auto-resolve to "Section 1", "Figure 2" etc.; stripped in Markdown, live OOXML bookmarks in DOCX that survive manual Word edits
• Bidirectional Harris Matrix editor — drag context nodes to reorder the stratigraphic narrative in real time; move paragraphs to update the matrix DAG (cycle-safe with automatic rollback)
• Queue-and-batch change management — spatial and matrix changes produce a diff queue the author reviews and applies/dismisses as a batch
• Photo plate builder — auto-generates plates from geotagged images with EXIF GPS, regulatory captions, and UTM coordinates
• Programmatic site maps — trench plans, feature distributions, finds heatmaps, and section profiles at 300 DPI
• Field database connectors — import directly from FAIMS Mobile, ARK, and Intrasis exports
• Radiocarbon calibration — calibrate C14 dates via Libby integration (IntCal20). Generates BC/AD labels, HPD ranges, bimodal detection, Hallstatt plateau warnings
• FAIR-compliant archival export — Dig Digital v1.2 DMP, Dublin Core XML, structured JSON data alongside PDF/A and DOCX
• Offline Getty vocabulary lookup — standardise material and period names via Cache & Carry's AAT/ULAN/TGN index
• Lithic analysis appendix — import Dibble CSV/JSON, generate measurement tables and statistical summaries
• Interactive review workflows — paragraph-level comments with source-data tracing back to the original database entries
• AI-assisted NLG (optional) — enhance prose via Ollama/OpenAI/Anthropic with full CIfA 2025 provenance tracking

Quick Start

# Install from PyPI (recommended)
pip install trowel
trowel

# Or from source
git clone https://github.com/mabo-du/trowel.git
cd trowel
pip install -e .
trowel

# Or web UI (requires streamlit)
pip install trowel[web]
streamlit run $(python3 -c "import trowel; print(trowel.__file__)")/../app.py

Load sample_data/synthetic_contexts.csv to see it work in under a minute. See the Quickstart for a 60-second walkthrough.

The Trowel desktop app — import CSV/Excel data, connect to field databases, or load HOARD digitised context sheets

Report preview with 6 tabs — report sections, spatial maps, Harris Matrix, photo plates, AI tools, and peer review

Features

Dual Interface

• Desktop (PyQt6): Native file dialogs, wizard-style workflow, dark Fusion theme, 6-tab report preview (Report / Map / Matrix / Photos / AI / Review) with section-level toggles
• Web (Streamlit): Browser-based alternative, deployable as a team tool, premium CSS design

Data Ingestion

• CSV and Excel parsing with 70+ auto-detected column names (UK and US conventions)
• HOARD JSON import — open a directory of HOARD Phase 1 digitised context sheets; extracts contexts, finds, and samples automatically
• Field database connectors — import directly from FAIMS Mobile, ARK (Archaeological Recording Kit), and Intrasis export directories
• Validates stratigraphic logic: missing references, self-references, cut/fill consistency
• Empty-project guard — when a CSV lacks recognisable context records, shows a clear error instead of generating a fake-looking report
• Quality gate — detects when >90% of parsed contexts have no archaeological data and warns before generation
• Background-thread parsing keeps the UI responsive

Report Generation

• Deterministic NLG — no LLM API calls, no GPU required
• ROMFA inclusion scale — frequent charcoal, occasional CBM, rare flecks, all correctly expanded
• Soil texture vocabulary — silty clay ≠ clayey silt (geologically precise, never treated as synonyms)
• Controlled period labels — Iron Age, Romano-British, post-medieval, etc.
• Section-by-section preview — toggle sections on/off, see live updates
• 12 report sections — frontmatter, introduction, methodology, stratigraphy, finds catalogue, discussion, specialist assessments, archive, site photographs, site maps, and AI disclosure

Jurisdiction Templates

| Jurisdiction | Standard | Config | |---|---|---|---| | UK | CIfA Standard & Guidance / MoRPHE | uk.json | | US | Section 106 (NHPA) | us.json | | US — California | OHP DPR 523 forms | us_ca.json | | US — Texas | THC/TARL TexSite | us_tx.json | | US — Arizona | ASM/SHPO | us_az.json | | US — Colorado | OAHP | us_co.json | | US — North Carolina | OSA | us_nc.json | | Scotland | HES Data Structure Report | scotland.json | | Wales | RCAHMW/Cadw | wales.json | | Ireland | NMS Section 26 | ireland.json | | Australia (NSW) | NSW Heritage Act 1977 | au.json | | Australia (Burra) | ICOMOS Burra Charter | australia_burra.json | | Netherlands | KNA 5.0 | netherlands.json | | France | INRAP / Code du Patrimoine | france.json | | Germany | Landesdenkmalpflege | germany.json | | Canada — Ontario | MCM Standards & Guidelines | canada_ontario.json | | New Zealand | Heritage NZ Pouhere Taonga | new_zealand.json | | South Africa | SAHRA | south_africa.json | | Generic | International fallback | generic.json |

