expunct-cli 0.1.0__tar.gz → 0.2.0__tar.gz

{expunct_cli-0.1.0 → expunct_cli-0.2.0}/PKG-INFO

@@ -1,13 +1,13 @@
 Metadata-Version: 2.4
 Name: expunct-cli
-Version: 0.1.0
+Version: 0.2.0
 Summary: CLI for the Expunct PII redaction API — redact, detect, and manage sensitive data from the command line.
 Project-URL: Homepage, https://expunct.ai
 Project-URL: Documentation, https://docs.expunct.ai
 Project-URL: Repository, https://github.com/expunct/cli
 Author: Expunct
 License-Expression: MIT
-Keywords: cli,pii,privacy,redaction,security
+Keywords: ai,cli,gdpr,hipaa,llm,pdf,pii,privacy,rag,redaction,security
 Classifier: Development Status :: 4 - Beta
 Classifier: Environment :: Console
 Classifier: Intended Audience :: Developers
@@ -18,10 +18,11 @@ 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 :: Scientific/Engineering :: Artificial Intelligence
 Classifier: Topic :: Security
 Classifier: Topic :: Software Development :: Libraries
 Requires-Python: >=3.10
-Requires-Dist: expunct>=0.1.1
+Requires-Dist: expunct>=0.2.0
 Requires-Dist: rich>=13.0
 Requires-Dist: typer>=0.15
 Provides-Extra: dev
@@ -212,6 +213,79 @@ expunct audit list --event-type redaction --page-size 50
 expunct audit list --json
 ```
 
+### Document Intelligence commands (beta)
+
+`parse`, `extract`, and `safe-parse` call the Expunct Document Intelligence API,
+which is currently in **beta and feature-flag gated**. Your tenant must be
+enabled before these commands will succeed; calls from disabled tenants return a
+`403`. PDF and DOCX are the supported formats during beta.
+
+### `expunct parse`
+
+Parse a PDF or DOCX into a canonical document structure (text, tables, headings, layout).
+
+```bash
+expunct parse report.pdf
+expunct parse contract.docx --language en
+expunct parse report.pdf --no-wait          # submit and return job ID immediately
+expunct parse report.pdf --json             # raw JSON output
+```
+
+| Flag | Description |
+|------|-------------|
+| `--language, -l` | Language code (default: `en`) |
+| `--wait/--no-wait` | Wait for job to complete (default: `--wait`) |
+| `--timeout` | Wait timeout in seconds (default: `300`) |
+| `--json` | Raw JSON output |
+
+### `expunct extract`
+
+Extract structured fields from a parsed document using a JSON Schema or built-in template.
+
+```bash
+# From an existing parse artifact (preferred — avoids re-parsing)
+expunct extract art-abc123 --schema invoice_schema.json
+
+# Parse and extract in one step
+expunct extract --file report.pdf --template invoice
+
+# Inline schema
+expunct extract art-abc123 --schema-json '{"type":"object","properties":{"total":{"type":"number"}}}'
+```
+
+| Flag | Description |
+|------|-------------|
+| `PARSE_ARTIFACT_ID` | Canonical document artifact ID from a completed parse job |
+| `--file, -f` | PDF or DOCX to parse and extract in one step (mutually exclusive with artifact ID) |
+| `--schema, -s` | Path to JSON Schema file defining fields to extract |
+| `--schema-json` | Inline JSON Schema string |
+| `--template, -t` | Built-in template ID (e.g. `invoice`) |
+| `--language, -l` | Language code (default: `en`) |
+| `--wait/--no-wait` | Wait for job to complete (default: `--wait`) |
+| `--timeout` | Wait timeout in seconds (default: `300`) |
+| `--json` | Raw JSON output |
+
+### `expunct safe-parse`
+
+Parse a PDF or DOCX and sanitize PII in a single workflow. Produces sanitized
+canonical document, sanitized markdown, and sanitized chunk artifacts suitable
+for AI ingestion (RAG, prompts, embeddings).
+
+```bash
+expunct safe-parse contract.pdf
+expunct safe-parse report.docx --policy-id strict
+expunct safe-parse contract.pdf --no-wait        # submit and return job ID immediately
+expunct safe-parse contract.pdf --json           # raw JSON output
+```
+
+| Flag | Description |
+|------|-------------|
+| `--policy-id, -p` | Redaction policy ID applied during sanitization |
+| `--language, -l` | Language code (default: `en`) |
+| `--wait/--no-wait` | Wait for job to complete (default: `--wait`) |
+| `--timeout` | Wait timeout in seconds (default: `300`) |
+| `--json` | Raw JSON output |
+
 ### `expunct config`
 
 Manage CLI configuration.

{expunct_cli-0.1.0 → expunct_cli-0.2.0}/README.md

@@ -181,6 +181,79 @@ expunct audit list --event-type redaction --page-size 50
 expunct audit list --json
 ```
 
+### Document Intelligence commands (beta)
+
+`parse`, `extract`, and `safe-parse` call the Expunct Document Intelligence API,
+which is currently in **beta and feature-flag gated**. Your tenant must be
+enabled before these commands will succeed; calls from disabled tenants return a
+`403`. PDF and DOCX are the supported formats during beta.
+
+### `expunct parse`
+
+Parse a PDF or DOCX into a canonical document structure (text, tables, headings, layout).
+
+```bash
+expunct parse report.pdf
+expunct parse contract.docx --language en
+expunct parse report.pdf --no-wait          # submit and return job ID immediately
+expunct parse report.pdf --json             # raw JSON output
+```
+
+| Flag | Description |
+|------|-------------|
+| `--language, -l` | Language code (default: `en`) |
+| `--wait/--no-wait` | Wait for job to complete (default: `--wait`) |
+| `--timeout` | Wait timeout in seconds (default: `300`) |
+| `--json` | Raw JSON output |
+
+### `expunct extract`
+
+Extract structured fields from a parsed document using a JSON Schema or built-in template.
+
+```bash
+# From an existing parse artifact (preferred — avoids re-parsing)
+expunct extract art-abc123 --schema invoice_schema.json
+
+# Parse and extract in one step
+expunct extract --file report.pdf --template invoice
+
+# Inline schema
+expunct extract art-abc123 --schema-json '{"type":"object","properties":{"total":{"type":"number"}}}'
+```
+
+| Flag | Description |
+|------|-------------|
+| `PARSE_ARTIFACT_ID` | Canonical document artifact ID from a completed parse job |
+| `--file, -f` | PDF or DOCX to parse and extract in one step (mutually exclusive with artifact ID) |
+| `--schema, -s` | Path to JSON Schema file defining fields to extract |
+| `--schema-json` | Inline JSON Schema string |
+| `--template, -t` | Built-in template ID (e.g. `invoice`) |
+| `--language, -l` | Language code (default: `en`) |
+| `--wait/--no-wait` | Wait for job to complete (default: `--wait`) |
+| `--timeout` | Wait timeout in seconds (default: `300`) |
+| `--json` | Raw JSON output |
+
+### `expunct safe-parse`
+
+Parse a PDF or DOCX and sanitize PII in a single workflow. Produces sanitized
+canonical document, sanitized markdown, and sanitized chunk artifacts suitable
+for AI ingestion (RAG, prompts, embeddings).
+
+```bash
+expunct safe-parse contract.pdf
+expunct safe-parse report.docx --policy-id strict
+expunct safe-parse contract.pdf --no-wait        # submit and return job ID immediately
+expunct safe-parse contract.pdf --json           # raw JSON output
+```
+
+| Flag | Description |
+|------|-------------|
+| `--policy-id, -p` | Redaction policy ID applied during sanitization |
+| `--language, -l` | Language code (default: `en`) |
+| `--wait/--no-wait` | Wait for job to complete (default: `--wait`) |
+| `--timeout` | Wait timeout in seconds (default: `300`) |
+| `--json` | Raw JSON output |
+
 ### `expunct config`
 
 Manage CLI configuration.

