mdengine 0.4.0__tar.gz → 0.6.0__tar.gz

{mdengine-0.4.0 → mdengine-0.6.0}/PKG-INFO

@@ -1,13 +1,13 @@
 Metadata-Version: 2.4
 Name: mdengine
-Version: 0.4.0
-Summary: Convert PDF, Office, images, audio, video, text/JSON/XML, ZIP archives, and web URLs to Markdown.
+Version: 0.6.0
+Summary: Convert PDF, Office, images, audio, video, text/JSON/XML, ZIP archives, web URLs, databases, graphs, and OpenAPI specs to Markdown.
 Author: mdengine contributors
 License-Expression: MIT
 Project-URL: Homepage, https://github.com/vishal7090/md-generator
 Project-URL: Repository, https://github.com/vishal7090/md-generator
 Project-URL: Issues, https://github.com/vishal7090/md-generator/issues
-Keywords: markdown,pdf,docx,pptx,xlsx,ocr,zip,url,html,youtube,playwright
+Keywords: markdown,pdf,docx,pptx,xlsx,ocr,zip,url,html,youtube,playwright,database,openapi
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3 :: Only
 Classifier: Topic :: Text Processing :: Markup :: Markdown
@@ -87,6 +87,22 @@ Requires-Dist: lxml>=5.0.0; extra == "playwright"
 Requires-Dist: markdownify>=0.14.0; extra == "playwright"
 Requires-Dist: readability-lxml>=0.8.1; extra == "playwright"
 Requires-Dist: Pillow>=10.0.0; extra == "playwright"
+Provides-Extra: db
+Requires-Dist: sqlalchemy>=2.0.0; extra == "db"
+Requires-Dist: pyyaml>=6.0.0; extra == "db"
+Requires-Dist: psycopg2-binary>=2.9.9; extra == "db"
+Requires-Dist: pymysql>=1.1.0; extra == "db"
+Requires-Dist: oracledb>=2.0.0; extra == "db"
+Requires-Dist: pymongo>=4.6.0; extra == "db"
+Requires-Dist: mermaid-py>=0.8.0; extra == "db"
+Provides-Extra: graph
+Requires-Dist: networkx>=3.2.0; extra == "graph"
+Requires-Dist: neo4j>=5.14.0; extra == "graph"
+Requires-Dist: pyyaml>=6.0.0; extra == "graph"
+Provides-Extra: openapi
+Requires-Dist: pyyaml>=6.0.0; extra == "openapi"
+Requires-Dist: prance>=23.6.0; extra == "openapi"
+Requires-Dist: openapi-spec-validator>=0.7.0; extra == "openapi"
 Provides-Extra: api
 Requires-Dist: fastapi>=0.115.0; extra == "api"
 Requires-Dist: uvicorn[standard]>=0.32.0; extra == "api"
@@ -106,6 +122,9 @@ Requires-Dist: mdengine[api]; extra == "dev"
 Requires-Dist: mdengine[mcp]; extra == "dev"
 Requires-Dist: mdengine[url]; extra == "dev"
 Requires-Dist: mdengine[playwright]; extra == "dev"
+Requires-Dist: mdengine[db]; extra == "dev"
+Requires-Dist: mdengine[graph]; extra == "dev"
+Requires-Dist: mdengine[openapi]; extra == "dev"
 Provides-Extra: all
 Requires-Dist: pymupdf>=1.24.0; extra == "all"
 Requires-Dist: pdfplumber>=0.11.0; extra == "all"
@@ -136,7 +155,7 @@ Dynamic: license-file
 
 # mdengine
 
-Single Python distribution for converting **PDF**, **Word (.docx)**, **PowerPoint (.pptx)**, **Excel (.xlsx/.xlsm)**, **images** (OCR), **plain text / JSON / XML**, **ZIP archives**, and **audio / video** (Whisper transcription → Markdown) into **Markdown** (and related assets). Install only the extras you need; everything imports under the **`md_generator`** package.
+Single Python distribution for converting **PDF**, **Word (.docx)**, **PowerPoint (.pptx)**, **Excel (.xlsx/.xlsm)**, **images** (OCR), **plain text / JSON / XML**, **ZIP archives**, **audio / video** (Whisper transcription → Markdown), **database metadata** (SQL + Mongo), and **graphs** (Neo4j / NetworkX → Markdown) into **Markdown** (and related assets). Install only the extras you need; everything imports under the **`md_generator`** package.
 
 - **PyPI name:** `mdengine` (import package: `md_generator`)
 - **Source:** [github.com/vishal7090/md-generator](https://github.com/vishal7090/md-generator)
@@ -214,6 +233,7 @@ pip install "mdengine[all]"
 | `video` | **Video → Markdown** (ffmpeg extracts mono 16 kHz WAV, then same Whisper stack as `audio`) |
 | `api` | FastAPI, uvicorn, httpx, pydantic-settings |
 | `mcp` | MCP servers (`mcp`, `fastmcp` where used) |
+| `graph` | **Graph → Markdown** (Neo4j Bolt + NetworkX GraphML/GML): `networkx`, `neo4j`, `pyyaml` |
 | `dev` | pytest + API/MCP test helpers |
 | `all` | Large superset of dependencies (use only if you need everything) |
 
