worai 1.0.0__tar.gz

worai-1.0.0/PKG-INFO

@@ -0,0 +1,120 @@
+Metadata-Version: 2.4
+Name: worai
+Version: 1.0.0
+Summary: Add your description here
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+Requires-Dist: google-auth>=2.35.0
+Requires-Dist: google-auth-oauthlib>=1.2.1
+Requires-Dist: playwright>=1.48.0
+Requires-Dist: rdflib>=7.5.0
+Requires-Dist: requests>=2.32.5
+Requires-Dist: tqdm>=4.67.1
+Requires-Dist: typer>=0.12.5
+Requires-Dist: wordlift-client>=1.133.0
+Provides-Extra: dev
+Requires-Dist: pytest>=8.3.4; extra == "dev"
+
+This folder contains WORAi CLI utilities.
+
+Install
+- Local: `pipx install .`
+- From git: `pipx install git+<repo_url>`
+- Curl installer: `curl -fsSL <install.sh_url> | bash -s -- <repo_url>`
+
+Usage
+- `worai --help`
+- `worai seocheck <sitemap_url_or_path>`
+- `worai google-search-console --site sc-domain:example.com --client-secrets /path/to/client_secrets.json`
+
+Configuration
+- Config file (TOML) discovery order: `--config`, `WORAI_CONFIG`, `./worai.toml`, `~/.config/worai/config.toml`, `~/.worai.toml`.
+- Profiles: `[profile.<name>]` with `--profile` or `WORAI_PROFILE`.
+- Common keys:
+  - `wordlift.api_key`
+  - `gsc.client_secrets`
+  - `gsc.token`
+
+seocheck
+The `seocheck` command runs SEO checks against URLs found in a sitemap. It supports remote sitemap URLs and local sitemap files.
+
+Usage
+- `worai seocheck <sitemap_url_or_path>`
+
+Options
+- `sitemap_url`: URL or local file path to a sitemap XML (or sitemap index). Supports `.gz` files and `file://` URLs.
+- `--max-urls`: Limit the number of URLs checked. Default: no limit.
+- `--timeout`: Timeout in seconds for HTTP requests (sitemaps, robots.txt, llms.txt). Default: 20.0.
+- `--page-timeout`: Timeout in milliseconds for browser page loads. Default: 30000.
+- `--wait-until`: Playwright wait strategy for page load. Choices: `domcontentloaded`, `load`, `networkidle`. Default: `domcontentloaded`.
+- `--ttfb-ok-ms`: TTFB ok threshold in ms. Default: 200.
+- `--ttfb-warn-ms`: TTFB warn threshold in ms. Default: 500.
+- `--headed`: Run the browser with a visible UI instead of headless mode.
+- `--format`: Output format. Choices: `text`, `json`. Default: `text`.
+- `--output-dir`: Write report outputs to this directory (report.json, summary.txt, per-page JSONs, report UI).
+- `--output`: Write a comprehensive JSON report to this file path.
+- `--output-summary`: Write a human-readable summary report to this file path.
+- `--save-html`: Save rendered HTML for each page to the output directory.
+- `--checks`: Comma-separated list of page check names to run (others disabled).
+- `--disable-checks`: Comma-separated list of page check names to skip.
+- `--concurrency`: Number of pages to process concurrently, or `auto`. Default: 1.
+
+Notes
+- The page checks are modular. Add a new check under `worai/seocheck/checks` and register it in `worai/seocheck/checks/__init__.py`.
+- The browser is Playwright (Chromium) to ensure JavaScript rendering.
+- When using `--output-dir`, open `index.html` from that directory to view the report UI (or serve it with a web server).
+
+Examples
+- `worai seocheck https://example.com/sitemap.xml`
+- `worai seocheck ./sitemap.xml`
+- `worai seocheck /path/to/sitemap.xml.gz`
+- `worai seocheck https://example.com/sitemap.xml --wait-until networkidle`
+- `worai seocheck https://example.com/sitemap.xml --max-urls 25 --format json`
+- `worai seocheck https://example.com/sitemap.xml --output ./report.json --output-summary ./report.txt`
+- `worai seocheck https://example.com/sitemap.xml --output-dir ./seocheck-report --save-html`
+- `worai seocheck https://example.com/sitemap.xml --checks status,page_meta,canonical`
+
+Command Examples
+- `worai google-search-console --site sc-domain:example.com --client-secrets ./client_secrets.json`
+- `worai dedupe --dry-run`
+- `worai canonicalize-duplicate-pages --input gsc_pages.csv --output canonical_targets.csv --kpi-window 28d --kpi-metric clicks`
+- `worai delete-entities-from-csv ./entities.csv --batch-size 20`
+- `worai find-faq-page-wrong-type ./data.ttl`
+- `worai find-faq-page-wrong-type ./data.ttl --dry-run --replace-type`
+- `worai find-faq-page-wrong-type ./data.ttl --patch --replace-type`
+- `worai find-missing-names ./data.ttl`
+- `worai find-url-by-type ./data.ttl schema:Service schema:Product`
+- `worai link-groups ./links.csv --format turtle`
+- `worai link-groups ./links.csv --apply --dry-run --concurrency 4`
+- `worai patch ./data.ttl --dry-run --add-types`
+- `worai patch ./data.jsonld --types-only --workers 4`
+- `worai upload-entities-from-turtle ./entities --recursive --limit 50`
+
+Client secrets format
+The `--client-secrets` file is the OAuth2 client configuration downloaded from Google Cloud Console.
+It looks like:
+
+{
+  "installed": {
+    "client_id": "YOUR_CLIENT_ID.apps.googleusercontent.com",
+    "project_id": "your-project-id",
+    "auth_uri": "https://accounts.google.com/o/oauth2/auth",
+    "token_uri": "https://oauth2.googleapis.com/token",
+    "auth_provider_x509_cert_url": "https://www.googleapis.com/oauth2/v1/certs",
+    "client_secret": "YOUR_CLIENT_SECRET",
+    "redirect_uris": [
+      "http://localhost"
+    ]
+  }
+}
+
+Setup steps
+1. Google Cloud Console -> APIs & Services -> OAuth consent screen:
+   - Configure a consent screen (External or Internal) and add yourself as a test user if required.
+2. APIs & Services -> Credentials -> Create Credentials -> OAuth client ID:
+   - Application type: Desktop app.
+3. Download the JSON and pass its path to `--client-secrets`.
+4. Run the command:
+   - `worai google-search-console --site sc-domain:example.com --client-secrets /path/to/client_secrets.json`
+   - If your OAuth client requires a fixed redirect URI (e.g. Web app), add `--port 8080` and register `http://localhost:8080`.
+5. The first run opens a browser for consent and writes a token file (default `gsc_token.json`).