{expunct_cli-0.1.0 → expunct_cli-0.2.0}/pyproject.toml

@@ -4,13 +4,13 @@ build-backend = "hatchling.build"
 
 [project]
 name = "expunct-cli"
-version = "0.1.0"
+version = "0.2.0"
 description = "CLI for the Expunct PII redaction API — redact, detect, and manage sensitive data from the command line."
 readme = "README.md"
 license = "MIT"
 requires-python = ">=3.10"
 authors = [{ name = "Expunct" }]
-keywords = ["pii", "redaction", "privacy", "cli", "security"]
+keywords = ["pii", "redaction", "privacy", "cli", "security", "gdpr", "hipaa", "llm", "rag", "ai", "pdf"]
 classifiers = [
     "Development Status :: 4 - Beta",
     "Environment :: Console",
@@ -23,10 +23,11 @@ classifiers = [
     "Programming Language :: Python :: 3.12",
     "Programming Language :: Python :: 3.13",
     "Topic :: Security",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
     "Topic :: Software Development :: Libraries",
 ]
 dependencies = [
-    "expunct>=0.1.1",
+    "expunct>=0.2.0",
     "typer>=0.15",
     "rich>=13.0",
 ]

expunct_cli-0.2.0/src/expunct_cli/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.2.0"

expunct_cli-0.2.0/src/expunct_cli/commands/extract.py

@@ -0,0 +1,216 @@
+from __future__ import annotations
+
+import json
+import sys
+from pathlib import Path
+
+import typer
+from expunct import (
+    ApiError,
+    AuthenticationError,
+    NotFoundError,
+    PollingTimeoutError,
+    RateLimitError,
+    ValidationError,
+)
+
+from expunct_cli.client import get_client
+from expunct_cli.output import console, print_error, print_json
+
+app = typer.Typer(no_args_is_help=False, invoke_without_command=True)
+
+
+@app.callback(invoke_without_command=True)
+def extract(
+    ctx: typer.Context,
+    parse_artifact_id: str | None = typer.Argument(
+        None,
+        help="Canonical document artifact ID from a completed parse job. "
+             "Mutually exclusive with --file.",
+    ),
+    file: Path | None = typer.Option(
+        None, "--file", "-f",
+        help="PDF or DOCX file to parse and extract in one step. "
+             "Mutually exclusive with PARSE_ARTIFACT_ID.",
+    ),
+    schema: Path | None = typer.Option(
+        None, "--schema", "-s",
+        help="Path to a JSON Schema file defining the fields to extract.",
+    ),
+    schema_json: str | None = typer.Option(
+        None, "--schema-json",
+        help="Inline JSON Schema string (alternative to --schema).",
+    ),
+    template_id: str | None = typer.Option(
+        None, "--template", "-t",
+        help="Built-in extraction template ID (e.g. 'invoice'). "
+             "Mutually exclusive with --schema / --schema-json.",
+    ),
+    language: str = typer.Option("en", "--language", "-l", help="Language code."),
+    wait: bool = typer.Option(True, "--wait/--no-wait", help="Wait for job to complete."),
+    timeout: int = typer.Option(300, "--timeout", help="Timeout in seconds when waiting."),
+    json_output: bool = typer.Option(False, "--json", help="Output raw JSON."),
+) -> None:
+    """Extract structured fields from a parsed document.
+
+    Provide exactly one source: a PARSE_ARTIFACT_ID (canonical document artifact
+    from a completed parse job) or --file (parses and extracts in one step).
+
+    Provide exactly one schema: --schema / --schema-json or --template.
+
+    Examples:
+
+      expunct extract art-abc123 --schema invoice_schema.json
+
+      expunct extract --file report.pdf --template invoice
+
+      expunct extract art-abc123 \\
+        --schema-json '{"type":"object","properties":{"total":{"type":"number"}}}'
+    """
+    if ctx.invoked_subcommand is not None:
+        return
+
+    # Validate source
+    if parse_artifact_id is None and file is None:
+        print_error("Provide either a PARSE_ARTIFACT_ID argument or --file.")
+        raise typer.Exit(1)
+    if parse_artifact_id is not None and file is not None:
+        print_error("PARSE_ARTIFACT_ID and --file are mutually exclusive.")
+        raise typer.Exit(1)
+
+    # Validate schema
+    if schema is None and schema_json is None and template_id is None:
+        print_error("Provide --schema, --schema-json, or --template.")
+        raise typer.Exit(1)
+    if template_id is not None and (schema is not None or schema_json is not None):
+        print_error("--template and --schema/--schema-json are mutually exclusive.")
+        raise typer.Exit(1)
+    if schema is not None and schema_json is not None:
+        print_error("--schema and --schema-json are mutually exclusive.")
+        raise typer.Exit(1)
+
+    # Resolve schema dict