Spatial-Text Engine

• Load GeoJSON, shapefiles, or GeoPackage on the import page
• Template writers use {{ spatial.acreage("Trench 1") }}, {{ spatial.distance("F1", "F2") }}, {{ spatial.centroid_utm("Feature A") }}
• Interactive map preview tab with zoom, pan, and feature hover
• Auto-updates when shapefiles change (e.g., client APE revision)

Interactive Harris Matrix

• Visual DAG editor built into the report preview, colour-coded by context type
• Drag nodes to reorder; the stratigraphic narrative text re-aligns automatically
• Kahn's algorithm topological ordering — detects cycles in stratigraphic relationships
• EEDP export for StratiGraph ecosystem interop

Photo Plate Builder

• Ingests geotagged images from a site photo directory
• Extracts EXIF GPS coordinates, timestamps, and camera orientation via Pillow
• Auto-generates regulatory captions: UTM coordinates, orientation, context cross-references
• Thumbnail grid preview with editable captions
• A4-friendly plate layout (up to 6 images per plate)

Programmatic Site Maps (QGIS-free)

• Trench / Feature Plan — site layout colour-coded by context type
• Feature Distribution — scatter plot by context category
• Artefact Density Heatmap — hexbin finds density with colour bar
• Section Profile — depth transect with labelled stratigraphic units
• All maps at 300 DPI PNG, dark theme, auto-embedded in reports
• Requires matplotlib + geopandas (optional, graceful fallback)

Export Formats

• Editable DOCX — your company template, ready for PI review
• Archival PDF/A-2b — ready for HER deposition
• Plain Markdown — version-control friendly, universal
• Harris Matrix SVG — auto-generated from context relationships (no HOARD dependency)
• FAIR-Compliant Archive — structured package with:
  • Report formats (PDF/A, DOCX, Markdown)
  • Structured JSON data (contexts, finds, samples, spatial)
  • Dublin Core XML metadata (OAI-PMH)
  • Data Management Plan (Dig Digital v1.2 structure)
  • CIfA 2025 AI disclosure appendix
  • Harris Matrix SVG + auto-generated site maps
  • Archive manifest with file listing
• FAIR archive export accessible from the preview toolbar, buttons for individual formats alongside the archive bundle
• AI disclosure appendix auto-generated and included when AI NLG output has been approved

AI-Assisted NLG (Optional)

• Enhance generated prose via local Ollama, OpenAI, or Anthropic APIs
• Prompt-chain architecture: deterministic draft → structured context → LLM enhancement
• Per-sentence provenance tracking — every AI-generated sentence stores which source fields prompted it, the model used, and a timestamp
• CIfA 2025-compliant: AI disclosure appendix declares systems, sections, and validation status
• Human validation gate: AI output is visually distinct until approved
• Fully opt-in — disabled by default, no data ever leaves your machine unless you configure a remote API

Interactive Review Workflows

• Review mode toggle in the preview pane
• Click any paragraph to add a comment with source-data tracing
• Source-data panel shows which contexts, finds, and samples generated the selected text
• Comments are persisted in .trowel project files alongside the data
• Export review summary as Markdown for distribution

Keyboard Shortcuts

Shortcut	Action
Ctrl+O	Open .trowel project file
Ctrl+S	Save project
Ctrl+Shift+S	Save project as...
Ctrl+Shift+O	Import CSV/Excel data
Ctrl+H	Open HOARD project directory
Ctrl+N	New project (clear session)
Ctrl+Q	Quit

