fix: isolate metadata imports to doctype (#1671)

In a different PR, some no-extras tests started failing with import
errors when something innocuous was imported from
`unstructured.file_utils.metadata`. This turned out to be because of the
top-level, doctype-specific imports in that file. Importing a general
metadata object shouldn't require installation of modules like `PIL`,
`docx`, and `openpyxl`.

To fix, I moved these functions to be imported inside the functions that
use them, and added the `requires_dependencies` decorator to the
functions.

#### Testing:

You should be able to run something like:
```python
from unstructured.file_utils.metadata import Metadata
```

Without `openpyxl` installed.

CHANGELOG.md

@@ -1,8 +1,8 @@
-## 0.10.20-dev4
+## 0.10.20-dev5
 
 ### Enhancements
 
-* **Align to top left when shrinking bounding boxes for `xy-curt` sorting:** Update `shrink_bbox()` to keep top left rather than center
+* **Align to top left when shrinking bounding boxes for `xy-cut` sorting:** Update `shrink_bbox()` to keep top left rather than center.
 * **Add visualization script to annotate elements** This script is often used to analyze/visualize elements with coordinates (e.g. partition_pdf()).
 * **Adds data source properties to the Jira connector** These properties (date_created, date_modified, version, source_url, record_locator) are written to element metadata during ingest, mapping elements to information about the document source from which they derive. This functionality enables downstream applications to reveal source document applications, e.g. a link to a GDrive doc, Salesforce record, etc.
 * **Improve title detection in pptx documents** The default title textboxes on a pptx slide are now categorized as titles.
@@ -15,6 +15,7 @@ setting UNSTRUCTURED_INCLUDE_DEBUG_METADATA=true is needed.
 
 ### Fixes
 
+* **Fix prevent metadata module from importing dependencies from unnecessary modules** Problem: The `metadata` module had several top level imports that were only used in and applicable to code related to specific document types, while there were many general-purpose functions. As a result, general-purpose functions couldn't be used without unnecessary dependencies being installed. Fix: moved 3rd party dependency top level imports to inside the functions in which they are used and applied a decorator to check that the dependency is installed and emit a helpful error message if not.
 * **Fixes category_depth None value for Title elements** Problem: `Title` elements from `chipper` get `category_depth`= None even when `Headline` and/or `Subheadline` elements are present in the same page. Fix: all `Title` elements with `category_depth` = None should be set to have a depth of 0 instead iff there are `Headline` and/or `Subheadline` element-types present. Importance: `Title` elements should be equivalent html `H1` when nested headings are present; otherwise, `category_depth` metadata can result ambiguous within elements in a page.
 * **Tweak `xy-cut` ordering output to be more column friendly** This results in the order of elements more closely reflecting natural reading order which benefits downstream applications. While element ordering from `xy-cut` is usually mostly correct when ordering multi-column documents, sometimes elements from a RHS column will appear before elements in a LHS column. Fix: add swapped `xy-cut` ordering by sorting by X coordinate first and then Y coordinate.
 * **Fixes badly initialized Formula** Problem: YoloX contain new types of elements, when loading a document that contain formulas a new element of that class

unstructured/__version__.py

@@ -1 +1 @@
-__version__ = "0.10.20-dev4"  # pragma: no cover
+__version__ = "0.10.20-dev5"  # pragma: no cover

unstructured/file_utils/metadata.py

@@ -3,10 +3,7 @@ import io
 from dataclasses import dataclass, field
 from typing import IO, Any, Dict, Final, Optional
 
-import docx
-import openpyxl
-from PIL import Image
-from PIL.ExifTags import TAGS
+from unstructured.utils import requires_dependencies
 
 # NOTE(robison) - ref: https://www.media.mit.edu/pia/Research/deepview/exif.html
 EXIF_DATETIME_FMT: Final[str] = "%Y:%m:%d %H:%M:%S"
@@ -39,11 +36,14 @@ class Metadata:
         return self.__dict__
 
 
+@requires_dependencies("docx")
 def get_docx_metadata(
     filename: str = "",
     file: Optional[IO[bytes]] = None,
 ) -> Metadata:
     """Extracts document metadata from a Microsoft .docx document."""
+    import docx
+
     if filename:
         doc = docx.Document(filename)
     elif file:
@@ -72,11 +72,14 @@ def get_docx_metadata(
     return metadata
 
 
+@requires_dependencies("openpyxl")
 def get_xlsx_metadata(
     filename: str = "",
     file: Optional[IO[bytes]] = None,
 ) -> Metadata:
     """Extracts document metadata from a Microsoft .xlsx document."""
+    import openpyxl
+
     if filename:
         workbook = openpyxl.load_workbook(filename)
     elif file:
@@ -106,11 +109,15 @@ def get_xlsx_metadata(
     return metadata
 
 
+@requires_dependencies("PIL")
 def get_jpg_metadata(
     filename: str = "",
     file: Optional[IO[bytes]] = None,
 ) -> Metadata:
     """Extracts metadata from a JPG image, including EXIF metadata."""
+    from PIL import Image
+    from PIL.ExifTags import TAGS
+
     if filename:
         image = Image.open(filename)
     elif file: