Initial checkin. Base working version.

heckimp/misc.py

@@ -0,0 +1,70 @@
+import logging
+import urllib.parse
+
+import tqdm # type: ignore
+
+from typing import List, Set
+from pathlib import Path
+
+"""
+Miscellaneous utilities and constants.
+"""
+
+
+PROBABLY_BINARY_EXTENSIONS: List[str] = [
+    ".ico",
+    ".ppm",
+    ".pnm",
+    ".png",
+    ".gz",
+    ".svg",
+    ".pgm",
+    ".gih",
+    ".gbr",
+]
+
+
+class TqdmLoggingHandler(logging.Handler):
+    """
+    A simple logging wrapper that won't clobber TQDM's progress bar.
+    """
+    def __init__(self, level=logging.NOTSET):
+        super().__init__(level)
+
+    def emit(self, record):
+        try:
+            msg = self.format(record)
+            tqdm.tqdm.write(msg)
+            self.flush()
+        except Exception:
+            self.handleError(record)
+
+
+## Utility Functions
+def is_binary(path: Path, amount: int = 256) -> bool:
+    """
+    A pretty sloppy way to determine if a file is binary or not. Takes a path and returns true/false. Bigger
+    amount means more accurate (more of the file read).
+    """
+    try:
+        b = path.open().read(amount)
+        return False
+    except UnicodeDecodeError:
+        return True
+
+def reverse_domain(url: str) -> str:
+    """
+    Create a 'reverse domain' used for labeling objects and whatnot.
+    """
+    p = urllib.parse.urlparse(url)
+    domain = p.netloc
+    return '.'.join(reversed(domain.split('.')))
+
+def find_file(fname: str, searchpaths: Set[Path]) -> Path:
+    """
+    Return a path object for the first file we find in the search paths with the filename or raise FileNotFound error.
+    """
+    for path in searchpaths:
+        if (path / fname).exists():
+            return (path / fname)
+    raise FileNotFoundError(f"can't find {fname} in searchpaths")