---

The StratiGraph Ecosystem

Trowel is part of a suite of open-source tools for digital heritage and archaeology:

| Tool | Repository | Role | Trowel Integration | |---|---|---|---|---| | Trowel | (this repo) | Report drafting from digital field data | — | | HOARD | Heritage Observation And Report Drafter | Paper + photo digitisation pipeline | hoard_import.py / hoard_export.py — bidirectional JSON format; HOARD's docx_writer for premium DOCX | | StratiGraph | Harris Matrix generator | Interactive DAG editor | harris_editor.py → EEDP export; stratigraph_import.py ← HMDP import | | Libby | Radiocarbon calibration | IntCal20 calibration engine | radiocarbon.py — wraps Libby's iosacal-based calibration | | dibble | Lithic analysis | 3D stone tool measurement | lithics.py — imports Dibble CSV/JSON, generates specialist appendix | | Cache & Carry | github.com/mabo-du/cache-and-carry | Offline CMS with Getty vocabularies | vocab_terms.py — reads SQLite for AAT/ULAN/TGN offline term lookup | | Paleo | Palaeontology AI platform | Fossil identification, paleoclimate reconstruction | Adjacent domain | | Fritts | Dendrochronology | Tree-ring cross-dating | Adjacent domain |

How Trowel Integrates

                    ┌──────────────┐
                    │   Libby      │ ← C14 calibration
                    │  (Python)    │
                    └──────┬───────┘
                           │ calibrated dates, SPD curves
                           ▼
┌──────────────┐    ┌──────────────┐    ┌──────────────┐
│   HOARD      │◀──▶│   Trowel     │◀──▶│ StratiGraph  │
│ paper→digital│    │ digital→draft│    │   HMDP DAG   │
└──────────────┘    └──────┬───────┘    └──────────────┘
                           │
                    ┌──────┴───────┐
                    │   Dibble     │ ← lithic measurements
                    │  (Python)    │
                    └──────────────┘
                    ┌─────────────────┐
                    │ Cache & Carry   │ ← Getty AAT/ULAN/TGN
                    │  (Tauri/Rust)   │
                    └─────────────────┘

• HOARD ↔ Trowel: Bidirectional — hoard_import.py reads digitised context sheets; hoard_export.py writes HOARD-compatible JSON for Phase 5 processing.
• Trowel ↔ StratiGraph: Bidirectional — harris_editor.py:to_eedp_dict() exports EEDP paths; stratigraph_import.py:hmdp_to_model() imports HMDP matrices.
• Libby → Trowel: radiocarbon.py wraps Libby's iosacal calibration for C14 dates in specialist appendices.
• Dibble → Trowel: lithics.py imports CSV/JSON measurement output and classification results.
• Cache & Carry → Trowel: vocab_terms.py reads the offline SQLite vocabulary database for material/period standardisation.
• Trowel → QField: qfield_schema.py generates CSV templates matching Trowel's ingest aliases for mobile field collection.

---

Architecture

src/
├── __init__.py         # Package marker
├── main.py             # PyQt6 desktop entry point
├── app.py              # Streamlit web entry point
├── models.py           # Context, Find, Sample, C14Date, ProjectData dataclasses
├── ingest.py           # CSV/Excel parsing, 70+ column aliases, validation
├── vocabulary.py       # ROMFA scale, soil textures, controlled terminology
├── vocab_terms.py      # Getty AAT/ULAN/TGN offline lookup via Cache & Carry
├── nlg.py              # Deterministic NLG engine + Jinja2 section templates
├── nlg_ai.py           # AI NLG (3 backends: Ollama, OpenAI, Anthropic) + provenance
├── report_model.py     # Structured report model with provenance tracking
├── export.py           # Markdown, DOCX (plus OOXML cross-refs), PDF/A, archive
├── eedp.py             # StratiGraph EEDP integration for strat narratives
├── harris_editor.py    # Bidirectional Harris Matrix DAG + semantic diffing
├── spatial_text.py     # Spatial-Text query engine (acreage, distance, UTM)
├── radiocarbon.py      # Libby C14 calibration integration
├── lithics.py          # Dibble lithic analysis specialist appendix
├── hoard_import.py     # HOARD JSON context-sheet import
├── hoard_export.py     # Trowel → HOARD JSON export (bidirectional)
├── stratigraph_import.py # StratiGraph HMDP import for matrix sync
├── qfield_schema.py    # QField mobile field data collection templates
├── automap.py          # QGIS-free site maps (trench, feature, hexbin, section)
├── images.py           # Photo plate builder (EXIF GPS, auto-captions)
├── compliance.py       # DMP (Dig Digital v1.2), Dublin Core XML, AI disclosure
├── review.py           # ReviewComment/ReviewSession models, source-data tracing
├── trowel_io.py        # .trowel project file serialisation (JSON)
├── jurisdictions/      # 19 config-driven jurisdiction definitions
│   ├── __init__.py     # JurisdictionConfig loader, list_jurisdictions()
│   ├── uk.json, us.json, au.json, generic.json
│   ├── us_ca.json, us_tx.json, us_az.json, us_co.json, us_nc.json
│   ├── scotland.json, wales.json, ireland.json
│   ├── netherlands.json, france.json, germany.json
│   ├── canada_ontario.json, australia_burra.json
│   ├── new_zealand.json, south_africa.json
├── connectors/         # Field database connector registry
│   ├── __init__.py, base.py, faims.py, ark.py, intrasis.py
├── ui/                 # PyQt6 desktop UI package
│   ├── __init__.py, theme.py, session.py, main_window.py
│   ├── import_page.py, preview_page.py, map_pane.py
│   ├── matrix_widget.py, plate_view.py, ai_panel.py
│   ├── review_panel.py, connector_dialog.py
├── templates/          # Jinja2 report section templates (6 sections × 19 jurisdictions)
│   ├── generic/, uk/, us/, au/
sample_data/            # Synthetic (37 ctx + 28 finds + 10 samples), GeoJSON
schemas/                # report.schema.json for structured report validation
tests/                  # 373 unit + integration tests

