arcade-google-docs 2.0.0rc1__tar.gz

arcade_google_docs-2.0.0rc1/.gitignore

@@ -0,0 +1,175 @@
+.DS_Store
+credentials.yaml
+docker/credentials.yaml
+
+*.lock
+
+# example data
+examples/data
+scratch
+
+
+docs/source
+
+# From https://raw.githubusercontent.com/github/gitignore/main/Python.gitignore
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$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
+
+# 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
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.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/

arcade_google_docs-2.0.0rc1/.pre-commit-config.yaml

@@ -0,0 +1,18 @@
+files: ^.*/google_docs/.*
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: "v4.4.0"
+    hooks:
+      - id: check-case-conflict
+      - id: check-merge-conflict
+      - id: check-toml
+      - id: check-yaml
+      - id: end-of-file-fixer
+      - id: trailing-whitespace
+
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.6.7
+    hooks:
+      - id: ruff
+        args: [--fix]
+      - id: ruff-format

arcade_google_docs-2.0.0rc1/.ruff.toml

@@ -0,0 +1,46 @@
+target-version = "py310"
+line-length = 100
+fix = true
+
+[lint]
+select = [
+    # flake8-2020
+    "YTT",
+    # flake8-bandit
+    "S",
+    # flake8-bugbear
+    "B",
+    # flake8-builtins
+    "A",
+    # flake8-comprehensions
+    "C4",
+    # flake8-debugger
+    "T10",
+    # flake8-simplify
+    "SIM",
+    # isort
+    "I",
+    # mccabe
+    "C90",
+    # pycodestyle
+    "E", "W",
+    # pyflakes
+    "F",
+    # pygrep-hooks
+    "PGH",
+    # pyupgrade
+    "UP",
+    # ruff
+    "RUF",
+    # tryceratops
+    "TRY",
+]
+
+[lint.per-file-ignores]
+"*" = ["TRY003", "B904"]
+"**/tests/*" = ["S101", "E501"]
+"**/evals/*" = ["S101", "E501"]
+
+[format]
+preview = true
+skip-magic-trailing-comma = false

arcade_google_docs-2.0.0rc1/Makefile

@@ -0,0 +1,55 @@
+.PHONY: help
+
+help:
+	@echo "🛠️ github Commands:\n"
+	@grep -E '^[a-zA-Z_-]+:.*?## .*$$' $(MAKEFILE_LIST) | sort | awk 'BEGIN {FS = ":.*?## "}; {printf "\033[36m%-30s\033[0m %s\n", $$1, $$2}'
+
+.PHONY: install
+install: ## Install the uv environment and install all packages with dependencies
+	@echo "🚀 Creating virtual environment and installing all packages using uv"
+	@uv sync --active --all-extras --no-sources
+	@if [ -f .pre-commit-config.yaml ]; then uv run --no-sources pre-commit install; fi
+	@echo "✅ All packages and dependencies installed via uv"
+
+.PHONY: install-local
+install-local: ## Install the uv environment and install all packages with dependencies with local Arcade sources
+	@echo "🚀 Creating virtual environment and installing all packages using uv"
+	@uv sync --active --all-extras
+	@if [ -f .pre-commit-config.yaml ]; then uv run pre-commit install; fi
+	@echo "✅ All packages and dependencies installed via uv"
+
+.PHONY: build
+build: clean-build ## Build wheel file using poetry
+	@echo "🚀 Creating wheel file"
+	uv build
+
+.PHONY: clean-build
+clean-build: ## clean build artifacts
+	@echo "🗑️ Cleaning dist directory"
+	rm -rf dist
+
+.PHONY: test
+test: ## Test the code with pytest
+	@echo "🚀 Testing code: Running pytest"
+	@uv run --no-sources pytest -W ignore -v --cov --cov-config=pyproject.toml --cov-report=xml
+
+.PHONY: coverage
+coverage: ## Generate coverage report
+	@echo "coverage report"
+	@uv run --no-sources coverage report
+	@echo "Generating coverage report"
+	@uv run --no-sources coverage html
+
+.PHONY: bump-version
+bump-version: ## Bump the version in the pyproject.toml file by a patch version
+	@echo "🚀 Bumping version in pyproject.toml"
+	uv version --no-sources --bump patch
+
+.PHONY: check
+check: ## Run code quality tools.
+	@if [ -f .pre-commit-config.yaml ]; then\
+		echo "🚀 Linting code: Running pre-commit";\
+		uv run --no-sources pre-commit run -a;\
+	fi
+	@echo "🚀 Static type checking: Running mypy"
+	@uv run --no-sources mypy --config-file=pyproject.toml

