Increasing archive file name character limit.

modules/archive/lib.py

@@ -70,6 +70,9 @@ def get_domain_directory(url: str) -> pathlib.Path:
     return directory
 
 
+MAXIMUM_ARCHIVE_FILE_CHARACTER_LENGTH = 200
+
+
 def get_new_archive_files(url: str, title: Optional[str]) -> ArchiveFiles:
     """Create a list of archive files using a shared name schema.  Raise an error if any of them exist."""
     directory = get_domain_directory(url)
@@ -77,7 +80,7 @@ def get_new_archive_files(url: str, title: Optional[str]) -> ArchiveFiles:
     dt = archive_strftime(now())
 
     title = escape_file_name(title or 'NA')
-    title = title[:50]
+    title = title[:MAXIMUM_ARCHIVE_FILE_CHARACTER_LENGTH]
     prefix = f'{dt}_{title}'
     singlefile_path = directory / f'{prefix}.html'
     readability_path = directory / f'{prefix}.readability.html'

modules/archive/test/test_lib.py

@@ -298,6 +298,18 @@ async def test_get_title_from_html(test_session, fake_now):
         assert archive.title is None
 
 
+@skip_circleci
+def test_get_new_archive_files_length(fake_now):
+    """Archive titles are truncated to fit file system length limit.  (255-character limit for most file systems)"""
+    fake_now(datetime(2001, 1, 1))
+    archive_files = get_new_archive_files('https://example.com', 'a' * 500)
+    assert len(str(archive_files.singlefile.name)) == 225
+    assert len(str(archive_files.readability.name)) == 237
+    assert len(str(archive_files.readability_txt.name)) == 236
+    assert len(str(archive_files.readability_json.name)) == 237
+    assert len(str(archive_files.screenshot.name)) == 224
+
+
 @skip_circleci
 def test_get_new_archive_files(fake_now):
     """Archive files have a specific format so they are sorted by datetime, and are near each other."""