rclone-api 1.3.14__py2.py3-none-any.whl → 1.3.17__py2.py3-none-any.whl

rclone_api/db/db.py

@@ -178,7 +178,7 @@ class DBRepo:
                 "size": file.size,
                 "mime_type": file.mime_type,
                 "mod_time": file.mod_time,
-                "suffix": file.suffix,
+                "suffix": file.real_suffix,
             }
             for file in is_new
         ]
@@ -213,7 +213,7 @@ class DBRepo:
                             "size": file.size,
                             "mime_type": file.mime_type,
                             "mod_time": file.mod_time,
-                            "suffix": file.suffix,
+                            "suffix": file.real_suffix,
                         }
                     )
             if update_values:

rclone_api/file.py

@@ -12,6 +12,56 @@ def _intern(s: str) -> str:
     return _STRING_INTERNER.setdefault(s, s)
 
 
+_SUFFIX_LARGEST_SIZE = len("torrents") + 2
+
+
+def _suffix_clean_bad_parts(suffix: list[str]) -> list[str]:
+    """Remove any bad parts from the suffix list."""
+    out = []
+    for part in suffix:
+        if part in ["", ""]:
+            continue
+        if " " in part:
+            # split on spaces
+            continue
+        if "--" in part:
+            # split on --
+            parts = part.split("--")
+            parts = [x.strip() for x in parts if x.strip()]
+            out.extend(parts)
+        out.append(part)
+
+    out, tmp = [], out
+    for part in tmp:
+        if len(part) > _SUFFIX_LARGEST_SIZE:
+            continue
+        out.append(part)
+    return out
+
+
+def _get_suffix(name: str, chop_compressed_suffixes: bool = True) -> str:
+    # name.sql.gz -> sql.gz
+    try:
+        parts = name.split(".")
+        if len(parts) == 1:
+            return ""
+        parts = _suffix_clean_bad_parts(parts)
+        last_part = parts[-1]
+        if chop_compressed_suffixes:
+            if last_part == "gz" and len(parts) > 2:
+                parts = parts[:-1]
+        if len(parts) > 2:
+            # grab the last two parts
+            return ".".join(parts[-2:])
+        return ".".join(parts[1:])
+    except IndexError:
+        warnings.warn(f"Invalid name: {name} for normal suffix extraction")
+        suffix = Path(name).suffix
+        if suffix.startswith("."):
+            return suffix[1:]
+        return suffix
+
+
 # File is too complex, this is a simple dataclass that can be streamed out.
 @dataclass
 class FileItem:
@@ -40,14 +90,14 @@ class FileItem:
             return f"{self.parent}/{self.name}"
 
     @property
-    def suffix(self) -> str:
+    def real_suffix(self) -> str:
         return self._suffix
 
     def __post_init__(self):
         self.parent = _intern(self.parent)
         self.mime_type = _intern(self.mime_type)
         self.remote = _intern(self.remote)
-        self._suffix = _intern(Path(self.name).suffix)
+        self._suffix = _intern(_get_suffix(self.name))
 
     @staticmethod
     def from_json(remote: str, data: dict) -> "FileItem | None":