arcade_google_docs-2.0.0rc1/PKG-INFO

@@ -0,0 +1,23 @@
+Metadata-Version: 2.4
+Name: arcade_google_docs
+Version: 2.0.0rc1
+Summary: Arcade.dev LLM tools for Google Docs
+Author-email: Arcade <dev@arcade.dev>
+Requires-Python: >=3.10
+Requires-Dist: arcade-tdk<3.0.0,>=2.0.0
+Requires-Dist: google-api-core<3.0.0,>=2.19.1
+Requires-Dist: google-api-python-client<3.0.0,>=2.137.0
+Requires-Dist: google-auth-httplib2<1.0.0,>=0.2.0
+Requires-Dist: google-auth<3.0.0,>=2.32.0
+Requires-Dist: googleapis-common-protos<2.0.0,>=1.63.2
+Provides-Extra: dev
+Requires-Dist: arcade-ai[evals]<3.0.0,>=2.0.4; extra == 'dev'
+Requires-Dist: arcade-serve<3.0.0,>=2.0.0; extra == 'dev'
+Requires-Dist: mypy<1.6.0,>=1.5.1; extra == 'dev'
+Requires-Dist: pre-commit<3.5.0,>=3.4.0; extra == 'dev'
+Requires-Dist: pytest-asyncio<0.25.0,>=0.24.0; extra == 'dev'
+Requires-Dist: pytest-cov<4.1.0,>=4.0.0; extra == 'dev'
+Requires-Dist: pytest-mock<3.12.0,>=3.11.1; extra == 'dev'
+Requires-Dist: pytest<8.4.0,>=8.3.0; extra == 'dev'
+Requires-Dist: ruff<0.8.0,>=0.7.4; extra == 'dev'
+Requires-Dist: tox<4.12.0,>=4.11.1; extra == 'dev'

arcade_google_docs-2.0.0rc1/arcade_google_docs/__init__.py

@@ -0,0 +1,17 @@
+from arcade_google_docs.tools import (
+    create_blank_document,
+    create_document_from_text,
+    get_document_by_id,
+    insert_text_at_end_of_document,
+    search_and_retrieve_documents,
+    search_documents,
+)
+
+__all__ = [
+    "create_blank_document",
+    "create_document_from_text",
+    "get_document_by_id",
+    "insert_text_at_end_of_document",
+    "search_and_retrieve_documents",
+    "search_documents",
+]

arcade_google_docs-2.0.0rc1/arcade_google_docs/decorators.py

@@ -0,0 +1,24 @@
+import functools
+from collections.abc import Callable
+from typing import Any
+
+from arcade_tdk import ToolContext
+from googleapiclient.errors import HttpError
+
+from arcade_google_docs.file_picker import generate_google_file_picker_url
+
+
+def with_filepicker_fallback(func: Callable[..., Any]) -> Callable[..., Any]:
+    """ """
+
+    @functools.wraps(func)
+    async def async_wrapper(context: ToolContext, *args: Any, **kwargs: Any) -> Any:
+        try:
+            return await func(context, *args, **kwargs)
+        except HttpError as e:
+            if e.status_code in [403, 404]:
+                file_picker_response = generate_google_file_picker_url(context)
+                return file_picker_response
+            raise
+
+    return async_wrapper

arcade_google_docs-2.0.0rc1/arcade_google_docs/doc_to_html.py

@@ -0,0 +1,99 @@
+def convert_document_to_html(document: dict) -> str:
+    html = (
+        "<html><head>"
+        f"<title>{document['title']}</title>"
+        f'<meta name="documentId" content="{document["documentId"]}">'
+        "</head><body>"
+    )
+    for element in document["body"]["content"]:
+        html += convert_structural_element(element)
+    html += "</body></html>"
+    return html
+
+
+def convert_structural_element(element: dict, wrap_paragraphs: bool = True) -> str:
+    if "sectionBreak" in element or "tableOfContents" in element:
+        return ""
+
+    elif "paragraph" in element:
+        paragraph_content = ""
+
+        prepend, append = get_paragraph_style_tags(
+            style=element["paragraph"]["paragraphStyle"],
+            wrap_paragraphs=wrap_paragraphs,
+        )
+
+        for item in element["paragraph"]["elements"]:
+            if "textRun" not in item:
+                continue
+            paragraph_content += extract_paragraph_content(item["textRun"])
+
+        if not paragraph_content:
+            return ""
+
+        return f"{prepend}{paragraph_content.strip()}{append}"
+
+    elif "table" in element:
+        table = [
+            [
+                "".join([
+                    convert_structural_element(element=cell_element, wrap_paragraphs=False)
+                    for cell_element in cell["content"]
+                ])
+                for cell in row["tableCells"]
+            ]
+            for row in element["table"]["tableRows"]
+        ]
+        return table_list_to_html(table)
+
+    else:
+        raise ValueError(f"Unknown document body element type: {element}")
+
+
+def extract_paragraph_content(text_run: dict) -> str:
+    content = text_run["content"]
+    style = text_run["textStyle"]
+    return apply_text_style(content, style)
+
+
+def apply_text_style(content: str, style: dict) -> str:
+    content = content.rstrip("\n")
+    content = content.replace("\n", "<br>")
+    italic = style.get("italic", False)
+    bold = style.get("bold", False)
+    if italic:
+        content = f"<i>{content}</i>"
+    if bold:
+        content = f"<b>{content}</b>"
+    return content
+
+
+def get_paragraph_style_tags(style: dict, wrap_paragraphs: bool = True) -> tuple[str, str]:
+    named_style = style["namedStyleType"]
+    if named_style == "NORMAL_TEXT":
+        return ("<p>", "</p>") if wrap_paragraphs else ("", "")
+    elif named_style == "TITLE":
+        return "<h1>", "</h1>"
+    elif named_style == "SUBTITLE":
+        return "<h2>", "</h2>"
+    elif named_style.startswith("HEADING_"):
+        try:
+            heading_level = int(named_style.split("_")[1])
+        except ValueError:
+            return ("<p>", "</p>") if wrap_paragraphs else ("", "")
+        else:
+            return f"<h{heading_level}>", f"</h{heading_level}>"
+    return ("<p>", "</p>") if wrap_paragraphs else ("", "")
+
+
+def table_list_to_html(table: list[list[str]]) -> str:
+    html = "<table>"
+    for row in table:
+        html += "<tr>"
+        for cell in row:
+            if cell.endswith("<br>"):
+                cell = cell[:-4]
+            html += f"<td>{cell}</td>"
+        html += "</tr>"
+    html += "</table>"
+    return html

arcade_google_docs-2.0.0rc1/arcade_google_docs/doc_to_markdown.py

@@ -0,0 +1,64 @@
+import arcade_google_docs.doc_to_html as doc_to_html
+
+
+def convert_document_to_markdown(document: dict) -> str:
+    md = f"---\ntitle: {document['title']}\ndocumentId: {document['documentId']}\n---\n"
+    for element in document["body"]["content"]:
+        md += convert_structural_element(element)
+    return md
+
+
+def convert_structural_element(element: dict) -> str:
+    if "sectionBreak" in element or "tableOfContents" in element:
+        return ""
+
+    elif "paragraph" in element:
+        md = ""
+        prepend = get_paragraph_style_prepend_str(element["paragraph"]["paragraphStyle"])
+        for item in element["paragraph"]["elements"]:
+            if "textRun" not in item:
+                continue
+            content = extract_paragraph_content(item["textRun"])
+            md += f"{prepend}{content}"
+        return md
+
+    elif "table" in element:
+        return doc_to_html.convert_structural_element(element)
+
+    else:
+        raise ValueError(f"Unknown document body element type: {element}")
+
+
+def extract_paragraph_content(text_run: dict) -> str:
+    content = text_run["content"]
+    style = text_run["textStyle"]
+    return apply_text_style(content, style)
+
+
+def apply_text_style(content: str, style: dict) -> str:
+    append = "\n" if content.endswith("\n") else ""
+    content = content.rstrip("\n")
+    italic = style.get("italic", False)
+    bold = style.get("bold", False)
+    if italic:
+        content = f"_{content}_"
+    if bold:
+        content = f"**{content}**"
+    return f"{content}{append}"
+
+
+def get_paragraph_style_prepend_str(style: dict) -> str:
+    named_style = style["namedStyleType"]
+    if named_style == "NORMAL_TEXT":
+        return ""
+    elif named_style == "TITLE":
+        return "# "
+    elif named_style == "SUBTITLE":
+        return "## "
+    elif named_style.startswith("HEADING_"):
+        try:
+            heading_level = int(named_style.split("_")[1])
+            return f"{'#' * heading_level} "
+        except ValueError:
+            return ""
+    return ""

arcade_google_docs-2.0.0rc1/arcade_google_docs/enum.py

@@ -0,0 +1,116 @@
+from enum import Enum
+
+
+class Corpora(str, Enum):
+    """
+    Bodies of items (files/documents) to which the query applies.
+    Prefer 'user' or 'drive' to 'allDrives' for efficiency.
+    By default, corpora is set to 'user'.
+    """
+
+    USER = "user"
+    DOMAIN = "domain"
+    DRIVE = "drive"
+    ALL_DRIVES = "allDrives"
+
+
+class DocumentFormat(str, Enum):
+    MARKDOWN = "markdown"
+    HTML = "html"
+    GOOGLE_API_JSON = "google_api_json"
+
+
+class OrderBy(str, Enum):
+    """
+    Sort keys for ordering files in Google Drive.
+    Each key has both ascending and descending options.
+    """
+
+    CREATED_TIME = (
+        # When the file was created (ascending)
+        "createdTime"
+    )
+    CREATED_TIME_DESC = (
+        # When the file was created (descending)
+        "createdTime desc"
+    )
+    FOLDER = (
+        # The folder ID, sorted using alphabetical ordering (ascending)
+        "folder"
+    )
+    FOLDER_DESC = (
+        # The folder ID, sorted using alphabetical ordering (descending)
+        "folder desc"
+    )
+    MODIFIED_BY_ME_TIME = (
+        # The last time the file was modified by the user (ascending)
+        "modifiedByMeTime"
+    )
+    MODIFIED_BY_ME_TIME_DESC = (
+        # The last time the file was modified by the user (descending)
+        "modifiedByMeTime desc"
+    )
+    MODIFIED_TIME = (
+        # The last time the file was modified by anyone (ascending)
+        "modifiedTime"
+    )
+    MODIFIED_TIME_DESC = (
+        # The last time the file was modified by anyone (descending)
+        "modifiedTime desc"
+    )
+    NAME = (
+        # The name of the file, sorted using alphabetical ordering (e.g., 1, 12, 2, 22) (ascending)
+        "name"
+    )
+    NAME_DESC = (
+        # The name of the file, sorted using alphabetical ordering (e.g., 1, 12, 2, 22) (descending)
+        "name desc"
+    )
+    NAME_NATURAL = (
+        # The name of the file, sorted using natural sort ordering (e.g., 1, 2, 12, 22) (ascending)
+        "name_natural"
+    )
+    NAME_NATURAL_DESC = (
+        # The name of the file, sorted using natural sort ordering (e.g., 1, 2, 12, 22) (descending)
+        "name_natural desc"
+    )
+    QUOTA_BYTES_USED = (
+        # The number of storage quota bytes used by the file (ascending)
+        "quotaBytesUsed"
+    )
+    QUOTA_BYTES_USED_DESC = (
+        # The number of storage quota bytes used by the file (descending)
+        "quotaBytesUsed desc"
+    )
+    RECENCY = (
+        # The most recent timestamp from the file's date-time fields (ascending)
+        "recency"
+    )
+    RECENCY_DESC = (
+        # The most recent timestamp from the file's date-time fields (descending)
+        "recency desc"
+    )
+    SHARED_WITH_ME_TIME = (
+        # When the file was shared with the user, if applicable (ascending)
+        "sharedWithMeTime"
+    )
+    SHARED_WITH_ME_TIME_DESC = (
+        # When the file was shared with the user, if applicable (descending)
+        "sharedWithMeTime desc"
+    )
+    STARRED = (
+        # Whether the user has starred the file (ascending)
+        "starred"
+    )
+    STARRED_DESC = (
+        # Whether the user has starred the file (descending)
+        "starred desc"
+    )
+    VIEWED_BY_ME_TIME = (
+        # The last time the file was viewed by the user (ascending)
+        "viewedByMeTime"
+    )
+    VIEWED_BY_ME_TIME_DESC = (
+        # The last time the file was viewed by the user (descending)
+        "viewedByMeTime desc"
+    )