+    resolved_schema: dict | None = None
+    if schema is not None:
+        if not schema.exists():
+            print_error(f"Schema file not found: {schema}")
+            raise typer.Exit(1)
+        try:
+            resolved_schema = json.loads(schema.read_text())
+        except json.JSONDecodeError as e:
+            print_error(f"Invalid JSON in schema file: {e}")
+            raise typer.Exit(1)
+    elif schema_json is not None:
+        try:
+            resolved_schema = json.loads(schema_json)
+        except json.JSONDecodeError as e:
+            print_error(f"Invalid --schema-json: {e}")
+            raise typer.Exit(1)
+
+    try:
+        client = get_client()
+
+        if parse_artifact_id is not None:
+            job = client.documents.extract(
+                parse_artifact_id=parse_artifact_id,
+                schema=resolved_schema,
+                template_id=template_id,
+                language=language,
+            )
+        else:
+            assert file is not None
+            if not file.exists():
+                print_error(f"File not found: {file}")
+                raise typer.Exit(1)
+            suffix = file.suffix.lower()
+            if suffix not in {".pdf", ".docx"}:
+                print_error(f"Unsupported file type: {suffix}. Accepted: .pdf, .docx")
+                raise typer.Exit(1)
+            with open(file, "rb") as f_obj:
+                job = client.documents.extract(
+                    file=f_obj,
+                    schema=resolved_schema,
+                    template_id=template_id,
+                    language=language,
+                )
+
+        if not wait:
+            if json_output:
+                print_json(job)
+            else:
+                console.print(f"[bold cyan]Job submitted:[/] [dim]{job.id}[/]")
+                console.print(f"Status: {job.status}")
+            return
+
+        # Poll until complete
+        import time
+
+        deadline = time.monotonic() + timeout
+        detail = client.documents.get_job(job.id)
+
+        while detail.status not in {"completed", "failed", "error"}:
+            if time.monotonic() >= deadline:
+                print_error(f"Timed out waiting for job {job.id}")
+                raise typer.Exit(1)
+            time.sleep(2)
+            detail = client.documents.get_job(job.id)
+
+        if detail.status in {"failed", "error"}:
+            print_error(f"Job {job.id} failed: {detail.error_message or 'unknown error'}")
+            raise typer.Exit(1)
+
+        # Find the extract_result artifact
+        result_artifact = next(
+            (a for a in detail.artifacts if a.artifact_kind == "extract_result"), None
+        )
+
+        if result_artifact is None:
+            print_error("No extract_result artifact found in completed job.")
+            raise typer.Exit(1)
+
+        # Fetch artifact content (JSON payload, not metadata)
+        content = client.documents.get_artifact_content(result_artifact.id)
+
+        if json_output:
+            json.dump(content, sys.stdout, indent=2, default=str)
+            sys.stdout.write("\n")
+        else:
+            console.print(f"[bold green]Extraction complete[/] — job [dim]{detail.id}[/]")
+            _print_fields(content)
+
+    except (
+        ApiError, AuthenticationError, NotFoundError,
+        RateLimitError, ValidationError, PollingTimeoutError,
+    ) as e:
+        print_error(str(e))
+        raise typer.Exit(1)
+
+
+def _print_fields(content: dict) -> None:
+    """Pretty-print extracted fields from an extract_result artifact."""
+    from rich.table import Table
+
+    fields = content.get("fields", [])
+    if not fields:
+        console.print("[dim]No fields extracted.[/]")
+        return
+
+    table = Table(title="Extracted Fields")
+    table.add_column("Field", style="cyan")
+    table.add_column("Value", style="bold")
+    table.add_column("Confidence", justify="right", style="yellow")
+
+    for field in fields:
+        name = field.get("name", "")
+        value = field.get("value", "")
+        confidence = field.get("confidence")
+        conf_str = f"{confidence:.2f}" if isinstance(confidence, float) else str(confidence or "")
+        table.add_row(str(name), str(value) if value is not None else "[dim]null[/]", conf_str)
+
+    console.print(table)
+
+    errors = content.get("validation_errors", [])
+    if errors:
+        console.print(f"\n[yellow]Validation errors:[/] {len(errors)}")
+        for err in errors:
+            console.print(f"  [red]•[/] {err}")

expunct_cli-0.2.0/src/expunct_cli/commands/parse.py

@@ -0,0 +1,115 @@
+from __future__ import annotations
+
+from pathlib import Path
+
+import typer
+from expunct import (
+    ApiError,
+    AuthenticationError,
+    NotFoundError,
+    PollingTimeoutError,
+    RateLimitError,
+    ValidationError,
+)
+
+from expunct_cli.client import get_client
+from expunct_cli.output import console, print_error, print_json
+
+app = typer.Typer(no_args_is_help=False, invoke_without_command=True)
+
+
+@app.callback(invoke_without_command=True)
+def parse(
+    ctx: typer.Context,
+    file: Path = typer.Argument(..., help="PDF or DOCX file to parse."),
+    language: str = typer.Option("en", "--language", "-l", help="Language code."),
+    wait: bool = typer.Option(True, "--wait/--no-wait", help="Wait for job to complete."),
+    timeout: int = typer.Option(300, "--timeout", help="Timeout in seconds when waiting."),
+    json_output: bool = typer.Option(False, "--json", help="Output raw JSON."),
+) -> None:
+    """Parse a PDF or DOCX into a canonical document structure.
+
+    Submits the file to the Document Intelligence API and (by default) waits
+    for the job to complete, then prints a summary of the produced artifacts.
+
+    Use --no-wait to return the job ID immediately for manual polling.
+    """
+    if ctx.invoked_subcommand is not None:
+        return
+
+    if not file.exists():
+        print_error(f"File not found: {file}")
+        raise typer.Exit(1)
+
+    suffix = file.suffix.lower()
+    if suffix not in {".pdf", ".docx"}:
+        print_error(f"Unsupported file type: {suffix}. Accepted: .pdf, .docx")
+        raise typer.Exit(1)
+
+    try:
+        client = get_client()
+
+        with open(file, "rb") as f:
+            job = client.documents.parse(f, language=language)
+
+        if json_output and not wait:
+            print_json(job)
+            return
+
+        if not wait:
+            if json_output:
+                print_json(job)
+            else:
+                console.print(f"[bold cyan]Job submitted:[/] [dim]{job.id}[/]")
+                console.print(f"Status: {job.status}")
+                console.print(
+                    f"Poll with: [bold]expunct jobs get {job.id}[/] "
+                    f"(or use expunct_get_document_job in MCP)"
+                )
+            return
+
+        # Wait for job to complete by polling
+        import time
+
+        deadline = time.monotonic() + timeout
+        detail = client.documents.get_job(job.id)
+
+        while detail.status not in {"completed", "failed", "error"}:
+            if time.monotonic() >= deadline:
+                print_error(f"Timed out waiting for job {job.id}")
+                raise typer.Exit(1)
+            time.sleep(2)
+            detail = client.documents.get_job(job.id)
+
+        if detail.status in {"failed", "error"}:
+            print_error(f"Job {job.id} failed: {detail.error_message or 'unknown error'}")
+            raise typer.Exit(1)
+
+        if json_output:
+            print_json(detail)
+        else:
+            console.print(f"[bold green]Parse complete[/] — job [dim]{detail.id}[/]")
+            console.print(f"  Pages: {_pages(detail.artifacts)}")
+            console.print(f"  Artifacts produced: {len(detail.artifacts)}")
+            for artifact in detail.artifacts:
+                console.print(
+                    f"    [cyan]{artifact.artifact_kind}[/]  id=[dim]{artifact.id}[/]"
+                )
+            console.print(
+                "\nRetrieve artifact content with: "
+                "[bold]expunct_get_artifact[/] (MCP) or the Expunct SDK."
+            )
+
+    except (
+        ApiError, AuthenticationError, NotFoundError,
+        RateLimitError, ValidationError, PollingTimeoutError,
+    ) as e:
+        print_error(str(e))
+        raise typer.Exit(1)
+
+
+def _pages(artifacts: list) -> str:
+    for a in artifacts:
+        if a.artifact_kind == "canonical_document" and a.page_count is not None:
+            return str(a.page_count)
+    return "unknown"