worai-1.0.0/README.md

@@ -0,0 +1,103 @@
+This folder contains WORAi CLI utilities.
+
+Install
+- Local: `pipx install .`
+- From git: `pipx install git+<repo_url>`
+- Curl installer: `curl -fsSL <install.sh_url> | bash -s -- <repo_url>`
+
+Usage
+- `worai --help`
+- `worai seocheck <sitemap_url_or_path>`
+- `worai google-search-console --site sc-domain:example.com --client-secrets /path/to/client_secrets.json`
+
+Configuration
+- Config file (TOML) discovery order: `--config`, `WORAI_CONFIG`, `./worai.toml`, `~/.config/worai/config.toml`, `~/.worai.toml`.
+- Profiles: `[profile.<name>]` with `--profile` or `WORAI_PROFILE`.
+- Common keys:
+  - `wordlift.api_key`
+  - `gsc.client_secrets`
+  - `gsc.token`
+
+seocheck
+The `seocheck` command runs SEO checks against URLs found in a sitemap. It supports remote sitemap URLs and local sitemap files.
+
+Usage
+- `worai seocheck <sitemap_url_or_path>`
+
+Options
+- `sitemap_url`: URL or local file path to a sitemap XML (or sitemap index). Supports `.gz` files and `file://` URLs.
+- `--max-urls`: Limit the number of URLs checked. Default: no limit.
+- `--timeout`: Timeout in seconds for HTTP requests (sitemaps, robots.txt, llms.txt). Default: 20.0.
+- `--page-timeout`: Timeout in milliseconds for browser page loads. Default: 30000.
+- `--wait-until`: Playwright wait strategy for page load. Choices: `domcontentloaded`, `load`, `networkidle`. Default: `domcontentloaded`.
+- `--ttfb-ok-ms`: TTFB ok threshold in ms. Default: 200.
+- `--ttfb-warn-ms`: TTFB warn threshold in ms. Default: 500.
+- `--headed`: Run the browser with a visible UI instead of headless mode.
+- `--format`: Output format. Choices: `text`, `json`. Default: `text`.
+- `--output-dir`: Write report outputs to this directory (report.json, summary.txt, per-page JSONs, report UI).
+- `--output`: Write a comprehensive JSON report to this file path.
+- `--output-summary`: Write a human-readable summary report to this file path.
+- `--save-html`: Save rendered HTML for each page to the output directory.
+- `--checks`: Comma-separated list of page check names to run (others disabled).
+- `--disable-checks`: Comma-separated list of page check names to skip.
+- `--concurrency`: Number of pages to process concurrently, or `auto`. Default: 1.
+
+Notes
+- The page checks are modular. Add a new check under `worai/seocheck/checks` and register it in `worai/seocheck/checks/__init__.py`.
+- The browser is Playwright (Chromium) to ensure JavaScript rendering.
+- When using `--output-dir`, open `index.html` from that directory to view the report UI (or serve it with a web server).
+
+Examples
+- `worai seocheck https://example.com/sitemap.xml`
+- `worai seocheck ./sitemap.xml`
+- `worai seocheck /path/to/sitemap.xml.gz`
+- `worai seocheck https://example.com/sitemap.xml --wait-until networkidle`
+- `worai seocheck https://example.com/sitemap.xml --max-urls 25 --format json`
+- `worai seocheck https://example.com/sitemap.xml --output ./report.json --output-summary ./report.txt`
+- `worai seocheck https://example.com/sitemap.xml --output-dir ./seocheck-report --save-html`
+- `worai seocheck https://example.com/sitemap.xml --checks status,page_meta,canonical`
+
+Command Examples
+- `worai google-search-console --site sc-domain:example.com --client-secrets ./client_secrets.json`
+- `worai dedupe --dry-run`
+- `worai canonicalize-duplicate-pages --input gsc_pages.csv --output canonical_targets.csv --kpi-window 28d --kpi-metric clicks`
+- `worai delete-entities-from-csv ./entities.csv --batch-size 20`
+- `worai find-faq-page-wrong-type ./data.ttl`
+- `worai find-faq-page-wrong-type ./data.ttl --dry-run --replace-type`
+- `worai find-faq-page-wrong-type ./data.ttl --patch --replace-type`
+- `worai find-missing-names ./data.ttl`
+- `worai find-url-by-type ./data.ttl schema:Service schema:Product`
+- `worai link-groups ./links.csv --format turtle`
+- `worai link-groups ./links.csv --apply --dry-run --concurrency 4`
+- `worai patch ./data.ttl --dry-run --add-types`
+- `worai patch ./data.jsonld --types-only --workers 4`
+- `worai upload-entities-from-turtle ./entities --recursive --limit 50`
+
+Client secrets format
+The `--client-secrets` file is the OAuth2 client configuration downloaded from Google Cloud Console.
+It looks like:
+
+{
+  "installed": {
+    "client_id": "YOUR_CLIENT_ID.apps.googleusercontent.com",
+    "project_id": "your-project-id",
+    "auth_uri": "https://accounts.google.com/o/oauth2/auth",
+    "token_uri": "https://oauth2.googleapis.com/token",
+    "auth_provider_x509_cert_url": "https://www.googleapis.com/oauth2/v1/certs",
+    "client_secret": "YOUR_CLIENT_SECRET",
+    "redirect_uris": [
+      "http://localhost"
+    ]
+  }
+}
+
+Setup steps
+1. Google Cloud Console -> APIs & Services -> OAuth consent screen:
+   - Configure a consent screen (External or Internal) and add yourself as a test user if required.
+2. APIs & Services -> Credentials -> Create Credentials -> OAuth client ID:
+   - Application type: Desktop app.
+3. Download the JSON and pass its path to `--client-secrets`.
+4. Run the command:
+   - `worai google-search-console --site sc-domain:example.com --client-secrets /path/to/client_secrets.json`
+   - If your OAuth client requires a fixed redirect URI (e.g. Web app), add `--port 8080` and register `http://localhost:8080`.
+5. The first run opens a browser for consent and writes a token file (default `gsc_token.json`).