@@ -228,7 +248,7 @@ All converters can be run from a terminal after you install the package (with th
 ### 1. Install (once)
 
 ```bash
-pip install "mdengine[pdf,word]"          # adjust extras: ppt, xlsx, image, archive, text, …
+pip install "mdengine[pdf,word]"          # adjust extras: ppt, xlsx, image, archive, text, db, graph, …
 # or from a clone:
 pip install -e ".[pdf,word,archive]"
 ```
@@ -263,6 +283,28 @@ If the shell reports “command not found”, ensure the Python **Scripts** dire
 | `md-audio-mcp` | `md_generator.media.audio.api.mcp_server:main` | Standalone MCP (`--transport stdio` \| `sse` \| `streamable-http`) |
 | `md-video-mcp` | `md_generator.media.video.api.mcp_server:main` | Same for video |
 | `md-youtube-mcp` | `md_generator.media.youtube.api.mcp_server:main` | Same for YouTube (`youtube_url_to_markdown`) |
+| `md-db` | `md_generator.db.cli.main:main` | `pip install "mdengine[db]"` then `md-db --config db.yaml` (or `mdengine db-to-md …`) |
+| `md-db-api` | `md_generator.db.api.run:main` | FastAPI on port **8010** (`DB_TO_MD_PORT`): `POST /db-to-md/run`, `POST /db-to-md/run/sqlite` (upload + ZIP), `POST /db-to-md/job`, `POST /db-to-md/job/sqlite` (upload + async job), SSE `/db-to-md/job/{id}/events` |
+| `md-db-mcp` | `md_generator.db.api.mcp_server:main` | Standalone MCP for metadata export tools |
+| `md-graph` | `md_generator.graph.cli.main:main` | `pip install "mdengine[graph]"` then `md-graph --source neo4j --uri bolt://…` (or `mdengine graph-to-md …`) |
+| `md-graph-api` | `md_generator.graph.api.run:main` | FastAPI on port **8012** (`GRAPH_TO_MD_PORT`): `POST /graph-to-md/run`, `/graph-to-md/job`, SSE `/graph-to-md/job/{id}/events` |
+| `md-graph-mcp` | `md_generator.graph.api.mcp_server:main` | Standalone MCP for graph export tools |
+| `md-openapi` | `md_generator.openapi.cli.main:main` | `pip install "mdengine[openapi]"` then `md-openapi generate --file openapi.yaml --output ./docs` (or `mdengine openapi-to-md generate …`) |
+| `md-openapi-api` | `md_generator.openapi.api.run:main` | FastAPI on port **8015** (`OPENAPI_TO_MD_PORT`): `POST /openapi-to-md/generate` (OpenAPI upload → ZIP), `/health`, MCP at **`/mcp`** |
+| `md-openapi-mcp` | `md_generator.openapi.api.mcp_server:main` | Standalone MCP: `api_validate_openapi_yaml`, `api_generate_readme_markdown`, `api_run_sync_zip_base64` |
+| `mdengine` | `md_generator.engine_cli:main` | `mdengine db-to-md …` / `mdengine graph-to-md …` / `mdengine openapi-to-md generate …` |
+
+**openapi-to-md (`md-openapi`):** OpenAPI **3.x** is parsed directly; **Swagger 2.0** (`swagger: "2.0"`) documents are **converted in-process** to OpenAPI 3.0.3 (deterministic, in-repo converter) before `$ref` resolution. Edge-heavy specs (unusual OAuth2 flows, vendor extensions) may still need fixes after conversion.
+
+**db-to-md ER diagrams:** add **`erd`** to the export feature list (YAML `features.include`, API body, or CLI `--include …,erd`). **Preferred:** **Graphviz** (`dot` on `PATH`, or **`GRAPHVIZ_DOT`**) produces `erd/*.dot`, `erd/*.png`, and `erd/*.svg`. **If Graphviz is missing,** the exporter falls back to **Mermaid** (`erDiagram`): it writes `erd/*.mermaid` plus a fenced **`erd/*.md`** for GitHub-style preview. With **`mermaid-py`** (included in `mdengine[db]`), it also requests **PNG/SVG** via mermaid.ink (requires network unless you self-host mermaid.ink and set **`MERMAID_INK_SERVER`** per [mermaid-py](https://pypi.org/project/mermaid-py/)). Tune **`erd.max_tables`** (default 100) and **`erd.scope`** (`full` \| `per_schema` \| `per_table`) under `erd:` in YAML; CLI: `--erd-max-tables`, `--erd-scope`. Async job SSE uses `progress_update` with `current` starting with `erd:`.
+
+**db-to-md split exports and README merge:** with **`output.split_files: true`**, set **`output.write_combined_feature_markdown: true`** to also write root-level combined Markdown (for example `tables.md`, `functions.md`, `indexes.md`, and feature-specific paths such as `oracle/packages.md` or `mongodb/collections.md` when those features run). Set **`output.readme_feature_merge`** to **`inline`** (append full bundle bodies into `README.md`) or **`toc`** (append a linked list to those files). If merge is not **`none`** and split files are on, combined bundle writes are turned on automatically when loading config. CLI: `--write-combined-feature-markdown`, `--readme-feature-merge none|inline|toc`.
+
+**db-to-md SQLite:** set **`database.type: sqlite`** and **`database.uri`** to a SQLAlchemy URL such as **`sqlite:///my.db`** or **`sqlite:////C:/data/my.db`**. The default SQLite catalog is **`main`**; packaged YAML that still has **`schema: public`** is normalized to **`main`** when the type is SQLite. CLI: **`--type sqlite`**. Stored routines, sequences, and partitions are not used by SQLite and stay empty; tables, indexes, views, triggers, and ERD (via FK introspection) follow the same export path as other SQL engines.
+
+**db-to-md API SQLite upload:** **`POST /db-to-md/run/sqlite`** — `multipart/form-data` with field **`file`** (the `.sqlite` / `.db` bytes; must start with the standard `SQLite format 3` header) and optional **`config`** (JSON string with the same shape as a normal run body minus `database`: `schema`, `output`, `features`, `execution`, `limits`, `erd`). Returns the metadata ZIP immediately. **`POST /db-to-md/job/sqlite`** — same form fields; saves the file under the job workspace and runs the existing job pipeline (`GET /db-to-md/job/{id}/download` when complete). Upload size cap: env **`DB_TO_MD_MAX_SQLITE_UPLOAD_MB`** (default **256**). Large ZIPs may still require the async job path if they exceed **`DB_TO_MD_MAX_SYNC_ZIP_MB`** on the sync upload route.
+
+**graph-to-md (Neo4j + NetworkX):** library lives under [`md_generator/graph/`](src/md_generator/graph/). **Sources:** **`networkx`** (GraphML/GML via `graph.graph_file` or `--graph-file`) or **`neo4j`** (`graph.uri`, `graph.user`, `graph.password`, optional `graph.database` for `session(database=…)`). **Output layout:** by default **`output.combine_markdown: true`** writes **`nodes.md`**, **`relationship.md`**, and **`graph_summary.md`** (summary plus embedded nodes and relationships). Set **`combine_markdown: false`** or CLI **`--individual` / `--markdown-layout individual`** for per-entity files under **`nodes/`** and **`relationships/`**. **Diagrams:** **`viz.mermaid: true`** (default) writes **`graph/graph.mmd`** and embeds a fenced Mermaid block in the export **`README.md`** (no Graphviz required). **`viz.enabled: true`** or CLI **`--viz`** also writes **`graph/graph.dot`** and runs **`dot`** for PNG/SVG/PDF when Graphviz is on `PATH` (or **`GRAPHVIZ_DOT`**). CLI **`--no-mermaid`** disables Mermaid; **`--depth`**, **`--start-node`**, **`--max-nodes`**, **`--max-edges`** bound traversal. Packaged defaults: [`src/md_generator/graph/config/default.yaml`](src/md_generator/graph/config/default.yaml). Tests: **`graph-to-md/tests/`**; API image: [`graph-to-md/Dockerfile.api`](graph-to-md/Dockerfile.api).
 
 Every command accepts **`-h` / `--help`** for full flags (artifact layout, OCR, ZIP options, etc.).
 
