jmd-format 0.4__tar.gz

jmd_format-0.4/LICENSE

@@ -0,0 +1,28 @@
+MIT License
+
+Copyright (c) 2026 Andreas Ostermeyer <andreas@ostermeyer.de>
+
+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.
+
+---
+
+This license applies to the benchmark code only (the `benchmark/` and
+`benchmark_results/` directories). It does not grant any rights to the JMD
+format specification, which is licensed separately under CC BY-NC-SA 4.0.
+See LICENSE for details.

jmd_format-0.4/PKG-INFO

@@ -0,0 +1,166 @@
+Metadata-Version: 2.4
+Name: jmd-format
+Version: 0.4
+Summary: JMD (JSON Markdown) — structured data format for LLM-driven infrastructure
+Author-email: Andreas Ostermeyer <andreas@ostermeyer.de>
+License: MIT License
+        
+        Copyright (c) 2026 Andreas Ostermeyer <andreas@ostermeyer.de>
+        
+        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.
+        
+        ---
+        
+        This license applies to the benchmark code only (the `benchmark/` and
+        `benchmark_results/` directories). It does not grant any rights to the JMD
+        format specification, which is licensed separately under CC BY-NC-SA 4.0.
+        See LICENSE for details.
+        
+Project-URL: Homepage, https://github.com/ostermeyer/jmd-spec
+Project-URL: Repository, https://github.com/ostermeyer/jmd-impl
+Keywords: jmd,llm,structured-data,json,markdown,mcp
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: License :: Other/Proprietary License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Topic :: Text Processing :: Markup
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: lxml>=5.0
+Dynamic: license-file
+
+# jmd-format — Python Reference Implementation
+
+Python reference implementation of the [JMD specification](https://github.com/ostermeyer/jmd-spec) (v0.4). Includes a C-accelerated parser and serializer, plus lossless XML↔JMD conversion.
+
+## Installation
+
+Install the latest version directly from GitHub:
+
+```bash
+pip install git+https://github.com/ostermeyer/jmd-impl.git
+```
+
+Or pin a specific release:
+
+```bash
+pip install git+https://github.com/ostermeyer/jmd-impl.git@v0.4
+```
+
+Pre-built wheels for Linux, macOS, and Windows are attached to each
+[GitHub Release](https://github.com/ostermeyer/jmd-impl/releases) and can be
+installed directly:
+
+```bash
+pip install https://github.com/ostermeyer/jmd-impl/releases/download/v0.4/jmd_format-0.3-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
+```
+
+The C extensions are built automatically during installation if a C compiler is available. If not, the pure-Python fallback is used transparently.
+
+## Quick Start
+
+```python
+from jmd import parse, serialize
+
+data = parse("""
+# Order
+id: 42
+status: pending
+
+## customer
+name: Anna Müller
+email: anna@example.com
+""")
+
+print(data)
+# {'id': 42, 'status': 'pending', 'customer': {'name': 'Anna Müller', 'email': 'anna@example.com'}}
+
+print(serialize(data, label="Order"))
+```
+
+## Document Modes
+
+```python
+from jmd import jmd_mode, JMDQueryParser, JMDSchemaParser, JMDDeleteParser, parse_error
+
+# Detect mode without full parse
+mode = jmd_mode(source)   # 'data' | 'query' | 'schema' | 'delete'
+
+# Query by Example (#?)
+query = JMDQueryParser().parse("#? Order\nstatus: pending")
+
+# Schema (#!)
+schema = JMDSchemaParser().parse("#! Order\nid: integer readonly\nstatus: string")
+
+# Delete (#-)
+delete = JMDDeleteParser().parse("#- Order\nid: 42")
+
+# Error (# Error)
+error = parse_error("# Error\nstatus: 404\ncode: not_found\nmessage: Not found")
+```
+
+## Streaming
+
+```python
+from jmd import jmd_stream
+
+for event in jmd_stream(source):
+    print(event)
+```
+
+## XML Mapping
+
+Lossless conversion between data XML and JMD (requires `lxml`):
+
+```python
+from jmd.xml import xml_to_jmd, jmd_to_xml
+
+jmd_source = xml_to_jmd(xml_bytes_or_str)  # XML → JMD string
+xml_output  = jmd_to_xml(jmd_source)        # JMD → XML bytes
+```
+
+Targets data XML — OOXML (WordprocessingML, DrawingML, SpreadsheetML),
+SOAP, XBRL, XRechnung, and similar formats. Mixed-content XML (ODF, XHTML)
+is out of scope.
+
+See the [JMD over XML companion specification](https://github.com/ostermeyer/jmd-spec/blob/main/jmd-over-xml.md) for the full mapping rules.
+
+## C Extensions
+
+Build manually if needed:
+
+```bash
+python build_ext.py build_ext --inplace
+```
+
+## Specification
+
+See [jmd-spec](https://github.com/ostermeyer/jmd-spec) for the full format specification, benchmark results, and design documentation.
+
+## License
+
+Licensed under the MIT License. See [LICENSE](LICENSE).
+
+The JMD format specification is licensed separately under CC BY-NC-SA 4.0.