expunct_cli-0.2.0/src/expunct_cli/commands/safe_parse.py

@@ -0,0 +1,118 @@
+from __future__ import annotations
+
+from pathlib import Path
+
+import typer
+from expunct import (
+    ApiError,
+    AuthenticationError,
+    NotFoundError,
+    PollingTimeoutError,
+    RateLimitError,
+    ValidationError,
+)
+
+from expunct_cli.client import get_client
+from expunct_cli.output import console, print_error, print_json
+
+app = typer.Typer(no_args_is_help=False, invoke_without_command=True)
+
+
+@app.callback(invoke_without_command=True)
+def safe_parse(
+    ctx: typer.Context,
+    file: Path = typer.Argument(..., help="PDF or DOCX file to safe-parse."),
+    policy_id: str | None = typer.Option(
+        None, "--policy-id", "-p",
+        help="Redaction policy ID to apply during sanitization.",
+    ),
+    language: str = typer.Option("en", "--language", "-l", help="Language code."),
+    wait: bool = typer.Option(True, "--wait/--no-wait", help="Wait for job to complete."),
+    timeout: int = typer.Option(300, "--timeout", help="Timeout in seconds when waiting."),
+    json_output: bool = typer.Option(False, "--json", help="Output raw JSON."),
+) -> None:
+    """Parse a PDF or DOCX and sanitize PII in one workflow (beta).
+
+    Produces sanitized canonical document, sanitized markdown, and sanitized
+    chunk artifacts suitable for downstream AI ingestion (RAG, prompts, etc.).
+
+    Document Intelligence is currently in beta and gated by feature flag —
+    your tenant must be enabled before this command will succeed.
+    """
+    if ctx.invoked_subcommand is not None:
+        return
+
+    if not file.exists():
+        print_error(f"File not found: {file}")
+        raise typer.Exit(1)
+
+    suffix = file.suffix.lower()
+    if suffix not in {".pdf", ".docx"}:
+        print_error(f"Unsupported file type: {suffix}. Accepted: .pdf, .docx")
+        raise typer.Exit(1)
+
+    try:
+        client = get_client()
+
+        with open(file, "rb") as f:
+            job = client.documents.safe_parse(f, policy_id=policy_id, language=language)
+
+        if not wait:
+            if json_output:
+                print_json(job)
+            else:
+                console.print(f"[bold cyan]Job submitted:[/] [dim]{job.id}[/]")
+                console.print(f"Status: {job.status}")
+                console.print(
+                    f"Poll with: [bold]expunct jobs get {job.id}[/] "
+                    f"(or use expunct_get_document_job in MCP)"
+                )
+            return
+
+        import time
+
+        deadline = time.monotonic() + timeout
+        detail = client.documents.get_job(job.id)
+
+        while detail.status not in {"completed", "failed", "error"}:
+            if time.monotonic() >= deadline:
+                print_error(f"Timed out waiting for job {job.id}")
+                raise typer.Exit(1)
+            time.sleep(2)
+            detail = client.documents.get_job(job.id)