arcade_google_docs-2.0.0rc1/arcade_google_docs/file_picker.py

@@ -0,0 +1,49 @@
+import base64
+import json
+
+from arcade_tdk import ToolContext, ToolMetadataKey
+from arcade_tdk.errors import ToolExecutionError
+
+
+def generate_google_file_picker_url(context: ToolContext) -> dict:
+    """Generate a Google File Picker URL for user-driven file selection and authorization.
+
+    Generates a URL that directs the end-user to a Google File Picker interface where
+    where they can select or upload Google Drive files. Users can grant permission to access their
+    Drive files, providing a secure and authorized way to interact with their files.
+
+    This is particularly useful when prior tools (e.g., those accessing or modifying
+    Google Docs, Google Sheets, etc.) encountered failures due to file non-existence
+    (Requested entity was not found) or permission errors. Once the user completes the file
+    picker flow, the prior tool can be retried.
+
+    Returns:
+        A dictionary containing the URL and instructions for the llm to instruct the user.
+    """
+    client_id = context.get_metadata(ToolMetadataKey.CLIENT_ID)
+    client_id_parts = client_id.split("-")
+    if not client_id_parts:
+        raise ToolExecutionError(
+            message="Invalid Google Client ID",
+            developer_message=f"Google Client ID '{client_id}' is not valid",
+        )
+    app_id = client_id_parts[0]
+    cloud_coordinator_url = context.get_metadata(ToolMetadataKey.COORDINATOR_URL).strip("/")
+
+    config = {
+        "auth": {
+            "client_id": client_id,
+            "app_id": app_id,
+        },
+    }
+    config_json = json.dumps(config)
+    config_base64 = base64.urlsafe_b64encode(config_json.encode("utf-8")).decode("utf-8")
+    url = f"{cloud_coordinator_url}/google/drive_picker?config={config_base64}"
+
+    return {
+        "url": url,
+        "llm_instructions": (
+            "Instruct the user to click the following link to open the Google Drive File Picker. "
+            f"This will allow them to select files and grant access permissions: {url}"
+        ),
+    }