annotate a couple more scripts; document sketchy code

mypy.ini

@@ -20,9 +20,6 @@ disallow_untyped_calls = False
 [mypy-cryptography.hazmat.*]
 ignore_missing_imports = True
 
-[mypy-hotshot.*]
-ignore_missing_imports = True
-
 [mypy-nose.*]
 ignore_missing_imports = True
 

tools/pdfdiff.py

@@ -6,6 +6,7 @@
 import io
 import logging
 import sys
+from typing import Any, Iterable, List, Optional
 
 import pdfminer.settings
 from pdfminer import high_level, layout
@@ -16,7 +17,7 @@
 logging.basicConfig()
 
 
-def compare(file1, file2, **kwargs):
+def compare(file1: str, file2: str, **kwargs: Any) -> Iterable[str]:
     # If any LAParams group arguments were passed,
     # create an LAParams object and
     # populate with given args. Otherwise, set it to None.
@@ -26,7 +27,7 @@ def compare(file1, file2, **kwargs):
                       "char_margin", "line_margin", "boxes_flow"):
             paramv = kwargs.get(param, None)
             if paramv is not None:
-                laparams[param] = paramv
+                setattr(laparams, param, paramv)
         kwargs['laparams'] = laparams
 
     s1 = io.StringIO()
@@ -40,20 +41,20 @@ def compare(file1, file2, **kwargs):
     import difflib
     s1.seek(0)
     s2.seek(0)
-    s1, s2 = s1.readlines(), s2.readlines()
+    s1_lines, s2_lines = s1.readlines(), s2.readlines()
 
     import os.path
     try:
         extension = os.path.splitext(kwargs['outfile'])[1][1:4]
         if extension.lower() == 'htm':
-            return difflib.HtmlDiff().make_file(s1, s2)
+            return difflib.HtmlDiff().make_file(s1_lines, s2_lines)
     except KeyError:
         pass
-    return difflib.unified_diff(s1, s2, n=kwargs['context_lines'])
+    return difflib.unified_diff(s1_lines, s2_lines, n=kwargs['context_lines'])
 
 
 # main
-def main(args=None):
+def main(args: Optional[List[str]] = None) -> int:
     import argparse
     P = argparse.ArgumentParser(description=__doc__)
     P.add_argument("file1", type=str, default=None, help="File 1 to compare.")
@@ -142,4 +143,4 @@ def main(args=None):
 
 
 if __name__ == '__main__':
-    sys.exit(main())  # type: ignore[no-untyped-call]
+    sys.exit(main())

tools/pdfstats.py

@@ -7,6 +7,7 @@
 import sys
 import os
 import collections
+from typing import Any, Counter, Iterator, List
 
 from pdfminer.pdfparser import PDFParser
 from pdfminer.pdfdocument import PDFDocument, PDFTextExtractionNotAllowed
@@ -19,18 +20,18 @@
 _, SCRIPT = os.path.split(__file__)
 
 
-def msg(*args, **kwargs):
+def msg(*args: Any, **kwargs: Any) -> None:
     print(' '.join(map(str, args)), **kwargs)  # noqa E999
 
 
-def flat_iter(obj):
+def flat_iter(obj: Any) -> Iterator[Any]:
     yield obj
     if isinstance(obj, LTContainer):
         for ob in obj:
             yield from flat_iter(ob)
 
 
-def main(args):
+def main(args: List[str]) -> int:
     msg(SCRIPT, args)
 
     if len(args) != 1:
@@ -40,7 +41,7 @@ def main(args):
 
     infilename, = args
 
-    lt_types = collections.Counter()
+    lt_types: Counter[str] = collections.Counter()
 
     with open(infilename, 'rb') as pdf_file:
 
@@ -77,6 +78,8 @@ def main(args):
     msg('page_count', page_count)
     msg('lt_types:', ' '.join('{}:{}'.format(*tc) for tc in lt_types.items()))
 
+    return 0
+
 
 if __name__ == '__main__':
-    sys.exit(main(sys.argv[1:]))  # type: ignore[no-untyped-call]
+    sys.exit(main(sys.argv[1:]))

tools/prof.py

@@ -1,11 +1,12 @@
 #!/usr/bin/env python3
 import sys
+from typing import List
 
 
-def prof_main(argv):
-    import hotshot.stats
+def prof_main(argv: List[str]) -> int:
+    import hotshot.stats  # type: ignore[import]
 
-    def usage():
+    def usage() -> int:
         print('usage: %s module.function [args ...]' % argv[0])
         return 100
     args = argv[1:]
@@ -15,20 +16,25 @@ def usage():
     prof = name+'.prof'
     i = name.rindex('.')
     (modname, funcname) = (name[:i], name[i+1:])
-    module = __import__(modname, fromlist=1)
+
+    # Type error: fromlist expects sequence of strings; presumably the intent
+    # is to retrieve the named module rather than a top-level package (as in
+    # "when a non-empty fromlist argument is given...").
+    module = __import__(modname, fromlist=1)  # type: ignore[arg-type]
+
     func = getattr(module, funcname)
     if args:
         args.insert(0, argv[0])
-        prof = hotshot.Profile(prof)
-        prof.runcall(lambda: func(args))
-        prof.close()
+        profile = hotshot.Profile(prof)
+        profile.runcall(lambda: func(args))
+        profile.close()
     else:
         stats = hotshot.stats.load(prof)
         stats.strip_dirs()
         stats.sort_stats('time', 'calls')
         stats.print_stats(1000)
-    return
+    return 0
 
 
 if __name__ == '__main__':
-    sys.exit(prof_main(sys.argv))  # type: ignore[no-untyped-call]
+    sys.exit(prof_main(sys.argv))