+
+        if detail.status in {"failed", "error"}:
+            print_error(f"Job {job.id} failed: {detail.error_message or 'unknown error'}")
+            raise typer.Exit(1)
+
+        if json_output:
+            print_json(detail)
+        else:
+            console.print(f"[bold green]Safe-parse complete[/] — job [dim]{detail.id}[/]")
+            console.print(f"  Pages: {_pages(detail.artifacts)}")
+            console.print(f"  Artifacts produced: {len(detail.artifacts)}")
+            for artifact in detail.artifacts:
+                console.print(
+                    f"    [cyan]{artifact.artifact_kind}[/]  id=[dim]{artifact.id}[/]"
+                )
+            console.print(
+                "\nRetrieve sanitized artifact content with: "
+                "[bold]expunct_get_artifact[/] (MCP) or the Expunct SDK."
+            )
+
+    except (
+        ApiError, AuthenticationError, NotFoundError,
+        RateLimitError, ValidationError, PollingTimeoutError,
+    ) as e:
+        print_error(str(e))
+        raise typer.Exit(1)
+
+
+def _pages(artifacts: list) -> str:
+    for a in artifacts:
+        if a.artifact_kind == "sanitized_canonical_document" and a.page_count is not None:
+            return str(a.page_count)
+    for a in artifacts:
+        if a.artifact_kind == "canonical_document" and a.page_count is not None:
+            return str(a.page_count)
+    return "unknown"

{expunct_cli-0.1.0 → expunct_cli-0.2.0}/src/expunct_cli/main.py

@@ -6,9 +6,12 @@ from expunct_cli import __version__
 from expunct_cli.commands.audit import app as audit_app
 from expunct_cli.commands.config_cmd import app as config_app
 from expunct_cli.commands.detect import app as detect_app
+from expunct_cli.commands.extract import app as extract_app
 from expunct_cli.commands.jobs import app as jobs_app
+from expunct_cli.commands.parse import app as parse_app
 from expunct_cli.commands.policies import app as policies_app
 from expunct_cli.commands.redact import app as redact_app
+from expunct_cli.commands.safe_parse import app as safe_parse_app
 
 app = typer.Typer(
     name="expunct",
@@ -41,6 +44,21 @@ app.add_typer(jobs_app, name="jobs", help="Manage redaction jobs.")
 app.add_typer(policies_app, name="policies", help="Manage redaction policies.")
 app.add_typer(audit_app, name="audit", help="View audit logs.")
 app.add_typer(config_app, name="config", help="Manage CLI configuration.")
+app.add_typer(
+    parse_app,
+    name="parse",
+    help="Parse a PDF or DOCX into structured document artifacts.",
+)
+app.add_typer(
+    extract_app,
+    name="extract",
+    help="Extract structured fields from a parsed document.",
+)
+app.add_typer(
+    safe_parse_app,
+    name="safe-parse",
+    help="Parse a PDF or DOCX and sanitize PII in one workflow (beta).",
+)
 
 if __name__ == "__main__":
     app()

expunct_cli-0.1.0/src/expunct_cli/__init__.py

@@ -1 +0,0 @@
-__version__ = "0.1.0"