@@ -282,6 +324,7 @@ md-zip archive.zip ./unzipped-md
 md-url https://example.com/page ./page-bundle --artifact-layout
 md-audio ./voice.mp3 ./voice.md --model tiny
 md-video ./screen.mp4 ./screen.md --model base
+pip install "mdengine[graph]" && md-graph --source neo4j --uri neo4j://localhost:7687 --user neo4j --password secret --database neo4j --output ./graph-out --viz
 ```
 
 **Windows PowerShell** (same commands; use backslashes for paths if you prefer)
@@ -292,6 +335,8 @@ md-zip .\archive.zip .\zip-out
 md-url https://example.com/page .\page-bundle --artifact-layout
 md-audio .\voice.mp3 .\voice.md --model tiny
 md-video .\screen.mp4 .\screen.md --model base
+pip install "mdengine[graph]"
+md-graph --source neo4j --uri neo4j://localhost:7687 --user neo4j --password secret --database neo4j --output .\graph-out --viz
 ```
 
 **Windows CMD**
@@ -575,7 +620,7 @@ Equivalent modules: `python -m md_generator.media.audio.api.mcp_server`, `python
 
 ### Thin shims (repo clone)
 
-[`audio-to-md/converter.py`](audio-to-md/converter.py), [`video-to-md/converter.py`](video-to-md/converter.py), and [`youtube-to-md/converter.py`](youtube-to-md/converter.py) delegate to the same `main` as `md-audio` / `md-video` / `md-youtube`. Tests and `pytest.ini` live under `audio-to-md/tests/`, `video-to-md/tests/`, and `youtube-to-md/tests/`.
+[`audio-to-md/converter.py`](audio-to-md/converter.py), [`video-to-md/converter.py`](video-to-md/converter.py), and [`youtube-to-md/converter.py`](youtube-to-md/converter.py) delegate to the same `main` as `md-audio` / `md-video` / `md-youtube`. Tests and `pytest.ini` live under `audio-to-md/tests/`, `video-to-md/tests/`, and `youtube-to-md/tests/`. [`db-to-md/converter.py`](db-to-md/converter.py) delegates to `md-db`; tests live under `db-to-md/tests/`. **graph-to-md** uses `md-graph` / `mdengine graph-to-md` directly (no thin `converter.py` shim); tests live under [`graph-to-md/tests/`](graph-to-md/tests/). [`openapi-to-md/converter.py`](openapi-to-md/converter.py) delegates to `md-openapi`; tests live under [`openapi-to-md/tests/`](openapi-to-md/tests/); example OpenAPI and output notes: [`openapi-to-md/examples/`](openapi-to-md/examples/).
 
 ---
 
@@ -605,6 +650,9 @@ Install `mdengine[api]` plus the format extra(s), then run the **`app`** object
 | ZIP | `md_generator.archive.api.main:app` | `archive`, `api`, `mcp` (+ extras for nested office/PDF) |
 | URL / HTML | `md_generator.url.api.main:app` | `url`, `api`, `mcp` |
 | Playwright / SPA | `md_generator.playwright.api.main:app` | `playwright`, `api`, `mcp` |
+| Database metadata | `md_generator.db.api.main:app` | `db`, `api`, `mcp` |
+| Graph metadata (Neo4j / NetworkX) | `md_generator.graph.api.main:app` | `graph`, `api`, `mcp` |
+| OpenAPI → Markdown | `md_generator.openapi.api.main:app` | `openapi`, `api`, `mcp` |
 | Audio (Whisper) | `md_generator.media.audio.api.main:create_app` (use **`--factory`**) or `…main:app` | `audio`, `api`, `mcp` |
 | Video (Whisper) | `md_generator.media.video.api.main:create_app` (use **`--factory`**) or `…main:app` | `video`, `api`, `mcp` |
 | YouTube | `md_generator.media.youtube.api.main:create_app` (use **`--factory`**) or `…main:app` | `youtube`, `api`, `mcp` |
@@ -617,11 +665,15 @@ uvicorn md_generator.word.api.main:app --host 127.0.0.1 --port 8002
 uvicorn md_generator.archive.api.main:app --host 127.0.0.1 --port 8010
 uvicorn md_generator.url.api.main:app --host 127.0.0.1 --port 8011
 uvicorn md_generator.playwright.api.main:app --host 127.0.0.1 --port 8014
+uvicorn md_generator.graph.api.main:app --host 127.0.0.1 --port 8012
+uvicorn md_generator.openapi.api.main:app --host 127.0.0.1 --port 8015
 uvicorn md_generator.media.audio.api.main:create_app --factory --host 127.0.0.1 --port 8011
 uvicorn md_generator.media.video.api.main:create_app --factory --host 127.0.0.1 --port 8012
 uvicorn md_generator.media.youtube.api.main:create_app --factory --host 127.0.0.1 --port 8013
 ```
 
+**Port note:** **`md-graph-api`** and **`md-video-api`** both default to **8012**; set **`GRAPH_TO_MD_PORT`** or **`MD_VIDEO_API_PORT`** when you need both on one machine. **`md-openapi-api`** defaults to **8015** (`OPENAPI_TO_MD_PORT`) so it does not collide with **`md-youtube-api`** (**8013**) or **`md-playwright-api`** (**8014**).
+
 ### MCP over HTTP on the same server
 
 These apps mount an MCP HTTP app at **`/mcp`** (Streamable HTTP / framework-specific). Start the API as above, then point an MCP client at `http://<host>:<port>/mcp` where supported.
@@ -640,6 +692,9 @@ Prefixes differ per service (often read from a `.env` file next to the process):
 | XLSX | `XLSX_TO_MD_` | `XLSX_TO_MD_TEMP_DIR`, `XLSX_TO_MD_CORS_ORIGINS`, etc. (see `md_generator.xlsx.api.app`) |
 | URL | `URL_TO_MD_` | `URL_TO_MD_MAX_SYNC_URLS`, `URL_TO_MD_MAX_SYNC_CRAWL_PAGES`, `URL_TO_MD_MAX_JOB_URLS`, `URL_TO_MD_JOB_TTL_SECONDS`, `URL_TO_MD_TEMP_DIR`, `URL_TO_MD_CORS_ORIGINS` |
 | Playwright / SPA | `PLAYWRIGHT_TO_MD_` | `PLAYWRIGHT_TO_MD_MAX_SYNC_URLS`, `PLAYWRIGHT_TO_MD_MAX_JOB_URLS`, `PLAYWRIGHT_TO_MD_JOB_TTL_SECONDS`, `PLAYWRIGHT_TO_MD_TEMP_DIR`, `PLAYWRIGHT_TO_MD_CORS_ORIGINS`, `PLAYWRIGHT_TO_MD_API_HOST`, `PLAYWRIGHT_TO_MD_API_PORT` (default **8014**) |
+| Database metadata | `DB_TO_MD_` | `DB_TO_MD_JOB_SQLITE_PATH`, `DB_TO_MD_JOB_WORKSPACE_ROOT`, `DB_TO_MD_CORS_ORIGINS`, `DB_TO_MD_MAX_SYNC_ZIP_MB`, `DB_TO_MD_HOST`, `DB_TO_MD_PORT` (default **8010**) |
+| Graph metadata | `GRAPH_TO_MD_` | `GRAPH_TO_MD_JOB_SQLITE_PATH`, `GRAPH_TO_MD_JOB_WORKSPACE_ROOT`, `GRAPH_TO_MD_CORS_ORIGINS`, `GRAPH_TO_MD_MAX_SYNC_ZIP_MB`, `GRAPH_TO_MD_HOST`, `GRAPH_TO_MD_PORT` (default **8012**) |
+| OpenAPI → Markdown | `OPENAPI_TO_MD_` | `OPENAPI_TO_MD_CORS_ORIGINS`, `OPENAPI_TO_MD_MAX_SYNC_ZIP_MB`, `OPENAPI_TO_MD_HOST`, `OPENAPI_TO_MD_PORT` (default **8015**) |
 | Audio API | `MD_AUDIO_` | `MD_AUDIO_MAX_UPLOAD_MB`, `MD_AUDIO_MAX_SYNC_UPLOAD_MB`, `MD_AUDIO_JOB_TTL_SECONDS`, `MD_AUDIO_TEMP_DIR`, `MD_AUDIO_CORS_ORIGINS`, `MD_AUDIO_API_HOST`, `MD_AUDIO_API_PORT` |
 | Video API | `MD_VIDEO_` | Same pattern as audio with `MD_VIDEO_*` (defaults: larger upload/sync caps, port **8012**) |
 | YouTube API | `MD_YOUTUBE_` | `MD_YOUTUBE_JOB_TTL_SECONDS`, `MD_YOUTUBE_TEMP_DIR`, `MD_YOUTUBE_CORS_ORIGINS`, `MD_YOUTUBE_API_HOST`, `MD_YOUTUBE_API_PORT` (default **8013**); optional `MD_YOUTUBE_YTDLP` path for audio fallback |
@@ -670,6 +725,9 @@ Two usage patterns:
 | Audio | `md-audio-mcp` or `python -m md_generator.media.audio.api.mcp_server` — `--transport stdio` (default), `sse`, `streamable-http` |
 | Video | `md-video-mcp` or `python -m md_generator.media.video.api.mcp_server` — same transports |
 | YouTube | `md-youtube-mcp` or `python -m md_generator.media.youtube.api.mcp_server` — same transports |
+| Database metadata | `md-db-mcp` or `python -m md_generator.db.api.mcp_server` — `--transport stdio` (default), `sse`, `streamable-http` |
+| Graph (Neo4j / NetworkX) | `md-graph-mcp` or `python -m md_generator.graph.api.mcp_server` — `--transport stdio` (default), `sse`, `streamable-http` |
+| OpenAPI → Markdown | `md-openapi-mcp` or `python -m md_generator.openapi.api.mcp_server` — `--transport stdio` (default), `sse`, `streamable-http` |
 
 **Word** and **XLSX** also ship a small runner script in the repo:
 
@@ -694,7 +752,7 @@ pip install -e ".[dev,all]"   # or a smaller subset of extras
 python -m pytest
 ```
 
-Tests live under each legacy folder’s `tests/` directory (e.g. `pdf-to-md/tests/`); `pyproject.toml` configures `pythonpath = ["src"]` so `md_generator` resolves without a separate `PYTHONPATH`.
+Tests live under each legacy folder’s `tests/` directory (e.g. `pdf-to-md/tests/`), **`graph-to-md/tests/`**, and **`openapi-to-md/tests/`**; `pyproject.toml` configures `pythonpath = ["src"]` so `md_generator` resolves without a separate `PYTHONPATH`.
 
 ---
 
@@ -704,7 +762,7 @@ Tests live under each legacy folder’s `tests/` directory (e.g. `pdf-to-md/test
 |------|------|
 | `LICENSE` | MIT license text |
 | `CODE_OF_CONDUCT.md` | [Contributor Covenant](https://www.contributor-covenant.org/) 2.1 |
-| `src/md_generator/` | **Library source** (all formats + `api` subpackages); **audio/video** under [`media/audio/`](src/md_generator/media/audio/) and [`media/video/`](src/md_generator/media/video/) |
+| `src/md_generator/` | **Library source** (all formats + `api` subpackages); **audio/video** under [`media/audio/`](src/md_generator/media/audio/) and [`media/video/`](src/md_generator/media/video/); **graph-to-md** under [`graph/`](src/md_generator/graph/) |
 | `pyproject.toml` | Packaging, extras, CLI entry points, pytest |
 | `*-to-md/` | **Docs, tests, fixtures**, thin `converter.py` shims, some `run.py` helpers |
 | `README.md` | This document |

{mdengine-0.4.0 → mdengine-0.6.0}/README.md

@@ -1,6 +1,6 @@
 # mdengine
 
-Single Python distribution for converting **PDF**, **Word (.docx)**, **PowerPoint (.pptx)**, **Excel (.xlsx/.xlsm)**, **images** (OCR), **plain text / JSON / XML**, **ZIP archives**, and **audio / video** (Whisper transcription → Markdown) into **Markdown** (and related assets). Install only the extras you need; everything imports under the **`md_generator`** package.
+Single Python distribution for converting **PDF**, **Word (.docx)**, **PowerPoint (.pptx)**, **Excel (.xlsx/.xlsm)**, **images** (OCR), **plain text / JSON / XML**, **ZIP archives**, **audio / video** (Whisper transcription → Markdown), **database metadata** (SQL + Mongo), and **graphs** (Neo4j / NetworkX → Markdown) into **Markdown** (and related assets). Install only the extras you need; everything imports under the **`md_generator`** package.
 
 - **PyPI name:** `mdengine` (import package: `md_generator`)
 - **Source:** [github.com/vishal7090/md-generator](https://github.com/vishal7090/md-generator)
@@ -78,6 +78,7 @@ pip install "mdengine[all]"
 | `video` | **Video → Markdown** (ffmpeg extracts mono 16 kHz WAV, then same Whisper stack as `audio`) |
 | `api` | FastAPI, uvicorn, httpx, pydantic-settings |
 | `mcp` | MCP servers (`mcp`, `fastmcp` where used) |
+| `graph` | **Graph → Markdown** (Neo4j Bolt + NetworkX GraphML/GML): `networkx`, `neo4j`, `pyyaml` |
 | `dev` | pytest + API/MCP test helpers |
 | `all` | Large superset of dependencies (use only if you need everything) |
 
@@ -92,7 +93,7 @@ All converters can be run from a terminal after you install the package (with th
 ### 1. Install (once)
 
 ```bash
-pip install "mdengine[pdf,word]"          # adjust extras: ppt, xlsx, image, archive, text, …
+pip install "mdengine[pdf,word]"          # adjust extras: ppt, xlsx, image, archive, text, db, graph, …
 # or from a clone:
 pip install -e ".[pdf,word,archive]"
 ```
@@ -127,6 +128,28 @@ If the shell reports “command not found”, ensure the Python **Scripts** dire
 | `md-audio-mcp` | `md_generator.media.audio.api.mcp_server:main` | Standalone MCP (`--transport stdio` \| `sse` \| `streamable-http`) |
 | `md-video-mcp` | `md_generator.media.video.api.mcp_server:main` | Same for video |
 | `md-youtube-mcp` | `md_generator.media.youtube.api.mcp_server:main` | Same for YouTube (`youtube_url_to_markdown`) |
+| `md-db` | `md_generator.db.cli.main:main` | `pip install "mdengine[db]"` then `md-db --config db.yaml` (or `mdengine db-to-md …`) |
+| `md-db-api` | `md_generator.db.api.run:main` | FastAPI on port **8010** (`DB_TO_MD_PORT`): `POST /db-to-md/run`, `POST /db-to-md/run/sqlite` (upload + ZIP), `POST /db-to-md/job`, `POST /db-to-md/job/sqlite` (upload + async job), SSE `/db-to-md/job/{id}/events` |
+| `md-db-mcp` | `md_generator.db.api.mcp_server:main` | Standalone MCP for metadata export tools |
+| `md-graph` | `md_generator.graph.cli.main:main` | `pip install "mdengine[graph]"` then `md-graph --source neo4j --uri bolt://…` (or `mdengine graph-to-md …`) |
+| `md-graph-api` | `md_generator.graph.api.run:main` | FastAPI on port **8012** (`GRAPH_TO_MD_PORT`): `POST /graph-to-md/run`, `/graph-to-md/job`, SSE `/graph-to-md/job/{id}/events` |
+| `md-graph-mcp` | `md_generator.graph.api.mcp_server:main` | Standalone MCP for graph export tools |
+| `md-openapi` | `md_generator.openapi.cli.main:main` | `pip install "mdengine[openapi]"` then `md-openapi generate --file openapi.yaml --output ./docs` (or `mdengine openapi-to-md generate …`) |
+| `md-openapi-api` | `md_generator.openapi.api.run:main` | FastAPI on port **8015** (`OPENAPI_TO_MD_PORT`): `POST /openapi-to-md/generate` (OpenAPI upload → ZIP), `/health`, MCP at **`/mcp`** |
+| `md-openapi-mcp` | `md_generator.openapi.api.mcp_server:main` | Standalone MCP: `api_validate_openapi_yaml`, `api_generate_readme_markdown`, `api_run_sync_zip_base64` |
+| `mdengine` | `md_generator.engine_cli:main` | `mdengine db-to-md …` / `mdengine graph-to-md …` / `mdengine openapi-to-md generate …` |
+
+**openapi-to-md (`md-openapi`):** OpenAPI **3.x** is parsed directly; **Swagger 2.0** (`swagger: "2.0"`) documents are **converted in-process** to OpenAPI 3.0.3 (deterministic, in-repo converter) before `$ref` resolution. Edge-heavy specs (unusual OAuth2 flows, vendor extensions) may still need fixes after conversion.
+
+**db-to-md ER diagrams:** add **`erd`** to the export feature list (YAML `features.include`, API body, or CLI `--include …,erd`). **Preferred:** **Graphviz** (`dot` on `PATH`, or **`GRAPHVIZ_DOT`**) produces `erd/*.dot`, `erd/*.png`, and `erd/*.svg`. **If Graphviz is missing,** the exporter falls back to **Mermaid** (`erDiagram`): it writes `erd/*.mermaid` plus a fenced **`erd/*.md`** for GitHub-style preview. With **`mermaid-py`** (included in `mdengine[db]`), it also requests **PNG/SVG** via mermaid.ink (requires network unless you self-host mermaid.ink and set **`MERMAID_INK_SERVER`** per [mermaid-py](https://pypi.org/project/mermaid-py/)). Tune **`erd.max_tables`** (default 100) and **`erd.scope`** (`full` \| `per_schema` \| `per_table`) under `erd:` in YAML; CLI: `--erd-max-tables`, `--erd-scope`. Async job SSE uses `progress_update` with `current` starting with `erd:`.
+
+**db-to-md split exports and README merge:** with **`output.split_files: true`**, set **`output.write_combined_feature_markdown: true`** to also write root-level combined Markdown (for example `tables.md`, `functions.md`, `indexes.md`, and feature-specific paths such as `oracle/packages.md` or `mongodb/collections.md` when those features run). Set **`output.readme_feature_merge`** to **`inline`** (append full bundle bodies into `README.md`) or **`toc`** (append a linked list to those files). If merge is not **`none`** and split files are on, combined bundle writes are turned on automatically when loading config. CLI: `--write-combined-feature-markdown`, `--readme-feature-merge none|inline|toc`.
+
+**db-to-md SQLite:** set **`database.type: sqlite`** and **`database.uri`** to a SQLAlchemy URL such as **`sqlite:///my.db`** or **`sqlite:////C:/data/my.db`**. The default SQLite catalog is **`main`**; packaged YAML that still has **`schema: public`** is normalized to **`main`** when the type is SQLite. CLI: **`--type sqlite`**. Stored routines, sequences, and partitions are not used by SQLite and stay empty; tables, indexes, views, triggers, and ERD (via FK introspection) follow the same export path as other SQL engines.
+
+**db-to-md API SQLite upload:** **`POST /db-to-md/run/sqlite`** — `multipart/form-data` with field **`file`** (the `.sqlite` / `.db` bytes; must start with the standard `SQLite format 3` header) and optional **`config`** (JSON string with the same shape as a normal run body minus `database`: `schema`, `output`, `features`, `execution`, `limits`, `erd`). Returns the metadata ZIP immediately. **`POST /db-to-md/job/sqlite`** — same form fields; saves the file under the job workspace and runs the existing job pipeline (`GET /db-to-md/job/{id}/download` when complete). Upload size cap: env **`DB_TO_MD_MAX_SQLITE_UPLOAD_MB`** (default **256**). Large ZIPs may still require the async job path if they exceed **`DB_TO_MD_MAX_SYNC_ZIP_MB`** on the sync upload route.
+
+**graph-to-md (Neo4j + NetworkX):** library lives under [`md_generator/graph/`](src/md_generator/graph/). **Sources:** **`networkx`** (GraphML/GML via `graph.graph_file` or `--graph-file`) or **`neo4j`** (`graph.uri`, `graph.user`, `graph.password`, optional `graph.database` for `session(database=…)`). **Output layout:** by default **`output.combine_markdown: true`** writes **`nodes.md`**, **`relationship.md`**, and **`graph_summary.md`** (summary plus embedded nodes and relationships). Set **`combine_markdown: false`** or CLI **`--individual` / `--markdown-layout individual`** for per-entity files under **`nodes/`** and **`relationships/`**. **Diagrams:** **`viz.mermaid: true`** (default) writes **`graph/graph.mmd`** and embeds a fenced Mermaid block in the export **`README.md`** (no Graphviz required). **`viz.enabled: true`** or CLI **`--viz`** also writes **`graph/graph.dot`** and runs **`dot`** for PNG/SVG/PDF when Graphviz is on `PATH` (or **`GRAPHVIZ_DOT`**). CLI **`--no-mermaid`** disables Mermaid; **`--depth`**, **`--start-node`**, **`--max-nodes`**, **`--max-edges`** bound traversal. Packaged defaults: [`src/md_generator/graph/config/default.yaml`](src/md_generator/graph/config/default.yaml). Tests: **`graph-to-md/tests/`**; API image: [`graph-to-md/Dockerfile.api`](graph-to-md/Dockerfile.api).
 
 Every command accepts **`-h` / `--help`** for full flags (artifact layout, OCR, ZIP options, etc.).
 
@@ -146,6 +169,7 @@ md-zip archive.zip ./unzipped-md
 md-url https://example.com/page ./page-bundle --artifact-layout
 md-audio ./voice.mp3 ./voice.md --model tiny
 md-video ./screen.mp4 ./screen.md --model base
+pip install "mdengine[graph]" && md-graph --source neo4j --uri neo4j://localhost:7687 --user neo4j --password secret --database neo4j --output ./graph-out --viz
 ```
 
 **Windows PowerShell** (same commands; use backslashes for paths if you prefer)
@@ -156,6 +180,8 @@ md-zip .\archive.zip .\zip-out
 md-url https://example.com/page .\page-bundle --artifact-layout
 md-audio .\voice.mp3 .\voice.md --model tiny
 md-video .\screen.mp4 .\screen.md --model base
+pip install "mdengine[graph]"
+md-graph --source neo4j --uri neo4j://localhost:7687 --user neo4j --password secret --database neo4j --output .\graph-out --viz
 ```
 
 **Windows CMD**
@@ -439,7 +465,7 @@ Equivalent modules: `python -m md_generator.media.audio.api.mcp_server`, `python
 
 ### Thin shims (repo clone)
 
-[`audio-to-md/converter.py`](audio-to-md/converter.py), [`video-to-md/converter.py`](video-to-md/converter.py), and [`youtube-to-md/converter.py`](youtube-to-md/converter.py) delegate to the same `main` as `md-audio` / `md-video` / `md-youtube`. Tests and `pytest.ini` live under `audio-to-md/tests/`, `video-to-md/tests/`, and `youtube-to-md/tests/`.
+[`audio-to-md/converter.py`](audio-to-md/converter.py), [`video-to-md/converter.py`](video-to-md/converter.py), and [`youtube-to-md/converter.py`](youtube-to-md/converter.py) delegate to the same `main` as `md-audio` / `md-video` / `md-youtube`. Tests and `pytest.ini` live under `audio-to-md/tests/`, `video-to-md/tests/`, and `youtube-to-md/tests/`. [`db-to-md/converter.py`](db-to-md/converter.py) delegates to `md-db`; tests live under `db-to-md/tests/`. **graph-to-md** uses `md-graph` / `mdengine graph-to-md` directly (no thin `converter.py` shim); tests live under [`graph-to-md/tests/`](graph-to-md/tests/). [`openapi-to-md/converter.py`](openapi-to-md/converter.py) delegates to `md-openapi`; tests live under [`openapi-to-md/tests/`](openapi-to-md/tests/); example OpenAPI and output notes: [`openapi-to-md/examples/`](openapi-to-md/examples/).
 
 ---
 
@@ -469,6 +495,9 @@ Install `mdengine[api]` plus the format extra(s), then run the **`app`** object
 | ZIP | `md_generator.archive.api.main:app` | `archive`, `api`, `mcp` (+ extras for nested office/PDF) |
 | URL / HTML | `md_generator.url.api.main:app` | `url`, `api`, `mcp` |
 | Playwright / SPA | `md_generator.playwright.api.main:app` | `playwright`, `api`, `mcp` |
+| Database metadata | `md_generator.db.api.main:app` | `db`, `api`, `mcp` |
+| Graph metadata (Neo4j / NetworkX) | `md_generator.graph.api.main:app` | `graph`, `api`, `mcp` |
+| OpenAPI → Markdown | `md_generator.openapi.api.main:app` | `openapi`, `api`, `mcp` |
 | Audio (Whisper) | `md_generator.media.audio.api.main:create_app` (use **`--factory`**) or `…main:app` | `audio`, `api`, `mcp` |
 | Video (Whisper) | `md_generator.media.video.api.main:create_app` (use **`--factory`**) or `…main:app` | `video`, `api`, `mcp` |
 | YouTube | `md_generator.media.youtube.api.main:create_app` (use **`--factory`**) or `…main:app` | `youtube`, `api`, `mcp` |
@@ -481,11 +510,15 @@ uvicorn md_generator.word.api.main:app --host 127.0.0.1 --port 8002
 uvicorn md_generator.archive.api.main:app --host 127.0.0.1 --port 8010
 uvicorn md_generator.url.api.main:app --host 127.0.0.1 --port 8011
 uvicorn md_generator.playwright.api.main:app --host 127.0.0.1 --port 8014
+uvicorn md_generator.graph.api.main:app --host 127.0.0.1 --port 8012
+uvicorn md_generator.openapi.api.main:app --host 127.0.0.1 --port 8015
 uvicorn md_generator.media.audio.api.main:create_app --factory --host 127.0.0.1 --port 8011
 uvicorn md_generator.media.video.api.main:create_app --factory --host 127.0.0.1 --port 8012
 uvicorn md_generator.media.youtube.api.main:create_app --factory --host 127.0.0.1 --port 8013
 ```
 
+**Port note:** **`md-graph-api`** and **`md-video-api`** both default to **8012**; set **`GRAPH_TO_MD_PORT`** or **`MD_VIDEO_API_PORT`** when you need both on one machine. **`md-openapi-api`** defaults to **8015** (`OPENAPI_TO_MD_PORT`) so it does not collide with **`md-youtube-api`** (**8013**) or **`md-playwright-api`** (**8014**).
+
 ### MCP over HTTP on the same server
 
 These apps mount an MCP HTTP app at **`/mcp`** (Streamable HTTP / framework-specific). Start the API as above, then point an MCP client at `http://<host>:<port>/mcp` where supported.
@@ -504,6 +537,9 @@ Prefixes differ per service (often read from a `.env` file next to the process):
 | XLSX | `XLSX_TO_MD_` | `XLSX_TO_MD_TEMP_DIR`, `XLSX_TO_MD_CORS_ORIGINS`, etc. (see `md_generator.xlsx.api.app`) |
 | URL | `URL_TO_MD_` | `URL_TO_MD_MAX_SYNC_URLS`, `URL_TO_MD_MAX_SYNC_CRAWL_PAGES`, `URL_TO_MD_MAX_JOB_URLS`, `URL_TO_MD_JOB_TTL_SECONDS`, `URL_TO_MD_TEMP_DIR`, `URL_TO_MD_CORS_ORIGINS` |
 | Playwright / SPA | `PLAYWRIGHT_TO_MD_` | `PLAYWRIGHT_TO_MD_MAX_SYNC_URLS`, `PLAYWRIGHT_TO_MD_MAX_JOB_URLS`, `PLAYWRIGHT_TO_MD_JOB_TTL_SECONDS`, `PLAYWRIGHT_TO_MD_TEMP_DIR`, `PLAYWRIGHT_TO_MD_CORS_ORIGINS`, `PLAYWRIGHT_TO_MD_API_HOST`, `PLAYWRIGHT_TO_MD_API_PORT` (default **8014**) |
+| Database metadata | `DB_TO_MD_` | `DB_TO_MD_JOB_SQLITE_PATH`, `DB_TO_MD_JOB_WORKSPACE_ROOT`, `DB_TO_MD_CORS_ORIGINS`, `DB_TO_MD_MAX_SYNC_ZIP_MB`, `DB_TO_MD_HOST`, `DB_TO_MD_PORT` (default **8010**) |
+| Graph metadata | `GRAPH_TO_MD_` | `GRAPH_TO_MD_JOB_SQLITE_PATH`, `GRAPH_TO_MD_JOB_WORKSPACE_ROOT`, `GRAPH_TO_MD_CORS_ORIGINS`, `GRAPH_TO_MD_MAX_SYNC_ZIP_MB`, `GRAPH_TO_MD_HOST`, `GRAPH_TO_MD_PORT` (default **8012**) |
+| OpenAPI → Markdown | `OPENAPI_TO_MD_` | `OPENAPI_TO_MD_CORS_ORIGINS`, `OPENAPI_TO_MD_MAX_SYNC_ZIP_MB`, `OPENAPI_TO_MD_HOST`, `OPENAPI_TO_MD_PORT` (default **8015**) |
 | Audio API | `MD_AUDIO_` | `MD_AUDIO_MAX_UPLOAD_MB`, `MD_AUDIO_MAX_SYNC_UPLOAD_MB`, `MD_AUDIO_JOB_TTL_SECONDS`, `MD_AUDIO_TEMP_DIR`, `MD_AUDIO_CORS_ORIGINS`, `MD_AUDIO_API_HOST`, `MD_AUDIO_API_PORT` |
 | Video API | `MD_VIDEO_` | Same pattern as audio with `MD_VIDEO_*` (defaults: larger upload/sync caps, port **8012**) |
 | YouTube API | `MD_YOUTUBE_` | `MD_YOUTUBE_JOB_TTL_SECONDS`, `MD_YOUTUBE_TEMP_DIR`, `MD_YOUTUBE_CORS_ORIGINS`, `MD_YOUTUBE_API_HOST`, `MD_YOUTUBE_API_PORT` (default **8013**); optional `MD_YOUTUBE_YTDLP` path for audio fallback |
@@ -534,6 +570,9 @@ Two usage patterns:
 | Audio | `md-audio-mcp` or `python -m md_generator.media.audio.api.mcp_server` — `--transport stdio` (default), `sse`, `streamable-http` |
 | Video | `md-video-mcp` or `python -m md_generator.media.video.api.mcp_server` — same transports |
 | YouTube | `md-youtube-mcp` or `python -m md_generator.media.youtube.api.mcp_server` — same transports |
+| Database metadata | `md-db-mcp` or `python -m md_generator.db.api.mcp_server` — `--transport stdio` (default), `sse`, `streamable-http` |
+| Graph (Neo4j / NetworkX) | `md-graph-mcp` or `python -m md_generator.graph.api.mcp_server` — `--transport stdio` (default), `sse`, `streamable-http` |
+| OpenAPI → Markdown | `md-openapi-mcp` or `python -m md_generator.openapi.api.mcp_server` — `--transport stdio` (default), `sse`, `streamable-http` |
 
 **Word** and **XLSX** also ship a small runner script in the repo:
 
@@ -558,7 +597,7 @@ pip install -e ".[dev,all]"   # or a smaller subset of extras
 python -m pytest
 ```
 
-Tests live under each legacy folder’s `tests/` directory (e.g. `pdf-to-md/tests/`); `pyproject.toml` configures `pythonpath = ["src"]` so `md_generator` resolves without a separate `PYTHONPATH`.
+Tests live under each legacy folder’s `tests/` directory (e.g. `pdf-to-md/tests/`), **`graph-to-md/tests/`**, and **`openapi-to-md/tests/`**; `pyproject.toml` configures `pythonpath = ["src"]` so `md_generator` resolves without a separate `PYTHONPATH`.
 
 ---
 
@@ -568,7 +607,7 @@ Tests live under each legacy folder’s `tests/` directory (e.g. `pdf-to-md/test
 |------|------|
 | `LICENSE` | MIT license text |
 | `CODE_OF_CONDUCT.md` | [Contributor Covenant](https://www.contributor-covenant.org/) 2.1 |
-| `src/md_generator/` | **Library source** (all formats + `api` subpackages); **audio/video** under [`media/audio/`](src/md_generator/media/audio/) and [`media/video/`](src/md_generator/media/video/) |
+| `src/md_generator/` | **Library source** (all formats + `api` subpackages); **audio/video** under [`media/audio/`](src/md_generator/media/audio/) and [`media/video/`](src/md_generator/media/video/); **graph-to-md** under [`graph/`](src/md_generator/graph/) |
 | `pyproject.toml` | Packaging, extras, CLI entry points, pytest |
 | `*-to-md/` | **Docs, tests, fixtures**, thin `converter.py` shims, some `run.py` helpers |
 | `README.md` | This document |

{mdengine-0.4.0 → mdengine-0.6.0}/pyproject.toml

@@ -4,14 +4,14 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "mdengine"
-version = "0.4.0"
-description = "Convert PDF, Office, images, audio, video, text/JSON/XML, ZIP archives, and web URLs to Markdown."
+version = "0.6.0"
+description = "Convert PDF, Office, images, audio, video, text/JSON/XML, ZIP archives, web URLs, databases, graphs, and OpenAPI specs to Markdown."
 readme = "README.md"
 requires-python = ">=3.10"
 license = "MIT"
 license-files = ["LICENSE"]
 authors = [{ name = "mdengine contributors" }]
-keywords = ["markdown", "pdf", "docx", "pptx", "xlsx", "ocr", "zip", "url", "html", "youtube", "playwright"]
+keywords = ["markdown", "pdf", "docx", "pptx", "xlsx", "ocr", "zip", "url", "html", "youtube", "playwright", "database", "openapi"]
 classifiers = [
   "Programming Language :: Python :: 3",
   "Programming Language :: Python :: 3 :: Only",
@@ -92,6 +92,25 @@ playwright = [
   "readability-lxml>=0.8.1",
   "Pillow>=10.0.0",
 ]
+db = [
+  "sqlalchemy>=2.0.0",
+  "pyyaml>=6.0.0",
+  "psycopg2-binary>=2.9.9",
+  "pymysql>=1.1.0",
+  "oracledb>=2.0.0",
+  "pymongo>=4.6.0",
+  "mermaid-py>=0.8.0",
+]
+graph = [
+  "networkx>=3.2.0",
+  "neo4j>=5.14.0",
+  "pyyaml>=6.0.0",
+]
+openapi = [
+  "pyyaml>=6.0.0",
+  "prance>=23.6.0",
+  "openapi-spec-validator>=0.7.0",
+]
 api = [
   "fastapi>=0.115.0",
   "uvicorn[standard]>=0.32.0",
@@ -110,6 +129,9 @@ dev = [
   "mdengine[mcp]",
   "mdengine[url]",
   "mdengine[playwright]",
+  "mdengine[db]",
+  "mdengine[graph]",
+  "mdengine[openapi]",
 ]
 all = [
   "pymupdf>=1.24.0",
@@ -165,10 +187,25 @@ md-youtube-mcp = "md_generator.media.youtube.api.mcp_server:main"
 md-playwright = "md_generator.playwright.cli:main"
 md-playwright-api = "md_generator.playwright.api.run:main"
 md-playwright-mcp = "md_generator.playwright.api.mcp_server:main"
+md-db = "md_generator.db.cli.main:main"
+md-db-api = "md_generator.db.api.run:main"
+md-db-mcp = "md_generator.db.api.mcp_server:main"
+md-graph = "md_generator.graph.cli.main:main"
+md-graph-api = "md_generator.graph.api.run:main"
+md-graph-mcp = "md_generator.graph.api.mcp_server:main"
+md-openapi = "md_generator.openapi.cli.main:main"
+md-openapi-api = "md_generator.openapi.api.run:main"
+md-openapi-mcp = "md_generator.openapi.api.mcp_server:main"
+mdengine = "md_generator.engine_cli:main"
 
 [tool.setuptools.packages.find]
 where = ["src"]
 
+[tool.setuptools.package-data]
+"md_generator.db.config" = ["*.yaml"]
+"md_generator.graph.config" = ["*.yaml"]
+"md_generator.openapi.config" = ["*.yaml"]
+
 [tool.pytest.ini_options]
 pythonpath = ["src"]
 testpaths = [
@@ -184,5 +221,8 @@ testpaths = [
   "video-to-md/tests",
   "youtube-to-md/tests",
   "playwright-to-md/tests",
+  "db-to-md/tests",
+  "graph-to-md/tests",
+  "openapi-to-md/tests",
 ]
 markers = ["integration: optional dependency or slower checks"]

{mdengine-0.4.0 → mdengine-0.6.0}/src/md_generator/__init__.py

@@ -1,5 +1,5 @@
 """md_generator: PDF, Office, image, text, and ZIP to Markdown conversion."""
 
-__version__ = "0.4.0"
+__version__ = "0.6.0"
 
 __all__ = ["__version__"]

mdengine-0.6.0/src/md_generator/db/__init__.py

@@ -0,0 +1,5 @@
+"""Database metadata to Markdown (LLM-ready, deterministic)."""
+
+from md_generator.db.core.models import RunMetadata
+
+__all__ = ["RunMetadata"]

mdengine-0.6.0/src/md_generator/db/adapters/__init__.py

@@ -0,0 +1,3 @@
+from md_generator.db.adapters.factory import create_adapter
+
+__all__ = ["create_adapter"]

mdengine-0.6.0/src/md_generator/db/adapters/factory.py

@@ -0,0 +1,46 @@
+from __future__ import annotations
+
+from typing import Any
+
+from sqlalchemy.engine.url import make_url
+
+from md_generator.db.adapters.mongo_adapter import MongoAdapter
+from md_generator.db.adapters.mysql_adapter import MysqlAdapter
+from md_generator.db.adapters.oracle_adapter import OracleAdapter
+from md_generator.db.adapters.postgres_adapter import PostgresAdapter
+from md_generator.db.adapters.sqlite_adapter import SqliteAdapter
+from md_generator.db.core.base_adapter import BaseAdapter
+
+
+def create_adapter(
+    db_type: str,
+    uri: str,
+    *,
+    schema: str | None = None,
+    database: str | None = None,
+    limits: dict[str, Any] | None = None,
+) -> BaseAdapter:
+    lim = dict(limits or {})
+    t = db_type.lower().strip()
+    if t in ("postgres", "postgresql"):
+        sch = schema or "public"
+        return PostgresAdapter(uri, sch, lim)
+    if t in ("mysql", "mariadb"):
+        sch = schema or make_url(uri).database
+        if not sch:
+            raise ValueError("MySQL requires database in URI path or --schema")
+        return MysqlAdapter(uri, sch, lim)
+    if t in ("oracle",):
+        if not schema:
+            raise ValueError("Oracle requires schema (owner) in config or --schema")
+        return OracleAdapter(uri, schema, lim)
+    if t in ("mongo", "mongodb"):
+        if not database:
+            raise ValueError("MongoDB requires database name in config or --database")
+        return MongoAdapter(uri, database, lim)
+    if t in ("sqlite",):
+        sch = (schema or "main").strip()
+        if sch.lower() == "public":
+            sch = "main"
+        return SqliteAdapter(uri, sch, lim)
+    raise ValueError(f"Unsupported database type: {db_type!r}")