enhancement: file detection for .wav files (#2387)

### Summary

Adds filetype detection for `.wav` audio files

### Testing

```python
from unstructured.file_utils.filetype import detect_filetype

filename = "example-docs/CantinaBand3.wav"
detect_filetype(filename=filename) # Should be FileType.WAV
```

CHANGELOG.md

@@ -2,6 +2,7 @@
 
 ### Enhancements
 
+* **Add filetype detection for `.wav` files.** Add filetpye detection for `.wav` files.
 * **Add "basic" chunking strategy.** Add baseline chunking strategy that includes all shared chunking behaviors without breaking chunks on section or page boundaries.
 * **Add overlap option for chunking.** Add option to overlap chunks. Intra-chunk and inter-chunk overlap are requested separately. Intra-chunk overlap is applied only to the second and later chunks formed by text-splitting an oversized chunk. Inter-chunk overlap may also be specified; this applies overlap between "normal" (not-oversized) chunks.
 * **Salesforce connector accepts private key path or value.** Salesforce parameter `private-key-file` has been renamed to `private-key`. Private key can be provided as path to file or file contents.

test_unstructured/file_utils/test_filetype.py

@@ -445,3 +445,12 @@ def test_detect_filetype_skips_escape_commas_for_csv(tmpdir):
 def test_detect_filetype_from_octet_stream(filename="example-docs/emoji.xlsx"):
     with open(filename, "rb") as f:
         assert _detect_filetype_from_octet_stream(file=f) == FileType.XLSX
+
+
+def test_detect_wav_from_filename(filename="example-docs/CantinaBand3.wav"):
+    assert detect_filetype(filename=filename) == FileType.WAV
+
+
+def test_detect_wav_from_file(filename="example-docs/CantinaBand3.wav"):
+    with open(filename, "rb") as f:
+        assert detect_filetype(file=f) == FileType.WAV

test_unstructured/partition/test_auto.py

@@ -730,7 +730,7 @@ FILETYPE_TO_MODULE = {
 
 @pytest.mark.parametrize("filetype", supported_filetypes)
 def test_file_specific_produces_correct_filetype(filetype: FileType):
-    if filetype in (FileType.JPG, FileType.PNG, FileType.TIFF, FileType.EMPTY):
+    if filetype in (FileType.JPG, FileType.PNG, FileType.TIFF, FileType.WAV, FileType.EMPTY):
         pytest.skip()
     extension = filetype.name.lower()
     filetype_module = (

unstructured/file_utils/filetype.py

@@ -97,6 +97,9 @@ class FileType(enum.Enum):
     # Open Office Types
     ODT = 70
 
+    # Audio Files
+    WAV = 80
+
     # NOTE(robinson) - This is to support sorting for pandas groupby functions
     def __lt__(self, other):
         return self.name < other.name
@@ -136,6 +139,12 @@ STR_TO_FILETYPE = {
     "message/rfc822": FileType.EML,
     "application/x-ole-storage": FileType.MSG,
     "application/vnd.ms-outlook": FileType.MSG,
+    # NOTE(robinson) - https://mimetype.io/audio/wav
+    "audio/vnd.wav": FileType.WAV,
+    "audio/vnd.wave": FileType.WAV,
+    "audio/wave": FileType.WAV,
+    "audio/x-pn-wav": FileType.WAV,
+    "audio/x-wav": FileType.WAV,
     "inode/x-empty": FileType.EMPTY,
 }
 
@@ -182,6 +191,7 @@ EXT_TO_FILETYPE = {
     ".tsv": FileType.TSV,
     ".tab": FileType.TSV,
     ".tiff": FileType.TIFF,
+    ".wav": FileType.WAV,
     # NOTE(robinson) - for now we are treating code files as plain text
     ".js": FileType.TXT,
     ".py": FileType.TXT,