feather-structured-output 0.1.1__tar.gz

feather_structured_output-0.1.1/.gitignore

@@ -0,0 +1,221 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#   Usually these files are written by a python script from a template
+#   before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py.cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+# Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+# uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+# poetry.lock
+# poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+# pdm.lock
+# pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+# pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# Redis
+*.rdb
+*.aof
+*.pid
+
+# RabbitMQ
+mnesia/
+rabbitmq/
+rabbitmq-data/
+
+# ActiveMQ
+activemq-data/
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#   JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#   be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#   and can be added to the global gitignore or merged into this file.  For a more nuclear
+#   option (not recommended) you can uncomment the following to ignore the entire idea folder.
+# .idea/
+
+# Abstra
+#   Abstra is an AI-powered process automation framework.
+#   Ignore directories containing user credentials, local state, and settings.
+#   Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#   Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#   that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#   and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#   you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+# Temporary file for partial code execution
+tempCodeRunnerFile.py
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Local task runner configuration with publishing tokens
+mise.toml
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+# Streamlit
+.streamlit/secrets.toml

feather_structured_output-0.1.1/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 第一無重工
+
+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.

feather_structured_output-0.1.1/PKG-INFO

@@ -0,0 +1,219 @@
+Metadata-Version: 2.4
+Name: feather-structured-output
+Version: 0.1.1
+Summary: Add your description here
+License-File: LICENSE
+Requires-Python: >=3.13
+Description-Content-Type: text/markdown
+
+# feather-structured-output
+
+`feather-structured-output` is a lightweight Python library for turning LLM text
+responses into validated Python dictionaries.
+
+It does not call an LLM, retry requests, or manage conversation history. It only
+handles schema definition, short JSON prompt generation, JSON extraction, field
+validation, normalization, and retry-friendly error messages.
+
+## Installation
+
+This repository uses `uv`.
+
+```powershell
+uv run pytest
+```
+
+## Basic Usage
+
+```python
+from feather_structured_output import IntField, Schema, StringField
+
+schema = Schema(
+    instruction="Extract the following JSON.",
+    fields=[
+        StringField(
+            source_label="Company name",
+            output_name="name",
+            description="Use the formal company name.",
+            example="Acme Corp",
+        ),
+        IntField(
+            source_label="Quantity",
+            output_name="quantity",
+            gt=0,
+        ),
+    ],
+)
+
+prompt = schema.dump_prompt()
+```
+
+`prompt` becomes a compact JSON example with comments:
+
+```text
+Extract the following JSON.
+
+{
+  "name": "Acme Corp", // Company name。String. Use the formal company name. Required.
+  "quantity": 1 // Quantity。Integer. Greater than 0. Required.
+}
+```
+
+Pass that prompt to any LLM client yourself, then validate the response:
+
+```python
+result = schema.extract('{"name": "Acme Corp", "quantity": 3}')
+
+if result.ok:
+    data = result.data
+else:
+    retry_prompt = result.error_message
+```
+
+## Fields
+
+Available field types:
+
+- `StringField`
+- `IntField`
+- `FloatField`
+- `BooleanField`
+- `ObjectField`
+- `UnionField`
+
+Common field options:
+
+- `source_label`: label from the source document or UI; optional
+- `output_name`: JSON key; if omitted, `source_label` is used
+- `description`: extra instruction for the LLM
+- `example`: sample value in the generated prompt
+- `allowed_values`: fixed allowed values for the field
+- `presence`: missing value policy
+- `repeatable`, `min_items`, `max_items`: array support
+
+At least one of `output_name` or `source_label` is required when a field is used
+in a `Schema`.
+
+## Presence Policy
+
+```python
+from feather_structured_output import PresencePolicy, StringField
+
+StringField(
+    output_name="note",
+    presence=PresencePolicy.NULLABLE,
+)
+```
+
+Policies:
+
+- `REQUIRED`: value is required
+- `OMITTABLE`: missing value is omitted from normalized data
+- `NULLABLE`: missing value is normalized to `None`
+- `BLANKABLE`: missing value is normalized to `""`
+
+`""` is treated as a missing value during validation.
+
+## Arrays and Objects
+
+```python
+from feather_structured_output import IntField, ObjectField, StringField
+
+items = ObjectField(
+    output_name="items",
+    repeatable=True,
+    min_items=1,
+    fields=[
+        StringField(output_name="name"),
+        IntField(output_name="quantity", gt=0),
+    ],
+)
+```
+
+## Fixed Values and Unions
+
+Use `allowed_values` for fixed values. Use `UnionField` when a value may match
+more than one field shape.
+
+```python
+from feather_structured_output import IntField, StringField, UnionField
+
+dog_age = UnionField(
+    output_name="dog_age",
+    variants=[
+        StringField(allowed_values=["N/A"]),
+        StringField(allowed_values=["-"]),
+        IntField(gt=0),
+    ],
+)
+```
+
+## JSON Extraction
+
+`Schema.extract()` accepts raw JSON or a single fenced `json` code block. Text
+outside one JSON code block is ignored.
+
+````python
+result = schema.extract(
+    """Here is the result:
+```json
+{"name": "Acme Corp", "quantity": 3}
+```"""
+)
+````
+
+Multiple JSON code blocks, non-JSON code blocks, invalid JSON, and non-object
+JSON values return `ExtractResult` with validation errors.
+
+## Custom Validators
+
+Use validators for cross-field rules.
+
+```python
+from feather_structured_output import IntField, Schema, StringField, ValidationError
+
+
+def validate_octopus_legs(data: dict[str, object]) -> list[ValidationError]:
+    if data.get("pet") == "octopus" and data.get("legs") != 8:
+        return [
+            ValidationError(
+                path="legs",
+                message={
+                    "en": "legs must be 8 when pet is octopus.",
+                    "ja": "pet が octopus の場合、legs は 8 である必要があります。",
+                },
+                actual=data.get("legs"),
+            )
+        ]
+    return []
+
+
+schema = Schema(
+    fields=[
+        StringField(output_name="pet"),
+        IntField(output_name="legs", ge=0),
+    ],
+    validators=[validate_octopus_legs],
+)
+```
+
+Validators run only after field validation succeeds. Exceptions raised inside a
+validator are not converted to LLM-facing validation errors.
+
+## Error Messages and Locale
+
+English is the default. Japanese retry messages are available with
+`locale="ja"`.
+
+```python
+schema = Schema(
+    locale="ja",
+    fields=[IntField(output_name="quantity", gt=0)],
+)
+
+result = schema.extract('{"quantity": 0}')
+print(result.error_message)
+```
+
+Internal message templates are split by locale under
+`src/feather_structured_output/locales/`.

feather_structured_output-0.1.1/README.md

@@ -0,0 +1,211 @@
+# feather-structured-output
+
+`feather-structured-output` is a lightweight Python library for turning LLM text
+responses into validated Python dictionaries.
+
+It does not call an LLM, retry requests, or manage conversation history. It only
+handles schema definition, short JSON prompt generation, JSON extraction, field
+validation, normalization, and retry-friendly error messages.
+
+## Installation
+
+This repository uses `uv`.
+
+```powershell
+uv run pytest
+```
+
+## Basic Usage
+
+```python
+from feather_structured_output import IntField, Schema, StringField
+
+schema = Schema(
+    instruction="Extract the following JSON.",
+    fields=[
+        StringField(
+            source_label="Company name",
+            output_name="name",
+            description="Use the formal company name.",
+            example="Acme Corp",
+        ),
+        IntField(
+            source_label="Quantity",
+            output_name="quantity",
+            gt=0,
+        ),
+    ],
+)
+
+prompt = schema.dump_prompt()
+```
+
+`prompt` becomes a compact JSON example with comments:
+
+```text
+Extract the following JSON.
+
+{
+  "name": "Acme Corp", // Company name。String. Use the formal company name. Required.
+  "quantity": 1 // Quantity。Integer. Greater than 0. Required.
+}
+```
+
+Pass that prompt to any LLM client yourself, then validate the response:
+
+```python
+result = schema.extract('{"name": "Acme Corp", "quantity": 3}')
+
+if result.ok:
+    data = result.data
+else:
+    retry_prompt = result.error_message
+```
+
+## Fields
+
+Available field types:
+
+- `StringField`
+- `IntField`
+- `FloatField`
+- `BooleanField`
+- `ObjectField`
+- `UnionField`
+
+Common field options:
+
+- `source_label`: label from the source document or UI; optional
+- `output_name`: JSON key; if omitted, `source_label` is used
+- `description`: extra instruction for the LLM
+- `example`: sample value in the generated prompt
+- `allowed_values`: fixed allowed values for the field
+- `presence`: missing value policy
+- `repeatable`, `min_items`, `max_items`: array support
+
+At least one of `output_name` or `source_label` is required when a field is used
+in a `Schema`.
+
+## Presence Policy
+
+```python
+from feather_structured_output import PresencePolicy, StringField
+
+StringField(
+    output_name="note",
+    presence=PresencePolicy.NULLABLE,
+)
+```
+
+Policies:
+
+- `REQUIRED`: value is required
+- `OMITTABLE`: missing value is omitted from normalized data
+- `NULLABLE`: missing value is normalized to `None`
+- `BLANKABLE`: missing value is normalized to `""`
+
+`""` is treated as a missing value during validation.
+
+## Arrays and Objects
+
+```python
+from feather_structured_output import IntField, ObjectField, StringField
+
+items = ObjectField(
+    output_name="items",
+    repeatable=True,
+    min_items=1,
+    fields=[
+        StringField(output_name="name"),
+        IntField(output_name="quantity", gt=0),
+    ],
+)
+```
+
+## Fixed Values and Unions
+
+Use `allowed_values` for fixed values. Use `UnionField` when a value may match
+more than one field shape.
+
+```python
+from feather_structured_output import IntField, StringField, UnionField
+
+dog_age = UnionField(
+    output_name="dog_age",
+    variants=[
+        StringField(allowed_values=["N/A"]),
+        StringField(allowed_values=["-"]),
+        IntField(gt=0),
+    ],
+)
+```
+
+## JSON Extraction
+
+`Schema.extract()` accepts raw JSON or a single fenced `json` code block. Text
+outside one JSON code block is ignored.
+
+````python
+result = schema.extract(
+    """Here is the result:
+```json
+{"name": "Acme Corp", "quantity": 3}
+```"""
+)
+````
+
+Multiple JSON code blocks, non-JSON code blocks, invalid JSON, and non-object
+JSON values return `ExtractResult` with validation errors.
+
+## Custom Validators
+
+Use validators for cross-field rules.
+
+```python
+from feather_structured_output import IntField, Schema, StringField, ValidationError
+
+
+def validate_octopus_legs(data: dict[str, object]) -> list[ValidationError]:
+    if data.get("pet") == "octopus" and data.get("legs") != 8:
+        return [
+            ValidationError(
+                path="legs",
+                message={
+                    "en": "legs must be 8 when pet is octopus.",
+                    "ja": "pet が octopus の場合、legs は 8 である必要があります。",
+                },
+                actual=data.get("legs"),
+            )
+        ]
+    return []
+
+
+schema = Schema(
+    fields=[
+        StringField(output_name="pet"),
+        IntField(output_name="legs", ge=0),
+    ],
+    validators=[validate_octopus_legs],
+)
+```
+
+Validators run only after field validation succeeds. Exceptions raised inside a
+validator are not converted to LLM-facing validation errors.
+
+## Error Messages and Locale
+
+English is the default. Japanese retry messages are available with
+`locale="ja"`.
+
+```python
+schema = Schema(
+    locale="ja",
+    fields=[IntField(output_name="quantity", gt=0)],
+)
+
+result = schema.extract('{"quantity": 0}')
+print(result.error_message)
+```
+
+Internal message templates are split by locale under
+`src/feather_structured_output/locales/`.

feather_structured_output-0.1.1/pyproject.toml

@@ -0,0 +1,39 @@
+[project]
+name = "feather-structured-output"
+dynamic = ["version"]
+description = "Add your description here"
+readme = "README.md"
+requires-python = ">=3.13"
+dependencies = []
+
+[dependency-groups]
+dev = [
+    "pytest>=8.3",
+]
+integration = [
+    "pydantic>=2",
+    "pymupdf>=1.24",
+    "strands-agents[openai]>=1.0",
+]
+
+[build-system]
+requires = ["hatchling", "hatch-vcs"]
+build-backend = "hatchling.build"
+
+[tool.hatch.version]
+source = "vcs"
+fallback-version = "0.0.0"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/feather_structured_output"]
+
+[tool.hatch.build.targets.sdist]
+include = [
+    "/src",
+]
+
+[tool.pytest.ini_options]
+pythonpath = ["src"]
+markers = [
+    "integration: tests that require external services such as LM Studio",
+]