Sample Data

Two example datasets are provided in sample_data/:

Synthetic dataset (recommended for first use): synthetic_contexts.csv — 37 contexts across 5 phases, designed to exercise all jurisdiction templates and edge cases:

Phase	Features
Phase 1 — Natural	River terrace gravels
Phase 2 — Iron Age (800 BC–AD 43)	Enclosure ditch with 3 fills, roundhouse ring-groove, central posthole with in-situ burning, occupation layer
Phase 3 — Roman (AD 43–410)	Stone building with opus signinum floor, limestone walls, clay floor, hearth, demolition layer, quarry pit with 3 fills, inhumation burial
Phase 4 — Medieval (1066–1550)	Cultivation horizon, drainage ditch, rubbish pit with dense artefact assemblage
Phase 5 — Post-Med/Modern	Ploughsoil, modern topsoil with 20th-century inclusions

Plus edge cases: context with interpretation only (998), completely empty context (999), finds referencing non-existent contexts. Also includes synthetic_finds.csv (28 finds) and synthetic_samples.csv (10 samples).

Quick demo: Load sample_data/synthetic_contexts.csv, add the finds and samples files, select UK jurisdiction, and preview all sections.

Original demo: contexts.csv — 12-context Iron Age / Roman site with 12 finds and 5 samples.

---

Requirements

• Python 3.11+
• PyQt6 (desktop UI)
• pandas, openpyxl, jinja2, python-docx, Pillow (core engine)
• matplotlib, geopandas, cartopy (programmatic site maps; pip install trowel[automap])
• openai, anthropic (AI NLG backends; pip install trowel[ai])
• Streamlit (web UI; pip install trowel[web])
• hoard-erd (premium DOCX/PDF/A export; pip install hoard-erd)
• libby, iosacal, numpy (C14 calibration; pip install trowel[c14]) (optional)

Contributing

See CONTRIBUTING.md for the development workflow, code style guide, testing, and PR checklist. All contributions are welcome.

Changelog

See CHANGELOG.md for version history.

Development

Setup

pip install -e ".[dev]"

# Install pre-commit hooks (ruff check + format on every commit)
pre-commit install

Lint & Format

ruff check src/ tests/
ruff format src/ tests/ --check

Run Tests

pytest -v

All three — lint, format check, and tests — run in CI on every push and pull request to main across Linux, Windows, and macOS (Python 3.11–3.13).

Packaging (Standalone Executable)

Trowel can be packaged as a standalone executable so users don't need Python installed.

pip install pyinstaller
make build          # Linux
make build-windows  # on Windows
make build-macos    # on macOS

The output is in dist/Trowel/ — a single folder you can zip and distribute. Double-click Trowel (or Trowel.exe on Windows) to launch.

GitHub Actions runs lint, tests, and builds standalone executables for Linux, Windows, and macOS on every push to main. Download the artifacts from the Actions tab.

Project File Format

Trowel saves and loads projects in .trowel format — a JSON file containing all excavation data and UI state. Use File → Save (Ctrl+S) and File → Open (Ctrl+O) to persist your work.

License

MIT — use it, modify it, ship it. Archaeology deserves better tools, and they should be free.