Fixed exiftool to ignore unsupported file types, #615

MANIFEST.in

@@ -1,7 +1,7 @@
-include README.md
+include osxphotos/*.json
-include README.rst
+include osxphotos/*.md
-include osxphotos/templates/*
 include osxphotos/phototemplate.tx
-include osxphotos/phototemplate.md
+include osxphotos/queries/*
-include osxphotos/tutorial.md
+include osxphotos/templates/*
-include osxphotos/queries/*
+include README.md
+include README.rst

osxphotos/_version.py

@@ -1,3 +1,3 @@
 """ version info """
 
-__version__ = "0.45.6"
+__version__ = "0.45.7"

osxphotos/exiftool.py

@@ -11,6 +11,7 @@ import html
 import json
 import logging
 import os
+import pathlib
 import re
 import shutil
 import subprocess
@@ -19,11 +20,12 @@ from functools import lru_cache  # pylint: disable=syntax-error
 
 __all__ = [
     "escape_str",
-    "unescape_str",
+    "exiftool_can_write",
-    "terminate_exiftool",
-    "get_exiftool_path",
     "ExifTool",
     "ExifToolCaching",
+    "get_exiftool_path",
+    "terminate_exiftool",
+    "unescape_str",
 ]
 
 # exiftool -stay_open commands outputs this EOF marker after command is run
@@ -33,6 +35,24 @@ EXIFTOOL_STAYOPEN_EOF_LEN = len(EXIFTOOL_STAYOPEN_EOF)
 # list of exiftool processes to cleanup when exiting or when terminate is called
 EXIFTOOL_PROCESSES = []
 
+# exiftool supported file types, created by utils/exiftool_supported_types.py
+EXIFTOOL_FILETYPES_JSON = "exiftool_filetypes.json"
+with (pathlib.Path(__file__).parent / EXIFTOOL_FILETYPES_JSON).open("r") as f:
+    EXIFTOOL_SUPPORTED_FILETYPES = json.load(f)
+
+
+def exiftool_can_write(suffix: str) -> bool:
+    """Return True if exiftool supports writing to a file with the given suffix, otherwise False"""
+    if not suffix:
+        return False
+    suffix = suffix.lower()
+    if suffix[0] == ".":
+        suffix = suffix[1:]
+    return (
+        suffix in EXIFTOOL_SUPPORTED_FILETYPES
+        and EXIFTOOL_SUPPORTED_FILETYPES[suffix]["write"]
+    )
+
 
 def escape_str(s):
     """escape string for use with exiftool -E"""

osxphotos/photoexporter.py

@@ -3,7 +3,6 @@
 
 
 import dataclasses
-import glob
 import hashlib
 import json
 import logging
@@ -33,7 +32,7 @@ from ._constants import (
 )
 from ._version import __version__
 from .datetime_utils import datetime_tz_to_utc
-from .exiftool import ExifTool
+from .exiftool import ExifTool, exiftool_can_write
 from .export_db import ExportDB_ABC, ExportDBNoOp
 from .fileutil import FileUtil
 from .photokit import (
@@ -1260,11 +1259,20 @@ class PhotoExporter:
 
         exiftool_results = ExportResults()
 
+        # don't try to write if unsupported file type for exiftool
+        if not exiftool_can_write(os.path.splitext(src)[-1]):
+            exiftool_results.exiftool_warning.append(
+                (
+                    dest,
+                    f"Unsupported file type for exiftool, skipping exiftool for {dest}",
+                )
+            )
+            return exiftool_results
+
         # determine if we need to write the exif metadata
         # if we are not updating, we always write
         # else, need to check the database to determine if we need to write
         run_exiftool = not options.update
-        current_data = "foo"
         if options.update:
             files_are_different = False
             old_data = export_db.get_exifdata_for_file(dest)

utils/exiftool_supported_types.py

@@ -0,0 +1,57 @@
+"""Read the "Supported File Types" table from exiftool.org and build a json file from the table"""
+
+import json
+import sys
+
+import requests
+from bs4 import BeautifulSoup
+
+
+if __name__ == "__main__":
+    url = "https://www.exiftool.org/"
+    json_file = "exiftool_filetypes.json"
+
+    html_content = requests.get(url).text
+
+    soup = BeautifulSoup(html_content, "html.parser")
+
+    # uncomment to see all table classes
+    # print("Classes of each table:")
+    # for table in soup.find_all("table"):
+    #     print(table.get("class"))
+
+    # strip footnotes in <span> tags
+    for span_tag in soup.findAll("span"):
+        span_tag.replace_with("")
+
+    # find the table for Supported File Types
+    table = soup.find("table", class_="sticky tight sm bm")
+
+    # get table headers
+    table_headers = [tx.text.lower() for tx in table.find_all("th")]
+
+    # get table data
+    table_data = []
+    for tr in table.find_all("tr"):
+        if row := [td.text for td in tr.find_all("td")]:
+            table_data.append(row)
+
+    # make a dictionary of the table data
+    supported_filetypes = {}
+    for row in table_data:
+        row_dict = dict(zip(table_headers, row))
+        for key, value in row_dict.items():
+            if value == "-":
+                row_dict[key] = None
+        row_dict["file type"] = row_dict["file type"].split(",")
+        row_dict["file type"] = [ft.strip() for ft in row_dict["file type"]]
+        row_dict["read"] = "R" in row_dict["support"]
+        row_dict["write"] = "W" in row_dict["support"]
+        row_dict["create"] = "C" in row_dict["support"]
+        filetypes = [ft.lower() for ft in row_dict["file type"]]
+        for filetype in filetypes:
+            supported_filetypes[filetype] = {"extension": filetype, **row_dict}
+
+    with open(json_file, "w") as jsonfile:
+        print(f"Writing {json_file}...")
+        json.dump(supported_filetypes, jsonfile, indent=4)