jmd_format-0.4/README.md

@@ -0,0 +1,113 @@
+# jmd-format — Python Reference Implementation
+
+Python reference implementation of the [JMD specification](https://github.com/ostermeyer/jmd-spec) (v0.4). Includes a C-accelerated parser and serializer, plus lossless XML↔JMD conversion.
+
+## Installation
+
+Install the latest version directly from GitHub:
+
+```bash
+pip install git+https://github.com/ostermeyer/jmd-impl.git
+```
+
+Or pin a specific release:
+
+```bash
+pip install git+https://github.com/ostermeyer/jmd-impl.git@v0.4
+```
+
+Pre-built wheels for Linux, macOS, and Windows are attached to each
+[GitHub Release](https://github.com/ostermeyer/jmd-impl/releases) and can be
+installed directly:
+
+```bash
+pip install https://github.com/ostermeyer/jmd-impl/releases/download/v0.4/jmd_format-0.3-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
+```
+
+The C extensions are built automatically during installation if a C compiler is available. If not, the pure-Python fallback is used transparently.
+
+## Quick Start
+
+```python
+from jmd import parse, serialize
+
+data = parse("""
+# Order
+id: 42
+status: pending
+
+## customer
+name: Anna Müller
+email: anna@example.com
+""")
+
+print(data)
+# {'id': 42, 'status': 'pending', 'customer': {'name': 'Anna Müller', 'email': 'anna@example.com'}}
+
+print(serialize(data, label="Order"))
+```
+
+## Document Modes
+
+```python
+from jmd import jmd_mode, JMDQueryParser, JMDSchemaParser, JMDDeleteParser, parse_error
+
+# Detect mode without full parse
+mode = jmd_mode(source)   # 'data' | 'query' | 'schema' | 'delete'
+
+# Query by Example (#?)
+query = JMDQueryParser().parse("#? Order\nstatus: pending")
+
+# Schema (#!)
+schema = JMDSchemaParser().parse("#! Order\nid: integer readonly\nstatus: string")
+
+# Delete (#-)
+delete = JMDDeleteParser().parse("#- Order\nid: 42")
+
+# Error (# Error)
+error = parse_error("# Error\nstatus: 404\ncode: not_found\nmessage: Not found")
+```
+
+## Streaming
+
+```python
+from jmd import jmd_stream
+
+for event in jmd_stream(source):
+    print(event)
+```
+
+## XML Mapping
+
+Lossless conversion between data XML and JMD (requires `lxml`):
+
+```python
+from jmd.xml import xml_to_jmd, jmd_to_xml
+
+jmd_source = xml_to_jmd(xml_bytes_or_str)  # XML → JMD string
+xml_output  = jmd_to_xml(jmd_source)        # JMD → XML bytes
+```
+
+Targets data XML — OOXML (WordprocessingML, DrawingML, SpreadsheetML),
+SOAP, XBRL, XRechnung, and similar formats. Mixed-content XML (ODF, XHTML)
+is out of scope.
+
+See the [JMD over XML companion specification](https://github.com/ostermeyer/jmd-spec/blob/main/jmd-over-xml.md) for the full mapping rules.
+
+## C Extensions
+
+Build manually if needed:
+
+```bash
+python build_ext.py build_ext --inplace
+```
+
+## Specification
+
+See [jmd-spec](https://github.com/ostermeyer/jmd-spec) for the full format specification, benchmark results, and design documentation.
+
+## License
+
+Licensed under the MIT License. See [LICENSE](LICENSE).
+
+The JMD format specification is licensed separately under CC BY-NC-SA 4.0.

jmd_format-0.4/jmd/__init__.py

@@ -0,0 +1,213 @@
+"""JMD (JSON Markdown) — Parser, Serializer, and Tooling.
+
+Implements JMD Specification v0.3 — heading-scope model with blockquotes
+and indentation continuation.
+
+Usage:
+    python -m jmd                          # demo + roundtrip test
+    python -m jmd to-json input.jmd        # pretty-print JSON
+    python -m jmd from-json input.json     # convert JSON to JMD
+    python -m jmd render input.jmd         # render HTML to stdout
+    python -m jmd roundtrip input.jmd      # JMD -> JSON -> JMD, assert lossless
+
+    As a library:
+        from jmd import parse, serialize
+        data = parse(text)
+        jmd  = serialize(data, label="Order")
+"""
+
+from __future__ import annotations
+
+from typing import Any
+
+from ._cli import (
+    SAMPLE_JMD,
+    SAMPLE_QUERY,
+    SAMPLE_RECORDS,
+    SAMPLE_SCHEMA,
+    dict_to_jmd,
+    jmd_parse_schema,
+    jmd_query,
+    jmd_schema_to_json_schema,
+    jmd_to_dict,
+    jmd_to_json,
+    json_schema_to_jmd_schema,
+    json_to_jmd,
+)
+from ._delete import JMDDelete, JMDDeleteParser
+from ._error import JMDError, JMDErrorItem, is_error_document, parse_error
+from ._html import JMDHTMLRenderer
+from ._parser import JMDParser
+from ._query import (
+    Condition,
+    JMDQuery,
+    JMDQueryExecutor,
+    JMDQueryParser,
+    QueryArray,
+    QueryField,
+    QueryObject,
+)
+from ._scalars import parse_key, parse_scalar, quote_key, serialize_scalar
+from ._schema import (
+    JMDSchema,
+    JMDSchemaParser,
+    SchemaArray,
+    SchemaField,
+    SchemaObject,
+    SchemaRef,
+)
+from ._serializer import JMDSerializer
+from ._streaming import StreamEvent, jmd_stream
+from ._tokenizer import Line, tokenize
+
+# ---------------------------------------------------------------------------
+# C extension detection — done once at import time, not on every call
+# ---------------------------------------------------------------------------
+
+try:
+    from ._cparser import parse as _c_parse
+    _HAS_CPARSER: bool = True
+except ImportError:
+    _HAS_CPARSER = False
+
+try:
+    from ._cserializer import serialize as _c_serialize
+    _HAS_CSERIALIZER: bool = True
+except ImportError:
+    _HAS_CSERIALIZER = False
+
+
+# ---------------------------------------------------------------------------
+# Public API — C-accelerated by default, Python fallback
+# ---------------------------------------------------------------------------
+
+def parse(source: str) -> Any:
+    """Parse a JMD document into a Python value.
+
+    Uses the C-accelerated parser if available; falls back to the pure-Python
+    :class:`JMDParser` otherwise.
+
+    Args:
+        source: Complete JMD document text.
+
+    Returns:
+        A Python ``dict``, ``list``, or scalar value.
+    """
+    if _HAS_CPARSER:
+        return _c_parse(source)
+    return JMDParser().parse(source)
+
+
+def serialize(data: Any, label: str = "Document") -> str:
+    """Serialize a Python value to a JMD document string.
+
+    Uses the C-accelerated serializer if available; falls back to the
+    pure-Python :class:`JMDSerializer` otherwise.
+
+    Args:
+        data:  Python ``dict``, ``list``, or scalar value.
+        label: Root heading label.
+
+    Returns:
+        A JMD document string.
+    """
+    if _HAS_CSERIALIZER:
+        return str(_c_serialize(data, label))
+    return JMDSerializer().serialize(data, label=label)
+
+
+# ---------------------------------------------------------------------------
+# Document mode detection
+# ---------------------------------------------------------------------------
+
+_MODE_PREFIXES = {
+    "? ": "query",
+    "! ": "schema",
+    "- ": "delete",
+}
+
+
+def jmd_mode(source: str) -> str:
+    """Detect the document mode of a JMD source string.
+
+    Inspects only the first non-blank heading line; does not parse the full
+    document.
+
+    Args:
+        source: JMD document text.
+
+    Returns:
+        One of ``'data'``, ``'query'``, ``'schema'``, or ``'delete'``.
+        Returns ``'data'`` for ``# Error`` documents (error documents are
+        standard data documents with a reserved label).
+    """
+    lines = tokenize(source)
+    for line in lines:
+        if line.heading_depth == 1:
+            for prefix, mode in _MODE_PREFIXES.items():
+                if line.content.startswith(prefix):
+                    return mode
+            return "data"
+    return "data"
+
+
+__all__ = [
+    # Tokenizer
+    "Line",
+    "tokenize",
+    # Scalars
+    "parse_scalar",
+    "parse_key",
+    "serialize_scalar",
+    "quote_key",
+    # Parser & Serializer (Python classes)
+    "JMDParser",
+    "JMDSerializer",
+    # Top-level API (C-accelerated by default)
+    "parse",
+    "serialize",
+    # Mode detection
+    "jmd_mode",
+    # HTML
+    "JMDHTMLRenderer",
+    # Streaming
+    "StreamEvent",
+    "jmd_stream",
+    # QBE
+    "Condition",
+    "QueryField",
+    "QueryObject",
+    "QueryArray",
+    "JMDQuery",
+    "JMDQueryParser",
+    "JMDQueryExecutor",
+    # Schema
+    "SchemaField",
+    "SchemaObject",
+    "SchemaArray",
+    "SchemaRef",
+    "JMDSchema",
+    "JMDSchemaParser",
+    # Delete
+    "JMDDelete",
+    "JMDDeleteParser",
+    # Error
+    "JMDError",
+    "JMDErrorItem",
+    "is_error_document",
+    "parse_error",
+    # Convenience functions
+    "jmd_to_json",
+    "json_to_jmd",
+    "jmd_to_dict",
+    "dict_to_jmd",
+    "jmd_query",
+    "jmd_parse_schema",
+    "jmd_schema_to_json_schema",
+    "json_schema_to_jmd_schema",
+    # Sample data
+    "SAMPLE_JMD",
+    "SAMPLE_QUERY",
+    "SAMPLE_SCHEMA",
+    "SAMPLE_RECORDS",
+]

jmd_format-0.4/jmd/__main__.py

@@ -0,0 +1,6 @@
+"""Allow running JMD as ``python -m jmd``."""
+
+from ._cli import main
+
+if __name__ == "__main__":
+    main()