worai-1.0.0/pyproject.toml

@@ -0,0 +1,34 @@
+[project]
+name = "worai"
+version = "1.0.0"
+description = "Add your description here"
+readme = "README.md"
+requires-python = ">=3.11"
+dependencies = [
+    "google-auth>=2.35.0",
+    "google-auth-oauthlib>=1.2.1",
+    "playwright>=1.48.0",
+    "rdflib>=7.5.0",
+    "requests>=2.32.5",
+    "tqdm>=4.67.1",
+    "typer>=0.12.5",
+    "wordlift-client>=1.133.0",
+]
+
+[project.optional-dependencies]
+dev = [
+    "pytest>=8.3.4",
+]
+
+[tool.pytest.ini_options]
+pythonpath = ["."]
+
+[project.scripts]
+worai = "worai.cli:run"
+
+[tool.setuptools]
+package-dir = {"" = "."}
+
+[tool.setuptools.packages.find]
+include = ["worai*"]
+exclude = ["specs*", "scripts*"]

worai-1.0.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

worai-1.0.0/tests/test_canonicalize_duplicate_pages.py

@@ -0,0 +1,27 @@
+from __future__ import annotations
+
+from pathlib import Path
+
+from worai.core.canonicalize_duplicate_pages import load_gsc_csv, select_canonical
+
+
+def test_load_gsc_csv(tmp_path: Path) -> None:
+    csv_path = tmp_path / "gsc.csv"
+    csv_path.write_text(
+        "page,clicks_28d,impressions_28d\n"
+        "https://example.com/a,10,100\n"
+        "https://example.com/b,5,50\n"
+    )
+
+    data = load_gsc_csv(str(csv_path), None)
+    assert data["https://example.com/a"]["clicks_28d"] == 10.0
+
+
+def test_select_canonical() -> None:
+    urls = ["https://example.com/a", "https://example.com/b"]
+    kpis = {
+        "https://example.com/a": {"clicks_28d": 10.0},
+        "https://example.com/b": {"clicks_28d": 5.0},
+    }
+    canonical = select_canonical(urls, kpis, "clicks_28d")
+    assert canonical == "https://example.com/a"

worai-1.0.0/tests/test_config.py

@@ -0,0 +1,32 @@
+from __future__ import annotations
+
+import os
+from pathlib import Path
+
+from worai.config import load_config
+
+
+def test_load_config_profile(tmp_path: Path, monkeypatch) -> None:
+    config_path = tmp_path / "worai.toml"
+    config_path.write_text(
+        """
+        [defaults]
+        timeout = 10
+
+        [profile.dev]
+        timeout = 20
+        """
+    )
+
+    cfg = load_config(str(config_path), "dev", env={})
+    assert cfg.get("defaults.timeout") == 10
+    assert cfg.get("timeout") == 20
+
+
+def test_env_config_override(tmp_path: Path, monkeypatch) -> None:
+    config_path = tmp_path / "worai.toml"
+    config_path.write_text("[defaults]\nlog_level = 'info'\n")
+
+    env = {"WORAI_CONFIG": str(config_path)}
+    cfg = load_config(None, None, env=env)
+    assert cfg.get("defaults.log_level") == "info"

worai-1.0.0/tests/test_dedupe.py

@@ -0,0 +1,14 @@
+from __future__ import annotations
+
+from worai.core.dedupe import group_by_url
+
+
+def test_group_by_url() -> None:
+    entities = [
+        {"iri": "iri1", "url": "https://example.com/a"},
+        {"iri": "iri2", "url": "https://example.com/a"},
+        {"iri": "iri3", "url": "https://example.com/b"},
+    ]
+    grouped = group_by_url(entities)
+    assert grouped["https://example.com/a"] == ["iri1", "iri2"]
+    assert grouped["https://example.com/b"] == ["iri3"]

worai-1.0.0/tests/test_find_missing_names.py

@@ -0,0 +1,24 @@
+from __future__ import annotations
+
+from pathlib import Path
+
+from worai.core.find_missing_names import find_pages_without_name_or_headline
+
+
+def test_find_pages_without_name_or_headline(tmp_path: Path) -> None:
+    ttl = """
+    @prefix schema: <http://schema.org/> .
+    @prefix rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#> .
+
+    <https://example.com/page1> rdf:type schema:CollectionPage ;
+      schema:url <https://example.com/page1> .
+
+    <https://example.com/page2> rdf:type schema:CollectionPage ;
+      schema:url <https://example.com/page2> ;
+      schema:name "Has name" .
+    """
+    ttl_path = tmp_path / "data.ttl"
+    ttl_path.write_text(ttl)
+
+    results = find_pages_without_name_or_headline(str(ttl_path))
+    assert results == ["https://example.com/page1"]

worai-1.0.0/tests/test_find_url_by_type.py

@@ -0,0 +1,28 @@
+from __future__ import annotations
+
+from pathlib import Path
+
+from worai.core.find_url_by_type import FindUrlByTypeOptions, find_urls, resolve_types
+
+
+def test_resolve_types_filters_schema_prefix() -> None:
+    types = resolve_types(["schema:Service", "BadType"])
+    assert types == ["http://schema.org/Service"]
+
+
+def test_find_urls(tmp_path: Path) -> None:
+    ttl = """
+    @prefix schema: <http://schema.org/> .
+
+    <https://example.com/a> a schema:Service ;
+      schema:url <https://example.com/a> .
+
+    <https://example.com/b> a schema:Product ;
+      schema:url <https://example.com/b> .
+    """
+    ttl_path = tmp_path / "data.ttl"
+    ttl_path.write_text(ttl)
+
+    options = FindUrlByTypeOptions(filename=str(ttl_path), types=["schema:Service"], show_id=False)
+    results = find_urls(options)
+    assert results == [("https://example.com/a", "https://example.com/a")]

worai-1.0.0/worai/__init__.py

@@ -0,0 +1,4 @@
+"""WORAi CLI package."""
+
+__all__ = ["__version__"]
+__version__ = "0.1.0"

worai-1.0.0/worai/cli.py

@@ -0,0 +1,79 @@
+"""WORAi root CLI."""
+
+from __future__ import annotations
+
+import logging
+
+import typer
+
+from worai.config import load_config
+from worai.errors import WoraError
+from worai.logging import setup_logging
+
+app = typer.Typer(add_completion=True, no_args_is_help=True)
+
+
+@app.callback()
+def main(
+    ctx: typer.Context,
+    config: str | None = typer.Option(None, "--config", help="Path to config TOML."),
+    profile: str | None = typer.Option(None, "--profile", help="Config profile name."),
+    log_level: str = typer.Option("info", "--log-level", help="Log level."),
+    log_format: str = typer.Option("text", "--log-format", help="Log format: text or json."),
+    quiet: bool = typer.Option(False, "--quiet", help="Only warnings and errors."),
+) -> None:
+    """WORAi command-line tools."""
+    setup_logging(level=log_level, fmt=log_format, quiet=quiet)
+    ctx.obj = {
+        "config": load_config(config, profile),
+        "log_level": log_level,
+        "log_format": log_format,
+        "quiet": quiet,
+    }
+
+
+@app.command("version")
+def version() -> None:
+    """Print version."""
+    from worai import __version__
+
+    typer.echo(__version__)
+
+
+def _install_commands() -> None:
+    from worai.commands import (
+        canonicalize_duplicate_pages,
+        delete_entities_from_csv,
+        dedupe,
+        find_faq_page_wrong_type,
+        find_missing_names,
+        find_url_by_type,
+        google_search_console,
+        link_groups,
+        patch,
+        seocheck,
+        upload_entities_from_turtle,
+    )
+
+    app.add_typer(seocheck.app, name="seocheck")
+    app.add_typer(google_search_console.app, name="google-search-console")
+    app.add_typer(dedupe.app, name="dedupe")
+    app.add_typer(canonicalize_duplicate_pages.app, name="canonicalize-duplicate-pages")
+    app.add_typer(delete_entities_from_csv.app, name="delete-entities-from-csv")
+    app.add_typer(find_faq_page_wrong_type.app, name="find-faq-page-wrong-type")
+    app.add_typer(find_missing_names.app, name="find-missing-names")
+    app.add_typer(find_url_by_type.app, name="find-url-by-type")
+    app.add_typer(link_groups.app, name="link-groups")
+    app.add_typer(patch.app, name="patch")
+    app.add_typer(upload_entities_from_turtle.app, name="upload-entities-from-turtle")
+
+
+_install_commands()
+
+
+def run() -> None:
+    try:
+        app()
+    except WoraError as exc:
+        logging.getLogger("worai").error(str(exc))
+        raise SystemExit(exc.exit_code) from exc

worai-1.0.0/worai/commands/__init__.py

@@ -0,0 +1 @@
+"""CLI subcommands."""

worai-1.0.0/worai/commands/canonicalize_duplicate_pages.py

@@ -0,0 +1,39 @@
+"""CLI wrapper for canonicalize-duplicate-pages."""
+
+from __future__ import annotations
+
+import typer
+
+from worai.core.canonicalize_duplicate_pages import CanonicalizeOptions, run as canonicalize_run
+from worai.core.wordlift import DEFAULT_GRAPHQL_ENDPOINT, resolve_api_key
+from worai.errors import UsageError
+
+app = typer.Typer(add_completion=False, no_args_is_help=True)
+
+
+@app.callback()
+def run(
+    ctx: typer.Context,
+    input_csv: str = typer.Option(..., "--input", help="Input GSC CSV from worai google-search-console."),
+    output_csv: str = typer.Option("canonical_targets.csv", "--output", help="Output CSV path."),
+    url_regex: str | None = typer.Option(None, "--url-regex", help="Regex to filter URLs of interest."),
+    endpoint: str = typer.Option(DEFAULT_GRAPHQL_ENDPOINT, "--endpoint", help="WordLift GraphQL endpoint."),
+    batch_size: int = typer.Option(25, "--batch-size", help="Batch size for GraphQL queries."),
+    kpi_window: str = typer.Option("28d", "--kpi-window", help="KPI time window (7d, 28d, 3m)."),
+    kpi_metric: str = typer.Option("clicks", "--kpi-metric", help="KPI metric (clicks, impressions, ctr)."),
+) -> None:
+    api_key = resolve_api_key(ctx.obj.get("config") if ctx.obj else None)
+    if not api_key:
+        raise UsageError("WORDLIFT_KEY is required (or set wordlift.api_key in config).")
+
+    options = CanonicalizeOptions(
+        api_key=api_key,
+        input_csv=input_csv,
+        output_csv=output_csv,
+        url_regex=url_regex,
+        endpoint=endpoint,
+        batch_size=batch_size,
+        kpi_window=kpi_window,
+        kpi_metric=kpi_metric,
+    )
+    canonicalize_run(options)

worai-1.0.0/worai/commands/dedupe.py

@@ -0,0 +1,33 @@
+"""CLI wrapper for dedupe."""
+
+from __future__ import annotations
+
+import typer
+
+from worai.core.dedupe import DedupeOptions, run as dedupe_run
+from worai.core.wordlift import resolve_api_key, DEFAULT_GRAPHQL_ENDPOINT
+from worai.errors import UsageError
+
+app = typer.Typer(add_completion=False, no_args_is_help=True)
+
+
+@app.callback()
+def run(
+    ctx: typer.Context,
+    endpoint: str = typer.Option(DEFAULT_GRAPHQL_ENDPOINT, "--endpoint", help="GraphQL endpoint URL."),
+    dry_run: bool = typer.Option(False, "--dry-run", help="Show delete calls without executing them."),
+    rate_delay: float = typer.Option(0.0, "--rate-delay", help="Seconds to sleep between delete calls."),
+    auto: bool = typer.Option(False, "--auto", help="Automatically keep the last IRI in each group."),
+) -> None:
+    api_key = resolve_api_key(ctx.obj.get("config") if ctx.obj else None)
+    if not api_key:
+        raise UsageError("WORDLIFT_KEY is required (or set wordlift.api_key in config).")
+
+    options = DedupeOptions(
+        api_key=api_key,
+        endpoint=endpoint,
+        dry_run=dry_run,
+        rate_delay=rate_delay,
+        auto=auto,
+    )
+    dedupe_run(options)

worai-1.0.0/worai/commands/delete_entities_from_csv.py

@@ -0,0 +1,25 @@
+"""CLI wrapper for delete-entities-from-csv."""
+
+from __future__ import annotations
+
+import typer
+
+from worai.core.delete_entities_from_csv import DeleteEntitiesOptions, delete_entities
+from worai.core.wordlift import resolve_api_key
+from worai.errors import UsageError
+
+app = typer.Typer(add_completion=False, no_args_is_help=True)
+
+
+@app.callback()
+def run(
+    ctx: typer.Context,
+    csv_file: str = typer.Argument(..., help="CSV file with IRIs (first column)."),
+    batch_size: int = typer.Option(10, "--batch-size", help="Number of IRIs to delete per batch."),
+) -> None:
+    api_key = resolve_api_key(ctx.obj.get("config") if ctx.obj else None)
+    if not api_key:
+        raise UsageError("WORDLIFT_KEY is required (or set wordlift.api_key in config).")
+
+    options = DeleteEntitiesOptions(api_key=api_key, csv_file=csv_file, batch_size=batch_size)
+    delete_entities(options)

worai-1.0.0/worai/commands/find_faq_page_wrong_type.py

@@ -0,0 +1,41 @@
+"""CLI wrapper for find-faq-page-wrong-type."""
+
+from __future__ import annotations
+
+import os
+import typer
+
+from worai.core.find_faq_page_wrong_type import FaqFixOptions, run as faq_run
+from worai.core.wordlift import resolve_api_key
+from worai.errors import UsageError
+
+app = typer.Typer(add_completion=False, no_args_is_help=True)
+
+
+@app.callback()
+def run(
+    ctx: typer.Context,
+    file_path: str = typer.Argument(..., help="Path to Turtle RDF file."),
+    patch: bool = typer.Option(False, "--patch", help="Execute live API patch calls."),
+    dry_run: bool = typer.Option(False, "--dry-run", help="Show what would be patched."),
+    replace_type: bool = typer.Option(False, "--replace-type", help="Remove existing types before adding FAQPage."),
+) -> None:
+    mode = "find"
+    if patch:
+        mode = "patch"
+    elif dry_run:
+        mode = "dry-run"
+
+    api_key = None
+    if mode == "patch":
+        api_key = resolve_api_key(ctx.obj.get("config") if ctx.obj else None) or os.environ.get("WORDLIFT_API_KEY")
+        if not api_key:
+            raise UsageError("WORDLIFT_KEY is required for --patch (or set wordlift.api_key in config).")
+
+    options = FaqFixOptions(
+        file_path=file_path,
+        mode=mode,
+        replace_type=replace_type,
+        api_key=api_key,
+    )
+    faq_run(options)

worai-1.0.0/worai/commands/find_missing_names.py

@@ -0,0 +1,35 @@
+"""CLI wrapper for find-missing-names."""
+
+from __future__ import annotations
+
+import sys
+
+import typer
+
+from worai.core.find_missing_names import run as find_run
+
+app = typer.Typer(add_completion=False, no_args_is_help=True)
+
+
+@app.callback()
+def run(
+    file_path: str = typer.Argument(..., help="Path to RDF file."),
+) -> None:
+    try:
+        results = find_run(file_path)
+    except FileNotFoundError:
+        typer.echo(f"Error: The file '{file_path}' was not found.", err=True)
+        raise typer.Exit(code=1)
+    except Exception as exc:
+        typer.echo(f"An error occurred while parsing the file: {exc}", err=True)
+        raise typer.Exit(code=1)
+
+    if results:
+        typer.echo(
+            f"Found URLs for {len(results)} schema:CollectionPage entities without a 'schema:name' or 'schema:headline':"
+        )
+        typer.echo("-" * 80)
+        for url in results:
+            typer.echo(url)
+    else:
+        typer.echo("No schema:CollectionPage entities are missing both 'schema:name' and 'schema:headline'.")